Merge branch 'linus' into x86/urgent

Merge reason: Merge upstream commits to avoid conflicts in upcoming patches.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

549 files changed, 20984 insertions, 13281 deletions

diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt
index cfaac34c4557..6ef692667e2f 100644
--- a/Documentation/RCU/whatisRCU.txt
+++ b/Documentation/RCU/whatisRCU.txt
@@ -849,6 +849,37 @@ All:  lockdep-checked RCU-protected pointer access
 See the comment headers in the source code (or the docbook generated
 from them) for more information.
 
+However, given that there are no fewer than four families of RCU APIs
+in the Linux kernel, how do you choose which one to use?  The following
+list can be helpful:
+
+a.	Will readers need to block?  If so, you need SRCU.
+
+b.	What about the -rt patchset?  If readers would need to block
+	in an non-rt kernel, you need SRCU.  If readers would block
+	in a -rt kernel, but not in a non-rt kernel, SRCU is not
+	necessary.
+
+c.	Do you need to treat NMI handlers, hardirq handlers,
+	and code segments with preemption disabled (whether
+	via preempt_disable(), local_irq_save(), local_bh_disable(),
+	or some other mechanism) as if they were explicit RCU readers?
+	If so, you need RCU-sched.
+
+d.	Do you need RCU grace periods to complete even in the face
+	of softirq monopolization of one or more of the CPUs?  For
+	example, is your code subject to network-based denial-of-service
+	attacks?  If so, you need RCU-bh.
+
+e.	Is your workload too update-intensive for normal use of
+	RCU, but inappropriate for other synchronization mechanisms?
+	If so, consider SLAB_DESTROY_BY_RCU.  But please be careful!
+
+f.	Otherwise, use RCU.
+
+Of course, this all assumes that you have determined that RCU is in fact
+the right tool for your job.
+
 
 8.  ANSWERS TO QUICK QUIZZES
 
diff --git a/Documentation/devicetree/bindings/i2c/ce4100-i2c.txt b/Documentation/devicetree/bindings/i2c/ce4100-i2c.txt
new file mode 100644
index 000000000000..569b16248514
--- /dev/null
+++ b/Documentation/devicetree/bindings/i2c/ce4100-i2c.txt
@@ -0,0 +1,93 @@
+CE4100 I2C
+----------
+
+CE4100 has one PCI device which is described as the I2C-Controller. This
+PCI device has three PCI-bars, each bar contains a complete I2C
+controller. So we have a total of three independent I2C-Controllers
+which share only an interrupt line.
+The driver is probed via the PCI-ID and is gathering the information of
+attached devices from the devices tree.
+Grant Likely recommended to use the ranges property to map the PCI-Bar
+number to its physical address and to use this to find the child nodes
+of the specific I2C controller. This were his exact words:
+
+       Here's where the magic happens.  Each entry in
+       ranges describes how the parent pci address space
+       (middle group of 3) is translated to the local
+       address space (first group of 2) and the size of
+       each range (last cell).  In this particular case,
+       the first cell of the local address is chosen to be
+       1:1 mapped to the BARs, and the second is the
+       offset from be base of the BAR (which would be
+       non-zero if you had 2 or more devices mapped off
+       the same BAR)
+
+       ranges allows the address mapping to be described
+       in a way that the OS can interpret without
+       requiring custom device driver code.
+
+This is an example which is used on FalconFalls:
+------------------------------------------------
+	i2c-controller@b,2 {
+		#address-cells = <2>;
+		#size-cells = <1>;
+		compatible = "pci8086,2e68.2",
+				"pci8086,2e68",
+				"pciclass,ff0000",
+				"pciclass,ff00";
+
+		reg = <0x15a00 0x0 0x0 0x0 0x0>;
+		interrupts = <16 1>;
+
+		/* as described by Grant, the first number in the group of
+		* three is the bar number followed by the 64bit bar address
+		* followed by size of the mapping. The bar address
+		* requires also a valid translation in parents ranges
+		* property.
+		*/
+		ranges = <0 0   0x02000000 0 0xdffe0500 0x100
+			  1 0   0x02000000 0 0xdffe0600 0x100
+			  2 0   0x02000000 0 0xdffe0700 0x100>;
+
+		i2c@0 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			compatible = "intel,ce4100-i2c-controller";
+
+			/* The first number in the reg property is the
+			* number of the bar
+			*/
+			reg = <0 0 0x100>;
+
+			/* This I2C controller has no devices */
+		};
+
+		i2c@1 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			compatible = "intel,ce4100-i2c-controller";
+			reg = <1 0 0x100>;
+
+			/* This I2C controller has one gpio controller */
+			gpio@26 {
+				#gpio-cells = <2>;
+				compatible = "ti,pcf8575";
+				reg = <0x26>;
+				gpio-controller;
+			};
+		};
+
+		i2c@2 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			compatible = "intel,ce4100-i2c-controller";
+			reg = <2 0 0x100>;
+
+			gpio@26 {
+				#gpio-cells = <2>;
+				compatible = "ti,pcf8575";
+				reg = <0x26>;
+				gpio-controller;
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/rtc/rtc-cmos.txt b/Documentation/devicetree/bindings/rtc/rtc-cmos.txt
new file mode 100644
index 000000000000..7382989b3052
--- /dev/null
+++ b/Documentation/devicetree/bindings/rtc/rtc-cmos.txt
@@ -0,0 +1,28 @@
+ Motorola mc146818 compatible RTC
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Required properties:
+  - compatible : "motorola,mc146818"
+  - reg : should contain registers location and length.
+
+Optional properties:
+  - interrupts : should contain interrupt.
+  - interrupt-parent : interrupt source phandle.
+  - ctrl-reg : Contains the initial value of the control register also
+    called "Register B".
+  - freq-reg : Contains the initial value of the frequency register also
+    called "Regsiter A".
+
+"Register A" and "B" are usually initialized by the firmware (BIOS for
+instance). If this is not done, it can be performed by the driver.
+
+ISA Example:
+
+	rtc@70 {
+	         compatible = "motorola,mc146818";
+	         interrupts = <8 3>;
+	         interrupt-parent = <&ioapic1>;
+	         ctrl-reg = <2>;
+	         freq-reg = <0x26>;
+	         reg = <1 0x70 2>;
+	 };
diff --git a/Documentation/devicetree/bindings/x86/ce4100.txt b/Documentation/devicetree/bindings/x86/ce4100.txt
new file mode 100644
index 000000000000..b49ae593a60b
--- /dev/null
+++ b/Documentation/devicetree/bindings/x86/ce4100.txt
@@ -0,0 +1,38 @@
+CE4100 Device Tree Bindings
+---------------------------
+
+The CE4100 SoC uses for in core peripherals the following compatible
+format: <vendor>,<chip>-<device>.
+Many of the "generic" devices like HPET or IO APIC have the ce4100
+name in their compatible property because they first appeared in this
+SoC.
+
+The CPU node
+------------
+	cpu@0 {
+		device_type = "cpu";
+		compatible = "intel,ce4100";
+		reg = <0>;
+		lapic = <&lapic0>;
+	};
+
+The reg property describes the CPU number. The lapic property points to
+the local APIC timer.
+
+The SoC node
+------------
+
+This node describes the in-core peripherals. Required property:
+  compatible = "intel,ce4100-cp";
+
+The PCI node
+------------
+This node describes the PCI bus on the SoC. Its property should be
+  compatible = "intel,ce4100-pci", "pci";
+
+If the OS is using the IO-APIC for interrupt routing then the reported
+interrupt numbers for devices is no longer true. In order to obtain the
+correct interrupt number, the child node which represents the device has
+to contain the interrupt property. Besides the interrupt property it has
+to contain at least the reg property containing the PCI bus address and
+compatible property according to "PCI Bus Binding Revision 2.1".
diff --git a/Documentation/devicetree/bindings/x86/interrupt.txt b/Documentation/devicetree/bindings/x86/interrupt.txt
new file mode 100644
index 000000000000..7d19f494f19a
--- /dev/null
+++ b/Documentation/devicetree/bindings/x86/interrupt.txt
@@ -0,0 +1,26 @@
+Interrupt chips
+---------------
+
+* Intel I/O Advanced Programmable Interrupt Controller (IO APIC)
+
+  Required properties:
+  --------------------
+     compatible = "intel,ce4100-ioapic";
+     #interrupt-cells = <2>;
+
+  Device's interrupt property:
+
+     interrupts = <P S>;
+
+  The first number (P) represents the interrupt pin which is wired to the
+  IO APIC. The second number (S) represents the sense of interrupt which
+  should be configured and can be one of:
+    0 - Edge Rising
+    1 - Level Low
+    2 - Level High
+    3 - Edge Falling
+
+* Local APIC
+  Required property:
+
+     compatible = "intel,ce4100-lapic";
diff --git a/Documentation/devicetree/bindings/x86/timer.txt b/Documentation/devicetree/bindings/x86/timer.txt
new file mode 100644
index 000000000000..c688af58e3bd
--- /dev/null
+++ b/Documentation/devicetree/bindings/x86/timer.txt
@@ -0,0 +1,6 @@
+Timers
+------
+
+* High Precision Event Timer (HPET)
+  Required property:
+     compatible = "intel,ce4100-hpet";
diff --git a/Documentation/devicetree/booting-without-of.txt b/Documentation/devicetree/booting-without-of.txt
index 28b1c9d3d351..55fd2623445b 100644
--- a/Documentation/devicetree/booting-without-of.txt
+++ b/Documentation/devicetree/booting-without-of.txt
@@ -13,6 +13,7 @@ Table of Contents
 
   I - Introduction
     1) Entry point for arch/powerpc
+    2) Entry point for arch/x86
 
   II - The DT block format
     1) Header
@@ -225,6 +226,25 @@ it with special cases.
   cannot support both configurations with Book E and configurations
   with classic Powerpc architectures.
 
+2) Entry point for arch/x86
+-------------------------------
+
+  There is one single 32bit entry point to the kernel at code32_start,
+  the decompressor (the real mode entry point goes to the same  32bit
+  entry point once it switched into protected mode). That entry point
+  supports one calling convention which is documented in
+  Documentation/x86/boot.txt
+  The physical pointer to the device-tree block (defined in chapter II)
+  is passed via setup_data which requires at least boot protocol 2.09.
+  The type filed is defined as
+
+  #define SETUP_DTB                      2
+
+  This device-tree is used as an extension to the "boot page". As such it
+  does not parse / consider data which is already covered by the boot
+  page. This includes memory size, reserved ranges, command line arguments
+  or initrd address. It simply holds information which can not be retrieved
+  otherwise like interrupt routing or a list of devices behind an I2C bus.
 
 II - The DT block format
 ========================
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index f4a04c0c7edc..738c6fda3fb0 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -2444,6 +2444,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			<deci-seconds>: poll all this frequency
 			0: no polling (default)
 
+	threadirqs	[KNL]
+			Force threading of all interrupt handlers except those
+			marked explicitely IRQF_NO_THREAD.
+
 	topology=	[S390]
 			Format: {off | on}
 			Specify if the kernel should make use of the cpu
diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index 631ad2f1b229..f0d3a8026a56 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -21,6 +21,7 @@ Contents:
      - SMP barrier pairing.
      - Examples of memory barrier sequences.
      - Read memory barriers vs load speculation.
+     - Transitivity
 
  (*) Explicit kernel barriers.
 
@@ -959,6 +960,63 @@ the speculation will be cancelled and the value reloaded:
 	retrieved                               :       :       +-------+
 
 
+TRANSITIVITY
+------------
+
+Transitivity is a deeply intuitive notion about ordering that is not
+always provided by real computer systems.  The following example
+demonstrates transitivity (also called "cumulativity"):
+
+	CPU 1			CPU 2			CPU 3
+	=======================	=======================	=======================
+		{ X = 0, Y = 0 }
+	STORE X=1		LOAD X			STORE Y=1
+				<general barrier>	<general barrier>
+				LOAD Y			LOAD X
+
+Suppose that CPU 2's load from X returns 1 and its load from Y returns 0.
+This indicates that CPU 2's load from X in some sense follows CPU 1's
+store to X and that CPU 2's load from Y in some sense preceded CPU 3's
+store to Y.  The question is then "Can CPU 3's load from X return 0?"
+
+Because CPU 2's load from X in some sense came after CPU 1's store, it
+is natural to expect that CPU 3's load from X must therefore return 1.
+This expectation is an example of transitivity: if a load executing on
+CPU A follows a load from the same variable executing on CPU B, then
+CPU A's load must either return the same value that CPU B's load did,
+or must return some later value.
+
+In the Linux kernel, use of general memory barriers guarantees
+transitivity.  Therefore, in the above example, if CPU 2's load from X
+returns 1 and its load from Y returns 0, then CPU 3's load from X must
+also return 1.
+
+However, transitivity is -not- guaranteed for read or write barriers.
+For example, suppose that CPU 2's general barrier in the above example
+is changed to a read barrier as shown below:
+
+	CPU 1			CPU 2			CPU 3
+	=======================	=======================	=======================
+		{ X = 0, Y = 0 }
+	STORE X=1		LOAD X			STORE Y=1
+				<read barrier>		<general barrier>
+				LOAD Y			LOAD X
+
+This substitution destroys transitivity: in this example, it is perfectly
+legal for CPU 2's load from X to return 1, its load from Y to return 0,
+and CPU 3's load from X to return 0.
+
+The key point is that although CPU 2's read barrier orders its pair
+of loads, it does not guarantee to order CPU 1's store.  Therefore, if
+this example runs on a system where CPUs 1 and 2 share a store buffer
+or a level of cache, CPU 2 might have early access to CPU 1's writes.
+General barriers are therefore required to ensure that all CPUs agree
+on the combined order of CPU 1's and CPU 2's accesses.
+
+To reiterate, if your code requires transitivity, use general barriers
+throughout.
+
+
 ========================
 EXPLICIT KERNEL BARRIERS
 ========================
diff --git a/Documentation/rtc.txt b/Documentation/rtc.txt
index 9104c1062084..250160469d83 100644
--- a/Documentation/rtc.txt
+++ b/Documentation/rtc.txt
@@ -178,38 +178,29 @@ RTC class framework, but can't be supported by the older driver.
 	setting the longer alarm time and enabling its IRQ using a single
 	request (using the same model as EFI firmware).
 
-    *	RTC_UIE_ON, RTC_UIE_OFF ... if the RTC offers IRQs, it probably
-	also offers update IRQs whenever the "seconds" counter changes.
-	If needed, the RTC framework can emulate this mechanism.
+    *	RTC_UIE_ON, RTC_UIE_OFF ... if the RTC offers IRQs, the RTC framework
+	will emulate this mechanism.
 
-    *	RTC_PIE_ON, RTC_PIE_OFF, RTC_IRQP_SET, RTC_IRQP_READ ... another
-	feature often accessible with an IRQ line is a periodic IRQ, issued
-	at settable frequencies (usually 2^N Hz).
+    *	RTC_PIE_ON, RTC_PIE_OFF, RTC_IRQP_SET, RTC_IRQP_READ ... these icotls
+	are emulated via a kernel hrtimer.
 
 In many cases, the RTC alarm can be a system wake event, used to force
 Linux out of a low power sleep state (or hibernation) back to a fully
 operational state.  For example, a system could enter a deep power saving
 state until it's time to execute some scheduled tasks.
 
-Note that many of these ioctls need not actually be implemented by your
-driver.  The common rtc-dev interface handles many of these nicely if your
-driver returns ENOIOCTLCMD.  Some common examples:
+Note that many of these ioctls are handled by the common rtc-dev interface.
+Some common examples:
 
     *	RTC_RD_TIME, RTC_SET_TIME: the read_time/set_time functions will be
 	called with appropriate values.
 
-    *	RTC_ALM_SET, RTC_ALM_READ, RTC_WKALM_SET, RTC_WKALM_RD: the
-	set_alarm/read_alarm functions will be called.
+    *	RTC_ALM_SET, RTC_ALM_READ, RTC_WKALM_SET, RTC_WKALM_RD: gets or sets
+	the alarm rtc_timer. May call the set_alarm driver function.
 
-    *	RTC_IRQP_SET, RTC_IRQP_READ: the irq_set_freq function will be called
-	to set the frequency while the framework will handle the read for you
-	since the frequency is stored in the irq_freq member of the rtc_device
-	structure.  Your driver needs to initialize the irq_freq member during
-	init.  Make sure you check the requested frequency is in range of your
-	hardware in the irq_set_freq function.  If it isn't, return -EINVAL.  If
-	you cannot actually change the frequency, do not define irq_set_freq.
+    *	RTC_IRQP_SET, RTC_IRQP_READ: These are emulated by the generic code.
 
-    *	RTC_PIE_ON, RTC_PIE_OFF: the irq_set_state function will be called.
+    *	RTC_PIE_ON, RTC_PIE_OFF: These are also emulated by the generic code.
 
 If all else fails, check out the rtc-test.c driver!
 
diff --git a/Documentation/spinlocks.txt b/Documentation/spinlocks.txt
index 178c831b907d..2e3c64b1a6a5 100644
--- a/Documentation/spinlocks.txt
+++ b/Documentation/spinlocks.txt
@@ -86,7 +86,7 @@ to change the variables it has to get an exclusive write lock.
 
 The routines look the same as above:
 
-   rwlock_t xxx_lock = RW_LOCK_UNLOCKED;
+   rwlock_t xxx_lock = __RW_LOCK_UNLOCKED(xxx_lock);
 
 	unsigned long flags;
 
@@ -196,25 +196,3 @@ appropriate:
 
 For static initialization, use DEFINE_SPINLOCK() / DEFINE_RWLOCK() or
 __SPIN_LOCK_UNLOCKED() / __RW_LOCK_UNLOCKED() as appropriate.
-
-SPIN_LOCK_UNLOCKED and RW_LOCK_UNLOCKED are deprecated.  These interfere
-with lockdep state tracking.
-
-Most of the time, you can simply turn:
-	static spinlock_t xxx_lock = SPIN_LOCK_UNLOCKED;
-into:
-	static DEFINE_SPINLOCK(xxx_lock);
-
-Static structure member variables go from:
-
-	struct foo bar {
-		.lock	=	SPIN_LOCK_UNLOCKED;
-	};
-
-to:
-
-	struct foo bar {
-		.lock	=	__SPIN_LOCK_UNLOCKED(bar.lock);
-	};
-
-Declaration of static rw_locks undergo a similar transformation.
diff --git a/Documentation/trace/ftrace-design.txt b/Documentation/trace/ftrace-design.txt
index dc52bd442c92..79fcafc7fd64 100644
--- a/Documentation/trace/ftrace-design.txt
+++ b/Documentation/trace/ftrace-design.txt
@@ -247,6 +247,13 @@ You need very few things to get the syscalls tracing in an arch.
 - Support the TIF_SYSCALL_TRACEPOINT thread flags.
 - Put the trace_sys_enter() and trace_sys_exit() tracepoints calls from ptrace
   in the ptrace syscalls tracing path.
+- If the system call table on this arch is more complicated than a simple array
+  of addresses of the system calls, implement an arch_syscall_addr to return
+  the address of a given system call.
+- If the symbol names of the system calls do not match the function names on
+  this arch, define ARCH_HAS_SYSCALL_MATCH_SYM_NAME in asm/ftrace.h and
+  implement arch_syscall_match_sym_name with the appropriate logic to return
+  true if the function name corresponds with the symbol name.
 - Tag this arch as HAVE_SYSCALL_TRACEPOINTS.
 
 
diff --git a/Documentation/trace/ftrace.txt b/Documentation/trace/ftrace.txt
index 557c1edeccaf..1ebc24cf9a55 100644
--- a/Documentation/trace/ftrace.txt
+++ b/Documentation/trace/ftrace.txt
@@ -80,11 +80,11 @@ of ftrace. Here is a list of some of the key files:
 	tracers listed here can be configured by
 	echoing their name into current_tracer.
 
-  tracing_enabled:
+  tracing_on:
 
-	This sets or displays whether the current_tracer
-	is activated and tracing or not. Echo 0 into this
-	file to disable the tracer or 1 to enable it.
+	This sets or displays whether writing to the trace
+	ring buffer is enabled. Echo 0 into this file to disable
+	the tracer or 1 to enable it.
 
   trace:
 
@@ -202,10 +202,6 @@ Here is the list of current tracers that may be configured.
 	to draw a graph of function calls similar to C code
 	source.
 
-  "sched_switch"
-
-	Traces the context switches and wakeups between tasks.
-
   "irqsoff"
 
 	Traces the areas that disable interrupts and saves
@@ -273,39 +269,6 @@ format, the function name that was traced "path_put" and the
 parent function that called this function "path_walk". The
 timestamp is the time at which the function was entered.
 
-The sched_switch tracer also includes tracing of task wakeups
-and context switches.
-
-     ksoftirqd/1-7     [01]  1453.070013:      7:115:R   +  2916:115:S
-     ksoftirqd/1-7     [01]  1453.070013:      7:115:R   +    10:115:S
-     ksoftirqd/1-7     [01]  1453.070013:      7:115:R ==>    10:115:R
-        events/1-10    [01]  1453.070013:     10:115:S ==>  2916:115:R
-     kondemand/1-2916  [01]  1453.070013:   2916:115:S ==>     7:115:R
-     ksoftirqd/1-7     [01]  1453.070013:      7:115:S ==>     0:140:R
-
-Wake ups are represented by a "+" and the context switches are
-shown as "==>".  The format is:
-
- Context switches:
-
-       Previous task              Next Task
-
-  <pid>:<prio>:<state>  ==>  <pid>:<prio>:<state>
-
- Wake ups:
-
-       Current task               Task waking up
-
-  <pid>:<prio>:<state>    +  <pid>:<prio>:<state>
-
-The prio is the internal kernel priority, which is the inverse
-of the priority that is usually displayed by user-space tools.
-Zero represents the highest priority (99). Prio 100 starts the
-"nice" priorities with 100 being equal to nice -20 and 139 being
-nice 19. The prio "140" is reserved for the idle task which is
-the lowest priority thread (pid 0).
-
-
 Latency trace format
 --------------------
 
@@ -491,78 +454,10 @@ x494] <- /root/a.out[+0x4a8] <- /lib/libc-2.7.so[+0x1e1a6]
                    latencies, as described in "Latency
                    trace format".
 
-sched_switch
-------------
-
-This tracer simply records schedule switches. Here is an example
-of how to use it.
-
- # echo sched_switch > current_tracer
- # echo 1 > tracing_enabled
- # sleep 1
- # echo 0 > tracing_enabled
- # cat trace
-
-# tracer: sched_switch
-#
-#           TASK-PID   CPU#    TIMESTAMP  FUNCTION
-#              | |      |          |         |
-            bash-3997  [01]   240.132281:   3997:120:R   +  4055:120:R
-            bash-3997  [01]   240.132284:   3997:120:R ==>  4055:120:R
-           sleep-4055  [01]   240.132371:   4055:120:S ==>  3997:120:R
-            bash-3997  [01]   240.132454:   3997:120:R   +  4055:120:S
-            bash-3997  [01]   240.132457:   3997:120:R ==>  4055:120:R
-           sleep-4055  [01]   240.132460:   4055:120:D ==>  3997:120:R
-            bash-3997  [01]   240.132463:   3997:120:R   +  4055:120:D
-            bash-3997  [01]   240.132465:   3997:120:R ==>  4055:120:R
-          <idle>-0     [00]   240.132589:      0:140:R   +     4:115:S
-          <idle>-0     [00]   240.132591:      0:140:R ==>     4:115:R
-     ksoftirqd/0-4     [00]   240.132595:      4:115:S ==>     0:140:R
-          <idle>-0     [00]   240.132598:      0:140:R   +     4:115:S
-          <idle>-0     [00]   240.132599:      0:140:R ==>     4:115:R
-     ksoftirqd/0-4     [00]   240.132603:      4:115:S ==>     0:140:R
-           sleep-4055  [01]   240.133058:   4055:120:S ==>  3997:120:R
- [...]
-
-
-As we have discussed previously about this format, the header
-shows the name of the trace and points to the options. The
-"FUNCTION" is a misnomer since here it represents the wake ups
-and context switches.
-
-The sched_switch file only lists the wake ups (represented with
-'+') and context switches ('==>') with the previous task or
-current task first followed by the next task or task waking up.
-The format for both of these is PID:KERNEL-PRIO:TASK-STATE.
-Remember that the KERNEL-PRIO is the inverse of the actual
-priority with zero (0) being the highest priority and the nice
-values starting at 100 (nice -20). Below is a quick chart to map
-the kernel priority to user land priorities.
-
-   Kernel Space                     User Space
- ===============================================================
-   0(high) to  98(low)     user RT priority 99(high) to 1(low)
-                           with SCHED_RR or SCHED_FIFO
- ---------------------------------------------------------------
-  99                       sched_priority is not used in scheduling
-                           decisions(it must be specified as 0)
- ---------------------------------------------------------------
- 100(high) to 139(low)     user nice -20(high) to 19(low)
- ---------------------------------------------------------------
- 140                       idle task priority
- ---------------------------------------------------------------
-
-The task states are:
-
- R - running : wants to run, may not actually be running
- S - sleep   : process is waiting to be woken up (handles signals)
- D - disk sleep (uninterruptible sleep) : process must be woken up
-					(ignores signals)
- T - stopped : process suspended
- t - traced  : process is being traced (with something like gdb)
- Z - zombie  : process waiting to be cleaned up
- X - unknown
-
+  overwrite - This controls what happens when the trace buffer is
+              full. If "1" (default), the oldest events are
+              discarded and overwritten. If "0", then the newest
+              events are discarded.
 
 ftrace_enabled
 --------------
@@ -607,10 +502,10 @@ an example:
  # echo irqsoff > current_tracer
  # echo latency-format > trace_options
  # echo 0 > tracing_max_latency
- # echo 1 > tracing_enabled
+ # echo 1 > tracing_on
  # ls -ltr
  [...]
- # echo 0 > tracing_enabled
+ # echo 0 > tracing_on
  # cat trace
 # tracer: irqsoff
 #
@@ -715,10 +610,10 @@ is much like the irqsoff tracer.
  # echo preemptoff > current_tracer
  # echo latency-format > trace_options
  # echo 0 > tracing_max_latency
- # echo 1 > tracing_enabled
+ # echo 1 > tracing_on
  # ls -ltr
  [...]
- # echo 0 > tracing_enabled
+ # echo 0 > tracing_on
  # cat trace
 # tracer: preemptoff
 #
@@ -863,10 +758,10 @@ tracers.
  # echo preemptirqsoff > current_tracer
  # echo latency-format > trace_options
  # echo 0 > tracing_max_latency
- # echo 1 > tracing_enabled
+ # echo 1 > tracing_on
  # ls -ltr
  [...]
- # echo 0 > tracing_enabled
+ # echo 0 > tracing_on
  # cat trace
 # tracer: preemptirqsoff
 #
@@ -1026,9 +921,9 @@ Instead of performing an 'ls', we will run 'sleep 1' under
  # echo wakeup > current_tracer
  # echo latency-format > trace_options
  # echo 0 > tracing_max_latency
- # echo 1 > tracing_enabled
+ # echo 1 > tracing_on
  # chrt -f 5 sleep 1
- # echo 0 > tracing_enabled
+ # echo 0 > tracing_on
  # cat trace
 # tracer: wakeup
 #
@@ -1140,9 +1035,9 @@ ftrace_enabled is set; otherwise this tracer is a nop.
 
  # sysctl kernel.ftrace_enabled=1
  # echo function > current_tracer
- # echo 1 > tracing_enabled
+ # echo 1 > tracing_on
  # usleep 1
- # echo 0 > tracing_enabled
+ # echo 0 > tracing_on
  # cat trace
 # tracer: function
 #
@@ -1180,7 +1075,7 @@ int trace_fd;
 [...]
 int main(int argc, char *argv[]) {
 	[...]
-	trace_fd = open(tracing_file("tracing_enabled"), O_WRONLY);
+	trace_fd = open(tracing_file("tracing_on"), O_WRONLY);
 	[...]
 	if (condition_hit()) {
 		write(trace_fd, "0", 1);
@@ -1631,9 +1526,9 @@ If I am only interested in sys_nanosleep and hrtimer_interrupt:
  # echo sys_nanosleep hrtimer_interrupt \
 		> set_ftrace_filter
  # echo function > current_tracer
- # echo 1 > tracing_enabled
+ # echo 1 > tracing_on
  # usleep 1
- # echo 0 > tracing_enabled
+ # echo 0 > tracing_on
  # cat trace
 # tracer: ftrace
 #
@@ -1879,9 +1774,9 @@ different. The trace is live.
  # echo function > current_tracer
  # cat trace_pipe > /tmp/trace.out &
 [1] 4153
- # echo 1 > tracing_enabled
+ # echo 1 > tracing_on
  # usleep 1
- # echo 0 > tracing_enabled
+ # echo 0 > tracing_on
  # cat trace
 # tracer: function
 #
diff --git a/Documentation/trace/kprobetrace.txt b/Documentation/trace/kprobetrace.txt
index 5f77d94598dd..6d27ab8d6e9f 100644
--- a/Documentation/trace/kprobetrace.txt
+++ b/Documentation/trace/kprobetrace.txt
@@ -42,11 +42,25 @@ Synopsis of kprobe_events
   +|-offs(FETCHARG) : Fetch memory at FETCHARG +|- offs address.(**)
   NAME=FETCHARG : Set NAME as the argument name of FETCHARG.
   FETCHARG:TYPE : Set TYPE as the type of FETCHARG. Currently, basic types
-		  (u8/u16/u32/u64/s8/s16/s32/s64) and string are supported.
+		  (u8/u16/u32/u64/s8/s16/s32/s64), "string" and bitfield
+		  are supported.
 
   (*) only for return probe.
   (**) this is useful for fetching a field of data structures.
 
+Types
+-----
+Several types are supported for fetch-args. Kprobe tracer will access memory
+by given type. Prefix 's' and 'u' means those types are signed and unsigned
+respectively. Traced arguments are shown in decimal (signed) or hex (unsigned).
+String type is a special type, which fetches a "null-terminated" string from
+kernel space. This means it will fail and store NULL if the string container
+has been paged out.
+Bitfield is another special type, which takes 3 parameters, bit-width, bit-
+offset, and container-size (usually 32). The syntax is;
+
+ b<bit-width>@<bit-offset>/<container-size>
+
 
 Per-Probe Event Filtering
 -------------------------
diff --git a/arch/alpha/include/asm/fcntl.h b/arch/alpha/include/asm/fcntl.h
index 70145cbb21cb..1b71ca70c9f6 100644
--- a/arch/alpha/include/asm/fcntl.h
+++ b/arch/alpha/include/asm/fcntl.h
@@ -31,6 +31,8 @@
 #define __O_SYNC	020000000
 #define O_SYNC		(__O_SYNC|O_DSYNC)
 
+#define O_PATH		040000000
+
 #define F_GETLK		7
 #define F_SETLK		8
 #define F_SETLKW	9
diff --git a/arch/alpha/include/asm/futex.h b/arch/alpha/include/asm/futex.h
index 945de222ab91..e8a761aee088 100644
--- a/arch/alpha/include/asm/futex.h
+++ b/arch/alpha/include/asm/futex.h
@@ -29,7 +29,7 @@
 	:	"r" (uaddr), "r"(oparg)				\
 	:	"memory")
 
-static inline int futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
+static inline int futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 {
 	int op = (encoded_op >> 28) & 7;
 	int cmp = (encoded_op >> 24) & 15;
@@ -39,7 +39,7 @@ static inline int futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
 	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
 		oparg = 1 << oparg;
 
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
 	pagefault_disable();
@@ -81,21 +81,23 @@ static inline int futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
 }
 
 static inline int
-futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+			      u32 oldval, u32 newval)
 {
-	int prev, cmp;
+	int ret = 0, cmp;
+	u32 prev;
 
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
 	__asm__ __volatile__ (
 		__ASM_SMP_MB
-	"1:	ldl_l	%0,0(%2)\n"
-	"	cmpeq	%0,%3,%1\n"
-	"	beq	%1,3f\n"
-	"	mov	%4,%1\n"
-	"2:	stl_c	%1,0(%2)\n"
-	"	beq	%1,4f\n"
+	"1:	ldl_l	%1,0(%3)\n"
+	"	cmpeq	%1,%4,%2\n"
+	"	beq	%2,3f\n"
+	"	mov	%5,%2\n"
+	"2:	stl_c	%2,0(%3)\n"
+	"	beq	%2,4f\n"
 	"3:	.subsection 2\n"
 	"4:	br	1b\n"
 	"	.previous\n"
@@ -105,11 +107,12 @@ futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
 	"	.long	2b-.\n"
 	"	lda	$31,3b-2b(%0)\n"
 	"	.previous\n"
-	:	"=&r"(prev), "=&r"(cmp)
+	:	"+r"(ret), "=&r"(prev), "=&r"(cmp)
 	:	"r"(uaddr), "r"((long)oldval), "r"(newval)
 	:	"memory");
 
-	return prev;
+	*uval = prev;
+	return ret;
 }
 
 #endif /* __KERNEL__ */
diff --git a/arch/alpha/include/asm/rwsem.h b/arch/alpha/include/asm/rwsem.h
index 1570c0b54336..a83bbea62c67 100644
--- a/arch/alpha/include/asm/rwsem.h
+++ b/arch/alpha/include/asm/rwsem.h
@@ -13,44 +13,13 @@
 #ifdef __KERNEL__
 
 #include <linux/compiler.h>
-#include <linux/list.h>
-#include <linux/spinlock.h>
 
-struct rwsem_waiter;
-
-extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *);
-extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
-
-/*
- * the semaphore definition
- */
-struct rw_semaphore {
-	long			count;
 #define RWSEM_UNLOCKED_VALUE		0x0000000000000000L
 #define RWSEM_ACTIVE_BIAS		0x0000000000000001L
 #define RWSEM_ACTIVE_MASK		0x00000000ffffffffL
 #define RWSEM_WAITING_BIAS		(-0x0000000100000000L)
 #define RWSEM_ACTIVE_READ_BIAS		RWSEM_ACTIVE_BIAS
 #define RWSEM_ACTIVE_WRITE_BIAS		(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
-	spinlock_t		wait_lock;
-	struct list_head	wait_list;
-};
-
-#define __RWSEM_INITIALIZER(name) \
-	{ RWSEM_UNLOCKED_VALUE, SPIN_LOCK_UNLOCKED, \
-	LIST_HEAD_INIT((name).wait_list) }
-
-#define DECLARE_RWSEM(name) \
-	struct rw_semaphore name = __RWSEM_INITIALIZER(name)
-
-static inline void init_rwsem(struct rw_semaphore *sem)
-{
-	sem->count = RWSEM_UNLOCKED_VALUE;
-	spin_lock_init(&sem->wait_lock);
-	INIT_LIST_HEAD(&sem->wait_list);
-}
 
 static inline void __down_read(struct rw_semaphore *sem)
 {
@@ -250,10 +219,5 @@ static inline long rwsem_atomic_update(long val, struct rw_semaphore *sem)
 #endif
 }
 
-static inline int rwsem_is_locked(struct rw_semaphore *sem)
-{
-	return (sem->count != 0);
-}
-
 #endif /* __KERNEL__ */
 #endif /* _ALPHA_RWSEM_H */
diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c
index fe698b5045e9..376f22130791 100644
--- a/arch/alpha/kernel/osf_sys.c
+++ b/arch/alpha/kernel/osf_sys.c
@@ -230,44 +230,24 @@ linux_to_osf_statfs(struct kstatfs *linux_stat, struct osf_statfs __user *osf_st
 	return copy_to_user(osf_stat, &tmp_stat, bufsiz) ? -EFAULT : 0;
 }
 
-static int
-do_osf_statfs(struct path *path, struct osf_statfs __user *buffer,
-	      unsigned long bufsiz)
+SYSCALL_DEFINE3(osf_statfs, const char __user *, pathname,
+		struct osf_statfs __user *, buffer, unsigned long, bufsiz)
 {
 	struct kstatfs linux_stat;
-	int error = vfs_statfs(path, &linux_stat);
+	int error = user_statfs(pathname, &linux_stat);
 	if (!error)
 		error = linux_to_osf_statfs(&linux_stat, buffer, bufsiz);
 	return error;	
 }
 
-SYSCALL_DEFINE3(osf_statfs, const char __user *, pathname,
-		struct osf_statfs __user *, buffer, unsigned long, bufsiz)
-{
-	struct path path;
-	int retval;
-
-	retval = user_path(pathname, &path);
-	if (!retval) {
-		retval = do_osf_statfs(&path, buffer, bufsiz);
-		path_put(&path);
-	}
-	return retval;
-}
-
 SYSCALL_DEFINE3(osf_fstatfs, unsigned long, fd,
 		struct osf_statfs __user *, buffer, unsigned long, bufsiz)
 {
-	struct file *file;
-	int retval;
-
-	retval = -EBADF;
-	file = fget(fd);
-	if (file) {
-		retval = do_osf_statfs(&file->f_path, buffer, bufsiz);
-		fput(file);
-	}
-	return retval;
+	struct kstatfs linux_stat;
+	int error = fd_statfs(fd, &linux_stat);
+	if (!error)
+		error = linux_to_osf_statfs(&linux_stat, buffer, bufsiz);
+	return error;
 }
 
 /*
diff --git a/arch/alpha/kernel/time.c b/arch/alpha/kernel/time.c
index c1f3e7cb82a4..a58e84f1a63b 100644
--- a/arch/alpha/kernel/time.c
+++ b/arch/alpha/kernel/time.c
@@ -159,7 +159,7 @@ void read_persistent_clock(struct timespec *ts)
 
 /*
  * timer_interrupt() needs to keep up the real-time clock,
- * as well as call the "do_timer()" routine every clocktick
+ * as well as call the "xtime_update()" routine every clocktick
  */
 irqreturn_t timer_interrupt(int irq, void *dev)
 {
@@ -172,8 +172,6 @@ irqreturn_t timer_interrupt(int irq, void *dev)
 	profile_tick(CPU_PROFILING);
 #endif
 
-	write_seqlock(&xtime_lock);
-
 	/*
 	 * Calculate how many ticks have passed since the last update,
 	 * including any previous partial leftover.  Save any resulting
@@ -187,9 +185,7 @@ irqreturn_t timer_interrupt(int irq, void *dev)
 	nticks = delta >> FIX_SHIFT;
 
 	if (nticks)
-		do_timer(nticks);
-
-	write_sequnlock(&xtime_lock);
+		xtime_update(nticks);
 
 	if (test_irq_work_pending()) {
 		clear_irq_work_pending();
diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h
index b33fe7065b38..199a6b6de7f4 100644
--- a/arch/arm/include/asm/futex.h
+++ b/arch/arm/include/asm/futex.h
@@ -35,7 +35,7 @@
 	: "cc", "memory")
 
 static inline int
-futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
+futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 {
 	int op = (encoded_op >> 28) & 7;
 	int cmp = (encoded_op >> 24) & 15;
@@ -46,7 +46,7 @@ futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
 	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
 		oparg = 1 << oparg;
 
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
 	pagefault_disable();	/* implies preempt_disable() */
@@ -88,36 +88,35 @@ futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
 }
 
 static inline int
-futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+			      u32 oldval, u32 newval)
 {
-	int val;
+	int ret = 0;
+	u32 val;
 
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
-	pagefault_disable();	/* implies preempt_disable() */
-
 	__asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n"
-	"1:	" T(ldr) "	%0, [%3]\n"
-	"	teq	%0, %1\n"
+	"1:	" T(ldr) "	%1, [%4]\n"
+	"	teq	%1, %2\n"
 	"	it	eq	@ explicit IT needed for the 2b label\n"
-	"2:	" T(streq) "	%2, [%3]\n"
+	"2:	" T(streq) "	%3, [%4]\n"
 	"3:\n"
 	"	.pushsection __ex_table,\"a\"\n"
 	"	.align	3\n"
 	"	.long	1b, 4f, 2b, 4f\n"
 	"	.popsection\n"
 	"	.pushsection .fixup,\"ax\"\n"
-	"4:	mov	%0, %4\n"
+	"4:	mov	%0, %5\n"
 	"	b	3b\n"
 	"	.popsection"
-	: "=&r" (val)
+	: "+r" (ret), "=&r" (val)
 	: "r" (oldval), "r" (newval), "r" (uaddr), "Ir" (-EFAULT)
 	: "cc", "memory");
 
-	pagefault_enable();	/* subsumes preempt_enable() */
-
-	return val;
+	*uval = val;
+	return ret;
 }
 
 #endif /* !SMP */
diff --git a/arch/arm/kernel/time.c b/arch/arm/kernel/time.c
index 3d76bf233734..1ff46cabc7ef 100644
--- a/arch/arm/kernel/time.c
+++ b/arch/arm/kernel/time.c
@@ -107,9 +107,7 @@ void timer_tick(void)
 {
 	profile_tick(CPU_PROFILING);
 	do_leds();
-	write_seqlock(&xtime_lock);
-	do_timer(1);
-	write_sequnlock(&xtime_lock);
+	xtime_update(1);
 #ifndef CONFIG_SMP
 	update_process_times(user_mode(get_irq_regs()));
 #endif
diff --git a/arch/arm/mach-clps711x/include/mach/time.h b/arch/arm/mach-clps711x/include/mach/time.h
index 8fe283ccd1f3..61fef9129c6a 100644
--- a/arch/arm/mach-clps711x/include/mach/time.h
+++ b/arch/arm/mach-clps711x/include/mach/time.h
@@ -30,7 +30,7 @@ p720t_timer_interrupt(int irq, void *dev_id)
 {
 	struct pt_regs *regs = get_irq_regs();
 	do_leds();
-	do_timer(1);
+	xtime_update(1);
 #ifndef CONFIG_SMP
 	update_process_times(user_mode(regs));
 #endif
diff --git a/arch/blackfin/kernel/time.c b/arch/blackfin/kernel/time.c
index c9113619029f..8d73724c0092 100644
--- a/arch/blackfin/kernel/time.c
+++ b/arch/blackfin/kernel/time.c
@@ -114,16 +114,14 @@ u32 arch_gettimeoffset(void)
 
 /*
  * timer_interrupt() needs to keep up the real-time clock,
- * as well as call the "do_timer()" routine every clocktick
+ * as well as call the "xtime_update()" routine every clocktick
  */
 #ifdef CONFIG_CORE_TIMER_IRQ_L1
 __attribute__((l1_text))
 #endif
 irqreturn_t timer_interrupt(int irq, void *dummy)
 {
-	write_seqlock(&xtime_lock);
-	do_timer(1);
-	write_sequnlock(&xtime_lock);
+	xtime_update(1);
 
 #ifdef CONFIG_IPIPE
 	update_root_process_times(get_irq_regs());
diff --git a/arch/cris/arch-v10/kernel/time.c b/arch/cris/arch-v10/kernel/time.c
index 00eb36f8debf..20c85b5dc7d0 100644
--- a/arch/cris/arch-v10/kernel/time.c
+++ b/arch/cris/arch-v10/kernel/time.c
@@ -140,7 +140,7 @@ stop_watchdog(void)
 
 /*
  * timer_interrupt() needs to keep up the real-time clock,
- * as well as call the "do_timer()" routine every clocktick
+ * as well as call the "xtime_update()" routine every clocktick
  */
 
 //static unsigned short myjiff; /* used by our debug routine print_timestamp */
@@ -176,7 +176,7 @@ timer_interrupt(int irq, void *dev_id)
 
 	/* call the real timer interrupt handler */
 
-	do_timer(1);
+	xtime_update(1);
 	
         cris_do_profile(regs); /* Save profiling information */
         return IRQ_HANDLED;
diff --git a/arch/cris/arch-v32/kernel/smp.c b/arch/cris/arch-v32/kernel/smp.c
index 84fed3b4b079..4c9e3e1ba5d1 100644
--- a/arch/cris/arch-v32/kernel/smp.c
+++ b/arch/cris/arch-v32/kernel/smp.c
@@ -26,7 +26,9 @@
 #define FLUSH_ALL (void*)0xffffffff
 
 /* Vector of locks used for various atomic operations */
-spinlock_t cris_atomic_locks[] = { [0 ... LOCK_COUNT - 1] = SPIN_LOCK_UNLOCKED};
+spinlock_t cris_atomic_locks[] = {
+	[0 ... LOCK_COUNT - 1] = __SPIN_LOCK_UNLOCKED(cris_atomic_locks)
+};
 
 /* CPU masks */
 cpumask_t phys_cpu_present_map = CPU_MASK_NONE;
diff --git a/arch/cris/arch-v32/kernel/time.c b/arch/cris/arch-v32/kernel/time.c
index a545211e999d..bb978ede8985 100644
--- a/arch/cris/arch-v32/kernel/time.c
+++ b/arch/cris/arch-v32/kernel/time.c
@@ -183,7 +183,7 @@ void handle_watchdog_bite(struct pt_regs *regs)
 
 /*
  * timer_interrupt() needs to keep up the real-time clock,
- * as well as call the "do_timer()" routine every clocktick.
+ * as well as call the "xtime_update()" routine every clocktick.
  */
 extern void cris_do_profile(struct pt_regs *regs);
 
@@ -216,9 +216,7 @@ static inline irqreturn_t timer_interrupt(int irq, void *dev_id)
 		return IRQ_HANDLED;
 
 	/* Call the real timer interrupt handler */
-	write_seqlock(&xtime_lock);
-	do_timer(1);
-	write_sequnlock(&xtime_lock);
+	xtime_update(1);
         return IRQ_HANDLED;
 }
 
diff --git a/arch/frv/include/asm/futex.h b/arch/frv/include/asm/futex.h
index 08b3d1da3583..4bea27f50a7a 100644
--- a/arch/frv/include/asm/futex.h
+++ b/arch/frv/include/asm/futex.h
@@ -7,10 +7,11 @@
 #include <asm/errno.h>
 #include <asm/uaccess.h>
 
-extern int futex_atomic_op_inuser(int encoded_op, int __user *uaddr);
+extern int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr);
 
 static inline int
-futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+			      u32 oldval, u32 newval)
 {
 	return -ENOSYS;
 }
diff --git a/arch/frv/kernel/futex.c b/arch/frv/kernel/futex.c
index 14f64b054c7e..d155ca9e5098 100644
--- a/arch/frv/kernel/futex.c
+++ b/arch/frv/kernel/futex.c
@@ -18,7 +18,7 @@
  * the various futex operations; MMU fault checking is ignored under no-MMU
  * conditions
  */
-static inline int atomic_futex_op_xchg_set(int oparg, int __user *uaddr, int *_oldval)
+static inline int atomic_futex_op_xchg_set(int oparg, u32 __user *uaddr, int *_oldval)
 {
 	int oldval, ret;
 
@@ -50,7 +50,7 @@ static inline int atomic_futex_op_xchg_set(int oparg, int __user *uaddr, int *_o
 	return ret;
 }
 
-static inline int atomic_futex_op_xchg_add(int oparg, int __user *uaddr, int *_oldval)
+static inline int atomic_futex_op_xchg_add(int oparg, u32 __user *uaddr, int *_oldval)
 {
 	int oldval, ret;
 
@@ -83,7 +83,7 @@ static inline int atomic_futex_op_xchg_add(int oparg, int __user *uaddr, int *_o
 	return ret;
 }
 
-static inline int atomic_futex_op_xchg_or(int oparg, int __user *uaddr, int *_oldval)
+static inline int atomic_futex_op_xchg_or(int oparg, u32 __user *uaddr, int *_oldval)
 {
 	int oldval, ret;
 
@@ -116,7 +116,7 @@ static inline int atomic_futex_op_xchg_or(int oparg, int __user *uaddr, int *_ol
 	return ret;
 }
 
-static inline int atomic_futex_op_xchg_and(int oparg, int __user *uaddr, int *_oldval)
+static inline int atomic_futex_op_xchg_and(int oparg, u32 __user *uaddr, int *_oldval)
 {
 	int oldval, ret;
 
@@ -149,7 +149,7 @@ static inline int atomic_futex_op_xchg_and(int oparg, int __user *uaddr, int *_o
 	return ret;
 }
 
-static inline int atomic_futex_op_xchg_xor(int oparg, int __user *uaddr, int *_oldval)
+static inline int atomic_futex_op_xchg_xor(int oparg, u32 __user *uaddr, int *_oldval)
 {
 	int oldval, ret;
 
@@ -186,7 +186,7 @@ static inline int atomic_futex_op_xchg_xor(int oparg, int __user *uaddr, int *_o
 /*
  * do the futex operations
  */
-int futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
+int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 {
 	int op = (encoded_op >> 28) & 7;
 	int cmp = (encoded_op >> 24) & 15;
@@ -197,7 +197,7 @@ int futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
 	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
 		oparg = 1 << oparg;
 
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
 	pagefault_disable();
diff --git a/arch/frv/kernel/time.c b/arch/frv/kernel/time.c
index 0ddbbae83cb2..b457de496b70 100644
--- a/arch/frv/kernel/time.c
+++ b/arch/frv/kernel/time.c
@@ -50,21 +50,13 @@ static struct irqaction timer_irq  = {
 
 /*
  * timer_interrupt() needs to keep up the real-time clock,
- * as well as call the "do_timer()" routine every clocktick
+ * as well as call the "xtime_update()" routine every clocktick
  */
 static irqreturn_t timer_interrupt(int irq, void *dummy)
 {
 	profile_tick(CPU_PROFILING);
-	/*
-	 * Here we are in the timer irq handler. We just have irqs locally
-	 * disabled but we don't know if the timer_bh is running on the other
-	 * CPU. We need to avoid to SMP race with it. NOTE: we don't need
-	 * the irq version of write_lock because as just said we have irq
-	 * locally disabled. -arca
-	 */
-	write_seqlock(&xtime_lock);
 
-	do_timer(1);
+	xtime_update(1);
 
 #ifdef CONFIG_HEARTBEAT
 	static unsigned short n;
@@ -72,8 +64,6 @@ static irqreturn_t timer_interrupt(int irq, void *dummy)
 	__set_LEDS(n);
 #endif /* CONFIG_HEARTBEAT */
 
-	write_sequnlock(&xtime_lock);
-
 	update_process_times(user_mode(get_irq_regs()));
 
 	return IRQ_HANDLED;
diff --git a/arch/h8300/kernel/time.c b/arch/h8300/kernel/time.c
index 165005aff9df..32263a138aa6 100644
--- a/arch/h8300/kernel/time.c
+++ b/arch/h8300/kernel/time.c
@@ -35,9 +35,7 @@ void h8300_timer_tick(void)
 {
 	if (current->pid)
 		profile_tick(CPU_PROFILING);
-	write_seqlock(&xtime_lock);
-	do_timer(1);
-	write_sequnlock(&xtime_lock);
+	xtime_update(1);
 	update_process_times(user_mode(get_irq_regs()));
 }
 
diff --git a/arch/h8300/kernel/timer/timer8.c b/arch/h8300/kernel/timer/timer8.c
index 3946c0fa8374..7a1533fad47d 100644
--- a/arch/h8300/kernel/timer/timer8.c
+++ b/arch/h8300/kernel/timer/timer8.c
@@ -61,7 +61,7 @@
 
 /*
  * timer_interrupt() needs to keep up the real-time clock,
- * as well as call the "do_timer()" routine every clocktick
+ * as well as call the "xtime_update()" routine every clocktick
  */
 
 static irqreturn_t timer_interrupt(int irq, void *dev_id)
diff --git a/arch/ia64/include/asm/futex.h b/arch/ia64/include/asm/futex.h
index c7f0f062239c..8428525ddb22 100644
--- a/arch/ia64/include/asm/futex.h
+++ b/arch/ia64/include/asm/futex.h
@@ -46,7 +46,7 @@ do {									\
 } while (0)
 
 static inline int
-futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
+futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 {
 	int op = (encoded_op >> 28) & 7;
 	int cmp = (encoded_op >> 24) & 15;
@@ -56,7 +56,7 @@ futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
 	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
 		oparg = 1 << oparg;
 
-	if (! access_ok (VERIFY_WRITE, uaddr, sizeof(int)))
+	if (! access_ok (VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
 	pagefault_disable();
@@ -100,23 +100,26 @@ futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
 }
 
 static inline int
-futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+			      u32 oldval, u32 newval)
 {
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
 	{
-		register unsigned long r8 __asm ("r8");
+		register unsigned long r8 __asm ("r8") = 0;
+		unsigned long prev;
 		__asm__ __volatile__(
 			"	mf;;					\n"
 			"	mov ar.ccv=%3;;				\n"
 			"[1:]	cmpxchg4.acq %0=[%1],%2,ar.ccv		\n"
 			"	.xdata4 \"__ex_table\", 1b-., 2f-.	\n"
 			"[2:]"
-			: "=r" (r8)
+			: "=r" (prev)
 			: "r" (uaddr), "r" (newval),
 			  "rO" ((long) (unsigned) oldval)
 			: "memory");
+		*uval = prev;
 		return r8;
 	}
 }
diff --git a/arch/ia64/include/asm/rwsem.h b/arch/ia64/include/asm/rwsem.h
index 215d5454c7d3..3027e7516d85 100644
--- a/arch/ia64/include/asm/rwsem.h
+++ b/arch/ia64/include/asm/rwsem.h
@@ -25,20 +25,8 @@
 #error "Please don't include <asm/rwsem.h> directly, use <linux/rwsem.h> instead."
 #endif
 
-#include <linux/list.h>
-#include <linux/spinlock.h>
-
 #include <asm/intrinsics.h>
 
-/*
- * the semaphore definition
- */
-struct rw_semaphore {
-	signed long		count;
-	spinlock_t		wait_lock;
-	struct list_head	wait_list;
-};
-
 #define RWSEM_UNLOCKED_VALUE		__IA64_UL_CONST(0x0000000000000000)
 #define RWSEM_ACTIVE_BIAS		(1L)
 #define RWSEM_ACTIVE_MASK		(0xffffffffL)
@@ -46,26 +34,6 @@ struct rw_semaphore {
 #define RWSEM_ACTIVE_READ_BIAS		RWSEM_ACTIVE_BIAS
 #define RWSEM_ACTIVE_WRITE_BIAS		(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
 
-#define __RWSEM_INITIALIZER(name) \
-	{ RWSEM_UNLOCKED_VALUE, __SPIN_LOCK_UNLOCKED((name).wait_lock), \
-	  LIST_HEAD_INIT((name).wait_list) }
-
-#define DECLARE_RWSEM(name) \
-	struct rw_semaphore name = __RWSEM_INITIALIZER(name)
-
-extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
-
-static inline void
-init_rwsem (struct rw_semaphore *sem)
-{
-	sem->count = RWSEM_UNLOCKED_VALUE;
-	spin_lock_init(&sem->wait_lock);
-	INIT_LIST_HEAD(&sem->wait_list);
-}
-
 /*
  * lock for reading
  */
@@ -174,9 +142,4 @@ __downgrade_write (struct rw_semaphore *sem)
 #define rwsem_atomic_add(delta, sem)	atomic64_add(delta, (atomic64_t *)(&(sem)->count))
 #define rwsem_atomic_update(delta, sem)	atomic64_add_return(delta, (atomic64_t *)(&(sem)->count))
 
-static inline int rwsem_is_locked(struct rw_semaphore *sem)
-{
-	return (sem->count != 0);
-}
-
 #endif /* _ASM_IA64_RWSEM_H */
diff --git a/arch/ia64/include/asm/xen/hypercall.h b/arch/ia64/include/asm/xen/hypercall.h
index 96fc62366aa4..ed28bcd5bb85 100644
--- a/arch/ia64/include/asm/xen/hypercall.h
+++ b/arch/ia64/include/asm/xen/hypercall.h
@@ -107,7 +107,7 @@ extern unsigned long __hypercall(unsigned long a1, unsigned long a2,
 static inline int
 xencomm_arch_hypercall_sched_op(int cmd, struct xencomm_handle *arg)
 {
-	return _hypercall2(int, sched_op_new, cmd, arg);
+	return _hypercall2(int, sched_op, cmd, arg);
 }
 
 static inline long
diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c
index 9702fa92489e..156ad803d5b7 100644
--- a/arch/ia64/kernel/time.c
+++ b/arch/ia64/kernel/time.c
@@ -190,19 +190,10 @@ timer_interrupt (int irq, void *dev_id)
 
 		new_itm += local_cpu_data->itm_delta;
 
-		if (smp_processor_id() == time_keeper_id) {
-			/*
-			 * Here we are in the timer irq handler. We have irqs locally
-			 * disabled, but we don't know if the timer_bh is running on
-			 * another CPU. We need to avoid to SMP race by acquiring the
-			 * xtime_lock.
-			 */
-			write_seqlock(&xtime_lock);
-			do_timer(1);
-			local_cpu_data->itm_next = new_itm;
-			write_sequnlock(&xtime_lock);
-		} else
-			local_cpu_data->itm_next = new_itm;
+		if (smp_processor_id() == time_keeper_id)
+			xtime_update(1);
+
+		local_cpu_data->itm_next = new_itm;
 
 		if (time_after(new_itm, ia64_get_itc()))
 			break;
@@ -222,7 +213,7 @@ skip_process_time_accounting:
 		 * comfort, we increase the safety margin by
 		 * intentionally dropping the next tick(s).  We do NOT
 		 * update itm.next because that would force us to call
-		 * do_timer() which in turn would let our clock run
+		 * xtime_update() which in turn would let our clock run
 		 * too fast (with the potentially devastating effect
 		 * of losing monotony of time).
 		 */
diff --git a/arch/ia64/xen/suspend.c b/arch/ia64/xen/suspend.c
index fd66b048c6fa..419c8620945a 100644
--- a/arch/ia64/xen/suspend.c
+++ b/arch/ia64/xen/suspend.c
@@ -37,19 +37,14 @@ xen_mm_unpin_all(void)
 	/* nothing */
 }
 
-void xen_pre_device_suspend(void)
-{
-	/* nothing */
-}
-
 void
-xen_pre_suspend()
+xen_arch_pre_suspend()
 {
 	/* nothing */
 }
 
 void
-xen_post_suspend(int suspend_cancelled)
+xen_arch_post_suspend(int suspend_cancelled)
 {
 	if (suspend_cancelled)
 		return;
diff --git a/arch/ia64/xen/time.c b/arch/ia64/xen/time.c
index c1c544513e8d..1f8244a78bee 100644
--- a/arch/ia64/xen/time.c
+++ b/arch/ia64/xen/time.c
@@ -139,14 +139,11 @@ consider_steal_time(unsigned long new_itm)
 		run_posix_cpu_timers(p);
 		delta_itm += local_cpu_data->itm_delta * (stolen + blocked);
 
-		if (cpu == time_keeper_id) {
-			write_seqlock(&xtime_lock);
-			do_timer(stolen + blocked);
-			local_cpu_data->itm_next = delta_itm + new_itm;
-			write_sequnlock(&xtime_lock);
-		} else {
-			local_cpu_data->itm_next = delta_itm + new_itm;
-		}
+		if (cpu == time_keeper_id)
+			xtime_update(stolen + blocked);
+
+		local_cpu_data->itm_next = delta_itm + new_itm;
+
 		per_cpu(xen_stolen_time, cpu) += NS_PER_TICK * stolen;
 		per_cpu(xen_blocked_time, cpu) += NS_PER_TICK * blocked;
 	}
diff --git a/arch/m32r/kernel/time.c b/arch/m32r/kernel/time.c
index bda86820bffd..84dd04048db9 100644
--- a/arch/m32r/kernel/time.c
+++ b/arch/m32r/kernel/time.c
@@ -107,15 +107,14 @@ u32 arch_gettimeoffset(void)
 
 /*
  * timer_interrupt() needs to keep up the real-time clock,
- * as well as call the "do_timer()" routine every clocktick
+ * as well as call the "xtime_update()" routine every clocktick
  */
 static irqreturn_t timer_interrupt(int irq, void *dev_id)
 {
 #ifndef CONFIG_SMP
 	profile_tick(CPU_PROFILING);
 #endif
-	/* XXX FIXME. Uh, the xtime_lock should be held here, no? */
-	do_timer(1);
+	xtime_update(1);
 
 #ifndef CONFIG_SMP
 	update_process_times(user_mode(get_irq_regs()));
diff --git a/arch/m68k/bvme6000/config.c b/arch/m68k/bvme6000/config.c
index 9fe6fefb5e14..1edd95095cb4 100644
--- a/arch/m68k/bvme6000/config.c
+++ b/arch/m68k/bvme6000/config.c
@@ -45,8 +45,8 @@ extern int bvme6000_set_clock_mmss (unsigned long);
 extern void bvme6000_reset (void);
 void bvme6000_set_vectors (void);
 
-/* Save tick handler routine pointer, will point to do_timer() in
- * kernel/sched.c, called via bvme6000_process_int() */
+/* Save tick handler routine pointer, will point to xtime_update() in
+ * kernel/timer/timekeeping.c, called via bvme6000_process_int() */
 
 static irq_handler_t tick_handler;
 
diff --git a/arch/m68k/kernel/time.c b/arch/m68k/kernel/time.c
index 06438dac08ff..18b34ee5db3b 100644
--- a/arch/m68k/kernel/time.c
+++ b/arch/m68k/kernel/time.c
@@ -37,11 +37,11 @@ static inline int set_rtc_mmss(unsigned long nowtime)
 
 /*
  * timer_interrupt() needs to keep up the real-time clock,
- * as well as call the "do_timer()" routine every clocktick
+ * as well as call the "xtime_update()" routine every clocktick
  */
 static irqreturn_t timer_interrupt(int irq, void *dummy)
 {
-	do_timer(1);
+	xtime_update(1);
 	update_process_times(user_mode(get_irq_regs()));
 	profile_tick(CPU_PROFILING);
 
diff --git a/arch/m68k/mvme147/config.c b/arch/m68k/mvme147/config.c
index 100baaa692a1..6cb9c3a9b6c9 100644
--- a/arch/m68k/mvme147/config.c
+++ b/arch/m68k/mvme147/config.c
@@ -46,8 +46,8 @@ extern void mvme147_reset (void);
 
 static int bcd2int (unsigned char b);
 
-/* Save tick handler routine pointer, will point to do_timer() in
- * kernel/sched.c, called via mvme147_process_int() */
+/* Save tick handler routine pointer, will point to xtime_update() in
+ * kernel/time/timekeeping.c, called via mvme147_process_int() */
 
 irq_handler_t tick_handler;
 
diff --git a/arch/m68k/mvme16x/config.c b/arch/m68k/mvme16x/config.c
index 11edf61cc2c4..0b28e2621653 100644
--- a/arch/m68k/mvme16x/config.c
+++ b/arch/m68k/mvme16x/config.c
@@ -51,8 +51,8 @@ extern void mvme16x_reset (void);
 
 int bcd2int (unsigned char b);
 
-/* Save tick handler routine pointer, will point to do_timer() in
- * kernel/sched.c, called via mvme16x_process_int() */
+/* Save tick handler routine pointer, will point to xtime_update() in
+ * kernel/time/timekeeping.c, called via mvme16x_process_int() */
 
 static irq_handler_t tick_handler;
 
diff --git a/arch/m68k/sun3/sun3ints.c b/arch/m68k/sun3/sun3ints.c
index 2d9e21bd313a..6464ad3ae3e6 100644
--- a/arch/m68k/sun3/sun3ints.c
+++ b/arch/m68k/sun3/sun3ints.c
@@ -66,7 +66,7 @@ static irqreturn_t sun3_int5(int irq, void *dev_id)
 #ifdef CONFIG_SUN3
 	intersil_clear();
 #endif
-        do_timer(1);
+	xtime_update(1);
 	update_process_times(user_mode(get_irq_regs()));
         if (!(kstat_cpu(0).irqs[irq] % 20))
                 sun3_leds(led_pattern[(kstat_cpu(0).irqs[irq] % 160) / 20]);
diff --git a/arch/m68knommu/kernel/time.c b/arch/m68knommu/kernel/time.c
index d6ac2a43453c..6623909f70e6 100644
--- a/arch/m68knommu/kernel/time.c
+++ b/arch/m68knommu/kernel/time.c
@@ -36,7 +36,7 @@ static inline int set_rtc_mmss(unsigned long nowtime)
 #ifndef CONFIG_GENERIC_CLOCKEVENTS
 /*
  * timer_interrupt() needs to keep up the real-time clock,
- * as well as call the "do_timer()" routine every clocktick
+ * as well as call the "xtime_update()" routine every clocktick
  */
 irqreturn_t arch_timer_interrupt(int irq, void *dummy)
 {
@@ -44,11 +44,7 @@ irqreturn_t arch_timer_interrupt(int irq, void *dummy)
 	if (current->pid)
 		profile_tick(CPU_PROFILING);
 
-	write_seqlock(&xtime_lock);
-
-	do_timer(1);
-
-	write_sequnlock(&xtime_lock);
+	xtime_update(1);
 
 	update_process_times(user_mode(get_irq_regs()));
 
diff --git a/arch/microblaze/include/asm/futex.h b/arch/microblaze/include/asm/futex.h
index ad3fd61b2fe7..b0526d2716fa 100644
--- a/arch/microblaze/include/asm/futex.h
+++ b/arch/microblaze/include/asm/futex.h
@@ -29,7 +29,7 @@
 })
 
 static inline int
-futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
+futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 {
 	int op = (encoded_op >> 28) & 7;
 	int cmp = (encoded_op >> 24) & 15;
@@ -39,7 +39,7 @@ futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
 	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
 		oparg = 1 << oparg;
 
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
 	pagefault_disable();
@@ -94,31 +94,34 @@ futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
 }
 
 static inline int
-futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+			      u32 oldval, u32 newval)
 {
-	int prev, cmp;
+	int ret = 0, cmp;
+	u32 prev;
 
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
-	__asm__ __volatile__ ("1:	lwx	%0, %2, r0;		\
-					cmp	%1, %0, %3;		\
-					beqi	%1, 3f;			\
-				2:	swx	%4, %2, r0;		\
-					addic	%1, r0, 0;		\
-					bnei	%1, 1b;			\
+	__asm__ __volatile__ ("1:	lwx	%1, %3, r0;		\
+					cmp	%2, %1, %4;		\
+					beqi	%2, 3f;			\
+				2:	swx	%5, %3, r0;		\
+					addic	%2, r0, 0;		\
+					bnei	%2, 1b;			\
 				3:					\
 				.section .fixup,\"ax\";			\
 				4:	brid	3b;			\
-					addik	%0, r0, %5;		\
+					addik	%0, r0, %6;		\
 				.previous;				\
 				.section __ex_table,\"a\";		\
 				.word	1b,4b,2b,4b;			\
 				.previous;"				\
-		: "=&r" (prev), "=&r"(cmp)				\
+		: "+r" (ret), "=&r" (prev), "=&r"(cmp)	\
 		: "r" (uaddr), "r" (oldval), "r" (newval), "i" (-EFAULT));
 
-	return prev;
+	*uval = prev;
+	return ret;
 }
 
 #endif /* __KERNEL__ */
diff --git a/arch/microblaze/include/asm/pci-bridge.h b/arch/microblaze/include/asm/pci-bridge.h
index 0c68764ab547..10717669e0c2 100644
--- a/arch/microblaze/include/asm/pci-bridge.h
+++ b/arch/microblaze/include/asm/pci-bridge.h
@@ -104,11 +104,22 @@ struct pci_controller {
 	int global_number;	/* PCI domain number */
 };
 
+#ifdef CONFIG_PCI
 static inline struct pci_controller *pci_bus_to_host(const struct pci_bus *bus)
 {
 	return bus->sysdata;
 }
 
+static inline struct device_node *pci_bus_to_OF_node(struct pci_bus *bus)
+{
+	struct pci_controller *host;
+
+	if (bus->self)
+		return pci_device_to_OF_node(bus->self);
+	host = pci_bus_to_host(bus);
+	return host ? host->dn : NULL;
+}
+
 static inline int isa_vaddr_is_ioport(void __iomem *address)
 {
 	/* No specific ISA handling on ppc32 at this stage, it
@@ -116,6 +127,7 @@ static inline int isa_vaddr_is_ioport(void __iomem *address)
 	 */
 	return 0;
 }
+#endif /* CONFIG_PCI */
 
 /* These are used for config access before all the PCI probing
    has been done. */
diff --git a/arch/microblaze/include/asm/prom.h b/arch/microblaze/include/asm/prom.h
index 2e72af078b05..d0890d36ef61 100644
--- a/arch/microblaze/include/asm/prom.h
+++ b/arch/microblaze/include/asm/prom.h
@@ -64,21 +64,6 @@ extern void kdump_move_device_tree(void);
 /* CPU OF node matching */
 struct device_node *of_get_cpu_node(int cpu, unsigned int *thread);
 
-/**
- * of_irq_map_pci - Resolve the interrupt for a PCI device
- * @pdev:	the device whose interrupt is to be resolved
- * @out_irq:	structure of_irq filled by this function
- *
- * This function resolves the PCI interrupt for a given PCI device. If a
- * device-node exists for a given pci_dev, it will use normal OF tree
- * walking. If not, it will implement standard swizzling and walk up the
- * PCI tree until an device-node is found, at which point it will finish
- * resolving using the OF tree walking.
- */
-struct pci_dev;
-struct of_irq;
-extern int of_irq_map_pci(struct pci_dev *pdev, struct of_irq *out_irq);
-
 #endif /* __ASSEMBLY__ */
 #endif /* __KERNEL__ */
 
diff --git a/arch/microblaze/kernel/prom_parse.c b/arch/microblaze/kernel/prom_parse.c
index 9ae24f4b882b..47187cc2cf00 100644
--- a/arch/microblaze/kernel/prom_parse.c
+++ b/arch/microblaze/kernel/prom_parse.c
@@ -2,88 +2,11 @@
 
 #include <linux/kernel.h>
 #include <linux/string.h>
-#include <linux/pci_regs.h>
 #include <linux/module.h>
 #include <linux/ioport.h>
 #include <linux/etherdevice.h>
 #include <linux/of_address.h>
 #include <asm/prom.h>
-#include <asm/pci-bridge.h>
-
-#ifdef CONFIG_PCI
-int of_irq_map_pci(struct pci_dev *pdev, struct of_irq *out_irq)
-{
-	struct device_node *dn, *ppnode;
-	struct pci_dev *ppdev;
-	u32 lspec;
-	u32 laddr[3];
-	u8 pin;
-	int rc;
-
-	/* Check if we have a device node, if yes, fallback to standard OF
-	 * parsing
-	 */
-	dn = pci_device_to_OF_node(pdev);
-	if (dn)
-		return of_irq_map_one(dn, 0, out_irq);
-
-	/* Ok, we don't, time to have fun. Let's start by building up an
-	 * interrupt spec.  we assume #interrupt-cells is 1, which is standard
-	 * for PCI. If you do different, then don't use that routine.
-	 */
-	rc = pci_read_config_byte(pdev, PCI_INTERRUPT_PIN, &pin);
-	if (rc != 0)
-		return rc;
-	/* No pin, exit */
-	if (pin == 0)
-		return -ENODEV;
-
-	/* Now we walk up the PCI tree */
-	lspec = pin;
-	for (;;) {
-		/* Get the pci_dev of our parent */
-		ppdev = pdev->bus->self;
-
-		/* Ouch, it's a host bridge... */
-		if (ppdev == NULL) {
-			struct pci_controller *host;
-			host = pci_bus_to_host(pdev->bus);
-			ppnode = host ? host->dn : NULL;
-			/* No node for host bridge ? give up */
-			if (ppnode == NULL)
-				return -EINVAL;
-		} else
-			/* We found a P2P bridge, check if it has a node */
-			ppnode = pci_device_to_OF_node(ppdev);
-
-		/* Ok, we have found a parent with a device-node, hand over to
-		 * the OF parsing code.
-		 * We build a unit address from the linux device to be used for
-		 * resolution. Note that we use the linux bus number which may
-		 * not match your firmware bus numbering.
-		 * Fortunately, in most cases, interrupt-map-mask doesn't
-		 * include the bus number as part of the matching.
-		 * You should still be careful about that though if you intend
-		 * to rely on this function (you ship  a firmware that doesn't
-		 * create device nodes for all PCI devices).
-		 */
-		if (ppnode)
-			break;
-
-		/* We can only get here if we hit a P2P bridge with no node,
-		 * let's do standard swizzling and try again
-		 */
-		lspec = pci_swizzle_interrupt_pin(pdev, lspec);
-		pdev = ppdev;
-	}
-
-	laddr[0] = (pdev->bus->number << 16)
-		| (pdev->devfn << 8);
-	laddr[1]  = laddr[2] = 0;
-	return of_irq_map_raw(ppnode, &lspec, 1, laddr, out_irq);
-}
-EXPORT_SYMBOL_GPL(of_irq_map_pci);
-#endif /* CONFIG_PCI */
 
 void of_parse_dma_window(struct device_node *dn, const void *dma_window_prop,
 		unsigned long *busno, unsigned long *phys, unsigned long *size)
diff --git a/arch/microblaze/pci/pci-common.c b/arch/microblaze/pci/pci-common.c
index e363615d6798..1e01a1253631 100644
--- a/arch/microblaze/pci/pci-common.c
+++ b/arch/microblaze/pci/pci-common.c
@@ -29,6 +29,7 @@
 #include <linux/slab.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
+#include <linux/of_pci.h>
 
 #include <asm/processor.h>
 #include <asm/io.h>
diff --git a/arch/mips/include/asm/futex.h b/arch/mips/include/asm/futex.h
index b9cce90346cf..6ebf1734b411 100644
--- a/arch/mips/include/asm/futex.h
+++ b/arch/mips/include/asm/futex.h
@@ -75,7 +75,7 @@
 }
 
 static inline int
-futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
+futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 {
 	int op = (encoded_op >> 28) & 7;
 	int cmp = (encoded_op >> 24) & 15;
@@ -85,7 +85,7 @@ futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
 	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
 		oparg = 1 << oparg;
 
-	if (! access_ok (VERIFY_WRITE, uaddr, sizeof(int)))
+	if (! access_ok (VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
 	pagefault_disable();
@@ -132,11 +132,13 @@ futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
 }
 
 static inline int
-futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+			      u32 oldval, u32 newval)
 {
-	int retval;
+	int ret = 0;
+	u32 val;
 
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
 	if (cpu_has_llsc && R10000_LLSC_WAR) {
@@ -145,25 +147,25 @@ futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
 		"	.set	push					\n"
 		"	.set	noat					\n"
 		"	.set	mips3					\n"
-		"1:	ll	%0, %2					\n"
-		"	bne	%0, %z3, 3f				\n"
+		"1:	ll	%1, %3					\n"
+		"	bne	%1, %z4, 3f				\n"
 		"	.set	mips0					\n"
-		"	move	$1, %z4					\n"
+		"	move	$1, %z5					\n"
 		"	.set	mips3					\n"
-		"2:	sc	$1, %1					\n"
+		"2:	sc	$1, %2					\n"
 		"	beqzl	$1, 1b					\n"
 		__WEAK_LLSC_MB
 		"3:							\n"
 		"	.set	pop					\n"
 		"	.section .fixup,\"ax\"				\n"
-		"4:	li	%0, %5					\n"
+		"4:	li	%0, %6					\n"
 		"	j	3b					\n"
 		"	.previous					\n"
 		"	.section __ex_table,\"a\"			\n"
 		"	"__UA_ADDR "\t1b, 4b				\n"
 		"	"__UA_ADDR "\t2b, 4b				\n"
 		"	.previous					\n"
-		: "=&r" (retval), "=R" (*uaddr)
+		: "+r" (ret), "=&r" (val), "=R" (*uaddr)
 		: "R" (*uaddr), "Jr" (oldval), "Jr" (newval), "i" (-EFAULT)
 		: "memory");
 	} else if (cpu_has_llsc) {
@@ -172,31 +174,32 @@ futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
 		"	.set	push					\n"
 		"	.set	noat					\n"
 		"	.set	mips3					\n"
-		"1:	ll	%0, %2					\n"
-		"	bne	%0, %z3, 3f				\n"
+		"1:	ll	%1, %3					\n"
+		"	bne	%1, %z4, 3f				\n"
 		"	.set	mips0					\n"
-		"	move	$1, %z4					\n"
+		"	move	$1, %z5					\n"
 		"	.set	mips3					\n"
-		"2:	sc	$1, %1					\n"
+		"2:	sc	$1, %2					\n"
 		"	beqz	$1, 1b					\n"
 		__WEAK_LLSC_MB
 		"3:							\n"
 		"	.set	pop					\n"
 		"	.section .fixup,\"ax\"				\n"
-		"4:	li	%0, %5					\n"
+		"4:	li	%0, %6					\n"
 		"	j	3b					\n"
 		"	.previous					\n"
 		"	.section __ex_table,\"a\"			\n"
 		"	"__UA_ADDR "\t1b, 4b				\n"
 		"	"__UA_ADDR "\t2b, 4b				\n"
 		"	.previous					\n"
-		: "=&r" (retval), "=R" (*uaddr)
+		: "+r" (ret), "=&r" (val), "=R" (*uaddr)
 		: "R" (*uaddr), "Jr" (oldval), "Jr" (newval), "i" (-EFAULT)
 		: "memory");
 	} else
 		return -ENOSYS;
 
-	return retval;
+	*uval = val;
+	return ret;
 }
 
 #endif
diff --git a/arch/mn10300/kernel/time.c b/arch/mn10300/kernel/time.c
index 75da468090b9..5b955000626d 100644
--- a/arch/mn10300/kernel/time.c
+++ b/arch/mn10300/kernel/time.c
@@ -104,8 +104,6 @@ static irqreturn_t timer_interrupt(int irq, void *dev_id)
 	unsigned tsc, elapse;
 	irqreturn_t ret;
 
-	write_seqlock(&xtime_lock);
-
 	while (tsc = get_cycles(),
 	       elapse = tsc - mn10300_last_tsc, /* time elapsed since last
 						 * tick */
@@ -114,11 +112,9 @@ static irqreturn_t timer_interrupt(int irq, void *dev_id)
 		mn10300_last_tsc += MN10300_TSC_PER_HZ;
 
 		/* advance the kernel's time tracking system */
-		do_timer(1);
+		xtime_update(1);
 	}
 
-	write_sequnlock(&xtime_lock);
-
 	ret = local_timer_interrupt();
 #ifdef CONFIG_SMP
 	send_IPI_allbutself(LOCAL_TIMER_IPI);
diff --git a/arch/parisc/hpux/sys_hpux.c b/arch/parisc/hpux/sys_hpux.c
index 30394081d9b6..6ab9580b0b00 100644
--- a/arch/parisc/hpux/sys_hpux.c
+++ b/arch/parisc/hpux/sys_hpux.c
@@ -185,26 +185,21 @@ struct hpux_statfs {
      int16_t f_pad;
 };
 
-static int do_statfs_hpux(struct path *path, struct hpux_statfs *buf)
+static int do_statfs_hpux(struct kstatfs *st, struct hpux_statfs __user *p)
 {
-	struct kstatfs st;
-	int retval;
-	
-	retval = vfs_statfs(path, &st);
-	if (retval)
-		return retval;
-
-	memset(buf, 0, sizeof(*buf));
-	buf->f_type = st.f_type;
-	buf->f_bsize = st.f_bsize;
-	buf->f_blocks = st.f_blocks;
-	buf->f_bfree = st.f_bfree;
-	buf->f_bavail = st.f_bavail;
-	buf->f_files = st.f_files;
-	buf->f_ffree = st.f_ffree;
-	buf->f_fsid[0] = st.f_fsid.val[0];
-	buf->f_fsid[1] = st.f_fsid.val[1];
-
+	struct hpux_statfs buf;
+	memset(&buf, 0, sizeof(buf));
+	buf.f_type = st->f_type;
+	buf.f_bsize = st->f_bsize;
+	buf.f_blocks = st->f_blocks;
+	buf.f_bfree = st->f_bfree;
+	buf.f_bavail = st->f_bavail;
+	buf.f_files = st->f_files;
+	buf.f_ffree = st->f_ffree;
+	buf.f_fsid[0] = st->f_fsid.val[0];
+	buf.f_fsid[1] = st->f_fsid.val[1];
+	if (copy_to_user(p, &buf, sizeof(buf)))
+		return -EFAULT;
 	return 0;
 }
 
@@ -212,35 +207,19 @@ static int do_statfs_hpux(struct path *path, struct hpux_statfs *buf)
 asmlinkage long hpux_statfs(const char __user *pathname,
 						struct hpux_statfs __user *buf)
 {
-	struct path path;
-	int error;
-
-	error = user_path(pathname, &path);
-	if (!error) {
-		struct hpux_statfs tmp;
-		error = do_statfs_hpux(&path, &tmp);
-		if (!error && copy_to_user(buf, &tmp, sizeof(tmp)))
-			error = -EFAULT;
-		path_put(&path);
-	}
+	struct kstatfs st;
+	int error = user_statfs(pathname, &st);
+	if (!error)
+		error = do_statfs_hpux(&st, buf);
 	return error;
 }
 
 asmlinkage long hpux_fstatfs(unsigned int fd, struct hpux_statfs __user * buf)
 {
-	struct file *file;
-	struct hpux_statfs tmp;
-	int error;
-
-	error = -EBADF;
-	file = fget(fd);
-	if (!file)
-		goto out;
-	error = do_statfs_hpux(&file->f_path, &tmp);
-	if (!error && copy_to_user(buf, &tmp, sizeof(tmp)))
-		error = -EFAULT;
-	fput(file);
- out:
+	struct kstatfs st;
+	int error = fd_statfs(fd, &st);
+	if (!error)
+		error = do_statfs_hpux(&st, buf);
 	return error;
 }
 
diff --git a/arch/parisc/include/asm/fcntl.h b/arch/parisc/include/asm/fcntl.h
index f357fc693c89..0304b92ccfea 100644
--- a/arch/parisc/include/asm/fcntl.h
+++ b/arch/parisc/include/asm/fcntl.h
@@ -19,6 +19,8 @@
 #define O_NOFOLLOW	000000200 /* don't follow links */
 #define O_INVISIBLE	004000000 /* invisible I/O, for DMAPI/XDSM */
 
+#define O_PATH		020000000
+
 #define F_GETLK64	8
 #define F_SETLK64	9
 #define F_SETLKW64	10
diff --git a/arch/parisc/include/asm/futex.h b/arch/parisc/include/asm/futex.h
index 0c705c3a55ef..67a33cc27ef2 100644
--- a/arch/parisc/include/asm/futex.h
+++ b/arch/parisc/include/asm/futex.h
@@ -8,7 +8,7 @@
 #include <asm/errno.h>
 
 static inline int
-futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
+futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 {
 	int op = (encoded_op >> 28) & 7;
 	int cmp = (encoded_op >> 24) & 15;
@@ -18,7 +18,7 @@ futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
 	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
 		oparg = 1 << oparg;
 
-	if (! access_ok (VERIFY_WRITE, uaddr, sizeof(int)))
+	if (! access_ok (VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
 	pagefault_disable();
@@ -51,10 +51,10 @@ futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
 
 /* Non-atomic version */
 static inline int
-futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+			      u32 oldval, u32 newval)
 {
-	int err = 0;
-	int uval;
+	u32 val;
 
 	/* futex.c wants to do a cmpxchg_inatomic on kernel NULL, which is
 	 * our gateway page, and causes no end of trouble...
@@ -62,15 +62,15 @@ futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
 	if (segment_eq(KERNEL_DS, get_fs()) && !uaddr)
 		return -EFAULT;
 
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
-	err = get_user(uval, uaddr);
-	if (err) return -EFAULT;
-	if (uval == oldval)
-		err = put_user(newval, uaddr);
-	if (err) return -EFAULT;
-	return uval;
+	if (get_user(val, uaddr))
+		return -EFAULT;
+	if (val == oldval && put_user(newval, uaddr))
+		return -EFAULT;
+	*uval = val;
+	return 0;
 }
 
 #endif /*__KERNEL__*/
diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c
index 05511ccb61d2..45b7389d77aa 100644
--- a/arch/parisc/kernel/time.c
+++ b/arch/parisc/kernel/time.c
@@ -162,11 +162,8 @@ irqreturn_t __irq_entry timer_interrupt(int irq, void *dev_id)
 		update_process_times(user_mode(get_irq_regs()));
 	}
 
-	if (cpu == 0) {
-		write_seqlock(&xtime_lock);
-		do_timer(ticks_elapsed);
-		write_sequnlock(&xtime_lock);
-	}
+	if (cpu == 0)
+		xtime_update(ticks_elapsed);
 
 	return IRQ_HANDLED;
 }
diff --git a/arch/powerpc/include/asm/futex.h b/arch/powerpc/include/asm/futex.h
index 7c589ef81fb0..c94e4a3fe2ef 100644
--- a/arch/powerpc/include/asm/futex.h
+++ b/arch/powerpc/include/asm/futex.h
@@ -30,7 +30,7 @@
 	: "b" (uaddr), "i" (-EFAULT), "r" (oparg) \
 	: "cr0", "memory")
 
-static inline int futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
+static inline int futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 {
 	int op = (encoded_op >> 28) & 7;
 	int cmp = (encoded_op >> 24) & 15;
@@ -40,7 +40,7 @@ static inline int futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
 	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
 		oparg = 1 << oparg;
 
-	if (! access_ok (VERIFY_WRITE, uaddr, sizeof(int)))
+	if (! access_ok (VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
 	pagefault_disable();
@@ -82,35 +82,38 @@ static inline int futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
 }
 
 static inline int
-futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+			      u32 oldval, u32 newval)
 {
-	int prev;
+	int ret = 0;
+	u32 prev;
 
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
         __asm__ __volatile__ (
         PPC_RELEASE_BARRIER
-"1:     lwarx   %0,0,%2         # futex_atomic_cmpxchg_inatomic\n\
-        cmpw    0,%0,%3\n\
+"1:     lwarx   %1,0,%3         # futex_atomic_cmpxchg_inatomic\n\
+        cmpw    0,%1,%4\n\
         bne-    3f\n"
-        PPC405_ERR77(0,%2)
-"2:     stwcx.  %4,0,%2\n\
+        PPC405_ERR77(0,%3)
+"2:     stwcx.  %5,0,%3\n\
         bne-    1b\n"
         PPC_ACQUIRE_BARRIER
 "3:	.section .fixup,\"ax\"\n\
-4:	li	%0,%5\n\
+4:	li	%0,%6\n\
 	b	3b\n\
 	.previous\n\
 	.section __ex_table,\"a\"\n\
 	.align 3\n\
 	" PPC_LONG "1b,4b,2b,4b\n\
 	.previous" \
-        : "=&r" (prev), "+m" (*uaddr)
+        : "+r" (ret), "=&r" (prev), "+m" (*uaddr)
         : "r" (uaddr), "r" (oldval), "r" (newval), "i" (-EFAULT)
         : "cc", "memory");
 
-        return prev;
+	*uval = prev;
+        return ret;
 }
 
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index 51e9e6f90d12..edeb80fdd2c3 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -171,6 +171,16 @@ static inline struct pci_controller *pci_bus_to_host(const struct pci_bus *bus)
 	return bus->sysdata;
 }
 
+static inline struct device_node *pci_bus_to_OF_node(struct pci_bus *bus)
+{
+	struct pci_controller *host;
+
+	if (bus->self)
+		return pci_device_to_OF_node(bus->self);
+	host = pci_bus_to_host(bus);
+	return host ? host->dn : NULL;
+}
+
 static inline int isa_vaddr_is_ioport(void __iomem *address)
 {
 	/* No specific ISA handling on ppc32 at this stage, it
diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h
index d72757585595..c189aa5fe1f4 100644
--- a/arch/powerpc/include/asm/prom.h
+++ b/arch/powerpc/include/asm/prom.h
@@ -70,21 +70,6 @@ static inline int of_node_to_nid(struct device_node *device) { return 0; }
 #endif
 #define of_node_to_nid of_node_to_nid
 
-/**
- * of_irq_map_pci - Resolve the interrupt for a PCI device
- * @pdev:	the device whose interrupt is to be resolved
- * @out_irq:	structure of_irq filled by this function
- *
- * This function resolves the PCI interrupt for a given PCI device. If a
- * device-node exists for a given pci_dev, it will use normal OF tree
- * walking. If not, it will implement standard swizzling and walk up the
- * PCI tree until an device-node is found, at which point it will finish
- * resolving using the OF tree walking.
- */
-struct pci_dev;
-struct of_irq;
-extern int of_irq_map_pci(struct pci_dev *pdev, struct of_irq *out_irq);
-
 extern void of_instantiate_rtc(void);
 
 /* These includes are put at the bottom because they may contain things
diff --git a/arch/powerpc/include/asm/rwsem.h b/arch/powerpc/include/asm/rwsem.h
index 8447d89fbe72..bb1e2cdeb9bf 100644
--- a/arch/powerpc/include/asm/rwsem.h
+++ b/arch/powerpc/include/asm/rwsem.h
@@ -13,11 +13,6 @@
  * by Paul Mackerras <paulus@samba.org>.
  */
 
-#include <linux/list.h>
-#include <linux/spinlock.h>
-#include <asm/atomic.h>
-#include <asm/system.h>
-
 /*
  * the semaphore definition
  */
@@ -33,47 +28,6 @@
 #define RWSEM_ACTIVE_READ_BIAS		RWSEM_ACTIVE_BIAS
 #define RWSEM_ACTIVE_WRITE_BIAS		(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
 
-struct rw_semaphore {
-	long			count;
-	spinlock_t		wait_lock;
-	struct list_head	wait_list;
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-	struct lockdep_map	dep_map;
-#endif
-};
-
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define __RWSEM_DEP_MAP_INIT(lockname) , .dep_map = { .name = #lockname }
-#else
-# define __RWSEM_DEP_MAP_INIT(lockname)
-#endif
-
-#define __RWSEM_INITIALIZER(name)				\
-{								\
-	RWSEM_UNLOCKED_VALUE,					\
-	__SPIN_LOCK_UNLOCKED((name).wait_lock),			\
-	LIST_HEAD_INIT((name).wait_list)			\
-	__RWSEM_DEP_MAP_INIT(name)				\
-}
-
-#define DECLARE_RWSEM(name)		\
-	struct rw_semaphore name = __RWSEM_INITIALIZER(name)
-
-extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
-
-extern void __init_rwsem(struct rw_semaphore *sem, const char *name,
-			 struct lock_class_key *key);
-
-#define init_rwsem(sem)					\
-	do {						\
-		static struct lock_class_key __key;	\
-							\
-		__init_rwsem((sem), #sem, &__key);	\
-	} while (0)
-
 /*
  * lock for reading
  */
@@ -174,10 +128,5 @@ static inline long rwsem_atomic_update(long delta, struct rw_semaphore *sem)
 	return atomic_long_add_return(delta, (atomic_long_t *)&sem->count);
 }
 
-static inline int rwsem_is_locked(struct rw_semaphore *sem)
-{
-	return sem->count != 0;
-}
-
 #endif	/* __KERNEL__ */
 #endif	/* _ASM_POWERPC_RWSEM_H */
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 10a44e68ef11..eb341be9a4d9 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -22,6 +22,7 @@
 #include <linux/init.h>
 #include <linux/bootmem.h>
 #include <linux/of_address.h>
+#include <linux/of_pci.h>
 #include <linux/mm.h>
 #include <linux/list.h>
 #include <linux/syscalls.h>
diff --git a/arch/powerpc/kernel/prom_parse.c b/arch/powerpc/kernel/prom_parse.c
index c2b7a07cc3d3..47187cc2cf00 100644
--- a/arch/powerpc/kernel/prom_parse.c
+++ b/arch/powerpc/kernel/prom_parse.c
@@ -2,95 +2,11 @@
 
 #include <linux/kernel.h>
 #include <linux/string.h>
-#include <linux/pci_regs.h>
 #include <linux/module.h>
 #include <linux/ioport.h>
 #include <linux/etherdevice.h>
 #include <linux/of_address.h>
 #include <asm/prom.h>
-#include <asm/pci-bridge.h>
-
-#ifdef CONFIG_PCI
-int of_irq_map_pci(struct pci_dev *pdev, struct of_irq *out_irq)
-{
-	struct device_node *dn, *ppnode;
-	struct pci_dev *ppdev;
-	u32 lspec;
-	u32 laddr[3];
-	u8 pin;
-	int rc;
-
-	/* Check if we have a device node, if yes, fallback to standard OF
-	 * parsing
-	 */
-	dn = pci_device_to_OF_node(pdev);
-	if (dn) {
-		rc = of_irq_map_one(dn, 0, out_irq);
-		if (!rc)
-			return rc;
-	}
-
-	/* Ok, we don't, time to have fun. Let's start by building up an
-	 * interrupt spec.  we assume #interrupt-cells is 1, which is standard
-	 * for PCI. If you do different, then don't use that routine.
-	 */
-	rc = pci_read_config_byte(pdev, PCI_INTERRUPT_PIN, &pin);
-	if (rc != 0)
-		return rc;
-	/* No pin, exit */
-	if (pin == 0)
-		return -ENODEV;
-
-	/* Now we walk up the PCI tree */
-	lspec = pin;
-	for (;;) {
-		/* Get the pci_dev of our parent */
-		ppdev = pdev->bus->self;
-
-		/* Ouch, it's a host bridge... */
-		if (ppdev == NULL) {
-#ifdef CONFIG_PPC64
-			ppnode = pci_bus_to_OF_node(pdev->bus);
-#else
-			struct pci_controller *host;
-			host = pci_bus_to_host(pdev->bus);
-			ppnode = host ? host->dn : NULL;
-#endif
-			/* No node for host bridge ? give up */
-			if (ppnode == NULL)
-				return -EINVAL;
-		} else
-			/* We found a P2P bridge, check if it has a node */
-			ppnode = pci_device_to_OF_node(ppdev);
-
-		/* Ok, we have found a parent with a device-node, hand over to
-		 * the OF parsing code.
-		 * We build a unit address from the linux device to be used for
-		 * resolution. Note that we use the linux bus number which may
-		 * not match your firmware bus numbering.
-		 * Fortunately, in most cases, interrupt-map-mask doesn't include
-		 * the bus number as part of the matching.
-		 * You should still be careful about that though if you intend
-		 * to rely on this function (you ship  a firmware that doesn't
-		 * create device nodes for all PCI devices).
-		 */
-		if (ppnode)
-			break;
-
-		/* We can only get here if we hit a P2P bridge with no node,
-		 * let's do standard swizzling and try again
-		 */
-		lspec = pci_swizzle_interrupt_pin(pdev, lspec);
-		pdev = ppdev;
-	}
-
-	laddr[0] = (pdev->bus->number << 16)
-		| (pdev->devfn << 8);
-	laddr[1]  = laddr[2] = 0;
-	return of_irq_map_raw(ppnode, &lspec, 1, laddr, out_irq);
-}
-EXPORT_SYMBOL_GPL(of_irq_map_pci);
-#endif /* CONFIG_PCI */
 
 void of_parse_dma_window(struct device_node *dn, const void *dma_window_prop,
 		unsigned long *busno, unsigned long *phys, unsigned long *size)
diff --git a/arch/powerpc/platforms/cell/spufs/syscalls.c b/arch/powerpc/platforms/cell/spufs/syscalls.c
index 187a7d32f86a..a3d2ce54ea2e 100644
--- a/arch/powerpc/platforms/cell/spufs/syscalls.c
+++ b/arch/powerpc/platforms/cell/spufs/syscalls.c
@@ -70,7 +70,7 @@ static long do_spu_create(const char __user *pathname, unsigned int flags,
 	if (!IS_ERR(tmp)) {
 		struct nameidata nd;
 
-		ret = path_lookup(tmp, LOOKUP_PARENT, &nd);
+		ret = kern_path_parent(tmp, &nd);
 		if (!ret) {
 			nd.flags |= LOOKUP_OPEN | LOOKUP_CREATE;
 			ret = spufs_create(&nd, flags, mode, neighbor);
diff --git a/arch/s390/include/asm/futex.h b/arch/s390/include/asm/futex.h
index 5c5d02de49e9..81cf36b691f1 100644
--- a/arch/s390/include/asm/futex.h
+++ b/arch/s390/include/asm/futex.h
@@ -7,7 +7,7 @@
 #include <linux/uaccess.h>
 #include <asm/errno.h>
 
-static inline int futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
+static inline int futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 {
 	int op = (encoded_op >> 28) & 7;
 	int cmp = (encoded_op >> 24) & 15;
@@ -18,7 +18,7 @@ static inline int futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
 	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
 		oparg = 1 << oparg;
 
-	if (! access_ok (VERIFY_WRITE, uaddr, sizeof(int)))
+	if (! access_ok (VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
 	pagefault_disable();
@@ -39,13 +39,13 @@ static inline int futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
 	return ret;
 }
 
-static inline int futex_atomic_cmpxchg_inatomic(int __user *uaddr,
-						int oldval, int newval)
+static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+						u32 oldval, u32 newval)
 {
-	if (! access_ok (VERIFY_WRITE, uaddr, sizeof(int)))
+	if (! access_ok (VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
-	return uaccess.futex_atomic_cmpxchg(uaddr, oldval, newval);
+	return uaccess.futex_atomic_cmpxchg(uval, uaddr, oldval, newval);
 }
 
 #endif /* __KERNEL__ */
diff --git a/arch/s390/include/asm/rwsem.h b/arch/s390/include/asm/rwsem.h
index 423fdda2322d..d0eb4653cebd 100644
--- a/arch/s390/include/asm/rwsem.h
+++ b/arch/s390/include/asm/rwsem.h
@@ -43,29 +43,6 @@
 
 #ifdef __KERNEL__
 
-#include <linux/list.h>
-#include <linux/spinlock.h>
-
-struct rwsem_waiter;
-
-extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *);
-extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *);
-extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *);
-extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *);
-extern struct rw_semaphore *rwsem_downgrade_write(struct rw_semaphore *);
-
-/*
- * the semaphore definition
- */
-struct rw_semaphore {
-	signed long		count;
-	spinlock_t		wait_lock;
-	struct list_head	wait_list;
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-	struct lockdep_map	dep_map;
-#endif
-};
-
 #ifndef __s390x__
 #define RWSEM_UNLOCKED_VALUE	0x00000000
 #define RWSEM_ACTIVE_BIAS	0x00000001
@@ -81,41 +58,6 @@ struct rw_semaphore {
 #define RWSEM_ACTIVE_WRITE_BIAS	(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
 
 /*
- * initialisation
- */
-
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define __RWSEM_DEP_MAP_INIT(lockname) , .dep_map = { .name = #lockname }
-#else
-# define __RWSEM_DEP_MAP_INIT(lockname)
-#endif
-
-#define __RWSEM_INITIALIZER(name) \
- { RWSEM_UNLOCKED_VALUE, __SPIN_LOCK_UNLOCKED((name).wait.lock), \
-   LIST_HEAD_INIT((name).wait_list) __RWSEM_DEP_MAP_INIT(name) }
-
-#define DECLARE_RWSEM(name) \
-	struct rw_semaphore name = __RWSEM_INITIALIZER(name)
-
-static inline void init_rwsem(struct rw_semaphore *sem)
-{
-	sem->count = RWSEM_UNLOCKED_VALUE;
-	spin_lock_init(&sem->wait_lock);
-	INIT_LIST_HEAD(&sem->wait_list);
-}
-
-extern void __init_rwsem(struct rw_semaphore *sem, const char *name,
-			 struct lock_class_key *key);
-
-#define init_rwsem(sem)				\
-do {						\
-	static struct lock_class_key __key;	\
-						\
-	__init_rwsem((sem), #sem, &__key);	\
-} while (0)
-
-
-/*
  * lock for reading
  */
 static inline void __down_read(struct rw_semaphore *sem)
@@ -377,10 +319,5 @@ static inline long rwsem_atomic_update(long delta, struct rw_semaphore *sem)
 	return new;
 }
 
-static inline int rwsem_is_locked(struct rw_semaphore *sem)
-{
-	return (sem->count != 0);
-}
-
 #endif /* __KERNEL__ */
 #endif /* _S390_RWSEM_H */
diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h
index d6b1ed0ec52b..2d9ea11f919a 100644
--- a/arch/s390/include/asm/uaccess.h
+++ b/arch/s390/include/asm/uaccess.h
@@ -83,8 +83,8 @@ struct uaccess_ops {
 	size_t (*clear_user)(size_t, void __user *);
 	size_t (*strnlen_user)(size_t, const char __user *);
 	size_t (*strncpy_from_user)(size_t, const char __user *, char *);
-	int (*futex_atomic_op)(int op, int __user *, int oparg, int *old);
-	int (*futex_atomic_cmpxchg)(int __user *, int old, int new);
+	int (*futex_atomic_op)(int op, u32 __user *, int oparg, int *old);
+	int (*futex_atomic_cmpxchg)(u32 *, u32 __user *, u32 old, u32 new);
 };
 
 extern struct uaccess_ops uaccess;
diff --git a/arch/s390/lib/uaccess.h b/arch/s390/lib/uaccess.h
index 126011df14f1..1d2536cb630b 100644
--- a/arch/s390/lib/uaccess.h
+++ b/arch/s390/lib/uaccess.h
@@ -12,12 +12,12 @@ extern size_t copy_from_user_std(size_t, const void __user *, void *);
 extern size_t copy_to_user_std(size_t, void __user *, const void *);
 extern size_t strnlen_user_std(size_t, const char __user *);
 extern size_t strncpy_from_user_std(size_t, const char __user *, char *);
-extern int futex_atomic_cmpxchg_std(int __user *, int, int);
-extern int futex_atomic_op_std(int, int __user *, int, int *);
+extern int futex_atomic_cmpxchg_std(u32 *, u32 __user *, u32, u32);
+extern int futex_atomic_op_std(int, u32 __user *, int, int *);
 
 extern size_t copy_from_user_pt(size_t, const void __user *, void *);
 extern size_t copy_to_user_pt(size_t, void __user *, const void *);
-extern int futex_atomic_op_pt(int, int __user *, int, int *);
-extern int futex_atomic_cmpxchg_pt(int __user *, int, int);
+extern int futex_atomic_op_pt(int, u32 __user *, int, int *);
+extern int futex_atomic_cmpxchg_pt(u32 *, u32 __user *, u32, u32);
 
 #endif /* __ARCH_S390_LIB_UACCESS_H */
diff --git a/arch/s390/lib/uaccess_pt.c b/arch/s390/lib/uaccess_pt.c
index 404f2de296dc..74833831417f 100644
--- a/arch/s390/lib/uaccess_pt.c
+++ b/arch/s390/lib/uaccess_pt.c
@@ -302,7 +302,7 @@ fault:
 		     : "0" (-EFAULT), "d" (oparg), "a" (uaddr),		\
 		       "m" (*uaddr) : "cc" );
 
-static int __futex_atomic_op_pt(int op, int __user *uaddr, int oparg, int *old)
+static int __futex_atomic_op_pt(int op, u32 __user *uaddr, int oparg, int *old)
 {
 	int oldval = 0, newval, ret;
 
@@ -335,7 +335,7 @@ static int __futex_atomic_op_pt(int op, int __user *uaddr, int oparg, int *old)
 	return ret;
 }
 
-int futex_atomic_op_pt(int op, int __user *uaddr, int oparg, int *old)
+int futex_atomic_op_pt(int op, u32 __user *uaddr, int oparg, int *old)
 {
 	int ret;
 
@@ -354,26 +354,29 @@ int futex_atomic_op_pt(int op, int __user *uaddr, int oparg, int *old)
 	return ret;
 }
 
-static int __futex_atomic_cmpxchg_pt(int __user *uaddr, int oldval, int newval)
+static int __futex_atomic_cmpxchg_pt(u32 *uval, u32 __user *uaddr,
+				     u32 oldval, u32 newval)
 {
 	int ret;
 
 	asm volatile("0: cs   %1,%4,0(%5)\n"
-		     "1: lr   %0,%1\n"
+		     "1: la   %0,0\n"
 		     "2:\n"
 		     EX_TABLE(0b,2b) EX_TABLE(1b,2b)
 		     : "=d" (ret), "+d" (oldval), "=m" (*uaddr)
 		     : "0" (-EFAULT), "d" (newval), "a" (uaddr), "m" (*uaddr)
 		     : "cc", "memory" );
+	*uval = oldval;
 	return ret;
 }
 
-int futex_atomic_cmpxchg_pt(int __user *uaddr, int oldval, int newval)
+int futex_atomic_cmpxchg_pt(u32 *uval, u32 __user *uaddr,
+			    u32 oldval, u32 newval)
 {
 	int ret;
 
 	if (segment_eq(get_fs(), KERNEL_DS))
-		return __futex_atomic_cmpxchg_pt(uaddr, oldval, newval);
+		return __futex_atomic_cmpxchg_pt(uval, uaddr, oldval, newval);
 	spin_lock(&current->mm->page_table_lock);
 	uaddr = (int __user *) __dat_user_addr((unsigned long) uaddr);
 	if (!uaddr) {
@@ -382,7 +385,7 @@ int futex_atomic_cmpxchg_pt(int __user *uaddr, int oldval, int newval)
 	}
 	get_page(virt_to_page(uaddr));
 	spin_unlock(&current->mm->page_table_lock);
-	ret = __futex_atomic_cmpxchg_pt(uaddr, oldval, newval);
+	ret = __futex_atomic_cmpxchg_pt(uval, uaddr, oldval, newval);
 	put_page(virt_to_page(uaddr));
 	return ret;
 }
diff --git a/arch/s390/lib/uaccess_std.c b/arch/s390/lib/uaccess_std.c
index a6c4f7ed24a4..bb1a7eed42ce 100644
--- a/arch/s390/lib/uaccess_std.c
+++ b/arch/s390/lib/uaccess_std.c
@@ -255,7 +255,7 @@ size_t strncpy_from_user_std(size_t size, const char __user *src, char *dst)
 		: "0" (-EFAULT), "d" (oparg), "a" (uaddr),		\
 		  "m" (*uaddr) : "cc");
 
-int futex_atomic_op_std(int op, int __user *uaddr, int oparg, int *old)
+int futex_atomic_op_std(int op, u32 __user *uaddr, int oparg, int *old)
 {
 	int oldval = 0, newval, ret;
 
@@ -287,19 +287,21 @@ int futex_atomic_op_std(int op, int __user *uaddr, int oparg, int *old)
 	return ret;
 }
 
-int futex_atomic_cmpxchg_std(int __user *uaddr, int oldval, int newval)
+int futex_atomic_cmpxchg_std(u32 *uval, u32 __user *uaddr,
+			     u32 oldval, u32 newval)
 {
 	int ret;
 
 	asm volatile(
 		"   sacf 256\n"
 		"0: cs   %1,%4,0(%5)\n"
-		"1: lr   %0,%1\n"
+		"1: la   %0,0\n"
 		"2: sacf 0\n"
 		EX_TABLE(0b,2b) EX_TABLE(1b,2b)
 		: "=d" (ret), "+d" (oldval), "=m" (*uaddr)
 		: "0" (-EFAULT), "d" (newval), "a" (uaddr), "m" (*uaddr)
 		: "cc", "memory" );
+	*uval = oldval;
 	return ret;
 }
 
diff --git a/arch/sh/include/asm/futex-irq.h b/arch/sh/include/asm/futex-irq.h
index a9f16a7f9aea..6cb9f193a95e 100644
--- a/arch/sh/include/asm/futex-irq.h
+++ b/arch/sh/include/asm/futex-irq.h
@@ -3,7 +3,7 @@
 
 #include <asm/system.h>
 
-static inline int atomic_futex_op_xchg_set(int oparg, int __user *uaddr,
+static inline int atomic_futex_op_xchg_set(int oparg, u32 __user *uaddr,
 					   int *oldval)
 {
 	unsigned long flags;
@@ -20,7 +20,7 @@ static inline int atomic_futex_op_xchg_set(int oparg, int __user *uaddr,
 	return ret;
 }
 
-static inline int atomic_futex_op_xchg_add(int oparg, int __user *uaddr,
+static inline int atomic_futex_op_xchg_add(int oparg, u32 __user *uaddr,
 					   int *oldval)
 {
 	unsigned long flags;
@@ -37,7 +37,7 @@ static inline int atomic_futex_op_xchg_add(int oparg, int __user *uaddr,
 	return ret;
 }
 
-static inline int atomic_futex_op_xchg_or(int oparg, int __user *uaddr,
+static inline int atomic_futex_op_xchg_or(int oparg, u32 __user *uaddr,
 					  int *oldval)
 {
 	unsigned long flags;
@@ -54,7 +54,7 @@ static inline int atomic_futex_op_xchg_or(int oparg, int __user *uaddr,
 	return ret;
 }
 
-static inline int atomic_futex_op_xchg_and(int oparg, int __user *uaddr,
+static inline int atomic_futex_op_xchg_and(int oparg, u32 __user *uaddr,
 					   int *oldval)
 {
 	unsigned long flags;
@@ -71,7 +71,7 @@ static inline int atomic_futex_op_xchg_and(int oparg, int __user *uaddr,
 	return ret;
 }
 
-static inline int atomic_futex_op_xchg_xor(int oparg, int __user *uaddr,
+static inline int atomic_futex_op_xchg_xor(int oparg, u32 __user *uaddr,
 					   int *oldval)
 {
 	unsigned long flags;
@@ -88,11 +88,13 @@ static inline int atomic_futex_op_xchg_xor(int oparg, int __user *uaddr,
 	return ret;
 }
 
-static inline int atomic_futex_op_cmpxchg_inatomic(int __user *uaddr,
-						   int oldval, int newval)
+static inline int atomic_futex_op_cmpxchg_inatomic(u32 *uval,
+						   u32 __user *uaddr,
+						   u32 oldval, u32 newval)
 {
 	unsigned long flags;
-	int ret, prev = 0;
+	int ret;
+	u32 prev = 0;
 
 	local_irq_save(flags);
 
@@ -102,10 +104,8 @@ static inline int atomic_futex_op_cmpxchg_inatomic(int __user *uaddr,
 
 	local_irq_restore(flags);
 
-	if (ret)
-		return ret;
-
-	return prev;
+	*uval = prev;
+	return ret;
 }
 
 #endif /* __ASM_SH_FUTEX_IRQ_H */
diff --git a/arch/sh/include/asm/futex.h b/arch/sh/include/asm/futex.h
index 68256ec5fa35..7be39a646fbd 100644
--- a/arch/sh/include/asm/futex.h
+++ b/arch/sh/include/asm/futex.h
@@ -10,7 +10,7 @@
 /* XXX: UP variants, fix for SH-4A and SMP.. */
 #include <asm/futex-irq.h>
 
-static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
+static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 {
 	int op = (encoded_op >> 28) & 7;
 	int cmp = (encoded_op >> 24) & 15;
@@ -21,7 +21,7 @@ static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
 	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
 		oparg = 1 << oparg;
 
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
 	pagefault_disable();
@@ -65,12 +65,13 @@ static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
 }
 
 static inline int
-futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+			      u32 oldval, u32 newval)
 {
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
-	return atomic_futex_op_cmpxchg_inatomic(uaddr, oldval, newval);
+	return atomic_futex_op_cmpxchg_inatomic(uval, uaddr, oldval, newval);
 }
 
 #endif /* __KERNEL__ */
diff --git a/arch/sh/include/asm/rwsem.h b/arch/sh/include/asm/rwsem.h
index 06e2251a5e48..edab57265293 100644
--- a/arch/sh/include/asm/rwsem.h
+++ b/arch/sh/include/asm/rwsem.h
@@ -11,64 +11,13 @@
 #endif
 
 #ifdef __KERNEL__
-#include <linux/list.h>
-#include <linux/spinlock.h>
-#include <asm/atomic.h>
-#include <asm/system.h>
 
-/*
- * the semaphore definition
- */
-struct rw_semaphore {
-	long		count;
 #define RWSEM_UNLOCKED_VALUE		0x00000000
 #define RWSEM_ACTIVE_BIAS		0x00000001
 #define RWSEM_ACTIVE_MASK		0x0000ffff
 #define RWSEM_WAITING_BIAS		(-0x00010000)
 #define RWSEM_ACTIVE_READ_BIAS		RWSEM_ACTIVE_BIAS
 #define RWSEM_ACTIVE_WRITE_BIAS		(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
-	spinlock_t		wait_lock;
-	struct list_head	wait_list;
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-	struct lockdep_map	dep_map;
-#endif
-};
-
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define __RWSEM_DEP_MAP_INIT(lockname) , .dep_map = { .name = #lockname }
-#else
-# define __RWSEM_DEP_MAP_INIT(lockname)
-#endif
-
-#define __RWSEM_INITIALIZER(name) \
-	{ RWSEM_UNLOCKED_VALUE, __SPIN_LOCK_UNLOCKED((name).wait_lock), \
-	  LIST_HEAD_INIT((name).wait_list) \
-	  __RWSEM_DEP_MAP_INIT(name) }
-
-#define DECLARE_RWSEM(name)		\
-	struct rw_semaphore name = __RWSEM_INITIALIZER(name)
-
-extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
-
-extern void __init_rwsem(struct rw_semaphore *sem, const char *name,
-			 struct lock_class_key *key);
-
-#define init_rwsem(sem)				\
-do {						\
-	static struct lock_class_key __key;	\
-						\
-	__init_rwsem((sem), #sem, &__key);	\
-} while (0)
-
-static inline void init_rwsem(struct rw_semaphore *sem)
-{
-	sem->count = RWSEM_UNLOCKED_VALUE;
-	spin_lock_init(&sem->wait_lock);
-	INIT_LIST_HEAD(&sem->wait_list);
-}
 
 /*
  * lock for reading
@@ -179,10 +128,5 @@ static inline int rwsem_atomic_update(int delta, struct rw_semaphore *sem)
 	return atomic_add_return(delta, (atomic_t *)(&sem->count));
 }
 
-static inline int rwsem_is_locked(struct rw_semaphore *sem)
-{
-	return (sem->count != 0);
-}
-
 #endif /* __KERNEL__ */
 #endif /* _ASM_SH_RWSEM_H */
diff --git a/arch/sparc/include/asm/fcntl.h b/arch/sparc/include/asm/fcntl.h
index 38f37b333cc7..d0b83f66f356 100644
--- a/arch/sparc/include/asm/fcntl.h
+++ b/arch/sparc/include/asm/fcntl.h
@@ -34,6 +34,8 @@
 #define __O_SYNC	0x800000
 #define O_SYNC		(__O_SYNC|O_DSYNC)
 
+#define O_PATH		0x1000000
+
 #define F_GETOWN	5	/*  for sockets. */
 #define F_SETOWN	6	/*  for sockets. */
 #define F_GETLK		7
diff --git a/arch/sparc/include/asm/futex_64.h b/arch/sparc/include/asm/futex_64.h
index 47f95839dc69..444e7bea23bc 100644
--- a/arch/sparc/include/asm/futex_64.h
+++ b/arch/sparc/include/asm/futex_64.h
@@ -30,7 +30,7 @@
 	: "r" (uaddr), "r" (oparg), "i" (-EFAULT)	\
 	: "memory")
 
-static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
+static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 {
 	int op = (encoded_op >> 28) & 7;
 	int cmp = (encoded_op >> 24) & 15;
@@ -38,7 +38,7 @@ static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
 	int cmparg = (encoded_op << 20) >> 20;
 	int oldval = 0, ret, tem;
 
-	if (unlikely(!access_ok(VERIFY_WRITE, uaddr, sizeof(int))))
+	if (unlikely(!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))))
 		return -EFAULT;
 	if (unlikely((((unsigned long) uaddr) & 0x3UL)))
 		return -EINVAL;
@@ -85,26 +85,30 @@ static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
 }
 
 static inline int
-futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+			      u32 oldval, u32 newval)
 {
+	int ret = 0;
+
 	__asm__ __volatile__(
-	"\n1:	casa	[%3] %%asi, %2, %0\n"
+	"\n1:	casa	[%4] %%asi, %3, %1\n"
 	"2:\n"
 	"	.section .fixup,#alloc,#execinstr\n"
 	"	.align	4\n"
 	"3:	sethi	%%hi(2b), %0\n"
 	"	jmpl	%0 + %%lo(2b), %%g0\n"
-	"	 mov	%4, %0\n"
+	"	mov	%5, %0\n"
 	"	.previous\n"
 	"	.section __ex_table,\"a\"\n"
 	"	.align	4\n"
 	"	.word	1b, 3b\n"
 	"	.previous\n"
-	: "=r" (newval)
-	: "0" (newval), "r" (oldval), "r" (uaddr), "i" (-EFAULT)
+	: "+r" (ret), "=r" (newval)
+	: "1" (newval), "r" (oldval), "r" (uaddr), "i" (-EFAULT)
 	: "memory");
 
-	return newval;
+	*uval = newval;
+	return ret;
 }
 
 #endif /* !(_SPARC64_FUTEX_H) */
diff --git a/arch/sparc/include/asm/rwsem.h b/arch/sparc/include/asm/rwsem.h
index a2b4302869bc..069bf4d663a1 100644
--- a/arch/sparc/include/asm/rwsem.h
+++ b/arch/sparc/include/asm/rwsem.h
@@ -13,53 +13,12 @@
 
 #ifdef __KERNEL__
 
-#include <linux/list.h>
-#include <linux/spinlock.h>
-
-struct rwsem_waiter;
-
-struct rw_semaphore {
-	signed long			count;
 #define RWSEM_UNLOCKED_VALUE		0x00000000L
 #define RWSEM_ACTIVE_BIAS		0x00000001L
 #define RWSEM_ACTIVE_MASK		0xffffffffL
 #define RWSEM_WAITING_BIAS		(-RWSEM_ACTIVE_MASK-1)
 #define RWSEM_ACTIVE_READ_BIAS		RWSEM_ACTIVE_BIAS
 #define RWSEM_ACTIVE_WRITE_BIAS		(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
-	spinlock_t			wait_lock;
-	struct list_head		wait_list;
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-	struct lockdep_map		dep_map;
-#endif
-};
-
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define __RWSEM_DEP_MAP_INIT(lockname) , .dep_map = { .name = #lockname }
-#else
-# define __RWSEM_DEP_MAP_INIT(lockname)
-#endif
-
-#define __RWSEM_INITIALIZER(name) \
-{ RWSEM_UNLOCKED_VALUE, __SPIN_LOCK_UNLOCKED((name).wait_lock), \
-  LIST_HEAD_INIT((name).wait_list) __RWSEM_DEP_MAP_INIT(name) }
-
-#define DECLARE_RWSEM(name) \
-	struct rw_semaphore name = __RWSEM_INITIALIZER(name)
-
-extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
-
-extern void __init_rwsem(struct rw_semaphore *sem, const char *name,
-			 struct lock_class_key *key);
-
-#define init_rwsem(sem)						\
-do {								\
-	static struct lock_class_key __key;			\
-								\
-	__init_rwsem((sem), #sem, &__key);			\
-} while (0)
 
 /*
  * lock for reading
@@ -160,11 +119,6 @@ static inline long rwsem_atomic_update(long delta, struct rw_semaphore *sem)
 	return atomic64_add_return(delta, (atomic64_t *)(&sem->count));
 }
 
-static inline int rwsem_is_locked(struct rw_semaphore *sem)
-{
-	return (sem->count != 0);
-}
-
 #endif /* __KERNEL__ */
 
 #endif /* _SPARC64_RWSEM_H */
diff --git a/arch/sparc/kernel/pcic.c b/arch/sparc/kernel/pcic.c
index aeaa09a3c655..2cdc131b50ac 100644
--- a/arch/sparc/kernel/pcic.c
+++ b/arch/sparc/kernel/pcic.c
@@ -700,10 +700,8 @@ static void pcic_clear_clock_irq(void)
 
 static irqreturn_t pcic_timer_handler (int irq, void *h)
 {
-	write_seqlock(&xtime_lock);	/* Dummy, to show that we remember */
 	pcic_clear_clock_irq();
-	do_timer(1);
-	write_sequnlock(&xtime_lock);
+	xtime_update(1);
 #ifndef CONFIG_SMP
 	update_process_times(user_mode(get_irq_regs()));
 #endif
diff --git a/arch/sparc/kernel/time_32.c b/arch/sparc/kernel/time_32.c
index 9c743b1886ff..4211bfc9bcad 100644
--- a/arch/sparc/kernel/time_32.c
+++ b/arch/sparc/kernel/time_32.c
@@ -85,7 +85,7 @@ int update_persistent_clock(struct timespec now)
 
 /*
  * timer_interrupt() needs to keep up the real-time clock,
- * as well as call the "do_timer()" routine every clocktick
+ * as well as call the "xtime_update()" routine every clocktick
  */
 
 #define TICK_SIZE (tick_nsec / 1000)
@@ -96,14 +96,9 @@ static irqreturn_t timer_interrupt(int dummy, void *dev_id)
 	profile_tick(CPU_PROFILING);
 #endif
 
-	/* Protect counter clear so that do_gettimeoffset works */
-	write_seqlock(&xtime_lock);
-
 	clear_clock_irq();
 
-	do_timer(1);
-
-	write_sequnlock(&xtime_lock);
+	xtime_update(1);
 
 #ifndef CONFIG_SMP
 	update_process_times(user_mode(get_irq_regs()));
diff --git a/arch/sparc/lib/atomic32.c b/arch/sparc/lib/atomic32.c
index cbddeb38ffda..d3c7a12ad879 100644
--- a/arch/sparc/lib/atomic32.c
+++ b/arch/sparc/lib/atomic32.c
@@ -16,7 +16,7 @@
 #define ATOMIC_HASH(a)	(&__atomic_hash[(((unsigned long)a)>>8) & (ATOMIC_HASH_SIZE-1)])
 
 spinlock_t __atomic_hash[ATOMIC_HASH_SIZE] = {
-	[0 ... (ATOMIC_HASH_SIZE-1)] = SPIN_LOCK_UNLOCKED
+	[0 ... (ATOMIC_HASH_SIZE-1)] = __SPIN_LOCK_UNLOCKED(__atomic_hash)
 };
 
 #else /* SMP */
diff --git a/arch/tile/include/asm/futex.h b/arch/tile/include/asm/futex.h
index fe0d10dcae57..d03ec124a598 100644
--- a/arch/tile/include/asm/futex.h
+++ b/arch/tile/include/asm/futex.h
@@ -29,16 +29,16 @@
 #include <linux/uaccess.h>
 #include <linux/errno.h>
 
-extern struct __get_user futex_set(int __user *v, int i);
-extern struct __get_user futex_add(int __user *v, int n);
-extern struct __get_user futex_or(int __user *v, int n);
-extern struct __get_user futex_andn(int __user *v, int n);
-extern struct __get_user futex_cmpxchg(int __user *v, int o, int n);
+extern struct __get_user futex_set(u32 __user *v, int i);
+extern struct __get_user futex_add(u32 __user *v, int n);
+extern struct __get_user futex_or(u32 __user *v, int n);
+extern struct __get_user futex_andn(u32 __user *v, int n);
+extern struct __get_user futex_cmpxchg(u32 __user *v, int o, int n);
 
 #ifndef __tilegx__
-extern struct __get_user futex_xor(int __user *v, int n);
+extern struct __get_user futex_xor(u32 __user *v, int n);
 #else
-static inline struct __get_user futex_xor(int __user *uaddr, int n)
+static inline struct __get_user futex_xor(u32 __user *uaddr, int n)
 {
 	struct __get_user asm_ret = __get_user_4(uaddr);
 	if (!asm_ret.err) {
@@ -53,7 +53,7 @@ static inline struct __get_user futex_xor(int __user *uaddr, int n)
 }
 #endif
 
-static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
+static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 {
 	int op = (encoded_op >> 28) & 7;
 	int cmp = (encoded_op >> 24) & 15;
@@ -65,7 +65,7 @@ static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
 	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
 		oparg = 1 << oparg;
 
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
 	pagefault_disable();
@@ -119,16 +119,17 @@ static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
 	return ret;
 }
 
-static inline int futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval,
-						int newval)
+static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+						u32 oldval, u32 newval)
 {
 	struct __get_user asm_ret;
 
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
 	asm_ret = futex_cmpxchg(uaddr, oldval, newval);
-	return asm_ret.err ? asm_ret.err : asm_ret.val;
+	*uval = asm_ret.val;
+	return asm_ret.err;
 }
 
 #ifndef __tilegx__
diff --git a/arch/um/Kconfig.common b/arch/um/Kconfig.common
index e351e14b4339..1e78940218c0 100644
--- a/arch/um/Kconfig.common
+++ b/arch/um/Kconfig.common
@@ -7,6 +7,7 @@ config UML
 	bool
 	default y
 	select HAVE_GENERIC_HARDIRQS
+	select GENERIC_HARDIRQS_NO_DEPRECATED
 
 config MMU
 	bool
diff --git a/arch/um/Kconfig.x86 b/arch/um/Kconfig.x86
index 5ee328099c63..02fb017fed47 100644
--- a/arch/um/Kconfig.x86
+++ b/arch/um/Kconfig.x86
@@ -10,6 +10,8 @@ endmenu
 
 config UML_X86
 	def_bool y
+	select GENERIC_FIND_FIRST_BIT
+	select GENERIC_FIND_NEXT_BIT
 
 config 64BIT
 	bool
@@ -19,6 +21,9 @@ config X86_32
 	def_bool !64BIT
 	select HAVE_AOUT
 
+config X86_64
+	def_bool 64BIT
+
 config RWSEM_XCHGADD_ALGORITHM
 	def_bool X86_XADD
 
diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c
index 975613b23dcf..c70e047eed72 100644
--- a/arch/um/drivers/mconsole_kern.c
+++ b/arch/um/drivers/mconsole_kern.c
@@ -124,35 +124,18 @@ void mconsole_log(struct mc_request *req)
 #if 0
 void mconsole_proc(struct mc_request *req)
 {
-	struct nameidata nd;
 	struct vfsmount *mnt = current->nsproxy->pid_ns->proc_mnt;
 	struct file *file;
-	int n, err;
+	int n;
 	char *ptr = req->request.data, *buf;
 	mm_segment_t old_fs = get_fs();
 
 	ptr += strlen("proc");
 	ptr = skip_spaces(ptr);
 
-	err = vfs_path_lookup(mnt->mnt_root, mnt, ptr, LOOKUP_FOLLOW, &nd);
-	if (err) {
-		mconsole_reply(req, "Failed to look up file", 1, 0);
-		goto out;
-	}
-
-	err = may_open(&nd.path, MAY_READ, O_RDONLY);
-	if (result) {
-		mconsole_reply(req, "Failed to open file", 1, 0);
-		path_put(&nd.path);
-		goto out;
-	}
-
-	file = dentry_open(nd.path.dentry, nd.path.mnt, O_RDONLY,
-			   current_cred());
-	err = PTR_ERR(file);
+	file = file_open_root(mnt->mnt_root, mnt, ptr, O_RDONLY);
 	if (IS_ERR(file)) {
 		mconsole_reply(req, "Failed to open file", 1, 0);
-		path_put(&nd.path);
 		goto out;
 	}
 
diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c
index ba4a98ba39c0..620f5b70957d 100644
--- a/arch/um/drivers/ubd_kern.c
+++ b/arch/um/drivers/ubd_kern.c
@@ -185,7 +185,7 @@ struct ubd {
 	.no_cow =               0, \
 	.shared =		0, \
 	.cow =			DEFAULT_COW, \
-	.lock =			SPIN_LOCK_UNLOCKED,	\
+	.lock =			__SPIN_LOCK_UNLOCKED(ubd_devs.lock), \
 	.request =		NULL, \
 	.start_sg =		0, \
 	.end_sg =		0, \
diff --git a/arch/um/kernel/irq.c b/arch/um/kernel/irq.c
index 3f0ac9e0c966..64cfea80cfe2 100644
--- a/arch/um/kernel/irq.c
+++ b/arch/um/kernel/irq.c
@@ -35,8 +35,10 @@ int show_interrupts(struct seq_file *p, void *v)
 	}
 
 	if (i < NR_IRQS) {
-		raw_spin_lock_irqsave(&irq_desc[i].lock, flags);
-		action = irq_desc[i].action;
+		struct irq_desc *desc = irq_to_desc(i);
+
+		raw_spin_lock_irqsave(&desc->lock, flags);
+		action = desc->action;
 		if (!action)
 			goto skip;
 		seq_printf(p, "%3d: ",i);
@@ -46,7 +48,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		for_each_online_cpu(j)
 			seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
 #endif
-		seq_printf(p, " %14s", irq_desc[i].chip->name);
+		seq_printf(p, " %14s", get_irq_desc_chip(desc)->name);
 		seq_printf(p, "  %s", action->name);
 
 		for (action=action->next; action; action = action->next)
@@ -54,7 +56,7 @@ int show_interrupts(struct seq_file *p, void *v)
 
 		seq_putc(p, '\n');
 skip:
-		raw_spin_unlock_irqrestore(&irq_desc[i].lock, flags);
+		raw_spin_unlock_irqrestore(&desc->lock, flags);
 	} else if (i == NR_IRQS)
 		seq_putc(p, '\n');
 
@@ -360,10 +362,10 @@ EXPORT_SYMBOL(um_request_irq);
 EXPORT_SYMBOL(reactivate_fd);
 
 /*
- * irq_chip must define (startup || enable) &&
- * (shutdown || disable) && end
+ * irq_chip must define at least enable/disable and ack when
+ * the edge handler is used.
  */
-static void dummy(unsigned int irq)
+static void dummy(struct irq_data *d)
 {
 }
 
@@ -371,20 +373,17 @@ static void dummy(unsigned int irq)
 static struct irq_chip normal_irq_type = {
 	.name = "SIGIO",
 	.release = free_irq_by_irq_and_dev,
-	.disable = dummy,
-	.enable = dummy,
-	.ack = dummy,
-	.end = dummy
+	.irq_disable = dummy,
+	.irq_enable = dummy,
+	.irq_ack = dummy,
 };
 
 static struct irq_chip SIGVTALRM_irq_type = {
 	.name = "SIGVTALRM",
 	.release = free_irq_by_irq_and_dev,
-	.shutdown = dummy, /* never called */
-	.disable = dummy,
-	.enable = dummy,
-	.ack = dummy,
-	.end = dummy
+	.irq_disable = dummy,
+	.irq_enable = dummy,
+	.irq_ack = dummy,
 };
 
 void __init init_IRQ(void)
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index d5ed94d30aad..f8958b01b975 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -64,8 +64,12 @@ config X86
 	select HAVE_TEXT_POKE_SMP
 	select HAVE_GENERIC_HARDIRQS
 	select HAVE_SPARSE_IRQ
+	select GENERIC_FIND_FIRST_BIT
+	select GENERIC_FIND_NEXT_BIT
 	select GENERIC_IRQ_PROBE
 	select GENERIC_PENDING_IRQ if SMP
+	select GENERIC_IRQ_SHOW
+	select IRQ_FORCED_THREADING
 	select USE_GENERIC_SMP_HELPERS if SMP
 
 config INSTRUCTION_DECODER
@@ -382,6 +386,8 @@ config X86_INTEL_CE
 	depends on X86_32
 	depends on X86_EXTENDED_PLATFORM
 	select X86_REBOOTFIXUPS
+	select OF
+	select OF_EARLY_FLATTREE
 	---help---
 	  Select for the Intel CE media processor (CE4100) SOC.
 	  This option compiles in support for the CE4100 SOC for settop
@@ -811,7 +817,7 @@ config X86_LOCAL_APIC
 
 config X86_IO_APIC
 	def_bool y
-	depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_APIC
+	depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_IOAPIC
 
 config X86_VISWS_APIC
 	def_bool y
@@ -1705,7 +1711,7 @@ config HAVE_ARCH_EARLY_PFN_TO_NID
 	depends on NUMA
 
 config USE_PERCPU_NUMA_NODE_ID
-	def_bool X86_64
+	def_bool y
 	depends on NUMA
 
 menu "Power management and ACPI options"
@@ -2066,9 +2072,10 @@ config SCx200HR_TIMER
 
 config OLPC
 	bool "One Laptop Per Child support"
+	depends on !X86_PAE
 	select GPIOLIB
-	select OLPC_OPENFIRMWARE
-	depends on !X86_64 && !X86_PAE
+	select OF
+	select OF_PROMTREE if PROC_DEVICETREE
 	---help---
 	  Add support for detecting the unique features of the OLPC
 	  XO hardware.
@@ -2079,21 +2086,6 @@ config OLPC_XO1
 	---help---
 	  Add support for non-essential features of the OLPC XO-1 laptop.
 
-config OLPC_OPENFIRMWARE
-	bool "Support for OLPC's Open Firmware"
-	depends on !X86_64 && !X86_PAE
-	default n
-	select OF
-	help
-	  This option adds support for the implementation of Open Firmware
-	  that is used on the OLPC XO-1 Children's Machine.
-	  If unsure, say N here.
-
-config OLPC_OPENFIRMWARE_DT
-	bool
-	default y if OLPC_OPENFIRMWARE && PROC_DEVICETREE
-	select OF_PROMTREE
-
 endif # X86_32
 
 config AMD_NB
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index e6d3013f7ec3..75d89ac58d28 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -294,11 +294,6 @@ config X86_GENERIC
 
 endif
 
-config X86_CPU
-	def_bool y
-	select GENERIC_FIND_FIRST_BIT
-	select GENERIC_FIND_NEXT_BIT
-
 #
 # Define implied options from the CPU selection here
 config X86_INTERNODE_CACHE_SHIFT
diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 518bb99c3394..430312ba6e3f 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -25,6 +25,8 @@
 #define sysretl_audit ia32_ret_from_sys_call
 #endif
 
+	.section .entry.text, "ax"
+
 #define IA32_NR_syscalls ((ia32_syscall_end - ia32_sys_call_table)/8)
 
 	.macro IA32_ARG_FIXUP noebp=0
@@ -126,26 +128,20 @@ ENTRY(ia32_sysenter_target)
 	 */
 	ENABLE_INTERRUPTS(CLBR_NONE)
  	movl	%ebp,%ebp		/* zero extension */
-	pushq	$__USER32_DS
-	CFI_ADJUST_CFA_OFFSET 8
+	pushq_cfi $__USER32_DS
 	/*CFI_REL_OFFSET ss,0*/
-	pushq	%rbp
-	CFI_ADJUST_CFA_OFFSET 8
+	pushq_cfi %rbp
 	CFI_REL_OFFSET rsp,0
-	pushfq
-	CFI_ADJUST_CFA_OFFSET 8
+	pushfq_cfi
 	/*CFI_REL_OFFSET rflags,0*/
 	movl	8*3-THREAD_SIZE+TI_sysenter_return(%rsp), %r10d
 	CFI_REGISTER rip,r10
-	pushq	$__USER32_CS
-	CFI_ADJUST_CFA_OFFSET 8
+	pushq_cfi $__USER32_CS
 	/*CFI_REL_OFFSET cs,0*/
 	movl	%eax, %eax
-	pushq	%r10
-	CFI_ADJUST_CFA_OFFSET 8
+	pushq_cfi %r10
 	CFI_REL_OFFSET rip,0
-	pushq	%rax
-	CFI_ADJUST_CFA_OFFSET 8
+	pushq_cfi %rax
 	cld
 	SAVE_ARGS 0,0,1
  	/* no need to do an access_ok check here because rbp has been
@@ -182,11 +178,9 @@ sysexit_from_sys_call:
 	xorq	%r9,%r9
 	xorq	%r10,%r10
 	xorq	%r11,%r11
-	popfq
-	CFI_ADJUST_CFA_OFFSET -8
+	popfq_cfi
 	/*CFI_RESTORE rflags*/
-	popq	%rcx				/* User %esp */
-	CFI_ADJUST_CFA_OFFSET -8
+	popq_cfi %rcx				/* User %esp */
 	CFI_REGISTER rsp,rcx
 	TRACE_IRQS_ON
 	ENABLE_INTERRUPTS_SYSEXIT32
@@ -421,8 +415,7 @@ ENTRY(ia32_syscall)
 	 */
 	ENABLE_INTERRUPTS(CLBR_NONE)
 	movl %eax,%eax
-	pushq %rax
-	CFI_ADJUST_CFA_OFFSET 8
+	pushq_cfi %rax
 	cld
 	/* note the registers are not zero extended to the sf.
 	   this could be a problem. */
@@ -851,4 +844,7 @@ ia32_sys_call_table:
 	.quad sys_fanotify_init
 	.quad sys32_fanotify_mark
 	.quad sys_prlimit64		/* 340 */
+	.quad sys_name_to_handle_at
+	.quad compat_sys_open_by_handle_at
+	.quad compat_sys_clock_adjtime
 ia32_syscall_end:
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 4ea15ca89b2b..b964ec457546 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -186,15 +186,7 @@ struct bootnode;
 
 #ifdef CONFIG_ACPI_NUMA
 extern int acpi_numa;
-extern void acpi_get_nodes(struct bootnode *physnodes, unsigned long start,
-				unsigned long end);
-extern int acpi_scan_nodes(unsigned long start, unsigned long end);
-#define NR_NODE_MEMBLKS (MAX_NUMNODES*2)
-
-#ifdef CONFIG_NUMA_EMU
-extern void acpi_fake_nodes(const struct bootnode *fake_nodes,
-				   int num_nodes);
-#endif
+extern int x86_acpi_numa_init(void);
 #endif /* CONFIG_ACPI_NUMA */
 
 #define acpi_unlazy_tlb(x)	leave_mm(x)
diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h
index 527fb966ab5c..331682231bb4 100644
--- a/arch/x86/include/asm/amd_nb.h
+++ b/arch/x86/include/asm/amd_nb.h
@@ -16,16 +16,10 @@ struct bootnode;
 extern bool early_is_amd_nb(u32 value);
 extern int amd_cache_northbridges(void);
 extern void amd_flush_garts(void);
-extern int amd_numa_init(unsigned long start_pfn, unsigned long end_pfn);
-extern int amd_scan_nodes(void);
+extern int amd_numa_init(void);
 extern int amd_get_subcaches(int);
 extern int amd_set_subcaches(int, int);
 
-#ifdef CONFIG_NUMA_EMU
-extern void amd_fake_nodes(const struct bootnode *nodes, int nr_nodes);
-extern void amd_get_nodes(struct bootnode *nodes);
-#endif
-
 struct amd_northbridge {
 	struct pci_dev *misc;
 	struct pci_dev *link;
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 3c896946f4cc..a279d98ea95e 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -220,7 +220,6 @@ extern void enable_IR_x2apic(void);
 
 extern int get_physical_broadcast(void);
 
-extern void apic_disable(void);
 extern int lapic_get_maxlvt(void);
 extern void clear_local_APIC(void);
 extern void connect_bsp_APIC(void);
@@ -228,7 +227,6 @@ extern void disconnect_bsp_APIC(int virt_wire_setup);
 extern void disable_local_APIC(void);
 extern void lapic_shutdown(void);
 extern int verify_local_APIC(void);
-extern void cache_APIC_registers(void);
 extern void sync_Arb_IDs(void);
 extern void init_bsp_APIC(void);
 extern void setup_local_APIC(void);
@@ -239,8 +237,7 @@ void register_lapic_address(unsigned long address);
 extern void setup_boot_APIC_clock(void);
 extern void setup_secondary_APIC_clock(void);
 extern int APIC_init_uniprocessor(void);
-extern void enable_NMI_through_LVT0(void);
-extern int apic_force_enable(void);
+extern int apic_force_enable(unsigned long addr);
 
 /*
  * On 32bit this is mach-xxx local
@@ -261,7 +258,6 @@ static inline void lapic_shutdown(void) { }
 #define local_apic_timer_c2_ok		1
 static inline void init_apic_mappings(void) { }
 static inline void disable_local_APIC(void) { }
-static inline void apic_disable(void) { }
 # define setup_boot_APIC_clock x86_init_noop
 # define setup_secondary_APIC_clock x86_init_noop
 #endif /* !CONFIG_X86_LOCAL_APIC */
@@ -307,8 +303,6 @@ struct apic {
 
 	void (*setup_apic_routing)(void);
 	int (*multi_timer_check)(int apic, int irq);
-	int (*apicid_to_node)(int logical_apicid);
-	int (*cpu_to_logical_apicid)(int cpu);
 	int (*cpu_present_to_apicid)(int mps_cpu);
 	void (*apicid_to_cpu_present)(int phys_apicid, physid_mask_t *retmap);
 	void (*setup_portio_remap)(void);
@@ -356,6 +350,23 @@ struct apic {
 	void (*icr_write)(u32 low, u32 high);
 	void (*wait_icr_idle)(void);
 	u32 (*safe_wait_icr_idle)(void);
+
+#ifdef CONFIG_X86_32
+	/*
+	 * Called very early during boot from get_smp_config().  It should
+	 * return the logical apicid.  x86_[bios]_cpu_to_apicid is
+	 * initialized before this function is called.
+	 *
+	 * If logical apicid can't be determined that early, the function
+	 * may return BAD_APICID.  Logical apicid will be configured after
+	 * init_apic_ldr() while bringing up CPUs.  Note that NUMA affinity
+	 * won't be applied properly during early boot in this case.
+	 */
+	int (*x86_32_early_logical_apicid)(int cpu);
+
+	/* determine CPU -> NUMA node mapping */
+	int (*x86_32_numa_cpu_node)(int cpu);
+#endif
 };
 
 /*
@@ -503,6 +514,11 @@ extern struct apic apic_noop;
 
 extern struct apic apic_default;
 
+static inline int noop_x86_32_early_logical_apicid(int cpu)
+{
+	return BAD_APICID;
+}
+
 /*
  * Set up the logical destination ID.
  *
@@ -522,7 +538,7 @@ static inline int default_phys_pkg_id(int cpuid_apic, int index_msb)
 	return cpuid_apic >> index_msb;
 }
 
-extern int default_apicid_to_node(int logical_apicid);
+extern int default_x86_32_numa_cpu_node(int cpu);
 
 #endif
 
@@ -558,12 +574,6 @@ static inline void default_ioapic_phys_id_map(physid_mask_t *phys_map, physid_ma
 	*retmap = *phys_map;
 }
 
-/* Mapping from cpu number to logical apicid */
-static inline int default_cpu_to_logical_apicid(int cpu)
-{
-	return 1 << cpu;
-}
-
 static inline int __default_cpu_present_to_apicid(int mps_cpu)
 {
 	if (mps_cpu < nr_cpu_ids && cpu_present(mps_cpu))
@@ -596,8 +606,4 @@ extern int default_check_phys_apicid_present(int phys_apicid);
 
 #endif /* CONFIG_X86_LOCAL_APIC */
 
-#ifdef CONFIG_X86_32
-extern u8 cpu_2_logical_apicid[NR_CPUS];
-#endif
-
 #endif /* _ASM_X86_APIC_H */
diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h
index 47a30ff8e517..d87988bacf3e 100644
--- a/arch/x86/include/asm/apicdef.h
+++ b/arch/x86/include/asm/apicdef.h
@@ -426,4 +426,16 @@ struct local_apic {
 #else
  #define BAD_APICID 0xFFFFu
 #endif
+
+enum ioapic_irq_destination_types {
+	dest_Fixed		= 0,
+	dest_LowestPrio		= 1,
+	dest_SMI		= 2,
+	dest__reserved_1	= 3,
+	dest_NMI		= 4,
+	dest_INIT		= 5,
+	dest__reserved_2	= 6,
+	dest_ExtINT		= 7
+};
+
 #endif /* _ASM_X86_APICDEF_H */
diff --git a/arch/x86/include/asm/bootparam.h b/arch/x86/include/asm/bootparam.h
index c8bfe63a06de..e020d88ec02d 100644
--- a/arch/x86/include/asm/bootparam.h
+++ b/arch/x86/include/asm/bootparam.h
@@ -12,6 +12,7 @@
 /* setup data types */
 #define SETUP_NONE			0
 #define SETUP_E820_EXT			1
+#define SETUP_DTB			2
 
 /* extensible setup data list node */
 struct setup_data {
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 220e2ea08e80..91f3e087cf21 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -160,6 +160,7 @@
 #define X86_FEATURE_NODEID_MSR	(6*32+19) /* NodeId MSR */
 #define X86_FEATURE_TBM		(6*32+21) /* trailing bit manipulations */
 #define X86_FEATURE_TOPOEXT	(6*32+22) /* topology extensions CPUID leafs */
+#define X86_FEATURE_PERFCTR_CORE (6*32+23) /* core performance counter extensions */
 
 /*
  * Auxiliary flags: Linux defined - For features scattered in various
@@ -279,6 +280,7 @@ extern const char * const x86_power_flags[32];
 #define cpu_has_xsave		boot_cpu_has(X86_FEATURE_XSAVE)
 #define cpu_has_hypervisor	boot_cpu_has(X86_FEATURE_HYPERVISOR)
 #define cpu_has_pclmulqdq	boot_cpu_has(X86_FEATURE_PCLMULQDQ)
+#define cpu_has_perfctr_core	boot_cpu_has(X86_FEATURE_PERFCTR_CORE)
 
 #if defined(CONFIG_X86_INVLPG) || defined(CONFIG_X86_64)
 # define cpu_has_invlpg		1
diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h
index e99d55d74df5..908b96957d88 100644
--- a/arch/x86/include/asm/e820.h
+++ b/arch/x86/include/asm/e820.h
@@ -96,7 +96,7 @@ extern void e820_setup_gap(void);
 extern int e820_search_gap(unsigned long *gapstart, unsigned long *gapsize,
 			unsigned long start_addr, unsigned long long end_addr);
 struct setup_data;
-extern void parse_e820_ext(struct setup_data *data, unsigned long pa_data);
+extern void parse_e820_ext(struct setup_data *data);
 
 #if defined(CONFIG_X86_64) || \
 	(defined(CONFIG_X86_32) && defined(CONFIG_HIBERNATION))
diff --git a/arch/x86/include/asm/entry_arch.h b/arch/x86/include/asm/entry_arch.h
index 57650ab4a5f5..1cd6d26a0a8d 100644
--- a/arch/x86/include/asm/entry_arch.h
+++ b/arch/x86/include/asm/entry_arch.h
@@ -16,10 +16,13 @@ BUILD_INTERRUPT(call_function_single_interrupt,CALL_FUNCTION_SINGLE_VECTOR)
 BUILD_INTERRUPT(irq_move_cleanup_interrupt,IRQ_MOVE_CLEANUP_VECTOR)
 BUILD_INTERRUPT(reboot_interrupt,REBOOT_VECTOR)
 
-.irpc idx, "01234567"
+.irp idx,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15, \
+	16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31
+.if NUM_INVALIDATE_TLB_VECTORS > \idx
 BUILD_INTERRUPT3(invalidate_interrupt\idx,
 		 (INVALIDATE_TLB_VECTOR_START)+\idx,
 		 smp_invalidate_interrupt)
+.endif
 .endr
 #endif
 
diff --git a/arch/x86/include/asm/frame.h b/arch/x86/include/asm/frame.h
index 06850a7194e1..2c6fc9e62812 100644
--- a/arch/x86/include/asm/frame.h
+++ b/arch/x86/include/asm/frame.h
@@ -7,14 +7,12 @@
    frame pointer later */
 #ifdef CONFIG_FRAME_POINTER
 	.macro FRAME
-	pushl %ebp
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %ebp
 	CFI_REL_OFFSET ebp,0
 	movl %esp,%ebp
 	.endm
 	.macro ENDFRAME
-	popl %ebp
-	CFI_ADJUST_CFA_OFFSET -4
+	popl_cfi %ebp
 	CFI_RESTORE ebp
 	.endm
 #else
diff --git a/arch/x86/include/asm/futex.h b/arch/x86/include/asm/futex.h
index 1f11ce44e956..d09bb03653f0 100644
--- a/arch/x86/include/asm/futex.h
+++ b/arch/x86/include/asm/futex.h
@@ -37,7 +37,7 @@
 		       "+m" (*uaddr), "=&r" (tem)		\
 		     : "r" (oparg), "i" (-EFAULT), "1" (0))
 
-static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
+static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 {
 	int op = (encoded_op >> 28) & 7;
 	int cmp = (encoded_op >> 24) & 15;
@@ -48,7 +48,7 @@ static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
 	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
 		oparg = 1 << oparg;
 
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
 #if defined(CONFIG_X86_32) && !defined(CONFIG_X86_BSWAP)
@@ -109,9 +109,10 @@ static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
 	return ret;
 }
 
-static inline int futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval,
-						int newval)
+static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+						u32 oldval, u32 newval)
 {
+	int ret = 0;
 
 #if defined(CONFIG_X86_32) && !defined(CONFIG_X86_BSWAP)
 	/* Real i386 machines have no cmpxchg instruction */
@@ -119,21 +120,22 @@ static inline int futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval,
 		return -ENOSYS;
 #endif
 
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
-	asm volatile("1:\t" LOCK_PREFIX "cmpxchgl %3, %1\n"
+	asm volatile("1:\t" LOCK_PREFIX "cmpxchgl %4, %2\n"
 		     "2:\t.section .fixup, \"ax\"\n"
-		     "3:\tmov     %2, %0\n"
+		     "3:\tmov     %3, %0\n"
 		     "\tjmp     2b\n"
 		     "\t.previous\n"
 		     _ASM_EXTABLE(1b, 3b)
-		     : "=a" (oldval), "+m" (*uaddr)
-		     : "i" (-EFAULT), "r" (newval), "0" (oldval)
+		     : "+r" (ret), "=a" (oldval), "+m" (*uaddr)
+		     : "i" (-EFAULT), "r" (newval), "1" (oldval)
 		     : "memory"
 	);
 
-	return oldval;
+	*uval = oldval;
+	return ret;
 }
 
 #endif
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index 0274ec5a7e62..bb9efe8706e2 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -45,6 +45,30 @@ extern void invalidate_interrupt4(void);
 extern void invalidate_interrupt5(void);
 extern void invalidate_interrupt6(void);
 extern void invalidate_interrupt7(void);
+extern void invalidate_interrupt8(void);
+extern void invalidate_interrupt9(void);
+extern void invalidate_interrupt10(void);
+extern void invalidate_interrupt11(void);
+extern void invalidate_interrupt12(void);
+extern void invalidate_interrupt13(void);
+extern void invalidate_interrupt14(void);
+extern void invalidate_interrupt15(void);
+extern void invalidate_interrupt16(void);
+extern void invalidate_interrupt17(void);
+extern void invalidate_interrupt18(void);
+extern void invalidate_interrupt19(void);
+extern void invalidate_interrupt20(void);
+extern void invalidate_interrupt21(void);
+extern void invalidate_interrupt22(void);
+extern void invalidate_interrupt23(void);
+extern void invalidate_interrupt24(void);
+extern void invalidate_interrupt25(void);
+extern void invalidate_interrupt26(void);
+extern void invalidate_interrupt27(void);
+extern void invalidate_interrupt28(void);
+extern void invalidate_interrupt29(void);
+extern void invalidate_interrupt30(void);
+extern void invalidate_interrupt31(void);
 
 extern void irq_move_cleanup_interrupt(void);
 extern void reboot_interrupt(void);
diff --git a/arch/x86/include/asm/init.h b/arch/x86/include/asm/init.h
index 36fb1a6a5109..8dbe353e41e1 100644
--- a/arch/x86/include/asm/init.h
+++ b/arch/x86/include/asm/init.h
@@ -11,8 +11,8 @@ kernel_physical_mapping_init(unsigned long start,
 			     unsigned long page_size_mask);
 
 
-extern unsigned long __initdata e820_table_start;
-extern unsigned long __meminitdata e820_table_end;
-extern unsigned long __meminitdata e820_table_top;
+extern unsigned long __initdata pgt_buf_start;
+extern unsigned long __meminitdata pgt_buf_end;
+extern unsigned long __meminitdata pgt_buf_top;
 
 #endif /* _ASM_X86_INIT_32_H */
diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h
index f327d386d6cc..c4bd267dfc50 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/arch/x86/include/asm/io_apic.h
@@ -63,17 +63,6 @@ union IO_APIC_reg_03 {
 	} __attribute__ ((packed)) bits;
 };
 
-enum ioapic_irq_destination_types {
-	dest_Fixed = 0,
-	dest_LowestPrio = 1,
-	dest_SMI = 2,
-	dest__reserved_1 = 3,
-	dest_NMI = 4,
-	dest_INIT = 5,
-	dest__reserved_2 = 6,
-	dest_ExtINT = 7
-};
-
 struct IO_APIC_route_entry {
 	__u32	vector		:  8,
 		delivery_mode	:  3,	/* 000: FIXED
@@ -106,6 +95,10 @@ struct IR_IO_APIC_route_entry {
 		index		: 15;
 } __attribute__ ((packed));
 
+#define IOAPIC_AUTO     -1
+#define IOAPIC_EDGE     0
+#define IOAPIC_LEVEL    1
+
 #ifdef CONFIG_X86_IO_APIC
 
 /*
@@ -150,11 +143,6 @@ extern int timer_through_8259;
 #define io_apic_assign_pci_irqs \
 	(mp_irq_entries && !skip_ioapic_setup && io_apic_irqs)
 
-extern u8 io_apic_unique_id(u8 id);
-extern int io_apic_get_unique_id(int ioapic, int apic_id);
-extern int io_apic_get_version(int ioapic);
-extern int io_apic_get_redir_entries(int ioapic);
-
 struct io_apic_irq_attr;
 extern int io_apic_set_pci_routing(struct device *dev, int irq,
 		 struct io_apic_irq_attr *irq_attr);
@@ -162,6 +150,8 @@ void setup_IO_APIC_irq_extra(u32 gsi);
 extern void ioapic_and_gsi_init(void);
 extern void ioapic_insert_resources(void);
 
+int io_apic_setup_irq_pin(unsigned int irq, int node, struct io_apic_irq_attr *attr);
+
 extern struct IO_APIC_route_entry **alloc_ioapic_entries(void);
 extern void free_ioapic_entries(struct IO_APIC_route_entry **ioapic_entries);
 extern int save_IO_APIC_setup(struct IO_APIC_route_entry **ioapic_entries);
@@ -186,6 +176,8 @@ extern void __init pre_init_apic_IRQ0(void);
 
 extern void mp_save_irq(struct mpc_intsrc *m);
 
+extern void disable_ioapic_support(void);
+
 #else  /* !CONFIG_X86_IO_APIC */
 
 #define io_apic_assign_pci_irqs 0
@@ -199,6 +191,26 @@ static inline int mp_find_ioapic(u32 gsi) { return 0; }
 struct io_apic_irq_attr;
 static inline int io_apic_set_pci_routing(struct device *dev, int irq,
 		 struct io_apic_irq_attr *irq_attr) { return 0; }
+
+static inline struct IO_APIC_route_entry **alloc_ioapic_entries(void)
+{
+	return NULL;
+}
+
+static inline void free_ioapic_entries(struct IO_APIC_route_entry **ent) { }
+static inline int save_IO_APIC_setup(struct IO_APIC_route_entry **ent)
+{
+	return -ENOMEM;
+}
+
+static inline void mask_IO_APIC_setup(struct IO_APIC_route_entry **ent) { }
+static inline int restore_IO_APIC_setup(struct IO_APIC_route_entry **ent)
+{
+	return -ENOMEM;
+}
+
+static inline void mp_save_irq(struct mpc_intsrc *m) { };
+static inline void disable_ioapic_support(void) { }
 #endif
 
 #endif /* _ASM_X86_IO_APIC_H */
diff --git a/arch/x86/include/asm/ipi.h b/arch/x86/include/asm/ipi.h
index 0b7228268a63..615fa9061b57 100644
--- a/arch/x86/include/asm/ipi.h
+++ b/arch/x86/include/asm/ipi.h
@@ -123,10 +123,6 @@ extern void default_send_IPI_mask_sequence_phys(const struct cpumask *mask,
 						 int vector);
 extern void default_send_IPI_mask_allbutself_phys(const struct cpumask *mask,
 							 int vector);
-extern void default_send_IPI_mask_sequence_logical(const struct cpumask *mask,
-							 int vector);
-extern void default_send_IPI_mask_allbutself_logical(const struct cpumask *mask,
-							 int vector);
 
 /* Avoid include hell */
 #define NMI_VECTOR 0x02
@@ -150,6 +146,10 @@ static inline void __default_local_send_IPI_all(int vector)
 }
 
 #ifdef CONFIG_X86_32
+extern void default_send_IPI_mask_sequence_logical(const struct cpumask *mask,
+							 int vector);
+extern void default_send_IPI_mask_allbutself_logical(const struct cpumask *mask,
+							 int vector);
 extern void default_send_IPI_mask_logical(const struct cpumask *mask,
 						 int vector);
 extern void default_send_IPI_allbutself(int vector);
diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h
index c704b38c57a2..ba870bb6dd8e 100644
--- a/arch/x86/include/asm/irq.h
+++ b/arch/x86/include/asm/irq.h
@@ -10,9 +10,6 @@
 #include <asm/apicdef.h>
 #include <asm/irq_vectors.h>
 
-/* Even though we don't support this, supply it to appease OF */
-static inline void irq_dispose_mapping(unsigned int virq) { }
-
 static inline int irq_canonicalize(int irq)
 {
 	return ((irq == 2) ? 9 : irq);
diff --git a/arch/x86/include/asm/irq_controller.h b/arch/x86/include/asm/irq_controller.h
new file mode 100644
index 000000000000..423bbbddf36d
--- /dev/null
+++ b/arch/x86/include/asm/irq_controller.h
@@ -0,0 +1,12 @@
+#ifndef __IRQ_CONTROLLER__
+#define __IRQ_CONTROLLER__
+
+struct irq_domain {
+	int (*xlate)(struct irq_domain *h, const u32 *intspec, u32 intsize,
+			u32 *out_hwirq, u32 *out_type);
+	void *priv;
+	struct device_node *controller;
+	struct list_head l;
+};
+
+#endif
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index 6af0894dafb4..6e976ee3b3ef 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -1,6 +1,7 @@
 #ifndef _ASM_X86_IRQ_VECTORS_H
 #define _ASM_X86_IRQ_VECTORS_H
 
+#include <linux/threads.h>
 /*
  * Linux IRQ vector layout.
  *
@@ -16,8 +17,8 @@
  *  Vectors   0 ...  31 : system traps and exceptions - hardcoded events
  *  Vectors  32 ... 127 : device interrupts
  *  Vector  128         : legacy int80 syscall interface
- *  Vectors 129 ... 237 : device interrupts
- *  Vectors 238 ... 255 : special interrupts
+ *  Vectors 129 ... INVALIDATE_TLB_VECTOR_START-1 : device interrupts
+ *  Vectors INVALIDATE_TLB_VECTOR_START ... 255 : special interrupts
  *
  * 64-bit x86 has per CPU IDT tables, 32-bit has one shared IDT table.
  *
@@ -96,37 +97,43 @@
 #define THRESHOLD_APIC_VECTOR		0xf9
 #define REBOOT_VECTOR			0xf8
 
-/* f0-f7 used for spreading out TLB flushes: */
-#define INVALIDATE_TLB_VECTOR_END	0xf7
-#define INVALIDATE_TLB_VECTOR_START	0xf0
-#define NUM_INVALIDATE_TLB_VECTORS	   8
-
-/*
- * Local APIC timer IRQ vector is on a different priority level,
- * to work around the 'lost local interrupt if more than 2 IRQ
- * sources per level' errata.
- */
-#define LOCAL_TIMER_VECTOR		0xef
-
 /*
  * Generic system vector for platform specific use
  */
-#define X86_PLATFORM_IPI_VECTOR		0xed
+#define X86_PLATFORM_IPI_VECTOR		0xf7
 
 /*
  * IRQ work vector:
  */
-#define IRQ_WORK_VECTOR			0xec
+#define IRQ_WORK_VECTOR			0xf6
 
-#define UV_BAU_MESSAGE			0xea
+#define UV_BAU_MESSAGE			0xf5
 
 /*
  * Self IPI vector for machine checks
  */
-#define MCE_SELF_VECTOR			0xeb
+#define MCE_SELF_VECTOR			0xf4
 
 /* Xen vector callback to receive events in a HVM domain */
-#define XEN_HVM_EVTCHN_CALLBACK		0xe9
+#define XEN_HVM_EVTCHN_CALLBACK		0xf3
+
+/*
+ * Local APIC timer IRQ vector is on a different priority level,
+ * to work around the 'lost local interrupt if more than 2 IRQ
+ * sources per level' errata.
+ */
+#define LOCAL_TIMER_VECTOR		0xef
+
+/* up to 32 vectors used for spreading out TLB flushes: */
+#if NR_CPUS <= 32
+# define NUM_INVALIDATE_TLB_VECTORS	(NR_CPUS)
+#else
+# define NUM_INVALIDATE_TLB_VECTORS	(32)
+#endif
+
+#define INVALIDATE_TLB_VECTOR_END	(0xee)
+#define INVALIDATE_TLB_VECTOR_START	\
+	(INVALIDATE_TLB_VECTOR_END-NUM_INVALIDATE_TLB_VECTORS+1)
 
 #define NR_VECTORS			 256
 
diff --git a/arch/x86/include/asm/kdebug.h b/arch/x86/include/asm/kdebug.h
index ca242d35e873..518bbbb9ee59 100644
--- a/arch/x86/include/asm/kdebug.h
+++ b/arch/x86/include/asm/kdebug.h
@@ -13,7 +13,6 @@ enum die_val {
 	DIE_PANIC,
 	DIE_NMI,
 	DIE_DIE,
-	DIE_NMIWATCHDOG,
 	DIE_KERNELDEBUG,
 	DIE_TRAP,
 	DIE_GPF,
diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h
index 0c90dd9f0505..9c7d95f6174b 100644
--- a/arch/x86/include/asm/mpspec.h
+++ b/arch/x86/include/asm/mpspec.h
@@ -25,7 +25,6 @@ extern int pic_mode;
 #define MAX_IRQ_SOURCES		256
 
 extern unsigned int def_to_bigsmp;
-extern u8 apicid_2_node[];
 
 #ifdef CONFIG_X86_NUMAQ
 extern int mp_bus_id_to_node[MAX_MP_BUSSES];
@@ -33,8 +32,6 @@ extern int mp_bus_id_to_local[MAX_MP_BUSSES];
 extern int quad_local_to_mp_bus_id [NR_CPUS/4][4];
 #endif
 
-#define MAX_APICID		256
-
 #else /* CONFIG_X86_64: */
 
 #define MAX_MP_BUSSES		256
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 43a18c77676d..823d48223400 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -52,6 +52,9 @@
 #define MSR_IA32_MCG_STATUS		0x0000017a
 #define MSR_IA32_MCG_CTL		0x0000017b
 
+#define MSR_OFFCORE_RSP_0		0x000001a6
+#define MSR_OFFCORE_RSP_1		0x000001a7
+
 #define MSR_IA32_PEBS_ENABLE		0x000003f1
 #define MSR_IA32_DS_AREA		0x00000600
 #define MSR_IA32_PERF_CAPABILITIES	0x00000345
diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h
index c76f5b92b840..07f46016d3ff 100644
--- a/arch/x86/include/asm/nmi.h
+++ b/arch/x86/include/asm/nmi.h
@@ -7,7 +7,6 @@
 
 #ifdef CONFIG_X86_LOCAL_APIC
 
-extern void die_nmi(char *str, struct pt_regs *regs, int do_panic);
 extern int avail_to_resrv_perfctr_nmi_bit(unsigned int);
 extern int reserve_perfctr_nmi(unsigned int);
 extern void release_perfctr_nmi(unsigned int);
diff --git a/arch/x86/include/asm/numa.h b/arch/x86/include/asm/numa.h
index 27da400d3138..3d4dab43c994 100644
--- a/arch/x86/include/asm/numa.h
+++ b/arch/x86/include/asm/numa.h
@@ -1,5 +1,57 @@
+#ifndef _ASM_X86_NUMA_H
+#define _ASM_X86_NUMA_H
+
+#include <asm/topology.h>
+#include <asm/apicdef.h>
+
+#ifdef CONFIG_NUMA
+
+#define NR_NODE_MEMBLKS		(MAX_NUMNODES*2)
+
+/*
+ * __apicid_to_node[] stores the raw mapping between physical apicid and
+ * node and is used to initialize cpu_to_node mapping.
+ *
+ * The mapping may be overridden by apic->numa_cpu_node() on 32bit and thus
+ * should be accessed by the accessors - set_apicid_to_node() and
+ * numa_cpu_node().
+ */
+extern s16 __apicid_to_node[MAX_LOCAL_APIC];
+
+static inline void set_apicid_to_node(int apicid, s16 node)
+{
+	__apicid_to_node[apicid] = node;
+}
+#else	/* CONFIG_NUMA */
+static inline void set_apicid_to_node(int apicid, s16 node)
+{
+}
+#endif	/* CONFIG_NUMA */
+
 #ifdef CONFIG_X86_32
 # include "numa_32.h"
 #else
 # include "numa_64.h"
 #endif
+
+#ifdef CONFIG_NUMA
+extern void __cpuinit numa_set_node(int cpu, int node);
+extern void __cpuinit numa_clear_node(int cpu);
+extern void __init numa_init_array(void);
+extern void __init init_cpu_to_node(void);
+extern void __cpuinit numa_add_cpu(int cpu);
+extern void __cpuinit numa_remove_cpu(int cpu);
+#else	/* CONFIG_NUMA */
+static inline void numa_set_node(int cpu, int node)	{ }
+static inline void numa_clear_node(int cpu)		{ }
+static inline void numa_init_array(void)		{ }
+static inline void init_cpu_to_node(void)		{ }
+static inline void numa_add_cpu(int cpu)		{ }
+static inline void numa_remove_cpu(int cpu)		{ }
+#endif	/* CONFIG_NUMA */
+
+#ifdef CONFIG_DEBUG_PER_CPU_MAPS
+struct cpumask __cpuinit *debug_cpumask_set_cpu(int cpu, int enable);
+#endif
+
+#endif	/* _ASM_X86_NUMA_H */
diff --git a/arch/x86/include/asm/numa_32.h b/arch/x86/include/asm/numa_32.h
index b0ef2b449a9d..c6beed1ef103 100644
--- a/arch/x86/include/asm/numa_32.h
+++ b/arch/x86/include/asm/numa_32.h
@@ -4,7 +4,12 @@
 extern int numa_off;
 
 extern int pxm_to_nid(int pxm);
-extern void numa_remove_cpu(int cpu);
+
+#ifdef CONFIG_NUMA
+extern int __cpuinit numa_cpu_node(int cpu);
+#else	/* CONFIG_NUMA */
+static inline int numa_cpu_node(int cpu)		{ return NUMA_NO_NODE; }
+#endif	/* CONFIG_NUMA */
 
 #ifdef CONFIG_HIGHMEM
 extern void set_highmem_pages_init(void);
diff --git a/arch/x86/include/asm/numa_64.h b/arch/x86/include/asm/numa_64.h
index 0493be39607c..344eb1790b46 100644
--- a/arch/x86/include/asm/numa_64.h
+++ b/arch/x86/include/asm/numa_64.h
@@ -2,23 +2,16 @@
 #define _ASM_X86_NUMA_64_H
 
 #include <linux/nodemask.h>
-#include <asm/apicdef.h>
 
 struct bootnode {
 	u64 start;
 	u64 end;
 };
 
-extern int compute_hash_shift(struct bootnode *nodes, int numblks,
-			      int *nodeids);
-
 #define ZONE_ALIGN (1UL << (MAX_ORDER+PAGE_SHIFT))
 
-extern void numa_init_array(void);
 extern int numa_off;
 
-extern s16 apicid_to_node[MAX_LOCAL_APIC];
-
 extern unsigned long numa_free_all_bootmem(void);
 extern void setup_node_bootmem(int nodeid, unsigned long start,
 			       unsigned long end);
@@ -31,11 +24,11 @@ extern void setup_node_bootmem(int nodeid, unsigned long start,
  */
 #define NODE_MIN_SIZE (4*1024*1024)
 
-extern void __init init_cpu_to_node(void);
-extern void __cpuinit numa_set_node(int cpu, int node);
-extern void __cpuinit numa_clear_node(int cpu);
-extern void __cpuinit numa_add_cpu(int cpu);
-extern void __cpuinit numa_remove_cpu(int cpu);
+extern nodemask_t numa_nodes_parsed __initdata;
+
+extern int __cpuinit numa_cpu_node(int cpu);
+extern int __init numa_add_memblk(int nodeid, u64 start, u64 end);
+extern void __init numa_set_distance(int from, int to, int distance);
 
 #ifdef CONFIG_NUMA_EMU
 #define FAKE_NODE_MIN_SIZE	((u64)32 << 20)
@@ -43,11 +36,7 @@ extern void __cpuinit numa_remove_cpu(int cpu);
 void numa_emu_cmdline(char *);
 #endif /* CONFIG_NUMA_EMU */
 #else
-static inline void init_cpu_to_node(void)		{ }
-static inline void numa_set_node(int cpu, int node)	{ }
-static inline void numa_clear_node(int cpu)		{ }
-static inline void numa_add_cpu(int cpu, int node)	{ }
-static inline void numa_remove_cpu(int cpu)		{ }
+static inline int numa_cpu_node(int cpu)		{ return NUMA_NO_NODE; }
 #endif
 
 #endif /* _ASM_X86_NUMA_64_H */
diff --git a/arch/x86/include/asm/olpc_ofw.h b/arch/x86/include/asm/olpc_ofw.h
index 641988efe063..c5d3a5abbb9f 100644
--- a/arch/x86/include/asm/olpc_ofw.h
+++ b/arch/x86/include/asm/olpc_ofw.h
@@ -6,7 +6,7 @@
 
 #define OLPC_OFW_SIG 0x2057464F	/* aka "OFW " */
 
-#ifdef CONFIG_OLPC_OPENFIRMWARE
+#ifdef CONFIG_OLPC
 
 extern bool olpc_ofw_is_installed(void);
 
@@ -26,19 +26,15 @@ extern void setup_olpc_ofw_pgd(void);
 /* check if OFW was detected during boot */
 extern bool olpc_ofw_present(void);
 
-#else /* !CONFIG_OLPC_OPENFIRMWARE */
-
-static inline bool olpc_ofw_is_installed(void) { return false; }
+#else /* !CONFIG_OLPC */
 static inline void olpc_ofw_detect(void) { }
 static inline void setup_olpc_ofw_pgd(void) { }
-static inline bool olpc_ofw_present(void) { return false; }
-
-#endif /* !CONFIG_OLPC_OPENFIRMWARE */
+#endif /* !CONFIG_OLPC */
 
-#ifdef CONFIG_OLPC_OPENFIRMWARE_DT
+#ifdef CONFIG_OF_PROMTREE
 extern void olpc_dt_build_devicetree(void);
 #else
 static inline void olpc_dt_build_devicetree(void) { }
-#endif /* CONFIG_OLPC_OPENFIRMWARE_DT */
+#endif
 
 #endif /* _ASM_X86_OLPC_OFW_H */
diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h
index 1df66211fd1b..bce688d54c12 100644
--- a/arch/x86/include/asm/page_types.h
+++ b/arch/x86/include/asm/page_types.h
@@ -2,6 +2,7 @@
 #define _ASM_X86_PAGE_DEFS_H
 
 #include <linux/const.h>
+#include <linux/types.h>
 
 /* PAGE_SHIFT determines the page size */
 #define PAGE_SHIFT	12
@@ -45,11 +46,15 @@ extern int devmem_is_allowed(unsigned long pagenr);
 extern unsigned long max_low_pfn_mapped;
 extern unsigned long max_pfn_mapped;
 
+static inline phys_addr_t get_max_mapped(void)
+{
+	return (phys_addr_t)max_pfn_mapped << PAGE_SHIFT;
+}
+
 extern unsigned long init_memory_mapping(unsigned long start,
 					 unsigned long end);
 
-extern void initmem_init(unsigned long start_pfn, unsigned long end_pfn,
-				int acpi, int k8);
+extern void initmem_init(void);
 extern void free_initmem(void);
 
 #endif	/* !__ASSEMBLY__ */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 45636cefa186..4c25ab48257b 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -94,10 +94,6 @@ struct cpuinfo_x86 {
 	int			x86_cache_alignment;	/* In bytes */
 	int			x86_power;
 	unsigned long		loops_per_jiffy;
-#ifdef CONFIG_SMP
-	/* cpus sharing the last level cache: */
-	cpumask_var_t		llc_shared_map;
-#endif
 	/* cpuid returned max cores value: */
 	u16			 x86_max_cores;
 	u16			apicid;
diff --git a/arch/x86/include/asm/prom.h b/arch/x86/include/asm/prom.h
index b4ec95f07518..971e0b46446e 100644
--- a/arch/x86/include/asm/prom.h
+++ b/arch/x86/include/asm/prom.h
@@ -1 +1,69 @@
-/* dummy prom.h; here to make linux/of.h's #includes happy */
+/*
+ * Definitions for Device tree / OpenFirmware handling on X86
+ *
+ * based on arch/powerpc/include/asm/prom.h which is
+ *         Copyright (C) 1996-2005 Paul Mackerras.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _ASM_X86_PROM_H
+#define _ASM_X86_PROM_H
+#ifndef __ASSEMBLY__
+
+#include <linux/of.h>
+#include <linux/types.h>
+#include <linux/pci.h>
+
+#include <asm/irq.h>
+#include <asm/atomic.h>
+#include <asm/setup.h>
+#include <asm/irq_controller.h>
+
+#ifdef CONFIG_OF
+extern int of_ioapic;
+extern u64 initial_dtb;
+extern void add_dtb(u64 data);
+extern void x86_add_irq_domains(void);
+void __cpuinit x86_of_pci_init(void);
+void x86_dtb_init(void);
+
+static inline struct device_node *pci_device_to_OF_node(struct pci_dev *pdev)
+{
+	return pdev ? pdev->dev.of_node : NULL;
+}
+
+static inline struct device_node *pci_bus_to_OF_node(struct pci_bus *bus)
+{
+	return pci_device_to_OF_node(bus->self);
+}
+
+#else
+static inline void add_dtb(u64 data) { }
+static inline void x86_add_irq_domains(void) { }
+static inline void x86_of_pci_init(void) { }
+static inline void x86_dtb_init(void) { }
+#define of_ioapic 0
+#endif
+
+extern char cmd_line[COMMAND_LINE_SIZE];
+
+#define pci_address_to_pio pci_address_to_pio
+unsigned long pci_address_to_pio(phys_addr_t addr);
+
+/**
+ * irq_dispose_mapping - Unmap an interrupt
+ * @virq: linux virq number of the interrupt to unmap
+ *
+ * FIXME: We really should implement proper virq handling like power,
+ * but that's going to be major surgery.
+ */
+static inline void irq_dispose_mapping(unsigned int virq) { }
+
+#define HAVE_ARCH_DEVTREE_FIXUPS
+
+#endif /* __ASSEMBLY__ */
+#endif
diff --git a/arch/x86/include/asm/rwsem.h b/arch/x86/include/asm/rwsem.h
index d1e41b0f9b60..df4cd32b4cc6 100644
--- a/arch/x86/include/asm/rwsem.h
+++ b/arch/x86/include/asm/rwsem.h
@@ -37,26 +37,9 @@
 #endif
 
 #ifdef __KERNEL__
-
-#include <linux/list.h>
-#include <linux/spinlock.h>
-#include <linux/lockdep.h>
 #include <asm/asm.h>
 
-struct rwsem_waiter;
-
-extern asmregparm struct rw_semaphore *
- rwsem_down_read_failed(struct rw_semaphore *sem);
-extern asmregparm struct rw_semaphore *
- rwsem_down_write_failed(struct rw_semaphore *sem);
-extern asmregparm struct rw_semaphore *
- rwsem_wake(struct rw_semaphore *);
-extern asmregparm struct rw_semaphore *
- rwsem_downgrade_wake(struct rw_semaphore *sem);
-
 /*
- * the semaphore definition
- *
  * The bias values and the counter type limits the number of
  * potential readers/writers to 32767 for 32 bits and 2147483647
  * for 64 bits.
@@ -74,43 +57,6 @@ extern asmregparm struct rw_semaphore *
 #define RWSEM_ACTIVE_READ_BIAS		RWSEM_ACTIVE_BIAS
 #define RWSEM_ACTIVE_WRITE_BIAS		(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
 
-typedef signed long rwsem_count_t;
-
-struct rw_semaphore {
-	rwsem_count_t		count;
-	spinlock_t		wait_lock;
-	struct list_head	wait_list;
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-	struct lockdep_map dep_map;
-#endif
-};
-
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define __RWSEM_DEP_MAP_INIT(lockname) , .dep_map = { .name = #lockname }
-#else
-# define __RWSEM_DEP_MAP_INIT(lockname)
-#endif
-
-
-#define __RWSEM_INITIALIZER(name)				\
-{								\
-	RWSEM_UNLOCKED_VALUE, __SPIN_LOCK_UNLOCKED((name).wait_lock), \
-	LIST_HEAD_INIT((name).wait_list) __RWSEM_DEP_MAP_INIT(name) \
-}
-
-#define DECLARE_RWSEM(name)					\
-	struct rw_semaphore name = __RWSEM_INITIALIZER(name)
-
-extern void __init_rwsem(struct rw_semaphore *sem, const char *name,
-			 struct lock_class_key *key);
-
-#define init_rwsem(sem)						\
-do {								\
-	static struct lock_class_key __key;			\
-								\
-	__init_rwsem((sem), #sem, &__key);			\
-} while (0)
-
 /*
  * lock for reading
  */
@@ -133,7 +79,7 @@ static inline void __down_read(struct rw_semaphore *sem)
  */
 static inline int __down_read_trylock(struct rw_semaphore *sem)
 {
-	rwsem_count_t result, tmp;
+	long result, tmp;
 	asm volatile("# beginning __down_read_trylock\n\t"
 		     "  mov          %0,%1\n\t"
 		     "1:\n\t"
@@ -155,7 +101,7 @@ static inline int __down_read_trylock(struct rw_semaphore *sem)
  */
 static inline void __down_write_nested(struct rw_semaphore *sem, int subclass)
 {
-	rwsem_count_t tmp;
+	long tmp;
 	asm volatile("# beginning down_write\n\t"
 		     LOCK_PREFIX "  xadd      %1,(%2)\n\t"
 		     /* adds 0xffff0001, returns the old value */
@@ -180,9 +126,8 @@ static inline void __down_write(struct rw_semaphore *sem)
  */
 static inline int __down_write_trylock(struct rw_semaphore *sem)
 {
-	rwsem_count_t ret = cmpxchg(&sem->count,
-				    RWSEM_UNLOCKED_VALUE,
-				    RWSEM_ACTIVE_WRITE_BIAS);
+	long ret = cmpxchg(&sem->count, RWSEM_UNLOCKED_VALUE,
+			   RWSEM_ACTIVE_WRITE_BIAS);
 	if (ret == RWSEM_UNLOCKED_VALUE)
 		return 1;
 	return 0;
@@ -193,7 +138,7 @@ static inline int __down_write_trylock(struct rw_semaphore *sem)
  */
 static inline void __up_read(struct rw_semaphore *sem)
 {
-	rwsem_count_t tmp;
+	long tmp;
 	asm volatile("# beginning __up_read\n\t"
 		     LOCK_PREFIX "  xadd      %1,(%2)\n\t"
 		     /* subtracts 1, returns the old value */
@@ -211,7 +156,7 @@ static inline void __up_read(struct rw_semaphore *sem)
  */
 static inline void __up_write(struct rw_semaphore *sem)
 {
-	rwsem_count_t tmp;
+	long tmp;
 	asm volatile("# beginning __up_write\n\t"
 		     LOCK_PREFIX "  xadd      %1,(%2)\n\t"
 		     /* subtracts 0xffff0001, returns the old value */
@@ -247,8 +192,7 @@ static inline void __downgrade_write(struct rw_semaphore *sem)
 /*
  * implement atomic add functionality
  */
-static inline void rwsem_atomic_add(rwsem_count_t delta,
-				    struct rw_semaphore *sem)
+static inline void rwsem_atomic_add(long delta, struct rw_semaphore *sem)
 {
 	asm volatile(LOCK_PREFIX _ASM_ADD "%1,%0"
 		     : "+m" (sem->count)
@@ -258,10 +202,9 @@ static inline void rwsem_atomic_add(rwsem_count_t delta,
 /*
  * implement exchange and add functionality
  */
-static inline rwsem_count_t rwsem_atomic_update(rwsem_count_t delta,
-						struct rw_semaphore *sem)
+static inline long rwsem_atomic_update(long delta, struct rw_semaphore *sem)
 {
-	rwsem_count_t tmp = delta;
+	long tmp = delta;
 
 	asm volatile(LOCK_PREFIX "xadd %0,%1"
 		     : "+r" (tmp), "+m" (sem->count)
@@ -270,10 +213,5 @@ static inline rwsem_count_t rwsem_atomic_update(rwsem_count_t delta,
 	return tmp + delta;
 }
 
-static inline int rwsem_is_locked(struct rw_semaphore *sem)
-{
-	return (sem->count != 0);
-}
-
 #endif /* __KERNEL__ */
 #endif /* _ASM_X86_RWSEM_H */
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 1f4695136776..73b11bc0ae6f 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -17,12 +17,24 @@
 #endif
 #include <asm/thread_info.h>
 #include <asm/cpumask.h>
+#include <asm/cpufeature.h>
 
 extern int smp_num_siblings;
 extern unsigned int num_processors;
 
+static inline bool cpu_has_ht_siblings(void)
+{
+	bool has_siblings = false;
+#ifdef CONFIG_SMP
+	has_siblings = cpu_has_ht && smp_num_siblings > 1;
+#endif
+	return has_siblings;
+}
+
 DECLARE_PER_CPU(cpumask_var_t, cpu_sibling_map);
 DECLARE_PER_CPU(cpumask_var_t, cpu_core_map);
+/* cpus sharing the last level cache: */
+DECLARE_PER_CPU(cpumask_var_t, cpu_llc_shared_map);
 DECLARE_PER_CPU(u16, cpu_llc_id);
 DECLARE_PER_CPU(int, cpu_number);
 
@@ -36,8 +48,16 @@ static inline struct cpumask *cpu_core_mask(int cpu)
 	return per_cpu(cpu_core_map, cpu);
 }
 
+static inline struct cpumask *cpu_llc_shared_mask(int cpu)
+{
+	return per_cpu(cpu_llc_shared_map, cpu);
+}
+
 DECLARE_EARLY_PER_CPU(u16, x86_cpu_to_apicid);
 DECLARE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid);
+#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_32)
+DECLARE_EARLY_PER_CPU(int, x86_cpu_to_logical_apicid);
+#endif
 
 /* Static state in head.S used to set up a CPU */
 extern unsigned long stack_start; /* Initial stack pointer address */
diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h
index 33ecc3ea8782..12569e691ce3 100644
--- a/arch/x86/include/asm/system.h
+++ b/arch/x86/include/asm/system.h
@@ -98,8 +98,6 @@ do {									\
  */
 #define HAVE_DISABLE_HLT
 #else
-#define __SAVE(reg, offset) "movq %%" #reg ",(14-" #offset ")*8(%%rsp)\n\t"
-#define __RESTORE(reg, offset) "movq (14-" #offset ")*8(%%rsp),%%" #reg "\n\t"
 
 /* frame pointer must be last for get_wchan */
 #define SAVE_CONTEXT    "pushf ; pushq %%rbp ; movq %%rsi,%%rbp\n\t"
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 21899cc31e52..910a7084f7f2 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -47,21 +47,6 @@
 
 #include <asm/mpspec.h>
 
-#ifdef CONFIG_X86_32
-
-/* Mappings between logical cpu number and node number */
-extern int cpu_to_node_map[];
-
-/* Returns the number of the node containing CPU 'cpu' */
-static inline int __cpu_to_node(int cpu)
-{
-	return cpu_to_node_map[cpu];
-}
-#define early_cpu_to_node __cpu_to_node
-#define cpu_to_node __cpu_to_node
-
-#else /* CONFIG_X86_64 */
-
 /* Mappings between logical cpu number and node number */
 DECLARE_EARLY_PER_CPU(int, x86_cpu_to_node_map);
 
@@ -84,8 +69,6 @@ static inline int early_cpu_to_node(int cpu)
 
 #endif /* !CONFIG_DEBUG_PER_CPU_MAPS */
 
-#endif /* CONFIG_X86_64 */
-
 /* Mappings between node number and cpus on that node. */
 extern cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
 
@@ -155,7 +138,7 @@ extern unsigned long node_remap_size[];
 	.balance_interval	= 1,					\
 }
 
-#ifdef CONFIG_X86_64_ACPI_NUMA
+#ifdef CONFIG_X86_64
 extern int __node_distance(int, int);
 #define node_distance(a, b) __node_distance(a, b)
 #endif
diff --git a/arch/x86/include/asm/unistd_32.h b/arch/x86/include/asm/unistd_32.h
index b766a5e8ba0e..ffaf183c619a 100644
--- a/arch/x86/include/asm/unistd_32.h
+++ b/arch/x86/include/asm/unistd_32.h
@@ -346,10 +346,13 @@
 #define __NR_fanotify_init	338
 #define __NR_fanotify_mark	339
 #define __NR_prlimit64		340
+#define __NR_name_to_handle_at	341
+#define __NR_open_by_handle_at  342
+#define __NR_clock_adjtime	343
 
 #ifdef __KERNEL__
 
-#define NR_syscalls 341
+#define NR_syscalls 344
 
 #define __ARCH_WANT_IPC_PARSE_VERSION
 #define __ARCH_WANT_OLD_READDIR
diff --git a/arch/x86/include/asm/unistd_64.h b/arch/x86/include/asm/unistd_64.h
index 363e9b8a715b..5466bea670e7 100644
--- a/arch/x86/include/asm/unistd_64.h
+++ b/arch/x86/include/asm/unistd_64.h
@@ -669,6 +669,12 @@ __SYSCALL(__NR_fanotify_init, sys_fanotify_init)
 __SYSCALL(__NR_fanotify_mark, sys_fanotify_mark)
 #define __NR_prlimit64				302
 __SYSCALL(__NR_prlimit64, sys_prlimit64)
+#define __NR_name_to_handle_at			303
+__SYSCALL(__NR_name_to_handle_at, sys_name_to_handle_at)
+#define __NR_open_by_handle_at			304
+__SYSCALL(__NR_open_by_handle_at, sys_open_by_handle_at)
+#define __NR_clock_adjtime			305
+__SYSCALL(__NR_clock_adjtime, sys_clock_adjtime)
 
 #ifndef __NO_STUBS
 #define __ARCH_WANT_OLD_READDIR
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index 64642ad019fb..643ebf2e2ad8 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -83,11 +83,13 @@ struct x86_init_paging {
  *				boot cpu
  * @tsc_pre_init:		platform function called before TSC init
  * @timer_init:			initialize the platform timer (default PIT/HPET)
+ * @wallclock_init:		init the wallclock device
  */
 struct x86_init_timers {
 	void (*setup_percpu_clockev)(void);
 	void (*tsc_pre_init)(void);
 	void (*timer_init)(void);
+	void (*wallclock_init)(void);
 };
 
 /**
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index a3c28ae4025b..8508bfe52296 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -287,7 +287,7 @@ HYPERVISOR_fpu_taskswitch(int set)
 static inline int
 HYPERVISOR_sched_op(int cmd, void *arg)
 {
-	return _hypercall2(int, sched_op_new, cmd, arg);
+	return _hypercall2(int, sched_op, cmd, arg);
 }
 
 static inline long
@@ -422,10 +422,17 @@ HYPERVISOR_set_segment_base(int reg, unsigned long value)
 #endif
 
 static inline int
-HYPERVISOR_suspend(unsigned long srec)
+HYPERVISOR_suspend(unsigned long start_info_mfn)
 {
-	return _hypercall3(int, sched_op, SCHEDOP_shutdown,
-			   SHUTDOWN_suspend, srec);
+	struct sched_shutdown r = { .reason = SHUTDOWN_suspend };
+
+	/*
+	 * For a PV guest the tools require that the start_info mfn be
+	 * present in rdx/edx when the hypercall is made. Per the
+	 * hypercall calling convention this is the third hypercall
+	 * argument, which is start_info_mfn here.
+	 */
+	return _hypercall3(int, sched_op, SCHEDOP_shutdown, &r, start_info_mfn);
 }
 
 static inline int
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index f25bdf238a33..c61934fbf22a 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -29,8 +29,10 @@ typedef struct xpaddr {
 
 /**** MACHINE <-> PHYSICAL CONVERSION MACROS ****/
 #define INVALID_P2M_ENTRY	(~0UL)
-#define FOREIGN_FRAME_BIT	(1UL<<31)
+#define FOREIGN_FRAME_BIT	(1UL<<(BITS_PER_LONG-1))
+#define IDENTITY_FRAME_BIT	(1UL<<(BITS_PER_LONG-2))
 #define FOREIGN_FRAME(m)	((m) | FOREIGN_FRAME_BIT)
+#define IDENTITY_FRAME(m)	((m) | IDENTITY_FRAME_BIT)
 
 /* Maximum amount of memory we can handle in a domain in pages */
 #define MAX_DOMAIN_PAGES						\
@@ -41,12 +43,18 @@ extern unsigned int   machine_to_phys_order;
 
 extern unsigned long get_phys_to_machine(unsigned long pfn);
 extern bool set_phys_to_machine(unsigned long pfn, unsigned long mfn);
+extern bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn);
+extern unsigned long set_phys_range_identity(unsigned long pfn_s,
+					     unsigned long pfn_e);
 
 extern int m2p_add_override(unsigned long mfn, struct page *page);
 extern int m2p_remove_override(struct page *page);
 extern struct page *m2p_find_override(unsigned long mfn);
 extern unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn);
 
+#ifdef CONFIG_XEN_DEBUG_FS
+extern int p2m_dump_show(struct seq_file *m, void *v);
+#endif
 static inline unsigned long pfn_to_mfn(unsigned long pfn)
 {
 	unsigned long mfn;
@@ -57,7 +65,7 @@ static inline unsigned long pfn_to_mfn(unsigned long pfn)
 	mfn = get_phys_to_machine(pfn);
 
 	if (mfn != INVALID_P2M_ENTRY)
-		mfn &= ~FOREIGN_FRAME_BIT;
+		mfn &= ~(FOREIGN_FRAME_BIT | IDENTITY_FRAME_BIT);
 
 	return mfn;
 }
@@ -73,25 +81,44 @@ static inline int phys_to_machine_mapping_valid(unsigned long pfn)
 static inline unsigned long mfn_to_pfn(unsigned long mfn)
 {
 	unsigned long pfn;
+	int ret = 0;
 
 	if (xen_feature(XENFEAT_auto_translated_physmap))
 		return mfn;
 
+	if (unlikely((mfn >> machine_to_phys_order) != 0)) {
+		pfn = ~0;
+		goto try_override;
+	}
 	pfn = 0;
 	/*
 	 * The array access can fail (e.g., device space beyond end of RAM).
 	 * In such cases it doesn't matter what we return (we return garbage),
 	 * but we must handle the fault without crashing!
 	 */
-	__get_user(pfn, &machine_to_phys_mapping[mfn]);
-
-	/*
-	 * If this appears to be a foreign mfn (because the pfn
-	 * doesn't map back to the mfn), then check the local override
-	 * table to see if there's a better pfn to use.
+	ret = __get_user(pfn, &machine_to_phys_mapping[mfn]);
+try_override:
+	/* ret might be < 0 if there are no entries in the m2p for mfn */
+	if (ret < 0)
+		pfn = ~0;
+	else if (get_phys_to_machine(pfn) != mfn)
+		/*
+		 * If this appears to be a foreign mfn (because the pfn
+		 * doesn't map back to the mfn), then check the local override
+		 * table to see if there's a better pfn to use.
+		 *
+		 * m2p_find_override_pfn returns ~0 if it doesn't find anything.
+		 */
+		pfn = m2p_find_override_pfn(mfn, ~0);
+
+	/* 
+	 * pfn is ~0 if there are no entries in the m2p for mfn or if the
+	 * entry doesn't map back to the mfn and m2p_override doesn't have a
+	 * valid entry for it.
 	 */
-	if (get_phys_to_machine(pfn) != mfn)
-		pfn = m2p_find_override_pfn(mfn, pfn);
+	if (pfn == ~0 &&
+			get_phys_to_machine(mfn) == IDENTITY_FRAME(mfn))
+		pfn = mfn;
 
 	return pfn;
 }
diff --git a/arch/x86/include/asm/xen/pci.h b/arch/x86/include/asm/xen/pci.h
index 2329b3eaf8d3..aa8620989162 100644
--- a/arch/x86/include/asm/xen/pci.h
+++ b/arch/x86/include/asm/xen/pci.h
@@ -27,16 +27,16 @@ static inline void __init xen_setup_pirqs(void)
  * its own functions.
  */
 struct xen_pci_frontend_ops {
-	int (*enable_msi)(struct pci_dev *dev, int **vectors);
+	int (*enable_msi)(struct pci_dev *dev, int vectors[]);
 	void (*disable_msi)(struct pci_dev *dev);
-	int (*enable_msix)(struct pci_dev *dev, int **vectors, int nvec);
+	int (*enable_msix)(struct pci_dev *dev, int vectors[], int nvec);
 	void (*disable_msix)(struct pci_dev *dev);
 };
 
 extern struct xen_pci_frontend_ops *xen_pci_frontend;
 
 static inline int xen_pci_frontend_enable_msi(struct pci_dev *dev,
-					      int **vectors)
+					      int vectors[])
 {
 	if (xen_pci_frontend && xen_pci_frontend->enable_msi)
 		return xen_pci_frontend->enable_msi(dev, vectors);
@@ -48,7 +48,7 @@ static inline void xen_pci_frontend_disable_msi(struct pci_dev *dev)
 			xen_pci_frontend->disable_msi(dev);
 }
 static inline int xen_pci_frontend_enable_msix(struct pci_dev *dev,
-					       int **vectors, int nvec)
+					       int vectors[], int nvec)
 {
 	if (xen_pci_frontend && xen_pci_frontend->enable_msix)
 		return xen_pci_frontend->enable_msix(dev, vectors, nvec);
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 34244b2cd880..62445ba2f8a8 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -66,9 +66,9 @@ obj-$(CONFIG_PCI)		+= early-quirks.o
 apm-y				:= apm_32.o
 obj-$(CONFIG_APM)		+= apm.o
 obj-$(CONFIG_SMP)		+= smp.o
-obj-$(CONFIG_SMP)		+= smpboot.o tsc_sync.o
+obj-$(CONFIG_SMP)		+= smpboot.o
+obj-$(CONFIG_SMP)		+= tsc_sync.o
 obj-$(CONFIG_SMP)		+= setup_percpu.o
-obj-$(CONFIG_X86_64_SMP)	+= tsc_sync.o
 obj-$(CONFIG_X86_TRAMPOLINE)	+= trampoline_$(BITS).o
 obj-$(CONFIG_X86_MPPARSE)	+= mpparse.o
 obj-y				+= apic/
@@ -109,6 +109,7 @@ obj-$(CONFIG_MICROCODE)			+= microcode.o
 obj-$(CONFIG_X86_CHECK_BIOS_CORRUPTION) += check.o
 
 obj-$(CONFIG_SWIOTLB)			+= pci-swiotlb.o
+obj-$(CONFIG_OF)			+= devicetree.o
 
 ###
 # 64 bit specific files
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 3e6e2d68f761..9a966c579af5 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -595,14 +595,8 @@ static void acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)
 	nid = acpi_get_node(handle);
 	if (nid == -1 || !node_online(nid))
 		return;
-#ifdef CONFIG_X86_64
-	apicid_to_node[physid] = nid;
+	set_apicid_to_node(physid, nid);
 	numa_set_node(cpu, nid);
-#else /* CONFIG_X86_32 */
-	apicid_2_node[physid] = nid;
-	cpu_to_node_map[cpu] = nid;
-#endif
-
 #endif
 }
 
diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c
index 51d4e1663066..1293c709ee85 100644
--- a/arch/x86/kernel/apb_timer.c
+++ b/arch/x86/kernel/apb_timer.c
@@ -508,64 +508,12 @@ static int apbt_next_event(unsigned long delta,
 	return 0;
 }
 
-/*
- * APB timer clock is not in sync with pclk on Langwell, which translates to
- * unreliable read value caused by sampling error. the error does not add up
- * overtime and only happens when sampling a 0 as a 1 by mistake. so the time
- * would go backwards. the following code is trying to prevent time traveling
- * backwards. little bit paranoid.
- */
 static cycle_t apbt_read_clocksource(struct clocksource *cs)
 {
-	unsigned long t0, t1, t2;
-	static unsigned long last_read;
-
-bad_count:
-	t1 = apbt_readl(phy_cs_timer_id,
-			APBTMR_N_CURRENT_VALUE);
-	t2 = apbt_readl(phy_cs_timer_id,
-			APBTMR_N_CURRENT_VALUE);
-	if (unlikely(t1 < t2)) {
-		pr_debug("APBT: read current count error %lx:%lx:%lx\n",
-			 t1, t2, t2 - t1);
-		goto bad_count;
-	}
-	/*
-	 * check against cached last read, makes sure time does not go back.
-	 * it could be a normal rollover but we will do tripple check anyway
-	 */
-	if (unlikely(t2 > last_read)) {
-		/* check if we have a normal rollover */
-		unsigned long raw_intr_status =
-			apbt_readl_reg(APBTMRS_RAW_INT_STATUS);
-		/*
-		 * cs timer interrupt is masked but raw intr bit is set if
-		 * rollover occurs. then we read EOI reg to clear it.
-		 */
-		if (raw_intr_status & (1 << phy_cs_timer_id)) {
-			apbt_readl(phy_cs_timer_id, APBTMR_N_EOI);
-			goto out;
-		}
-		pr_debug("APB CS going back %lx:%lx:%lx ",
-			 t2, last_read, t2 - last_read);
-bad_count_x3:
-		pr_debug("triple check enforced\n");
-		t0 = apbt_readl(phy_cs_timer_id,
-				APBTMR_N_CURRENT_VALUE);
-		udelay(1);
-		t1 = apbt_readl(phy_cs_timer_id,
-				APBTMR_N_CURRENT_VALUE);
-		udelay(1);
-		t2 = apbt_readl(phy_cs_timer_id,
-				APBTMR_N_CURRENT_VALUE);
-		if ((t2 > t1) || (t1 > t0)) {
-			printk(KERN_ERR "Error: APB CS tripple check failed\n");
-			goto bad_count_x3;
-		}
-	}
-out:
-	last_read = t2;
-	return (cycle_t)~t2;
+	unsigned long current_count;
+
+	current_count = apbt_readl(phy_cs_timer_id, APBTMR_N_CURRENT_VALUE);
+	return (cycle_t)~current_count;
 }
 
 static int apbt_clocksource_register(void)
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index 5955a7800a96..7b1e8e10b89c 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -13,7 +13,7 @@
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/init.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/mmzone.h>
 #include <linux/pci_ids.h>
 #include <linux/pci.h>
@@ -57,7 +57,7 @@ static void __init insert_aperture_resource(u32 aper_base, u32 aper_size)
 static u32 __init allocate_aperture(void)
 {
 	u32 aper_size;
-	void *p;
+	unsigned long addr;
 
 	/* aper_size should <= 1G */
 	if (fallback_aper_order > 5)
@@ -83,27 +83,26 @@ static u32 __init allocate_aperture(void)
 	 * so don't use 512M below as gart iommu, leave the space for kernel
 	 * code for safe
 	 */
-	p = __alloc_bootmem_nopanic(aper_size, aper_size, 512ULL<<20);
+	addr = memblock_find_in_range(0, 1ULL<<32, aper_size, 512ULL<<20);
+	if (addr == MEMBLOCK_ERROR || addr + aper_size > 0xffffffff) {
+		printk(KERN_ERR
+			"Cannot allocate aperture memory hole (%lx,%uK)\n",
+				addr, aper_size>>10);
+		return 0;
+	}
+	memblock_x86_reserve_range(addr, addr + aper_size, "aperture64");
 	/*
 	 * Kmemleak should not scan this block as it may not be mapped via the
 	 * kernel direct mapping.
 	 */
-	kmemleak_ignore(p);
-	if (!p || __pa(p)+aper_size > 0xffffffff) {
-		printk(KERN_ERR
-			"Cannot allocate aperture memory hole (%p,%uK)\n",
-				p, aper_size>>10);
-		if (p)
-			free_bootmem(__pa(p), aper_size);
-		return 0;
-	}
+	kmemleak_ignore(phys_to_virt(addr));
 	printk(KERN_INFO "Mapping aperture over %d KB of RAM @ %lx\n",
-			aper_size >> 10, __pa(p));
-	insert_aperture_resource((u32)__pa(p), aper_size);
-	register_nosave_region((u32)__pa(p) >> PAGE_SHIFT,
-				(u32)__pa(p+aper_size) >> PAGE_SHIFT);
+			aper_size >> 10, addr);
+	insert_aperture_resource((u32)addr, aper_size);
+	register_nosave_region(addr >> PAGE_SHIFT,
+			       (addr+aper_size) >> PAGE_SHIFT);
 
-	return (u32)__pa(p);
+	return (u32)addr;
 }
 
 
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 76b96d74978a..966673f44141 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -43,6 +43,7 @@
 #include <asm/i8259.h>
 #include <asm/proto.h>
 #include <asm/apic.h>
+#include <asm/io_apic.h>
 #include <asm/desc.h>
 #include <asm/hpet.h>
 #include <asm/idle.h>
@@ -78,12 +79,21 @@ EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_apicid);
 EXPORT_EARLY_PER_CPU_SYMBOL(x86_bios_cpu_apicid);
 
 #ifdef CONFIG_X86_32
+
+/*
+ * On x86_32, the mapping between cpu and logical apicid may vary
+ * depending on apic in use.  The following early percpu variable is
+ * used for the mapping.  This is where the behaviors of x86_64 and 32
+ * actually diverge.  Let's keep it ugly for now.
+ */
+DEFINE_EARLY_PER_CPU(int, x86_cpu_to_logical_apicid, BAD_APICID);
+
 /*
  * Knob to control our willingness to enable the local APIC.
  *
  * +1=force-enable
  */
-static int force_enable_local_apic;
+static int force_enable_local_apic __initdata;
 /*
  * APIC command line parameters
  */
@@ -153,7 +163,7 @@ early_param("nox2apic", setup_nox2apic);
 unsigned long mp_lapic_addr;
 int disable_apic;
 /* Disable local APIC timer from the kernel commandline or via dmi quirk */
-static int disable_apic_timer __cpuinitdata;
+static int disable_apic_timer __initdata;
 /* Local APIC timer works in C2 */
 int local_apic_timer_c2_ok;
 EXPORT_SYMBOL_GPL(local_apic_timer_c2_ok);
@@ -177,29 +187,8 @@ static struct resource lapic_resource = {
 
 static unsigned int calibration_result;
 
-static int lapic_next_event(unsigned long delta,
-			    struct clock_event_device *evt);
-static void lapic_timer_setup(enum clock_event_mode mode,
-			      struct clock_event_device *evt);
-static void lapic_timer_broadcast(const struct cpumask *mask);
 static void apic_pm_activate(void);
 
-/*
- * The local apic timer can be used for any function which is CPU local.
- */
-static struct clock_event_device lapic_clockevent = {
-	.name		= "lapic",
-	.features	= CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT
-			| CLOCK_EVT_FEAT_C3STOP | CLOCK_EVT_FEAT_DUMMY,
-	.shift		= 32,
-	.set_mode	= lapic_timer_setup,
-	.set_next_event	= lapic_next_event,
-	.broadcast	= lapic_timer_broadcast,
-	.rating		= 100,
-	.irq		= -1,
-};
-static DEFINE_PER_CPU(struct clock_event_device, lapic_events);
-
 static unsigned long apic_phys;
 
 /*
@@ -238,7 +227,7 @@ static int modern_apic(void)
  * right after this call apic become NOOP driven
  * so apic->write/read doesn't do anything
  */
-void apic_disable(void)
+static void __init apic_disable(void)
 {
 	pr_info("APIC: switched to apic NOOP\n");
 	apic = &apic_noop;
@@ -282,23 +271,6 @@ u64 native_apic_icr_read(void)
 	return icr1 | ((u64)icr2 << 32);
 }
 
-/**
- * enable_NMI_through_LVT0 - enable NMI through local vector table 0
- */
-void __cpuinit enable_NMI_through_LVT0(void)
-{
-	unsigned int v;
-
-	/* unmask and set to NMI */
-	v = APIC_DM_NMI;
-
-	/* Level triggered for 82489DX (32bit mode) */
-	if (!lapic_is_integrated())
-		v |= APIC_LVT_LEVEL_TRIGGER;
-
-	apic_write(APIC_LVT0, v);
-}
-
 #ifdef CONFIG_X86_32
 /**
  * get_physical_broadcast - Get number of physical broadcast IDs
@@ -508,6 +480,23 @@ static void lapic_timer_broadcast(const struct cpumask *mask)
 #endif
 }
 
+
+/*
+ * The local apic timer can be used for any function which is CPU local.
+ */
+static struct clock_event_device lapic_clockevent = {
+	.name		= "lapic",
+	.features	= CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT
+			| CLOCK_EVT_FEAT_C3STOP | CLOCK_EVT_FEAT_DUMMY,
+	.shift		= 32,
+	.set_mode	= lapic_timer_setup,
+	.set_next_event	= lapic_next_event,
+	.broadcast	= lapic_timer_broadcast,
+	.rating		= 100,
+	.irq		= -1,
+};
+static DEFINE_PER_CPU(struct clock_event_device, lapic_events);
+
 /*
  * Setup the local APIC timer for this CPU. Copy the initialized values
  * of the boot CPU and register the clock event in the framework.
@@ -1209,7 +1198,7 @@ void __cpuinit setup_local_APIC(void)
 		rdtscll(tsc);
 
 	if (disable_apic) {
-		arch_disable_smp_support();
+		disable_ioapic_support();
 		return;
 	}
 
@@ -1237,6 +1226,19 @@ void __cpuinit setup_local_APIC(void)
 	 */
 	apic->init_apic_ldr();
 
+#ifdef CONFIG_X86_32
+	/*
+	 * APIC LDR is initialized.  If logical_apicid mapping was
+	 * initialized during get_smp_config(), make sure it matches the
+	 * actual value.
+	 */
+	i = early_per_cpu(x86_cpu_to_logical_apicid, cpu);
+	WARN_ON(i != BAD_APICID && i != logical_smp_processor_id());
+	/* always use the value from LDR */
+	early_per_cpu(x86_cpu_to_logical_apicid, cpu) =
+		logical_smp_processor_id();
+#endif
+
 	/*
 	 * Set Task Priority to 'accept all'. We never change this
 	 * later on.
@@ -1448,7 +1450,7 @@ int __init enable_IR(void)
 void __init enable_IR_x2apic(void)
 {
 	unsigned long flags;
-	struct IO_APIC_route_entry **ioapic_entries = NULL;
+	struct IO_APIC_route_entry **ioapic_entries;
 	int ret, x2apic_enabled = 0;
 	int dmar_table_init_ret;
 
@@ -1537,7 +1539,7 @@ static int __init detect_init_APIC(void)
 }
 #else
 
-static int apic_verify(void)
+static int __init apic_verify(void)
 {
 	u32 features, h, l;
 
@@ -1562,7 +1564,7 @@ static int apic_verify(void)
 	return 0;
 }
 
-int apic_force_enable(void)
+int __init apic_force_enable(unsigned long addr)
 {
 	u32 h, l;
 
@@ -1578,7 +1580,7 @@ int apic_force_enable(void)
 	if (!(l & MSR_IA32_APICBASE_ENABLE)) {
 		pr_info("Local APIC disabled by BIOS -- reenabling.\n");
 		l &= ~MSR_IA32_APICBASE_BASE;
-		l |= MSR_IA32_APICBASE_ENABLE | APIC_DEFAULT_PHYS_BASE;
+		l |= MSR_IA32_APICBASE_ENABLE | addr;
 		wrmsr(MSR_IA32_APICBASE, l, h);
 		enabled_via_apicbase = 1;
 	}
@@ -1619,7 +1621,7 @@ static int __init detect_init_APIC(void)
 				"you can enable it with \"lapic\"\n");
 			return -1;
 		}
-		if (apic_force_enable())
+		if (apic_force_enable(APIC_DEFAULT_PHYS_BASE))
 			return -1;
 	} else {
 		if (apic_verify())
@@ -1930,17 +1932,6 @@ void __cpuinit generic_processor_info(int apicid, int version)
 {
 	int cpu;
 
-	/*
-	 * Validate version
-	 */
-	if (version == 0x0) {
-		pr_warning("BIOS bug, APIC version is 0 for CPU#%d! "
-			   "fixing up to 0x10. (tell your hw vendor)\n",
-				version);
-		version = 0x10;
-	}
-	apic_version[apicid] = version;
-
 	if (num_processors >= nr_cpu_ids) {
 		int max = nr_cpu_ids;
 		int thiscpu = max + disabled_cpus;
@@ -1954,22 +1945,34 @@ void __cpuinit generic_processor_info(int apicid, int version)
 	}
 
 	num_processors++;
-	cpu = cpumask_next_zero(-1, cpu_present_mask);
-
-	if (version != apic_version[boot_cpu_physical_apicid])
-		WARN_ONCE(1,
-			"ACPI: apic version mismatch, bootcpu: %x cpu %d: %x\n",
-			apic_version[boot_cpu_physical_apicid], cpu, version);
-
-	physid_set(apicid, phys_cpu_present_map);
 	if (apicid == boot_cpu_physical_apicid) {
 		/*
 		 * x86_bios_cpu_apicid is required to have processors listed
 		 * in same order as logical cpu numbers. Hence the first
 		 * entry is BSP, and so on.
+		 * boot_cpu_init() already hold bit 0 in cpu_present_mask
+		 * for BSP.
 		 */
 		cpu = 0;
+	} else
+		cpu = cpumask_next_zero(-1, cpu_present_mask);
+
+	/*
+	 * Validate version
+	 */
+	if (version == 0x0) {
+		pr_warning("BIOS bug: APIC version is 0 for CPU %d/0x%x, fixing up to 0x10\n",
+			   cpu, apicid);
+		version = 0x10;
 	}
+	apic_version[apicid] = version;
+
+	if (version != apic_version[boot_cpu_physical_apicid]) {
+		pr_warning("BIOS bug: APIC version mismatch, boot CPU: %x, CPU %d: version %x\n",
+			apic_version[boot_cpu_physical_apicid], cpu, version);
+	}
+
+	physid_set(apicid, phys_cpu_present_map);
 	if (apicid > max_physical_apicid)
 		max_physical_apicid = apicid;
 
@@ -1977,7 +1980,10 @@ void __cpuinit generic_processor_info(int apicid, int version)
 	early_per_cpu(x86_cpu_to_apicid, cpu) = apicid;
 	early_per_cpu(x86_bios_cpu_apicid, cpu) = apicid;
 #endif
-
+#ifdef CONFIG_X86_32
+	early_per_cpu(x86_cpu_to_logical_apicid, cpu) =
+		apic->x86_32_early_logical_apicid(cpu);
+#endif
 	set_cpu_possible(cpu, true);
 	set_cpu_present(cpu, true);
 }
@@ -1998,10 +2004,14 @@ void default_init_apic_ldr(void)
 }
 
 #ifdef CONFIG_X86_32
-int default_apicid_to_node(int logical_apicid)
+int default_x86_32_numa_cpu_node(int cpu)
 {
-#ifdef CONFIG_SMP
-	return apicid_2_node[hard_smp_processor_id()];
+#ifdef CONFIG_NUMA
+	int apicid = early_per_cpu(x86_cpu_to_apicid, cpu);
+
+	if (apicid != BAD_APICID)
+		return __apicid_to_node[apicid];
+	return NUMA_NO_NODE;
 #else
 	return 0;
 #endif
diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c
index 09d3b17ce0c2..5652d31fe108 100644
--- a/arch/x86/kernel/apic/apic_flat_64.c
+++ b/arch/x86/kernel/apic/apic_flat_64.c
@@ -185,8 +185,6 @@ struct apic apic_flat =  {
 	.ioapic_phys_id_map		= NULL,
 	.setup_apic_routing		= NULL,
 	.multi_timer_check		= NULL,
-	.apicid_to_node			= NULL,
-	.cpu_to_logical_apicid		= NULL,
 	.cpu_present_to_apicid		= default_cpu_present_to_apicid,
 	.apicid_to_cpu_present		= NULL,
 	.setup_portio_remap		= NULL,
@@ -337,8 +335,6 @@ struct apic apic_physflat =  {
 	.ioapic_phys_id_map		= NULL,
 	.setup_apic_routing		= NULL,
 	.multi_timer_check		= NULL,
-	.apicid_to_node			= NULL,
-	.cpu_to_logical_apicid		= NULL,
 	.cpu_present_to_apicid		= default_cpu_present_to_apicid,
 	.apicid_to_cpu_present		= NULL,
 	.setup_portio_remap		= NULL,
diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c
index e31b9ffe25f5..f1baa2dc087a 100644
--- a/arch/x86/kernel/apic/apic_noop.c
+++ b/arch/x86/kernel/apic/apic_noop.c
@@ -54,11 +54,6 @@ static u64 noop_apic_icr_read(void)
 	return 0;
 }
 
-static int noop_cpu_to_logical_apicid(int cpu)
-{
-	return 0;
-}
-
 static int noop_phys_pkg_id(int cpuid_apic, int index_msb)
 {
 	return 0;
@@ -113,12 +108,6 @@ static void noop_vector_allocation_domain(int cpu, struct cpumask *retmask)
 	cpumask_set_cpu(cpu, retmask);
 }
 
-int noop_apicid_to_node(int logical_apicid)
-{
-	/* we're always on node 0 */
-	return 0;
-}
-
 static u32 noop_apic_read(u32 reg)
 {
 	WARN_ON_ONCE((cpu_has_apic && !disable_apic));
@@ -130,6 +119,14 @@ static void noop_apic_write(u32 reg, u32 v)
 	WARN_ON_ONCE(cpu_has_apic && !disable_apic);
 }
 
+#ifdef CONFIG_X86_32
+static int noop_x86_32_numa_cpu_node(int cpu)
+{
+	/* we're always on node 0 */
+	return 0;
+}
+#endif
+
 struct apic apic_noop = {
 	.name				= "noop",
 	.probe				= noop_probe,
@@ -153,9 +150,7 @@ struct apic apic_noop = {
 	.ioapic_phys_id_map		= default_ioapic_phys_id_map,
 	.setup_apic_routing		= NULL,
 	.multi_timer_check		= NULL,
-	.apicid_to_node			= noop_apicid_to_node,
 
-	.cpu_to_logical_apicid		= noop_cpu_to_logical_apicid,
 	.cpu_present_to_apicid		= default_cpu_present_to_apicid,
 	.apicid_to_cpu_present		= physid_set_mask_of_physid,
 
@@ -197,4 +192,9 @@ struct apic apic_noop = {
 	.icr_write			= noop_apic_icr_write,
 	.wait_icr_idle			= noop_apic_wait_icr_idle,
 	.safe_wait_icr_idle		= noop_safe_apic_wait_icr_idle,
+
+#ifdef CONFIG_X86_32
+	.x86_32_early_logical_apicid	= noop_x86_32_early_logical_apicid,
+	.x86_32_numa_cpu_node		= noop_x86_32_numa_cpu_node,
+#endif
 };
diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c
index cb804c5091b9..541a2e431659 100644
--- a/arch/x86/kernel/apic/bigsmp_32.c
+++ b/arch/x86/kernel/apic/bigsmp_32.c
@@ -45,6 +45,12 @@ static unsigned long bigsmp_check_apicid_present(int bit)
 	return 1;
 }
 
+static int bigsmp_early_logical_apicid(int cpu)
+{
+	/* on bigsmp, logical apicid is the same as physical */
+	return early_per_cpu(x86_cpu_to_apicid, cpu);
+}
+
 static inline unsigned long calculate_ldr(int cpu)
 {
 	unsigned long val, id;
@@ -80,11 +86,6 @@ static void bigsmp_setup_apic_routing(void)
 		nr_ioapics);
 }
 
-static int bigsmp_apicid_to_node(int logical_apicid)
-{
-	return apicid_2_node[hard_smp_processor_id()];
-}
-
 static int bigsmp_cpu_present_to_apicid(int mps_cpu)
 {
 	if (mps_cpu < nr_cpu_ids)
@@ -93,14 +94,6 @@ static int bigsmp_cpu_present_to_apicid(int mps_cpu)
 	return BAD_APICID;
 }
 
-/* Mapping from cpu number to logical apicid */
-static inline int bigsmp_cpu_to_logical_apicid(int cpu)
-{
-	if (cpu >= nr_cpu_ids)
-		return BAD_APICID;
-	return cpu_physical_id(cpu);
-}
-
 static void bigsmp_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask_t *retmap)
 {
 	/* For clustered we don't have a good way to do this yet - hack */
@@ -115,7 +108,11 @@ static int bigsmp_check_phys_apicid_present(int phys_apicid)
 /* As we are using single CPU as destination, pick only one CPU here */
 static unsigned int bigsmp_cpu_mask_to_apicid(const struct cpumask *cpumask)
 {
-	return bigsmp_cpu_to_logical_apicid(cpumask_first(cpumask));
+	int cpu = cpumask_first(cpumask);
+
+	if (cpu < nr_cpu_ids)
+		return cpu_physical_id(cpu);
+	return BAD_APICID;
 }
 
 static unsigned int bigsmp_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
@@ -129,9 +126,9 @@ static unsigned int bigsmp_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
 	 */
 	for_each_cpu_and(cpu, cpumask, andmask) {
 		if (cpumask_test_cpu(cpu, cpu_online_mask))
-			break;
+			return cpu_physical_id(cpu);
 	}
-	return bigsmp_cpu_to_logical_apicid(cpu);
+	return BAD_APICID;
 }
 
 static int bigsmp_phys_pkg_id(int cpuid_apic, int index_msb)
@@ -219,8 +216,6 @@ struct apic apic_bigsmp = {
 	.ioapic_phys_id_map		= bigsmp_ioapic_phys_id_map,
 	.setup_apic_routing		= bigsmp_setup_apic_routing,
 	.multi_timer_check		= NULL,
-	.apicid_to_node			= bigsmp_apicid_to_node,
-	.cpu_to_logical_apicid		= bigsmp_cpu_to_logical_apicid,
 	.cpu_present_to_apicid		= bigsmp_cpu_present_to_apicid,
 	.apicid_to_cpu_present		= physid_set_mask_of_physid,
 	.setup_portio_remap		= NULL,
@@ -256,4 +251,7 @@ struct apic apic_bigsmp = {
 	.icr_write			= native_apic_icr_write,
 	.wait_icr_idle			= native_apic_wait_icr_idle,
 	.safe_wait_icr_idle		= native_safe_apic_wait_icr_idle,
+
+	.x86_32_early_logical_apicid	= bigsmp_early_logical_apicid,
+	.x86_32_numa_cpu_node		= default_x86_32_numa_cpu_node,
 };
diff --git a/arch/x86/kernel/apic/es7000_32.c b/arch/x86/kernel/apic/es7000_32.c
index 8593582d8022..3e9de4854c5b 100644
--- a/arch/x86/kernel/apic/es7000_32.c
+++ b/arch/x86/kernel/apic/es7000_32.c
@@ -460,6 +460,12 @@ static unsigned long es7000_check_apicid_present(int bit)
 	return physid_isset(bit, phys_cpu_present_map);
 }
 
+static int es7000_early_logical_apicid(int cpu)
+{
+	/* on es7000, logical apicid is the same as physical */
+	return early_per_cpu(x86_bios_cpu_apicid, cpu);
+}
+
 static unsigned long calculate_ldr(int cpu)
 {
 	unsigned long id = per_cpu(x86_bios_cpu_apicid, cpu);
@@ -504,12 +510,11 @@ static void es7000_setup_apic_routing(void)
 		nr_ioapics, cpumask_bits(es7000_target_cpus())[0]);
 }
 
-static int es7000_apicid_to_node(int logical_apicid)
+static int es7000_numa_cpu_node(int cpu)
 {
 	return 0;
 }
 
-
 static int es7000_cpu_present_to_apicid(int mps_cpu)
 {
 	if (!mps_cpu)
@@ -528,18 +533,6 @@ static void es7000_apicid_to_cpu_present(int phys_apicid, physid_mask_t *retmap)
 	++cpu_id;
 }
 
-/* Mapping from cpu number to logical apicid */
-static int es7000_cpu_to_logical_apicid(int cpu)
-{
-#ifdef CONFIG_SMP
-	if (cpu >= nr_cpu_ids)
-		return BAD_APICID;
-	return cpu_2_logical_apicid[cpu];
-#else
-	return logical_smp_processor_id();
-#endif
-}
-
 static void es7000_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask_t *retmap)
 {
 	/* For clustered we don't have a good way to do this yet - hack */
@@ -561,7 +554,7 @@ static unsigned int es7000_cpu_mask_to_apicid(const struct cpumask *cpumask)
 	 * The cpus in the mask must all be on the apic cluster.
 	 */
 	for_each_cpu(cpu, cpumask) {
-		int new_apicid = es7000_cpu_to_logical_apicid(cpu);
+		int new_apicid = early_per_cpu(x86_cpu_to_logical_apicid, cpu);
 
 		if (round && APIC_CLUSTER(apicid) != APIC_CLUSTER(new_apicid)) {
 			WARN(1, "Not a valid mask!");
@@ -578,7 +571,7 @@ static unsigned int
 es7000_cpu_mask_to_apicid_and(const struct cpumask *inmask,
 			      const struct cpumask *andmask)
 {
-	int apicid = es7000_cpu_to_logical_apicid(0);
+	int apicid = early_per_cpu(x86_cpu_to_logical_apicid, 0);
 	cpumask_var_t cpumask;
 
 	if (!alloc_cpumask_var(&cpumask, GFP_ATOMIC))
@@ -655,8 +648,6 @@ struct apic __refdata apic_es7000_cluster = {
 	.ioapic_phys_id_map		= es7000_ioapic_phys_id_map,
 	.setup_apic_routing		= es7000_setup_apic_routing,
 	.multi_timer_check		= NULL,
-	.apicid_to_node			= es7000_apicid_to_node,
-	.cpu_to_logical_apicid		= es7000_cpu_to_logical_apicid,
 	.cpu_present_to_apicid		= es7000_cpu_present_to_apicid,
 	.apicid_to_cpu_present		= es7000_apicid_to_cpu_present,
 	.setup_portio_remap		= NULL,
@@ -695,6 +686,9 @@ struct apic __refdata apic_es7000_cluster = {
 	.icr_write			= native_apic_icr_write,
 	.wait_icr_idle			= native_apic_wait_icr_idle,
 	.safe_wait_icr_idle		= native_safe_apic_wait_icr_idle,
+
+	.x86_32_early_logical_apicid	= es7000_early_logical_apicid,
+	.x86_32_numa_cpu_node		= es7000_numa_cpu_node,
 };
 
 struct apic __refdata apic_es7000 = {
@@ -720,8 +714,6 @@ struct apic __refdata apic_es7000 = {
 	.ioapic_phys_id_map		= es7000_ioapic_phys_id_map,
 	.setup_apic_routing		= es7000_setup_apic_routing,
 	.multi_timer_check		= NULL,
-	.apicid_to_node			= es7000_apicid_to_node,
-	.cpu_to_logical_apicid		= es7000_cpu_to_logical_apicid,
 	.cpu_present_to_apicid		= es7000_cpu_present_to_apicid,
 	.apicid_to_cpu_present		= es7000_apicid_to_cpu_present,
 	.setup_portio_remap		= NULL,
@@ -758,4 +750,7 @@ struct apic __refdata apic_es7000 = {
 	.icr_write			= native_apic_icr_write,
 	.wait_icr_idle			= native_apic_wait_icr_idle,
 	.safe_wait_icr_idle		= native_safe_apic_wait_icr_idle,
+
+	.x86_32_early_logical_apicid	= es7000_early_logical_apicid,
+	.x86_32_numa_cpu_node		= es7000_numa_cpu_node,
 };
diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c
index 79fd43ca6f96..c4e557a1ebb6 100644
--- a/arch/x86/kernel/apic/hw_nmi.c
+++ b/arch/x86/kernel/apic/hw_nmi.c
@@ -83,7 +83,6 @@ arch_trigger_all_cpu_backtrace_handler(struct notifier_block *self,
 		arch_spin_lock(&lock);
 		printk(KERN_WARNING "NMI backtrace for cpu %d\n", cpu);
 		show_regs(regs);
-		dump_stack();
 		arch_spin_unlock(&lock);
 		cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask));
 		return NOTIFY_STOP;
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index ca9e2a3545a9..4b5ebd26f565 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -108,7 +108,10 @@ DECLARE_BITMAP(mp_bus_not_pci, MAX_MP_BUSSES);
 
 int skip_ioapic_setup;
 
-void arch_disable_smp_support(void)
+/**
+ * disable_ioapic_support() - disables ioapic support at runtime
+ */
+void disable_ioapic_support(void)
 {
 #ifdef CONFIG_PCI
 	noioapicquirk = 1;
@@ -120,11 +123,14 @@ void arch_disable_smp_support(void)
 static int __init parse_noapic(char *str)
 {
 	/* disable IO-APIC */
-	arch_disable_smp_support();
+	disable_ioapic_support();
 	return 0;
 }
 early_param("noapic", parse_noapic);
 
+static int io_apic_setup_irq_pin_once(unsigned int irq, int node,
+				      struct io_apic_irq_attr *attr);
+
 /* Will be called in mpparse/acpi/sfi codes for saving IRQ info */
 void mp_save_irq(struct mpc_intsrc *m)
 {
@@ -181,7 +187,7 @@ int __init arch_early_irq_init(void)
 	irq_reserve_irqs(0, legacy_pic->nr_legacy_irqs);
 
 	for (i = 0; i < count; i++) {
-		set_irq_chip_data(i, &cfg[i]);
+		irq_set_chip_data(i, &cfg[i]);
 		zalloc_cpumask_var_node(&cfg[i].domain, GFP_KERNEL, node);
 		zalloc_cpumask_var_node(&cfg[i].old_domain, GFP_KERNEL, node);
 		/*
@@ -200,7 +206,7 @@ int __init arch_early_irq_init(void)
 #ifdef CONFIG_SPARSE_IRQ
 static struct irq_cfg *irq_cfg(unsigned int irq)
 {
-	return get_irq_chip_data(irq);
+	return irq_get_chip_data(irq);
 }
 
 static struct irq_cfg *alloc_irq_cfg(unsigned int irq, int node)
@@ -226,7 +232,7 @@ static void free_irq_cfg(unsigned int at, struct irq_cfg *cfg)
 {
 	if (!cfg)
 		return;
-	set_irq_chip_data(at, NULL);
+	irq_set_chip_data(at, NULL);
 	free_cpumask_var(cfg->domain);
 	free_cpumask_var(cfg->old_domain);
 	kfree(cfg);
@@ -256,14 +262,14 @@ static struct irq_cfg *alloc_irq_and_cfg_at(unsigned int at, int node)
 	if (res < 0) {
 		if (res != -EEXIST)
 			return NULL;
-		cfg = get_irq_chip_data(at);
+		cfg = irq_get_chip_data(at);
 		if (cfg)
 			return cfg;
 	}
 
 	cfg = alloc_irq_cfg(at, node);
 	if (cfg)
-		set_irq_chip_data(at, cfg);
+		irq_set_chip_data(at, cfg);
 	else
 		irq_free_desc(at);
 	return cfg;
@@ -818,7 +824,7 @@ static int EISA_ELCR(unsigned int irq)
 #define default_MCA_trigger(idx)	(1)
 #define default_MCA_polarity(idx)	default_ISA_polarity(idx)
 
-static int MPBIOS_polarity(int idx)
+static int irq_polarity(int idx)
 {
 	int bus = mp_irqs[idx].srcbus;
 	int polarity;
@@ -860,7 +866,7 @@ static int MPBIOS_polarity(int idx)
 	return polarity;
 }
 
-static int MPBIOS_trigger(int idx)
+static int irq_trigger(int idx)
 {
 	int bus = mp_irqs[idx].srcbus;
 	int trigger;
@@ -932,16 +938,6 @@ static int MPBIOS_trigger(int idx)
 	return trigger;
 }
 
-static inline int irq_polarity(int idx)
-{
-	return MPBIOS_polarity(idx);
-}
-
-static inline int irq_trigger(int idx)
-{
-	return MPBIOS_trigger(idx);
-}
-
 static int pin_2_irq(int idx, int apic, int pin)
 {
 	int irq;
@@ -1189,7 +1185,7 @@ void __setup_vector_irq(int cpu)
 	raw_spin_lock(&vector_lock);
 	/* Mark the inuse vectors */
 	for_each_active_irq(irq) {
-		cfg = get_irq_chip_data(irq);
+		cfg = irq_get_chip_data(irq);
 		if (!cfg)
 			continue;
 		/*
@@ -1220,10 +1216,6 @@ void __setup_vector_irq(int cpu)
 static struct irq_chip ioapic_chip;
 static struct irq_chip ir_ioapic_chip;
 
-#define IOAPIC_AUTO     -1
-#define IOAPIC_EDGE     0
-#define IOAPIC_LEVEL    1
-
 #ifdef CONFIG_X86_32
 static inline int IO_APIC_irq_trigger(int irq)
 {
@@ -1248,35 +1240,31 @@ static inline int IO_APIC_irq_trigger(int irq)
 }
 #endif
 
-static void ioapic_register_intr(unsigned int irq, unsigned long trigger)
+static void ioapic_register_intr(unsigned int irq, struct irq_cfg *cfg,
+				 unsigned long trigger)
 {
+	struct irq_chip *chip = &ioapic_chip;
+	irq_flow_handler_t hdl;
+	bool fasteoi;
 
 	if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) ||
-	    trigger == IOAPIC_LEVEL)
+	    trigger == IOAPIC_LEVEL) {
 		irq_set_status_flags(irq, IRQ_LEVEL);
-	else
+		fasteoi = true;
+	} else {
 		irq_clear_status_flags(irq, IRQ_LEVEL);
+		fasteoi = false;
+	}
 
-	if (irq_remapped(get_irq_chip_data(irq))) {
+	if (irq_remapped(cfg)) {
 		irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
-		if (trigger)
-			set_irq_chip_and_handler_name(irq, &ir_ioapic_chip,
-						      handle_fasteoi_irq,
-						     "fasteoi");
-		else
-			set_irq_chip_and_handler_name(irq, &ir_ioapic_chip,
-						      handle_edge_irq, "edge");
-		return;
+		chip = &ir_ioapic_chip;
+		fasteoi = trigger != 0;
 	}
 
-	if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) ||
-	    trigger == IOAPIC_LEVEL)
-		set_irq_chip_and_handler_name(irq, &ioapic_chip,
-					      handle_fasteoi_irq,
-					      "fasteoi");
-	else
-		set_irq_chip_and_handler_name(irq, &ioapic_chip,
-					      handle_edge_irq, "edge");
+	hdl = fasteoi ? handle_fasteoi_irq : handle_edge_irq;
+	irq_set_chip_and_handler_name(irq, chip, hdl,
+				      fasteoi ? "fasteoi" : "edge");
 }
 
 static int setup_ioapic_entry(int apic_id, int irq,
@@ -1374,7 +1362,7 @@ static void setup_ioapic_irq(int apic_id, int pin, unsigned int irq,
 		return;
 	}
 
-	ioapic_register_intr(irq, trigger);
+	ioapic_register_intr(irq, cfg, trigger);
 	if (irq < legacy_pic->nr_legacy_irqs)
 		legacy_pic->mask(irq);
 
@@ -1385,33 +1373,26 @@ static struct {
 	DECLARE_BITMAP(pin_programmed, MP_MAX_IOAPIC_PIN + 1);
 } mp_ioapic_routing[MAX_IO_APICS];
 
-static void __init setup_IO_APIC_irqs(void)
+static bool __init io_apic_pin_not_connected(int idx, int apic_id, int pin)
 {
-	int apic_id, pin, idx, irq, notcon = 0;
-	int node = cpu_to_node(0);
-	struct irq_cfg *cfg;
+	if (idx != -1)
+		return false;
 
-	apic_printk(APIC_VERBOSE, KERN_DEBUG "init IO_APIC IRQs\n");
+	apic_printk(APIC_VERBOSE, KERN_DEBUG " apic %d pin %d not connected\n",
+		    mp_ioapics[apic_id].apicid, pin);
+	return true;
+}
+
+static void __init __io_apic_setup_irqs(unsigned int apic_id)
+{
+	int idx, node = cpu_to_node(0);
+	struct io_apic_irq_attr attr;
+	unsigned int pin, irq;
 
-	for (apic_id = 0; apic_id < nr_ioapics; apic_id++)
 	for (pin = 0; pin < nr_ioapic_registers[apic_id]; pin++) {
 		idx = find_irq_entry(apic_id, pin, mp_INT);
-		if (idx == -1) {
-			if (!notcon) {
-				notcon = 1;
-				apic_printk(APIC_VERBOSE,
-					KERN_DEBUG " %d-%d",
-					mp_ioapics[apic_id].apicid, pin);
-			} else
-				apic_printk(APIC_VERBOSE, " %d-%d",
-					mp_ioapics[apic_id].apicid, pin);
+		if (io_apic_pin_not_connected(idx, apic_id, pin))
 			continue;
-		}
-		if (notcon) {
-			apic_printk(APIC_VERBOSE,
-				" (apicid-pin) not connected\n");
-			notcon = 0;
-		}
 
 		irq = pin_2_irq(idx, apic_id, pin);
 
@@ -1423,25 +1404,24 @@ static void __init setup_IO_APIC_irqs(void)
 		 * installed and if it returns 1:
 		 */
 		if (apic->multi_timer_check &&
-				apic->multi_timer_check(apic_id, irq))
+		    apic->multi_timer_check(apic_id, irq))
 			continue;
 
-		cfg = alloc_irq_and_cfg_at(irq, node);
-		if (!cfg)
-			continue;
+		set_io_apic_irq_attr(&attr, apic_id, pin, irq_trigger(idx),
+				     irq_polarity(idx));
 
-		add_pin_to_irq_node(cfg, node, apic_id, pin);
-		/*
-		 * don't mark it in pin_programmed, so later acpi could
-		 * set it correctly when irq < 16
-		 */
-		setup_ioapic_irq(apic_id, pin, irq, cfg, irq_trigger(idx),
-				  irq_polarity(idx));
+		io_apic_setup_irq_pin(irq, node, &attr);
 	}
+}
 
-	if (notcon)
-		apic_printk(APIC_VERBOSE,
-			" (apicid-pin) not connected\n");
+static void __init setup_IO_APIC_irqs(void)
+{
+	unsigned int apic_id;
+
+	apic_printk(APIC_VERBOSE, KERN_DEBUG "init IO_APIC IRQs\n");
+
+	for (apic_id = 0; apic_id < nr_ioapics; apic_id++)
+		__io_apic_setup_irqs(apic_id);
 }
 
 /*
@@ -1452,7 +1432,7 @@ static void __init setup_IO_APIC_irqs(void)
 void setup_IO_APIC_irq_extra(u32 gsi)
 {
 	int apic_id = 0, pin, idx, irq, node = cpu_to_node(0);
-	struct irq_cfg *cfg;
+	struct io_apic_irq_attr attr;
 
 	/*
 	 * Convert 'gsi' to 'ioapic.pin'.
@@ -1472,21 +1452,10 @@ void setup_IO_APIC_irq_extra(u32 gsi)
 	if (apic_id == 0 || irq < NR_IRQS_LEGACY)
 		return;
 
-	cfg = alloc_irq_and_cfg_at(irq, node);
-	if (!cfg)
-		return;
-
-	add_pin_to_irq_node(cfg, node, apic_id, pin);
-
-	if (test_bit(pin, mp_ioapic_routing[apic_id].pin_programmed)) {
-		pr_debug("Pin %d-%d already programmed\n",
-			 mp_ioapics[apic_id].apicid, pin);
-		return;
-	}
-	set_bit(pin, mp_ioapic_routing[apic_id].pin_programmed);
+	set_io_apic_irq_attr(&attr, apic_id, pin, irq_trigger(idx),
+			     irq_polarity(idx));
 
-	setup_ioapic_irq(apic_id, pin, irq, cfg,
-			irq_trigger(idx), irq_polarity(idx));
+	io_apic_setup_irq_pin_once(irq, node, &attr);
 }
 
 /*
@@ -1518,7 +1487,8 @@ static void __init setup_timer_IRQ0_pin(unsigned int apic_id, unsigned int pin,
 	 * The timer IRQ doesn't have to know that behind the
 	 * scene we may have a 8259A-master in AEOI mode ...
 	 */
-	set_irq_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq, "edge");
+	irq_set_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq,
+				      "edge");
 
 	/*
 	 * Add it to the IO-APIC irq-routing table:
@@ -1625,7 +1595,7 @@ __apicdebuginit(void) print_IO_APIC(void)
 	for_each_active_irq(irq) {
 		struct irq_pin_list *entry;
 
-		cfg = get_irq_chip_data(irq);
+		cfg = irq_get_chip_data(irq);
 		if (!cfg)
 			continue;
 		entry = cfg->irq_2_pin;
@@ -2391,7 +2361,7 @@ static void irq_complete_move(struct irq_cfg *cfg)
 
 void irq_force_complete_move(int irq)
 {
-	struct irq_cfg *cfg = get_irq_chip_data(irq);
+	struct irq_cfg *cfg = irq_get_chip_data(irq);
 
 	if (!cfg)
 		return;
@@ -2405,7 +2375,7 @@ static inline void irq_complete_move(struct irq_cfg *cfg) { }
 static void ack_apic_edge(struct irq_data *data)
 {
 	irq_complete_move(data->chip_data);
-	move_native_irq(data->irq);
+	irq_move_irq(data);
 	ack_APIC_irq();
 }
 
@@ -2462,7 +2432,7 @@ static void ack_apic_level(struct irq_data *data)
 	irq_complete_move(cfg);
 #ifdef CONFIG_GENERIC_PENDING_IRQ
 	/* If we are moving the irq we need to mask it */
-	if (unlikely(irq_to_desc(irq)->status & IRQ_MOVE_PENDING)) {
+	if (unlikely(irqd_is_setaffinity_pending(data))) {
 		do_unmask_irq = 1;
 		mask_ioapic(cfg);
 	}
@@ -2551,7 +2521,7 @@ static void ack_apic_level(struct irq_data *data)
 		 * and you can go talk to the chipset vendor about it.
 		 */
 		if (!io_apic_level_ack_pending(cfg))
-			move_masked_irq(irq);
+			irq_move_masked_irq(data);
 		unmask_ioapic(cfg);
 	}
 }
@@ -2614,7 +2584,7 @@ static inline void init_IO_APIC_traps(void)
 	 * 0x80, because int 0x80 is hm, kind of importantish. ;)
 	 */
 	for_each_active_irq(irq) {
-		cfg = get_irq_chip_data(irq);
+		cfg = irq_get_chip_data(irq);
 		if (IO_APIC_IRQ(irq) && cfg && !cfg->vector) {
 			/*
 			 * Hmm.. We don't have an entry for this,
@@ -2625,7 +2595,7 @@ static inline void init_IO_APIC_traps(void)
 				legacy_pic->make_irq(irq);
 			else
 				/* Strange. Oh, well.. */
-				set_irq_chip(irq, &no_irq_chip);
+				irq_set_chip(irq, &no_irq_chip);
 		}
 	}
 }
@@ -2665,7 +2635,7 @@ static struct irq_chip lapic_chip __read_mostly = {
 static void lapic_register_intr(int irq)
 {
 	irq_clear_status_flags(irq, IRQ_LEVEL);
-	set_irq_chip_and_handler_name(irq, &lapic_chip, handle_edge_irq,
+	irq_set_chip_and_handler_name(irq, &lapic_chip, handle_edge_irq,
 				      "edge");
 }
 
@@ -2749,7 +2719,7 @@ int timer_through_8259 __initdata;
  */
 static inline void __init check_timer(void)
 {
-	struct irq_cfg *cfg = get_irq_chip_data(0);
+	struct irq_cfg *cfg = irq_get_chip_data(0);
 	int node = cpu_to_node(0);
 	int apic1, pin1, apic2, pin2;
 	unsigned long flags;
@@ -3060,7 +3030,7 @@ unsigned int create_irq_nr(unsigned int from, int node)
 	raw_spin_unlock_irqrestore(&vector_lock, flags);
 
 	if (ret) {
-		set_irq_chip_data(irq, cfg);
+		irq_set_chip_data(irq, cfg);
 		irq_clear_status_flags(irq, IRQ_NOREQUEST);
 	} else {
 		free_irq_at(irq, cfg);
@@ -3085,7 +3055,7 @@ int create_irq(void)
 
 void destroy_irq(unsigned int irq)
 {
-	struct irq_cfg *cfg = get_irq_chip_data(irq);
+	struct irq_cfg *cfg = irq_get_chip_data(irq);
 	unsigned long flags;
 
 	irq_set_status_flags(irq, IRQ_NOREQUEST|IRQ_NOPROBE);
@@ -3119,7 +3089,7 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq,
 
 	dest = apic->cpu_mask_to_apicid_and(cfg->domain, apic->target_cpus());
 
-	if (irq_remapped(get_irq_chip_data(irq))) {
+	if (irq_remapped(cfg)) {
 		struct irte irte;
 		int ir_index;
 		u16 sub_handle;
@@ -3291,6 +3261,7 @@ static int msi_alloc_irte(struct pci_dev *dev, int irq, int nvec)
 
 static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int irq)
 {
+	struct irq_chip *chip = &msi_chip;
 	struct msi_msg msg;
 	int ret;
 
@@ -3298,14 +3269,15 @@ static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int irq)
 	if (ret < 0)
 		return ret;
 
-	set_irq_msi(irq, msidesc);
+	irq_set_msi_desc(irq, msidesc);
 	write_msi_msg(irq, &msg);
 
-	if (irq_remapped(get_irq_chip_data(irq))) {
+	if (irq_remapped(irq_get_chip_data(irq))) {
 		irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
-		set_irq_chip_and_handler_name(irq, &msi_ir_chip, handle_edge_irq, "edge");
-	} else
-		set_irq_chip_and_handler_name(irq, &msi_chip, handle_edge_irq, "edge");
+		chip = &msi_ir_chip;
+	}
+
+	irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge");
 
 	dev_printk(KERN_DEBUG, &dev->dev, "irq %d for MSI/MSI-X\n", irq);
 
@@ -3423,8 +3395,8 @@ int arch_setup_dmar_msi(unsigned int irq)
 	if (ret < 0)
 		return ret;
 	dmar_msi_write(irq, &msg);
-	set_irq_chip_and_handler_name(irq, &dmar_msi_type, handle_edge_irq,
-		"edge");
+	irq_set_chip_and_handler_name(irq, &dmar_msi_type, handle_edge_irq,
+				      "edge");
 	return 0;
 }
 #endif
@@ -3482,6 +3454,7 @@ static struct irq_chip hpet_msi_type = {
 
 int arch_setup_hpet_msi(unsigned int irq, unsigned int id)
 {
+	struct irq_chip *chip = &hpet_msi_type;
 	struct msi_msg msg;
 	int ret;
 
@@ -3501,15 +3474,12 @@ int arch_setup_hpet_msi(unsigned int irq, unsigned int id)
 	if (ret < 0)
 		return ret;
 
-	hpet_msi_write(get_irq_data(irq), &msg);
+	hpet_msi_write(irq_get_handler_data(irq), &msg);
 	irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
-	if (irq_remapped(get_irq_chip_data(irq)))
-		set_irq_chip_and_handler_name(irq, &ir_hpet_msi_type,
-					      handle_edge_irq, "edge");
-	else
-		set_irq_chip_and_handler_name(irq, &hpet_msi_type,
-					      handle_edge_irq, "edge");
+	if (irq_remapped(irq_get_chip_data(irq)))
+		chip = &ir_hpet_msi_type;
 
+	irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge");
 	return 0;
 }
 #endif
@@ -3596,7 +3566,7 @@ int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev)
 
 		write_ht_irq_msg(irq, &msg);
 
-		set_irq_chip_and_handler_name(irq, &ht_irq_chip,
+		irq_set_chip_and_handler_name(irq, &ht_irq_chip,
 					      handle_edge_irq, "edge");
 
 		dev_printk(KERN_DEBUG, &dev->dev, "irq %d for HT\n", irq);
@@ -3605,7 +3575,40 @@ int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev)
 }
 #endif /* CONFIG_HT_IRQ */
 
-int __init io_apic_get_redir_entries (int ioapic)
+int
+io_apic_setup_irq_pin(unsigned int irq, int node, struct io_apic_irq_attr *attr)
+{
+	struct irq_cfg *cfg = alloc_irq_and_cfg_at(irq, node);
+	int ret;
+
+	if (!cfg)
+		return -EINVAL;
+	ret = __add_pin_to_irq_node(cfg, node, attr->ioapic, attr->ioapic_pin);
+	if (!ret)
+		setup_ioapic_irq(attr->ioapic, attr->ioapic_pin, irq, cfg,
+				 attr->trigger, attr->polarity);
+	return ret;
+}
+
+static int io_apic_setup_irq_pin_once(unsigned int irq, int node,
+				      struct io_apic_irq_attr *attr)
+{
+	unsigned int id = attr->ioapic, pin = attr->ioapic_pin;
+	int ret;
+
+	/* Avoid redundant programming */
+	if (test_bit(pin, mp_ioapic_routing[id].pin_programmed)) {
+		pr_debug("Pin %d-%d already programmed\n",
+			 mp_ioapics[id].apicid, pin);
+		return 0;
+	}
+	ret = io_apic_setup_irq_pin(irq, node, attr);
+	if (!ret)
+		set_bit(pin, mp_ioapic_routing[id].pin_programmed);
+	return ret;
+}
+
+static int __init io_apic_get_redir_entries(int ioapic)
 {
 	union IO_APIC_reg_01	reg_01;
 	unsigned long flags;
@@ -3659,96 +3662,24 @@ int __init arch_probe_nr_irqs(void)
 }
 #endif
 
-static int __io_apic_set_pci_routing(struct device *dev, int irq,
-				struct io_apic_irq_attr *irq_attr)
+int io_apic_set_pci_routing(struct device *dev, int irq,
+			    struct io_apic_irq_attr *irq_attr)
 {
-	struct irq_cfg *cfg;
 	int node;
-	int ioapic, pin;
-	int trigger, polarity;
 
-	ioapic = irq_attr->ioapic;
 	if (!IO_APIC_IRQ(irq)) {
 		apic_printk(APIC_QUIET,KERN_ERR "IOAPIC[%d]: Invalid reference to IRQ 0\n",
-			ioapic);
+			    irq_attr->ioapic);
 		return -EINVAL;
 	}
 
-	if (dev)
-		node = dev_to_node(dev);
-	else
-		node = cpu_to_node(0);
-
-	cfg = alloc_irq_and_cfg_at(irq, node);
-	if (!cfg)
-		return 0;
-
-	pin = irq_attr->ioapic_pin;
-	trigger = irq_attr->trigger;
-	polarity = irq_attr->polarity;
+	node = dev ? dev_to_node(dev) : cpu_to_node(0);
 
-	/*
-	 * IRQs < 16 are already in the irq_2_pin[] map
-	 */
-	if (irq >= legacy_pic->nr_legacy_irqs) {
-		if (__add_pin_to_irq_node(cfg, node, ioapic, pin)) {
-			printk(KERN_INFO "can not add pin %d for irq %d\n",
-				pin, irq);
-			return 0;
-		}
-	}
-
-	setup_ioapic_irq(ioapic, pin, irq, cfg, trigger, polarity);
-
-	return 0;
+	return io_apic_setup_irq_pin_once(irq, node, irq_attr);
 }
 
-int io_apic_set_pci_routing(struct device *dev, int irq,
-				struct io_apic_irq_attr *irq_attr)
-{
-	int ioapic, pin;
-	/*
-	 * Avoid pin reprogramming.  PRTs typically include entries
-	 * with redundant pin->gsi mappings (but unique PCI devices);
-	 * we only program the IOAPIC on the first.
-	 */
-	ioapic = irq_attr->ioapic;
-	pin = irq_attr->ioapic_pin;
-	if (test_bit(pin, mp_ioapic_routing[ioapic].pin_programmed)) {
-		pr_debug("Pin %d-%d already programmed\n",
-			 mp_ioapics[ioapic].apicid, pin);
-		return 0;
-	}
-	set_bit(pin, mp_ioapic_routing[ioapic].pin_programmed);
-
-	return __io_apic_set_pci_routing(dev, irq, irq_attr);
-}
-
-u8 __init io_apic_unique_id(u8 id)
-{
 #ifdef CONFIG_X86_32
-	if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) &&
-	    !APIC_XAPIC(apic_version[boot_cpu_physical_apicid]))
-		return io_apic_get_unique_id(nr_ioapics, id);
-	else
-		return id;
-#else
-	int i;
-	DECLARE_BITMAP(used, 256);
-
-	bitmap_zero(used, 256);
-	for (i = 0; i < nr_ioapics; i++) {
-		struct mpc_ioapic *ia = &mp_ioapics[i];
-		__set_bit(ia->apicid, used);
-	}
-	if (!test_bit(id, used))
-		return id;
-	return find_first_zero_bit(used, 256);
-#endif
-}
-
-#ifdef CONFIG_X86_32
-int __init io_apic_get_unique_id(int ioapic, int apic_id)
+static int __init io_apic_get_unique_id(int ioapic, int apic_id)
 {
 	union IO_APIC_reg_00 reg_00;
 	static physid_mask_t apic_id_map = PHYSID_MASK_NONE;
@@ -3821,9 +3752,33 @@ int __init io_apic_get_unique_id(int ioapic, int apic_id)
 
 	return apic_id;
 }
+
+static u8 __init io_apic_unique_id(u8 id)
+{
+	if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) &&
+	    !APIC_XAPIC(apic_version[boot_cpu_physical_apicid]))
+		return io_apic_get_unique_id(nr_ioapics, id);
+	else
+		return id;
+}
+#else
+static u8 __init io_apic_unique_id(u8 id)
+{
+	int i;
+	DECLARE_BITMAP(used, 256);
+
+	bitmap_zero(used, 256);
+	for (i = 0; i < nr_ioapics; i++) {
+		struct mpc_ioapic *ia = &mp_ioapics[i];
+		__set_bit(ia->apicid, used);
+	}
+	if (!test_bit(id, used))
+		return id;
+	return find_first_zero_bit(used, 256);
+}
 #endif
 
-int __init io_apic_get_version(int ioapic)
+static int __init io_apic_get_version(int ioapic)
 {
 	union IO_APIC_reg_01	reg_01;
 	unsigned long flags;
@@ -3868,8 +3823,8 @@ int acpi_get_override_irq(u32 gsi, int *trigger, int *polarity)
 void __init setup_ioapic_dest(void)
 {
 	int pin, ioapic, irq, irq_entry;
-	struct irq_desc *desc;
 	const struct cpumask *mask;
+	struct irq_data *idata;
 
 	if (skip_ioapic_setup == 1)
 		return;
@@ -3884,21 +3839,20 @@ void __init setup_ioapic_dest(void)
 		if ((ioapic > 0) && (irq > 16))
 			continue;
 
-		desc = irq_to_desc(irq);
+		idata = irq_get_irq_data(irq);
 
 		/*
 		 * Honour affinities which have been set in early boot
 		 */
-		if (desc->status &
-		    (IRQ_NO_BALANCING | IRQ_AFFINITY_SET))
-			mask = desc->irq_data.affinity;
+		if (!irqd_can_balance(idata) || irqd_affinity_was_set(idata))
+			mask = idata->affinity;
 		else
 			mask = apic->target_cpus();
 
 		if (intr_remapping_enabled)
-			ir_ioapic_set_affinity(&desc->irq_data, mask, false);
+			ir_ioapic_set_affinity(idata, mask, false);
 		else
-			ioapic_set_affinity(&desc->irq_data, mask, false);
+			ioapic_set_affinity(idata, mask, false);
 	}
 
 }
@@ -4026,7 +3980,7 @@ int mp_find_ioapic_pin(int ioapic, u32 gsi)
 	return gsi - mp_gsi_routing[ioapic].gsi_base;
 }
 
-static int bad_ioapic(unsigned long address)
+static __init int bad_ioapic(unsigned long address)
 {
 	if (nr_ioapics >= MAX_IO_APICS) {
 		printk(KERN_WARNING "WARING: Max # of I/O APICs (%d) exceeded "
@@ -4086,20 +4040,16 @@ void __init mp_register_ioapic(int id, u32 address, u32 gsi_base)
 /* Enable IOAPIC early just for system timer */
 void __init pre_init_apic_IRQ0(void)
 {
-	struct irq_cfg *cfg;
+	struct io_apic_irq_attr attr = { 0, 0, 0, 0 };
 
 	printk(KERN_INFO "Early APIC setup for system timer0\n");
 #ifndef CONFIG_SMP
 	physid_set_mask_of_physid(boot_cpu_physical_apicid,
 					 &phys_cpu_present_map);
 #endif
-	/* Make sure the irq descriptor is set up */
-	cfg = alloc_irq_and_cfg_at(0, 0);
-
 	setup_local_APIC();
 
-	add_pin_to_irq_node(cfg, 0, 0, 0);
-	set_irq_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq, "edge");
-
-	setup_ioapic_irq(0, 0, 0, cfg, 0, 0);
+	io_apic_setup_irq_pin(0, 0, &attr);
+	irq_set_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq,
+				      "edge");
 }
diff --git a/arch/x86/kernel/apic/ipi.c b/arch/x86/kernel/apic/ipi.c
index 08385e090a6f..cce91bf26676 100644
--- a/arch/x86/kernel/apic/ipi.c
+++ b/arch/x86/kernel/apic/ipi.c
@@ -56,6 +56,8 @@ void default_send_IPI_mask_allbutself_phys(const struct cpumask *mask,
 	local_irq_restore(flags);
 }
 
+#ifdef CONFIG_X86_32
+
 void default_send_IPI_mask_sequence_logical(const struct cpumask *mask,
 						 int vector)
 {
@@ -71,8 +73,8 @@ void default_send_IPI_mask_sequence_logical(const struct cpumask *mask,
 	local_irq_save(flags);
 	for_each_cpu(query_cpu, mask)
 		__default_send_IPI_dest_field(
-			apic->cpu_to_logical_apicid(query_cpu), vector,
-			apic->dest_logical);
+			early_per_cpu(x86_cpu_to_logical_apicid, query_cpu),
+			vector, apic->dest_logical);
 	local_irq_restore(flags);
 }
 
@@ -90,14 +92,12 @@ void default_send_IPI_mask_allbutself_logical(const struct cpumask *mask,
 		if (query_cpu == this_cpu)
 			continue;
 		__default_send_IPI_dest_field(
-			apic->cpu_to_logical_apicid(query_cpu), vector,
-			apic->dest_logical);
+			early_per_cpu(x86_cpu_to_logical_apicid, query_cpu),
+			vector, apic->dest_logical);
 		}
 	local_irq_restore(flags);
 }
 
-#ifdef CONFIG_X86_32
-
 /*
  * This is only used on smaller machines.
  */
diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c
index 960f26ab5c9f..6273eee5134b 100644
--- a/arch/x86/kernel/apic/numaq_32.c
+++ b/arch/x86/kernel/apic/numaq_32.c
@@ -373,13 +373,6 @@ static inline void numaq_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask
 	return physids_promote(0xFUL, retmap);
 }
 
-static inline int numaq_cpu_to_logical_apicid(int cpu)
-{
-	if (cpu >= nr_cpu_ids)
-		return BAD_APICID;
-	return cpu_2_logical_apicid[cpu];
-}
-
 /*
  * Supporting over 60 cpus on NUMA-Q requires a locality-dependent
  * cpu to APIC ID relation to properly interact with the intelligent
@@ -398,6 +391,15 @@ static inline int numaq_apicid_to_node(int logical_apicid)
 	return logical_apicid >> 4;
 }
 
+static int numaq_numa_cpu_node(int cpu)
+{
+	int logical_apicid = early_per_cpu(x86_cpu_to_logical_apicid, cpu);
+
+	if (logical_apicid != BAD_APICID)
+		return numaq_apicid_to_node(logical_apicid);
+	return NUMA_NO_NODE;
+}
+
 static void numaq_apicid_to_cpu_present(int logical_apicid, physid_mask_t *retmap)
 {
 	int node = numaq_apicid_to_node(logical_apicid);
@@ -508,8 +510,6 @@ struct apic __refdata apic_numaq = {
 	.ioapic_phys_id_map		= numaq_ioapic_phys_id_map,
 	.setup_apic_routing		= numaq_setup_apic_routing,
 	.multi_timer_check		= numaq_multi_timer_check,
-	.apicid_to_node			= numaq_apicid_to_node,
-	.cpu_to_logical_apicid		= numaq_cpu_to_logical_apicid,
 	.cpu_present_to_apicid		= numaq_cpu_present_to_apicid,
 	.apicid_to_cpu_present		= numaq_apicid_to_cpu_present,
 	.setup_portio_remap		= numaq_setup_portio_remap,
@@ -547,4 +547,7 @@ struct apic __refdata apic_numaq = {
 	.icr_write			= native_apic_icr_write,
 	.wait_icr_idle			= native_apic_wait_icr_idle,
 	.safe_wait_icr_idle		= native_safe_apic_wait_icr_idle,
+
+	.x86_32_early_logical_apicid	= noop_x86_32_early_logical_apicid,
+	.x86_32_numa_cpu_node		= numaq_numa_cpu_node,
 };
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index 99d2fe016084..fc84c7b61108 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -77,6 +77,11 @@ void __init default_setup_apic_routing(void)
 		apic->setup_apic_routing();
 }
 
+static int default_x86_32_early_logical_apicid(int cpu)
+{
+	return 1 << cpu;
+}
+
 static void setup_apic_flat_routing(void)
 {
 #ifdef CONFIG_X86_IO_APIC
@@ -130,8 +135,6 @@ struct apic apic_default = {
 	.ioapic_phys_id_map		= default_ioapic_phys_id_map,
 	.setup_apic_routing		= setup_apic_flat_routing,
 	.multi_timer_check		= NULL,
-	.apicid_to_node			= default_apicid_to_node,
-	.cpu_to_logical_apicid		= default_cpu_to_logical_apicid,
 	.cpu_present_to_apicid		= default_cpu_present_to_apicid,
 	.apicid_to_cpu_present		= physid_set_mask_of_physid,
 	.setup_portio_remap		= NULL,
@@ -167,6 +170,9 @@ struct apic apic_default = {
 	.icr_write			= native_apic_icr_write,
 	.wait_icr_idle			= native_apic_wait_icr_idle,
 	.safe_wait_icr_idle		= native_safe_apic_wait_icr_idle,
+
+	.x86_32_early_logical_apicid	= default_x86_32_early_logical_apicid,
+	.x86_32_numa_cpu_node		= default_x86_32_numa_cpu_node,
 };
 
 extern struct apic apic_numaq;
diff --git a/arch/x86/kernel/apic/summit_32.c b/arch/x86/kernel/apic/summit_32.c
index 9b419263d90d..e4b8059b414a 100644
--- a/arch/x86/kernel/apic/summit_32.c
+++ b/arch/x86/kernel/apic/summit_32.c
@@ -194,11 +194,10 @@ static unsigned long summit_check_apicid_present(int bit)
 	return 1;
 }
 
-static void summit_init_apic_ldr(void)
+static int summit_early_logical_apicid(int cpu)
 {
-	unsigned long val, id;
 	int count = 0;
-	u8 my_id = (u8)hard_smp_processor_id();
+	u8 my_id = early_per_cpu(x86_cpu_to_apicid, cpu);
 	u8 my_cluster = APIC_CLUSTER(my_id);
 #ifdef CONFIG_SMP
 	u8 lid;
@@ -206,7 +205,7 @@ static void summit_init_apic_ldr(void)
 
 	/* Create logical APIC IDs by counting CPUs already in cluster. */
 	for (count = 0, i = nr_cpu_ids; --i >= 0; ) {
-		lid = cpu_2_logical_apicid[i];
+		lid = early_per_cpu(x86_cpu_to_logical_apicid, i);
 		if (lid != BAD_APICID && APIC_CLUSTER(lid) == my_cluster)
 			++count;
 	}
@@ -214,7 +213,15 @@ static void summit_init_apic_ldr(void)
 	/* We only have a 4 wide bitmap in cluster mode.  If a deranged
 	 * BIOS puts 5 CPUs in one APIC cluster, we're hosed. */
 	BUG_ON(count >= XAPIC_DEST_CPUS_SHIFT);
-	id = my_cluster | (1UL << count);
+	return my_cluster | (1UL << count);
+}
+
+static void summit_init_apic_ldr(void)
+{
+	int cpu = smp_processor_id();
+	unsigned long id = early_per_cpu(x86_cpu_to_logical_apicid, cpu);
+	unsigned long val;
+
 	apic_write(APIC_DFR, SUMMIT_APIC_DFR_VALUE);
 	val = apic_read(APIC_LDR) & ~APIC_LDR_MASK;
 	val |= SET_APIC_LOGICAL_ID(id);
@@ -232,27 +239,6 @@ static void summit_setup_apic_routing(void)
 						nr_ioapics);
 }
 
-static int summit_apicid_to_node(int logical_apicid)
-{
-#ifdef CONFIG_SMP
-	return apicid_2_node[hard_smp_processor_id()];
-#else
-	return 0;
-#endif
-}
-
-/* Mapping from cpu number to logical apicid */
-static inline int summit_cpu_to_logical_apicid(int cpu)
-{
-#ifdef CONFIG_SMP
-	if (cpu >= nr_cpu_ids)
-		return BAD_APICID;
-	return cpu_2_logical_apicid[cpu];
-#else
-	return logical_smp_processor_id();
-#endif
-}
-
 static int summit_cpu_present_to_apicid(int mps_cpu)
 {
 	if (mps_cpu < nr_cpu_ids)
@@ -286,7 +272,7 @@ static unsigned int summit_cpu_mask_to_apicid(const struct cpumask *cpumask)
 	 * The cpus in the mask must all be on the apic cluster.
 	 */
 	for_each_cpu(cpu, cpumask) {
-		int new_apicid = summit_cpu_to_logical_apicid(cpu);
+		int new_apicid = early_per_cpu(x86_cpu_to_logical_apicid, cpu);
 
 		if (round && APIC_CLUSTER(apicid) != APIC_CLUSTER(new_apicid)) {
 			printk("%s: Not a valid mask!\n", __func__);
@@ -301,7 +287,7 @@ static unsigned int summit_cpu_mask_to_apicid(const struct cpumask *cpumask)
 static unsigned int summit_cpu_mask_to_apicid_and(const struct cpumask *inmask,
 			      const struct cpumask *andmask)
 {
-	int apicid = summit_cpu_to_logical_apicid(0);
+	int apicid = early_per_cpu(x86_cpu_to_logical_apicid, 0);
 	cpumask_var_t cpumask;
 
 	if (!alloc_cpumask_var(&cpumask, GFP_ATOMIC))
@@ -528,8 +514,6 @@ struct apic apic_summit = {
 	.ioapic_phys_id_map		= summit_ioapic_phys_id_map,
 	.setup_apic_routing		= summit_setup_apic_routing,
 	.multi_timer_check		= NULL,
-	.apicid_to_node			= summit_apicid_to_node,
-	.cpu_to_logical_apicid		= summit_cpu_to_logical_apicid,
 	.cpu_present_to_apicid		= summit_cpu_present_to_apicid,
 	.apicid_to_cpu_present		= summit_apicid_to_cpu_present,
 	.setup_portio_remap		= NULL,
@@ -565,4 +549,7 @@ struct apic apic_summit = {
 	.icr_write			= native_apic_icr_write,
 	.wait_icr_idle			= native_apic_wait_icr_idle,
 	.safe_wait_icr_idle		= native_safe_apic_wait_icr_idle,
+
+	.x86_32_early_logical_apicid	= summit_early_logical_apicid,
+	.x86_32_numa_cpu_node		= default_x86_32_numa_cpu_node,
 };
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index cf69c59f4910..90949bbd566d 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -206,8 +206,6 @@ struct apic apic_x2apic_cluster = {
 	.ioapic_phys_id_map		= NULL,
 	.setup_apic_routing		= NULL,
 	.multi_timer_check		= NULL,
-	.apicid_to_node			= NULL,
-	.cpu_to_logical_apicid		= NULL,
 	.cpu_present_to_apicid		= default_cpu_present_to_apicid,
 	.apicid_to_cpu_present		= NULL,
 	.setup_portio_remap		= NULL,
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index 8972f38c5ced..c7e6d6645bf4 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -195,8 +195,6 @@ struct apic apic_x2apic_phys = {
 	.ioapic_phys_id_map		= NULL,
 	.setup_apic_routing		= NULL,
 	.multi_timer_check		= NULL,
-	.apicid_to_node			= NULL,
-	.cpu_to_logical_apicid		= NULL,
 	.cpu_present_to_apicid		= default_cpu_present_to_apicid,
 	.apicid_to_cpu_present		= NULL,
 	.setup_portio_remap		= NULL,
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index bd16b58b8850..3c289281394c 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -338,8 +338,6 @@ struct apic __refdata apic_x2apic_uv_x = {
 	.ioapic_phys_id_map		= NULL,
 	.setup_apic_routing		= NULL,
 	.multi_timer_check		= NULL,
-	.apicid_to_node			= NULL,
-	.cpu_to_logical_apicid		= NULL,
 	.cpu_present_to_apicid		= default_cpu_present_to_apicid,
 	.apicid_to_cpu_present		= NULL,
 	.setup_portio_remap		= NULL,
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index cfa82c899f47..4f13fafc5264 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -1,5 +1,70 @@
+/*
+ * Generate definitions needed by assembly language modules.
+ * This code generates raw asm output which is post-processed to extract
+ * and format the required data.
+ */
+#define COMPILE_OFFSETS
+
+#include <linux/crypto.h>
+#include <linux/sched.h>
+#include <linux/stddef.h>
+#include <linux/hardirq.h>
+#include <linux/suspend.h>
+#include <linux/kbuild.h>
+#include <asm/processor.h>
+#include <asm/thread_info.h>
+#include <asm/sigframe.h>
+#include <asm/bootparam.h>
+#include <asm/suspend.h>
+
+#ifdef CONFIG_XEN
+#include <xen/interface/xen.h>
+#endif
+
 #ifdef CONFIG_X86_32
 # include "asm-offsets_32.c"
 #else
 # include "asm-offsets_64.c"
 #endif
+
+void common(void) {
+	BLANK();
+	OFFSET(TI_flags, thread_info, flags);
+	OFFSET(TI_status, thread_info, status);
+	OFFSET(TI_addr_limit, thread_info, addr_limit);
+	OFFSET(TI_preempt_count, thread_info, preempt_count);
+
+	BLANK();
+	OFFSET(crypto_tfm_ctx_offset, crypto_tfm, __crt_ctx);
+
+	BLANK();
+	OFFSET(pbe_address, pbe, address);
+	OFFSET(pbe_orig_address, pbe, orig_address);
+	OFFSET(pbe_next, pbe, next);
+
+#ifdef CONFIG_PARAVIRT
+	BLANK();
+	OFFSET(PARAVIRT_enabled, pv_info, paravirt_enabled);
+	OFFSET(PARAVIRT_PATCH_pv_cpu_ops, paravirt_patch_template, pv_cpu_ops);
+	OFFSET(PARAVIRT_PATCH_pv_irq_ops, paravirt_patch_template, pv_irq_ops);
+	OFFSET(PV_IRQ_irq_disable, pv_irq_ops, irq_disable);
+	OFFSET(PV_IRQ_irq_enable, pv_irq_ops, irq_enable);
+	OFFSET(PV_CPU_iret, pv_cpu_ops, iret);
+	OFFSET(PV_CPU_irq_enable_sysexit, pv_cpu_ops, irq_enable_sysexit);
+	OFFSET(PV_CPU_read_cr0, pv_cpu_ops, read_cr0);
+	OFFSET(PV_MMU_read_cr2, pv_mmu_ops, read_cr2);
+#endif
+
+#ifdef CONFIG_XEN
+	BLANK();
+	OFFSET(XEN_vcpu_info_mask, vcpu_info, evtchn_upcall_mask);
+	OFFSET(XEN_vcpu_info_pending, vcpu_info, evtchn_upcall_pending);
+#endif
+
+	BLANK();
+	OFFSET(BP_scratch, boot_params, scratch);
+	OFFSET(BP_loadflags, boot_params, hdr.loadflags);
+	OFFSET(BP_hardware_subarch, boot_params, hdr.hardware_subarch);
+	OFFSET(BP_version, boot_params, hdr.version);
+	OFFSET(BP_kernel_alignment, boot_params, hdr.kernel_alignment);
+}
diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c
index 1a4088dda37a..c29d631af6fc 100644
--- a/arch/x86/kernel/asm-offsets_32.c
+++ b/arch/x86/kernel/asm-offsets_32.c
@@ -1,26 +1,4 @@
-/*
- * Generate definitions needed by assembly language modules.
- * This code generates raw asm output which is post-processed
- * to extract and format the required data.
- */
-
-#include <linux/crypto.h>
-#include <linux/sched.h>
-#include <linux/signal.h>
-#include <linux/personality.h>
-#include <linux/suspend.h>
-#include <linux/kbuild.h>
 #include <asm/ucontext.h>
-#include <asm/sigframe.h>
-#include <asm/pgtable.h>
-#include <asm/fixmap.h>
-#include <asm/processor.h>
-#include <asm/thread_info.h>
-#include <asm/bootparam.h>
-#include <asm/elf.h>
-#include <asm/suspend.h>
-
-#include <xen/interface/xen.h>
 
 #include <linux/lguest.h>
 #include "../../../drivers/lguest/lg.h"
@@ -51,21 +29,10 @@ void foo(void)
 	OFFSET(CPUINFO_x86_vendor_id, cpuinfo_x86, x86_vendor_id);
 	BLANK();
 
-	OFFSET(TI_task, thread_info, task);
-	OFFSET(TI_exec_domain, thread_info, exec_domain);
-	OFFSET(TI_flags, thread_info, flags);
-	OFFSET(TI_status, thread_info, status);
-	OFFSET(TI_preempt_count, thread_info, preempt_count);
-	OFFSET(TI_addr_limit, thread_info, addr_limit);
-	OFFSET(TI_restart_block, thread_info, restart_block);
 	OFFSET(TI_sysenter_return, thread_info, sysenter_return);
 	OFFSET(TI_cpu, thread_info, cpu);
 	BLANK();
 
-	OFFSET(GDS_size, desc_ptr, size);
-	OFFSET(GDS_address, desc_ptr, address);
-	BLANK();
-
 	OFFSET(PT_EBX, pt_regs, bx);
 	OFFSET(PT_ECX, pt_regs, cx);
 	OFFSET(PT_EDX, pt_regs, dx);
@@ -85,42 +52,13 @@ void foo(void)
 	OFFSET(PT_OLDSS,  pt_regs, ss);
 	BLANK();
 
-	OFFSET(EXEC_DOMAIN_handler, exec_domain, handler);
 	OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe, uc.uc_mcontext);
 	BLANK();
 
-	OFFSET(pbe_address, pbe, address);
-	OFFSET(pbe_orig_address, pbe, orig_address);
-	OFFSET(pbe_next, pbe, next);
-
 	/* Offset from the sysenter stack to tss.sp0 */
 	DEFINE(TSS_sysenter_sp0, offsetof(struct tss_struct, x86_tss.sp0) -
 		 sizeof(struct tss_struct));
 
-	DEFINE(PAGE_SIZE_asm, PAGE_SIZE);
-	DEFINE(PAGE_SHIFT_asm, PAGE_SHIFT);
-	DEFINE(THREAD_SIZE_asm, THREAD_SIZE);
-
-	OFFSET(crypto_tfm_ctx_offset, crypto_tfm, __crt_ctx);
-
-#ifdef CONFIG_PARAVIRT
-	BLANK();
-	OFFSET(PARAVIRT_enabled, pv_info, paravirt_enabled);
-	OFFSET(PARAVIRT_PATCH_pv_cpu_ops, paravirt_patch_template, pv_cpu_ops);
-	OFFSET(PARAVIRT_PATCH_pv_irq_ops, paravirt_patch_template, pv_irq_ops);
-	OFFSET(PV_IRQ_irq_disable, pv_irq_ops, irq_disable);
-	OFFSET(PV_IRQ_irq_enable, pv_irq_ops, irq_enable);
-	OFFSET(PV_CPU_iret, pv_cpu_ops, iret);
-	OFFSET(PV_CPU_irq_enable_sysexit, pv_cpu_ops, irq_enable_sysexit);
-	OFFSET(PV_CPU_read_cr0, pv_cpu_ops, read_cr0);
-#endif
-
-#ifdef CONFIG_XEN
-	BLANK();
-	OFFSET(XEN_vcpu_info_mask, vcpu_info, evtchn_upcall_mask);
-	OFFSET(XEN_vcpu_info_pending, vcpu_info, evtchn_upcall_pending);
-#endif
-
 #if defined(CONFIG_LGUEST) || defined(CONFIG_LGUEST_GUEST) || defined(CONFIG_LGUEST_MODULE)
 	BLANK();
 	OFFSET(LGUEST_DATA_irq_enabled, lguest_data, irq_enabled);
@@ -139,11 +77,4 @@ void foo(void)
 	OFFSET(LGUEST_PAGES_regs_errcode, lguest_pages, regs.errcode);
 	OFFSET(LGUEST_PAGES_regs, lguest_pages, regs);
 #endif
-
-	BLANK();
-	OFFSET(BP_scratch, boot_params, scratch);
-	OFFSET(BP_loadflags, boot_params, hdr.loadflags);
-	OFFSET(BP_hardware_subarch, boot_params, hdr.hardware_subarch);
-	OFFSET(BP_version, boot_params, hdr.version);
-	OFFSET(BP_kernel_alignment, boot_params, hdr.kernel_alignment);
 }
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index 4a6aeedcd965..e72a1194af22 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -1,27 +1,4 @@
-/*
- * Generate definitions needed by assembly language modules.
- * This code generates raw asm output which is post-processed to extract
- * and format the required data.
- */
-#define COMPILE_OFFSETS
-
-#include <linux/crypto.h>
-#include <linux/sched.h> 
-#include <linux/stddef.h>
-#include <linux/errno.h> 
-#include <linux/hardirq.h>
-#include <linux/suspend.h>
-#include <linux/kbuild.h>
-#include <asm/processor.h>
-#include <asm/segment.h>
-#include <asm/thread_info.h>
 #include <asm/ia32.h>
-#include <asm/bootparam.h>
-#include <asm/suspend.h>
-
-#include <xen/interface/xen.h>
-
-#include <asm/sigframe.h>
 
 #define __NO_STUBS 1
 #undef __SYSCALL
@@ -33,41 +10,19 @@ static char syscalls[] = {
 
 int main(void)
 {
-#define ENTRY(entry) DEFINE(tsk_ ## entry, offsetof(struct task_struct, entry))
-	ENTRY(state);
-	ENTRY(flags); 
-	ENTRY(pid);
-	BLANK();
-#undef ENTRY
-#define ENTRY(entry) DEFINE(TI_ ## entry, offsetof(struct thread_info, entry))
-	ENTRY(flags);
-	ENTRY(addr_limit);
-	ENTRY(preempt_count);
-	ENTRY(status);
-#ifdef CONFIG_IA32_EMULATION
-	ENTRY(sysenter_return);
-#endif
-	BLANK();
-#undef ENTRY
 #ifdef CONFIG_PARAVIRT
-	BLANK();
-	OFFSET(PARAVIRT_enabled, pv_info, paravirt_enabled);
-	OFFSET(PARAVIRT_PATCH_pv_cpu_ops, paravirt_patch_template, pv_cpu_ops);
-	OFFSET(PARAVIRT_PATCH_pv_irq_ops, paravirt_patch_template, pv_irq_ops);
-	OFFSET(PV_IRQ_irq_disable, pv_irq_ops, irq_disable);
-	OFFSET(PV_IRQ_irq_enable, pv_irq_ops, irq_enable);
 	OFFSET(PV_IRQ_adjust_exception_frame, pv_irq_ops, adjust_exception_frame);
-	OFFSET(PV_CPU_iret, pv_cpu_ops, iret);
 	OFFSET(PV_CPU_usergs_sysret32, pv_cpu_ops, usergs_sysret32);
 	OFFSET(PV_CPU_usergs_sysret64, pv_cpu_ops, usergs_sysret64);
-	OFFSET(PV_CPU_irq_enable_sysexit, pv_cpu_ops, irq_enable_sysexit);
 	OFFSET(PV_CPU_swapgs, pv_cpu_ops, swapgs);
-	OFFSET(PV_MMU_read_cr2, pv_mmu_ops, read_cr2);
+	BLANK();
 #endif
 
-
 #ifdef CONFIG_IA32_EMULATION
-#define ENTRY(entry) DEFINE(IA32_SIGCONTEXT_ ## entry, offsetof(struct sigcontext_ia32, entry))
+	OFFSET(TI_sysenter_return, thread_info, sysenter_return);
+	BLANK();
+
+#define ENTRY(entry) OFFSET(IA32_SIGCONTEXT_ ## entry, sigcontext_ia32, entry)
 	ENTRY(ax);
 	ENTRY(bx);
 	ENTRY(cx);
@@ -79,15 +34,12 @@ int main(void)
 	ENTRY(ip);
 	BLANK();
 #undef ENTRY
-	DEFINE(IA32_RT_SIGFRAME_sigcontext,
-	       offsetof (struct rt_sigframe_ia32, uc.uc_mcontext));
+
+	OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe_ia32, uc.uc_mcontext);
 	BLANK();
 #endif
-	DEFINE(pbe_address, offsetof(struct pbe, address));
-	DEFINE(pbe_orig_address, offsetof(struct pbe, orig_address));
-	DEFINE(pbe_next, offsetof(struct pbe, next));
-	BLANK();
-#define ENTRY(entry) DEFINE(pt_regs_ ## entry, offsetof(struct pt_regs, entry))
+
+#define ENTRY(entry) OFFSET(pt_regs_ ## entry, pt_regs, entry)
 	ENTRY(bx);
 	ENTRY(bx);
 	ENTRY(cx);
@@ -107,7 +59,8 @@ int main(void)
 	ENTRY(flags);
 	BLANK();
 #undef ENTRY
-#define ENTRY(entry) DEFINE(saved_context_ ## entry, offsetof(struct saved_context, entry))
+
+#define ENTRY(entry) OFFSET(saved_context_ ## entry, saved_context, entry)
 	ENTRY(cr0);
 	ENTRY(cr2);
 	ENTRY(cr3);
@@ -115,26 +68,11 @@ int main(void)
 	ENTRY(cr8);
 	BLANK();
 #undef ENTRY
-	DEFINE(TSS_ist, offsetof(struct tss_struct, x86_tss.ist));
-	BLANK();
-	DEFINE(crypto_tfm_ctx_offset, offsetof(struct crypto_tfm, __crt_ctx));
-	BLANK();
-	DEFINE(__NR_syscall_max, sizeof(syscalls) - 1);
 
+	OFFSET(TSS_ist, tss_struct, x86_tss.ist);
 	BLANK();
-	OFFSET(BP_scratch, boot_params, scratch);
-	OFFSET(BP_loadflags, boot_params, hdr.loadflags);
-	OFFSET(BP_hardware_subarch, boot_params, hdr.hardware_subarch);
-	OFFSET(BP_version, boot_params, hdr.version);
-	OFFSET(BP_kernel_alignment, boot_params, hdr.kernel_alignment);
 
-	BLANK();
-	DEFINE(PAGE_SIZE_asm, PAGE_SIZE);
-#ifdef CONFIG_XEN
-	BLANK();
-	OFFSET(XEN_vcpu_info_mask, vcpu_info, evtchn_upcall_mask);
-	OFFSET(XEN_vcpu_info_pending, vcpu_info, evtchn_upcall_pending);
-#undef ENTRY
-#endif
+	DEFINE(__NR_syscall_max, sizeof(syscalls) - 1);
+
 	return 0;
 }
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 58f1b012e1c8..3ecece0217ef 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -233,18 +233,22 @@ static void __cpuinit init_amd_k7(struct cpuinfo_x86 *c)
 }
 #endif
 
-#if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
+#ifdef CONFIG_NUMA
+/*
+ * To workaround broken NUMA config.  Read the comment in
+ * srat_detect_node().
+ */
 static int __cpuinit nearby_node(int apicid)
 {
 	int i, node;
 
 	for (i = apicid - 1; i >= 0; i--) {
-		node = apicid_to_node[i];
+		node = __apicid_to_node[i];
 		if (node != NUMA_NO_NODE && node_online(node))
 			return node;
 	}
 	for (i = apicid + 1; i < MAX_LOCAL_APIC; i++) {
-		node = apicid_to_node[i];
+		node = __apicid_to_node[i];
 		if (node != NUMA_NO_NODE && node_online(node))
 			return node;
 	}
@@ -338,31 +342,40 @@ EXPORT_SYMBOL_GPL(amd_get_nb_id);
 
 static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c)
 {
-#if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
+#ifdef CONFIG_NUMA
 	int cpu = smp_processor_id();
 	int node;
 	unsigned apicid = c->apicid;
 
-	node = per_cpu(cpu_llc_id, cpu);
+	node = numa_cpu_node(cpu);
+	if (node == NUMA_NO_NODE)
+		node = per_cpu(cpu_llc_id, cpu);
 
-	if (apicid_to_node[apicid] != NUMA_NO_NODE)
-		node = apicid_to_node[apicid];
 	if (!node_online(node)) {
-		/* Two possibilities here:
-		   - The CPU is missing memory and no node was created.
-		   In that case try picking one from a nearby CPU
-		   - The APIC IDs differ from the HyperTransport node IDs
-		   which the K8 northbridge parsing fills in.
-		   Assume they are all increased by a constant offset,
-		   but in the same order as the HT nodeids.
-		   If that doesn't result in a usable node fall back to the
-		   path for the previous case.  */
-
+		/*
+		 * Two possibilities here:
+		 *
+		 * - The CPU is missing memory and no node was created.  In
+		 *   that case try picking one from a nearby CPU.
+		 *
+		 * - The APIC IDs differ from the HyperTransport node IDs
+		 *   which the K8 northbridge parsing fills in.  Assume
+		 *   they are all increased by a constant offset, but in
+		 *   the same order as the HT nodeids.  If that doesn't
+		 *   result in a usable node fall back to the path for the
+		 *   previous case.
+		 *
+		 * This workaround operates directly on the mapping between
+		 * APIC ID and NUMA node, assuming certain relationship
+		 * between APIC ID, HT node ID and NUMA topology.  As going
+		 * through CPU mapping may alter the outcome, directly
+		 * access __apicid_to_node[].
+		 */
 		int ht_nodeid = c->initial_apicid;
 
 		if (ht_nodeid >= 0 &&
-		    apicid_to_node[ht_nodeid] != NUMA_NO_NODE)
-			node = apicid_to_node[ht_nodeid];
+		    __apicid_to_node[ht_nodeid] != NUMA_NO_NODE)
+			node = __apicid_to_node[ht_nodeid];
 		/* Pick a nearby node */
 		if (!node_online(node))
 			node = nearby_node(apicid);
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 1d59834396bd..e2ced0074a45 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -675,7 +675,7 @@ void __init early_cpu_init(void)
 	const struct cpu_dev *const *cdev;
 	int count = 0;
 
-#ifdef PROCESSOR_SELECT
+#ifdef CONFIG_PROCESSOR_SELECT
 	printk(KERN_INFO "KERNEL supported cpus:\n");
 #endif
 
@@ -687,7 +687,7 @@ void __init early_cpu_init(void)
 		cpu_devs[count] = cpudev;
 		count++;
 
-#ifdef PROCESSOR_SELECT
+#ifdef CONFIG_PROCESSOR_SELECT
 		{
 			unsigned int j;
 
@@ -869,7 +869,7 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
 
 	select_idle_routine(c);
 
-#if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
+#ifdef CONFIG_NUMA
 	numa_add_cpu(smp_processor_id());
 #endif
 }
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index d16c2c53d6bf..df86bc8c859d 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -276,14 +276,13 @@ static void __cpuinit intel_workarounds(struct cpuinfo_x86 *c)
 
 static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c)
 {
-#if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
+#ifdef CONFIG_NUMA
 	unsigned node;
 	int cpu = smp_processor_id();
-	int apicid = cpu_has_apic ? hard_smp_processor_id() : c->apicid;
 
 	/* Don't do the funky fallback heuristics the AMD version employs
 	   for now. */
-	node = apicid_to_node[apicid];
+	node = numa_cpu_node(cpu);
 	if (node == NUMA_NO_NODE || !node_online(node)) {
 		/* reuse the value from init_cpu_to_node() */
 		node = cpu_to_node(cpu);
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 90cc675ac746..1ce1af2899df 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -768,11 +768,11 @@ static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index)
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 
 	if ((index == 3) && (c->x86_vendor == X86_VENDOR_AMD)) {
-		for_each_cpu(i, c->llc_shared_map) {
+		for_each_cpu(i, cpu_llc_shared_mask(cpu)) {
 			if (!per_cpu(ici_cpuid4_info, i))
 				continue;
 			this_leaf = CPUID4_INFO_IDX(i, index);
-			for_each_cpu(sibling, c->llc_shared_map) {
+			for_each_cpu(sibling, cpu_llc_shared_mask(cpu)) {
 				if (!cpu_online(sibling))
 					continue;
 				set_bit(sibling, this_leaf->shared_cpu_map);
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 5bf2fac52aca..167f97b5596e 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -527,15 +527,12 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
 	int i, err = 0;
 	struct threshold_bank *b = NULL;
 	char name[32];
-#ifdef CONFIG_SMP
-	struct cpuinfo_x86 *c = &cpu_data(cpu);
-#endif
 
 	sprintf(name, "threshold_bank%i", bank);
 
 #ifdef CONFIG_SMP
 	if (cpu_data(cpu).cpu_core_id && shared_bank[bank]) {	/* symlink */
-		i = cpumask_first(c->llc_shared_map);
+		i = cpumask_first(cpu_llc_shared_mask(cpu));
 
 		/* first core not up yet */
 		if (cpu_data(i).cpu_core_id)
@@ -555,7 +552,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
 		if (err)
 			goto out;
 
-		cpumask_copy(b->cpus, c->llc_shared_map);
+		cpumask_copy(b->cpus, cpu_llc_shared_mask(cpu));
 		per_cpu(threshold_banks, cpu)[bank] = b;
 
 		goto out;
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 9d977a2ea693..26604188aa49 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -30,6 +30,7 @@
 #include <asm/stacktrace.h>
 #include <asm/nmi.h>
 #include <asm/compat.h>
+#include <asm/smp.h>
 
 #if 0
 #undef wrmsrl
@@ -93,6 +94,8 @@ struct amd_nb {
 	struct event_constraint event_constraints[X86_PMC_IDX_MAX];
 };
 
+struct intel_percore;
+
 #define MAX_LBR_ENTRIES		16
 
 struct cpu_hw_events {
@@ -128,6 +131,13 @@ struct cpu_hw_events {
 	struct perf_branch_entry	lbr_entries[MAX_LBR_ENTRIES];
 
 	/*
+	 * Intel percore register state.
+	 * Coordinate shared resources between HT threads.
+	 */
+	int				percore_used; /* Used by this CPU? */
+	struct intel_percore		*per_core;
+
+	/*
 	 * AMD specific bits
 	 */
 	struct amd_nb		*amd_nb;
@@ -166,8 +176,10 @@ struct cpu_hw_events {
 /*
  * Constraint on the Event code + UMask
  */
-#define PEBS_EVENT_CONSTRAINT(c, n)	\
+#define INTEL_UEVENT_CONSTRAINT(c, n)	\
 	EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK)
+#define PEBS_EVENT_CONSTRAINT(c, n)	\
+	INTEL_UEVENT_CONSTRAINT(c, n)
 
 #define EVENT_CONSTRAINT_END		\
 	EVENT_CONSTRAINT(0, 0, 0)
@@ -175,6 +187,28 @@ struct cpu_hw_events {
 #define for_each_event_constraint(e, c)	\
 	for ((e) = (c); (e)->weight; (e)++)
 
+/*
+ * Extra registers for specific events.
+ * Some events need large masks and require external MSRs.
+ * Define a mapping to these extra registers.
+ */
+struct extra_reg {
+	unsigned int		event;
+	unsigned int		msr;
+	u64			config_mask;
+	u64			valid_mask;
+};
+
+#define EVENT_EXTRA_REG(e, ms, m, vm) {	\
+	.event = (e),		\
+	.msr = (ms),		\
+	.config_mask = (m),	\
+	.valid_mask = (vm),	\
+	}
+#define INTEL_EVENT_EXTRA_REG(event, msr, vm)	\
+	EVENT_EXTRA_REG(event, msr, ARCH_PERFMON_EVENTSEL_EVENT, vm)
+#define EVENT_EXTRA_END EVENT_EXTRA_REG(0, 0, 0, 0)
+
 union perf_capabilities {
 	struct {
 		u64	lbr_format    : 6;
@@ -219,6 +253,7 @@ struct x86_pmu {
 	void		(*put_event_constraints)(struct cpu_hw_events *cpuc,
 						 struct perf_event *event);
 	struct event_constraint *event_constraints;
+	struct event_constraint *percore_constraints;
 	void		(*quirks)(void);
 	int		perfctr_second_write;
 
@@ -247,6 +282,11 @@ struct x86_pmu {
 	 */
 	unsigned long	lbr_tos, lbr_from, lbr_to; /* MSR base regs       */
 	int		lbr_nr;			   /* hardware stack size */
+
+	/*
+	 * Extra registers for events
+	 */
+	struct extra_reg *extra_regs;
 };
 
 static struct x86_pmu x86_pmu __read_mostly;
@@ -271,6 +311,10 @@ static u64 __read_mostly hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
 				[PERF_COUNT_HW_CACHE_OP_MAX]
 				[PERF_COUNT_HW_CACHE_RESULT_MAX];
+static u64 __read_mostly hw_cache_extra_regs
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX];
 
 /*
  * Propagate event elapsed time into the generic event.
@@ -298,7 +342,7 @@ x86_perf_event_update(struct perf_event *event)
 	 */
 again:
 	prev_raw_count = local64_read(&hwc->prev_count);
-	rdmsrl(hwc->event_base + idx, new_raw_count);
+	rdmsrl(hwc->event_base, new_raw_count);
 
 	if (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
 					new_raw_count) != prev_raw_count)
@@ -321,6 +365,49 @@ again:
 	return new_raw_count;
 }
 
+/* using X86_FEATURE_PERFCTR_CORE to later implement ALTERNATIVE() here */
+static inline int x86_pmu_addr_offset(int index)
+{
+	if (boot_cpu_has(X86_FEATURE_PERFCTR_CORE))
+		return index << 1;
+	return index;
+}
+
+static inline unsigned int x86_pmu_config_addr(int index)
+{
+	return x86_pmu.eventsel + x86_pmu_addr_offset(index);
+}
+
+static inline unsigned int x86_pmu_event_addr(int index)
+{
+	return x86_pmu.perfctr + x86_pmu_addr_offset(index);
+}
+
+/*
+ * Find and validate any extra registers to set up.
+ */
+static int x86_pmu_extra_regs(u64 config, struct perf_event *event)
+{
+	struct extra_reg *er;
+
+	event->hw.extra_reg = 0;
+	event->hw.extra_config = 0;
+
+	if (!x86_pmu.extra_regs)
+		return 0;
+
+	for (er = x86_pmu.extra_regs; er->msr; er++) {
+		if (er->event != (config & er->config_mask))
+			continue;
+		if (event->attr.config1 & ~er->valid_mask)
+			return -EINVAL;
+		event->hw.extra_reg = er->msr;
+		event->hw.extra_config = event->attr.config1;
+		break;
+	}
+	return 0;
+}
+
 static atomic_t active_events;
 static DEFINE_MUTEX(pmc_reserve_mutex);
 
@@ -331,12 +418,12 @@ static bool reserve_pmc_hardware(void)
 	int i;
 
 	for (i = 0; i < x86_pmu.num_counters; i++) {
-		if (!reserve_perfctr_nmi(x86_pmu.perfctr + i))
+		if (!reserve_perfctr_nmi(x86_pmu_event_addr(i)))
 			goto perfctr_fail;
 	}
 
 	for (i = 0; i < x86_pmu.num_counters; i++) {
-		if (!reserve_evntsel_nmi(x86_pmu.eventsel + i))
+		if (!reserve_evntsel_nmi(x86_pmu_config_addr(i)))
 			goto eventsel_fail;
 	}
 
@@ -344,13 +431,13 @@ static bool reserve_pmc_hardware(void)
 
 eventsel_fail:
 	for (i--; i >= 0; i--)
-		release_evntsel_nmi(x86_pmu.eventsel + i);
+		release_evntsel_nmi(x86_pmu_config_addr(i));
 
 	i = x86_pmu.num_counters;
 
 perfctr_fail:
 	for (i--; i >= 0; i--)
-		release_perfctr_nmi(x86_pmu.perfctr + i);
+		release_perfctr_nmi(x86_pmu_event_addr(i));
 
 	return false;
 }
@@ -360,8 +447,8 @@ static void release_pmc_hardware(void)
 	int i;
 
 	for (i = 0; i < x86_pmu.num_counters; i++) {
-		release_perfctr_nmi(x86_pmu.perfctr + i);
-		release_evntsel_nmi(x86_pmu.eventsel + i);
+		release_perfctr_nmi(x86_pmu_event_addr(i));
+		release_evntsel_nmi(x86_pmu_config_addr(i));
 	}
 }
 
@@ -382,7 +469,7 @@ static bool check_hw_exists(void)
 	 * complain and bail.
 	 */
 	for (i = 0; i < x86_pmu.num_counters; i++) {
-		reg = x86_pmu.eventsel + i;
+		reg = x86_pmu_config_addr(i);
 		ret = rdmsrl_safe(reg, &val);
 		if (ret)
 			goto msr_fail;
@@ -407,8 +494,8 @@ static bool check_hw_exists(void)
 	 * that don't trap on the MSR access and always return 0s.
 	 */
 	val = 0xabcdUL;
-	ret = checking_wrmsrl(x86_pmu.perfctr, val);
-	ret |= rdmsrl_safe(x86_pmu.perfctr, &val_new);
+	ret = checking_wrmsrl(x86_pmu_event_addr(0), val);
+	ret |= rdmsrl_safe(x86_pmu_event_addr(0), &val_new);
 	if (ret || val != val_new)
 		goto msr_fail;
 
@@ -442,8 +529,9 @@ static inline int x86_pmu_initialized(void)
 }
 
 static inline int
-set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event_attr *attr)
+set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event *event)
 {
+	struct perf_event_attr *attr = &event->attr;
 	unsigned int cache_type, cache_op, cache_result;
 	u64 config, val;
 
@@ -470,8 +558,8 @@ set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event_attr *attr)
 		return -EINVAL;
 
 	hwc->config |= val;
-
-	return 0;
+	attr->config1 = hw_cache_extra_regs[cache_type][cache_op][cache_result];
+	return x86_pmu_extra_regs(val, event);
 }
 
 static int x86_setup_perfctr(struct perf_event *event)
@@ -496,10 +584,10 @@ static int x86_setup_perfctr(struct perf_event *event)
 	}
 
 	if (attr->type == PERF_TYPE_RAW)
-		return 0;
+		return x86_pmu_extra_regs(event->attr.config, event);
 
 	if (attr->type == PERF_TYPE_HW_CACHE)
-		return set_ext_hw_attr(hwc, attr);
+		return set_ext_hw_attr(hwc, event);
 
 	if (attr->config >= x86_pmu.max_events)
 		return -EINVAL;
@@ -617,11 +705,11 @@ static void x86_pmu_disable_all(void)
 
 		if (!test_bit(idx, cpuc->active_mask))
 			continue;
-		rdmsrl(x86_pmu.eventsel + idx, val);
+		rdmsrl(x86_pmu_config_addr(idx), val);
 		if (!(val & ARCH_PERFMON_EVENTSEL_ENABLE))
 			continue;
 		val &= ~ARCH_PERFMON_EVENTSEL_ENABLE;
-		wrmsrl(x86_pmu.eventsel + idx, val);
+		wrmsrl(x86_pmu_config_addr(idx), val);
 	}
 }
 
@@ -642,21 +730,26 @@ static void x86_pmu_disable(struct pmu *pmu)
 	x86_pmu.disable_all();
 }
 
+static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc,
+					  u64 enable_mask)
+{
+	if (hwc->extra_reg)
+		wrmsrl(hwc->extra_reg, hwc->extra_config);
+	wrmsrl(hwc->config_base, hwc->config | enable_mask);
+}
+
 static void x86_pmu_enable_all(int added)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	int idx;
 
 	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
-		struct perf_event *event = cpuc->events[idx];
-		u64 val;
+		struct hw_perf_event *hwc = &cpuc->events[idx]->hw;
 
 		if (!test_bit(idx, cpuc->active_mask))
 			continue;
 
-		val = event->hw.config;
-		val |= ARCH_PERFMON_EVENTSEL_ENABLE;
-		wrmsrl(x86_pmu.eventsel + idx, val);
+		__x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE);
 	}
 }
 
@@ -821,15 +914,10 @@ static inline void x86_assign_hw_event(struct perf_event *event,
 		hwc->event_base	= 0;
 	} else if (hwc->idx >= X86_PMC_IDX_FIXED) {
 		hwc->config_base = MSR_ARCH_PERFMON_FIXED_CTR_CTRL;
-		/*
-		 * We set it so that event_base + idx in wrmsr/rdmsr maps to
-		 * MSR_ARCH_PERFMON_FIXED_CTR0 ... CTR2:
-		 */
-		hwc->event_base =
-			MSR_ARCH_PERFMON_FIXED_CTR0 - X86_PMC_IDX_FIXED;
+		hwc->event_base = MSR_ARCH_PERFMON_FIXED_CTR0;
 	} else {
-		hwc->config_base = x86_pmu.eventsel;
-		hwc->event_base  = x86_pmu.perfctr;
+		hwc->config_base = x86_pmu_config_addr(hwc->idx);
+		hwc->event_base  = x86_pmu_event_addr(hwc->idx);
 	}
 }
 
@@ -915,17 +1003,11 @@ static void x86_pmu_enable(struct pmu *pmu)
 	x86_pmu.enable_all(added);
 }
 
-static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc,
-					  u64 enable_mask)
-{
-	wrmsrl(hwc->config_base + hwc->idx, hwc->config | enable_mask);
-}
-
 static inline void x86_pmu_disable_event(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
 
-	wrmsrl(hwc->config_base + hwc->idx, hwc->config);
+	wrmsrl(hwc->config_base, hwc->config);
 }
 
 static DEFINE_PER_CPU(u64 [X86_PMC_IDX_MAX], pmc_prev_left);
@@ -978,7 +1060,7 @@ x86_perf_event_set_period(struct perf_event *event)
 	 */
 	local64_set(&hwc->prev_count, (u64)-left);
 
-	wrmsrl(hwc->event_base + idx, (u64)(-left) & x86_pmu.cntval_mask);
+	wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask);
 
 	/*
 	 * Due to erratum on certan cpu we need
@@ -986,7 +1068,7 @@ x86_perf_event_set_period(struct perf_event *event)
 	 * is updated properly
 	 */
 	if (x86_pmu.perfctr_second_write) {
-		wrmsrl(hwc->event_base + idx,
+		wrmsrl(hwc->event_base,
 			(u64)(-left) & x86_pmu.cntval_mask);
 	}
 
@@ -1113,8 +1195,8 @@ void perf_event_print_debug(void)
 	pr_info("CPU#%d: active:     %016llx\n", cpu, *(u64 *)cpuc->active_mask);
 
 	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
-		rdmsrl(x86_pmu.eventsel + idx, pmc_ctrl);
-		rdmsrl(x86_pmu.perfctr  + idx, pmc_count);
+		rdmsrl(x86_pmu_config_addr(idx), pmc_ctrl);
+		rdmsrl(x86_pmu_event_addr(idx), pmc_count);
 
 		prev_left = per_cpu(pmc_prev_left[idx], cpu);
 
@@ -1389,7 +1471,7 @@ static void __init pmu_check_apic(void)
 	pr_info("no hardware sampling interrupt available.\n");
 }
 
-int __init init_hw_perf_events(void)
+static int __init init_hw_perf_events(void)
 {
 	struct event_constraint *c;
 	int err;
@@ -1608,7 +1690,7 @@ out:
 	return ret;
 }
 
-int x86_pmu_event_init(struct perf_event *event)
+static int x86_pmu_event_init(struct perf_event *event)
 {
 	struct pmu *tmp;
 	int err;
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index 67e2202a6039..461f62bbd774 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -127,6 +127,11 @@ static int amd_pmu_hw_config(struct perf_event *event)
 /*
  * AMD64 events are detected based on their event codes.
  */
+static inline unsigned int amd_get_event_code(struct hw_perf_event *hwc)
+{
+	return ((hwc->config >> 24) & 0x0f00) | (hwc->config & 0x00ff);
+}
+
 static inline int amd_is_nb_event(struct hw_perf_event *hwc)
 {
 	return (hwc->config & 0xe0) == 0xe0;
@@ -385,13 +390,181 @@ static __initconst const struct x86_pmu amd_pmu = {
 	.cpu_dead		= amd_pmu_cpu_dead,
 };
 
+/* AMD Family 15h */
+
+#define AMD_EVENT_TYPE_MASK	0x000000F0ULL
+
+#define AMD_EVENT_FP		0x00000000ULL ... 0x00000010ULL
+#define AMD_EVENT_LS		0x00000020ULL ... 0x00000030ULL
+#define AMD_EVENT_DC		0x00000040ULL ... 0x00000050ULL
+#define AMD_EVENT_CU		0x00000060ULL ... 0x00000070ULL
+#define AMD_EVENT_IC_DE		0x00000080ULL ... 0x00000090ULL
+#define AMD_EVENT_EX_LS		0x000000C0ULL
+#define AMD_EVENT_DE		0x000000D0ULL
+#define AMD_EVENT_NB		0x000000E0ULL ... 0x000000F0ULL
+
+/*
+ * AMD family 15h event code/PMC mappings:
+ *
+ * type = event_code & 0x0F0:
+ *
+ * 0x000	FP	PERF_CTL[5:3]
+ * 0x010	FP	PERF_CTL[5:3]
+ * 0x020	LS	PERF_CTL[5:0]
+ * 0x030	LS	PERF_CTL[5:0]
+ * 0x040	DC	PERF_CTL[5:0]
+ * 0x050	DC	PERF_CTL[5:0]
+ * 0x060	CU	PERF_CTL[2:0]
+ * 0x070	CU	PERF_CTL[2:0]
+ * 0x080	IC/DE	PERF_CTL[2:0]
+ * 0x090	IC/DE	PERF_CTL[2:0]
+ * 0x0A0	---
+ * 0x0B0	---
+ * 0x0C0	EX/LS	PERF_CTL[5:0]
+ * 0x0D0	DE	PERF_CTL[2:0]
+ * 0x0E0	NB	NB_PERF_CTL[3:0]
+ * 0x0F0	NB	NB_PERF_CTL[3:0]
+ *
+ * Exceptions:
+ *
+ * 0x003	FP	PERF_CTL[3]
+ * 0x00B	FP	PERF_CTL[3]
+ * 0x00D	FP	PERF_CTL[3]
+ * 0x023	DE	PERF_CTL[2:0]
+ * 0x02D	LS	PERF_CTL[3]
+ * 0x02E	LS	PERF_CTL[3,0]
+ * 0x043	CU	PERF_CTL[2:0]
+ * 0x045	CU	PERF_CTL[2:0]
+ * 0x046	CU	PERF_CTL[2:0]
+ * 0x054	CU	PERF_CTL[2:0]
+ * 0x055	CU	PERF_CTL[2:0]
+ * 0x08F	IC	PERF_CTL[0]
+ * 0x187	DE	PERF_CTL[0]
+ * 0x188	DE	PERF_CTL[0]
+ * 0x0DB	EX	PERF_CTL[5:0]
+ * 0x0DC	LS	PERF_CTL[5:0]
+ * 0x0DD	LS	PERF_CTL[5:0]
+ * 0x0DE	LS	PERF_CTL[5:0]
+ * 0x0DF	LS	PERF_CTL[5:0]
+ * 0x1D6	EX	PERF_CTL[5:0]
+ * 0x1D8	EX	PERF_CTL[5:0]
+ */
+
+static struct event_constraint amd_f15_PMC0  = EVENT_CONSTRAINT(0, 0x01, 0);
+static struct event_constraint amd_f15_PMC20 = EVENT_CONSTRAINT(0, 0x07, 0);
+static struct event_constraint amd_f15_PMC3  = EVENT_CONSTRAINT(0, 0x08, 0);
+static struct event_constraint amd_f15_PMC30 = EVENT_CONSTRAINT(0, 0x09, 0);
+static struct event_constraint amd_f15_PMC50 = EVENT_CONSTRAINT(0, 0x3F, 0);
+static struct event_constraint amd_f15_PMC53 = EVENT_CONSTRAINT(0, 0x38, 0);
+
+static struct event_constraint *
+amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, struct perf_event *event)
+{
+	unsigned int event_code = amd_get_event_code(&event->hw);
+
+	switch (event_code & AMD_EVENT_TYPE_MASK) {
+	case AMD_EVENT_FP:
+		switch (event_code) {
+		case 0x003:
+		case 0x00B:
+		case 0x00D:
+			return &amd_f15_PMC3;
+		default:
+			return &amd_f15_PMC53;
+		}
+	case AMD_EVENT_LS:
+	case AMD_EVENT_DC:
+	case AMD_EVENT_EX_LS:
+		switch (event_code) {
+		case 0x023:
+		case 0x043:
+		case 0x045:
+		case 0x046:
+		case 0x054:
+		case 0x055:
+			return &amd_f15_PMC20;
+		case 0x02D:
+			return &amd_f15_PMC3;
+		case 0x02E:
+			return &amd_f15_PMC30;
+		default:
+			return &amd_f15_PMC50;
+		}
+	case AMD_EVENT_CU:
+	case AMD_EVENT_IC_DE:
+	case AMD_EVENT_DE:
+		switch (event_code) {
+		case 0x08F:
+		case 0x187:
+		case 0x188:
+			return &amd_f15_PMC0;
+		case 0x0DB ... 0x0DF:
+		case 0x1D6:
+		case 0x1D8:
+			return &amd_f15_PMC50;
+		default:
+			return &amd_f15_PMC20;
+		}
+	case AMD_EVENT_NB:
+		/* not yet implemented */
+		return &emptyconstraint;
+	default:
+		return &emptyconstraint;
+	}
+}
+
+static __initconst const struct x86_pmu amd_pmu_f15h = {
+	.name			= "AMD Family 15h",
+	.handle_irq		= x86_pmu_handle_irq,
+	.disable_all		= x86_pmu_disable_all,
+	.enable_all		= x86_pmu_enable_all,
+	.enable			= x86_pmu_enable_event,
+	.disable		= x86_pmu_disable_event,
+	.hw_config		= amd_pmu_hw_config,
+	.schedule_events	= x86_schedule_events,
+	.eventsel		= MSR_F15H_PERF_CTL,
+	.perfctr		= MSR_F15H_PERF_CTR,
+	.event_map		= amd_pmu_event_map,
+	.max_events		= ARRAY_SIZE(amd_perfmon_event_map),
+	.num_counters		= 6,
+	.cntval_bits		= 48,
+	.cntval_mask		= (1ULL << 48) - 1,
+	.apic			= 1,
+	/* use highest bit to detect overflow */
+	.max_period		= (1ULL << 47) - 1,
+	.get_event_constraints	= amd_get_event_constraints_f15h,
+	/* nortbridge counters not yet implemented: */
+#if 0
+	.put_event_constraints	= amd_put_event_constraints,
+
+	.cpu_prepare		= amd_pmu_cpu_prepare,
+	.cpu_starting		= amd_pmu_cpu_starting,
+	.cpu_dead		= amd_pmu_cpu_dead,
+#endif
+};
+
 static __init int amd_pmu_init(void)
 {
 	/* Performance-monitoring supported from K7 and later: */
 	if (boot_cpu_data.x86 < 6)
 		return -ENODEV;
 
-	x86_pmu = amd_pmu;
+	/*
+	 * If core performance counter extensions exists, it must be
+	 * family 15h, otherwise fail. See x86_pmu_addr_offset().
+	 */
+	switch (boot_cpu_data.x86) {
+	case 0x15:
+		if (!cpu_has_perfctr_core)
+			return -ENODEV;
+		x86_pmu = amd_pmu_f15h;
+		break;
+	default:
+		if (cpu_has_perfctr_core)
+			return -ENODEV;
+		x86_pmu = amd_pmu;
+		break;
+	}
 
 	/* Events are common for all AMDs */
 	memcpy(hw_cache_event_ids, amd_hw_cache_event_ids,
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 008835c1d79c..8fc2b2cee1da 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1,5 +1,27 @@
 #ifdef CONFIG_CPU_SUP_INTEL
 
+#define MAX_EXTRA_REGS 2
+
+/*
+ * Per register state.
+ */
+struct er_account {
+	int			ref;		/* reference count */
+	unsigned int		extra_reg;	/* extra MSR number */
+	u64			extra_config;	/* extra MSR config */
+};
+
+/*
+ * Per core state
+ * This used to coordinate shared registers for HT threads.
+ */
+struct intel_percore {
+	raw_spinlock_t		lock;		/* protect structure */
+	struct er_account	regs[MAX_EXTRA_REGS];
+	int			refcnt;		/* number of threads */
+	unsigned		core_id;
+};
+
 /*
  * Intel PerfMon, used on Core and later.
  */
@@ -64,6 +86,18 @@ static struct event_constraint intel_nehalem_event_constraints[] =
 	EVENT_CONSTRAINT_END
 };
 
+static struct extra_reg intel_nehalem_extra_regs[] =
+{
+	INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff),
+	EVENT_EXTRA_END
+};
+
+static struct event_constraint intel_nehalem_percore_constraints[] =
+{
+	INTEL_EVENT_CONSTRAINT(0xb7, 0),
+	EVENT_CONSTRAINT_END
+};
+
 static struct event_constraint intel_westmere_event_constraints[] =
 {
 	FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
@@ -76,6 +110,33 @@ static struct event_constraint intel_westmere_event_constraints[] =
 	EVENT_CONSTRAINT_END
 };
 
+static struct event_constraint intel_snb_event_constraints[] =
+{
+	FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
+	FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
+	/* FIXED_EVENT_CONSTRAINT(0x013c, 2), CPU_CLK_UNHALTED.REF */
+	INTEL_EVENT_CONSTRAINT(0x48, 0x4), /* L1D_PEND_MISS.PENDING */
+	INTEL_EVENT_CONSTRAINT(0xb7, 0x1), /* OFF_CORE_RESPONSE_0 */
+	INTEL_EVENT_CONSTRAINT(0xbb, 0x8), /* OFF_CORE_RESPONSE_1 */
+	INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */
+	INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.LOAD_LATENCY */
+	EVENT_CONSTRAINT_END
+};
+
+static struct extra_reg intel_westmere_extra_regs[] =
+{
+	INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff),
+	INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0xffff),
+	EVENT_EXTRA_END
+};
+
+static struct event_constraint intel_westmere_percore_constraints[] =
+{
+	INTEL_EVENT_CONSTRAINT(0xb7, 0),
+	INTEL_EVENT_CONSTRAINT(0xbb, 0),
+	EVENT_CONSTRAINT_END
+};
+
 static struct event_constraint intel_gen_event_constraints[] =
 {
 	FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
@@ -89,6 +150,106 @@ static u64 intel_pmu_event_map(int hw_event)
 	return intel_perfmon_event_map[hw_event];
 }
 
+static __initconst const u64 snb_hw_cache_event_ids
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(L1D) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0xf1d0, /* MEM_UOP_RETIRED.LOADS        */
+		[ C(RESULT_MISS)   ] = 0x0151, /* L1D.REPLACEMENT              */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0xf2d0, /* MEM_UOP_RETIRED.STORES       */
+		[ C(RESULT_MISS)   ] = 0x0851, /* L1D.ALL_M_REPLACEMENT        */
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x024e, /* HW_PRE_REQ.DL1_MISS          */
+	},
+ },
+ [ C(L1I ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0280, /* ICACHE.MISSES */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+ [ C(LL  ) ] = {
+	/*
+	 * TBD: Need Off-core Response Performance Monitoring support
+	 */
+	[ C(OP_READ) ] = {
+		/* OFFCORE_RESPONSE_0.ANY_DATA.LOCAL_CACHE */
+		[ C(RESULT_ACCESS) ] = 0x01b7,
+		/* OFFCORE_RESPONSE_1.ANY_DATA.ANY_LLC_MISS */
+		[ C(RESULT_MISS)   ] = 0x01bb,
+	},
+	[ C(OP_WRITE) ] = {
+		/* OFFCORE_RESPONSE_0.ANY_RFO.LOCAL_CACHE */
+		[ C(RESULT_ACCESS) ] = 0x01b7,
+		/* OFFCORE_RESPONSE_1.ANY_RFO.ANY_LLC_MISS */
+		[ C(RESULT_MISS)   ] = 0x01bb,
+	},
+	[ C(OP_PREFETCH) ] = {
+		/* OFFCORE_RESPONSE_0.PREFETCH.LOCAL_CACHE */
+		[ C(RESULT_ACCESS) ] = 0x01b7,
+		/* OFFCORE_RESPONSE_1.PREFETCH.ANY_LLC_MISS */
+		[ C(RESULT_MISS)   ] = 0x01bb,
+	},
+ },
+ [ C(DTLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x81d0, /* MEM_UOP_RETIRED.ALL_LOADS */
+		[ C(RESULT_MISS)   ] = 0x0108, /* DTLB_LOAD_MISSES.CAUSES_A_WALK */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x82d0, /* MEM_UOP_RETIRED.ALL_STORES */
+		[ C(RESULT_MISS)   ] = 0x0149, /* DTLB_STORE_MISSES.MISS_CAUSES_A_WALK */
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+ [ C(ITLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x1085, /* ITLB_MISSES.STLB_HIT         */
+		[ C(RESULT_MISS)   ] = 0x0185, /* ITLB_MISSES.CAUSES_A_WALK    */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+ [ C(BPU ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x00c4, /* BR_INST_RETIRED.ALL_BRANCHES */
+		[ C(RESULT_MISS)   ] = 0x00c5, /* BR_MISP_RETIRED.ALL_BRANCHES */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+};
+
 static __initconst const u64 westmere_hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
 				[PERF_COUNT_HW_CACHE_OP_MAX]
@@ -124,16 +285,26 @@ static __initconst const u64 westmere_hw_cache_event_ids
  },
  [ C(LL  ) ] = {
 	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0324, /* L2_RQSTS.LOADS               */
-		[ C(RESULT_MISS)   ] = 0x0224, /* L2_RQSTS.LD_MISS             */
+		/* OFFCORE_RESPONSE_0.ANY_DATA.LOCAL_CACHE */
+		[ C(RESULT_ACCESS) ] = 0x01b7,
+		/* OFFCORE_RESPONSE_1.ANY_DATA.ANY_LLC_MISS */
+		[ C(RESULT_MISS)   ] = 0x01bb,
 	},
+	/*
+	 * Use RFO, not WRITEBACK, because a write miss would typically occur
+	 * on RFO.
+	 */
 	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0c24, /* L2_RQSTS.RFOS                */
-		[ C(RESULT_MISS)   ] = 0x0824, /* L2_RQSTS.RFO_MISS            */
+		/* OFFCORE_RESPONSE_1.ANY_RFO.LOCAL_CACHE */
+		[ C(RESULT_ACCESS) ] = 0x01bb,
+		/* OFFCORE_RESPONSE_0.ANY_RFO.ANY_LLC_MISS */
+		[ C(RESULT_MISS)   ] = 0x01b7,
 	},
 	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = 0x4f2e, /* LLC Reference                */
-		[ C(RESULT_MISS)   ] = 0x412e, /* LLC Misses                   */
+		/* OFFCORE_RESPONSE_0.PREFETCH.LOCAL_CACHE */
+		[ C(RESULT_ACCESS) ] = 0x01b7,
+		/* OFFCORE_RESPONSE_1.PREFETCH.ANY_LLC_MISS */
+		[ C(RESULT_MISS)   ] = 0x01bb,
 	},
  },
  [ C(DTLB) ] = {
@@ -180,6 +351,39 @@ static __initconst const u64 westmere_hw_cache_event_ids
  },
 };
 
+/*
+ * OFFCORE_RESPONSE MSR bits (subset), See IA32 SDM Vol 3 30.6.1.3
+ */
+
+#define DMND_DATA_RD     (1 << 0)
+#define DMND_RFO         (1 << 1)
+#define DMND_WB          (1 << 3)
+#define PF_DATA_RD       (1 << 4)
+#define PF_DATA_RFO      (1 << 5)
+#define RESP_UNCORE_HIT  (1 << 8)
+#define RESP_MISS        (0xf600) /* non uncore hit */
+
+static __initconst const u64 nehalem_hw_cache_extra_regs
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(LL  ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = DMND_DATA_RD|RESP_UNCORE_HIT,
+		[ C(RESULT_MISS)   ] = DMND_DATA_RD|RESP_MISS,
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = DMND_RFO|DMND_WB|RESP_UNCORE_HIT,
+		[ C(RESULT_MISS)   ] = DMND_RFO|DMND_WB|RESP_MISS,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = PF_DATA_RD|PF_DATA_RFO|RESP_UNCORE_HIT,
+		[ C(RESULT_MISS)   ] = PF_DATA_RD|PF_DATA_RFO|RESP_MISS,
+	},
+ }
+};
+
 static __initconst const u64 nehalem_hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
 				[PERF_COUNT_HW_CACHE_OP_MAX]
@@ -215,16 +419,26 @@ static __initconst const u64 nehalem_hw_cache_event_ids
  },
  [ C(LL  ) ] = {
 	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0324, /* L2_RQSTS.LOADS               */
-		[ C(RESULT_MISS)   ] = 0x0224, /* L2_RQSTS.LD_MISS             */
+		/* OFFCORE_RESPONSE.ANY_DATA.LOCAL_CACHE */
+		[ C(RESULT_ACCESS) ] = 0x01b7,
+		/* OFFCORE_RESPONSE.ANY_DATA.ANY_LLC_MISS */
+		[ C(RESULT_MISS)   ] = 0x01b7,
 	},
+	/*
+	 * Use RFO, not WRITEBACK, because a write miss would typically occur
+	 * on RFO.
+	 */
 	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0c24, /* L2_RQSTS.RFOS                */
-		[ C(RESULT_MISS)   ] = 0x0824, /* L2_RQSTS.RFO_MISS            */
+		/* OFFCORE_RESPONSE.ANY_RFO.LOCAL_CACHE */
+		[ C(RESULT_ACCESS) ] = 0x01b7,
+		/* OFFCORE_RESPONSE.ANY_RFO.ANY_LLC_MISS */
+		[ C(RESULT_MISS)   ] = 0x01b7,
 	},
 	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = 0x4f2e, /* LLC Reference                */
-		[ C(RESULT_MISS)   ] = 0x412e, /* LLC Misses                   */
+		/* OFFCORE_RESPONSE.PREFETCH.LOCAL_CACHE */
+		[ C(RESULT_ACCESS) ] = 0x01b7,
+		/* OFFCORE_RESPONSE.PREFETCH.ANY_LLC_MISS */
+		[ C(RESULT_MISS)   ] = 0x01b7,
 	},
  },
  [ C(DTLB) ] = {
@@ -691,8 +905,8 @@ static void intel_pmu_reset(void)
 	printk("clearing PMU state on CPU#%d\n", smp_processor_id());
 
 	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
-		checking_wrmsrl(x86_pmu.eventsel + idx, 0ull);
-		checking_wrmsrl(x86_pmu.perfctr  + idx, 0ull);
+		checking_wrmsrl(x86_pmu_config_addr(idx), 0ull);
+		checking_wrmsrl(x86_pmu_event_addr(idx),  0ull);
 	}
 	for (idx = 0; idx < x86_pmu.num_counters_fixed; idx++)
 		checking_wrmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, 0ull);
@@ -794,6 +1008,67 @@ intel_bts_constraints(struct perf_event *event)
 }
 
 static struct event_constraint *
+intel_percore_constraints(struct cpu_hw_events *cpuc, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	unsigned int e = hwc->config & ARCH_PERFMON_EVENTSEL_EVENT;
+	struct event_constraint *c;
+	struct intel_percore *pc;
+	struct er_account *era;
+	int i;
+	int free_slot;
+	int found;
+
+	if (!x86_pmu.percore_constraints || hwc->extra_alloc)
+		return NULL;
+
+	for (c = x86_pmu.percore_constraints; c->cmask; c++) {
+		if (e != c->code)
+			continue;
+
+		/*
+		 * Allocate resource per core.
+		 */
+		pc = cpuc->per_core;
+		if (!pc)
+			break;
+		c = &emptyconstraint;
+		raw_spin_lock(&pc->lock);
+		free_slot = -1;
+		found = 0;
+		for (i = 0; i < MAX_EXTRA_REGS; i++) {
+			era = &pc->regs[i];
+			if (era->ref > 0 && hwc->extra_reg == era->extra_reg) {
+				/* Allow sharing same config */
+				if (hwc->extra_config == era->extra_config) {
+					era->ref++;
+					cpuc->percore_used = 1;
+					hwc->extra_alloc = 1;
+					c = NULL;
+				}
+				/* else conflict */
+				found = 1;
+				break;
+			} else if (era->ref == 0 && free_slot == -1)
+				free_slot = i;
+		}
+		if (!found && free_slot != -1) {
+			era = &pc->regs[free_slot];
+			era->ref = 1;
+			era->extra_reg = hwc->extra_reg;
+			era->extra_config = hwc->extra_config;
+			cpuc->percore_used = 1;
+			hwc->extra_alloc = 1;
+			c = NULL;
+		}
+		raw_spin_unlock(&pc->lock);
+		return c;
+	}
+
+	return NULL;
+}
+
+static struct event_constraint *
 intel_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event)
 {
 	struct event_constraint *c;
@@ -806,9 +1081,51 @@ intel_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event
 	if (c)
 		return c;
 
+	c = intel_percore_constraints(cpuc, event);
+	if (c)
+		return c;
+
 	return x86_get_event_constraints(cpuc, event);
 }
 
+static void intel_put_event_constraints(struct cpu_hw_events *cpuc,
+					struct perf_event *event)
+{
+	struct extra_reg *er;
+	struct intel_percore *pc;
+	struct er_account *era;
+	struct hw_perf_event *hwc = &event->hw;
+	int i, allref;
+
+	if (!cpuc->percore_used)
+		return;
+
+	for (er = x86_pmu.extra_regs; er->msr; er++) {
+		if (er->event != (hwc->config & er->config_mask))
+			continue;
+
+		pc = cpuc->per_core;
+		raw_spin_lock(&pc->lock);
+		for (i = 0; i < MAX_EXTRA_REGS; i++) {
+			era = &pc->regs[i];
+			if (era->ref > 0 &&
+			    era->extra_config == hwc->extra_config &&
+			    era->extra_reg == er->msr) {
+				era->ref--;
+				hwc->extra_alloc = 0;
+				break;
+			}
+		}
+		allref = 0;
+		for (i = 0; i < MAX_EXTRA_REGS; i++)
+			allref += pc->regs[i].ref;
+		if (allref == 0)
+			cpuc->percore_used = 0;
+		raw_spin_unlock(&pc->lock);
+		break;
+	}
+}
+
 static int intel_pmu_hw_config(struct perf_event *event)
 {
 	int ret = x86_pmu_hw_config(event);
@@ -880,20 +1197,67 @@ static __initconst const struct x86_pmu core_pmu = {
 	 */
 	.max_period		= (1ULL << 31) - 1,
 	.get_event_constraints	= intel_get_event_constraints,
+	.put_event_constraints	= intel_put_event_constraints,
 	.event_constraints	= intel_core_event_constraints,
 };
 
+static int intel_pmu_cpu_prepare(int cpu)
+{
+	struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
+
+	if (!cpu_has_ht_siblings())
+		return NOTIFY_OK;
+
+	cpuc->per_core = kzalloc_node(sizeof(struct intel_percore),
+				      GFP_KERNEL, cpu_to_node(cpu));
+	if (!cpuc->per_core)
+		return NOTIFY_BAD;
+
+	raw_spin_lock_init(&cpuc->per_core->lock);
+	cpuc->per_core->core_id = -1;
+	return NOTIFY_OK;
+}
+
 static void intel_pmu_cpu_starting(int cpu)
 {
+	struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
+	int core_id = topology_core_id(cpu);
+	int i;
+
 	init_debug_store_on_cpu(cpu);
 	/*
 	 * Deal with CPUs that don't clear their LBRs on power-up.
 	 */
 	intel_pmu_lbr_reset();
+
+	if (!cpu_has_ht_siblings())
+		return;
+
+	for_each_cpu(i, topology_thread_cpumask(cpu)) {
+		struct intel_percore *pc = per_cpu(cpu_hw_events, i).per_core;
+
+		if (pc && pc->core_id == core_id) {
+			kfree(cpuc->per_core);
+			cpuc->per_core = pc;
+			break;
+		}
+	}
+
+	cpuc->per_core->core_id = core_id;
+	cpuc->per_core->refcnt++;
 }
 
 static void intel_pmu_cpu_dying(int cpu)
 {
+	struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
+	struct intel_percore *pc = cpuc->per_core;
+
+	if (pc) {
+		if (pc->core_id == -1 || --pc->refcnt == 0)
+			kfree(pc);
+		cpuc->per_core = NULL;
+	}
+
 	fini_debug_store_on_cpu(cpu);
 }
 
@@ -918,7 +1282,9 @@ static __initconst const struct x86_pmu intel_pmu = {
 	 */
 	.max_period		= (1ULL << 31) - 1,
 	.get_event_constraints	= intel_get_event_constraints,
+	.put_event_constraints	= intel_put_event_constraints,
 
+	.cpu_prepare		= intel_pmu_cpu_prepare,
 	.cpu_starting		= intel_pmu_cpu_starting,
 	.cpu_dying		= intel_pmu_cpu_dying,
 };
@@ -1024,6 +1390,7 @@ static __init int intel_pmu_init(void)
 		intel_pmu_lbr_init_core();
 
 		x86_pmu.event_constraints = intel_core2_event_constraints;
+		x86_pmu.pebs_constraints = intel_core2_pebs_event_constraints;
 		pr_cont("Core2 events, ");
 		break;
 
@@ -1032,11 +1399,16 @@ static __init int intel_pmu_init(void)
 	case 46: /* 45 nm nehalem-ex, "Beckton" */
 		memcpy(hw_cache_event_ids, nehalem_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
+		memcpy(hw_cache_extra_regs, nehalem_hw_cache_extra_regs,
+		       sizeof(hw_cache_extra_regs));
 
 		intel_pmu_lbr_init_nhm();
 
 		x86_pmu.event_constraints = intel_nehalem_event_constraints;
+		x86_pmu.pebs_constraints = intel_nehalem_pebs_event_constraints;
+		x86_pmu.percore_constraints = intel_nehalem_percore_constraints;
 		x86_pmu.enable_all = intel_pmu_nhm_enable_all;
+		x86_pmu.extra_regs = intel_nehalem_extra_regs;
 		pr_cont("Nehalem events, ");
 		break;
 
@@ -1047,6 +1419,7 @@ static __init int intel_pmu_init(void)
 		intel_pmu_lbr_init_atom();
 
 		x86_pmu.event_constraints = intel_gen_event_constraints;
+		x86_pmu.pebs_constraints = intel_atom_pebs_event_constraints;
 		pr_cont("Atom events, ");
 		break;
 
@@ -1054,14 +1427,30 @@ static __init int intel_pmu_init(void)
 	case 44: /* 32 nm nehalem, "Gulftown" */
 		memcpy(hw_cache_event_ids, westmere_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
+		memcpy(hw_cache_extra_regs, nehalem_hw_cache_extra_regs,
+		       sizeof(hw_cache_extra_regs));
 
 		intel_pmu_lbr_init_nhm();
 
 		x86_pmu.event_constraints = intel_westmere_event_constraints;
+		x86_pmu.percore_constraints = intel_westmere_percore_constraints;
 		x86_pmu.enable_all = intel_pmu_nhm_enable_all;
+		x86_pmu.pebs_constraints = intel_westmere_pebs_event_constraints;
+		x86_pmu.extra_regs = intel_westmere_extra_regs;
 		pr_cont("Westmere events, ");
 		break;
 
+	case 42: /* SandyBridge */
+		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
+		       sizeof(hw_cache_event_ids));
+
+		intel_pmu_lbr_init_nhm();
+
+		x86_pmu.event_constraints = intel_snb_event_constraints;
+		x86_pmu.pebs_constraints = intel_snb_pebs_events;
+		pr_cont("SandyBridge events, ");
+		break;
+
 	default:
 		/*
 		 * default constraints for v2 and up
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index b7dcd9f2b8a0..b95c66ae4a2a 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -361,30 +361,88 @@ static int intel_pmu_drain_bts_buffer(void)
 /*
  * PEBS
  */
-
-static struct event_constraint intel_core_pebs_events[] = {
-	PEBS_EVENT_CONSTRAINT(0x00c0, 0x1), /* INSTR_RETIRED.ANY */
+static struct event_constraint intel_core2_pebs_event_constraints[] = {
+	PEBS_EVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */
 	PEBS_EVENT_CONSTRAINT(0xfec1, 0x1), /* X87_OPS_RETIRED.ANY */
 	PEBS_EVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_RETIRED.MISPRED */
 	PEBS_EVENT_CONSTRAINT(0x1fc7, 0x1), /* SIMD_INST_RETURED.ANY */
-	PEBS_EVENT_CONSTRAINT(0x01cb, 0x1), /* MEM_LOAD_RETIRED.L1D_MISS */
-	PEBS_EVENT_CONSTRAINT(0x02cb, 0x1), /* MEM_LOAD_RETIRED.L1D_LINE_MISS */
-	PEBS_EVENT_CONSTRAINT(0x04cb, 0x1), /* MEM_LOAD_RETIRED.L2_MISS */
-	PEBS_EVENT_CONSTRAINT(0x08cb, 0x1), /* MEM_LOAD_RETIRED.L2_LINE_MISS */
-	PEBS_EVENT_CONSTRAINT(0x10cb, 0x1), /* MEM_LOAD_RETIRED.DTLB_MISS */
+	INTEL_EVENT_CONSTRAINT(0xcb, 0x1),  /* MEM_LOAD_RETIRED.* */
+	EVENT_CONSTRAINT_END
+};
+
+static struct event_constraint intel_atom_pebs_event_constraints[] = {
+	PEBS_EVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */
+	PEBS_EVENT_CONSTRAINT(0x00c5, 0x1), /* MISPREDICTED_BRANCH_RETIRED */
+	INTEL_EVENT_CONSTRAINT(0xcb, 0x1),  /* MEM_LOAD_RETIRED.* */
 	EVENT_CONSTRAINT_END
 };
 
-static struct event_constraint intel_nehalem_pebs_events[] = {
-	PEBS_EVENT_CONSTRAINT(0x00c0, 0xf), /* INSTR_RETIRED.ANY */
-	PEBS_EVENT_CONSTRAINT(0xfec1, 0xf), /* X87_OPS_RETIRED.ANY */
-	PEBS_EVENT_CONSTRAINT(0x00c5, 0xf), /* BR_INST_RETIRED.MISPRED */
-	PEBS_EVENT_CONSTRAINT(0x1fc7, 0xf), /* SIMD_INST_RETURED.ANY */
-	PEBS_EVENT_CONSTRAINT(0x01cb, 0xf), /* MEM_LOAD_RETIRED.L1D_MISS */
-	PEBS_EVENT_CONSTRAINT(0x02cb, 0xf), /* MEM_LOAD_RETIRED.L1D_LINE_MISS */
-	PEBS_EVENT_CONSTRAINT(0x04cb, 0xf), /* MEM_LOAD_RETIRED.L2_MISS */
-	PEBS_EVENT_CONSTRAINT(0x08cb, 0xf), /* MEM_LOAD_RETIRED.L2_LINE_MISS */
-	PEBS_EVENT_CONSTRAINT(0x10cb, 0xf), /* MEM_LOAD_RETIRED.DTLB_MISS */
+static struct event_constraint intel_nehalem_pebs_event_constraints[] = {
+	INTEL_EVENT_CONSTRAINT(0x0b, 0xf),  /* MEM_INST_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0x0f, 0xf),  /* MEM_UNCORE_RETIRED.* */
+	PEBS_EVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */
+	INTEL_EVENT_CONSTRAINT(0xc0, 0xf),  /* INST_RETIRED.ANY */
+	INTEL_EVENT_CONSTRAINT(0xc2, 0xf),  /* UOPS_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xc4, 0xf),  /* BR_INST_RETIRED.* */
+	PEBS_EVENT_CONSTRAINT(0x02c5, 0xf), /* BR_MISP_RETIRED.NEAR_CALL */
+	INTEL_EVENT_CONSTRAINT(0xc7, 0xf),  /* SSEX_UOPS_RETIRED.* */
+	PEBS_EVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */
+	INTEL_EVENT_CONSTRAINT(0xcb, 0xf),  /* MEM_LOAD_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xf7, 0xf),  /* FP_ASSIST.* */
+	EVENT_CONSTRAINT_END
+};
+
+static struct event_constraint intel_westmere_pebs_event_constraints[] = {
+	INTEL_EVENT_CONSTRAINT(0x0b, 0xf),  /* MEM_INST_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0x0f, 0xf),  /* MEM_UNCORE_RETIRED.* */
+	PEBS_EVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */
+	INTEL_EVENT_CONSTRAINT(0xc0, 0xf),  /* INSTR_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xc2, 0xf),  /* UOPS_RETIRED.* */
+
+	INTEL_EVENT_CONSTRAINT(0xc4, 0xf),  /* BR_INST_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xc5, 0xf),  /* BR_MISP_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xc7, 0xf),  /* SSEX_UOPS_RETIRED.* */
+	PEBS_EVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */
+	INTEL_EVENT_CONSTRAINT(0xcb, 0xf),  /* MEM_LOAD_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xf7, 0xf),  /* FP_ASSIST.* */
+	EVENT_CONSTRAINT_END
+};
+
+static struct event_constraint intel_snb_pebs_events[] = {
+	PEBS_EVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
+	PEBS_EVENT_CONSTRAINT(0x01c2, 0xf), /* UOPS_RETIRED.ALL */
+	PEBS_EVENT_CONSTRAINT(0x02c2, 0xf), /* UOPS_RETIRED.RETIRE_SLOTS */
+	PEBS_EVENT_CONSTRAINT(0x01c4, 0xf), /* BR_INST_RETIRED.CONDITIONAL */
+	PEBS_EVENT_CONSTRAINT(0x02c4, 0xf), /* BR_INST_RETIRED.NEAR_CALL */
+	PEBS_EVENT_CONSTRAINT(0x04c4, 0xf), /* BR_INST_RETIRED.ALL_BRANCHES */
+	PEBS_EVENT_CONSTRAINT(0x08c4, 0xf), /* BR_INST_RETIRED.NEAR_RETURN */
+	PEBS_EVENT_CONSTRAINT(0x10c4, 0xf), /* BR_INST_RETIRED.NOT_TAKEN */
+	PEBS_EVENT_CONSTRAINT(0x20c4, 0xf), /* BR_INST_RETIRED.NEAR_TAKEN */
+	PEBS_EVENT_CONSTRAINT(0x40c4, 0xf), /* BR_INST_RETIRED.FAR_BRANCH */
+	PEBS_EVENT_CONSTRAINT(0x01c5, 0xf), /* BR_MISP_RETIRED.CONDITIONAL */
+	PEBS_EVENT_CONSTRAINT(0x02c5, 0xf), /* BR_MISP_RETIRED.NEAR_CALL */
+	PEBS_EVENT_CONSTRAINT(0x04c5, 0xf), /* BR_MISP_RETIRED.ALL_BRANCHES */
+	PEBS_EVENT_CONSTRAINT(0x10c5, 0xf), /* BR_MISP_RETIRED.NOT_TAKEN */
+	PEBS_EVENT_CONSTRAINT(0x20c5, 0xf), /* BR_MISP_RETIRED.TAKEN */
+	PEBS_EVENT_CONSTRAINT(0x01cd, 0x8), /* MEM_TRANS_RETIRED.LOAD_LATENCY */
+	PEBS_EVENT_CONSTRAINT(0x02cd, 0x8), /* MEM_TRANS_RETIRED.PRECISE_STORE */
+	PEBS_EVENT_CONSTRAINT(0x11d0, 0xf), /* MEM_UOP_RETIRED.STLB_MISS_LOADS */
+	PEBS_EVENT_CONSTRAINT(0x12d0, 0xf), /* MEM_UOP_RETIRED.STLB_MISS_STORES */
+	PEBS_EVENT_CONSTRAINT(0x21d0, 0xf), /* MEM_UOP_RETIRED.LOCK_LOADS */
+	PEBS_EVENT_CONSTRAINT(0x22d0, 0xf), /* MEM_UOP_RETIRED.LOCK_STORES */
+	PEBS_EVENT_CONSTRAINT(0x41d0, 0xf), /* MEM_UOP_RETIRED.SPLIT_LOADS */
+	PEBS_EVENT_CONSTRAINT(0x42d0, 0xf), /* MEM_UOP_RETIRED.SPLIT_STORES */
+	PEBS_EVENT_CONSTRAINT(0x81d0, 0xf), /* MEM_UOP_RETIRED.ANY_LOADS */
+	PEBS_EVENT_CONSTRAINT(0x82d0, 0xf), /* MEM_UOP_RETIRED.ANY_STORES */
+	PEBS_EVENT_CONSTRAINT(0x01d1, 0xf), /* MEM_LOAD_UOPS_RETIRED.L1_HIT */
+	PEBS_EVENT_CONSTRAINT(0x02d1, 0xf), /* MEM_LOAD_UOPS_RETIRED.L2_HIT */
+	PEBS_EVENT_CONSTRAINT(0x04d1, 0xf), /* MEM_LOAD_UOPS_RETIRED.LLC_HIT */
+	PEBS_EVENT_CONSTRAINT(0x40d1, 0xf), /* MEM_LOAD_UOPS_RETIRED.HIT_LFB */
+	PEBS_EVENT_CONSTRAINT(0x01d2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS */
+	PEBS_EVENT_CONSTRAINT(0x02d2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT */
+	PEBS_EVENT_CONSTRAINT(0x04d2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM */
+	PEBS_EVENT_CONSTRAINT(0x08d2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_NONE */
+	PEBS_EVENT_CONSTRAINT(0x02d4, 0xf), /* MEM_LOAD_UOPS_MISC_RETIRED.LLC_MISS */
 	EVENT_CONSTRAINT_END
 };
 
@@ -695,20 +753,17 @@ static void intel_ds_init(void)
 			printk(KERN_CONT "PEBS fmt0%c, ", pebs_type);
 			x86_pmu.pebs_record_size = sizeof(struct pebs_record_core);
 			x86_pmu.drain_pebs = intel_pmu_drain_pebs_core;
-			x86_pmu.pebs_constraints = intel_core_pebs_events;
 			break;
 
 		case 1:
 			printk(KERN_CONT "PEBS fmt1%c, ", pebs_type);
 			x86_pmu.pebs_record_size = sizeof(struct pebs_record_nhm);
 			x86_pmu.drain_pebs = intel_pmu_drain_pebs_nhm;
-			x86_pmu.pebs_constraints = intel_nehalem_pebs_events;
 			break;
 
 		default:
 			printk(KERN_CONT "no PEBS fmt%d%c, ", format, pebs_type);
 			x86_pmu.pebs = 0;
-			break;
 		}
 	}
 }
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index ff751a9f182b..3769ac822f96 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -764,9 +764,9 @@ static inline int p4_pmu_clear_cccr_ovf(struct hw_perf_event *hwc)
 	u64 v;
 
 	/* an official way for overflow indication */
-	rdmsrl(hwc->config_base + hwc->idx, v);
+	rdmsrl(hwc->config_base, v);
 	if (v & P4_CCCR_OVF) {
-		wrmsrl(hwc->config_base + hwc->idx, v & ~P4_CCCR_OVF);
+		wrmsrl(hwc->config_base, v & ~P4_CCCR_OVF);
 		return 1;
 	}
 
@@ -815,7 +815,7 @@ static inline void p4_pmu_disable_event(struct perf_event *event)
 	 * state we need to clear P4_CCCR_OVF, otherwise interrupt get
 	 * asserted again and again
 	 */
-	(void)checking_wrmsrl(hwc->config_base + hwc->idx,
+	(void)checking_wrmsrl(hwc->config_base,
 		(u64)(p4_config_unpack_cccr(hwc->config)) &
 			~P4_CCCR_ENABLE & ~P4_CCCR_OVF & ~P4_CCCR_RESERVED);
 }
@@ -885,7 +885,7 @@ static void p4_pmu_enable_event(struct perf_event *event)
 	p4_pmu_enable_pebs(hwc->config);
 
 	(void)checking_wrmsrl(escr_addr, escr_conf);
-	(void)checking_wrmsrl(hwc->config_base + hwc->idx,
+	(void)checking_wrmsrl(hwc->config_base,
 				(cccr & ~P4_CCCR_RESERVED) | P4_CCCR_ENABLE);
 }
 
diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c
index 34ba07be2cda..20c097e33860 100644
--- a/arch/x86/kernel/cpu/perf_event_p6.c
+++ b/arch/x86/kernel/cpu/perf_event_p6.c
@@ -68,7 +68,7 @@ p6_pmu_disable_event(struct perf_event *event)
 	if (cpuc->enabled)
 		val |= ARCH_PERFMON_EVENTSEL_ENABLE;
 
-	(void)checking_wrmsrl(hwc->config_base + hwc->idx, val);
+	(void)checking_wrmsrl(hwc->config_base, val);
 }
 
 static void p6_pmu_enable_event(struct perf_event *event)
@@ -81,7 +81,7 @@ static void p6_pmu_enable_event(struct perf_event *event)
 	if (cpuc->enabled)
 		val |= ARCH_PERFMON_EVENTSEL_ENABLE;
 
-	(void)checking_wrmsrl(hwc->config_base + hwc->idx, val);
+	(void)checking_wrmsrl(hwc->config_base, val);
 }
 
 static __initconst const struct x86_pmu p6_pmu = {
diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c
index d5a236615501..966512b2cacf 100644
--- a/arch/x86/kernel/cpu/perfctr-watchdog.c
+++ b/arch/x86/kernel/cpu/perfctr-watchdog.c
@@ -46,6 +46,8 @@ static inline unsigned int nmi_perfctr_msr_to_bit(unsigned int msr)
 	/* returns the bit offset of the performance counter register */
 	switch (boot_cpu_data.x86_vendor) {
 	case X86_VENDOR_AMD:
+		if (msr >= MSR_F15H_PERF_CTR)
+			return (msr - MSR_F15H_PERF_CTR) >> 1;
 		return msr - MSR_K7_PERFCTR0;
 	case X86_VENDOR_INTEL:
 		if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON))
@@ -70,6 +72,8 @@ static inline unsigned int nmi_evntsel_msr_to_bit(unsigned int msr)
 	/* returns the bit offset of the event selection register */
 	switch (boot_cpu_data.x86_vendor) {
 	case X86_VENDOR_AMD:
+		if (msr >= MSR_F15H_PERF_CTL)
+			return (msr - MSR_F15H_PERF_CTL) >> 1;
 		return msr - MSR_K7_EVNTSEL0;
 	case X86_VENDOR_INTEL:
 		if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON))
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
new file mode 100644
index 000000000000..7a8cebc9ff29
--- /dev/null
+++ b/arch/x86/kernel/devicetree.c
@@ -0,0 +1,441 @@
+/*
+ * Architecture specific OF callbacks.
+ */
+#include <linux/bootmem.h>
+#include <linux/io.h>
+#include <linux/interrupt.h>
+#include <linux/list.h>
+#include <linux/of.h>
+#include <linux/of_fdt.h>
+#include <linux/of_address.h>
+#include <linux/of_platform.h>
+#include <linux/of_irq.h>
+#include <linux/slab.h>
+#include <linux/pci.h>
+#include <linux/of_pci.h>
+
+#include <asm/hpet.h>
+#include <asm/irq_controller.h>
+#include <asm/apic.h>
+#include <asm/pci_x86.h>
+
+__initdata u64 initial_dtb;
+char __initdata cmd_line[COMMAND_LINE_SIZE];
+static LIST_HEAD(irq_domains);
+static DEFINE_RAW_SPINLOCK(big_irq_lock);
+
+int __initdata of_ioapic;
+
+#ifdef CONFIG_X86_IO_APIC
+static void add_interrupt_host(struct irq_domain *ih)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&big_irq_lock, flags);
+	list_add(&ih->l, &irq_domains);
+	raw_spin_unlock_irqrestore(&big_irq_lock, flags);
+}
+#endif
+
+static struct irq_domain *get_ih_from_node(struct device_node *controller)
+{
+	struct irq_domain *ih, *found = NULL;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&big_irq_lock, flags);
+	list_for_each_entry(ih, &irq_domains, l) {
+		if (ih->controller ==  controller) {
+			found = ih;
+			break;
+		}
+	}
+	raw_spin_unlock_irqrestore(&big_irq_lock, flags);
+	return found;
+}
+
+unsigned int irq_create_of_mapping(struct device_node *controller,
+				   const u32 *intspec, unsigned int intsize)
+{
+	struct irq_domain *ih;
+	u32 virq, type;
+	int ret;
+
+	ih = get_ih_from_node(controller);
+	if (!ih)
+		return 0;
+	ret = ih->xlate(ih, intspec, intsize, &virq, &type);
+	if (ret)
+		return ret;
+	if (type == IRQ_TYPE_NONE)
+		return virq;
+	/* set the mask if it is different from current */
+	if (type == (irq_to_desc(virq)->status & IRQF_TRIGGER_MASK))
+		set_irq_type(virq, type);
+	return virq;
+}
+EXPORT_SYMBOL_GPL(irq_create_of_mapping);
+
+unsigned long pci_address_to_pio(phys_addr_t address)
+{
+	/*
+	 * The ioport address can be directly used by inX / outX
+	 */
+	BUG_ON(address >= (1 << 16));
+	return (unsigned long)address;
+}
+EXPORT_SYMBOL_GPL(pci_address_to_pio);
+
+void __init early_init_dt_scan_chosen_arch(unsigned long node)
+{
+	BUG();
+}
+
+void __init early_init_dt_add_memory_arch(u64 base, u64 size)
+{
+	BUG();
+}
+
+void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align)
+{
+	return __alloc_bootmem(size, align, __pa(MAX_DMA_ADDRESS));
+}
+
+void __init add_dtb(u64 data)
+{
+	initial_dtb = data + offsetof(struct setup_data, data);
+}
+
+/*
+ * CE4100 ids. Will be moved to machine_device_initcall() once we have it.
+ */
+static struct of_device_id __initdata ce4100_ids[] = {
+	{ .compatible = "intel,ce4100-cp", },
+	{ .compatible = "isa", },
+	{ .compatible = "pci", },
+	{},
+};
+
+static int __init add_bus_probe(void)
+{
+	if (!of_have_populated_dt())
+		return 0;
+
+	return of_platform_bus_probe(NULL, ce4100_ids, NULL);
+}
+module_init(add_bus_probe);
+
+#ifdef CONFIG_PCI
+static int x86_of_pci_irq_enable(struct pci_dev *dev)
+{
+	struct of_irq oirq;
+	u32 virq;
+	int ret;
+	u8 pin;
+
+	ret = pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin);
+	if (ret)
+		return ret;
+	if (!pin)
+		return 0;
+
+	ret = of_irq_map_pci(dev, &oirq);
+	if (ret)
+		return ret;
+
+	virq = irq_create_of_mapping(oirq.controller, oirq.specifier,
+			oirq.size);
+	if (virq == 0)
+		return -EINVAL;
+	dev->irq = virq;
+	return 0;
+}
+
+static void x86_of_pci_irq_disable(struct pci_dev *dev)
+{
+}
+
+void __cpuinit x86_of_pci_init(void)
+{
+	struct device_node *np;
+
+	pcibios_enable_irq = x86_of_pci_irq_enable;
+	pcibios_disable_irq = x86_of_pci_irq_disable;
+
+	for_each_node_by_type(np, "pci") {
+		const void *prop;
+		struct pci_bus *bus;
+		unsigned int bus_min;
+		struct device_node *child;
+
+		prop = of_get_property(np, "bus-range", NULL);
+		if (!prop)
+			continue;
+		bus_min = be32_to_cpup(prop);
+
+		bus = pci_find_bus(0, bus_min);
+		if (!bus) {
+			printk(KERN_ERR "Can't find a node for bus %s.\n",
+					np->full_name);
+			continue;
+		}
+
+		if (bus->self)
+			bus->self->dev.of_node = np;
+		else
+			bus->dev.of_node = np;
+
+		for_each_child_of_node(np, child) {
+			struct pci_dev *dev;
+			u32 devfn;
+
+			prop = of_get_property(child, "reg", NULL);
+			if (!prop)
+				continue;
+
+			devfn = (be32_to_cpup(prop) >> 8) & 0xff;
+			dev = pci_get_slot(bus, devfn);
+			if (!dev)
+				continue;
+			dev->dev.of_node = child;
+			pci_dev_put(dev);
+		}
+	}
+}
+#endif
+
+static void __init dtb_setup_hpet(void)
+{
+#ifdef CONFIG_HPET_TIMER
+	struct device_node *dn;
+	struct resource r;
+	int ret;
+
+	dn = of_find_compatible_node(NULL, NULL, "intel,ce4100-hpet");
+	if (!dn)
+		return;
+	ret = of_address_to_resource(dn, 0, &r);
+	if (ret) {
+		WARN_ON(1);
+		return;
+	}
+	hpet_address = r.start;
+#endif
+}
+
+static void __init dtb_lapic_setup(void)
+{
+#ifdef CONFIG_X86_LOCAL_APIC
+	struct device_node *dn;
+	struct resource r;
+	int ret;
+
+	dn = of_find_compatible_node(NULL, NULL, "intel,ce4100-lapic");
+	if (!dn)
+		return;
+
+	ret = of_address_to_resource(dn, 0, &r);
+	if (WARN_ON(ret))
+		return;
+
+	/* Did the boot loader setup the local APIC ? */
+	if (!cpu_has_apic) {
+		if (apic_force_enable(r.start))
+			return;
+	}
+	smp_found_config = 1;
+	pic_mode = 1;
+	register_lapic_address(r.start);
+	generic_processor_info(boot_cpu_physical_apicid,
+			       GET_APIC_VERSION(apic_read(APIC_LVR)));
+#endif
+}
+
+#ifdef CONFIG_X86_IO_APIC
+static unsigned int ioapic_id;
+
+static void __init dtb_add_ioapic(struct device_node *dn)
+{
+	struct resource r;
+	int ret;
+
+	ret = of_address_to_resource(dn, 0, &r);
+	if (ret) {
+		printk(KERN_ERR "Can't obtain address from node %s.\n",
+				dn->full_name);
+		return;
+	}
+	mp_register_ioapic(++ioapic_id, r.start, gsi_top);
+}
+
+static void __init dtb_ioapic_setup(void)
+{
+	struct device_node *dn;
+
+	for_each_compatible_node(dn, NULL, "intel,ce4100-ioapic")
+		dtb_add_ioapic(dn);
+
+	if (nr_ioapics) {
+		of_ioapic = 1;
+		return;
+	}
+	printk(KERN_ERR "Error: No information about IO-APIC in OF.\n");
+}
+#else
+static void __init dtb_ioapic_setup(void) {}
+#endif
+
+static void __init dtb_apic_setup(void)
+{
+	dtb_lapic_setup();
+	dtb_ioapic_setup();
+}
+
+#ifdef CONFIG_OF_FLATTREE
+static void __init x86_flattree_get_config(void)
+{
+	u32 size, map_len;
+	void *new_dtb;
+
+	if (!initial_dtb)
+		return;
+
+	map_len = max(PAGE_SIZE - (initial_dtb & ~PAGE_MASK),
+			(u64)sizeof(struct boot_param_header));
+
+	initial_boot_params = early_memremap(initial_dtb, map_len);
+	size = be32_to_cpu(initial_boot_params->totalsize);
+	if (map_len < size) {
+		early_iounmap(initial_boot_params, map_len);
+		initial_boot_params = early_memremap(initial_dtb, size);
+		map_len = size;
+	}
+
+	new_dtb = alloc_bootmem(size);
+	memcpy(new_dtb, initial_boot_params, size);
+	early_iounmap(initial_boot_params, map_len);
+
+	initial_boot_params = new_dtb;
+
+	/* root level address cells */
+	of_scan_flat_dt(early_init_dt_scan_root, NULL);
+
+	unflatten_device_tree();
+}
+#else
+static inline void x86_flattree_get_config(void) { }
+#endif
+
+void __init x86_dtb_init(void)
+{
+	x86_flattree_get_config();
+
+	if (!of_have_populated_dt())
+		return;
+
+	dtb_setup_hpet();
+	dtb_apic_setup();
+}
+
+#ifdef CONFIG_X86_IO_APIC
+
+struct of_ioapic_type {
+	u32 out_type;
+	u32 trigger;
+	u32 polarity;
+};
+
+static struct of_ioapic_type of_ioapic_type[] =
+{
+	{
+		.out_type	= IRQ_TYPE_EDGE_RISING,
+		.trigger	= IOAPIC_EDGE,
+		.polarity	= 1,
+	},
+	{
+		.out_type	= IRQ_TYPE_LEVEL_LOW,
+		.trigger	= IOAPIC_LEVEL,
+		.polarity	= 0,
+	},
+	{
+		.out_type	= IRQ_TYPE_LEVEL_HIGH,
+		.trigger	= IOAPIC_LEVEL,
+		.polarity	= 1,
+	},
+	{
+		.out_type	= IRQ_TYPE_EDGE_FALLING,
+		.trigger	= IOAPIC_EDGE,
+		.polarity	= 0,
+	},
+};
+
+static int ioapic_xlate(struct irq_domain *id, const u32 *intspec, u32 intsize,
+			u32 *out_hwirq, u32 *out_type)
+{
+	struct io_apic_irq_attr attr;
+	struct of_ioapic_type *it;
+	u32 line, idx, type;
+
+	if (intsize < 2)
+		return -EINVAL;
+
+	line = *intspec;
+	idx = (u32) id->priv;
+	*out_hwirq = line + mp_gsi_routing[idx].gsi_base;
+
+	intspec++;
+	type = *intspec;
+
+	if (type >= ARRAY_SIZE(of_ioapic_type))
+		return -EINVAL;
+
+	it = of_ioapic_type + type;
+	*out_type = it->out_type;
+
+	set_io_apic_irq_attr(&attr, idx, line, it->trigger, it->polarity);
+
+	return io_apic_setup_irq_pin(*out_hwirq, cpu_to_node(0), &attr);
+}
+
+static void __init ioapic_add_ofnode(struct device_node *np)
+{
+	struct resource r;
+	int i, ret;
+
+	ret = of_address_to_resource(np, 0, &r);
+	if (ret) {
+		printk(KERN_ERR "Failed to obtain address for %s\n",
+				np->full_name);
+		return;
+	}
+
+	for (i = 0; i < nr_ioapics; i++) {
+		if (r.start == mp_ioapics[i].apicaddr) {
+			struct irq_domain *id;
+
+			id = kzalloc(sizeof(*id), GFP_KERNEL);
+			BUG_ON(!id);
+			id->controller = np;
+			id->xlate = ioapic_xlate;
+			id->priv = (void *)i;
+			add_interrupt_host(id);
+			return;
+		}
+	}
+	printk(KERN_ERR "IOxAPIC at %s is not registered.\n", np->full_name);
+}
+
+void __init x86_add_irq_domains(void)
+{
+	struct device_node *dp;
+
+	if (!of_have_populated_dt())
+		return;
+
+	for_each_node_with_property(dp, "interrupt-controller") {
+		if (of_device_is_compatible(dp, "intel,ce4100-ioapic"))
+			ioapic_add_ofnode(dp);
+	}
+}
+#else
+void __init x86_add_irq_domains(void) { }
+#endif
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index df20723a6a1b..220a1c11cfde 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -320,31 +320,6 @@ void die(const char *str, struct pt_regs *regs, long err)
 	oops_end(flags, regs, sig);
 }
 
-void notrace __kprobes
-die_nmi(char *str, struct pt_regs *regs, int do_panic)
-{
-	unsigned long flags;
-
-	if (notify_die(DIE_NMIWATCHDOG, str, regs, 0, 2, SIGINT) == NOTIFY_STOP)
-		return;
-
-	/*
-	 * We are in trouble anyway, lets at least try
-	 * to get a message out.
-	 */
-	flags = oops_begin();
-	printk(KERN_EMERG "%s", str);
-	printk(" on CPU%d, ip %08lx, registers:\n",
-		smp_processor_id(), regs->ip);
-	show_registers(regs);
-	oops_end(flags, regs, 0);
-	if (do_panic || panic_on_oops)
-		panic("Non maskable interrupt");
-	nmi_exit();
-	local_irq_enable();
-	do_exit(SIGBUS);
-}
-
 static int __init oops_setup(char *s)
 {
 	if (!s)
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 294f26da0c0c..cdf5bfd9d4d5 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -667,21 +667,15 @@ __init void e820_setup_gap(void)
  * boot_params.e820_map, others are passed via SETUP_E820_EXT node of
  * linked list of struct setup_data, which is parsed here.
  */
-void __init parse_e820_ext(struct setup_data *sdata, unsigned long pa_data)
+void __init parse_e820_ext(struct setup_data *sdata)
 {
-	u32 map_len;
 	int entries;
 	struct e820entry *extmap;
 
 	entries = sdata->len / sizeof(struct e820entry);
-	map_len = sdata->len + sizeof(struct setup_data);
-	if (map_len > PAGE_SIZE)
-		sdata = early_ioremap(pa_data, map_len);
 	extmap = (struct e820entry *)(sdata->data);
 	__append_e820_map(extmap, entries);
 	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
-	if (map_len > PAGE_SIZE)
-		early_iounmap(sdata, map_len);
 	printk(KERN_INFO "extended physical RAM map:\n");
 	e820_print_map("extended");
 }
@@ -847,15 +841,21 @@ static int __init parse_memopt(char *p)
 	if (!p)
 		return -EINVAL;
 
-#ifdef CONFIG_X86_32
 	if (!strcmp(p, "nopentium")) {
+#ifdef CONFIG_X86_32
 		setup_clear_cpu_cap(X86_FEATURE_PSE);
 		return 0;
-	}
+#else
+		printk(KERN_WARNING "mem=nopentium ignored! (only supported on x86_32)\n");
+		return -EINVAL;
 #endif
+	}
 
 	userdef = 1;
 	mem_size = memparse(p, &p);
+	/* don't remove all of memory when handling "mem={invalid}" param */
+	if (mem_size == 0)
+		return -EINVAL;
 	e820_remove_range(mem_size, ULLONG_MAX - mem_size, E820_RAM, 1);
 
 	return 0;
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index c8b4efad7ebb..fa41f7298c84 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -65,6 +65,8 @@
 #define sysexit_audit	syscall_exit_work
 #endif
 
+	.section .entry.text, "ax"
+
 /*
  * We use macros for low-level operations which need to be overridden
  * for paravirtualization.  The following will never clobber any registers:
@@ -395,7 +397,7 @@ sysenter_past_esp:
 	 * A tiny bit of offset fixup is necessary - 4*4 means the 4 words
 	 * pushed above; +8 corresponds to copy_thread's esp0 setting.
 	 */
-	pushl_cfi ((TI_sysenter_return)-THREAD_SIZE_asm+8+4*4)(%esp)
+	pushl_cfi ((TI_sysenter_return)-THREAD_SIZE+8+4*4)(%esp)
 	CFI_REL_OFFSET eip, 0
 
 	pushl_cfi %eax
@@ -788,7 +790,7 @@ ENDPROC(ptregs_clone)
  */
 .section .init.rodata,"a"
 ENTRY(interrupt)
-.text
+.section .entry.text, "ax"
 	.p2align 5
 	.p2align CONFIG_X86_L1_CACHE_SHIFT
 ENTRY(irq_entries_start)
@@ -807,7 +809,7 @@ vector=FIRST_EXTERNAL_VECTOR
       .endif
       .previous
 	.long 1b
-      .text
+      .section .entry.text, "ax"
 vector=vector+1
     .endif
   .endr
@@ -1409,8 +1411,7 @@ END(general_protection)
 #ifdef CONFIG_KVM_GUEST
 ENTRY(async_page_fault)
 	RING0_EC_FRAME
-	pushl $do_async_page_fault
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi $do_async_page_fault
 	jmp error_code
 	CFI_ENDPROC
 END(apf_page_fault)
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index aed1ffbeb0c9..b72b4a6466a9 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -61,6 +61,8 @@
 #define __AUDIT_ARCH_LE	   0x40000000
 
 	.code64
+	.section .entry.text, "ax"
+
 #ifdef CONFIG_FUNCTION_TRACER
 #ifdef CONFIG_DYNAMIC_FTRACE
 ENTRY(mcount)
@@ -744,7 +746,7 @@ END(stub_rt_sigreturn)
  */
 	.section .init.rodata,"a"
 ENTRY(interrupt)
-	.text
+	.section .entry.text
 	.p2align 5
 	.p2align CONFIG_X86_L1_CACHE_SHIFT
 ENTRY(irq_entries_start)
@@ -763,7 +765,7 @@ vector=FIRST_EXTERNAL_VECTOR
       .endif
       .previous
 	.quad 1b
-      .text
+      .section .entry.text
 vector=vector+1
     .endif
   .endr
@@ -975,9 +977,12 @@ apicinterrupt X86_PLATFORM_IPI_VECTOR \
 	x86_platform_ipi smp_x86_platform_ipi
 
 #ifdef CONFIG_SMP
-.irpc idx, "01234567"
+.irp idx,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15, \
+	16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31
+.if NUM_INVALIDATE_TLB_VECTORS > \idx
 apicinterrupt (INVALIDATE_TLB_VECTOR_START)+\idx \
 	invalidate_interrupt\idx smp_invalidate_interrupt
+.endif
 .endr
 #endif
 
@@ -1248,7 +1253,7 @@ ENTRY(xen_do_hypervisor_callback)   # do_hypervisor_callback(struct *pt_regs)
 	decl PER_CPU_VAR(irq_count)
 	jmp  error_exit
 	CFI_ENDPROC
-END(do_hypervisor_callback)
+END(xen_do_hypervisor_callback)
 
 /*
  * Hypervisor uses this for application faults while it executes.
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 382eb2936d4d..a93742a57468 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -437,18 +437,19 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
 		return;
 	}
 
-	if (ftrace_push_return_trace(old, self_addr, &trace.depth,
-		    frame_pointer) == -EBUSY) {
-		*parent = old;
-		return;
-	}
-
 	trace.func = self_addr;
+	trace.depth = current->curr_ret_stack + 1;
 
 	/* Only trace if the calling function expects to */
 	if (!ftrace_graph_entry(&trace)) {
-		current->curr_ret_stack--;
 		*parent = old;
+		return;
+	}
+
+	if (ftrace_push_return_trace(old, self_addr, &trace.depth,
+		    frame_pointer) == -EBUSY) {
+		*parent = old;
+		return;
 	}
 }
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 767d6c43de37..ce0be7cd085e 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -73,7 +73,7 @@ MAPPING_BEYOND_END = PAGE_TABLE_SIZE(LOWMEM_PAGES) << PAGE_SHIFT
  */
 KERNEL_PAGES = LOWMEM_PAGES
 
-INIT_MAP_SIZE = PAGE_TABLE_SIZE(KERNEL_PAGES) * PAGE_SIZE_asm
+INIT_MAP_SIZE = PAGE_TABLE_SIZE(KERNEL_PAGES) * PAGE_SIZE
 RESERVE_BRK(pagetables, INIT_MAP_SIZE)
 
 /*
@@ -137,7 +137,7 @@ ENTRY(startup_32)
 	movsl
 1:
 
-#ifdef CONFIG_OLPC_OPENFIRMWARE
+#ifdef CONFIG_OLPC
 	/* save OFW's pgdir table for later use when calling into OFW */
 	movl %cr3, %eax
 	movl %eax, pa(olpc_ofw_pgd)
@@ -623,7 +623,7 @@ ENTRY(initial_code)
  * BSS section
  */
 __PAGE_ALIGNED_BSS
-	.align PAGE_SIZE_asm
+	.align PAGE_SIZE
 #ifdef CONFIG_X86_PAE
 initial_pg_pmd:
 	.fill 1024*KPMDS,4,0
@@ -644,7 +644,7 @@ ENTRY(swapper_pg_dir)
 #ifdef CONFIG_X86_PAE
 __PAGE_ALIGNED_DATA
 	/* Page-aligned for the benefit of paravirt? */
-	.align PAGE_SIZE_asm
+	.align PAGE_SIZE
 ENTRY(initial_page_table)
 	.long	pa(initial_pg_pmd+PGD_IDENT_ATTR),0	/* low identity map */
 # if KPMDS == 3
@@ -662,7 +662,7 @@ ENTRY(initial_page_table)
 # else
 #  error "Kernel PMDs should be 1, 2 or 3"
 # endif
-	.align PAGE_SIZE_asm		/* needs to be page-sized too */
+	.align PAGE_SIZE		/* needs to be page-sized too */
 #endif
 
 .data
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 4ff5968f12d2..bfe8f729e086 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -503,7 +503,7 @@ static int hpet_assign_irq(struct hpet_dev *dev)
 	if (!irq)
 		return -EINVAL;
 
-	set_irq_data(irq, dev);
+	irq_set_handler_data(irq, dev);
 
 	if (hpet_setup_msi_irq(irq))
 		return -EINVAL;
diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
index 20757cb2efa3..d9ca749c123b 100644
--- a/arch/x86/kernel/i8259.c
+++ b/arch/x86/kernel/i8259.c
@@ -112,7 +112,7 @@ static void make_8259A_irq(unsigned int irq)
 {
 	disable_irq_nosync(irq);
 	io_apic_irqs &= ~(1<<irq);
-	set_irq_chip_and_handler_name(irq, &i8259A_chip, handle_level_irq,
+	irq_set_chip_and_handler_name(irq, &i8259A_chip, handle_level_irq,
 				      i8259A_chip.name);
 	enable_irq(irq);
 }
diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c
index 8eec0ec59af2..8c968974253d 100644
--- a/arch/x86/kernel/ioport.c
+++ b/arch/x86/kernel/ioport.c
@@ -14,22 +14,9 @@
 #include <linux/slab.h>
 #include <linux/thread_info.h>
 #include <linux/syscalls.h>
+#include <linux/bitmap.h>
 #include <asm/syscalls.h>
 
-/* Set EXTENT bits starting at BASE in BITMAP to value TURN_ON. */
-static void set_bitmap(unsigned long *bitmap, unsigned int base,
-		       unsigned int extent, int new_value)
-{
-	unsigned int i;
-
-	for (i = base; i < base + extent; i++) {
-		if (new_value)
-			__set_bit(i, bitmap);
-		else
-			__clear_bit(i, bitmap);
-	}
-}
-
 /*
  * this changes the io permissions bitmap in the current task.
  */
@@ -69,7 +56,10 @@ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on)
 	 */
 	tss = &per_cpu(init_tss, get_cpu());
 
-	set_bitmap(t->io_bitmap_ptr, from, num, !turn_on);
+	if (turn_on)
+		bitmap_clear(t->io_bitmap_ptr, from, num);
+	else
+		bitmap_set(t->io_bitmap_ptr, from, num);
 
 	/*
 	 * Search for a (possibly new) maximum. This is simple and stupid,
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 387b6a0c9e81..948a31eae75f 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -44,9 +44,9 @@ void ack_bad_irq(unsigned int irq)
 
 #define irq_stats(x)		(&per_cpu(irq_stat, x))
 /*
- * /proc/interrupts printing:
+ * /proc/interrupts printing for arch specific interrupts
  */
-static int show_other_interrupts(struct seq_file *p, int prec)
+int arch_show_interrupts(struct seq_file *p, int prec)
 {
 	int j;
 
@@ -122,59 +122,6 @@ static int show_other_interrupts(struct seq_file *p, int prec)
 	return 0;
 }
 
-int show_interrupts(struct seq_file *p, void *v)
-{
-	unsigned long flags, any_count = 0;
-	int i = *(loff_t *) v, j, prec;
-	struct irqaction *action;
-	struct irq_desc *desc;
-
-	if (i > nr_irqs)
-		return 0;
-
-	for (prec = 3, j = 1000; prec < 10 && j <= nr_irqs; ++prec)
-		j *= 10;
-
-	if (i == nr_irqs)
-		return show_other_interrupts(p, prec);
-
-	/* print header */
-	if (i == 0) {
-		seq_printf(p, "%*s", prec + 8, "");
-		for_each_online_cpu(j)
-			seq_printf(p, "CPU%-8d", j);
-		seq_putc(p, '\n');
-	}
-
-	desc = irq_to_desc(i);
-	if (!desc)
-		return 0;
-
-	raw_spin_lock_irqsave(&desc->lock, flags);
-	for_each_online_cpu(j)
-		any_count |= kstat_irqs_cpu(i, j);
-	action = desc->action;
-	if (!action && !any_count)
-		goto out;
-
-	seq_printf(p, "%*d: ", prec, i);
-	for_each_online_cpu(j)
-		seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
-	seq_printf(p, " %8s", desc->irq_data.chip->name);
-	seq_printf(p, "-%-8s", desc->name);
-
-	if (action) {
-		seq_printf(p, "  %s", action->name);
-		while ((action = action->next) != NULL)
-			seq_printf(p, ", %s", action->name);
-	}
-
-	seq_putc(p, '\n');
-out:
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
-	return 0;
-}
-
 /*
  * /proc/stat helpers
  */
@@ -276,15 +223,6 @@ void smp_x86_platform_ipi(struct pt_regs *regs)
 
 EXPORT_SYMBOL_GPL(vector_used_by_percpu_irq);
 
-#ifdef CONFIG_OF
-unsigned int irq_create_of_mapping(struct device_node *controller,
-		const u32 *intspec, unsigned int intsize)
-{
-	return intspec[0];
-}
-EXPORT_SYMBOL_GPL(irq_create_of_mapping);
-#endif
-
 #ifdef CONFIG_HOTPLUG_CPU
 /* A cpu has been removed from cpu_online_mask.  Reset irq affinities. */
 void fixup_irqs(void)
@@ -293,6 +231,7 @@ void fixup_irqs(void)
 	static int warned;
 	struct irq_desc *desc;
 	struct irq_data *data;
+	struct irq_chip *chip;
 
 	for_each_irq_desc(irq, desc) {
 		int break_affinity = 0;
@@ -307,10 +246,10 @@ void fixup_irqs(void)
 		/* interrupt's are disabled at this point */
 		raw_spin_lock(&desc->lock);
 
-		data = &desc->irq_data;
+		data = irq_desc_get_irq_data(desc);
 		affinity = data->affinity;
 		if (!irq_has_action(irq) ||
-		    cpumask_equal(affinity, cpu_online_mask)) {
+		    cpumask_subset(affinity, cpu_online_mask)) {
 			raw_spin_unlock(&desc->lock);
 			continue;
 		}
@@ -327,16 +266,17 @@ void fixup_irqs(void)
 			affinity = cpu_all_mask;
 		}
 
-		if (!(desc->status & IRQ_MOVE_PCNTXT) && data->chip->irq_mask)
-			data->chip->irq_mask(data);
+		chip = irq_data_get_irq_chip(data);
+		if (!irqd_can_move_in_process_context(data) && chip->irq_mask)
+			chip->irq_mask(data);
 
-		if (data->chip->irq_set_affinity)
-			data->chip->irq_set_affinity(data, affinity, true);
+		if (chip->irq_set_affinity)
+			chip->irq_set_affinity(data, affinity, true);
 		else if (!(warned++))
 			set_affinity = 0;
 
-		if (!(desc->status & IRQ_MOVE_PCNTXT) && data->chip->irq_unmask)
-			data->chip->irq_unmask(data);
+		if (!irqd_can_move_in_process_context(data) && chip->irq_unmask)
+			chip->irq_unmask(data);
 
 		raw_spin_unlock(&desc->lock);
 
@@ -368,10 +308,11 @@ void fixup_irqs(void)
 			irq = __this_cpu_read(vector_irq[vector]);
 
 			desc = irq_to_desc(irq);
-			data = &desc->irq_data;
+			data = irq_desc_get_irq_data(desc);
+			chip = irq_data_get_irq_chip(data);
 			raw_spin_lock(&desc->lock);
-			if (data->chip->irq_retrigger)
-				data->chip->irq_retrigger(data);
+			if (chip->irq_retrigger)
+				chip->irq_retrigger(data);
 			raw_spin_unlock(&desc->lock);
 		}
 	}
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index c752e973958d..f470e4ef993e 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -25,6 +25,7 @@
 #include <asm/setup.h>
 #include <asm/i8259.h>
 #include <asm/traps.h>
+#include <asm/prom.h>
 
 /*
  * ISA PIC or low IO-APIC triggered (INTA-cycle or APIC) interrupts:
@@ -71,6 +72,7 @@ static irqreturn_t math_error_irq(int cpl, void *dev_id)
 static struct irqaction fpu_irq = {
 	.handler = math_error_irq,
 	.name = "fpu",
+	.flags = IRQF_NO_THREAD,
 };
 #endif
 
@@ -80,6 +82,7 @@ static struct irqaction fpu_irq = {
 static struct irqaction irq2 = {
 	.handler = no_action,
 	.name = "cascade",
+	.flags = IRQF_NO_THREAD,
 };
 
 DEFINE_PER_CPU(vector_irq_t, vector_irq) = {
@@ -110,7 +113,7 @@ void __init init_ISA_irqs(void)
 	legacy_pic->init(0);
 
 	for (i = 0; i < legacy_pic->nr_legacy_irqs; i++)
-		set_irq_chip_and_handler_name(i, chip, handle_level_irq, name);
+		irq_set_chip_and_handler_name(i, chip, handle_level_irq, name);
 }
 
 void __init init_IRQ(void)
@@ -118,6 +121,12 @@ void __init init_IRQ(void)
 	int i;
 
 	/*
+	 * We probably need a better place for this, but it works for
+	 * now ...
+	 */
+	x86_add_irq_domains();
+
+	/*
 	 * On cpu 0, Assign IRQ0_VECTOR..IRQ15_VECTOR's to IRQ 0..15.
 	 * If these IRQ's are handled by legacy interrupt-controllers like PIC,
 	 * then this configuration will likely be static after the boot. If
@@ -164,14 +173,77 @@ static void __init smp_intr_init(void)
 	alloc_intr_gate(RESCHEDULE_VECTOR, reschedule_interrupt);
 
 	/* IPIs for invalidation */
-	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+0, invalidate_interrupt0);
-	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+1, invalidate_interrupt1);
-	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+2, invalidate_interrupt2);
-	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+3, invalidate_interrupt3);
-	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+4, invalidate_interrupt4);
-	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+5, invalidate_interrupt5);
-	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+6, invalidate_interrupt6);
-	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+7, invalidate_interrupt7);
+#define ALLOC_INVTLB_VEC(NR) \
+	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+NR, \
+		invalidate_interrupt##NR)
+
+	switch (NUM_INVALIDATE_TLB_VECTORS) {
+	default:
+		ALLOC_INVTLB_VEC(31);
+	case 31:
+		ALLOC_INVTLB_VEC(30);
+	case 30:
+		ALLOC_INVTLB_VEC(29);
+	case 29:
+		ALLOC_INVTLB_VEC(28);
+	case 28:
+		ALLOC_INVTLB_VEC(27);
+	case 27:
+		ALLOC_INVTLB_VEC(26);
+	case 26:
+		ALLOC_INVTLB_VEC(25);
+	case 25:
+		ALLOC_INVTLB_VEC(24);
+	case 24:
+		ALLOC_INVTLB_VEC(23);
+	case 23:
+		ALLOC_INVTLB_VEC(22);
+	case 22:
+		ALLOC_INVTLB_VEC(21);
+	case 21:
+		ALLOC_INVTLB_VEC(20);
+	case 20:
+		ALLOC_INVTLB_VEC(19);
+	case 19:
+		ALLOC_INVTLB_VEC(18);
+	case 18:
+		ALLOC_INVTLB_VEC(17);
+	case 17:
+		ALLOC_INVTLB_VEC(16);
+	case 16:
+		ALLOC_INVTLB_VEC(15);
+	case 15:
+		ALLOC_INVTLB_VEC(14);
+	case 14:
+		ALLOC_INVTLB_VEC(13);
+	case 13:
+		ALLOC_INVTLB_VEC(12);
+	case 12:
+		ALLOC_INVTLB_VEC(11);
+	case 11:
+		ALLOC_INVTLB_VEC(10);
+	case 10:
+		ALLOC_INVTLB_VEC(9);
+	case 9:
+		ALLOC_INVTLB_VEC(8);
+	case 8:
+		ALLOC_INVTLB_VEC(7);
+	case 7:
+		ALLOC_INVTLB_VEC(6);
+	case 6:
+		ALLOC_INVTLB_VEC(5);
+	case 5:
+		ALLOC_INVTLB_VEC(4);
+	case 4:
+		ALLOC_INVTLB_VEC(3);
+	case 3:
+		ALLOC_INVTLB_VEC(2);
+	case 2:
+		ALLOC_INVTLB_VEC(1);
+	case 1:
+		ALLOC_INVTLB_VEC(0);
+		break;
+	}
 
 	/* IPI for generic function call */
 	alloc_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt);
@@ -243,7 +315,7 @@ void __init native_init_IRQ(void)
 			set_intr_gate(i, interrupt[i-FIRST_EXTERNAL_VECTOR]);
 	}
 
-	if (!acpi_ioapic)
+	if (!acpi_ioapic && !of_ioapic)
 		setup_irq(2, &irq2);
 
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index a4130005028a..7c64c420a9f6 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -533,15 +533,6 @@ static int __kgdb_notify(struct die_args *args, unsigned long cmd)
 		}
 		return NOTIFY_DONE;
 
-	case DIE_NMIWATCHDOG:
-		if (atomic_read(&kgdb_active) != -1) {
-			/* KGDB CPU roundup: */
-			kgdb_nmicallback(raw_smp_processor_id(), regs);
-			return NOTIFY_STOP;
-		}
-		/* Enter debugger: */
-		break;
-
 	case DIE_DEBUG:
 		if (atomic_read(&kgdb_cpu_doing_single_step) != -1) {
 			if (user_mode(regs))
diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c
index d91c477b3f62..c969fd9d1566 100644
--- a/arch/x86/kernel/kprobes.c
+++ b/arch/x86/kernel/kprobes.c
@@ -1276,6 +1276,14 @@ static int __kprobes can_optimize(unsigned long paddr)
 	if (!kallsyms_lookup_size_offset(paddr, &size, &offset))
 		return 0;
 
+	/*
+	 * Do not optimize in the entry code due to the unstable
+	 * stack handling.
+	 */
+	if ((paddr >= (unsigned long )__entry_text_start) &&
+	    (paddr <  (unsigned long )__entry_text_end))
+		return 0;
+
 	/* Check there is enough space for a relative jump. */
 	if (size - offset < RELATIVEJUMP_SIZE)
 		return 0;
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index 0fe6d1a66c38..c5610384ab16 100644
--- a/arch/x86/kernel/microcode_amd.c
+++ b/arch/x86/kernel/microcode_amd.c
@@ -66,7 +66,6 @@ struct microcode_amd {
 	unsigned int			mpb[0];
 };
 
-#define UCODE_MAX_SIZE			2048
 #define UCODE_CONTAINER_SECTION_HDR	8
 #define UCODE_CONTAINER_HEADER_SIZE	12
 
@@ -77,20 +76,20 @@ static int collect_cpu_info_amd(int cpu, struct cpu_signature *csig)
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 	u32 dummy;
 
-	memset(csig, 0, sizeof(*csig));
 	if (c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10) {
-		pr_warning("microcode: CPU%d: AMD CPU family 0x%x not "
-			   "supported\n", cpu, c->x86);
+		pr_warning("CPU%d: family %d not supported\n", cpu, c->x86);
 		return -1;
 	}
+
 	rdmsr(MSR_AMD64_PATCH_LEVEL, csig->rev, dummy);
-	pr_info("CPU%d: patch_level=0x%x\n", cpu, csig->rev);
+	pr_info("CPU%d: patch_level=0x%08x\n", cpu, csig->rev);
+
 	return 0;
 }
 
-static int get_matching_microcode(int cpu, void *mc, int rev)
+static int get_matching_microcode(int cpu, struct microcode_header_amd *mc_hdr,
+				  int rev)
 {
-	struct microcode_header_amd *mc_header = mc;
 	unsigned int current_cpu_id;
 	u16 equiv_cpu_id = 0;
 	unsigned int i = 0;
@@ -109,17 +108,17 @@ static int get_matching_microcode(int cpu, void *mc, int rev)
 	if (!equiv_cpu_id)
 		return 0;
 
-	if (mc_header->processor_rev_id != equiv_cpu_id)
+	if (mc_hdr->processor_rev_id != equiv_cpu_id)
 		return 0;
 
 	/* ucode might be chipset specific -- currently we don't support this */
-	if (mc_header->nb_dev_id || mc_header->sb_dev_id) {
-		pr_err("CPU%d: loading of chipset specific code not yet supported\n",
+	if (mc_hdr->nb_dev_id || mc_hdr->sb_dev_id) {
+		pr_err("CPU%d: chipset specific code not yet supported\n",
 		       cpu);
 		return 0;
 	}
 
-	if (mc_header->patch_id <= rev)
+	if (mc_hdr->patch_id <= rev)
 		return 0;
 
 	return 1;
@@ -144,71 +143,93 @@ static int apply_microcode_amd(int cpu)
 
 	/* check current patch id and patch's id for match */
 	if (rev != mc_amd->hdr.patch_id) {
-		pr_err("CPU%d: update failed (for patch_level=0x%x)\n",
+		pr_err("CPU%d: update failed for patch_level=0x%08x\n",
 		       cpu, mc_amd->hdr.patch_id);
 		return -1;
 	}
 
-	pr_info("CPU%d: updated (new patch_level=0x%x)\n", cpu, rev);
+	pr_info("CPU%d: new patch_level=0x%08x\n", cpu, rev);
 	uci->cpu_sig.rev = rev;
 
 	return 0;
 }
 
-static void *
-get_next_ucode(const u8 *buf, unsigned int size, unsigned int *mc_size)
+static unsigned int verify_ucode_size(int cpu, const u8 *buf, unsigned int size)
 {
-	unsigned int total_size;
-	u8 section_hdr[UCODE_CONTAINER_SECTION_HDR];
-	void *mc;
+	struct cpuinfo_x86 *c = &cpu_data(cpu);
+	unsigned int max_size, actual_size;
+
+#define F1XH_MPB_MAX_SIZE 2048
+#define F14H_MPB_MAX_SIZE 1824
+#define F15H_MPB_MAX_SIZE 4096
+
+	switch (c->x86) {
+	case 0x14:
+		max_size = F14H_MPB_MAX_SIZE;
+		break;
+	case 0x15:
+		max_size = F15H_MPB_MAX_SIZE;
+		break;
+	default:
+		max_size = F1XH_MPB_MAX_SIZE;
+		break;
+	}
 
-	get_ucode_data(section_hdr, buf, UCODE_CONTAINER_SECTION_HDR);
+	actual_size = buf[4] + (buf[5] << 8);
 
-	if (section_hdr[0] != UCODE_UCODE_TYPE) {
-		pr_err("error: invalid type field in container file section header\n");
-		return NULL;
+	if (actual_size > size || actual_size > max_size) {
+		pr_err("section size mismatch\n");
+		return 0;
 	}
 
-	total_size = (unsigned long) (section_hdr[4] + (section_hdr[5] << 8));
+	return actual_size;
+}
 
-	if (total_size > size || total_size > UCODE_MAX_SIZE) {
-		pr_err("error: size mismatch\n");
-		return NULL;
+static struct microcode_header_amd *
+get_next_ucode(int cpu, const u8 *buf, unsigned int size, unsigned int *mc_size)
+{
+	struct microcode_header_amd *mc = NULL;
+	unsigned int actual_size = 0;
+
+	if (buf[0] != UCODE_UCODE_TYPE) {
+		pr_err("invalid type field in container file section header\n");
+		goto out;
 	}
 
-	mc = vzalloc(UCODE_MAX_SIZE);
+	actual_size = verify_ucode_size(cpu, buf, size);
+	if (!actual_size)
+		goto out;
+
+	mc = vzalloc(actual_size);
 	if (!mc)
-		return NULL;
+		goto out;
 
-	get_ucode_data(mc, buf + UCODE_CONTAINER_SECTION_HDR, total_size);
-	*mc_size = total_size + UCODE_CONTAINER_SECTION_HDR;
+	get_ucode_data(mc, buf + UCODE_CONTAINER_SECTION_HDR, actual_size);
+	*mc_size = actual_size + UCODE_CONTAINER_SECTION_HDR;
 
+out:
 	return mc;
 }
 
 static int install_equiv_cpu_table(const u8 *buf)
 {
-	u8 *container_hdr[UCODE_CONTAINER_HEADER_SIZE];
-	unsigned int *buf_pos = (unsigned int *)container_hdr;
-	unsigned long size;
-
-	get_ucode_data(&container_hdr, buf, UCODE_CONTAINER_HEADER_SIZE);
-
-	size = buf_pos[2];
-
-	if (buf_pos[1] != UCODE_EQUIV_CPU_TABLE_TYPE || !size) {
-		pr_err("error: invalid type field in container file section header\n");
-		return 0;
+	unsigned int *ibuf = (unsigned int *)buf;
+	unsigned int type = ibuf[1];
+	unsigned int size = ibuf[2];
+
+	if (type != UCODE_EQUIV_CPU_TABLE_TYPE || !size) {
+		pr_err("empty section/"
+		       "invalid type field in container file section header\n");
+		return -EINVAL;
 	}
 
 	equiv_cpu_table = vmalloc(size);
 	if (!equiv_cpu_table) {
 		pr_err("failed to allocate equivalent CPU table\n");
-		return 0;
+		return -ENOMEM;
 	}
 
-	buf += UCODE_CONTAINER_HEADER_SIZE;
-	get_ucode_data(equiv_cpu_table, buf, size);
+	get_ucode_data(equiv_cpu_table, buf + UCODE_CONTAINER_HEADER_SIZE, size);
 
 	return size + UCODE_CONTAINER_HEADER_SIZE; /* add header length */
 }
@@ -223,16 +244,16 @@ static enum ucode_state
 generic_load_microcode(int cpu, const u8 *data, size_t size)
 {
 	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
+	struct microcode_header_amd *mc_hdr = NULL;
+	unsigned int mc_size, leftover;
+	int offset;
 	const u8 *ucode_ptr = data;
 	void *new_mc = NULL;
-	void *mc;
-	int new_rev = uci->cpu_sig.rev;
-	unsigned int leftover;
-	unsigned long offset;
+	unsigned int new_rev = uci->cpu_sig.rev;
 	enum ucode_state state = UCODE_OK;
 
 	offset = install_equiv_cpu_table(ucode_ptr);
-	if (!offset) {
+	if (offset < 0) {
 		pr_err("failed to create equivalent cpu table\n");
 		return UCODE_ERROR;
 	}
@@ -241,64 +262,65 @@ generic_load_microcode(int cpu, const u8 *data, size_t size)
 	leftover = size - offset;
 
 	while (leftover) {
-		unsigned int uninitialized_var(mc_size);
-		struct microcode_header_amd *mc_header;
-
-		mc = get_next_ucode(ucode_ptr, leftover, &mc_size);
-		if (!mc)
+		mc_hdr = get_next_ucode(cpu, ucode_ptr, leftover, &mc_size);
+		if (!mc_hdr)
 			break;
 
-		mc_header = (struct microcode_header_amd *)mc;
-		if (get_matching_microcode(cpu, mc, new_rev)) {
+		if (get_matching_microcode(cpu, mc_hdr, new_rev)) {
 			vfree(new_mc);
-			new_rev = mc_header->patch_id;
-			new_mc  = mc;
+			new_rev = mc_hdr->patch_id;
+			new_mc  = mc_hdr;
 		} else
-			vfree(mc);
+			vfree(mc_hdr);
 
 		ucode_ptr += mc_size;
 		leftover  -= mc_size;
 	}
 
-	if (new_mc) {
-		if (!leftover) {
-			vfree(uci->mc);
-			uci->mc = new_mc;
-			pr_debug("CPU%d found a matching microcode update with version 0x%x (current=0x%x)\n",
-				 cpu, new_rev, uci->cpu_sig.rev);
-		} else {
-			vfree(new_mc);
-			state = UCODE_ERROR;
-		}
-	} else
+	if (!new_mc) {
 		state = UCODE_NFOUND;
+		goto free_table;
+	}
 
+	if (!leftover) {
+		vfree(uci->mc);
+		uci->mc = new_mc;
+		pr_debug("CPU%d update ucode (0x%08x -> 0x%08x)\n",
+			 cpu, uci->cpu_sig.rev, new_rev);
+	} else {
+		vfree(new_mc);
+		state = UCODE_ERROR;
+	}
+
+free_table:
 	free_equiv_cpu_table();
 
 	return state;
 }
 
-static enum ucode_state request_microcode_fw(int cpu, struct device *device)
+static enum ucode_state request_microcode_amd(int cpu, struct device *device)
 {
 	const char *fw_name = "amd-ucode/microcode_amd.bin";
-	const struct firmware *firmware;
-	enum ucode_state ret;
+	const struct firmware *fw;
+	enum ucode_state ret = UCODE_NFOUND;
 
-	if (request_firmware(&firmware, fw_name, device)) {
-		printk(KERN_ERR "microcode: failed to load file %s\n", fw_name);
-		return UCODE_NFOUND;
+	if (request_firmware(&fw, fw_name, device)) {
+		pr_err("failed to load file %s\n", fw_name);
+		goto out;
 	}
 
-	if (*(u32 *)firmware->data != UCODE_MAGIC) {
-		pr_err("invalid UCODE_MAGIC (0x%08x)\n",
-		       *(u32 *)firmware->data);
-		return UCODE_ERROR;
+	ret = UCODE_ERROR;
+	if (*(u32 *)fw->data != UCODE_MAGIC) {
+		pr_err("invalid magic value (0x%08x)\n", *(u32 *)fw->data);
+		goto fw_release;
 	}
 
-	ret = generic_load_microcode(cpu, firmware->data, firmware->size);
+	ret = generic_load_microcode(cpu, fw->data, fw->size);
 
-	release_firmware(firmware);
+fw_release:
+	release_firmware(fw);
 
+out:
 	return ret;
 }
 
@@ -319,7 +341,7 @@ static void microcode_fini_cpu_amd(int cpu)
 
 static struct microcode_ops microcode_amd_ops = {
 	.request_microcode_user           = request_microcode_user,
-	.request_microcode_fw             = request_microcode_fw,
+	.request_microcode_fw             = request_microcode_amd,
 	.collect_cpu_info                 = collect_cpu_info_amd,
 	.apply_microcode                  = apply_microcode_amd,
 	.microcode_fini_cpu               = microcode_fini_cpu_amd,
diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c
index 1cca374a2bac..87af68e0e1e1 100644
--- a/arch/x86/kernel/microcode_core.c
+++ b/arch/x86/kernel/microcode_core.c
@@ -417,8 +417,10 @@ static int mc_sysdev_add(struct sys_device *sys_dev)
 	if (err)
 		return err;
 
-	if (microcode_init_cpu(cpu) == UCODE_ERROR)
-		err = -EINVAL;
+	if (microcode_init_cpu(cpu) == UCODE_ERROR) {
+		sysfs_remove_group(&sys_dev->kobj, &mc_attr_group);
+		return -EINVAL;
+	}
 
 	return err;
 }
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index ff4554198981..99fa3adf0141 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -110,12 +110,9 @@ void show_regs_common(void)
 		init_utsname()->release,
 		(int)strcspn(init_utsname()->version, " "),
 		init_utsname()->version);
-	printk(KERN_CONT " ");
-	printk(KERN_CONT "%s %s", vendor, product);
-	if (board) {
-		printk(KERN_CONT "/");
-		printk(KERN_CONT "%s", board);
-	}
+	printk(KERN_CONT " %s %s", vendor, product);
+	if (board)
+		printk(KERN_CONT "/%s", board);
 	printk(KERN_CONT "\n");
 }
 
diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c
index 6f39cab052d5..3f2ad2640d85 100644
--- a/arch/x86/kernel/rtc.c
+++ b/arch/x86/kernel/rtc.c
@@ -6,6 +6,7 @@
 #include <linux/acpi.h>
 #include <linux/bcd.h>
 #include <linux/pnp.h>
+#include <linux/of.h>
 
 #include <asm/vsyscall.h>
 #include <asm/x86_init.h>
@@ -236,6 +237,8 @@ static __init int add_rtc_cmos(void)
 		}
 	}
 #endif
+	if (of_have_populated_dt())
+		return 0;
 
 	platform_device_register(&rtc_device);
 	dev_info(&rtc_device.dev,
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index d3cfe26c0252..b176f2b1f45d 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -113,6 +113,7 @@
 #endif
 #include <asm/mce.h>
 #include <asm/alternative.h>
+#include <asm/prom.h>
 
 /*
  * end_pfn only includes RAM, while max_pfn_mapped includes all e820 entries.
@@ -293,10 +294,32 @@ static void __init init_gbpages(void)
 	else
 		direct_gbpages = 0;
 }
+
+static void __init cleanup_highmap_brk_end(void)
+{
+	pud_t *pud;
+	pmd_t *pmd;
+
+	mmu_cr4_features = read_cr4();
+
+	/*
+	 * _brk_end cannot change anymore, but it and _end may be
+	 * located on different 2M pages. cleanup_highmap(), however,
+	 * can only consider _end when it runs, so destroy any
+	 * mappings beyond _brk_end here.
+	 */
+	pud = pud_offset(pgd_offset_k(_brk_end), _brk_end);
+	pmd = pmd_offset(pud, _brk_end - 1);
+	while (++pmd <= pmd_offset(pud, (unsigned long)_end - 1))
+		pmd_clear(pmd);
+}
 #else
 static inline void init_gbpages(void)
 {
 }
+static inline void cleanup_highmap_brk_end(void)
+{
+}
 #endif
 
 static void __init reserve_brk(void)
@@ -307,6 +330,8 @@ static void __init reserve_brk(void)
 	/* Mark brk area as locked down and no longer taking any
 	   new allocations */
 	_brk_start = 0;
+
+	cleanup_highmap_brk_end();
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
@@ -429,16 +454,30 @@ static void __init parse_setup_data(void)
 		return;
 	pa_data = boot_params.hdr.setup_data;
 	while (pa_data) {
-		data = early_memremap(pa_data, PAGE_SIZE);
+		u32 data_len, map_len;
+
+		map_len = max(PAGE_SIZE - (pa_data & ~PAGE_MASK),
+			      (u64)sizeof(struct setup_data));
+		data = early_memremap(pa_data, map_len);
+		data_len = data->len + sizeof(struct setup_data);
+		if (data_len > map_len) {
+			early_iounmap(data, map_len);
+			data = early_memremap(pa_data, data_len);
+			map_len = data_len;
+		}
+
 		switch (data->type) {
 		case SETUP_E820_EXT:
-			parse_e820_ext(data, pa_data);
+			parse_e820_ext(data);
+			break;
+		case SETUP_DTB:
+			add_dtb(pa_data);
 			break;
 		default:
 			break;
 		}
 		pa_data = data->next;
-		early_iounmap(data, PAGE_SIZE);
+		early_iounmap(data, map_len);
 	}
 }
 
@@ -680,15 +719,6 @@ static int __init parse_reservelow(char *p)
 
 early_param("reservelow", parse_reservelow);
 
-static u64 __init get_max_mapped(void)
-{
-	u64 end = max_pfn_mapped;
-
-	end <<= PAGE_SHIFT;
-
-	return end;
-}
-
 /*
  * Determine if we were loaded by an EFI loader.  If so, then we have also been
  * passed the efi memmap, systab, etc., so we should use these data structures
@@ -704,8 +734,6 @@ static u64 __init get_max_mapped(void)
 
 void __init setup_arch(char **cmdline_p)
 {
-	int acpi = 0;
-	int amd = 0;
 	unsigned long flags;
 
 #ifdef CONFIG_X86_32
@@ -984,19 +1012,7 @@ void __init setup_arch(char **cmdline_p)
 
 	early_acpi_boot_init();
 
-#ifdef CONFIG_ACPI_NUMA
-	/*
-	 * Parse SRAT to discover nodes.
-	 */
-	acpi = acpi_numa_init();
-#endif
-
-#ifdef CONFIG_AMD_NUMA
-	if (!acpi)
-		amd = !amd_numa_init(0, max_pfn);
-#endif
-
-	initmem_init(0, max_pfn, acpi, amd);
+	initmem_init();
 	memblock_find_dma_reserve();
 	dma32_reserve_bootmem();
 
@@ -1029,8 +1045,8 @@ void __init setup_arch(char **cmdline_p)
 	 * Read APIC and some other early information from ACPI tables.
 	 */
 	acpi_boot_init();
-
 	sfi_init();
+	x86_dtb_init();
 
 	/*
 	 * get boot-time SMP configuration:
@@ -1040,9 +1056,7 @@ void __init setup_arch(char **cmdline_p)
 
 	prefill_possible_map();
 
-#ifdef CONFIG_X86_64
 	init_cpu_to_node();
-#endif
 
 	init_apic_mappings();
 	ioapic_and_gsi_init();
@@ -1066,6 +1080,8 @@ void __init setup_arch(char **cmdline_p)
 #endif
 	x86_init.oem.banner();
 
+	x86_init.timers.wallclock_init();
+
 	mcheck_init();
 
 	local_irq_save(flags);
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 002b79685f73..71f4727da373 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -225,10 +225,15 @@ void __init setup_per_cpu_areas(void)
 		per_cpu(x86_bios_cpu_apicid, cpu) =
 			early_per_cpu_map(x86_bios_cpu_apicid, cpu);
 #endif
+#ifdef CONFIG_X86_32
+		per_cpu(x86_cpu_to_logical_apicid, cpu) =
+			early_per_cpu_map(x86_cpu_to_logical_apicid, cpu);
+#endif
 #ifdef CONFIG_X86_64
 		per_cpu(irq_stack_ptr, cpu) =
 			per_cpu(irq_stack_union.irq_stack, cpu) +
 			IRQ_STACK_SIZE - 64;
+#endif
 #ifdef CONFIG_NUMA
 		per_cpu(x86_cpu_to_node_map, cpu) =
 			early_per_cpu_map(x86_cpu_to_node_map, cpu);
@@ -242,7 +247,6 @@ void __init setup_per_cpu_areas(void)
 		 */
 		set_cpu_numa_node(cpu, early_cpu_to_node(cpu));
 #endif
-#endif
 		/*
 		 * Up to this point, the boot CPU has been using .init.data
 		 * area.  Reload any changed state for the boot CPU.
@@ -256,7 +260,10 @@ void __init setup_per_cpu_areas(void)
 	early_per_cpu_ptr(x86_cpu_to_apicid) = NULL;
 	early_per_cpu_ptr(x86_bios_cpu_apicid) = NULL;
 #endif
-#if defined(CONFIG_X86_64) && defined(CONFIG_NUMA)
+#ifdef CONFIG_X86_32
+	early_per_cpu_ptr(x86_cpu_to_logical_apicid) = NULL;
+#endif
+#ifdef CONFIG_NUMA
 	early_per_cpu_ptr(x86_cpu_to_node_map) = NULL;
 #endif
 
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 1bfb1c615a62..e9efdfd51c8d 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -64,6 +64,7 @@
 #include <asm/mtrr.h>
 #include <asm/mwait.h>
 #include <asm/apic.h>
+#include <asm/io_apic.h>
 #include <asm/setup.h>
 #include <asm/uv/uv.h>
 #include <linux/mc146818rtc.h>
@@ -71,10 +72,6 @@
 #include <asm/smpboot_hooks.h>
 #include <asm/i8259.h>
 
-#ifdef CONFIG_X86_32
-u8 apicid_2_node[MAX_APICID];
-#endif
-
 /* State of each CPU */
 DEFINE_PER_CPU(int, cpu_state) = { 0 };
 
@@ -130,68 +127,14 @@ EXPORT_PER_CPU_SYMBOL(cpu_sibling_map);
 DEFINE_PER_CPU(cpumask_var_t, cpu_core_map);
 EXPORT_PER_CPU_SYMBOL(cpu_core_map);
 
+DEFINE_PER_CPU(cpumask_var_t, cpu_llc_shared_map);
+
 /* Per CPU bogomips and other parameters */
 DEFINE_PER_CPU_SHARED_ALIGNED(struct cpuinfo_x86, cpu_info);
 EXPORT_PER_CPU_SYMBOL(cpu_info);
 
 atomic_t init_deasserted;
 
-#if defined(CONFIG_NUMA) && defined(CONFIG_X86_32)
-/* which node each logical CPU is on */
-int cpu_to_node_map[NR_CPUS] __read_mostly = { [0 ... NR_CPUS-1] = 0 };
-EXPORT_SYMBOL(cpu_to_node_map);
-
-/* set up a mapping between cpu and node. */
-static void map_cpu_to_node(int cpu, int node)
-{
-	printk(KERN_INFO "Mapping cpu %d to node %d\n", cpu, node);
-	cpumask_set_cpu(cpu, node_to_cpumask_map[node]);
-	cpu_to_node_map[cpu] = node;
-}
-
-/* undo a mapping between cpu and node. */
-static void unmap_cpu_to_node(int cpu)
-{
-	int node;
-
-	printk(KERN_INFO "Unmapping cpu %d from all nodes\n", cpu);
-	for (node = 0; node < MAX_NUMNODES; node++)
-		cpumask_clear_cpu(cpu, node_to_cpumask_map[node]);
-	cpu_to_node_map[cpu] = 0;
-}
-#else /* !(CONFIG_NUMA && CONFIG_X86_32) */
-#define map_cpu_to_node(cpu, node)	({})
-#define unmap_cpu_to_node(cpu)	({})
-#endif
-
-#ifdef CONFIG_X86_32
-static int boot_cpu_logical_apicid;
-
-u8 cpu_2_logical_apicid[NR_CPUS] __read_mostly =
-					{ [0 ... NR_CPUS-1] = BAD_APICID };
-
-static void map_cpu_to_logical_apicid(void)
-{
-	int cpu = smp_processor_id();
-	int apicid = logical_smp_processor_id();
-	int node = apic->apicid_to_node(apicid);
-
-	if (!node_online(node))
-		node = first_online_node;
-
-	cpu_2_logical_apicid[cpu] = apicid;
-	map_cpu_to_node(cpu, node);
-}
-
-void numa_remove_cpu(int cpu)
-{
-	cpu_2_logical_apicid[cpu] = BAD_APICID;
-	unmap_cpu_to_node(cpu);
-}
-#else
-#define map_cpu_to_logical_apicid()  do {} while (0)
-#endif
-
 /*
  * Report back to the Boot Processor.
  * Running on AP.
@@ -259,7 +202,6 @@ static void __cpuinit smp_callin(void)
 		apic->smp_callin_clear_local_apic();
 	setup_local_APIC();
 	end_local_APIC_setup();
-	map_cpu_to_logical_apicid();
 
 	/*
 	 * Need to setup vector mappings before we enable interrupts.
@@ -355,23 +297,6 @@ notrace static void __cpuinit start_secondary(void *unused)
 	cpu_idle();
 }
 
-#ifdef CONFIG_CPUMASK_OFFSTACK
-/* In this case, llc_shared_map is a pointer to a cpumask. */
-static inline void copy_cpuinfo_x86(struct cpuinfo_x86 *dst,
-				    const struct cpuinfo_x86 *src)
-{
-	struct cpumask *llc = dst->llc_shared_map;
-	*dst = *src;
-	dst->llc_shared_map = llc;
-}
-#else
-static inline void copy_cpuinfo_x86(struct cpuinfo_x86 *dst,
-				    const struct cpuinfo_x86 *src)
-{
-	*dst = *src;
-}
-#endif /* CONFIG_CPUMASK_OFFSTACK */
-
 /*
  * The bootstrap kernel entry code has set these up. Save them for
  * a given CPU
@@ -381,7 +306,7 @@ void __cpuinit smp_store_cpu_info(int id)
 {
 	struct cpuinfo_x86 *c = &cpu_data(id);
 
-	copy_cpuinfo_x86(c, &boot_cpu_data);
+	*c = boot_cpu_data;
 	c->cpu_index = id;
 	if (id != 0)
 		identify_secondary_cpu(c);
@@ -389,15 +314,12 @@ void __cpuinit smp_store_cpu_info(int id)
 
 static void __cpuinit link_thread_siblings(int cpu1, int cpu2)
 {
-	struct cpuinfo_x86 *c1 = &cpu_data(cpu1);
-	struct cpuinfo_x86 *c2 = &cpu_data(cpu2);
-
 	cpumask_set_cpu(cpu1, cpu_sibling_mask(cpu2));
 	cpumask_set_cpu(cpu2, cpu_sibling_mask(cpu1));
 	cpumask_set_cpu(cpu1, cpu_core_mask(cpu2));
 	cpumask_set_cpu(cpu2, cpu_core_mask(cpu1));
-	cpumask_set_cpu(cpu1, c2->llc_shared_map);
-	cpumask_set_cpu(cpu2, c1->llc_shared_map);
+	cpumask_set_cpu(cpu1, cpu_llc_shared_mask(cpu2));
+	cpumask_set_cpu(cpu2, cpu_llc_shared_mask(cpu1));
 }
 
 
@@ -426,7 +348,7 @@ void __cpuinit set_cpu_sibling_map(int cpu)
 		cpumask_set_cpu(cpu, cpu_sibling_mask(cpu));
 	}
 
-	cpumask_set_cpu(cpu, c->llc_shared_map);
+	cpumask_set_cpu(cpu, cpu_llc_shared_mask(cpu));
 
 	if (__this_cpu_read(cpu_info.x86_max_cores) == 1) {
 		cpumask_copy(cpu_core_mask(cpu), cpu_sibling_mask(cpu));
@@ -437,8 +359,8 @@ void __cpuinit set_cpu_sibling_map(int cpu)
 	for_each_cpu(i, cpu_sibling_setup_mask) {
 		if (per_cpu(cpu_llc_id, cpu) != BAD_APICID &&
 		    per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i)) {
-			cpumask_set_cpu(i, c->llc_shared_map);
-			cpumask_set_cpu(cpu, cpu_data(i).llc_shared_map);
+			cpumask_set_cpu(i, cpu_llc_shared_mask(cpu));
+			cpumask_set_cpu(cpu, cpu_llc_shared_mask(i));
 		}
 		if (c->phys_proc_id == cpu_data(i).phys_proc_id) {
 			cpumask_set_cpu(i, cpu_core_mask(cpu));
@@ -477,7 +399,7 @@ const struct cpumask *cpu_coregroup_mask(int cpu)
 	    !(cpu_has(c, X86_FEATURE_AMD_DCM)))
 		return cpu_core_mask(cpu);
 	else
-		return c->llc_shared_map;
+		return cpu_llc_shared_mask(cpu);
 }
 
 static void impress_friends(void)
@@ -946,6 +868,14 @@ int __cpuinit native_cpu_up(unsigned int cpu)
 	return 0;
 }
 
+/**
+ * arch_disable_smp_support() - disables SMP support for x86 at runtime
+ */
+void arch_disable_smp_support(void)
+{
+	disable_ioapic_support();
+}
+
 /*
  * Fall back to non SMP mode after errors.
  *
@@ -961,7 +891,6 @@ static __init void disable_smp(void)
 		physid_set_mask_of_physid(boot_cpu_physical_apicid, &phys_cpu_present_map);
 	else
 		physid_set_mask_of_physid(0, &phys_cpu_present_map);
-	map_cpu_to_logical_apicid();
 	cpumask_set_cpu(0, cpu_sibling_mask(0));
 	cpumask_set_cpu(0, cpu_core_mask(0));
 }
@@ -1046,7 +975,7 @@ static int __init smp_sanity_check(unsigned max_cpus)
 				"(tell your hw vendor)\n");
 		}
 		smpboot_clear_io_apic();
-		arch_disable_smp_support();
+		disable_ioapic_support();
 		return -1;
 	}
 
@@ -1090,21 +1019,19 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 
 	preempt_disable();
 	smp_cpu_index_default();
-	memcpy(__this_cpu_ptr(&cpu_info), &boot_cpu_data, sizeof(cpu_info));
-	cpumask_copy(cpu_callin_mask, cpumask_of(0));
-	mb();
+
 	/*
 	 * Setup boot CPU information
 	 */
 	smp_store_cpu_info(0); /* Final full version of the data */
-#ifdef CONFIG_X86_32
-	boot_cpu_logical_apicid = logical_smp_processor_id();
-#endif
+	cpumask_copy(cpu_callin_mask, cpumask_of(0));
+	mb();
+
 	current_thread_info()->cpu = 0;  /* needed? */
 	for_each_possible_cpu(i) {
 		zalloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL);
 		zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL);
-		zalloc_cpumask_var(&cpu_data(i).llc_shared_map, GFP_KERNEL);
+		zalloc_cpumask_var(&per_cpu(cpu_llc_shared_map, i), GFP_KERNEL);
 	}
 	set_cpu_sibling_map(0);
 
@@ -1140,8 +1067,6 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 
 	bsp_end_local_APIC_setup();
 
-	map_cpu_to_logical_apicid();
-
 	if (apic->setup_portio_remap)
 		apic->setup_portio_remap();
 
diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S
index b35786dc9b8f..5f181742e8f9 100644
--- a/arch/x86/kernel/syscall_table_32.S
+++ b/arch/x86/kernel/syscall_table_32.S
@@ -340,3 +340,6 @@ ENTRY(sys_call_table)
 	.long sys_fanotify_init
 	.long sys_fanotify_mark
 	.long sys_prlimit64		/* 340 */
+	.long sys_name_to_handle_at
+	.long sys_open_by_handle_at
+	.long sys_clock_adjtime
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index bf4700755184..0381e1f3baed 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -105,6 +105,7 @@ SECTIONS
 		SCHED_TEXT
 		LOCK_TEXT
 		KPROBES_TEXT
+		ENTRY_TEXT
 		IRQENTRY_TEXT
 		*(.fixup)
 		*(.gnu.warning)
@@ -305,7 +306,7 @@ SECTIONS
 	}
 
 #if !defined(CONFIG_X86_64) || !defined(CONFIG_SMP)
-	PERCPU(THREAD_SIZE)
+	PERCPU(PAGE_SIZE)
 #endif
 
 	. = ALIGN(PAGE_SIZE);
diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c
index 1b950d151e58..9796c2f3d074 100644
--- a/arch/x86/kernel/x8664_ksyms_64.c
+++ b/arch/x86/kernel/x8664_ksyms_64.c
@@ -52,6 +52,7 @@ extern void *__memcpy(void *, const void *, __kernel_size_t);
 EXPORT_SYMBOL(memset);
 EXPORT_SYMBOL(memcpy);
 EXPORT_SYMBOL(__memcpy);
+EXPORT_SYMBOL(memmove);
 
 EXPORT_SYMBOL(empty_zero_page);
 #ifndef CONFIG_PARAVIRT
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index ceb2911aa439..c11514e9128b 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -70,6 +70,7 @@ struct x86_init_ops x86_init __initdata = {
 		.setup_percpu_clockev	= setup_boot_APIC_clock,
 		.tsc_pre_init		= x86_init_noop,
 		.timer_init		= hpet_time_init,
+		.wallclock_init		= x86_init_noop,
 	},
 
 	.iommu = {
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index 1357d7cf4ec8..db932760ea82 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -62,21 +62,21 @@ TRACE_EVENT(kvm_hv_hypercall,
 	TP_ARGS(code, fast, rep_cnt, rep_idx, ingpa, outgpa),
 
 	TP_STRUCT__entry(
-		__field(	__u16, 		code		)
-		__field(	bool,		fast		)
 		__field(	__u16,		rep_cnt		)
 		__field(	__u16,		rep_idx		)
 		__field(	__u64,		ingpa		)
 		__field(	__u64,		outgpa		)
+		__field(	__u16, 		code		)
+		__field(	bool,		fast		)
 	),
 
 	TP_fast_assign(
-		__entry->code		= code;
-		__entry->fast		= fast;
 		__entry->rep_cnt	= rep_cnt;
 		__entry->rep_idx	= rep_idx;
 		__entry->ingpa		= ingpa;
 		__entry->outgpa		= outgpa;
+		__entry->code		= code;
+		__entry->fast		= fast;
 	),
 
 	TP_printk("code 0x%x %s cnt 0x%x idx 0x%x in 0x%llx out 0x%llx",
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index eba687f0cc0c..b9ec1c74943c 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -847,7 +847,7 @@ static void __init lguest_init_IRQ(void)
 void lguest_setup_irq(unsigned int irq)
 {
 	irq_alloc_desc_at(irq, 0);
-	set_irq_chip_and_handler_name(irq, &lguest_irq_controller,
+	irq_set_chip_and_handler_name(irq, &lguest_irq_controller,
 				      handle_level_irq, "level");
 }
 
@@ -995,7 +995,7 @@ static void lguest_time_irq(unsigned int irq, struct irq_desc *desc)
 static void lguest_time_init(void)
 {
 	/* Set up the timer interrupt (0) to go to our simple timer routine */
-	set_irq_handler(0, lguest_time_irq);
+	irq_set_handler(0, lguest_time_irq);
 
 	clocksource_register(&lguest_clock);
 
diff --git a/arch/x86/lib/atomic64_386_32.S b/arch/x86/lib/atomic64_386_32.S
index 2cda60a06e65..e8e7e0d06f42 100644
--- a/arch/x86/lib/atomic64_386_32.S
+++ b/arch/x86/lib/atomic64_386_32.S
@@ -15,14 +15,12 @@
 
 /* if you want SMP support, implement these with real spinlocks */
 .macro LOCK reg
-	pushfl
-	CFI_ADJUST_CFA_OFFSET 4
+	pushfl_cfi
 	cli
 .endm
 
 .macro UNLOCK reg
-	popfl
-	CFI_ADJUST_CFA_OFFSET -4
+	popfl_cfi
 .endm
 
 #define BEGIN(op) \
diff --git a/arch/x86/lib/atomic64_cx8_32.S b/arch/x86/lib/atomic64_cx8_32.S
index 71e080de3352..391a083674b4 100644
--- a/arch/x86/lib/atomic64_cx8_32.S
+++ b/arch/x86/lib/atomic64_cx8_32.S
@@ -14,14 +14,12 @@
 #include <asm/dwarf2.h>
 
 .macro SAVE reg
-	pushl %\reg
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %\reg
 	CFI_REL_OFFSET \reg, 0
 .endm
 
 .macro RESTORE reg
-	popl %\reg
-	CFI_ADJUST_CFA_OFFSET -4
+	popl_cfi %\reg
 	CFI_RESTORE \reg
 .endm
 
diff --git a/arch/x86/lib/checksum_32.S b/arch/x86/lib/checksum_32.S
index adbccd0bbb78..78d16a554db0 100644
--- a/arch/x86/lib/checksum_32.S
+++ b/arch/x86/lib/checksum_32.S
@@ -50,11 +50,9 @@ unsigned int csum_partial(const unsigned char * buff, int len, unsigned int sum)
 	   */		
 ENTRY(csum_partial)
 	CFI_STARTPROC
-	pushl %esi
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %esi
 	CFI_REL_OFFSET esi, 0
-	pushl %ebx
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %ebx
 	CFI_REL_OFFSET ebx, 0
 	movl 20(%esp),%eax	# Function arg: unsigned int sum
 	movl 16(%esp),%ecx	# Function arg: int len
@@ -132,11 +130,9 @@ ENTRY(csum_partial)
 	jz 8f
 	roll $8, %eax
 8:
-	popl %ebx
-	CFI_ADJUST_CFA_OFFSET -4
+	popl_cfi %ebx
 	CFI_RESTORE ebx
-	popl %esi
-	CFI_ADJUST_CFA_OFFSET -4
+	popl_cfi %esi
 	CFI_RESTORE esi
 	ret
 	CFI_ENDPROC
@@ -148,11 +144,9 @@ ENDPROC(csum_partial)
 
 ENTRY(csum_partial)
 	CFI_STARTPROC
-	pushl %esi
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %esi
 	CFI_REL_OFFSET esi, 0
-	pushl %ebx
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %ebx
 	CFI_REL_OFFSET ebx, 0
 	movl 20(%esp),%eax	# Function arg: unsigned int sum
 	movl 16(%esp),%ecx	# Function arg: int len
@@ -260,11 +254,9 @@ ENTRY(csum_partial)
 	jz 90f
 	roll $8, %eax
 90: 
-	popl %ebx
-	CFI_ADJUST_CFA_OFFSET -4
+	popl_cfi %ebx
 	CFI_RESTORE ebx
-	popl %esi
-	CFI_ADJUST_CFA_OFFSET -4
+	popl_cfi %esi
 	CFI_RESTORE esi
 	ret
 	CFI_ENDPROC
@@ -309,14 +301,11 @@ ENTRY(csum_partial_copy_generic)
 	CFI_STARTPROC
 	subl  $4,%esp	
 	CFI_ADJUST_CFA_OFFSET 4
-	pushl %edi
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %edi
 	CFI_REL_OFFSET edi, 0
-	pushl %esi
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %esi
 	CFI_REL_OFFSET esi, 0
-	pushl %ebx
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %ebx
 	CFI_REL_OFFSET ebx, 0
 	movl ARGBASE+16(%esp),%eax	# sum
 	movl ARGBASE+12(%esp),%ecx	# len
@@ -426,17 +415,13 @@ DST(	movb %cl, (%edi)	)
 
 .previous
 
-	popl %ebx
-	CFI_ADJUST_CFA_OFFSET -4
+	popl_cfi %ebx
 	CFI_RESTORE ebx
-	popl %esi
-	CFI_ADJUST_CFA_OFFSET -4
+	popl_cfi %esi
 	CFI_RESTORE esi
-	popl %edi
-	CFI_ADJUST_CFA_OFFSET -4
+	popl_cfi %edi
 	CFI_RESTORE edi
-	popl %ecx			# equivalent to addl $4,%esp
-	CFI_ADJUST_CFA_OFFSET -4
+	popl_cfi %ecx			# equivalent to addl $4,%esp
 	ret	
 	CFI_ENDPROC
 ENDPROC(csum_partial_copy_generic)
@@ -459,14 +444,11 @@ ENDPROC(csum_partial_copy_generic)
 		
 ENTRY(csum_partial_copy_generic)
 	CFI_STARTPROC
-	pushl %ebx
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %ebx
 	CFI_REL_OFFSET ebx, 0
-	pushl %edi
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %edi
 	CFI_REL_OFFSET edi, 0
-	pushl %esi
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %esi
 	CFI_REL_OFFSET esi, 0
 	movl ARGBASE+4(%esp),%esi	#src
 	movl ARGBASE+8(%esp),%edi	#dst	
@@ -527,14 +509,11 @@ DST(	movb %dl, (%edi)         )
 	jmp  7b			
 .previous				
 
-	popl %esi
-	CFI_ADJUST_CFA_OFFSET -4
+	popl_cfi %esi
 	CFI_RESTORE esi
-	popl %edi
-	CFI_ADJUST_CFA_OFFSET -4
+	popl_cfi %edi
 	CFI_RESTORE edi
-	popl %ebx
-	CFI_ADJUST_CFA_OFFSET -4
+	popl_cfi %ebx
 	CFI_RESTORE ebx
 	ret
 	CFI_ENDPROC
diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S
new file mode 100644
index 000000000000..0ecb8433e5a8
--- /dev/null
+++ b/arch/x86/lib/memmove_64.S
@@ -0,0 +1,197 @@
+/*
+ * Normally compiler builtins are used, but sometimes the compiler calls out
+ * of line code. Based on asm-i386/string.h.
+ *
+ * This assembly file is re-written from memmove_64.c file.
+ *	- Copyright 2011 Fenghua Yu <fenghua.yu@intel.com>
+ */
+#define _STRING_C
+#include <linux/linkage.h>
+#include <asm/dwarf2.h>
+
+#undef memmove
+
+/*
+ * Implement memmove(). This can handle overlap between src and dst.
+ *
+ * Input:
+ * rdi: dest
+ * rsi: src
+ * rdx: count
+ *
+ * Output:
+ * rax: dest
+ */
+ENTRY(memmove)
+	CFI_STARTPROC
+	/* Handle more 32bytes in loop */
+	mov %rdi, %rax
+	cmp $0x20, %rdx
+	jb	1f
+
+	/* Decide forward/backward copy mode */
+	cmp %rdi, %rsi
+	jb	2f
+
+	/*
+	 * movsq instruction have many startup latency
+	 * so we handle small size by general register.
+	 */
+	cmp  $680, %rdx
+	jb	3f
+	/*
+	 * movsq instruction is only good for aligned case.
+	 */
+
+	cmpb %dil, %sil
+	je 4f
+3:
+	sub $0x20, %rdx
+	/*
+	 * We gobble 32byts forward in each loop.
+	 */
+5:
+	sub $0x20, %rdx
+	movq 0*8(%rsi), %r11
+	movq 1*8(%rsi), %r10
+	movq 2*8(%rsi), %r9
+	movq 3*8(%rsi), %r8
+	leaq 4*8(%rsi), %rsi
+
+	movq %r11, 0*8(%rdi)
+	movq %r10, 1*8(%rdi)
+	movq %r9, 2*8(%rdi)
+	movq %r8, 3*8(%rdi)
+	leaq 4*8(%rdi), %rdi
+	jae 5b
+	addq $0x20, %rdx
+	jmp 1f
+	/*
+	 * Handle data forward by movsq.
+	 */
+	.p2align 4
+4:
+	movq %rdx, %rcx
+	movq -8(%rsi, %rdx), %r11
+	lea -8(%rdi, %rdx), %r10
+	shrq $3, %rcx
+	rep movsq
+	movq %r11, (%r10)
+	jmp 13f
+	/*
+	 * Handle data backward by movsq.
+	 */
+	.p2align 4
+7:
+	movq %rdx, %rcx
+	movq (%rsi), %r11
+	movq %rdi, %r10
+	leaq -8(%rsi, %rdx), %rsi
+	leaq -8(%rdi, %rdx), %rdi
+	shrq $3, %rcx
+	std
+	rep movsq
+	cld
+	movq %r11, (%r10)
+	jmp 13f
+
+	/*
+	 * Start to prepare for backward copy.
+	 */
+	.p2align 4
+2:
+	cmp $680, %rdx
+	jb 6f
+	cmp %dil, %sil
+	je 7b
+6:
+	/*
+	 * Calculate copy position to tail.
+	 */
+	addq %rdx, %rsi
+	addq %rdx, %rdi
+	subq $0x20, %rdx
+	/*
+	 * We gobble 32byts backward in each loop.
+	 */
+8:
+	subq $0x20, %rdx
+	movq -1*8(%rsi), %r11
+	movq -2*8(%rsi), %r10
+	movq -3*8(%rsi), %r9
+	movq -4*8(%rsi), %r8
+	leaq -4*8(%rsi), %rsi
+
+	movq %r11, -1*8(%rdi)
+	movq %r10, -2*8(%rdi)
+	movq %r9, -3*8(%rdi)
+	movq %r8, -4*8(%rdi)
+	leaq -4*8(%rdi), %rdi
+	jae 8b
+	/*
+	 * Calculate copy position to head.
+	 */
+	addq $0x20, %rdx
+	subq %rdx, %rsi
+	subq %rdx, %rdi
+1:
+	cmpq $16, %rdx
+	jb 9f
+	/*
+	 * Move data from 16 bytes to 31 bytes.
+	 */
+	movq 0*8(%rsi), %r11
+	movq 1*8(%rsi), %r10
+	movq -2*8(%rsi, %rdx), %r9
+	movq -1*8(%rsi, %rdx), %r8
+	movq %r11, 0*8(%rdi)
+	movq %r10, 1*8(%rdi)
+	movq %r9, -2*8(%rdi, %rdx)
+	movq %r8, -1*8(%rdi, %rdx)
+	jmp 13f
+	.p2align 4
+9:
+	cmpq $8, %rdx
+	jb 10f
+	/*
+	 * Move data from 8 bytes to 15 bytes.
+	 */
+	movq 0*8(%rsi), %r11
+	movq -1*8(%rsi, %rdx), %r10
+	movq %r11, 0*8(%rdi)
+	movq %r10, -1*8(%rdi, %rdx)
+	jmp 13f
+10:
+	cmpq $4, %rdx
+	jb 11f
+	/*
+	 * Move data from 4 bytes to 7 bytes.
+	 */
+	movl (%rsi), %r11d
+	movl -4(%rsi, %rdx), %r10d
+	movl %r11d, (%rdi)
+	movl %r10d, -4(%rdi, %rdx)
+	jmp 13f
+11:
+	cmp $2, %rdx
+	jb 12f
+	/*
+	 * Move data from 2 bytes to 3 bytes.
+	 */
+	movw (%rsi), %r11w
+	movw -2(%rsi, %rdx), %r10w
+	movw %r11w, (%rdi)
+	movw %r10w, -2(%rdi, %rdx)
+	jmp 13f
+12:
+	cmp $1, %rdx
+	jb 13f
+	/*
+	 * Move data for 1 byte.
+	 */
+	movb (%rsi), %r11b
+	movb %r11b, (%rdi)
+13:
+	retq
+	CFI_ENDPROC
+ENDPROC(memmove)
diff --git a/arch/x86/lib/memmove_64.c b/arch/x86/lib/memmove_64.c
deleted file mode 100644
index 6d0f0ec41b34..000000000000
--- a/arch/x86/lib/memmove_64.c
+++ /dev/null
@@ -1,192 +0,0 @@
-/* Normally compiler builtins are used, but sometimes the compiler calls out
-   of line code. Based on asm-i386/string.h.
- */
-#define _STRING_C
-#include <linux/string.h>
-#include <linux/module.h>
-
-#undef memmove
-void *memmove(void *dest, const void *src, size_t count)
-{
-	unsigned long d0,d1,d2,d3,d4,d5,d6,d7;
-	char *ret;
-
-	__asm__ __volatile__(
-		/* Handle more 32bytes in loop */
-		"mov %2, %3\n\t"
-		"cmp $0x20, %0\n\t"
-		"jb	1f\n\t"
-
-		/* Decide forward/backward copy mode */
-		"cmp %2, %1\n\t"
-		"jb	2f\n\t"
-
-		/*
-		 * movsq instruction have many startup latency
-		 * so we handle small size by general register.
-		 */
-		"cmp  $680, %0\n\t"
-		"jb 3f\n\t"
-		/*
-		 * movsq instruction is only good for aligned case.
-		 */
-		"cmpb %%dil, %%sil\n\t"
-		"je 4f\n\t"
-		"3:\n\t"
-		"sub $0x20, %0\n\t"
-		/*
-		 * We gobble 32byts forward in each loop.
-		 */
-		"5:\n\t"
-		"sub $0x20, %0\n\t"
-		"movq 0*8(%1), %4\n\t"
-		"movq 1*8(%1), %5\n\t"
-		"movq 2*8(%1), %6\n\t"
-		"movq 3*8(%1), %7\n\t"
-		"leaq 4*8(%1), %1\n\t"
-
-		"movq %4, 0*8(%2)\n\t"
-		"movq %5, 1*8(%2)\n\t"
-		"movq %6, 2*8(%2)\n\t"
-		"movq %7, 3*8(%2)\n\t"
-		"leaq 4*8(%2), %2\n\t"
-		"jae 5b\n\t"
-		"addq $0x20, %0\n\t"
-		"jmp 1f\n\t"
-		/*
-		 * Handle data forward by movsq.
-		 */
-		".p2align 4\n\t"
-		"4:\n\t"
-		"movq %0, %8\n\t"
-		"movq -8(%1, %0), %4\n\t"
-		"lea -8(%2, %0), %5\n\t"
-		"shrq $3, %8\n\t"
-		"rep movsq\n\t"
-		"movq %4, (%5)\n\t"
-		"jmp 13f\n\t"
-		/*
-		 * Handle data backward by movsq.
-		 */
-		".p2align 4\n\t"
-		"7:\n\t"
-		"movq %0, %8\n\t"
-		"movq (%1), %4\n\t"
-		"movq %2, %5\n\t"
-		"leaq -8(%1, %0), %1\n\t"
-		"leaq -8(%2, %0), %2\n\t"
-		"shrq $3, %8\n\t"
-		"std\n\t"
-		"rep movsq\n\t"
-		"cld\n\t"
-		"movq %4, (%5)\n\t"
-		"jmp 13f\n\t"
-
-		/*
-		 * Start to prepare for backward copy.
-		 */
-		".p2align 4\n\t"
-		"2:\n\t"
-		"cmp $680, %0\n\t"
-		"jb 6f \n\t"
-		"cmp %%dil, %%sil\n\t"
-		"je 7b \n\t"
-		"6:\n\t"
-		/*
-		 * Calculate copy position to tail.
-		 */
-		"addq %0, %1\n\t"
-		"addq %0, %2\n\t"
-		"subq $0x20, %0\n\t"
-		/*
-		 * We gobble 32byts backward in each loop.
-		 */
-		"8:\n\t"
-		"subq $0x20, %0\n\t"
-		"movq -1*8(%1), %4\n\t"
-		"movq -2*8(%1), %5\n\t"
-		"movq -3*8(%1), %6\n\t"
-		"movq -4*8(%1), %7\n\t"
-		"leaq -4*8(%1), %1\n\t"
-
-		"movq %4, -1*8(%2)\n\t"
-		"movq %5, -2*8(%2)\n\t"
-		"movq %6, -3*8(%2)\n\t"
-		"movq %7, -4*8(%2)\n\t"
-		"leaq -4*8(%2), %2\n\t"
-		"jae 8b\n\t"
-		/*
-		 * Calculate copy position to head.
-		 */
-		"addq $0x20, %0\n\t"
-		"subq %0, %1\n\t"
-		"subq %0, %2\n\t"
-		"1:\n\t"
-		"cmpq $16, %0\n\t"
-		"jb 9f\n\t"
-		/*
-		 * Move data from 16 bytes to 31 bytes.
-		 */
-		"movq 0*8(%1), %4\n\t"
-		"movq 1*8(%1), %5\n\t"
-		"movq -2*8(%1, %0), %6\n\t"
-		"movq -1*8(%1, %0), %7\n\t"
-		"movq %4, 0*8(%2)\n\t"
-		"movq %5, 1*8(%2)\n\t"
-		"movq %6, -2*8(%2, %0)\n\t"
-		"movq %7, -1*8(%2, %0)\n\t"
-		"jmp 13f\n\t"
-		".p2align 4\n\t"
-		"9:\n\t"
-		"cmpq $8, %0\n\t"
-		"jb 10f\n\t"
-		/*
-		 * Move data from 8 bytes to 15 bytes.
-		 */
-		"movq 0*8(%1), %4\n\t"
-		"movq -1*8(%1, %0), %5\n\t"
-		"movq %4, 0*8(%2)\n\t"
-		"movq %5, -1*8(%2, %0)\n\t"
-		"jmp 13f\n\t"
-		"10:\n\t"
-		"cmpq $4, %0\n\t"
-		"jb 11f\n\t"
-		/*
-		 * Move data from 4 bytes to 7 bytes.
-		 */
-		"movl (%1), %4d\n\t"
-		"movl -4(%1, %0), %5d\n\t"
-		"movl %4d, (%2)\n\t"
-		"movl %5d, -4(%2, %0)\n\t"
-		"jmp 13f\n\t"
-		"11:\n\t"
-		"cmp $2, %0\n\t"
-		"jb 12f\n\t"
-		/*
-		 * Move data from 2 bytes to 3 bytes.
-		 */
-		"movw (%1), %4w\n\t"
-		"movw -2(%1, %0), %5w\n\t"
-		"movw %4w, (%2)\n\t"
-		"movw %5w, -2(%2, %0)\n\t"
-		"jmp 13f\n\t"
-		"12:\n\t"
-		"cmp $1, %0\n\t"
-		"jb 13f\n\t"
-		/*
-		 * Move data for 1 byte.
-		 */
-		"movb (%1), %4b\n\t"
-		"movb %4b, (%2)\n\t"
-		"13:\n\t"
-		: "=&d" (d0), "=&S" (d1), "=&D" (d2), "=&a" (ret) ,
-		  "=r"(d3), "=r"(d4), "=r"(d5), "=r"(d6), "=&c" (d7)
-		:"0" (count),
-		 "1" (src),
-		 "2" (dest)
-		:"memory");
-
-		return ret;
-
-}
-EXPORT_SYMBOL(memmove);
diff --git a/arch/x86/lib/rwsem_64.S b/arch/x86/lib/rwsem_64.S
index 41fcf00e49df..67743977398b 100644
--- a/arch/x86/lib/rwsem_64.S
+++ b/arch/x86/lib/rwsem_64.S
@@ -23,43 +23,50 @@
 #include <asm/dwarf2.h>
 
 #define save_common_regs \
-	pushq %rdi; \
-	pushq %rsi; \
-	pushq %rcx; \
-	pushq %r8; \
-	pushq %r9; \
-	pushq %r10; \
-	pushq %r11
+	pushq_cfi %rdi; CFI_REL_OFFSET rdi, 0; \
+	pushq_cfi %rsi; CFI_REL_OFFSET rsi, 0; \
+	pushq_cfi %rcx; CFI_REL_OFFSET rcx, 0; \
+	pushq_cfi %r8;  CFI_REL_OFFSET r8,  0; \
+	pushq_cfi %r9;  CFI_REL_OFFSET r9,  0; \
+	pushq_cfi %r10; CFI_REL_OFFSET r10, 0; \
+	pushq_cfi %r11; CFI_REL_OFFSET r11, 0
 
 #define restore_common_regs \
-	popq %r11; \
-	popq %r10; \
-	popq %r9; \
-	popq %r8; \
-	popq %rcx; \
-	popq %rsi; \
-	popq %rdi
+	popq_cfi %r11; CFI_RESTORE r11; \
+	popq_cfi %r10; CFI_RESTORE r10; \
+	popq_cfi %r9;  CFI_RESTORE r9; \
+	popq_cfi %r8;  CFI_RESTORE r8; \
+	popq_cfi %rcx; CFI_RESTORE rcx; \
+	popq_cfi %rsi; CFI_RESTORE rsi; \
+	popq_cfi %rdi; CFI_RESTORE rdi
 
 /* Fix up special calling conventions */
 ENTRY(call_rwsem_down_read_failed)
+	CFI_STARTPROC
 	save_common_regs
-	pushq %rdx
+	pushq_cfi %rdx
+	CFI_REL_OFFSET rdx, 0
 	movq %rax,%rdi
 	call rwsem_down_read_failed
-	popq %rdx
+	popq_cfi %rdx
+	CFI_RESTORE rdx
 	restore_common_regs
 	ret
-	ENDPROC(call_rwsem_down_read_failed)
+	CFI_ENDPROC
+ENDPROC(call_rwsem_down_read_failed)
 
 ENTRY(call_rwsem_down_write_failed)
+	CFI_STARTPROC
 	save_common_regs
 	movq %rax,%rdi
 	call rwsem_down_write_failed
 	restore_common_regs
 	ret
-	ENDPROC(call_rwsem_down_write_failed)
+	CFI_ENDPROC
+ENDPROC(call_rwsem_down_write_failed)
 
 ENTRY(call_rwsem_wake)
+	CFI_STARTPROC
 	decl %edx	/* do nothing if still outstanding active readers */
 	jnz 1f
 	save_common_regs
@@ -67,15 +74,20 @@ ENTRY(call_rwsem_wake)
 	call rwsem_wake
 	restore_common_regs
 1:	ret
-	ENDPROC(call_rwsem_wake)
+	CFI_ENDPROC
+ENDPROC(call_rwsem_wake)
 
 /* Fix up special calling conventions */
 ENTRY(call_rwsem_downgrade_wake)
+	CFI_STARTPROC
 	save_common_regs
-	pushq %rdx
+	pushq_cfi %rdx
+	CFI_REL_OFFSET rdx, 0
 	movq %rax,%rdi
 	call rwsem_downgrade_wake
-	popq %rdx
+	popq_cfi %rdx
+	CFI_RESTORE rdx
 	restore_common_regs
 	ret
-	ENDPROC(call_rwsem_downgrade_wake)
+	CFI_ENDPROC
+ENDPROC(call_rwsem_downgrade_wake)
diff --git a/arch/x86/lib/semaphore_32.S b/arch/x86/lib/semaphore_32.S
index 648fe4741782..06691daa4108 100644
--- a/arch/x86/lib/semaphore_32.S
+++ b/arch/x86/lib/semaphore_32.S
@@ -36,7 +36,7 @@
  */
 #ifdef CONFIG_SMP
 ENTRY(__write_lock_failed)
-	CFI_STARTPROC simple
+	CFI_STARTPROC
 	FRAME
 2: 	LOCK_PREFIX
 	addl	$ RW_LOCK_BIAS,(%eax)
@@ -74,29 +74,23 @@ ENTRY(__read_lock_failed)
 /* Fix up special calling conventions */
 ENTRY(call_rwsem_down_read_failed)
 	CFI_STARTPROC
-	push %ecx
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %ecx
 	CFI_REL_OFFSET ecx,0
-	push %edx
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %edx
 	CFI_REL_OFFSET edx,0
 	call rwsem_down_read_failed
-	pop %edx
-	CFI_ADJUST_CFA_OFFSET -4
-	pop %ecx
-	CFI_ADJUST_CFA_OFFSET -4
+	popl_cfi %edx
+	popl_cfi %ecx
 	ret
 	CFI_ENDPROC
 	ENDPROC(call_rwsem_down_read_failed)
 
 ENTRY(call_rwsem_down_write_failed)
 	CFI_STARTPROC
-	push %ecx
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %ecx
 	CFI_REL_OFFSET ecx,0
 	calll rwsem_down_write_failed
-	pop %ecx
-	CFI_ADJUST_CFA_OFFSET -4
+	popl_cfi %ecx
 	ret
 	CFI_ENDPROC
 	ENDPROC(call_rwsem_down_write_failed)
@@ -105,12 +99,10 @@ ENTRY(call_rwsem_wake)
 	CFI_STARTPROC
 	decw %dx    /* do nothing if still outstanding active readers */
 	jnz 1f
-	push %ecx
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %ecx
 	CFI_REL_OFFSET ecx,0
 	call rwsem_wake
-	pop %ecx
-	CFI_ADJUST_CFA_OFFSET -4
+	popl_cfi %ecx
 1:	ret
 	CFI_ENDPROC
 	ENDPROC(call_rwsem_wake)
@@ -118,17 +110,13 @@ ENTRY(call_rwsem_wake)
 /* Fix up special calling conventions */
 ENTRY(call_rwsem_downgrade_wake)
 	CFI_STARTPROC
-	push %ecx
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %ecx
 	CFI_REL_OFFSET ecx,0
-	push %edx
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %edx
 	CFI_REL_OFFSET edx,0
 	call rwsem_downgrade_wake
-	pop %edx
-	CFI_ADJUST_CFA_OFFSET -4
-	pop %ecx
-	CFI_ADJUST_CFA_OFFSET -4
+	popl_cfi %edx
+	popl_cfi %ecx
 	ret
 	CFI_ENDPROC
 	ENDPROC(call_rwsem_downgrade_wake)
diff --git a/arch/x86/lib/thunk_32.S b/arch/x86/lib/thunk_32.S
index 650b11e00ecc..2930ae05d773 100644
--- a/arch/x86/lib/thunk_32.S
+++ b/arch/x86/lib/thunk_32.S
@@ -7,24 +7,6 @@
 
 	#include <linux/linkage.h>
 
-#define ARCH_TRACE_IRQS_ON			\
-	pushl %eax;				\
-	pushl %ecx;				\
-	pushl %edx;				\
-	call trace_hardirqs_on;			\
-	popl %edx;				\
-	popl %ecx;				\
-	popl %eax;
-
-#define ARCH_TRACE_IRQS_OFF			\
-	pushl %eax;				\
-	pushl %ecx;				\
-	pushl %edx;				\
-	call trace_hardirqs_off;		\
-	popl %edx;				\
-	popl %ecx;				\
-	popl %eax;
-
 #ifdef CONFIG_TRACE_IRQFLAGS
 	/* put return address in eax (arg1) */
 	.macro thunk_ra name,func
diff --git a/arch/x86/lib/thunk_64.S b/arch/x86/lib/thunk_64.S
index bf9a7d5a5428..782b082c9ff7 100644
--- a/arch/x86/lib/thunk_64.S
+++ b/arch/x86/lib/thunk_64.S
@@ -22,26 +22,6 @@
 	CFI_ENDPROC
 	.endm
 
-	/* rdi:	arg1 ... normal C conventions. rax is passed from C. */ 	
-	.macro thunk_retrax name,func
-	.globl \name
-\name:	
-	CFI_STARTPROC
-	SAVE_ARGS
-	call \func
-	jmp  restore_norax
-	CFI_ENDPROC
-	.endm
-	
-
-	.section .sched.text, "ax"
-#ifdef CONFIG_RWSEM_XCHGADD_ALGORITHM
-	thunk rwsem_down_read_failed_thunk,rwsem_down_read_failed
-	thunk rwsem_down_write_failed_thunk,rwsem_down_write_failed
-	thunk rwsem_wake_thunk,rwsem_wake
-	thunk rwsem_downgrade_thunk,rwsem_downgrade_wake
-#endif	
-	
 #ifdef CONFIG_TRACE_IRQFLAGS
 	/* put return address in rdi (arg1) */
 	.macro thunk_ra name,func
@@ -72,10 +52,3 @@ restore:
 	RESTORE_ARGS
 	ret	
 	CFI_ENDPROC
-	
-	CFI_STARTPROC
-	SAVE_ARGS
-restore_norax:	
-	RESTORE_ARGS 1
-	ret
-	CFI_ENDPROC
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 09df2f9a3d69..3e608edf9958 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -25,6 +25,7 @@ obj-$(CONFIG_MMIOTRACE_TEST)	+= testmmiotrace.o
 obj-$(CONFIG_NUMA)		+= numa.o numa_$(BITS).o
 obj-$(CONFIG_AMD_NUMA)		+= amdtopology_64.o
 obj-$(CONFIG_ACPI_NUMA)		+= srat_$(BITS).o
+obj-$(CONFIG_NUMA_EMU)		+= numa_emulation.o
 
 obj-$(CONFIG_HAVE_MEMBLOCK)		+= memblock.o
 
diff --git a/arch/x86/mm/amdtopology_64.c b/arch/x86/mm/amdtopology_64.c
index f21962c435ed..0919c26820d4 100644
--- a/arch/x86/mm/amdtopology_64.c
+++ b/arch/x86/mm/amdtopology_64.c
@@ -26,9 +26,7 @@
 #include <asm/apic.h>
 #include <asm/amd_nb.h>
 
-static struct bootnode __initdata nodes[8];
 static unsigned char __initdata nodeids[8];
-static nodemask_t __initdata nodes_parsed = NODE_MASK_NONE;
 
 static __init int find_northbridge(void)
 {
@@ -51,7 +49,7 @@ static __init int find_northbridge(void)
 		return num;
 	}
 
-	return -1;
+	return -ENOENT;
 }
 
 static __init void early_get_boot_cpu_id(void)
@@ -69,17 +67,18 @@ static __init void early_get_boot_cpu_id(void)
 #endif
 }
 
-int __init amd_numa_init(unsigned long start_pfn, unsigned long end_pfn)
+int __init amd_numa_init(void)
 {
-	unsigned long start = PFN_PHYS(start_pfn);
-	unsigned long end = PFN_PHYS(end_pfn);
+	unsigned long start = PFN_PHYS(0);
+	unsigned long end = PFN_PHYS(max_pfn);
 	unsigned numnodes;
 	unsigned long prevbase;
-	int i, nb, found = 0;
+	int i, j, nb;
 	u32 nodeid, reg;
+	unsigned int bits, cores, apicid_base;
 
 	if (!early_pci_allowed())
-		return -1;
+		return -EINVAL;
 
 	nb = find_northbridge();
 	if (nb < 0)
@@ -90,7 +89,7 @@ int __init amd_numa_init(unsigned long start_pfn, unsigned long end_pfn)
 	reg = read_pci_config(0, nb, 0, 0x60);
 	numnodes = ((reg >> 4) & 0xF) + 1;
 	if (numnodes <= 1)
-		return -1;
+		return -ENOENT;
 
 	pr_info("Number of physical nodes %d\n", numnodes);
 
@@ -121,9 +120,9 @@ int __init amd_numa_init(unsigned long start_pfn, unsigned long end_pfn)
 		if ((base >> 8) & 3 || (limit >> 8) & 3) {
 			pr_err("Node %d using interleaving mode %lx/%lx\n",
 			       nodeid, (base >> 8) & 3, (limit >> 8) & 3);
-			return -1;
+			return -EINVAL;
 		}
-		if (node_isset(nodeid, nodes_parsed)) {
+		if (node_isset(nodeid, numa_nodes_parsed)) {
 			pr_info("Node %d already present, skipping\n",
 				nodeid);
 			continue;
@@ -160,117 +159,28 @@ int __init amd_numa_init(unsigned long start_pfn, unsigned long end_pfn)
 		if (prevbase > base) {
 			pr_err("Node map not sorted %lx,%lx\n",
 			       prevbase, base);
-			return -1;
+			return -EINVAL;
 		}
 
 		pr_info("Node %d MemBase %016lx Limit %016lx\n",
 			nodeid, base, limit);
 
-		found++;
-
-		nodes[nodeid].start = base;
-		nodes[nodeid].end = limit;
-
 		prevbase = base;
-
-		node_set(nodeid, nodes_parsed);
-	}
-
-	if (!found)
-		return -1;
-	return 0;
-}
-
-#ifdef CONFIG_NUMA_EMU
-static s16 fake_apicid_to_node[MAX_LOCAL_APIC] __initdata = {
-	[0 ... MAX_LOCAL_APIC-1] = NUMA_NO_NODE
-};
-
-void __init amd_get_nodes(struct bootnode *physnodes)
-{
-	int i;
-
-	for_each_node_mask(i, nodes_parsed) {
-		physnodes[i].start = nodes[i].start;
-		physnodes[i].end = nodes[i].end;
+		numa_add_memblk(nodeid, base, limit);
+		node_set(nodeid, numa_nodes_parsed);
 	}
-}
-
-static int __init find_node_by_addr(unsigned long addr)
-{
-	int ret = NUMA_NO_NODE;
-	int i;
-
-	for (i = 0; i < 8; i++)
-		if (addr >= nodes[i].start && addr < nodes[i].end) {
-			ret = i;
-			break;
-		}
-	return ret;
-}
 
-/*
- * For NUMA emulation, fake proximity domain (_PXM) to node id mappings must be
- * setup to represent the physical topology but reflect the emulated
- * environment.  For each emulated node, the real node which it appears on is
- * found and a fake pxm to nid mapping is created which mirrors the actual
- * locality.  node_distance() then represents the correct distances between
- * emulated nodes by using the fake acpi mappings to pxms.
- */
-void __init amd_fake_nodes(const struct bootnode *nodes, int nr_nodes)
-{
-	unsigned int bits;
-	unsigned int cores;
-	unsigned int apicid_base = 0;
-	int i;
+	if (!nodes_weight(numa_nodes_parsed))
+		return -ENOENT;
 
+	/*
+	 * We seem to have valid NUMA configuration.  Map apicids to nodes
+	 * using the coreid bits from early_identify_cpu.
+	 */
 	bits = boot_cpu_data.x86_coreid_bits;
 	cores = 1 << bits;
-	early_get_boot_cpu_id();
-	if (boot_cpu_physical_apicid > 0)
-		apicid_base = boot_cpu_physical_apicid;
-
-	for (i = 0; i < nr_nodes; i++) {
-		int index;
-		int nid;
-		int j;
-
-		nid = find_node_by_addr(nodes[i].start);
-		if (nid == NUMA_NO_NODE)
-			continue;
-
-		index = nodeids[nid] << bits;
-		if (fake_apicid_to_node[index + apicid_base] == NUMA_NO_NODE)
-			for (j = apicid_base; j < cores + apicid_base; j++)
-				fake_apicid_to_node[index + j] = i;
-#ifdef CONFIG_ACPI_NUMA
-		__acpi_map_pxm_to_node(nid, i);
-#endif
-	}
-	memcpy(apicid_to_node, fake_apicid_to_node, sizeof(apicid_to_node));
-}
-#endif /* CONFIG_NUMA_EMU */
-
-int __init amd_scan_nodes(void)
-{
-	unsigned int bits;
-	unsigned int cores;
-	unsigned int apicid_base;
-	int i;
-
-	BUG_ON(nodes_empty(nodes_parsed));
-	node_possible_map = nodes_parsed;
-	memnode_shift = compute_hash_shift(nodes, 8, NULL);
-	if (memnode_shift < 0) {
-		pr_err("No NUMA node hash function found. Contact maintainer\n");
-		return -1;
-	}
-	pr_info("Using node hash shift of %d\n", memnode_shift);
-
-	/* use the coreid bits from early_identify_cpu */
-	bits = boot_cpu_data.x86_coreid_bits;
-	cores = (1<<bits);
 	apicid_base = 0;
+
 	/* get the APIC ID of the BSP early for systems with apicid lifting */
 	early_get_boot_cpu_id();
 	if (boot_cpu_physical_apicid > 0) {
@@ -278,17 +188,9 @@ int __init amd_scan_nodes(void)
 		apicid_base = boot_cpu_physical_apicid;
 	}
 
-	for_each_node_mask(i, node_possible_map) {
-		int j;
-
-		memblock_x86_register_active_regions(i,
-				nodes[i].start >> PAGE_SHIFT,
-				nodes[i].end >> PAGE_SHIFT);
+	for_each_node_mask(i, numa_nodes_parsed)
 		for (j = apicid_base; j < cores + apicid_base; j++)
-			apicid_to_node[(i << bits) + j] = i;
-		setup_node_bootmem(i, nodes[i].start, nodes[i].end);
-	}
+			set_apicid_to_node((i << bits) + j, i);
 
-	numa_init_array();
 	return 0;
 }
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 947f42abe820..286d289b039b 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -18,9 +18,9 @@
 
 DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
 
-unsigned long __initdata e820_table_start;
-unsigned long __meminitdata e820_table_end;
-unsigned long __meminitdata e820_table_top;
+unsigned long __initdata pgt_buf_start;
+unsigned long __meminitdata pgt_buf_end;
+unsigned long __meminitdata pgt_buf_top;
 
 int after_bootmem;
 
@@ -33,7 +33,7 @@ int direct_gbpages
 static void __init find_early_table_space(unsigned long end, int use_pse,
 					  int use_gbpages)
 {
-	unsigned long puds, pmds, ptes, tables, start;
+	unsigned long puds, pmds, ptes, tables, start = 0, good_end = end;
 	phys_addr_t base;
 
 	puds = (end + PUD_SIZE - 1) >> PUD_SHIFT;
@@ -65,29 +65,20 @@ static void __init find_early_table_space(unsigned long end, int use_pse,
 #ifdef CONFIG_X86_32
 	/* for fixmap */
 	tables += roundup(__end_of_fixed_addresses * sizeof(pte_t), PAGE_SIZE);
-#endif
 
-	/*
-	 * RED-PEN putting page tables only on node 0 could
-	 * cause a hotspot and fill up ZONE_DMA. The page tables
-	 * need roughly 0.5KB per GB.
-	 */
-#ifdef CONFIG_X86_32
-	start = 0x7000;
-#else
-	start = 0x8000;
+	good_end = max_pfn_mapped << PAGE_SHIFT;
 #endif
-	base = memblock_find_in_range(start, max_pfn_mapped<<PAGE_SHIFT,
-					tables, PAGE_SIZE);
+
+	base = memblock_find_in_range(start, good_end, tables, PAGE_SIZE);
 	if (base == MEMBLOCK_ERROR)
 		panic("Cannot find space for the kernel page tables");
 
-	e820_table_start = base >> PAGE_SHIFT;
-	e820_table_end = e820_table_start;
-	e820_table_top = e820_table_start + (tables >> PAGE_SHIFT);
+	pgt_buf_start = base >> PAGE_SHIFT;
+	pgt_buf_end = pgt_buf_start;
+	pgt_buf_top = pgt_buf_start + (tables >> PAGE_SHIFT);
 
 	printk(KERN_DEBUG "kernel direct mapping tables up to %lx @ %lx-%lx\n",
-		end, e820_table_start << PAGE_SHIFT, e820_table_top << PAGE_SHIFT);
+		end, pgt_buf_start << PAGE_SHIFT, pgt_buf_top << PAGE_SHIFT);
 }
 
 struct map_range {
@@ -279,30 +270,11 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
 	load_cr3(swapper_pg_dir);
 #endif
 
-#ifdef CONFIG_X86_64
-	if (!after_bootmem && !start) {
-		pud_t *pud;
-		pmd_t *pmd;
-
-		mmu_cr4_features = read_cr4();
-
-		/*
-		 * _brk_end cannot change anymore, but it and _end may be
-		 * located on different 2M pages. cleanup_highmap(), however,
-		 * can only consider _end when it runs, so destroy any
-		 * mappings beyond _brk_end here.
-		 */
-		pud = pud_offset(pgd_offset_k(_brk_end), _brk_end);
-		pmd = pmd_offset(pud, _brk_end - 1);
-		while (++pmd <= pmd_offset(pud, (unsigned long)_end - 1))
-			pmd_clear(pmd);
-	}
-#endif
 	__flush_tlb_all();
 
-	if (!after_bootmem && e820_table_end > e820_table_start)
-		memblock_x86_reserve_range(e820_table_start << PAGE_SHIFT,
-				 e820_table_end << PAGE_SHIFT, "PGTABLE");
+	if (!after_bootmem && pgt_buf_end > pgt_buf_start)
+		memblock_x86_reserve_range(pgt_buf_start << PAGE_SHIFT,
+				 pgt_buf_end << PAGE_SHIFT, "PGTABLE");
 
 	if (!after_bootmem)
 		early_memtest(start, end);
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index c821074b7f0b..73ad7ebd6e9c 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -62,10 +62,10 @@ bool __read_mostly __vmalloc_start_set = false;
 
 static __init void *alloc_low_page(void)
 {
-	unsigned long pfn = e820_table_end++;
+	unsigned long pfn = pgt_buf_end++;
 	void *adr;
 
-	if (pfn >= e820_table_top)
+	if (pfn >= pgt_buf_top)
 		panic("alloc_low_page: ran out of memory");
 
 	adr = __va(pfn * PAGE_SIZE);
@@ -163,8 +163,8 @@ static pte_t *__init page_table_kmap_check(pte_t *pte, pmd_t *pmd,
 	if (pmd_idx_kmap_begin != pmd_idx_kmap_end
 	    && (vaddr >> PMD_SHIFT) >= pmd_idx_kmap_begin
 	    && (vaddr >> PMD_SHIFT) <= pmd_idx_kmap_end
-	    && ((__pa(pte) >> PAGE_SHIFT) < e820_table_start
-		|| (__pa(pte) >> PAGE_SHIFT) >= e820_table_end)) {
+	    && ((__pa(pte) >> PAGE_SHIFT) < pgt_buf_start
+		|| (__pa(pte) >> PAGE_SHIFT) >= pgt_buf_end)) {
 		pte_t *newpte;
 		int i;
 
@@ -644,8 +644,7 @@ void __init find_low_pfn_range(void)
 }
 
 #ifndef CONFIG_NEED_MULTIPLE_NODES
-void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn,
-				int acpi, int k8)
+void __init initmem_init(void)
 {
 #ifdef CONFIG_HIGHMEM
 	highstart_pfn = highend_pfn = max_pfn;
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index c14a5422e152..a08a62cb136e 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -314,7 +314,7 @@ void __init cleanup_highmap(void)
 
 static __ref void *alloc_low_page(unsigned long *phys)
 {
-	unsigned long pfn = e820_table_end++;
+	unsigned long pfn = pgt_buf_end++;
 	void *adr;
 
 	if (after_bootmem) {
@@ -324,7 +324,7 @@ static __ref void *alloc_low_page(unsigned long *phys)
 		return adr;
 	}
 
-	if (pfn >= e820_table_top)
+	if (pfn >= pgt_buf_top)
 		panic("alloc_low_page: ran out of memory");
 
 	adr = early_memremap(pfn * PAGE_SIZE, PAGE_SIZE);
@@ -333,12 +333,28 @@ static __ref void *alloc_low_page(unsigned long *phys)
 	return adr;
 }
 
+static __ref void *map_low_page(void *virt)
+{
+	void *adr;
+	unsigned long phys, left;
+
+	if (after_bootmem)
+		return virt;
+
+	phys = __pa(virt);
+	left = phys & (PAGE_SIZE - 1);
+	adr = early_memremap(phys & PAGE_MASK, PAGE_SIZE);
+	adr = (void *)(((unsigned long)adr) | left);
+
+	return adr;
+}
+
 static __ref void unmap_low_page(void *adr)
 {
 	if (after_bootmem)
 		return;
 
-	early_iounmap(adr, PAGE_SIZE);
+	early_iounmap((void *)((unsigned long)adr & PAGE_MASK), PAGE_SIZE);
 }
 
 static unsigned long __meminit
@@ -386,15 +402,6 @@ phys_pte_init(pte_t *pte_page, unsigned long addr, unsigned long end,
 }
 
 static unsigned long __meminit
-phys_pte_update(pmd_t *pmd, unsigned long address, unsigned long end,
-		pgprot_t prot)
-{
-	pte_t *pte = (pte_t *)pmd_page_vaddr(*pmd);
-
-	return phys_pte_init(pte, address, end, prot);
-}
-
-static unsigned long __meminit
 phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
 	      unsigned long page_size_mask, pgprot_t prot)
 {
@@ -420,8 +427,10 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
 		if (pmd_val(*pmd)) {
 			if (!pmd_large(*pmd)) {
 				spin_lock(&init_mm.page_table_lock);
-				last_map_addr = phys_pte_update(pmd, address,
+				pte = map_low_page((pte_t *)pmd_page_vaddr(*pmd));
+				last_map_addr = phys_pte_init(pte, address,
 								end, prot);
+				unmap_low_page(pte);
 				spin_unlock(&init_mm.page_table_lock);
 				continue;
 			}
@@ -468,18 +477,6 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
 }
 
 static unsigned long __meminit
-phys_pmd_update(pud_t *pud, unsigned long address, unsigned long end,
-		unsigned long page_size_mask, pgprot_t prot)
-{
-	pmd_t *pmd = pmd_offset(pud, 0);
-	unsigned long last_map_addr;
-
-	last_map_addr = phys_pmd_init(pmd, address, end, page_size_mask, prot);
-	__flush_tlb_all();
-	return last_map_addr;
-}
-
-static unsigned long __meminit
 phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end,
 			 unsigned long page_size_mask)
 {
@@ -504,8 +501,11 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end,
 
 		if (pud_val(*pud)) {
 			if (!pud_large(*pud)) {
-				last_map_addr = phys_pmd_update(pud, addr, end,
+				pmd = map_low_page(pmd_offset(pud, 0));
+				last_map_addr = phys_pmd_init(pmd, addr, end,
 							 page_size_mask, prot);
+				unmap_low_page(pmd);
+				__flush_tlb_all();
 				continue;
 			}
 			/*
@@ -553,17 +553,6 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end,
 	return last_map_addr;
 }
 
-static unsigned long __meminit
-phys_pud_update(pgd_t *pgd, unsigned long addr, unsigned long end,
-		 unsigned long page_size_mask)
-{
-	pud_t *pud;
-
-	pud = (pud_t *)pgd_page_vaddr(*pgd);
-
-	return phys_pud_init(pud, addr, end, page_size_mask);
-}
-
 unsigned long __meminit
 kernel_physical_mapping_init(unsigned long start,
 			     unsigned long end,
@@ -587,8 +576,10 @@ kernel_physical_mapping_init(unsigned long start,
 			next = end;
 
 		if (pgd_val(*pgd)) {
-			last_map_addr = phys_pud_update(pgd, __pa(start),
+			pud = map_low_page((pud_t *)pgd_page_vaddr(*pgd));
+			last_map_addr = phys_pud_init(pud, __pa(start),
 						 __pa(end), page_size_mask);
+			unmap_low_page(pud);
 			continue;
 		}
 
@@ -612,10 +603,9 @@ kernel_physical_mapping_init(unsigned long start,
 }
 
 #ifndef CONFIG_NUMA
-void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn,
-				int acpi, int k8)
+void __init initmem_init(void)
 {
-	memblock_x86_register_active_regions(0, start_pfn, end_pfn);
+	memblock_x86_register_active_regions(0, 0, max_pfn);
 }
 #endif
 
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index ebf6d7887a38..9559d360fde7 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -26,12 +26,50 @@ static __init int numa_setup(char *opt)
 early_param("numa", numa_setup);
 
 /*
- * Which logical CPUs are on which nodes
+ * apicid, cpu, node mappings
  */
+s16 __apicid_to_node[MAX_LOCAL_APIC] __cpuinitdata = {
+	[0 ... MAX_LOCAL_APIC-1] = NUMA_NO_NODE
+};
+
 cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
 EXPORT_SYMBOL(node_to_cpumask_map);
 
 /*
+ * Map cpu index to node index
+ */
+DEFINE_EARLY_PER_CPU(int, x86_cpu_to_node_map, NUMA_NO_NODE);
+EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_node_map);
+
+void __cpuinit numa_set_node(int cpu, int node)
+{
+	int *cpu_to_node_map = early_per_cpu_ptr(x86_cpu_to_node_map);
+
+	/* early setting, no percpu area yet */
+	if (cpu_to_node_map) {
+		cpu_to_node_map[cpu] = node;
+		return;
+	}
+
+#ifdef CONFIG_DEBUG_PER_CPU_MAPS
+	if (cpu >= nr_cpu_ids || !cpu_possible(cpu)) {
+		printk(KERN_ERR "numa_set_node: invalid cpu# (%d)\n", cpu);
+		dump_stack();
+		return;
+	}
+#endif
+	per_cpu(x86_cpu_to_node_map, cpu) = node;
+
+	if (node != NUMA_NO_NODE)
+		set_cpu_numa_node(cpu, node);
+}
+
+void __cpuinit numa_clear_node(int cpu)
+{
+	numa_set_node(cpu, NUMA_NO_NODE);
+}
+
+/*
  * Allocate node_to_cpumask_map based on number of available nodes
  * Requires node_possible_map to be valid.
  *
@@ -57,7 +95,174 @@ void __init setup_node_to_cpumask_map(void)
 	pr_debug("Node to cpumask map for %d nodes\n", nr_node_ids);
 }
 
-#ifdef CONFIG_DEBUG_PER_CPU_MAPS
+/*
+ * There are unfortunately some poorly designed mainboards around that
+ * only connect memory to a single CPU. This breaks the 1:1 cpu->node
+ * mapping. To avoid this fill in the mapping for all possible CPUs,
+ * as the number of CPUs is not known yet. We round robin the existing
+ * nodes.
+ */
+void __init numa_init_array(void)
+{
+	int rr, i;
+
+	rr = first_node(node_online_map);
+	for (i = 0; i < nr_cpu_ids; i++) {
+		if (early_cpu_to_node(i) != NUMA_NO_NODE)
+			continue;
+		numa_set_node(i, rr);
+		rr = next_node(rr, node_online_map);
+		if (rr == MAX_NUMNODES)
+			rr = first_node(node_online_map);
+	}
+}
+
+static __init int find_near_online_node(int node)
+{
+	int n, val;
+	int min_val = INT_MAX;
+	int best_node = -1;
+
+	for_each_online_node(n) {
+		val = node_distance(node, n);
+
+		if (val < min_val) {
+			min_val = val;
+			best_node = n;
+		}
+	}
+
+	return best_node;
+}
+
+/*
+ * Setup early cpu_to_node.
+ *
+ * Populate cpu_to_node[] only if x86_cpu_to_apicid[],
+ * and apicid_to_node[] tables have valid entries for a CPU.
+ * This means we skip cpu_to_node[] initialisation for NUMA
+ * emulation and faking node case (when running a kernel compiled
+ * for NUMA on a non NUMA box), which is OK as cpu_to_node[]
+ * is already initialized in a round robin manner at numa_init_array,
+ * prior to this call, and this initialization is good enough
+ * for the fake NUMA cases.
+ *
+ * Called before the per_cpu areas are setup.
+ */
+void __init init_cpu_to_node(void)
+{
+	int cpu;
+	u16 *cpu_to_apicid = early_per_cpu_ptr(x86_cpu_to_apicid);
+
+	BUG_ON(cpu_to_apicid == NULL);
+
+	for_each_possible_cpu(cpu) {
+		int node = numa_cpu_node(cpu);
+
+		if (node == NUMA_NO_NODE)
+			continue;
+		if (!node_online(node))
+			node = find_near_online_node(node);
+		numa_set_node(cpu, node);
+	}
+}
+
+#ifndef CONFIG_DEBUG_PER_CPU_MAPS
+
+# ifndef CONFIG_NUMA_EMU
+void __cpuinit numa_add_cpu(int cpu)
+{
+	cpumask_set_cpu(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
+}
+
+void __cpuinit numa_remove_cpu(int cpu)
+{
+	cpumask_clear_cpu(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
+}
+# endif	/* !CONFIG_NUMA_EMU */
+
+#else	/* !CONFIG_DEBUG_PER_CPU_MAPS */
+
+int __cpu_to_node(int cpu)
+{
+	if (early_per_cpu_ptr(x86_cpu_to_node_map)) {
+		printk(KERN_WARNING
+			"cpu_to_node(%d): usage too early!\n", cpu);
+		dump_stack();
+		return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu];
+	}
+	return per_cpu(x86_cpu_to_node_map, cpu);
+}
+EXPORT_SYMBOL(__cpu_to_node);
+
+/*
+ * Same function as cpu_to_node() but used if called before the
+ * per_cpu areas are setup.
+ */
+int early_cpu_to_node(int cpu)
+{
+	if (early_per_cpu_ptr(x86_cpu_to_node_map))
+		return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu];
+
+	if (!cpu_possible(cpu)) {
+		printk(KERN_WARNING
+			"early_cpu_to_node(%d): no per_cpu area!\n", cpu);
+		dump_stack();
+		return NUMA_NO_NODE;
+	}
+	return per_cpu(x86_cpu_to_node_map, cpu);
+}
+
+struct cpumask __cpuinit *debug_cpumask_set_cpu(int cpu, int enable)
+{
+	int node = early_cpu_to_node(cpu);
+	struct cpumask *mask;
+	char buf[64];
+
+	if (node == NUMA_NO_NODE) {
+		/* early_cpu_to_node() already emits a warning and trace */
+		return NULL;
+	}
+	mask = node_to_cpumask_map[node];
+	if (!mask) {
+		pr_err("node_to_cpumask_map[%i] NULL\n", node);
+		dump_stack();
+		return NULL;
+	}
+
+	cpulist_scnprintf(buf, sizeof(buf), mask);
+	printk(KERN_DEBUG "%s cpu %d node %d: mask now %s\n",
+		enable ? "numa_add_cpu" : "numa_remove_cpu",
+		cpu, node, buf);
+	return mask;
+}
+
+# ifndef CONFIG_NUMA_EMU
+static void __cpuinit numa_set_cpumask(int cpu, int enable)
+{
+	struct cpumask *mask;
+
+	mask = debug_cpumask_set_cpu(cpu, enable);
+	if (!mask)
+		return;
+
+	if (enable)
+		cpumask_set_cpu(cpu, mask);
+	else
+		cpumask_clear_cpu(cpu, mask);
+}
+
+void __cpuinit numa_add_cpu(int cpu)
+{
+	numa_set_cpumask(cpu, 1);
+}
+
+void __cpuinit numa_remove_cpu(int cpu)
+{
+	numa_set_cpumask(cpu, 0);
+}
+# endif	/* !CONFIG_NUMA_EMU */
+
 /*
  * Returns a pointer to the bitmask of CPUs on Node 'node'.
  */
@@ -80,4 +285,5 @@ const struct cpumask *cpumask_of_node(int node)
 	return node_to_cpumask_map[node];
 }
 EXPORT_SYMBOL(cpumask_of_node);
-#endif
+
+#endif	/* !CONFIG_DEBUG_PER_CPU_MAPS */
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index 84a3e4c9f277..bde3906420df 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -110,6 +110,12 @@ void set_pmd_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags);
 
 static unsigned long kva_start_pfn;
 static unsigned long kva_pages;
+
+int __cpuinit numa_cpu_node(int cpu)
+{
+	return apic->x86_32_numa_cpu_node(cpu);
+}
+
 /*
  * FLAT - support for basic PC memory model with discontig enabled, essentially
  *        a single node with all available processors in it with a flat
@@ -346,8 +352,7 @@ static void init_remap_allocator(int nid)
 		(ulong) node_remap_end_vaddr[nid]);
 }
 
-void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn,
-				int acpi, int k8)
+void __init initmem_init(void)
 {
 	int nid;
 	long kva_target_pfn;
@@ -361,6 +366,7 @@ void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn,
 	 */
 
 	get_memcfg_numa();
+	numa_init_array();
 
 	kva_pages = roundup(calculate_numa_remap_pages(), PTRS_PER_PTE);
 
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index 1337c51b07d7..9ec0f209a6a4 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -13,31 +13,30 @@
 #include <linux/module.h>
 #include <linux/nodemask.h>
 #include <linux/sched.h>
+#include <linux/acpi.h>
 
 #include <asm/e820.h>
 #include <asm/proto.h>
 #include <asm/dma.h>
-#include <asm/numa.h>
 #include <asm/acpi.h>
 #include <asm/amd_nb.h>
 
+#include "numa_internal.h"
+
 struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
 EXPORT_SYMBOL(node_data);
 
-struct memnode memnode;
+nodemask_t numa_nodes_parsed __initdata;
 
-s16 apicid_to_node[MAX_LOCAL_APIC] __cpuinitdata = {
-	[0 ... MAX_LOCAL_APIC-1] = NUMA_NO_NODE
-};
+struct memnode memnode;
 
 static unsigned long __initdata nodemap_addr;
 static unsigned long __initdata nodemap_size;
 
-/*
- * Map cpu index to node index
- */
-DEFINE_EARLY_PER_CPU(int, x86_cpu_to_node_map, NUMA_NO_NODE);
-EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_node_map);
+static struct numa_meminfo numa_meminfo __initdata;
+
+static int numa_distance_cnt;
+static u8 *numa_distance;
 
 /*
  * Given a shift value, try to populate memnodemap[]
@@ -46,16 +45,15 @@ EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_node_map);
  * 0 if memnodmap[] too small (of shift too small)
  * -1 if node overlap or lost ram (shift too big)
  */
-static int __init populate_memnodemap(const struct bootnode *nodes,
-				      int numnodes, int shift, int *nodeids)
+static int __init populate_memnodemap(const struct numa_meminfo *mi, int shift)
 {
 	unsigned long addr, end;
 	int i, res = -1;
 
 	memset(memnodemap, 0xff, sizeof(s16)*memnodemapsize);
-	for (i = 0; i < numnodes; i++) {
-		addr = nodes[i].start;
-		end = nodes[i].end;
+	for (i = 0; i < mi->nr_blks; i++) {
+		addr = mi->blk[i].start;
+		end = mi->blk[i].end;
 		if (addr >= end)
 			continue;
 		if ((end >> shift) >= memnodemapsize)
@@ -63,12 +61,7 @@ static int __init populate_memnodemap(const struct bootnode *nodes,
 		do {
 			if (memnodemap[addr >> shift] != NUMA_NO_NODE)
 				return -1;
-
-			if (!nodeids)
-				memnodemap[addr >> shift] = i;
-			else
-				memnodemap[addr >> shift] = nodeids[i];
-
+			memnodemap[addr >> shift] = mi->blk[i].nid;
 			addr += (1UL << shift);
 		} while (addr < end);
 		res = 1;
@@ -86,7 +79,7 @@ static int __init allocate_cachealigned_memnodemap(void)
 
 	addr = 0x8000;
 	nodemap_size = roundup(sizeof(s16) * memnodemapsize, L1_CACHE_BYTES);
-	nodemap_addr = memblock_find_in_range(addr, max_pfn<<PAGE_SHIFT,
+	nodemap_addr = memblock_find_in_range(addr, get_max_mapped(),
 				      nodemap_size, L1_CACHE_BYTES);
 	if (nodemap_addr == MEMBLOCK_ERROR) {
 		printk(KERN_ERR
@@ -106,16 +99,15 @@ static int __init allocate_cachealigned_memnodemap(void)
  * The LSB of all start and end addresses in the node map is the value of the
  * maximum possible shift.
  */
-static int __init extract_lsb_from_nodes(const struct bootnode *nodes,
-					 int numnodes)
+static int __init extract_lsb_from_nodes(const struct numa_meminfo *mi)
 {
 	int i, nodes_used = 0;
 	unsigned long start, end;
 	unsigned long bitfield = 0, memtop = 0;
 
-	for (i = 0; i < numnodes; i++) {
-		start = nodes[i].start;
-		end = nodes[i].end;
+	for (i = 0; i < mi->nr_blks; i++) {
+		start = mi->blk[i].start;
+		end = mi->blk[i].end;
 		if (start >= end)
 			continue;
 		bitfield |= start;
@@ -131,18 +123,17 @@ static int __init extract_lsb_from_nodes(const struct bootnode *nodes,
 	return i;
 }
 
-int __init compute_hash_shift(struct bootnode *nodes, int numnodes,
-			      int *nodeids)
+static int __init compute_hash_shift(const struct numa_meminfo *mi)
 {
 	int shift;
 
-	shift = extract_lsb_from_nodes(nodes, numnodes);
+	shift = extract_lsb_from_nodes(mi);
 	if (allocate_cachealigned_memnodemap())
 		return -1;
 	printk(KERN_DEBUG "NUMA: Using %d for the hash shift.\n",
 		shift);
 
-	if (populate_memnodemap(nodes, numnodes, shift, nodeids) != 1) {
+	if (populate_memnodemap(mi, shift) != 1) {
 		printk(KERN_INFO "Your memory is not aligned you need to "
 		       "rebuild your kernel with a bigger NODEMAPSIZE "
 		       "shift=%d\n", shift);
@@ -188,6 +179,63 @@ static void * __init early_node_mem(int nodeid, unsigned long start,
 	return NULL;
 }
 
+static int __init numa_add_memblk_to(int nid, u64 start, u64 end,
+				     struct numa_meminfo *mi)
+{
+	/* ignore zero length blks */
+	if (start == end)
+		return 0;
+
+	/* whine about and ignore invalid blks */
+	if (start > end || nid < 0 || nid >= MAX_NUMNODES) {
+		pr_warning("NUMA: Warning: invalid memblk node %d (%Lx-%Lx)\n",
+			   nid, start, end);
+		return 0;
+	}
+
+	if (mi->nr_blks >= NR_NODE_MEMBLKS) {
+		pr_err("NUMA: too many memblk ranges\n");
+		return -EINVAL;
+	}
+
+	mi->blk[mi->nr_blks].start = start;
+	mi->blk[mi->nr_blks].end = end;
+	mi->blk[mi->nr_blks].nid = nid;
+	mi->nr_blks++;
+	return 0;
+}
+
+/**
+ * numa_remove_memblk_from - Remove one numa_memblk from a numa_meminfo
+ * @idx: Index of memblk to remove
+ * @mi: numa_meminfo to remove memblk from
+ *
+ * Remove @idx'th numa_memblk from @mi by shifting @mi->blk[] and
+ * decrementing @mi->nr_blks.
+ */
+void __init numa_remove_memblk_from(int idx, struct numa_meminfo *mi)
+{
+	mi->nr_blks--;
+	memmove(&mi->blk[idx], &mi->blk[idx + 1],
+		(mi->nr_blks - idx) * sizeof(mi->blk[0]));
+}
+
+/**
+ * numa_add_memblk - Add one numa_memblk to numa_meminfo
+ * @nid: NUMA node ID of the new memblk
+ * @start: Start address of the new memblk
+ * @end: End address of the new memblk
+ *
+ * Add a new memblk to the default numa_meminfo.
+ *
+ * RETURNS:
+ * 0 on success, -errno on failure.
+ */
+int __init numa_add_memblk(int nid, u64 start, u64 end)
+{
+	return numa_add_memblk_to(nid, start, end, &numa_meminfo);
+}
+
 /* Initialize bootmem allocator for a node */
 void __init
 setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
@@ -234,692 +282,386 @@ setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
 	node_set_online(nodeid);
 }
 
-/*
- * There are unfortunately some poorly designed mainboards around that
- * only connect memory to a single CPU. This breaks the 1:1 cpu->node
- * mapping. To avoid this fill in the mapping for all possible CPUs,
- * as the number of CPUs is not known yet. We round robin the existing
- * nodes.
+/**
+ * numa_cleanup_meminfo - Cleanup a numa_meminfo
+ * @mi: numa_meminfo to clean up
+ *
+ * Sanitize @mi by merging and removing unncessary memblks.  Also check for
+ * conflicts and clear unused memblks.
+ *
+ * RETURNS:
+ * 0 on success, -errno on failure.
  */
-void __init numa_init_array(void)
+int __init numa_cleanup_meminfo(struct numa_meminfo *mi)
 {
-	int rr, i;
+	const u64 low = 0;
+	const u64 high = (u64)max_pfn << PAGE_SHIFT;
+	int i, j, k;
 
-	rr = first_node(node_online_map);
-	for (i = 0; i < nr_cpu_ids; i++) {
-		if (early_cpu_to_node(i) != NUMA_NO_NODE)
-			continue;
-		numa_set_node(i, rr);
-		rr = next_node(rr, node_online_map);
-		if (rr == MAX_NUMNODES)
-			rr = first_node(node_online_map);
-	}
-}
-
-#ifdef CONFIG_NUMA_EMU
-/* Numa emulation */
-static struct bootnode nodes[MAX_NUMNODES] __initdata;
-static struct bootnode physnodes[MAX_NUMNODES] __cpuinitdata;
-static char *cmdline __initdata;
+	for (i = 0; i < mi->nr_blks; i++) {
+		struct numa_memblk *bi = &mi->blk[i];
 
-void __init numa_emu_cmdline(char *str)
-{
-	cmdline = str;
-}
+		/* make sure all blocks are inside the limits */
+		bi->start = max(bi->start, low);
+		bi->end = min(bi->end, high);
 
-static int __init setup_physnodes(unsigned long start, unsigned long end,
-					int acpi, int amd)
-{
-	int ret = 0;
-	int i;
-
-	memset(physnodes, 0, sizeof(physnodes));
-#ifdef CONFIG_ACPI_NUMA
-	if (acpi)
-		acpi_get_nodes(physnodes, start, end);
-#endif
-#ifdef CONFIG_AMD_NUMA
-	if (amd)
-		amd_get_nodes(physnodes);
-#endif
-	/*
-	 * Basic sanity checking on the physical node map: there may be errors
-	 * if the SRAT or AMD code incorrectly reported the topology or the mem=
-	 * kernel parameter is used.
-	 */
-	for (i = 0; i < MAX_NUMNODES; i++) {
-		if (physnodes[i].start == physnodes[i].end)
-			continue;
-		if (physnodes[i].start > end) {
-			physnodes[i].end = physnodes[i].start;
-			continue;
-		}
-		if (physnodes[i].end < start) {
-			physnodes[i].start = physnodes[i].end;
+		/* and there's no empty block */
+		if (bi->start == bi->end) {
+			numa_remove_memblk_from(i--, mi);
 			continue;
 		}
-		if (physnodes[i].start < start)
-			physnodes[i].start = start;
-		if (physnodes[i].end > end)
-			physnodes[i].end = end;
-		ret++;
-	}
 
-	/*
-	 * If no physical topology was detected, a single node is faked to cover
-	 * the entire address space.
-	 */
-	if (!ret) {
-		physnodes[ret].start = start;
-		physnodes[ret].end = end;
-		ret = 1;
-	}
-	return ret;
-}
-
-static void __init fake_physnodes(int acpi, int amd, int nr_nodes)
-{
-	int i;
-
-	BUG_ON(acpi && amd);
-#ifdef CONFIG_ACPI_NUMA
-	if (acpi)
-		acpi_fake_nodes(nodes, nr_nodes);
-#endif
-#ifdef CONFIG_AMD_NUMA
-	if (amd)
-		amd_fake_nodes(nodes, nr_nodes);
-#endif
-	if (!acpi && !amd)
-		for (i = 0; i < nr_cpu_ids; i++)
-			numa_set_node(i, 0);
-}
-
-/*
- * Setups up nid to range from addr to addr + size.  If the end
- * boundary is greater than max_addr, then max_addr is used instead.
- * The return value is 0 if there is additional memory left for
- * allocation past addr and -1 otherwise.  addr is adjusted to be at
- * the end of the node.
- */
-static int __init setup_node_range(int nid, u64 *addr, u64 size, u64 max_addr)
-{
-	int ret = 0;
-	nodes[nid].start = *addr;
-	*addr += size;
-	if (*addr >= max_addr) {
-		*addr = max_addr;
-		ret = -1;
-	}
-	nodes[nid].end = *addr;
-	node_set(nid, node_possible_map);
-	printk(KERN_INFO "Faking node %d at %016Lx-%016Lx (%LuMB)\n", nid,
-	       nodes[nid].start, nodes[nid].end,
-	       (nodes[nid].end - nodes[nid].start) >> 20);
-	return ret;
-}
-
-/*
- * Sets up nr_nodes fake nodes interleaved over physical nodes ranging from addr
- * to max_addr.  The return value is the number of nodes allocated.
- */
-static int __init split_nodes_interleave(u64 addr, u64 max_addr, int nr_nodes)
-{
-	nodemask_t physnode_mask = NODE_MASK_NONE;
-	u64 size;
-	int big;
-	int ret = 0;
-	int i;
-
-	if (nr_nodes <= 0)
-		return -1;
-	if (nr_nodes > MAX_NUMNODES) {
-		pr_info("numa=fake=%d too large, reducing to %d\n",
-			nr_nodes, MAX_NUMNODES);
-		nr_nodes = MAX_NUMNODES;
-	}
-
-	size = (max_addr - addr - memblock_x86_hole_size(addr, max_addr)) / nr_nodes;
-	/*
-	 * Calculate the number of big nodes that can be allocated as a result
-	 * of consolidating the remainder.
-	 */
-	big = ((size & ~FAKE_NODE_MIN_HASH_MASK) * nr_nodes) /
-		FAKE_NODE_MIN_SIZE;
-
-	size &= FAKE_NODE_MIN_HASH_MASK;
-	if (!size) {
-		pr_err("Not enough memory for each node.  "
-			"NUMA emulation disabled.\n");
-		return -1;
-	}
-
-	for (i = 0; i < MAX_NUMNODES; i++)
-		if (physnodes[i].start != physnodes[i].end)
-			node_set(i, physnode_mask);
-
-	/*
-	 * Continue to fill physical nodes with fake nodes until there is no
-	 * memory left on any of them.
-	 */
-	while (nodes_weight(physnode_mask)) {
-		for_each_node_mask(i, physnode_mask) {
-			u64 end = physnodes[i].start + size;
-			u64 dma32_end = PFN_PHYS(MAX_DMA32_PFN);
-
-			if (ret < big)
-				end += FAKE_NODE_MIN_SIZE;
+		for (j = i + 1; j < mi->nr_blks; j++) {
+			struct numa_memblk *bj = &mi->blk[j];
+			unsigned long start, end;
 
 			/*
-			 * Continue to add memory to this fake node if its
-			 * non-reserved memory is less than the per-node size.
+			 * See whether there are overlapping blocks.  Whine
+			 * about but allow overlaps of the same nid.  They
+			 * will be merged below.
 			 */
-			while (end - physnodes[i].start -
-				memblock_x86_hole_size(physnodes[i].start, end) < size) {
-				end += FAKE_NODE_MIN_SIZE;
-				if (end > physnodes[i].end) {
-					end = physnodes[i].end;
-					break;
+			if (bi->end > bj->start && bi->start < bj->end) {
+				if (bi->nid != bj->nid) {
+					pr_err("NUMA: node %d (%Lx-%Lx) overlaps with node %d (%Lx-%Lx)\n",
+					       bi->nid, bi->start, bi->end,
+					       bj->nid, bj->start, bj->end);
+					return -EINVAL;
 				}
+				pr_warning("NUMA: Warning: node %d (%Lx-%Lx) overlaps with itself (%Lx-%Lx)\n",
+					   bi->nid, bi->start, bi->end,
+					   bj->start, bj->end);
 			}
 
 			/*
-			 * If there won't be at least FAKE_NODE_MIN_SIZE of
-			 * non-reserved memory in ZONE_DMA32 for the next node,
-			 * this one must extend to the boundary.
-			 */
-			if (end < dma32_end && dma32_end - end -
-			    memblock_x86_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE)
-				end = dma32_end;
-
-			/*
-			 * If there won't be enough non-reserved memory for the
-			 * next node, this one must extend to the end of the
-			 * physical node.
+			 * Join together blocks on the same node, holes
+			 * between which don't overlap with memory on other
+			 * nodes.
 			 */
-			if (physnodes[i].end - end -
-			    memblock_x86_hole_size(end, physnodes[i].end) < size)
-				end = physnodes[i].end;
-
-			/*
-			 * Avoid allocating more nodes than requested, which can
-			 * happen as a result of rounding down each node's size
-			 * to FAKE_NODE_MIN_SIZE.
-			 */
-			if (nodes_weight(physnode_mask) + ret >= nr_nodes)
-				end = physnodes[i].end;
-
-			if (setup_node_range(ret++, &physnodes[i].start,
-						end - physnodes[i].start,
-						physnodes[i].end) < 0)
-				node_clear(i, physnode_mask);
+			if (bi->nid != bj->nid)
+				continue;
+			start = max(min(bi->start, bj->start), low);
+			end = min(max(bi->end, bj->end), high);
+			for (k = 0; k < mi->nr_blks; k++) {
+				struct numa_memblk *bk = &mi->blk[k];
+
+				if (bi->nid == bk->nid)
+					continue;
+				if (start < bk->end && end > bk->start)
+					break;
+			}
+			if (k < mi->nr_blks)
+				continue;
+			printk(KERN_INFO "NUMA: Node %d [%Lx,%Lx) + [%Lx,%Lx) -> [%lx,%lx)\n",
+			       bi->nid, bi->start, bi->end, bj->start, bj->end,
+			       start, end);
+			bi->start = start;
+			bi->end = end;
+			numa_remove_memblk_from(j--, mi);
 		}
 	}
-	return ret;
-}
-
-/*
- * Returns the end address of a node so that there is at least `size' amount of
- * non-reserved memory or `max_addr' is reached.
- */
-static u64 __init find_end_of_node(u64 start, u64 max_addr, u64 size)
-{
-	u64 end = start + size;
 
-	while (end - start - memblock_x86_hole_size(start, end) < size) {
-		end += FAKE_NODE_MIN_SIZE;
-		if (end > max_addr) {
-			end = max_addr;
-			break;
-		}
+	for (i = mi->nr_blks; i < ARRAY_SIZE(mi->blk); i++) {
+		mi->blk[i].start = mi->blk[i].end = 0;
+		mi->blk[i].nid = NUMA_NO_NODE;
 	}
-	return end;
+
+	return 0;
 }
 
 /*
- * Sets up fake nodes of `size' interleaved over physical nodes ranging from
- * `addr' to `max_addr'.  The return value is the number of nodes allocated.
+ * Set nodes, which have memory in @mi, in *@nodemask.
  */
-static int __init split_nodes_size_interleave(u64 addr, u64 max_addr, u64 size)
+static void __init numa_nodemask_from_meminfo(nodemask_t *nodemask,
+					      const struct numa_meminfo *mi)
 {
-	nodemask_t physnode_mask = NODE_MASK_NONE;
-	u64 min_size;
-	int ret = 0;
 	int i;
 
-	if (!size)
-		return -1;
-	/*
-	 * The limit on emulated nodes is MAX_NUMNODES, so the size per node is
-	 * increased accordingly if the requested size is too small.  This
-	 * creates a uniform distribution of node sizes across the entire
-	 * machine (but not necessarily over physical nodes).
-	 */
-	min_size = (max_addr - addr - memblock_x86_hole_size(addr, max_addr)) /
-						MAX_NUMNODES;
-	min_size = max(min_size, FAKE_NODE_MIN_SIZE);
-	if ((min_size & FAKE_NODE_MIN_HASH_MASK) < min_size)
-		min_size = (min_size + FAKE_NODE_MIN_SIZE) &
-						FAKE_NODE_MIN_HASH_MASK;
-	if (size < min_size) {
-		pr_err("Fake node size %LuMB too small, increasing to %LuMB\n",
-			size >> 20, min_size >> 20);
-		size = min_size;
-	}
-	size &= FAKE_NODE_MIN_HASH_MASK;
-
-	for (i = 0; i < MAX_NUMNODES; i++)
-		if (physnodes[i].start != physnodes[i].end)
-			node_set(i, physnode_mask);
-	/*
-	 * Fill physical nodes with fake nodes of size until there is no memory
-	 * left on any of them.
-	 */
-	while (nodes_weight(physnode_mask)) {
-		for_each_node_mask(i, physnode_mask) {
-			u64 dma32_end = MAX_DMA32_PFN << PAGE_SHIFT;
-			u64 end;
-
-			end = find_end_of_node(physnodes[i].start,
-						physnodes[i].end, size);
-			/*
-			 * If there won't be at least FAKE_NODE_MIN_SIZE of
-			 * non-reserved memory in ZONE_DMA32 for the next node,
-			 * this one must extend to the boundary.
-			 */
-			if (end < dma32_end && dma32_end - end -
-			    memblock_x86_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE)
-				end = dma32_end;
+	for (i = 0; i < ARRAY_SIZE(mi->blk); i++)
+		if (mi->blk[i].start != mi->blk[i].end &&
+		    mi->blk[i].nid != NUMA_NO_NODE)
+			node_set(mi->blk[i].nid, *nodemask);
+}
 
-			/*
-			 * If there won't be enough non-reserved memory for the
-			 * next node, this one must extend to the end of the
-			 * physical node.
-			 */
-			if (physnodes[i].end - end -
-			    memblock_x86_hole_size(end, physnodes[i].end) < size)
-				end = physnodes[i].end;
+/**
+ * numa_reset_distance - Reset NUMA distance table
+ *
+ * The current table is freed.  The next numa_set_distance() call will
+ * create a new one.
+ */
+void __init numa_reset_distance(void)
+{
+	size_t size = numa_distance_cnt * numa_distance_cnt * sizeof(numa_distance[0]);
 
-			/*
-			 * Setup the fake node that will be allocated as bootmem
-			 * later.  If setup_node_range() returns non-zero, there
-			 * is no more memory available on this physical node.
-			 */
-			if (setup_node_range(ret++, &physnodes[i].start,
-						end - physnodes[i].start,
-						physnodes[i].end) < 0)
-				node_clear(i, physnode_mask);
-		}
-	}
-	return ret;
+	/* numa_distance could be 1LU marking allocation failure, test cnt */
+	if (numa_distance_cnt)
+		memblock_x86_free_range(__pa(numa_distance),
+					__pa(numa_distance) + size);
+	numa_distance_cnt = 0;
+	numa_distance = NULL;	/* enable table creation */
 }
 
-/*
- * Sets up the system RAM area from start_pfn to last_pfn according to the
- * numa=fake command-line option.
- */
-static int __init numa_emulation(unsigned long start_pfn,
-			unsigned long last_pfn, int acpi, int amd)
+static int __init numa_alloc_distance(void)
 {
-	u64 addr = start_pfn << PAGE_SHIFT;
-	u64 max_addr = last_pfn << PAGE_SHIFT;
-	int num_nodes;
-	int i;
+	nodemask_t nodes_parsed;
+	size_t size;
+	int i, j, cnt = 0;
+	u64 phys;
 
-	/*
-	 * If the numa=fake command-line contains a 'M' or 'G', it represents
-	 * the fixed node size.  Otherwise, if it is just a single number N,
-	 * split the system RAM into N fake nodes.
-	 */
-	if (strchr(cmdline, 'M') || strchr(cmdline, 'G')) {
-		u64 size;
+	/* size the new table and allocate it */
+	nodes_parsed = numa_nodes_parsed;
+	numa_nodemask_from_meminfo(&nodes_parsed, &numa_meminfo);
 
-		size = memparse(cmdline, &cmdline);
-		num_nodes = split_nodes_size_interleave(addr, max_addr, size);
-	} else {
-		unsigned long n;
+	for_each_node_mask(i, nodes_parsed)
+		cnt = i;
+	cnt++;
+	size = cnt * cnt * sizeof(numa_distance[0]);
 
-		n = simple_strtoul(cmdline, NULL, 0);
-		num_nodes = split_nodes_interleave(addr, max_addr, n);
+	phys = memblock_find_in_range(0, (u64)max_pfn_mapped << PAGE_SHIFT,
+				      size, PAGE_SIZE);
+	if (phys == MEMBLOCK_ERROR) {
+		pr_warning("NUMA: Warning: can't allocate distance table!\n");
+		/* don't retry until explicitly reset */
+		numa_distance = (void *)1LU;
+		return -ENOMEM;
 	}
+	memblock_x86_reserve_range(phys, phys + size, "NUMA DIST");
 
-	if (num_nodes < 0)
-		return num_nodes;
-	memnode_shift = compute_hash_shift(nodes, num_nodes, NULL);
-	if (memnode_shift < 0) {
-		memnode_shift = 0;
-		printk(KERN_ERR "No NUMA hash function found.  NUMA emulation "
-		       "disabled.\n");
-		return -1;
-	}
+	numa_distance = __va(phys);
+	numa_distance_cnt = cnt;
+
+	/* fill with the default distances */
+	for (i = 0; i < cnt; i++)
+		for (j = 0; j < cnt; j++)
+			numa_distance[i * cnt + j] = i == j ?
+				LOCAL_DISTANCE : REMOTE_DISTANCE;
+	printk(KERN_DEBUG "NUMA: Initialized distance table, cnt=%d\n", cnt);
 
-	/*
-	 * We need to vacate all active ranges that may have been registered for
-	 * the e820 memory map.
-	 */
-	remove_all_active_ranges();
-	for_each_node_mask(i, node_possible_map) {
-		memblock_x86_register_active_regions(i, nodes[i].start >> PAGE_SHIFT,
-						nodes[i].end >> PAGE_SHIFT);
-		setup_node_bootmem(i, nodes[i].start, nodes[i].end);
-	}
-	setup_physnodes(addr, max_addr, acpi, amd);
-	fake_physnodes(acpi, amd, num_nodes);
-	numa_init_array();
 	return 0;
 }
-#endif /* CONFIG_NUMA_EMU */
 
-void __init initmem_init(unsigned long start_pfn, unsigned long last_pfn,
-				int acpi, int amd)
+/**
+ * numa_set_distance - Set NUMA distance from one NUMA to another
+ * @from: the 'from' node to set distance
+ * @to: the 'to'  node to set distance
+ * @distance: NUMA distance
+ *
+ * Set the distance from node @from to @to to @distance.  If distance table
+ * doesn't exist, one which is large enough to accomodate all the currently
+ * known nodes will be created.
+ *
+ * If such table cannot be allocated, a warning is printed and further
+ * calls are ignored until the distance table is reset with
+ * numa_reset_distance().
+ *
+ * If @from or @to is higher than the highest known node at the time of
+ * table creation or @distance doesn't make sense, the call is ignored.
+ * This is to allow simplification of specific NUMA config implementations.
+ */
+void __init numa_set_distance(int from, int to, int distance)
 {
-	int i;
-
-	nodes_clear(node_possible_map);
-	nodes_clear(node_online_map);
-
-#ifdef CONFIG_NUMA_EMU
-	setup_physnodes(start_pfn << PAGE_SHIFT, last_pfn << PAGE_SHIFT,
-			acpi, amd);
-	if (cmdline && !numa_emulation(start_pfn, last_pfn, acpi, amd))
+	if (!numa_distance && numa_alloc_distance() < 0)
 		return;
-	setup_physnodes(start_pfn << PAGE_SHIFT, last_pfn << PAGE_SHIFT,
-			acpi, amd);
-	nodes_clear(node_possible_map);
-	nodes_clear(node_online_map);
-#endif
 
-#ifdef CONFIG_ACPI_NUMA
-	if (!numa_off && acpi && !acpi_scan_nodes(start_pfn << PAGE_SHIFT,
-						  last_pfn << PAGE_SHIFT))
+	if (from >= numa_distance_cnt || to >= numa_distance_cnt) {
+		printk_once(KERN_DEBUG "NUMA: Debug: distance out of bound, from=%d to=%d distance=%d\n",
+			    from, to, distance);
 		return;
-	nodes_clear(node_possible_map);
-	nodes_clear(node_online_map);
-#endif
+	}
 
-#ifdef CONFIG_AMD_NUMA
-	if (!numa_off && amd && !amd_scan_nodes())
+	if ((u8)distance != distance ||
+	    (from == to && distance != LOCAL_DISTANCE)) {
+		pr_warn_once("NUMA: Warning: invalid distance parameter, from=%d to=%d distance=%d\n",
+			     from, to, distance);
 		return;
-	nodes_clear(node_possible_map);
-	nodes_clear(node_online_map);
-#endif
-	printk(KERN_INFO "%s\n",
-	       numa_off ? "NUMA turned off" : "No NUMA configuration found");
+	}
 
-	printk(KERN_INFO "Faking a node at %016lx-%016lx\n",
-	       start_pfn << PAGE_SHIFT,
-	       last_pfn << PAGE_SHIFT);
-	/* setup dummy node covering all memory */
-	memnode_shift = 63;
-	memnodemap = memnode.embedded_map;
-	memnodemap[0] = 0;
-	node_set_online(0);
-	node_set(0, node_possible_map);
-	for (i = 0; i < nr_cpu_ids; i++)
-		numa_set_node(i, 0);
-	memblock_x86_register_active_regions(0, start_pfn, last_pfn);
-	setup_node_bootmem(0, start_pfn << PAGE_SHIFT, last_pfn << PAGE_SHIFT);
+	numa_distance[from * numa_distance_cnt + to] = distance;
 }
 
-unsigned long __init numa_free_all_bootmem(void)
+int __node_distance(int from, int to)
 {
-	unsigned long pages = 0;
-	int i;
+	if (from >= numa_distance_cnt || to >= numa_distance_cnt)
+		return from == to ? LOCAL_DISTANCE : REMOTE_DISTANCE;
+	return numa_distance[from * numa_distance_cnt + to];
+}
+EXPORT_SYMBOL(__node_distance);
 
-	for_each_online_node(i)
-		pages += free_all_bootmem_node(NODE_DATA(i));
+/*
+ * Sanity check to catch more bad NUMA configurations (they are amazingly
+ * common).  Make sure the nodes cover all memory.
+ */
+static bool __init numa_meminfo_cover_memory(const struct numa_meminfo *mi)
+{
+	unsigned long numaram, e820ram;
+	int i;
 
-	pages += free_all_memory_core_early(MAX_NUMNODES);
+	numaram = 0;
+	for (i = 0; i < mi->nr_blks; i++) {
+		unsigned long s = mi->blk[i].start >> PAGE_SHIFT;
+		unsigned long e = mi->blk[i].end >> PAGE_SHIFT;
+		numaram += e - s;
+		numaram -= __absent_pages_in_range(mi->blk[i].nid, s, e);
+		if ((long)numaram < 0)
+			numaram = 0;
+	}
 
-	return pages;
+	e820ram = max_pfn - (memblock_x86_hole_size(0,
+					max_pfn << PAGE_SHIFT) >> PAGE_SHIFT);
+	/* We seem to lose 3 pages somewhere. Allow 1M of slack. */
+	if ((long)(e820ram - numaram) >= (1 << (20 - PAGE_SHIFT))) {
+		printk(KERN_ERR "NUMA: nodes only cover %luMB of your %luMB e820 RAM. Not used.\n",
+		       (numaram << PAGE_SHIFT) >> 20,
+		       (e820ram << PAGE_SHIFT) >> 20);
+		return false;
+	}
+	return true;
 }
 
-#ifdef CONFIG_NUMA
-
-static __init int find_near_online_node(int node)
+static int __init numa_register_memblks(struct numa_meminfo *mi)
 {
-	int n, val;
-	int min_val = INT_MAX;
-	int best_node = -1;
+	int i, nid;
 
-	for_each_online_node(n) {
-		val = node_distance(node, n);
+	/* Account for nodes with cpus and no memory */
+	node_possible_map = numa_nodes_parsed;
+	numa_nodemask_from_meminfo(&node_possible_map, mi);
+	if (WARN_ON(nodes_empty(node_possible_map)))
+		return -EINVAL;
 
-		if (val < min_val) {
-			min_val = val;
-			best_node = n;
+	memnode_shift = compute_hash_shift(mi);
+	if (memnode_shift < 0) {
+		printk(KERN_ERR "NUMA: No NUMA node hash function found. Contact maintainer\n");
+		return -EINVAL;
+	}
+
+	for (i = 0; i < mi->nr_blks; i++)
+		memblock_x86_register_active_regions(mi->blk[i].nid,
+					mi->blk[i].start >> PAGE_SHIFT,
+					mi->blk[i].end >> PAGE_SHIFT);
+
+	/* for out of order entries */
+	sort_node_map();
+	if (!numa_meminfo_cover_memory(mi))
+		return -EINVAL;
+
+	/* Finally register nodes. */
+	for_each_node_mask(nid, node_possible_map) {
+		u64 start = (u64)max_pfn << PAGE_SHIFT;
+		u64 end = 0;
+
+		for (i = 0; i < mi->nr_blks; i++) {
+			if (nid != mi->blk[i].nid)
+				continue;
+			start = min(mi->blk[i].start, start);
+			end = max(mi->blk[i].end, end);
 		}
+
+		if (start < end)
+			setup_node_bootmem(nid, start, end);
 	}
 
-	return best_node;
+	return 0;
 }
 
-/*
- * Setup early cpu_to_node.
+/**
+ * dummy_numma_init - Fallback dummy NUMA init
  *
- * Populate cpu_to_node[] only if x86_cpu_to_apicid[],
- * and apicid_to_node[] tables have valid entries for a CPU.
- * This means we skip cpu_to_node[] initialisation for NUMA
- * emulation and faking node case (when running a kernel compiled
- * for NUMA on a non NUMA box), which is OK as cpu_to_node[]
- * is already initialized in a round robin manner at numa_init_array,
- * prior to this call, and this initialization is good enough
- * for the fake NUMA cases.
+ * Used if there's no underlying NUMA architecture, NUMA initialization
+ * fails, or NUMA is disabled on the command line.
  *
- * Called before the per_cpu areas are setup.
+ * Must online at least one node and add memory blocks that cover all
+ * allowed memory.  This function must not fail.
  */
-void __init init_cpu_to_node(void)
+static int __init dummy_numa_init(void)
 {
-	int cpu;
-	u16 *cpu_to_apicid = early_per_cpu_ptr(x86_cpu_to_apicid);
-
-	BUG_ON(cpu_to_apicid == NULL);
+	printk(KERN_INFO "%s\n",
+	       numa_off ? "NUMA turned off" : "No NUMA configuration found");
+	printk(KERN_INFO "Faking a node at %016lx-%016lx\n",
+	       0LU, max_pfn << PAGE_SHIFT);
 
-	for_each_possible_cpu(cpu) {
-		int node;
-		u16 apicid = cpu_to_apicid[cpu];
+	node_set(0, numa_nodes_parsed);
+	numa_add_memblk(0, 0, (u64)max_pfn << PAGE_SHIFT);
 
-		if (apicid == BAD_APICID)
-			continue;
-		node = apicid_to_node[apicid];
-		if (node == NUMA_NO_NODE)
-			continue;
-		if (!node_online(node))
-			node = find_near_online_node(node);
-		numa_set_node(cpu, node);
-	}
+	return 0;
 }
-#endif
 
-
-void __cpuinit numa_set_node(int cpu, int node)
+static int __init numa_init(int (*init_func)(void))
 {
-	int *cpu_to_node_map = early_per_cpu_ptr(x86_cpu_to_node_map);
-
-	/* early setting, no percpu area yet */
-	if (cpu_to_node_map) {
-		cpu_to_node_map[cpu] = node;
-		return;
-	}
-
-#ifdef CONFIG_DEBUG_PER_CPU_MAPS
-	if (cpu >= nr_cpu_ids || !cpu_possible(cpu)) {
-		printk(KERN_ERR "numa_set_node: invalid cpu# (%d)\n", cpu);
-		dump_stack();
-		return;
-	}
-#endif
-	per_cpu(x86_cpu_to_node_map, cpu) = node;
+	int i;
+	int ret;
 
-	if (node != NUMA_NO_NODE)
-		set_cpu_numa_node(cpu, node);
-}
+	for (i = 0; i < MAX_LOCAL_APIC; i++)
+		set_apicid_to_node(i, NUMA_NO_NODE);
 
-void __cpuinit numa_clear_node(int cpu)
-{
-	numa_set_node(cpu, NUMA_NO_NODE);
-}
-
-#ifndef CONFIG_DEBUG_PER_CPU_MAPS
+	nodes_clear(numa_nodes_parsed);
+	nodes_clear(node_possible_map);
+	nodes_clear(node_online_map);
+	memset(&numa_meminfo, 0, sizeof(numa_meminfo));
+	remove_all_active_ranges();
+	numa_reset_distance();
 
-#ifndef CONFIG_NUMA_EMU
-void __cpuinit numa_add_cpu(int cpu)
-{
-	cpumask_set_cpu(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
-}
+	ret = init_func();
+	if (ret < 0)
+		return ret;
+	ret = numa_cleanup_meminfo(&numa_meminfo);
+	if (ret < 0)
+		return ret;
 
-void __cpuinit numa_remove_cpu(int cpu)
-{
-	cpumask_clear_cpu(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
-}
-#else
-void __cpuinit numa_add_cpu(int cpu)
-{
-	unsigned long addr;
-	u16 apicid;
-	int physnid;
-	int nid = NUMA_NO_NODE;
+	numa_emulation(&numa_meminfo, numa_distance_cnt);
 
-	nid = early_cpu_to_node(cpu);
-	BUG_ON(nid == NUMA_NO_NODE || !node_online(nid));
+	ret = numa_register_memblks(&numa_meminfo);
+	if (ret < 0)
+		return ret;
 
-	/*
-	 * Use the starting address of the emulated node to find which physical
-	 * node it is allocated on.
-	 */
-	addr = node_start_pfn(nid) << PAGE_SHIFT;
-	for (physnid = 0; physnid < MAX_NUMNODES; physnid++)
-		if (addr >= physnodes[physnid].start &&
-		    addr < physnodes[physnid].end)
-			break;
+	for (i = 0; i < nr_cpu_ids; i++) {
+		int nid = early_cpu_to_node(i);
 
-	/*
-	 * Map the cpu to each emulated node that is allocated on the physical
-	 * node of the cpu's apic id.
-	 */
-	for_each_online_node(nid) {
-		addr = node_start_pfn(nid) << PAGE_SHIFT;
-		if (addr >= physnodes[physnid].start &&
-		    addr < physnodes[physnid].end)
-			cpumask_set_cpu(cpu, node_to_cpumask_map[nid]);
+		if (nid == NUMA_NO_NODE)
+			continue;
+		if (!node_online(nid))
+			numa_clear_node(i);
 	}
+	numa_init_array();
+	return 0;
 }
 
-void __cpuinit numa_remove_cpu(int cpu)
+void __init initmem_init(void)
 {
-	int i;
+	int ret;
 
-	for_each_online_node(i)
-		cpumask_clear_cpu(cpu, node_to_cpumask_map[i]);
-}
-#endif /* !CONFIG_NUMA_EMU */
-
-#else /* CONFIG_DEBUG_PER_CPU_MAPS */
-static struct cpumask __cpuinit *debug_cpumask_set_cpu(int cpu, int enable)
-{
-	int node = early_cpu_to_node(cpu);
-	struct cpumask *mask;
-	char buf[64];
-
-	mask = node_to_cpumask_map[node];
-	if (!mask) {
-		pr_err("node_to_cpumask_map[%i] NULL\n", node);
-		dump_stack();
-		return NULL;
+	if (!numa_off) {
+#ifdef CONFIG_ACPI_NUMA
+		ret = numa_init(x86_acpi_numa_init);
+		if (!ret)
+			return;
+#endif
+#ifdef CONFIG_AMD_NUMA
+		ret = numa_init(amd_numa_init);
+		if (!ret)
+			return;
+#endif
 	}
 
-	cpulist_scnprintf(buf, sizeof(buf), mask);
-	printk(KERN_DEBUG "%s cpu %d node %d: mask now %s\n",
-		enable ? "numa_add_cpu" : "numa_remove_cpu",
-		cpu, node, buf);
-	return mask;
+	numa_init(dummy_numa_init);
 }
 
-/*
- * --------- debug versions of the numa functions ---------
- */
-#ifndef CONFIG_NUMA_EMU
-static void __cpuinit numa_set_cpumask(int cpu, int enable)
-{
-	struct cpumask *mask;
-
-	mask = debug_cpumask_set_cpu(cpu, enable);
-	if (!mask)
-		return;
-
-	if (enable)
-		cpumask_set_cpu(cpu, mask);
-	else
-		cpumask_clear_cpu(cpu, mask);
-}
-#else
-static void __cpuinit numa_set_cpumask(int cpu, int enable)
+unsigned long __init numa_free_all_bootmem(void)
 {
-	int node = early_cpu_to_node(cpu);
-	struct cpumask *mask;
+	unsigned long pages = 0;
 	int i;
 
-	for_each_online_node(i) {
-		unsigned long addr;
-
-		addr = node_start_pfn(i) << PAGE_SHIFT;
-		if (addr < physnodes[node].start ||
-					addr >= physnodes[node].end)
-			continue;
-		mask = debug_cpumask_set_cpu(cpu, enable);
-		if (!mask)
-			return;
-
-		if (enable)
-			cpumask_set_cpu(cpu, mask);
-		else
-			cpumask_clear_cpu(cpu, mask);
-	}
-}
-#endif /* CONFIG_NUMA_EMU */
+	for_each_online_node(i)
+		pages += free_all_bootmem_node(NODE_DATA(i));
 
-void __cpuinit numa_add_cpu(int cpu)
-{
-	numa_set_cpumask(cpu, 1);
-}
+	pages += free_all_memory_core_early(MAX_NUMNODES);
 
-void __cpuinit numa_remove_cpu(int cpu)
-{
-	numa_set_cpumask(cpu, 0);
+	return pages;
 }
 
-int __cpu_to_node(int cpu)
+int __cpuinit numa_cpu_node(int cpu)
 {
-	if (early_per_cpu_ptr(x86_cpu_to_node_map)) {
-		printk(KERN_WARNING
-			"cpu_to_node(%d): usage too early!\n", cpu);
-		dump_stack();
-		return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu];
-	}
-	return per_cpu(x86_cpu_to_node_map, cpu);
-}
-EXPORT_SYMBOL(__cpu_to_node);
+	int apicid = early_per_cpu(x86_cpu_to_apicid, cpu);
 
-/*
- * Same function as cpu_to_node() but used if called before the
- * per_cpu areas are setup.
- */
-int early_cpu_to_node(int cpu)
-{
-	if (early_per_cpu_ptr(x86_cpu_to_node_map))
-		return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu];
-
-	if (!cpu_possible(cpu)) {
-		printk(KERN_WARNING
-			"early_cpu_to_node(%d): no per_cpu area!\n", cpu);
-		dump_stack();
-		return NUMA_NO_NODE;
-	}
-	return per_cpu(x86_cpu_to_node_map, cpu);
+	if (apicid != BAD_APICID)
+		return __apicid_to_node[apicid];
+	return NUMA_NO_NODE;
 }
-
-/*
- * --------- end of debug versions of the numa functions ---------
- */
-
-#endif /* CONFIG_DEBUG_PER_CPU_MAPS */
diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c
new file mode 100644
index 000000000000..ad091e4cff17
--- /dev/null
+++ b/arch/x86/mm/numa_emulation.c
@@ -0,0 +1,494 @@
+/*
+ * NUMA emulation
+ */
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/topology.h>
+#include <linux/memblock.h>
+#include <asm/dma.h>
+
+#include "numa_internal.h"
+
+static int emu_nid_to_phys[MAX_NUMNODES] __cpuinitdata;
+static char *emu_cmdline __initdata;
+
+void __init numa_emu_cmdline(char *str)
+{
+	emu_cmdline = str;
+}
+
+static int __init emu_find_memblk_by_nid(int nid, const struct numa_meminfo *mi)
+{
+	int i;
+
+	for (i = 0; i < mi->nr_blks; i++)
+		if (mi->blk[i].nid == nid)
+			return i;
+	return -ENOENT;
+}
+
+/*
+ * Sets up nid to range from @start to @end.  The return value is -errno if
+ * something went wrong, 0 otherwise.
+ */
+static int __init emu_setup_memblk(struct numa_meminfo *ei,
+				   struct numa_meminfo *pi,
+				   int nid, int phys_blk, u64 size)
+{
+	struct numa_memblk *eb = &ei->blk[ei->nr_blks];
+	struct numa_memblk *pb = &pi->blk[phys_blk];
+
+	if (ei->nr_blks >= NR_NODE_MEMBLKS) {
+		pr_err("NUMA: Too many emulated memblks, failing emulation\n");
+		return -EINVAL;
+	}
+
+	ei->nr_blks++;
+	eb->start = pb->start;
+	eb->end = pb->start + size;
+	eb->nid = nid;
+
+	if (emu_nid_to_phys[nid] == NUMA_NO_NODE)
+		emu_nid_to_phys[nid] = pb->nid;
+
+	pb->start += size;
+	if (pb->start >= pb->end) {
+		WARN_ON_ONCE(pb->start > pb->end);
+		numa_remove_memblk_from(phys_blk, pi);
+	}
+
+	printk(KERN_INFO "Faking node %d at %016Lx-%016Lx (%LuMB)\n", nid,
+	       eb->start, eb->end, (eb->end - eb->start) >> 20);
+	return 0;
+}
+
+/*
+ * Sets up nr_nodes fake nodes interleaved over physical nodes ranging from addr
+ * to max_addr.  The return value is the number of nodes allocated.
+ */
+static int __init split_nodes_interleave(struct numa_meminfo *ei,
+					 struct numa_meminfo *pi,
+					 u64 addr, u64 max_addr, int nr_nodes)
+{
+	nodemask_t physnode_mask = NODE_MASK_NONE;
+	u64 size;
+	int big;
+	int nid = 0;
+	int i, ret;
+
+	if (nr_nodes <= 0)
+		return -1;
+	if (nr_nodes > MAX_NUMNODES) {
+		pr_info("numa=fake=%d too large, reducing to %d\n",
+			nr_nodes, MAX_NUMNODES);
+		nr_nodes = MAX_NUMNODES;
+	}
+
+	size = (max_addr - addr - memblock_x86_hole_size(addr, max_addr)) / nr_nodes;
+	/*
+	 * Calculate the number of big nodes that can be allocated as a result
+	 * of consolidating the remainder.
+	 */
+	big = ((size & ~FAKE_NODE_MIN_HASH_MASK) * nr_nodes) /
+		FAKE_NODE_MIN_SIZE;
+
+	size &= FAKE_NODE_MIN_HASH_MASK;
+	if (!size) {
+		pr_err("Not enough memory for each node.  "
+			"NUMA emulation disabled.\n");
+		return -1;
+	}
+
+	for (i = 0; i < pi->nr_blks; i++)
+		node_set(pi->blk[i].nid, physnode_mask);
+
+	/*
+	 * Continue to fill physical nodes with fake nodes until there is no
+	 * memory left on any of them.
+	 */
+	while (nodes_weight(physnode_mask)) {
+		for_each_node_mask(i, physnode_mask) {
+			u64 dma32_end = PFN_PHYS(MAX_DMA32_PFN);
+			u64 start, limit, end;
+			int phys_blk;
+
+			phys_blk = emu_find_memblk_by_nid(i, pi);
+			if (phys_blk < 0) {
+				node_clear(i, physnode_mask);
+				continue;
+			}
+			start = pi->blk[phys_blk].start;
+			limit = pi->blk[phys_blk].end;
+			end = start + size;
+
+			if (nid < big)
+				end += FAKE_NODE_MIN_SIZE;
+
+			/*
+			 * Continue to add memory to this fake node if its
+			 * non-reserved memory is less than the per-node size.
+			 */
+			while (end - start -
+			       memblock_x86_hole_size(start, end) < size) {
+				end += FAKE_NODE_MIN_SIZE;
+				if (end > limit) {
+					end = limit;
+					break;
+				}
+			}
+
+			/*
+			 * If there won't be at least FAKE_NODE_MIN_SIZE of
+			 * non-reserved memory in ZONE_DMA32 for the next node,
+			 * this one must extend to the boundary.
+			 */
+			if (end < dma32_end && dma32_end - end -
+			    memblock_x86_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE)
+				end = dma32_end;
+
+			/*
+			 * If there won't be enough non-reserved memory for the
+			 * next node, this one must extend to the end of the
+			 * physical node.
+			 */
+			if (limit - end -
+			    memblock_x86_hole_size(end, limit) < size)
+				end = limit;
+
+			ret = emu_setup_memblk(ei, pi, nid++ % nr_nodes,
+					       phys_blk,
+					       min(end, limit) - start);
+			if (ret < 0)
+				return ret;
+		}
+	}
+	return 0;
+}
+
+/*
+ * Returns the end address of a node so that there is at least `size' amount of
+ * non-reserved memory or `max_addr' is reached.
+ */
+static u64 __init find_end_of_node(u64 start, u64 max_addr, u64 size)
+{
+	u64 end = start + size;
+
+	while (end - start - memblock_x86_hole_size(start, end) < size) {
+		end += FAKE_NODE_MIN_SIZE;
+		if (end > max_addr) {
+			end = max_addr;
+			break;
+		}
+	}
+	return end;
+}
+
+/*
+ * Sets up fake nodes of `size' interleaved over physical nodes ranging from
+ * `addr' to `max_addr'.  The return value is the number of nodes allocated.
+ */
+static int __init split_nodes_size_interleave(struct numa_meminfo *ei,
+					      struct numa_meminfo *pi,
+					      u64 addr, u64 max_addr, u64 size)
+{
+	nodemask_t physnode_mask = NODE_MASK_NONE;
+	u64 min_size;
+	int nid = 0;
+	int i, ret;
+
+	if (!size)
+		return -1;
+	/*
+	 * The limit on emulated nodes is MAX_NUMNODES, so the size per node is
+	 * increased accordingly if the requested size is too small.  This
+	 * creates a uniform distribution of node sizes across the entire
+	 * machine (but not necessarily over physical nodes).
+	 */
+	min_size = (max_addr - addr - memblock_x86_hole_size(addr, max_addr)) /
+						MAX_NUMNODES;
+	min_size = max(min_size, FAKE_NODE_MIN_SIZE);
+	if ((min_size & FAKE_NODE_MIN_HASH_MASK) < min_size)
+		min_size = (min_size + FAKE_NODE_MIN_SIZE) &
+						FAKE_NODE_MIN_HASH_MASK;
+	if (size < min_size) {
+		pr_err("Fake node size %LuMB too small, increasing to %LuMB\n",
+			size >> 20, min_size >> 20);
+		size = min_size;
+	}
+	size &= FAKE_NODE_MIN_HASH_MASK;
+
+	for (i = 0; i < pi->nr_blks; i++)
+		node_set(pi->blk[i].nid, physnode_mask);
+
+	/*
+	 * Fill physical nodes with fake nodes of size until there is no memory
+	 * left on any of them.
+	 */
+	while (nodes_weight(physnode_mask)) {
+		for_each_node_mask(i, physnode_mask) {
+			u64 dma32_end = MAX_DMA32_PFN << PAGE_SHIFT;
+			u64 start, limit, end;
+			int phys_blk;
+
+			phys_blk = emu_find_memblk_by_nid(i, pi);
+			if (phys_blk < 0) {
+				node_clear(i, physnode_mask);
+				continue;
+			}
+			start = pi->blk[phys_blk].start;
+			limit = pi->blk[phys_blk].end;
+
+			end = find_end_of_node(start, limit, size);
+			/*
+			 * If there won't be at least FAKE_NODE_MIN_SIZE of
+			 * non-reserved memory in ZONE_DMA32 for the next node,
+			 * this one must extend to the boundary.
+			 */
+			if (end < dma32_end && dma32_end - end -
+			    memblock_x86_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE)
+				end = dma32_end;
+
+			/*
+			 * If there won't be enough non-reserved memory for the
+			 * next node, this one must extend to the end of the
+			 * physical node.
+			 */
+			if (limit - end -
+			    memblock_x86_hole_size(end, limit) < size)
+				end = limit;
+
+			ret = emu_setup_memblk(ei, pi, nid++ % MAX_NUMNODES,
+					       phys_blk,
+					       min(end, limit) - start);
+			if (ret < 0)
+				return ret;
+		}
+	}
+	return 0;
+}
+
+/**
+ * numa_emulation - Emulate NUMA nodes
+ * @numa_meminfo: NUMA configuration to massage
+ * @numa_dist_cnt: The size of the physical NUMA distance table
+ *
+ * Emulate NUMA nodes according to the numa=fake kernel parameter.
+ * @numa_meminfo contains the physical memory configuration and is modified
+ * to reflect the emulated configuration on success.  @numa_dist_cnt is
+ * used to determine the size of the physical distance table.
+ *
+ * On success, the following modifications are made.
+ *
+ * - @numa_meminfo is updated to reflect the emulated nodes.
+ *
+ * - __apicid_to_node[] is updated such that APIC IDs are mapped to the
+ *   emulated nodes.
+ *
+ * - NUMA distance table is rebuilt to represent distances between emulated
+ *   nodes.  The distances are determined considering how emulated nodes
+ *   are mapped to physical nodes and match the actual distances.
+ *
+ * - emu_nid_to_phys[] reflects how emulated nodes are mapped to physical
+ *   nodes.  This is used by numa_add_cpu() and numa_remove_cpu().
+ *
+ * If emulation is not enabled or fails, emu_nid_to_phys[] is filled with
+ * identity mapping and no other modification is made.
+ */
+void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
+{
+	static struct numa_meminfo ei __initdata;
+	static struct numa_meminfo pi __initdata;
+	const u64 max_addr = max_pfn << PAGE_SHIFT;
+	u8 *phys_dist = NULL;
+	size_t phys_size = numa_dist_cnt * numa_dist_cnt * sizeof(phys_dist[0]);
+	int max_emu_nid, dfl_phys_nid;
+	int i, j, ret;
+
+	if (!emu_cmdline)
+		goto no_emu;
+
+	memset(&ei, 0, sizeof(ei));
+	pi = *numa_meminfo;
+
+	for (i = 0; i < MAX_NUMNODES; i++)
+		emu_nid_to_phys[i] = NUMA_NO_NODE;
+
+	/*
+	 * If the numa=fake command-line contains a 'M' or 'G', it represents
+	 * the fixed node size.  Otherwise, if it is just a single number N,
+	 * split the system RAM into N fake nodes.
+	 */
+	if (strchr(emu_cmdline, 'M') || strchr(emu_cmdline, 'G')) {
+		u64 size;
+
+		size = memparse(emu_cmdline, &emu_cmdline);
+		ret = split_nodes_size_interleave(&ei, &pi, 0, max_addr, size);
+	} else {
+		unsigned long n;
+
+		n = simple_strtoul(emu_cmdline, NULL, 0);
+		ret = split_nodes_interleave(&ei, &pi, 0, max_addr, n);
+	}
+
+	if (ret < 0)
+		goto no_emu;
+
+	if (numa_cleanup_meminfo(&ei) < 0) {
+		pr_warning("NUMA: Warning: constructed meminfo invalid, disabling emulation\n");
+		goto no_emu;
+	}
+
+	/* copy the physical distance table */
+	if (numa_dist_cnt) {
+		u64 phys;
+
+		phys = memblock_find_in_range(0,
+					      (u64)max_pfn_mapped << PAGE_SHIFT,
+					      phys_size, PAGE_SIZE);
+		if (phys == MEMBLOCK_ERROR) {
+			pr_warning("NUMA: Warning: can't allocate copy of distance table, disabling emulation\n");
+			goto no_emu;
+		}
+		memblock_x86_reserve_range(phys, phys + phys_size, "TMP NUMA DIST");
+		phys_dist = __va(phys);
+
+		for (i = 0; i < numa_dist_cnt; i++)
+			for (j = 0; j < numa_dist_cnt; j++)
+				phys_dist[i * numa_dist_cnt + j] =
+					node_distance(i, j);
+	}
+
+	/*
+	 * Determine the max emulated nid and the default phys nid to use
+	 * for unmapped nodes.
+	 */
+	max_emu_nid = 0;
+	dfl_phys_nid = NUMA_NO_NODE;
+	for (i = 0; i < ARRAY_SIZE(emu_nid_to_phys); i++) {
+		if (emu_nid_to_phys[i] != NUMA_NO_NODE) {
+			max_emu_nid = i;
+			if (dfl_phys_nid == NUMA_NO_NODE)
+				dfl_phys_nid = emu_nid_to_phys[i];
+		}
+	}
+	if (dfl_phys_nid == NUMA_NO_NODE) {
+		pr_warning("NUMA: Warning: can't determine default physical node, disabling emulation\n");
+		goto no_emu;
+	}
+
+	/* commit */
+	*numa_meminfo = ei;
+
+	/*
+	 * Transform __apicid_to_node table to use emulated nids by
+	 * reverse-mapping phys_nid.  The maps should always exist but fall
+	 * back to zero just in case.
+	 */
+	for (i = 0; i < ARRAY_SIZE(__apicid_to_node); i++) {
+		if (__apicid_to_node[i] == NUMA_NO_NODE)
+			continue;
+		for (j = 0; j < ARRAY_SIZE(emu_nid_to_phys); j++)
+			if (__apicid_to_node[i] == emu_nid_to_phys[j])
+				break;
+		__apicid_to_node[i] = j < ARRAY_SIZE(emu_nid_to_phys) ? j : 0;
+	}
+
+	/* make sure all emulated nodes are mapped to a physical node */
+	for (i = 0; i < ARRAY_SIZE(emu_nid_to_phys); i++)
+		if (emu_nid_to_phys[i] == NUMA_NO_NODE)
+			emu_nid_to_phys[i] = dfl_phys_nid;
+
+	/* transform distance table */
+	numa_reset_distance();
+	for (i = 0; i < max_emu_nid + 1; i++) {
+		for (j = 0; j < max_emu_nid + 1; j++) {
+			int physi = emu_nid_to_phys[i];
+			int physj = emu_nid_to_phys[j];
+			int dist;
+
+			if (physi >= numa_dist_cnt || physj >= numa_dist_cnt)
+				dist = physi == physj ?
+					LOCAL_DISTANCE : REMOTE_DISTANCE;
+			else
+				dist = phys_dist[physi * numa_dist_cnt + physj];
+
+			numa_set_distance(i, j, dist);
+		}
+	}
+
+	/* free the copied physical distance table */
+	if (phys_dist)
+		memblock_x86_free_range(__pa(phys_dist), __pa(phys_dist) + phys_size);
+	return;
+
+no_emu:
+	/* No emulation.  Build identity emu_nid_to_phys[] for numa_add_cpu() */
+	for (i = 0; i < ARRAY_SIZE(emu_nid_to_phys); i++)
+		emu_nid_to_phys[i] = i;
+}
+
+#ifndef CONFIG_DEBUG_PER_CPU_MAPS
+void __cpuinit numa_add_cpu(int cpu)
+{
+	int physnid, nid;
+
+	nid = early_cpu_to_node(cpu);
+	BUG_ON(nid == NUMA_NO_NODE || !node_online(nid));
+
+	physnid = emu_nid_to_phys[nid];
+
+	/*
+	 * Map the cpu to each emulated node that is allocated on the physical
+	 * node of the cpu's apic id.
+	 */
+	for_each_online_node(nid)
+		if (emu_nid_to_phys[nid] == physnid)
+			cpumask_set_cpu(cpu, node_to_cpumask_map[nid]);
+}
+
+void __cpuinit numa_remove_cpu(int cpu)
+{
+	int i;
+
+	for_each_online_node(i)
+		cpumask_clear_cpu(cpu, node_to_cpumask_map[i]);
+}
+#else	/* !CONFIG_DEBUG_PER_CPU_MAPS */
+static void __cpuinit numa_set_cpumask(int cpu, int enable)
+{
+	struct cpumask *mask;
+	int nid, physnid, i;
+
+	nid = early_cpu_to_node(cpu);
+	if (nid == NUMA_NO_NODE) {
+		/* early_cpu_to_node() already emits a warning and trace */
+		return;
+	}
+
+	physnid = emu_nid_to_phys[nid];
+
+	for_each_online_node(i) {
+		if (emu_nid_to_phys[nid] != physnid)
+			continue;
+
+		mask = debug_cpumask_set_cpu(cpu, enable);
+		if (!mask)
+			return;
+
+		if (enable)
+			cpumask_set_cpu(cpu, mask);
+		else
+			cpumask_clear_cpu(cpu, mask);
+	}
+}
+
+void __cpuinit numa_add_cpu(int cpu)
+{
+	numa_set_cpumask(cpu, 1);
+}
+
+void __cpuinit numa_remove_cpu(int cpu)
+{
+	numa_set_cpumask(cpu, 0);
+}
+#endif	/* !CONFIG_DEBUG_PER_CPU_MAPS */
diff --git a/arch/x86/mm/numa_internal.h b/arch/x86/mm/numa_internal.h
new file mode 100644
index 000000000000..ef2d97377d7c
--- /dev/null
+++ b/arch/x86/mm/numa_internal.h
@@ -0,0 +1,31 @@
+#ifndef __X86_MM_NUMA_INTERNAL_H
+#define __X86_MM_NUMA_INTERNAL_H
+
+#include <linux/types.h>
+#include <asm/numa.h>
+
+struct numa_memblk {
+	u64			start;
+	u64			end;
+	int			nid;
+};
+
+struct numa_meminfo {
+	int			nr_blks;
+	struct numa_memblk	blk[NR_NODE_MEMBLKS];
+};
+
+void __init numa_remove_memblk_from(int idx, struct numa_meminfo *mi);
+int __init numa_cleanup_meminfo(struct numa_meminfo *mi);
+void __init numa_reset_distance(void);
+
+#ifdef CONFIG_NUMA_EMU
+void __init numa_emulation(struct numa_meminfo *numa_meminfo,
+			   int numa_dist_cnt);
+#else
+static inline void numa_emulation(struct numa_meminfo *numa_meminfo,
+				  int numa_dist_cnt)
+{ }
+#endif
+
+#endif	/* __X86_MM_NUMA_INTERNAL_H */
diff --git a/arch/x86/mm/srat_32.c b/arch/x86/mm/srat_32.c
index ae96e7b8051d..48651c6f657d 100644
--- a/arch/x86/mm/srat_32.c
+++ b/arch/x86/mm/srat_32.c
@@ -57,7 +57,7 @@ struct node_memory_chunk_s {
 static struct node_memory_chunk_s __initdata node_memory_chunk[MAXCHUNKS];
 
 static int __initdata num_memory_chunks; /* total number of memory chunks */
-static u8 __initdata apicid_to_pxm[MAX_APICID];
+static u8 __initdata apicid_to_pxm[MAX_LOCAL_APIC];
 
 int acpi_numa __initdata;
 
@@ -254,8 +254,8 @@ int __init get_memcfg_from_srat(void)
 	printk(KERN_DEBUG "Number of memory chunks in system = %d\n",
 			 num_memory_chunks);
 
-	for (i = 0; i < MAX_APICID; i++)
-		apicid_2_node[i] = pxm_to_node(apicid_to_pxm[i]);
+	for (i = 0; i < MAX_LOCAL_APIC; i++)
+		set_apicid_to_node(i, pxm_to_node(apicid_to_pxm[i]));
 
 	for (j = 0; j < num_memory_chunks; j++){
 		struct node_memory_chunk_s * chunk = &node_memory_chunk[j];
diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c
index 603d285d1daa..8e9d3394f6d4 100644
--- a/arch/x86/mm/srat_64.c
+++ b/arch/x86/mm/srat_64.c
@@ -26,88 +26,34 @@
 
 int acpi_numa __initdata;
 
-static struct acpi_table_slit *acpi_slit;
-
-static nodemask_t nodes_parsed __initdata;
-static nodemask_t cpu_nodes_parsed __initdata;
-static struct bootnode nodes[MAX_NUMNODES] __initdata;
 static struct bootnode nodes_add[MAX_NUMNODES];
 
-static int num_node_memblks __initdata;
-static struct bootnode node_memblk_range[NR_NODE_MEMBLKS] __initdata;
-static int memblk_nodeid[NR_NODE_MEMBLKS] __initdata;
-
 static __init int setup_node(int pxm)
 {
 	return acpi_map_pxm_to_node(pxm);
 }
 
-static __init int conflicting_memblks(unsigned long start, unsigned long end)
-{
-	int i;
-	for (i = 0; i < num_node_memblks; i++) {
-		struct bootnode *nd = &node_memblk_range[i];
-		if (nd->start == nd->end)
-			continue;
-		if (nd->end > start && nd->start < end)
-			return memblk_nodeid[i];
-		if (nd->end == end && nd->start == start)
-			return memblk_nodeid[i];
-	}
-	return -1;
-}
-
-static __init void cutoff_node(int i, unsigned long start, unsigned long end)
-{
-	struct bootnode *nd = &nodes[i];
-
-	if (nd->start < start) {
-		nd->start = start;
-		if (nd->end < nd->start)
-			nd->start = nd->end;
-	}
-	if (nd->end > end) {
-		nd->end = end;
-		if (nd->start > nd->end)
-			nd->start = nd->end;
-	}
-}
-
 static __init void bad_srat(void)
 {
-	int i;
 	printk(KERN_ERR "SRAT: SRAT not used.\n");
 	acpi_numa = -1;
-	for (i = 0; i < MAX_LOCAL_APIC; i++)
-		apicid_to_node[i] = NUMA_NO_NODE;
-	for (i = 0; i < MAX_NUMNODES; i++) {
-		nodes[i].start = nodes[i].end = 0;
-		nodes_add[i].start = nodes_add[i].end = 0;
-	}
-	remove_all_active_ranges();
+	memset(nodes_add, 0, sizeof(nodes_add));
 }
 
 static __init inline int srat_disabled(void)
 {
-	return numa_off || acpi_numa < 0;
+	return acpi_numa < 0;
 }
 
 /* Callback for SLIT parsing */
 void __init acpi_numa_slit_init(struct acpi_table_slit *slit)
 {
-	unsigned length;
-	unsigned long phys;
-
-	length = slit->header.length;
-	phys = memblock_find_in_range(0, max_pfn_mapped<<PAGE_SHIFT, length,
-		 PAGE_SIZE);
-
-	if (phys == MEMBLOCK_ERROR)
-		panic(" Can not save slit!\n");
+	int i, j;
 
-	acpi_slit = __va(phys);
-	memcpy(acpi_slit, slit, length);
-	memblock_x86_reserve_range(phys, phys + length, "ACPI SLIT");
+	for (i = 0; i < slit->locality_count; i++)
+		for (j = 0; j < slit->locality_count; j++)
+			numa_set_distance(pxm_to_node(i), pxm_to_node(j),
+				slit->entry[slit->locality_count * i + j]);
 }
 
 /* Callback for Proximity Domain -> x2APIC mapping */
@@ -138,8 +84,8 @@ acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa)
 		printk(KERN_INFO "SRAT: PXM %u -> APIC 0x%04x -> Node %u skipped apicid that is too big\n", pxm, apic_id, node);
 		return;
 	}
-	apicid_to_node[apic_id] = node;
-	node_set(node, cpu_nodes_parsed);
+	set_apicid_to_node(apic_id, node);
+	node_set(node, numa_nodes_parsed);
 	acpi_numa = 1;
 	printk(KERN_INFO "SRAT: PXM %u -> APIC 0x%04x -> Node %u\n",
 	       pxm, apic_id, node);
@@ -178,8 +124,8 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa)
 		return;
 	}
 
-	apicid_to_node[apic_id] = node;
-	node_set(node, cpu_nodes_parsed);
+	set_apicid_to_node(apic_id, node);
+	node_set(node, numa_nodes_parsed);
 	acpi_numa = 1;
 	printk(KERN_INFO "SRAT: PXM %u -> APIC 0x%02x -> Node %u\n",
 	       pxm, apic_id, node);
@@ -241,7 +187,7 @@ update_nodes_add(int node, unsigned long start, unsigned long end)
 	}
 
 	if (changed) {
-		node_set(node, cpu_nodes_parsed);
+		node_set(node, numa_nodes_parsed);
 		printk(KERN_INFO "SRAT: hot plug zone found %Lx - %Lx\n",
 				 nd->start, nd->end);
 	}
@@ -251,10 +197,8 @@ update_nodes_add(int node, unsigned long start, unsigned long end)
 void __init
 acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
 {
-	struct bootnode *nd, oldnode;
 	unsigned long start, end;
 	int node, pxm;
-	int i;
 
 	if (srat_disabled())
 		return;
@@ -276,300 +220,31 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
 		bad_srat();
 		return;
 	}
-	i = conflicting_memblks(start, end);
-	if (i == node) {
-		printk(KERN_WARNING
-		"SRAT: Warning: PXM %d (%lx-%lx) overlaps with itself (%Lx-%Lx)\n",
-			pxm, start, end, nodes[i].start, nodes[i].end);
-	} else if (i >= 0) {
-		printk(KERN_ERR
-		       "SRAT: PXM %d (%lx-%lx) overlaps with PXM %d (%Lx-%Lx)\n",
-		       pxm, start, end, node_to_pxm(i),
-			nodes[i].start, nodes[i].end);
+
+	if (numa_add_memblk(node, start, end) < 0) {
 		bad_srat();
 		return;
 	}
-	nd = &nodes[node];
-	oldnode = *nd;
-	if (!node_test_and_set(node, nodes_parsed)) {
-		nd->start = start;
-		nd->end = end;
-	} else {
-		if (start < nd->start)
-			nd->start = start;
-		if (nd->end < end)
-			nd->end = end;
-	}
 
 	printk(KERN_INFO "SRAT: Node %u PXM %u %lx-%lx\n", node, pxm,
 	       start, end);
 
-	if (ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) {
+	if (ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE)
 		update_nodes_add(node, start, end);
-		/* restore nodes[node] */
-		*nd = oldnode;
-		if ((nd->start | nd->end) == 0)
-			node_clear(node, nodes_parsed);
-	}
-
-	node_memblk_range[num_node_memblks].start = start;
-	node_memblk_range[num_node_memblks].end = end;
-	memblk_nodeid[num_node_memblks] = node;
-	num_node_memblks++;
-}
-
-/* Sanity check to catch more bad SRATs (they are amazingly common).
-   Make sure the PXMs cover all memory. */
-static int __init nodes_cover_memory(const struct bootnode *nodes)
-{
-	int i;
-	unsigned long pxmram, e820ram;
-
-	pxmram = 0;
-	for_each_node_mask(i, nodes_parsed) {
-		unsigned long s = nodes[i].start >> PAGE_SHIFT;
-		unsigned long e = nodes[i].end >> PAGE_SHIFT;
-		pxmram += e - s;
-		pxmram -= __absent_pages_in_range(i, s, e);
-		if ((long)pxmram < 0)
-			pxmram = 0;
-	}
-
-	e820ram = max_pfn - (memblock_x86_hole_size(0, max_pfn<<PAGE_SHIFT)>>PAGE_SHIFT);
-	/* We seem to lose 3 pages somewhere. Allow 1M of slack. */
-	if ((long)(e820ram - pxmram) >= (1<<(20 - PAGE_SHIFT))) {
-		printk(KERN_ERR
-	"SRAT: PXMs only cover %luMB of your %luMB e820 RAM. Not used.\n",
-			(pxmram << PAGE_SHIFT) >> 20,
-			(e820ram << PAGE_SHIFT) >> 20);
-		return 0;
-	}
-	return 1;
 }
 
 void __init acpi_numa_arch_fixup(void) {}
 
-#ifdef CONFIG_NUMA_EMU
-void __init acpi_get_nodes(struct bootnode *physnodes, unsigned long start,
-				unsigned long end)
-{
-	int i;
-
-	for_each_node_mask(i, nodes_parsed) {
-		cutoff_node(i, start, end);
-		physnodes[i].start = nodes[i].start;
-		physnodes[i].end = nodes[i].end;
-	}
-}
-#endif /* CONFIG_NUMA_EMU */
-
-/* Use the information discovered above to actually set up the nodes. */
-int __init acpi_scan_nodes(unsigned long start, unsigned long end)
+int __init x86_acpi_numa_init(void)
 {
-	int i;
-
-	if (acpi_numa <= 0)
-		return -1;
-
-	/* First clean up the node list */
-	for (i = 0; i < MAX_NUMNODES; i++)
-		cutoff_node(i, start, end);
-
-	/*
-	 * Join together blocks on the same node, holes between
-	 * which don't overlap with memory on other nodes.
-	 */
-	for (i = 0; i < num_node_memblks; ++i) {
-		int j, k;
-
-		for (j = i + 1; j < num_node_memblks; ++j) {
-			unsigned long start, end;
-
-			if (memblk_nodeid[i] != memblk_nodeid[j])
-				continue;
-			start = min(node_memblk_range[i].end,
-			            node_memblk_range[j].end);
-			end = max(node_memblk_range[i].start,
-			          node_memblk_range[j].start);
-			for (k = 0; k < num_node_memblks; ++k) {
-				if (memblk_nodeid[i] == memblk_nodeid[k])
-					continue;
-				if (start < node_memblk_range[k].end &&
-				    end > node_memblk_range[k].start)
-					break;
-			}
-			if (k < num_node_memblks)
-				continue;
-			start = min(node_memblk_range[i].start,
-			            node_memblk_range[j].start);
-			end = max(node_memblk_range[i].end,
-			          node_memblk_range[j].end);
-			printk(KERN_INFO "SRAT: Node %d "
-			       "[%Lx,%Lx) + [%Lx,%Lx) -> [%lx,%lx)\n",
-			       memblk_nodeid[i],
-			       node_memblk_range[i].start,
-			       node_memblk_range[i].end,
-			       node_memblk_range[j].start,
-			       node_memblk_range[j].end,
-			       start, end);
-			node_memblk_range[i].start = start;
-			node_memblk_range[i].end = end;
-			k = --num_node_memblks - j;
-			memmove(memblk_nodeid + j, memblk_nodeid + j+1,
-				k * sizeof(*memblk_nodeid));
-			memmove(node_memblk_range + j, node_memblk_range + j+1,
-				k * sizeof(*node_memblk_range));
-			--j;
-		}
-	}
-
-	memnode_shift = compute_hash_shift(node_memblk_range, num_node_memblks,
-					   memblk_nodeid);
-	if (memnode_shift < 0) {
-		printk(KERN_ERR
-		     "SRAT: No NUMA node hash function found. Contact maintainer\n");
-		bad_srat();
-		return -1;
-	}
-
-	for (i = 0; i < num_node_memblks; i++)
-		memblock_x86_register_active_regions(memblk_nodeid[i],
-				node_memblk_range[i].start >> PAGE_SHIFT,
-				node_memblk_range[i].end >> PAGE_SHIFT);
-
-	/* for out of order entries in SRAT */
-	sort_node_map();
-	if (!nodes_cover_memory(nodes)) {
-		bad_srat();
-		return -1;
-	}
+	int ret;
 
-	/* Account for nodes with cpus and no memory */
-	nodes_or(node_possible_map, nodes_parsed, cpu_nodes_parsed);
-
-	/* Finally register nodes */
-	for_each_node_mask(i, node_possible_map)
-		setup_node_bootmem(i, nodes[i].start, nodes[i].end);
-	/* Try again in case setup_node_bootmem missed one due
-	   to missing bootmem */
-	for_each_node_mask(i, node_possible_map)
-		if (!node_online(i))
-			setup_node_bootmem(i, nodes[i].start, nodes[i].end);
-
-	for (i = 0; i < nr_cpu_ids; i++) {
-		int node = early_cpu_to_node(i);
-
-		if (node == NUMA_NO_NODE)
-			continue;
-		if (!node_online(node))
-			numa_clear_node(i);
-	}
-	numa_init_array();
-	return 0;
-}
-
-#ifdef CONFIG_NUMA_EMU
-static int fake_node_to_pxm_map[MAX_NUMNODES] __initdata = {
-	[0 ... MAX_NUMNODES-1] = PXM_INVAL
-};
-static s16 fake_apicid_to_node[MAX_LOCAL_APIC] __initdata = {
-	[0 ... MAX_LOCAL_APIC-1] = NUMA_NO_NODE
-};
-static int __init find_node_by_addr(unsigned long addr)
-{
-	int ret = NUMA_NO_NODE;
-	int i;
-
-	for_each_node_mask(i, nodes_parsed) {
-		/*
-		 * Find the real node that this emulated node appears on.  For
-		 * the sake of simplicity, we only use a real node's starting
-		 * address to determine which emulated node it appears on.
-		 */
-		if (addr >= nodes[i].start && addr < nodes[i].end) {
-			ret = i;
-			break;
-		}
-	}
-	return ret;
+	ret = acpi_numa_init();
+	if (ret < 0)
+		return ret;
+	return srat_disabled() ? -EINVAL : 0;
 }
 
-/*
- * In NUMA emulation, we need to setup proximity domain (_PXM) to node ID
- * mappings that respect the real ACPI topology but reflect our emulated
- * environment.  For each emulated node, we find which real node it appears on
- * and create PXM to NID mappings for those fake nodes which mirror that
- * locality.  SLIT will now represent the correct distances between emulated
- * nodes as a result of the real topology.
- */
-void __init acpi_fake_nodes(const struct bootnode *fake_nodes, int num_nodes)
-{
-	int i, j;
-
-	for (i = 0; i < num_nodes; i++) {
-		int nid, pxm;
-
-		nid = find_node_by_addr(fake_nodes[i].start);
-		if (nid == NUMA_NO_NODE)
-			continue;
-		pxm = node_to_pxm(nid);
-		if (pxm == PXM_INVAL)
-			continue;
-		fake_node_to_pxm_map[i] = pxm;
-		/*
-		 * For each apicid_to_node mapping that exists for this real
-		 * node, it must now point to the fake node ID.
-		 */
-		for (j = 0; j < MAX_LOCAL_APIC; j++)
-			if (apicid_to_node[j] == nid &&
-			    fake_apicid_to_node[j] == NUMA_NO_NODE)
-				fake_apicid_to_node[j] = i;
-	}
-
-	/*
-	 * If there are apicid-to-node mappings for physical nodes that do not
-	 * have a corresponding emulated node, it should default to a guaranteed
-	 * value.
-	 */
-	for (i = 0; i < MAX_LOCAL_APIC; i++)
-		if (apicid_to_node[i] != NUMA_NO_NODE &&
-		    fake_apicid_to_node[i] == NUMA_NO_NODE)
-			fake_apicid_to_node[i] = 0;
-
-	for (i = 0; i < num_nodes; i++)
-		__acpi_map_pxm_to_node(fake_node_to_pxm_map[i], i);
-	memcpy(apicid_to_node, fake_apicid_to_node, sizeof(apicid_to_node));
-
-	nodes_clear(nodes_parsed);
-	for (i = 0; i < num_nodes; i++)
-		if (fake_nodes[i].start != fake_nodes[i].end)
-			node_set(i, nodes_parsed);
-}
-
-static int null_slit_node_compare(int a, int b)
-{
-	return node_to_pxm(a) == node_to_pxm(b);
-}
-#else
-static int null_slit_node_compare(int a, int b)
-{
-	return a == b;
-}
-#endif /* CONFIG_NUMA_EMU */
-
-int __node_distance(int a, int b)
-{
-	int index;
-
-	if (!acpi_slit)
-		return null_slit_node_compare(a, b) ? LOCAL_DISTANCE :
-						      REMOTE_DISTANCE;
-	index = acpi_slit->locality_count * node_to_pxm(a);
-	return acpi_slit->entry[index + node_to_pxm(b)];
-}
-
-EXPORT_SYMBOL(__node_distance);
-
 #if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) || defined(CONFIG_ACPI_HOTPLUG_MEMORY)
 int memory_add_physaddr_to_nid(u64 start)
 {
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 6acc724d5d8f..d6c0418c3e47 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -179,12 +179,8 @@ static void flush_tlb_others_ipi(const struct cpumask *cpumask,
 	sender = this_cpu_read(tlb_vector_offset);
 	f = &flush_state[sender];
 
-	/*
-	 * Could avoid this lock when
-	 * num_online_cpus() <= NUM_INVALIDATE_TLB_VECTORS, but it is
-	 * probably not worth checking this for a cache-hot lock.
-	 */
-	raw_spin_lock(&f->tlbstate_lock);
+	if (nr_cpu_ids > NUM_INVALIDATE_TLB_VECTORS)
+		raw_spin_lock(&f->tlbstate_lock);
 
 	f->flush_mm = mm;
 	f->flush_va = va;
@@ -202,7 +198,8 @@ static void flush_tlb_others_ipi(const struct cpumask *cpumask,
 
 	f->flush_mm = NULL;
 	f->flush_va = 0;
-	raw_spin_unlock(&f->tlbstate_lock);
+	if (nr_cpu_ids > NUM_INVALIDATE_TLB_VECTORS)
+		raw_spin_unlock(&f->tlbstate_lock);
 }
 
 void native_flush_tlb_others(const struct cpumask *cpumask,
@@ -211,11 +208,10 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
 	if (is_uv_system()) {
 		unsigned int cpu;
 
-		cpu = get_cpu();
+		cpu = smp_processor_id();
 		cpumask = uv_flush_tlb_others(cpumask, mm, va, cpu);
 		if (cpumask)
 			flush_tlb_others_ipi(cpumask, mm, va);
-		put_cpu();
 		return;
 	}
 	flush_tlb_others_ipi(cpumask, mm, va);
diff --git a/arch/x86/pci/ce4100.c b/arch/x86/pci/ce4100.c
index 9260b3eb18d4..67858be4b52b 100644
--- a/arch/x86/pci/ce4100.c
+++ b/arch/x86/pci/ce4100.c
@@ -255,7 +255,7 @@ int bridge_read(unsigned int devfn, int reg, int len, u32 *value)
 static int ce4100_conf_read(unsigned int seg, unsigned int bus,
 			    unsigned int devfn, int reg, int len, u32 *value)
 {
-	int i, retval = 1;
+	int i;
 
 	if (bus == 1) {
 		for (i = 0; i < ARRAY_SIZE(bus1_fixups); i++) {
diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index 25cd4a07d09f..8c4085a95ef1 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -20,7 +20,8 @@
 #include <asm/xen/pci.h>
 
 #ifdef CONFIG_ACPI
-static int xen_hvm_register_pirq(u32 gsi, int triggering)
+static int acpi_register_gsi_xen_hvm(struct device *dev, u32 gsi,
+				 int trigger, int polarity)
 {
 	int rc, irq;
 	struct physdev_map_pirq map_irq;
@@ -41,7 +42,7 @@ static int xen_hvm_register_pirq(u32 gsi, int triggering)
 		return -1;
 	}
 
-	if (triggering == ACPI_EDGE_SENSITIVE) {
+	if (trigger == ACPI_EDGE_SENSITIVE) {
 		shareable = 0;
 		name = "ioapic-edge";
 	} else {
@@ -55,12 +56,6 @@ static int xen_hvm_register_pirq(u32 gsi, int triggering)
 
 	return irq;
 }
-
-static int acpi_register_gsi_xen_hvm(struct device *dev, u32 gsi,
-				 int trigger, int polarity)
-{
-	return xen_hvm_register_pirq(gsi, trigger);
-}
 #endif
 
 #if defined(CONFIG_PCI_MSI)
@@ -91,7 +86,7 @@ static void xen_msi_compose_msg(struct pci_dev *pdev, unsigned int pirq,
 
 static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 {
-	int irq, pirq, ret = 0;
+	int irq, pirq;
 	struct msi_desc *msidesc;
 	struct msi_msg msg;
 
@@ -99,39 +94,32 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 		__read_msi_msg(msidesc, &msg);
 		pirq = MSI_ADDR_EXT_DEST_ID(msg.address_hi) |
 			((msg.address_lo >> MSI_ADDR_DEST_ID_SHIFT) & 0xff);
-		if (xen_irq_from_pirq(pirq) >= 0 && msg.data == XEN_PIRQ_MSI_DATA) {
-			xen_allocate_pirq_msi((type == PCI_CAP_ID_MSIX) ?
-					"msi-x" : "msi", &irq, &pirq, XEN_ALLOC_IRQ);
-			if (irq < 0)
+		if (msg.data != XEN_PIRQ_MSI_DATA ||
+		    xen_irq_from_pirq(pirq) < 0) {
+			pirq = xen_allocate_pirq_msi(dev, msidesc);
+			if (pirq < 0)
 				goto error;
-			ret = set_irq_msi(irq, msidesc);
-			if (ret < 0)
-				goto error_while;
-			printk(KERN_DEBUG "xen: msi already setup: msi --> irq=%d"
-					" pirq=%d\n", irq, pirq);
-			return 0;
+			xen_msi_compose_msg(dev, pirq, &msg);
+			__write_msi_msg(msidesc, &msg);
+			dev_dbg(&dev->dev, "xen: msi bound to pirq=%d\n", pirq);
+		} else {
+			dev_dbg(&dev->dev,
+				"xen: msi already bound to pirq=%d\n", pirq);
 		}
-		xen_allocate_pirq_msi((type == PCI_CAP_ID_MSIX) ?
-				"msi-x" : "msi", &irq, &pirq, (XEN_ALLOC_IRQ | XEN_ALLOC_PIRQ));
-		if (irq < 0 || pirq < 0)
+		irq = xen_bind_pirq_msi_to_irq(dev, msidesc, pirq, 0,
+					       (type == PCI_CAP_ID_MSIX) ?
+					       "msi-x" : "msi");
+		if (irq < 0)
 			goto error;
-		printk(KERN_DEBUG "xen: msi --> irq=%d, pirq=%d\n", irq, pirq);
-		xen_msi_compose_msg(dev, pirq, &msg);
-		ret = set_irq_msi(irq, msidesc);
-		if (ret < 0)
-			goto error_while;
-		write_msi_msg(irq, &msg);
+		dev_dbg(&dev->dev,
+			"xen: msi --> pirq=%d --> irq=%d\n", pirq, irq);
 	}
 	return 0;
 
-error_while:
-	unbind_from_irqhandler(irq, NULL);
 error:
-	if (ret == -ENODEV)
-		dev_err(&dev->dev, "Xen PCI frontend has not registered" \
-				" MSI/MSI-X support!\n");
-
-	return ret;
+	dev_err(&dev->dev,
+		"Xen PCI frontend has not registered MSI/MSI-X support!\n");
+	return -ENODEV;
 }
 
 /*
@@ -150,35 +138,26 @@ static int xen_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 		return -ENOMEM;
 
 	if (type == PCI_CAP_ID_MSIX)
-		ret = xen_pci_frontend_enable_msix(dev, &v, nvec);
+		ret = xen_pci_frontend_enable_msix(dev, v, nvec);
 	else
-		ret = xen_pci_frontend_enable_msi(dev, &v);
+		ret = xen_pci_frontend_enable_msi(dev, v);
 	if (ret)
 		goto error;
 	i = 0;
 	list_for_each_entry(msidesc, &dev->msi_list, list) {
-		irq = xen_allocate_pirq(v[i], 0, /* not sharable */
-			(type == PCI_CAP_ID_MSIX) ?
-			"pcifront-msi-x" : "pcifront-msi");
-		if (irq < 0) {
-			ret = -1;
+		irq = xen_bind_pirq_msi_to_irq(dev, msidesc, v[i], 0,
+					       (type == PCI_CAP_ID_MSIX) ?
+					       "pcifront-msi-x" :
+					       "pcifront-msi");
+		if (irq < 0)
 			goto free;
-		}
-
-		ret = set_irq_msi(irq, msidesc);
-		if (ret)
-			goto error_while;
 		i++;
 	}
 	kfree(v);
 	return 0;
 
-error_while:
-	unbind_from_irqhandler(irq, NULL);
 error:
-	if (ret == -ENODEV)
-		dev_err(&dev->dev, "Xen PCI frontend has not registered" \
-			" MSI/MSI-X support!\n");
+	dev_err(&dev->dev, "Xen PCI frontend has not registered MSI/MSI-X support!\n");
 free:
 	kfree(v);
 	return ret;
@@ -193,6 +172,9 @@ static void xen_teardown_msi_irqs(struct pci_dev *dev)
 		xen_pci_frontend_disable_msix(dev);
 	else
 		xen_pci_frontend_disable_msi(dev);
+
+	/* Free the IRQ's and the msidesc using the generic code. */
+	default_teardown_msi_irqs(dev);
 }
 
 static void xen_teardown_msi_irq(unsigned int irq)
@@ -200,47 +182,82 @@ static void xen_teardown_msi_irq(unsigned int irq)
 	xen_destroy_irq(irq);
 }
 
+#ifdef CONFIG_XEN_DOM0
 static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 {
-	int irq, ret;
+	int ret = 0;
 	struct msi_desc *msidesc;
 
 	list_for_each_entry(msidesc, &dev->msi_list, list) {
-		irq = xen_create_msi_irq(dev, msidesc, type);
-		if (irq < 0)
-			return -1;
+		struct physdev_map_pirq map_irq;
 
-		ret = set_irq_msi(irq, msidesc);
-		if (ret)
-			goto error;
-	}
-	return 0;
+		memset(&map_irq, 0, sizeof(map_irq));
+		map_irq.domid = DOMID_SELF;
+		map_irq.type = MAP_PIRQ_TYPE_MSI;
+		map_irq.index = -1;
+		map_irq.pirq = -1;
+		map_irq.bus = dev->bus->number;
+		map_irq.devfn = dev->devfn;
 
-error:
-	xen_destroy_irq(irq);
+		if (type == PCI_CAP_ID_MSIX) {
+			int pos;
+			u32 table_offset, bir;
+
+			pos = pci_find_capability(dev, PCI_CAP_ID_MSIX);
+
+			pci_read_config_dword(dev, pos + PCI_MSIX_TABLE,
+					      &table_offset);
+			bir = (u8)(table_offset & PCI_MSIX_FLAGS_BIRMASK);
+
+			map_irq.table_base = pci_resource_start(dev, bir);
+			map_irq.entry_nr = msidesc->msi_attrib.entry_nr;
+		}
+
+		ret = HYPERVISOR_physdev_op(PHYSDEVOP_map_pirq, &map_irq);
+		if (ret) {
+			dev_warn(&dev->dev, "xen map irq failed %d\n", ret);
+			goto out;
+		}
+
+		ret = xen_bind_pirq_msi_to_irq(dev, msidesc,
+					       map_irq.pirq, map_irq.index,
+					       (type == PCI_CAP_ID_MSIX) ?
+					       "msi-x" : "msi");
+		if (ret < 0)
+			goto out;
+	}
+	ret = 0;
+out:
 	return ret;
 }
 #endif
+#endif
 
 static int xen_pcifront_enable_irq(struct pci_dev *dev)
 {
 	int rc;
 	int share = 1;
+	u8 gsi;
 
-	dev_info(&dev->dev, "Xen PCI enabling IRQ: %d\n", dev->irq);
-
-	if (dev->irq < 0)
-		return -EINVAL;
+	rc = pci_read_config_byte(dev, PCI_INTERRUPT_LINE, &gsi);
+	if (rc < 0) {
+		dev_warn(&dev->dev, "Xen PCI: failed to read interrupt line: %d\n",
+			 rc);
+		return rc;
+	}
 
-	if (dev->irq < NR_IRQS_LEGACY)
+	if (gsi < NR_IRQS_LEGACY)
 		share = 0;
 
-	rc = xen_allocate_pirq(dev->irq, share, "pcifront");
+	rc = xen_allocate_pirq(gsi, share, "pcifront");
 	if (rc < 0) {
-		dev_warn(&dev->dev, "Xen PCI IRQ: %d, failed to register:%d\n",
-			 dev->irq, rc);
+		dev_warn(&dev->dev, "Xen PCI: failed to register GSI%d: %d\n",
+			 gsi, rc);
 		return rc;
 	}
+
+	dev->irq = rc;
+	dev_info(&dev->dev, "Xen PCI mapped GSI%d to IRQ%d\n", gsi, dev->irq);
 	return 0;
 }
 
diff --git a/arch/x86/platform/ce4100/ce4100.c b/arch/x86/platform/ce4100/ce4100.c
index cd6f184c3b3f..28071bb31db7 100644
--- a/arch/x86/platform/ce4100/ce4100.c
+++ b/arch/x86/platform/ce4100/ce4100.c
@@ -16,21 +16,19 @@
 #include <linux/serial_8250.h>
 
 #include <asm/ce4100.h>
+#include <asm/prom.h>
 #include <asm/setup.h>
+#include <asm/i8259.h>
 #include <asm/io.h>
+#include <asm/io_apic.h>
 
 static int ce4100_i8042_detect(void)
 {
 	return 0;
 }
 
-static void __init sdv_find_smp_config(void)
-{
-}
-
 #ifdef CONFIG_SERIAL_8250
 
-
 static unsigned int mem_serial_in(struct uart_port *p, int offset)
 {
 	offset = offset << p->regshift;
@@ -119,6 +117,15 @@ static void __init sdv_arch_setup(void)
 	sdv_serial_fixup();
 }
 
+#ifdef CONFIG_X86_IO_APIC
+static void __cpuinit sdv_pci_init(void)
+{
+	x86_of_pci_init();
+	/* We can't set this earlier, because we need to calibrate the timer */
+	legacy_pic = &null_legacy_pic;
+}
+#endif
+
 /*
  * CE4100 specific x86_init function overrides and early setup
  * calls.
@@ -129,6 +136,11 @@ void __init x86_ce4100_early_setup(void)
 	x86_platform.i8042_detect = ce4100_i8042_detect;
 	x86_init.resources.probe_roms = x86_init_noop;
 	x86_init.mpparse.get_smp_config = x86_init_uint_noop;
-	x86_init.mpparse.find_smp_config = sdv_find_smp_config;
+	x86_init.mpparse.find_smp_config = x86_init_noop;
 	x86_init.pci.init = ce4100_pci_init;
+
+#ifdef CONFIG_X86_IO_APIC
+	x86_init.pci.init_irq = sdv_pci_init;
+	x86_init.mpparse.setup_ioapic_ids = setup_ioapic_ids_from_mpc_nocheck;
+#endif
 }
diff --git a/arch/x86/platform/ce4100/falconfalls.dts b/arch/x86/platform/ce4100/falconfalls.dts
new file mode 100644
index 000000000000..dc701ea58546
--- /dev/null
+++ b/arch/x86/platform/ce4100/falconfalls.dts
@@ -0,0 +1,428 @@
+/*
+ * CE4100 on Falcon Falls
+ *
+ * (c) Copyright 2010 Intel Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; version 2 of the License.
+ */
+/dts-v1/;
+/ {
+	model = "intel,falconfalls";
+	compatible = "intel,falconfalls";
+	#address-cells = <1>;
+	#size-cells = <1>;
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu@0 {
+			device_type = "cpu";
+			compatible = "intel,ce4100";
+			reg = <0>;
+			lapic = <&lapic0>;
+		};
+	};
+
+	soc@0 {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		compatible = "intel,ce4100-cp";
+		ranges;
+
+		ioapic1: interrupt-controller@fec00000 {
+			#interrupt-cells = <2>;
+			compatible = "intel,ce4100-ioapic";
+			interrupt-controller;
+			reg = <0xfec00000 0x1000>;
+		};
+
+		timer@fed00000 {
+			compatible = "intel,ce4100-hpet";
+			reg = <0xfed00000 0x200>;
+		};
+
+		lapic0: interrupt-controller@fee00000 {
+			compatible = "intel,ce4100-lapic";
+			reg = <0xfee00000 0x1000>;
+		};
+
+		pci@3fc {
+			#address-cells = <3>;
+			#size-cells = <2>;
+			compatible = "intel,ce4100-pci", "pci";
+			device_type = "pci";
+			bus-range = <0 0>;
+			ranges = <0x2000000 0 0xbffff000 0xbffff000 0 0x1000
+				  0x2000000 0 0xdffe0000 0xdffe0000 0 0x1000
+				  0x0000000 0 0x0	 0x0	    0 0x100>;
+
+			/* Secondary IO-APIC */
+			ioapic2: interrupt-controller@0,1 {
+				#interrupt-cells = <2>;
+				compatible = "intel,ce4100-ioapic";
+				interrupt-controller;
+				reg = <0x100 0x0 0x0 0x0 0x0>;
+				assigned-addresses = <0x02000000 0x0 0xbffff000 0x0 0x1000>;
+			};
+
+			pci@1,0 {
+				#address-cells = <3>;
+				#size-cells = <2>;
+				compatible = "intel,ce4100-pci", "pci";
+				device_type = "pci";
+				bus-range = <1 1>;
+				ranges = <0x2000000 0 0xdffe0000 0x2000000 0 0xdffe0000 0 0x1000>;
+
+				interrupt-parent = <&ioapic2>;
+
+				display@2,0 {
+					compatible = "pci8086,2e5b.2",
+						   "pci8086,2e5b",
+						   "pciclass038000",
+						   "pciclass0380";
+
+					reg = <0x11000 0x0 0x0 0x0 0x0>;
+					interrupts = <0 1>;
+				};
+
+				multimedia@3,0 {
+					compatible = "pci8086,2e5c.2",
+						   "pci8086,2e5c",
+						   "pciclass048000",
+						   "pciclass0480";
+
+					reg = <0x11800 0x0 0x0 0x0 0x0>;
+					interrupts = <2 1>;
+				};
+
+				multimedia@4,0 {
+					compatible = "pci8086,2e5d.2",
+						   "pci8086,2e5d",
+						   "pciclass048000",
+						   "pciclass0480";
+
+					reg = <0x12000 0x0 0x0 0x0 0x0>;
+					interrupts = <4 1>;
+				};
+
+				multimedia@4,1 {
+					compatible = "pci8086,2e5e.2",
+						   "pci8086,2e5e",
+						   "pciclass048000",
+						   "pciclass0480";
+
+					reg = <0x12100 0x0 0x0 0x0 0x0>;
+					interrupts = <5 1>;
+				};
+
+				sound@6,0 {
+					compatible = "pci8086,2e5f.2",
+						   "pci8086,2e5f",
+						   "pciclass040100",
+						   "pciclass0401";
+
+					reg = <0x13000 0x0 0x0 0x0 0x0>;
+					interrupts = <6 1>;
+				};
+
+				sound@6,1 {
+					compatible = "pci8086,2e5f.2",
+						   "pci8086,2e5f",
+						   "pciclass040100",
+						   "pciclass0401";
+
+					reg = <0x13100 0x0 0x0 0x0 0x0>;
+					interrupts = <7 1>;
+				};
+
+				sound@6,2 {
+					compatible = "pci8086,2e60.2",
+						   "pci8086,2e60",
+						   "pciclass040100",
+						   "pciclass0401";
+
+					reg = <0x13200 0x0 0x0 0x0 0x0>;
+					interrupts = <8 1>;
+				};
+
+				display@8,0 {
+					compatible = "pci8086,2e61.2",
+						   "pci8086,2e61",
+						   "pciclass038000",
+						   "pciclass0380";
+
+					reg = <0x14000 0x0 0x0 0x0 0x0>;
+					interrupts = <9 1>;
+				};
+
+				display@8,1 {
+					compatible = "pci8086,2e62.2",
+						   "pci8086,2e62",
+						   "pciclass038000",
+						   "pciclass0380";
+
+					reg = <0x14100 0x0 0x0 0x0 0x0>;
+					interrupts = <10 1>;
+				};
+
+				multimedia@8,2 {
+					compatible = "pci8086,2e63.2",
+						   "pci8086,2e63",
+						   "pciclass048000",
+						   "pciclass0480";
+
+					reg = <0x14200 0x0 0x0 0x0 0x0>;
+					interrupts = <11 1>;
+				};
+
+				entertainment-encryption@9,0 {
+					compatible = "pci8086,2e64.2",
+						   "pci8086,2e64",
+						   "pciclass101000",
+						   "pciclass1010";
+
+					reg = <0x14800 0x0 0x0 0x0 0x0>;
+					interrupts = <12 1>;
+				};
+
+				localbus@a,0 {
+					compatible = "pci8086,2e65.2",
+						   "pci8086,2e65",
+						   "pciclassff0000",
+						   "pciclassff00";
+
+					reg = <0x15000 0x0 0x0 0x0 0x0>;
+				};
+
+				serial@b,0 {
+					compatible = "pci8086,2e66.2",
+						   "pci8086,2e66",
+						   "pciclass070003",
+						   "pciclass0700";
+
+					reg = <0x15800 0x0 0x0 0x0 0x0>;
+					interrupts = <14 1>;
+				};
+
+				gpio@b,1 {
+					compatible = "pci8086,2e67.2",
+						   "pci8086,2e67",
+						   "pciclassff0000",
+						   "pciclassff00";
+
+					#gpio-cells = <2>;
+					reg = <0x15900 0x0 0x0 0x0 0x0>;
+					interrupts = <15 1>;
+					gpio-controller;
+				};
+
+				i2c-controller@b,2 {
+					#address-cells = <2>;
+					#size-cells = <1>;
+					compatible = "pci8086,2e68.2",
+						   "pci8086,2e68",
+						   "pciclass,ff0000",
+						   "pciclass,ff00";
+
+					reg = <0x15a00 0x0 0x0 0x0 0x0>;
+					interrupts = <16 1>;
+					ranges = <0 0	0x02000000 0 0xdffe0500	0x100
+						  1 0	0x02000000 0 0xdffe0600	0x100
+						  2 0	0x02000000 0 0xdffe0700	0x100>;
+
+					i2c@0 {
+						#address-cells = <1>;
+						#size-cells = <0>;
+						compatible = "intel,ce4100-i2c-controller";
+						reg = <0 0 0x100>;
+					};
+
+					i2c@1 {
+						#address-cells = <1>;
+						#size-cells = <0>;
+						compatible = "intel,ce4100-i2c-controller";
+						reg = <1 0 0x100>;
+
+						gpio@26 {
+							#gpio-cells = <2>;
+							compatible = "ti,pcf8575";
+							reg = <0x26>;
+							gpio-controller;
+						};
+					};
+
+					i2c@2 {
+						#address-cells = <1>;
+						#size-cells = <0>;
+						compatible = "intel,ce4100-i2c-controller";
+						reg = <2 0 0x100>;
+
+						gpio@26 {
+							#gpio-cells = <2>;
+							compatible = "ti,pcf8575";
+							reg = <0x26>;
+							gpio-controller;
+						};
+					};
+				};
+
+				smard-card@b,3 {
+					compatible = "pci8086,2e69.2",
+						   "pci8086,2e69",
+						   "pciclass070500",
+						   "pciclass0705";
+
+					reg = <0x15b00 0x0 0x0 0x0 0x0>;
+					interrupts = <15 1>;
+				};
+
+				spi-controller@b,4 {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					compatible =
+						"pci8086,2e6a.2",
+						"pci8086,2e6a",
+						"pciclass,ff0000",
+						"pciclass,ff00";
+
+					reg = <0x15c00 0x0 0x0 0x0 0x0>;
+					interrupts = <15 1>;
+
+					dac@0 {
+						compatible = "ti,pcm1755";
+						reg = <0>;
+						spi-max-frequency = <115200>;
+					};
+
+					dac@1 {
+						compatible = "ti,pcm1609a";
+						reg = <1>;
+						spi-max-frequency = <115200>;
+					};
+
+					eeprom@2 {
+						compatible = "atmel,at93c46";
+						reg = <2>;
+						spi-max-frequency = <115200>;
+					};
+				};
+
+				multimedia@b,7 {
+					compatible = "pci8086,2e6d.2",
+						   "pci8086,2e6d",
+						   "pciclassff0000",
+						   "pciclassff00";
+
+					reg = <0x15f00 0x0 0x0 0x0 0x0>;
+				};
+
+				ethernet@c,0 {
+					compatible = "pci8086,2e6e.2",
+						   "pci8086,2e6e",
+						   "pciclass020000",
+						   "pciclass0200";
+
+					reg = <0x16000 0x0 0x0 0x0 0x0>;
+					interrupts = <21 1>;
+				};
+
+				clock@c,1 {
+					compatible = "pci8086,2e6f.2",
+						   "pci8086,2e6f",
+						   "pciclassff0000",
+						   "pciclassff00";
+
+					reg = <0x16100 0x0 0x0 0x0 0x0>;
+					interrupts = <3 1>;
+				};
+
+				usb@d,0 {
+					compatible = "pci8086,2e70.2",
+						   "pci8086,2e70",
+						   "pciclass0c0320",
+						   "pciclass0c03";
+
+					reg = <0x16800 0x0 0x0 0x0 0x0>;
+					interrupts = <22 3>;
+				};
+
+				usb@d,1 {
+					compatible = "pci8086,2e70.2",
+						   "pci8086,2e70",
+						   "pciclass0c0320",
+						   "pciclass0c03";
+
+					reg = <0x16900 0x0 0x0 0x0 0x0>;
+					interrupts = <22 3>;
+				};
+
+				sata@e,0 {
+					compatible = "pci8086,2e71.0",
+						   "pci8086,2e71",
+						   "pciclass010601",
+						   "pciclass0106";
+
+					reg = <0x17000 0x0 0x0 0x0 0x0>;
+					interrupts = <23 3>;
+				};
+
+				flash@f,0 {
+					compatible = "pci8086,701.1",
+						   "pci8086,701",
+						   "pciclass050100",
+						   "pciclass0501";
+
+					reg = <0x17800 0x0 0x0 0x0 0x0>;
+					interrupts = <13 1>;
+				};
+
+				entertainment-encryption@10,0 {
+					compatible = "pci8086,702.1",
+						   "pci8086,702",
+						   "pciclass101000",
+						   "pciclass1010";
+
+					reg = <0x18000 0x0 0x0 0x0 0x0>;
+				};
+
+				co-processor@11,0 {
+					compatible = "pci8086,703.1",
+						   "pci8086,703",
+						   "pciclass0b4000",
+						   "pciclass0b40";
+
+					reg = <0x18800 0x0 0x0 0x0 0x0>;
+					interrupts = <1 1>;
+				};
+
+				multimedia@12,0 {
+					compatible = "pci8086,704.0",
+						   "pci8086,704",
+						   "pciclass048000",
+						   "pciclass0480";
+
+					reg = <0x19000 0x0 0x0 0x0 0x0>;
+				};
+			};
+
+			isa@1f,0 {
+				#address-cells = <2>;
+				#size-cells = <1>;
+				compatible = "isa";
+				ranges = <1 0 0 0 0 0x100>;
+
+				rtc@70 {
+					compatible = "intel,ce4100-rtc", "motorola,mc146818";
+					interrupts = <8 3>;
+					interrupt-parent = <&ioapic1>;
+					ctrl-reg = <2>;
+					freq-reg = <0x26>;
+					reg = <1 0x70 2>;
+				};
+			};
+		};
+	};
+};
diff --git a/arch/x86/platform/mrst/mrst.c b/arch/x86/platform/mrst/mrst.c
index ea6529e93c6f..5c0207bf959b 100644
--- a/arch/x86/platform/mrst/mrst.c
+++ b/arch/x86/platform/mrst/mrst.c
@@ -31,6 +31,7 @@
 #include <asm/apic.h>
 #include <asm/io_apic.h>
 #include <asm/mrst.h>
+#include <asm/mrst-vrtc.h>
 #include <asm/io.h>
 #include <asm/i8259.h>
 #include <asm/intel_scu_ipc.h>
@@ -268,6 +269,7 @@ void __init x86_mrst_early_setup(void)
 
 	x86_platform.calibrate_tsc = mrst_calibrate_tsc;
 	x86_platform.i8042_detect = mrst_i8042_detect;
+	x86_init.timers.wallclock_init = mrst_rtc_init;
 	x86_init.pci.init = pci_mrst_init;
 	x86_init.pci.fixup_irqs = x86_init_noop;
 
diff --git a/arch/x86/platform/mrst/vrtc.c b/arch/x86/platform/mrst/vrtc.c
index 32cd7edd71a0..04cf645feb92 100644
--- a/arch/x86/platform/mrst/vrtc.c
+++ b/arch/x86/platform/mrst/vrtc.c
@@ -100,22 +100,14 @@ int vrtc_set_mmss(unsigned long nowtime)
 
 void __init mrst_rtc_init(void)
 {
-	unsigned long rtc_paddr;
-	void __iomem *virt_base;
+	unsigned long vrtc_paddr = sfi_mrtc_array[0].phys_addr;
 
 	sfi_table_parse(SFI_SIG_MRTC, NULL, NULL, sfi_parse_mrtc);
-	if (!sfi_mrtc_num)
+	if (!sfi_mrtc_num || !vrtc_paddr)
 		return;
 
-	rtc_paddr = sfi_mrtc_array[0].phys_addr;
-
-	/* vRTC's register address may not be page aligned */
-	set_fixmap_nocache(FIX_LNW_VRTC, rtc_paddr);
-
-	virt_base = (void __iomem *)__fix_to_virt(FIX_LNW_VRTC);
-	virt_base += rtc_paddr & ~PAGE_MASK;
-	vrtc_virt_base = virt_base;
-
+	vrtc_virt_base = (void __iomem *)set_fixmap_offset_nocache(FIX_LNW_VRTC,
+								vrtc_paddr);
 	x86_platform.get_wallclock = vrtc_get_time;
 	x86_platform.set_wallclock = vrtc_set_mmss;
 }
diff --git a/arch/x86/platform/olpc/Makefile b/arch/x86/platform/olpc/Makefile
index e797428b163b..c2a8cab65e5d 100644
--- a/arch/x86/platform/olpc/Makefile
+++ b/arch/x86/platform/olpc/Makefile
@@ -1,4 +1,4 @@
 obj-$(CONFIG_OLPC)		+= olpc.o
 obj-$(CONFIG_OLPC_XO1)		+= olpc-xo1.o
-obj-$(CONFIG_OLPC_OPENFIRMWARE)	+= olpc_ofw.o
-obj-$(CONFIG_OLPC_OPENFIRMWARE_DT)	+= olpc_dt.o
+obj-$(CONFIG_OLPC)		+= olpc_ofw.o
+obj-$(CONFIG_OF_PROMTREE)	+= olpc_dt.o
diff --git a/arch/x86/platform/uv/uv_irq.c b/arch/x86/platform/uv/uv_irq.c
index 7b24460917d5..374a05d8ad22 100644
--- a/arch/x86/platform/uv/uv_irq.c
+++ b/arch/x86/platform/uv/uv_irq.c
@@ -131,7 +131,7 @@ arch_enable_uv_irq(char *irq_name, unsigned int irq, int cpu, int mmr_blade,
 		       unsigned long mmr_offset, int limit)
 {
 	const struct cpumask *eligible_cpu = cpumask_of(cpu);
-	struct irq_cfg *cfg = get_irq_chip_data(irq);
+	struct irq_cfg *cfg = irq_get_chip_data(irq);
 	unsigned long mmr_value;
 	struct uv_IO_APIC_route_entry *entry;
 	int mmr_pnode, err;
@@ -148,7 +148,7 @@ arch_enable_uv_irq(char *irq_name, unsigned int irq, int cpu, int mmr_blade,
 	else
 		irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
 
-	set_irq_chip_and_handler_name(irq, &uv_irq_chip, handle_percpu_irq,
+	irq_set_chip_and_handler_name(irq, &uv_irq_chip, handle_percpu_irq,
 				      irq_name);
 
 	mmr_value = 0;
diff --git a/arch/x86/platform/visws/visws_quirks.c b/arch/x86/platform/visws/visws_quirks.c
index 632037671746..fe4cf8294878 100644
--- a/arch/x86/platform/visws/visws_quirks.c
+++ b/arch/x86/platform/visws/visws_quirks.c
@@ -569,11 +569,13 @@ out_unlock:
 static struct irqaction master_action = {
 	.handler =	piix4_master_intr,
 	.name =		"PIIX4-8259",
+	.flags =	IRQF_NO_THREAD,
 };
 
 static struct irqaction cascade_action = {
 	.handler = 	no_action,
 	.name =		"cascade",
+	.flags =	IRQF_NO_THREAD,
 };
 
 static inline void set_piix4_virtual_irq_type(void)
@@ -606,7 +608,7 @@ static void __init visws_pre_intr_init(void)
 			chip = &cobalt_irq_type;
 
 		if (chip)
-			set_irq_chip(i, chip);
+			irq_set_chip(i, chip);
 	}
 
 	setup_irq(CO_IRQ_8259, &master_action);
diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig
index 5b54892e4bc3..e4343fe488ed 100644
--- a/arch/x86/xen/Kconfig
+++ b/arch/x86/xen/Kconfig
@@ -48,3 +48,11 @@ config XEN_DEBUG_FS
 	help
 	  Enable statistics output and various tuning options in debugfs.
 	  Enabling this option may incur a significant performance overhead.
+
+config XEN_DEBUG
+	bool "Enable Xen debug checks"
+	depends on XEN
+	default n
+	help
+	  Enable various WARN_ON checks in the Xen MMU code.
+	  Enabling this option WILL incur a significant performance overhead.
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 50542efe45fb..49dbd78ec3cb 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1284,15 +1284,14 @@ static int init_hvm_pv_info(int *major, int *minor)
 
 	xen_setup_features();
 
-	pv_info = xen_info;
-	pv_info.kernel_rpl = 0;
+	pv_info.name = "Xen HVM";
 
 	xen_domain_type = XEN_HVM_DOMAIN;
 
 	return 0;
 }
 
-void xen_hvm_init_shared_info(void)
+void __ref xen_hvm_init_shared_info(void)
 {
 	int cpu;
 	struct xen_add_to_physmap xatp;
@@ -1331,6 +1330,8 @@ static int __cpuinit xen_hvm_cpu_notify(struct notifier_block *self,
 	switch (action) {
 	case CPU_UP_PREPARE:
 		per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu];
+		if (xen_have_vector_callback)
+			xen_init_lock_cpu(cpu);
 		break;
 	default:
 		break;
@@ -1355,6 +1356,7 @@ static void __init xen_hvm_guest_init(void)
 
 	if (xen_feature(XENFEAT_hvm_callback_vector))
 		xen_have_vector_callback = 1;
+	xen_hvm_smp_init();
 	register_cpu_notifier(&xen_hvm_cpu_notifier);
 	xen_unplug_emulated_devices();
 	have_vcpu_info_placement = 0;
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index f6089421147a..3f6f3347aa17 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -46,6 +46,7 @@
 #include <linux/module.h>
 #include <linux/gfp.h>
 #include <linux/memblock.h>
+#include <linux/seq_file.h>
 
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
@@ -416,8 +417,12 @@ static pteval_t pte_pfn_to_mfn(pteval_t val)
 	if (val & _PAGE_PRESENT) {
 		unsigned long pfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT;
 		pteval_t flags = val & PTE_FLAGS_MASK;
-		unsigned long mfn = pfn_to_mfn(pfn);
+		unsigned long mfn;
 
+		if (!xen_feature(XENFEAT_auto_translated_physmap))
+			mfn = get_phys_to_machine(pfn);
+		else
+			mfn = pfn;
 		/*
 		 * If there's no mfn for the pfn, then just create an
 		 * empty non-present pte.  Unfortunately this loses
@@ -427,8 +432,18 @@ static pteval_t pte_pfn_to_mfn(pteval_t val)
 		if (unlikely(mfn == INVALID_P2M_ENTRY)) {
 			mfn = 0;
 			flags = 0;
+		} else {
+			/*
+			 * Paramount to do this test _after_ the
+			 * INVALID_P2M_ENTRY as INVALID_P2M_ENTRY &
+			 * IDENTITY_FRAME_BIT resolves to true.
+			 */
+			mfn &= ~FOREIGN_FRAME_BIT;
+			if (mfn & IDENTITY_FRAME_BIT) {
+				mfn &= ~IDENTITY_FRAME_BIT;
+				flags |= _PAGE_IOMAP;
+			}
 		}
-
 		val = ((pteval_t)mfn << PAGE_SHIFT) | flags;
 	}
 
@@ -532,6 +547,41 @@ pte_t xen_make_pte(pteval_t pte)
 }
 PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte);
 
+#ifdef CONFIG_XEN_DEBUG
+pte_t xen_make_pte_debug(pteval_t pte)
+{
+	phys_addr_t addr = (pte & PTE_PFN_MASK);
+	phys_addr_t other_addr;
+	bool io_page = false;
+	pte_t _pte;
+
+	if (pte & _PAGE_IOMAP)
+		io_page = true;
+
+	_pte = xen_make_pte(pte);
+
+	if (!addr)
+		return _pte;
+
+	if (io_page &&
+	    (xen_initial_domain() || addr >= ISA_END_ADDRESS)) {
+		other_addr = pfn_to_mfn(addr >> PAGE_SHIFT) << PAGE_SHIFT;
+		WARN(addr != other_addr,
+			"0x%lx is using VM_IO, but it is 0x%lx!\n",
+			(unsigned long)addr, (unsigned long)other_addr);
+	} else {
+		pteval_t iomap_set = (_pte.pte & PTE_FLAGS_MASK) & _PAGE_IOMAP;
+		other_addr = (_pte.pte & PTE_PFN_MASK);
+		WARN((addr == other_addr) && (!io_page) && (!iomap_set),
+			"0x%lx is missing VM_IO (and wasn't fixed)!\n",
+			(unsigned long)addr);
+	}
+
+	return _pte;
+}
+PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte_debug);
+#endif
+
 pgd_t xen_make_pgd(pgdval_t pgd)
 {
 	pgd = pte_pfn_to_mfn(pgd);
@@ -1441,7 +1491,7 @@ static __init pte_t mask_rw_pte(pte_t *ptep, pte_t pte)
 	 * early_ioremap fixmap slot, make sure it is RO.
 	 */
 	if (!is_early_ioremap_ptep(ptep) &&
-	    pfn >= e820_table_start && pfn < e820_table_end)
+	    pfn >= pgt_buf_start && pfn < pgt_buf_end)
 		pte = pte_wrprotect(pte);
 
 	return pte;
@@ -1940,6 +1990,9 @@ __init void xen_ident_map_ISA(void)
 
 static __init void xen_post_allocator_init(void)
 {
+#ifdef CONFIG_XEN_DEBUG
+	pv_mmu_ops.make_pte = PV_CALLEE_SAVE(xen_make_pte_debug);
+#endif
 	pv_mmu_ops.set_pte = xen_set_pte;
 	pv_mmu_ops.set_pmd = xen_set_pmd;
 	pv_mmu_ops.set_pud = xen_set_pud;
@@ -2072,7 +2125,7 @@ static void xen_zap_pfn_range(unsigned long vaddr, unsigned int order,
 			in_frames[i] = virt_to_mfn(vaddr);
 
 		MULTI_update_va_mapping(mcs.mc, vaddr, VOID_PTE, 0);
-		set_phys_to_machine(virt_to_pfn(vaddr), INVALID_P2M_ENTRY);
+		__set_phys_to_machine(virt_to_pfn(vaddr), INVALID_P2M_ENTRY);
 
 		if (out_frames)
 			out_frames[i] = virt_to_pfn(vaddr);
@@ -2351,6 +2404,18 @@ EXPORT_SYMBOL_GPL(xen_remap_domain_mfn_range);
 
 #ifdef CONFIG_XEN_DEBUG_FS
 
+static int p2m_dump_open(struct inode *inode, struct file *filp)
+{
+	return single_open(filp, p2m_dump_show, NULL);
+}
+
+static const struct file_operations p2m_dump_fops = {
+	.open		= p2m_dump_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
 static struct dentry *d_mmu_debug;
 
 static int __init xen_mmu_debugfs(void)
@@ -2406,6 +2471,7 @@ static int __init xen_mmu_debugfs(void)
 	debugfs_create_u32("prot_commit_batched", 0444, d_mmu_debug,
 			   &mmu_stats.prot_commit_batched);
 
+	debugfs_create_file("p2m", 0600, d_mmu_debug, NULL, &p2m_dump_fops);
 	return 0;
 }
 fs_initcall(xen_mmu_debugfs);
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index fd12d7ce7ff9..215a3ce61068 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -23,6 +23,129 @@
  * P2M_PER_PAGE depends on the architecture, as a mfn is always
  * unsigned long (8 bytes on 64-bit, 4 bytes on 32), leading to
  * 512 and 1024 entries respectively. 
+ *
+ * In short, these structures contain the Machine Frame Number (MFN) of the PFN.
+ *
+ * However not all entries are filled with MFNs. Specifically for all other
+ * leaf entries, or for the top  root, or middle one, for which there is a void
+ * entry, we assume it is  "missing". So (for example)
+ *  pfn_to_mfn(0x90909090)=INVALID_P2M_ENTRY.
+ *
+ * We also have the possibility of setting 1-1 mappings on certain regions, so
+ * that:
+ *  pfn_to_mfn(0xc0000)=0xc0000
+ *
+ * The benefit of this is, that we can assume for non-RAM regions (think
+ * PCI BARs, or ACPI spaces), we can create mappings easily b/c we
+ * get the PFN value to match the MFN.
+ *
+ * For this to work efficiently we have one new page p2m_identity and
+ * allocate (via reserved_brk) any other pages we need to cover the sides
+ * (1GB or 4MB boundary violations). All entries in p2m_identity are set to
+ * INVALID_P2M_ENTRY type (Xen toolstack only recognizes that and MFNs,
+ * no other fancy value).
+ *
+ * On lookup we spot that the entry points to p2m_identity and return the
+ * identity value instead of dereferencing and returning INVALID_P2M_ENTRY.
+ * If the entry points to an allocated page, we just proceed as before and
+ * return the PFN.  If the PFN has IDENTITY_FRAME_BIT set we unmask that in
+ * appropriate functions (pfn_to_mfn).
+ *
+ * The reason for having the IDENTITY_FRAME_BIT instead of just returning the
+ * PFN is that we could find ourselves where pfn_to_mfn(pfn)==pfn for a
+ * non-identity pfn. To protect ourselves against we elect to set (and get) the
+ * IDENTITY_FRAME_BIT on all identity mapped PFNs.
+ *
+ * This simplistic diagram is used to explain the more subtle piece of code.
+ * There is also a digram of the P2M at the end that can help.
+ * Imagine your E820 looking as so:
+ *
+ *                    1GB                                           2GB
+ * /-------------------+---------\/----\         /----------\    /---+-----\
+ * | System RAM        | Sys RAM ||ACPI|         | reserved |    | Sys RAM |
+ * \-------------------+---------/\----/         \----------/    \---+-----/
+ *                               ^- 1029MB                       ^- 2001MB
+ *
+ * [1029MB = 263424 (0x40500), 2001MB = 512256 (0x7D100),
+ *  2048MB = 524288 (0x80000)]
+ *
+ * And dom0_mem=max:3GB,1GB is passed in to the guest, meaning memory past 1GB
+ * is actually not present (would have to kick the balloon driver to put it in).
+ *
+ * When we are told to set the PFNs for identity mapping (see patch: "xen/setup:
+ * Set identity mapping for non-RAM E820 and E820 gaps.") we pass in the start
+ * of the PFN and the end PFN (263424 and 512256 respectively). The first step
+ * is to reserve_brk a top leaf page if the p2m[1] is missing. The top leaf page
+ * covers 512^2 of page estate (1GB) and in case the start or end PFN is not
+ * aligned on 512^2*PAGE_SIZE (1GB) we loop on aligned 1GB PFNs from start pfn
+ * to end pfn.  We reserve_brk top leaf pages if they are missing (means they
+ * point to p2m_mid_missing).
+ *
+ * With the E820 example above, 263424 is not 1GB aligned so we allocate a
+ * reserve_brk page which will cover the PFNs estate from 0x40000 to 0x80000.
+ * Each entry in the allocate page is "missing" (points to p2m_missing).
+ *
+ * Next stage is to determine if we need to do a more granular boundary check
+ * on the 4MB (or 2MB depending on architecture) off the start and end pfn's.
+ * We check if the start pfn and end pfn violate that boundary check, and if
+ * so reserve_brk a middle (p2m[x][y]) leaf page. This way we have a much finer
+ * granularity of setting which PFNs are missing and which ones are identity.
+ * In our example 263424 and 512256 both fail the check so we reserve_brk two
+ * pages. Populate them with INVALID_P2M_ENTRY (so they both have "missing"
+ * values) and assign them to p2m[1][2] and p2m[1][488] respectively.
+ *
+ * At this point we would at minimum reserve_brk one page, but could be up to
+ * three. Each call to set_phys_range_identity has at maximum a three page
+ * cost. If we were to query the P2M at this stage, all those entries from
+ * start PFN through end PFN (so 1029MB -> 2001MB) would return
+ * INVALID_P2M_ENTRY ("missing").
+ *
+ * The next step is to walk from the start pfn to the end pfn setting
+ * the IDENTITY_FRAME_BIT on each PFN. This is done in set_phys_range_identity.
+ * If we find that the middle leaf is pointing to p2m_missing we can swap it
+ * over to p2m_identity - this way covering 4MB (or 2MB) PFN space.  At this
+ * point we do not need to worry about boundary aligment (so no need to
+ * reserve_brk a middle page, figure out which PFNs are "missing" and which
+ * ones are identity), as that has been done earlier.  If we find that the
+ * middle leaf is not occupied by p2m_identity or p2m_missing, we dereference
+ * that page (which covers 512 PFNs) and set the appropriate PFN with
+ * IDENTITY_FRAME_BIT. In our example 263424 and 512256 end up there, and we
+ * set from p2m[1][2][256->511] and p2m[1][488][0->256] with
+ * IDENTITY_FRAME_BIT set.
+ *
+ * All other regions that are void (or not filled) either point to p2m_missing
+ * (considered missing) or have the default value of INVALID_P2M_ENTRY (also
+ * considered missing). In our case, p2m[1][2][0->255] and p2m[1][488][257->511]
+ * contain the INVALID_P2M_ENTRY value and are considered "missing."
+ *
+ * This is what the p2m ends up looking (for the E820 above) with this
+ * fabulous drawing:
+ *
+ *    p2m         /--------------\
+ *  /-----\       | &mfn_list[0],|                           /-----------------\
+ *  |  0  |------>| &mfn_list[1],|    /---------------\      | ~0, ~0, ..      |
+ *  |-----|       |  ..., ~0, ~0 |    | ~0, ~0, [x]---+----->| IDENTITY [@256] |
+ *  |  1  |---\   \--------------/    | [p2m_identity]+\     | IDENTITY [@257] |
+ *  |-----|    \                      | [p2m_identity]+\\    | ....            |
+ *  |  2  |--\  \-------------------->|  ...          | \\   \----------------/
+ *  |-----|   \                       \---------------/  \\
+ *  |  3  |\   \                                          \\  p2m_identity
+ *  |-----| \   \-------------------->/---------------\   /-----------------\
+ *  | ..  +->+                        | [p2m_identity]+-->| ~0, ~0, ~0, ... |
+ *  \-----/ /                         | [p2m_identity]+-->| ..., ~0         |
+ *         / /---------------\        | ....          |   \-----------------/
+ *        /  | IDENTITY[@0]  |      /-+-[x], ~0, ~0.. |
+ *       /   | IDENTITY[@256]|<----/  \---------------/
+ *      /    | ~0, ~0, ....  |
+ *     |     \---------------/
+ *     |
+ *     p2m_missing             p2m_missing
+ * /------------------\     /------------\
+ * | [p2m_mid_missing]+---->| ~0, ~0, ~0 |
+ * | [p2m_mid_missing]+---->| ..., ~0    |
+ * \------------------/     \------------/
+ *
+ * where ~0 is INVALID_P2M_ENTRY. IDENTITY is (PFN | IDENTITY_BIT)
  */
 
 #include <linux/init.h>
@@ -30,6 +153,7 @@
 #include <linux/list.h>
 #include <linux/hash.h>
 #include <linux/sched.h>
+#include <linux/seq_file.h>
 
 #include <asm/cache.h>
 #include <asm/setup.h>
@@ -59,9 +183,15 @@ static RESERVE_BRK_ARRAY(unsigned long **, p2m_top, P2M_TOP_PER_PAGE);
 static RESERVE_BRK_ARRAY(unsigned long, p2m_top_mfn, P2M_TOP_PER_PAGE);
 static RESERVE_BRK_ARRAY(unsigned long *, p2m_top_mfn_p, P2M_TOP_PER_PAGE);
 
+static RESERVE_BRK_ARRAY(unsigned long, p2m_identity, P2M_PER_PAGE);
+
 RESERVE_BRK(p2m_mid, PAGE_SIZE * (MAX_DOMAIN_PAGES / (P2M_PER_PAGE * P2M_MID_PER_PAGE)));
 RESERVE_BRK(p2m_mid_mfn, PAGE_SIZE * (MAX_DOMAIN_PAGES / (P2M_PER_PAGE * P2M_MID_PER_PAGE)));
 
+/* We might hit two boundary violations at the start and end, at max each
+ * boundary violation will require three middle nodes. */
+RESERVE_BRK(p2m_mid_identity, PAGE_SIZE * 2 * 3);
+
 static inline unsigned p2m_top_index(unsigned long pfn)
 {
 	BUG_ON(pfn >= MAX_P2M_PFN);
@@ -136,7 +266,7 @@ static void p2m_init(unsigned long *p2m)
  * - After resume we're called from within stop_machine, but the mfn
  *   tree should alreay be completely allocated.
  */
-void xen_build_mfn_list_list(void)
+void __ref xen_build_mfn_list_list(void)
 {
 	unsigned long pfn;
 
@@ -221,6 +351,9 @@ void __init xen_build_dynamic_phys_to_machine(void)
 	p2m_top = extend_brk(PAGE_SIZE, PAGE_SIZE);
 	p2m_top_init(p2m_top);
 
+	p2m_identity = extend_brk(PAGE_SIZE, PAGE_SIZE);
+	p2m_init(p2m_identity);
+
 	/*
 	 * The domain builder gives us a pre-constructed p2m array in
 	 * mfn_list for all the pages initially given to us, so we just
@@ -266,6 +399,14 @@ unsigned long get_phys_to_machine(unsigned long pfn)
 	mididx = p2m_mid_index(pfn);
 	idx = p2m_index(pfn);
 
+	/*
+	 * The INVALID_P2M_ENTRY is filled in both p2m_*identity
+	 * and in p2m_*missing, so returning the INVALID_P2M_ENTRY
+	 * would be wrong.
+	 */
+	if (p2m_top[topidx][mididx] == p2m_identity)
+		return IDENTITY_FRAME(pfn);
+
 	return p2m_top[topidx][mididx][idx];
 }
 EXPORT_SYMBOL_GPL(get_phys_to_machine);
@@ -335,9 +476,11 @@ static bool alloc_p2m(unsigned long pfn)
 			p2m_top_mfn_p[topidx] = mid_mfn;
 	}
 
-	if (p2m_top[topidx][mididx] == p2m_missing) {
+	if (p2m_top[topidx][mididx] == p2m_identity ||
+	    p2m_top[topidx][mididx] == p2m_missing) {
 		/* p2m leaf page is missing */
 		unsigned long *p2m;
+		unsigned long *p2m_orig = p2m_top[topidx][mididx];
 
 		p2m = alloc_p2m_page();
 		if (!p2m)
@@ -345,7 +488,7 @@ static bool alloc_p2m(unsigned long pfn)
 
 		p2m_init(p2m);
 
-		if (cmpxchg(&mid[mididx], p2m_missing, p2m) != p2m_missing)
+		if (cmpxchg(&mid[mididx], p2m_orig, p2m) != p2m_orig)
 			free_p2m_page(p2m);
 		else
 			mid_mfn[mididx] = virt_to_mfn(p2m);
@@ -354,11 +497,91 @@ static bool alloc_p2m(unsigned long pfn)
 	return true;
 }
 
+bool __early_alloc_p2m(unsigned long pfn)
+{
+	unsigned topidx, mididx, idx;
+
+	topidx = p2m_top_index(pfn);
+	mididx = p2m_mid_index(pfn);
+	idx = p2m_index(pfn);
+
+	/* Pfff.. No boundary cross-over, lets get out. */
+	if (!idx)
+		return false;
+
+	WARN(p2m_top[topidx][mididx] == p2m_identity,
+		"P2M[%d][%d] == IDENTITY, should be MISSING (or alloced)!\n",
+		topidx, mididx);
+
+	/*
+	 * Could be done by xen_build_dynamic_phys_to_machine..
+	 */
+	if (p2m_top[topidx][mididx] != p2m_missing)
+		return false;
+
+	/* Boundary cross-over for the edges: */
+	if (idx) {
+		unsigned long *p2m = extend_brk(PAGE_SIZE, PAGE_SIZE);
+
+		p2m_init(p2m);
+
+		p2m_top[topidx][mididx] = p2m;
+
+	}
+	return idx != 0;
+}
+unsigned long set_phys_range_identity(unsigned long pfn_s,
+				      unsigned long pfn_e)
+{
+	unsigned long pfn;
+
+	if (unlikely(pfn_s >= MAX_P2M_PFN || pfn_e >= MAX_P2M_PFN))
+		return 0;
+
+	if (unlikely(xen_feature(XENFEAT_auto_translated_physmap)))
+		return pfn_e - pfn_s;
+
+	if (pfn_s > pfn_e)
+		return 0;
+
+	for (pfn = (pfn_s & ~(P2M_MID_PER_PAGE * P2M_PER_PAGE - 1));
+		pfn < ALIGN(pfn_e, (P2M_MID_PER_PAGE * P2M_PER_PAGE));
+		pfn += P2M_MID_PER_PAGE * P2M_PER_PAGE)
+	{
+		unsigned topidx = p2m_top_index(pfn);
+		if (p2m_top[topidx] == p2m_mid_missing) {
+			unsigned long **mid = extend_brk(PAGE_SIZE, PAGE_SIZE);
+
+			p2m_mid_init(mid);
+
+			p2m_top[topidx] = mid;
+		}
+	}
+
+	__early_alloc_p2m(pfn_s);
+	__early_alloc_p2m(pfn_e);
+
+	for (pfn = pfn_s; pfn < pfn_e; pfn++)
+		if (!__set_phys_to_machine(pfn, IDENTITY_FRAME(pfn)))
+			break;
+
+	if (!WARN((pfn - pfn_s) != (pfn_e - pfn_s),
+		"Identity mapping failed. We are %ld short of 1-1 mappings!\n",
+		(pfn_e - pfn_s) - (pfn - pfn_s)))
+		printk(KERN_DEBUG "1-1 mapping on %lx->%lx\n", pfn_s, pfn);
+
+	return pfn - pfn_s;
+}
+
 /* Try to install p2m mapping; fail if intermediate bits missing */
 bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn)
 {
 	unsigned topidx, mididx, idx;
 
+	if (unlikely(xen_feature(XENFEAT_auto_translated_physmap))) {
+		BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY);
+		return true;
+	}
 	if (unlikely(pfn >= MAX_P2M_PFN)) {
 		BUG_ON(mfn != INVALID_P2M_ENTRY);
 		return true;
@@ -368,6 +591,21 @@ bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn)
 	mididx = p2m_mid_index(pfn);
 	idx = p2m_index(pfn);
 
+	/* For sparse holes were the p2m leaf has real PFN along with
+	 * PCI holes, stick in the PFN as the MFN value.
+	 */
+	if (mfn != INVALID_P2M_ENTRY && (mfn & IDENTITY_FRAME_BIT)) {
+		if (p2m_top[topidx][mididx] == p2m_identity)
+			return true;
+
+		/* Swap over from MISSING to IDENTITY if needed. */
+		if (p2m_top[topidx][mididx] == p2m_missing) {
+			WARN_ON(cmpxchg(&p2m_top[topidx][mididx], p2m_missing,
+				p2m_identity) != p2m_missing);
+			return true;
+		}
+	}
+
 	if (p2m_top[topidx][mididx] == p2m_missing)
 		return mfn == INVALID_P2M_ENTRY;
 
@@ -378,11 +616,6 @@ bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn)
 
 bool set_phys_to_machine(unsigned long pfn, unsigned long mfn)
 {
-	if (unlikely(xen_feature(XENFEAT_auto_translated_physmap))) {
-		BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY);
-		return true;
-	}
-
 	if (unlikely(!__set_phys_to_machine(pfn, mfn)))  {
 		if (!alloc_p2m(pfn))
 			return false;
@@ -421,7 +654,7 @@ int m2p_add_override(unsigned long mfn, struct page *page)
 {
 	unsigned long flags;
 	unsigned long pfn;
-	unsigned long address;
+	unsigned long uninitialized_var(address);
 	unsigned level;
 	pte_t *ptep = NULL;
 
@@ -455,7 +688,7 @@ int m2p_remove_override(struct page *page)
 	unsigned long flags;
 	unsigned long mfn;
 	unsigned long pfn;
-	unsigned long address;
+	unsigned long uninitialized_var(address);
 	unsigned level;
 	pte_t *ptep = NULL;
 
@@ -520,3 +753,80 @@ unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn)
 	return ret;
 }
 EXPORT_SYMBOL_GPL(m2p_find_override_pfn);
+
+#ifdef CONFIG_XEN_DEBUG_FS
+
+int p2m_dump_show(struct seq_file *m, void *v)
+{
+	static const char * const level_name[] = { "top", "middle",
+						"entry", "abnormal" };
+	static const char * const type_name[] = { "identity", "missing",
+						"pfn", "abnormal"};
+#define TYPE_IDENTITY 0
+#define TYPE_MISSING 1
+#define TYPE_PFN 2
+#define TYPE_UNKNOWN 3
+	unsigned long pfn, prev_pfn_type = 0, prev_pfn_level = 0;
+	unsigned int uninitialized_var(prev_level);
+	unsigned int uninitialized_var(prev_type);
+
+	if (!p2m_top)
+		return 0;
+
+	for (pfn = 0; pfn < MAX_DOMAIN_PAGES; pfn++) {
+		unsigned topidx = p2m_top_index(pfn);
+		unsigned mididx = p2m_mid_index(pfn);
+		unsigned idx = p2m_index(pfn);
+		unsigned lvl, type;
+
+		lvl = 4;
+		type = TYPE_UNKNOWN;
+		if (p2m_top[topidx] == p2m_mid_missing) {
+			lvl = 0; type = TYPE_MISSING;
+		} else if (p2m_top[topidx] == NULL) {
+			lvl = 0; type = TYPE_UNKNOWN;
+		} else if (p2m_top[topidx][mididx] == NULL) {
+			lvl = 1; type = TYPE_UNKNOWN;
+		} else if (p2m_top[topidx][mididx] == p2m_identity) {
+			lvl = 1; type = TYPE_IDENTITY;
+		} else if (p2m_top[topidx][mididx] == p2m_missing) {
+			lvl = 1; type = TYPE_MISSING;
+		} else if (p2m_top[topidx][mididx][idx] == 0) {
+			lvl = 2; type = TYPE_UNKNOWN;
+		} else if (p2m_top[topidx][mididx][idx] == IDENTITY_FRAME(pfn)) {
+			lvl = 2; type = TYPE_IDENTITY;
+		} else if (p2m_top[topidx][mididx][idx] == INVALID_P2M_ENTRY) {
+			lvl = 2; type = TYPE_MISSING;
+		} else if (p2m_top[topidx][mididx][idx] == pfn) {
+			lvl = 2; type = TYPE_PFN;
+		} else if (p2m_top[topidx][mididx][idx] != pfn) {
+			lvl = 2; type = TYPE_PFN;
+		}
+		if (pfn == 0) {
+			prev_level = lvl;
+			prev_type = type;
+		}
+		if (pfn == MAX_DOMAIN_PAGES-1) {
+			lvl = 3;
+			type = TYPE_UNKNOWN;
+		}
+		if (prev_type != type) {
+			seq_printf(m, " [0x%lx->0x%lx] %s\n",
+				prev_pfn_type, pfn, type_name[prev_type]);
+			prev_pfn_type = pfn;
+			prev_type = type;
+		}
+		if (prev_level != lvl) {
+			seq_printf(m, " [0x%lx->0x%lx] level %s\n",
+				prev_pfn_level, pfn, level_name[prev_level]);
+			prev_pfn_level = pfn;
+			prev_level = lvl;
+		}
+	}
+	return 0;
+#undef TYPE_IDENTITY
+#undef TYPE_MISSING
+#undef TYPE_PFN
+#undef TYPE_UNKNOWN
+}
+#endif
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index a8a66a50d446..fa0269a99377 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -52,6 +52,8 @@ phys_addr_t xen_extra_mem_start, xen_extra_mem_size;
 
 static __init void xen_add_extra_mem(unsigned long pages)
 {
+	unsigned long pfn;
+
 	u64 size = (u64)pages * PAGE_SIZE;
 	u64 extra_start = xen_extra_mem_start + xen_extra_mem_size;
 
@@ -66,6 +68,9 @@ static __init void xen_add_extra_mem(unsigned long pages)
 	xen_extra_mem_size += size;
 
 	xen_max_p2m_pfn = PFN_DOWN(extra_start + size);
+
+	for (pfn = PFN_DOWN(extra_start); pfn <= xen_max_p2m_pfn; pfn++)
+		__set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
 }
 
 static unsigned long __init xen_release_chunk(phys_addr_t start_addr,
@@ -104,7 +109,7 @@ static unsigned long __init xen_release_chunk(phys_addr_t start_addr,
 		WARN(ret != 1, "Failed to release memory %lx-%lx err=%d\n",
 		     start, end, ret);
 		if (ret == 1) {
-			set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
+			__set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
 			len++;
 		}
 	}
@@ -138,12 +143,55 @@ static unsigned long __init xen_return_unused_memory(unsigned long max_pfn,
 	return released;
 }
 
+static unsigned long __init xen_set_identity(const struct e820entry *list,
+					     ssize_t map_size)
+{
+	phys_addr_t last = xen_initial_domain() ? 0 : ISA_END_ADDRESS;
+	phys_addr_t start_pci = last;
+	const struct e820entry *entry;
+	unsigned long identity = 0;
+	int i;
+
+	for (i = 0, entry = list; i < map_size; i++, entry++) {
+		phys_addr_t start = entry->addr;
+		phys_addr_t end = start + entry->size;
+
+		if (start < last)
+			start = last;
+
+		if (end <= start)
+			continue;
+
+		/* Skip over the 1MB region. */
+		if (last > end)
+			continue;
+
+		if (entry->type == E820_RAM) {
+			if (start > start_pci)
+				identity += set_phys_range_identity(
+						PFN_UP(start_pci), PFN_DOWN(start));
+
+			/* Without saving 'last' we would gooble RAM too
+			 * at the end of the loop. */
+			last = end;
+			start_pci = end;
+			continue;
+		}
+		start_pci = min(start, start_pci);
+		last = end;
+	}
+	if (last > start_pci)
+		identity += set_phys_range_identity(
+					PFN_UP(start_pci), PFN_DOWN(last));
+	return identity;
+}
 /**
  * machine_specific_memory_setup - Hook for machine specific memory setup.
  **/
 char * __init xen_memory_setup(void)
 {
 	static struct e820entry map[E820MAX] __initdata;
+	static struct e820entry map_raw[E820MAX] __initdata;
 
 	unsigned long max_pfn = xen_start_info->nr_pages;
 	unsigned long long mem_end;
@@ -151,6 +199,7 @@ char * __init xen_memory_setup(void)
 	struct xen_memory_map memmap;
 	unsigned long extra_pages = 0;
 	unsigned long extra_limit;
+	unsigned long identity_pages = 0;
 	int i;
 	int op;
 
@@ -176,6 +225,7 @@ char * __init xen_memory_setup(void)
 	}
 	BUG_ON(rc);
 
+	memcpy(map_raw, map, sizeof(map));
 	e820.nr_map = 0;
 	xen_extra_mem_start = mem_end;
 	for (i = 0; i < memmap.nr_entries; i++) {
@@ -194,6 +244,15 @@ char * __init xen_memory_setup(void)
 			end -= delta;
 
 			extra_pages += PFN_DOWN(delta);
+			/*
+			 * Set RAM below 4GB that is not for us to be unusable.
+			 * This prevents "System RAM" address space from being
+			 * used as potential resource for I/O address (happens
+			 * when 'allocate_resource' is called).
+			 */
+			if (delta &&
+				(xen_initial_domain() && end < 0x100000000ULL))
+				e820_add_region(end, delta, E820_UNUSABLE);
 		}
 
 		if (map[i].size > 0 && end > xen_extra_mem_start)
@@ -251,6 +310,13 @@ char * __init xen_memory_setup(void)
 
 	xen_add_extra_mem(extra_pages);
 
+	/*
+	 * Set P2M for all non-RAM pages and E820 gaps to be identity
+	 * type PFNs. We supply it with the non-sanitized version
+	 * of the E820.
+	 */
+	identity_pages = xen_set_identity(map_raw, memmap.nr_entries);
+	printk(KERN_INFO "Set %ld page(s) to 1-1 mapping.\n", identity_pages);
 	return "Xen";
 }
 
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 72a4c7959045..30612441ed99 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -509,3 +509,41 @@ void __init xen_smp_init(void)
 	xen_fill_possible_map();
 	xen_init_spinlocks();
 }
+
+static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus)
+{
+	native_smp_prepare_cpus(max_cpus);
+	WARN_ON(xen_smp_intr_init(0));
+
+	if (!xen_have_vector_callback)
+		return;
+	xen_init_lock_cpu(0);
+	xen_init_spinlocks();
+}
+
+static int __cpuinit xen_hvm_cpu_up(unsigned int cpu)
+{
+	int rc;
+	rc = native_cpu_up(cpu);
+	WARN_ON (xen_smp_intr_init(cpu));
+	return rc;
+}
+
+static void xen_hvm_cpu_die(unsigned int cpu)
+{
+	unbind_from_irqhandler(per_cpu(xen_resched_irq, cpu), NULL);
+	unbind_from_irqhandler(per_cpu(xen_callfunc_irq, cpu), NULL);
+	unbind_from_irqhandler(per_cpu(xen_debug_irq, cpu), NULL);
+	unbind_from_irqhandler(per_cpu(xen_callfuncsingle_irq, cpu), NULL);
+	native_cpu_die(cpu);
+}
+
+void __init xen_hvm_smp_init(void)
+{
+	smp_ops.smp_prepare_cpus = xen_hvm_smp_prepare_cpus;
+	smp_ops.smp_send_reschedule = xen_smp_send_reschedule;
+	smp_ops.cpu_up = xen_hvm_cpu_up;
+	smp_ops.cpu_die = xen_hvm_cpu_die;
+	smp_ops.send_call_func_ipi = xen_smp_send_call_function_ipi;
+	smp_ops.send_call_func_single_ipi = xen_smp_send_call_function_single_ipi;
+}
diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c
index 9bbd63a129b5..45329c8c226e 100644
--- a/arch/x86/xen/suspend.c
+++ b/arch/x86/xen/suspend.c
@@ -12,7 +12,7 @@
 #include "xen-ops.h"
 #include "mmu.h"
 
-void xen_pre_suspend(void)
+void xen_arch_pre_suspend(void)
 {
 	xen_start_info->store_mfn = mfn_to_pfn(xen_start_info->store_mfn);
 	xen_start_info->console.domU.mfn =
@@ -26,8 +26,9 @@ void xen_pre_suspend(void)
 		BUG();
 }
 
-void xen_hvm_post_suspend(int suspend_cancelled)
+void xen_arch_hvm_post_suspend(int suspend_cancelled)
 {
+#ifdef CONFIG_XEN_PVHVM
 	int cpu;
 	xen_hvm_init_shared_info();
 	xen_callback_vector();
@@ -37,9 +38,10 @@ void xen_hvm_post_suspend(int suspend_cancelled)
 			xen_setup_runstate_info(cpu);
 		}
 	}
+#endif
 }
 
-void xen_post_suspend(int suspend_cancelled)
+void xen_arch_post_suspend(int suspend_cancelled)
 {
 	xen_build_mfn_list_list();
 
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 067759e3d6a5..2e2d370a47b1 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -397,7 +397,9 @@ void xen_setup_timer(int cpu)
 		name = "<timer kasprintf failed>";
 
 	irq = bind_virq_to_irqhandler(VIRQ_TIMER, cpu, xen_timer_interrupt,
-				      IRQF_DISABLED|IRQF_PERCPU|IRQF_NOBALANCING|IRQF_TIMER,
+				      IRQF_DISABLED|IRQF_PERCPU|
+				      IRQF_NOBALANCING|IRQF_TIMER|
+				      IRQF_FORCE_RESUME,
 				      name, NULL);
 
 	evt = &per_cpu(xen_clock_events, cpu);
diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index 1a5ff24e29c0..aaa7291c9259 100644
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -28,9 +28,9 @@ ENTRY(startup_xen)
 	__FINIT
 
 .pushsection .text
-	.align PAGE_SIZE_asm
+	.align PAGE_SIZE
 ENTRY(hypercall_page)
-	.skip PAGE_SIZE_asm
+	.skip PAGE_SIZE
 .popsection
 
 	ELFNOTE(Xen, XEN_ELFNOTE_GUEST_OS,       .asciz "linux")
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 9d41bf985757..3112f55638c4 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -64,10 +64,12 @@ void xen_setup_vcpu_info_placement(void);
 
 #ifdef CONFIG_SMP
 void xen_smp_init(void);
+void __init xen_hvm_smp_init(void);
 
 extern cpumask_var_t xen_cpu_initialized_map;
 #else
 static inline void xen_smp_init(void) {}
+static inline void xen_hvm_smp_init(void) {}
 #endif
 
 #ifdef CONFIG_PARAVIRT_SPINLOCKS
diff --git a/arch/xtensa/include/asm/rwsem.h b/arch/xtensa/include/asm/rwsem.h
index e39edf5c86f2..249619e7e7f2 100644
--- a/arch/xtensa/include/asm/rwsem.h
+++ b/arch/xtensa/include/asm/rwsem.h
@@ -17,44 +17,12 @@
 #error "Please don't include <asm/rwsem.h> directly, use <linux/rwsem.h> instead."
 #endif
 
-#include <linux/list.h>
-#include <linux/spinlock.h>
-#include <asm/atomic.h>
-#include <asm/system.h>
-
-/*
- * the semaphore definition
- */
-struct rw_semaphore {
-	signed long		count;
 #define RWSEM_UNLOCKED_VALUE		0x00000000
 #define RWSEM_ACTIVE_BIAS		0x00000001
 #define RWSEM_ACTIVE_MASK		0x0000ffff
 #define RWSEM_WAITING_BIAS		(-0x00010000)
 #define RWSEM_ACTIVE_READ_BIAS		RWSEM_ACTIVE_BIAS
 #define RWSEM_ACTIVE_WRITE_BIAS		(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
-	spinlock_t		wait_lock;
-	struct list_head	wait_list;
-};
-
-#define __RWSEM_INITIALIZER(name) \
-	{ RWSEM_UNLOCKED_VALUE, SPIN_LOCK_UNLOCKED, \
-	  LIST_HEAD_INIT((name).wait_list) }
-
-#define DECLARE_RWSEM(name)		\
-	struct rw_semaphore name = __RWSEM_INITIALIZER(name)
-
-extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
-
-static inline void init_rwsem(struct rw_semaphore *sem)
-{
-	sem->count = RWSEM_UNLOCKED_VALUE;
-	spin_lock_init(&sem->wait_lock);
-	INIT_LIST_HEAD(&sem->wait_list);
-}
 
 /*
  * lock for reading
@@ -160,9 +128,4 @@ static inline int rwsem_atomic_update(int delta, struct rw_semaphore *sem)
 	return atomic_add_return(delta, (atomic_t *)(&sem->count));
 }
 
-static inline int rwsem_is_locked(struct rw_semaphore *sem)
-{
-	return (sem->count != 0);
-}
-
 #endif	/* _XTENSA_RWSEM_H */
diff --git a/arch/xtensa/kernel/time.c b/arch/xtensa/kernel/time.c
index 19df764f6399..f3e5eb43f71c 100644
--- a/arch/xtensa/kernel/time.c
+++ b/arch/xtensa/kernel/time.c
@@ -96,16 +96,12 @@ again:
 		update_process_times(user_mode(get_irq_regs()));
 #endif
 
-		write_seqlock(&xtime_lock);
-
-		do_timer(1); /* Linux handler in kernel/timer.c */
+		xtime_update(1); /* Linux handler in kernel/time/timekeeping */
 
 		/* Note that writing CCOMPARE clears the interrupt. */
 
 		next += CCOUNT_PER_JIFFY;
 		set_linux_timer(next);
-
-		write_sequnlock(&xtime_lock);
 	}
 
 	/* Allow platform to do something useful (Wdog). */
diff --git a/drivers/acpi/numa.c b/drivers/acpi/numa.c
index 5eb25eb3ea48..3b5c3189fd99 100644
--- a/drivers/acpi/numa.c
+++ b/drivers/acpi/numa.c
@@ -274,7 +274,7 @@ acpi_table_parse_srat(enum acpi_srat_type id,
 
 int __init acpi_numa_init(void)
 {
-	int ret = 0;
+	int cnt = 0;
 
 	/*
 	 * Should not limit number with cpu num that is from NR_CPUS or nr_cpus=
@@ -288,7 +288,7 @@ int __init acpi_numa_init(void)
 				     acpi_parse_x2apic_affinity, 0);
 		acpi_table_parse_srat(ACPI_SRAT_TYPE_CPU_AFFINITY,
 				     acpi_parse_processor_affinity, 0);
-		ret = acpi_table_parse_srat(ACPI_SRAT_TYPE_MEMORY_AFFINITY,
+		cnt = acpi_table_parse_srat(ACPI_SRAT_TYPE_MEMORY_AFFINITY,
 					    acpi_parse_memory_affinity,
 					    NR_NODE_MEMBLKS);
 	}
@@ -297,7 +297,10 @@ int __init acpi_numa_init(void)
 	acpi_table_parse(ACPI_SIG_SLIT, acpi_parse_slit);
 
 	acpi_numa_arch_fixup();
-	return ret;
+
+	if (cnt <= 0)
+		return cnt ?: -ENOENT;
+	return 0;
 }
 
 int acpi_get_pxm(acpi_handle h)
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index d7aa39e349a6..9cb8668ff5f4 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -120,6 +120,10 @@ static DEFINE_SPINLOCK(minor_lock);
 #define EXTENDED (1<<EXT_SHIFT)
 #define VDEV_IS_EXTENDED(dev) ((dev)&(EXTENDED))
 #define BLKIF_MINOR_EXT(dev) ((dev)&(~EXTENDED))
+#define EMULATED_HD_DISK_MINOR_OFFSET (0)
+#define EMULATED_HD_DISK_NAME_OFFSET (EMULATED_HD_DISK_MINOR_OFFSET / 256)
+#define EMULATED_SD_DISK_MINOR_OFFSET (EMULATED_HD_DISK_MINOR_OFFSET + (4 * 16))
+#define EMULATED_SD_DISK_NAME_OFFSET (EMULATED_HD_DISK_NAME_OFFSET + 4)
 
 #define DEV_NAME	"xvd"	/* name in /dev */
 
@@ -281,7 +285,7 @@ static int blkif_queue_request(struct request *req)
 	info->shadow[id].request = req;
 
 	ring_req->id = id;
-	ring_req->sector_number = (blkif_sector_t)blk_rq_pos(req);
+	ring_req->u.rw.sector_number = (blkif_sector_t)blk_rq_pos(req);
 	ring_req->handle = info->handle;
 
 	ring_req->operation = rq_data_dir(req) ?
@@ -317,7 +321,7 @@ static int blkif_queue_request(struct request *req)
 				rq_data_dir(req) );
 
 		info->shadow[id].frame[i] = mfn_to_pfn(buffer_mfn);
-		ring_req->seg[i] =
+		ring_req->u.rw.seg[i] =
 				(struct blkif_request_segment) {
 					.gref       = ref,
 					.first_sect = fsect,
@@ -434,6 +438,65 @@ static void xlvbd_flush(struct blkfront_info *info)
 	       info->feature_flush ? "enabled" : "disabled");
 }
 
+static int xen_translate_vdev(int vdevice, int *minor, unsigned int *offset)
+{
+	int major;
+	major = BLKIF_MAJOR(vdevice);
+	*minor = BLKIF_MINOR(vdevice);
+	switch (major) {
+		case XEN_IDE0_MAJOR:
+			*offset = (*minor / 64) + EMULATED_HD_DISK_NAME_OFFSET;
+			*minor = ((*minor / 64) * PARTS_PER_DISK) +
+				EMULATED_HD_DISK_MINOR_OFFSET;
+			break;
+		case XEN_IDE1_MAJOR:
+			*offset = (*minor / 64) + 2 + EMULATED_HD_DISK_NAME_OFFSET;
+			*minor = (((*minor / 64) + 2) * PARTS_PER_DISK) +
+				EMULATED_HD_DISK_MINOR_OFFSET;
+			break;
+		case XEN_SCSI_DISK0_MAJOR:
+			*offset = (*minor / PARTS_PER_DISK) + EMULATED_SD_DISK_NAME_OFFSET;
+			*minor = *minor + EMULATED_SD_DISK_MINOR_OFFSET;
+			break;
+		case XEN_SCSI_DISK1_MAJOR:
+		case XEN_SCSI_DISK2_MAJOR:
+		case XEN_SCSI_DISK3_MAJOR:
+		case XEN_SCSI_DISK4_MAJOR:
+		case XEN_SCSI_DISK5_MAJOR:
+		case XEN_SCSI_DISK6_MAJOR:
+		case XEN_SCSI_DISK7_MAJOR:
+			*offset = (*minor / PARTS_PER_DISK) + 
+				((major - XEN_SCSI_DISK1_MAJOR + 1) * 16) +
+				EMULATED_SD_DISK_NAME_OFFSET;
+			*minor = *minor +
+				((major - XEN_SCSI_DISK1_MAJOR + 1) * 16 * PARTS_PER_DISK) +
+				EMULATED_SD_DISK_MINOR_OFFSET;
+			break;
+		case XEN_SCSI_DISK8_MAJOR:
+		case XEN_SCSI_DISK9_MAJOR:
+		case XEN_SCSI_DISK10_MAJOR:
+		case XEN_SCSI_DISK11_MAJOR:
+		case XEN_SCSI_DISK12_MAJOR:
+		case XEN_SCSI_DISK13_MAJOR:
+		case XEN_SCSI_DISK14_MAJOR:
+		case XEN_SCSI_DISK15_MAJOR:
+			*offset = (*minor / PARTS_PER_DISK) + 
+				((major - XEN_SCSI_DISK8_MAJOR + 8) * 16) +
+				EMULATED_SD_DISK_NAME_OFFSET;
+			*minor = *minor +
+				((major - XEN_SCSI_DISK8_MAJOR + 8) * 16 * PARTS_PER_DISK) +
+				EMULATED_SD_DISK_MINOR_OFFSET;
+			break;
+		case XENVBD_MAJOR:
+			*offset = *minor / PARTS_PER_DISK;
+			break;
+		default:
+			printk(KERN_WARNING "blkfront: your disk configuration is "
+					"incorrect, please use an xvd device instead\n");
+			return -ENODEV;
+	}
+	return 0;
+}
 
 static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
 			       struct blkfront_info *info,
@@ -441,7 +504,7 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
 {
 	struct gendisk *gd;
 	int nr_minors = 1;
-	int err = -ENODEV;
+	int err;
 	unsigned int offset;
 	int minor;
 	int nr_parts;
@@ -456,12 +519,20 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
 	}
 
 	if (!VDEV_IS_EXTENDED(info->vdevice)) {
-		minor = BLKIF_MINOR(info->vdevice);
-		nr_parts = PARTS_PER_DISK;
+		err = xen_translate_vdev(info->vdevice, &minor, &offset);
+		if (err)
+			return err;		
+ 		nr_parts = PARTS_PER_DISK;
 	} else {
 		minor = BLKIF_MINOR_EXT(info->vdevice);
 		nr_parts = PARTS_PER_EXT_DISK;
+		offset = minor / nr_parts;
+		if (xen_hvm_domain() && offset <= EMULATED_HD_DISK_NAME_OFFSET + 4)
+			printk(KERN_WARNING "blkfront: vdevice 0x%x might conflict with "
+					"emulated IDE disks,\n\t choose an xvd device name"
+					"from xvde on\n", info->vdevice);
 	}
+	err = -ENODEV;
 
 	if ((minor % nr_parts) == 0)
 		nr_minors = nr_parts;
@@ -475,8 +546,6 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
 	if (gd == NULL)
 		goto release;
 
-	offset = minor / nr_parts;
-
 	if (nr_minors > 1) {
 		if (offset < 26)
 			sprintf(gd->disk_name, "%s%c", DEV_NAME, 'a' + offset);
@@ -615,7 +684,7 @@ static void blkif_completion(struct blk_shadow *s)
 {
 	int i;
 	for (i = 0; i < s->req.nr_segments; i++)
-		gnttab_end_foreign_access(s->req.seg[i].gref, 0, 0UL);
+		gnttab_end_foreign_access(s->req.u.rw.seg[i].gref, 0, 0UL);
 }
 
 static irqreturn_t blkif_interrupt(int irq, void *dev_id)
@@ -932,7 +1001,7 @@ static int blkif_recover(struct blkfront_info *info)
 		/* Rewrite any grant references invalidated by susp/resume. */
 		for (j = 0; j < req->nr_segments; j++)
 			gnttab_grant_foreign_access_ref(
-				req->seg[j].gref,
+				req->u.rw.seg[j].gref,
 				info->xbdev->otherend_id,
 				pfn_to_mfn(info->shadow[req->id].frame[j]),
 				rq_data_dir(info->shadow[req->id].request));
diff --git a/drivers/char/mmtimer.c b/drivers/char/mmtimer.c
index e6d75627c6c8..33dc2298af73 100644
--- a/drivers/char/mmtimer.c
+++ b/drivers/char/mmtimer.c
@@ -53,6 +53,8 @@ MODULE_LICENSE("GPL");
 
 #define RTC_BITS 55 /* 55 bits for this implementation */
 
+static struct k_clock sgi_clock;
+
 extern unsigned long sn_rtc_cycles_per_second;
 
 #define RTC_COUNTER_ADDR        ((long *)LOCAL_MMR_ADDR(SH_RTC))
@@ -487,7 +489,7 @@ static int sgi_clock_get(clockid_t clockid, struct timespec *tp)
 	return 0;
 };
 
-static int sgi_clock_set(clockid_t clockid, struct timespec *tp)
+static int sgi_clock_set(const clockid_t clockid, const struct timespec *tp)
 {
 
 	u64 nsec;
@@ -763,15 +765,21 @@ static int sgi_timer_set(struct k_itimer *timr, int flags,
 	return err;
 }
 
+static int sgi_clock_getres(const clockid_t which_clock, struct timespec *tp)
+{
+	tp->tv_sec = 0;
+	tp->tv_nsec = sgi_clock_period;
+	return 0;
+}
+
 static struct k_clock sgi_clock = {
-	.res = 0,
-	.clock_set = sgi_clock_set,
-	.clock_get = sgi_clock_get,
-	.timer_create = sgi_timer_create,
-	.nsleep = do_posix_clock_nonanosleep,
-	.timer_set = sgi_timer_set,
-	.timer_del = sgi_timer_del,
-	.timer_get = sgi_timer_get
+	.clock_set	= sgi_clock_set,
+	.clock_get	= sgi_clock_get,
+	.clock_getres	= sgi_clock_getres,
+	.timer_create	= sgi_timer_create,
+	.timer_set	= sgi_timer_set,
+	.timer_del	= sgi_timer_del,
+	.timer_get	= sgi_timer_get
 };
 
 /**
@@ -831,8 +839,8 @@ static int __init mmtimer_init(void)
 			(unsigned long) node);
 	}
 
-	sgi_clock_period = sgi_clock.res = NSEC_PER_SEC / sn_rtc_cycles_per_second;
-	register_posix_clock(CLOCK_SGI_CYCLE, &sgi_clock);
+	sgi_clock_period = NSEC_PER_SEC / sn_rtc_cycles_per_second;
+	posix_timers_register_clock(CLOCK_SGI_CYCLE, &sgi_clock);
 
 	printk(KERN_INFO "%s: v%s, %ld MHz\n", MMTIMER_DESC, MMTIMER_VERSION,
 	       sn_rtc_cycles_per_second/(unsigned long)1E6);
diff --git a/drivers/i2c/busses/i2c-ocores.c b/drivers/i2c/busses/i2c-ocores.c
index 61653f079671..1b46a9d9f907 100644
--- a/drivers/i2c/busses/i2c-ocores.c
+++ b/drivers/i2c/busses/i2c-ocores.c
@@ -330,9 +330,7 @@ static int __devinit ocores_i2c_probe(struct platform_device *pdev)
 	i2c->adap = ocores_adapter;
 	i2c_set_adapdata(&i2c->adap, i2c);
 	i2c->adap.dev.parent = &pdev->dev;
-#ifdef CONFIG_OF
 	i2c->adap.dev.of_node = pdev->dev.of_node;
-#endif
 
 	/* add i2c adapter to i2c tree */
 	ret = i2c_add_adapter(&i2c->adap);
@@ -390,15 +388,11 @@ static int ocores_i2c_resume(struct platform_device *pdev)
 #define ocores_i2c_resume	NULL
 #endif
 
-#ifdef CONFIG_OF
 static struct of_device_id ocores_i2c_match[] = {
-        {
-                .compatible = "opencores,i2c-ocores",
-        },
-        {},
+	{ .compatible = "opencores,i2c-ocores", },
+	{},
 };
 MODULE_DEVICE_TABLE(of, ocores_i2c_match);
-#endif
 
 /* work with hotplug and coldplug */
 MODULE_ALIAS("platform:ocores-i2c");
@@ -411,9 +405,7 @@ static struct platform_driver ocores_i2c_driver = {
 	.driver  = {
 		.owner = THIS_MODULE,
 		.name = "ocores-i2c",
-#ifdef CONFIG_OF
-                .of_match_table = ocores_i2c_match,
-#endif
+		.of_match_table = ocores_i2c_match,
 	},
 };
 
diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c
index f0bd5bcdf563..045ba6efea48 100644
--- a/drivers/i2c/i2c-core.c
+++ b/drivers/i2c/i2c-core.c
@@ -537,9 +537,7 @@ i2c_new_device(struct i2c_adapter *adap, struct i2c_board_info const *info)
 	client->dev.parent = &client->adapter->dev;
 	client->dev.bus = &i2c_bus_type;
 	client->dev.type = &i2c_client_type;
-#ifdef CONFIG_OF
 	client->dev.of_node = info->of_node;
-#endif
 
 	dev_set_name(&client->dev, "%d-%04x", i2c_adapter_id(adap),
 		     client->addr);
diff --git a/drivers/mmc/host/mmc_spi.c b/drivers/mmc/host/mmc_spi.c
index fd877f633dd2..2f7fc0c5146f 100644
--- a/drivers/mmc/host/mmc_spi.c
+++ b/drivers/mmc/host/mmc_spi.c
@@ -1516,21 +1516,17 @@ static int __devexit mmc_spi_remove(struct spi_device *spi)
 	return 0;
 }
 
-#if defined(CONFIG_OF)
 static struct of_device_id mmc_spi_of_match_table[] __devinitdata = {
 	{ .compatible = "mmc-spi-slot", },
 	{},
 };
-#endif
 
 static struct spi_driver mmc_spi_driver = {
 	.driver = {
 		.name =		"mmc_spi",
 		.bus =		&spi_bus_type,
 		.owner =	THIS_MODULE,
-#if defined(CONFIG_OF)
 		.of_match_table = mmc_spi_of_match_table,
-#endif
 	},
 	.probe =	mmc_spi_probe,
 	.remove =	__devexit_p(mmc_spi_remove),
diff --git a/drivers/net/ethoc.c b/drivers/net/ethoc.c
index b79d7e1555d5..db0290f05bdf 100644
--- a/drivers/net/ethoc.c
+++ b/drivers/net/ethoc.c
@@ -1163,15 +1163,11 @@ static int ethoc_resume(struct platform_device *pdev)
 # define ethoc_resume  NULL
 #endif
 
-#ifdef CONFIG_OF
 static struct of_device_id ethoc_match[] = {
-	{
-		.compatible = "opencores,ethoc",
-	},
+	{ .compatible = "opencores,ethoc", },
 	{},
 };
 MODULE_DEVICE_TABLE(of, ethoc_match);
-#endif
 
 static struct platform_driver ethoc_driver = {
 	.probe   = ethoc_probe,
@@ -1181,9 +1177,7 @@ static struct platform_driver ethoc_driver = {
 	.driver  = {
 		.name = "ethoc",
 		.owner = THIS_MODULE,
-#ifdef CONFIG_OF
 		.of_match_table = ethoc_match,
-#endif
 	},
 };
 
diff --git a/drivers/of/Kconfig b/drivers/of/Kconfig
index 3c6e100a3ad0..d06a6374ed6c 100644
--- a/drivers/of/Kconfig
+++ b/drivers/of/Kconfig
@@ -69,4 +69,10 @@ config OF_MDIO
 	help
 	  OpenFirmware MDIO bus (Ethernet PHY) accessors
 
+config OF_PCI
+	def_tristate PCI
+	depends on PCI && (PPC || MICROBLAZE || X86)
+	help
+	  OpenFirmware PCI bus accessors
+
 endmenu # OF
diff --git a/drivers/of/Makefile b/drivers/of/Makefile
index 3ab21a0a4907..f7861ed2f287 100644
--- a/drivers/of/Makefile
+++ b/drivers/of/Makefile
@@ -9,3 +9,4 @@ obj-$(CONFIG_OF_I2C)	+= of_i2c.o
 obj-$(CONFIG_OF_NET)	+= of_net.o
 obj-$(CONFIG_OF_SPI)	+= of_spi.o
 obj-$(CONFIG_OF_MDIO)	+= of_mdio.o
+obj-$(CONFIG_OF_PCI)	+= of_pci.o
diff --git a/drivers/of/of_pci.c b/drivers/of/of_pci.c
new file mode 100644
index 000000000000..ac1ec54e4fd5
--- /dev/null
+++ b/drivers/of/of_pci.c
@@ -0,0 +1,92 @@
+#include <linux/kernel.h>
+#include <linux/of_pci.h>
+#include <linux/of_irq.h>
+#include <asm/prom.h>
+
+/**
+ * of_irq_map_pci - Resolve the interrupt for a PCI device
+ * @pdev:       the device whose interrupt is to be resolved
+ * @out_irq:    structure of_irq filled by this function
+ *
+ * This function resolves the PCI interrupt for a given PCI device. If a
+ * device-node exists for a given pci_dev, it will use normal OF tree
+ * walking. If not, it will implement standard swizzling and walk up the
+ * PCI tree until an device-node is found, at which point it will finish
+ * resolving using the OF tree walking.
+ */
+int of_irq_map_pci(struct pci_dev *pdev, struct of_irq *out_irq)
+{
+	struct device_node *dn, *ppnode;
+	struct pci_dev *ppdev;
+	u32 lspec;
+	__be32 lspec_be;
+	__be32 laddr[3];
+	u8 pin;
+	int rc;
+
+	/* Check if we have a device node, if yes, fallback to standard
+	 * device tree parsing
+	 */
+	dn = pci_device_to_OF_node(pdev);
+	if (dn) {
+		rc = of_irq_map_one(dn, 0, out_irq);
+		if (!rc)
+			return rc;
+	}
+
+	/* Ok, we don't, time to have fun. Let's start by building up an
+	 * interrupt spec.  we assume #interrupt-cells is 1, which is standard
+	 * for PCI. If you do different, then don't use that routine.
+	 */
+	rc = pci_read_config_byte(pdev, PCI_INTERRUPT_PIN, &pin);
+	if (rc != 0)
+		return rc;
+	/* No pin, exit */
+	if (pin == 0)
+		return -ENODEV;
+
+	/* Now we walk up the PCI tree */
+	lspec = pin;
+	for (;;) {
+		/* Get the pci_dev of our parent */
+		ppdev = pdev->bus->self;
+
+		/* Ouch, it's a host bridge... */
+		if (ppdev == NULL) {
+			ppnode = pci_bus_to_OF_node(pdev->bus);
+
+			/* No node for host bridge ? give up */
+			if (ppnode == NULL)
+				return -EINVAL;
+		} else {
+			/* We found a P2P bridge, check if it has a node */
+			ppnode = pci_device_to_OF_node(ppdev);
+		}
+
+		/* Ok, we have found a parent with a device-node, hand over to
+		 * the OF parsing code.
+		 * We build a unit address from the linux device to be used for
+		 * resolution. Note that we use the linux bus number which may
+		 * not match your firmware bus numbering.
+		 * Fortunately, in most cases, interrupt-map-mask doesn't
+		 * include the bus number as part of the matching.
+		 * You should still be careful about that though if you intend
+		 * to rely on this function (you ship  a firmware that doesn't
+		 * create device nodes for all PCI devices).
+		 */
+		if (ppnode)
+			break;
+
+		/* We can only get here if we hit a P2P bridge with no node,
+		 * let's do standard swizzling and try again
+		 */
+		lspec = pci_swizzle_interrupt_pin(pdev, lspec);
+		pdev = ppdev;
+	}
+
+	lspec_be = cpu_to_be32(lspec);
+	laddr[0] = cpu_to_be32((pdev->bus->number << 16) | (pdev->devfn << 8));
+	laddr[1]  = laddr[2] = cpu_to_be32(0);
+	return of_irq_map_raw(ppnode, &lspec_be, 1, laddr, out_irq);
+}
+EXPORT_SYMBOL_GPL(of_irq_map_pci);
diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c
index 3a5a6fcc0ead..492b7d807fe8 100644
--- a/drivers/pci/xen-pcifront.c
+++ b/drivers/pci/xen-pcifront.c
@@ -243,7 +243,7 @@ struct pci_ops pcifront_bus_ops = {
 
 #ifdef CONFIG_PCI_MSI
 static int pci_frontend_enable_msix(struct pci_dev *dev,
-				    int **vector, int nvec)
+				    int vector[], int nvec)
 {
 	int err;
 	int i;
@@ -277,18 +277,24 @@ static int pci_frontend_enable_msix(struct pci_dev *dev,
 	if (likely(!err)) {
 		if (likely(!op.value)) {
 			/* we get the result */
-			for (i = 0; i < nvec; i++)
-				*(*vector+i) = op.msix_entries[i].vector;
-			return 0;
+			for (i = 0; i < nvec; i++) {
+				if (op.msix_entries[i].vector <= 0) {
+					dev_warn(&dev->dev, "MSI-X entry %d is invalid: %d!\n",
+						i, op.msix_entries[i].vector);
+					err = -EINVAL;
+					vector[i] = -1;
+					continue;
+				}
+				vector[i] = op.msix_entries[i].vector;
+			}
 		} else {
 			printk(KERN_DEBUG "enable msix get value %x\n",
 				op.value);
-			return op.value;
 		}
 	} else {
 		dev_err(&dev->dev, "enable msix get err %x\n", err);
-		return err;
 	}
+	return err;
 }
 
 static void pci_frontend_disable_msix(struct pci_dev *dev)
@@ -310,7 +316,7 @@ static void pci_frontend_disable_msix(struct pci_dev *dev)
 		dev_err(&dev->dev, "pci_disable_msix get err %x\n", err);
 }
 
-static int pci_frontend_enable_msi(struct pci_dev *dev, int **vector)
+static int pci_frontend_enable_msi(struct pci_dev *dev, int vector[])
 {
 	int err;
 	struct xen_pci_op op = {
@@ -324,7 +330,13 @@ static int pci_frontend_enable_msi(struct pci_dev *dev, int **vector)
 
 	err = do_pci_op(pdev, &op);
 	if (likely(!err)) {
-		*(*vector) = op.value;
+		vector[0] = op.value;
+		if (op.value <= 0) {
+			dev_warn(&dev->dev, "MSI entry is invalid: %d!\n",
+				op.value);
+			err = -EINVAL;
+			vector[0] = -1;
+		}
 	} else {
 		dev_err(&dev->dev, "pci frontend enable msi failed for dev "
 				    "%x:%x\n", op.bus, op.devfn);
@@ -733,8 +745,7 @@ static void free_pdev(struct pcifront_device *pdev)
 
 	pcifront_free_roots(pdev);
 
-	/*For PCIE_AER error handling job*/
-	flush_scheduled_work();
+	cancel_work_sync(&pdev->op_work);
 
 	if (pdev->irq >= 0)
 		unbind_from_irqhandler(pdev->irq, pdev);
diff --git a/drivers/rtc/class.c b/drivers/rtc/class.c
index c404b61386bf..09b4437b3e61 100644
--- a/drivers/rtc/class.c
+++ b/drivers/rtc/class.c
@@ -117,6 +117,7 @@ struct rtc_device *rtc_device_register(const char *name, struct device *dev,
 					struct module *owner)
 {
 	struct rtc_device *rtc;
+	struct rtc_wkalrm alrm;
 	int id, err;
 
 	if (idr_pre_get(&rtc_idr, GFP_KERNEL) == 0) {
@@ -166,6 +167,12 @@ struct rtc_device *rtc_device_register(const char *name, struct device *dev,
 	rtc->pie_timer.function = rtc_pie_update_irq;
 	rtc->pie_enabled = 0;
 
+	/* Check to see if there is an ALARM already set in hw */
+	err = __rtc_read_alarm(rtc, &alrm);
+
+	if (!err && !rtc_valid_tm(&alrm.time))
+		rtc_set_alarm(rtc, &alrm);
+
 	strlcpy(rtc->name, name, RTC_DEVICE_NAME_SIZE);
 	dev_set_name(&rtc->dev, "rtc%d", id);
 
diff --git a/drivers/rtc/interface.c b/drivers/rtc/interface.c
index cb2f0728fd70..8ec6b069a7f5 100644
--- a/drivers/rtc/interface.c
+++ b/drivers/rtc/interface.c
@@ -116,6 +116,186 @@ int rtc_set_mmss(struct rtc_device *rtc, unsigned long secs)
 }
 EXPORT_SYMBOL_GPL(rtc_set_mmss);
 
+static int rtc_read_alarm_internal(struct rtc_device *rtc, struct rtc_wkalrm *alarm)
+{
+	int err;
+
+	err = mutex_lock_interruptible(&rtc->ops_lock);
+	if (err)
+		return err;
+
+	if (rtc->ops == NULL)
+		err = -ENODEV;
+	else if (!rtc->ops->read_alarm)
+		err = -EINVAL;
+	else {
+		memset(alarm, 0, sizeof(struct rtc_wkalrm));
+		err = rtc->ops->read_alarm(rtc->dev.parent, alarm);
+	}
+
+	mutex_unlock(&rtc->ops_lock);
+	return err;
+}
+
+int __rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm)
+{
+	int err;
+	struct rtc_time before, now;
+	int first_time = 1;
+	unsigned long t_now, t_alm;
+	enum { none, day, month, year } missing = none;
+	unsigned days;
+
+	/* The lower level RTC driver may return -1 in some fields,
+	 * creating invalid alarm->time values, for reasons like:
+	 *
+	 *   - The hardware may not be capable of filling them in;
+	 *     many alarms match only on time-of-day fields, not
+	 *     day/month/year calendar data.
+	 *
+	 *   - Some hardware uses illegal values as "wildcard" match
+	 *     values, which non-Linux firmware (like a BIOS) may try
+	 *     to set up as e.g. "alarm 15 minutes after each hour".
+	 *     Linux uses only oneshot alarms.
+	 *
+	 * When we see that here, we deal with it by using values from
+	 * a current RTC timestamp for any missing (-1) values.  The
+	 * RTC driver prevents "periodic alarm" modes.
+	 *
+	 * But this can be racey, because some fields of the RTC timestamp
+	 * may have wrapped in the interval since we read the RTC alarm,
+	 * which would lead to us inserting inconsistent values in place
+	 * of the -1 fields.
+	 *
+	 * Reading the alarm and timestamp in the reverse sequence
+	 * would have the same race condition, and not solve the issue.
+	 *
+	 * So, we must first read the RTC timestamp,
+	 * then read the RTC alarm value,
+	 * and then read a second RTC timestamp.
+	 *
+	 * If any fields of the second timestamp have changed
+	 * when compared with the first timestamp, then we know
+	 * our timestamp may be inconsistent with that used by
+	 * the low-level rtc_read_alarm_internal() function.
+	 *
+	 * So, when the two timestamps disagree, we just loop and do
+	 * the process again to get a fully consistent set of values.
+	 *
+	 * This could all instead be done in the lower level driver,
+	 * but since more than one lower level RTC implementation needs it,
+	 * then it's probably best best to do it here instead of there..
+	 */
+
+	/* Get the "before" timestamp */
+	err = rtc_read_time(rtc, &before);
+	if (err < 0)
+		return err;
+	do {
+		if (!first_time)
+			memcpy(&before, &now, sizeof(struct rtc_time));
+		first_time = 0;
+
+		/* get the RTC alarm values, which may be incomplete */
+		err = rtc_read_alarm_internal(rtc, alarm);
+		if (err)
+			return err;
+
+		/* full-function RTCs won't have such missing fields */
+		if (rtc_valid_tm(&alarm->time) == 0)
+			return 0;
+
+		/* get the "after" timestamp, to detect wrapped fields */
+		err = rtc_read_time(rtc, &now);
+		if (err < 0)
+			return err;
+
+		/* note that tm_sec is a "don't care" value here: */
+	} while (   before.tm_min   != now.tm_min
+		 || before.tm_hour  != now.tm_hour
+		 || before.tm_mon   != now.tm_mon
+		 || before.tm_year  != now.tm_year);
+
+	/* Fill in the missing alarm fields using the timestamp; we
+	 * know there's at least one since alarm->time is invalid.
+	 */
+	if (alarm->time.tm_sec == -1)
+		alarm->time.tm_sec = now.tm_sec;
+	if (alarm->time.tm_min == -1)
+		alarm->time.tm_min = now.tm_min;
+	if (alarm->time.tm_hour == -1)
+		alarm->time.tm_hour = now.tm_hour;
+
+	/* For simplicity, only support date rollover for now */
+	if (alarm->time.tm_mday == -1) {
+		alarm->time.tm_mday = now.tm_mday;
+		missing = day;
+	}
+	if (alarm->time.tm_mon == -1) {
+		alarm->time.tm_mon = now.tm_mon;
+		if (missing == none)
+			missing = month;
+	}
+	if (alarm->time.tm_year == -1) {
+		alarm->time.tm_year = now.tm_year;
+		if (missing == none)
+			missing = year;
+	}
+
+	/* with luck, no rollover is needed */
+	rtc_tm_to_time(&now, &t_now);
+	rtc_tm_to_time(&alarm->time, &t_alm);
+	if (t_now < t_alm)
+		goto done;
+
+	switch (missing) {
+
+	/* 24 hour rollover ... if it's now 10am Monday, an alarm that
+	 * that will trigger at 5am will do so at 5am Tuesday, which
+	 * could also be in the next month or year.  This is a common
+	 * case, especially for PCs.
+	 */
+	case day:
+		dev_dbg(&rtc->dev, "alarm rollover: %s\n", "day");
+		t_alm += 24 * 60 * 60;
+		rtc_time_to_tm(t_alm, &alarm->time);
+		break;
+
+	/* Month rollover ... if it's the 31th, an alarm on the 3rd will
+	 * be next month.  An alarm matching on the 30th, 29th, or 28th
+	 * may end up in the month after that!  Many newer PCs support
+	 * this type of alarm.
+	 */
+	case month:
+		dev_dbg(&rtc->dev, "alarm rollover: %s\n", "month");
+		do {
+			if (alarm->time.tm_mon < 11)
+				alarm->time.tm_mon++;
+			else {
+				alarm->time.tm_mon = 0;
+				alarm->time.tm_year++;
+			}
+			days = rtc_month_days(alarm->time.tm_mon,
+					alarm->time.tm_year);
+		} while (days < alarm->time.tm_mday);
+		break;
+
+	/* Year rollover ... easy except for leap years! */
+	case year:
+		dev_dbg(&rtc->dev, "alarm rollover: %s\n", "year");
+		do {
+			alarm->time.tm_year++;
+		} while (rtc_valid_tm(&alarm->time) != 0);
+		break;
+
+	default:
+		dev_warn(&rtc->dev, "alarm rollover not handled\n");
+	}
+
+done:
+	return 0;
+}
+
 int rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm)
 {
 	int err;
diff --git a/drivers/rtc/rtc-at91rm9200.c b/drivers/rtc/rtc-at91rm9200.c
index 26d1cf5d19ae..518a76ec71ca 100644
--- a/drivers/rtc/rtc-at91rm9200.c
+++ b/drivers/rtc/rtc-at91rm9200.c
@@ -183,33 +183,6 @@ static int at91_rtc_setalarm(struct device *dev, struct rtc_wkalrm *alrm)
 	return 0;
 }
 
-/*
- * Handle commands from user-space
- */
-static int at91_rtc_ioctl(struct device *dev, unsigned int cmd,
-			unsigned long arg)
-{
-	int ret = 0;
-
-	pr_debug("%s(): cmd=%08x, arg=%08lx.\n", __func__, cmd, arg);
-
-	/* important:  scrub old status before enabling IRQs */
-	switch (cmd) {
-	case RTC_UIE_OFF:	/* update off */
-		at91_sys_write(AT91_RTC_IDR, AT91_RTC_SECEV);
-		break;
-	case RTC_UIE_ON:	/* update on */
-		at91_sys_write(AT91_RTC_SCCR, AT91_RTC_SECEV);
-		at91_sys_write(AT91_RTC_IER, AT91_RTC_SECEV);
-		break;
-	default:
-		ret = -ENOIOCTLCMD;
-		break;
-	}
-
-	return ret;
-}
-
 static int at91_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled)
 {
 	pr_debug("%s(): cmd=%08x\n", __func__, enabled);
@@ -269,7 +242,6 @@ static irqreturn_t at91_rtc_interrupt(int irq, void *dev_id)
 }
 
 static const struct rtc_class_ops at91_rtc_ops = {
-	.ioctl		= at91_rtc_ioctl,
 	.read_time	= at91_rtc_readtime,
 	.set_time	= at91_rtc_settime,
 	.read_alarm	= at91_rtc_readalarm,
diff --git a/drivers/rtc/rtc-at91sam9.c b/drivers/rtc/rtc-at91sam9.c
index 5469c52cba3d..a3ad957507dc 100644
--- a/drivers/rtc/rtc-at91sam9.c
+++ b/drivers/rtc/rtc-at91sam9.c
@@ -216,33 +216,6 @@ static int at91_rtc_setalarm(struct device *dev, struct rtc_wkalrm *alrm)
 	return 0;
 }
 
-/*
- * Handle commands from user-space
- */
-static int at91_rtc_ioctl(struct device *dev, unsigned int cmd,
-			unsigned long arg)
-{
-	struct sam9_rtc *rtc = dev_get_drvdata(dev);
-	int ret = 0;
-	u32 mr = rtt_readl(rtc, MR);
-
-	dev_dbg(dev, "ioctl: cmd=%08x, arg=%08lx, mr %08x\n", cmd, arg, mr);
-
-	switch (cmd) {
-	case RTC_UIE_OFF:		/* update off */
-		rtt_writel(rtc, MR, mr & ~AT91_RTT_RTTINCIEN);
-		break;
-	case RTC_UIE_ON:		/* update on */
-		rtt_writel(rtc, MR, mr | AT91_RTT_RTTINCIEN);
-		break;
-	default:
-		ret = -ENOIOCTLCMD;
-		break;
-	}
-
-	return ret;
-}
-
 static int at91_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled)
 {
 	struct sam9_rtc *rtc = dev_get_drvdata(dev);
@@ -303,7 +276,6 @@ static irqreturn_t at91_rtc_interrupt(int irq, void *_rtc)
 }
 
 static const struct rtc_class_ops at91_rtc_ops = {
-	.ioctl		= at91_rtc_ioctl,
 	.read_time	= at91_rtc_readtime,
 	.set_time	= at91_rtc_settime,
 	.read_alarm	= at91_rtc_readalarm,
diff --git a/drivers/rtc/rtc-bfin.c b/drivers/rtc/rtc-bfin.c
index 17971d93354d..ca9cff85ab8a 100644
--- a/drivers/rtc/rtc-bfin.c
+++ b/drivers/rtc/rtc-bfin.c
@@ -240,32 +240,6 @@ static void bfin_rtc_int_set_alarm(struct bfin_rtc *rtc)
 	 */
 	bfin_rtc_int_set(rtc->rtc_alarm.tm_yday == -1 ? RTC_ISTAT_ALARM : RTC_ISTAT_ALARM_DAY);
 }
-static int bfin_rtc_ioctl(struct device *dev, unsigned int cmd, unsigned long arg)
-{
-	struct bfin_rtc *rtc = dev_get_drvdata(dev);
-	int ret = 0;
-
-	dev_dbg_stamp(dev);
-
-	bfin_rtc_sync_pending(dev);
-
-	switch (cmd) {
-	case RTC_UIE_ON:
-		dev_dbg_stamp(dev);
-		bfin_rtc_int_set(RTC_ISTAT_SEC);
-		break;
-	case RTC_UIE_OFF:
-		dev_dbg_stamp(dev);
-		bfin_rtc_int_clear(~RTC_ISTAT_SEC);
-		break;
-
-	default:
-		dev_dbg_stamp(dev);
-		ret = -ENOIOCTLCMD;
-	}
-
-	return ret;
-}
 
 static int bfin_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled)
 {
@@ -358,7 +332,6 @@ static int bfin_rtc_proc(struct device *dev, struct seq_file *seq)
 }
 
 static struct rtc_class_ops bfin_rtc_ops = {
-	.ioctl         = bfin_rtc_ioctl,
 	.read_time     = bfin_rtc_read_time,
 	.set_time      = bfin_rtc_set_time,
 	.read_alarm    = bfin_rtc_read_alarm,
diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c
index c7ff8df347e7..911e75cdc125 100644
--- a/drivers/rtc/rtc-cmos.c
+++ b/drivers/rtc/rtc-cmos.c
@@ -37,6 +37,8 @@
 #include <linux/mod_devicetable.h>
 #include <linux/log2.h>
 #include <linux/pm.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
 
 /* this is for "generic access to PC-style RTC" using CMOS_READ/CMOS_WRITE */
 #include <asm-generic/rtc.h>
@@ -375,50 +377,6 @@ static int cmos_set_alarm(struct device *dev, struct rtc_wkalrm *t)
 	return 0;
 }
 
-static int cmos_irq_set_freq(struct device *dev, int freq)
-{
-	struct cmos_rtc	*cmos = dev_get_drvdata(dev);
-	int		f;
-	unsigned long	flags;
-
-	if (!is_valid_irq(cmos->irq))
-		return -ENXIO;
-
-	if (!is_power_of_2(freq))
-		return -EINVAL;
-	/* 0 = no irqs; 1 = 2^15 Hz ... 15 = 2^0 Hz */
-	f = ffs(freq);
-	if (f-- > 16)
-		return -EINVAL;
-	f = 16 - f;
-
-	spin_lock_irqsave(&rtc_lock, flags);
-	hpet_set_periodic_freq(freq);
-	CMOS_WRITE(RTC_REF_CLCK_32KHZ | f, RTC_FREQ_SELECT);
-	spin_unlock_irqrestore(&rtc_lock, flags);
-
-	return 0;
-}
-
-static int cmos_irq_set_state(struct device *dev, int enabled)
-{
-	struct cmos_rtc	*cmos = dev_get_drvdata(dev);
-	unsigned long	flags;
-
-	if (!is_valid_irq(cmos->irq))
-		return -ENXIO;
-
-	spin_lock_irqsave(&rtc_lock, flags);
-
-	if (enabled)
-		cmos_irq_enable(cmos, RTC_PIE);
-	else
-		cmos_irq_disable(cmos, RTC_PIE);
-
-	spin_unlock_irqrestore(&rtc_lock, flags);
-	return 0;
-}
-
 static int cmos_alarm_irq_enable(struct device *dev, unsigned int enabled)
 {
 	struct cmos_rtc	*cmos = dev_get_drvdata(dev);
@@ -438,25 +396,6 @@ static int cmos_alarm_irq_enable(struct device *dev, unsigned int enabled)
 	return 0;
 }
 
-static int cmos_update_irq_enable(struct device *dev, unsigned int enabled)
-{
-	struct cmos_rtc	*cmos = dev_get_drvdata(dev);
-	unsigned long	flags;
-
-	if (!is_valid_irq(cmos->irq))
-		return -EINVAL;
-
-	spin_lock_irqsave(&rtc_lock, flags);
-
-	if (enabled)
-		cmos_irq_enable(cmos, RTC_UIE);
-	else
-		cmos_irq_disable(cmos, RTC_UIE);
-
-	spin_unlock_irqrestore(&rtc_lock, flags);
-	return 0;
-}
-
 #if defined(CONFIG_RTC_INTF_PROC) || defined(CONFIG_RTC_INTF_PROC_MODULE)
 
 static int cmos_procfs(struct device *dev, struct seq_file *seq)
@@ -501,10 +440,7 @@ static const struct rtc_class_ops cmos_rtc_ops = {
 	.read_alarm		= cmos_read_alarm,
 	.set_alarm		= cmos_set_alarm,
 	.proc			= cmos_procfs,
-	.irq_set_freq		= cmos_irq_set_freq,
-	.irq_set_state		= cmos_irq_set_state,
 	.alarm_irq_enable	= cmos_alarm_irq_enable,
-	.update_irq_enable	= cmos_update_irq_enable,
 };
 
 /*----------------------------------------------------------------*/
@@ -1123,6 +1059,47 @@ static struct pnp_driver cmos_pnp_driver = {
 
 #endif	/* CONFIG_PNP */
 
+#ifdef CONFIG_OF
+static const struct of_device_id of_cmos_match[] = {
+	{
+		.compatible = "motorola,mc146818",
+	},
+	{ },
+};
+MODULE_DEVICE_TABLE(of, of_cmos_match);
+
+static __init void cmos_of_init(struct platform_device *pdev)
+{
+	struct device_node *node = pdev->dev.of_node;
+	struct rtc_time time;
+	int ret;
+	const __be32 *val;
+
+	if (!node)
+		return;
+
+	val = of_get_property(node, "ctrl-reg", NULL);
+	if (val)
+		CMOS_WRITE(be32_to_cpup(val), RTC_CONTROL);
+
+	val = of_get_property(node, "freq-reg", NULL);
+	if (val)
+		CMOS_WRITE(be32_to_cpup(val), RTC_FREQ_SELECT);
+
+	get_rtc_time(&time);
+	ret = rtc_valid_tm(&time);
+	if (ret) {
+		struct rtc_time def_time = {
+			.tm_year = 1,
+			.tm_mday = 1,
+		};
+		set_rtc_time(&def_time);
+	}
+}
+#else
+static inline void cmos_of_init(struct platform_device *pdev) {}
+#define of_cmos_match NULL
+#endif
 /*----------------------------------------------------------------*/
 
 /* Platform setup should have set up an RTC device, when PNP is
@@ -1131,6 +1108,7 @@ static struct pnp_driver cmos_pnp_driver = {
 
 static int __init cmos_platform_probe(struct platform_device *pdev)
 {
+	cmos_of_init(pdev);
 	cmos_wake_setup(&pdev->dev);
 	return cmos_do_probe(&pdev->dev,
 			platform_get_resource(pdev, IORESOURCE_IO, 0),
@@ -1162,6 +1140,7 @@ static struct platform_driver cmos_platform_driver = {
 #ifdef CONFIG_PM
 		.pm		= &cmos_pm_ops,
 #endif
+		.of_match_table = of_cmos_match,
 	}
 };
 
diff --git a/drivers/rtc/rtc-davinci.c b/drivers/rtc/rtc-davinci.c
index 34647fc1ee98..8d46838dff8a 100644
--- a/drivers/rtc/rtc-davinci.c
+++ b/drivers/rtc/rtc-davinci.c
@@ -231,10 +231,6 @@ davinci_rtc_ioctl(struct device *dev, unsigned int cmd, unsigned long arg)
 	case RTC_WIE_OFF:
 		rtc_ctrl &= ~PRTCSS_RTC_CTRL_WEN;
 		break;
-	case RTC_UIE_OFF:
-	case RTC_UIE_ON:
-		ret = -ENOTTY;
-		break;
 	default:
 		ret = -ENOIOCTLCMD;
 	}
@@ -473,55 +469,6 @@ static int davinci_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alm)
 	return 0;
 }
 
-static int davinci_rtc_irq_set_state(struct device *dev, int enabled)
-{
-	struct davinci_rtc *davinci_rtc = dev_get_drvdata(dev);
-	unsigned long flags;
-	u8 rtc_ctrl;
-
-	spin_lock_irqsave(&davinci_rtc_lock, flags);
-
-	rtc_ctrl = rtcss_read(davinci_rtc, PRTCSS_RTC_CTRL);
-
-	if (enabled) {
-		while (rtcss_read(davinci_rtc, PRTCSS_RTC_CTRL)
-		       & PRTCSS_RTC_CTRL_WDTBUS)
-			cpu_relax();
-
-		rtc_ctrl |= PRTCSS_RTC_CTRL_TE;
-		rtcss_write(davinci_rtc, rtc_ctrl, PRTCSS_RTC_CTRL);
-
-		rtcss_write(davinci_rtc, 0x0, PRTCSS_RTC_CLKC_CNT);
-
-		rtc_ctrl |= PRTCSS_RTC_CTRL_TIEN |
-			    PRTCSS_RTC_CTRL_TMMD |
-			    PRTCSS_RTC_CTRL_TMRFLG;
-	} else
-		rtc_ctrl &= ~PRTCSS_RTC_CTRL_TIEN;
-
-	rtcss_write(davinci_rtc, rtc_ctrl, PRTCSS_RTC_CTRL);
-
-	spin_unlock_irqrestore(&davinci_rtc_lock, flags);
-
-	return 0;
-}
-
-static int davinci_rtc_irq_set_freq(struct device *dev, int freq)
-{
-	struct davinci_rtc *davinci_rtc = dev_get_drvdata(dev);
-	unsigned long flags;
-	u16 tmr_counter = (0x8000 >> (ffs(freq) - 1));
-
-	spin_lock_irqsave(&davinci_rtc_lock, flags);
-
-	rtcss_write(davinci_rtc, tmr_counter & 0xFF, PRTCSS_RTC_TMR0);
-	rtcss_write(davinci_rtc, (tmr_counter & 0xFF00) >> 8, PRTCSS_RTC_TMR1);
-
-	spin_unlock_irqrestore(&davinci_rtc_lock, flags);
-
-	return 0;
-}
-
 static struct rtc_class_ops davinci_rtc_ops = {
 	.ioctl			= davinci_rtc_ioctl,
 	.read_time		= davinci_rtc_read_time,
@@ -529,8 +476,6 @@ static struct rtc_class_ops davinci_rtc_ops = {
 	.alarm_irq_enable	= davinci_rtc_alarm_irq_enable,
 	.read_alarm		= davinci_rtc_read_alarm,
 	.set_alarm		= davinci_rtc_set_alarm,
-	.irq_set_state		= davinci_rtc_irq_set_state,
-	.irq_set_freq		= davinci_rtc_irq_set_freq,
 };
 
 static int __init davinci_rtc_probe(struct platform_device *pdev)
diff --git a/drivers/rtc/rtc-ds1511.c b/drivers/rtc/rtc-ds1511.c
index 37268e97de49..3fffd708711f 100644
--- a/drivers/rtc/rtc-ds1511.c
+++ b/drivers/rtc/rtc-ds1511.c
@@ -397,29 +397,12 @@ static int ds1511_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled)
 	return 0;
 }
 
-static int ds1511_rtc_update_irq_enable(struct device *dev,
-	unsigned int enabled)
-{
-	struct platform_device *pdev = to_platform_device(dev);
-	struct rtc_plat_data *pdata = platform_get_drvdata(pdev);
-
-	if (pdata->irq <= 0)
-		return -EINVAL;
-	if (enabled)
-		pdata->irqen |= RTC_UF;
-	else
-		pdata->irqen &= ~RTC_UF;
-	ds1511_rtc_update_alarm(pdata);
-	return 0;
-}
-
 static const struct rtc_class_ops ds1511_rtc_ops = {
 	.read_time		= ds1511_rtc_read_time,
 	.set_time		= ds1511_rtc_set_time,
 	.read_alarm		= ds1511_rtc_read_alarm,
 	.set_alarm		= ds1511_rtc_set_alarm,
 	.alarm_irq_enable	= ds1511_rtc_alarm_irq_enable,
-	.update_irq_enable	= ds1511_rtc_update_irq_enable,
 };
 
  static ssize_t
diff --git a/drivers/rtc/rtc-ds1553.c b/drivers/rtc/rtc-ds1553.c
index ff432e2ca275..fee41b97c9e8 100644
--- a/drivers/rtc/rtc-ds1553.c
+++ b/drivers/rtc/rtc-ds1553.c
@@ -227,29 +227,12 @@ static int ds1553_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled)
 	return 0;
 }
 
-static int ds1553_rtc_update_irq_enable(struct device *dev,
-	unsigned int enabled)
-{
-	struct platform_device *pdev = to_platform_device(dev);
-	struct rtc_plat_data *pdata = platform_get_drvdata(pdev);
-
-	if (pdata->irq <= 0)
-		return -EINVAL;
-	if (enabled)
-		pdata->irqen |= RTC_UF;
-	else
-		pdata->irqen &= ~RTC_UF;
-	ds1553_rtc_update_alarm(pdata);
-	return 0;
-}
-
 static const struct rtc_class_ops ds1553_rtc_ops = {
 	.read_time		= ds1553_rtc_read_time,
 	.set_time		= ds1553_rtc_set_time,
 	.read_alarm		= ds1553_rtc_read_alarm,
 	.set_alarm		= ds1553_rtc_set_alarm,
 	.alarm_irq_enable	= ds1553_rtc_alarm_irq_enable,
-	.update_irq_enable	= ds1553_rtc_update_irq_enable,
 };
 
 static ssize_t ds1553_nvram_read(struct file *filp, struct kobject *kobj,
diff --git a/drivers/rtc/rtc-ds3232.c b/drivers/rtc/rtc-ds3232.c
index 950735415a7c..27b7bf672ac6 100644
--- a/drivers/rtc/rtc-ds3232.c
+++ b/drivers/rtc/rtc-ds3232.c
@@ -339,23 +339,6 @@ static int ds3232_alarm_irq_enable(struct device *dev, unsigned int enabled)
 	return 0;
 }
 
-static int ds3232_update_irq_enable(struct device *dev, unsigned int enabled)
-{
-	struct i2c_client *client = to_i2c_client(dev);
-	struct ds3232 *ds3232 = i2c_get_clientdata(client);
-
-	if (client->irq <= 0)
-		return -EINVAL;
-
-	if (enabled)
-		ds3232->rtc->irq_data |= RTC_UF;
-	else
-		ds3232->rtc->irq_data &= ~RTC_UF;
-
-	ds3232_update_alarm(client);
-	return 0;
-}
-
 static irqreturn_t ds3232_irq(int irq, void *dev_id)
 {
 	struct i2c_client *client = dev_id;
@@ -406,7 +389,6 @@ static const struct rtc_class_ops ds3232_rtc_ops = {
 	.read_alarm = ds3232_read_alarm,
 	.set_alarm = ds3232_set_alarm,
 	.alarm_irq_enable = ds3232_alarm_irq_enable,
-	.update_irq_enable = ds3232_update_irq_enable,
 };
 
 static int __devinit ds3232_probe(struct i2c_client *client,
diff --git a/drivers/rtc/rtc-jz4740.c b/drivers/rtc/rtc-jz4740.c
index 2e16f72c9056..b6473631d182 100644
--- a/drivers/rtc/rtc-jz4740.c
+++ b/drivers/rtc/rtc-jz4740.c
@@ -168,12 +168,6 @@ static int jz4740_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
 	return ret;
 }
 
-static int jz4740_rtc_update_irq_enable(struct device *dev, unsigned int enable)
-{
-	struct jz4740_rtc *rtc = dev_get_drvdata(dev);
-	return jz4740_rtc_ctrl_set_bits(rtc, JZ_RTC_CTRL_1HZ_IRQ, enable);
-}
-
 static int jz4740_rtc_alarm_irq_enable(struct device *dev, unsigned int enable)
 {
 	struct jz4740_rtc *rtc = dev_get_drvdata(dev);
@@ -185,7 +179,6 @@ static struct rtc_class_ops jz4740_rtc_ops = {
 	.set_mmss	= jz4740_rtc_set_mmss,
 	.read_alarm	= jz4740_rtc_read_alarm,
 	.set_alarm	= jz4740_rtc_set_alarm,
-	.update_irq_enable = jz4740_rtc_update_irq_enable,
 	.alarm_irq_enable = jz4740_rtc_alarm_irq_enable,
 };
 
diff --git a/drivers/rtc/rtc-mc13xxx.c b/drivers/rtc/rtc-mc13xxx.c
index 5314b153bfba..c42006469559 100644
--- a/drivers/rtc/rtc-mc13xxx.c
+++ b/drivers/rtc/rtc-mc13xxx.c
@@ -282,12 +282,6 @@ static irqreturn_t mc13xxx_rtc_update_handler(int irq, void *dev)
 	return IRQ_HANDLED;
 }
 
-static int mc13xxx_rtc_update_irq_enable(struct device *dev,
-		unsigned int enabled)
-{
-	return mc13xxx_rtc_irq_enable(dev, enabled, MC13XXX_IRQ_1HZ);
-}
-
 static int mc13xxx_rtc_alarm_irq_enable(struct device *dev,
 		unsigned int enabled)
 {
@@ -300,7 +294,6 @@ static const struct rtc_class_ops mc13xxx_rtc_ops = {
 	.read_alarm = mc13xxx_rtc_read_alarm,
 	.set_alarm = mc13xxx_rtc_set_alarm,
 	.alarm_irq_enable = mc13xxx_rtc_alarm_irq_enable,
-	.update_irq_enable = mc13xxx_rtc_update_irq_enable,
 };
 
 static irqreturn_t mc13xxx_rtc_reset_handler(int irq, void *dev)
diff --git a/drivers/rtc/rtc-mpc5121.c b/drivers/rtc/rtc-mpc5121.c
index dfcdf0901d21..b40c1ff1ebc8 100644
--- a/drivers/rtc/rtc-mpc5121.c
+++ b/drivers/rtc/rtc-mpc5121.c
@@ -240,32 +240,12 @@ static int mpc5121_rtc_alarm_irq_enable(struct device *dev,
 	return 0;
 }
 
-static int mpc5121_rtc_update_irq_enable(struct device *dev,
-					 unsigned int enabled)
-{
-	struct mpc5121_rtc_data *rtc = dev_get_drvdata(dev);
-	struct mpc5121_rtc_regs __iomem *regs = rtc->regs;
-	int val;
-
-	val = in_8(&regs->int_enable);
-
-	if (enabled)
-		val = (val & ~0x8) | 0x1;
-	else
-		val &= ~0x1;
-
-	out_8(&regs->int_enable, val);
-
-	return 0;
-}
-
 static const struct rtc_class_ops mpc5121_rtc_ops = {
 	.read_time = mpc5121_rtc_read_time,
 	.set_time = mpc5121_rtc_set_time,
 	.read_alarm = mpc5121_rtc_read_alarm,
 	.set_alarm = mpc5121_rtc_set_alarm,
 	.alarm_irq_enable = mpc5121_rtc_alarm_irq_enable,
-	.update_irq_enable = mpc5121_rtc_update_irq_enable,
 };
 
 static int __devinit mpc5121_rtc_probe(struct platform_device *op,
diff --git a/drivers/rtc/rtc-mrst.c b/drivers/rtc/rtc-mrst.c
index 1db62db8469d..b86bc328463b 100644
--- a/drivers/rtc/rtc-mrst.c
+++ b/drivers/rtc/rtc-mrst.c
@@ -62,6 +62,17 @@ static inline int is_intr(u8 rtc_intr)
 	return rtc_intr & RTC_IRQMASK;
 }
 
+static inline unsigned char vrtc_is_updating(void)
+{
+	unsigned char uip;
+	unsigned long flags;
+
+	spin_lock_irqsave(&rtc_lock, flags);
+	uip = (vrtc_cmos_read(RTC_FREQ_SELECT) & RTC_UIP);
+	spin_unlock_irqrestore(&rtc_lock, flags);
+	return uip;
+}
+
 /*
  * rtc_time's year contains the increment over 1900, but vRTC's YEAR
  * register can't be programmed to value larger than 0x64, so vRTC
@@ -76,7 +87,7 @@ static int mrst_read_time(struct device *dev, struct rtc_time *time)
 {
 	unsigned long flags;
 
-	if (rtc_is_updating())
+	if (vrtc_is_updating())
 		mdelay(20);
 
 	spin_lock_irqsave(&rtc_lock, flags);
@@ -236,25 +247,6 @@ static int mrst_set_alarm(struct device *dev, struct rtc_wkalrm *t)
 	return 0;
 }
 
-static int mrst_irq_set_state(struct device *dev, int enabled)
-{
-	struct mrst_rtc	*mrst = dev_get_drvdata(dev);
-	unsigned long	flags;
-
-	if (!mrst->irq)
-		return -ENXIO;
-
-	spin_lock_irqsave(&rtc_lock, flags);
-
-	if (enabled)
-		mrst_irq_enable(mrst, RTC_PIE);
-	else
-		mrst_irq_disable(mrst, RTC_PIE);
-
-	spin_unlock_irqrestore(&rtc_lock, flags);
-	return 0;
-}
-
 /* Currently, the vRTC doesn't support UIE ON/OFF */
 static int mrst_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled)
 {
@@ -301,7 +293,6 @@ static const struct rtc_class_ops mrst_rtc_ops = {
 	.read_alarm	= mrst_read_alarm,
 	.set_alarm	= mrst_set_alarm,
 	.proc		= mrst_procfs,
-	.irq_set_state	= mrst_irq_set_state,
 	.alarm_irq_enable = mrst_rtc_alarm_irq_enable,
 };
 
diff --git a/drivers/rtc/rtc-mxc.c b/drivers/rtc/rtc-mxc.c
index 0b06c1e03fd5..826ab64a8fa9 100644
--- a/drivers/rtc/rtc-mxc.c
+++ b/drivers/rtc/rtc-mxc.c
@@ -274,12 +274,6 @@ static int mxc_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled)
 	return 0;
 }
 
-static int mxc_rtc_update_irq_enable(struct device *dev, unsigned int enabled)
-{
-	mxc_rtc_irq_enable(dev, RTC_1HZ_BIT, enabled);
-	return 0;
-}
-
 /*
  * This function reads the current RTC time into tm in Gregorian date.
  */
@@ -368,7 +362,6 @@ static struct rtc_class_ops mxc_rtc_ops = {
 	.read_alarm		= mxc_rtc_read_alarm,
 	.set_alarm		= mxc_rtc_set_alarm,
 	.alarm_irq_enable	= mxc_rtc_alarm_irq_enable,
-	.update_irq_enable	= mxc_rtc_update_irq_enable,
 };
 
 static int __init mxc_rtc_probe(struct platform_device *pdev)
diff --git a/drivers/rtc/rtc-nuc900.c b/drivers/rtc/rtc-nuc900.c
index ddb0857e15a4..781068d62f23 100644
--- a/drivers/rtc/rtc-nuc900.c
+++ b/drivers/rtc/rtc-nuc900.c
@@ -134,20 +134,6 @@ static void nuc900_rtc_bin2bcd(struct device *dev, struct rtc_time *settm,
 	gettm->bcd_hour = bin2bcd(settm->tm_hour) << 16;
 }
 
-static int nuc900_update_irq_enable(struct device *dev, unsigned int enabled)
-{
-	struct nuc900_rtc *rtc = dev_get_drvdata(dev);
-
-	if (enabled)
-		__raw_writel(__raw_readl(rtc->rtc_reg + REG_RTC_RIER)|
-				(TICKINTENB), rtc->rtc_reg + REG_RTC_RIER);
-	else
-		__raw_writel(__raw_readl(rtc->rtc_reg + REG_RTC_RIER)&
-				(~TICKINTENB), rtc->rtc_reg + REG_RTC_RIER);
-
-	return 0;
-}
-
 static int nuc900_alarm_irq_enable(struct device *dev, unsigned int enabled)
 {
 	struct nuc900_rtc *rtc = dev_get_drvdata(dev);
@@ -234,7 +220,6 @@ static struct rtc_class_ops nuc900_rtc_ops = {
 	.read_alarm = nuc900_rtc_read_alarm,
 	.set_alarm = nuc900_rtc_set_alarm,
 	.alarm_irq_enable = nuc900_alarm_irq_enable,
-	.update_irq_enable = nuc900_update_irq_enable,
 };
 
 static int __devinit nuc900_rtc_probe(struct platform_device *pdev)
diff --git a/drivers/rtc/rtc-omap.c b/drivers/rtc/rtc-omap.c
index b4dbf3a319b3..de0dd7b1f146 100644
--- a/drivers/rtc/rtc-omap.c
+++ b/drivers/rtc/rtc-omap.c
@@ -135,44 +135,6 @@ static irqreturn_t rtc_irq(int irq, void *rtc)
 	return IRQ_HANDLED;
 }
 
-#ifdef	CONFIG_RTC_INTF_DEV
-
-static int
-omap_rtc_ioctl(struct device *dev, unsigned int cmd, unsigned long arg)
-{
-	u8 reg;
-
-	switch (cmd) {
-	case RTC_UIE_OFF:
-	case RTC_UIE_ON:
-		break;
-	default:
-		return -ENOIOCTLCMD;
-	}
-
-	local_irq_disable();
-	rtc_wait_not_busy();
-	reg = rtc_read(OMAP_RTC_INTERRUPTS_REG);
-	switch (cmd) {
-	/* UIE = Update Interrupt Enable (1/second) */
-	case RTC_UIE_OFF:
-		reg &= ~OMAP_RTC_INTERRUPTS_IT_TIMER;
-		break;
-	case RTC_UIE_ON:
-		reg |= OMAP_RTC_INTERRUPTS_IT_TIMER;
-		break;
-	}
-	rtc_wait_not_busy();
-	rtc_write(reg, OMAP_RTC_INTERRUPTS_REG);
-	local_irq_enable();
-
-	return 0;
-}
-
-#else
-#define	omap_rtc_ioctl	NULL
-#endif
-
 static int omap_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled)
 {
 	u8 reg;
@@ -313,7 +275,6 @@ static int omap_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alm)
 }
 
 static struct rtc_class_ops omap_rtc_ops = {
-	.ioctl		= omap_rtc_ioctl,
 	.read_time	= omap_rtc_read_time,
 	.set_time	= omap_rtc_set_time,
 	.read_alarm	= omap_rtc_read_alarm,
diff --git a/drivers/rtc/rtc-pcap.c b/drivers/rtc/rtc-pcap.c
index 25c0b3fd44f1..a633abc42896 100644
--- a/drivers/rtc/rtc-pcap.c
+++ b/drivers/rtc/rtc-pcap.c
@@ -131,18 +131,12 @@ static int pcap_rtc_alarm_irq_enable(struct device *dev, unsigned int en)
 	return pcap_rtc_irq_enable(dev, PCAP_IRQ_TODA, en);
 }
 
-static int pcap_rtc_update_irq_enable(struct device *dev, unsigned int en)
-{
-	return pcap_rtc_irq_enable(dev, PCAP_IRQ_1HZ, en);
-}
-
 static const struct rtc_class_ops pcap_rtc_ops = {
 	.read_time = pcap_rtc_read_time,
 	.read_alarm = pcap_rtc_read_alarm,
 	.set_alarm = pcap_rtc_set_alarm,
 	.set_mmss = pcap_rtc_set_mmss,
 	.alarm_irq_enable = pcap_rtc_alarm_irq_enable,
-	.update_irq_enable = pcap_rtc_update_irq_enable,
 };
 
 static int __devinit pcap_rtc_probe(struct platform_device *pdev)
diff --git a/drivers/rtc/rtc-pcf50633.c b/drivers/rtc/rtc-pcf50633.c
index 16edf94ab42f..f90c574f9d05 100644
--- a/drivers/rtc/rtc-pcf50633.c
+++ b/drivers/rtc/rtc-pcf50633.c
@@ -106,25 +106,6 @@ pcf50633_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled)
 	return 0;
 }
 
-static int
-pcf50633_rtc_update_irq_enable(struct device *dev, unsigned int enabled)
-{
-	struct pcf50633_rtc *rtc = dev_get_drvdata(dev);
-	int err;
-
-	if (enabled)
-		err = pcf50633_irq_unmask(rtc->pcf, PCF50633_IRQ_SECOND);
-	else
-		err = pcf50633_irq_mask(rtc->pcf, PCF50633_IRQ_SECOND);
-
-	if (err < 0)
-		return err;
-
-	rtc->second_enabled = enabled;
-
-	return 0;
-}
-
 static int pcf50633_rtc_read_time(struct device *dev, struct rtc_time *tm)
 {
 	struct pcf50633_rtc *rtc;
@@ -262,8 +243,7 @@ static struct rtc_class_ops pcf50633_rtc_ops = {
 	.set_time		= pcf50633_rtc_set_time,
 	.read_alarm		= pcf50633_rtc_read_alarm,
 	.set_alarm		= pcf50633_rtc_set_alarm,
-	.alarm_irq_enable 	= pcf50633_rtc_alarm_irq_enable,
-	.update_irq_enable 	= pcf50633_rtc_update_irq_enable,
+	.alarm_irq_enable	= pcf50633_rtc_alarm_irq_enable,
 };
 
 static void pcf50633_rtc_irq(int irq, void *data)
diff --git a/drivers/rtc/rtc-pl030.c b/drivers/rtc/rtc-pl030.c
index bbdb2f02798a..d554368c9f57 100644
--- a/drivers/rtc/rtc-pl030.c
+++ b/drivers/rtc/rtc-pl030.c
@@ -35,11 +35,6 @@ static irqreturn_t pl030_interrupt(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static int pl030_ioctl(struct device *dev, unsigned int cmd, unsigned long arg)
-{
-	return -ENOIOCTLCMD;
-}
-
 static int pl030_read_alarm(struct device *dev, struct rtc_wkalrm *alrm)
 {
 	struct pl030_rtc *rtc = dev_get_drvdata(dev);
@@ -96,7 +91,6 @@ static int pl030_set_time(struct device *dev, struct rtc_time *tm)
 }
 
 static const struct rtc_class_ops pl030_ops = {
-	.ioctl		= pl030_ioctl,
 	.read_time	= pl030_read_time,
 	.set_time	= pl030_set_time,
 	.read_alarm	= pl030_read_alarm,
diff --git a/drivers/rtc/rtc-pl031.c b/drivers/rtc/rtc-pl031.c
index b7a6690e5b35..d829ea63c4fb 100644
--- a/drivers/rtc/rtc-pl031.c
+++ b/drivers/rtc/rtc-pl031.c
@@ -293,57 +293,6 @@ static int pl031_set_alarm(struct device *dev, struct rtc_wkalrm *alarm)
 	return ret;
 }
 
-/* Periodic interrupt is only available in ST variants. */
-static int pl031_irq_set_state(struct device *dev, int enabled)
-{
-	struct pl031_local *ldata = dev_get_drvdata(dev);
-
-	if (enabled == 1) {
-		/* Clear any pending timer interrupt. */
-		writel(RTC_BIT_PI, ldata->base + RTC_ICR);
-
-		writel(readl(ldata->base + RTC_IMSC) | RTC_BIT_PI,
-			ldata->base + RTC_IMSC);
-
-		/* Now start the timer */
-		writel(readl(ldata->base + RTC_TCR) | RTC_TCR_EN,
-			ldata->base + RTC_TCR);
-
-	} else {
-		writel(readl(ldata->base + RTC_IMSC) & (~RTC_BIT_PI),
-			ldata->base + RTC_IMSC);
-
-		/* Also stop the timer */
-		writel(readl(ldata->base + RTC_TCR) & (~RTC_TCR_EN),
-			ldata->base + RTC_TCR);
-	}
-	/* Wait at least 1 RTC32 clock cycle to ensure next access
-	 * to RTC_TCR will succeed.
-	 */
-	udelay(40);
-
-	return 0;
-}
-
-static int pl031_irq_set_freq(struct device *dev, int freq)
-{
-	struct pl031_local *ldata = dev_get_drvdata(dev);
-
-	/* Cant set timer if it is already enabled */
-	if (readl(ldata->base + RTC_TCR) & RTC_TCR_EN) {
-		dev_err(dev, "can't change frequency while timer enabled\n");
-		return -EINVAL;
-	}
-
-	/* If self start bit in RTC_TCR is set timer will start here,
-	 * but we never set that bit. Instead we start the timer when
-	 * set_state is called with enabled == 1.
-	 */
-	writel(RTC_TIMER_FREQ / freq, ldata->base + RTC_TLR);
-
-	return 0;
-}
-
 static int pl031_remove(struct amba_device *adev)
 {
 	struct pl031_local *ldata = dev_get_drvdata(&adev->dev);
@@ -440,8 +389,6 @@ static struct rtc_class_ops stv1_pl031_ops = {
 	.read_alarm = pl031_read_alarm,
 	.set_alarm = pl031_set_alarm,
 	.alarm_irq_enable = pl031_alarm_irq_enable,
-	.irq_set_state = pl031_irq_set_state,
-	.irq_set_freq = pl031_irq_set_freq,
 };
 
 /* And the second ST derivative */
@@ -451,8 +398,6 @@ static struct rtc_class_ops stv2_pl031_ops = {
 	.read_alarm = pl031_stv2_read_alarm,
 	.set_alarm = pl031_stv2_set_alarm,
 	.alarm_irq_enable = pl031_alarm_irq_enable,
-	.irq_set_state = pl031_irq_set_state,
-	.irq_set_freq = pl031_irq_set_freq,
 };
 
 static struct amba_id pl031_ids[] = {
diff --git a/drivers/rtc/rtc-proc.c b/drivers/rtc/rtc-proc.c
index 242bbf86c74a..0a59fda5c09d 100644
--- a/drivers/rtc/rtc-proc.c
+++ b/drivers/rtc/rtc-proc.c
@@ -69,6 +69,14 @@ static int rtc_proc_show(struct seq_file *seq, void *offset)
 				alrm.enabled ? "yes" : "no");
 		seq_printf(seq, "alrm_pending\t: %s\n",
 				alrm.pending ? "yes" : "no");
+		seq_printf(seq, "update IRQ enabled\t: %s\n",
+			(rtc->uie_rtctimer.enabled) ? "yes" : "no");
+		seq_printf(seq, "periodic IRQ enabled\t: %s\n",
+			(rtc->pie_enabled) ? "yes" : "no");
+		seq_printf(seq, "periodic IRQ frequency\t: %d\n",
+			rtc->irq_freq);
+		seq_printf(seq, "max user IRQ frequency\t: %d\n",
+			rtc->max_user_freq);
 	}
 
 	seq_printf(seq, "24hr\t\t: yes\n");
diff --git a/drivers/rtc/rtc-pxa.c b/drivers/rtc/rtc-pxa.c
index 29e867a1aaa8..fc9f4991574b 100644
--- a/drivers/rtc/rtc-pxa.c
+++ b/drivers/rtc/rtc-pxa.c
@@ -209,32 +209,6 @@ static void pxa_rtc_release(struct device *dev)
 	free_irq(pxa_rtc->irq_1Hz, dev);
 }
 
-static int pxa_periodic_irq_set_freq(struct device *dev, int freq)
-{
-	struct pxa_rtc *pxa_rtc = dev_get_drvdata(dev);
-	int period_ms;
-
-	if (freq < 1 || freq > MAXFREQ_PERIODIC)
-		return -EINVAL;
-
-	period_ms = 1000 / freq;
-	rtc_writel(pxa_rtc, PIAR, period_ms);
-
-	return 0;
-}
-
-static int pxa_periodic_irq_set_state(struct device *dev, int enabled)
-{
-	struct pxa_rtc *pxa_rtc = dev_get_drvdata(dev);
-
-	if (enabled)
-		rtsr_set_bits(pxa_rtc, RTSR_PIALE | RTSR_PICE);
-	else
-		rtsr_clear_bits(pxa_rtc, RTSR_PIALE | RTSR_PICE);
-
-	return 0;
-}
-
 static int pxa_alarm_irq_enable(struct device *dev, unsigned int enabled)
 {
 	struct pxa_rtc *pxa_rtc = dev_get_drvdata(dev);
@@ -250,21 +224,6 @@ static int pxa_alarm_irq_enable(struct device *dev, unsigned int enabled)
 	return 0;
 }
 
-static int pxa_update_irq_enable(struct device *dev, unsigned int enabled)
-{
-	struct pxa_rtc *pxa_rtc = dev_get_drvdata(dev);
-
-	spin_lock_irq(&pxa_rtc->lock);
-
-	if (enabled)
-		rtsr_set_bits(pxa_rtc, RTSR_HZE);
-	else
-		rtsr_clear_bits(pxa_rtc, RTSR_HZE);
-
-	spin_unlock_irq(&pxa_rtc->lock);
-	return 0;
-}
-
 static int pxa_rtc_read_time(struct device *dev, struct rtc_time *tm)
 {
 	struct pxa_rtc *pxa_rtc = dev_get_drvdata(dev);
@@ -346,10 +305,7 @@ static const struct rtc_class_ops pxa_rtc_ops = {
 	.read_alarm = pxa_rtc_read_alarm,
 	.set_alarm = pxa_rtc_set_alarm,
 	.alarm_irq_enable = pxa_alarm_irq_enable,
-	.update_irq_enable = pxa_update_irq_enable,
 	.proc = pxa_rtc_proc,
-	.irq_set_state = pxa_periodic_irq_set_state,
-	.irq_set_freq = pxa_periodic_irq_set_freq,
 };
 
 static int __init pxa_rtc_probe(struct platform_device *pdev)
diff --git a/drivers/rtc/rtc-rs5c372.c b/drivers/rtc/rtc-rs5c372.c
index 6aaa1550e3b1..85c1b848dd72 100644
--- a/drivers/rtc/rtc-rs5c372.c
+++ b/drivers/rtc/rtc-rs5c372.c
@@ -281,57 +281,6 @@ static int rs5c372_rtc_set_time(struct device *dev, struct rtc_time *tm)
 	return rs5c372_set_datetime(to_i2c_client(dev), tm);
 }
 
-#if defined(CONFIG_RTC_INTF_DEV) || defined(CONFIG_RTC_INTF_DEV_MODULE)
-
-static int
-rs5c_rtc_ioctl(struct device *dev, unsigned int cmd, unsigned long arg)
-{
-	struct i2c_client	*client = to_i2c_client(dev);
-	struct rs5c372		*rs5c = i2c_get_clientdata(client);
-	unsigned char		buf;
-	int			status, addr;
-
-	buf = rs5c->regs[RS5C_REG_CTRL1];
-	switch (cmd) {
-	case RTC_UIE_OFF:
-	case RTC_UIE_ON:
-		/* some 327a modes use a different IRQ pin for 1Hz irqs */
-		if (rs5c->type == rtc_rs5c372a
-				&& (buf & RS5C372A_CTRL1_SL1))
-			return -ENOIOCTLCMD;
-	default:
-		return -ENOIOCTLCMD;
-	}
-
-	status = rs5c_get_regs(rs5c);
-	if (status < 0)
-		return status;
-
-	addr = RS5C_ADDR(RS5C_REG_CTRL1);
-	switch (cmd) {
-	case RTC_UIE_OFF:	/* update off */
-		buf &= ~RS5C_CTRL1_CT_MASK;
-		break;
-	case RTC_UIE_ON:	/* update on */
-		buf &= ~RS5C_CTRL1_CT_MASK;
-		buf |= RS5C_CTRL1_CT4;
-		break;
-	}
-
-	if (i2c_smbus_write_byte_data(client, addr, buf) < 0) {
-		printk(KERN_WARNING "%s: can't update alarm\n",
-			rs5c->rtc->name);
-		status = -EIO;
-	} else
-		rs5c->regs[RS5C_REG_CTRL1] = buf;
-
-	return status;
-}
-
-#else
-#define	rs5c_rtc_ioctl	NULL
-#endif
-
 
 static int rs5c_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled)
 {
@@ -480,7 +429,6 @@ static int rs5c372_rtc_proc(struct device *dev, struct seq_file *seq)
 
 static const struct rtc_class_ops rs5c372_rtc_ops = {
 	.proc		= rs5c372_rtc_proc,
-	.ioctl		= rs5c_rtc_ioctl,
 	.read_time	= rs5c372_rtc_read_time,
 	.set_time	= rs5c372_rtc_set_time,
 	.read_alarm	= rs5c_read_alarm,
diff --git a/drivers/rtc/rtc-rx8025.c b/drivers/rtc/rtc-rx8025.c
index af32a62e12a8..fde172fb2abe 100644
--- a/drivers/rtc/rtc-rx8025.c
+++ b/drivers/rtc/rtc-rx8025.c
@@ -424,37 +424,12 @@ static int rx8025_alarm_irq_enable(struct device *dev, unsigned int enabled)
 	return 0;
 }
 
-static int rx8025_irq_set_state(struct device *dev, int enabled)
-{
-	struct i2c_client *client = to_i2c_client(dev);
-	struct rx8025_data *rx8025 = i2c_get_clientdata(client);
-	int ctrl1;
-	int err;
-
-	if (client->irq <= 0)
-		return -ENXIO;
-
-	ctrl1 = rx8025->ctrl1 & ~RX8025_BIT_CTRL1_CT;
-	if (enabled)
-		ctrl1 |= RX8025_BIT_CTRL1_CT_1HZ;
-	if (ctrl1 != rx8025->ctrl1) {
-		rx8025->ctrl1 = ctrl1;
-		err = rx8025_write_reg(rx8025->client, RX8025_REG_CTRL1,
-				       rx8025->ctrl1);
-		if (err)
-			return err;
-	}
-
-	return 0;
-}
-
 static struct rtc_class_ops rx8025_rtc_ops = {
 	.read_time = rx8025_get_time,
 	.set_time = rx8025_set_time,
 	.read_alarm = rx8025_read_alarm,
 	.set_alarm = rx8025_set_alarm,
 	.alarm_irq_enable = rx8025_alarm_irq_enable,
-	.irq_set_state  = rx8025_irq_set_state,
 };
 
 /*
diff --git a/drivers/rtc/rtc-s3c.c b/drivers/rtc/rtc-s3c.c
index b80fa2882408..714964913e5e 100644
--- a/drivers/rtc/rtc-s3c.c
+++ b/drivers/rtc/rtc-s3c.c
@@ -93,37 +93,6 @@ static int s3c_rtc_setaie(struct device *dev, unsigned int enabled)
 	return 0;
 }
 
-static int s3c_rtc_setpie(struct device *dev, int enabled)
-{
-	unsigned int tmp;
-
-	pr_debug("%s: pie=%d\n", __func__, enabled);
-
-	spin_lock_irq(&s3c_rtc_pie_lock);
-
-	if (s3c_rtc_cpu_type == TYPE_S3C64XX) {
-		tmp = readw(s3c_rtc_base + S3C2410_RTCCON);
-		tmp &= ~S3C64XX_RTCCON_TICEN;
-
-		if (enabled)
-			tmp |= S3C64XX_RTCCON_TICEN;
-
-		writew(tmp, s3c_rtc_base + S3C2410_RTCCON);
-	} else {
-		tmp = readb(s3c_rtc_base + S3C2410_TICNT);
-		tmp &= ~S3C2410_TICNT_ENABLE;
-
-		if (enabled)
-			tmp |= S3C2410_TICNT_ENABLE;
-
-		writeb(tmp, s3c_rtc_base + S3C2410_TICNT);
-	}
-
-	spin_unlock_irq(&s3c_rtc_pie_lock);
-
-	return 0;
-}
-
 static int s3c_rtc_setfreq(struct device *dev, int freq)
 {
 	struct platform_device *pdev = to_platform_device(dev);
@@ -379,8 +348,6 @@ static const struct rtc_class_ops s3c_rtcops = {
 	.set_time	= s3c_rtc_settime,
 	.read_alarm	= s3c_rtc_getalarm,
 	.set_alarm	= s3c_rtc_setalarm,
-	.irq_set_freq	= s3c_rtc_setfreq,
-	.irq_set_state	= s3c_rtc_setpie,
 	.proc		= s3c_rtc_proc,
 	.alarm_irq_enable = s3c_rtc_setaie,
 };
diff --git a/drivers/rtc/rtc-sa1100.c b/drivers/rtc/rtc-sa1100.c
index 5dfe5ffcb0d3..0b40bb88a884 100644
--- a/drivers/rtc/rtc-sa1100.c
+++ b/drivers/rtc/rtc-sa1100.c
@@ -43,7 +43,6 @@
 #define RTC_DEF_TRIM		0
 
 static const unsigned long RTC_FREQ = 1024;
-static unsigned long timer_freq;
 static struct rtc_time rtc_alarm;
 static DEFINE_SPINLOCK(sa1100_rtc_lock);
 
@@ -156,114 +155,11 @@ static irqreturn_t sa1100_rtc_interrupt(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static int sa1100_irq_set_freq(struct device *dev, int freq)
-{
-	if (freq < 1 || freq > timer_freq) {
-		return -EINVAL;
-	} else {
-		struct rtc_device *rtc = (struct rtc_device *)dev;
-
-		rtc->irq_freq = freq;
-
-		return 0;
-	}
-}
-
-static int rtc_timer1_count;
-
-static int sa1100_irq_set_state(struct device *dev, int enabled)
-{
-	spin_lock_irq(&sa1100_rtc_lock);
-	if (enabled) {
-		struct rtc_device *rtc = (struct rtc_device *)dev;
-
-		OSMR1 = timer_freq / rtc->irq_freq + OSCR;
-		OIER |= OIER_E1;
-		rtc_timer1_count = 1;
-	} else {
-		OIER &= ~OIER_E1;
-	}
-	spin_unlock_irq(&sa1100_rtc_lock);
-
-	return 0;
-}
-
-static inline int sa1100_timer1_retrigger(struct rtc_device *rtc)
-{
-	unsigned long diff;
-	unsigned long period = timer_freq / rtc->irq_freq;
-
-	spin_lock_irq(&sa1100_rtc_lock);
-
-	do {
-		OSMR1 += period;
-		diff = OSMR1 - OSCR;
-		/* If OSCR > OSMR1, diff is a very large number (unsigned
-		 * math). This means we have a lost interrupt. */
-	} while (diff > period);
-	OIER |= OIER_E1;
-
-	spin_unlock_irq(&sa1100_rtc_lock);
-
-	return 0;
-}
-
-static irqreturn_t timer1_interrupt(int irq, void *dev_id)
-{
-	struct platform_device *pdev = to_platform_device(dev_id);
-	struct rtc_device *rtc = platform_get_drvdata(pdev);
-
-	/*
-	 * If we match for the first time, rtc_timer1_count will be 1.
-	 * Otherwise, we wrapped around (very unlikely but
-	 * still possible) so compute the amount of missed periods.
-	 * The match reg is updated only when the data is actually retrieved
-	 * to avoid unnecessary interrupts.
-	 */
-	OSSR = OSSR_M1;	/* clear match on timer1 */
-
-	rtc_update_irq(rtc, rtc_timer1_count, RTC_PF | RTC_IRQF);
-
-	if (rtc_timer1_count == 1)
-		rtc_timer1_count =
-			(rtc->irq_freq * ((1 << 30) / (timer_freq >> 2)));
-
-	/* retrigger. */
-	sa1100_timer1_retrigger(rtc);
-
-	return IRQ_HANDLED;
-}
-
-static int sa1100_rtc_read_callback(struct device *dev, int data)
-{
-	if (data & RTC_PF) {
-		struct rtc_device *rtc = (struct rtc_device *)dev;
-
-		/* interpolate missed periods and set match for the next */
-		unsigned long period = timer_freq / rtc->irq_freq;
-		unsigned long oscr = OSCR;
-		unsigned long osmr1 = OSMR1;
-		unsigned long missed = (oscr - osmr1)/period;
-		data += missed << 8;
-		OSSR = OSSR_M1;	/* clear match on timer 1 */
-		OSMR1 = osmr1 + (missed + 1)*period;
-		/* Ensure we didn't miss another match in the mean time.
-		 * Here we compare (match - OSCR) 8 instead of 0 --
-		 * see comment in pxa_timer_interrupt() for explanation.
-		 */
-		while ((signed long)((osmr1 = OSMR1) - OSCR) <= 8) {
-			data += 0x100;
-			OSSR = OSSR_M1;	/* clear match on timer 1 */
-			OSMR1 = osmr1 + period;
-		}
-	}
-	return data;
-}
-
 static int sa1100_rtc_open(struct device *dev)
 {
 	int ret;
-	struct rtc_device *rtc = (struct rtc_device *)dev;
+	struct platform_device *plat_dev = to_platform_device(dev);
+	struct rtc_device *rtc = platform_get_drvdata(plat_dev);
 
 	ret = request_irq(IRQ_RTC1Hz, sa1100_rtc_interrupt, IRQF_DISABLED,
 		"rtc 1Hz", dev);
@@ -277,19 +173,11 @@ static int sa1100_rtc_open(struct device *dev)
 		dev_err(dev, "IRQ %d already in use.\n", IRQ_RTCAlrm);
 		goto fail_ai;
 	}
-	ret = request_irq(IRQ_OST1, timer1_interrupt, IRQF_DISABLED,
-		"rtc timer", dev);
-	if (ret) {
-		dev_err(dev, "IRQ %d already in use.\n", IRQ_OST1);
-		goto fail_pi;
-	}
 	rtc->max_user_freq = RTC_FREQ;
-	sa1100_irq_set_freq(dev, RTC_FREQ);
+	rtc_irq_set_freq(rtc, NULL, RTC_FREQ);
 
 	return 0;
 
- fail_pi:
-	free_irq(IRQ_RTCAlrm, dev);
  fail_ai:
 	free_irq(IRQ_RTC1Hz, dev);
  fail_ui:
@@ -304,30 +192,10 @@ static void sa1100_rtc_release(struct device *dev)
 	OSSR = OSSR_M1;
 	spin_unlock_irq(&sa1100_rtc_lock);
 
-	free_irq(IRQ_OST1, dev);
 	free_irq(IRQ_RTCAlrm, dev);
 	free_irq(IRQ_RTC1Hz, dev);
 }
 
-
-static int sa1100_rtc_ioctl(struct device *dev, unsigned int cmd,
-		unsigned long arg)
-{
-	switch (cmd) {
-	case RTC_UIE_OFF:
-		spin_lock_irq(&sa1100_rtc_lock);
-		RTSR &= ~RTSR_HZE;
-		spin_unlock_irq(&sa1100_rtc_lock);
-		return 0;
-	case RTC_UIE_ON:
-		spin_lock_irq(&sa1100_rtc_lock);
-		RTSR |= RTSR_HZE;
-		spin_unlock_irq(&sa1100_rtc_lock);
-		return 0;
-	}
-	return -ENOIOCTLCMD;
-}
-
 static int sa1100_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled)
 {
 	spin_lock_irq(&sa1100_rtc_lock);
@@ -386,31 +254,20 @@ static int sa1100_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
 
 static int sa1100_rtc_proc(struct device *dev, struct seq_file *seq)
 {
-	struct rtc_device *rtc = (struct rtc_device *)dev;
-
-	seq_printf(seq, "trim/divider\t: 0x%08x\n", (u32) RTTR);
-	seq_printf(seq, "update_IRQ\t: %s\n",
-			(RTSR & RTSR_HZE) ? "yes" : "no");
-	seq_printf(seq, "periodic_IRQ\t: %s\n",
-			(OIER & OIER_E1) ? "yes" : "no");
-	seq_printf(seq, "periodic_freq\t: %d\n", rtc->irq_freq);
-	seq_printf(seq, "RTSR\t\t: 0x%08x\n", (u32)RTSR);
+	seq_printf(seq, "trim/divider\t\t: 0x%08x\n", (u32) RTTR);
+	seq_printf(seq, "RTSR\t\t\t: 0x%08x\n", (u32)RTSR);
 
 	return 0;
 }
 
 static const struct rtc_class_ops sa1100_rtc_ops = {
 	.open = sa1100_rtc_open,
-	.read_callback = sa1100_rtc_read_callback,
 	.release = sa1100_rtc_release,
-	.ioctl = sa1100_rtc_ioctl,
 	.read_time = sa1100_rtc_read_time,
 	.set_time = sa1100_rtc_set_time,
 	.read_alarm = sa1100_rtc_read_alarm,
 	.set_alarm = sa1100_rtc_set_alarm,
 	.proc = sa1100_rtc_proc,
-	.irq_set_freq = sa1100_irq_set_freq,
-	.irq_set_state = sa1100_irq_set_state,
 	.alarm_irq_enable = sa1100_rtc_alarm_irq_enable,
 };
 
@@ -418,8 +275,6 @@ static int sa1100_rtc_probe(struct platform_device *pdev)
 {
 	struct rtc_device *rtc;
 
-	timer_freq = get_clock_tick_rate();
-
 	/*
 	 * According to the manual we should be able to let RTTR be zero
 	 * and then a default diviser for a 32.768KHz clock is used.
@@ -445,11 +300,6 @@ static int sa1100_rtc_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, rtc);
 
-	/* Set the irq_freq */
-	/*TODO: Find out who is messing with this value after we initialize
-	 * it here.*/
-	rtc->irq_freq = RTC_FREQ;
-
 	/* Fix for a nasty initialization problem the in SA11xx RTSR register.
 	 * See also the comments in sa1100_rtc_interrupt().
 	 *
diff --git a/drivers/rtc/rtc-sh.c b/drivers/rtc/rtc-sh.c
index 93314a9e7fa9..e55dc1ac83ab 100644
--- a/drivers/rtc/rtc-sh.c
+++ b/drivers/rtc/rtc-sh.c
@@ -344,27 +344,6 @@ static inline void sh_rtc_setcie(struct device *dev, unsigned int enable)
 	spin_unlock_irq(&rtc->lock);
 }
 
-static int sh_rtc_ioctl(struct device *dev, unsigned int cmd, unsigned long arg)
-{
-	struct sh_rtc *rtc = dev_get_drvdata(dev);
-	unsigned int ret = 0;
-
-	switch (cmd) {
-	case RTC_UIE_OFF:
-		rtc->periodic_freq &= ~PF_OXS;
-		sh_rtc_setcie(dev, 0);
-		break;
-	case RTC_UIE_ON:
-		rtc->periodic_freq |= PF_OXS;
-		sh_rtc_setcie(dev, 1);
-		break;
-	default:
-		ret = -ENOIOCTLCMD;
-	}
-
-	return ret;
-}
-
 static int sh_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled)
 {
 	sh_rtc_setaie(dev, enabled);
@@ -598,13 +577,10 @@ static int sh_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *wkalrm)
 }
 
 static struct rtc_class_ops sh_rtc_ops = {
-	.ioctl		= sh_rtc_ioctl,
 	.read_time	= sh_rtc_read_time,
 	.set_time	= sh_rtc_set_time,
 	.read_alarm	= sh_rtc_read_alarm,
 	.set_alarm	= sh_rtc_set_alarm,
-	.irq_set_state	= sh_rtc_irq_set_state,
-	.irq_set_freq	= sh_rtc_irq_set_freq,
 	.proc		= sh_rtc_proc,
 	.alarm_irq_enable = sh_rtc_alarm_irq_enable,
 };
diff --git a/drivers/rtc/rtc-stmp3xxx.c b/drivers/rtc/rtc-stmp3xxx.c
index 7e7d0c806f2d..572e9534b591 100644
--- a/drivers/rtc/rtc-stmp3xxx.c
+++ b/drivers/rtc/rtc-stmp3xxx.c
@@ -115,19 +115,6 @@ static int stmp3xxx_alarm_irq_enable(struct device *dev, unsigned int enabled)
 	return 0;
 }
 
-static int stmp3xxx_update_irq_enable(struct device *dev, unsigned int enabled)
-{
-	struct stmp3xxx_rtc_data *rtc_data = dev_get_drvdata(dev);
-
-	if (enabled)
-		stmp3xxx_setl(BM_RTC_CTRL_ONEMSEC_IRQ_EN,
-				rtc_data->io + HW_RTC_CTRL);
-	else
-		stmp3xxx_clearl(BM_RTC_CTRL_ONEMSEC_IRQ_EN,
-				rtc_data->io + HW_RTC_CTRL);
-	return 0;
-}
-
 static int stmp3xxx_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alm)
 {
 	struct stmp3xxx_rtc_data *rtc_data = dev_get_drvdata(dev);
@@ -149,8 +136,6 @@ static int stmp3xxx_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alm)
 static struct rtc_class_ops stmp3xxx_rtc_ops = {
 	.alarm_irq_enable =
 			  stmp3xxx_alarm_irq_enable,
-	.update_irq_enable =
-			  stmp3xxx_update_irq_enable,
 	.read_time	= stmp3xxx_rtc_gettime,
 	.set_mmss	= stmp3xxx_rtc_set_mmss,
 	.read_alarm	= stmp3xxx_rtc_read_alarm,
diff --git a/drivers/rtc/rtc-test.c b/drivers/rtc/rtc-test.c
index a82d6fe97076..7e96254bd365 100644
--- a/drivers/rtc/rtc-test.c
+++ b/drivers/rtc/rtc-test.c
@@ -78,11 +78,16 @@ static ssize_t test_irq_store(struct device *dev,
 	struct rtc_device *rtc = platform_get_drvdata(plat_dev);
 
 	retval = count;
-	if (strncmp(buf, "tick", 4) == 0)
+	if (strncmp(buf, "tick", 4) == 0 && rtc->pie_enabled)
 		rtc_update_irq(rtc, 1, RTC_PF | RTC_IRQF);
-	else if (strncmp(buf, "alarm", 5) == 0)
-		rtc_update_irq(rtc, 1, RTC_AF | RTC_IRQF);
-	else if (strncmp(buf, "update", 6) == 0)
+	else if (strncmp(buf, "alarm", 5) == 0) {
+		struct rtc_wkalrm alrm;
+		int err = rtc_read_alarm(rtc, &alrm);
+
+		if (!err && alrm.enabled)
+			rtc_update_irq(rtc, 1, RTC_AF | RTC_IRQF);
+
+	} else if (strncmp(buf, "update", 6) == 0 && rtc->uie_rtctimer.enabled)
 		rtc_update_irq(rtc, 1, RTC_UF | RTC_IRQF);
 	else
 		retval = -EINVAL;
diff --git a/drivers/rtc/rtc-twl.c b/drivers/rtc/rtc-twl.c
index ed1b86828124..f9a2799c44d6 100644
--- a/drivers/rtc/rtc-twl.c
+++ b/drivers/rtc/rtc-twl.c
@@ -213,18 +213,6 @@ static int twl_rtc_alarm_irq_enable(struct device *dev, unsigned enabled)
 	return ret;
 }
 
-static int twl_rtc_update_irq_enable(struct device *dev, unsigned enabled)
-{
-	int ret;
-
-	if (enabled)
-		ret = set_rtc_irq_bit(BIT_RTC_INTERRUPTS_REG_IT_TIMER_M);
-	else
-		ret = mask_rtc_irq_bit(BIT_RTC_INTERRUPTS_REG_IT_TIMER_M);
-
-	return ret;
-}
-
 /*
  * Gets current TWL RTC time and date parameters.
  *
@@ -433,7 +421,6 @@ static struct rtc_class_ops twl_rtc_ops = {
 	.read_alarm	= twl_rtc_read_alarm,
 	.set_alarm	= twl_rtc_set_alarm,
 	.alarm_irq_enable = twl_rtc_alarm_irq_enable,
-	.update_irq_enable = twl_rtc_update_irq_enable,
 };
 
 /*----------------------------------------------------------------------*/
diff --git a/drivers/rtc/rtc-vr41xx.c b/drivers/rtc/rtc-vr41xx.c
index 769190ac6d11..c5698cda366a 100644
--- a/drivers/rtc/rtc-vr41xx.c
+++ b/drivers/rtc/rtc-vr41xx.c
@@ -207,36 +207,6 @@ static int vr41xx_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *wkalrm)
 	return 0;
 }
 
-static int vr41xx_rtc_irq_set_freq(struct device *dev, int freq)
-{
-	u64 count;
-
-	if (!is_power_of_2(freq))
-		return -EINVAL;
-	count = RTC_FREQUENCY;
-	do_div(count, freq);
-
-	spin_lock_irq(&rtc_lock);
-
-	periodic_count = count;
-	rtc1_write(RTCL1LREG, periodic_count);
-	rtc1_write(RTCL1HREG, periodic_count >> 16);
-
-	spin_unlock_irq(&rtc_lock);
-
-	return 0;
-}
-
-static int vr41xx_rtc_irq_set_state(struct device *dev, int enabled)
-{
-	if (enabled)
-		enable_irq(pie_irq);
-	else
-		disable_irq(pie_irq);
-
-	return 0;
-}
-
 static int vr41xx_rtc_ioctl(struct device *dev, unsigned int cmd, unsigned long arg)
 {
 	switch (cmd) {
@@ -308,8 +278,6 @@ static const struct rtc_class_ops vr41xx_rtc_ops = {
 	.set_time	= vr41xx_rtc_set_time,
 	.read_alarm	= vr41xx_rtc_read_alarm,
 	.set_alarm	= vr41xx_rtc_set_alarm,
-	.irq_set_freq	= vr41xx_rtc_irq_set_freq,
-	.irq_set_state	= vr41xx_rtc_irq_set_state,
 };
 
 static int __devinit rtc_probe(struct platform_device *pdev)
diff --git a/drivers/rtc/rtc-wm831x.c b/drivers/rtc/rtc-wm831x.c
index 82931dc65c0b..bdc909bd56da 100644
--- a/drivers/rtc/rtc-wm831x.c
+++ b/drivers/rtc/rtc-wm831x.c
@@ -315,21 +315,6 @@ static int wm831x_rtc_alarm_irq_enable(struct device *dev,
 		return wm831x_rtc_stop_alarm(wm831x_rtc);
 }
 
-static int wm831x_rtc_update_irq_enable(struct device *dev,
-					unsigned int enabled)
-{
-	struct wm831x_rtc *wm831x_rtc = dev_get_drvdata(dev);
-	int val;
-
-	if (enabled)
-		val = 1 << WM831X_RTC_PINT_FREQ_SHIFT;
-	else
-		val = 0;
-
-	return wm831x_set_bits(wm831x_rtc->wm831x, WM831X_RTC_CONTROL,
-			       WM831X_RTC_PINT_FREQ_MASK, val);
-}
-
 static irqreturn_t wm831x_alm_irq(int irq, void *data)
 {
 	struct wm831x_rtc *wm831x_rtc = data;
@@ -354,7 +339,6 @@ static const struct rtc_class_ops wm831x_rtc_ops = {
 	.read_alarm = wm831x_rtc_readalarm,
 	.set_alarm = wm831x_rtc_setalarm,
 	.alarm_irq_enable = wm831x_rtc_alarm_irq_enable,
-	.update_irq_enable = wm831x_rtc_update_irq_enable,
 };
 
 #ifdef CONFIG_PM
diff --git a/drivers/rtc/rtc-wm8350.c b/drivers/rtc/rtc-wm8350.c
index 3d0dc76b38af..66421426e404 100644
--- a/drivers/rtc/rtc-wm8350.c
+++ b/drivers/rtc/rtc-wm8350.c
@@ -302,26 +302,6 @@ static int wm8350_rtc_setalarm(struct device *dev, struct rtc_wkalrm *alrm)
 	return ret;
 }
 
-static int wm8350_rtc_update_irq_enable(struct device *dev,
-					unsigned int enabled)
-{
-	struct wm8350 *wm8350 = dev_get_drvdata(dev);
-
-	/* Suppress duplicate changes since genirq nests enable and
-	 * disable calls. */
-	if (enabled == wm8350->rtc.update_enabled)
-		return 0;
-
-	if (enabled)
-		wm8350_unmask_irq(wm8350, WM8350_IRQ_RTC_SEC);
-	else
-		wm8350_mask_irq(wm8350, WM8350_IRQ_RTC_SEC);
-
-	wm8350->rtc.update_enabled = enabled;
-
-	return 0;
-}
-
 static irqreturn_t wm8350_rtc_alarm_handler(int irq, void *data)
 {
 	struct wm8350 *wm8350 = data;
@@ -357,7 +337,6 @@ static const struct rtc_class_ops wm8350_rtc_ops = {
 	.read_alarm = wm8350_rtc_readalarm,
 	.set_alarm = wm8350_rtc_setalarm,
 	.alarm_irq_enable = wm8350_rtc_alarm_irq_enable,
-	.update_irq_enable = wm8350_rtc_update_irq_enable,
 };
 
 #ifdef CONFIG_PM
diff --git a/drivers/spi/pxa2xx_spi.c b/drivers/spi/pxa2xx_spi.c
index 95928833855b..a429b01d0285 100644
--- a/drivers/spi/pxa2xx_spi.c
+++ b/drivers/spi/pxa2xx_spi.c
@@ -1557,9 +1557,7 @@ static int __devinit pxa2xx_spi_probe(struct platform_device *pdev)
 	drv_data->ssp = ssp;
 
 	master->dev.parent = &pdev->dev;
-#ifdef CONFIG_OF
 	master->dev.of_node = pdev->dev.of_node;
-#endif
 	/* the spi->mode bits understood by this driver: */
 	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH;
 
diff --git a/drivers/spi/pxa2xx_spi_pci.c b/drivers/spi/pxa2xx_spi_pci.c
index 19752b09e155..378e504f89eb 100644
--- a/drivers/spi/pxa2xx_spi_pci.c
+++ b/drivers/spi/pxa2xx_spi_pci.c
@@ -89,9 +89,7 @@ static int __devinit ce4100_spi_probe(struct pci_dev *dev,
 		goto err_nomem;
 
 	pdev->dev.parent = &dev->dev;
-#ifdef CONFIG_OF
 	pdev->dev.of_node = dev->dev.of_node;
-#endif
 	ssp = &spi_info->ssp;
 	ssp->phys_base = pci_resource_start(dev, 0);
 	ssp->mmio_base = ioremap(phys_beg, phys_len);
diff --git a/drivers/spi/xilinx_spi.c b/drivers/spi/xilinx_spi.c
index 7adaef62a991..4d2c75df886c 100644
--- a/drivers/spi/xilinx_spi.c
+++ b/drivers/spi/xilinx_spi.c
@@ -351,14 +351,12 @@ static irqreturn_t xilinx_spi_irq(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-#ifdef CONFIG_OF
 static const struct of_device_id xilinx_spi_of_match[] = {
 	{ .compatible = "xlnx,xps-spi-2.00.a", },
 	{ .compatible = "xlnx,xps-spi-2.00.b", },
 	{}
 };
 MODULE_DEVICE_TABLE(of, xilinx_spi_of_match);
-#endif
 
 struct spi_master *xilinx_spi_init(struct device *dev, struct resource *mem,
 	u32 irq, s16 bus_num, int num_cs, int little_endian, int bits_per_word)
@@ -394,9 +392,7 @@ struct spi_master *xilinx_spi_init(struct device *dev, struct resource *mem,
 
 	master->bus_num = bus_num;
 	master->num_chipselect = num_cs;
-#ifdef CONFIG_OF
 	master->dev.of_node = dev->of_node;
-#endif
 
 	xspi->mem = *mem;
 	xspi->irq = irq;
@@ -539,9 +535,7 @@ static struct platform_driver xilinx_spi_driver = {
 	.driver = {
 		.name = XILINX_SPI_NAME,
 		.owner = THIS_MODULE,
-#ifdef CONFIG_OF
 		.of_match_table = xilinx_spi_of_match,
-#endif
 	},
 };
 
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index 43f9f02c7db0..718050ace08f 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -232,7 +232,7 @@ static int increase_reservation(unsigned long nr_pages)
 		set_phys_to_machine(pfn, frame_list[i]);
 
 		/* Link back into the page tables if not highmem. */
-		if (pfn < max_low_pfn) {
+		if (!xen_hvm_domain() && pfn < max_low_pfn) {
 			int ret;
 			ret = HYPERVISOR_update_va_mapping(
 				(unsigned long)__va(pfn << PAGE_SHIFT),
@@ -280,7 +280,7 @@ static int decrease_reservation(unsigned long nr_pages)
 
 		scrub_page(page);
 
-		if (!PageHighMem(page)) {
+		if (!xen_hvm_domain() && !PageHighMem(page)) {
 			ret = HYPERVISOR_update_va_mapping(
 				(unsigned long)__va(pfn << PAGE_SHIFT),
 				__pte_ma(0), 0);
@@ -296,7 +296,7 @@ static int decrease_reservation(unsigned long nr_pages)
 	/* No more mappings: invalidate P2M and add to balloon. */
 	for (i = 0; i < nr_pages; i++) {
 		pfn = mfn_to_pfn(frame_list[i]);
-		set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
+		__set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
 		balloon_append(pfn_to_page(pfn));
 	}
 
@@ -392,15 +392,19 @@ static struct notifier_block xenstore_notifier;
 
 static int __init balloon_init(void)
 {
-	unsigned long pfn, extra_pfn_end;
+ 	unsigned long pfn, nr_pages, extra_pfn_end;
 	struct page *page;
 
-	if (!xen_pv_domain())
+	if (!xen_domain())
 		return -ENODEV;
 
 	pr_info("xen_balloon: Initialising balloon driver.\n");
 
-	balloon_stats.current_pages = min(xen_start_info->nr_pages, max_pfn);
+ 	if (xen_pv_domain())
+ 		nr_pages = xen_start_info->nr_pages;
+ 	else
+ 		nr_pages = max_pfn;
+ 	balloon_stats.current_pages = min(nr_pages, max_pfn);
 	balloon_stats.target_pages  = balloon_stats.current_pages;
 	balloon_stats.balloon_low   = 0;
 	balloon_stats.balloon_high  = 0;
diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index 74681478100a..0ad1699a1b3e 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -114,7 +114,7 @@ struct cpu_evtchn_s {
 static __initdata struct cpu_evtchn_s init_evtchn_mask = {
 	.bits[0 ... (NR_EVENT_CHANNELS/BITS_PER_LONG)-1] = ~0ul,
 };
-static struct cpu_evtchn_s *cpu_evtchn_mask_p = &init_evtchn_mask;
+static struct cpu_evtchn_s __refdata *cpu_evtchn_mask_p = &init_evtchn_mask;
 
 static inline unsigned long *cpu_evtchn_mask(int cpu)
 {
@@ -277,7 +277,7 @@ static void bind_evtchn_to_cpu(unsigned int chn, unsigned int cpu)
 
 	BUG_ON(irq == -1);
 #ifdef CONFIG_SMP
-	cpumask_copy(irq_to_desc(irq)->affinity, cpumask_of(cpu));
+	cpumask_copy(irq_to_desc(irq)->irq_data.affinity, cpumask_of(cpu));
 #endif
 
 	clear_bit(chn, cpu_evtchn_mask(cpu_from_irq(irq)));
@@ -294,7 +294,7 @@ static void init_evtchn_cpu_bindings(void)
 
 	/* By default all event channels notify CPU#0. */
 	for_each_irq_desc(i, desc) {
-		cpumask_copy(desc->affinity, cpumask_of(0));
+		cpumask_copy(desc->irq_data.affinity, cpumask_of(0));
 	}
 #endif
 
@@ -376,81 +376,69 @@ static void unmask_evtchn(int port)
 	put_cpu();
 }
 
-static int get_nr_hw_irqs(void)
+static int xen_allocate_irq_dynamic(void)
 {
-	int ret = 1;
+	int first = 0;
+	int irq;
 
 #ifdef CONFIG_X86_IO_APIC
-	ret = get_nr_irqs_gsi();
+	/*
+	 * For an HVM guest or domain 0 which see "real" (emulated or
+	 * actual repectively) GSIs we allocate dynamic IRQs
+	 * e.g. those corresponding to event channels or MSIs
+	 * etc. from the range above those "real" GSIs to avoid
+	 * collisions.
+	 */
+	if (xen_initial_domain() || xen_hvm_domain())
+		first = get_nr_irqs_gsi();
 #endif
 
-	return ret;
-}
+retry:
+	irq = irq_alloc_desc_from(first, -1);
 
-static int find_unbound_pirq(int type)
-{
-	int rc, i;
-	struct physdev_get_free_pirq op_get_free_pirq;
-	op_get_free_pirq.type = type;
+	if (irq == -ENOMEM && first > NR_IRQS_LEGACY) {
+		printk(KERN_ERR "Out of dynamic IRQ space and eating into GSI space. You should increase nr_irqs\n");
+		first = max(NR_IRQS_LEGACY, first - NR_IRQS_LEGACY);
+		goto retry;
+	}
 
-	rc = HYPERVISOR_physdev_op(PHYSDEVOP_get_free_pirq, &op_get_free_pirq);
-	if (!rc)
-		return op_get_free_pirq.pirq;
+	if (irq < 0)
+		panic("No available IRQ to bind to: increase nr_irqs!\n");
 
-	for (i = 0; i < nr_irqs; i++) {
-		if (pirq_to_irq[i] < 0)
-			return i;
-	}
-	return -1;
+	return irq;
 }
 
-static int find_unbound_irq(void)
+static int xen_allocate_irq_gsi(unsigned gsi)
 {
-	struct irq_data *data;
-	int irq, res;
-	int bottom = get_nr_hw_irqs();
-	int top = nr_irqs-1;
-
-	if (bottom == nr_irqs)
-		goto no_irqs;
+	int irq;
 
-	/* This loop starts from the top of IRQ space and goes down.
-	 * We need this b/c if we have a PCI device in a Xen PV guest
-	 * we do not have an IO-APIC (though the backend might have them)
-	 * mapped in. To not have a collision of physical IRQs with the Xen
-	 * event channels start at the top of the IRQ space for virtual IRQs.
+	/*
+	 * A PV guest has no concept of a GSI (since it has no ACPI
+	 * nor access to/knowledge of the physical APICs). Therefore
+	 * all IRQs are dynamically allocated from the entire IRQ
+	 * space.
 	 */
-	for (irq = top; irq > bottom; irq--) {
-		data = irq_get_irq_data(irq);
-		/* only 15->0 have init'd desc; handle irq > 16 */
-		if (!data)
-			break;
-		if (data->chip == &no_irq_chip)
-			break;
-		if (data->chip != &xen_dynamic_chip)
-			continue;
-		if (irq_info[irq].type == IRQT_UNBOUND)
-			return irq;
-	}
-
-	if (irq == bottom)
-		goto no_irqs;
+	if (xen_pv_domain() && !xen_initial_domain())
+		return xen_allocate_irq_dynamic();
 
-	res = irq_alloc_desc_at(irq, -1);
+	/* Legacy IRQ descriptors are already allocated by the arch. */
+	if (gsi < NR_IRQS_LEGACY)
+		return gsi;
 
-	if (WARN_ON(res != irq))
-		return -1;
+	irq = irq_alloc_desc_at(gsi, -1);
+	if (irq < 0)
+		panic("Unable to allocate to IRQ%d (%d)\n", gsi, irq);
 
 	return irq;
-
-no_irqs:
-	panic("No available IRQ to bind to: increase nr_irqs!\n");
 }
 
-static bool identity_mapped_irq(unsigned irq)
+static void xen_free_irq(unsigned irq)
 {
-	/* identity map all the hardware irqs */
-	return irq < get_nr_hw_irqs();
+	/* Legacy IRQ descriptors are managed by the arch. */
+	if (irq < NR_IRQS_LEGACY)
+		return;
+
+	irq_free_desc(irq);
 }
 
 static void pirq_unmask_notify(int irq)
@@ -486,7 +474,7 @@ static bool probing_irq(int irq)
 	return desc && desc->action == NULL;
 }
 
-static unsigned int startup_pirq(unsigned int irq)
+static unsigned int __startup_pirq(unsigned int irq)
 {
 	struct evtchn_bind_pirq bind_pirq;
 	struct irq_info *info = info_for_irq(irq);
@@ -524,9 +512,15 @@ out:
 	return 0;
 }
 
-static void shutdown_pirq(unsigned int irq)
+static unsigned int startup_pirq(struct irq_data *data)
+{
+	return __startup_pirq(data->irq);
+}
+
+static void shutdown_pirq(struct irq_data *data)
 {
 	struct evtchn_close close;
+	unsigned int irq = data->irq;
 	struct irq_info *info = info_for_irq(irq);
 	int evtchn = evtchn_from_irq(irq);
 
@@ -546,20 +540,20 @@ static void shutdown_pirq(unsigned int irq)
 	info->evtchn = 0;
 }
 
-static void enable_pirq(unsigned int irq)
+static void enable_pirq(struct irq_data *data)
 {
-	startup_pirq(irq);
+	startup_pirq(data);
 }
 
-static void disable_pirq(unsigned int irq)
+static void disable_pirq(struct irq_data *data)
 {
 }
 
-static void ack_pirq(unsigned int irq)
+static void ack_pirq(struct irq_data *data)
 {
-	int evtchn = evtchn_from_irq(irq);
+	int evtchn = evtchn_from_irq(data->irq);
 
-	move_native_irq(irq);
+	move_native_irq(data->irq);
 
 	if (VALID_EVTCHN(evtchn)) {
 		mask_evtchn(evtchn);
@@ -567,23 +561,6 @@ static void ack_pirq(unsigned int irq)
 	}
 }
 
-static void end_pirq(unsigned int irq)
-{
-	int evtchn = evtchn_from_irq(irq);
-	struct irq_desc *desc = irq_to_desc(irq);
-
-	if (WARN_ON(!desc))
-		return;
-
-	if ((desc->status & (IRQ_DISABLED|IRQ_PENDING)) ==
-	    (IRQ_DISABLED|IRQ_PENDING)) {
-		shutdown_pirq(irq);
-	} else if (VALID_EVTCHN(evtchn)) {
-		unmask_evtchn(evtchn);
-		pirq_unmask_notify(irq);
-	}
-}
-
 static int find_irq_by_gsi(unsigned gsi)
 {
 	int irq;
@@ -638,14 +615,7 @@ int xen_map_pirq_gsi(unsigned pirq, unsigned gsi, int shareable, char *name)
 		goto out;	/* XXX need refcount? */
 	}
 
-	/* If we are a PV guest, we don't have GSIs (no ACPI passed). Therefore
-	 * we are using the !xen_initial_domain() to drop in the function.*/
-	if (identity_mapped_irq(gsi) || (!xen_initial_domain() &&
-				xen_pv_domain())) {
-		irq = gsi;
-		irq_alloc_desc_at(irq, -1);
-	} else
-		irq = find_unbound_irq();
+	irq = xen_allocate_irq_gsi(gsi);
 
 	set_irq_chip_and_handler_name(irq, &xen_pirq_chip,
 				      handle_level_irq, name);
@@ -658,7 +628,7 @@ int xen_map_pirq_gsi(unsigned pirq, unsigned gsi, int shareable, char *name)
 	 * this in the priv domain. */
 	if (xen_initial_domain() &&
 	    HYPERVISOR_physdev_op(PHYSDEVOP_alloc_irq_vector, &irq_op)) {
-		irq_free_desc(irq);
+		xen_free_irq(irq);
 		irq = -ENOSPC;
 		goto out;
 	}
@@ -674,87 +644,46 @@ out:
 }
 
 #ifdef CONFIG_PCI_MSI
-#include <linux/msi.h>
-#include "../pci/msi.h"
-
-void xen_allocate_pirq_msi(char *name, int *irq, int *pirq, int alloc)
+int xen_allocate_pirq_msi(struct pci_dev *dev, struct msi_desc *msidesc)
 {
-	spin_lock(&irq_mapping_update_lock);
-
-	if (alloc & XEN_ALLOC_IRQ) {
-		*irq = find_unbound_irq();
-		if (*irq == -1)
-			goto out;
-	}
-
-	if (alloc & XEN_ALLOC_PIRQ) {
-		*pirq = find_unbound_pirq(MAP_PIRQ_TYPE_MSI);
-		if (*pirq == -1)
-			goto out;
-	}
+	int rc;
+	struct physdev_get_free_pirq op_get_free_pirq;
 
-	set_irq_chip_and_handler_name(*irq, &xen_pirq_chip,
-				      handle_level_irq, name);
+	op_get_free_pirq.type = MAP_PIRQ_TYPE_MSI;
+	rc = HYPERVISOR_physdev_op(PHYSDEVOP_get_free_pirq, &op_get_free_pirq);
 
-	irq_info[*irq] = mk_pirq_info(0, *pirq, 0, 0);
-	pirq_to_irq[*pirq] = *irq;
+	WARN_ONCE(rc == -ENOSYS,
+		  "hypervisor does not support the PHYSDEVOP_get_free_pirq interface\n");
 
-out:
-	spin_unlock(&irq_mapping_update_lock);
+	return rc ? -1 : op_get_free_pirq.pirq;
 }
 
-int xen_create_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int type)
+int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc,
+			     int pirq, int vector, const char *name)
 {
-	int irq = -1;
-	struct physdev_map_pirq map_irq;
-	int rc;
-	int pos;
-	u32 table_offset, bir;
-
-	memset(&map_irq, 0, sizeof(map_irq));
-	map_irq.domid = DOMID_SELF;
-	map_irq.type = MAP_PIRQ_TYPE_MSI;
-	map_irq.index = -1;
-	map_irq.pirq = -1;
-	map_irq.bus = dev->bus->number;
-	map_irq.devfn = dev->devfn;
-
-	if (type == PCI_CAP_ID_MSIX) {
-		pos = pci_find_capability(dev, PCI_CAP_ID_MSIX);
-
-		pci_read_config_dword(dev, msix_table_offset_reg(pos),
-					&table_offset);
-		bir = (u8)(table_offset & PCI_MSIX_FLAGS_BIRMASK);
-
-		map_irq.table_base = pci_resource_start(dev, bir);
-		map_irq.entry_nr = msidesc->msi_attrib.entry_nr;
-	}
+	int irq, ret;
 
 	spin_lock(&irq_mapping_update_lock);
 
-	irq = find_unbound_irq();
-
+	irq = xen_allocate_irq_dynamic();
 	if (irq == -1)
 		goto out;
 
-	rc = HYPERVISOR_physdev_op(PHYSDEVOP_map_pirq, &map_irq);
-	if (rc) {
-		printk(KERN_WARNING "xen map irq failed %d\n", rc);
-
-		irq_free_desc(irq);
-
-		irq = -1;
-		goto out;
-	}
-	irq_info[irq] = mk_pirq_info(0, map_irq.pirq, 0, map_irq.index);
-
 	set_irq_chip_and_handler_name(irq, &xen_pirq_chip,
-			handle_level_irq,
-			(type == PCI_CAP_ID_MSIX) ? "msi-x":"msi");
+				      handle_level_irq, name);
 
+	irq_info[irq] = mk_pirq_info(0, pirq, 0, vector);
+	pirq_to_irq[pirq] = irq;
+	ret = irq_set_msi_desc(irq, msidesc);
+	if (ret < 0)
+		goto error_irq;
 out:
 	spin_unlock(&irq_mapping_update_lock);
 	return irq;
+error_irq:
+	spin_unlock(&irq_mapping_update_lock);
+	xen_free_irq(irq);
+	return -1;
 }
 #endif
 
@@ -779,11 +708,12 @@ int xen_destroy_irq(int irq)
 			printk(KERN_WARNING "unmap irq failed %d\n", rc);
 			goto out;
 		}
-		pirq_to_irq[info->u.pirq.pirq] = -1;
 	}
+	pirq_to_irq[info->u.pirq.pirq] = -1;
+
 	irq_info[irq] = mk_unbound_info();
 
-	irq_free_desc(irq);
+	xen_free_irq(irq);
 
 out:
 	spin_unlock(&irq_mapping_update_lock);
@@ -814,7 +744,7 @@ int bind_evtchn_to_irq(unsigned int evtchn)
 	irq = evtchn_to_irq[evtchn];
 
 	if (irq == -1) {
-		irq = find_unbound_irq();
+		irq = xen_allocate_irq_dynamic();
 
 		set_irq_chip_and_handler_name(irq, &xen_dynamic_chip,
 					      handle_fasteoi_irq, "event");
@@ -839,7 +769,7 @@ static int bind_ipi_to_irq(unsigned int ipi, unsigned int cpu)
 	irq = per_cpu(ipi_to_irq, cpu)[ipi];
 
 	if (irq == -1) {
-		irq = find_unbound_irq();
+		irq = xen_allocate_irq_dynamic();
 		if (irq < 0)
 			goto out;
 
@@ -875,7 +805,7 @@ int bind_virq_to_irq(unsigned int virq, unsigned int cpu)
 	irq = per_cpu(virq_to_irq, cpu)[virq];
 
 	if (irq == -1) {
-		irq = find_unbound_irq();
+		irq = xen_allocate_irq_dynamic();
 
 		set_irq_chip_and_handler_name(irq, &xen_percpu_chip,
 					      handle_percpu_irq, "virq");
@@ -934,7 +864,7 @@ static void unbind_from_irq(unsigned int irq)
 	if (irq_info[irq].type != IRQT_UNBOUND) {
 		irq_info[irq] = mk_unbound_info();
 
-		irq_free_desc(irq);
+		xen_free_irq(irq);
 	}
 
 	spin_unlock(&irq_mapping_update_lock);
@@ -990,7 +920,7 @@ int bind_ipi_to_irqhandler(enum ipi_vector ipi,
 	if (irq < 0)
 		return irq;
 
-	irqflags |= IRQF_NO_SUSPEND;
+	irqflags |= IRQF_NO_SUSPEND | IRQF_FORCE_RESUME;
 	retval = request_irq(irq, handler, irqflags, devname, dev_id);
 	if (retval != 0) {
 		unbind_from_irq(irq);
@@ -1234,11 +1164,12 @@ static int rebind_irq_to_cpu(unsigned irq, unsigned tcpu)
 	return 0;
 }
 
-static int set_affinity_irq(unsigned irq, const struct cpumask *dest)
+static int set_affinity_irq(struct irq_data *data, const struct cpumask *dest,
+			    bool force)
 {
 	unsigned tcpu = cpumask_first(dest);
 
-	return rebind_irq_to_cpu(irq, tcpu);
+	return rebind_irq_to_cpu(data->irq, tcpu);
 }
 
 int resend_irq_on_evtchn(unsigned int irq)
@@ -1257,35 +1188,35 @@ int resend_irq_on_evtchn(unsigned int irq)
 	return 1;
 }
 
-static void enable_dynirq(unsigned int irq)
+static void enable_dynirq(struct irq_data *data)
 {
-	int evtchn = evtchn_from_irq(irq);
+	int evtchn = evtchn_from_irq(data->irq);
 
 	if (VALID_EVTCHN(evtchn))
 		unmask_evtchn(evtchn);
 }
 
-static void disable_dynirq(unsigned int irq)
+static void disable_dynirq(struct irq_data *data)
 {
-	int evtchn = evtchn_from_irq(irq);
+	int evtchn = evtchn_from_irq(data->irq);
 
 	if (VALID_EVTCHN(evtchn))
 		mask_evtchn(evtchn);
 }
 
-static void ack_dynirq(unsigned int irq)
+static void ack_dynirq(struct irq_data *data)
 {
-	int evtchn = evtchn_from_irq(irq);
+	int evtchn = evtchn_from_irq(data->irq);
 
-	move_masked_irq(irq);
+	move_masked_irq(data->irq);
 
 	if (VALID_EVTCHN(evtchn))
 		unmask_evtchn(evtchn);
 }
 
-static int retrigger_dynirq(unsigned int irq)
+static int retrigger_dynirq(struct irq_data *data)
 {
-	int evtchn = evtchn_from_irq(irq);
+	int evtchn = evtchn_from_irq(data->irq);
 	struct shared_info *sh = HYPERVISOR_shared_info;
 	int ret = 0;
 
@@ -1334,7 +1265,7 @@ static void restore_cpu_pirqs(void)
 
 		printk(KERN_DEBUG "xen: --> irq=%d, pirq=%d\n", irq, map_irq.pirq);
 
-		startup_pirq(irq);
+		__startup_pirq(irq);
 	}
 }
 
@@ -1445,7 +1376,6 @@ void xen_poll_irq(int irq)
 void xen_irq_resume(void)
 {
 	unsigned int cpu, irq, evtchn;
-	struct irq_desc *desc;
 
 	init_evtchn_cpu_bindings();
 
@@ -1465,66 +1395,48 @@ void xen_irq_resume(void)
 		restore_cpu_ipis(cpu);
 	}
 
-	/*
-	 * Unmask any IRQF_NO_SUSPEND IRQs which are enabled. These
-	 * are not handled by the IRQ core.
-	 */
-	for_each_irq_desc(irq, desc) {
-		if (!desc->action || !(desc->action->flags & IRQF_NO_SUSPEND))
-			continue;
-		if (desc->status & IRQ_DISABLED)
-			continue;
-
-		evtchn = evtchn_from_irq(irq);
-		if (evtchn == -1)
-			continue;
-
-		unmask_evtchn(evtchn);
-	}
-
 	restore_cpu_pirqs();
 }
 
 static struct irq_chip xen_dynamic_chip __read_mostly = {
-	.name		= "xen-dyn",
+	.name			= "xen-dyn",
 
-	.disable	= disable_dynirq,
-	.mask		= disable_dynirq,
-	.unmask		= enable_dynirq,
+	.irq_disable		= disable_dynirq,
+	.irq_mask		= disable_dynirq,
+	.irq_unmask		= enable_dynirq,
 
-	.eoi		= ack_dynirq,
-	.set_affinity	= set_affinity_irq,
-	.retrigger	= retrigger_dynirq,
+	.irq_eoi		= ack_dynirq,
+	.irq_set_affinity	= set_affinity_irq,
+	.irq_retrigger		= retrigger_dynirq,
 };
 
 static struct irq_chip xen_pirq_chip __read_mostly = {
-	.name		= "xen-pirq",
+	.name			= "xen-pirq",
 
-	.startup	= startup_pirq,
-	.shutdown	= shutdown_pirq,
+	.irq_startup		= startup_pirq,
+	.irq_shutdown		= shutdown_pirq,
 
-	.enable		= enable_pirq,
-	.unmask		= enable_pirq,
+	.irq_enable		= enable_pirq,
+	.irq_unmask		= enable_pirq,
 
-	.disable	= disable_pirq,
-	.mask		= disable_pirq,
+	.irq_disable		= disable_pirq,
+	.irq_mask		= disable_pirq,
 
-	.ack		= ack_pirq,
-	.end		= end_pirq,
+	.irq_ack		= ack_pirq,
 
-	.set_affinity	= set_affinity_irq,
+	.irq_set_affinity	= set_affinity_irq,
 
-	.retrigger	= retrigger_dynirq,
+	.irq_retrigger		= retrigger_dynirq,
 };
 
 static struct irq_chip xen_percpu_chip __read_mostly = {
-	.name		= "xen-percpu",
+	.name			= "xen-percpu",
 
-	.disable	= disable_dynirq,
-	.mask		= disable_dynirq,
-	.unmask		= enable_dynirq,
+	.irq_disable		= disable_dynirq,
+	.irq_mask		= disable_dynirq,
+	.irq_unmask		= enable_dynirq,
 
-	.ack		= ack_dynirq,
+	.irq_ack		= ack_dynirq,
 };
 
 int xen_set_callback_via(uint64_t via)
diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c
index 24177272bcb8..ebb292859b59 100644
--- a/drivers/xen/manage.c
+++ b/drivers/xen/manage.c
@@ -34,42 +34,38 @@ enum shutdown_state {
 /* Ignore multiple shutdown requests. */
 static enum shutdown_state shutting_down = SHUTDOWN_INVALID;
 
-#ifdef CONFIG_PM_SLEEP
-static int xen_hvm_suspend(void *data)
-{
-	int err;
-	struct sched_shutdown r = { .reason = SHUTDOWN_suspend };
-	int *cancelled = data;
-
-	BUG_ON(!irqs_disabled());
-
-	err = sysdev_suspend(PMSG_SUSPEND);
-	if (err) {
-		printk(KERN_ERR "xen_hvm_suspend: sysdev_suspend failed: %d\n",
-		       err);
-		return err;
-	}
-
-	*cancelled = HYPERVISOR_sched_op(SCHEDOP_shutdown, &r);
+struct suspend_info {
+	int cancelled;
+	unsigned long arg; /* extra hypercall argument */
+	void (*pre)(void);
+	void (*post)(int cancelled);
+};
 
-	xen_hvm_post_suspend(*cancelled);
+static void xen_hvm_post_suspend(int cancelled)
+{
+	xen_arch_hvm_post_suspend(cancelled);
 	gnttab_resume();
+}
 
-	if (!*cancelled) {
-		xen_irq_resume();
-		xen_console_resume();
-		xen_timer_resume();
-	}
-
-	sysdev_resume();
+static void xen_pre_suspend(void)
+{
+	xen_mm_pin_all();
+	gnttab_suspend();
+	xen_arch_pre_suspend();
+}
 
-	return 0;
+static void xen_post_suspend(int cancelled)
+{
+	xen_arch_post_suspend(cancelled);
+	gnttab_resume();
+	xen_mm_unpin_all();
 }
 
+#ifdef CONFIG_PM_SLEEP
 static int xen_suspend(void *data)
 {
+	struct suspend_info *si = data;
 	int err;
-	int *cancelled = data;
 
 	BUG_ON(!irqs_disabled());
 
@@ -80,22 +76,20 @@ static int xen_suspend(void *data)
 		return err;
 	}
 
-	xen_mm_pin_all();
-	gnttab_suspend();
-	xen_pre_suspend();
+	if (si->pre)
+		si->pre();
 
 	/*
 	 * This hypercall returns 1 if suspend was cancelled
 	 * or the domain was merely checkpointed, and 0 if it
 	 * is resuming in a new domain.
 	 */
-	*cancelled = HYPERVISOR_suspend(virt_to_mfn(xen_start_info));
+	si->cancelled = HYPERVISOR_suspend(si->arg);
 
-	xen_post_suspend(*cancelled);
-	gnttab_resume();
-	xen_mm_unpin_all();
+	if (si->post)
+		si->post(si->cancelled);
 
-	if (!*cancelled) {
+	if (!si->cancelled) {
 		xen_irq_resume();
 		xen_console_resume();
 		xen_timer_resume();
@@ -109,7 +103,7 @@ static int xen_suspend(void *data)
 static void do_suspend(void)
 {
 	int err;
-	int cancelled = 1;
+	struct suspend_info si;
 
 	shutting_down = SHUTDOWN_SUSPEND;
 
@@ -139,20 +133,29 @@ static void do_suspend(void)
 		goto out_resume;
 	}
 
-	if (xen_hvm_domain())
-		err = stop_machine(xen_hvm_suspend, &cancelled, cpumask_of(0));
-	else
-		err = stop_machine(xen_suspend, &cancelled, cpumask_of(0));
+	si.cancelled = 1;
+
+	if (xen_hvm_domain()) {
+		si.arg = 0UL;
+		si.pre = NULL;
+		si.post = &xen_hvm_post_suspend;
+	} else {
+		si.arg = virt_to_mfn(xen_start_info);
+		si.pre = &xen_pre_suspend;
+		si.post = &xen_post_suspend;
+	}
+
+	err = stop_machine(xen_suspend, &si, cpumask_of(0));
 
 	dpm_resume_noirq(PMSG_RESUME);
 
 	if (err) {
 		printk(KERN_ERR "failed to start xen_suspend: %d\n", err);
-		cancelled = 1;
+		si.cancelled = 1;
 	}
 
 out_resume:
-	if (!cancelled) {
+	if (!si.cancelled) {
 		xen_arch_resume();
 		xs_resume();
 	} else
@@ -172,12 +175,39 @@ out:
 }
 #endif	/* CONFIG_PM_SLEEP */
 
+struct shutdown_handler {
+	const char *command;
+	void (*cb)(void);
+};
+
+static void do_poweroff(void)
+{
+	shutting_down = SHUTDOWN_POWEROFF;
+	orderly_poweroff(false);
+}
+
+static void do_reboot(void)
+{
+	shutting_down = SHUTDOWN_POWEROFF; /* ? */
+	ctrl_alt_del();
+}
+
 static void shutdown_handler(struct xenbus_watch *watch,
 			     const char **vec, unsigned int len)
 {
 	char *str;
 	struct xenbus_transaction xbt;
 	int err;
+	static struct shutdown_handler handlers[] = {
+		{ "poweroff",	do_poweroff },
+		{ "halt",	do_poweroff },
+		{ "reboot",	do_reboot   },
+#ifdef CONFIG_PM_SLEEP
+		{ "suspend",	do_suspend  },
+#endif
+		{NULL, NULL},
+	};
+	static struct shutdown_handler *handler;
 
 	if (shutting_down != SHUTDOWN_INVALID)
 		return;
@@ -194,7 +224,14 @@ static void shutdown_handler(struct xenbus_watch *watch,
 		return;
 	}
 
-	xenbus_write(xbt, "control", "shutdown", "");
+	for (handler = &handlers[0]; handler->command; handler++) {
+		if (strcmp(str, handler->command) == 0)
+			break;
+	}
+
+	/* Only acknowledge commands which we are prepared to handle. */
+	if (handler->cb)
+		xenbus_write(xbt, "control", "shutdown", "");
 
 	err = xenbus_transaction_end(xbt, 0);
 	if (err == -EAGAIN) {
@@ -202,17 +239,8 @@ static void shutdown_handler(struct xenbus_watch *watch,
 		goto again;
 	}
 
-	if (strcmp(str, "poweroff") == 0 ||
-	    strcmp(str, "halt") == 0) {
-		shutting_down = SHUTDOWN_POWEROFF;
-		orderly_poweroff(false);
-	} else if (strcmp(str, "reboot") == 0) {
-		shutting_down = SHUTDOWN_POWEROFF; /* ? */
-		ctrl_alt_del();
-#ifdef CONFIG_PM_SLEEP
-	} else if (strcmp(str, "suspend") == 0) {
-		do_suspend();
-#endif
+	if (handler->cb) {
+		handler->cb();
 	} else {
 		printk(KERN_INFO "Ignoring shutdown request: %s\n", str);
 		shutting_down = SHUTDOWN_INVALID;
@@ -291,27 +319,18 @@ static int shutdown_event(struct notifier_block *notifier,
 	return NOTIFY_DONE;
 }
 
-static int __init __setup_shutdown_event(void)
-{
-	/* Delay initialization in the PV on HVM case */
-	if (xen_hvm_domain())
-		return 0;
-
-	if (!xen_pv_domain())
-		return -ENODEV;
-
-	return xen_setup_shutdown_event();
-}
-
 int xen_setup_shutdown_event(void)
 {
 	static struct notifier_block xenstore_notifier = {
 		.notifier_call = shutdown_event
 	};
+
+	if (!xen_domain())
+		return -ENODEV;
 	register_xenstore_notifier(&xenstore_notifier);
 
 	return 0;
 }
 EXPORT_SYMBOL_GPL(xen_setup_shutdown_event);
 
-subsys_initcall(__setup_shutdown_event);
+subsys_initcall(xen_setup_shutdown_event);
diff --git a/drivers/xen/platform-pci.c b/drivers/xen/platform-pci.c
index afbe041f42c5..319dd0a94d51 100644
--- a/drivers/xen/platform-pci.c
+++ b/drivers/xen/platform-pci.c
@@ -156,9 +156,6 @@ static int __devinit platform_pci_init(struct pci_dev *pdev,
 	if (ret)
 		goto out;
 	xenbus_probe(NULL);
-	ret = xen_setup_shutdown_event();
-	if (ret)
-		goto out;
 	return 0;
 
 out:
diff --git a/fs/Kconfig b/fs/Kconfig
index 3db9caa57edc..7cb53aafac1e 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -47,7 +47,7 @@ config FS_POSIX_ACL
 	def_bool n
 
 config EXPORTFS
-	tristate
+	bool
 
 config FILE_LOCKING
 	bool "Enable POSIX file locking API" if EXPERT
diff --git a/fs/Makefile b/fs/Makefile
index a7f7cef0c0c8..ba01202844c5 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -48,6 +48,8 @@ obj-$(CONFIG_FS_POSIX_ACL)	+= posix_acl.o xattr_acl.o
 obj-$(CONFIG_NFS_COMMON)	+= nfs_common/
 obj-$(CONFIG_GENERIC_ACL)	+= generic_acl.o
 
+obj-$(CONFIG_FHANDLE)		+= fhandle.o
+
 obj-y				+= quota/
 
 obj-$(CONFIG_PROC_FS)		+= proc/
diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c
index ff27d7a477b2..b4ffad859adb 100644
--- a/fs/btrfs/export.c
+++ b/fs/btrfs/export.c
@@ -21,9 +21,13 @@ static int btrfs_encode_fh(struct dentry *dentry, u32 *fh, int *max_len,
 	int len = *max_len;
 	int type;
 
-	if ((len < BTRFS_FID_SIZE_NON_CONNECTABLE) ||
-	    (connectable && len < BTRFS_FID_SIZE_CONNECTABLE))
+	if (connectable && (len < BTRFS_FID_SIZE_CONNECTABLE)) {
+		*max_len = BTRFS_FID_SIZE_CONNECTABLE;
 		return 255;
+	} else if (len < BTRFS_FID_SIZE_NON_CONNECTABLE) {
+		*max_len = BTRFS_FID_SIZE_NON_CONNECTABLE;
+		return 255;
+	}
 
 	len  = BTRFS_FID_SIZE_NON_CONNECTABLE;
 	type = FILEID_BTRFS_WITHOUT_PARENT;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 9007bbd01dbf..4a0107e18747 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4806,9 +4806,6 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
 	int err;
 	int drop_inode = 0;
 
-	if (inode->i_nlink == 0)
-		return -ENOENT;
-
 	/* do not allow sys_link's with other subvols of the same device */
 	if (root->objectid != BTRFS_I(inode)->root->objectid)
 		return -EPERM;
diff --git a/fs/compat.c b/fs/compat.c
index 691c3fd8ce1d..c6d31a3bab88 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -262,35 +262,19 @@ static int put_compat_statfs(struct compat_statfs __user *ubuf, struct kstatfs *
  */
 asmlinkage long compat_sys_statfs(const char __user *pathname, struct compat_statfs __user *buf)
 {
-	struct path path;
-	int error;
-
-	error = user_path(pathname, &path);
-	if (!error) {
-		struct kstatfs tmp;
-		error = vfs_statfs(&path, &tmp);
-		if (!error)
-			error = put_compat_statfs(buf, &tmp);
-		path_put(&path);
-	}
+	struct kstatfs tmp;
+	int error = user_statfs(pathname, &tmp);
+	if (!error)
+		error = put_compat_statfs(buf, &tmp);
 	return error;
 }
 
 asmlinkage long compat_sys_fstatfs(unsigned int fd, struct compat_statfs __user *buf)
 {
-	struct file * file;
 	struct kstatfs tmp;
-	int error;
-
-	error = -EBADF;
-	file = fget(fd);
-	if (!file)
-		goto out;
-	error = vfs_statfs(&file->f_path, &tmp);
+	int error = fd_statfs(fd, &tmp);
 	if (!error)
 		error = put_compat_statfs(buf, &tmp);
-	fput(file);
-out:
 	return error;
 }
 
@@ -329,41 +313,29 @@ static int put_compat_statfs64(struct compat_statfs64 __user *ubuf, struct kstat
 
 asmlinkage long compat_sys_statfs64(const char __user *pathname, compat_size_t sz, struct compat_statfs64 __user *buf)
 {
-	struct path path;
+	struct kstatfs tmp;
 	int error;
 
 	if (sz != sizeof(*buf))
 		return -EINVAL;
 
-	error = user_path(pathname, &path);
-	if (!error) {
-		struct kstatfs tmp;
-		error = vfs_statfs(&path, &tmp);
-		if (!error)
-			error = put_compat_statfs64(buf, &tmp);
-		path_put(&path);
-	}
+	error = user_statfs(pathname, &tmp);
+	if (!error)
+		error = put_compat_statfs64(buf, &tmp);
 	return error;
 }
 
 asmlinkage long compat_sys_fstatfs64(unsigned int fd, compat_size_t sz, struct compat_statfs64 __user *buf)
 {
-	struct file * file;
 	struct kstatfs tmp;
 	int error;
 
 	if (sz != sizeof(*buf))
 		return -EINVAL;
 
-	error = -EBADF;
-	file = fget(fd);
-	if (!file)
-		goto out;
-	error = vfs_statfs(&file->f_path, &tmp);
+	error = fd_statfs(fd, &tmp);
 	if (!error)
 		error = put_compat_statfs64(buf, &tmp);
-	fput(file);
-out:
 	return error;
 }
 
@@ -2312,3 +2284,16 @@ asmlinkage long compat_sys_timerfd_gettime(int ufd,
 }
 
 #endif /* CONFIG_TIMERFD */
+
+#ifdef CONFIG_FHANDLE
+/*
+ * Exactly like fs/open.c:sys_open_by_handle_at(), except that it
+ * doesn't set the O_LARGEFILE flag.
+ */
+asmlinkage long
+compat_sys_open_by_handle_at(int mountdirfd,
+			     struct file_handle __user *handle, int flags)
+{
+	return do_handle_open(mountdirfd, handle, flags);
+}
+#endif
diff --git a/fs/dcache.c b/fs/dcache.c
index 611ffe928c03..a39fe47c466f 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -296,8 +296,12 @@ static struct dentry *d_kill(struct dentry *dentry, struct dentry *parent)
 	__releases(parent->d_lock)
 	__releases(dentry->d_inode->i_lock)
 {
-	dentry->d_parent = NULL;
 	list_del(&dentry->d_u.d_child);
+	/*
+	 * Inform try_to_ascend() that we are no longer attached to the
+	 * dentry tree
+	 */
+	dentry->d_flags |= DCACHE_DISCONNECTED;
 	if (parent)
 		spin_unlock(&parent->d_lock);
 	dentry_iput(dentry);
@@ -1012,6 +1016,35 @@ void shrink_dcache_for_umount(struct super_block *sb)
 }
 
 /*
+ * This tries to ascend one level of parenthood, but
+ * we can race with renaming, so we need to re-check
+ * the parenthood after dropping the lock and check
+ * that the sequence number still matches.
+ */
+static struct dentry *try_to_ascend(struct dentry *old, int locked, unsigned seq)
+{
+	struct dentry *new = old->d_parent;
+
+	rcu_read_lock();
+	spin_unlock(&old->d_lock);
+	spin_lock(&new->d_lock);
+
+	/*
+	 * might go back up the wrong parent if we have had a rename
+	 * or deletion
+	 */
+	if (new != old->d_parent ||
+		 (old->d_flags & DCACHE_DISCONNECTED) ||
+		 (!locked && read_seqretry(&rename_lock, seq))) {
+		spin_unlock(&new->d_lock);
+		new = NULL;
+	}
+	rcu_read_unlock();
+	return new;
+}
+
+
+/*
  * Search for at least 1 mount point in the dentry's subdirs.
  * We descend to the next level whenever the d_subdirs
  * list is non-empty and continue searching.
@@ -1066,24 +1099,10 @@ resume:
 	 * All done at this level ... ascend and resume the search.
 	 */
 	if (this_parent != parent) {
-		struct dentry *tmp;
-		struct dentry *child;
-
-		tmp = this_parent->d_parent;
-		rcu_read_lock();
-		spin_unlock(&this_parent->d_lock);
-		child = this_parent;
-		this_parent = tmp;
-		spin_lock(&this_parent->d_lock);
-		/* might go back up the wrong parent if we have had a rename
-		 * or deletion */
-		if (this_parent != child->d_parent ||
-			 (!locked && read_seqretry(&rename_lock, seq))) {
-			spin_unlock(&this_parent->d_lock);
-			rcu_read_unlock();
+		struct dentry *child = this_parent;
+		this_parent = try_to_ascend(this_parent, locked, seq);
+		if (!this_parent)
 			goto rename_retry;
-		}
-		rcu_read_unlock();
 		next = child->d_u.d_child.next;
 		goto resume;
 	}
@@ -1181,24 +1200,10 @@ resume:
 	 * All done at this level ... ascend and resume the search.
 	 */
 	if (this_parent != parent) {
-		struct dentry *tmp;
-		struct dentry *child;
-
-		tmp = this_parent->d_parent;
-		rcu_read_lock();
-		spin_unlock(&this_parent->d_lock);
-		child = this_parent;
-		this_parent = tmp;
-		spin_lock(&this_parent->d_lock);
-		/* might go back up the wrong parent if we have had a rename
-		 * or deletion */
-		if (this_parent != child->d_parent ||
-			(!locked && read_seqretry(&rename_lock, seq))) {
-			spin_unlock(&this_parent->d_lock);
-			rcu_read_unlock();
+		struct dentry *child = this_parent;
+		this_parent = try_to_ascend(this_parent, locked, seq);
+		if (!this_parent)
 			goto rename_retry;
-		}
-		rcu_read_unlock();
 		next = child->d_u.d_child.next;
 		goto resume;
 	}
@@ -2942,28 +2947,14 @@ resume:
 		spin_unlock(&dentry->d_lock);
 	}
 	if (this_parent != root) {
-		struct dentry *tmp;
-		struct dentry *child;
-
-		tmp = this_parent->d_parent;
+		struct dentry *child = this_parent;
 		if (!(this_parent->d_flags & DCACHE_GENOCIDE)) {
 			this_parent->d_flags |= DCACHE_GENOCIDE;
 			this_parent->d_count--;
 		}
-		rcu_read_lock();
-		spin_unlock(&this_parent->d_lock);
-		child = this_parent;
-		this_parent = tmp;
-		spin_lock(&this_parent->d_lock);
-		/* might go back up the wrong parent if we have had a rename
-		 * or deletion */
-		if (this_parent != child->d_parent ||
-			 (!locked && read_seqretry(&rename_lock, seq))) {
-			spin_unlock(&this_parent->d_lock);
-			rcu_read_unlock();
+		this_parent = try_to_ascend(this_parent, locked, seq);
+		if (!this_parent)
 			goto rename_retry;
-		}
-		rcu_read_unlock();
 		next = child->d_u.d_child.next;
 		goto resume;
 	}
diff --git a/fs/exec.c b/fs/exec.c
index 52a447d9b6ab..ba99e1abb1aa 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -115,13 +115,16 @@ SYSCALL_DEFINE1(uselib, const char __user *, library)
 	struct file *file;
 	char *tmp = getname(library);
 	int error = PTR_ERR(tmp);
+	static const struct open_flags uselib_flags = {
+		.open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC,
+		.acc_mode = MAY_READ | MAY_EXEC | MAY_OPEN,
+		.intent = LOOKUP_OPEN
+	};
 
 	if (IS_ERR(tmp))
 		goto out;
 
-	file = do_filp_open(AT_FDCWD, tmp,
-				O_LARGEFILE | O_RDONLY | __FMODE_EXEC, 0,
-				MAY_READ | MAY_EXEC | MAY_OPEN);
+	file = do_filp_open(AT_FDCWD, tmp, &uselib_flags, LOOKUP_FOLLOW);
 	putname(tmp);
 	error = PTR_ERR(file);
 	if (IS_ERR(file))
@@ -721,10 +724,13 @@ struct file *open_exec(const char *name)
 {
 	struct file *file;
 	int err;
+	static const struct open_flags open_exec_flags = {
+		.open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC,
+		.acc_mode = MAY_EXEC | MAY_OPEN,
+		.intent = LOOKUP_OPEN
+	};
 
-	file = do_filp_open(AT_FDCWD, name,
-				O_LARGEFILE | O_RDONLY | __FMODE_EXEC, 0,
-				MAY_EXEC | MAY_OPEN);
+	file = do_filp_open(AT_FDCWD, name, &open_exec_flags, LOOKUP_FOLLOW);
 	if (IS_ERR(file))
 		goto out;
 
diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c
index 4b6825740dd5..b05acb796135 100644
--- a/fs/exportfs/expfs.c
+++ b/fs/exportfs/expfs.c
@@ -320,9 +320,14 @@ static int export_encode_fh(struct dentry *dentry, struct fid *fid,
 	struct inode * inode = dentry->d_inode;
 	int len = *max_len;
 	int type = FILEID_INO32_GEN;
-	
-	if (len < 2 || (connectable && len < 4))
+
+	if (connectable && (len < 4)) {
+		*max_len = 4;
+		return 255;
+	} else if (len < 2) {
+		*max_len = 2;
 		return 255;
+	}
 
 	len = 2;
 	fid->i32.ino = inode->i_ino;
@@ -369,6 +374,8 @@ struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid,
 	/*
 	 * Try to get any dentry for the given file handle from the filesystem.
 	 */
+	if (!nop || !nop->fh_to_dentry)
+		return ERR_PTR(-ESTALE);
 	result = nop->fh_to_dentry(mnt->mnt_sb, fid, fh_len, fileid_type);
 	if (!result)
 		result = ERR_PTR(-ESTALE);
diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c
index b27ba71810ec..561f69256266 100644
--- a/fs/ext3/namei.c
+++ b/fs/ext3/namei.c
@@ -2253,13 +2253,6 @@ static int ext3_link (struct dentry * old_dentry,
 
 	dquot_initialize(dir);
 
-	/*
-	 * Return -ENOENT if we've raced with unlink and i_nlink is 0.  Doing
-	 * otherwise has the potential to corrupt the orphan inode list.
-	 */
-	if (inode->i_nlink == 0)
-		return -ENOENT;
-
 retry:
 	handle = ext3_journal_start(dir, EXT3_DATA_TRANS_BLOCKS(dir->i_sb) +
 					EXT3_INDEX_EXTRA_TRANS_BLOCKS);
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index 85c8cc8f2473..9cc19a1dea8e 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -1936,6 +1936,7 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent)
 	sb->s_qcop = &ext3_qctl_operations;
 	sb->dq_op = &ext3_quota_operations;
 #endif
+	memcpy(sb->s_uuid, es->s_uuid, sizeof(es->s_uuid));
 	INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */
 	mutex_init(&sbi->s_orphan_lock);
 	mutex_init(&sbi->s_resize_lock);
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 5485390d32c5..e781b7ea5630 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -2304,13 +2304,6 @@ static int ext4_link(struct dentry *old_dentry,
 
 	dquot_initialize(dir);
 
-	/*
-	 * Return -ENOENT if we've raced with unlink and i_nlink is 0.  Doing
-	 * otherwise has the potential to corrupt the orphan inode list.
-	 */
-	if (inode->i_nlink == 0)
-		return -ENOENT;
-
 retry:
 	handle = ext4_journal_start(dir, EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
 					EXT4_INDEX_EXTRA_TRANS_BLOCKS);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index f6a318f836b2..5977b356a435 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -3415,6 +3415,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	sb->s_qcop = &ext4_qctl_operations;
 	sb->dq_op = &ext4_quota_operations;
 #endif
+	memcpy(sb->s_uuid, es->s_uuid, sizeof(es->s_uuid));
+
 	INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */
 	mutex_init(&sbi->s_orphan_lock);
 	mutex_init(&sbi->s_resize_lock);
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 86753fe10bd1..0e277ec4b612 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -757,8 +757,10 @@ fat_encode_fh(struct dentry *de, __u32 *fh, int *lenp, int connectable)
 	struct inode *inode =  de->d_inode;
 	u32 ipos_h, ipos_m, ipos_l;
 
-	if (len < 5)
+	if (len < 5) {
+		*lenp = 5;
 		return 255; /* no room */
+	}
 
 	ipos_h = MSDOS_I(inode)->i_pos >> 8;
 	ipos_m = (MSDOS_I(inode)->i_pos & 0xf0) << 24;
diff --git a/fs/fcntl.c b/fs/fcntl.c
index cb1026181bdc..6c82e5bac039 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -131,7 +131,7 @@ SYSCALL_DEFINE2(dup2, unsigned int, oldfd, unsigned int, newfd)
 SYSCALL_DEFINE1(dup, unsigned int, fildes)
 {
 	int ret = -EBADF;
-	struct file *file = fget(fildes);
+	struct file *file = fget_raw(fildes);
 
 	if (file) {
 		ret = get_unused_fd();
@@ -426,15 +426,35 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
 	return err;
 }
 
+static int check_fcntl_cmd(unsigned cmd)
+{
+	switch (cmd) {
+	case F_DUPFD:
+	case F_DUPFD_CLOEXEC:
+	case F_GETFD:
+	case F_SETFD:
+	case F_GETFL:
+		return 1;
+	}
+	return 0;
+}
+
 SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, unsigned long, arg)
 {	
 	struct file *filp;
 	long err = -EBADF;
 
-	filp = fget(fd);
+	filp = fget_raw(fd);
 	if (!filp)
 		goto out;
 
+	if (unlikely(filp->f_mode & FMODE_PATH)) {
+		if (!check_fcntl_cmd(cmd)) {
+			fput(filp);
+			goto out;
+		}
+	}
+
 	err = security_file_fcntl(filp, cmd, arg);
 	if (err) {
 		fput(filp);
@@ -456,10 +476,17 @@ SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd,
 	long err;
 
 	err = -EBADF;
-	filp = fget(fd);
+	filp = fget_raw(fd);
 	if (!filp)
 		goto out;
 
+	if (unlikely(filp->f_mode & FMODE_PATH)) {
+		if (!check_fcntl_cmd(cmd)) {
+			fput(filp);
+			goto out;
+		}
+	}
+
 	err = security_file_fcntl(filp, cmd, arg);
 	if (err) {
 		fput(filp);
@@ -808,14 +835,14 @@ static int __init fcntl_init(void)
 	 * Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY
 	 * is defined as O_NONBLOCK on some platforms and not on others.
 	 */
-	BUILD_BUG_ON(18 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32(
+	BUILD_BUG_ON(19 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32(
 		O_RDONLY	| O_WRONLY	| O_RDWR	|
 		O_CREAT		| O_EXCL	| O_NOCTTY	|
 		O_TRUNC		| O_APPEND	| /* O_NONBLOCK	| */
 		__O_SYNC	| O_DSYNC	| FASYNC	|
 		O_DIRECT	| O_LARGEFILE	| O_DIRECTORY	|
 		O_NOFOLLOW	| O_NOATIME	| O_CLOEXEC	|
-		__FMODE_EXEC
+		__FMODE_EXEC	| O_PATH
 		));
 
 	fasync_cache = kmem_cache_create("fasync_cache",
diff --git a/fs/fhandle.c b/fs/fhandle.c
new file mode 100644
index 000000000000..bf93ad2bee07
--- /dev/null
+++ b/fs/fhandle.c
@@ -0,0 +1,265 @@
+#include <linux/syscalls.h>
+#include <linux/slab.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/mount.h>
+#include <linux/namei.h>
+#include <linux/exportfs.h>
+#include <linux/fs_struct.h>
+#include <linux/fsnotify.h>
+#include <asm/uaccess.h>
+#include "internal.h"
+
+static long do_sys_name_to_handle(struct path *path,
+				  struct file_handle __user *ufh,
+				  int __user *mnt_id)
+{
+	long retval;
+	struct file_handle f_handle;
+	int handle_dwords, handle_bytes;
+	struct file_handle *handle = NULL;
+
+	/*
+	 * We need t make sure wether the file system
+	 * support decoding of the file handle
+	 */
+	if (!path->mnt->mnt_sb->s_export_op ||
+	    !path->mnt->mnt_sb->s_export_op->fh_to_dentry)
+		return -EOPNOTSUPP;
+
+	if (copy_from_user(&f_handle, ufh, sizeof(struct file_handle)))
+		return -EFAULT;
+
+	if (f_handle.handle_bytes > MAX_HANDLE_SZ)
+		return -EINVAL;
+
+	handle = kmalloc(sizeof(struct file_handle) + f_handle.handle_bytes,
+			 GFP_KERNEL);
+	if (!handle)
+		return -ENOMEM;
+
+	/* convert handle size to  multiple of sizeof(u32) */
+	handle_dwords = f_handle.handle_bytes >> 2;
+
+	/* we ask for a non connected handle */
+	retval = exportfs_encode_fh(path->dentry,
+				    (struct fid *)handle->f_handle,
+				    &handle_dwords,  0);
+	handle->handle_type = retval;
+	/* convert handle size to bytes */
+	handle_bytes = handle_dwords * sizeof(u32);
+	handle->handle_bytes = handle_bytes;
+	if ((handle->handle_bytes > f_handle.handle_bytes) ||
+	    (retval == 255) || (retval == -ENOSPC)) {
+		/* As per old exportfs_encode_fh documentation
+		 * we could return ENOSPC to indicate overflow
+		 * But file system returned 255 always. So handle
+		 * both the values
+		 */
+		/*
+		 * set the handle size to zero so we copy only
+		 * non variable part of the file_handle
+		 */
+		handle_bytes = 0;
+		retval = -EOVERFLOW;
+	} else
+		retval = 0;
+	/* copy the mount id */
+	if (copy_to_user(mnt_id, &path->mnt->mnt_id, sizeof(*mnt_id)) ||
+	    copy_to_user(ufh, handle,
+			 sizeof(struct file_handle) + handle_bytes))
+		retval = -EFAULT;
+	kfree(handle);
+	return retval;
+}
+
+/**
+ * sys_name_to_handle_at: convert name to handle
+ * @dfd: directory relative to which name is interpreted if not absolute
+ * @name: name that should be converted to handle.
+ * @handle: resulting file handle
+ * @mnt_id: mount id of the file system containing the file
+ * @flag: flag value to indicate whether to follow symlink or not
+ *
+ * @handle->handle_size indicate the space available to store the
+ * variable part of the file handle in bytes. If there is not
+ * enough space, the field is updated to return the minimum
+ * value required.
+ */
+SYSCALL_DEFINE5(name_to_handle_at, int, dfd, const char __user *, name,
+		struct file_handle __user *, handle, int __user *, mnt_id,
+		int, flag)
+{
+	struct path path;
+	int lookup_flags;
+	int err;
+
+	if ((flag & ~(AT_SYMLINK_FOLLOW | AT_EMPTY_PATH)) != 0)
+		return -EINVAL;
+
+	lookup_flags = (flag & AT_SYMLINK_FOLLOW) ? LOOKUP_FOLLOW : 0;
+	if (flag & AT_EMPTY_PATH)
+		lookup_flags |= LOOKUP_EMPTY;
+	err = user_path_at(dfd, name, lookup_flags, &path);
+	if (!err) {
+		err = do_sys_name_to_handle(&path, handle, mnt_id);
+		path_put(&path);
+	}
+	return err;
+}
+
+static struct vfsmount *get_vfsmount_from_fd(int fd)
+{
+	struct path path;
+
+	if (fd == AT_FDCWD) {
+		struct fs_struct *fs = current->fs;
+		spin_lock(&fs->lock);
+		path = fs->pwd;
+		mntget(path.mnt);
+		spin_unlock(&fs->lock);
+	} else {
+		int fput_needed;
+		struct file *file = fget_light(fd, &fput_needed);
+		if (!file)
+			return ERR_PTR(-EBADF);
+		path = file->f_path;
+		mntget(path.mnt);
+		fput_light(file, fput_needed);
+	}
+	return path.mnt;
+}
+
+static int vfs_dentry_acceptable(void *context, struct dentry *dentry)
+{
+	return 1;
+}
+
+static int do_handle_to_path(int mountdirfd, struct file_handle *handle,
+			     struct path *path)
+{
+	int retval = 0;
+	int handle_dwords;
+
+	path->mnt = get_vfsmount_from_fd(mountdirfd);
+	if (IS_ERR(path->mnt)) {
+		retval = PTR_ERR(path->mnt);
+		goto out_err;
+	}
+	/* change the handle size to multiple of sizeof(u32) */
+	handle_dwords = handle->handle_bytes >> 2;
+	path->dentry = exportfs_decode_fh(path->mnt,
+					  (struct fid *)handle->f_handle,
+					  handle_dwords, handle->handle_type,
+					  vfs_dentry_acceptable, NULL);
+	if (IS_ERR(path->dentry)) {
+		retval = PTR_ERR(path->dentry);
+		goto out_mnt;
+	}
+	return 0;
+out_mnt:
+	mntput(path->mnt);
+out_err:
+	return retval;
+}
+
+static int handle_to_path(int mountdirfd, struct file_handle __user *ufh,
+		   struct path *path)
+{
+	int retval = 0;
+	struct file_handle f_handle;
+	struct file_handle *handle = NULL;
+
+	/*
+	 * With handle we don't look at the execute bit on the
+	 * the directory. Ideally we would like CAP_DAC_SEARCH.
+	 * But we don't have that
+	 */
+	if (!capable(CAP_DAC_READ_SEARCH)) {
+		retval = -EPERM;
+		goto out_err;
+	}
+	if (copy_from_user(&f_handle, ufh, sizeof(struct file_handle))) {
+		retval = -EFAULT;
+		goto out_err;
+	}
+	if ((f_handle.handle_bytes > MAX_HANDLE_SZ) ||
+	    (f_handle.handle_bytes == 0)) {
+		retval = -EINVAL;
+		goto out_err;
+	}
+	handle = kmalloc(sizeof(struct file_handle) + f_handle.handle_bytes,
+			 GFP_KERNEL);
+	if (!handle) {
+		retval = -ENOMEM;
+		goto out_err;
+	}
+	/* copy the full handle */
+	if (copy_from_user(handle, ufh,
+			   sizeof(struct file_handle) +
+			   f_handle.handle_bytes)) {
+		retval = -EFAULT;
+		goto out_handle;
+	}
+
+	retval = do_handle_to_path(mountdirfd, handle, path);
+
+out_handle:
+	kfree(handle);
+out_err:
+	return retval;
+}
+
+long do_handle_open(int mountdirfd,
+		    struct file_handle __user *ufh, int open_flag)
+{
+	long retval = 0;
+	struct path path;
+	struct file *file;
+	int fd;
+
+	retval = handle_to_path(mountdirfd, ufh, &path);
+	if (retval)
+		return retval;
+
+	fd = get_unused_fd_flags(open_flag);
+	if (fd < 0) {
+		path_put(&path);
+		return fd;
+	}
+	file = file_open_root(path.dentry, path.mnt, "", open_flag);
+	if (IS_ERR(file)) {
+		put_unused_fd(fd);
+		retval =  PTR_ERR(file);
+	} else {
+		retval = fd;
+		fsnotify_open(file);
+		fd_install(fd, file);
+	}
+	path_put(&path);
+	return retval;
+}
+
+/**
+ * sys_open_by_handle_at: Open the file handle
+ * @mountdirfd: directory file descriptor
+ * @handle: file handle to be opened
+ * @flag: open flags.
+ *
+ * @mountdirfd indicate the directory file descriptor
+ * of the mount point. file handle is decoded relative
+ * to the vfsmount pointed by the @mountdirfd. @flags
+ * value is same as the open(2) flags.
+ */
+SYSCALL_DEFINE3(open_by_handle_at, int, mountdirfd,
+		struct file_handle __user *, handle,
+		int, flags)
+{
+	long ret;
+
+	if (force_o_largefile())
+		flags |= O_LARGEFILE;
+
+	ret = do_handle_open(mountdirfd, handle, flags);
+	return ret;
+}
diff --git a/fs/file_table.c b/fs/file_table.c
index eb36b6b17e26..74a9544ac770 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -276,11 +276,10 @@ struct file *fget(unsigned int fd)
 	rcu_read_lock();
 	file = fcheck_files(files, fd);
 	if (file) {
-		if (!atomic_long_inc_not_zero(&file->f_count)) {
-			/* File object ref couldn't be taken */
-			rcu_read_unlock();
-			return NULL;
-		}
+		/* File object ref couldn't be taken */
+		if (file->f_mode & FMODE_PATH ||
+		    !atomic_long_inc_not_zero(&file->f_count))
+			file = NULL;
 	}
 	rcu_read_unlock();
 
@@ -289,6 +288,25 @@ struct file *fget(unsigned int fd)
 
 EXPORT_SYMBOL(fget);
 
+struct file *fget_raw(unsigned int fd)
+{
+	struct file *file;
+	struct files_struct *files = current->files;
+
+	rcu_read_lock();
+	file = fcheck_files(files, fd);
+	if (file) {
+		/* File object ref couldn't be taken */
+		if (!atomic_long_inc_not_zero(&file->f_count))
+			file = NULL;
+	}
+	rcu_read_unlock();
+
+	return file;
+}
+
+EXPORT_SYMBOL(fget_raw);
+
 /*
  * Lightweight file lookup - no refcnt increment if fd table isn't shared.
  *
@@ -313,6 +331,33 @@ struct file *fget_light(unsigned int fd, int *fput_needed)
 	*fput_needed = 0;
 	if (atomic_read(&files->count) == 1) {
 		file = fcheck_files(files, fd);
+		if (file && (file->f_mode & FMODE_PATH))
+			file = NULL;
+	} else {
+		rcu_read_lock();
+		file = fcheck_files(files, fd);
+		if (file) {
+			if (!(file->f_mode & FMODE_PATH) &&
+			    atomic_long_inc_not_zero(&file->f_count))
+				*fput_needed = 1;
+			else
+				/* Didn't get the reference, someone's freed */
+				file = NULL;
+		}
+		rcu_read_unlock();
+	}
+
+	return file;
+}
+
+struct file *fget_raw_light(unsigned int fd, int *fput_needed)
+{
+	struct file *file;
+	struct files_struct *files = current->files;
+
+	*fput_needed = 0;
+	if (atomic_read(&files->count) == 1) {
+		file = fcheck_files(files, fd);
 	} else {
 		rcu_read_lock();
 		file = fcheck_files(files, fd);
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 9e3f68cc1bd1..051b1a084528 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -637,8 +637,10 @@ static int fuse_encode_fh(struct dentry *dentry, u32 *fh, int *max_len,
 	u64 nodeid;
 	u32 generation;
 
-	if (*max_len < len)
+	if (*max_len < len) {
+		*max_len = len;
 		return  255;
+	}
 
 	nodeid = get_fuse_inode(inode)->nodeid;
 	generation = inode->i_generation;
diff --git a/fs/gfs2/export.c b/fs/gfs2/export.c
index 9023db8184f9..b5a5e60df0d5 100644
--- a/fs/gfs2/export.c
+++ b/fs/gfs2/export.c
@@ -36,9 +36,13 @@ static int gfs2_encode_fh(struct dentry *dentry, __u32 *p, int *len,
 	struct super_block *sb = inode->i_sb;
 	struct gfs2_inode *ip = GFS2_I(inode);
 
-	if (*len < GFS2_SMALL_FH_SIZE ||
-	    (connectable && *len < GFS2_LARGE_FH_SIZE))
+	if (connectable && (*len < GFS2_LARGE_FH_SIZE)) {
+		*len = GFS2_LARGE_FH_SIZE;
 		return 255;
+	} else if (*len < GFS2_SMALL_FH_SIZE) {
+		*len = GFS2_SMALL_FH_SIZE;
+		return 255;
+	}
 
 	fh[0] = cpu_to_be32(ip->i_no_formal_ino >> 32);
 	fh[1] = cpu_to_be32(ip->i_no_formal_ino & 0xFFFFFFFF);
diff --git a/fs/inode.c b/fs/inode.c
index 0647d80accf6..9910c039f026 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -84,16 +84,13 @@ static struct hlist_head *inode_hashtable __read_mostly;
 DEFINE_SPINLOCK(inode_lock);
 
 /*
- * iprune_sem provides exclusion between the kswapd or try_to_free_pages
- * icache shrinking path, and the umount path.  Without this exclusion,
- * by the time prune_icache calls iput for the inode whose pages it has
- * been invalidating, or by the time it calls clear_inode & destroy_inode
- * from its final dispose_list, the struct super_block they refer to
- * (for inode->i_sb->s_op) may already have been freed and reused.
+ * iprune_sem provides exclusion between the icache shrinking and the
+ * umount path.
  *
- * We make this an rwsem because the fastpath is icache shrinking. In
- * some cases a filesystem may be doing a significant amount of work in
- * its inode reclaim code, so this should improve parallelism.
+ * We don't actually need it to protect anything in the umount path,
+ * but only need to cycle through it to make sure any inode that
+ * prune_icache took off the LRU list has been fully torn down by the
+ * time we are past evict_inodes.
  */
 static DECLARE_RWSEM(iprune_sem);
 
@@ -516,17 +513,12 @@ void evict_inodes(struct super_block *sb)
 	struct inode *inode, *next;
 	LIST_HEAD(dispose);
 
-	down_write(&iprune_sem);
-
 	spin_lock(&inode_lock);
 	list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) {
 		if (atomic_read(&inode->i_count))
 			continue;
-
-		if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) {
-			WARN_ON(1);
+		if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE))
 			continue;
-		}
 
 		inode->i_state |= I_FREEING;
 
@@ -542,6 +534,13 @@ void evict_inodes(struct super_block *sb)
 	spin_unlock(&inode_lock);
 
 	dispose_list(&dispose);
+
+	/*
+	 * Cycle through iprune_sem to make sure any inode that prune_icache
+	 * moved off the list before we took the lock has been fully torn
+	 * down.
+	 */
+	down_write(&iprune_sem);
 	up_write(&iprune_sem);
 }
 
@@ -561,8 +560,6 @@ int invalidate_inodes(struct super_block *sb, bool kill_dirty)
 	struct inode *inode, *next;
 	LIST_HEAD(dispose);
 
-	down_write(&iprune_sem);
-
 	spin_lock(&inode_lock);
 	list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) {
 		if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE))
@@ -590,7 +587,6 @@ int invalidate_inodes(struct super_block *sb, bool kill_dirty)
 	spin_unlock(&inode_lock);
 
 	dispose_list(&dispose);
-	up_write(&iprune_sem);
 
 	return busy;
 }
diff --git a/fs/internal.h b/fs/internal.h
index 9b976b57d7fe..f3d15de44b15 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -106,6 +106,19 @@ extern void put_super(struct super_block *sb);
 struct nameidata;
 extern struct file *nameidata_to_filp(struct nameidata *);
 extern void release_open_intent(struct nameidata *);
+struct open_flags {
+	int open_flag;
+	int mode;
+	int acc_mode;
+	int intent;
+};
+extern struct file *do_filp_open(int dfd, const char *pathname,
+		const struct open_flags *op, int lookup_flags);
+extern struct file *do_file_open_root(struct dentry *, struct vfsmount *,
+		const char *, const struct open_flags *, int lookup_flags);
+
+extern long do_handle_open(int mountdirfd,
+			   struct file_handle __user *ufh, int open_flag);
 
 /*
  * inode.c
diff --git a/fs/isofs/export.c b/fs/isofs/export.c
index ed752cb38474..dd4687ff30d0 100644
--- a/fs/isofs/export.c
+++ b/fs/isofs/export.c
@@ -124,9 +124,13 @@ isofs_export_encode_fh(struct dentry *dentry,
 	 * offset of the inode and the upper 16 bits of fh32[1] to
 	 * hold the offset of the parent.
 	 */
-
-	if (len < 3 || (connectable && len < 5))
+	if (connectable && (len < 5)) {
+		*max_len = 5;
+		return 255;
+	} else if (len < 3) {
+		*max_len = 3;
 		return 255;
+	}
 
 	len = 3;
 	fh32[0] = ei->i_iget5_block;
diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c
index 5a2b269428a6..3f04a1804931 100644
--- a/fs/jfs/namei.c
+++ b/fs/jfs/namei.c
@@ -809,9 +809,6 @@ static int jfs_link(struct dentry *old_dentry,
 	if (ip->i_nlink == JFS_LINK_MAX)
 		return -EMLINK;
 
-	if (ip->i_nlink == 0)
-		return -ENOENT;
-
 	dquot_initialize(dir);
 
 	tid = txBegin(ip->i_sb, 0);
diff --git a/fs/namei.c b/fs/namei.c
index a4689eb2df28..b912b7abe747 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -136,7 +136,7 @@ static int do_getname(const char __user *filename, char *page)
 	return retval;
 }
 
-char * getname(const char __user * filename)
+static char *getname_flags(const char __user * filename, int flags)
 {
 	char *tmp, *result;
 
@@ -147,14 +147,21 @@ char * getname(const char __user * filename)
 
 		result = tmp;
 		if (retval < 0) {
-			__putname(tmp);
-			result = ERR_PTR(retval);
+			if (retval != -ENOENT || !(flags & LOOKUP_EMPTY)) {
+				__putname(tmp);
+				result = ERR_PTR(retval);
+			}
 		}
 	}
 	audit_getname(result);
 	return result;
 }
 
+char *getname(const char __user * filename)
+{
+	return getname_flags(filename, 0);
+}
+
 #ifdef CONFIG_AUDITSYSCALL
 void putname(const char *name)
 {
@@ -401,9 +408,11 @@ static int nameidata_drop_rcu(struct nameidata *nd)
 {
 	struct fs_struct *fs = current->fs;
 	struct dentry *dentry = nd->path.dentry;
+	int want_root = 0;
 
 	BUG_ON(!(nd->flags & LOOKUP_RCU));
-	if (nd->root.mnt) {
+	if (nd->root.mnt && !(nd->flags & LOOKUP_ROOT)) {
+		want_root = 1;
 		spin_lock(&fs->lock);
 		if (nd->root.mnt != fs->root.mnt ||
 				nd->root.dentry != fs->root.dentry)
@@ -414,7 +423,7 @@ static int nameidata_drop_rcu(struct nameidata *nd)
 		goto err;
 	BUG_ON(nd->inode != dentry->d_inode);
 	spin_unlock(&dentry->d_lock);
-	if (nd->root.mnt) {
+	if (want_root) {
 		path_get(&nd->root);
 		spin_unlock(&fs->lock);
 	}
@@ -427,7 +436,7 @@ static int nameidata_drop_rcu(struct nameidata *nd)
 err:
 	spin_unlock(&dentry->d_lock);
 err_root:
-	if (nd->root.mnt)
+	if (want_root)
 		spin_unlock(&fs->lock);
 	return -ECHILD;
 }
@@ -454,9 +463,11 @@ static int nameidata_dentry_drop_rcu(struct nameidata *nd, struct dentry *dentry
 {
 	struct fs_struct *fs = current->fs;
 	struct dentry *parent = nd->path.dentry;
+	int want_root = 0;
 
 	BUG_ON(!(nd->flags & LOOKUP_RCU));
-	if (nd->root.mnt) {
+	if (nd->root.mnt && !(nd->flags & LOOKUP_ROOT)) {
+		want_root = 1;
 		spin_lock(&fs->lock);
 		if (nd->root.mnt != fs->root.mnt ||
 				nd->root.dentry != fs->root.dentry)
@@ -476,7 +487,7 @@ static int nameidata_dentry_drop_rcu(struct nameidata *nd, struct dentry *dentry
 	parent->d_count++;
 	spin_unlock(&dentry->d_lock);
 	spin_unlock(&parent->d_lock);
-	if (nd->root.mnt) {
+	if (want_root) {
 		path_get(&nd->root);
 		spin_unlock(&fs->lock);
 	}
@@ -490,7 +501,7 @@ err:
 	spin_unlock(&dentry->d_lock);
 	spin_unlock(&parent->d_lock);
 err_root:
-	if (nd->root.mnt)
+	if (want_root)
 		spin_unlock(&fs->lock);
 	return -ECHILD;
 }
@@ -498,8 +509,16 @@ err_root:
 /* Try to drop out of rcu-walk mode if we were in it, otherwise do nothing.  */
 static inline int nameidata_dentry_drop_rcu_maybe(struct nameidata *nd, struct dentry *dentry)
 {
-	if (nd->flags & LOOKUP_RCU)
-		return nameidata_dentry_drop_rcu(nd, dentry);
+	if (nd->flags & LOOKUP_RCU) {
+		if (unlikely(nameidata_dentry_drop_rcu(nd, dentry))) {
+			nd->flags &= ~LOOKUP_RCU;
+			if (!(nd->flags & LOOKUP_ROOT))
+				nd->root.mnt = NULL;
+			rcu_read_unlock();
+			br_read_unlock(vfsmount_lock);
+			return -ECHILD;
+		}
+	}
 	return 0;
 }
 
@@ -518,7 +537,8 @@ static int nameidata_drop_rcu_last(struct nameidata *nd)
 
 	BUG_ON(!(nd->flags & LOOKUP_RCU));
 	nd->flags &= ~LOOKUP_RCU;
-	nd->root.mnt = NULL;
+	if (!(nd->flags & LOOKUP_ROOT))
+		nd->root.mnt = NULL;
 	spin_lock(&dentry->d_lock);
 	if (!__d_rcu_to_refcount(dentry, nd->seq))
 		goto err_unlock;
@@ -539,14 +559,6 @@ err_unlock:
 	return -ECHILD;
 }
 
-/* Try to drop out of rcu-walk mode if we were in it, otherwise do nothing.  */
-static inline int nameidata_drop_rcu_last_maybe(struct nameidata *nd)
-{
-	if (likely(nd->flags & LOOKUP_RCU))
-		return nameidata_drop_rcu_last(nd);
-	return 0;
-}
-
 /**
  * release_open_intent - free up open intent resources
  * @nd: pointer to nameidata
@@ -590,42 +602,8 @@ do_revalidate(struct dentry *dentry, struct nameidata *nd)
 	return dentry;
 }
 
-static inline struct dentry *
-do_revalidate_rcu(struct dentry *dentry, struct nameidata *nd)
-{
-	int status = d_revalidate(dentry, nd);
-	if (likely(status > 0))
-		return dentry;
-	if (status == -ECHILD) {
-		if (nameidata_dentry_drop_rcu(nd, dentry))
-			return ERR_PTR(-ECHILD);
-		return do_revalidate(dentry, nd);
-	}
-	if (status < 0)
-		return ERR_PTR(status);
-	/* Don't d_invalidate in rcu-walk mode */
-	if (nameidata_dentry_drop_rcu(nd, dentry))
-		return ERR_PTR(-ECHILD);
-	if (!d_invalidate(dentry)) {
-		dput(dentry);
-		dentry = NULL;
-	}
-	return dentry;
-}
-
-static inline int need_reval_dot(struct dentry *dentry)
-{
-	if (likely(!(dentry->d_flags & DCACHE_OP_REVALIDATE)))
-		return 0;
-
-	if (likely(!(dentry->d_sb->s_type->fs_flags & FS_REVAL_DOT)))
-		return 0;
-
-	return 1;
-}
-
 /*
- * force_reval_path - force revalidation of a dentry
+ * handle_reval_path - force revalidation of a dentry
  *
  * In some situations the path walking code will trust dentries without
  * revalidating them. This causes problems for filesystems that depend on
@@ -639,27 +617,28 @@ static inline int need_reval_dot(struct dentry *dentry)
  * invalidate the dentry. It's up to the caller to handle putting references
  * to the path if necessary.
  */
-static int
-force_reval_path(struct path *path, struct nameidata *nd)
+static inline int handle_reval_path(struct nameidata *nd)
 {
+	struct dentry *dentry = nd->path.dentry;
 	int status;
-	struct dentry *dentry = path->dentry;
 
-	/*
-	 * only check on filesystems where it's possible for the dentry to
-	 * become stale.
-	 */
-	if (!need_reval_dot(dentry))
+	if (likely(!(nd->flags & LOOKUP_JUMPED)))
+		return 0;
+
+	if (likely(!(dentry->d_flags & DCACHE_OP_REVALIDATE)))
+		return 0;
+
+	if (likely(!(dentry->d_sb->s_type->fs_flags & FS_REVAL_DOT)))
 		return 0;
 
+	/* Note: we do not d_invalidate() */
 	status = d_revalidate(dentry, nd);
 	if (status > 0)
 		return 0;
 
-	if (!status) {
-		d_invalidate(dentry);
+	if (!status)
 		status = -ESTALE;
-	}
+
 	return status;
 }
 
@@ -728,6 +707,7 @@ static __always_inline int __vfs_follow_link(struct nameidata *nd, const char *l
 		path_put(&nd->path);
 		nd->path = nd->root;
 		path_get(&nd->root);
+		nd->flags |= LOOKUP_JUMPED;
 	}
 	nd->inode = nd->path.dentry->d_inode;
 
@@ -757,19 +737,42 @@ static inline void path_to_nameidata(const struct path *path,
 	nd->path.dentry = path->dentry;
 }
 
+static inline void put_link(struct nameidata *nd, struct path *link, void *cookie)
+{
+	struct inode *inode = link->dentry->d_inode;
+	if (!IS_ERR(cookie) && inode->i_op->put_link)
+		inode->i_op->put_link(link->dentry, nd, cookie);
+	path_put(link);
+}
+
 static __always_inline int
-__do_follow_link(const struct path *link, struct nameidata *nd, void **p)
+follow_link(struct path *link, struct nameidata *nd, void **p)
 {
 	int error;
 	struct dentry *dentry = link->dentry;
 
 	BUG_ON(nd->flags & LOOKUP_RCU);
 
+	if (link->mnt == nd->path.mnt)
+		mntget(link->mnt);
+
+	if (unlikely(current->total_link_count >= 40)) {
+		*p = ERR_PTR(-ELOOP); /* no ->put_link(), please */
+		path_put(&nd->path);
+		return -ELOOP;
+	}
+	cond_resched();
+	current->total_link_count++;
+
 	touch_atime(link->mnt, dentry);
 	nd_set_link(nd, NULL);
 
-	if (link->mnt == nd->path.mnt)
-		mntget(link->mnt);
+	error = security_inode_follow_link(link->dentry, nd);
+	if (error) {
+		*p = ERR_PTR(error); /* no ->put_link(), please */
+		path_put(&nd->path);
+		return error;
+	}
 
 	nd->last_type = LAST_BIND;
 	*p = dentry->d_inode->i_op->follow_link(dentry, nd);
@@ -780,56 +783,18 @@ __do_follow_link(const struct path *link, struct nameidata *nd, void **p)
 		if (s)
 			error = __vfs_follow_link(nd, s);
 		else if (nd->last_type == LAST_BIND) {
-			error = force_reval_path(&nd->path, nd);
-			if (error)
+			nd->flags |= LOOKUP_JUMPED;
+			nd->inode = nd->path.dentry->d_inode;
+			if (nd->inode->i_op->follow_link) {
+				/* stepped on a _really_ weird one */
 				path_put(&nd->path);
+				error = -ELOOP;
+			}
 		}
 	}
 	return error;
 }
 
-/*
- * This limits recursive symlink follows to 8, while
- * limiting consecutive symlinks to 40.
- *
- * Without that kind of total limit, nasty chains of consecutive
- * symlinks can cause almost arbitrarily long lookups. 
- */
-static inline int do_follow_link(struct inode *inode, struct path *path, struct nameidata *nd)
-{
-	void *cookie;
-	int err = -ELOOP;
-
-	/* We drop rcu-walk here */
-	if (nameidata_dentry_drop_rcu_maybe(nd, path->dentry))
-		return -ECHILD;
-	BUG_ON(inode != path->dentry->d_inode);
-
-	if (current->link_count >= MAX_NESTED_LINKS)
-		goto loop;
-	if (current->total_link_count >= 40)
-		goto loop;
-	BUG_ON(nd->depth >= MAX_NESTED_LINKS);
-	cond_resched();
-	err = security_inode_follow_link(path->dentry, nd);
-	if (err)
-		goto loop;
-	current->link_count++;
-	current->total_link_count++;
-	nd->depth++;
-	err = __do_follow_link(path, nd, &cookie);
-	if (!IS_ERR(cookie) && path->dentry->d_inode->i_op->put_link)
-		path->dentry->d_inode->i_op->put_link(path->dentry, nd, cookie);
-	path_put(path);
-	current->link_count--;
-	nd->depth--;
-	return err;
-loop:
-	path_put_conditional(path, nd);
-	path_put(&nd->path);
-	return err;
-}
-
 static int follow_up_rcu(struct path *path)
 {
 	struct vfsmount *parent;
@@ -1068,7 +1033,7 @@ static int follow_dotdot_rcu(struct nameidata *nd)
 
 			seq = read_seqcount_begin(&parent->d_seq);
 			if (read_seqcount_retry(&old->d_seq, nd->seq))
-				return -ECHILD;
+				goto failed;
 			inode = parent->d_inode;
 			nd->path.dentry = parent;
 			nd->seq = seq;
@@ -1081,8 +1046,15 @@ static int follow_dotdot_rcu(struct nameidata *nd)
 	}
 	__follow_mount_rcu(nd, &nd->path, &inode, true);
 	nd->inode = inode;
-
 	return 0;
+
+failed:
+	nd->flags &= ~LOOKUP_RCU;
+	if (!(nd->flags & LOOKUP_ROOT))
+		nd->root.mnt = NULL;
+	rcu_read_unlock();
+	br_read_unlock(vfsmount_lock);
+	return -ECHILD;
 }
 
 /*
@@ -1216,68 +1188,85 @@ static int do_lookup(struct nameidata *nd, struct qstr *name,
 {
 	struct vfsmount *mnt = nd->path.mnt;
 	struct dentry *dentry, *parent = nd->path.dentry;
-	struct inode *dir;
+	int need_reval = 1;
+	int status = 1;
 	int err;
 
 	/*
-	 * See if the low-level filesystem might want
-	 * to use its own hash..
-	 */
-	if (unlikely(parent->d_flags & DCACHE_OP_HASH)) {
-		err = parent->d_op->d_hash(parent, nd->inode, name);
-		if (err < 0)
-			return err;
-	}
-
-	/*
 	 * Rename seqlock is not required here because in the off chance
 	 * of a false negative due to a concurrent rename, we're going to
 	 * do the non-racy lookup, below.
 	 */
 	if (nd->flags & LOOKUP_RCU) {
 		unsigned seq;
-
 		*inode = nd->inode;
 		dentry = __d_lookup_rcu(parent, name, &seq, inode);
-		if (!dentry) {
-			if (nameidata_drop_rcu(nd))
-				return -ECHILD;
-			goto need_lookup;
-		}
+		if (!dentry)
+			goto unlazy;
+
 		/* Memory barrier in read_seqcount_begin of child is enough */
 		if (__read_seqcount_retry(&parent->d_seq, nd->seq))
 			return -ECHILD;
-
 		nd->seq = seq;
+
 		if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE)) {
-			dentry = do_revalidate_rcu(dentry, nd);
-			if (!dentry)
-				goto need_lookup;
-			if (IS_ERR(dentry))
-				goto fail;
-			if (!(nd->flags & LOOKUP_RCU))
-				goto done;
+			status = d_revalidate(dentry, nd);
+			if (unlikely(status <= 0)) {
+				if (status != -ECHILD)
+					need_reval = 0;
+				goto unlazy;
+			}
 		}
 		path->mnt = mnt;
 		path->dentry = dentry;
 		if (likely(__follow_mount_rcu(nd, path, inode, false)))
 			return 0;
-		if (nameidata_drop_rcu(nd))
-			return -ECHILD;
-		/* fallthru */
+unlazy:
+		if (dentry) {
+			if (nameidata_dentry_drop_rcu(nd, dentry))
+				return -ECHILD;
+		} else {
+			if (nameidata_drop_rcu(nd))
+				return -ECHILD;
+		}
+	} else {
+		dentry = __d_lookup(parent, name);
 	}
-	dentry = __d_lookup(parent, name);
-	if (!dentry)
-		goto need_lookup;
-found:
-	if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE)) {
-		dentry = do_revalidate(dentry, nd);
-		if (!dentry)
-			goto need_lookup;
-		if (IS_ERR(dentry))
-			goto fail;
+
+retry:
+	if (unlikely(!dentry)) {
+		struct inode *dir = parent->d_inode;
+		BUG_ON(nd->inode != dir);
+
+		mutex_lock(&dir->i_mutex);
+		dentry = d_lookup(parent, name);
+		if (likely(!dentry)) {
+			dentry = d_alloc_and_lookup(parent, name, nd);
+			if (IS_ERR(dentry)) {
+				mutex_unlock(&dir->i_mutex);
+				return PTR_ERR(dentry);
+			}
+			/* known good */
+			need_reval = 0;
+			status = 1;
+		}
+		mutex_unlock(&dir->i_mutex);
 	}
-done:
+	if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE) && need_reval)
+		status = d_revalidate(dentry, nd);
+	if (unlikely(status <= 0)) {
+		if (status < 0) {
+			dput(dentry);
+			return status;
+		}
+		if (!d_invalidate(dentry)) {
+			dput(dentry);
+			dentry = NULL;
+			need_reval = 1;
+			goto retry;
+		}
+	}
+
 	path->mnt = mnt;
 	path->dentry = dentry;
 	err = follow_managed(path, nd->flags);
@@ -1287,39 +1276,113 @@ done:
 	}
 	*inode = path->dentry->d_inode;
 	return 0;
+}
+
+static inline int may_lookup(struct nameidata *nd)
+{
+	if (nd->flags & LOOKUP_RCU) {
+		int err = exec_permission(nd->inode, IPERM_FLAG_RCU);
+		if (err != -ECHILD)
+			return err;
+		if (nameidata_drop_rcu(nd))
+			return -ECHILD;
+	}
+	return exec_permission(nd->inode, 0);
+}
 
-need_lookup:
-	dir = parent->d_inode;
-	BUG_ON(nd->inode != dir);
+static inline int handle_dots(struct nameidata *nd, int type)
+{
+	if (type == LAST_DOTDOT) {
+		if (nd->flags & LOOKUP_RCU) {
+			if (follow_dotdot_rcu(nd))
+				return -ECHILD;
+		} else
+			follow_dotdot(nd);
+	}
+	return 0;
+}
 
-	mutex_lock(&dir->i_mutex);
-	/*
-	 * First re-do the cached lookup just in case it was created
-	 * while we waited for the directory semaphore, or the first
-	 * lookup failed due to an unrelated rename.
-	 *
-	 * This could use version numbering or similar to avoid unnecessary
-	 * cache lookups, but then we'd have to do the first lookup in the
-	 * non-racy way. However in the common case here, everything should
-	 * be hot in cache, so would it be a big win?
-	 */
-	dentry = d_lookup(parent, name);
-	if (likely(!dentry)) {
-		dentry = d_alloc_and_lookup(parent, name, nd);
-		mutex_unlock(&dir->i_mutex);
-		if (IS_ERR(dentry))
-			goto fail;
-		goto done;
+static void terminate_walk(struct nameidata *nd)
+{
+	if (!(nd->flags & LOOKUP_RCU)) {
+		path_put(&nd->path);
+	} else {
+		nd->flags &= ~LOOKUP_RCU;
+		if (!(nd->flags & LOOKUP_ROOT))
+			nd->root.mnt = NULL;
+		rcu_read_unlock();
+		br_read_unlock(vfsmount_lock);
 	}
+}
+
+static inline int walk_component(struct nameidata *nd, struct path *path,
+		struct qstr *name, int type, int follow)
+{
+	struct inode *inode;
+	int err;
 	/*
-	 * Uhhuh! Nasty case: the cache was re-populated while
-	 * we waited on the semaphore. Need to revalidate.
+	 * "." and ".." are special - ".." especially so because it has
+	 * to be able to know about the current root directory and
+	 * parent relationships.
 	 */
-	mutex_unlock(&dir->i_mutex);
-	goto found;
+	if (unlikely(type != LAST_NORM))
+		return handle_dots(nd, type);
+	err = do_lookup(nd, name, path, &inode);
+	if (unlikely(err)) {
+		terminate_walk(nd);
+		return err;
+	}
+	if (!inode) {
+		path_to_nameidata(path, nd);
+		terminate_walk(nd);
+		return -ENOENT;
+	}
+	if (unlikely(inode->i_op->follow_link) && follow) {
+		if (nameidata_dentry_drop_rcu_maybe(nd, path->dentry))
+			return -ECHILD;
+		BUG_ON(inode != path->dentry->d_inode);
+		return 1;
+	}
+	path_to_nameidata(path, nd);
+	nd->inode = inode;
+	return 0;
+}
 
-fail:
-	return PTR_ERR(dentry);
+/*
+ * This limits recursive symlink follows to 8, while
+ * limiting consecutive symlinks to 40.
+ *
+ * Without that kind of total limit, nasty chains of consecutive
+ * symlinks can cause almost arbitrarily long lookups.
+ */
+static inline int nested_symlink(struct path *path, struct nameidata *nd)
+{
+	int res;
+
+	BUG_ON(nd->depth >= MAX_NESTED_LINKS);
+	if (unlikely(current->link_count >= MAX_NESTED_LINKS)) {
+		path_put_conditional(path, nd);
+		path_put(&nd->path);
+		return -ELOOP;
+	}
+
+	nd->depth++;
+	current->link_count++;
+
+	do {
+		struct path link = *path;
+		void *cookie;
+
+		res = follow_link(&link, nd, &cookie);
+		if (!res)
+			res = walk_component(nd, path, &nd->last,
+					     nd->last_type, LOOKUP_FOLLOW);
+		put_link(nd, &link, cookie);
+	} while (res > 0);
+
+	current->link_count--;
+	nd->depth--;
+	return res;
 }
 
 /*
@@ -1339,30 +1402,18 @@ static int link_path_walk(const char *name, struct nameidata *nd)
 	while (*name=='/')
 		name++;
 	if (!*name)
-		goto return_reval;
-
-	if (nd->depth)
-		lookup_flags = LOOKUP_FOLLOW | (nd->flags & LOOKUP_CONTINUE);
+		return 0;
 
 	/* At this point we know we have a real path component. */
 	for(;;) {
-		struct inode *inode;
 		unsigned long hash;
 		struct qstr this;
 		unsigned int c;
+		int type;
 
 		nd->flags |= LOOKUP_CONTINUE;
-		if (nd->flags & LOOKUP_RCU) {
-			err = exec_permission(nd->inode, IPERM_FLAG_RCU);
-			if (err == -ECHILD) {
-				if (nameidata_drop_rcu(nd))
-					return -ECHILD;
-				goto exec_again;
-			}
-		} else {
-exec_again:
-			err = exec_permission(nd->inode, 0);
-		}
+
+		err = may_lookup(nd);
  		if (err)
 			break;
 
@@ -1378,52 +1429,43 @@ exec_again:
 		this.len = name - (const char *) this.name;
 		this.hash = end_name_hash(hash);
 
+		type = LAST_NORM;
+		if (this.name[0] == '.') switch (this.len) {
+			case 2:
+				if (this.name[1] == '.') {
+					type = LAST_DOTDOT;
+					nd->flags |= LOOKUP_JUMPED;
+				}
+				break;
+			case 1:
+				type = LAST_DOT;
+		}
+		if (likely(type == LAST_NORM)) {
+			struct dentry *parent = nd->path.dentry;
+			nd->flags &= ~LOOKUP_JUMPED;
+			if (unlikely(parent->d_flags & DCACHE_OP_HASH)) {
+				err = parent->d_op->d_hash(parent, nd->inode,
+							   &this);
+				if (err < 0)
+					break;
+			}
+		}
+
 		/* remove trailing slashes? */
 		if (!c)
 			goto last_component;
 		while (*++name == '/');
 		if (!*name)
-			goto last_with_slashes;
+			goto last_component;
 
-		/*
-		 * "." and ".." are special - ".." especially so because it has
-		 * to be able to know about the current root directory and
-		 * parent relationships.
-		 */
-		if (this.name[0] == '.') switch (this.len) {
-			default:
-				break;
-			case 2:
-				if (this.name[1] != '.')
-					break;
-				if (nd->flags & LOOKUP_RCU) {
-					if (follow_dotdot_rcu(nd))
-						return -ECHILD;
-				} else
-					follow_dotdot(nd);
-				/* fallthrough */
-			case 1:
-				continue;
-		}
-		/* This does the actual lookups.. */
-		err = do_lookup(nd, &this, &next, &inode);
-		if (err)
-			break;
-		err = -ENOENT;
-		if (!inode)
-			goto out_dput;
+		err = walk_component(nd, &next, &this, type, LOOKUP_FOLLOW);
+		if (err < 0)
+			return err;
 
-		if (inode->i_op->follow_link) {
-			err = do_follow_link(inode, &next, nd);
+		if (err) {
+			err = nested_symlink(&next, nd);
 			if (err)
-				goto return_err;
-			nd->inode = nd->path.dentry->d_inode;
-			err = -ENOENT;
-			if (!nd->inode)
-				break;
-		} else {
-			path_to_nameidata(&next, nd);
-			nd->inode = inode;
+				return err;
 		}
 		err = -ENOTDIR; 
 		if (!nd->inode->i_op->lookup)
@@ -1431,210 +1473,109 @@ exec_again:
 		continue;
 		/* here ends the main loop */
 
-last_with_slashes:
-		lookup_flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
 last_component:
 		/* Clear LOOKUP_CONTINUE iff it was previously unset */
 		nd->flags &= lookup_flags | ~LOOKUP_CONTINUE;
-		if (lookup_flags & LOOKUP_PARENT)
-			goto lookup_parent;
-		if (this.name[0] == '.') switch (this.len) {
-			default:
-				break;
-			case 2:
-				if (this.name[1] != '.')
-					break;
-				if (nd->flags & LOOKUP_RCU) {
-					if (follow_dotdot_rcu(nd))
-						return -ECHILD;
-				} else
-					follow_dotdot(nd);
-				/* fallthrough */
-			case 1:
-				goto return_reval;
-		}
-		err = do_lookup(nd, &this, &next, &inode);
-		if (err)
-			break;
-		if (inode && unlikely(inode->i_op->follow_link) &&
-		    (lookup_flags & LOOKUP_FOLLOW)) {
-			err = do_follow_link(inode, &next, nd);
-			if (err)
-				goto return_err;
-			nd->inode = nd->path.dentry->d_inode;
-		} else {
-			path_to_nameidata(&next, nd);
-			nd->inode = inode;
-		}
-		err = -ENOENT;
-		if (!nd->inode)
-			break;
-		if (lookup_flags & LOOKUP_DIRECTORY) {
-			err = -ENOTDIR; 
-			if (!nd->inode->i_op->lookup)
-				break;
-		}
-		goto return_base;
-lookup_parent:
 		nd->last = this;
-		nd->last_type = LAST_NORM;
-		if (this.name[0] != '.')
-			goto return_base;
-		if (this.len == 1)
-			nd->last_type = LAST_DOT;
-		else if (this.len == 2 && this.name[1] == '.')
-			nd->last_type = LAST_DOTDOT;
-		else
-			goto return_base;
-return_reval:
-		/*
-		 * We bypassed the ordinary revalidation routines.
-		 * We may need to check the cached dentry for staleness.
-		 */
-		if (need_reval_dot(nd->path.dentry)) {
-			if (nameidata_drop_rcu_last_maybe(nd))
-				return -ECHILD;
-			/* Note: we do not d_invalidate() */
-			err = d_revalidate(nd->path.dentry, nd);
-			if (!err)
-				err = -ESTALE;
-			if (err < 0)
-				break;
-			return 0;
-		}
-return_base:
-		if (nameidata_drop_rcu_last_maybe(nd))
-			return -ECHILD;
+		nd->last_type = type;
 		return 0;
-out_dput:
-		if (!(nd->flags & LOOKUP_RCU))
-			path_put_conditional(&next, nd);
-		break;
 	}
-	if (!(nd->flags & LOOKUP_RCU))
-		path_put(&nd->path);
-return_err:
+	terminate_walk(nd);
 	return err;
 }
 
-static inline int path_walk_rcu(const char *name, struct nameidata *nd)
-{
-	current->total_link_count = 0;
-
-	return link_path_walk(name, nd);
-}
-
-static inline int path_walk_simple(const char *name, struct nameidata *nd)
-{
-	current->total_link_count = 0;
-
-	return link_path_walk(name, nd);
-}
-
-static int path_walk(const char *name, struct nameidata *nd)
-{
-	struct path save = nd->path;
-	int result;
-
-	current->total_link_count = 0;
-
-	/* make sure the stuff we saved doesn't go away */
-	path_get(&save);
-
-	result = link_path_walk(name, nd);
-	if (result == -ESTALE) {
-		/* nd->path had been dropped */
-		current->total_link_count = 0;
-		nd->path = save;
-		nd->inode = save.dentry->d_inode;
-		path_get(&nd->path);
-		nd->flags |= LOOKUP_REVAL;
-		result = link_path_walk(name, nd);
-	}
-
-	path_put(&save);
-
-	return result;
-}
-
-static void path_finish_rcu(struct nameidata *nd)
-{
-	if (nd->flags & LOOKUP_RCU) {
-		/* RCU dangling. Cancel it. */
-		nd->flags &= ~LOOKUP_RCU;
-		nd->root.mnt = NULL;
-		rcu_read_unlock();
-		br_read_unlock(vfsmount_lock);
-	}
-	if (nd->file)
-		fput(nd->file);
-}
-
-static int path_init_rcu(int dfd, const char *name, unsigned int flags, struct nameidata *nd)
+static int path_init(int dfd, const char *name, unsigned int flags,
+		     struct nameidata *nd, struct file **fp)
 {
 	int retval = 0;
 	int fput_needed;
 	struct file *file;
 
 	nd->last_type = LAST_ROOT; /* if there are only slashes... */
-	nd->flags = flags | LOOKUP_RCU;
+	nd->flags = flags | LOOKUP_JUMPED;
 	nd->depth = 0;
+	if (flags & LOOKUP_ROOT) {
+		struct inode *inode = nd->root.dentry->d_inode;
+		if (*name) {
+			if (!inode->i_op->lookup)
+				return -ENOTDIR;
+			retval = inode_permission(inode, MAY_EXEC);
+			if (retval)
+				return retval;
+		}
+		nd->path = nd->root;
+		nd->inode = inode;
+		if (flags & LOOKUP_RCU) {
+			br_read_lock(vfsmount_lock);
+			rcu_read_lock();
+			nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
+		} else {
+			path_get(&nd->path);
+		}
+		return 0;
+	}
+
 	nd->root.mnt = NULL;
-	nd->file = NULL;
 
 	if (*name=='/') {
-		struct fs_struct *fs = current->fs;
-		unsigned seq;
-
-		br_read_lock(vfsmount_lock);
-		rcu_read_lock();
-
-		do {
-			seq = read_seqcount_begin(&fs->seq);
-			nd->root = fs->root;
-			nd->path = nd->root;
-			nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
-		} while (read_seqcount_retry(&fs->seq, seq));
-
+		if (flags & LOOKUP_RCU) {
+			br_read_lock(vfsmount_lock);
+			rcu_read_lock();
+			set_root_rcu(nd);
+		} else {
+			set_root(nd);
+			path_get(&nd->root);
+		}
+		nd->path = nd->root;
 	} else if (dfd == AT_FDCWD) {
-		struct fs_struct *fs = current->fs;
-		unsigned seq;
-
-		br_read_lock(vfsmount_lock);
-		rcu_read_lock();
+		if (flags & LOOKUP_RCU) {
+			struct fs_struct *fs = current->fs;
+			unsigned seq;
 
-		do {
-			seq = read_seqcount_begin(&fs->seq);
-			nd->path = fs->pwd;
-			nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
-		} while (read_seqcount_retry(&fs->seq, seq));
+			br_read_lock(vfsmount_lock);
+			rcu_read_lock();
 
+			do {
+				seq = read_seqcount_begin(&fs->seq);
+				nd->path = fs->pwd;
+				nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
+			} while (read_seqcount_retry(&fs->seq, seq));
+		} else {
+			get_fs_pwd(current->fs, &nd->path);
+		}
 	} else {
 		struct dentry *dentry;
 
-		file = fget_light(dfd, &fput_needed);
+		file = fget_raw_light(dfd, &fput_needed);
 		retval = -EBADF;
 		if (!file)
 			goto out_fail;
 
 		dentry = file->f_path.dentry;
 
-		retval = -ENOTDIR;
-		if (!S_ISDIR(dentry->d_inode->i_mode))
-			goto fput_fail;
+		if (*name) {
+			retval = -ENOTDIR;
+			if (!S_ISDIR(dentry->d_inode->i_mode))
+				goto fput_fail;
 
-		retval = file_permission(file, MAY_EXEC);
-		if (retval)
-			goto fput_fail;
+			retval = file_permission(file, MAY_EXEC);
+			if (retval)
+				goto fput_fail;
+		}
 
 		nd->path = file->f_path;
-		if (fput_needed)
-			nd->file = file;
-
-		nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
-		br_read_lock(vfsmount_lock);
-		rcu_read_lock();
+		if (flags & LOOKUP_RCU) {
+			if (fput_needed)
+				*fp = file;
+			nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
+			br_read_lock(vfsmount_lock);
+			rcu_read_lock();
+		} else {
+			path_get(&file->f_path);
+			fput_light(file, fput_needed);
+		}
 	}
+
 	nd->inode = nd->path.dentry->d_inode;
 	return 0;
 
@@ -1644,60 +1585,23 @@ out_fail:
 	return retval;
 }
 
-static int path_init(int dfd, const char *name, unsigned int flags, struct nameidata *nd)
+static inline int lookup_last(struct nameidata *nd, struct path *path)
 {
-	int retval = 0;
-	int fput_needed;
-	struct file *file;
-
-	nd->last_type = LAST_ROOT; /* if there are only slashes... */
-	nd->flags = flags;
-	nd->depth = 0;
-	nd->root.mnt = NULL;
-
-	if (*name=='/') {
-		set_root(nd);
-		nd->path = nd->root;
-		path_get(&nd->root);
-	} else if (dfd == AT_FDCWD) {
-		get_fs_pwd(current->fs, &nd->path);
-	} else {
-		struct dentry *dentry;
-
-		file = fget_light(dfd, &fput_needed);
-		retval = -EBADF;
-		if (!file)
-			goto out_fail;
-
-		dentry = file->f_path.dentry;
-
-		retval = -ENOTDIR;
-		if (!S_ISDIR(dentry->d_inode->i_mode))
-			goto fput_fail;
-
-		retval = file_permission(file, MAY_EXEC);
-		if (retval)
-			goto fput_fail;
+	if (nd->last_type == LAST_NORM && nd->last.name[nd->last.len])
+		nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
 
-		nd->path = file->f_path;
-		path_get(&file->f_path);
-
-		fput_light(file, fput_needed);
-	}
-	nd->inode = nd->path.dentry->d_inode;
-	return 0;
-
-fput_fail:
-	fput_light(file, fput_needed);
-out_fail:
-	return retval;
+	nd->flags &= ~LOOKUP_PARENT;
+	return walk_component(nd, path, &nd->last, nd->last_type,
+					nd->flags & LOOKUP_FOLLOW);
 }
 
 /* Returns 0 and nd will be valid on success; Retuns error, otherwise. */
-static int do_path_lookup(int dfd, const char *name,
+static int path_lookupat(int dfd, const char *name,
 				unsigned int flags, struct nameidata *nd)
 {
-	int retval;
+	struct file *base = NULL;
+	struct path path;
+	int err;
 
 	/*
 	 * Path walking is largely split up into 2 different synchronisation
@@ -1713,44 +1617,75 @@ static int do_path_lookup(int dfd, const char *name,
 	 * be handled by restarting a traditional ref-walk (which will always
 	 * be able to complete).
 	 */
-	retval = path_init_rcu(dfd, name, flags, nd);
-	if (unlikely(retval))
-		return retval;
-	retval = path_walk_rcu(name, nd);
-	path_finish_rcu(nd);
-	if (nd->root.mnt) {
-		path_put(&nd->root);
-		nd->root.mnt = NULL;
+	err = path_init(dfd, name, flags | LOOKUP_PARENT, nd, &base);
+
+	if (unlikely(err))
+		return err;
+
+	current->total_link_count = 0;
+	err = link_path_walk(name, nd);
+
+	if (!err && !(flags & LOOKUP_PARENT)) {
+		err = lookup_last(nd, &path);
+		while (err > 0) {
+			void *cookie;
+			struct path link = path;
+			nd->flags |= LOOKUP_PARENT;
+			err = follow_link(&link, nd, &cookie);
+			if (!err)
+				err = lookup_last(nd, &path);
+			put_link(nd, &link, cookie);
+		}
 	}
 
-	if (unlikely(retval == -ECHILD || retval == -ESTALE)) {
-		/* slower, locked walk */
-		if (retval == -ESTALE)
-			flags |= LOOKUP_REVAL;
-		retval = path_init(dfd, name, flags, nd);
-		if (unlikely(retval))
-			return retval;
-		retval = path_walk(name, nd);
-		if (nd->root.mnt) {
-			path_put(&nd->root);
-			nd->root.mnt = NULL;
+	if (nd->flags & LOOKUP_RCU) {
+		/* went all way through without dropping RCU */
+		BUG_ON(err);
+		if (nameidata_drop_rcu_last(nd))
+			err = -ECHILD;
+	}
+
+	if (!err)
+		err = handle_reval_path(nd);
+
+	if (!err && nd->flags & LOOKUP_DIRECTORY) {
+		if (!nd->inode->i_op->lookup) {
+			path_put(&nd->path);
+			return -ENOTDIR;
 		}
 	}
 
+	if (base)
+		fput(base);
+
+	if (nd->root.mnt && !(nd->flags & LOOKUP_ROOT)) {
+		path_put(&nd->root);
+		nd->root.mnt = NULL;
+	}
+	return err;
+}
+
+static int do_path_lookup(int dfd, const char *name,
+				unsigned int flags, struct nameidata *nd)
+{
+	int retval = path_lookupat(dfd, name, flags | LOOKUP_RCU, nd);
+	if (unlikely(retval == -ECHILD))
+		retval = path_lookupat(dfd, name, flags, nd);
+	if (unlikely(retval == -ESTALE))
+		retval = path_lookupat(dfd, name, flags | LOOKUP_REVAL, nd);
+
 	if (likely(!retval)) {
 		if (unlikely(!audit_dummy_context())) {
 			if (nd->path.dentry && nd->inode)
 				audit_inode(name, nd->path.dentry);
 		}
 	}
-
 	return retval;
 }
 
-int path_lookup(const char *name, unsigned int flags,
-			struct nameidata *nd)
+int kern_path_parent(const char *name, struct nameidata *nd)
 {
-	return do_path_lookup(AT_FDCWD, name, flags, nd);
+	return do_path_lookup(AT_FDCWD, name, LOOKUP_PARENT, nd);
 }
 
 int kern_path(const char *name, unsigned int flags, struct path *path)
@@ -1774,29 +1709,10 @@ int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt,
 		    const char *name, unsigned int flags,
 		    struct nameidata *nd)
 {
-	int retval;
-
-	/* same as do_path_lookup */
-	nd->last_type = LAST_ROOT;
-	nd->flags = flags;
-	nd->depth = 0;
-
-	nd->path.dentry = dentry;
-	nd->path.mnt = mnt;
-	path_get(&nd->path);
-	nd->root = nd->path;
-	path_get(&nd->root);
-	nd->inode = nd->path.dentry->d_inode;
-
-	retval = path_walk(name, nd);
-	if (unlikely(!retval && !audit_dummy_context() && nd->path.dentry &&
-				nd->inode))
-		audit_inode(name, nd->path.dentry);
-
-	path_put(&nd->root);
-	nd->root.mnt = NULL;
-
-	return retval;
+	nd->root.dentry = dentry;
+	nd->root.mnt = mnt;
+	/* the first argument of do_path_lookup() is ignored with LOOKUP_ROOT */
+	return do_path_lookup(AT_FDCWD, name, flags | LOOKUP_ROOT, nd);
 }
 
 static struct dentry *__lookup_hash(struct qstr *name,
@@ -1811,17 +1727,6 @@ static struct dentry *__lookup_hash(struct qstr *name,
 		return ERR_PTR(err);
 
 	/*
-	 * See if the low-level filesystem might want
-	 * to use its own hash..
-	 */
-	if (base->d_flags & DCACHE_OP_HASH) {
-		err = base->d_op->d_hash(base, inode, name);
-		dentry = ERR_PTR(err);
-		if (err < 0)
-			goto out;
-	}
-
-	/*
 	 * Don't bother with __d_lookup: callers are for creat as
 	 * well as unlink, so a lot of the time it would cost
 	 * a double lookup.
@@ -1833,7 +1738,7 @@ static struct dentry *__lookup_hash(struct qstr *name,
 
 	if (!dentry)
 		dentry = d_alloc_and_lookup(base, name, nd);
-out:
+
 	return dentry;
 }
 
@@ -1847,28 +1752,6 @@ static struct dentry *lookup_hash(struct nameidata *nd)
 	return __lookup_hash(&nd->last, nd->path.dentry, nd);
 }
 
-static int __lookup_one_len(const char *name, struct qstr *this,
-		struct dentry *base, int len)
-{
-	unsigned long hash;
-	unsigned int c;
-
-	this->name = name;
-	this->len = len;
-	if (!len)
-		return -EACCES;
-
-	hash = init_name_hash();
-	while (len--) {
-		c = *(const unsigned char *)name++;
-		if (c == '/' || c == '\0')
-			return -EACCES;
-		hash = partial_name_hash(c, hash);
-	}
-	this->hash = end_name_hash(hash);
-	return 0;
-}
-
 /**
  * lookup_one_len - filesystem helper to lookup single pathname component
  * @name:	pathname component to lookup
@@ -1882,14 +1765,34 @@ static int __lookup_one_len(const char *name, struct qstr *this,
  */
 struct dentry *lookup_one_len(const char *name, struct dentry *base, int len)
 {
-	int err;
 	struct qstr this;
+	unsigned long hash;
+	unsigned int c;
 
 	WARN_ON_ONCE(!mutex_is_locked(&base->d_inode->i_mutex));
 
-	err = __lookup_one_len(name, &this, base, len);
-	if (err)
-		return ERR_PTR(err);
+	this.name = name;
+	this.len = len;
+	if (!len)
+		return ERR_PTR(-EACCES);
+
+	hash = init_name_hash();
+	while (len--) {
+		c = *(const unsigned char *)name++;
+		if (c == '/' || c == '\0')
+			return ERR_PTR(-EACCES);
+		hash = partial_name_hash(c, hash);
+	}
+	this.hash = end_name_hash(hash);
+	/*
+	 * See if the low-level filesystem might want
+	 * to use its own hash..
+	 */
+	if (base->d_flags & DCACHE_OP_HASH) {
+		int err = base->d_op->d_hash(base, base->d_inode, &this);
+		if (err < 0)
+			return ERR_PTR(err);
+	}
 
 	return __lookup_hash(&this, base, NULL);
 }
@@ -1898,7 +1801,7 @@ int user_path_at(int dfd, const char __user *name, unsigned flags,
 		 struct path *path)
 {
 	struct nameidata nd;
-	char *tmp = getname(name);
+	char *tmp = getname_flags(name, flags);
 	int err = PTR_ERR(tmp);
 	if (!IS_ERR(tmp)) {
 
@@ -2078,12 +1981,16 @@ int vfs_create(struct inode *dir, struct dentry *dentry, int mode,
 	return error;
 }
 
-int may_open(struct path *path, int acc_mode, int flag)
+static int may_open(struct path *path, int acc_mode, int flag)
 {
 	struct dentry *dentry = path->dentry;
 	struct inode *inode = dentry->d_inode;
 	int error;
 
+	/* O_PATH? */
+	if (!acc_mode)
+		return 0;
+
 	if (!inode)
 		return -ENOENT;
 
@@ -2152,34 +2059,6 @@ static int handle_truncate(struct file *filp)
 }
 
 /*
- * Be careful about ever adding any more callers of this
- * function.  Its flags must be in the namei format, not
- * what get passed to sys_open().
- */
-static int __open_namei_create(struct nameidata *nd, struct path *path,
-				int open_flag, int mode)
-{
-	int error;
-	struct dentry *dir = nd->path.dentry;
-
-	if (!IS_POSIXACL(dir->d_inode))
-		mode &= ~current_umask();
-	error = security_path_mknod(&nd->path, path->dentry, mode, 0);
-	if (error)
-		goto out_unlock;
-	error = vfs_create(dir->d_inode, path->dentry, mode, nd);
-out_unlock:
-	mutex_unlock(&dir->d_inode->i_mutex);
-	dput(nd->path.dentry);
-	nd->path.dentry = path->dentry;
-
-	if (error)
-		return error;
-	/* Don't check for write permission, don't truncate */
-	return may_open(&nd->path, 0, open_flag & ~O_TRUNC);
-}
-
-/*
  * Note that while the flag value (low two bits) for sys_open means:
  *	00 - read-only
  *	01 - write-only
@@ -2203,126 +2082,115 @@ static inline int open_to_namei_flags(int flag)
 	return flag;
 }
 
-static int open_will_truncate(int flag, struct inode *inode)
-{
-	/*
-	 * We'll never write to the fs underlying
-	 * a device file.
-	 */
-	if (special_file(inode->i_mode))
-		return 0;
-	return (flag & O_TRUNC);
-}
-
-static struct file *finish_open(struct nameidata *nd,
-				int open_flag, int acc_mode)
-{
-	struct file *filp;
-	int will_truncate;
-	int error;
-
-	will_truncate = open_will_truncate(open_flag, nd->path.dentry->d_inode);
-	if (will_truncate) {
-		error = mnt_want_write(nd->path.mnt);
-		if (error)
-			goto exit;
-	}
-	error = may_open(&nd->path, acc_mode, open_flag);
-	if (error) {
-		if (will_truncate)
-			mnt_drop_write(nd->path.mnt);
-		goto exit;
-	}
-	filp = nameidata_to_filp(nd);
-	if (!IS_ERR(filp)) {
-		error = ima_file_check(filp, acc_mode);
-		if (error) {
-			fput(filp);
-			filp = ERR_PTR(error);
-		}
-	}
-	if (!IS_ERR(filp)) {
-		if (will_truncate) {
-			error = handle_truncate(filp);
-			if (error) {
-				fput(filp);
-				filp = ERR_PTR(error);
-			}
-		}
-	}
-	/*
-	 * It is now safe to drop the mnt write
-	 * because the filp has had a write taken
-	 * on its behalf.
-	 */
-	if (will_truncate)
-		mnt_drop_write(nd->path.mnt);
-	path_put(&nd->path);
-	return filp;
-
-exit:
-	path_put(&nd->path);
-	return ERR_PTR(error);
-}
-
 /*
- * Handle O_CREAT case for do_filp_open
+ * Handle the last step of open()
  */
 static struct file *do_last(struct nameidata *nd, struct path *path,
-			    int open_flag, int acc_mode,
-			    int mode, const char *pathname)
+			    const struct open_flags *op, const char *pathname)
 {
 	struct dentry *dir = nd->path.dentry;
+	struct dentry *dentry;
+	int open_flag = op->open_flag;
+	int will_truncate = open_flag & O_TRUNC;
+	int want_write = 0;
+	int acc_mode = op->acc_mode;
 	struct file *filp;
-	int error = -EISDIR;
+	int error;
+
+	nd->flags &= ~LOOKUP_PARENT;
+	nd->flags |= op->intent;
 
 	switch (nd->last_type) {
 	case LAST_DOTDOT:
-		follow_dotdot(nd);
-		dir = nd->path.dentry;
 	case LAST_DOT:
-		if (need_reval_dot(dir)) {
-			int status = d_revalidate(nd->path.dentry, nd);
-			if (!status)
-				status = -ESTALE;
-			if (status < 0) {
-				error = status;
-				goto exit;
-			}
-		}
+		error = handle_dots(nd, nd->last_type);
+		if (error)
+			return ERR_PTR(error);
 		/* fallthrough */
 	case LAST_ROOT:
-		goto exit;
+		if (nd->flags & LOOKUP_RCU) {
+			if (nameidata_drop_rcu_last(nd))
+				return ERR_PTR(-ECHILD);
+		}
+		error = handle_reval_path(nd);
+		if (error)
+			goto exit;
+		audit_inode(pathname, nd->path.dentry);
+		if (open_flag & O_CREAT) {
+			error = -EISDIR;
+			goto exit;
+		}
+		goto ok;
 	case LAST_BIND:
+		/* can't be RCU mode here */
+		error = handle_reval_path(nd);
+		if (error)
+			goto exit;
 		audit_inode(pathname, dir);
 		goto ok;
 	}
 
+	if (!(open_flag & O_CREAT)) {
+		int symlink_ok = 0;
+		if (nd->last.name[nd->last.len])
+			nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
+		if (open_flag & O_PATH && !(nd->flags & LOOKUP_FOLLOW))
+			symlink_ok = 1;
+		/* we _can_ be in RCU mode here */
+		error = walk_component(nd, path, &nd->last, LAST_NORM,
+					!symlink_ok);
+		if (error < 0)
+			return ERR_PTR(error);
+		if (error) /* symlink */
+			return NULL;
+		/* sayonara */
+		if (nd->flags & LOOKUP_RCU) {
+			if (nameidata_drop_rcu_last(nd))
+				return ERR_PTR(-ECHILD);
+		}
+
+		error = -ENOTDIR;
+		if (nd->flags & LOOKUP_DIRECTORY) {
+			if (!nd->inode->i_op->lookup)
+				goto exit;
+		}
+		audit_inode(pathname, nd->path.dentry);
+		goto ok;
+	}
+
+	/* create side of things */
+
+	if (nd->flags & LOOKUP_RCU) {
+		if (nameidata_drop_rcu_last(nd))
+			return ERR_PTR(-ECHILD);
+	}
+
+	audit_inode(pathname, dir);
+	error = -EISDIR;
 	/* trailing slashes? */
 	if (nd->last.name[nd->last.len])
 		goto exit;
 
 	mutex_lock(&dir->d_inode->i_mutex);
 
-	path->dentry = lookup_hash(nd);
-	path->mnt = nd->path.mnt;
-
-	error = PTR_ERR(path->dentry);
-	if (IS_ERR(path->dentry)) {
+	dentry = lookup_hash(nd);
+	error = PTR_ERR(dentry);
+	if (IS_ERR(dentry)) {
 		mutex_unlock(&dir->d_inode->i_mutex);
 		goto exit;
 	}
 
-	if (IS_ERR(nd->intent.open.file)) {
-		error = PTR_ERR(nd->intent.open.file);
-		goto exit_mutex_unlock;
-	}
+	path->dentry = dentry;
+	path->mnt = nd->path.mnt;
 
 	/* Negative dentry, just create the file */
-	if (!path->dentry->d_inode) {
+	if (!dentry->d_inode) {
+		int mode = op->mode;
+		if (!IS_POSIXACL(dir->d_inode))
+			mode &= ~current_umask();
 		/*
 		 * This write is needed to ensure that a
-		 * ro->rw transition does not occur between
+		 * rw->ro transition does not occur between
 		 * the time when the file is created and when
 		 * a permanent write count is taken through
 		 * the 'struct file' in nameidata_to_filp().
@@ -2330,22 +2198,21 @@ static struct file *do_last(struct nameidata *nd, struct path *path,
 		error = mnt_want_write(nd->path.mnt);
 		if (error)
 			goto exit_mutex_unlock;
-		error = __open_namei_create(nd, path, open_flag, mode);
-		if (error) {
-			mnt_drop_write(nd->path.mnt);
-			goto exit;
-		}
-		filp = nameidata_to_filp(nd);
-		mnt_drop_write(nd->path.mnt);
-		path_put(&nd->path);
-		if (!IS_ERR(filp)) {
-			error = ima_file_check(filp, acc_mode);
-			if (error) {
-				fput(filp);
-				filp = ERR_PTR(error);
-			}
-		}
-		return filp;
+		want_write = 1;
+		/* Don't check for write permission, don't truncate */
+		open_flag &= ~O_TRUNC;
+		will_truncate = 0;
+		acc_mode = MAY_OPEN;
+		error = security_path_mknod(&nd->path, dentry, mode, 0);
+		if (error)
+			goto exit_mutex_unlock;
+		error = vfs_create(dir->d_inode, dentry, mode, nd);
+		if (error)
+			goto exit_mutex_unlock;
+		mutex_unlock(&dir->d_inode->i_mutex);
+		dput(nd->path.dentry);
+		nd->path.dentry = dentry;
+		goto common;
 	}
 
 	/*
@@ -2375,7 +2242,40 @@ static struct file *do_last(struct nameidata *nd, struct path *path,
 	if (S_ISDIR(nd->inode->i_mode))
 		goto exit;
 ok:
-	filp = finish_open(nd, open_flag, acc_mode);
+	if (!S_ISREG(nd->inode->i_mode))
+		will_truncate = 0;
+
+	if (will_truncate) {
+		error = mnt_want_write(nd->path.mnt);
+		if (error)
+			goto exit;
+		want_write = 1;
+	}
+common:
+	error = may_open(&nd->path, acc_mode, open_flag);
+	if (error)
+		goto exit;
+	filp = nameidata_to_filp(nd);
+	if (!IS_ERR(filp)) {
+		error = ima_file_check(filp, op->acc_mode);
+		if (error) {
+			fput(filp);
+			filp = ERR_PTR(error);
+		}
+	}
+	if (!IS_ERR(filp)) {
+		if (will_truncate) {
+			error = handle_truncate(filp);
+			if (error) {
+				fput(filp);
+				filp = ERR_PTR(error);
+			}
+		}
+	}
+out:
+	if (want_write)
+		mnt_drop_write(nd->path.mnt);
+	path_put(&nd->path);
 	return filp;
 
 exit_mutex_unlock:
@@ -2383,204 +2283,103 @@ exit_mutex_unlock:
 exit_dput:
 	path_put_conditional(path, nd);
 exit:
-	path_put(&nd->path);
-	return ERR_PTR(error);
+	filp = ERR_PTR(error);
+	goto out;
 }
 
-/*
- * Note that the low bits of the passed in "open_flag"
- * are not the same as in the local variable "flag". See
- * open_to_namei_flags() for more details.
- */
-struct file *do_filp_open(int dfd, const char *pathname,
-		int open_flag, int mode, int acc_mode)
+static struct file *path_openat(int dfd, const char *pathname,
+		struct nameidata *nd, const struct open_flags *op, int flags)
 {
+	struct file *base = NULL;
 	struct file *filp;
-	struct nameidata nd;
-	int error;
 	struct path path;
-	int count = 0;
-	int flag = open_to_namei_flags(open_flag);
-	int flags;
-
-	if (!(open_flag & O_CREAT))
-		mode = 0;
-
-	/* Must never be set by userspace */
-	open_flag &= ~FMODE_NONOTIFY;
-
-	/*
-	 * O_SYNC is implemented as __O_SYNC|O_DSYNC.  As many places only
-	 * check for O_DSYNC if the need any syncing at all we enforce it's
-	 * always set instead of having to deal with possibly weird behaviour
-	 * for malicious applications setting only __O_SYNC.
-	 */
-	if (open_flag & __O_SYNC)
-		open_flag |= O_DSYNC;
-
-	if (!acc_mode)
-		acc_mode = MAY_OPEN | ACC_MODE(open_flag);
-
-	/* O_TRUNC implies we need access checks for write permissions */
-	if (open_flag & O_TRUNC)
-		acc_mode |= MAY_WRITE;
-
-	/* Allow the LSM permission hook to distinguish append 
-	   access from general write access. */
-	if (open_flag & O_APPEND)
-		acc_mode |= MAY_APPEND;
-
-	flags = LOOKUP_OPEN;
-	if (open_flag & O_CREAT) {
-		flags |= LOOKUP_CREATE;
-		if (open_flag & O_EXCL)
-			flags |= LOOKUP_EXCL;
-	}
-	if (open_flag & O_DIRECTORY)
-		flags |= LOOKUP_DIRECTORY;
-	if (!(open_flag & O_NOFOLLOW))
-		flags |= LOOKUP_FOLLOW;
+	int error;
 
 	filp = get_empty_filp();
 	if (!filp)
 		return ERR_PTR(-ENFILE);
 
-	filp->f_flags = open_flag;
-	nd.intent.open.file = filp;
-	nd.intent.open.flags = flag;
-	nd.intent.open.create_mode = mode;
-
-	if (open_flag & O_CREAT)
-		goto creat;
+	filp->f_flags = op->open_flag;
+	nd->intent.open.file = filp;
+	nd->intent.open.flags = open_to_namei_flags(op->open_flag);
+	nd->intent.open.create_mode = op->mode;
 
-	/* !O_CREAT, simple open */
-	error = do_path_lookup(dfd, pathname, flags, &nd);
+	error = path_init(dfd, pathname, flags | LOOKUP_PARENT, nd, &base);
 	if (unlikely(error))
-		goto out_filp2;
-	error = -ELOOP;
-	if (!(nd.flags & LOOKUP_FOLLOW)) {
-		if (nd.inode->i_op->follow_link)
-			goto out_path2;
-	}
-	error = -ENOTDIR;
-	if (nd.flags & LOOKUP_DIRECTORY) {
-		if (!nd.inode->i_op->lookup)
-			goto out_path2;
-	}
-	audit_inode(pathname, nd.path.dentry);
-	filp = finish_open(&nd, open_flag, acc_mode);
-out2:
-	release_open_intent(&nd);
-	return filp;
-
-out_path2:
-	path_put(&nd.path);
-out_filp2:
-	filp = ERR_PTR(error);
-	goto out2;
-
-creat:
-	/* OK, have to create the file. Find the parent. */
-	error = path_init_rcu(dfd, pathname,
-			LOOKUP_PARENT | (flags & LOOKUP_REVAL), &nd);
-	if (error)
 		goto out_filp;
-	error = path_walk_rcu(pathname, &nd);
-	path_finish_rcu(&nd);
-	if (unlikely(error == -ECHILD || error == -ESTALE)) {
-		/* slower, locked walk */
-		if (error == -ESTALE) {
-reval:
-			flags |= LOOKUP_REVAL;
-		}
-		error = path_init(dfd, pathname,
-				LOOKUP_PARENT | (flags & LOOKUP_REVAL), &nd);
-		if (error)
-			goto out_filp;
 
-		error = path_walk_simple(pathname, &nd);
-	}
+	current->total_link_count = 0;
+	error = link_path_walk(pathname, nd);
 	if (unlikely(error))
 		goto out_filp;
-	if (unlikely(!audit_dummy_context()))
-		audit_inode(pathname, nd.path.dentry);
 
-	/*
-	 * We have the parent and last component.
-	 */
-	nd.flags = flags;
-	filp = do_last(&nd, &path, open_flag, acc_mode, mode, pathname);
+	filp = do_last(nd, &path, op, pathname);
 	while (unlikely(!filp)) { /* trailing symlink */
 		struct path link = path;
-		struct inode *linki = link.dentry->d_inode;
 		void *cookie;
-		error = -ELOOP;
-		if (!(nd.flags & LOOKUP_FOLLOW))
-			goto exit_dput;
-		if (count++ == 32)
-			goto exit_dput;
-		/*
-		 * This is subtle. Instead of calling do_follow_link() we do
-		 * the thing by hands. The reason is that this way we have zero
-		 * link_count and path_walk() (called from ->follow_link)
-		 * honoring LOOKUP_PARENT.  After that we have the parent and
-		 * last component, i.e. we are in the same situation as after
-		 * the first path_walk().  Well, almost - if the last component
-		 * is normal we get its copy stored in nd->last.name and we will
-		 * have to putname() it when we are done. Procfs-like symlinks
-		 * just set LAST_BIND.
-		 */
-		nd.flags |= LOOKUP_PARENT;
-		error = security_inode_follow_link(link.dentry, &nd);
-		if (error)
-			goto exit_dput;
-		error = __do_follow_link(&link, &nd, &cookie);
-		if (unlikely(error)) {
-			if (!IS_ERR(cookie) && linki->i_op->put_link)
-				linki->i_op->put_link(link.dentry, &nd, cookie);
-			/* nd.path had been dropped */
-			nd.path = link;
-			goto out_path;
+		if (!(nd->flags & LOOKUP_FOLLOW)) {
+			path_put_conditional(&path, nd);
+			path_put(&nd->path);
+			filp = ERR_PTR(-ELOOP);
+			break;
 		}
-		nd.flags &= ~LOOKUP_PARENT;
-		filp = do_last(&nd, &path, open_flag, acc_mode, mode, pathname);
-		if (linki->i_op->put_link)
-			linki->i_op->put_link(link.dentry, &nd, cookie);
-		path_put(&link);
+		nd->flags |= LOOKUP_PARENT;
+		nd->flags &= ~(LOOKUP_OPEN|LOOKUP_CREATE|LOOKUP_EXCL);
+		error = follow_link(&link, nd, &cookie);
+		if (unlikely(error))
+			filp = ERR_PTR(error);
+		else
+			filp = do_last(nd, &path, op, pathname);
+		put_link(nd, &link, cookie);
 	}
 out:
-	if (nd.root.mnt)
-		path_put(&nd.root);
-	if (filp == ERR_PTR(-ESTALE) && !(flags & LOOKUP_REVAL))
-		goto reval;
-	release_open_intent(&nd);
+	if (nd->root.mnt && !(nd->flags & LOOKUP_ROOT))
+		path_put(&nd->root);
+	if (base)
+		fput(base);
+	release_open_intent(nd);
 	return filp;
 
-exit_dput:
-	path_put_conditional(&path, &nd);
-out_path:
-	path_put(&nd.path);
 out_filp:
 	filp = ERR_PTR(error);
 	goto out;
 }
 
-/**
- * filp_open - open file and return file pointer
- *
- * @filename:	path to open
- * @flags:	open flags as per the open(2) second argument
- * @mode:	mode for the new file if O_CREAT is set, else ignored
- *
- * This is the helper to open a file from kernelspace if you really
- * have to.  But in generally you should not do this, so please move
- * along, nothing to see here..
- */
-struct file *filp_open(const char *filename, int flags, int mode)
+struct file *do_filp_open(int dfd, const char *pathname,
+		const struct open_flags *op, int flags)
 {
-	return do_filp_open(AT_FDCWD, filename, flags, mode, 0);
+	struct nameidata nd;
+	struct file *filp;
+
+	filp = path_openat(dfd, pathname, &nd, op, flags | LOOKUP_RCU);
+	if (unlikely(filp == ERR_PTR(-ECHILD)))
+		filp = path_openat(dfd, pathname, &nd, op, flags);
+	if (unlikely(filp == ERR_PTR(-ESTALE)))
+		filp = path_openat(dfd, pathname, &nd, op, flags | LOOKUP_REVAL);
+	return filp;
+}
+
+struct file *do_file_open_root(struct dentry *dentry, struct vfsmount *mnt,
+		const char *name, const struct open_flags *op, int flags)
+{
+	struct nameidata nd;
+	struct file *file;
+
+	nd.root.mnt = mnt;
+	nd.root.dentry = dentry;
+
+	flags |= LOOKUP_ROOT;
+
+	if (dentry->d_inode->i_op->follow_link && op->intent & LOOKUP_OPEN)
+		return ERR_PTR(-ELOOP);
+
+	file = path_openat(-1, name, &nd, op, flags | LOOKUP_RCU);
+	if (unlikely(file == ERR_PTR(-ECHILD)))
+		file = path_openat(-1, name, &nd, op, flags);
+	if (unlikely(file == ERR_PTR(-ESTALE)))
+		file = path_openat(-1, name, &nd, op, flags | LOOKUP_REVAL);
+	return file;
 }
-EXPORT_SYMBOL(filp_open);
 
 /**
  * lookup_create - lookup a dentry, creating it if it doesn't exist
@@ -3119,7 +2918,11 @@ int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_de
 		return error;
 
 	mutex_lock(&inode->i_mutex);
-	error = dir->i_op->link(old_dentry, dir, new_dentry);
+	/* Make sure we don't allow creating hardlink to an unlinked file */
+	if (inode->i_nlink == 0)
+		error =  -ENOENT;
+	else
+		error = dir->i_op->link(old_dentry, dir, new_dentry);
 	mutex_unlock(&inode->i_mutex);
 	if (!error)
 		fsnotify_link(dir, inode, new_dentry);
@@ -3141,15 +2944,27 @@ SYSCALL_DEFINE5(linkat, int, olddfd, const char __user *, oldname,
 	struct dentry *new_dentry;
 	struct nameidata nd;
 	struct path old_path;
+	int how = 0;
 	int error;
 	char *to;
 
-	if ((flags & ~AT_SYMLINK_FOLLOW) != 0)
+	if ((flags & ~(AT_SYMLINK_FOLLOW | AT_EMPTY_PATH)) != 0)
 		return -EINVAL;
+	/*
+	 * To use null names we require CAP_DAC_READ_SEARCH
+	 * This ensures that not everyone will be able to create
+	 * handlink using the passed filedescriptor.
+	 */
+	if (flags & AT_EMPTY_PATH) {
+		if (!capable(CAP_DAC_READ_SEARCH))
+			return -ENOENT;
+		how = LOOKUP_EMPTY;
+	}
+
+	if (flags & AT_SYMLINK_FOLLOW)
+		how |= LOOKUP_FOLLOW;
 
-	error = user_path_at(olddfd, oldname,
-			     flags & AT_SYMLINK_FOLLOW ? LOOKUP_FOLLOW : 0,
-			     &old_path);
+	error = user_path_at(olddfd, oldname, how, &old_path);
 	if (error)
 		return error;
 
@@ -3586,7 +3401,7 @@ EXPORT_SYMBOL(page_readlink);
 EXPORT_SYMBOL(__page_symlink);
 EXPORT_SYMBOL(page_symlink);
 EXPORT_SYMBOL(page_symlink_inode_operations);
-EXPORT_SYMBOL(path_lookup);
+EXPORT_SYMBOL(kern_path_parent);
 EXPORT_SYMBOL(kern_path);
 EXPORT_SYMBOL(vfs_path_lookup);
 EXPORT_SYMBOL(inode_permission);
diff --git a/fs/namespace.c b/fs/namespace.c
index d1edf26025dc..dffe6f49ab93 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1002,6 +1002,18 @@ const struct seq_operations mounts_op = {
 	.show	= show_vfsmnt
 };
 
+static int uuid_is_nil(u8 *uuid)
+{
+	int i;
+	u8  *cp = (u8 *)uuid;
+
+	for (i = 0; i < 16; i++) {
+		if (*cp++)
+			return 0;
+	}
+	return 1;
+}
+
 static int show_mountinfo(struct seq_file *m, void *v)
 {
 	struct proc_mounts *p = m->private;
@@ -1040,6 +1052,10 @@ static int show_mountinfo(struct seq_file *m, void *v)
 	if (IS_MNT_UNBINDABLE(mnt))
 		seq_puts(m, " unbindable");
 
+	if (!uuid_is_nil(mnt->mnt_sb->s_uuid))
+		/* print the uuid */
+		seq_printf(m, " uuid:%pU", mnt->mnt_sb->s_uuid);
+
 	/* Filesystem specific data */
 	seq_puts(m, " - ");
 	show_type(m, sb);
diff --git a/fs/nfsctl.c b/fs/nfsctl.c
index bf9cbd242ddd..124e8fcb0dd6 100644
--- a/fs/nfsctl.c
+++ b/fs/nfsctl.c
@@ -22,30 +22,17 @@
 
 static struct file *do_open(char *name, int flags)
 {
-	struct nameidata nd;
 	struct vfsmount *mnt;
-	int error;
+	struct file *file;
 
 	mnt = do_kern_mount("nfsd", 0, "nfsd", NULL);
 	if (IS_ERR(mnt))
 		return (struct file *)mnt;
 
-	error = vfs_path_lookup(mnt->mnt_root, mnt, name, 0, &nd);
-	mntput(mnt);	/* drop do_kern_mount reference */
-	if (error)
-		return ERR_PTR(error);
-
-	if (flags == O_RDWR)
-		error = may_open(&nd.path, MAY_READ|MAY_WRITE, flags);
-	else
-		error = may_open(&nd.path, MAY_WRITE, flags);
+	file = file_open_root(mnt->mnt_root, mnt, name, flags);
 
-	if (!error)
-		return dentry_open(nd.path.dentry, nd.path.mnt, flags,
-				   current_cred());
-
-	path_put(&nd.path);
-	return ERR_PTR(error);
+	mntput(mnt);	/* drop do_kern_mount reference */
+	return file;
 }
 
 static struct {
diff --git a/fs/ocfs2/export.c b/fs/ocfs2/export.c
index 5dbc3062b4fd..254652a9b542 100644
--- a/fs/ocfs2/export.c
+++ b/fs/ocfs2/export.c
@@ -197,8 +197,12 @@ static int ocfs2_encode_fh(struct dentry *dentry, u32 *fh_in, int *max_len,
 		   dentry->d_name.len, dentry->d_name.name,
 		   fh, len, connectable);
 
-	if (len < 3 || (connectable && len < 6)) {
-		mlog(ML_ERROR, "fh buffer is too small for encoding\n");
+	if (connectable && (len < 6)) {
+		*max_len = 6;
+		type = 255;
+		goto bail;
+	} else if (len < 3) {
+		*max_len = 3;
 		type = 255;
 		goto bail;
 	}
diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index 19ebc5aad391..29623da133cc 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -4379,7 +4379,7 @@ static int ocfs2_user_path_parent(const char __user *path,
 	if (IS_ERR(s))
 		return PTR_ERR(s);
 
-	error = path_lookup(s, LOOKUP_PARENT, nd);
+	error = kern_path_parent(s, nd);
 	if (error)
 		putname(s);
 	else
diff --git a/fs/open.c b/fs/open.c
index b47aab39c057..3cac0bda46df 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -573,13 +573,15 @@ SYSCALL_DEFINE5(fchownat, int, dfd, const char __user *, filename, uid_t, user,
 {
 	struct path path;
 	int error = -EINVAL;
-	int follow;
+	int lookup_flags;
 
-	if ((flag & ~AT_SYMLINK_NOFOLLOW) != 0)
+	if ((flag & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0)
 		goto out;
 
-	follow = (flag & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW;
-	error = user_path_at(dfd, filename, follow, &path);
+	lookup_flags = (flag & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW;
+	if (flag & AT_EMPTY_PATH)
+		lookup_flags |= LOOKUP_EMPTY;
+	error = user_path_at(dfd, filename, lookup_flags, &path);
 	if (error)
 		goto out;
 	error = mnt_want_write(path.mnt);
@@ -669,11 +671,16 @@ static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt,
 					int (*open)(struct inode *, struct file *),
 					const struct cred *cred)
 {
+	static const struct file_operations empty_fops = {};
 	struct inode *inode;
 	int error;
 
 	f->f_mode = OPEN_FMODE(f->f_flags) | FMODE_LSEEK |
 				FMODE_PREAD | FMODE_PWRITE;
+
+	if (unlikely(f->f_flags & O_PATH))
+		f->f_mode = FMODE_PATH;
+
 	inode = dentry->d_inode;
 	if (f->f_mode & FMODE_WRITE) {
 		error = __get_file_write_access(inode, mnt);
@@ -687,9 +694,15 @@ static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt,
 	f->f_path.dentry = dentry;
 	f->f_path.mnt = mnt;
 	f->f_pos = 0;
-	f->f_op = fops_get(inode->i_fop);
 	file_sb_list_add(f, inode->i_sb);
 
+	if (unlikely(f->f_mode & FMODE_PATH)) {
+		f->f_op = &empty_fops;
+		return f;
+	}
+
+	f->f_op = fops_get(inode->i_fop);
+
 	error = security_dentry_open(f, cred);
 	if (error)
 		goto cleanup_all;
@@ -890,15 +903,110 @@ void fd_install(unsigned int fd, struct file *file)
 
 EXPORT_SYMBOL(fd_install);
 
+static inline int build_open_flags(int flags, int mode, struct open_flags *op)
+{
+	int lookup_flags = 0;
+	int acc_mode;
+
+	if (!(flags & O_CREAT))
+		mode = 0;
+	op->mode = mode;
+
+	/* Must never be set by userspace */
+	flags &= ~FMODE_NONOTIFY;
+
+	/*
+	 * O_SYNC is implemented as __O_SYNC|O_DSYNC.  As many places only
+	 * check for O_DSYNC if the need any syncing at all we enforce it's
+	 * always set instead of having to deal with possibly weird behaviour
+	 * for malicious applications setting only __O_SYNC.
+	 */
+	if (flags & __O_SYNC)
+		flags |= O_DSYNC;
+
+	/*
+	 * If we have O_PATH in the open flag. Then we
+	 * cannot have anything other than the below set of flags
+	 */
+	if (flags & O_PATH) {
+		flags &= O_DIRECTORY | O_NOFOLLOW | O_PATH;
+		acc_mode = 0;
+	} else {
+		acc_mode = MAY_OPEN | ACC_MODE(flags);
+	}
+
+	op->open_flag = flags;
+
+	/* O_TRUNC implies we need access checks for write permissions */
+	if (flags & O_TRUNC)
+		acc_mode |= MAY_WRITE;
+
+	/* Allow the LSM permission hook to distinguish append
+	   access from general write access. */
+	if (flags & O_APPEND)
+		acc_mode |= MAY_APPEND;
+
+	op->acc_mode = acc_mode;
+
+	op->intent = flags & O_PATH ? 0 : LOOKUP_OPEN;
+
+	if (flags & O_CREAT) {
+		op->intent |= LOOKUP_CREATE;
+		if (flags & O_EXCL)
+			op->intent |= LOOKUP_EXCL;
+	}
+
+	if (flags & O_DIRECTORY)
+		lookup_flags |= LOOKUP_DIRECTORY;
+	if (!(flags & O_NOFOLLOW))
+		lookup_flags |= LOOKUP_FOLLOW;
+	return lookup_flags;
+}
+
+/**
+ * filp_open - open file and return file pointer
+ *
+ * @filename:	path to open
+ * @flags:	open flags as per the open(2) second argument
+ * @mode:	mode for the new file if O_CREAT is set, else ignored
+ *
+ * This is the helper to open a file from kernelspace if you really
+ * have to.  But in generally you should not do this, so please move
+ * along, nothing to see here..
+ */
+struct file *filp_open(const char *filename, int flags, int mode)
+{
+	struct open_flags op;
+	int lookup = build_open_flags(flags, mode, &op);
+	return do_filp_open(AT_FDCWD, filename, &op, lookup);
+}
+EXPORT_SYMBOL(filp_open);
+
+struct file *file_open_root(struct dentry *dentry, struct vfsmount *mnt,
+			    const char *filename, int flags)
+{
+	struct open_flags op;
+	int lookup = build_open_flags(flags, 0, &op);
+	if (flags & O_CREAT)
+		return ERR_PTR(-EINVAL);
+	if (!filename && (flags & O_DIRECTORY))
+		if (!dentry->d_inode->i_op->lookup)
+			return ERR_PTR(-ENOTDIR);
+	return do_file_open_root(dentry, mnt, filename, &op, lookup);
+}
+EXPORT_SYMBOL(file_open_root);
+
 long do_sys_open(int dfd, const char __user *filename, int flags, int mode)
 {
+	struct open_flags op;
+	int lookup = build_open_flags(flags, mode, &op);
 	char *tmp = getname(filename);
 	int fd = PTR_ERR(tmp);
 
 	if (!IS_ERR(tmp)) {
 		fd = get_unused_fd_flags(flags);
 		if (fd >= 0) {
-			struct file *f = do_filp_open(dfd, tmp, flags, mode, 0);
+			struct file *f = do_filp_open(dfd, tmp, &op, lookup);
 			if (IS_ERR(f)) {
 				put_unused_fd(fd);
 				fd = PTR_ERR(f);
@@ -968,8 +1076,10 @@ int filp_close(struct file *filp, fl_owner_t id)
 	if (filp->f_op && filp->f_op->flush)
 		retval = filp->f_op->flush(filp, id);
 
-	dnotify_flush(filp, id);
-	locks_remove_posix(filp, id);
+	if (likely(!(filp->f_mode & FMODE_PATH))) {
+		dnotify_flush(filp, id);
+		locks_remove_posix(filp, id);
+	}
 	fput(filp);
 	return retval;
 }
diff --git a/fs/partitions/osf.c b/fs/partitions/osf.c
index be03a0b08b47..764b86a01965 100644
--- a/fs/partitions/osf.c
+++ b/fs/partitions/osf.c
@@ -10,7 +10,7 @@
 #include "check.h"
 #include "osf.h"
 
-#define MAX_OSF_PARTITIONS 8
+#define MAX_OSF_PARTITIONS 18
 
 int osf_partition(struct parsed_partitions *state)
 {
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index 0bae036831e2..1bba24bad820 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -1593,8 +1593,13 @@ int reiserfs_encode_fh(struct dentry *dentry, __u32 * data, int *lenp,
 	struct inode *inode = dentry->d_inode;
 	int maxlen = *lenp;
 
-	if (maxlen < 3)
+	if (need_parent && (maxlen < 5)) {
+		*lenp = 5;
 		return 255;
+	} else if (maxlen < 3) {
+		*lenp = 3;
+		return 255;
+	}
 
 	data[0] = inode->i_ino;
 	data[1] = le32_to_cpu(INODE_PKEY(inode)->k_dir_id);
diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c
index 68fdf45cc6c9..4b2eb564fdad 100644
--- a/fs/reiserfs/namei.c
+++ b/fs/reiserfs/namei.c
@@ -1122,10 +1122,6 @@ static int reiserfs_link(struct dentry *old_dentry, struct inode *dir,
 		reiserfs_write_unlock(dir->i_sb);
 		return -EMLINK;
 	}
-	if (inode->i_nlink == 0) {
-		reiserfs_write_unlock(dir->i_sb);
-		return -ENOENT;
-	}
 
 	/* inc before scheduling so reiserfs_unlink knows we are here */
 	inc_nlink(inode);
diff --git a/fs/stat.c b/fs/stat.c
index d5c61cf2b703..961039121cb8 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -75,13 +75,16 @@ int vfs_fstatat(int dfd, const char __user *filename, struct kstat *stat,
 	int error = -EINVAL;
 	int lookup_flags = 0;
 
-	if ((flag & ~(AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT)) != 0)
+	if ((flag & ~(AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT |
+		      AT_EMPTY_PATH)) != 0)
 		goto out;
 
 	if (!(flag & AT_SYMLINK_NOFOLLOW))
 		lookup_flags |= LOOKUP_FOLLOW;
 	if (flag & AT_NO_AUTOMOUNT)
 		lookup_flags |= LOOKUP_NO_AUTOMOUNT;
+	if (flag & AT_EMPTY_PATH)
+		lookup_flags |= LOOKUP_EMPTY;
 
 	error = user_path_at(dfd, filename, lookup_flags, &path);
 	if (error)
@@ -297,7 +300,7 @@ SYSCALL_DEFINE4(readlinkat, int, dfd, const char __user *, pathname,
 	if (bufsiz <= 0)
 		return -EINVAL;
 
-	error = user_path_at(dfd, pathname, 0, &path);
+	error = user_path_at(dfd, pathname, LOOKUP_EMPTY, &path);
 	if (!error) {
 		struct inode *inode = path.dentry->d_inode;
 
diff --git a/fs/statfs.c b/fs/statfs.c
index 30ea8c8a996b..8244924dec55 100644
--- a/fs/statfs.c
+++ b/fs/statfs.c
@@ -73,149 +73,135 @@ int vfs_statfs(struct path *path, struct kstatfs *buf)
 }
 EXPORT_SYMBOL(vfs_statfs);
 
-static int do_statfs_native(struct path *path, struct statfs *buf)
+int user_statfs(const char __user *pathname, struct kstatfs *st)
 {
-	struct kstatfs st;
-	int retval;
+	struct path path;
+	int error = user_path(pathname, &path);
+	if (!error) {
+		error = vfs_statfs(&path, st);
+		path_put(&path);
+	}
+	return error;
+}
 
-	retval = vfs_statfs(path, &st);
-	if (retval)
-		return retval;
+int fd_statfs(int fd, struct kstatfs *st)
+{
+	struct file *file = fget(fd);
+	int error = -EBADF;
+	if (file) {
+		error = vfs_statfs(&file->f_path, st);
+		fput(file);
+	}
+	return error;
+}
 
-	if (sizeof(*buf) == sizeof(st))
-		memcpy(buf, &st, sizeof(st));
+static int do_statfs_native(struct kstatfs *st, struct statfs __user *p)
+{
+	struct statfs buf;
+
+	if (sizeof(buf) == sizeof(*st))
+		memcpy(&buf, st, sizeof(*st));
 	else {
-		if (sizeof buf->f_blocks == 4) {
-			if ((st.f_blocks | st.f_bfree | st.f_bavail |
-			     st.f_bsize | st.f_frsize) &
+		if (sizeof buf.f_blocks == 4) {
+			if ((st->f_blocks | st->f_bfree | st->f_bavail |
+			     st->f_bsize | st->f_frsize) &
 			    0xffffffff00000000ULL)
 				return -EOVERFLOW;
 			/*
 			 * f_files and f_ffree may be -1; it's okay to stuff
 			 * that into 32 bits
 			 */
-			if (st.f_files != -1 &&
-			    (st.f_files & 0xffffffff00000000ULL))
+			if (st->f_files != -1 &&
+			    (st->f_files & 0xffffffff00000000ULL))
 				return -EOVERFLOW;
-			if (st.f_ffree != -1 &&
-			    (st.f_ffree & 0xffffffff00000000ULL))
+			if (st->f_ffree != -1 &&
+			    (st->f_ffree & 0xffffffff00000000ULL))
 				return -EOVERFLOW;
 		}
 
-		buf->f_type = st.f_type;
-		buf->f_bsize = st.f_bsize;
-		buf->f_blocks = st.f_blocks;
-		buf->f_bfree = st.f_bfree;
-		buf->f_bavail = st.f_bavail;
-		buf->f_files = st.f_files;
-		buf->f_ffree = st.f_ffree;
-		buf->f_fsid = st.f_fsid;
-		buf->f_namelen = st.f_namelen;
-		buf->f_frsize = st.f_frsize;
-		buf->f_flags = st.f_flags;
-		memset(buf->f_spare, 0, sizeof(buf->f_spare));
+		buf.f_type = st->f_type;
+		buf.f_bsize = st->f_bsize;
+		buf.f_blocks = st->f_blocks;
+		buf.f_bfree = st->f_bfree;
+		buf.f_bavail = st->f_bavail;
+		buf.f_files = st->f_files;
+		buf.f_ffree = st->f_ffree;
+		buf.f_fsid = st->f_fsid;
+		buf.f_namelen = st->f_namelen;
+		buf.f_frsize = st->f_frsize;
+		buf.f_flags = st->f_flags;
+		memset(buf.f_spare, 0, sizeof(buf.f_spare));
 	}
+	if (copy_to_user(p, &buf, sizeof(buf)))
+		return -EFAULT;
 	return 0;
 }
 
-static int do_statfs64(struct path *path, struct statfs64 *buf)
+static int do_statfs64(struct kstatfs *st, struct statfs64 __user *p)
 {
-	struct kstatfs st;
-	int retval;
-
-	retval = vfs_statfs(path, &st);
-	if (retval)
-		return retval;
-
-	if (sizeof(*buf) == sizeof(st))
-		memcpy(buf, &st, sizeof(st));
+	struct statfs64 buf;
+	if (sizeof(buf) == sizeof(*st))
+		memcpy(&buf, st, sizeof(*st));
 	else {
-		buf->f_type = st.f_type;
-		buf->f_bsize = st.f_bsize;
-		buf->f_blocks = st.f_blocks;
-		buf->f_bfree = st.f_bfree;
-		buf->f_bavail = st.f_bavail;
-		buf->f_files = st.f_files;
-		buf->f_ffree = st.f_ffree;
-		buf->f_fsid = st.f_fsid;
-		buf->f_namelen = st.f_namelen;
-		buf->f_frsize = st.f_frsize;
-		buf->f_flags = st.f_flags;
-		memset(buf->f_spare, 0, sizeof(buf->f_spare));
+		buf.f_type = st->f_type;
+		buf.f_bsize = st->f_bsize;
+		buf.f_blocks = st->f_blocks;
+		buf.f_bfree = st->f_bfree;
+		buf.f_bavail = st->f_bavail;
+		buf.f_files = st->f_files;
+		buf.f_ffree = st->f_ffree;
+		buf.f_fsid = st->f_fsid;
+		buf.f_namelen = st->f_namelen;
+		buf.f_frsize = st->f_frsize;
+		buf.f_flags = st->f_flags;
+		memset(buf.f_spare, 0, sizeof(buf.f_spare));
 	}
+	if (copy_to_user(p, &buf, sizeof(buf)))
+		return -EFAULT;
 	return 0;
 }
 
 SYSCALL_DEFINE2(statfs, const char __user *, pathname, struct statfs __user *, buf)
 {
-	struct path path;
-	int error;
-
-	error = user_path(pathname, &path);
-	if (!error) {
-		struct statfs tmp;
-		error = do_statfs_native(&path, &tmp);
-		if (!error && copy_to_user(buf, &tmp, sizeof(tmp)))
-			error = -EFAULT;
-		path_put(&path);
-	}
+	struct kstatfs st;
+	int error = user_statfs(pathname, &st);
+	if (!error)
+		error = do_statfs_native(&st, buf);
 	return error;
 }
 
 SYSCALL_DEFINE3(statfs64, const char __user *, pathname, size_t, sz, struct statfs64 __user *, buf)
 {
-	struct path path;
-	long error;
-
+	struct kstatfs st;
+	int error;
 	if (sz != sizeof(*buf))
 		return -EINVAL;
-	error = user_path(pathname, &path);
-	if (!error) {
-		struct statfs64 tmp;
-		error = do_statfs64(&path, &tmp);
-		if (!error && copy_to_user(buf, &tmp, sizeof(tmp)))
-			error = -EFAULT;
-		path_put(&path);
-	}
+	error = user_statfs(pathname, &st);
+	if (!error)
+		error = do_statfs64(&st, buf);
 	return error;
 }
 
 SYSCALL_DEFINE2(fstatfs, unsigned int, fd, struct statfs __user *, buf)
 {
-	struct file *file;
-	struct statfs tmp;
-	int error;
-
-	error = -EBADF;
-	file = fget(fd);
-	if (!file)
-		goto out;
-	error = do_statfs_native(&file->f_path, &tmp);
-	if (!error && copy_to_user(buf, &tmp, sizeof(tmp)))
-		error = -EFAULT;
-	fput(file);
-out:
+	struct kstatfs st;
+	int error = fd_statfs(fd, &st);
+	if (!error)
+		error = do_statfs_native(&st, buf);
 	return error;
 }
 
 SYSCALL_DEFINE3(fstatfs64, unsigned int, fd, size_t, sz, struct statfs64 __user *, buf)
 {
-	struct file *file;
-	struct statfs64 tmp;
+	struct kstatfs st;
 	int error;
 
 	if (sz != sizeof(*buf))
 		return -EINVAL;
 
-	error = -EBADF;
-	file = fget(fd);
-	if (!file)
-		goto out;
-	error = do_statfs64(&file->f_path, &tmp);
-	if (!error && copy_to_user(buf, &tmp, sizeof(tmp)))
-		error = -EFAULT;
-	fput(file);
-out:
+	error = fd_statfs(fd, &st);
+	if (!error)
+		error = do_statfs64(&st, buf);
 	return error;
 }
 
diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c
index 14f64b689d7f..7217d67a80a6 100644
--- a/fs/ubifs/dir.c
+++ b/fs/ubifs/dir.c
@@ -522,24 +522,6 @@ static int ubifs_link(struct dentry *old_dentry, struct inode *dir,
 	ubifs_assert(mutex_is_locked(&dir->i_mutex));
 	ubifs_assert(mutex_is_locked(&inode->i_mutex));
 
-	/*
-	 * Return -ENOENT if we've raced with unlink and i_nlink is 0.  Doing
-	 * otherwise has the potential to corrupt the orphan inode list.
-	 *
-	 * Indeed, consider a scenario when 'vfs_link(dirA/fileA)' and
-	 * 'vfs_unlink(dirA/fileA, dirB/fileB)' race. 'vfs_link()' does not
-	 * lock 'dirA->i_mutex', so this is possible. Both of the functions
-	 * lock 'fileA->i_mutex' though. Suppose 'vfs_unlink()' wins, and takes
-	 * 'fileA->i_mutex' mutex first. Suppose 'fileA->i_nlink' is 1. In this
-	 * case 'ubifs_unlink()' will drop the last reference, and put 'inodeA'
-	 * to the list of orphans. After this, 'vfs_link()' will link
-	 * 'dirB/fileB' to 'inodeA'. This is a problem because, for example,
-	 * the subsequent 'vfs_unlink(dirB/fileB)' will add the same inode
-	 * to the list of orphans.
-	 */
-	 if (inode->i_nlink == 0)
-		 return -ENOENT;
-
 	err = dbg_check_synced_i_size(inode);
 	if (err)
 		return err;
diff --git a/fs/udf/namei.c b/fs/udf/namei.c
index b7c338d5e9df..f1dce848ef96 100644
--- a/fs/udf/namei.c
+++ b/fs/udf/namei.c
@@ -1286,8 +1286,13 @@ static int udf_encode_fh(struct dentry *de, __u32 *fh, int *lenp,
 	struct fid *fid = (struct fid *)fh;
 	int type = FILEID_UDF_WITHOUT_PARENT;
 
-	if (len < 3 || (connectable && len < 5))
+	if (connectable && (len < 5)) {
+		*lenp = 5;
+		return 255;
+	} else if (len < 3) {
+		*lenp = 3;
 		return 255;
+	}
 
 	*lenp = 3;
 	fid->udf.block = location.logicalBlockNum;
diff --git a/fs/xfs/linux-2.6/xfs_export.c b/fs/xfs/linux-2.6/xfs_export.c
index fc0114da7fdd..f4f878fc0083 100644
--- a/fs/xfs/linux-2.6/xfs_export.c
+++ b/fs/xfs/linux-2.6/xfs_export.c
@@ -89,8 +89,10 @@ xfs_fs_encode_fh(
 	 * seven combinations work.  The real answer is "don't use v2".
 	 */
 	len = xfs_fileid_length(fileid_type);
-	if (*max_len < len)
+	if (*max_len < len) {
+		*max_len = len;
 		return 255;
+	}
 	*max_len = len;
 
 	switch (fileid_type) {
diff --git a/include/asm-generic/cputime.h b/include/asm-generic/cputime.h
index 2bcc5c7c22a6..61e03dd7939e 100644
--- a/include/asm-generic/cputime.h
+++ b/include/asm-generic/cputime.h
@@ -30,6 +30,9 @@ typedef u64 cputime64_t;
 #define cputime64_to_jiffies64(__ct)	(__ct)
 #define jiffies64_to_cputime64(__jif)	(__jif)
 #define cputime_to_cputime64(__ct)	((u64) __ct)
+#define cputime64_gt(__a, __b)		((__a) >  (__b))
+
+#define nsecs_to_cputime64(__ct)	nsecs_to_jiffies64(__ct)
 
 
 /*
diff --git a/include/asm-generic/fcntl.h b/include/asm-generic/fcntl.h
index 0fc16e3f0bfc..84793c7025e2 100644
--- a/include/asm-generic/fcntl.h
+++ b/include/asm-generic/fcntl.h
@@ -80,6 +80,10 @@
 #define O_SYNC		(__O_SYNC|O_DSYNC)
 #endif
 
+#ifndef O_PATH
+#define O_PATH		010000000
+#endif
+
 #ifndef O_NDELAY
 #define O_NDELAY	O_NONBLOCK
 #endif
diff --git a/include/asm-generic/futex.h b/include/asm-generic/futex.h
index 3c2344f48136..01f227e14254 100644
--- a/include/asm-generic/futex.h
+++ b/include/asm-generic/futex.h
@@ -6,7 +6,7 @@
 #include <asm/errno.h>
 
 static inline int
-futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
+futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 {
 	int op = (encoded_op >> 28) & 7;
 	int cmp = (encoded_op >> 24) & 15;
@@ -16,7 +16,7 @@ futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
 	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
 		oparg = 1 << oparg;
 
-	if (! access_ok (VERIFY_WRITE, uaddr, sizeof(int)))
+	if (! access_ok (VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
 	pagefault_disable();
@@ -48,7 +48,8 @@ futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
 }
 
 static inline int
-futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+			      u32 oldval, u32 newval)
 {
 	return -ENOSYS;
 }
diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h
index b3bfabc258f3..c1a1216e29ce 100644
--- a/include/asm-generic/sections.h
+++ b/include/asm-generic/sections.h
@@ -11,6 +11,7 @@ extern char _sinittext[], _einittext[];
 extern char _end[];
 extern char __per_cpu_load[], __per_cpu_start[], __per_cpu_end[];
 extern char __kprobes_text_start[], __kprobes_text_end[];
+extern char __entry_text_start[], __entry_text_end[];
 extern char __initdata_begin[], __initdata_end[];
 extern char __start_rodata[], __end_rodata[];
 
diff --git a/include/asm-generic/unistd.h b/include/asm-generic/unistd.h
index b969770196c2..57af0338d270 100644
--- a/include/asm-generic/unistd.h
+++ b/include/asm-generic/unistd.h
@@ -646,9 +646,13 @@ __SYSCALL(__NR_prlimit64, sys_prlimit64)
 __SYSCALL(__NR_fanotify_init, sys_fanotify_init)
 #define __NR_fanotify_mark 263
 __SYSCALL(__NR_fanotify_mark, sys_fanotify_mark)
+#define __NR_name_to_handle_at		264
+__SYSCALL(__NR_name_to_handle_at, sys_name_to_handle_at)
+#define __NR_open_by_handle_at		265
+__SYSCALL(__NR_open_by_handle_at, sys_open_by_handle_at)
 
 #undef __NR_syscalls
-#define __NR_syscalls 264
+#define __NR_syscalls 266
 
 /*
  * All syscalls below here should go away really,
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index fe77e3395b40..906c3ceca9a2 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -424,6 +424,12 @@
 		*(.kprobes.text)					\
 		VMLINUX_SYMBOL(__kprobes_text_end) = .;
 
+#define ENTRY_TEXT							\
+		ALIGN_FUNCTION();					\
+		VMLINUX_SYMBOL(__entry_text_start) = .;			\
+		*(.entry.text)						\
+		VMLINUX_SYMBOL(__entry_text_end) = .;
+
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 #define IRQENTRY_TEXT							\
 		ALIGN_FUNCTION();					\
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index ce104e33cd22..e654fa239916 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -474,7 +474,8 @@ struct cgroup_subsys {
 			struct cgroup *old_cgrp, struct task_struct *tsk,
 			bool threadgroup);
 	void (*fork)(struct cgroup_subsys *ss, struct task_struct *task);
-	void (*exit)(struct cgroup_subsys *ss, struct task_struct *task);
+	void (*exit)(struct cgroup_subsys *ss, struct cgroup *cgrp,
+			struct cgroup *old_cgrp, struct task_struct *task);
 	int (*populate)(struct cgroup_subsys *ss,
 			struct cgroup *cgrp);
 	void (*post_clone)(struct cgroup_subsys *ss, struct cgroup *cgrp);
@@ -626,6 +627,7 @@ bool css_is_ancestor(struct cgroup_subsys_state *cg,
 /* Get id and depth of css */
 unsigned short css_id(struct cgroup_subsys_state *css);
 unsigned short css_depth(struct cgroup_subsys_state *css);
+struct cgroup_subsys_state *cgroup_css_from_dir(struct file *f, int id);
 
 #else /* !CONFIG_CGROUPS */
 
diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h
index ccefff02b6cb..cdbfcb8780ec 100644
--- a/include/linux/cgroup_subsys.h
+++ b/include/linux/cgroup_subsys.h
@@ -65,4 +65,8 @@ SUBSYS(net_cls)
 SUBSYS(blkio)
 #endif
 
+#ifdef CONFIG_CGROUP_PERF
+SUBSYS(perf)
+#endif
+
 /* */
diff --git a/include/linux/debugobjects.h b/include/linux/debugobjects.h
index 597692f1fc8d..65970b811e22 100644
--- a/include/linux/debugobjects.h
+++ b/include/linux/debugobjects.h
@@ -34,7 +34,10 @@ struct debug_obj {
 
 /**
  * struct debug_obj_descr - object type specific debug description structure
+ *
  * @name:		name of the object typee
+ * @debug_hint:		function returning address, which have associated
+ *			kernel symbol, to allow identify the object
  * @fixup_init:		fixup function, which is called when the init check
  *			fails
  * @fixup_activate:	fixup function, which is called when the activate check
@@ -46,7 +49,7 @@ struct debug_obj {
  */
 struct debug_obj_descr {
 	const char		*name;
-
+	void *(*debug_hint)	(void *addr);
 	int (*fixup_init)	(void *addr, enum debug_obj_state state);
 	int (*fixup_activate)	(void *addr, enum debug_obj_state state);
 	int (*fixup_destroy)	(void *addr, enum debug_obj_state state);
diff --git a/include/linux/device.h b/include/linux/device.h
index 1bf5cf0b4513..ca5d25225aab 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -128,9 +128,7 @@ struct device_driver {
 
 	bool suppress_bind_attrs;	/* disables bind/unbind via sysfs */
 
-#if defined(CONFIG_OF)
 	const struct of_device_id	*of_match_table;
-#endif
 
 	int (*probe) (struct device *dev);
 	int (*remove) (struct device *dev);
@@ -441,9 +439,8 @@ struct device {
 					     override */
 	/* arch specific additions */
 	struct dev_archdata	archdata;
-#ifdef CONFIG_OF
-	struct device_node	*of_node;
-#endif
+
+	struct device_node	*of_node; /* associated device tree node */
 
 	dev_t			devt;	/* dev_t, creates the sysfs "dev" */
 
diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h
index 28028988c862..33a42f24b275 100644
--- a/include/linux/exportfs.h
+++ b/include/linux/exportfs.h
@@ -8,6 +8,9 @@ struct inode;
 struct super_block;
 struct vfsmount;
 
+/* limit the handle size to NFSv4 handle size now */
+#define MAX_HANDLE_SZ 128
+
 /*
  * The fileid_type identifies how the file within the filesystem is encoded.
  * In theory this is freely set and parsed by the filesystem, but we try to
@@ -121,8 +124,10 @@ struct fid {
  *    set, the encode_fh() should store sufficient information so that a good
  *    attempt can be made to find not only the file but also it's place in the
  *    filesystem.   This typically means storing a reference to de->d_parent in
- *    the filehandle fragment.  encode_fh() should return the number of bytes
- *    stored or a negative error code such as %-ENOSPC
+ *    the filehandle fragment.  encode_fh() should return the fileid_type on
+ *    success and on error returns 255 (if the space needed to encode fh is
+ *    greater than @max_len*4 bytes). On error @max_len contains the minimum
+ *    size(in 4 byte unit) needed to encode the file handle.
  *
  * fh_to_dentry:
  *    @fh_to_dentry is given a &struct super_block (@sb) and a file handle
diff --git a/include/linux/fcntl.h b/include/linux/fcntl.h
index a562fa5fb4e3..f550f894ba15 100644
--- a/include/linux/fcntl.h
+++ b/include/linux/fcntl.h
@@ -46,6 +46,7 @@
                                            unlinking file.  */
 #define AT_SYMLINK_FOLLOW	0x400   /* Follow symbolic links.  */
 #define AT_NO_AUTOMOUNT		0x800	/* Suppress terminal automount traversal */
+#define AT_EMPTY_PATH		0x1000	/* Allow empty relative pathname */
 
 #ifdef __KERNEL__
 
diff --git a/include/linux/file.h b/include/linux/file.h
index e85baebf6279..21a79958541c 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -29,6 +29,8 @@ static inline void fput_light(struct file *file, int fput_needed)
 
 extern struct file *fget(unsigned int fd);
 extern struct file *fget_light(unsigned int fd, int *fput_needed);
+extern struct file *fget_raw(unsigned int fd);
+extern struct file *fget_raw_light(unsigned int fd, int *fput_needed);
 extern void set_close_on_exec(unsigned int fd, int flag);
 extern void put_filp(struct file *);
 extern int alloc_fd(unsigned start, unsigned flags);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index e38b50a4b9d2..13df14e2c42e 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -102,6 +102,9 @@ struct inodes_stat_t {
 /* File is huge (eg. /dev/kmem): treat loff_t as unsigned */
 #define FMODE_UNSIGNED_OFFSET	((__force fmode_t)0x2000)
 
+/* File is opened with O_PATH; almost nothing can be done with it */
+#define FMODE_PATH		((__force fmode_t)0x4000)
+
 /* File was opened by fanotify and shouldn't generate fanotify events */
 #define FMODE_NONOTIFY		((__force fmode_t)0x1000000)
 
@@ -978,6 +981,13 @@ struct file {
 #endif
 };
 
+struct file_handle {
+	__u32 handle_bytes;
+	int handle_type;
+	/* file identifier */
+	unsigned char f_handle[0];
+};
+
 #define get_file(x)	atomic_long_inc(&(x)->f_count)
 #define fput_atomic(x)	atomic_long_add_unless(&(x)->f_count, -1, 1)
 #define file_count(x)	atomic_long_read(&(x)->f_count)
@@ -1401,6 +1411,7 @@ struct super_block {
 	wait_queue_head_t	s_wait_unfrozen;
 
 	char s_id[32];				/* Informational name */
+	u8 s_uuid[16];				/* UUID */
 
 	void 			*s_fs_info;	/* Filesystem private info */
 	fmode_t			s_mode;
@@ -1874,6 +1885,8 @@ extern void drop_collected_mounts(struct vfsmount *);
 extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *,
 			  struct vfsmount *);
 extern int vfs_statfs(struct path *, struct kstatfs *);
+extern int user_statfs(const char __user *, struct kstatfs *);
+extern int fd_statfs(int, struct kstatfs *);
 extern int statfs_by_dentry(struct dentry *, struct kstatfs *);
 extern int freeze_super(struct super_block *super);
 extern int thaw_super(struct super_block *super);
@@ -1990,6 +2003,8 @@ extern int do_fallocate(struct file *file, int mode, loff_t offset,
 extern long do_sys_open(int dfd, const char __user *filename, int flags,
 			int mode);
 extern struct file *filp_open(const char *, int, int);
+extern struct file *file_open_root(struct dentry *, struct vfsmount *,
+				   const char *, int);
 extern struct file * dentry_open(struct dentry *, struct vfsmount *, int,
 				 const struct cred *);
 extern int filp_close(struct file *, fl_owner_t id);
@@ -2205,10 +2220,6 @@ extern struct file *create_read_pipe(struct file *f, int flags);
 extern struct file *create_write_pipe(int flags);
 extern void free_write_pipe(struct file *);
 
-extern struct file *do_filp_open(int dfd, const char *pathname,
-		int open_flag, int mode, int acc_mode);
-extern int may_open(struct path *, int, int);
-
 extern int kernel_read(struct file *, loff_t, char *, unsigned long);
 extern struct file * open_exec(const char *);
  
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index dcd6a7c3a435..ca29e03c1fac 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -428,6 +428,7 @@ extern void unregister_ftrace_graph(void);
 
 extern void ftrace_graph_init_task(struct task_struct *t);
 extern void ftrace_graph_exit_task(struct task_struct *t);
+extern void ftrace_graph_init_idle_task(struct task_struct *t, int cpu);
 
 static inline int task_curr_ret_stack(struct task_struct *t)
 {
@@ -451,6 +452,7 @@ static inline void unpause_graph_tracing(void)
 
 static inline void ftrace_graph_init_task(struct task_struct *t) { }
 static inline void ftrace_graph_exit_task(struct task_struct *t) { }
+static inline void ftrace_graph_init_idle_task(struct task_struct *t, int cpu) { }
 
 static inline int register_ftrace_graph(trace_func_graph_ret_t retfunc,
 			  trace_func_graph_ent_t entryfunc)
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 47e3997f7b5c..22b32af1b5ec 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -37,7 +37,6 @@ struct trace_entry {
 	unsigned char		flags;
 	unsigned char		preempt_count;
 	int			pid;
-	int			lock_depth;
 };
 
 #define FTRACE_MAX_EVENT						\
@@ -208,7 +207,6 @@ struct ftrace_event_call {
 
 #define PERF_MAX_TRACE_SIZE	2048
 
-#define MAX_FILTER_PRED		32
 #define MAX_FILTER_STR_VAL	256	/* Should handle KSYM_SYMBOL_LEN */
 
 extern void destroy_preds(struct ftrace_event_call *call);
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index f376ddc64c4d..62f500c724f9 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -54,11 +54,13 @@ enum hrtimer_restart {
  * 0x00		inactive
  * 0x01		enqueued into rbtree
  * 0x02		callback function running
+ * 0x04		timer is migrated to another cpu
  *
  * Special cases:
  * 0x03		callback function running and enqueued
  *		(was requeued on another CPU)
- * 0x09		timer was migrated on CPU hotunplug
+ * 0x05		timer was migrated on CPU hotunplug
+ *
  * The "callback function running and enqueued" status is only possible on
  * SMP. It happens for example when a posix timer expired and the callback
  * queued a signal. Between dropping the lock which protects the posix timer
@@ -67,8 +69,11 @@ enum hrtimer_restart {
  * as otherwise the timer could be removed before the softirq code finishes the
  * the handling of the timer.
  *
- * The HRTIMER_STATE_ENQUEUED bit is always or'ed to the current state to
- * preserve the HRTIMER_STATE_CALLBACK bit in the above scenario.
+ * The HRTIMER_STATE_ENQUEUED bit is always or'ed to the current state
+ * to preserve the HRTIMER_STATE_CALLBACK in the above scenario. This
+ * also affects HRTIMER_STATE_MIGRATE where the preservation is not
+ * necessary. HRTIMER_STATE_MIGRATE is cleared after the timer is
+ * enqueued on the new cpu.
  *
  * All state transitions are protected by cpu_base->lock.
  */
@@ -148,7 +153,12 @@ struct hrtimer_clock_base {
 #endif
 };
 
-#define HRTIMER_MAX_CLOCK_BASES 2
+enum  hrtimer_base_type {
+	HRTIMER_BASE_REALTIME,
+	HRTIMER_BASE_MONOTONIC,
+	HRTIMER_BASE_BOOTTIME,
+	HRTIMER_MAX_CLOCK_BASES,
+};
 
 /*
  * struct hrtimer_cpu_base - the per cpu clock bases
@@ -308,6 +318,7 @@ static inline int hrtimer_is_hres_active(struct hrtimer *timer)
 
 extern ktime_t ktime_get(void);
 extern ktime_t ktime_get_real(void);
+extern ktime_t ktime_get_boottime(void);
 
 
 DECLARE_PER_CPU(struct tick_device, tick_cpu_device);
@@ -370,8 +381,9 @@ extern int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp);
 extern ktime_t hrtimer_get_next_event(void);
 
 /*
- * A timer is active, when it is enqueued into the rbtree or the callback
- * function is running.
+ * A timer is active, when it is enqueued into the rbtree or the
+ * callback function is running or it's in the state of being migrated
+ * to another cpu.
  */
 static inline int hrtimer_active(const struct hrtimer *timer)
 {
diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index 903576df88dc..06a8d9c7de98 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -258,9 +258,7 @@ struct i2c_board_info {
 	unsigned short	addr;
 	void		*platform_data;
 	struct dev_archdata	*archdata;
-#ifdef CONFIG_OF
 	struct device_node *of_node;
-#endif
 	int		irq;
 };
 
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 55e0d4253e49..59b72ca1c5d1 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -14,6 +14,8 @@
 #include <linux/smp.h>
 #include <linux/percpu.h>
 #include <linux/hrtimer.h>
+#include <linux/kref.h>
+#include <linux/workqueue.h>
 
 #include <asm/atomic.h>
 #include <asm/ptrace.h>
@@ -55,7 +57,8 @@
  *                Used by threaded interrupts which need to keep the
  *                irq line disabled until the threaded handler has been run.
  * IRQF_NO_SUSPEND - Do not disable this IRQ during suspend
- *
+ * IRQF_FORCE_RESUME - Force enable it on resume even if IRQF_NO_SUSPEND is set
+ * IRQF_NO_THREAD - Interrupt cannot be threaded
  */
 #define IRQF_DISABLED		0x00000020
 #define IRQF_SAMPLE_RANDOM	0x00000040
@@ -67,22 +70,10 @@
 #define IRQF_IRQPOLL		0x00001000
 #define IRQF_ONESHOT		0x00002000
 #define IRQF_NO_SUSPEND		0x00004000
+#define IRQF_FORCE_RESUME	0x00008000
+#define IRQF_NO_THREAD		0x00010000
 
-#define IRQF_TIMER		(__IRQF_TIMER | IRQF_NO_SUSPEND)
-
-/*
- * Bits used by threaded handlers:
- * IRQTF_RUNTHREAD - signals that the interrupt handler thread should run
- * IRQTF_DIED      - handler thread died
- * IRQTF_WARNED    - warning "IRQ_WAKE_THREAD w/o thread_fn" has been printed
- * IRQTF_AFFINITY  - irq thread is requested to adjust affinity
- */
-enum {
-	IRQTF_RUNTHREAD,
-	IRQTF_DIED,
-	IRQTF_WARNED,
-	IRQTF_AFFINITY,
-};
+#define IRQF_TIMER		(__IRQF_TIMER | IRQF_NO_SUSPEND | IRQF_NO_THREAD)
 
 /*
  * These values can be returned by request_any_context_irq() and
@@ -110,6 +101,7 @@ typedef irqreturn_t (*irq_handler_t)(int, void *);
  * @thread_fn:	interupt handler function for threaded interrupts
  * @thread:	thread pointer for threaded interrupts
  * @thread_flags:	flags related to @thread
+ * @thread_mask:	bitmask for keeping track of @thread activity
  */
 struct irqaction {
 	irq_handler_t handler;
@@ -120,6 +112,7 @@ struct irqaction {
 	irq_handler_t thread_fn;
 	struct task_struct *thread;
 	unsigned long thread_flags;
+	unsigned long thread_mask;
 	const char *name;
 	struct proc_dir_entry *dir;
 } ____cacheline_internodealigned_in_smp;
@@ -240,6 +233,35 @@ extern int irq_can_set_affinity(unsigned int irq);
 extern int irq_select_affinity(unsigned int irq);
 
 extern int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m);
+
+/**
+ * struct irq_affinity_notify - context for notification of IRQ affinity changes
+ * @irq:		Interrupt to which notification applies
+ * @kref:		Reference count, for internal use
+ * @work:		Work item, for internal use
+ * @notify:		Function to be called on change.  This will be
+ *			called in process context.
+ * @release:		Function to be called on release.  This will be
+ *			called in process context.  Once registered, the
+ *			structure must only be freed when this function is
+ *			called or later.
+ */
+struct irq_affinity_notify {
+	unsigned int irq;
+	struct kref kref;
+	struct work_struct work;
+	void (*notify)(struct irq_affinity_notify *, const cpumask_t *mask);
+	void (*release)(struct kref *ref);
+};
+
+extern int
+irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify);
+
+static inline void irq_run_affinity_notifiers(void)
+{
+	flush_scheduled_work();
+}
+
 #else /* CONFIG_SMP */
 
 static inline int irq_set_affinity(unsigned int irq, const struct cpumask *m)
@@ -255,7 +277,7 @@ static inline int irq_can_set_affinity(unsigned int irq)
 static inline int irq_select_affinity(unsigned int irq)  { return 0; }
 
 static inline int irq_set_affinity_hint(unsigned int irq,
-                                        const struct cpumask *m)
+					const struct cpumask *m)
 {
 	return -EINVAL;
 }
@@ -314,16 +336,24 @@ static inline void enable_irq_lockdep_irqrestore(unsigned int irq, unsigned long
 }
 
 /* IRQ wakeup (PM) control: */
-extern int set_irq_wake(unsigned int irq, unsigned int on);
+extern int irq_set_irq_wake(unsigned int irq, unsigned int on);
+
+#ifndef CONFIG_GENERIC_HARDIRQS_NO_COMPAT
+/* Please do not use: Use the replacement functions instead */
+static inline int set_irq_wake(unsigned int irq, unsigned int on)
+{
+	return irq_set_irq_wake(irq, on);
+}
+#endif
 
 static inline int enable_irq_wake(unsigned int irq)
 {
-	return set_irq_wake(irq, 1);
+	return irq_set_irq_wake(irq, 1);
 }
 
 static inline int disable_irq_wake(unsigned int irq)
 {
-	return set_irq_wake(irq, 0);
+	return irq_set_irq_wake(irq, 0);
 }
 
 #else /* !CONFIG_GENERIC_HARDIRQS */
@@ -353,6 +383,13 @@ static inline int disable_irq_wake(unsigned int irq)
 }
 #endif /* CONFIG_GENERIC_HARDIRQS */
 
+
+#ifdef CONFIG_IRQ_FORCED_THREADING
+extern bool force_irqthreads;
+#else
+#define force_irqthreads	(0)
+#endif
+
 #ifndef __ARCH_SET_SOFTIRQ_PENDING
 #define set_softirq_pending(x) (local_softirq_pending() = (x))
 #define or_softirq_pending(x)  (local_softirq_pending() |= (x))
@@ -426,6 +463,13 @@ extern void raise_softirq(unsigned int nr);
  */
 DECLARE_PER_CPU(struct list_head [NR_SOFTIRQS], softirq_work_list);
 
+DECLARE_PER_CPU(struct task_struct *, ksoftirqd);
+
+static inline struct task_struct *this_cpu_ksoftirqd(void)
+{
+	return this_cpu_read(ksoftirqd);
+}
+
 /* Try to send a softirq to a remote cpu.  If this cannot be done, the
  * work will be queued to the local cpu.
  */
@@ -645,6 +689,7 @@ static inline void init_irq_proc(void)
 
 struct seq_file;
 int show_interrupts(struct seq_file *p, void *v);
+int arch_show_interrupts(struct seq_file *p, int prec);
 
 extern int early_irq_init(void);
 extern int arch_probe_nr_irqs(void);
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 80fcb53057bc..1d3577f30d45 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -29,61 +29,104 @@
 #include <asm/irq_regs.h>
 
 struct irq_desc;
+struct irq_data;
 typedef	void (*irq_flow_handler_t)(unsigned int irq,
 					    struct irq_desc *desc);
-
+typedef	void (*irq_preflow_handler_t)(struct irq_data *data);
 
 /*
  * IRQ line status.
  *
- * Bits 0-7 are reserved for the IRQF_* bits in linux/interrupt.h
+ * Bits 0-7 are the same as the IRQF_* bits in linux/interrupt.h
+ *
+ * IRQ_TYPE_NONE		- default, unspecified type
+ * IRQ_TYPE_EDGE_RISING		- rising edge triggered
+ * IRQ_TYPE_EDGE_FALLING	- falling edge triggered
+ * IRQ_TYPE_EDGE_BOTH		- rising and falling edge triggered
+ * IRQ_TYPE_LEVEL_HIGH		- high level triggered
+ * IRQ_TYPE_LEVEL_LOW		- low level triggered
+ * IRQ_TYPE_LEVEL_MASK		- Mask to filter out the level bits
+ * IRQ_TYPE_SENSE_MASK		- Mask for all the above bits
+ * IRQ_TYPE_PROBE		- Special flag for probing in progress
+ *
+ * Bits which can be modified via irq_set/clear/modify_status_flags()
+ * IRQ_LEVEL			- Interrupt is level type. Will be also
+ *				  updated in the code when the above trigger
+ *				  bits are modified via set_irq_type()
+ * IRQ_PER_CPU			- Mark an interrupt PER_CPU. Will protect
+ *				  it from affinity setting
+ * IRQ_NOPROBE			- Interrupt cannot be probed by autoprobing
+ * IRQ_NOREQUEST		- Interrupt cannot be requested via
+ *				  request_irq()
+ * IRQ_NOAUTOEN			- Interrupt is not automatically enabled in
+ *				  request/setup_irq()
+ * IRQ_NO_BALANCING		- Interrupt cannot be balanced (affinity set)
+ * IRQ_MOVE_PCNTXT		- Interrupt can be migrated from process context
+ * IRQ_NESTED_TRHEAD		- Interrupt nests into another thread
+ *
+ * Deprecated bits. They are kept updated as long as
+ * CONFIG_GENERIC_HARDIRQS_NO_COMPAT is not set. Will go away soon. These bits
+ * are internal state of the core code and if you really need to acces
+ * them then talk to the genirq maintainer instead of hacking
+ * something weird.
  *
- * IRQ types
  */
-#define IRQ_TYPE_NONE		0x00000000	/* Default, unspecified type */
-#define IRQ_TYPE_EDGE_RISING	0x00000001	/* Edge rising type */
-#define IRQ_TYPE_EDGE_FALLING	0x00000002	/* Edge falling type */
-#define IRQ_TYPE_EDGE_BOTH (IRQ_TYPE_EDGE_FALLING | IRQ_TYPE_EDGE_RISING)
-#define IRQ_TYPE_LEVEL_HIGH	0x00000004	/* Level high type */
-#define IRQ_TYPE_LEVEL_LOW	0x00000008	/* Level low type */
-#define IRQ_TYPE_SENSE_MASK	0x0000000f	/* Mask of the above */
-#define IRQ_TYPE_PROBE		0x00000010	/* Probing in progress */
-
-/* Internal flags */
-#define IRQ_INPROGRESS		0x00000100	/* IRQ handler active - do not enter! */
-#define IRQ_DISABLED		0x00000200	/* IRQ disabled - do not enter! */
-#define IRQ_PENDING		0x00000400	/* IRQ pending - replay on enable */
-#define IRQ_REPLAY		0x00000800	/* IRQ has been replayed but not acked yet */
-#define IRQ_AUTODETECT		0x00001000	/* IRQ is being autodetected */
-#define IRQ_WAITING		0x00002000	/* IRQ not yet seen - for autodetection */
-#define IRQ_LEVEL		0x00004000	/* IRQ level triggered */
-#define IRQ_MASKED		0x00008000	/* IRQ masked - shouldn't be seen again */
-#define IRQ_PER_CPU		0x00010000	/* IRQ is per CPU */
-#define IRQ_NOPROBE		0x00020000	/* IRQ is not valid for probing */
-#define IRQ_NOREQUEST		0x00040000	/* IRQ cannot be requested */
-#define IRQ_NOAUTOEN		0x00080000	/* IRQ will not be enabled on request irq */
-#define IRQ_WAKEUP		0x00100000	/* IRQ triggers system wakeup */
-#define IRQ_MOVE_PENDING	0x00200000	/* need to re-target IRQ destination */
-#define IRQ_NO_BALANCING	0x00400000	/* IRQ is excluded from balancing */
-#define IRQ_SPURIOUS_DISABLED	0x00800000	/* IRQ was disabled by the spurious trap */
-#define IRQ_MOVE_PCNTXT		0x01000000	/* IRQ migration from process context */
-#define IRQ_AFFINITY_SET	0x02000000	/* IRQ affinity was set from userspace*/
-#define IRQ_SUSPENDED		0x04000000	/* IRQ has gone through suspend sequence */
-#define IRQ_ONESHOT		0x08000000	/* IRQ is not unmasked after hardirq */
-#define IRQ_NESTED_THREAD	0x10000000	/* IRQ is nested into another, no own handler thread */
+enum {
+	IRQ_TYPE_NONE		= 0x00000000,
+	IRQ_TYPE_EDGE_RISING	= 0x00000001,
+	IRQ_TYPE_EDGE_FALLING	= 0x00000002,
+	IRQ_TYPE_EDGE_BOTH	= (IRQ_TYPE_EDGE_FALLING | IRQ_TYPE_EDGE_RISING),
+	IRQ_TYPE_LEVEL_HIGH	= 0x00000004,
+	IRQ_TYPE_LEVEL_LOW	= 0x00000008,
+	IRQ_TYPE_LEVEL_MASK	= (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH),
+	IRQ_TYPE_SENSE_MASK	= 0x0000000f,
+
+	IRQ_TYPE_PROBE		= 0x00000010,
+
+	IRQ_LEVEL		= (1 <<  8),
+	IRQ_PER_CPU		= (1 <<  9),
+	IRQ_NOPROBE		= (1 << 10),
+	IRQ_NOREQUEST		= (1 << 11),
+	IRQ_NOAUTOEN		= (1 << 12),
+	IRQ_NO_BALANCING	= (1 << 13),
+	IRQ_MOVE_PCNTXT		= (1 << 14),
+	IRQ_NESTED_THREAD	= (1 << 15),
+
+#ifndef CONFIG_GENERIC_HARDIRQS_NO_COMPAT
+	IRQ_INPROGRESS		= (1 << 16),
+	IRQ_REPLAY		= (1 << 17),
+	IRQ_WAITING		= (1 << 18),
+	IRQ_DISABLED		= (1 << 19),
+	IRQ_PENDING		= (1 << 20),
+	IRQ_MASKED		= (1 << 21),
+	IRQ_MOVE_PENDING	= (1 << 22),
+	IRQ_AFFINITY_SET	= (1 << 23),
+	IRQ_WAKEUP		= (1 << 24),
+#endif
+};
 
 #define IRQF_MODIFY_MASK	\
 	(IRQ_TYPE_SENSE_MASK | IRQ_NOPROBE | IRQ_NOREQUEST | \
 	 IRQ_NOAUTOEN | IRQ_MOVE_PCNTXT | IRQ_LEVEL | IRQ_NO_BALANCING | \
-	 IRQ_PER_CPU)
+	 IRQ_PER_CPU | IRQ_NESTED_THREAD)
 
-#ifdef CONFIG_IRQ_PER_CPU
-# define CHECK_IRQ_PER_CPU(var) ((var) & IRQ_PER_CPU)
-# define IRQ_NO_BALANCING_MASK	(IRQ_PER_CPU | IRQ_NO_BALANCING)
-#else
-# define CHECK_IRQ_PER_CPU(var) 0
-# define IRQ_NO_BALANCING_MASK	IRQ_NO_BALANCING
-#endif
+#define IRQ_NO_BALANCING_MASK	(IRQ_PER_CPU | IRQ_NO_BALANCING)
+
+static inline __deprecated bool CHECK_IRQ_PER_CPU(unsigned int status)
+{
+	return status & IRQ_PER_CPU;
+}
+
+/*
+ * Return value for chip->irq_set_affinity()
+ *
+ * IRQ_SET_MASK_OK	- OK, core updates irq_data.affinity
+ * IRQ_SET_MASK_NOCPY	- OK, chip did update irq_data.affinity
+ */
+enum {
+	IRQ_SET_MASK_OK = 0,
+	IRQ_SET_MASK_OK_NOCOPY,
+};
 
 struct msi_desc;
 
@@ -91,6 +134,8 @@ struct msi_desc;
  * struct irq_data - per irq and irq chip data passed down to chip functions
  * @irq:		interrupt number
  * @node:		node index useful for balancing
+ * @state_use_accessor: status information for irq chip functions.
+ *			Use accessor functions to deal with it
  * @chip:		low level interrupt hardware access
  * @handler_data:	per-IRQ data for the irq_chip methods
  * @chip_data:		platform-specific per-chip private data for the chip
@@ -105,6 +150,7 @@ struct msi_desc;
 struct irq_data {
 	unsigned int		irq;
 	unsigned int		node;
+	unsigned int		state_use_accessors;
 	struct irq_chip		*chip;
 	void			*handler_data;
 	void			*chip_data;
@@ -114,6 +160,80 @@ struct irq_data {
 #endif
 };
 
+/*
+ * Bit masks for irq_data.state
+ *
+ * IRQD_TRIGGER_MASK		- Mask for the trigger type bits
+ * IRQD_SETAFFINITY_PENDING	- Affinity setting is pending
+ * IRQD_NO_BALANCING		- Balancing disabled for this IRQ
+ * IRQD_PER_CPU			- Interrupt is per cpu
+ * IRQD_AFFINITY_SET		- Interrupt affinity was set
+ * IRQD_LEVEL			- Interrupt is level triggered
+ * IRQD_WAKEUP_STATE		- Interrupt is configured for wakeup
+ *				  from suspend
+ * IRDQ_MOVE_PCNTXT		- Interrupt can be moved in process
+ *				  context
+ */
+enum {
+	IRQD_TRIGGER_MASK		= 0xf,
+	IRQD_SETAFFINITY_PENDING	= (1 <<  8),
+	IRQD_NO_BALANCING		= (1 << 10),
+	IRQD_PER_CPU			= (1 << 11),
+	IRQD_AFFINITY_SET		= (1 << 12),
+	IRQD_LEVEL			= (1 << 13),
+	IRQD_WAKEUP_STATE		= (1 << 14),
+	IRQD_MOVE_PCNTXT		= (1 << 15),
+};
+
+static inline bool irqd_is_setaffinity_pending(struct irq_data *d)
+{
+	return d->state_use_accessors & IRQD_SETAFFINITY_PENDING;
+}
+
+static inline bool irqd_is_per_cpu(struct irq_data *d)
+{
+	return d->state_use_accessors & IRQD_PER_CPU;
+}
+
+static inline bool irqd_can_balance(struct irq_data *d)
+{
+	return !(d->state_use_accessors & (IRQD_PER_CPU | IRQD_NO_BALANCING));
+}
+
+static inline bool irqd_affinity_was_set(struct irq_data *d)
+{
+	return d->state_use_accessors & IRQD_AFFINITY_SET;
+}
+
+static inline u32 irqd_get_trigger_type(struct irq_data *d)
+{
+	return d->state_use_accessors & IRQD_TRIGGER_MASK;
+}
+
+/*
+ * Must only be called inside irq_chip.irq_set_type() functions.
+ */
+static inline void irqd_set_trigger_type(struct irq_data *d, u32 type)
+{
+	d->state_use_accessors &= ~IRQD_TRIGGER_MASK;
+	d->state_use_accessors |= type & IRQD_TRIGGER_MASK;
+}
+
+static inline bool irqd_is_level_type(struct irq_data *d)
+{
+	return d->state_use_accessors & IRQD_LEVEL;
+}
+
+static inline bool irqd_is_wakeup_set(struct irq_data *d)
+{
+	return d->state_use_accessors & IRQD_WAKEUP_STATE;
+}
+
+static inline bool irqd_can_move_in_process_context(struct irq_data *d)
+{
+	return d->state_use_accessors & IRQD_MOVE_PCNTXT;
+}
+
 /**
  * struct irq_chip - hardware interrupt chip descriptor
  *
@@ -150,6 +270,7 @@ struct irq_data {
  * @irq_set_wake:	enable/disable power-management wake-on of an IRQ
  * @irq_bus_lock:	function to lock access to slow bus (i2c) chips
  * @irq_bus_sync_unlock:function to sync and unlock slow bus (i2c) chips
+ * @flags:		chip specific flags
  *
  * @release:		release function solely used by UML
  */
@@ -196,12 +317,27 @@ struct irq_chip {
 	void		(*irq_bus_lock)(struct irq_data *data);
 	void		(*irq_bus_sync_unlock)(struct irq_data *data);
 
+	unsigned long	flags;
+
 	/* Currently used only by UML, might disappear one day.*/
 #ifdef CONFIG_IRQ_RELEASE_METHOD
 	void		(*release)(unsigned int irq, void *dev_id);
 #endif
 };
 
+/*
+ * irq_chip specific flags
+ *
+ * IRQCHIP_SET_TYPE_MASKED:	Mask before calling chip.irq_set_type()
+ * IRQCHIP_EOI_IF_HANDLED:	Only issue irq_eoi() when irq was handled
+ * IRQCHIP_MASK_ON_SUSPEND:	Mask non wake irqs in the suspend path
+ */
+enum {
+	IRQCHIP_SET_TYPE_MASKED		= (1 <<  0),
+	IRQCHIP_EOI_IF_HANDLED		= (1 <<  1),
+	IRQCHIP_MASK_ON_SUSPEND		= (1 <<  2),
+};
+
 /* This include will go away once we isolated irq_desc usage to core code */
 #include <linux/irqdesc.h>
 
@@ -218,7 +354,7 @@ struct irq_chip {
 # define ARCH_IRQ_INIT_FLAGS	0
 #endif
 
-#define IRQ_DEFAULT_INIT_FLAGS	(IRQ_DISABLED | ARCH_IRQ_INIT_FLAGS)
+#define IRQ_DEFAULT_INIT_FLAGS	ARCH_IRQ_INIT_FLAGS
 
 struct irqaction;
 extern int setup_irq(unsigned int irq, struct irqaction *new);
@@ -229,9 +365,13 @@ extern void remove_irq(unsigned int irq, struct irqaction *act);
 #if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_PENDING_IRQ)
 void move_native_irq(int irq);
 void move_masked_irq(int irq);
+void irq_move_irq(struct irq_data *data);
+void irq_move_masked_irq(struct irq_data *data);
 #else
 static inline void move_native_irq(int irq) { }
 static inline void move_masked_irq(int irq) { }
+static inline void irq_move_irq(struct irq_data *data) { }
+static inline void irq_move_masked_irq(struct irq_data *data) { }
 #endif
 
 extern int no_irq_affinity;
@@ -267,23 +407,23 @@ extern struct irq_chip no_irq_chip;
 extern struct irq_chip dummy_irq_chip;
 
 extern void
-set_irq_chip_and_handler(unsigned int irq, struct irq_chip *chip,
-			 irq_flow_handler_t handle);
-extern void
-set_irq_chip_and_handler_name(unsigned int irq, struct irq_chip *chip,
+irq_set_chip_and_handler_name(unsigned int irq, struct irq_chip *chip,
 			      irq_flow_handler_t handle, const char *name);
 
+static inline void irq_set_chip_and_handler(unsigned int irq, struct irq_chip *chip,
+					    irq_flow_handler_t handle)
+{
+	irq_set_chip_and_handler_name(irq, chip, handle, NULL);
+}
+
 extern void
-__set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
+__irq_set_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
 		  const char *name);
 
-/*
- * Set a highlevel flow handler for a given IRQ:
- */
 static inline void
-set_irq_handler(unsigned int irq, irq_flow_handler_t handle)
+irq_set_handler(unsigned int irq, irq_flow_handler_t handle)
 {
-	__set_irq_handler(irq, handle, 0, NULL);
+	__irq_set_handler(irq, handle, 0, NULL);
 }
 
 /*
@@ -292,14 +432,11 @@ set_irq_handler(unsigned int irq, irq_flow_handler_t handle)
  *  IRQ_NOREQUEST and IRQ_NOPROBE)
  */
 static inline void
-set_irq_chained_handler(unsigned int irq,
-			irq_flow_handler_t handle)
+irq_set_chained_handler(unsigned int irq, irq_flow_handler_t handle)
 {
-	__set_irq_handler(irq, handle, 1, NULL);
+	__irq_set_handler(irq, handle, 1, NULL);
 }
 
-extern void set_irq_nested_thread(unsigned int irq, int nest);
-
 void irq_modify_status(unsigned int irq, unsigned long clr, unsigned long set);
 
 static inline void irq_set_status_flags(unsigned int irq, unsigned long set)
@@ -312,16 +449,24 @@ static inline void irq_clear_status_flags(unsigned int irq, unsigned long clr)
 	irq_modify_status(irq, clr, 0);
 }
 
-static inline void set_irq_noprobe(unsigned int irq)
+static inline void irq_set_noprobe(unsigned int irq)
 {
 	irq_modify_status(irq, 0, IRQ_NOPROBE);
 }
 
-static inline void set_irq_probe(unsigned int irq)
+static inline void irq_set_probe(unsigned int irq)
 {
 	irq_modify_status(irq, IRQ_NOPROBE, 0);
 }
 
+static inline void irq_set_nested_thread(unsigned int irq, bool nest)
+{
+	if (nest)
+		irq_set_status_flags(irq, IRQ_NESTED_THREAD);
+	else
+		irq_clear_status_flags(irq, IRQ_NESTED_THREAD);
+}
+
 /* Handle dynamic irq creation and destruction */
 extern unsigned int create_irq_nr(unsigned int irq_want, int node);
 extern int create_irq(void);
@@ -338,14 +483,14 @@ static inline void dynamic_irq_init(unsigned int irq)
 }
 
 /* Set/get chip/data for an IRQ: */
-extern int set_irq_chip(unsigned int irq, struct irq_chip *chip);
-extern int set_irq_data(unsigned int irq, void *data);
-extern int set_irq_chip_data(unsigned int irq, void *data);
-extern int set_irq_type(unsigned int irq, unsigned int type);
-extern int set_irq_msi(unsigned int irq, struct msi_desc *entry);
+extern int irq_set_chip(unsigned int irq, struct irq_chip *chip);
+extern int irq_set_handler_data(unsigned int irq, void *data);
+extern int irq_set_chip_data(unsigned int irq, void *data);
+extern int irq_set_irq_type(unsigned int irq, unsigned int type);
+extern int irq_set_msi_desc(unsigned int irq, struct msi_desc *entry);
 extern struct irq_data *irq_get_irq_data(unsigned int irq);
 
-static inline struct irq_chip *get_irq_chip(unsigned int irq)
+static inline struct irq_chip *irq_get_chip(unsigned int irq)
 {
 	struct irq_data *d = irq_get_irq_data(irq);
 	return d ? d->chip : NULL;
@@ -356,7 +501,7 @@ static inline struct irq_chip *irq_data_get_irq_chip(struct irq_data *d)
 	return d->chip;
 }
 
-static inline void *get_irq_chip_data(unsigned int irq)
+static inline void *irq_get_chip_data(unsigned int irq)
 {
 	struct irq_data *d = irq_get_irq_data(irq);
 	return d ? d->chip_data : NULL;
@@ -367,18 +512,18 @@ static inline void *irq_data_get_irq_chip_data(struct irq_data *d)
 	return d->chip_data;
 }
 
-static inline void *get_irq_data(unsigned int irq)
+static inline void *irq_get_handler_data(unsigned int irq)
 {
 	struct irq_data *d = irq_get_irq_data(irq);
 	return d ? d->handler_data : NULL;
 }
 
-static inline void *irq_data_get_irq_data(struct irq_data *d)
+static inline void *irq_data_get_irq_handler_data(struct irq_data *d)
 {
 	return d->handler_data;
 }
 
-static inline struct msi_desc *get_irq_msi(unsigned int irq)
+static inline struct msi_desc *irq_get_msi_desc(unsigned int irq)
 {
 	struct irq_data *d = irq_get_irq_data(irq);
 	return d ? d->msi_desc : NULL;
@@ -389,6 +534,89 @@ static inline struct msi_desc *irq_data_get_msi(struct irq_data *d)
 	return d->msi_desc;
 }
 
+#ifndef CONFIG_GENERIC_HARDIRQS_NO_COMPAT
+/* Please do not use: Use the replacement functions instead */
+static inline int set_irq_chip(unsigned int irq, struct irq_chip *chip)
+{
+	return irq_set_chip(irq, chip);
+}
+static inline int set_irq_data(unsigned int irq, void *data)
+{
+	return irq_set_handler_data(irq, data);
+}
+static inline int set_irq_chip_data(unsigned int irq, void *data)
+{
+	return irq_set_chip_data(irq, data);
+}
+static inline int set_irq_type(unsigned int irq, unsigned int type)
+{
+	return irq_set_irq_type(irq, type);
+}
+static inline int set_irq_msi(unsigned int irq, struct msi_desc *entry)
+{
+	return irq_set_msi_desc(irq, entry);
+}
+static inline struct irq_chip *get_irq_chip(unsigned int irq)
+{
+	return irq_get_chip(irq);
+}
+static inline void *get_irq_chip_data(unsigned int irq)
+{
+	return irq_get_chip_data(irq);
+}
+static inline void *get_irq_data(unsigned int irq)
+{
+	return irq_get_handler_data(irq);
+}
+static inline void *irq_data_get_irq_data(struct irq_data *d)
+{
+	return irq_data_get_irq_handler_data(d);
+}
+static inline struct msi_desc *get_irq_msi(unsigned int irq)
+{
+	return irq_get_msi_desc(irq);
+}
+static inline void set_irq_noprobe(unsigned int irq)
+{
+	irq_set_noprobe(irq);
+}
+static inline void set_irq_probe(unsigned int irq)
+{
+	irq_set_probe(irq);
+}
+static inline void set_irq_nested_thread(unsigned int irq, int nest)
+{
+	irq_set_nested_thread(irq, nest);
+}
+static inline void
+set_irq_chip_and_handler_name(unsigned int irq, struct irq_chip *chip,
+			      irq_flow_handler_t handle, const char *name)
+{
+	irq_set_chip_and_handler_name(irq, chip, handle, name);
+}
+static inline void
+set_irq_chip_and_handler(unsigned int irq, struct irq_chip *chip,
+			 irq_flow_handler_t handle)
+{
+	irq_set_chip_and_handler(irq, chip, handle);
+}
+static inline void
+__set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
+		  const char *name)
+{
+	__irq_set_handler(irq, handle, is_chained, name);
+}
+static inline void set_irq_handler(unsigned int irq, irq_flow_handler_t handle)
+{
+	irq_set_handler(irq, handle);
+}
+static inline void
+set_irq_chained_handler(unsigned int irq, irq_flow_handler_t handle)
+{
+	irq_set_chained_handler(irq, handle);
+}
+#endif
+
 int irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node);
 void irq_free_descs(unsigned int irq, unsigned int cnt);
 int irq_reserve_irqs(unsigned int from, unsigned int cnt);
diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index c1a95b7b58de..00218371518b 100644
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -8,6 +8,7 @@
  * For now it's included from <linux/irq.h>
  */
 
+struct irq_affinity_notify;
 struct proc_dir_entry;
 struct timer_rand_state;
 /**
@@ -18,13 +19,16 @@ struct timer_rand_state;
  * @handle_irq:		highlevel irq-events handler [if NULL, __do_IRQ()]
  * @action:		the irq action chain
  * @status:		status information
+ * @core_internal_state__do_not_mess_with_it: core internal status information
  * @depth:		disable-depth, for nested irq_disable() calls
  * @wake_depth:		enable depth, for multiple set_irq_wake() callers
  * @irq_count:		stats field to detect stalled irqs
  * @last_unhandled:	aging timer for unhandled count
  * @irqs_unhandled:	stats field for spurious unhandled interrupts
  * @lock:		locking for SMP
+ * @affinity_notify:	context for notification of affinity changes
  * @pending_mask:	pending rebalanced interrupts
+ * @threads_oneshot:	bitfield to handle shared oneshot threads
  * @threads_active:	number of irqaction threads currently running
  * @wait_for_threads:	wait queue for sync_irq to wait for threaded handlers
  * @dir:		/proc/irq/ procfs entry
@@ -45,6 +49,7 @@ struct irq_desc {
 		struct {
 			unsigned int		irq;
 			unsigned int		node;
+			unsigned int		pad_do_not_even_think_about_it;
 			struct irq_chip		*chip;
 			void			*handler_data;
 			void			*chip_data;
@@ -59,9 +64,16 @@ struct irq_desc {
 	struct timer_rand_state *timer_rand_state;
 	unsigned int __percpu	*kstat_irqs;
 	irq_flow_handler_t	handle_irq;
+#ifdef CONFIG_IRQ_PREFLOW_FASTEOI
+	irq_preflow_handler_t	preflow_handler;
+#endif
 	struct irqaction	*action;	/* IRQ action list */
+#ifdef CONFIG_GENERIC_HARDIRQS_NO_COMPAT
+	unsigned int		status_use_accessors;
+#else
 	unsigned int		status;		/* IRQ status */
-
+#endif
+	unsigned int		core_internal_state__do_not_mess_with_it;
 	unsigned int		depth;		/* nested irq disables */
 	unsigned int		wake_depth;	/* nested wake enables */
 	unsigned int		irq_count;	/* For detecting broken IRQs */
@@ -70,10 +82,12 @@ struct irq_desc {
 	raw_spinlock_t		lock;
 #ifdef CONFIG_SMP
 	const struct cpumask	*affinity_hint;
+	struct irq_affinity_notify *affinity_notify;
 #ifdef CONFIG_GENERIC_PENDING_IRQ
 	cpumask_var_t		pending_mask;
 #endif
 #endif
+	unsigned long		threads_oneshot;
 	atomic_t		threads_active;
 	wait_queue_head_t       wait_for_threads;
 #ifdef CONFIG_PROC_FS
@@ -95,10 +109,51 @@ static inline struct irq_desc *move_irq_desc(struct irq_desc *desc, int node)
 
 #ifdef CONFIG_GENERIC_HARDIRQS
 
-#define get_irq_desc_chip(desc)		((desc)->irq_data.chip)
-#define get_irq_desc_chip_data(desc)	((desc)->irq_data.chip_data)
-#define get_irq_desc_data(desc)		((desc)->irq_data.handler_data)
-#define get_irq_desc_msi(desc)		((desc)->irq_data.msi_desc)
+static inline struct irq_data *irq_desc_get_irq_data(struct irq_desc *desc)
+{
+	return &desc->irq_data;
+}
+
+static inline struct irq_chip *irq_desc_get_chip(struct irq_desc *desc)
+{
+	return desc->irq_data.chip;
+}
+
+static inline void *irq_desc_get_chip_data(struct irq_desc *desc)
+{
+	return desc->irq_data.chip_data;
+}
+
+static inline void *irq_desc_get_handler_data(struct irq_desc *desc)
+{
+	return desc->irq_data.handler_data;
+}
+
+static inline struct msi_desc *irq_desc_get_msi_desc(struct irq_desc *desc)
+{
+	return desc->irq_data.msi_desc;
+}
+
+#ifndef CONFIG_GENERIC_HARDIRQS_NO_COMPAT
+static inline struct irq_chip *get_irq_desc_chip(struct irq_desc *desc)
+{
+	return irq_desc_get_chip(desc);
+}
+static inline void *get_irq_desc_data(struct irq_desc *desc)
+{
+	return irq_desc_get_handler_data(desc);
+}
+
+static inline void *get_irq_desc_chip_data(struct irq_desc *desc)
+{
+	return irq_desc_get_chip_data(desc);
+}
+
+static inline struct msi_desc *get_irq_desc_msi(struct irq_desc *desc)
+{
+	return irq_desc_get_msi_desc(desc);
+}
+#endif
 
 /*
  * Architectures call this to let the generic IRQ layer
@@ -123,6 +178,7 @@ static inline int irq_has_action(unsigned int irq)
 	return desc->action != NULL;
 }
 
+#ifndef CONFIG_GENERIC_HARDIRQS_NO_COMPAT
 static inline int irq_balancing_disabled(unsigned int irq)
 {
 	struct irq_desc *desc;
@@ -130,6 +186,7 @@ static inline int irq_balancing_disabled(unsigned int irq)
 	desc = irq_to_desc(irq);
 	return desc->status & IRQ_NO_BALANCING_MASK;
 }
+#endif
 
 /* caller has locked the irq_desc and both params are valid */
 static inline void __set_irq_handler_unlocked(int irq,
@@ -140,6 +197,17 @@ static inline void __set_irq_handler_unlocked(int irq,
 	desc = irq_to_desc(irq);
 	desc->handle_irq = handler;
 }
+
+#ifdef CONFIG_IRQ_PREFLOW_FASTEOI
+static inline void
+__irq_set_preflow_handler(unsigned int irq, irq_preflow_handler_t handler)
+{
+	struct irq_desc *desc;
+
+	desc = irq_to_desc(irq);
+	desc->preflow_handler = handler;
+}
+#endif
 #endif
 
 #endif
diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h
index 6811f4bfc6e7..922aa313c9f9 100644
--- a/include/linux/jiffies.h
+++ b/include/linux/jiffies.h
@@ -307,6 +307,7 @@ extern clock_t jiffies_to_clock_t(long x);
 extern unsigned long clock_t_to_jiffies(unsigned long x);
 extern u64 jiffies_64_to_clock_t(u64 x);
 extern u64 nsec_to_clock_t(u64 x);
+extern u64 nsecs_to_jiffies64(u64 n);
 extern unsigned long nsecs_to_jiffies(u64 n);
 
 #define TIMESTAMP_SIZE	30
diff --git a/include/linux/kthread.h b/include/linux/kthread.h
index ce0775aa64c3..7ff16f7d3ed4 100644
--- a/include/linux/kthread.h
+++ b/include/linux/kthread.h
@@ -64,7 +64,7 @@ struct kthread_work {
 };
 
 #define KTHREAD_WORKER_INIT(worker)	{				\
-	.lock = SPIN_LOCK_UNLOCKED,					\
+	.lock = __SPIN_LOCK_UNLOCKED((worker).lock),			\
 	.work_list = LIST_HEAD_INIT((worker).work_list),		\
 	}
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index f6385fc17ad4..679300c050f5 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1309,8 +1309,6 @@ int add_from_early_node_map(struct range *range, int az,
 				   int nr_range, int nid);
 u64 __init find_memory_core_early(int nid, u64 size, u64 align,
 					u64 goal, u64 limit);
-void *__alloc_memory_core_early(int nodeid, u64 size, u64 align,
-				 u64 goal, u64 limit);
 typedef int (*work_fn_t)(unsigned long, unsigned long, void *);
 extern void work_with_active_regions(int nid, work_fn_t work_fn, void *data);
 extern void sparse_memory_present_with_active_regions(int nid);
diff --git a/include/linux/namei.h b/include/linux/namei.h
index f276d4fa01fc..9c8603872c36 100644
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -19,7 +19,6 @@ struct nameidata {
 	struct path	path;
 	struct qstr	last;
 	struct path	root;
-	struct file	*file;
 	struct inode	*inode; /* path.dentry.d_inode */
 	unsigned int	flags;
 	unsigned	seq;
@@ -63,6 +62,10 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND};
 #define LOOKUP_EXCL		0x0400
 #define LOOKUP_RENAME_TARGET	0x0800
 
+#define LOOKUP_JUMPED		0x1000
+#define LOOKUP_ROOT		0x2000
+#define LOOKUP_EMPTY		0x4000
+
 extern int user_path_at(int, const char __user *, unsigned, struct path *);
 
 #define user_path(name, path) user_path_at(AT_FDCWD, name, LOOKUP_FOLLOW, path)
@@ -72,7 +75,7 @@ extern int user_path_at(int, const char __user *, unsigned, struct path *);
 
 extern int kern_path(const char *, unsigned, struct path *);
 
-extern int path_lookup(const char *, unsigned, struct nameidata *);
+extern int kern_path_parent(const char *, struct nameidata *);
 extern int vfs_path_lookup(struct dentry *, struct vfsmount *,
 			   const char *, unsigned int, struct nameidata *);
 
diff --git a/include/linux/of.h b/include/linux/of.h
index cad7cf0ab278..266db1d0baa9 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -23,8 +23,6 @@
 
 #include <asm/byteorder.h>
 
-#ifdef CONFIG_OF
-
 typedef u32 phandle;
 typedef u32 ihandle;
 
@@ -65,11 +63,18 @@ struct device_node {
 #endif
 };
 
+#ifdef CONFIG_OF
+
 /* Pointer for first entry in chain of all nodes. */
 extern struct device_node *allnodes;
 extern struct device_node *of_chosen;
 extern rwlock_t devtree_lock;
 
+static inline bool of_have_populated_dt(void)
+{
+	return allnodes != NULL;
+}
+
 static inline bool of_node_is_root(const struct device_node *node)
 {
 	return node && (node->parent == NULL);
@@ -222,5 +227,12 @@ extern void of_attach_node(struct device_node *);
 extern void of_detach_node(struct device_node *);
 #endif
 
+#else
+
+static inline bool of_have_populated_dt(void)
+{
+	return false;
+}
+
 #endif /* CONFIG_OF */
 #endif /* _LINUX_OF_H */
diff --git a/include/linux/of_pci.h b/include/linux/of_pci.h
new file mode 100644
index 000000000000..85a27b650d76
--- /dev/null
+++ b/include/linux/of_pci.h
@@ -0,0 +1,9 @@
+#ifndef __OF_PCI_H
+#define __OF_PCI_H
+
+#include <linux/pci.h>
+
+struct pci_dev;
+struct of_irq;
+int of_irq_map_pci(struct pci_dev *pdev, struct of_irq *out_irq);
+#endif
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index dda5b0a3ff60..614615b8d42b 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -225,8 +225,14 @@ struct perf_event_attr {
 	};
 
 	__u32			bp_type;
-	__u64			bp_addr;
-	__u64			bp_len;
+	union {
+		__u64		bp_addr;
+		__u64		config1; /* extension of config */
+	};
+	union {
+		__u64		bp_len;
+		__u64		config2; /* extension of config1 */
+	};
 };
 
 /*
@@ -464,6 +470,7 @@ enum perf_callchain_context {
 
 #define PERF_FLAG_FD_NO_GROUP	(1U << 0)
 #define PERF_FLAG_FD_OUTPUT	(1U << 1)
+#define PERF_FLAG_PID_CGROUP	(1U << 2) /* pid=cgroup id, per-cpu mode only */
 
 #ifdef __KERNEL__
 /*
@@ -471,6 +478,7 @@ enum perf_callchain_context {
  */
 
 #ifdef CONFIG_PERF_EVENTS
+# include <linux/cgroup.h>
 # include <asm/perf_event.h>
 # include <asm/local64.h>
 #endif
@@ -539,6 +547,9 @@ struct hw_perf_event {
 			unsigned long	event_base;
 			int		idx;
 			int		last_cpu;
+			unsigned int	extra_reg;
+			u64		extra_config;
+			int		extra_alloc;
 		};
 		struct { /* software */
 			struct hrtimer	hrtimer;
@@ -716,6 +727,22 @@ struct swevent_hlist {
 #define PERF_ATTACH_GROUP	0x02
 #define PERF_ATTACH_TASK	0x04
 
+#ifdef CONFIG_CGROUP_PERF
+/*
+ * perf_cgroup_info keeps track of time_enabled for a cgroup.
+ * This is a per-cpu dynamically allocated data structure.
+ */
+struct perf_cgroup_info {
+	u64 time;
+	u64 timestamp;
+};
+
+struct perf_cgroup {
+	struct cgroup_subsys_state css;
+	struct perf_cgroup_info *info;	/* timing info, one per cpu */
+};
+#endif
+
 /**
  * struct perf_event - performance event kernel representation:
  */
@@ -832,6 +859,11 @@ struct perf_event {
 	struct event_filter		*filter;
 #endif
 
+#ifdef CONFIG_CGROUP_PERF
+	struct perf_cgroup		*cgrp; /* cgroup event is attach to */
+	int				cgrp_defer_enabled;
+#endif
+
 #endif /* CONFIG_PERF_EVENTS */
 };
 
@@ -886,6 +918,7 @@ struct perf_event_context {
 	u64				generation;
 	int				pin_count;
 	struct rcu_head			rcu_head;
+	int				nr_cgroups; /* cgroup events present */
 };
 
 /*
@@ -905,6 +938,9 @@ struct perf_cpu_context {
 	struct list_head		rotation_list;
 	int				jiffies_interval;
 	struct pmu			*active_pmu;
+#ifdef CONFIG_CGROUP_PERF
+	struct perf_cgroup		*cgrp;
+#endif
 };
 
 struct perf_output_handle {
@@ -1040,11 +1076,11 @@ have_event:
 	__perf_sw_event(event_id, nr, nmi, regs, addr);
 }
 
-extern atomic_t perf_task_events;
+extern atomic_t perf_sched_events;
 
 static inline void perf_event_task_sched_in(struct task_struct *task)
 {
-	COND_STMT(&perf_task_events, __perf_event_task_sched_in(task));
+	COND_STMT(&perf_sched_events, __perf_event_task_sched_in(task));
 }
 
 static inline
@@ -1052,7 +1088,7 @@ void perf_event_task_sched_out(struct task_struct *task, struct task_struct *nex
 {
 	perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 1, NULL, 0);
 
-	COND_STMT(&perf_task_events, __perf_event_task_sched_out(task, next));
+	COND_STMT(&perf_sched_events, __perf_event_task_sched_out(task, next));
 }
 
 extern void perf_event_mmap(struct vm_area_struct *vma);
@@ -1083,6 +1119,10 @@ extern int sysctl_perf_event_paranoid;
 extern int sysctl_perf_event_mlock;
 extern int sysctl_perf_event_sample_rate;
 
+extern int perf_proc_update_handler(struct ctl_table *table, int write,
+		void __user *buffer, size_t *lenp,
+		loff_t *ppos);
+
 static inline bool perf_paranoid_tracepoint_raw(void)
 {
 	return sysctl_perf_event_paranoid > -1;
diff --git a/include/linux/plist.h b/include/linux/plist.h
index 7254eda078e5..c9b9f322c8d8 100644
--- a/include/linux/plist.h
+++ b/include/linux/plist.h
@@ -31,15 +31,17 @@
  *
  * Simple ASCII art explanation:
  *
- * |HEAD          |
- * |              |
- * |prio_list.prev|<------------------------------------|
- * |prio_list.next|<->|pl|<->|pl|<--------------->|pl|<-|
- * |10            |   |10|   |21|   |21|   |21|   |40|   (prio)
- * |              |   |  |   |  |   |  |   |  |   |  |
- * |              |   |  |   |  |   |  |   |  |   |  |
- * |node_list.next|<->|nl|<->|nl|<->|nl|<->|nl|<->|nl|<-|
- * |node_list.prev|<------------------------------------|
+ * pl:prio_list (only for plist_node)
+ * nl:node_list
+ *   HEAD|             NODE(S)
+ *       |
+ *       ||------------------------------------|
+ *       ||->|pl|<->|pl|<--------------->|pl|<-|
+ *       |   |10|   |21|   |21|   |21|   |40|   (prio)
+ *       |   |  |   |  |   |  |   |  |   |  |
+ *       |   |  |   |  |   |  |   |  |   |  |
+ * |->|nl|<->|nl|<->|nl|<->|nl|<->|nl|<->|nl|<-|
+ * |-------------------------------------------|
  *
  * The nodes on the prio_list list are sorted by priority to simplify
  * the insertion of new nodes. There are no nodes with duplicate
@@ -78,7 +80,6 @@
 #include <linux/spinlock_types.h>
 
 struct plist_head {
-	struct list_head prio_list;
 	struct list_head node_list;
 #ifdef CONFIG_DEBUG_PI_LIST
 	raw_spinlock_t *rawlock;
@@ -88,7 +89,8 @@ struct plist_head {
 
 struct plist_node {
 	int			prio;
-	struct plist_head	plist;
+	struct list_head	prio_list;
+	struct list_head	node_list;
 };
 
 #ifdef CONFIG_DEBUG_PI_LIST
@@ -100,7 +102,6 @@ struct plist_node {
 #endif
 
 #define _PLIST_HEAD_INIT(head)				\
-	.prio_list = LIST_HEAD_INIT((head).prio_list),	\
 	.node_list = LIST_HEAD_INIT((head).node_list)
 
 /**
@@ -133,7 +134,8 @@ struct plist_node {
 #define PLIST_NODE_INIT(node, __prio)			\
 {							\
 	.prio  = (__prio),				\
-	.plist = { _PLIST_HEAD_INIT((node).plist) },	\
+	.prio_list = LIST_HEAD_INIT((node).prio_list),	\
+	.node_list = LIST_HEAD_INIT((node).node_list),	\
 }
 
 /**
@@ -144,7 +146,6 @@ struct plist_node {
 static inline void
 plist_head_init(struct plist_head *head, spinlock_t *lock)
 {
-	INIT_LIST_HEAD(&head->prio_list);
 	INIT_LIST_HEAD(&head->node_list);
 #ifdef CONFIG_DEBUG_PI_LIST
 	head->spinlock = lock;
@@ -160,7 +161,6 @@ plist_head_init(struct plist_head *head, spinlock_t *lock)
 static inline void
 plist_head_init_raw(struct plist_head *head, raw_spinlock_t *lock)
 {
-	INIT_LIST_HEAD(&head->prio_list);
 	INIT_LIST_HEAD(&head->node_list);
 #ifdef CONFIG_DEBUG_PI_LIST
 	head->rawlock = lock;
@@ -176,7 +176,8 @@ plist_head_init_raw(struct plist_head *head, raw_spinlock_t *lock)
 static inline void plist_node_init(struct plist_node *node, int prio)
 {
 	node->prio = prio;
-	plist_head_init(&node->plist, NULL);
+	INIT_LIST_HEAD(&node->prio_list);
+	INIT_LIST_HEAD(&node->node_list);
 }
 
 extern void plist_add(struct plist_node *node, struct plist_head *head);
@@ -188,7 +189,7 @@ extern void plist_del(struct plist_node *node, struct plist_head *head);
  * @head:	the head for your list
  */
 #define plist_for_each(pos, head)	\
-	 list_for_each_entry(pos, &(head)->node_list, plist.node_list)
+	 list_for_each_entry(pos, &(head)->node_list, node_list)
 
 /**
  * plist_for_each_safe - iterate safely over a plist of given type
@@ -199,7 +200,7 @@ extern void plist_del(struct plist_node *node, struct plist_head *head);
  * Iterate over a plist of given type, safe against removal of list entry.
  */
 #define plist_for_each_safe(pos, n, head)	\
-	 list_for_each_entry_safe(pos, n, &(head)->node_list, plist.node_list)
+	 list_for_each_entry_safe(pos, n, &(head)->node_list, node_list)
 
 /**
  * plist_for_each_entry	- iterate over list of given type
@@ -208,7 +209,7 @@ extern void plist_del(struct plist_node *node, struct plist_head *head);
  * @mem:	the name of the list_struct within the struct
  */
 #define plist_for_each_entry(pos, head, mem)	\
-	 list_for_each_entry(pos, &(head)->node_list, mem.plist.node_list)
+	 list_for_each_entry(pos, &(head)->node_list, mem.node_list)
 
 /**
  * plist_for_each_entry_safe - iterate safely over list of given type
@@ -220,7 +221,7 @@ extern void plist_del(struct plist_node *node, struct plist_head *head);
  * Iterate over list of given type, safe against removal of list entry.
  */
 #define plist_for_each_entry_safe(pos, n, head, m)	\
-	list_for_each_entry_safe(pos, n, &(head)->node_list, m.plist.node_list)
+	list_for_each_entry_safe(pos, n, &(head)->node_list, m.node_list)
 
 /**
  * plist_head_empty - return !0 if a plist_head is empty
@@ -237,7 +238,7 @@ static inline int plist_head_empty(const struct plist_head *head)
  */
 static inline int plist_node_empty(const struct plist_node *node)
 {
-	return plist_head_empty(&node->plist);
+	return list_empty(&node->node_list);
 }
 
 /* All functions below assume the plist_head is not empty. */
@@ -285,7 +286,7 @@ static inline int plist_node_empty(const struct plist_node *node)
 static inline struct plist_node *plist_first(const struct plist_head *head)
 {
 	return list_entry(head->node_list.next,
-			  struct plist_node, plist.node_list);
+			  struct plist_node, node_list);
 }
 
 /**
@@ -297,7 +298,7 @@ static inline struct plist_node *plist_first(const struct plist_head *head)
 static inline struct plist_node *plist_last(const struct plist_head *head)
 {
 	return list_entry(head->node_list.prev,
-			  struct plist_node, plist.node_list);
+			  struct plist_node, node_list);
 }
 
 #endif
diff --git a/include/linux/posix-clock.h b/include/linux/posix-clock.h
new file mode 100644
index 000000000000..369e19d3750b
--- /dev/null
+++ b/include/linux/posix-clock.h
@@ -0,0 +1,150 @@
+/*
+ * posix-clock.h - support for dynamic clock devices
+ *
+ * Copyright (C) 2010 OMICRON electronics GmbH
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to the Free Software
+ *  Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+#ifndef _LINUX_POSIX_CLOCK_H_
+#define _LINUX_POSIX_CLOCK_H_
+
+#include <linux/cdev.h>
+#include <linux/fs.h>
+#include <linux/poll.h>
+#include <linux/posix-timers.h>
+
+struct posix_clock;
+
+/**
+ * struct posix_clock_operations - functional interface to the clock
+ *
+ * Every posix clock is represented by a character device. Drivers may
+ * optionally offer extended capabilities by implementing the
+ * character device methods. The character device file operations are
+ * first handled by the clock device layer, then passed on to the
+ * driver by calling these functions.
+ *
+ * @owner:          The clock driver should set to THIS_MODULE
+ * @clock_adjtime:  Adjust the clock
+ * @clock_gettime:  Read the current time
+ * @clock_getres:   Get the clock resolution
+ * @clock_settime:  Set the current time value
+ * @timer_create:   Create a new timer
+ * @timer_delete:   Remove a previously created timer
+ * @timer_gettime:  Get remaining time and interval of a timer
+ * @timer_setttime: Set a timer's initial expiration and interval
+ * @fasync:         Optional character device fasync method
+ * @mmap:           Optional character device mmap method
+ * @open:           Optional character device open method
+ * @release:        Optional character device release method
+ * @ioctl:          Optional character device ioctl method
+ * @read:           Optional character device read method
+ * @poll:           Optional character device poll method
+ */
+struct posix_clock_operations {
+	struct module *owner;
+
+	int  (*clock_adjtime)(struct posix_clock *pc, struct timex *tx);
+
+	int  (*clock_gettime)(struct posix_clock *pc, struct timespec *ts);
+
+	int  (*clock_getres) (struct posix_clock *pc, struct timespec *ts);
+
+	int  (*clock_settime)(struct posix_clock *pc,
+			      const struct timespec *ts);
+
+	int  (*timer_create) (struct posix_clock *pc, struct k_itimer *kit);
+
+	int  (*timer_delete) (struct posix_clock *pc, struct k_itimer *kit);
+
+	void (*timer_gettime)(struct posix_clock *pc,
+			      struct k_itimer *kit, struct itimerspec *tsp);
+
+	int  (*timer_settime)(struct posix_clock *pc,
+			      struct k_itimer *kit, int flags,
+			      struct itimerspec *tsp, struct itimerspec *old);
+	/*
+	 * Optional character device methods:
+	 */
+	int     (*fasync)  (struct posix_clock *pc,
+			    int fd, struct file *file, int on);
+
+	long    (*ioctl)   (struct posix_clock *pc,
+			    unsigned int cmd, unsigned long arg);
+
+	int     (*mmap)    (struct posix_clock *pc,
+			    struct vm_area_struct *vma);
+
+	int     (*open)    (struct posix_clock *pc, fmode_t f_mode);
+
+	uint    (*poll)    (struct posix_clock *pc,
+			    struct file *file, poll_table *wait);
+
+	int     (*release) (struct posix_clock *pc);
+
+	ssize_t (*read)    (struct posix_clock *pc,
+			    uint flags, char __user *buf, size_t cnt);
+};
+
+/**
+ * struct posix_clock - represents a dynamic posix clock
+ *
+ * @ops:     Functional interface to the clock
+ * @cdev:    Character device instance for this clock
+ * @kref:    Reference count.
+ * @mutex:   Protects the 'zombie' field from concurrent access.
+ * @zombie:  If 'zombie' is true, then the hardware has disappeared.
+ * @release: A function to free the structure when the reference count reaches
+ *           zero. May be NULL if structure is statically allocated.
+ *
+ * Drivers should embed their struct posix_clock within a private
+ * structure, obtaining a reference to it during callbacks using
+ * container_of().
+ */
+struct posix_clock {
+	struct posix_clock_operations ops;
+	struct cdev cdev;
+	struct kref kref;
+	struct mutex mutex;
+	bool zombie;
+	void (*release)(struct posix_clock *clk);
+};
+
+/**
+ * posix_clock_register() - register a new clock
+ * @clk:   Pointer to the clock. Caller must provide 'ops' and 'release'
+ * @devid: Allocated device id
+ *
+ * A clock driver calls this function to register itself with the
+ * clock device subsystem. If 'clk' points to dynamically allocated
+ * memory, then the caller must provide a 'release' function to free
+ * that memory.
+ *
+ * Returns zero on success, non-zero otherwise.
+ */
+int posix_clock_register(struct posix_clock *clk, dev_t devid);
+
+/**
+ * posix_clock_unregister() - unregister a clock
+ * @clk: Clock instance previously registered via posix_clock_register()
+ *
+ * A clock driver calls this function to remove itself from the clock
+ * device subsystem. The posix_clock itself will remain (in an
+ * inactive state) until its reference count drops to zero, at which
+ * point it will be deallocated with its 'release' method.
+ */
+void posix_clock_unregister(struct posix_clock *clk);
+
+#endif
diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h
index 3e23844a6990..d51243ae0726 100644
--- a/include/linux/posix-timers.h
+++ b/include/linux/posix-timers.h
@@ -4,6 +4,7 @@
 #include <linux/spinlock.h>
 #include <linux/list.h>
 #include <linux/sched.h>
+#include <linux/timex.h>
 
 union cpu_time_count {
 	cputime_t cpu;
@@ -17,10 +18,21 @@ struct cpu_timer_list {
 	int firing;
 };
 
+/*
+ * Bit fields within a clockid:
+ *
+ * The most significant 29 bits hold either a pid or a file descriptor.
+ *
+ * Bit 2 indicates whether a cpu clock refers to a thread or a process.
+ *
+ * Bits 1 and 0 give the type: PROF=0, VIRT=1, SCHED=2, or FD=3.
+ *
+ * A clockid is invalid if bits 2, 1, and 0 are all set.
+ */
 #define CPUCLOCK_PID(clock)		((pid_t) ~((clock) >> 3))
 #define CPUCLOCK_PERTHREAD(clock) \
 	(((clock) & (clockid_t) CPUCLOCK_PERTHREAD_MASK) != 0)
-#define CPUCLOCK_PID_MASK	7
+
 #define CPUCLOCK_PERTHREAD_MASK	4
 #define CPUCLOCK_WHICH(clock)	((clock) & (clockid_t) CPUCLOCK_CLOCK_MASK)
 #define CPUCLOCK_CLOCK_MASK	3
@@ -28,12 +40,17 @@ struct cpu_timer_list {
 #define CPUCLOCK_VIRT		1
 #define CPUCLOCK_SCHED		2
 #define CPUCLOCK_MAX		3
+#define CLOCKFD			CPUCLOCK_MAX
+#define CLOCKFD_MASK		(CPUCLOCK_PERTHREAD_MASK|CPUCLOCK_CLOCK_MASK)
 
 #define MAKE_PROCESS_CPUCLOCK(pid, clock) \
 	((~(clockid_t) (pid) << 3) | (clockid_t) (clock))
 #define MAKE_THREAD_CPUCLOCK(tid, clock) \
 	MAKE_PROCESS_CPUCLOCK((tid), (clock) | CPUCLOCK_PERTHREAD_MASK)
 
+#define FD_TO_CLOCKID(fd)	((~(clockid_t) (fd) << 3) | CLOCKFD)
+#define CLOCKID_TO_FD(clk)	((unsigned int) ~((clk) >> 3))
+
 /* POSIX.1b interval timer structure. */
 struct k_itimer {
 	struct list_head list;		/* free/ allocate list */
@@ -67,10 +84,11 @@ struct k_itimer {
 };
 
 struct k_clock {
-	int res;		/* in nanoseconds */
 	int (*clock_getres) (const clockid_t which_clock, struct timespec *tp);
-	int (*clock_set) (const clockid_t which_clock, struct timespec * tp);
+	int (*clock_set) (const clockid_t which_clock,
+			  const struct timespec *tp);
 	int (*clock_get) (const clockid_t which_clock, struct timespec * tp);
+	int (*clock_adj) (const clockid_t which_clock, struct timex *tx);
 	int (*timer_create) (struct k_itimer *timer);
 	int (*nsleep) (const clockid_t which_clock, int flags,
 		       struct timespec *, struct timespec __user *);
@@ -84,28 +102,14 @@ struct k_clock {
 			   struct itimerspec * cur_setting);
 };
 
-void register_posix_clock(const clockid_t clock_id, struct k_clock *new_clock);
+extern struct k_clock clock_posix_cpu;
+extern struct k_clock clock_posix_dynamic;
 
-/* error handlers for timer_create, nanosleep and settime */
-int do_posix_clock_nonanosleep(const clockid_t, int flags, struct timespec *,
-			       struct timespec __user *);
-int do_posix_clock_nosettime(const clockid_t, struct timespec *tp);
+void posix_timers_register_clock(const clockid_t clock_id, struct k_clock *new_clock);
 
 /* function to call to trigger timer event */
 int posix_timer_event(struct k_itimer *timr, int si_private);
 
-int posix_cpu_clock_getres(const clockid_t which_clock, struct timespec *ts);
-int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *ts);
-int posix_cpu_clock_set(const clockid_t which_clock, const struct timespec *ts);
-int posix_cpu_timer_create(struct k_itimer *timer);
-int posix_cpu_nsleep(const clockid_t which_clock, int flags,
-		     struct timespec *rqtp, struct timespec __user *rmtp);
-long posix_cpu_nsleep_restart(struct restart_block *restart_block);
-int posix_cpu_timer_set(struct k_itimer *timer, int flags,
-			struct itimerspec *new, struct itimerspec *old);
-int posix_cpu_timer_del(struct k_itimer *timer);
-void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp);
-
 void posix_cpu_timer_schedule(struct k_itimer *timer);
 
 void run_posix_cpu_timers(struct task_struct *task);
diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index 8d3a2486544d..ab38ac80b0f9 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -100,6 +100,8 @@ void ring_buffer_free(struct ring_buffer *buffer);
 
 int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size);
 
+void ring_buffer_change_overwrite(struct ring_buffer *buffer, int val);
+
 struct ring_buffer_event *ring_buffer_lock_reserve(struct ring_buffer *buffer,
 						   unsigned long length);
 int ring_buffer_unlock_commit(struct ring_buffer *buffer,
diff --git a/include/linux/rtc.h b/include/linux/rtc.h
index 89c3e5182991..2ca7e8a78060 100644
--- a/include/linux/rtc.h
+++ b/include/linux/rtc.h
@@ -133,7 +133,6 @@ extern struct class *rtc_class;
  * The (current) exceptions are mostly filesystem hooks:
  *   - the proc() hook for procfs
  *   - non-ioctl() chardev hooks:  open(), release(), read_callback()
- *   - periodic irq calls:  irq_set_state(), irq_set_freq()
  *
  * REVISIT those periodic irq calls *do* have ops_lock when they're
  * issued through ioctl() ...
@@ -148,11 +147,8 @@ struct rtc_class_ops {
 	int (*set_alarm)(struct device *, struct rtc_wkalrm *);
 	int (*proc)(struct device *, struct seq_file *);
 	int (*set_mmss)(struct device *, unsigned long secs);
-	int (*irq_set_state)(struct device *, int enabled);
-	int (*irq_set_freq)(struct device *, int freq);
 	int (*read_callback)(struct device *, int data);
 	int (*alarm_irq_enable)(struct device *, unsigned int enabled);
-	int (*update_irq_enable)(struct device *, unsigned int enabled);
 };
 
 #define RTC_DEVICE_NAME_SIZE 20
@@ -227,6 +223,7 @@ extern void rtc_device_unregister(struct rtc_device *rtc);
 extern int rtc_read_time(struct rtc_device *rtc, struct rtc_time *tm);
 extern int rtc_set_time(struct rtc_device *rtc, struct rtc_time *tm);
 extern int rtc_set_mmss(struct rtc_device *rtc, unsigned long secs);
+int __rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm);
 extern int rtc_read_alarm(struct rtc_device *rtc,
 			struct rtc_wkalrm *alrm);
 extern int rtc_set_alarm(struct rtc_device *rtc,
diff --git a/include/linux/rwlock_types.h b/include/linux/rwlock_types.h
index bd31808c7d8e..cc0072e93e36 100644
--- a/include/linux/rwlock_types.h
+++ b/include/linux/rwlock_types.h
@@ -43,14 +43,6 @@ typedef struct {
 				RW_DEP_MAP_INIT(lockname) }
 #endif
 
-/*
- * RW_LOCK_UNLOCKED defeat lockdep state tracking and is hence
- * deprecated.
- *
- * Please use DEFINE_RWLOCK() or __RW_LOCK_UNLOCKED() as appropriate.
- */
-#define RW_LOCK_UNLOCKED	__RW_LOCK_UNLOCKED(old_style_rw_init)
-
 #define DEFINE_RWLOCK(x)	rwlock_t x = __RW_LOCK_UNLOCKED(x)
 
 #endif /* __LINUX_RWLOCK_TYPES_H */
diff --git a/include/linux/rwsem-spinlock.h b/include/linux/rwsem-spinlock.h
index bdfcc2527970..34701241b673 100644
--- a/include/linux/rwsem-spinlock.h
+++ b/include/linux/rwsem-spinlock.h
@@ -12,15 +12,7 @@
 #error "please don't include linux/rwsem-spinlock.h directly, use linux/rwsem.h instead"
 #endif
 
-#include <linux/spinlock.h>
-#include <linux/list.h>
-
 #ifdef __KERNEL__
-
-#include <linux/types.h>
-
-struct rwsem_waiter;
-
 /*
  * the rw-semaphore definition
  * - if activity is 0 then there are no active readers or writers
@@ -37,28 +29,7 @@ struct rw_semaphore {
 #endif
 };
 
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define __RWSEM_DEP_MAP_INIT(lockname) , .dep_map = { .name = #lockname }
-#else
-# define __RWSEM_DEP_MAP_INIT(lockname)
-#endif
-
-#define __RWSEM_INITIALIZER(name) \
-{ 0, __SPIN_LOCK_UNLOCKED(name.wait_lock), LIST_HEAD_INIT((name).wait_list) \
-  __RWSEM_DEP_MAP_INIT(name) }
-
-#define DECLARE_RWSEM(name) \
-	struct rw_semaphore name = __RWSEM_INITIALIZER(name)
-
-extern void __init_rwsem(struct rw_semaphore *sem, const char *name,
-			 struct lock_class_key *key);
-
-#define init_rwsem(sem)						\
-do {								\
-	static struct lock_class_key __key;			\
-								\
-	__init_rwsem((sem), #sem, &__key);			\
-} while (0)
+#define RWSEM_UNLOCKED_VALUE		0x00000000
 
 extern void __down_read(struct rw_semaphore *sem);
 extern int __down_read_trylock(struct rw_semaphore *sem);
diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
index efd348fe8ca7..a8afe9cd000c 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -11,6 +11,9 @@
 
 #include <linux/types.h>
 #include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+
 #include <asm/system.h>
 #include <asm/atomic.h>
 
@@ -19,9 +22,57 @@ struct rw_semaphore;
 #ifdef CONFIG_RWSEM_GENERIC_SPINLOCK
 #include <linux/rwsem-spinlock.h> /* use a generic implementation */
 #else
-#include <asm/rwsem.h> /* use an arch-specific implementation */
+/* All arch specific implementations share the same struct */
+struct rw_semaphore {
+	long			count;
+	spinlock_t		wait_lock;
+	struct list_head	wait_list;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	struct lockdep_map	dep_map;
+#endif
+};
+
+extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem);
+extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
+extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *);
+extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
+
+/* Include the arch specific part */
+#include <asm/rwsem.h>
+
+/* In all implementations count != 0 means locked */
+static inline int rwsem_is_locked(struct rw_semaphore *sem)
+{
+	return sem->count != 0;
+}
+
+#endif
+
+/* Common initializer macros and functions */
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+# define __RWSEM_DEP_MAP_INIT(lockname) , .dep_map = { .name = #lockname }
+#else
+# define __RWSEM_DEP_MAP_INIT(lockname)
 #endif
 
+#define __RWSEM_INITIALIZER(name) \
+	{ RWSEM_UNLOCKED_VALUE, __SPIN_LOCK_UNLOCKED(name.wait_lock),	\
+	  LIST_HEAD_INIT((name).wait_list) __RWSEM_DEP_MAP_INIT(name) }
+
+#define DECLARE_RWSEM(name) \
+	struct rw_semaphore name = __RWSEM_INITIALIZER(name)
+
+extern void __init_rwsem(struct rw_semaphore *sem, const char *name,
+			 struct lock_class_key *key);
+
+#define init_rwsem(sem)						\
+do {								\
+	static struct lock_class_key __key;			\
+								\
+	__init_rwsem((sem), #sem, &__key);			\
+} while (0)
+
 /*
  * lock for reading
  */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 777d8a5ed06b..c15936fe998b 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1058,6 +1058,7 @@ struct sched_class {
 	void (*enqueue_task) (struct rq *rq, struct task_struct *p, int flags);
 	void (*dequeue_task) (struct rq *rq, struct task_struct *p, int flags);
 	void (*yield_task) (struct rq *rq);
+	bool (*yield_to_task) (struct rq *rq, struct task_struct *p, bool preempt);
 
 	void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int flags);
 
@@ -1084,12 +1085,10 @@ struct sched_class {
 	void (*task_tick) (struct rq *rq, struct task_struct *p, int queued);
 	void (*task_fork) (struct task_struct *p);
 
-	void (*switched_from) (struct rq *this_rq, struct task_struct *task,
-			       int running);
-	void (*switched_to) (struct rq *this_rq, struct task_struct *task,
-			     int running);
+	void (*switched_from) (struct rq *this_rq, struct task_struct *task);
+	void (*switched_to) (struct rq *this_rq, struct task_struct *task);
 	void (*prio_changed) (struct rq *this_rq, struct task_struct *task,
-			     int oldprio, int running);
+			     int oldprio);
 
 	unsigned int (*get_rr_interval) (struct rq *rq,
 					 struct task_struct *task);
@@ -1715,7 +1714,6 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *
 /*
  * Per process flags
  */
-#define PF_KSOFTIRQD	0x00000001	/* I am ksoftirqd */
 #define PF_STARTING	0x00000002	/* being created */
 #define PF_EXITING	0x00000004	/* getting shut down */
 #define PF_EXITPIDONE	0x00000008	/* pi exit done on shut down */
@@ -1945,8 +1943,6 @@ int sched_rt_handler(struct ctl_table *table, int write,
 		void __user *buffer, size_t *lenp,
 		loff_t *ppos);
 
-extern unsigned int sysctl_sched_compat_yield;
-
 #ifdef CONFIG_SCHED_AUTOGROUP
 extern unsigned int sysctl_sched_autogroup_enabled;
 
@@ -1977,6 +1973,7 @@ static inline int rt_mutex_getprio(struct task_struct *p)
 # define rt_mutex_adjust_pi(p)		do { } while (0)
 #endif
 
+extern bool yield_to(struct task_struct *p, bool preempt);
 extern void set_user_nice(struct task_struct *p, long nice);
 extern int task_prio(const struct task_struct *p);
 extern int task_nice(const struct task_struct *p);
@@ -2049,7 +2046,7 @@ extern void release_uids(struct user_namespace *ns);
 
 #include <asm/current.h>
 
-extern void do_timer(unsigned long ticks);
+extern void xtime_update(unsigned long ticks);
 
 extern int wake_up_state(struct task_struct *tsk, unsigned int state);
 extern int wake_up_process(struct task_struct *tsk);
@@ -2578,13 +2575,6 @@ static inline void inc_syscw(struct task_struct *tsk)
 #define TASK_SIZE_OF(tsk)	TASK_SIZE
 #endif
 
-/*
- * Call the function if the target task is executing on a CPU right now:
- */
-extern void task_oncpu_function_call(struct task_struct *p,
-				     void (*func) (void *info), void *info);
-
-
 #ifdef CONFIG_MM_OWNER
 extern void mm_update_next_owner(struct mm_struct *mm);
 extern void mm_init_owner(struct mm_struct *mm, struct task_struct *p);
diff --git a/include/linux/security.h b/include/linux/security.h
index b2b7f9749f5e..debbd97db7ab 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -53,7 +53,7 @@ struct audit_krule;
  */
 extern int cap_capable(struct task_struct *tsk, const struct cred *cred,
 		       int cap, int audit);
-extern int cap_settime(struct timespec *ts, struct timezone *tz);
+extern int cap_settime(const struct timespec *ts, const struct timezone *tz);
 extern int cap_ptrace_access_check(struct task_struct *child, unsigned int mode);
 extern int cap_ptrace_traceme(struct task_struct *parent);
 extern int cap_capget(struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted);
@@ -1387,7 +1387,7 @@ struct security_operations {
 	int (*quotactl) (int cmds, int type, int id, struct super_block *sb);
 	int (*quota_on) (struct dentry *dentry);
 	int (*syslog) (int type);
-	int (*settime) (struct timespec *ts, struct timezone *tz);
+	int (*settime) (const struct timespec *ts, const struct timezone *tz);
 	int (*vm_enough_memory) (struct mm_struct *mm, long pages);
 
 	int (*bprm_set_creds) (struct linux_binprm *bprm);
@@ -1669,7 +1669,7 @@ int security_sysctl(struct ctl_table *table, int op);
 int security_quotactl(int cmds, int type, int id, struct super_block *sb);
 int security_quota_on(struct dentry *dentry);
 int security_syslog(int type);
-int security_settime(struct timespec *ts, struct timezone *tz);
+int security_settime(const struct timespec *ts, const struct timezone *tz);
 int security_vm_enough_memory(long pages);
 int security_vm_enough_memory_mm(struct mm_struct *mm, long pages);
 int security_vm_enough_memory_kern(long pages);
@@ -1904,7 +1904,8 @@ static inline int security_syslog(int type)
 	return 0;
 }
 
-static inline int security_settime(struct timespec *ts, struct timezone *tz)
+static inline int security_settime(const struct timespec *ts,
+				   const struct timezone *tz)
 {
 	return cap_settime(ts, tz);
 }
diff --git a/include/linux/spinlock_types.h b/include/linux/spinlock_types.h
index 851b7783720d..73548eb13a5d 100644
--- a/include/linux/spinlock_types.h
+++ b/include/linux/spinlock_types.h
@@ -81,14 +81,6 @@ typedef struct spinlock {
 #define __SPIN_LOCK_UNLOCKED(lockname) \
 	(spinlock_t ) __SPIN_LOCK_INITIALIZER(lockname)
 
-/*
- * SPIN_LOCK_UNLOCKED defeats lockdep state tracking and is hence
- * deprecated.
- * Please use DEFINE_SPINLOCK() or __SPIN_LOCK_UNLOCKED() as
- * appropriate.
- */
-#define SPIN_LOCK_UNLOCKED	__SPIN_LOCK_UNLOCKED(old_style_spin_init)
-
 #define DEFINE_SPINLOCK(x)	spinlock_t x = __SPIN_LOCK_UNLOCKED(x)
 
 #include <linux/rwlock_types.h>
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 98664db1be47..1f5c18e6f4f1 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -62,6 +62,7 @@ struct robust_list_head;
 struct getcpu_cache;
 struct old_linux_dirent;
 struct perf_event_attr;
+struct file_handle;
 
 #include <linux/types.h>
 #include <linux/aio_abi.h>
@@ -132,11 +133,11 @@ extern struct trace_event_functions exit_syscall_print_funcs;
 		.class			= &event_class_syscall_enter,	\
 		.event.funcs            = &enter_syscall_print_funcs,	\
 		.data			= (void *)&__syscall_meta_##sname,\
+		.flags			= TRACE_EVENT_FL_CAP_ANY,	\
 	};								\
 	static struct ftrace_event_call __used				\
 	  __attribute__((section("_ftrace_events")))			\
-	 *__event_enter_##sname = &event_enter_##sname;			\
-	__TRACE_EVENT_FLAGS(enter_##sname, TRACE_EVENT_FL_CAP_ANY)
+	 *__event_enter_##sname = &event_enter_##sname;
 
 #define SYSCALL_TRACE_EXIT_EVENT(sname)					\
 	static struct syscall_metadata __syscall_meta_##sname;		\
@@ -146,11 +147,11 @@ extern struct trace_event_functions exit_syscall_print_funcs;
 		.class			= &event_class_syscall_exit,	\
 		.event.funcs		= &exit_syscall_print_funcs,	\
 		.data			= (void *)&__syscall_meta_##sname,\
+		.flags			= TRACE_EVENT_FL_CAP_ANY,	\
 	};								\
 	static struct ftrace_event_call __used				\
 	  __attribute__((section("_ftrace_events")))			\
-	*__event_exit_##sname = &event_exit_##sname;			\
-	__TRACE_EVENT_FLAGS(exit_##sname, TRACE_EVENT_FL_CAP_ANY)
+	*__event_exit_##sname = &event_exit_##sname;
 
 #define SYSCALL_METADATA(sname, nb)				\
 	SYSCALL_TRACE_ENTER_EVENT(sname);			\
@@ -158,6 +159,7 @@ extern struct trace_event_functions exit_syscall_print_funcs;
 	static struct syscall_metadata __used			\
 	  __syscall_meta_##sname = {				\
 		.name 		= "sys"#sname,			\
+		.syscall_nr	= -1,	/* Filled in at boot */	\
 		.nb_args 	= nb,				\
 		.types		= types_##sname,		\
 		.args		= args_##sname,			\
@@ -175,6 +177,7 @@ extern struct trace_event_functions exit_syscall_print_funcs;
 	static struct syscall_metadata __used			\
 	  __syscall_meta__##sname = {				\
 		.name 		= "sys_"#sname,			\
+		.syscall_nr	= -1,	/* Filled in at boot */	\
 		.nb_args 	= 0,				\
 		.enter_event	= &event_enter__##sname,	\
 		.exit_event	= &event_exit__##sname,		\
@@ -313,6 +316,8 @@ asmlinkage long sys_clock_settime(clockid_t which_clock,
 				const struct timespec __user *tp);
 asmlinkage long sys_clock_gettime(clockid_t which_clock,
 				struct timespec __user *tp);
+asmlinkage long sys_clock_adjtime(clockid_t which_clock,
+				struct timex __user *tx);
 asmlinkage long sys_clock_getres(clockid_t which_clock,
 				struct timespec __user *tp);
 asmlinkage long sys_clock_nanosleep(clockid_t which_clock, int flags,
@@ -832,5 +837,10 @@ asmlinkage long sys_mmap_pgoff(unsigned long addr, unsigned long len,
 			unsigned long prot, unsigned long flags,
 			unsigned long fd, unsigned long pgoff);
 asmlinkage long sys_old_mmap(struct mmap_arg_struct __user *arg);
-
+asmlinkage long sys_name_to_handle_at(int dfd, const char __user *name,
+				      struct file_handle __user *handle,
+				      int __user *mnt_id, int flag);
+asmlinkage long sys_open_by_handle_at(int mountdirfd,
+				      struct file_handle __user *handle,
+				      int flags);
 #endif
diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index c90696544176..20fc303947d3 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -18,9 +18,6 @@ struct compat_timespec;
 struct restart_block {
 	long (*fn)(struct restart_block *);
 	union {
-		struct {
-			unsigned long arg0, arg1, arg2, arg3;
-		};
 		/* For futex_wait and futex_wait_requeue_pi */
 		struct {
 			u32 __user *uaddr;
diff --git a/include/linux/time.h b/include/linux/time.h
index 1e6d3b59238d..454a26205787 100644
--- a/include/linux/time.h
+++ b/include/linux/time.h
@@ -113,8 +113,6 @@ static inline struct timespec timespec_sub(struct timespec lhs,
 #define timespec_valid(ts) \
 	(((ts)->tv_sec >= 0) && (((unsigned long) (ts)->tv_nsec) < NSEC_PER_SEC))
 
-extern seqlock_t xtime_lock;
-
 extern void read_persistent_clock(struct timespec *ts);
 extern void read_boot_clock(struct timespec *ts);
 extern int update_persistent_clock(struct timespec now);
@@ -125,8 +123,9 @@ extern int timekeeping_suspended;
 unsigned long get_seconds(void);
 struct timespec current_kernel_time(void);
 struct timespec __current_kernel_time(void); /* does not take xtime_lock */
-struct timespec __get_wall_to_monotonic(void); /* does not take xtime_lock */
 struct timespec get_monotonic_coarse(void);
+void get_xtime_and_monotonic_and_sleep_offset(struct timespec *xtim,
+				struct timespec *wtom, struct timespec *sleep);
 
 #define CURRENT_TIME		(current_kernel_time())
 #define CURRENT_TIME_SEC	((struct timespec) { get_seconds(), 0 })
@@ -147,8 +146,9 @@ static inline u32 arch_gettimeoffset(void) { return 0; }
 #endif
 
 extern void do_gettimeofday(struct timeval *tv);
-extern int do_settimeofday(struct timespec *tv);
-extern int do_sys_settimeofday(struct timespec *tv, struct timezone *tz);
+extern int do_settimeofday(const struct timespec *tv);
+extern int do_sys_settimeofday(const struct timespec *tv,
+			       const struct timezone *tz);
 #define do_posix_clock_monotonic_gettime(ts) ktime_get_ts(ts)
 extern long do_utimes(int dfd, const char __user *filename, struct timespec *times, int flags);
 struct itimerval;
@@ -162,12 +162,13 @@ extern void getnstime_raw_and_real(struct timespec *ts_raw,
 		struct timespec *ts_real);
 extern void getboottime(struct timespec *ts);
 extern void monotonic_to_bootbased(struct timespec *ts);
+extern void get_monotonic_boottime(struct timespec *ts);
 
 extern struct timespec timespec_trunc(struct timespec t, unsigned gran);
 extern int timekeeping_valid_for_hres(void);
 extern u64 timekeeping_max_deferment(void);
-extern void update_wall_time(void);
 extern void timekeeping_leap_insert(int leapsecond);
+extern int timekeeping_inject_offset(struct timespec *ts);
 
 struct tms;
 extern void do_sys_times(struct tms *);
@@ -292,6 +293,7 @@ struct itimerval {
 #define CLOCK_MONOTONIC_RAW		4
 #define CLOCK_REALTIME_COARSE		5
 #define CLOCK_MONOTONIC_COARSE		6
+#define CLOCK_BOOTTIME			7
 
 /*
  * The IDs of various hardware clocks:
diff --git a/include/linux/timex.h b/include/linux/timex.h
index d23999f9499d..aa60fe7b6ed6 100644
--- a/include/linux/timex.h
+++ b/include/linux/timex.h
@@ -73,7 +73,7 @@ struct timex {
 	long tolerance;		/* clock frequency tolerance (ppm)
 				 * (read only)
 				 */
-	struct timeval time;	/* (read only) */
+	struct timeval time;	/* (read only, except for ADJ_SETOFFSET) */
 	long tick;		/* (modified) usecs between clock ticks */
 
 	long ppsfreq;           /* pps frequency (scaled ppm) (ro) */
@@ -102,6 +102,7 @@ struct timex {
 #define ADJ_STATUS		0x0010	/* clock status */
 #define ADJ_TIMECONST		0x0020	/* pll time constant */
 #define ADJ_TAI			0x0080	/* set TAI offset */
+#define ADJ_SETOFFSET		0x0100  /* add 'time' to current time */
 #define ADJ_MICRO		0x1000	/* select microsecond resolution */
 #define ADJ_NANO		0x2000	/* select nanosecond resolution */
 #define ADJ_TICK		0x4000	/* tick value */
diff --git a/include/trace/events/mce.h b/include/trace/events/mce.h
index 7eee77895cb3..4cbbcef6baa8 100644
--- a/include/trace/events/mce.h
+++ b/include/trace/events/mce.h
@@ -17,36 +17,36 @@ TRACE_EVENT(mce_record,
 	TP_STRUCT__entry(
 		__field(	u64,		mcgcap		)
 		__field(	u64,		mcgstatus	)
-		__field(	u8,		bank		)
 		__field(	u64,		status		)
 		__field(	u64,		addr		)
 		__field(	u64,		misc		)
 		__field(	u64,		ip		)
-		__field(	u8,		cs		)
 		__field(	u64,		tsc		)
 		__field(	u64,		walltime	)
 		__field(	u32,		cpu		)
 		__field(	u32,		cpuid		)
 		__field(	u32,		apicid		)
 		__field(	u32,		socketid	)
+		__field(	u8,		cs		)
+		__field(	u8,		bank		)
 		__field(	u8,		cpuvendor	)
 	),
 
 	TP_fast_assign(
 		__entry->mcgcap		= m->mcgcap;
 		__entry->mcgstatus	= m->mcgstatus;
-		__entry->bank		= m->bank;
 		__entry->status		= m->status;
 		__entry->addr		= m->addr;
 		__entry->misc		= m->misc;
 		__entry->ip		= m->ip;
-		__entry->cs		= m->cs;
 		__entry->tsc		= m->tsc;
 		__entry->walltime	= m->time;
 		__entry->cpu		= m->extcpu;
 		__entry->cpuid		= m->cpuid;
 		__entry->apicid		= m->apicid;
 		__entry->socketid	= m->socketid;
+		__entry->cs		= m->cs;
+		__entry->bank		= m->bank;
 		__entry->cpuvendor	= m->cpuvendor;
 	),
 
diff --git a/include/trace/events/module.h b/include/trace/events/module.h
index c6bae36547e5..21a546d27c0c 100644
--- a/include/trace/events/module.h
+++ b/include/trace/events/module.h
@@ -108,14 +108,14 @@ TRACE_EVENT(module_request,
 	TP_ARGS(name, wait, ip),
 
 	TP_STRUCT__entry(
-		__field(	bool,		wait		)
 		__field(	unsigned long,	ip		)
+		__field(	bool,		wait		)
 		__string(	name,		name		)
 	),
 
 	TP_fast_assign(
-		__entry->wait	= wait;
 		__entry->ip	= ip;
+		__entry->wait	= wait;
 		__assign_str(name, name);
 	),
 
@@ -129,4 +129,3 @@ TRACE_EVENT(module_request,
 
 /* This part must be outside protection */
 #include <trace/define_trace.h>
-
diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h
index f10293c41b1e..0c68ae22da22 100644
--- a/include/trace/events/skb.h
+++ b/include/trace/events/skb.h
@@ -19,14 +19,14 @@ TRACE_EVENT(kfree_skb,
 
 	TP_STRUCT__entry(
 		__field(	void *,		skbaddr		)
-		__field(	unsigned short,	protocol	)
 		__field(	void *,		location	)
+		__field(	unsigned short,	protocol	)
 	),
 
 	TP_fast_assign(
 		__entry->skbaddr = skb;
-		__entry->protocol = ntohs(skb->protocol);
 		__entry->location = location;
+		__entry->protocol = ntohs(skb->protocol);
 	),
 
 	TP_printk("skbaddr=%p protocol=%u location=%p",
diff --git a/include/xen/events.h b/include/xen/events.h
index 00f53ddcc062..962da2ced5b4 100644
--- a/include/xen/events.h
+++ b/include/xen/events.h
@@ -75,11 +75,9 @@ int xen_allocate_pirq(unsigned gsi, int shareable, char *name);
 int xen_map_pirq_gsi(unsigned pirq, unsigned gsi, int shareable, char *name);
 
 #ifdef CONFIG_PCI_MSI
-/* Allocate an irq and a pirq to be used with MSIs. */
-#define XEN_ALLOC_PIRQ (1 << 0)
-#define XEN_ALLOC_IRQ  (1 << 1)
-void xen_allocate_pirq_msi(char *name, int *irq, int *pirq, int alloc_mask);
-int xen_create_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int type);
+int xen_allocate_pirq_msi(struct pci_dev *dev, struct msi_desc *msidesc);
+int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc,
+			     int pirq, int vector, const char *name);
 #endif
 
 /* De-allocates the above mentioned physical interrupt. */
diff --git a/include/xen/interface/io/blkif.h b/include/xen/interface/io/blkif.h
index c2d1fa4dc1ee..61e523af3c46 100644
--- a/include/xen/interface/io/blkif.h
+++ b/include/xen/interface/io/blkif.h
@@ -51,11 +51,7 @@ typedef uint64_t blkif_sector_t;
  */
 #define BLKIF_MAX_SEGMENTS_PER_REQUEST 11
 
-struct blkif_request {
-	uint8_t        operation;    /* BLKIF_OP_???                         */
-	uint8_t        nr_segments;  /* number of segments                   */
-	blkif_vdev_t   handle;       /* only for read/write requests         */
-	uint64_t       id;           /* private guest value, echoed in resp  */
+struct blkif_request_rw {
 	blkif_sector_t sector_number;/* start sector idx on disk (r/w only)  */
 	struct blkif_request_segment {
 		grant_ref_t gref;        /* reference to I/O buffer frame        */
@@ -65,6 +61,16 @@ struct blkif_request {
 	} seg[BLKIF_MAX_SEGMENTS_PER_REQUEST];
 };
 
+struct blkif_request {
+	uint8_t        operation;    /* BLKIF_OP_???                         */
+	uint8_t        nr_segments;  /* number of segments                   */
+	blkif_vdev_t   handle;       /* only for read/write requests         */
+	uint64_t       id;           /* private guest value, echoed in resp  */
+	union {
+		struct blkif_request_rw rw;
+	} u;
+};
+
 struct blkif_response {
 	uint64_t        id;              /* copied from request */
 	uint8_t         operation;       /* copied from request */
@@ -91,4 +97,25 @@ DEFINE_RING_TYPES(blkif, struct blkif_request, struct blkif_response);
 #define VDISK_REMOVABLE    0x2
 #define VDISK_READONLY     0x4
 
+/* Xen-defined major numbers for virtual disks, they look strangely
+ * familiar */
+#define XEN_IDE0_MAJOR	3
+#define XEN_IDE1_MAJOR	22
+#define XEN_SCSI_DISK0_MAJOR	8
+#define XEN_SCSI_DISK1_MAJOR	65
+#define XEN_SCSI_DISK2_MAJOR	66
+#define XEN_SCSI_DISK3_MAJOR	67
+#define XEN_SCSI_DISK4_MAJOR	68
+#define XEN_SCSI_DISK5_MAJOR	69
+#define XEN_SCSI_DISK6_MAJOR	70
+#define XEN_SCSI_DISK7_MAJOR	71
+#define XEN_SCSI_DISK8_MAJOR	128
+#define XEN_SCSI_DISK9_MAJOR	129
+#define XEN_SCSI_DISK10_MAJOR	130
+#define XEN_SCSI_DISK11_MAJOR	131
+#define XEN_SCSI_DISK12_MAJOR	132
+#define XEN_SCSI_DISK13_MAJOR	133
+#define XEN_SCSI_DISK14_MAJOR	134
+#define XEN_SCSI_DISK15_MAJOR	135
+
 #endif /* __XEN_PUBLIC_IO_BLKIF_H__ */
diff --git a/include/xen/interface/xen.h b/include/xen/interface/xen.h
index 2befa3e2f1bc..b33257bc7e83 100644
--- a/include/xen/interface/xen.h
+++ b/include/xen/interface/xen.h
@@ -30,7 +30,7 @@
 #define __HYPERVISOR_stack_switch          3
 #define __HYPERVISOR_set_callbacks         4
 #define __HYPERVISOR_fpu_taskswitch        5
-#define __HYPERVISOR_sched_op              6
+#define __HYPERVISOR_sched_op_compat       6
 #define __HYPERVISOR_dom0_op               7
 #define __HYPERVISOR_set_debugreg          8
 #define __HYPERVISOR_get_debugreg          9
@@ -52,7 +52,7 @@
 #define __HYPERVISOR_mmuext_op            26
 #define __HYPERVISOR_acm_op               27
 #define __HYPERVISOR_nmi_op               28
-#define __HYPERVISOR_sched_op_new         29
+#define __HYPERVISOR_sched_op             29
 #define __HYPERVISOR_callback_op          30
 #define __HYPERVISOR_xenoprof_op          31
 #define __HYPERVISOR_event_channel_op     32
diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h
index 98b92154a264..03c85d7387fb 100644
--- a/include/xen/xen-ops.h
+++ b/include/xen/xen-ops.h
@@ -5,9 +5,9 @@
 
 DECLARE_PER_CPU(struct vcpu_info *, xen_vcpu);
 
-void xen_pre_suspend(void);
-void xen_post_suspend(int suspend_cancelled);
-void xen_hvm_post_suspend(int suspend_cancelled);
+void xen_arch_pre_suspend(void);
+void xen_arch_post_suspend(int suspend_cancelled);
+void xen_arch_hvm_post_suspend(int suspend_cancelled);
 
 void xen_mm_pin_all(void);
 void xen_mm_unpin_all(void);
diff --git a/init/Kconfig b/init/Kconfig
index be788c0957d4..5721d27af626 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -287,6 +287,18 @@ config BSD_PROCESS_ACCT_V3
 	  for processing it. A preliminary version of these tools is available
 	  at <http://www.gnu.org/software/acct/>.
 
+config FHANDLE
+	bool "open by fhandle syscalls"
+	select EXPORTFS
+	help
+	  If you say Y here, a user level program will be able to map
+	  file names to handle and then later use the handle for
+	  different file system operations. This is useful in implementing
+	  userspace file servers, which now track files using handles instead
+	  of names. The handle would remain the same even if file names
+	  get renamed. Enables open_by_handle_at(2) and name_to_handle_at(2)
+	  syscalls.
+
 config TASKSTATS
 	bool "Export task/process statistics through netlink (EXPERIMENTAL)"
 	depends on NET
@@ -683,6 +695,16 @@ config CGROUP_MEM_RES_CTLR_SWAP_ENABLED
 	  select this option (if, for some reason, they need to disable it
 	  then noswapaccount does the trick).
 
+config CGROUP_PERF
+	bool "Enable perf_event per-cpu per-container group (cgroup) monitoring"
+	depends on PERF_EVENTS && CGROUPS
+	help
+	  This option extends the per-cpu mode to restrict monitoring to
+	  threads which belong to the cgroup specified and run on the
+	  designated cpu.
+
+	  Say N if unsure.
+
 menuconfig CGROUP_SCHED
 	bool "Group CPU scheduler"
 	depends on EXPERIMENTAL
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index d2e3c7866460..e683869365d9 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -144,9 +144,9 @@ int audit_watch_compare(struct audit_watch *watch, unsigned long ino, dev_t dev)
 }
 
 /* Initialize a parent watch entry. */
-static struct audit_parent *audit_init_parent(struct nameidata *ndp)
+static struct audit_parent *audit_init_parent(struct path *path)
 {
-	struct inode *inode = ndp->path.dentry->d_inode;
+	struct inode *inode = path->dentry->d_inode;
 	struct audit_parent *parent;
 	int ret;
 
@@ -353,53 +353,40 @@ static void audit_remove_parent_watches(struct audit_parent *parent)
 }
 
 /* Get path information necessary for adding watches. */
-static int audit_get_nd(char *path, struct nameidata **ndp, struct nameidata **ndw)
+static int audit_get_nd(struct audit_watch *watch, struct path *parent)
 {
-	struct nameidata *ndparent, *ndwatch;
+	struct nameidata nd;
+	struct dentry *d;
 	int err;
 
-	ndparent = kmalloc(sizeof(*ndparent), GFP_KERNEL);
-	if (unlikely(!ndparent))
-		return -ENOMEM;
+	err = kern_path_parent(watch->path, &nd);
+	if (err)
+		return err;
 
-	ndwatch = kmalloc(sizeof(*ndwatch), GFP_KERNEL);
-	if (unlikely(!ndwatch)) {
-		kfree(ndparent);
-		return -ENOMEM;
+	if (nd.last_type != LAST_NORM) {
+		path_put(&nd.path);
+		return -EINVAL;
 	}
 
-	err = path_lookup(path, LOOKUP_PARENT, ndparent);
-	if (err) {
-		kfree(ndparent);
-		kfree(ndwatch);
-		return err;
+	mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
+	d = lookup_one_len(nd.last.name, nd.path.dentry, nd.last.len);
+	if (IS_ERR(d)) {
+		mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
+		path_put(&nd.path);
+		return PTR_ERR(d);
 	}
-
-	err = path_lookup(path, 0, ndwatch);
-	if (err) {
-		kfree(ndwatch);
-		ndwatch = NULL;
+	if (d->d_inode) {
+		/* update watch filter fields */
+		watch->dev = d->d_inode->i_sb->s_dev;
+		watch->ino = d->d_inode->i_ino;
 	}
+	mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
 
-	*ndp = ndparent;
-	*ndw = ndwatch;
-
+	*parent = nd.path;
+	dput(d);
 	return 0;
 }
 
-/* Release resources used for watch path information. */
-static void audit_put_nd(struct nameidata *ndp, struct nameidata *ndw)
-{
-	if (ndp) {
-		path_put(&ndp->path);
-		kfree(ndp);
-	}
-	if (ndw) {
-		path_put(&ndw->path);
-		kfree(ndw);
-	}
-}
-
 /* Associate the given rule with an existing parent.
  * Caller must hold audit_filter_mutex. */
 static void audit_add_to_parent(struct audit_krule *krule,
@@ -440,31 +427,24 @@ int audit_add_watch(struct audit_krule *krule, struct list_head **list)
 {
 	struct audit_watch *watch = krule->watch;
 	struct audit_parent *parent;
-	struct nameidata *ndp = NULL, *ndw = NULL;
+	struct path parent_path;
 	int h, ret = 0;
 
 	mutex_unlock(&audit_filter_mutex);
 
 	/* Avoid calling path_lookup under audit_filter_mutex. */
-	ret = audit_get_nd(watch->path, &ndp, &ndw);
-	if (ret) {
-		/* caller expects mutex locked */
-		mutex_lock(&audit_filter_mutex);
-		goto error;
-	}
+	ret = audit_get_nd(watch, &parent_path);
 
+	/* caller expects mutex locked */
 	mutex_lock(&audit_filter_mutex);
 
-	/* update watch filter fields */
-	if (ndw) {
-		watch->dev = ndw->path.dentry->d_inode->i_sb->s_dev;
-		watch->ino = ndw->path.dentry->d_inode->i_ino;
-	}
+	if (ret)
+		return ret;
 
 	/* either find an old parent or attach a new one */
-	parent = audit_find_parent(ndp->path.dentry->d_inode);
+	parent = audit_find_parent(parent_path.dentry->d_inode);
 	if (!parent) {
-		parent = audit_init_parent(ndp);
+		parent = audit_init_parent(&parent_path);
 		if (IS_ERR(parent)) {
 			ret = PTR_ERR(parent);
 			goto error;
@@ -479,9 +459,8 @@ int audit_add_watch(struct audit_krule *krule, struct list_head **list)
 	h = audit_hash_ino((u32)watch->ino);
 	*list = &audit_inode_hash[h];
 error:
-	audit_put_nd(ndp, ndw);		/* NULL args OK */
+	path_put(&parent_path);
 	return ret;
-
 }
 
 void audit_remove_watch_rule(struct audit_krule *krule)
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index b24d7027b83c..95362d15128c 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -4230,20 +4230,8 @@ void cgroup_post_fork(struct task_struct *child)
  */
 void cgroup_exit(struct task_struct *tsk, int run_callbacks)
 {
-	int i;
 	struct css_set *cg;
-
-	if (run_callbacks && need_forkexit_callback) {
-		/*
-		 * modular subsystems can't use callbacks, so no need to lock
-		 * the subsys array
-		 */
-		for (i = 0; i < CGROUP_BUILTIN_SUBSYS_COUNT; i++) {
-			struct cgroup_subsys *ss = subsys[i];
-			if (ss->exit)
-				ss->exit(ss, tsk);
-		}
-	}
+	int i;
 
 	/*
 	 * Unlink from the css_set task list if necessary.
@@ -4261,7 +4249,24 @@ void cgroup_exit(struct task_struct *tsk, int run_callbacks)
 	task_lock(tsk);
 	cg = tsk->cgroups;
 	tsk->cgroups = &init_css_set;
+
+	if (run_callbacks && need_forkexit_callback) {
+		/*
+		 * modular subsystems can't use callbacks, so no need to lock
+		 * the subsys array
+		 */
+		for (i = 0; i < CGROUP_BUILTIN_SUBSYS_COUNT; i++) {
+			struct cgroup_subsys *ss = subsys[i];
+			if (ss->exit) {
+				struct cgroup *old_cgrp =
+					rcu_dereference_raw(cg->subsys[i])->cgroup;
+				struct cgroup *cgrp = task_cgroup(tsk, i);
+				ss->exit(ss, cgrp, old_cgrp, tsk);
+			}
+		}
+	}
 	task_unlock(tsk);
+
 	if (cg)
 		put_css_set_taskexit(cg);
 }
@@ -4813,6 +4818,29 @@ css_get_next(struct cgroup_subsys *ss, int id,
 	return ret;
 }
 
+/*
+ * get corresponding css from file open on cgroupfs directory
+ */
+struct cgroup_subsys_state *cgroup_css_from_dir(struct file *f, int id)
+{
+	struct cgroup *cgrp;
+	struct inode *inode;
+	struct cgroup_subsys_state *css;
+
+	inode = f->f_dentry->d_inode;
+	/* check in cgroup filesystem dir */
+	if (inode->i_op != &cgroup_dir_inode_operations)
+		return ERR_PTR(-EBADF);
+
+	if (id < 0 || id >= CGROUP_SUBSYS_COUNT)
+		return ERR_PTR(-EINVAL);
+
+	/* get cgroup */
+	cgrp = __d_cgrp(f->f_dentry);
+	css = cgrp->subsys[id];
+	return css ? css : ERR_PTR(-ENOENT);
+}
+
 #ifdef CONFIG_CGROUP_DEBUG
 static struct cgroup_subsys_state *debug_create(struct cgroup_subsys *ss,
 						   struct cgroup *cont)
diff --git a/kernel/compat.c b/kernel/compat.c
index c9e2ec0b34a8..38b1d2c1cbe8 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -52,6 +52,64 @@ static int compat_put_timeval(struct compat_timeval __user *o,
 		put_user(i->tv_usec, &o->tv_usec)) ? -EFAULT : 0;
 }
 
+static int compat_get_timex(struct timex *txc, struct compat_timex __user *utp)
+{
+	memset(txc, 0, sizeof(struct timex));
+
+	if (!access_ok(VERIFY_READ, utp, sizeof(struct compat_timex)) ||
+			__get_user(txc->modes, &utp->modes) ||
+			__get_user(txc->offset, &utp->offset) ||
+			__get_user(txc->freq, &utp->freq) ||
+			__get_user(txc->maxerror, &utp->maxerror) ||
+			__get_user(txc->esterror, &utp->esterror) ||
+			__get_user(txc->status, &utp->status) ||
+			__get_user(txc->constant, &utp->constant) ||
+			__get_user(txc->precision, &utp->precision) ||
+			__get_user(txc->tolerance, &utp->tolerance) ||
+			__get_user(txc->time.tv_sec, &utp->time.tv_sec) ||
+			__get_user(txc->time.tv_usec, &utp->time.tv_usec) ||
+			__get_user(txc->tick, &utp->tick) ||
+			__get_user(txc->ppsfreq, &utp->ppsfreq) ||
+			__get_user(txc->jitter, &utp->jitter) ||
+			__get_user(txc->shift, &utp->shift) ||
+			__get_user(txc->stabil, &utp->stabil) ||
+			__get_user(txc->jitcnt, &utp->jitcnt) ||
+			__get_user(txc->calcnt, &utp->calcnt) ||
+			__get_user(txc->errcnt, &utp->errcnt) ||
+			__get_user(txc->stbcnt, &utp->stbcnt))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int compat_put_timex(struct compat_timex __user *utp, struct timex *txc)
+{
+	if (!access_ok(VERIFY_WRITE, utp, sizeof(struct compat_timex)) ||
+			__put_user(txc->modes, &utp->modes) ||
+			__put_user(txc->offset, &utp->offset) ||
+			__put_user(txc->freq, &utp->freq) ||
+			__put_user(txc->maxerror, &utp->maxerror) ||
+			__put_user(txc->esterror, &utp->esterror) ||
+			__put_user(txc->status, &utp->status) ||
+			__put_user(txc->constant, &utp->constant) ||
+			__put_user(txc->precision, &utp->precision) ||
+			__put_user(txc->tolerance, &utp->tolerance) ||
+			__put_user(txc->time.tv_sec, &utp->time.tv_sec) ||
+			__put_user(txc->time.tv_usec, &utp->time.tv_usec) ||
+			__put_user(txc->tick, &utp->tick) ||
+			__put_user(txc->ppsfreq, &utp->ppsfreq) ||
+			__put_user(txc->jitter, &utp->jitter) ||
+			__put_user(txc->shift, &utp->shift) ||
+			__put_user(txc->stabil, &utp->stabil) ||
+			__put_user(txc->jitcnt, &utp->jitcnt) ||
+			__put_user(txc->calcnt, &utp->calcnt) ||
+			__put_user(txc->errcnt, &utp->errcnt) ||
+			__put_user(txc->stbcnt, &utp->stbcnt) ||
+			__put_user(txc->tai, &utp->tai))
+		return -EFAULT;
+	return 0;
+}
+
 asmlinkage long compat_sys_gettimeofday(struct compat_timeval __user *tv,
 		struct timezone __user *tz)
 {
@@ -617,6 +675,29 @@ long compat_sys_clock_gettime(clockid_t which_clock,
 	return err;
 }
 
+long compat_sys_clock_adjtime(clockid_t which_clock,
+		struct compat_timex __user *utp)
+{
+	struct timex txc;
+	mm_segment_t oldfs;
+	int err, ret;
+
+	err = compat_get_timex(&txc, utp);
+	if (err)
+		return err;
+
+	oldfs = get_fs();
+	set_fs(KERNEL_DS);
+	ret = sys_clock_adjtime(which_clock, (struct timex __user *) &txc);
+	set_fs(oldfs);
+
+	err = compat_put_timex(utp, &txc);
+	if (err)
+		return err;
+
+	return ret;
+}
+
 long compat_sys_clock_getres(clockid_t which_clock,
 		struct compat_timespec __user *tp)
 {
@@ -951,58 +1032,17 @@ asmlinkage long compat_sys_rt_sigsuspend(compat_sigset_t __user *unewset, compat
 asmlinkage long compat_sys_adjtimex(struct compat_timex __user *utp)
 {
 	struct timex txc;
-	int ret;
-
-	memset(&txc, 0, sizeof(struct timex));
+	int err, ret;
 
-	if (!access_ok(VERIFY_READ, utp, sizeof(struct compat_timex)) ||
-			__get_user(txc.modes, &utp->modes) ||
-			__get_user(txc.offset, &utp->offset) ||
-			__get_user(txc.freq, &utp->freq) ||
-			__get_user(txc.maxerror, &utp->maxerror) ||
-			__get_user(txc.esterror, &utp->esterror) ||
-			__get_user(txc.status, &utp->status) ||
-			__get_user(txc.constant, &utp->constant) ||
-			__get_user(txc.precision, &utp->precision) ||
-			__get_user(txc.tolerance, &utp->tolerance) ||
-			__get_user(txc.time.tv_sec, &utp->time.tv_sec) ||
-			__get_user(txc.time.tv_usec, &utp->time.tv_usec) ||
-			__get_user(txc.tick, &utp->tick) ||
-			__get_user(txc.ppsfreq, &utp->ppsfreq) ||
-			__get_user(txc.jitter, &utp->jitter) ||
-			__get_user(txc.shift, &utp->shift) ||
-			__get_user(txc.stabil, &utp->stabil) ||
-			__get_user(txc.jitcnt, &utp->jitcnt) ||
-			__get_user(txc.calcnt, &utp->calcnt) ||
-			__get_user(txc.errcnt, &utp->errcnt) ||
-			__get_user(txc.stbcnt, &utp->stbcnt))
-		return -EFAULT;
+	err = compat_get_timex(&txc, utp);
+	if (err)
+		return err;
 
 	ret = do_adjtimex(&txc);
 
-	if (!access_ok(VERIFY_WRITE, utp, sizeof(struct compat_timex)) ||
-			__put_user(txc.modes, &utp->modes) ||
-			__put_user(txc.offset, &utp->offset) ||
-			__put_user(txc.freq, &utp->freq) ||
-			__put_user(txc.maxerror, &utp->maxerror) ||
-			__put_user(txc.esterror, &utp->esterror) ||
-			__put_user(txc.status, &utp->status) ||
-			__put_user(txc.constant, &utp->constant) ||
-			__put_user(txc.precision, &utp->precision) ||
-			__put_user(txc.tolerance, &utp->tolerance) ||
-			__put_user(txc.time.tv_sec, &utp->time.tv_sec) ||
-			__put_user(txc.time.tv_usec, &utp->time.tv_usec) ||
-			__put_user(txc.tick, &utp->tick) ||
-			__put_user(txc.ppsfreq, &utp->ppsfreq) ||
-			__put_user(txc.jitter, &utp->jitter) ||
-			__put_user(txc.shift, &utp->shift) ||
-			__put_user(txc.stabil, &utp->stabil) ||
-			__put_user(txc.jitcnt, &utp->jitcnt) ||
-			__put_user(txc.calcnt, &utp->calcnt) ||
-			__put_user(txc.errcnt, &utp->errcnt) ||
-			__put_user(txc.stbcnt, &utp->stbcnt) ||
-			__put_user(txc.tai, &utp->tai))
-		ret = -EFAULT;
+	err = compat_put_timex(utp, &txc);
+	if (err)
+		return err;
 
 	return ret;
 }
diff --git a/kernel/cred.c b/kernel/cred.c
index 3a9d6dd53a6c..2343c132c5a7 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -35,7 +35,7 @@ static struct kmem_cache *cred_jar;
 static struct thread_group_cred init_tgcred = {
 	.usage	= ATOMIC_INIT(2),
 	.tgid	= 0,
-	.lock	= SPIN_LOCK_UNLOCKED,
+	.lock	= __SPIN_LOCK_UNLOCKED(init_cred.tgcred.lock),
 };
 #endif
 
diff --git a/kernel/futex.c b/kernel/futex.c
index b766d28accd6..bda415715382 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -381,15 +381,16 @@ static struct futex_q *futex_top_waiter(struct futex_hash_bucket *hb,
 	return NULL;
 }
 
-static u32 cmpxchg_futex_value_locked(u32 __user *uaddr, u32 uval, u32 newval)
+static int cmpxchg_futex_value_locked(u32 *curval, u32 __user *uaddr,
+				      u32 uval, u32 newval)
 {
-	u32 curval;
+	int ret;
 
 	pagefault_disable();
-	curval = futex_atomic_cmpxchg_inatomic(uaddr, uval, newval);
+	ret = futex_atomic_cmpxchg_inatomic(curval, uaddr, uval, newval);
 	pagefault_enable();
 
-	return curval;
+	return ret;
 }
 
 static int get_futex_value_locked(u32 *dest, u32 __user *from)
@@ -674,7 +675,7 @@ static int futex_lock_pi_atomic(u32 __user *uaddr, struct futex_hash_bucket *hb,
 				struct task_struct *task, int set_waiters)
 {
 	int lock_taken, ret, ownerdied = 0;
-	u32 uval, newval, curval;
+	u32 uval, newval, curval, vpid = task_pid_vnr(task);
 
 retry:
 	ret = lock_taken = 0;
@@ -684,19 +685,17 @@ retry:
 	 * (by doing a 0 -> TID atomic cmpxchg), while holding all
 	 * the locks. It will most likely not succeed.
 	 */
-	newval = task_pid_vnr(task);
+	newval = vpid;
 	if (set_waiters)
 		newval |= FUTEX_WAITERS;
 
-	curval = cmpxchg_futex_value_locked(uaddr, 0, newval);
-
-	if (unlikely(curval == -EFAULT))
+	if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, 0, newval)))
 		return -EFAULT;
 
 	/*
 	 * Detect deadlocks.
 	 */
-	if ((unlikely((curval & FUTEX_TID_MASK) == task_pid_vnr(task))))
+	if ((unlikely((curval & FUTEX_TID_MASK) == vpid)))
 		return -EDEADLK;
 
 	/*
@@ -723,14 +722,12 @@ retry:
 	 */
 	if (unlikely(ownerdied || !(curval & FUTEX_TID_MASK))) {
 		/* Keep the OWNER_DIED bit */
-		newval = (curval & ~FUTEX_TID_MASK) | task_pid_vnr(task);
+		newval = (curval & ~FUTEX_TID_MASK) | vpid;
 		ownerdied = 0;
 		lock_taken = 1;
 	}
 
-	curval = cmpxchg_futex_value_locked(uaddr, uval, newval);
-
-	if (unlikely(curval == -EFAULT))
+	if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)))
 		return -EFAULT;
 	if (unlikely(curval != uval))
 		goto retry;
@@ -775,6 +772,24 @@ retry:
 	return ret;
 }
 
+/**
+ * __unqueue_futex() - Remove the futex_q from its futex_hash_bucket
+ * @q:	The futex_q to unqueue
+ *
+ * The q->lock_ptr must not be NULL and must be held by the caller.
+ */
+static void __unqueue_futex(struct futex_q *q)
+{
+	struct futex_hash_bucket *hb;
+
+	if (WARN_ON(!q->lock_ptr || !spin_is_locked(q->lock_ptr)
+			|| plist_node_empty(&q->list)))
+		return;
+
+	hb = container_of(q->lock_ptr, struct futex_hash_bucket, lock);
+	plist_del(&q->list, &hb->chain);
+}
+
 /*
  * The hash bucket lock must be held when this is called.
  * Afterwards, the futex_q must not be accessed.
@@ -792,7 +807,7 @@ static void wake_futex(struct futex_q *q)
 	 */
 	get_task_struct(p);
 
-	plist_del(&q->list, &q->list.plist);
+	__unqueue_futex(q);
 	/*
 	 * The waiting task can free the futex_q as soon as
 	 * q->lock_ptr = NULL is written, without taking any locks. A
@@ -843,9 +858,7 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this)
 
 		newval = FUTEX_WAITERS | task_pid_vnr(new_owner);
 
-		curval = cmpxchg_futex_value_locked(uaddr, uval, newval);
-
-		if (curval == -EFAULT)
+		if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval))
 			ret = -EFAULT;
 		else if (curval != uval)
 			ret = -EINVAL;
@@ -880,10 +893,8 @@ static int unlock_futex_pi(u32 __user *uaddr, u32 uval)
 	 * There is no waiter, so we unlock the futex. The owner died
 	 * bit has not to be preserved here. We are the owner:
 	 */
-	oldval = cmpxchg_futex_value_locked(uaddr, uval, 0);
-
-	if (oldval == -EFAULT)
-		return oldval;
+	if (cmpxchg_futex_value_locked(&oldval, uaddr, uval, 0))
+		return -EFAULT;
 	if (oldval != uval)
 		return -EAGAIN;
 
@@ -1071,9 +1082,6 @@ void requeue_futex(struct futex_q *q, struct futex_hash_bucket *hb1,
 		plist_del(&q->list, &hb1->chain);
 		plist_add(&q->list, &hb2->chain);
 		q->lock_ptr = &hb2->lock;
-#ifdef CONFIG_DEBUG_PI_LIST
-		q->list.plist.spinlock = &hb2->lock;
-#endif
 	}
 	get_futex_key_refs(key2);
 	q->key = *key2;
@@ -1100,16 +1108,12 @@ void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key,
 	get_futex_key_refs(key);
 	q->key = *key;
 
-	WARN_ON(plist_node_empty(&q->list));
-	plist_del(&q->list, &q->list.plist);
+	__unqueue_futex(q);
 
 	WARN_ON(!q->rt_waiter);
 	q->rt_waiter = NULL;
 
 	q->lock_ptr = &hb->lock;
-#ifdef CONFIG_DEBUG_PI_LIST
-	q->list.plist.spinlock = &hb->lock;
-#endif
 
 	wake_up_state(q->task, TASK_NORMAL);
 }
@@ -1457,9 +1461,6 @@ static inline void queue_me(struct futex_q *q, struct futex_hash_bucket *hb)
 	prio = min(current->normal_prio, MAX_RT_PRIO);
 
 	plist_node_init(&q->list, prio);
-#ifdef CONFIG_DEBUG_PI_LIST
-	q->list.plist.spinlock = &hb->lock;
-#endif
 	plist_add(&q->list, &hb->chain);
 	q->task = current;
 	spin_unlock(&hb->lock);
@@ -1504,8 +1505,7 @@ retry:
 			spin_unlock(lock_ptr);
 			goto retry;
 		}
-		WARN_ON(plist_node_empty(&q->list));
-		plist_del(&q->list, &q->list.plist);
+		__unqueue_futex(q);
 
 		BUG_ON(q->pi_state);
 
@@ -1525,8 +1525,7 @@ retry:
 static void unqueue_me_pi(struct futex_q *q)
 	__releases(q->lock_ptr)
 {
-	WARN_ON(plist_node_empty(&q->list));
-	plist_del(&q->list, &q->list.plist);
+	__unqueue_futex(q);
 
 	BUG_ON(!q->pi_state);
 	free_pi_state(q->pi_state);
@@ -1556,10 +1555,10 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
 
 	/*
 	 * We are here either because we stole the rtmutex from the
-	 * pending owner or we are the pending owner which failed to
-	 * get the rtmutex. We have to replace the pending owner TID
-	 * in the user space variable. This must be atomic as we have
-	 * to preserve the owner died bit here.
+	 * previous highest priority waiter or we are the highest priority
+	 * waiter but failed to get the rtmutex the first time.
+	 * We have to replace the newowner TID in the user space variable.
+	 * This must be atomic as we have to preserve the owner died bit here.
 	 *
 	 * Note: We write the user space value _before_ changing the pi_state
 	 * because we can fault here. Imagine swapped out pages or a fork
@@ -1578,9 +1577,7 @@ retry:
 	while (1) {
 		newval = (uval & FUTEX_OWNER_DIED) | newtid;
 
-		curval = cmpxchg_futex_value_locked(uaddr, uval, newval);
-
-		if (curval == -EFAULT)
+		if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval))
 			goto handle_fault;
 		if (curval == uval)
 			break;
@@ -1608,8 +1605,8 @@ retry:
 
 	/*
 	 * To handle the page fault we need to drop the hash bucket
-	 * lock here. That gives the other task (either the pending
-	 * owner itself or the task which stole the rtmutex) the
+	 * lock here. That gives the other task (either the highest priority
+	 * waiter itself or the task which stole the rtmutex) the
 	 * chance to try the fixup of the pi_state. So once we are
 	 * back from handling the fault we need to check the pi_state
 	 * after reacquiring the hash bucket lock and before trying to
@@ -1685,18 +1682,20 @@ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked)
 		/*
 		 * pi_state is incorrect, some other task did a lock steal and
 		 * we returned due to timeout or signal without taking the
-		 * rt_mutex. Too late. We can access the rt_mutex_owner without
-		 * locking, as the other task is now blocked on the hash bucket
-		 * lock. Fix the state up.
+		 * rt_mutex. Too late.
 		 */
+		raw_spin_lock(&q->pi_state->pi_mutex.wait_lock);
 		owner = rt_mutex_owner(&q->pi_state->pi_mutex);
+		if (!owner)
+			owner = rt_mutex_next_owner(&q->pi_state->pi_mutex);
+		raw_spin_unlock(&q->pi_state->pi_mutex.wait_lock);
 		ret = fixup_pi_state_owner(uaddr, q, owner);
 		goto out;
 	}
 
 	/*
 	 * Paranoia check. If we did not take the lock, then we should not be
-	 * the owner, nor the pending owner, of the rt_mutex.
+	 * the owner of the rt_mutex.
 	 */
 	if (rt_mutex_owner(&q->pi_state->pi_mutex) == current)
 		printk(KERN_ERR "fixup_owner: ret = %d pi-mutex: %p "
@@ -1781,13 +1780,14 @@ static int futex_wait_setup(u32 __user *uaddr, u32 val, unsigned int flags,
 	 *
 	 * The basic logical guarantee of a futex is that it blocks ONLY
 	 * if cond(var) is known to be true at the time of blocking, for
-	 * any cond.  If we queued after testing *uaddr, that would open
-	 * a race condition where we could block indefinitely with
+	 * any cond.  If we locked the hash-bucket after testing *uaddr, that
+	 * would open a race condition where we could block indefinitely with
 	 * cond(var) false, which would violate the guarantee.
 	 *
-	 * A consequence is that futex_wait() can return zero and absorb
-	 * a wakeup when *uaddr != val on entry to the syscall.  This is
-	 * rare, but normal.
+	 * On the other hand, we insert q and release the hash-bucket only
+	 * after testing *uaddr.  This guarantees that futex_wait() will NOT
+	 * absorb a wakeup if *uaddr does not match the desired values
+	 * while the syscall executes.
 	 */
 retry:
 	ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &q->key);
@@ -2046,9 +2046,9 @@ static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
 {
 	struct futex_hash_bucket *hb;
 	struct futex_q *this, *next;
-	u32 uval;
 	struct plist_head *head;
 	union futex_key key = FUTEX_KEY_INIT;
+	u32 uval, vpid = task_pid_vnr(current);
 	int ret;
 
 retry:
@@ -2057,7 +2057,7 @@ retry:
 	/*
 	 * We release only a lock we actually own:
 	 */
-	if ((uval & FUTEX_TID_MASK) != task_pid_vnr(current))
+	if ((uval & FUTEX_TID_MASK) != vpid)
 		return -EPERM;
 
 	ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &key);
@@ -2072,17 +2072,14 @@ retry:
 	 * again. If it succeeds then we can return without waking
 	 * anyone else up:
 	 */
-	if (!(uval & FUTEX_OWNER_DIED))
-		uval = cmpxchg_futex_value_locked(uaddr, task_pid_vnr(current), 0);
-
-
-	if (unlikely(uval == -EFAULT))
+	if (!(uval & FUTEX_OWNER_DIED) &&
+	    cmpxchg_futex_value_locked(&uval, uaddr, vpid, 0))
 		goto pi_faulted;
 	/*
 	 * Rare case: we managed to release the lock atomically,
 	 * no need to wake anyone else up:
 	 */
-	if (unlikely(uval == task_pid_vnr(current)))
+	if (unlikely(uval == vpid))
 		goto out_unlock;
 
 	/*
@@ -2167,7 +2164,7 @@ int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb,
 		 * We were woken prior to requeue by a timeout or a signal.
 		 * Unqueue the futex_q and determine which it was.
 		 */
-		plist_del(&q->list, &q->list.plist);
+		plist_del(&q->list, &hb->chain);
 
 		/* Handle spurious wakeups gracefully */
 		ret = -EWOULDBLOCK;
@@ -2463,11 +2460,20 @@ retry:
 		 * userspace.
 		 */
 		mval = (uval & FUTEX_WAITERS) | FUTEX_OWNER_DIED;
-		nval = futex_atomic_cmpxchg_inatomic(uaddr, uval, mval);
-
-		if (nval == -EFAULT)
-			return -1;
-
+		/*
+		 * We are not holding a lock here, but we want to have
+		 * the pagefault_disable/enable() protection because
+		 * we want to handle the fault gracefully. If the
+		 * access fails we try to fault in the futex with R/W
+		 * verification via get_user_pages. get_user() above
+		 * does not guarantee R/W access. If that fails we
+		 * give up and leave the futex locked.
+		 */
+		if (cmpxchg_futex_value_locked(&nval, uaddr, uval, mval)) {
+			if (fault_in_user_writeable(uaddr))
+				return -1;
+			goto retry;
+		}
 		if (nval != uval)
 			goto retry;
 
@@ -2678,8 +2684,7 @@ static int __init futex_init(void)
 	 * implementation, the non-functional ones will return
 	 * -ENOSYS.
 	 */
-	curval = cmpxchg_futex_value_locked(NULL, 0, 0);
-	if (curval == -EFAULT)
+	if (cmpxchg_futex_value_locked(&curval, NULL, 0, 0) == -EFAULT)
 		futex_cmpxchg_enabled = 1;
 
 	for (i = 0; i < ARRAY_SIZE(futex_queues); i++) {
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 0c8d7c048615..9017478c5d4c 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -53,11 +53,10 @@
 /*
  * The timer bases:
  *
- * Note: If we want to add new timer bases, we have to skip the two
- * clock ids captured by the cpu-timers. We do this by holding empty
- * entries rather than doing math adjustment of the clock ids.
- * This ensures that we capture erroneous accesses to these clock ids
- * rather than moving them into the range of valid clock id's.
+ * There are more clockids then hrtimer bases. Thus, we index
+ * into the timer bases by the hrtimer_base_type enum. When trying
+ * to reach a base using a clockid, hrtimer_clockid_to_base()
+ * is used to convert from clockid to the proper hrtimer_base_type.
  */
 DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
 {
@@ -74,30 +73,39 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
 			.get_time = &ktime_get,
 			.resolution = KTIME_LOW_RES,
 		},
+		{
+			.index = CLOCK_BOOTTIME,
+			.get_time = &ktime_get_boottime,
+			.resolution = KTIME_LOW_RES,
+		},
 	}
 };
 
+static int hrtimer_clock_to_base_table[MAX_CLOCKS];
+
+static inline int hrtimer_clockid_to_base(clockid_t clock_id)
+{
+	return hrtimer_clock_to_base_table[clock_id];
+}
+
+
 /*
  * Get the coarse grained time at the softirq based on xtime and
  * wall_to_monotonic.
  */
 static void hrtimer_get_softirq_time(struct hrtimer_cpu_base *base)
 {
-	ktime_t xtim, tomono;
-	struct timespec xts, tom;
-	unsigned long seq;
+	ktime_t xtim, mono, boot;
+	struct timespec xts, tom, slp;
 
-	do {
-		seq = read_seqbegin(&xtime_lock);
-		xts = __current_kernel_time();
-		tom = __get_wall_to_monotonic();
-	} while (read_seqretry(&xtime_lock, seq));
+	get_xtime_and_monotonic_and_sleep_offset(&xts, &tom, &slp);
 
 	xtim = timespec_to_ktime(xts);
-	tomono = timespec_to_ktime(tom);
-	base->clock_base[CLOCK_REALTIME].softirq_time = xtim;
-	base->clock_base[CLOCK_MONOTONIC].softirq_time =
-		ktime_add(xtim, tomono);
+	mono = ktime_add(xtim, timespec_to_ktime(tom));
+	boot = ktime_add(mono, timespec_to_ktime(slp));
+	base->clock_base[HRTIMER_BASE_REALTIME].softirq_time = xtim;
+	base->clock_base[HRTIMER_BASE_MONOTONIC].softirq_time = mono;
+	base->clock_base[HRTIMER_BASE_BOOTTIME].softirq_time = boot;
 }
 
 /*
@@ -184,10 +192,11 @@ switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base,
 	struct hrtimer_cpu_base *new_cpu_base;
 	int this_cpu = smp_processor_id();
 	int cpu = hrtimer_get_target(this_cpu, pinned);
+	int basenum = hrtimer_clockid_to_base(base->index);
 
 again:
 	new_cpu_base = &per_cpu(hrtimer_bases, cpu);
-	new_base = &new_cpu_base->clock_base[base->index];
+	new_base = &new_cpu_base->clock_base[basenum];
 
 	if (base != new_base) {
 		/*
@@ -334,6 +343,11 @@ EXPORT_SYMBOL_GPL(ktime_add_safe);
 
 static struct debug_obj_descr hrtimer_debug_descr;
 
+static void *hrtimer_debug_hint(void *addr)
+{
+	return ((struct hrtimer *) addr)->function;
+}
+
 /*
  * fixup_init is called when:
  * - an active object is initialized
@@ -393,6 +407,7 @@ static int hrtimer_fixup_free(void *addr, enum debug_obj_state state)
 
 static struct debug_obj_descr hrtimer_debug_descr = {
 	.name		= "hrtimer",
+	.debug_hint	= hrtimer_debug_hint,
 	.fixup_init	= hrtimer_fixup_init,
 	.fixup_activate	= hrtimer_fixup_activate,
 	.fixup_free	= hrtimer_fixup_free,
@@ -611,24 +626,23 @@ static int hrtimer_reprogram(struct hrtimer *timer,
 static void retrigger_next_event(void *arg)
 {
 	struct hrtimer_cpu_base *base;
-	struct timespec realtime_offset, wtm;
-	unsigned long seq;
+	struct timespec realtime_offset, wtm, sleep;
 
 	if (!hrtimer_hres_active())
 		return;
 
-	do {
-		seq = read_seqbegin(&xtime_lock);
-		wtm = __get_wall_to_monotonic();
-	} while (read_seqretry(&xtime_lock, seq));
+	get_xtime_and_monotonic_and_sleep_offset(&realtime_offset, &wtm,
+							&sleep);
 	set_normalized_timespec(&realtime_offset, -wtm.tv_sec, -wtm.tv_nsec);
 
 	base = &__get_cpu_var(hrtimer_bases);
 
 	/* Adjust CLOCK_REALTIME offset */
 	raw_spin_lock(&base->lock);
-	base->clock_base[CLOCK_REALTIME].offset =
+	base->clock_base[HRTIMER_BASE_REALTIME].offset =
 		timespec_to_ktime(realtime_offset);
+	base->clock_base[HRTIMER_BASE_BOOTTIME].offset =
+		timespec_to_ktime(sleep);
 
 	hrtimer_force_reprogram(base, 0);
 	raw_spin_unlock(&base->lock);
@@ -673,14 +687,6 @@ static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base)
 }
 
 /*
- * Initialize the high resolution related parts of a hrtimer
- */
-static inline void hrtimer_init_timer_hres(struct hrtimer *timer)
-{
-}
-
-
-/*
  * When High resolution timers are active, try to reprogram. Note, that in case
  * the state has HRTIMER_STATE_CALLBACK set, no reprogramming and no expiry
  * check happens. The timer gets enqueued into the rbtree. The reprogramming
@@ -725,8 +731,9 @@ static int hrtimer_switch_to_hres(void)
 		return 0;
 	}
 	base->hres_active = 1;
-	base->clock_base[CLOCK_REALTIME].resolution = KTIME_HIGH_RES;
-	base->clock_base[CLOCK_MONOTONIC].resolution = KTIME_HIGH_RES;
+	base->clock_base[HRTIMER_BASE_REALTIME].resolution = KTIME_HIGH_RES;
+	base->clock_base[HRTIMER_BASE_MONOTONIC].resolution = KTIME_HIGH_RES;
+	base->clock_base[HRTIMER_BASE_BOOTTIME].resolution = KTIME_HIGH_RES;
 
 	tick_setup_sched_timer();
 
@@ -750,7 +757,6 @@ static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
 	return 0;
 }
 static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base) { }
-static inline void hrtimer_init_timer_hres(struct hrtimer *timer) { }
 
 #endif /* CONFIG_HIGH_RES_TIMERS */
 
@@ -1121,6 +1127,7 @@ static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
 			   enum hrtimer_mode mode)
 {
 	struct hrtimer_cpu_base *cpu_base;
+	int base;
 
 	memset(timer, 0, sizeof(struct hrtimer));
 
@@ -1129,8 +1136,8 @@ static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
 	if (clock_id == CLOCK_REALTIME && mode != HRTIMER_MODE_ABS)
 		clock_id = CLOCK_MONOTONIC;
 
-	timer->base = &cpu_base->clock_base[clock_id];
-	hrtimer_init_timer_hres(timer);
+	base = hrtimer_clockid_to_base(clock_id);
+	timer->base = &cpu_base->clock_base[base];
 	timerqueue_init(&timer->node);
 
 #ifdef CONFIG_TIMER_STATS
@@ -1165,9 +1172,10 @@ EXPORT_SYMBOL_GPL(hrtimer_init);
 int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp)
 {
 	struct hrtimer_cpu_base *cpu_base;
+	int base = hrtimer_clockid_to_base(which_clock);
 
 	cpu_base = &__raw_get_cpu_var(hrtimer_bases);
-	*tp = ktime_to_timespec(cpu_base->clock_base[which_clock].resolution);
+	*tp = ktime_to_timespec(cpu_base->clock_base[base].resolution);
 
 	return 0;
 }
@@ -1714,6 +1722,10 @@ static struct notifier_block __cpuinitdata hrtimers_nb = {
 
 void __init hrtimers_init(void)
 {
+	hrtimer_clock_to_base_table[CLOCK_REALTIME] = HRTIMER_BASE_REALTIME;
+	hrtimer_clock_to_base_table[CLOCK_MONOTONIC] = HRTIMER_BASE_MONOTONIC;
+	hrtimer_clock_to_base_table[CLOCK_BOOTTIME] = HRTIMER_BASE_BOOTTIME;
+
 	hrtimer_cpu_notify(&hrtimers_nb, (unsigned long)CPU_UP_PREPARE,
 			  (void *)(long)smp_processor_id());
 	register_cpu_notifier(&hrtimers_nb);
diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig
index 8e42fec7686d..09bef82d74cb 100644
--- a/kernel/irq/Kconfig
+++ b/kernel/irq/Kconfig
@@ -1,5 +1,6 @@
+# Select this to activate the generic irq options below
 config HAVE_GENERIC_HARDIRQS
-	def_bool n
+	bool
 
 if HAVE_GENERIC_HARDIRQS
 menu "IRQ subsystem"
@@ -11,26 +12,44 @@ config GENERIC_HARDIRQS
 
 # Select this to disable the deprecated stuff
 config GENERIC_HARDIRQS_NO_DEPRECATED
-       def_bool n
+       bool
+
+config GENERIC_HARDIRQS_NO_COMPAT
+       bool
 
 # Options selectable by the architecture code
+
+# Make sparse irq Kconfig switch below available
 config HAVE_SPARSE_IRQ
-       def_bool n
+       bool
 
+# Enable the generic irq autoprobe mechanism
 config GENERIC_IRQ_PROBE
-	def_bool n
+	bool
+
+# Use the generic /proc/interrupts implementation
+config GENERIC_IRQ_SHOW
+       bool
 
+# Support for delayed migration from interrupt context
 config GENERIC_PENDING_IRQ
-	def_bool n
+	bool
 
+# Alpha specific irq affinity mechanism
 config AUTO_IRQ_AFFINITY
-       def_bool n
-
-config IRQ_PER_CPU
-       def_bool n
+       bool
 
+# Tasklet based software resend for pending interrupts on enable_irq()
 config HARDIRQS_SW_RESEND
-       def_bool n
+       bool
+
+# Preflow handler support for fasteoi (sparc64)
+config IRQ_PREFLOW_FASTEOI
+       bool
+
+# Support forced irq threading
+config IRQ_FORCED_THREADING
+       bool
 
 config SPARSE_IRQ
 	bool "Support sparse irq numbering"
diff --git a/kernel/irq/autoprobe.c b/kernel/irq/autoprobe.c
index 505798f86c36..394784c57060 100644
--- a/kernel/irq/autoprobe.c
+++ b/kernel/irq/autoprobe.c
@@ -17,7 +17,7 @@
 /*
  * Autodetection depends on the fact that any interrupt that
  * comes in on to an unassigned handler will get stuck with
- * "IRQ_WAITING" cleared and the interrupt disabled.
+ * "IRQS_WAITING" cleared and the interrupt disabled.
  */
 static DEFINE_MUTEX(probing_active);
 
@@ -32,7 +32,6 @@ unsigned long probe_irq_on(void)
 {
 	struct irq_desc *desc;
 	unsigned long mask = 0;
-	unsigned int status;
 	int i;
 
 	/*
@@ -46,13 +45,7 @@ unsigned long probe_irq_on(void)
 	 */
 	for_each_irq_desc_reverse(i, desc) {
 		raw_spin_lock_irq(&desc->lock);
-		if (!desc->action && !(desc->status & IRQ_NOPROBE)) {
-			/*
-			 * An old-style architecture might still have
-			 * the handle_bad_irq handler there:
-			 */
-			compat_irq_chip_set_default_handler(desc);
-
+		if (!desc->action && irq_settings_can_probe(desc)) {
 			/*
 			 * Some chips need to know about probing in
 			 * progress:
@@ -60,7 +53,7 @@ unsigned long probe_irq_on(void)
 			if (desc->irq_data.chip->irq_set_type)
 				desc->irq_data.chip->irq_set_type(&desc->irq_data,
 							 IRQ_TYPE_PROBE);
-			desc->irq_data.chip->irq_startup(&desc->irq_data);
+			irq_startup(desc);
 		}
 		raw_spin_unlock_irq(&desc->lock);
 	}
@@ -75,10 +68,12 @@ unsigned long probe_irq_on(void)
 	 */
 	for_each_irq_desc_reverse(i, desc) {
 		raw_spin_lock_irq(&desc->lock);
-		if (!desc->action && !(desc->status & IRQ_NOPROBE)) {
-			desc->status |= IRQ_AUTODETECT | IRQ_WAITING;
-			if (desc->irq_data.chip->irq_startup(&desc->irq_data))
-				desc->status |= IRQ_PENDING;
+		if (!desc->action && irq_settings_can_probe(desc)) {
+			desc->istate |= IRQS_AUTODETECT | IRQS_WAITING;
+			if (irq_startup(desc)) {
+				irq_compat_set_pending(desc);
+				desc->istate |= IRQS_PENDING;
+			}
 		}
 		raw_spin_unlock_irq(&desc->lock);
 	}
@@ -93,13 +88,12 @@ unsigned long probe_irq_on(void)
 	 */
 	for_each_irq_desc(i, desc) {
 		raw_spin_lock_irq(&desc->lock);
-		status = desc->status;
 
-		if (status & IRQ_AUTODETECT) {
+		if (desc->istate & IRQS_AUTODETECT) {
 			/* It triggered already - consider it spurious. */
-			if (!(status & IRQ_WAITING)) {
-				desc->status = status & ~IRQ_AUTODETECT;
-				desc->irq_data.chip->irq_shutdown(&desc->irq_data);
+			if (!(desc->istate & IRQS_WAITING)) {
+				desc->istate &= ~IRQS_AUTODETECT;
+				irq_shutdown(desc);
 			} else
 				if (i < 32)
 					mask |= 1 << i;
@@ -125,20 +119,18 @@ EXPORT_SYMBOL(probe_irq_on);
  */
 unsigned int probe_irq_mask(unsigned long val)
 {
-	unsigned int status, mask = 0;
+	unsigned int mask = 0;
 	struct irq_desc *desc;
 	int i;
 
 	for_each_irq_desc(i, desc) {
 		raw_spin_lock_irq(&desc->lock);
-		status = desc->status;
-
-		if (status & IRQ_AUTODETECT) {
-			if (i < 16 && !(status & IRQ_WAITING))
+		if (desc->istate & IRQS_AUTODETECT) {
+			if (i < 16 && !(desc->istate & IRQS_WAITING))
 				mask |= 1 << i;
 
-			desc->status = status & ~IRQ_AUTODETECT;
-			desc->irq_data.chip->irq_shutdown(&desc->irq_data);
+			desc->istate &= ~IRQS_AUTODETECT;
+			irq_shutdown(desc);
 		}
 		raw_spin_unlock_irq(&desc->lock);
 	}
@@ -169,20 +161,18 @@ int probe_irq_off(unsigned long val)
 {
 	int i, irq_found = 0, nr_of_irqs = 0;
 	struct irq_desc *desc;
-	unsigned int status;
 
 	for_each_irq_desc(i, desc) {
 		raw_spin_lock_irq(&desc->lock);
-		status = desc->status;
 
-		if (status & IRQ_AUTODETECT) {
-			if (!(status & IRQ_WAITING)) {
+		if (desc->istate & IRQS_AUTODETECT) {
+			if (!(desc->istate & IRQS_WAITING)) {
 				if (!nr_of_irqs)
 					irq_found = i;
 				nr_of_irqs++;
 			}
-			desc->status = status & ~IRQ_AUTODETECT;
-			desc->irq_data.chip->irq_shutdown(&desc->irq_data);
+			desc->istate &= ~IRQS_AUTODETECT;
+			irq_shutdown(desc);
 		}
 		raw_spin_unlock_irq(&desc->lock);
 	}
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index baa5c4acad83..c9c0601f0615 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -19,140 +19,110 @@
 #include "internals.h"
 
 /**
- *	set_irq_chip - set the irq chip for an irq
+ *	irq_set_chip - set the irq chip for an irq
  *	@irq:	irq number
  *	@chip:	pointer to irq chip description structure
  */
-int set_irq_chip(unsigned int irq, struct irq_chip *chip)
+int irq_set_chip(unsigned int irq, struct irq_chip *chip)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long flags;
+	struct irq_desc *desc = irq_get_desc_lock(irq, &flags);
 
-	if (!desc) {
-		WARN(1, KERN_ERR "Trying to install chip for IRQ%d\n", irq);
+	if (!desc)
 		return -EINVAL;
-	}
 
 	if (!chip)
 		chip = &no_irq_chip;
 
-	raw_spin_lock_irqsave(&desc->lock, flags);
 	irq_chip_set_defaults(chip);
 	desc->irq_data.chip = chip;
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
-
+	irq_put_desc_unlock(desc, flags);
 	return 0;
 }
-EXPORT_SYMBOL(set_irq_chip);
+EXPORT_SYMBOL(irq_set_chip);
 
 /**
- *	set_irq_type - set the irq trigger type for an irq
+ *	irq_set_type - set the irq trigger type for an irq
  *	@irq:	irq number
  *	@type:	IRQ_TYPE_{LEVEL,EDGE}_* value - see include/linux/irq.h
  */
-int set_irq_type(unsigned int irq, unsigned int type)
+int irq_set_irq_type(unsigned int irq, unsigned int type)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long flags;
-	int ret = -ENXIO;
+	struct irq_desc *desc = irq_get_desc_buslock(irq, &flags);
+	int ret = 0;
 
-	if (!desc) {
-		printk(KERN_ERR "Trying to set irq type for IRQ%d\n", irq);
-		return -ENODEV;
-	}
+	if (!desc)
+		return -EINVAL;
 
 	type &= IRQ_TYPE_SENSE_MASK;
-	if (type == IRQ_TYPE_NONE)
-		return 0;
-
-	raw_spin_lock_irqsave(&desc->lock, flags);
-	ret = __irq_set_trigger(desc, irq, type);
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
+	if (type != IRQ_TYPE_NONE)
+		ret = __irq_set_trigger(desc, irq, type);
+	irq_put_desc_busunlock(desc, flags);
 	return ret;
 }
-EXPORT_SYMBOL(set_irq_type);
+EXPORT_SYMBOL(irq_set_irq_type);
 
 /**
- *	set_irq_data - set irq type data for an irq
+ *	irq_set_handler_data - set irq handler data for an irq
  *	@irq:	Interrupt number
  *	@data:	Pointer to interrupt specific data
  *
  *	Set the hardware irq controller data for an irq
  */
-int set_irq_data(unsigned int irq, void *data)
+int irq_set_handler_data(unsigned int irq, void *data)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long flags;
+	struct irq_desc *desc = irq_get_desc_lock(irq, &flags);
 
-	if (!desc) {
-		printk(KERN_ERR
-		       "Trying to install controller data for IRQ%d\n", irq);
+	if (!desc)
 		return -EINVAL;
-	}
-
-	raw_spin_lock_irqsave(&desc->lock, flags);
 	desc->irq_data.handler_data = data;
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
+	irq_put_desc_unlock(desc, flags);
 	return 0;
 }
-EXPORT_SYMBOL(set_irq_data);
+EXPORT_SYMBOL(irq_set_handler_data);
 
 /**
- *	set_irq_msi - set MSI descriptor data for an irq
+ *	irq_set_msi_desc - set MSI descriptor data for an irq
  *	@irq:	Interrupt number
  *	@entry:	Pointer to MSI descriptor data
  *
  *	Set the MSI descriptor entry for an irq
  */
-int set_irq_msi(unsigned int irq, struct msi_desc *entry)
+int irq_set_msi_desc(unsigned int irq, struct msi_desc *entry)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long flags;
+	struct irq_desc *desc = irq_get_desc_lock(irq, &flags);
 
-	if (!desc) {
-		printk(KERN_ERR
-		       "Trying to install msi data for IRQ%d\n", irq);
+	if (!desc)
 		return -EINVAL;
-	}
-
-	raw_spin_lock_irqsave(&desc->lock, flags);
 	desc->irq_data.msi_desc = entry;
 	if (entry)
 		entry->irq = irq;
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
+	irq_put_desc_unlock(desc, flags);
 	return 0;
 }
 
 /**
- *	set_irq_chip_data - set irq chip data for an irq
+ *	irq_set_chip_data - set irq chip data for an irq
  *	@irq:	Interrupt number
  *	@data:	Pointer to chip specific data
  *
  *	Set the hardware irq chip data for an irq
  */
-int set_irq_chip_data(unsigned int irq, void *data)
+int irq_set_chip_data(unsigned int irq, void *data)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long flags;
+	struct irq_desc *desc = irq_get_desc_lock(irq, &flags);
 
-	if (!desc) {
-		printk(KERN_ERR
-		       "Trying to install chip data for IRQ%d\n", irq);
-		return -EINVAL;
-	}
-
-	if (!desc->irq_data.chip) {
-		printk(KERN_ERR "BUG: bad set_irq_chip_data(IRQ#%d)\n", irq);
+	if (!desc)
 		return -EINVAL;
-	}
-
-	raw_spin_lock_irqsave(&desc->lock, flags);
 	desc->irq_data.chip_data = data;
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
-
+	irq_put_desc_unlock(desc, flags);
 	return 0;
 }
-EXPORT_SYMBOL(set_irq_chip_data);
+EXPORT_SYMBOL(irq_set_chip_data);
 
 struct irq_data *irq_get_irq_data(unsigned int irq)
 {
@@ -162,72 +132,75 @@ struct irq_data *irq_get_irq_data(unsigned int irq)
 }
 EXPORT_SYMBOL_GPL(irq_get_irq_data);
 
-/**
- *	set_irq_nested_thread - Set/Reset the IRQ_NESTED_THREAD flag of an irq
- *
- *	@irq:	Interrupt number
- *	@nest:	0 to clear / 1 to set the IRQ_NESTED_THREAD flag
- *
- *	The IRQ_NESTED_THREAD flag indicates that on
- *	request_threaded_irq() no separate interrupt thread should be
- *	created for the irq as the handler are called nested in the
- *	context of a demultiplexing interrupt handler thread.
- */
-void set_irq_nested_thread(unsigned int irq, int nest)
+static void irq_state_clr_disabled(struct irq_desc *desc)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
-	unsigned long flags;
-
-	if (!desc)
-		return;
-
-	raw_spin_lock_irqsave(&desc->lock, flags);
-	if (nest)
-		desc->status |= IRQ_NESTED_THREAD;
-	else
-		desc->status &= ~IRQ_NESTED_THREAD;
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
+	desc->istate &= ~IRQS_DISABLED;
+	irq_compat_clr_disabled(desc);
 }
-EXPORT_SYMBOL_GPL(set_irq_nested_thread);
 
-/*
- * default enable function
- */
-static void default_enable(struct irq_data *data)
+static void irq_state_set_disabled(struct irq_desc *desc)
 {
-	struct irq_desc *desc = irq_data_to_desc(data);
+	desc->istate |= IRQS_DISABLED;
+	irq_compat_set_disabled(desc);
+}
 
-	desc->irq_data.chip->irq_unmask(&desc->irq_data);
-	desc->status &= ~IRQ_MASKED;
+static void irq_state_clr_masked(struct irq_desc *desc)
+{
+	desc->istate &= ~IRQS_MASKED;
+	irq_compat_clr_masked(desc);
 }
 
-/*
- * default disable function
- */
-static void default_disable(struct irq_data *data)
+static void irq_state_set_masked(struct irq_desc *desc)
 {
+	desc->istate |= IRQS_MASKED;
+	irq_compat_set_masked(desc);
 }
 
-/*
- * default startup function
- */
-static unsigned int default_startup(struct irq_data *data)
+int irq_startup(struct irq_desc *desc)
 {
-	struct irq_desc *desc = irq_data_to_desc(data);
+	irq_state_clr_disabled(desc);
+	desc->depth = 0;
+
+	if (desc->irq_data.chip->irq_startup) {
+		int ret = desc->irq_data.chip->irq_startup(&desc->irq_data);
+		irq_state_clr_masked(desc);
+		return ret;
+	}
 
-	desc->irq_data.chip->irq_enable(data);
+	irq_enable(desc);
 	return 0;
 }
 
-/*
- * default shutdown function
- */
-static void default_shutdown(struct irq_data *data)
+void irq_shutdown(struct irq_desc *desc)
 {
-	struct irq_desc *desc = irq_data_to_desc(data);
+	irq_state_set_disabled(desc);
+	desc->depth = 1;
+	if (desc->irq_data.chip->irq_shutdown)
+		desc->irq_data.chip->irq_shutdown(&desc->irq_data);
+	if (desc->irq_data.chip->irq_disable)
+		desc->irq_data.chip->irq_disable(&desc->irq_data);
+	else
+		desc->irq_data.chip->irq_mask(&desc->irq_data);
+	irq_state_set_masked(desc);
+}
 
-	desc->irq_data.chip->irq_mask(&desc->irq_data);
-	desc->status |= IRQ_MASKED;
+void irq_enable(struct irq_desc *desc)
+{
+	irq_state_clr_disabled(desc);
+	if (desc->irq_data.chip->irq_enable)
+		desc->irq_data.chip->irq_enable(&desc->irq_data);
+	else
+		desc->irq_data.chip->irq_unmask(&desc->irq_data);
+	irq_state_clr_masked(desc);
+}
+
+void irq_disable(struct irq_desc *desc)
+{
+	irq_state_set_disabled(desc);
+	if (desc->irq_data.chip->irq_disable) {
+		desc->irq_data.chip->irq_disable(&desc->irq_data);
+		irq_state_set_masked(desc);
+	}
 }
 
 #ifndef CONFIG_GENERIC_HARDIRQS_NO_DEPRECATED
@@ -315,10 +288,6 @@ static void compat_bus_sync_unlock(struct irq_data *data)
 void irq_chip_set_defaults(struct irq_chip *chip)
 {
 #ifndef CONFIG_GENERIC_HARDIRQS_NO_DEPRECATED
-	/*
-	 * Compat fixup functions need to be before we set the
-	 * defaults for enable/disable/startup/shutdown
-	 */
 	if (chip->enable)
 		chip->irq_enable = compat_irq_enable;
 	if (chip->disable)
@@ -327,33 +296,8 @@ void irq_chip_set_defaults(struct irq_chip *chip)
 		chip->irq_shutdown = compat_irq_shutdown;
 	if (chip->startup)
 		chip->irq_startup = compat_irq_startup;
-#endif
-	/*
-	 * The real defaults
-	 */
-	if (!chip->irq_enable)
-		chip->irq_enable = default_enable;
-	if (!chip->irq_disable)
-		chip->irq_disable = default_disable;
-	if (!chip->irq_startup)
-		chip->irq_startup = default_startup;
-	/*
-	 * We use chip->irq_disable, when the user provided its own. When
-	 * we have default_disable set for chip->irq_disable, then we need
-	 * to use default_shutdown, otherwise the irq line is not
-	 * disabled on free_irq():
-	 */
-	if (!chip->irq_shutdown)
-		chip->irq_shutdown = chip->irq_disable != default_disable ?
-			chip->irq_disable : default_shutdown;
-
-#ifndef CONFIG_GENERIC_HARDIRQS_NO_DEPRECATED
 	if (!chip->end)
 		chip->end = dummy_irq_chip.end;
-
-	/*
-	 * Now fix up the remaining compat handlers
-	 */
 	if (chip->bus_lock)
 		chip->irq_bus_lock = compat_bus_lock;
 	if (chip->bus_sync_unlock)
@@ -388,22 +332,22 @@ static inline void mask_ack_irq(struct irq_desc *desc)
 		if (desc->irq_data.chip->irq_ack)
 			desc->irq_data.chip->irq_ack(&desc->irq_data);
 	}
-	desc->status |= IRQ_MASKED;
+	irq_state_set_masked(desc);
 }
 
-static inline void mask_irq(struct irq_desc *desc)
+void mask_irq(struct irq_desc *desc)
 {
 	if (desc->irq_data.chip->irq_mask) {
 		desc->irq_data.chip->irq_mask(&desc->irq_data);
-		desc->status |= IRQ_MASKED;
+		irq_state_set_masked(desc);
 	}
 }
 
-static inline void unmask_irq(struct irq_desc *desc)
+void unmask_irq(struct irq_desc *desc)
 {
 	if (desc->irq_data.chip->irq_unmask) {
 		desc->irq_data.chip->irq_unmask(&desc->irq_data);
-		desc->status &= ~IRQ_MASKED;
+		irq_state_clr_masked(desc);
 	}
 }
 
@@ -428,10 +372,11 @@ void handle_nested_irq(unsigned int irq)
 	kstat_incr_irqs_this_cpu(irq, desc);
 
 	action = desc->action;
-	if (unlikely(!action || (desc->status & IRQ_DISABLED)))
+	if (unlikely(!action || (desc->istate & IRQS_DISABLED)))
 		goto out_unlock;
 
-	desc->status |= IRQ_INPROGRESS;
+	irq_compat_set_progress(desc);
+	desc->istate |= IRQS_INPROGRESS;
 	raw_spin_unlock_irq(&desc->lock);
 
 	action_ret = action->thread_fn(action->irq, action->dev_id);
@@ -439,13 +384,21 @@ void handle_nested_irq(unsigned int irq)
 		note_interrupt(irq, desc, action_ret);
 
 	raw_spin_lock_irq(&desc->lock);
-	desc->status &= ~IRQ_INPROGRESS;
+	desc->istate &= ~IRQS_INPROGRESS;
+	irq_compat_clr_progress(desc);
 
 out_unlock:
 	raw_spin_unlock_irq(&desc->lock);
 }
 EXPORT_SYMBOL_GPL(handle_nested_irq);
 
+static bool irq_check_poll(struct irq_desc *desc)
+{
+	if (!(desc->istate & IRQS_POLL_INPROGRESS))
+		return false;
+	return irq_wait_for_poll(desc);
+}
+
 /**
  *	handle_simple_irq - Simple and software-decoded IRQs.
  *	@irq:	the interrupt number
@@ -461,29 +414,20 @@ EXPORT_SYMBOL_GPL(handle_nested_irq);
 void
 handle_simple_irq(unsigned int irq, struct irq_desc *desc)
 {
-	struct irqaction *action;
-	irqreturn_t action_ret;
-
 	raw_spin_lock(&desc->lock);
 
-	if (unlikely(desc->status & IRQ_INPROGRESS))
-		goto out_unlock;
-	desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
+	if (unlikely(desc->istate & IRQS_INPROGRESS))
+		if (!irq_check_poll(desc))
+			goto out_unlock;
+
+	desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
 	kstat_incr_irqs_this_cpu(irq, desc);
 
-	action = desc->action;
-	if (unlikely(!action || (desc->status & IRQ_DISABLED)))
+	if (unlikely(!desc->action || (desc->istate & IRQS_DISABLED)))
 		goto out_unlock;
 
-	desc->status |= IRQ_INPROGRESS;
-	raw_spin_unlock(&desc->lock);
+	handle_irq_event(desc);
 
-	action_ret = handle_IRQ_event(irq, action);
-	if (!noirqdebug)
-		note_interrupt(irq, desc, action_ret);
-
-	raw_spin_lock(&desc->lock);
-	desc->status &= ~IRQ_INPROGRESS;
 out_unlock:
 	raw_spin_unlock(&desc->lock);
 }
@@ -501,42 +445,42 @@ out_unlock:
 void
 handle_level_irq(unsigned int irq, struct irq_desc *desc)
 {
-	struct irqaction *action;
-	irqreturn_t action_ret;
-
 	raw_spin_lock(&desc->lock);
 	mask_ack_irq(desc);
 
-	if (unlikely(desc->status & IRQ_INPROGRESS))
-		goto out_unlock;
-	desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
+	if (unlikely(desc->istate & IRQS_INPROGRESS))
+		if (!irq_check_poll(desc))
+			goto out_unlock;
+
+	desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
 	kstat_incr_irqs_this_cpu(irq, desc);
 
 	/*
 	 * If its disabled or no action available
 	 * keep it masked and get out of here
 	 */
-	action = desc->action;
-	if (unlikely(!action || (desc->status & IRQ_DISABLED)))
+	if (unlikely(!desc->action || (desc->istate & IRQS_DISABLED)))
 		goto out_unlock;
 
-	desc->status |= IRQ_INPROGRESS;
-	raw_spin_unlock(&desc->lock);
-
-	action_ret = handle_IRQ_event(irq, action);
-	if (!noirqdebug)
-		note_interrupt(irq, desc, action_ret);
+	handle_irq_event(desc);
 
-	raw_spin_lock(&desc->lock);
-	desc->status &= ~IRQ_INPROGRESS;
-
-	if (!(desc->status & (IRQ_DISABLED | IRQ_ONESHOT)))
+	if (!(desc->istate & (IRQS_DISABLED | IRQS_ONESHOT)))
 		unmask_irq(desc);
 out_unlock:
 	raw_spin_unlock(&desc->lock);
 }
 EXPORT_SYMBOL_GPL(handle_level_irq);
 
+#ifdef CONFIG_IRQ_PREFLOW_FASTEOI
+static inline void preflow_handler(struct irq_desc *desc)
+{
+	if (desc->preflow_handler)
+		desc->preflow_handler(&desc->irq_data);
+}
+#else
+static inline void preflow_handler(struct irq_desc *desc) { }
+#endif
+
 /**
  *	handle_fasteoi_irq - irq handler for transparent controllers
  *	@irq:	the interrupt number
@@ -550,42 +494,41 @@ EXPORT_SYMBOL_GPL(handle_level_irq);
 void
 handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc)
 {
-	struct irqaction *action;
-	irqreturn_t action_ret;
-
 	raw_spin_lock(&desc->lock);
 
-	if (unlikely(desc->status & IRQ_INPROGRESS))
-		goto out;
+	if (unlikely(desc->istate & IRQS_INPROGRESS))
+		if (!irq_check_poll(desc))
+			goto out;
 
-	desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
+	desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
 	kstat_incr_irqs_this_cpu(irq, desc);
 
 	/*
 	 * If its disabled or no action available
 	 * then mask it and get out of here:
 	 */
-	action = desc->action;
-	if (unlikely(!action || (desc->status & IRQ_DISABLED))) {
-		desc->status |= IRQ_PENDING;
+	if (unlikely(!desc->action || (desc->istate & IRQS_DISABLED))) {
+		irq_compat_set_pending(desc);
+		desc->istate |= IRQS_PENDING;
 		mask_irq(desc);
 		goto out;
 	}
 
-	desc->status |= IRQ_INPROGRESS;
-	desc->status &= ~IRQ_PENDING;
-	raw_spin_unlock(&desc->lock);
+	if (desc->istate & IRQS_ONESHOT)
+		mask_irq(desc);
 
-	action_ret = handle_IRQ_event(irq, action);
-	if (!noirqdebug)
-		note_interrupt(irq, desc, action_ret);
+	preflow_handler(desc);
+	handle_irq_event(desc);
 
-	raw_spin_lock(&desc->lock);
-	desc->status &= ~IRQ_INPROGRESS;
-out:
+out_eoi:
 	desc->irq_data.chip->irq_eoi(&desc->irq_data);
-
+out_unlock:
 	raw_spin_unlock(&desc->lock);
+	return;
+out:
+	if (!(desc->irq_data.chip->flags & IRQCHIP_EOI_IF_HANDLED))
+		goto out_eoi;
+	goto out_unlock;
 }
 
 /**
@@ -609,32 +552,28 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc)
 {
 	raw_spin_lock(&desc->lock);
 
-	desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
-
+	desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
 	/*
 	 * If we're currently running this IRQ, or its disabled,
 	 * we shouldn't process the IRQ. Mark it pending, handle
 	 * the necessary masking and go out
 	 */
-	if (unlikely((desc->status & (IRQ_INPROGRESS | IRQ_DISABLED)) ||
-		    !desc->action)) {
-		desc->status |= (IRQ_PENDING | IRQ_MASKED);
-		mask_ack_irq(desc);
-		goto out_unlock;
+	if (unlikely((desc->istate & (IRQS_DISABLED | IRQS_INPROGRESS) ||
+		      !desc->action))) {
+		if (!irq_check_poll(desc)) {
+			irq_compat_set_pending(desc);
+			desc->istate |= IRQS_PENDING;
+			mask_ack_irq(desc);
+			goto out_unlock;
+		}
 	}
 	kstat_incr_irqs_this_cpu(irq, desc);
 
 	/* Start handling the irq */
 	desc->irq_data.chip->irq_ack(&desc->irq_data);
 
-	/* Mark the IRQ currently in progress.*/
-	desc->status |= IRQ_INPROGRESS;
-
 	do {
-		struct irqaction *action = desc->action;
-		irqreturn_t action_ret;
-
-		if (unlikely(!action)) {
+		if (unlikely(!desc->action)) {
 			mask_irq(desc);
 			goto out_unlock;
 		}
@@ -644,22 +583,17 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc)
 		 * one, we could have masked the irq.
 		 * Renable it, if it was not disabled in meantime.
 		 */
-		if (unlikely((desc->status &
-			       (IRQ_PENDING | IRQ_MASKED | IRQ_DISABLED)) ==
-			      (IRQ_PENDING | IRQ_MASKED))) {
-			unmask_irq(desc);
+		if (unlikely(desc->istate & IRQS_PENDING)) {
+			if (!(desc->istate & IRQS_DISABLED) &&
+			    (desc->istate & IRQS_MASKED))
+				unmask_irq(desc);
 		}
 
-		desc->status &= ~IRQ_PENDING;
-		raw_spin_unlock(&desc->lock);
-		action_ret = handle_IRQ_event(irq, action);
-		if (!noirqdebug)
-			note_interrupt(irq, desc, action_ret);
-		raw_spin_lock(&desc->lock);
+		handle_irq_event(desc);
 
-	} while ((desc->status & (IRQ_PENDING | IRQ_DISABLED)) == IRQ_PENDING);
+	} while ((desc->istate & IRQS_PENDING) &&
+		 !(desc->istate & IRQS_DISABLED));
 
-	desc->status &= ~IRQ_INPROGRESS;
 out_unlock:
 	raw_spin_unlock(&desc->lock);
 }
@@ -674,103 +608,84 @@ out_unlock:
 void
 handle_percpu_irq(unsigned int irq, struct irq_desc *desc)
 {
-	irqreturn_t action_ret;
+	struct irq_chip *chip = irq_desc_get_chip(desc);
 
 	kstat_incr_irqs_this_cpu(irq, desc);
 
-	if (desc->irq_data.chip->irq_ack)
-		desc->irq_data.chip->irq_ack(&desc->irq_data);
+	if (chip->irq_ack)
+		chip->irq_ack(&desc->irq_data);
 
-	action_ret = handle_IRQ_event(irq, desc->action);
-	if (!noirqdebug)
-		note_interrupt(irq, desc, action_ret);
+	handle_irq_event_percpu(desc, desc->action);
 
-	if (desc->irq_data.chip->irq_eoi)
-		desc->irq_data.chip->irq_eoi(&desc->irq_data);
+	if (chip->irq_eoi)
+		chip->irq_eoi(&desc->irq_data);
 }
 
 void
-__set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
+__irq_set_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
 		  const char *name)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long flags;
+	struct irq_desc *desc = irq_get_desc_buslock(irq, &flags);
 
-	if (!desc) {
-		printk(KERN_ERR
-		       "Trying to install type control for IRQ%d\n", irq);
+	if (!desc)
 		return;
-	}
 
-	if (!handle)
+	if (!handle) {
 		handle = handle_bad_irq;
-	else if (desc->irq_data.chip == &no_irq_chip) {
-		printk(KERN_WARNING "Trying to install %sinterrupt handler "
-		       "for IRQ%d\n", is_chained ? "chained " : "", irq);
-		/*
-		 * Some ARM implementations install a handler for really dumb
-		 * interrupt hardware without setting an irq_chip. This worked
-		 * with the ARM no_irq_chip but the check in setup_irq would
-		 * prevent us to setup the interrupt at all. Switch it to
-		 * dummy_irq_chip for easy transition.
-		 */
-		desc->irq_data.chip = &dummy_irq_chip;
+	} else {
+		if (WARN_ON(desc->irq_data.chip == &no_irq_chip))
+			goto out;
 	}
 
-	chip_bus_lock(desc);
-	raw_spin_lock_irqsave(&desc->lock, flags);
-
 	/* Uninstall? */
 	if (handle == handle_bad_irq) {
 		if (desc->irq_data.chip != &no_irq_chip)
 			mask_ack_irq(desc);
-		desc->status |= IRQ_DISABLED;
+		irq_compat_set_disabled(desc);
+		desc->istate |= IRQS_DISABLED;
 		desc->depth = 1;
 	}
 	desc->handle_irq = handle;
 	desc->name = name;
 
 	if (handle != handle_bad_irq && is_chained) {
-		desc->status &= ~IRQ_DISABLED;
-		desc->status |= IRQ_NOREQUEST | IRQ_NOPROBE;
-		desc->depth = 0;
-		desc->irq_data.chip->irq_startup(&desc->irq_data);
+		irq_settings_set_noprobe(desc);
+		irq_settings_set_norequest(desc);
+		irq_startup(desc);
 	}
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
-	chip_bus_sync_unlock(desc);
-}
-EXPORT_SYMBOL_GPL(__set_irq_handler);
-
-void
-set_irq_chip_and_handler(unsigned int irq, struct irq_chip *chip,
-			 irq_flow_handler_t handle)
-{
-	set_irq_chip(irq, chip);
-	__set_irq_handler(irq, handle, 0, NULL);
+out:
+	irq_put_desc_busunlock(desc, flags);
 }
+EXPORT_SYMBOL_GPL(__irq_set_handler);
 
 void
-set_irq_chip_and_handler_name(unsigned int irq, struct irq_chip *chip,
+irq_set_chip_and_handler_name(unsigned int irq, struct irq_chip *chip,
 			      irq_flow_handler_t handle, const char *name)
 {
-	set_irq_chip(irq, chip);
-	__set_irq_handler(irq, handle, 0, name);
+	irq_set_chip(irq, chip);
+	__irq_set_handler(irq, handle, 0, name);
 }
 
 void irq_modify_status(unsigned int irq, unsigned long clr, unsigned long set)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long flags;
+	struct irq_desc *desc = irq_get_desc_lock(irq, &flags);
 
 	if (!desc)
 		return;
+	irq_settings_clr_and_set(desc, clr, set);
+
+	irqd_clear(&desc->irq_data, IRQD_NO_BALANCING | IRQD_PER_CPU |
+		   IRQD_TRIGGER_MASK | IRQD_LEVEL | IRQD_MOVE_PCNTXT);
+	if (irq_settings_has_no_balance_set(desc))
+		irqd_set(&desc->irq_data, IRQD_NO_BALANCING);
+	if (irq_settings_is_per_cpu(desc))
+		irqd_set(&desc->irq_data, IRQD_PER_CPU);
+	if (irq_settings_can_move_pcntxt(desc))
+		irqd_set(&desc->irq_data, IRQD_MOVE_PCNTXT);
 
-	/* Sanitize flags */
-	set &= IRQF_MODIFY_MASK;
-	clr &= IRQF_MODIFY_MASK;
+	irqd_set(&desc->irq_data, irq_settings_get_trigger_mask(desc));
 
-	raw_spin_lock_irqsave(&desc->lock, flags);
-	desc->status &= ~clr;
-	desc->status |= set;
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
+	irq_put_desc_unlock(desc, flags);
 }
diff --git a/kernel/irq/compat.h b/kernel/irq/compat.h
new file mode 100644
index 000000000000..6bbaf66aca85
--- /dev/null
+++ b/kernel/irq/compat.h
@@ -0,0 +1,72 @@
+/*
+ * Compat layer for transition period
+ */
+#ifndef CONFIG_GENERIC_HARDIRQS_NO_COMPAT
+static inline void irq_compat_set_progress(struct irq_desc *desc)
+{
+	desc->status |= IRQ_INPROGRESS;
+}
+
+static inline void irq_compat_clr_progress(struct irq_desc *desc)
+{
+	desc->status &= ~IRQ_INPROGRESS;
+}
+static inline void irq_compat_set_disabled(struct irq_desc *desc)
+{
+	desc->status |= IRQ_DISABLED;
+}
+static inline void irq_compat_clr_disabled(struct irq_desc *desc)
+{
+	desc->status &= ~IRQ_DISABLED;
+}
+static inline void irq_compat_set_pending(struct irq_desc *desc)
+{
+	desc->status |= IRQ_PENDING;
+}
+
+static inline void irq_compat_clr_pending(struct irq_desc *desc)
+{
+	desc->status &= ~IRQ_PENDING;
+}
+static inline void irq_compat_set_masked(struct irq_desc *desc)
+{
+	desc->status |= IRQ_MASKED;
+}
+
+static inline void irq_compat_clr_masked(struct irq_desc *desc)
+{
+	desc->status &= ~IRQ_MASKED;
+}
+static inline void irq_compat_set_move_pending(struct irq_desc *desc)
+{
+	desc->status |= IRQ_MOVE_PENDING;
+}
+
+static inline void irq_compat_clr_move_pending(struct irq_desc *desc)
+{
+	desc->status &= ~IRQ_MOVE_PENDING;
+}
+static inline void irq_compat_set_affinity(struct irq_desc *desc)
+{
+	desc->status |= IRQ_AFFINITY_SET;
+}
+
+static inline void irq_compat_clr_affinity(struct irq_desc *desc)
+{
+	desc->status &= ~IRQ_AFFINITY_SET;
+}
+#else
+static inline void irq_compat_set_progress(struct irq_desc *desc) { }
+static inline void irq_compat_clr_progress(struct irq_desc *desc) { }
+static inline void irq_compat_set_disabled(struct irq_desc *desc) { }
+static inline void irq_compat_clr_disabled(struct irq_desc *desc) { }
+static inline void irq_compat_set_pending(struct irq_desc *desc) { }
+static inline void irq_compat_clr_pending(struct irq_desc *desc) { }
+static inline void irq_compat_set_masked(struct irq_desc *desc) { }
+static inline void irq_compat_clr_masked(struct irq_desc *desc) { }
+static inline void irq_compat_set_move_pending(struct irq_desc *desc) { }
+static inline void irq_compat_clr_move_pending(struct irq_desc *desc) { }
+static inline void irq_compat_set_affinity(struct irq_desc *desc) { }
+static inline void irq_compat_clr_affinity(struct irq_desc *desc) { }
+#endif
+
diff --git a/kernel/irq/debug.h b/kernel/irq/debug.h
new file mode 100644
index 000000000000..d1a33b7fa61d
--- /dev/null
+++ b/kernel/irq/debug.h
@@ -0,0 +1,40 @@
+/*
+ * Debugging printout:
+ */
+
+#include <linux/kallsyms.h>
+
+#define P(f) if (desc->status & f) printk("%14s set\n", #f)
+#define PS(f) if (desc->istate & f) printk("%14s set\n", #f)
+
+static inline void print_irq_desc(unsigned int irq, struct irq_desc *desc)
+{
+	printk("irq %d, desc: %p, depth: %d, count: %d, unhandled: %d\n",
+		irq, desc, desc->depth, desc->irq_count, desc->irqs_unhandled);
+	printk("->handle_irq():  %p, ", desc->handle_irq);
+	print_symbol("%s\n", (unsigned long)desc->handle_irq);
+	printk("->irq_data.chip(): %p, ", desc->irq_data.chip);
+	print_symbol("%s\n", (unsigned long)desc->irq_data.chip);
+	printk("->action(): %p\n", desc->action);
+	if (desc->action) {
+		printk("->action->handler(): %p, ", desc->action->handler);
+		print_symbol("%s\n", (unsigned long)desc->action->handler);
+	}
+
+	P(IRQ_LEVEL);
+	P(IRQ_PER_CPU);
+	P(IRQ_NOPROBE);
+	P(IRQ_NOREQUEST);
+	P(IRQ_NOAUTOEN);
+
+	PS(IRQS_AUTODETECT);
+	PS(IRQS_INPROGRESS);
+	PS(IRQS_REPLAY);
+	PS(IRQS_WAITING);
+	PS(IRQS_DISABLED);
+	PS(IRQS_PENDING);
+	PS(IRQS_MASKED);
+}
+
+#undef P
+#undef PS
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index 3540a7190122..517561fc7317 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -51,30 +51,92 @@ static void warn_no_thread(unsigned int irq, struct irqaction *action)
 	       "but no thread function available.", irq, action->name);
 }
 
-/**
- * handle_IRQ_event - irq action chain handler
- * @irq:	the interrupt number
- * @action:	the interrupt action chain for this irq
- *
- * Handles the action chain of an irq event
- */
-irqreturn_t handle_IRQ_event(unsigned int irq, struct irqaction *action)
+static void irq_wake_thread(struct irq_desc *desc, struct irqaction *action)
+{
+	/*
+	 * Wake up the handler thread for this action. In case the
+	 * thread crashed and was killed we just pretend that we
+	 * handled the interrupt. The hardirq handler has disabled the
+	 * device interrupt, so no irq storm is lurking. If the
+	 * RUNTHREAD bit is already set, nothing to do.
+	 */
+	if (test_bit(IRQTF_DIED, &action->thread_flags) ||
+	    test_and_set_bit(IRQTF_RUNTHREAD, &action->thread_flags))
+		return;
+
+	/*
+	 * It's safe to OR the mask lockless here. We have only two
+	 * places which write to threads_oneshot: This code and the
+	 * irq thread.
+	 *
+	 * This code is the hard irq context and can never run on two
+	 * cpus in parallel. If it ever does we have more serious
+	 * problems than this bitmask.
+	 *
+	 * The irq threads of this irq which clear their "running" bit
+	 * in threads_oneshot are serialized via desc->lock against
+	 * each other and they are serialized against this code by
+	 * IRQS_INPROGRESS.
+	 *
+	 * Hard irq handler:
+	 *
+	 *	spin_lock(desc->lock);
+	 *	desc->state |= IRQS_INPROGRESS;
+	 *	spin_unlock(desc->lock);
+	 *	set_bit(IRQTF_RUNTHREAD, &action->thread_flags);
+	 *	desc->threads_oneshot |= mask;
+	 *	spin_lock(desc->lock);
+	 *	desc->state &= ~IRQS_INPROGRESS;
+	 *	spin_unlock(desc->lock);
+	 *
+	 * irq thread:
+	 *
+	 * again:
+	 *	spin_lock(desc->lock);
+	 *	if (desc->state & IRQS_INPROGRESS) {
+	 *		spin_unlock(desc->lock);
+	 *		while(desc->state & IRQS_INPROGRESS)
+	 *			cpu_relax();
+	 *		goto again;
+	 *	}
+	 *	if (!test_bit(IRQTF_RUNTHREAD, &action->thread_flags))
+	 *		desc->threads_oneshot &= ~mask;
+	 *	spin_unlock(desc->lock);
+	 *
+	 * So either the thread waits for us to clear IRQS_INPROGRESS
+	 * or we are waiting in the flow handler for desc->lock to be
+	 * released before we reach this point. The thread also checks
+	 * IRQTF_RUNTHREAD under desc->lock. If set it leaves
+	 * threads_oneshot untouched and runs the thread another time.
+	 */
+	desc->threads_oneshot |= action->thread_mask;
+	wake_up_process(action->thread);
+}
+
+irqreturn_t
+handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action)
 {
-	irqreturn_t ret, retval = IRQ_NONE;
-	unsigned int status = 0;
+	irqreturn_t retval = IRQ_NONE;
+	unsigned int random = 0, irq = desc->irq_data.irq;
 
 	do {
+		irqreturn_t res;
+
 		trace_irq_handler_entry(irq, action);
-		ret = action->handler(irq, action->dev_id);
-		trace_irq_handler_exit(irq, action, ret);
+		res = action->handler(irq, action->dev_id);
+		trace_irq_handler_exit(irq, action, res);
 
-		switch (ret) {
+		if (WARN_ONCE(!irqs_disabled(),"irq %u handler %pF enabled interrupts\n",
+			      irq, action->handler))
+			local_irq_disable();
+
+		switch (res) {
 		case IRQ_WAKE_THREAD:
 			/*
 			 * Set result to handled so the spurious check
 			 * does not trigger.
 			 */
-			ret = IRQ_HANDLED;
+			res = IRQ_HANDLED;
 
 			/*
 			 * Catch drivers which return WAKE_THREAD but
@@ -85,36 +147,56 @@ irqreturn_t handle_IRQ_event(unsigned int irq, struct irqaction *action)
 				break;
 			}
 
-			/*
-			 * Wake up the handler thread for this
-			 * action. In case the thread crashed and was
-			 * killed we just pretend that we handled the
-			 * interrupt. The hardirq handler above has
-			 * disabled the device interrupt, so no irq
-			 * storm is lurking.
-			 */
-			if (likely(!test_bit(IRQTF_DIED,
-					     &action->thread_flags))) {
-				set_bit(IRQTF_RUNTHREAD, &action->thread_flags);
-				wake_up_process(action->thread);
-			}
+			irq_wake_thread(desc, action);
 
 			/* Fall through to add to randomness */
 		case IRQ_HANDLED:
-			status |= action->flags;
+			random |= action->flags;
 			break;
 
 		default:
 			break;
 		}
 
-		retval |= ret;
+		retval |= res;
 		action = action->next;
 	} while (action);
 
-	if (status & IRQF_SAMPLE_RANDOM)
+	if (random & IRQF_SAMPLE_RANDOM)
 		add_interrupt_randomness(irq);
-	local_irq_disable();
 
+	if (!noirqdebug)
+		note_interrupt(irq, desc, retval);
 	return retval;
 }
+
+irqreturn_t handle_irq_event(struct irq_desc *desc)
+{
+	struct irqaction *action = desc->action;
+	irqreturn_t ret;
+
+	irq_compat_clr_pending(desc);
+	desc->istate &= ~IRQS_PENDING;
+	irq_compat_set_progress(desc);
+	desc->istate |= IRQS_INPROGRESS;
+	raw_spin_unlock(&desc->lock);
+
+	ret = handle_irq_event_percpu(desc, action);
+
+	raw_spin_lock(&desc->lock);
+	desc->istate &= ~IRQS_INPROGRESS;
+	irq_compat_clr_progress(desc);
+	return ret;
+}
+
+/**
+ * handle_IRQ_event - irq action chain handler
+ * @irq:	the interrupt number
+ * @action:	the interrupt action chain for this irq
+ *
+ * Handles the action chain of an irq event
+ */
+irqreturn_t handle_IRQ_event(unsigned int irq, struct irqaction *action)
+{
+	return handle_irq_event_percpu(irq_to_desc(irq), action);
+}
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 99c3bc8a6fb4..6c6ec9a49027 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -1,5 +1,9 @@
 /*
  * IRQ subsystem internal functions and variables:
+ *
+ * Do not ever include this file from anything else than
+ * kernel/irq/. Do not even think about using any information outside
+ * of this file for your non core code.
  */
 #include <linux/irqdesc.h>
 
@@ -9,25 +13,89 @@
 # define IRQ_BITMAP_BITS	NR_IRQS
 #endif
 
+#define istate core_internal_state__do_not_mess_with_it
+
+#ifdef CONFIG_GENERIC_HARDIRQS_NO_COMPAT
+# define status status_use_accessors
+#endif
+
 extern int noirqdebug;
 
+/*
+ * Bits used by threaded handlers:
+ * IRQTF_RUNTHREAD - signals that the interrupt handler thread should run
+ * IRQTF_DIED      - handler thread died
+ * IRQTF_WARNED    - warning "IRQ_WAKE_THREAD w/o thread_fn" has been printed
+ * IRQTF_AFFINITY  - irq thread is requested to adjust affinity
+ * IRQTF_FORCED_THREAD  - irq action is force threaded
+ */
+enum {
+	IRQTF_RUNTHREAD,
+	IRQTF_DIED,
+	IRQTF_WARNED,
+	IRQTF_AFFINITY,
+	IRQTF_FORCED_THREAD,
+};
+
+/*
+ * Bit masks for desc->state
+ *
+ * IRQS_AUTODETECT		- autodetection in progress
+ * IRQS_SPURIOUS_DISABLED	- was disabled due to spurious interrupt
+ *				  detection
+ * IRQS_POLL_INPROGRESS		- polling in progress
+ * IRQS_INPROGRESS		- Interrupt in progress
+ * IRQS_ONESHOT			- irq is not unmasked in primary handler
+ * IRQS_REPLAY			- irq is replayed
+ * IRQS_WAITING			- irq is waiting
+ * IRQS_DISABLED		- irq is disabled
+ * IRQS_PENDING			- irq is pending and replayed later
+ * IRQS_MASKED			- irq is masked
+ * IRQS_SUSPENDED		- irq is suspended
+ */
+enum {
+	IRQS_AUTODETECT		= 0x00000001,
+	IRQS_SPURIOUS_DISABLED	= 0x00000002,
+	IRQS_POLL_INPROGRESS	= 0x00000008,
+	IRQS_INPROGRESS		= 0x00000010,
+	IRQS_ONESHOT		= 0x00000020,
+	IRQS_REPLAY		= 0x00000040,
+	IRQS_WAITING		= 0x00000080,
+	IRQS_DISABLED		= 0x00000100,
+	IRQS_PENDING		= 0x00000200,
+	IRQS_MASKED		= 0x00000400,
+	IRQS_SUSPENDED		= 0x00000800,
+};
+
+#include "compat.h"
+#include "debug.h"
+#include "settings.h"
+
 #define irq_data_to_desc(data)	container_of(data, struct irq_desc, irq_data)
 
 /* Set default functions for irq_chip structures: */
 extern void irq_chip_set_defaults(struct irq_chip *chip);
 
-/* Set default handler: */
-extern void compat_irq_chip_set_default_handler(struct irq_desc *desc);
-
 extern int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
 		unsigned long flags);
 extern void __disable_irq(struct irq_desc *desc, unsigned int irq, bool susp);
 extern void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume);
 
+extern int irq_startup(struct irq_desc *desc);
+extern void irq_shutdown(struct irq_desc *desc);
+extern void irq_enable(struct irq_desc *desc);
+extern void irq_disable(struct irq_desc *desc);
+extern void mask_irq(struct irq_desc *desc);
+extern void unmask_irq(struct irq_desc *desc);
+
 extern void init_kstat_irqs(struct irq_desc *desc, int node, int nr);
 
+irqreturn_t handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action);
+irqreturn_t handle_irq_event(struct irq_desc *desc);
+
 /* Resending of interrupts :*/
 void check_irq_resend(struct irq_desc *desc, unsigned int irq);
+bool irq_wait_for_poll(struct irq_desc *desc);
 
 #ifdef CONFIG_PROC_FS
 extern void register_irq_proc(unsigned int irq, struct irq_desc *desc);
@@ -43,20 +111,10 @@ static inline void unregister_handler_proc(unsigned int irq,
 					   struct irqaction *action) { }
 #endif
 
-extern int irq_select_affinity_usr(unsigned int irq);
+extern int irq_select_affinity_usr(unsigned int irq, struct cpumask *mask);
 
 extern void irq_set_thread_affinity(struct irq_desc *desc);
 
-#ifndef CONFIG_GENERIC_HARDIRQS_NO_DEPRECATED
-static inline void irq_end(unsigned int irq, struct irq_desc *desc)
-{
-	if (desc->irq_data.chip && desc->irq_data.chip->end)
-		desc->irq_data.chip->end(irq);
-}
-#else
-static inline void irq_end(unsigned int irq, struct irq_desc *desc) { }
-#endif
-
 /* Inline functions for support of irq chips on slow busses */
 static inline void chip_bus_lock(struct irq_desc *desc)
 {
@@ -70,43 +128,60 @@ static inline void chip_bus_sync_unlock(struct irq_desc *desc)
 		desc->irq_data.chip->irq_bus_sync_unlock(&desc->irq_data);
 }
 
+struct irq_desc *
+__irq_get_desc_lock(unsigned int irq, unsigned long *flags, bool bus);
+void __irq_put_desc_unlock(struct irq_desc *desc, unsigned long flags, bool bus);
+
+static inline struct irq_desc *
+irq_get_desc_buslock(unsigned int irq, unsigned long *flags)
+{
+	return __irq_get_desc_lock(irq, flags, true);
+}
+
+static inline void
+irq_put_desc_busunlock(struct irq_desc *desc, unsigned long flags)
+{
+	__irq_put_desc_unlock(desc, flags, true);
+}
+
+static inline struct irq_desc *
+irq_get_desc_lock(unsigned int irq, unsigned long *flags)
+{
+	return __irq_get_desc_lock(irq, flags, false);
+}
+
+static inline void
+irq_put_desc_unlock(struct irq_desc *desc, unsigned long flags)
+{
+	__irq_put_desc_unlock(desc, flags, false);
+}
+
 /*
- * Debugging printout:
+ * Manipulation functions for irq_data.state
  */
+static inline void irqd_set_move_pending(struct irq_data *d)
+{
+	d->state_use_accessors |= IRQD_SETAFFINITY_PENDING;
+	irq_compat_set_move_pending(irq_data_to_desc(d));
+}
 
-#include <linux/kallsyms.h>
-
-#define P(f) if (desc->status & f) printk("%14s set\n", #f)
+static inline void irqd_clr_move_pending(struct irq_data *d)
+{
+	d->state_use_accessors &= ~IRQD_SETAFFINITY_PENDING;
+	irq_compat_clr_move_pending(irq_data_to_desc(d));
+}
 
-static inline void print_irq_desc(unsigned int irq, struct irq_desc *desc)
+static inline void irqd_clear(struct irq_data *d, unsigned int mask)
 {
-	printk("irq %d, desc: %p, depth: %d, count: %d, unhandled: %d\n",
-		irq, desc, desc->depth, desc->irq_count, desc->irqs_unhandled);
-	printk("->handle_irq():  %p, ", desc->handle_irq);
-	print_symbol("%s\n", (unsigned long)desc->handle_irq);
-	printk("->irq_data.chip(): %p, ", desc->irq_data.chip);
-	print_symbol("%s\n", (unsigned long)desc->irq_data.chip);
-	printk("->action(): %p\n", desc->action);
-	if (desc->action) {
-		printk("->action->handler(): %p, ", desc->action->handler);
-		print_symbol("%s\n", (unsigned long)desc->action->handler);
-	}
-
-	P(IRQ_INPROGRESS);
-	P(IRQ_DISABLED);
-	P(IRQ_PENDING);
-	P(IRQ_REPLAY);
-	P(IRQ_AUTODETECT);
-	P(IRQ_WAITING);
-	P(IRQ_LEVEL);
-	P(IRQ_MASKED);
-#ifdef CONFIG_IRQ_PER_CPU
-	P(IRQ_PER_CPU);
-#endif
-	P(IRQ_NOPROBE);
-	P(IRQ_NOREQUEST);
-	P(IRQ_NOAUTOEN);
+	d->state_use_accessors &= ~mask;
 }
 
-#undef P
+static inline void irqd_set(struct irq_data *d, unsigned int mask)
+{
+	d->state_use_accessors |= mask;
+}
 
+static inline bool irqd_has_set(struct irq_data *d, unsigned int mask)
+{
+	return d->state_use_accessors & mask;
+}
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 2039bea31bdf..dbccc799407f 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -79,7 +79,8 @@ static void desc_set_defaults(unsigned int irq, struct irq_desc *desc, int node)
 	desc->irq_data.chip_data = NULL;
 	desc->irq_data.handler_data = NULL;
 	desc->irq_data.msi_desc = NULL;
-	desc->status = IRQ_DEFAULT_INIT_FLAGS;
+	irq_settings_clr_and_set(desc, ~0, _IRQ_DEFAULT_INIT_FLAGS);
+	desc->istate = IRQS_DISABLED;
 	desc->handle_irq = handle_bad_irq;
 	desc->depth = 1;
 	desc->irq_count = 0;
@@ -206,6 +207,14 @@ struct irq_desc * __ref irq_to_desc_alloc_node(unsigned int irq, int node)
 	return NULL;
 }
 
+static int irq_expand_nr_irqs(unsigned int nr)
+{
+	if (nr > IRQ_BITMAP_BITS)
+		return -ENOMEM;
+	nr_irqs = nr;
+	return 0;
+}
+
 int __init early_irq_init(void)
 {
 	int i, initcnt, node = first_online_node;
@@ -238,7 +247,7 @@ int __init early_irq_init(void)
 
 struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = {
 	[0 ... NR_IRQS-1] = {
-		.status		= IRQ_DEFAULT_INIT_FLAGS,
+		.istate		= IRQS_DISABLED,
 		.handle_irq	= handle_bad_irq,
 		.depth		= 1,
 		.lock		= __RAW_SPIN_LOCK_UNLOCKED(irq_desc->lock),
@@ -260,8 +269,8 @@ int __init early_irq_init(void)
 	for (i = 0; i < count; i++) {
 		desc[i].irq_data.irq = i;
 		desc[i].irq_data.chip = &no_irq_chip;
-		/* TODO : do this allocation on-demand ... */
 		desc[i].kstat_irqs = alloc_percpu(unsigned int);
+		irq_settings_clr_and_set(desc, ~0, _IRQ_DEFAULT_INIT_FLAGS);
 		alloc_masks(desc + i, GFP_KERNEL, node);
 		desc_smp_init(desc + i, node);
 		lockdep_set_class(&desc[i].lock, &irq_desc_lock_class);
@@ -286,24 +295,14 @@ static void free_desc(unsigned int irq)
 
 static inline int alloc_descs(unsigned int start, unsigned int cnt, int node)
 {
-#if defined(CONFIG_KSTAT_IRQS_ONDEMAND)
-	struct irq_desc *desc;
-	unsigned int i;
-
-	for (i = 0; i < cnt; i++) {
-		desc = irq_to_desc(start + i);
-		if (desc && !desc->kstat_irqs) {
-			unsigned int __percpu *stats = alloc_percpu(unsigned int);
-
-			if (!stats)
-				return -1;
-			if (cmpxchg(&desc->kstat_irqs, NULL, stats) != NULL)
-				free_percpu(stats);
-		}
-	}
-#endif
 	return start;
 }
+
+static int irq_expand_nr_irqs(unsigned int nr)
+{
+	return -ENOMEM;
+}
+
 #endif /* !CONFIG_SPARSE_IRQ */
 
 /* Dynamic interrupt handling */
@@ -347,14 +346,17 @@ irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node)
 
 	mutex_lock(&sparse_irq_lock);
 
-	start = bitmap_find_next_zero_area(allocated_irqs, nr_irqs, from, cnt, 0);
+	start = bitmap_find_next_zero_area(allocated_irqs, IRQ_BITMAP_BITS,
+					   from, cnt, 0);
 	ret = -EEXIST;
 	if (irq >=0 && start != irq)
 		goto err;
 
-	ret = -ENOMEM;
-	if (start >= nr_irqs)
-		goto err;
+	if (start + cnt > nr_irqs) {
+		ret = irq_expand_nr_irqs(start + cnt);
+		if (ret)
+			goto err;
+	}
 
 	bitmap_set(allocated_irqs, start, cnt);
 	mutex_unlock(&sparse_irq_lock);
@@ -401,6 +403,26 @@ unsigned int irq_get_next_irq(unsigned int offset)
 	return find_next_bit(allocated_irqs, nr_irqs, offset);
 }
 
+struct irq_desc *
+__irq_get_desc_lock(unsigned int irq, unsigned long *flags, bool bus)
+{
+	struct irq_desc *desc = irq_to_desc(irq);
+
+	if (desc) {
+		if (bus)
+			chip_bus_lock(desc);
+		raw_spin_lock_irqsave(&desc->lock, *flags);
+	}
+	return desc;
+}
+
+void __irq_put_desc_unlock(struct irq_desc *desc, unsigned long flags, bool bus)
+{
+	raw_spin_unlock_irqrestore(&desc->lock, flags);
+	if (bus)
+		chip_bus_sync_unlock(desc);
+}
+
 /**
  * dynamic_irq_cleanup - cleanup a dynamically allocated irq
  * @irq:	irq number to initialize
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 9033c1c70828..acd599a43bfb 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -17,6 +17,17 @@
 
 #include "internals.h"
 
+#ifdef CONFIG_IRQ_FORCED_THREADING
+__read_mostly bool force_irqthreads;
+
+static int __init setup_forced_irqthreads(char *arg)
+{
+	force_irqthreads = true;
+	return 0;
+}
+early_param("threadirqs", setup_forced_irqthreads);
+#endif
+
 /**
  *	synchronize_irq - wait for pending IRQ handlers (on other CPUs)
  *	@irq: interrupt number to wait for
@@ -30,7 +41,7 @@
 void synchronize_irq(unsigned int irq)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
-	unsigned int status;
+	unsigned int state;
 
 	if (!desc)
 		return;
@@ -42,16 +53,16 @@ void synchronize_irq(unsigned int irq)
 		 * Wait until we're out of the critical section.  This might
 		 * give the wrong answer due to the lack of memory barriers.
 		 */
-		while (desc->status & IRQ_INPROGRESS)
+		while (desc->istate & IRQS_INPROGRESS)
 			cpu_relax();
 
 		/* Ok, that indicated we're done: double-check carefully. */
 		raw_spin_lock_irqsave(&desc->lock, flags);
-		status = desc->status;
+		state = desc->istate;
 		raw_spin_unlock_irqrestore(&desc->lock, flags);
 
 		/* Oops, that failed? */
-	} while (status & IRQ_INPROGRESS);
+	} while (state & IRQS_INPROGRESS);
 
 	/*
 	 * We made sure that no hardirq handler is running. Now verify
@@ -73,8 +84,8 @@ int irq_can_set_affinity(unsigned int irq)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 
-	if (CHECK_IRQ_PER_CPU(desc->status) || !desc->irq_data.chip ||
-	    !desc->irq_data.chip->irq_set_affinity)
+	if (!desc || !irqd_can_balance(&desc->irq_data) ||
+	    !desc->irq_data.chip || !desc->irq_data.chip->irq_set_affinity)
 		return 0;
 
 	return 1;
@@ -100,67 +111,169 @@ void irq_set_thread_affinity(struct irq_desc *desc)
 	}
 }
 
+#ifdef CONFIG_GENERIC_PENDING_IRQ
+static inline bool irq_can_move_pcntxt(struct irq_desc *desc)
+{
+	return irq_settings_can_move_pcntxt(desc);
+}
+static inline bool irq_move_pending(struct irq_desc *desc)
+{
+	return irqd_is_setaffinity_pending(&desc->irq_data);
+}
+static inline void
+irq_copy_pending(struct irq_desc *desc, const struct cpumask *mask)
+{
+	cpumask_copy(desc->pending_mask, mask);
+}
+static inline void
+irq_get_pending(struct cpumask *mask, struct irq_desc *desc)
+{
+	cpumask_copy(mask, desc->pending_mask);
+}
+#else
+static inline bool irq_can_move_pcntxt(struct irq_desc *desc) { return true; }
+static inline bool irq_move_pending(struct irq_desc *desc) { return false; }
+static inline void
+irq_copy_pending(struct irq_desc *desc, const struct cpumask *mask) { }
+static inline void
+irq_get_pending(struct cpumask *mask, struct irq_desc *desc) { }
+#endif
+
 /**
  *	irq_set_affinity - Set the irq affinity of a given irq
  *	@irq:		Interrupt to set affinity
  *	@cpumask:	cpumask
  *
  */
-int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask)
+int irq_set_affinity(unsigned int irq, const struct cpumask *mask)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	struct irq_chip *chip = desc->irq_data.chip;
 	unsigned long flags;
+	int ret = 0;
 
 	if (!chip->irq_set_affinity)
 		return -EINVAL;
 
 	raw_spin_lock_irqsave(&desc->lock, flags);
 
-#ifdef CONFIG_GENERIC_PENDING_IRQ
-	if (desc->status & IRQ_MOVE_PCNTXT) {
-		if (!chip->irq_set_affinity(&desc->irq_data, cpumask, false)) {
-			cpumask_copy(desc->irq_data.affinity, cpumask);
+	if (irq_can_move_pcntxt(desc)) {
+		ret = chip->irq_set_affinity(&desc->irq_data, mask, false);
+		switch (ret) {
+		case IRQ_SET_MASK_OK:
+			cpumask_copy(desc->irq_data.affinity, mask);
+		case IRQ_SET_MASK_OK_NOCOPY:
 			irq_set_thread_affinity(desc);
+			ret = 0;
 		}
+	} else {
+		irqd_set_move_pending(&desc->irq_data);
+		irq_copy_pending(desc, mask);
 	}
-	else {
-		desc->status |= IRQ_MOVE_PENDING;
-		cpumask_copy(desc->pending_mask, cpumask);
-	}
-#else
-	if (!chip->irq_set_affinity(&desc->irq_data, cpumask, false)) {
-		cpumask_copy(desc->irq_data.affinity, cpumask);
-		irq_set_thread_affinity(desc);
+
+	if (desc->affinity_notify) {
+		kref_get(&desc->affinity_notify->kref);
+		schedule_work(&desc->affinity_notify->work);
 	}
-#endif
-	desc->status |= IRQ_AFFINITY_SET;
+	irq_compat_set_affinity(desc);
+	irqd_set(&desc->irq_data, IRQD_AFFINITY_SET);
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
-	return 0;
+	return ret;
 }
 
 int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m)
 {
+	unsigned long flags;
+	struct irq_desc *desc = irq_get_desc_lock(irq, &flags);
+
+	if (!desc)
+		return -EINVAL;
+	desc->affinity_hint = m;
+	irq_put_desc_unlock(desc, flags);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(irq_set_affinity_hint);
+
+static void irq_affinity_notify(struct work_struct *work)
+{
+	struct irq_affinity_notify *notify =
+		container_of(work, struct irq_affinity_notify, work);
+	struct irq_desc *desc = irq_to_desc(notify->irq);
+	cpumask_var_t cpumask;
+	unsigned long flags;
+
+	if (!desc || !alloc_cpumask_var(&cpumask, GFP_KERNEL))
+		goto out;
+
+	raw_spin_lock_irqsave(&desc->lock, flags);
+	if (irq_move_pending(desc))
+		irq_get_pending(cpumask, desc);
+	else
+		cpumask_copy(cpumask, desc->irq_data.affinity);
+	raw_spin_unlock_irqrestore(&desc->lock, flags);
+
+	notify->notify(notify, cpumask);
+
+	free_cpumask_var(cpumask);
+out:
+	kref_put(&notify->kref, notify->release);
+}
+
+/**
+ *	irq_set_affinity_notifier - control notification of IRQ affinity changes
+ *	@irq:		Interrupt for which to enable/disable notification
+ *	@notify:	Context for notification, or %NULL to disable
+ *			notification.  Function pointers must be initialised;
+ *			the other fields will be initialised by this function.
+ *
+ *	Must be called in process context.  Notification may only be enabled
+ *	after the IRQ is allocated and must be disabled before the IRQ is
+ *	freed using free_irq().
+ */
+int
+irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify)
+{
 	struct irq_desc *desc = irq_to_desc(irq);
+	struct irq_affinity_notify *old_notify;
 	unsigned long flags;
 
+	/* The release function is promised process context */
+	might_sleep();
+
 	if (!desc)
 		return -EINVAL;
 
+	/* Complete initialisation of *notify */
+	if (notify) {
+		notify->irq = irq;
+		kref_init(&notify->kref);
+		INIT_WORK(&notify->work, irq_affinity_notify);
+	}
+
 	raw_spin_lock_irqsave(&desc->lock, flags);
-	desc->affinity_hint = m;
+	old_notify = desc->affinity_notify;
+	desc->affinity_notify = notify;
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 
+	if (old_notify)
+		kref_put(&old_notify->kref, old_notify->release);
+
 	return 0;
 }
-EXPORT_SYMBOL_GPL(irq_set_affinity_hint);
+EXPORT_SYMBOL_GPL(irq_set_affinity_notifier);
 
 #ifndef CONFIG_AUTO_IRQ_AFFINITY
 /*
  * Generic version of the affinity autoselector.
  */
-static int setup_affinity(unsigned int irq, struct irq_desc *desc)
+static int
+setup_affinity(unsigned int irq, struct irq_desc *desc, struct cpumask *mask)
 {
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	struct cpumask *set = irq_default_affinity;
+	int ret;
+
+	/* Excludes PER_CPU and NO_BALANCE interrupts */
 	if (!irq_can_set_affinity(irq))
 		return 0;
 
@@ -168,22 +281,29 @@ static int setup_affinity(unsigned int irq, struct irq_desc *desc)
 	 * Preserve an userspace affinity setup, but make sure that
 	 * one of the targets is online.
 	 */
-	if (desc->status & (IRQ_AFFINITY_SET | IRQ_NO_BALANCING)) {
-		if (cpumask_any_and(desc->irq_data.affinity, cpu_online_mask)
-		    < nr_cpu_ids)
-			goto set_affinity;
-		else
-			desc->status &= ~IRQ_AFFINITY_SET;
+	if (irqd_has_set(&desc->irq_data, IRQD_AFFINITY_SET)) {
+		if (cpumask_intersects(desc->irq_data.affinity,
+				       cpu_online_mask))
+			set = desc->irq_data.affinity;
+		else {
+			irq_compat_clr_affinity(desc);
+			irqd_clear(&desc->irq_data, IRQD_AFFINITY_SET);
+		}
 	}
 
-	cpumask_and(desc->irq_data.affinity, cpu_online_mask, irq_default_affinity);
-set_affinity:
-	desc->irq_data.chip->irq_set_affinity(&desc->irq_data, desc->irq_data.affinity, false);
-
+	cpumask_and(mask, cpu_online_mask, set);
+	ret = chip->irq_set_affinity(&desc->irq_data, mask, false);
+	switch (ret) {
+	case IRQ_SET_MASK_OK:
+		cpumask_copy(desc->irq_data.affinity, mask);
+	case IRQ_SET_MASK_OK_NOCOPY:
+		irq_set_thread_affinity(desc);
+	}
 	return 0;
 }
 #else
-static inline int setup_affinity(unsigned int irq, struct irq_desc *d)
+static inline int
+setup_affinity(unsigned int irq, struct irq_desc *d, struct cpumask *mask)
 {
 	return irq_select_affinity(irq);
 }
@@ -192,23 +312,21 @@ static inline int setup_affinity(unsigned int irq, struct irq_desc *d)
 /*
  * Called when affinity is set via /proc/irq
  */
-int irq_select_affinity_usr(unsigned int irq)
+int irq_select_affinity_usr(unsigned int irq, struct cpumask *mask)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long flags;
 	int ret;
 
 	raw_spin_lock_irqsave(&desc->lock, flags);
-	ret = setup_affinity(irq, desc);
-	if (!ret)
-		irq_set_thread_affinity(desc);
+	ret = setup_affinity(irq, desc, mask);
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
-
 	return ret;
 }
 
 #else
-static inline int setup_affinity(unsigned int irq, struct irq_desc *desc)
+static inline int
+setup_affinity(unsigned int irq, struct irq_desc *desc, struct cpumask *mask)
 {
 	return 0;
 }
@@ -219,13 +337,23 @@ void __disable_irq(struct irq_desc *desc, unsigned int irq, bool suspend)
 	if (suspend) {
 		if (!desc->action || (desc->action->flags & IRQF_NO_SUSPEND))
 			return;
-		desc->status |= IRQ_SUSPENDED;
+		desc->istate |= IRQS_SUSPENDED;
 	}
 
-	if (!desc->depth++) {
-		desc->status |= IRQ_DISABLED;
-		desc->irq_data.chip->irq_disable(&desc->irq_data);
-	}
+	if (!desc->depth++)
+		irq_disable(desc);
+}
+
+static int __disable_irq_nosync(unsigned int irq)
+{
+	unsigned long flags;
+	struct irq_desc *desc = irq_get_desc_buslock(irq, &flags);
+
+	if (!desc)
+		return -EINVAL;
+	__disable_irq(desc, irq, false);
+	irq_put_desc_busunlock(desc, flags);
+	return 0;
 }
 
 /**
@@ -241,17 +369,7 @@ void __disable_irq(struct irq_desc *desc, unsigned int irq, bool suspend)
  */
 void disable_irq_nosync(unsigned int irq)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
-	unsigned long flags;
-
-	if (!desc)
-		return;
-
-	chip_bus_lock(desc);
-	raw_spin_lock_irqsave(&desc->lock, flags);
-	__disable_irq(desc, irq, false);
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
-	chip_bus_sync_unlock(desc);
+	__disable_irq_nosync(irq);
 }
 EXPORT_SYMBOL(disable_irq_nosync);
 
@@ -269,21 +387,24 @@ EXPORT_SYMBOL(disable_irq_nosync);
  */
 void disable_irq(unsigned int irq)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
-
-	if (!desc)
-		return;
-
-	disable_irq_nosync(irq);
-	if (desc->action)
+	if (!__disable_irq_nosync(irq))
 		synchronize_irq(irq);
 }
 EXPORT_SYMBOL(disable_irq);
 
 void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume)
 {
-	if (resume)
-		desc->status &= ~IRQ_SUSPENDED;
+	if (resume) {
+		if (!(desc->istate & IRQS_SUSPENDED)) {
+			if (!desc->action)
+				return;
+			if (!(desc->action->flags & IRQF_FORCE_RESUME))
+				return;
+			/* Pretend that it got disabled ! */
+			desc->depth++;
+		}
+		desc->istate &= ~IRQS_SUSPENDED;
+	}
 
 	switch (desc->depth) {
 	case 0:
@@ -291,12 +412,11 @@ void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume)
 		WARN(1, KERN_WARNING "Unbalanced enable for IRQ %d\n", irq);
 		break;
 	case 1: {
-		unsigned int status = desc->status & ~IRQ_DISABLED;
-
-		if (desc->status & IRQ_SUSPENDED)
+		if (desc->istate & IRQS_SUSPENDED)
 			goto err_out;
 		/* Prevent probing on this irq: */
-		desc->status = status | IRQ_NOPROBE;
+		irq_settings_set_noprobe(desc);
+		irq_enable(desc);
 		check_irq_resend(desc, irq);
 		/* fall-through */
 	}
@@ -318,21 +438,18 @@ void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume)
  */
 void enable_irq(unsigned int irq)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long flags;
+	struct irq_desc *desc = irq_get_desc_buslock(irq, &flags);
 
 	if (!desc)
 		return;
+	if (WARN(!desc->irq_data.chip,
+		 KERN_ERR "enable_irq before setup/request_irq: irq %u\n", irq))
+		goto out;
 
-	if (WARN(!desc->irq_data.chip || !desc->irq_data.chip->irq_enable,
-	    KERN_ERR "enable_irq before setup/request_irq: irq %u\n", irq))
-		return;
-
-	chip_bus_lock(desc);
-	raw_spin_lock_irqsave(&desc->lock, flags);
 	__enable_irq(desc, irq, false);
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
-	chip_bus_sync_unlock(desc);
+out:
+	irq_put_desc_busunlock(desc, flags);
 }
 EXPORT_SYMBOL(enable_irq);
 
@@ -348,7 +465,7 @@ static int set_irq_wake_real(unsigned int irq, unsigned int on)
 }
 
 /**
- *	set_irq_wake - control irq power management wakeup
+ *	irq_set_irq_wake - control irq power management wakeup
  *	@irq:	interrupt to control
  *	@on:	enable/disable power management wakeup
  *
@@ -359,23 +476,22 @@ static int set_irq_wake_real(unsigned int irq, unsigned int on)
  *	Wakeup mode lets this IRQ wake the system from sleep
  *	states like "suspend to RAM".
  */
-int set_irq_wake(unsigned int irq, unsigned int on)
+int irq_set_irq_wake(unsigned int irq, unsigned int on)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long flags;
+	struct irq_desc *desc = irq_get_desc_buslock(irq, &flags);
 	int ret = 0;
 
 	/* wakeup-capable irqs can be shared between drivers that
 	 * don't need to have the same sleep mode behaviors.
 	 */
-	raw_spin_lock_irqsave(&desc->lock, flags);
 	if (on) {
 		if (desc->wake_depth++ == 0) {
 			ret = set_irq_wake_real(irq, on);
 			if (ret)
 				desc->wake_depth = 0;
 			else
-				desc->status |= IRQ_WAKEUP;
+				irqd_set(&desc->irq_data, IRQD_WAKEUP_STATE);
 		}
 	} else {
 		if (desc->wake_depth == 0) {
@@ -385,14 +501,13 @@ int set_irq_wake(unsigned int irq, unsigned int on)
 			if (ret)
 				desc->wake_depth = 1;
 			else
-				desc->status &= ~IRQ_WAKEUP;
+				irqd_clear(&desc->irq_data, IRQD_WAKEUP_STATE);
 		}
 	}
-
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
+	irq_put_desc_busunlock(desc, flags);
 	return ret;
 }
-EXPORT_SYMBOL(set_irq_wake);
+EXPORT_SYMBOL(irq_set_irq_wake);
 
 /*
  * Internal function that tells the architecture code whether a
@@ -401,43 +516,27 @@ EXPORT_SYMBOL(set_irq_wake);
  */
 int can_request_irq(unsigned int irq, unsigned long irqflags)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
-	struct irqaction *action;
 	unsigned long flags;
+	struct irq_desc *desc = irq_get_desc_lock(irq, &flags);
+	int canrequest = 0;
 
 	if (!desc)
 		return 0;
 
-	if (desc->status & IRQ_NOREQUEST)
-		return 0;
-
-	raw_spin_lock_irqsave(&desc->lock, flags);
-	action = desc->action;
-	if (action)
-		if (irqflags & action->flags & IRQF_SHARED)
-			action = NULL;
-
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
-
-	return !action;
-}
-
-void compat_irq_chip_set_default_handler(struct irq_desc *desc)
-{
-	/*
-	 * If the architecture still has not overriden
-	 * the flow handler then zap the default. This
-	 * should catch incorrect flow-type setting.
-	 */
-	if (desc->handle_irq == &handle_bad_irq)
-		desc->handle_irq = NULL;
+	if (irq_settings_can_request(desc)) {
+		if (desc->action)
+			if (irqflags & desc->action->flags & IRQF_SHARED)
+				canrequest =1;
+	}
+	irq_put_desc_unlock(desc, flags);
+	return canrequest;
 }
 
 int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
 		      unsigned long flags)
 {
-	int ret;
 	struct irq_chip *chip = desc->irq_data.chip;
+	int ret, unmask = 0;
 
 	if (!chip || !chip->irq_set_type) {
 		/*
@@ -449,23 +548,43 @@ int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
 		return 0;
 	}
 
+	flags &= IRQ_TYPE_SENSE_MASK;
+
+	if (chip->flags & IRQCHIP_SET_TYPE_MASKED) {
+		if (!(desc->istate & IRQS_MASKED))
+			mask_irq(desc);
+		if (!(desc->istate & IRQS_DISABLED))
+			unmask = 1;
+	}
+
 	/* caller masked out all except trigger mode flags */
 	ret = chip->irq_set_type(&desc->irq_data, flags);
 
-	if (ret)
-		pr_err("setting trigger mode %lu for irq %u failed (%pF)\n",
-		       flags, irq, chip->irq_set_type);
-	else {
-		if (flags & (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH))
-			flags |= IRQ_LEVEL;
-		/* note that IRQF_TRIGGER_MASK == IRQ_TYPE_SENSE_MASK */
-		desc->status &= ~(IRQ_LEVEL | IRQ_TYPE_SENSE_MASK);
-		desc->status |= flags;
+	switch (ret) {
+	case IRQ_SET_MASK_OK:
+		irqd_clear(&desc->irq_data, IRQD_TRIGGER_MASK);
+		irqd_set(&desc->irq_data, flags);
+
+	case IRQ_SET_MASK_OK_NOCOPY:
+		flags = irqd_get_trigger_type(&desc->irq_data);
+		irq_settings_set_trigger_mask(desc, flags);
+		irqd_clear(&desc->irq_data, IRQD_LEVEL);
+		irq_settings_clr_level(desc);
+		if (flags & IRQ_TYPE_LEVEL_MASK) {
+			irq_settings_set_level(desc);
+			irqd_set(&desc->irq_data, IRQD_LEVEL);
+		}
 
 		if (chip != desc->irq_data.chip)
 			irq_chip_set_defaults(desc->irq_data.chip);
+		ret = 0;
+		break;
+	default:
+		pr_err("setting trigger mode %lu for irq %u failed (%pF)\n",
+		       flags, irq, chip->irq_set_type);
 	}
-
+	if (unmask)
+		unmask_irq(desc);
 	return ret;
 }
 
@@ -509,8 +628,11 @@ static int irq_wait_for_interrupt(struct irqaction *action)
  * handler finished. unmask if the interrupt has not been disabled and
  * is marked MASKED.
  */
-static void irq_finalize_oneshot(unsigned int irq, struct irq_desc *desc)
+static void irq_finalize_oneshot(struct irq_desc *desc,
+				 struct irqaction *action, bool force)
 {
+	if (!(desc->istate & IRQS_ONESHOT))
+		return;
 again:
 	chip_bus_lock(desc);
 	raw_spin_lock_irq(&desc->lock);
@@ -522,26 +644,44 @@ again:
 	 * The thread is faster done than the hard interrupt handler
 	 * on the other CPU. If we unmask the irq line then the
 	 * interrupt can come in again and masks the line, leaves due
-	 * to IRQ_INPROGRESS and the irq line is masked forever.
+	 * to IRQS_INPROGRESS and the irq line is masked forever.
+	 *
+	 * This also serializes the state of shared oneshot handlers
+	 * versus "desc->threads_onehsot |= action->thread_mask;" in
+	 * irq_wake_thread(). See the comment there which explains the
+	 * serialization.
 	 */
-	if (unlikely(desc->status & IRQ_INPROGRESS)) {
+	if (unlikely(desc->istate & IRQS_INPROGRESS)) {
 		raw_spin_unlock_irq(&desc->lock);
 		chip_bus_sync_unlock(desc);
 		cpu_relax();
 		goto again;
 	}
 
-	if (!(desc->status & IRQ_DISABLED) && (desc->status & IRQ_MASKED)) {
-		desc->status &= ~IRQ_MASKED;
+	/*
+	 * Now check again, whether the thread should run. Otherwise
+	 * we would clear the threads_oneshot bit of this thread which
+	 * was just set.
+	 */
+	if (!force && test_bit(IRQTF_RUNTHREAD, &action->thread_flags))
+		goto out_unlock;
+
+	desc->threads_oneshot &= ~action->thread_mask;
+
+	if (!desc->threads_oneshot && !(desc->istate & IRQS_DISABLED) &&
+	    (desc->istate & IRQS_MASKED)) {
+		irq_compat_clr_masked(desc);
+		desc->istate &= ~IRQS_MASKED;
 		desc->irq_data.chip->irq_unmask(&desc->irq_data);
 	}
+out_unlock:
 	raw_spin_unlock_irq(&desc->lock);
 	chip_bus_sync_unlock(desc);
 }
 
 #ifdef CONFIG_SMP
 /*
- * Check whether we need to change the affinity of the interrupt thread.
+ * Check whether we need to chasnge the affinity of the interrupt thread.
  */
 static void
 irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action)
@@ -573,6 +713,32 @@ irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action) { }
 #endif
 
 /*
+ * Interrupts which are not explicitely requested as threaded
+ * interrupts rely on the implicit bh/preempt disable of the hard irq
+ * context. So we need to disable bh here to avoid deadlocks and other
+ * side effects.
+ */
+static void
+irq_forced_thread_fn(struct irq_desc *desc, struct irqaction *action)
+{
+	local_bh_disable();
+	action->thread_fn(action->irq, action->dev_id);
+	irq_finalize_oneshot(desc, action, false);
+	local_bh_enable();
+}
+
+/*
+ * Interrupts explicitely requested as threaded interupts want to be
+ * preemtible - many of them need to sleep and wait for slow busses to
+ * complete.
+ */
+static void irq_thread_fn(struct irq_desc *desc, struct irqaction *action)
+{
+	action->thread_fn(action->irq, action->dev_id);
+	irq_finalize_oneshot(desc, action, false);
+}
+
+/*
  * Interrupt handler thread
  */
 static int irq_thread(void *data)
@@ -582,7 +748,14 @@ static int irq_thread(void *data)
 	};
 	struct irqaction *action = data;
 	struct irq_desc *desc = irq_to_desc(action->irq);
-	int wake, oneshot = desc->status & IRQ_ONESHOT;
+	void (*handler_fn)(struct irq_desc *desc, struct irqaction *action);
+	int wake;
+
+	if (force_irqthreads & test_bit(IRQTF_FORCED_THREAD,
+					&action->thread_flags))
+		handler_fn = irq_forced_thread_fn;
+	else
+		handler_fn = irq_thread_fn;
 
 	sched_setscheduler(current, SCHED_FIFO, &param);
 	current->irqaction = action;
@@ -594,23 +767,20 @@ static int irq_thread(void *data)
 		atomic_inc(&desc->threads_active);
 
 		raw_spin_lock_irq(&desc->lock);
-		if (unlikely(desc->status & IRQ_DISABLED)) {
+		if (unlikely(desc->istate & IRQS_DISABLED)) {
 			/*
 			 * CHECKME: We might need a dedicated
 			 * IRQ_THREAD_PENDING flag here, which
 			 * retriggers the thread in check_irq_resend()
-			 * but AFAICT IRQ_PENDING should be fine as it
+			 * but AFAICT IRQS_PENDING should be fine as it
 			 * retriggers the interrupt itself --- tglx
 			 */
-			desc->status |= IRQ_PENDING;
+			irq_compat_set_pending(desc);
+			desc->istate |= IRQS_PENDING;
 			raw_spin_unlock_irq(&desc->lock);
 		} else {
 			raw_spin_unlock_irq(&desc->lock);
-
-			action->thread_fn(action->irq, action->dev_id);
-
-			if (oneshot)
-				irq_finalize_oneshot(action->irq, desc);
+			handler_fn(desc, action);
 		}
 
 		wake = atomic_dec_and_test(&desc->threads_active);
@@ -619,6 +789,9 @@ static int irq_thread(void *data)
 			wake_up(&desc->wait_for_threads);
 	}
 
+	/* Prevent a stale desc->threads_oneshot */
+	irq_finalize_oneshot(desc, action, true);
+
 	/*
 	 * Clear irqaction. Otherwise exit_irq_thread() would make
 	 * fuzz about an active irq thread going into nirvana.
@@ -633,6 +806,7 @@ static int irq_thread(void *data)
 void exit_irq_thread(void)
 {
 	struct task_struct *tsk = current;
+	struct irq_desc *desc;
 
 	if (!tsk->irqaction)
 		return;
@@ -641,6 +815,14 @@ void exit_irq_thread(void)
 	       "exiting task \"%s\" (%d) is an active IRQ thread (irq %d)\n",
 	       tsk->comm ? tsk->comm : "", tsk->pid, tsk->irqaction->irq);
 
+	desc = irq_to_desc(tsk->irqaction->irq);
+
+	/*
+	 * Prevent a stale desc->threads_oneshot. Must be called
+	 * before setting the IRQTF_DIED flag.
+	 */
+	irq_finalize_oneshot(desc, tsk->irqaction, true);
+
 	/*
 	 * Set the THREAD DIED flag to prevent further wakeups of the
 	 * soon to be gone threaded handler.
@@ -648,6 +830,22 @@ void exit_irq_thread(void)
 	set_bit(IRQTF_DIED, &tsk->irqaction->flags);
 }
 
+static void irq_setup_forced_threading(struct irqaction *new)
+{
+	if (!force_irqthreads)
+		return;
+	if (new->flags & (IRQF_NO_THREAD | IRQF_PERCPU | IRQF_ONESHOT))
+		return;
+
+	new->flags |= IRQF_ONESHOT;
+
+	if (!new->thread_fn) {
+		set_bit(IRQTF_FORCED_THREAD, &new->thread_flags);
+		new->thread_fn = new->handler;
+		new->handler = irq_default_primary_handler;
+	}
+}
+
 /*
  * Internal function to register an irqaction - typically used to
  * allocate special interrupts that are part of the architecture.
@@ -657,9 +855,9 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 {
 	struct irqaction *old, **old_ptr;
 	const char *old_name = NULL;
-	unsigned long flags;
-	int nested, shared = 0;
-	int ret;
+	unsigned long flags, thread_mask = 0;
+	int ret, nested, shared = 0;
+	cpumask_var_t mask;
 
 	if (!desc)
 		return -EINVAL;
@@ -683,15 +881,11 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 		rand_initialize_irq(irq);
 	}
 
-	/* Oneshot interrupts are not allowed with shared */
-	if ((new->flags & IRQF_ONESHOT) && (new->flags & IRQF_SHARED))
-		return -EINVAL;
-
 	/*
 	 * Check whether the interrupt nests into another interrupt
 	 * thread.
 	 */
-	nested = desc->status & IRQ_NESTED_THREAD;
+	nested = irq_settings_is_nested_thread(desc);
 	if (nested) {
 		if (!new->thread_fn)
 			return -EINVAL;
@@ -701,6 +895,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 		 * dummy function which warns when called.
 		 */
 		new->handler = irq_nested_primary_handler;
+	} else {
+		irq_setup_forced_threading(new);
 	}
 
 	/*
@@ -724,6 +920,11 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 		new->thread = t;
 	}
 
+	if (!alloc_cpumask_var(&mask, GFP_KERNEL)) {
+		ret = -ENOMEM;
+		goto out_thread;
+	}
+
 	/*
 	 * The following block of code has to be executed atomically
 	 */
@@ -735,29 +936,40 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 		 * Can't share interrupts unless both agree to and are
 		 * the same type (level, edge, polarity). So both flag
 		 * fields must have IRQF_SHARED set and the bits which
-		 * set the trigger type must match.
+		 * set the trigger type must match. Also all must
+		 * agree on ONESHOT.
 		 */
 		if (!((old->flags & new->flags) & IRQF_SHARED) ||
-		    ((old->flags ^ new->flags) & IRQF_TRIGGER_MASK)) {
+		    ((old->flags ^ new->flags) & IRQF_TRIGGER_MASK) ||
+		    ((old->flags ^ new->flags) & IRQF_ONESHOT)) {
 			old_name = old->name;
 			goto mismatch;
 		}
 
-#if defined(CONFIG_IRQ_PER_CPU)
 		/* All handlers must agree on per-cpuness */
 		if ((old->flags & IRQF_PERCPU) !=
 		    (new->flags & IRQF_PERCPU))
 			goto mismatch;
-#endif
 
 		/* add new interrupt at end of irq queue */
 		do {
+			thread_mask |= old->thread_mask;
 			old_ptr = &old->next;
 			old = *old_ptr;
 		} while (old);
 		shared = 1;
 	}
 
+	/*
+	 * Setup the thread mask for this irqaction. Unlikely to have
+	 * 32 resp 64 irqs sharing one line, but who knows.
+	 */
+	if (new->flags & IRQF_ONESHOT && thread_mask == ~0UL) {
+		ret = -EBUSY;
+		goto out_mask;
+	}
+	new->thread_mask = 1 << ffz(thread_mask);
+
 	if (!shared) {
 		irq_chip_set_defaults(desc->irq_data.chip);
 
@@ -769,42 +981,44 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 					new->flags & IRQF_TRIGGER_MASK);
 
 			if (ret)
-				goto out_thread;
-		} else
-			compat_irq_chip_set_default_handler(desc);
-#if defined(CONFIG_IRQ_PER_CPU)
-		if (new->flags & IRQF_PERCPU)
-			desc->status |= IRQ_PER_CPU;
-#endif
+				goto out_mask;
+		}
 
-		desc->status &= ~(IRQ_AUTODETECT | IRQ_WAITING | IRQ_ONESHOT |
-				  IRQ_INPROGRESS | IRQ_SPURIOUS_DISABLED);
+		desc->istate &= ~(IRQS_AUTODETECT | IRQS_SPURIOUS_DISABLED | \
+				  IRQS_INPROGRESS | IRQS_ONESHOT | \
+				  IRQS_WAITING);
+
+		if (new->flags & IRQF_PERCPU) {
+			irqd_set(&desc->irq_data, IRQD_PER_CPU);
+			irq_settings_set_per_cpu(desc);
+		}
 
 		if (new->flags & IRQF_ONESHOT)
-			desc->status |= IRQ_ONESHOT;
+			desc->istate |= IRQS_ONESHOT;
 
-		if (!(desc->status & IRQ_NOAUTOEN)) {
-			desc->depth = 0;
-			desc->status &= ~IRQ_DISABLED;
-			desc->irq_data.chip->irq_startup(&desc->irq_data);
-		} else
+		if (irq_settings_can_autoenable(desc))
+			irq_startup(desc);
+		else
 			/* Undo nested disables: */
 			desc->depth = 1;
 
 		/* Exclude IRQ from balancing if requested */
-		if (new->flags & IRQF_NOBALANCING)
-			desc->status |= IRQ_NO_BALANCING;
+		if (new->flags & IRQF_NOBALANCING) {
+			irq_settings_set_no_balancing(desc);
+			irqd_set(&desc->irq_data, IRQD_NO_BALANCING);
+		}
 
 		/* Set default affinity mask once everything is setup */
-		setup_affinity(irq, desc);
-
-	} else if ((new->flags & IRQF_TRIGGER_MASK)
-			&& (new->flags & IRQF_TRIGGER_MASK)
-				!= (desc->status & IRQ_TYPE_SENSE_MASK)) {
-		/* hope the handler works with the actual trigger mode... */
-		pr_warning("IRQ %d uses trigger mode %d; requested %d\n",
-				irq, (int)(desc->status & IRQ_TYPE_SENSE_MASK),
-				(int)(new->flags & IRQF_TRIGGER_MASK));
+		setup_affinity(irq, desc, mask);
+
+	} else if (new->flags & IRQF_TRIGGER_MASK) {
+		unsigned int nmsk = new->flags & IRQF_TRIGGER_MASK;
+		unsigned int omsk = irq_settings_get_trigger_mask(desc);
+
+		if (nmsk != omsk)
+			/* hope the handler works with current  trigger mode */
+			pr_warning("IRQ %d uses trigger mode %u; requested %u\n",
+				   irq, nmsk, omsk);
 	}
 
 	new->irq = irq;
@@ -818,8 +1032,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 	 * Check whether we disabled the irq via the spurious handler
 	 * before. Reenable it and give it another chance.
 	 */
-	if (shared && (desc->status & IRQ_SPURIOUS_DISABLED)) {
-		desc->status &= ~IRQ_SPURIOUS_DISABLED;
+	if (shared && (desc->istate & IRQS_SPURIOUS_DISABLED)) {
+		desc->istate &= ~IRQS_SPURIOUS_DISABLED;
 		__enable_irq(desc, irq, false);
 	}
 
@@ -849,6 +1063,9 @@ mismatch:
 #endif
 	ret = -EBUSY;
 
+out_mask:
+	free_cpumask_var(mask);
+
 out_thread:
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 	if (new->thread) {
@@ -871,9 +1088,14 @@ out_thread:
  */
 int setup_irq(unsigned int irq, struct irqaction *act)
 {
+	int retval;
 	struct irq_desc *desc = irq_to_desc(irq);
 
-	return __setup_irq(irq, desc, act);
+	chip_bus_lock(desc);
+	retval = __setup_irq(irq, desc, act);
+	chip_bus_sync_unlock(desc);
+
+	return retval;
 }
 EXPORT_SYMBOL_GPL(setup_irq);
 
@@ -924,13 +1146,8 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id)
 #endif
 
 	/* If this was the last handler, shut down the IRQ line: */
-	if (!desc->action) {
-		desc->status |= IRQ_DISABLED;
-		if (desc->irq_data.chip->irq_shutdown)
-			desc->irq_data.chip->irq_shutdown(&desc->irq_data);
-		else
-			desc->irq_data.chip->irq_disable(&desc->irq_data);
-	}
+	if (!desc->action)
+		irq_shutdown(desc);
 
 #ifdef CONFIG_SMP
 	/* make sure affinity_hint is cleaned up */
@@ -1004,6 +1221,11 @@ void free_irq(unsigned int irq, void *dev_id)
 	if (!desc)
 		return;
 
+#ifdef CONFIG_SMP
+	if (WARN_ON(desc->affinity_notify))
+		desc->affinity_notify = NULL;
+#endif
+
 	chip_bus_lock(desc);
 	kfree(__free_irq(irq, dev_id));
 	chip_bus_sync_unlock(desc);
@@ -1074,7 +1296,7 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler,
 	if (!desc)
 		return -EINVAL;
 
-	if (desc->status & IRQ_NOREQUEST)
+	if (!irq_settings_can_request(desc))
 		return -EINVAL;
 
 	if (!handler) {
@@ -1149,7 +1371,7 @@ int request_any_context_irq(unsigned int irq, irq_handler_t handler,
 	if (!desc)
 		return -EINVAL;
 
-	if (desc->status & IRQ_NESTED_THREAD) {
+	if (irq_settings_is_nested_thread(desc)) {
 		ret = request_threaded_irq(irq, NULL, handler,
 					   flags, name, dev_id);
 		return !ret ? IRQC_IS_NESTED : ret;
diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c
index 441fd629ff04..ec4806d4778b 100644
--- a/kernel/irq/migration.c
+++ b/kernel/irq/migration.c
@@ -4,23 +4,23 @@
 
 #include "internals.h"
 
-void move_masked_irq(int irq)
+void irq_move_masked_irq(struct irq_data *idata)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
-	struct irq_chip *chip = desc->irq_data.chip;
+	struct irq_desc *desc = irq_data_to_desc(idata);
+	struct irq_chip *chip = idata->chip;
 
-	if (likely(!(desc->status & IRQ_MOVE_PENDING)))
+	if (likely(!irqd_is_setaffinity_pending(&desc->irq_data)))
 		return;
 
 	/*
 	 * Paranoia: cpu-local interrupts shouldn't be calling in here anyway.
 	 */
-	if (CHECK_IRQ_PER_CPU(desc->status)) {
+	if (!irqd_can_balance(&desc->irq_data)) {
 		WARN_ON(1);
 		return;
 	}
 
-	desc->status &= ~IRQ_MOVE_PENDING;
+	irqd_clr_move_pending(&desc->irq_data);
 
 	if (unlikely(cpumask_empty(desc->pending_mask)))
 		return;
@@ -53,15 +53,20 @@ void move_masked_irq(int irq)
 	cpumask_clear(desc->pending_mask);
 }
 
-void move_native_irq(int irq)
+void move_masked_irq(int irq)
+{
+	irq_move_masked_irq(irq_get_irq_data(irq));
+}
+
+void irq_move_irq(struct irq_data *idata)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
+	struct irq_desc *desc = irq_data_to_desc(idata);
 	bool masked;
 
-	if (likely(!(desc->status & IRQ_MOVE_PENDING)))
+	if (likely(!irqd_is_setaffinity_pending(idata)))
 		return;
 
-	if (unlikely(desc->status & IRQ_DISABLED))
+	if (unlikely(desc->istate & IRQS_DISABLED))
 		return;
 
 	/*
@@ -69,10 +74,15 @@ void move_native_irq(int irq)
 	 * threaded interrupt with ONESHOT set, we can end up with an
 	 * interrupt storm.
 	 */
-	masked = desc->status & IRQ_MASKED;
+	masked = desc->istate & IRQS_MASKED;
 	if (!masked)
-		desc->irq_data.chip->irq_mask(&desc->irq_data);
-	move_masked_irq(irq);
+		idata->chip->irq_mask(idata);
+	irq_move_masked_irq(idata);
 	if (!masked)
-		desc->irq_data.chip->irq_unmask(&desc->irq_data);
+		idata->chip->irq_unmask(idata);
+}
+
+void move_native_irq(int irq)
+{
+	irq_move_irq(irq_get_irq_data(irq));
 }
diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c
index 0d4005d85b03..f76fc00c9877 100644
--- a/kernel/irq/pm.c
+++ b/kernel/irq/pm.c
@@ -18,7 +18,7 @@
  * During system-wide suspend or hibernation device drivers need to be prevented
  * from receiving interrupts and this function is provided for this purpose.
  * It marks all interrupt lines in use, except for the timer ones, as disabled
- * and sets the IRQ_SUSPENDED flag for each of them.
+ * and sets the IRQS_SUSPENDED flag for each of them.
  */
 void suspend_device_irqs(void)
 {
@@ -34,7 +34,7 @@ void suspend_device_irqs(void)
 	}
 
 	for_each_irq_desc(irq, desc)
-		if (desc->status & IRQ_SUSPENDED)
+		if (desc->istate & IRQS_SUSPENDED)
 			synchronize_irq(irq);
 }
 EXPORT_SYMBOL_GPL(suspend_device_irqs);
@@ -43,7 +43,7 @@ EXPORT_SYMBOL_GPL(suspend_device_irqs);
  * resume_device_irqs - enable interrupt lines disabled by suspend_device_irqs()
  *
  * Enable all interrupt lines previously disabled by suspend_device_irqs() that
- * have the IRQ_SUSPENDED flag set.
+ * have the IRQS_SUSPENDED flag set.
  */
 void resume_device_irqs(void)
 {
@@ -53,9 +53,6 @@ void resume_device_irqs(void)
 	for_each_irq_desc(irq, desc) {
 		unsigned long flags;
 
-		if (!(desc->status & IRQ_SUSPENDED))
-			continue;
-
 		raw_spin_lock_irqsave(&desc->lock, flags);
 		__enable_irq(desc, irq, true);
 		raw_spin_unlock_irqrestore(&desc->lock, flags);
@@ -71,9 +68,24 @@ int check_wakeup_irqs(void)
 	struct irq_desc *desc;
 	int irq;
 
-	for_each_irq_desc(irq, desc)
-		if ((desc->status & IRQ_WAKEUP) && (desc->status & IRQ_PENDING))
-			return -EBUSY;
+	for_each_irq_desc(irq, desc) {
+		if (irqd_is_wakeup_set(&desc->irq_data)) {
+			if (desc->istate & IRQS_PENDING)
+				return -EBUSY;
+			continue;
+		}
+		/*
+		 * Check the non wakeup interrupts whether they need
+		 * to be masked before finally going into suspend
+		 * state. That's for hardware which has no wakeup
+		 * source configuration facility. The chip
+		 * implementation indicates that with
+		 * IRQCHIP_MASK_ON_SUSPEND.
+		 */
+		if (desc->istate & IRQS_SUSPENDED &&
+		    irq_desc_get_chip(desc)->flags & IRQCHIP_MASK_ON_SUSPEND)
+			mask_irq(desc);
+	}
 
 	return 0;
 }
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 6c8a2a9f8a7b..4cc2e5ed0bec 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -11,6 +11,7 @@
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/interrupt.h>
+#include <linux/kernel_stat.h>
 
 #include "internals.h"
 
@@ -24,7 +25,7 @@ static int irq_affinity_proc_show(struct seq_file *m, void *v)
 	const struct cpumask *mask = desc->irq_data.affinity;
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
-	if (desc->status & IRQ_MOVE_PENDING)
+	if (irqd_is_setaffinity_pending(&desc->irq_data))
 		mask = desc->pending_mask;
 #endif
 	seq_cpumask(m, mask);
@@ -65,8 +66,7 @@ static ssize_t irq_affinity_proc_write(struct file *file,
 	cpumask_var_t new_value;
 	int err;
 
-	if (!irq_to_desc(irq)->irq_data.chip->irq_set_affinity || no_irq_affinity ||
-	    irq_balancing_disabled(irq))
+	if (!irq_can_set_affinity(irq) || no_irq_affinity)
 		return -EIO;
 
 	if (!alloc_cpumask_var(&new_value, GFP_KERNEL))
@@ -89,7 +89,7 @@ static ssize_t irq_affinity_proc_write(struct file *file,
 	if (!cpumask_intersects(new_value, cpu_online_mask)) {
 		/* Special case for empty set - allow the architecture
 		   code to set default SMP affinity. */
-		err = irq_select_affinity_usr(irq) ? -EINVAL : count;
+		err = irq_select_affinity_usr(irq, new_value) ? -EINVAL : count;
 	} else {
 		irq_set_affinity(irq, new_value);
 		err = count;
@@ -357,3 +357,65 @@ void init_irq_proc(void)
 	}
 }
 
+#ifdef CONFIG_GENERIC_IRQ_SHOW
+
+int __weak arch_show_interrupts(struct seq_file *p, int prec)
+{
+	return 0;
+}
+
+int show_interrupts(struct seq_file *p, void *v)
+{
+	static int prec;
+
+	unsigned long flags, any_count = 0;
+	int i = *(loff_t *) v, j;
+	struct irqaction *action;
+	struct irq_desc *desc;
+
+	if (i > nr_irqs)
+		return 0;
+
+	if (i == nr_irqs)
+		return arch_show_interrupts(p, prec);
+
+	/* print header and calculate the width of the first column */
+	if (i == 0) {
+		for (prec = 3, j = 1000; prec < 10 && j <= nr_irqs; ++prec)
+			j *= 10;
+
+		seq_printf(p, "%*s", prec + 8, "");
+		for_each_online_cpu(j)
+			seq_printf(p, "CPU%-8d", j);
+		seq_putc(p, '\n');
+	}
+
+	desc = irq_to_desc(i);
+	if (!desc)
+		return 0;
+
+	raw_spin_lock_irqsave(&desc->lock, flags);
+	for_each_online_cpu(j)
+		any_count |= kstat_irqs_cpu(i, j);
+	action = desc->action;
+	if (!action && !any_count)
+		goto out;
+
+	seq_printf(p, "%*d: ", prec, i);
+	for_each_online_cpu(j)
+		seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
+	seq_printf(p, " %8s", desc->irq_data.chip->name);
+	seq_printf(p, "-%-8s", desc->name);
+
+	if (action) {
+		seq_printf(p, "  %s", action->name);
+		while ((action = action->next) != NULL)
+			seq_printf(p, ", %s", action->name);
+	}
+
+	seq_putc(p, '\n');
+out:
+	raw_spin_unlock_irqrestore(&desc->lock, flags);
+	return 0;
+}
+#endif
diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c
index dc49358b73fa..ad683a99b1ec 100644
--- a/kernel/irq/resend.c
+++ b/kernel/irq/resend.c
@@ -55,20 +55,19 @@ static DECLARE_TASKLET(resend_tasklet, resend_irqs, 0);
  */
 void check_irq_resend(struct irq_desc *desc, unsigned int irq)
 {
-	unsigned int status = desc->status;
-
-	/*
-	 * Make sure the interrupt is enabled, before resending it:
-	 */
-	desc->irq_data.chip->irq_enable(&desc->irq_data);
-
 	/*
 	 * We do not resend level type interrupts. Level type
 	 * interrupts are resent by hardware when they are still
 	 * active.
 	 */
-	if ((status & (IRQ_LEVEL | IRQ_PENDING | IRQ_REPLAY)) == IRQ_PENDING) {
-		desc->status = (status & ~IRQ_PENDING) | IRQ_REPLAY;
+	if (irq_settings_is_level(desc))
+		return;
+	if (desc->istate & IRQS_REPLAY)
+		return;
+	if (desc->istate & IRQS_PENDING) {
+		irq_compat_clr_pending(desc);
+		desc->istate &= ~IRQS_PENDING;
+		desc->istate |= IRQS_REPLAY;
 
 		if (!desc->irq_data.chip->irq_retrigger ||
 		    !desc->irq_data.chip->irq_retrigger(&desc->irq_data)) {
diff --git a/kernel/irq/settings.h b/kernel/irq/settings.h
new file mode 100644
index 000000000000..0227ad358272
--- /dev/null
+++ b/kernel/irq/settings.h
@@ -0,0 +1,138 @@
+/*
+ * Internal header to deal with irq_desc->status which will be renamed
+ * to irq_desc->settings.
+ */
+enum {
+	_IRQ_DEFAULT_INIT_FLAGS	= IRQ_DEFAULT_INIT_FLAGS,
+	_IRQ_PER_CPU		= IRQ_PER_CPU,
+	_IRQ_LEVEL		= IRQ_LEVEL,
+	_IRQ_NOPROBE		= IRQ_NOPROBE,
+	_IRQ_NOREQUEST		= IRQ_NOREQUEST,
+	_IRQ_NOAUTOEN		= IRQ_NOAUTOEN,
+	_IRQ_MOVE_PCNTXT	= IRQ_MOVE_PCNTXT,
+	_IRQ_NO_BALANCING	= IRQ_NO_BALANCING,
+	_IRQ_NESTED_THREAD	= IRQ_NESTED_THREAD,
+	_IRQF_MODIFY_MASK	= IRQF_MODIFY_MASK,
+};
+
+#define IRQ_INPROGRESS		GOT_YOU_MORON
+#define IRQ_REPLAY		GOT_YOU_MORON
+#define IRQ_WAITING		GOT_YOU_MORON
+#define IRQ_DISABLED		GOT_YOU_MORON
+#define IRQ_PENDING		GOT_YOU_MORON
+#define IRQ_MASKED		GOT_YOU_MORON
+#define IRQ_WAKEUP		GOT_YOU_MORON
+#define IRQ_MOVE_PENDING	GOT_YOU_MORON
+#define IRQ_PER_CPU		GOT_YOU_MORON
+#define IRQ_NO_BALANCING	GOT_YOU_MORON
+#define IRQ_AFFINITY_SET	GOT_YOU_MORON
+#define IRQ_LEVEL		GOT_YOU_MORON
+#define IRQ_NOPROBE		GOT_YOU_MORON
+#define IRQ_NOREQUEST		GOT_YOU_MORON
+#define IRQ_NOAUTOEN		GOT_YOU_MORON
+#define IRQ_NESTED_THREAD	GOT_YOU_MORON
+#undef IRQF_MODIFY_MASK
+#define IRQF_MODIFY_MASK	GOT_YOU_MORON
+
+static inline void
+irq_settings_clr_and_set(struct irq_desc *desc, u32 clr, u32 set)
+{
+	desc->status &= ~(clr & _IRQF_MODIFY_MASK);
+	desc->status |= (set & _IRQF_MODIFY_MASK);
+}
+
+static inline bool irq_settings_is_per_cpu(struct irq_desc *desc)
+{
+	return desc->status & _IRQ_PER_CPU;
+}
+
+static inline void irq_settings_set_per_cpu(struct irq_desc *desc)
+{
+	desc->status |= _IRQ_PER_CPU;
+}
+
+static inline void irq_settings_set_no_balancing(struct irq_desc *desc)
+{
+	desc->status |= _IRQ_NO_BALANCING;
+}
+
+static inline bool irq_settings_has_no_balance_set(struct irq_desc *desc)
+{
+	return desc->status & _IRQ_NO_BALANCING;
+}
+
+static inline u32 irq_settings_get_trigger_mask(struct irq_desc *desc)
+{
+	return desc->status & IRQ_TYPE_SENSE_MASK;
+}
+
+static inline void
+irq_settings_set_trigger_mask(struct irq_desc *desc, u32 mask)
+{
+	desc->status &= ~IRQ_TYPE_SENSE_MASK;
+	desc->status |= mask & IRQ_TYPE_SENSE_MASK;
+}
+
+static inline bool irq_settings_is_level(struct irq_desc *desc)
+{
+	return desc->status & _IRQ_LEVEL;
+}
+
+static inline void irq_settings_clr_level(struct irq_desc *desc)
+{
+	desc->status &= ~_IRQ_LEVEL;
+}
+
+static inline void irq_settings_set_level(struct irq_desc *desc)
+{
+	desc->status |= _IRQ_LEVEL;
+}
+
+static inline bool irq_settings_can_request(struct irq_desc *desc)
+{
+	return !(desc->status & _IRQ_NOREQUEST);
+}
+
+static inline void irq_settings_clr_norequest(struct irq_desc *desc)
+{
+	desc->status &= ~_IRQ_NOREQUEST;
+}
+
+static inline void irq_settings_set_norequest(struct irq_desc *desc)
+{
+	desc->status |= _IRQ_NOREQUEST;
+}
+
+static inline bool irq_settings_can_probe(struct irq_desc *desc)
+{
+	return !(desc->status & _IRQ_NOPROBE);
+}
+
+static inline void irq_settings_clr_noprobe(struct irq_desc *desc)
+{
+	desc->status &= ~_IRQ_NOPROBE;
+}
+
+static inline void irq_settings_set_noprobe(struct irq_desc *desc)
+{
+	desc->status |= _IRQ_NOPROBE;
+}
+
+static inline bool irq_settings_can_move_pcntxt(struct irq_desc *desc)
+{
+	return desc->status & _IRQ_MOVE_PCNTXT;
+}
+
+static inline bool irq_settings_can_autoenable(struct irq_desc *desc)
+{
+	return !(desc->status & _IRQ_NOAUTOEN);
+}
+
+static inline bool irq_settings_is_nested_thread(struct irq_desc *desc)
+{
+	return desc->status & _IRQ_NESTED_THREAD;
+}
+
+/* Nothing should touch desc->status from now on */
+#undef status
+#define status		USE_THE_PROPER_WRAPPERS_YOU_MORON
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index 3089d3b9d5f3..dd586ebf9c8c 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -21,70 +21,94 @@ static int irqfixup __read_mostly;
 #define POLL_SPURIOUS_IRQ_INTERVAL (HZ/10)
 static void poll_spurious_irqs(unsigned long dummy);
 static DEFINE_TIMER(poll_spurious_irq_timer, poll_spurious_irqs, 0, 0);
+static int irq_poll_cpu;
+static atomic_t irq_poll_active;
+
+/*
+ * We wait here for a poller to finish.
+ *
+ * If the poll runs on this CPU, then we yell loudly and return
+ * false. That will leave the interrupt line disabled in the worst
+ * case, but it should never happen.
+ *
+ * We wait until the poller is done and then recheck disabled and
+ * action (about to be disabled). Only if it's still active, we return
+ * true and let the handler run.
+ */
+bool irq_wait_for_poll(struct irq_desc *desc)
+{
+	if (WARN_ONCE(irq_poll_cpu == smp_processor_id(),
+		      "irq poll in progress on cpu %d for irq %d\n",
+		      smp_processor_id(), desc->irq_data.irq))
+		return false;
+
+#ifdef CONFIG_SMP
+	do {
+		raw_spin_unlock(&desc->lock);
+		while (desc->istate & IRQS_INPROGRESS)
+			cpu_relax();
+		raw_spin_lock(&desc->lock);
+	} while (desc->istate & IRQS_INPROGRESS);
+	/* Might have been disabled in meantime */
+	return !(desc->istate & IRQS_DISABLED) && desc->action;
+#else
+	return false;
+#endif
+}
+
 
 /*
  * Recovery handler for misrouted interrupts.
  */
-static int try_one_irq(int irq, struct irq_desc *desc)
+static int try_one_irq(int irq, struct irq_desc *desc, bool force)
 {
+	irqreturn_t ret = IRQ_NONE;
 	struct irqaction *action;
-	int ok = 0, work = 0;
 
 	raw_spin_lock(&desc->lock);
-	/* Already running on another processor */
-	if (desc->status & IRQ_INPROGRESS) {
-		/*
-		 * Already running: If it is shared get the other
-		 * CPU to go looking for our mystery interrupt too
-		 */
-		if (desc->action && (desc->action->flags & IRQF_SHARED))
-			desc->status |= IRQ_PENDING;
-		raw_spin_unlock(&desc->lock);
-		return ok;
-	}
-	/* Honour the normal IRQ locking */
-	desc->status |= IRQ_INPROGRESS;
-	action = desc->action;
-	raw_spin_unlock(&desc->lock);
 
-	while (action) {
-		/* Only shared IRQ handlers are safe to call */
-		if (action->flags & IRQF_SHARED) {
-			if (action->handler(irq, action->dev_id) ==
-				IRQ_HANDLED)
-				ok = 1;
-		}
-		action = action->next;
-	}
-	local_irq_disable();
-	/* Now clean up the flags */
-	raw_spin_lock(&desc->lock);
-	action = desc->action;
+	/* PER_CPU and nested thread interrupts are never polled */
+	if (irq_settings_is_per_cpu(desc) || irq_settings_is_nested_thread(desc))
+		goto out;
 
 	/*
-	 * While we were looking for a fixup someone queued a real
-	 * IRQ clashing with our walk:
+	 * Do not poll disabled interrupts unless the spurious
+	 * disabled poller asks explicitely.
 	 */
-	while ((desc->status & IRQ_PENDING) && action) {
+	if ((desc->istate & IRQS_DISABLED) && !force)
+		goto out;
+
+	/*
+	 * All handlers must agree on IRQF_SHARED, so we test just the
+	 * first. Check for action->next as well.
+	 */
+	action = desc->action;
+	if (!action || !(action->flags & IRQF_SHARED) ||
+	    (action->flags & __IRQF_TIMER) || !action->next)
+		goto out;
+
+	/* Already running on another processor */
+	if (desc->istate & IRQS_INPROGRESS) {
 		/*
-		 * Perform real IRQ processing for the IRQ we deferred
+		 * Already running: If it is shared get the other
+		 * CPU to go looking for our mystery interrupt too
 		 */
-		work = 1;
-		raw_spin_unlock(&desc->lock);
-		handle_IRQ_event(irq, action);
-		raw_spin_lock(&desc->lock);
-		desc->status &= ~IRQ_PENDING;
+		irq_compat_set_pending(desc);
+		desc->istate |= IRQS_PENDING;
+		goto out;
 	}
-	desc->status &= ~IRQ_INPROGRESS;
-	/*
-	 * If we did actual work for the real IRQ line we must let the
-	 * IRQ controller clean up too
-	 */
-	if (work)
-		irq_end(irq, desc);
-	raw_spin_unlock(&desc->lock);
 
-	return ok;
+	/* Mark it poll in progress */
+	desc->istate |= IRQS_POLL_INPROGRESS;
+	do {
+		if (handle_irq_event(desc) == IRQ_HANDLED)
+			ret = IRQ_HANDLED;
+		action = desc->action;
+	} while ((desc->istate & IRQS_PENDING) && action);
+	desc->istate &= ~IRQS_POLL_INPROGRESS;
+out:
+	raw_spin_unlock(&desc->lock);
+	return ret == IRQ_HANDLED;
 }
 
 static int misrouted_irq(int irq)
@@ -92,6 +116,11 @@ static int misrouted_irq(int irq)
 	struct irq_desc *desc;
 	int i, ok = 0;
 
+	if (atomic_inc_return(&irq_poll_active) == 1)
+		goto out;
+
+	irq_poll_cpu = smp_processor_id();
+
 	for_each_irq_desc(i, desc) {
 		if (!i)
 			 continue;
@@ -99,9 +128,11 @@ static int misrouted_irq(int irq)
 		if (i == irq)	/* Already tried */
 			continue;
 
-		if (try_one_irq(i, desc))
+		if (try_one_irq(i, desc, false))
 			ok = 1;
 	}
+out:
+	atomic_dec(&irq_poll_active);
 	/* So the caller can adjust the irq error counts */
 	return ok;
 }
@@ -111,23 +142,28 @@ static void poll_spurious_irqs(unsigned long dummy)
 	struct irq_desc *desc;
 	int i;
 
+	if (atomic_inc_return(&irq_poll_active) != 1)
+		goto out;
+	irq_poll_cpu = smp_processor_id();
+
 	for_each_irq_desc(i, desc) {
-		unsigned int status;
+		unsigned int state;
 
 		if (!i)
 			 continue;
 
 		/* Racy but it doesn't matter */
-		status = desc->status;
+		state = desc->istate;
 		barrier();
-		if (!(status & IRQ_SPURIOUS_DISABLED))
+		if (!(state & IRQS_SPURIOUS_DISABLED))
 			continue;
 
 		local_irq_disable();
-		try_one_irq(i, desc);
+		try_one_irq(i, desc, true);
 		local_irq_enable();
 	}
-
+out:
+	atomic_dec(&irq_poll_active);
 	mod_timer(&poll_spurious_irq_timer,
 		  jiffies + POLL_SPURIOUS_IRQ_INTERVAL);
 }
@@ -139,15 +175,13 @@ static void poll_spurious_irqs(unsigned long dummy)
  *
  * (The other 100-of-100,000 interrupts may have been a correctly
  *  functioning device sharing an IRQ with the failing one)
- *
- * Called under desc->lock
  */
-
 static void
 __report_bad_irq(unsigned int irq, struct irq_desc *desc,
 		 irqreturn_t action_ret)
 {
 	struct irqaction *action;
+	unsigned long flags;
 
 	if (action_ret != IRQ_HANDLED && action_ret != IRQ_NONE) {
 		printk(KERN_ERR "irq event %d: bogus return value %x\n",
@@ -159,6 +193,13 @@ __report_bad_irq(unsigned int irq, struct irq_desc *desc,
 	dump_stack();
 	printk(KERN_ERR "handlers:\n");
 
+	/*
+	 * We need to take desc->lock here. note_interrupt() is called
+	 * w/o desc->lock held, but IRQ_PROGRESS set. We might race
+	 * with something else removing an action. It's ok to take
+	 * desc->lock here. See synchronize_irq().
+	 */
+	raw_spin_lock_irqsave(&desc->lock, flags);
 	action = desc->action;
 	while (action) {
 		printk(KERN_ERR "[<%p>]", action->handler);
@@ -167,6 +208,7 @@ __report_bad_irq(unsigned int irq, struct irq_desc *desc,
 		printk("\n");
 		action = action->next;
 	}
+	raw_spin_unlock_irqrestore(&desc->lock, flags);
 }
 
 static void
@@ -218,6 +260,9 @@ try_misrouted_irq(unsigned int irq, struct irq_desc *desc,
 void note_interrupt(unsigned int irq, struct irq_desc *desc,
 		    irqreturn_t action_ret)
 {
+	if (desc->istate & IRQS_POLL_INPROGRESS)
+		return;
+
 	if (unlikely(action_ret != IRQ_HANDLED)) {
 		/*
 		 * If we are seeing only the odd spurious IRQ caused by
@@ -254,9 +299,9 @@ void note_interrupt(unsigned int irq, struct irq_desc *desc,
 		 * Now kill the IRQ
 		 */
 		printk(KERN_EMERG "Disabling IRQ #%d\n", irq);
-		desc->status |= IRQ_DISABLED | IRQ_SPURIOUS_DISABLED;
+		desc->istate |= IRQS_SPURIOUS_DISABLED;
 		desc->depth++;
-		desc->irq_data.chip->irq_disable(&desc->irq_data);
+		irq_disable(desc);
 
 		mod_timer(&poll_spurious_irq_timer,
 			  jiffies + POLL_SPURIOUS_IRQ_INTERVAL);
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 656222fcf767..ed253aa24ba4 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -38,13 +38,96 @@
 
 #include <asm/irq_regs.h>
 
+struct remote_function_call {
+	struct task_struct *p;
+	int (*func)(void *info);
+	void *info;
+	int ret;
+};
+
+static void remote_function(void *data)
+{
+	struct remote_function_call *tfc = data;
+	struct task_struct *p = tfc->p;
+
+	if (p) {
+		tfc->ret = -EAGAIN;
+		if (task_cpu(p) != smp_processor_id() || !task_curr(p))
+			return;
+	}
+
+	tfc->ret = tfc->func(tfc->info);
+}
+
+/**
+ * task_function_call - call a function on the cpu on which a task runs
+ * @p:		the task to evaluate
+ * @func:	the function to be called
+ * @info:	the function call argument
+ *
+ * Calls the function @func when the task is currently running. This might
+ * be on the current CPU, which just calls the function directly
+ *
+ * returns: @func return value, or
+ *	    -ESRCH  - when the process isn't running
+ *	    -EAGAIN - when the process moved away
+ */
+static int
+task_function_call(struct task_struct *p, int (*func) (void *info), void *info)
+{
+	struct remote_function_call data = {
+		.p = p,
+		.func = func,
+		.info = info,
+		.ret = -ESRCH, /* No such (running) process */
+	};
+
+	if (task_curr(p))
+		smp_call_function_single(task_cpu(p), remote_function, &data, 1);
+
+	return data.ret;
+}
+
+/**
+ * cpu_function_call - call a function on the cpu
+ * @func:	the function to be called
+ * @info:	the function call argument
+ *
+ * Calls the function @func on the remote cpu.
+ *
+ * returns: @func return value or -ENXIO when the cpu is offline
+ */
+static int cpu_function_call(int cpu, int (*func) (void *info), void *info)
+{
+	struct remote_function_call data = {
+		.p = NULL,
+		.func = func,
+		.info = info,
+		.ret = -ENXIO, /* No such CPU */
+	};
+
+	smp_call_function_single(cpu, remote_function, &data, 1);
+
+	return data.ret;
+}
+
+#define PERF_FLAG_ALL (PERF_FLAG_FD_NO_GROUP |\
+		       PERF_FLAG_FD_OUTPUT  |\
+		       PERF_FLAG_PID_CGROUP)
+
 enum event_type_t {
 	EVENT_FLEXIBLE = 0x1,
 	EVENT_PINNED = 0x2,
 	EVENT_ALL = EVENT_FLEXIBLE | EVENT_PINNED,
 };
 
-atomic_t perf_task_events __read_mostly;
+/*
+ * perf_sched_events : >0 events exist
+ * perf_cgroup_events: >0 per-cpu cgroup events exist on this cpu
+ */
+atomic_t perf_sched_events __read_mostly;
+static DEFINE_PER_CPU(atomic_t, perf_cgroup_events);
+
 static atomic_t nr_mmap_events __read_mostly;
 static atomic_t nr_comm_events __read_mostly;
 static atomic_t nr_task_events __read_mostly;
@@ -67,7 +150,24 @@ int sysctl_perf_event_mlock __read_mostly = 512; /* 'free' kb per user */
 /*
  * max perf event sample rate
  */
-int sysctl_perf_event_sample_rate __read_mostly = 100000;
+#define DEFAULT_MAX_SAMPLE_RATE 100000
+int sysctl_perf_event_sample_rate __read_mostly = DEFAULT_MAX_SAMPLE_RATE;
+static int max_samples_per_tick __read_mostly =
+	DIV_ROUND_UP(DEFAULT_MAX_SAMPLE_RATE, HZ);
+
+int perf_proc_update_handler(struct ctl_table *table, int write,
+		void __user *buffer, size_t *lenp,
+		loff_t *ppos)
+{
+	int ret = proc_dointvec(table, write, buffer, lenp, ppos);
+
+	if (ret || !write)
+		return ret;
+
+	max_samples_per_tick = DIV_ROUND_UP(sysctl_perf_event_sample_rate, HZ);
+
+	return 0;
+}
 
 static atomic64_t perf_event_id;
 
@@ -75,7 +175,11 @@ static void cpu_ctx_sched_out(struct perf_cpu_context *cpuctx,
 			      enum event_type_t event_type);
 
 static void cpu_ctx_sched_in(struct perf_cpu_context *cpuctx,
-			     enum event_type_t event_type);
+			     enum event_type_t event_type,
+			     struct task_struct *task);
+
+static void update_context_time(struct perf_event_context *ctx);
+static u64 perf_event_time(struct perf_event *event);
 
 void __weak perf_event_print_debug(void)	{ }
 
@@ -89,6 +193,360 @@ static inline u64 perf_clock(void)
 	return local_clock();
 }
 
+static inline struct perf_cpu_context *
+__get_cpu_context(struct perf_event_context *ctx)
+{
+	return this_cpu_ptr(ctx->pmu->pmu_cpu_context);
+}
+
+#ifdef CONFIG_CGROUP_PERF
+
+/*
+ * Must ensure cgroup is pinned (css_get) before calling
+ * this function. In other words, we cannot call this function
+ * if there is no cgroup event for the current CPU context.
+ */
+static inline struct perf_cgroup *
+perf_cgroup_from_task(struct task_struct *task)
+{
+	return container_of(task_subsys_state(task, perf_subsys_id),
+			struct perf_cgroup, css);
+}
+
+static inline bool
+perf_cgroup_match(struct perf_event *event)
+{
+	struct perf_event_context *ctx = event->ctx;
+	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
+
+	return !event->cgrp || event->cgrp == cpuctx->cgrp;
+}
+
+static inline void perf_get_cgroup(struct perf_event *event)
+{
+	css_get(&event->cgrp->css);
+}
+
+static inline void perf_put_cgroup(struct perf_event *event)
+{
+	css_put(&event->cgrp->css);
+}
+
+static inline void perf_detach_cgroup(struct perf_event *event)
+{
+	perf_put_cgroup(event);
+	event->cgrp = NULL;
+}
+
+static inline int is_cgroup_event(struct perf_event *event)
+{
+	return event->cgrp != NULL;
+}
+
+static inline u64 perf_cgroup_event_time(struct perf_event *event)
+{
+	struct perf_cgroup_info *t;
+
+	t = per_cpu_ptr(event->cgrp->info, event->cpu);
+	return t->time;
+}
+
+static inline void __update_cgrp_time(struct perf_cgroup *cgrp)
+{
+	struct perf_cgroup_info *info;
+	u64 now;
+
+	now = perf_clock();
+
+	info = this_cpu_ptr(cgrp->info);
+
+	info->time += now - info->timestamp;
+	info->timestamp = now;
+}
+
+static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx)
+{
+	struct perf_cgroup *cgrp_out = cpuctx->cgrp;
+	if (cgrp_out)
+		__update_cgrp_time(cgrp_out);
+}
+
+static inline void update_cgrp_time_from_event(struct perf_event *event)
+{
+	struct perf_cgroup *cgrp;
+
+	/*
+	 * ensure we access cgroup data only when needed and
+	 * when we know the cgroup is pinned (css_get)
+	 */
+	if (!is_cgroup_event(event))
+		return;
+
+	cgrp = perf_cgroup_from_task(current);
+	/*
+	 * Do not update time when cgroup is not active
+	 */
+	if (cgrp == event->cgrp)
+		__update_cgrp_time(event->cgrp);
+}
+
+static inline void
+perf_cgroup_set_timestamp(struct task_struct *task,
+			  struct perf_event_context *ctx)
+{
+	struct perf_cgroup *cgrp;
+	struct perf_cgroup_info *info;
+
+	/*
+	 * ctx->lock held by caller
+	 * ensure we do not access cgroup data
+	 * unless we have the cgroup pinned (css_get)
+	 */
+	if (!task || !ctx->nr_cgroups)
+		return;
+
+	cgrp = perf_cgroup_from_task(task);
+	info = this_cpu_ptr(cgrp->info);
+	info->timestamp = ctx->timestamp;
+}
+
+#define PERF_CGROUP_SWOUT	0x1 /* cgroup switch out every event */
+#define PERF_CGROUP_SWIN	0x2 /* cgroup switch in events based on task */
+
+/*
+ * reschedule events based on the cgroup constraint of task.
+ *
+ * mode SWOUT : schedule out everything
+ * mode SWIN : schedule in based on cgroup for next
+ */
+void perf_cgroup_switch(struct task_struct *task, int mode)
+{
+	struct perf_cpu_context *cpuctx;
+	struct pmu *pmu;
+	unsigned long flags;
+
+	/*
+	 * disable interrupts to avoid geting nr_cgroup
+	 * changes via __perf_event_disable(). Also
+	 * avoids preemption.
+	 */
+	local_irq_save(flags);
+
+	/*
+	 * we reschedule only in the presence of cgroup
+	 * constrained events.
+	 */
+	rcu_read_lock();
+
+	list_for_each_entry_rcu(pmu, &pmus, entry) {
+
+		cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
+
+		perf_pmu_disable(cpuctx->ctx.pmu);
+
+		/*
+		 * perf_cgroup_events says at least one
+		 * context on this CPU has cgroup events.
+		 *
+		 * ctx->nr_cgroups reports the number of cgroup
+		 * events for a context.
+		 */
+		if (cpuctx->ctx.nr_cgroups > 0) {
+
+			if (mode & PERF_CGROUP_SWOUT) {
+				cpu_ctx_sched_out(cpuctx, EVENT_ALL);
+				/*
+				 * must not be done before ctxswout due
+				 * to event_filter_match() in event_sched_out()
+				 */
+				cpuctx->cgrp = NULL;
+			}
+
+			if (mode & PERF_CGROUP_SWIN) {
+				/* set cgrp before ctxsw in to
+				 * allow event_filter_match() to not
+				 * have to pass task around
+				 */
+				cpuctx->cgrp = perf_cgroup_from_task(task);
+				cpu_ctx_sched_in(cpuctx, EVENT_ALL, task);
+			}
+		}
+
+		perf_pmu_enable(cpuctx->ctx.pmu);
+	}
+
+	rcu_read_unlock();
+
+	local_irq_restore(flags);
+}
+
+static inline void perf_cgroup_sched_out(struct task_struct *task)
+{
+	perf_cgroup_switch(task, PERF_CGROUP_SWOUT);
+}
+
+static inline void perf_cgroup_sched_in(struct task_struct *task)
+{
+	perf_cgroup_switch(task, PERF_CGROUP_SWIN);
+}
+
+static inline int perf_cgroup_connect(int fd, struct perf_event *event,
+				      struct perf_event_attr *attr,
+				      struct perf_event *group_leader)
+{
+	struct perf_cgroup *cgrp;
+	struct cgroup_subsys_state *css;
+	struct file *file;
+	int ret = 0, fput_needed;
+
+	file = fget_light(fd, &fput_needed);
+	if (!file)
+		return -EBADF;
+
+	css = cgroup_css_from_dir(file, perf_subsys_id);
+	if (IS_ERR(css)) {
+		ret = PTR_ERR(css);
+		goto out;
+	}
+
+	cgrp = container_of(css, struct perf_cgroup, css);
+	event->cgrp = cgrp;
+
+	/* must be done before we fput() the file */
+	perf_get_cgroup(event);
+
+	/*
+	 * all events in a group must monitor
+	 * the same cgroup because a task belongs
+	 * to only one perf cgroup at a time
+	 */
+	if (group_leader && group_leader->cgrp != cgrp) {
+		perf_detach_cgroup(event);
+		ret = -EINVAL;
+	}
+out:
+	fput_light(file, fput_needed);
+	return ret;
+}
+
+static inline void
+perf_cgroup_set_shadow_time(struct perf_event *event, u64 now)
+{
+	struct perf_cgroup_info *t;
+	t = per_cpu_ptr(event->cgrp->info, event->cpu);
+	event->shadow_ctx_time = now - t->timestamp;
+}
+
+static inline void
+perf_cgroup_defer_enabled(struct perf_event *event)
+{
+	/*
+	 * when the current task's perf cgroup does not match
+	 * the event's, we need to remember to call the
+	 * perf_mark_enable() function the first time a task with
+	 * a matching perf cgroup is scheduled in.
+	 */
+	if (is_cgroup_event(event) && !perf_cgroup_match(event))
+		event->cgrp_defer_enabled = 1;
+}
+
+static inline void
+perf_cgroup_mark_enabled(struct perf_event *event,
+			 struct perf_event_context *ctx)
+{
+	struct perf_event *sub;
+	u64 tstamp = perf_event_time(event);
+
+	if (!event->cgrp_defer_enabled)
+		return;
+
+	event->cgrp_defer_enabled = 0;
+
+	event->tstamp_enabled = tstamp - event->total_time_enabled;
+	list_for_each_entry(sub, &event->sibling_list, group_entry) {
+		if (sub->state >= PERF_EVENT_STATE_INACTIVE) {
+			sub->tstamp_enabled = tstamp - sub->total_time_enabled;
+			sub->cgrp_defer_enabled = 0;
+		}
+	}
+}
+#else /* !CONFIG_CGROUP_PERF */
+
+static inline bool
+perf_cgroup_match(struct perf_event *event)
+{
+	return true;
+}
+
+static inline void perf_detach_cgroup(struct perf_event *event)
+{}
+
+static inline int is_cgroup_event(struct perf_event *event)
+{
+	return 0;
+}
+
+static inline u64 perf_cgroup_event_cgrp_time(struct perf_event *event)
+{
+	return 0;
+}
+
+static inline void update_cgrp_time_from_event(struct perf_event *event)
+{
+}
+
+static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx)
+{
+}
+
+static inline void perf_cgroup_sched_out(struct task_struct *task)
+{
+}
+
+static inline void perf_cgroup_sched_in(struct task_struct *task)
+{
+}
+
+static inline int perf_cgroup_connect(pid_t pid, struct perf_event *event,
+				      struct perf_event_attr *attr,
+				      struct perf_event *group_leader)
+{
+	return -EINVAL;
+}
+
+static inline void
+perf_cgroup_set_timestamp(struct task_struct *task,
+			  struct perf_event_context *ctx)
+{
+}
+
+void
+perf_cgroup_switch(struct task_struct *task, struct task_struct *next)
+{
+}
+
+static inline void
+perf_cgroup_set_shadow_time(struct perf_event *event, u64 now)
+{
+}
+
+static inline u64 perf_cgroup_event_time(struct perf_event *event)
+{
+	return 0;
+}
+
+static inline void
+perf_cgroup_defer_enabled(struct perf_event *event)
+{
+}
+
+static inline void
+perf_cgroup_mark_enabled(struct perf_event *event,
+			 struct perf_event_context *ctx)
+{
+}
+#endif
+
 void perf_pmu_disable(struct pmu *pmu)
 {
 	int *count = this_cpu_ptr(pmu->pmu_disable_count);
@@ -254,7 +712,6 @@ static void perf_unpin_context(struct perf_event_context *ctx)
 	raw_spin_lock_irqsave(&ctx->lock, flags);
 	--ctx->pin_count;
 	raw_spin_unlock_irqrestore(&ctx->lock, flags);
-	put_ctx(ctx);
 }
 
 /*
@@ -271,6 +728,10 @@ static void update_context_time(struct perf_event_context *ctx)
 static u64 perf_event_time(struct perf_event *event)
 {
 	struct perf_event_context *ctx = event->ctx;
+
+	if (is_cgroup_event(event))
+		return perf_cgroup_event_time(event);
+
 	return ctx ? ctx->time : 0;
 }
 
@@ -285,9 +746,20 @@ static void update_event_times(struct perf_event *event)
 	if (event->state < PERF_EVENT_STATE_INACTIVE ||
 	    event->group_leader->state < PERF_EVENT_STATE_INACTIVE)
 		return;
-
-	if (ctx->is_active)
+	/*
+	 * in cgroup mode, time_enabled represents
+	 * the time the event was enabled AND active
+	 * tasks were in the monitored cgroup. This is
+	 * independent of the activity of the context as
+	 * there may be a mix of cgroup and non-cgroup events.
+	 *
+	 * That is why we treat cgroup events differently
+	 * here.
+	 */
+	if (is_cgroup_event(event))
 		run_end = perf_event_time(event);
+	else if (ctx->is_active)
+		run_end = ctx->time;
 	else
 		run_end = event->tstamp_stopped;
 
@@ -299,6 +771,7 @@ static void update_event_times(struct perf_event *event)
 		run_end = perf_event_time(event);
 
 	event->total_time_running = run_end - event->tstamp_running;
+
 }
 
 /*
@@ -347,6 +820,9 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx)
 		list_add_tail(&event->group_entry, list);
 	}
 
+	if (is_cgroup_event(event))
+		ctx->nr_cgroups++;
+
 	list_add_rcu(&event->event_entry, &ctx->event_list);
 	if (!ctx->nr_events)
 		perf_pmu_rotate_start(ctx->pmu);
@@ -473,6 +949,9 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx)
 
 	event->attach_state &= ~PERF_ATTACH_CONTEXT;
 
+	if (is_cgroup_event(event))
+		ctx->nr_cgroups--;
+
 	ctx->nr_events--;
 	if (event->attr.inherit_stat)
 		ctx->nr_stat--;
@@ -544,7 +1023,8 @@ out:
 static inline int
 event_filter_match(struct perf_event *event)
 {
-	return event->cpu == -1 || event->cpu == smp_processor_id();
+	return (event->cpu == -1 || event->cpu == smp_processor_id())
+	    && perf_cgroup_match(event);
 }
 
 static void
@@ -562,7 +1042,7 @@ event_sched_out(struct perf_event *event,
 	 */
 	if (event->state == PERF_EVENT_STATE_INACTIVE
 	    && !event_filter_match(event)) {
-		delta = ctx->time - event->tstamp_stopped;
+		delta = tstamp - event->tstamp_stopped;
 		event->tstamp_running += delta;
 		event->tstamp_stopped = tstamp;
 	}
@@ -606,47 +1086,30 @@ group_sched_out(struct perf_event *group_event,
 		cpuctx->exclusive = 0;
 }
 
-static inline struct perf_cpu_context *
-__get_cpu_context(struct perf_event_context *ctx)
-{
-	return this_cpu_ptr(ctx->pmu->pmu_cpu_context);
-}
-
 /*
  * Cross CPU call to remove a performance event
  *
  * We disable the event on the hardware level first. After that we
  * remove it from the context list.
  */
-static void __perf_event_remove_from_context(void *info)
+static int __perf_remove_from_context(void *info)
 {
 	struct perf_event *event = info;
 	struct perf_event_context *ctx = event->ctx;
 	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
 
-	/*
-	 * If this is a task context, we need to check whether it is
-	 * the current task context of this cpu. If not it has been
-	 * scheduled out before the smp call arrived.
-	 */
-	if (ctx->task && cpuctx->task_ctx != ctx)
-		return;
-
 	raw_spin_lock(&ctx->lock);
-
 	event_sched_out(event, cpuctx, ctx);
-
 	list_del_event(event, ctx);
-
 	raw_spin_unlock(&ctx->lock);
+
+	return 0;
 }
 
 
 /*
  * Remove the event from a task's (or a CPU's) list of events.
  *
- * Must be called with ctx->mutex held.
- *
  * CPU events are removed with a smp call. For task events we only
  * call when the task is on a CPU.
  *
@@ -657,49 +1120,48 @@ static void __perf_event_remove_from_context(void *info)
  * When called from perf_event_exit_task, it's OK because the
  * context has been detached from its task.
  */
-static void perf_event_remove_from_context(struct perf_event *event)
+static void perf_remove_from_context(struct perf_event *event)
 {
 	struct perf_event_context *ctx = event->ctx;
 	struct task_struct *task = ctx->task;
 
+	lockdep_assert_held(&ctx->mutex);
+
 	if (!task) {
 		/*
 		 * Per cpu events are removed via an smp call and
 		 * the removal is always successful.
 		 */
-		smp_call_function_single(event->cpu,
-					 __perf_event_remove_from_context,
-					 event, 1);
+		cpu_function_call(event->cpu, __perf_remove_from_context, event);
 		return;
 	}
 
 retry:
-	task_oncpu_function_call(task, __perf_event_remove_from_context,
-				 event);
+	if (!task_function_call(task, __perf_remove_from_context, event))
+		return;
 
 	raw_spin_lock_irq(&ctx->lock);
 	/*
-	 * If the context is active we need to retry the smp call.
+	 * If we failed to find a running task, but find the context active now
+	 * that we've acquired the ctx->lock, retry.
 	 */
-	if (ctx->nr_active && !list_empty(&event->group_entry)) {
+	if (ctx->is_active) {
 		raw_spin_unlock_irq(&ctx->lock);
 		goto retry;
 	}
 
 	/*
-	 * The lock prevents that this context is scheduled in so we
-	 * can remove the event safely, if the call above did not
-	 * succeed.
+	 * Since the task isn't running, its safe to remove the event, us
+	 * holding the ctx->lock ensures the task won't get scheduled in.
 	 */
-	if (!list_empty(&event->group_entry))
-		list_del_event(event, ctx);
+	list_del_event(event, ctx);
 	raw_spin_unlock_irq(&ctx->lock);
 }
 
 /*
  * Cross CPU call to disable a performance event
  */
-static void __perf_event_disable(void *info)
+static int __perf_event_disable(void *info)
 {
 	struct perf_event *event = info;
 	struct perf_event_context *ctx = event->ctx;
@@ -708,9 +1170,12 @@ static void __perf_event_disable(void *info)
 	/*
 	 * If this is a per-task event, need to check whether this
 	 * event's task is the current task on this cpu.
+	 *
+	 * Can trigger due to concurrent perf_event_context_sched_out()
+	 * flipping contexts around.
 	 */
 	if (ctx->task && cpuctx->task_ctx != ctx)
-		return;
+		return -EINVAL;
 
 	raw_spin_lock(&ctx->lock);
 
@@ -720,6 +1185,7 @@ static void __perf_event_disable(void *info)
 	 */
 	if (event->state >= PERF_EVENT_STATE_INACTIVE) {
 		update_context_time(ctx);
+		update_cgrp_time_from_event(event);
 		update_group_times(event);
 		if (event == event->group_leader)
 			group_sched_out(event, cpuctx, ctx);
@@ -729,6 +1195,8 @@ static void __perf_event_disable(void *info)
 	}
 
 	raw_spin_unlock(&ctx->lock);
+
+	return 0;
 }
 
 /*
@@ -753,13 +1221,13 @@ void perf_event_disable(struct perf_event *event)
 		/*
 		 * Disable the event on the cpu that it's on
 		 */
-		smp_call_function_single(event->cpu, __perf_event_disable,
-					 event, 1);
+		cpu_function_call(event->cpu, __perf_event_disable, event);
 		return;
 	}
 
 retry:
-	task_oncpu_function_call(task, __perf_event_disable, event);
+	if (!task_function_call(task, __perf_event_disable, event))
+		return;
 
 	raw_spin_lock_irq(&ctx->lock);
 	/*
@@ -767,6 +1235,11 @@ retry:
 	 */
 	if (event->state == PERF_EVENT_STATE_ACTIVE) {
 		raw_spin_unlock_irq(&ctx->lock);
+		/*
+		 * Reload the task pointer, it might have been changed by
+		 * a concurrent perf_event_context_sched_out().
+		 */
+		task = ctx->task;
 		goto retry;
 	}
 
@@ -778,10 +1251,44 @@ retry:
 		update_group_times(event);
 		event->state = PERF_EVENT_STATE_OFF;
 	}
-
 	raw_spin_unlock_irq(&ctx->lock);
 }
 
+static void perf_set_shadow_time(struct perf_event *event,
+				 struct perf_event_context *ctx,
+				 u64 tstamp)
+{
+	/*
+	 * use the correct time source for the time snapshot
+	 *
+	 * We could get by without this by leveraging the
+	 * fact that to get to this function, the caller
+	 * has most likely already called update_context_time()
+	 * and update_cgrp_time_xx() and thus both timestamp
+	 * are identical (or very close). Given that tstamp is,
+	 * already adjusted for cgroup, we could say that:
+	 *    tstamp - ctx->timestamp
+	 * is equivalent to
+	 *    tstamp - cgrp->timestamp.
+	 *
+	 * Then, in perf_output_read(), the calculation would
+	 * work with no changes because:
+	 * - event is guaranteed scheduled in
+	 * - no scheduled out in between
+	 * - thus the timestamp would be the same
+	 *
+	 * But this is a bit hairy.
+	 *
+	 * So instead, we have an explicit cgroup call to remain
+	 * within the time time source all along. We believe it
+	 * is cleaner and simpler to understand.
+	 */
+	if (is_cgroup_event(event))
+		perf_cgroup_set_shadow_time(event, tstamp);
+	else
+		event->shadow_ctx_time = tstamp - ctx->timestamp;
+}
+
 #define MAX_INTERRUPTS (~0ULL)
 
 static void perf_log_throttle(struct perf_event *event, int enable);
@@ -822,7 +1329,7 @@ event_sched_in(struct perf_event *event,
 
 	event->tstamp_running += tstamp - event->tstamp_stopped;
 
-	event->shadow_ctx_time = tstamp - ctx->timestamp;
+	perf_set_shadow_time(event, ctx, tstamp);
 
 	if (!is_software_event(event))
 		cpuctx->active_oncpu++;
@@ -943,12 +1450,15 @@ static void add_event_to_ctx(struct perf_event *event,
 	event->tstamp_stopped = tstamp;
 }
 
+static void perf_event_context_sched_in(struct perf_event_context *ctx,
+					struct task_struct *tsk);
+
 /*
  * Cross CPU call to install and enable a performance event
  *
  * Must be called with ctx->mutex held
  */
-static void __perf_install_in_context(void *info)
+static int  __perf_install_in_context(void *info)
 {
 	struct perf_event *event = info;
 	struct perf_event_context *ctx = event->ctx;
@@ -957,21 +1467,22 @@ static void __perf_install_in_context(void *info)
 	int err;
 
 	/*
-	 * If this is a task context, we need to check whether it is
-	 * the current task context of this cpu. If not it has been
-	 * scheduled out before the smp call arrived.
-	 * Or possibly this is the right context but it isn't
-	 * on this cpu because it had no events.
+	 * In case we're installing a new context to an already running task,
+	 * could also happen before perf_event_task_sched_in() on architectures
+	 * which do context switches with IRQs enabled.
 	 */
-	if (ctx->task && cpuctx->task_ctx != ctx) {
-		if (cpuctx->task_ctx || ctx->task != current)
-			return;
-		cpuctx->task_ctx = ctx;
-	}
+	if (ctx->task && !cpuctx->task_ctx)
+		perf_event_context_sched_in(ctx, ctx->task);
 
 	raw_spin_lock(&ctx->lock);
 	ctx->is_active = 1;
 	update_context_time(ctx);
+	/*
+	 * update cgrp time only if current cgrp
+	 * matches event->cgrp. Must be done before
+	 * calling add_event_to_ctx()
+	 */
+	update_cgrp_time_from_event(event);
 
 	add_event_to_ctx(event, ctx);
 
@@ -1012,6 +1523,8 @@ static void __perf_install_in_context(void *info)
 
 unlock:
 	raw_spin_unlock(&ctx->lock);
+
+	return 0;
 }
 
 /*
@@ -1023,8 +1536,6 @@ unlock:
  * If the event is attached to a task which is on a CPU we use a smp
  * call to enable it in the task context. The task might have been
  * scheduled away, but we check this in the smp call again.
- *
- * Must be called with ctx->mutex held.
  */
 static void
 perf_install_in_context(struct perf_event_context *ctx,
@@ -1033,6 +1544,8 @@ perf_install_in_context(struct perf_event_context *ctx,
 {
 	struct task_struct *task = ctx->task;
 
+	lockdep_assert_held(&ctx->mutex);
+
 	event->ctx = ctx;
 
 	if (!task) {
@@ -1040,31 +1553,29 @@ perf_install_in_context(struct perf_event_context *ctx,
 		 * Per cpu events are installed via an smp call and
 		 * the install is always successful.
 		 */
-		smp_call_function_single(cpu, __perf_install_in_context,
-					 event, 1);
+		cpu_function_call(cpu, __perf_install_in_context, event);
 		return;
 	}
 
 retry:
-	task_oncpu_function_call(task, __perf_install_in_context,
-				 event);
+	if (!task_function_call(task, __perf_install_in_context, event))
+		return;
 
 	raw_spin_lock_irq(&ctx->lock);
 	/*
-	 * we need to retry the smp call.
+	 * If we failed to find a running task, but find the context active now
+	 * that we've acquired the ctx->lock, retry.
 	 */
-	if (ctx->is_active && list_empty(&event->group_entry)) {
+	if (ctx->is_active) {
 		raw_spin_unlock_irq(&ctx->lock);
 		goto retry;
 	}
 
 	/*
-	 * The lock prevents that this context is scheduled in so we
-	 * can add the event safely, if it the call above did not
-	 * succeed.
+	 * Since the task isn't running, its safe to add the event, us holding
+	 * the ctx->lock ensures the task won't get scheduled in.
 	 */
-	if (list_empty(&event->group_entry))
-		add_event_to_ctx(event, ctx);
+	add_event_to_ctx(event, ctx);
 	raw_spin_unlock_irq(&ctx->lock);
 }
 
@@ -1093,7 +1604,7 @@ static void __perf_event_mark_enabled(struct perf_event *event,
 /*
  * Cross CPU call to enable a performance event
  */
-static void __perf_event_enable(void *info)
+static int __perf_event_enable(void *info)
 {
 	struct perf_event *event = info;
 	struct perf_event_context *ctx = event->ctx;
@@ -1101,26 +1612,27 @@ static void __perf_event_enable(void *info)
 	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
 	int err;
 
-	/*
-	 * If this is a per-task event, need to check whether this
-	 * event's task is the current task on this cpu.
-	 */
-	if (ctx->task && cpuctx->task_ctx != ctx) {
-		if (cpuctx->task_ctx || ctx->task != current)
-			return;
-		cpuctx->task_ctx = ctx;
-	}
+	if (WARN_ON_ONCE(!ctx->is_active))
+		return -EINVAL;
 
 	raw_spin_lock(&ctx->lock);
-	ctx->is_active = 1;
 	update_context_time(ctx);
 
 	if (event->state >= PERF_EVENT_STATE_INACTIVE)
 		goto unlock;
+
+	/*
+	 * set current task's cgroup time reference point
+	 */
+	perf_cgroup_set_timestamp(current, ctx);
+
 	__perf_event_mark_enabled(event, ctx);
 
-	if (!event_filter_match(event))
+	if (!event_filter_match(event)) {
+		if (is_cgroup_event(event))
+			perf_cgroup_defer_enabled(event);
 		goto unlock;
+	}
 
 	/*
 	 * If the event is in a group and isn't the group leader,
@@ -1153,6 +1665,8 @@ static void __perf_event_enable(void *info)
 
 unlock:
 	raw_spin_unlock(&ctx->lock);
+
+	return 0;
 }
 
 /*
@@ -1173,8 +1687,7 @@ void perf_event_enable(struct perf_event *event)
 		/*
 		 * Enable the event on the cpu that it's on
 		 */
-		smp_call_function_single(event->cpu, __perf_event_enable,
-					 event, 1);
+		cpu_function_call(event->cpu, __perf_event_enable, event);
 		return;
 	}
 
@@ -1193,8 +1706,15 @@ void perf_event_enable(struct perf_event *event)
 		event->state = PERF_EVENT_STATE_OFF;
 
 retry:
+	if (!ctx->is_active) {
+		__perf_event_mark_enabled(event, ctx);
+		goto out;
+	}
+
 	raw_spin_unlock_irq(&ctx->lock);
-	task_oncpu_function_call(task, __perf_event_enable, event);
+
+	if (!task_function_call(task, __perf_event_enable, event))
+		return;
 
 	raw_spin_lock_irq(&ctx->lock);
 
@@ -1202,15 +1722,14 @@ retry:
 	 * If the context is active and the event is still off,
 	 * we need to retry the cross-call.
 	 */
-	if (ctx->is_active && event->state == PERF_EVENT_STATE_OFF)
+	if (ctx->is_active && event->state == PERF_EVENT_STATE_OFF) {
+		/*
+		 * task could have been flipped by a concurrent
+		 * perf_event_context_sched_out()
+		 */
+		task = ctx->task;
 		goto retry;
-
-	/*
-	 * Since we have the lock this context can't be scheduled
-	 * in, so we can change the state safely.
-	 */
-	if (event->state == PERF_EVENT_STATE_OFF)
-		__perf_event_mark_enabled(event, ctx);
+	}
 
 out:
 	raw_spin_unlock_irq(&ctx->lock);
@@ -1242,6 +1761,7 @@ static void ctx_sched_out(struct perf_event_context *ctx,
 	if (likely(!ctx->nr_events))
 		goto out;
 	update_context_time(ctx);
+	update_cgrp_time_from_cpuctx(cpuctx);
 
 	if (!ctx->nr_active)
 		goto out;
@@ -1354,8 +1874,8 @@ static void perf_event_sync_stat(struct perf_event_context *ctx,
 	}
 }
 
-void perf_event_context_sched_out(struct task_struct *task, int ctxn,
-				  struct task_struct *next)
+static void perf_event_context_sched_out(struct task_struct *task, int ctxn,
+					 struct task_struct *next)
 {
 	struct perf_event_context *ctx = task->perf_event_ctxp[ctxn];
 	struct perf_event_context *next_ctx;
@@ -1431,6 +1951,14 @@ void __perf_event_task_sched_out(struct task_struct *task,
 
 	for_each_task_context_nr(ctxn)
 		perf_event_context_sched_out(task, ctxn, next);
+
+	/*
+	 * if cgroup events exist on this CPU, then we need
+	 * to check if we have to switch out PMU state.
+	 * cgroup event are system-wide mode only
+	 */
+	if (atomic_read(&__get_cpu_var(perf_cgroup_events)))
+		perf_cgroup_sched_out(task);
 }
 
 static void task_ctx_sched_out(struct perf_event_context *ctx,
@@ -1469,6 +1997,10 @@ ctx_pinned_sched_in(struct perf_event_context *ctx,
 		if (!event_filter_match(event))
 			continue;
 
+		/* may need to reset tstamp_enabled */
+		if (is_cgroup_event(event))
+			perf_cgroup_mark_enabled(event, ctx);
+
 		if (group_can_go_on(event, cpuctx, 1))
 			group_sched_in(event, cpuctx, ctx);
 
@@ -1501,6 +2033,10 @@ ctx_flexible_sched_in(struct perf_event_context *ctx,
 		if (!event_filter_match(event))
 			continue;
 
+		/* may need to reset tstamp_enabled */
+		if (is_cgroup_event(event))
+			perf_cgroup_mark_enabled(event, ctx);
+
 		if (group_can_go_on(event, cpuctx, can_add_hw)) {
 			if (group_sched_in(event, cpuctx, ctx))
 				can_add_hw = 0;
@@ -1511,15 +2047,19 @@ ctx_flexible_sched_in(struct perf_event_context *ctx,
 static void
 ctx_sched_in(struct perf_event_context *ctx,
 	     struct perf_cpu_context *cpuctx,
-	     enum event_type_t event_type)
+	     enum event_type_t event_type,
+	     struct task_struct *task)
 {
+	u64 now;
+
 	raw_spin_lock(&ctx->lock);
 	ctx->is_active = 1;
 	if (likely(!ctx->nr_events))
 		goto out;
 
-	ctx->timestamp = perf_clock();
-
+	now = perf_clock();
+	ctx->timestamp = now;
+	perf_cgroup_set_timestamp(task, ctx);
 	/*
 	 * First go through the list and put on any pinned groups
 	 * in order to give them the best chance of going on.
@@ -1536,11 +2076,12 @@ out:
 }
 
 static void cpu_ctx_sched_in(struct perf_cpu_context *cpuctx,
-			     enum event_type_t event_type)
+			     enum event_type_t event_type,
+			     struct task_struct *task)
 {
 	struct perf_event_context *ctx = &cpuctx->ctx;
 
-	ctx_sched_in(ctx, cpuctx, event_type);
+	ctx_sched_in(ctx, cpuctx, event_type, task);
 }
 
 static void task_ctx_sched_in(struct perf_event_context *ctx,
@@ -1548,15 +2089,16 @@ static void task_ctx_sched_in(struct perf_event_context *ctx,
 {
 	struct perf_cpu_context *cpuctx;
 
-       	cpuctx = __get_cpu_context(ctx);
+	cpuctx = __get_cpu_context(ctx);
 	if (cpuctx->task_ctx == ctx)
 		return;
 
-	ctx_sched_in(ctx, cpuctx, event_type);
+	ctx_sched_in(ctx, cpuctx, event_type, NULL);
 	cpuctx->task_ctx = ctx;
 }
 
-void perf_event_context_sched_in(struct perf_event_context *ctx)
+static void perf_event_context_sched_in(struct perf_event_context *ctx,
+					struct task_struct *task)
 {
 	struct perf_cpu_context *cpuctx;
 
@@ -1572,9 +2114,9 @@ void perf_event_context_sched_in(struct perf_event_context *ctx)
 	 */
 	cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
 
-	ctx_sched_in(ctx, cpuctx, EVENT_PINNED);
-	cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE);
-	ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE);
+	ctx_sched_in(ctx, cpuctx, EVENT_PINNED, task);
+	cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE, task);
+	ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE, task);
 
 	cpuctx->task_ctx = ctx;
 
@@ -1607,8 +2149,15 @@ void __perf_event_task_sched_in(struct task_struct *task)
 		if (likely(!ctx))
 			continue;
 
-		perf_event_context_sched_in(ctx);
+		perf_event_context_sched_in(ctx, task);
 	}
+	/*
+	 * if cgroup events exist on this CPU, then we need
+	 * to check if we have to switch in PMU state.
+	 * cgroup event are system-wide mode only
+	 */
+	if (atomic_read(&__get_cpu_var(perf_cgroup_events)))
+		perf_cgroup_sched_in(task);
 }
 
 static u64 perf_calculate_period(struct perf_event *event, u64 nsec, u64 count)
@@ -1638,7 +2187,7 @@ static u64 perf_calculate_period(struct perf_event *event, u64 nsec, u64 count)
 	 * Reduce accuracy by one bit such that @a and @b converge
 	 * to a similar magnitude.
 	 */
-#define REDUCE_FLS(a, b) 		\
+#define REDUCE_FLS(a, b)		\
 do {					\
 	if (a##_fls > b##_fls) {	\
 		a >>= 1;		\
@@ -1808,7 +2357,7 @@ static void perf_rotate_context(struct perf_cpu_context *cpuctx)
 	if (ctx)
 		rotate_ctx(ctx);
 
-	cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE);
+	cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE, current);
 	if (ctx)
 		task_ctx_sched_in(ctx, EVENT_FLEXIBLE);
 
@@ -1887,7 +2436,7 @@ static void perf_event_enable_on_exec(struct perf_event_context *ctx)
 
 	raw_spin_unlock(&ctx->lock);
 
-	perf_event_context_sched_in(ctx);
+	perf_event_context_sched_in(ctx, ctx->task);
 out:
 	local_irq_restore(flags);
 }
@@ -1912,8 +2461,10 @@ static void __perf_event_read(void *info)
 		return;
 
 	raw_spin_lock(&ctx->lock);
-	if (ctx->is_active)
+	if (ctx->is_active) {
 		update_context_time(ctx);
+		update_cgrp_time_from_event(event);
+	}
 	update_event_times(event);
 	if (event->state == PERF_EVENT_STATE_ACTIVE)
 		event->pmu->read(event);
@@ -1944,8 +2495,10 @@ static u64 perf_event_read(struct perf_event *event)
 		 * (e.g., thread is blocked), in that case
 		 * we cannot update context time
 		 */
-		if (ctx->is_active)
+		if (ctx->is_active) {
 			update_context_time(ctx);
+			update_cgrp_time_from_event(event);
+		}
 		update_event_times(event);
 		raw_spin_unlock_irqrestore(&ctx->lock, flags);
 	}
@@ -2224,6 +2777,9 @@ errout:
 
 }
 
+/*
+ * Returns a matching context with refcount and pincount.
+ */
 static struct perf_event_context *
 find_get_context(struct pmu *pmu, struct task_struct *task, int cpu)
 {
@@ -2248,6 +2804,7 @@ find_get_context(struct pmu *pmu, struct task_struct *task, int cpu)
 		cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
 		ctx = &cpuctx->ctx;
 		get_ctx(ctx);
+		++ctx->pin_count;
 
 		return ctx;
 	}
@@ -2261,6 +2818,7 @@ retry:
 	ctx = perf_lock_task_context(task, ctxn, &flags);
 	if (ctx) {
 		unclone_ctx(ctx);
+		++ctx->pin_count;
 		raw_spin_unlock_irqrestore(&ctx->lock, flags);
 	}
 
@@ -2282,8 +2840,10 @@ retry:
 			err = -ESRCH;
 		else if (task->perf_event_ctxp[ctxn])
 			err = -EAGAIN;
-		else
+		else {
+			++ctx->pin_count;
 			rcu_assign_pointer(task->perf_event_ctxp[ctxn], ctx);
+		}
 		mutex_unlock(&task->perf_event_mutex);
 
 		if (unlikely(err)) {
@@ -2323,7 +2883,7 @@ static void free_event(struct perf_event *event)
 
 	if (!event->parent) {
 		if (event->attach_state & PERF_ATTACH_TASK)
-			jump_label_dec(&perf_task_events);
+			jump_label_dec(&perf_sched_events);
 		if (event->attr.mmap || event->attr.mmap_data)
 			atomic_dec(&nr_mmap_events);
 		if (event->attr.comm)
@@ -2332,6 +2892,10 @@ static void free_event(struct perf_event *event)
 			atomic_dec(&nr_task_events);
 		if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN)
 			put_callchain_buffers();
+		if (is_cgroup_event(event)) {
+			atomic_dec(&per_cpu(perf_cgroup_events, event->cpu));
+			jump_label_dec(&perf_sched_events);
+		}
 	}
 
 	if (event->buffer) {
@@ -2339,6 +2903,9 @@ static void free_event(struct perf_event *event)
 		event->buffer = NULL;
 	}
 
+	if (is_cgroup_event(event))
+		perf_detach_cgroup(event);
+
 	if (event->destroy)
 		event->destroy(event);
 
@@ -4406,26 +4973,14 @@ static int __perf_event_overflow(struct perf_event *event, int nmi,
 	if (unlikely(!is_sampling_event(event)))
 		return 0;
 
-	if (!throttle) {
-		hwc->interrupts++;
-	} else {
-		if (hwc->interrupts != MAX_INTERRUPTS) {
-			hwc->interrupts++;
-			if (HZ * hwc->interrupts >
-					(u64)sysctl_perf_event_sample_rate) {
-				hwc->interrupts = MAX_INTERRUPTS;
-				perf_log_throttle(event, 0);
-				ret = 1;
-			}
-		} else {
-			/*
-			 * Keep re-disabling events even though on the previous
-			 * pass we disabled it - just in case we raced with a
-			 * sched-in and the event got enabled again:
-			 */
+	if (unlikely(hwc->interrupts >= max_samples_per_tick)) {
+		if (throttle) {
+			hwc->interrupts = MAX_INTERRUPTS;
+			perf_log_throttle(event, 0);
 			ret = 1;
 		}
-	}
+	} else
+		hwc->interrupts++;
 
 	if (event->attr.freq) {
 		u64 now = perf_clock();
@@ -5062,6 +5617,10 @@ static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer)
 	u64 period;
 
 	event = container_of(hrtimer, struct perf_event, hw.hrtimer);
+
+	if (event->state != PERF_EVENT_STATE_ACTIVE)
+		return HRTIMER_NORESTART;
+
 	event->pmu->read(event);
 
 	perf_sample_data_init(&data, 0);
@@ -5088,9 +5647,6 @@ static void perf_swevent_start_hrtimer(struct perf_event *event)
 	if (!is_sampling_event(event))
 		return;
 
-	hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	hwc->hrtimer.function = perf_swevent_hrtimer;
-
 	period = local64_read(&hwc->period_left);
 	if (period) {
 		if (period < 0)
@@ -5117,6 +5673,30 @@ static void perf_swevent_cancel_hrtimer(struct perf_event *event)
 	}
 }
 
+static void perf_swevent_init_hrtimer(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (!is_sampling_event(event))
+		return;
+
+	hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	hwc->hrtimer.function = perf_swevent_hrtimer;
+
+	/*
+	 * Since hrtimers have a fixed rate, we can do a static freq->period
+	 * mapping and avoid the whole period adjust feedback stuff.
+	 */
+	if (event->attr.freq) {
+		long freq = event->attr.sample_freq;
+
+		event->attr.sample_period = NSEC_PER_SEC / freq;
+		hwc->sample_period = event->attr.sample_period;
+		local64_set(&hwc->period_left, hwc->sample_period);
+		event->attr.freq = 0;
+	}
+}
+
 /*
  * Software event: cpu wall time clock
  */
@@ -5169,6 +5749,8 @@ static int cpu_clock_event_init(struct perf_event *event)
 	if (event->attr.config != PERF_COUNT_SW_CPU_CLOCK)
 		return -ENOENT;
 
+	perf_swevent_init_hrtimer(event);
+
 	return 0;
 }
 
@@ -5224,16 +5806,9 @@ static void task_clock_event_del(struct perf_event *event, int flags)
 
 static void task_clock_event_read(struct perf_event *event)
 {
-	u64 time;
-
-	if (!in_nmi()) {
-		update_context_time(event->ctx);
-		time = event->ctx->time;
-	} else {
-		u64 now = perf_clock();
-		u64 delta = now - event->ctx->timestamp;
-		time = event->ctx->time + delta;
-	}
+	u64 now = perf_clock();
+	u64 delta = now - event->ctx->timestamp;
+	u64 time = event->ctx->time + delta;
 
 	task_clock_event_update(event, time);
 }
@@ -5246,6 +5821,8 @@ static int task_clock_event_init(struct perf_event *event)
 	if (event->attr.config != PERF_COUNT_SW_TASK_CLOCK)
 		return -ENOENT;
 
+	perf_swevent_init_hrtimer(event);
+
 	return 0;
 }
 
@@ -5517,17 +6094,22 @@ struct pmu *perf_init_event(struct perf_event *event)
 {
 	struct pmu *pmu = NULL;
 	int idx;
+	int ret;
 
 	idx = srcu_read_lock(&pmus_srcu);
 
 	rcu_read_lock();
 	pmu = idr_find(&pmu_idr, event->attr.type);
 	rcu_read_unlock();
-	if (pmu)
+	if (pmu) {
+		ret = pmu->event_init(event);
+		if (ret)
+			pmu = ERR_PTR(ret);
 		goto unlock;
+	}
 
 	list_for_each_entry_rcu(pmu, &pmus, entry) {
-		int ret = pmu->event_init(event);
+		ret = pmu->event_init(event);
 		if (!ret)
 			goto unlock;
 
@@ -5653,7 +6235,7 @@ done:
 
 	if (!event->parent) {
 		if (event->attach_state & PERF_ATTACH_TASK)
-			jump_label_inc(&perf_task_events);
+			jump_label_inc(&perf_sched_events);
 		if (event->attr.mmap || event->attr.mmap_data)
 			atomic_inc(&nr_mmap_events);
 		if (event->attr.comm)
@@ -5828,7 +6410,7 @@ SYSCALL_DEFINE5(perf_event_open,
 	int err;
 
 	/* for future expandability... */
-	if (flags & ~(PERF_FLAG_FD_NO_GROUP | PERF_FLAG_FD_OUTPUT))
+	if (flags & ~PERF_FLAG_ALL)
 		return -EINVAL;
 
 	err = perf_copy_attr(attr_uptr, &attr);
@@ -5845,6 +6427,15 @@ SYSCALL_DEFINE5(perf_event_open,
 			return -EINVAL;
 	}
 
+	/*
+	 * In cgroup mode, the pid argument is used to pass the fd
+	 * opened to the cgroup directory in cgroupfs. The cpu argument
+	 * designates the cpu on which to monitor threads from that
+	 * cgroup.
+	 */
+	if ((flags & PERF_FLAG_PID_CGROUP) && (pid == -1 || cpu == -1))
+		return -EINVAL;
+
 	event_fd = get_unused_fd_flags(O_RDWR);
 	if (event_fd < 0)
 		return event_fd;
@@ -5862,7 +6453,7 @@ SYSCALL_DEFINE5(perf_event_open,
 			group_leader = NULL;
 	}
 
-	if (pid != -1) {
+	if (pid != -1 && !(flags & PERF_FLAG_PID_CGROUP)) {
 		task = find_lively_task_by_vpid(pid);
 		if (IS_ERR(task)) {
 			err = PTR_ERR(task);
@@ -5876,6 +6467,19 @@ SYSCALL_DEFINE5(perf_event_open,
 		goto err_task;
 	}
 
+	if (flags & PERF_FLAG_PID_CGROUP) {
+		err = perf_cgroup_connect(pid, event, &attr, group_leader);
+		if (err)
+			goto err_alloc;
+		/*
+		 * one more event:
+		 * - that has cgroup constraint on event->cpu
+		 * - that may need work on context switch
+		 */
+		atomic_inc(&per_cpu(perf_cgroup_events, event->cpu));
+		jump_label_inc(&perf_sched_events);
+	}
+
 	/*
 	 * Special case software events and allow them to be part of
 	 * any hardware group.
@@ -5961,10 +6565,10 @@ SYSCALL_DEFINE5(perf_event_open,
 		struct perf_event_context *gctx = group_leader->ctx;
 
 		mutex_lock(&gctx->mutex);
-		perf_event_remove_from_context(group_leader);
+		perf_remove_from_context(group_leader);
 		list_for_each_entry(sibling, &group_leader->sibling_list,
 				    group_entry) {
-			perf_event_remove_from_context(sibling);
+			perf_remove_from_context(sibling);
 			put_ctx(gctx);
 		}
 		mutex_unlock(&gctx->mutex);
@@ -5987,6 +6591,7 @@ SYSCALL_DEFINE5(perf_event_open,
 
 	perf_install_in_context(ctx, event, cpu);
 	++ctx->generation;
+	perf_unpin_context(ctx);
 	mutex_unlock(&ctx->mutex);
 
 	event->owner = current;
@@ -6012,6 +6617,7 @@ SYSCALL_DEFINE5(perf_event_open,
 	return event_fd;
 
 err_context:
+	perf_unpin_context(ctx);
 	put_ctx(ctx);
 err_alloc:
 	free_event(event);
@@ -6062,6 +6668,7 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
 	mutex_lock(&ctx->mutex);
 	perf_install_in_context(ctx, event, cpu);
 	++ctx->generation;
+	perf_unpin_context(ctx);
 	mutex_unlock(&ctx->mutex);
 
 	return event;
@@ -6115,7 +6722,7 @@ __perf_event_exit_task(struct perf_event *child_event,
 {
 	struct perf_event *parent_event;
 
-	perf_event_remove_from_context(child_event);
+	perf_remove_from_context(child_event);
 
 	parent_event = child_event->parent;
 	/*
@@ -6422,7 +7029,7 @@ inherit_task_group(struct perf_event *event, struct task_struct *parent,
 		return 0;
 	}
 
-       	child_ctx = child->perf_event_ctxp[ctxn];
+	child_ctx = child->perf_event_ctxp[ctxn];
 	if (!child_ctx) {
 		/*
 		 * This is executed from the parent task context, so
@@ -6537,6 +7144,7 @@ int perf_event_init_context(struct task_struct *child, int ctxn)
 	mutex_unlock(&parent_ctx->mutex);
 
 	perf_unpin_context(parent_ctx);
+	put_ctx(parent_ctx);
 
 	return ret;
 }
@@ -6606,9 +7214,9 @@ static void __perf_event_exit_context(void *__info)
 	perf_pmu_rotate_stop(ctx->pmu);
 
 	list_for_each_entry_safe(event, tmp, &ctx->pinned_groups, group_entry)
-		__perf_event_remove_from_context(event);
+		__perf_remove_from_context(event);
 	list_for_each_entry_safe(event, tmp, &ctx->flexible_groups, group_entry)
-		__perf_event_remove_from_context(event);
+		__perf_remove_from_context(event);
 }
 
 static void perf_event_exit_cpu_context(int cpu)
@@ -6732,3 +7340,83 @@ unlock:
 	return ret;
 }
 device_initcall(perf_event_sysfs_init);
+
+#ifdef CONFIG_CGROUP_PERF
+static struct cgroup_subsys_state *perf_cgroup_create(
+	struct cgroup_subsys *ss, struct cgroup *cont)
+{
+	struct perf_cgroup *jc;
+
+	jc = kzalloc(sizeof(*jc), GFP_KERNEL);
+	if (!jc)
+		return ERR_PTR(-ENOMEM);
+
+	jc->info = alloc_percpu(struct perf_cgroup_info);
+	if (!jc->info) {
+		kfree(jc);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	return &jc->css;
+}
+
+static void perf_cgroup_destroy(struct cgroup_subsys *ss,
+				struct cgroup *cont)
+{
+	struct perf_cgroup *jc;
+	jc = container_of(cgroup_subsys_state(cont, perf_subsys_id),
+			  struct perf_cgroup, css);
+	free_percpu(jc->info);
+	kfree(jc);
+}
+
+static int __perf_cgroup_move(void *info)
+{
+	struct task_struct *task = info;
+	perf_cgroup_switch(task, PERF_CGROUP_SWOUT | PERF_CGROUP_SWIN);
+	return 0;
+}
+
+static void perf_cgroup_move(struct task_struct *task)
+{
+	task_function_call(task, __perf_cgroup_move, task);
+}
+
+static void perf_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
+		struct cgroup *old_cgrp, struct task_struct *task,
+		bool threadgroup)
+{
+	perf_cgroup_move(task);
+	if (threadgroup) {
+		struct task_struct *c;
+		rcu_read_lock();
+		list_for_each_entry_rcu(c, &task->thread_group, thread_group) {
+			perf_cgroup_move(c);
+		}
+		rcu_read_unlock();
+	}
+}
+
+static void perf_cgroup_exit(struct cgroup_subsys *ss, struct cgroup *cgrp,
+		struct cgroup *old_cgrp, struct task_struct *task)
+{
+	/*
+	 * cgroup_exit() is called in the copy_process() failure path.
+	 * Ignore this case since the task hasn't ran yet, this avoids
+	 * trying to poke a half freed task state from generic code.
+	 */
+	if (!(task->flags & PF_EXITING))
+		return;
+
+	perf_cgroup_move(task);
+}
+
+struct cgroup_subsys perf_subsys = {
+	.name = "perf_event",
+	.subsys_id = perf_subsys_id,
+	.create = perf_cgroup_create,
+	.destroy = perf_cgroup_destroy,
+	.exit = perf_cgroup_exit,
+	.attach = perf_cgroup_attach,
+};
+#endif /* CONFIG_CGROUP_PERF */
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index 05bb7173850e..67fea9d25d55 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -176,7 +176,8 @@ static inline cputime_t virt_ticks(struct task_struct *p)
 	return p->utime;
 }
 
-int posix_cpu_clock_getres(const clockid_t which_clock, struct timespec *tp)
+static int
+posix_cpu_clock_getres(const clockid_t which_clock, struct timespec *tp)
 {
 	int error = check_clock(which_clock);
 	if (!error) {
@@ -194,7 +195,8 @@ int posix_cpu_clock_getres(const clockid_t which_clock, struct timespec *tp)
 	return error;
 }
 
-int posix_cpu_clock_set(const clockid_t which_clock, const struct timespec *tp)
+static int
+posix_cpu_clock_set(const clockid_t which_clock, const struct timespec *tp)
 {
 	/*
 	 * You can never reset a CPU clock, but we check for other errors
@@ -317,7 +319,7 @@ static int cpu_clock_sample_group(const clockid_t which_clock,
 }
 
 
-int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp)
+static int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp)
 {
 	const pid_t pid = CPUCLOCK_PID(which_clock);
 	int error = -EINVAL;
@@ -379,7 +381,7 @@ int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp)
  * This is called from sys_timer_create() and do_cpu_nanosleep() with the
  * new timer already all-zeros initialized.
  */
-int posix_cpu_timer_create(struct k_itimer *new_timer)
+static int posix_cpu_timer_create(struct k_itimer *new_timer)
 {
 	int ret = 0;
 	const pid_t pid = CPUCLOCK_PID(new_timer->it_clock);
@@ -425,7 +427,7 @@ int posix_cpu_timer_create(struct k_itimer *new_timer)
  * If we return TIMER_RETRY, it's necessary to release the timer's lock
  * and try again.  (This happens when the timer is in the middle of firing.)
  */
-int posix_cpu_timer_del(struct k_itimer *timer)
+static int posix_cpu_timer_del(struct k_itimer *timer)
 {
 	struct task_struct *p = timer->it.cpu.task;
 	int ret = 0;
@@ -665,8 +667,8 @@ static int cpu_timer_sample_group(const clockid_t which_clock,
  * If we return TIMER_RETRY, it's necessary to release the timer's lock
  * and try again.  (This happens when the timer is in the middle of firing.)
  */
-int posix_cpu_timer_set(struct k_itimer *timer, int flags,
-			struct itimerspec *new, struct itimerspec *old)
+static int posix_cpu_timer_set(struct k_itimer *timer, int flags,
+			       struct itimerspec *new, struct itimerspec *old)
 {
 	struct task_struct *p = timer->it.cpu.task;
 	union cpu_time_count old_expires, new_expires, old_incr, val;
@@ -820,7 +822,7 @@ int posix_cpu_timer_set(struct k_itimer *timer, int flags,
 	return ret;
 }
 
-void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
+static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
 {
 	union cpu_time_count now;
 	struct task_struct *p = timer->it.cpu.task;
@@ -1481,11 +1483,13 @@ static int do_cpu_nanosleep(const clockid_t which_clock, int flags,
 	return error;
 }
 
-int posix_cpu_nsleep(const clockid_t which_clock, int flags,
-		     struct timespec *rqtp, struct timespec __user *rmtp)
+static long posix_cpu_nsleep_restart(struct restart_block *restart_block);
+
+static int posix_cpu_nsleep(const clockid_t which_clock, int flags,
+			    struct timespec *rqtp, struct timespec __user *rmtp)
 {
 	struct restart_block *restart_block =
-	    &current_thread_info()->restart_block;
+		&current_thread_info()->restart_block;
 	struct itimerspec it;
 	int error;
 
@@ -1501,56 +1505,47 @@ int posix_cpu_nsleep(const clockid_t which_clock, int flags,
 
 	if (error == -ERESTART_RESTARTBLOCK) {
 
-	       	if (flags & TIMER_ABSTIME)
+		if (flags & TIMER_ABSTIME)
 			return -ERESTARTNOHAND;
 		/*
-	 	 * Report back to the user the time still remaining.
-	 	 */
-		if (rmtp != NULL && copy_to_user(rmtp, &it.it_value, sizeof *rmtp))
+		 * Report back to the user the time still remaining.
+		 */
+		if (rmtp && copy_to_user(rmtp, &it.it_value, sizeof *rmtp))
 			return -EFAULT;
 
 		restart_block->fn = posix_cpu_nsleep_restart;
-		restart_block->arg0 = which_clock;
-		restart_block->arg1 = (unsigned long) rmtp;
-		restart_block->arg2 = rqtp->tv_sec;
-		restart_block->arg3 = rqtp->tv_nsec;
+		restart_block->nanosleep.index = which_clock;
+		restart_block->nanosleep.rmtp = rmtp;
+		restart_block->nanosleep.expires = timespec_to_ns(rqtp);
 	}
 	return error;
 }
 
-long posix_cpu_nsleep_restart(struct restart_block *restart_block)
+static long posix_cpu_nsleep_restart(struct restart_block *restart_block)
 {
-	clockid_t which_clock = restart_block->arg0;
-	struct timespec __user *rmtp;
+	clockid_t which_clock = restart_block->nanosleep.index;
 	struct timespec t;
 	struct itimerspec it;
 	int error;
 
-	rmtp = (struct timespec __user *) restart_block->arg1;
-	t.tv_sec = restart_block->arg2;
-	t.tv_nsec = restart_block->arg3;
+	t = ns_to_timespec(restart_block->nanosleep.expires);
 
-	restart_block->fn = do_no_restart_syscall;
 	error = do_cpu_nanosleep(which_clock, TIMER_ABSTIME, &t, &it);
 
 	if (error == -ERESTART_RESTARTBLOCK) {
+		struct timespec __user *rmtp = restart_block->nanosleep.rmtp;
 		/*
-	 	 * Report back to the user the time still remaining.
-	 	 */
-		if (rmtp != NULL && copy_to_user(rmtp, &it.it_value, sizeof *rmtp))
+		 * Report back to the user the time still remaining.
+		 */
+		if (rmtp && copy_to_user(rmtp, &it.it_value, sizeof *rmtp))
 			return -EFAULT;
 
-		restart_block->fn = posix_cpu_nsleep_restart;
-		restart_block->arg0 = which_clock;
-		restart_block->arg1 = (unsigned long) rmtp;
-		restart_block->arg2 = t.tv_sec;
-		restart_block->arg3 = t.tv_nsec;
+		restart_block->nanosleep.expires = timespec_to_ns(&t);
 	}
 	return error;
 
 }
 
-
 #define PROCESS_CLOCK	MAKE_PROCESS_CPUCLOCK(0, CPUCLOCK_SCHED)
 #define THREAD_CLOCK	MAKE_THREAD_CPUCLOCK(0, CPUCLOCK_SCHED)
 
@@ -1594,38 +1589,37 @@ static int thread_cpu_timer_create(struct k_itimer *timer)
 	timer->it_clock = THREAD_CLOCK;
 	return posix_cpu_timer_create(timer);
 }
-static int thread_cpu_nsleep(const clockid_t which_clock, int flags,
-			      struct timespec *rqtp, struct timespec __user *rmtp)
-{
-	return -EINVAL;
-}
-static long thread_cpu_nsleep_restart(struct restart_block *restart_block)
-{
-	return -EINVAL;
-}
+
+struct k_clock clock_posix_cpu = {
+	.clock_getres	= posix_cpu_clock_getres,
+	.clock_set	= posix_cpu_clock_set,
+	.clock_get	= posix_cpu_clock_get,
+	.timer_create	= posix_cpu_timer_create,
+	.nsleep		= posix_cpu_nsleep,
+	.nsleep_restart	= posix_cpu_nsleep_restart,
+	.timer_set	= posix_cpu_timer_set,
+	.timer_del	= posix_cpu_timer_del,
+	.timer_get	= posix_cpu_timer_get,
+};
 
 static __init int init_posix_cpu_timers(void)
 {
 	struct k_clock process = {
-		.clock_getres = process_cpu_clock_getres,
-		.clock_get = process_cpu_clock_get,
-		.clock_set = do_posix_clock_nosettime,
-		.timer_create = process_cpu_timer_create,
-		.nsleep = process_cpu_nsleep,
-		.nsleep_restart = process_cpu_nsleep_restart,
+		.clock_getres	= process_cpu_clock_getres,
+		.clock_get	= process_cpu_clock_get,
+		.timer_create	= process_cpu_timer_create,
+		.nsleep		= process_cpu_nsleep,
+		.nsleep_restart	= process_cpu_nsleep_restart,
 	};
 	struct k_clock thread = {
-		.clock_getres = thread_cpu_clock_getres,
-		.clock_get = thread_cpu_clock_get,
-		.clock_set = do_posix_clock_nosettime,
-		.timer_create = thread_cpu_timer_create,
-		.nsleep = thread_cpu_nsleep,
-		.nsleep_restart = thread_cpu_nsleep_restart,
+		.clock_getres	= thread_cpu_clock_getres,
+		.clock_get	= thread_cpu_clock_get,
+		.timer_create	= thread_cpu_timer_create,
 	};
 	struct timespec ts;
 
-	register_posix_clock(CLOCK_PROCESS_CPUTIME_ID, &process);
-	register_posix_clock(CLOCK_THREAD_CPUTIME_ID, &thread);
+	posix_timers_register_clock(CLOCK_PROCESS_CPUTIME_ID, &process);
+	posix_timers_register_clock(CLOCK_THREAD_CPUTIME_ID, &thread);
 
 	cputime_to_timespec(cputime_one_jiffy, &ts);
 	onecputick = ts.tv_nsec;
diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c
index 93bd2eb2bc53..4c0124919f9a 100644
--- a/kernel/posix-timers.c
+++ b/kernel/posix-timers.c
@@ -41,6 +41,7 @@
 #include <linux/init.h>
 #include <linux/compiler.h>
 #include <linux/idr.h>
+#include <linux/posix-clock.h>
 #include <linux/posix-timers.h>
 #include <linux/syscalls.h>
 #include <linux/wait.h>
@@ -81,6 +82,14 @@ static DEFINE_SPINLOCK(idr_lock);
 #error "SIGEV_THREAD_ID must not share bit with other SIGEV values!"
 #endif
 
+/*
+ * parisc wants ENOTSUP instead of EOPNOTSUPP
+ */
+#ifndef ENOTSUP
+# define ENANOSLEEP_NOTSUP EOPNOTSUPP
+#else
+# define ENANOSLEEP_NOTSUP ENOTSUP
+#endif
 
 /*
  * The timer ID is turned into a timer address by idr_find().
@@ -94,11 +103,7 @@ static DEFINE_SPINLOCK(idr_lock);
 /*
  * CLOCKs: The POSIX standard calls for a couple of clocks and allows us
  *	    to implement others.  This structure defines the various
- *	    clocks and allows the possibility of adding others.	 We
- *	    provide an interface to add clocks to the table and expect
- *	    the "arch" code to add at least one clock that is high
- *	    resolution.	 Here we define the standard CLOCK_REALTIME as a
- *	    1/HZ resolution clock.
+ *	    clocks.
  *
  * RESOLUTION: Clock resolution is used to round up timer and interval
  *	    times, NOT to report clock times, which are reported with as
@@ -108,20 +113,13 @@ static DEFINE_SPINLOCK(idr_lock);
  *	    necessary code is written.	The standard says we should say
  *	    something about this issue in the documentation...
  *
- * FUNCTIONS: The CLOCKs structure defines possible functions to handle
- *	    various clock functions.  For clocks that use the standard
- *	    system timer code these entries should be NULL.  This will
- *	    allow dispatch without the overhead of indirect function
- *	    calls.  CLOCKS that depend on other sources (e.g. WWV or GPS)
- *	    must supply functions here, even if the function just returns
- *	    ENOSYS.  The standard POSIX timer management code assumes the
- *	    following: 1.) The k_itimer struct (sched.h) is used for the
- *	    timer.  2.) The list, it_lock, it_clock, it_id and it_pid
- *	    fields are not modified by timer code.
+ * FUNCTIONS: The CLOCKs structure defines possible functions to
+ *	    handle various clock functions.
  *
- *          At this time all functions EXCEPT clock_nanosleep can be
- *          redirected by the CLOCKS structure.  Clock_nanosleep is in
- *          there, but the code ignores it.
+ *	    The standard POSIX timer management code assumes the
+ *	    following: 1.) The k_itimer struct (sched.h) is used for
+ *	    the timer.  2.) The list, it_lock, it_clock, it_id and
+ *	    it_pid fields are not modified by timer code.
  *
  * Permissions: It is assumed that the clock_settime() function defined
  *	    for each clock will take care of permission checks.	 Some
@@ -138,6 +136,7 @@ static struct k_clock posix_clocks[MAX_CLOCKS];
  */
 static int common_nsleep(const clockid_t, int flags, struct timespec *t,
 			 struct timespec __user *rmtp);
+static int common_timer_create(struct k_itimer *new_timer);
 static void common_timer_get(struct k_itimer *, struct itimerspec *);
 static int common_timer_set(struct k_itimer *, int,
 			    struct itimerspec *, struct itimerspec *);
@@ -158,76 +157,24 @@ static inline void unlock_timer(struct k_itimer *timr, unsigned long flags)
 	spin_unlock_irqrestore(&timr->it_lock, flags);
 }
 
-/*
- * Call the k_clock hook function if non-null, or the default function.
- */
-#define CLOCK_DISPATCH(clock, call, arglist) \
- 	((clock) < 0 ? posix_cpu_##call arglist : \
- 	 (posix_clocks[clock].call != NULL \
- 	  ? (*posix_clocks[clock].call) arglist : common_##call arglist))
-
-/*
- * Default clock hook functions when the struct k_clock passed
- * to register_posix_clock leaves a function pointer null.
- *
- * The function common_CALL is the default implementation for
- * the function pointer CALL in struct k_clock.
- */
-
-static inline int common_clock_getres(const clockid_t which_clock,
-				      struct timespec *tp)
-{
-	tp->tv_sec = 0;
-	tp->tv_nsec = posix_clocks[which_clock].res;
-	return 0;
-}
-
-/*
- * Get real time for posix timers
- */
-static int common_clock_get(clockid_t which_clock, struct timespec *tp)
+/* Get clock_realtime */
+static int posix_clock_realtime_get(clockid_t which_clock, struct timespec *tp)
 {
 	ktime_get_real_ts(tp);
 	return 0;
 }
 
-static inline int common_clock_set(const clockid_t which_clock,
-				   struct timespec *tp)
+/* Set clock_realtime */
+static int posix_clock_realtime_set(const clockid_t which_clock,
+				    const struct timespec *tp)
 {
 	return do_sys_settimeofday(tp, NULL);
 }
 
-static int common_timer_create(struct k_itimer *new_timer)
-{
-	hrtimer_init(&new_timer->it.real.timer, new_timer->it_clock, 0);
-	return 0;
-}
-
-static int no_timer_create(struct k_itimer *new_timer)
-{
-	return -EOPNOTSUPP;
-}
-
-static int no_nsleep(const clockid_t which_clock, int flags,
-		     struct timespec *tsave, struct timespec __user *rmtp)
-{
-	return -EOPNOTSUPP;
-}
-
-/*
- * Return nonzero if we know a priori this clockid_t value is bogus.
- */
-static inline int invalid_clockid(const clockid_t which_clock)
+static int posix_clock_realtime_adj(const clockid_t which_clock,
+				    struct timex *t)
 {
-	if (which_clock < 0)	/* CPU clock, posix_cpu_* will check it */
-		return 0;
-	if ((unsigned) which_clock >= MAX_CLOCKS)
-		return 1;
-	if (posix_clocks[which_clock].clock_getres != NULL)
-		return 0;
-	if (posix_clocks[which_clock].res != 0)
-		return 0;
-	return 1;
+	return do_adjtimex(t);
 }
 
 /*
@@ -240,7 +187,7 @@ static int posix_ktime_get_ts(clockid_t which_clock, struct timespec *tp)
 }
 
 /*
- * Get monotonic time for posix timers
+ * Get monotonic-raw time for posix timers
  */
 static int posix_get_monotonic_raw(clockid_t which_clock, struct timespec *tp)
 {
@@ -267,46 +214,70 @@ static int posix_get_coarse_res(const clockid_t which_clock, struct timespec *tp
 	*tp = ktime_to_timespec(KTIME_LOW_RES);
 	return 0;
 }
+
+static int posix_get_boottime(const clockid_t which_clock, struct timespec *tp)
+{
+	get_monotonic_boottime(tp);
+	return 0;
+}
+
+
 /*
  * Initialize everything, well, just everything in Posix clocks/timers ;)
  */
 static __init int init_posix_timers(void)
 {
 	struct k_clock clock_realtime = {
-		.clock_getres = hrtimer_get_res,
+		.clock_getres	= hrtimer_get_res,
+		.clock_get	= posix_clock_realtime_get,
+		.clock_set	= posix_clock_realtime_set,
+		.clock_adj	= posix_clock_realtime_adj,
+		.nsleep		= common_nsleep,
+		.nsleep_restart	= hrtimer_nanosleep_restart,
+		.timer_create	= common_timer_create,
+		.timer_set	= common_timer_set,
+		.timer_get	= common_timer_get,
+		.timer_del	= common_timer_del,
 	};
 	struct k_clock clock_monotonic = {
-		.clock_getres = hrtimer_get_res,
-		.clock_get = posix_ktime_get_ts,
-		.clock_set = do_posix_clock_nosettime,
+		.clock_getres	= hrtimer_get_res,
+		.clock_get	= posix_ktime_get_ts,
+		.nsleep		= common_nsleep,
+		.nsleep_restart	= hrtimer_nanosleep_restart,
+		.timer_create	= common_timer_create,
+		.timer_set	= common_timer_set,
+		.timer_get	= common_timer_get,
+		.timer_del	= common_timer_del,
 	};
 	struct k_clock clock_monotonic_raw = {
-		.clock_getres = hrtimer_get_res,
-		.clock_get = posix_get_monotonic_raw,
-		.clock_set = do_posix_clock_nosettime,
-		.timer_create = no_timer_create,
-		.nsleep = no_nsleep,
+		.clock_getres	= hrtimer_get_res,
+		.clock_get	= posix_get_monotonic_raw,
 	};
 	struct k_clock clock_realtime_coarse = {
-		.clock_getres = posix_get_coarse_res,
-		.clock_get = posix_get_realtime_coarse,
-		.clock_set = do_posix_clock_nosettime,
-		.timer_create = no_timer_create,
-		.nsleep = no_nsleep,
+		.clock_getres	= posix_get_coarse_res,
+		.clock_get	= posix_get_realtime_coarse,
 	};
 	struct k_clock clock_monotonic_coarse = {
-		.clock_getres = posix_get_coarse_res,
-		.clock_get = posix_get_monotonic_coarse,
-		.clock_set = do_posix_clock_nosettime,
-		.timer_create = no_timer_create,
-		.nsleep = no_nsleep,
+		.clock_getres	= posix_get_coarse_res,
+		.clock_get	= posix_get_monotonic_coarse,
+	};
+	struct k_clock clock_boottime = {
+		.clock_getres	= hrtimer_get_res,
+		.clock_get	= posix_get_boottime,
+		.nsleep		= common_nsleep,
+		.nsleep_restart	= hrtimer_nanosleep_restart,
+		.timer_create	= common_timer_create,
+		.timer_set	= common_timer_set,
+		.timer_get	= common_timer_get,
+		.timer_del	= common_timer_del,
 	};
 
-	register_posix_clock(CLOCK_REALTIME, &clock_realtime);
-	register_posix_clock(CLOCK_MONOTONIC, &clock_monotonic);
-	register_posix_clock(CLOCK_MONOTONIC_RAW, &clock_monotonic_raw);
-	register_posix_clock(CLOCK_REALTIME_COARSE, &clock_realtime_coarse);
-	register_posix_clock(CLOCK_MONOTONIC_COARSE, &clock_monotonic_coarse);
+	posix_timers_register_clock(CLOCK_REALTIME, &clock_realtime);
+	posix_timers_register_clock(CLOCK_MONOTONIC, &clock_monotonic);
+	posix_timers_register_clock(CLOCK_MONOTONIC_RAW, &clock_monotonic_raw);
+	posix_timers_register_clock(CLOCK_REALTIME_COARSE, &clock_realtime_coarse);
+	posix_timers_register_clock(CLOCK_MONOTONIC_COARSE, &clock_monotonic_coarse);
+	posix_timers_register_clock(CLOCK_BOOTTIME, &clock_boottime);
 
 	posix_timers_cache = kmem_cache_create("posix_timers_cache",
 					sizeof (struct k_itimer), 0, SLAB_PANIC,
@@ -482,17 +453,29 @@ static struct pid *good_sigevent(sigevent_t * event)
 	return task_pid(rtn);
 }
 
-void register_posix_clock(const clockid_t clock_id, struct k_clock *new_clock)
+void posix_timers_register_clock(const clockid_t clock_id,
+				 struct k_clock *new_clock)
 {
 	if ((unsigned) clock_id >= MAX_CLOCKS) {
-		printk("POSIX clock register failed for clock_id %d\n",
+		printk(KERN_WARNING "POSIX clock register failed for clock_id %d\n",
+		       clock_id);
+		return;
+	}
+
+	if (!new_clock->clock_get) {
+		printk(KERN_WARNING "POSIX clock id %d lacks clock_get()\n",
+		       clock_id);
+		return;
+	}
+	if (!new_clock->clock_getres) {
+		printk(KERN_WARNING "POSIX clock id %d lacks clock_getres()\n",
 		       clock_id);
 		return;
 	}
 
 	posix_clocks[clock_id] = *new_clock;
 }
-EXPORT_SYMBOL_GPL(register_posix_clock);
+EXPORT_SYMBOL_GPL(posix_timers_register_clock);
 
 static struct k_itimer * alloc_posix_timer(void)
 {
@@ -523,19 +506,39 @@ static void release_posix_timer(struct k_itimer *tmr, int it_id_set)
 	kmem_cache_free(posix_timers_cache, tmr);
 }
 
+static struct k_clock *clockid_to_kclock(const clockid_t id)
+{
+	if (id < 0)
+		return (id & CLOCKFD_MASK) == CLOCKFD ?
+			&clock_posix_dynamic : &clock_posix_cpu;
+
+	if (id >= MAX_CLOCKS || !posix_clocks[id].clock_getres)
+		return NULL;
+	return &posix_clocks[id];
+}
+
+static int common_timer_create(struct k_itimer *new_timer)
+{
+	hrtimer_init(&new_timer->it.real.timer, new_timer->it_clock, 0);
+	return 0;
+}
+
 /* Create a POSIX.1b interval timer. */
 
 SYSCALL_DEFINE3(timer_create, const clockid_t, which_clock,
 		struct sigevent __user *, timer_event_spec,
 		timer_t __user *, created_timer_id)
 {
+	struct k_clock *kc = clockid_to_kclock(which_clock);
 	struct k_itimer *new_timer;
 	int error, new_timer_id;
 	sigevent_t event;
 	int it_id_set = IT_ID_NOT_SET;
 
-	if (invalid_clockid(which_clock))
+	if (!kc)
 		return -EINVAL;
+	if (!kc->timer_create)
+		return -EOPNOTSUPP;
 
 	new_timer = alloc_posix_timer();
 	if (unlikely(!new_timer))
@@ -597,7 +600,7 @@ SYSCALL_DEFINE3(timer_create, const clockid_t, which_clock,
 		goto out;
 	}
 
-	error = CLOCK_DISPATCH(which_clock, timer_create, (new_timer));
+	error = kc->timer_create(new_timer);
 	if (error)
 		goto out;
 
@@ -607,7 +610,7 @@ SYSCALL_DEFINE3(timer_create, const clockid_t, which_clock,
 	spin_unlock_irq(&current->sighand->siglock);
 
 	return 0;
- 	/*
+	/*
 	 * In the case of the timer belonging to another task, after
 	 * the task is unlocked, the timer is owned by the other task
 	 * and may cease to exist at any time.  Don't use or modify
@@ -709,22 +712,28 @@ common_timer_get(struct k_itimer *timr, struct itimerspec *cur_setting)
 SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id,
 		struct itimerspec __user *, setting)
 {
-	struct k_itimer *timr;
 	struct itimerspec cur_setting;
+	struct k_itimer *timr;
+	struct k_clock *kc;
 	unsigned long flags;
+	int ret = 0;
 
 	timr = lock_timer(timer_id, &flags);
 	if (!timr)
 		return -EINVAL;
 
-	CLOCK_DISPATCH(timr->it_clock, timer_get, (timr, &cur_setting));
+	kc = clockid_to_kclock(timr->it_clock);
+	if (WARN_ON_ONCE(!kc || !kc->timer_get))
+		ret = -EINVAL;
+	else
+		kc->timer_get(timr, &cur_setting);
 
 	unlock_timer(timr, flags);
 
-	if (copy_to_user(setting, &cur_setting, sizeof (cur_setting)))
+	if (!ret && copy_to_user(setting, &cur_setting, sizeof (cur_setting)))
 		return -EFAULT;
 
-	return 0;
+	return ret;
 }
 
 /*
@@ -813,6 +822,7 @@ SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags,
 	int error = 0;
 	unsigned long flag;
 	struct itimerspec *rtn = old_setting ? &old_spec : NULL;
+	struct k_clock *kc;
 
 	if (!new_setting)
 		return -EINVAL;
@@ -828,8 +838,11 @@ retry:
 	if (!timr)
 		return -EINVAL;
 
-	error = CLOCK_DISPATCH(timr->it_clock, timer_set,
-			       (timr, flags, &new_spec, rtn));
+	kc = clockid_to_kclock(timr->it_clock);
+	if (WARN_ON_ONCE(!kc || !kc->timer_set))
+		error = -EINVAL;
+	else
+		error = kc->timer_set(timr, flags, &new_spec, rtn);
 
 	unlock_timer(timr, flag);
 	if (error == TIMER_RETRY) {
@@ -844,7 +857,7 @@ retry:
 	return error;
 }
 
-static inline int common_timer_del(struct k_itimer *timer)
+static int common_timer_del(struct k_itimer *timer)
 {
 	timer->it.real.interval.tv64 = 0;
 
@@ -855,7 +868,11 @@ static inline int common_timer_del(struct k_itimer *timer)
 
 static inline int timer_delete_hook(struct k_itimer *timer)
 {
-	return CLOCK_DISPATCH(timer->it_clock, timer_del, (timer));
+	struct k_clock *kc = clockid_to_kclock(timer->it_clock);
+
+	if (WARN_ON_ONCE(!kc || !kc->timer_del))
+		return -EINVAL;
+	return kc->timer_del(timer);
 }
 
 /* Delete a POSIX.1b interval timer. */
@@ -927,69 +944,76 @@ void exit_itimers(struct signal_struct *sig)
 	}
 }
 
-/* Not available / possible... functions */
-int do_posix_clock_nosettime(const clockid_t clockid, struct timespec *tp)
-{
-	return -EINVAL;
-}
-EXPORT_SYMBOL_GPL(do_posix_clock_nosettime);
-
-int do_posix_clock_nonanosleep(const clockid_t clock, int flags,
-			       struct timespec *t, struct timespec __user *r)
-{
-#ifndef ENOTSUP
-	return -EOPNOTSUPP;	/* aka ENOTSUP in userland for POSIX */
-#else  /*  parisc does define it separately.  */
-	return -ENOTSUP;
-#endif
-}
-EXPORT_SYMBOL_GPL(do_posix_clock_nonanosleep);
-
 SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock,
 		const struct timespec __user *, tp)
 {
+	struct k_clock *kc = clockid_to_kclock(which_clock);
 	struct timespec new_tp;
 
-	if (invalid_clockid(which_clock))
+	if (!kc || !kc->clock_set)
 		return -EINVAL;
+
 	if (copy_from_user(&new_tp, tp, sizeof (*tp)))
 		return -EFAULT;
 
-	return CLOCK_DISPATCH(which_clock, clock_set, (which_clock, &new_tp));
+	return kc->clock_set(which_clock, &new_tp);
 }
 
 SYSCALL_DEFINE2(clock_gettime, const clockid_t, which_clock,
 		struct timespec __user *,tp)
 {
+	struct k_clock *kc = clockid_to_kclock(which_clock);
 	struct timespec kernel_tp;
 	int error;
 
-	if (invalid_clockid(which_clock))
+	if (!kc)
 		return -EINVAL;
-	error = CLOCK_DISPATCH(which_clock, clock_get,
-			       (which_clock, &kernel_tp));
+
+	error = kc->clock_get(which_clock, &kernel_tp);
+
 	if (!error && copy_to_user(tp, &kernel_tp, sizeof (kernel_tp)))
 		error = -EFAULT;
 
 	return error;
+}
+
+SYSCALL_DEFINE2(clock_adjtime, const clockid_t, which_clock,
+		struct timex __user *, utx)
+{
+	struct k_clock *kc = clockid_to_kclock(which_clock);
+	struct timex ktx;
+	int err;
+
+	if (!kc)
+		return -EINVAL;
+	if (!kc->clock_adj)
+		return -EOPNOTSUPP;
+
+	if (copy_from_user(&ktx, utx, sizeof(ktx)))
+		return -EFAULT;
+
+	err = kc->clock_adj(which_clock, &ktx);
+
+	if (!err && copy_to_user(utx, &ktx, sizeof(ktx)))
+		return -EFAULT;
 
+	return err;
 }
 
 SYSCALL_DEFINE2(clock_getres, const clockid_t, which_clock,
 		struct timespec __user *, tp)
 {
+	struct k_clock *kc = clockid_to_kclock(which_clock);
 	struct timespec rtn_tp;
 	int error;
 
-	if (invalid_clockid(which_clock))
+	if (!kc)
 		return -EINVAL;
 
-	error = CLOCK_DISPATCH(which_clock, clock_getres,
-			       (which_clock, &rtn_tp));
+	error = kc->clock_getres(which_clock, &rtn_tp);
 
-	if (!error && tp && copy_to_user(tp, &rtn_tp, sizeof (rtn_tp))) {
+	if (!error && tp && copy_to_user(tp, &rtn_tp, sizeof (rtn_tp)))
 		error = -EFAULT;
-	}
 
 	return error;
 }
@@ -1009,10 +1033,13 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
 		const struct timespec __user *, rqtp,
 		struct timespec __user *, rmtp)
 {
+	struct k_clock *kc = clockid_to_kclock(which_clock);
 	struct timespec t;
 
-	if (invalid_clockid(which_clock))
+	if (!kc)
 		return -EINVAL;
+	if (!kc->nsleep)
+		return -ENANOSLEEP_NOTSUP;
 
 	if (copy_from_user(&t, rqtp, sizeof (struct timespec)))
 		return -EFAULT;
@@ -1020,27 +1047,20 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
 	if (!timespec_valid(&t))
 		return -EINVAL;
 
-	return CLOCK_DISPATCH(which_clock, nsleep,
-			      (which_clock, flags, &t, rmtp));
-}
-
-/*
- * nanosleep_restart for monotonic and realtime clocks
- */
-static int common_nsleep_restart(struct restart_block *restart_block)
-{
-	return hrtimer_nanosleep_restart(restart_block);
+	return kc->nsleep(which_clock, flags, &t, rmtp);
 }
 
 /*
  * This will restart clock_nanosleep. This is required only by
  * compat_clock_nanosleep_restart for now.
  */
-long
-clock_nanosleep_restart(struct restart_block *restart_block)
+long clock_nanosleep_restart(struct restart_block *restart_block)
 {
-	clockid_t which_clock = restart_block->arg0;
+	clockid_t which_clock = restart_block->nanosleep.index;
+	struct k_clock *kc = clockid_to_kclock(which_clock);
+
+	if (WARN_ON_ONCE(!kc || !kc->nsleep_restart))
+		return -EINVAL;
 
-	return CLOCK_DISPATCH(which_clock, nsleep_restart,
-			      (restart_block));
+	return kc->nsleep_restart(restart_block);
 }
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index a23a57a976d1..f3240e987928 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -214,11 +214,12 @@ static int rcuhead_fixup_free(void *addr, enum debug_obj_state state)
 		 * Ensure that queued callbacks are all executed.
 		 * If we detect that we are nested in a RCU read-side critical
 		 * section, we should simply fail, otherwise we would deadlock.
+		 * Note that the machinery to reliably determine whether
+		 * or not we are in an RCU read-side critical section
+		 * exists only in the preemptible RCU implementations
+		 * (TINY_PREEMPT_RCU and TREE_PREEMPT_RCU), which is why
+		 * DEBUG_OBJECTS_RCU_HEAD is disallowed if !PREEMPT.
 		 */
-#ifndef CONFIG_PREEMPT
-		WARN_ON(1);
-		return 0;
-#else
 		if (rcu_preempt_depth() != 0 || preempt_count() != 0 ||
 		    irqs_disabled()) {
 			WARN_ON(1);
@@ -229,7 +230,6 @@ static int rcuhead_fixup_free(void *addr, enum debug_obj_state state)
 		rcu_barrier_bh();
 		debug_object_free(head, &rcuhead_debug_descr);
 		return 1;
-#endif
 	default:
 		return 0;
 	}
diff --git a/kernel/rcutiny_plugin.h b/kernel/rcutiny_plugin.h
index 015abaea962a..3cb8e362e883 100644
--- a/kernel/rcutiny_plugin.h
+++ b/kernel/rcutiny_plugin.h
@@ -852,7 +852,7 @@ void exit_rcu(void)
 	if (t->rcu_read_lock_nesting == 0)
 		return;
 	t->rcu_read_lock_nesting = 1;
-	rcu_read_unlock();
+	__rcu_read_unlock();
 }
 
 #else /* #ifdef CONFIG_TINY_PREEMPT_RCU */
diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c
index 89613f97ff26..c224da41890c 100644
--- a/kernel/rcutorture.c
+++ b/kernel/rcutorture.c
@@ -47,7 +47,6 @@
 #include <linux/srcu.h>
 #include <linux/slab.h>
 #include <asm/byteorder.h>
-#include <linux/sched.h>
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and "
diff --git a/kernel/rtmutex-debug.c b/kernel/rtmutex-debug.c
index ddabb54bb5c8..3c7cbc2c33be 100644
--- a/kernel/rtmutex-debug.c
+++ b/kernel/rtmutex-debug.c
@@ -215,7 +215,6 @@ void debug_rt_mutex_free_waiter(struct rt_mutex_waiter *waiter)
 	put_pid(waiter->deadlock_task_pid);
 	TRACE_WARN_ON(!plist_node_empty(&waiter->list_entry));
 	TRACE_WARN_ON(!plist_node_empty(&waiter->pi_list_entry));
-	TRACE_WARN_ON(waiter->task);
 	memset(waiter, 0x22, sizeof(*waiter));
 }
 
diff --git a/kernel/rtmutex-tester.c b/kernel/rtmutex-tester.c
index 66cb89bc5ef1..5c9ccd380966 100644
--- a/kernel/rtmutex-tester.c
+++ b/kernel/rtmutex-tester.c
@@ -9,7 +9,6 @@
 #include <linux/kthread.h>
 #include <linux/module.h>
 #include <linux/sched.h>
-#include <linux/smp_lock.h>
 #include <linux/spinlock.h>
 #include <linux/sysdev.h>
 #include <linux/timer.h>
@@ -27,7 +26,6 @@ struct test_thread_data {
 	int			opcode;
 	int			opdata;
 	int			mutexes[MAX_RT_TEST_MUTEXES];
-	int			bkl;
 	int			event;
 	struct sys_device	sysdev;
 };
@@ -46,9 +44,8 @@ enum test_opcodes {
 	RTTEST_LOCKINTNOWAIT,	/* 6 Lock interruptible no wait in wakeup, data = lockindex */
 	RTTEST_LOCKCONT,	/* 7 Continue locking after the wakeup delay */
 	RTTEST_UNLOCK,		/* 8 Unlock, data = lockindex */
-	RTTEST_LOCKBKL,		/* 9 Lock BKL */
-	RTTEST_UNLOCKBKL,	/* 10 Unlock BKL */
-	RTTEST_SIGNAL,		/* 11 Signal other test thread, data = thread id */
+	/* 9, 10 - reserved for BKL commemoration */
+	RTTEST_SIGNAL = 11,	/* 11 Signal other test thread, data = thread id */
 	RTTEST_RESETEVENT = 98,	/* 98 Reset event counter */
 	RTTEST_RESET = 99,	/* 99 Reset all pending operations */
 };
@@ -74,13 +71,6 @@ static int handle_op(struct test_thread_data *td, int lockwakeup)
 				td->mutexes[i] = 0;
 			}
 		}
-
-		if (!lockwakeup && td->bkl == 4) {
-#ifdef CONFIG_LOCK_KERNEL
-			unlock_kernel();
-#endif
-			td->bkl = 0;
-		}
 		return 0;
 
 	case RTTEST_RESETEVENT:
@@ -131,25 +121,6 @@ static int handle_op(struct test_thread_data *td, int lockwakeup)
 		td->mutexes[id] = 0;
 		return 0;
 
-	case RTTEST_LOCKBKL:
-		if (td->bkl)
-			return 0;
-		td->bkl = 1;
-#ifdef CONFIG_LOCK_KERNEL
-		lock_kernel();
-#endif
-		td->bkl = 4;
-		return 0;
-
-	case RTTEST_UNLOCKBKL:
-		if (td->bkl != 4)
-			break;
-#ifdef CONFIG_LOCK_KERNEL
-		unlock_kernel();
-#endif
-		td->bkl = 0;
-		return 0;
-
 	default:
 		break;
 	}
@@ -196,7 +167,6 @@ void schedule_rt_mutex_test(struct rt_mutex *mutex)
 		td->event = atomic_add_return(1, &rttest_event);
 		break;
 
-	case RTTEST_LOCKBKL:
 	default:
 		break;
 	}
@@ -229,8 +199,6 @@ void schedule_rt_mutex_test(struct rt_mutex *mutex)
 		td->event = atomic_add_return(1, &rttest_event);
 		return;
 
-	case RTTEST_LOCKBKL:
-		return;
 	default:
 		return;
 	}
@@ -380,11 +348,11 @@ static ssize_t sysfs_test_status(struct sys_device *dev, struct sysdev_attribute
 	spin_lock(&rttest_lock);
 
 	curr += sprintf(curr,
-		"O: %4d, E:%8d, S: 0x%08lx, P: %4d, N: %4d, B: %p, K: %d, M:",
+		"O: %4d, E:%8d, S: 0x%08lx, P: %4d, N: %4d, B: %p, M:",
 		td->opcode, td->event, tsk->state,
 			(MAX_RT_PRIO - 1) - tsk->prio,
 			(MAX_RT_PRIO - 1) - tsk->normal_prio,
-		tsk->pi_blocked_on, td->bkl);
+		tsk->pi_blocked_on);
 
 	for (i = MAX_RT_TEST_MUTEXES - 1; i >=0 ; i--)
 		curr += sprintf(curr, "%d", td->mutexes[i]);
diff --git a/kernel/rtmutex.c b/kernel/rtmutex.c
index a9604815786a..ab449117aaf2 100644
--- a/kernel/rtmutex.c
+++ b/kernel/rtmutex.c
@@ -20,41 +20,34 @@
 /*
  * lock->owner state tracking:
  *
- * lock->owner holds the task_struct pointer of the owner. Bit 0 and 1
- * are used to keep track of the "owner is pending" and "lock has
- * waiters" state.
+ * lock->owner holds the task_struct pointer of the owner. Bit 0
+ * is used to keep track of the "lock has waiters" state.
  *
- * owner	bit1	bit0
- * NULL		0	0	lock is free (fast acquire possible)
- * NULL		0	1	invalid state
- * NULL		1	0	Transitional State*
- * NULL		1	1	invalid state
- * taskpointer	0	0	lock is held (fast release possible)
- * taskpointer	0	1	task is pending owner
- * taskpointer	1	0	lock is held and has waiters
- * taskpointer	1	1	task is pending owner and lock has more waiters
- *
- * Pending ownership is assigned to the top (highest priority)
- * waiter of the lock, when the lock is released. The thread is woken
- * up and can now take the lock. Until the lock is taken (bit 0
- * cleared) a competing higher priority thread can steal the lock
- * which puts the woken up thread back on the waiters list.
+ * owner	bit0
+ * NULL		0	lock is free (fast acquire possible)
+ * NULL		1	lock is free and has waiters and the top waiter
+ *				is going to take the lock*
+ * taskpointer	0	lock is held (fast release possible)
+ * taskpointer	1	lock is held and has waiters**
  *
  * The fast atomic compare exchange based acquire and release is only
- * possible when bit 0 and 1 of lock->owner are 0.
+ * possible when bit 0 of lock->owner is 0.
+ *
+ * (*) It also can be a transitional state when grabbing the lock
+ * with ->wait_lock is held. To prevent any fast path cmpxchg to the lock,
+ * we need to set the bit0 before looking at the lock, and the owner may be
+ * NULL in this small time, hence this can be a transitional state.
  *
- * (*) There's a small time where the owner can be NULL and the
- * "lock has waiters" bit is set.  This can happen when grabbing the lock.
- * To prevent a cmpxchg of the owner releasing the lock, we need to set this
- * bit before looking at the lock, hence the reason this is a transitional
- * state.
+ * (**) There is a small time when bit 0 is set but there are no
+ * waiters. This can happen when grabbing the lock in the slow path.
+ * To prevent a cmpxchg of the owner releasing the lock, we need to
+ * set this bit before looking at the lock.
  */
 
 static void
-rt_mutex_set_owner(struct rt_mutex *lock, struct task_struct *owner,
-		   unsigned long mask)
+rt_mutex_set_owner(struct rt_mutex *lock, struct task_struct *owner)
 {
-	unsigned long val = (unsigned long)owner | mask;
+	unsigned long val = (unsigned long)owner;
 
 	if (rt_mutex_has_waiters(lock))
 		val |= RT_MUTEX_HAS_WAITERS;
@@ -203,15 +196,14 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 	 * reached or the state of the chain has changed while we
 	 * dropped the locks.
 	 */
-	if (!waiter || !waiter->task)
+	if (!waiter)
 		goto out_unlock_pi;
 
 	/*
 	 * Check the orig_waiter state. After we dropped the locks,
-	 * the previous owner of the lock might have released the lock
-	 * and made us the pending owner:
+	 * the previous owner of the lock might have released the lock.
 	 */
-	if (orig_waiter && !orig_waiter->task)
+	if (orig_waiter && !rt_mutex_owner(orig_lock))
 		goto out_unlock_pi;
 
 	/*
@@ -254,6 +246,17 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 
 	/* Release the task */
 	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+	if (!rt_mutex_owner(lock)) {
+		/*
+		 * If the requeue above changed the top waiter, then we need
+		 * to wake the new top waiter up to try to get the lock.
+		 */
+
+		if (top_waiter != rt_mutex_top_waiter(lock))
+			wake_up_process(rt_mutex_top_waiter(lock)->task);
+		raw_spin_unlock(&lock->wait_lock);
+		goto out_put_task;
+	}
 	put_task_struct(task);
 
 	/* Grab the next task */
@@ -296,78 +299,16 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 }
 
 /*
- * Optimization: check if we can steal the lock from the
- * assigned pending owner [which might not have taken the
- * lock yet]:
- */
-static inline int try_to_steal_lock(struct rt_mutex *lock,
-				    struct task_struct *task)
-{
-	struct task_struct *pendowner = rt_mutex_owner(lock);
-	struct rt_mutex_waiter *next;
-	unsigned long flags;
-
-	if (!rt_mutex_owner_pending(lock))
-		return 0;
-
-	if (pendowner == task)
-		return 1;
-
-	raw_spin_lock_irqsave(&pendowner->pi_lock, flags);
-	if (task->prio >= pendowner->prio) {
-		raw_spin_unlock_irqrestore(&pendowner->pi_lock, flags);
-		return 0;
-	}
-
-	/*
-	 * Check if a waiter is enqueued on the pending owners
-	 * pi_waiters list. Remove it and readjust pending owners
-	 * priority.
-	 */
-	if (likely(!rt_mutex_has_waiters(lock))) {
-		raw_spin_unlock_irqrestore(&pendowner->pi_lock, flags);
-		return 1;
-	}
-
-	/* No chain handling, pending owner is not blocked on anything: */
-	next = rt_mutex_top_waiter(lock);
-	plist_del(&next->pi_list_entry, &pendowner->pi_waiters);
-	__rt_mutex_adjust_prio(pendowner);
-	raw_spin_unlock_irqrestore(&pendowner->pi_lock, flags);
-
-	/*
-	 * We are going to steal the lock and a waiter was
-	 * enqueued on the pending owners pi_waiters queue. So
-	 * we have to enqueue this waiter into
-	 * task->pi_waiters list. This covers the case,
-	 * where task is boosted because it holds another
-	 * lock and gets unboosted because the booster is
-	 * interrupted, so we would delay a waiter with higher
-	 * priority as task->normal_prio.
-	 *
-	 * Note: in the rare case of a SCHED_OTHER task changing
-	 * its priority and thus stealing the lock, next->task
-	 * might be task:
-	 */
-	if (likely(next->task != task)) {
-		raw_spin_lock_irqsave(&task->pi_lock, flags);
-		plist_add(&next->pi_list_entry, &task->pi_waiters);
-		__rt_mutex_adjust_prio(task);
-		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
-	}
-	return 1;
-}
-
-/*
  * Try to take an rt-mutex
  *
- * This fails
- * - when the lock has a real owner
- * - when a different pending owner exists and has higher priority than current
- *
  * Must be called with lock->wait_lock held.
+ *
+ * @lock:   the lock to be acquired.
+ * @task:   the task which wants to acquire the lock
+ * @waiter: the waiter that is queued to the lock's wait list. (could be NULL)
  */
-static int try_to_take_rt_mutex(struct rt_mutex *lock)
+static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
+		struct rt_mutex_waiter *waiter)
 {
 	/*
 	 * We have to be careful here if the atomic speedups are
@@ -390,15 +331,52 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock)
 	 */
 	mark_rt_mutex_waiters(lock);
 
-	if (rt_mutex_owner(lock) && !try_to_steal_lock(lock, current))
+	if (rt_mutex_owner(lock))
 		return 0;
 
+	/*
+	 * It will get the lock because of one of these conditions:
+	 * 1) there is no waiter
+	 * 2) higher priority than waiters
+	 * 3) it is top waiter
+	 */
+	if (rt_mutex_has_waiters(lock)) {
+		if (task->prio >= rt_mutex_top_waiter(lock)->list_entry.prio) {
+			if (!waiter || waiter != rt_mutex_top_waiter(lock))
+				return 0;
+		}
+	}
+
+	if (waiter || rt_mutex_has_waiters(lock)) {
+		unsigned long flags;
+		struct rt_mutex_waiter *top;
+
+		raw_spin_lock_irqsave(&task->pi_lock, flags);
+
+		/* remove the queued waiter. */
+		if (waiter) {
+			plist_del(&waiter->list_entry, &lock->wait_list);
+			task->pi_blocked_on = NULL;
+		}
+
+		/*
+		 * We have to enqueue the top waiter(if it exists) into
+		 * task->pi_waiters list.
+		 */
+		if (rt_mutex_has_waiters(lock)) {
+			top = rt_mutex_top_waiter(lock);
+			top->pi_list_entry.prio = top->list_entry.prio;
+			plist_add(&top->pi_list_entry, &task->pi_waiters);
+		}
+		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+	}
+
 	/* We got the lock. */
 	debug_rt_mutex_lock(lock);
 
-	rt_mutex_set_owner(lock, current, 0);
+	rt_mutex_set_owner(lock, task);
 
-	rt_mutex_deadlock_account_lock(lock, current);
+	rt_mutex_deadlock_account_lock(lock, task);
 
 	return 1;
 }
@@ -436,6 +414,9 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 
 	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 
+	if (!owner)
+		return 0;
+
 	if (waiter == rt_mutex_top_waiter(lock)) {
 		raw_spin_lock_irqsave(&owner->pi_lock, flags);
 		plist_del(&top_waiter->pi_list_entry, &owner->pi_waiters);
@@ -472,21 +453,18 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 /*
  * Wake up the next waiter on the lock.
  *
- * Remove the top waiter from the current tasks waiter list and from
- * the lock waiter list. Set it as pending owner. Then wake it up.
+ * Remove the top waiter from the current tasks waiter list and wake it up.
  *
  * Called with lock->wait_lock held.
  */
 static void wakeup_next_waiter(struct rt_mutex *lock)
 {
 	struct rt_mutex_waiter *waiter;
-	struct task_struct *pendowner;
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&current->pi_lock, flags);
 
 	waiter = rt_mutex_top_waiter(lock);
-	plist_del(&waiter->list_entry, &lock->wait_list);
 
 	/*
 	 * Remove it from current->pi_waiters. We do not adjust a
@@ -495,43 +473,19 @@ static void wakeup_next_waiter(struct rt_mutex *lock)
 	 * lock->wait_lock.
 	 */
 	plist_del(&waiter->pi_list_entry, &current->pi_waiters);
-	pendowner = waiter->task;
-	waiter->task = NULL;
 
-	rt_mutex_set_owner(lock, pendowner, RT_MUTEX_OWNER_PENDING);
+	rt_mutex_set_owner(lock, NULL);
 
 	raw_spin_unlock_irqrestore(&current->pi_lock, flags);
 
-	/*
-	 * Clear the pi_blocked_on variable and enqueue a possible
-	 * waiter into the pi_waiters list of the pending owner. This
-	 * prevents that in case the pending owner gets unboosted a
-	 * waiter with higher priority than pending-owner->normal_prio
-	 * is blocked on the unboosted (pending) owner.
-	 */
-	raw_spin_lock_irqsave(&pendowner->pi_lock, flags);
-
-	WARN_ON(!pendowner->pi_blocked_on);
-	WARN_ON(pendowner->pi_blocked_on != waiter);
-	WARN_ON(pendowner->pi_blocked_on->lock != lock);
-
-	pendowner->pi_blocked_on = NULL;
-
-	if (rt_mutex_has_waiters(lock)) {
-		struct rt_mutex_waiter *next;
-
-		next = rt_mutex_top_waiter(lock);
-		plist_add(&next->pi_list_entry, &pendowner->pi_waiters);
-	}
-	raw_spin_unlock_irqrestore(&pendowner->pi_lock, flags);
-
-	wake_up_process(pendowner);
+	wake_up_process(waiter->task);
 }
 
 /*
- * Remove a waiter from a lock
+ * Remove a waiter from a lock and give up
  *
- * Must be called with lock->wait_lock held
+ * Must be called with lock->wait_lock held and
+ * have just failed to try_to_take_rt_mutex().
  */
 static void remove_waiter(struct rt_mutex *lock,
 			  struct rt_mutex_waiter *waiter)
@@ -543,11 +497,13 @@ static void remove_waiter(struct rt_mutex *lock,
 
 	raw_spin_lock_irqsave(&current->pi_lock, flags);
 	plist_del(&waiter->list_entry, &lock->wait_list);
-	waiter->task = NULL;
 	current->pi_blocked_on = NULL;
 	raw_spin_unlock_irqrestore(&current->pi_lock, flags);
 
-	if (first && owner != current) {
+	if (!owner)
+		return;
+
+	if (first) {
 
 		raw_spin_lock_irqsave(&owner->pi_lock, flags);
 
@@ -614,21 +570,19 @@ void rt_mutex_adjust_pi(struct task_struct *task)
  * 			 or TASK_UNINTERRUPTIBLE)
  * @timeout:		 the pre-initialized and started timer, or NULL for none
  * @waiter:		 the pre-initialized rt_mutex_waiter
- * @detect_deadlock:	 passed to task_blocks_on_rt_mutex
  *
  * lock->wait_lock must be held by the caller.
  */
 static int __sched
 __rt_mutex_slowlock(struct rt_mutex *lock, int state,
 		    struct hrtimer_sleeper *timeout,
-		    struct rt_mutex_waiter *waiter,
-		    int detect_deadlock)
+		    struct rt_mutex_waiter *waiter)
 {
 	int ret = 0;
 
 	for (;;) {
 		/* Try to acquire the lock: */
-		if (try_to_take_rt_mutex(lock))
+		if (try_to_take_rt_mutex(lock, current, waiter))
 			break;
 
 		/*
@@ -645,39 +599,11 @@ __rt_mutex_slowlock(struct rt_mutex *lock, int state,
 				break;
 		}
 
-		/*
-		 * waiter->task is NULL the first time we come here and
-		 * when we have been woken up by the previous owner
-		 * but the lock got stolen by a higher prio task.
-		 */
-		if (!waiter->task) {
-			ret = task_blocks_on_rt_mutex(lock, waiter, current,
-						      detect_deadlock);
-			/*
-			 * If we got woken up by the owner then start loop
-			 * all over without going into schedule to try
-			 * to get the lock now:
-			 */
-			if (unlikely(!waiter->task)) {
-				/*
-				 * Reset the return value. We might
-				 * have returned with -EDEADLK and the
-				 * owner released the lock while we
-				 * were walking the pi chain.
-				 */
-				ret = 0;
-				continue;
-			}
-			if (unlikely(ret))
-				break;
-		}
-
 		raw_spin_unlock(&lock->wait_lock);
 
 		debug_rt_mutex_print_deadlock(waiter);
 
-		if (waiter->task)
-			schedule_rt_mutex(lock);
+		schedule_rt_mutex(lock);
 
 		raw_spin_lock(&lock->wait_lock);
 		set_current_state(state);
@@ -698,12 +624,11 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
 	int ret = 0;
 
 	debug_rt_mutex_init_waiter(&waiter);
-	waiter.task = NULL;
 
 	raw_spin_lock(&lock->wait_lock);
 
 	/* Try to acquire the lock again: */
-	if (try_to_take_rt_mutex(lock)) {
+	if (try_to_take_rt_mutex(lock, current, NULL)) {
 		raw_spin_unlock(&lock->wait_lock);
 		return 0;
 	}
@@ -717,12 +642,14 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
 			timeout->task = NULL;
 	}
 
-	ret = __rt_mutex_slowlock(lock, state, timeout, &waiter,
-				  detect_deadlock);
+	ret = task_blocks_on_rt_mutex(lock, &waiter, current, detect_deadlock);
+
+	if (likely(!ret))
+		ret = __rt_mutex_slowlock(lock, state, timeout, &waiter);
 
 	set_current_state(TASK_RUNNING);
 
-	if (unlikely(waiter.task))
+	if (unlikely(ret))
 		remove_waiter(lock, &waiter);
 
 	/*
@@ -737,14 +664,6 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
 	if (unlikely(timeout))
 		hrtimer_cancel(&timeout->timer);
 
-	/*
-	 * Readjust priority, when we did not get the lock. We might
-	 * have been the pending owner and boosted. Since we did not
-	 * take the lock, the PI boost has to go.
-	 */
-	if (unlikely(ret))
-		rt_mutex_adjust_prio(current);
-
 	debug_rt_mutex_free_waiter(&waiter);
 
 	return ret;
@@ -762,7 +681,7 @@ rt_mutex_slowtrylock(struct rt_mutex *lock)
 
 	if (likely(rt_mutex_owner(lock) != current)) {
 
-		ret = try_to_take_rt_mutex(lock);
+		ret = try_to_take_rt_mutex(lock, current, NULL);
 		/*
 		 * try_to_take_rt_mutex() sets the lock waiters
 		 * bit unconditionally. Clean this up.
@@ -992,7 +911,7 @@ void rt_mutex_init_proxy_locked(struct rt_mutex *lock,
 {
 	__rt_mutex_init(lock, NULL);
 	debug_rt_mutex_proxy_lock(lock, proxy_owner);
-	rt_mutex_set_owner(lock, proxy_owner, 0);
+	rt_mutex_set_owner(lock, proxy_owner);
 	rt_mutex_deadlock_account_lock(lock, proxy_owner);
 }
 
@@ -1008,7 +927,7 @@ void rt_mutex_proxy_unlock(struct rt_mutex *lock,
 			   struct task_struct *proxy_owner)
 {
 	debug_rt_mutex_proxy_unlock(lock);
-	rt_mutex_set_owner(lock, NULL, 0);
+	rt_mutex_set_owner(lock, NULL);
 	rt_mutex_deadlock_account_unlock(proxy_owner);
 }
 
@@ -1034,20 +953,14 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 
 	raw_spin_lock(&lock->wait_lock);
 
-	mark_rt_mutex_waiters(lock);
-
-	if (!rt_mutex_owner(lock) || try_to_steal_lock(lock, task)) {
-		/* We got the lock for task. */
-		debug_rt_mutex_lock(lock);
-		rt_mutex_set_owner(lock, task, 0);
+	if (try_to_take_rt_mutex(lock, task, NULL)) {
 		raw_spin_unlock(&lock->wait_lock);
-		rt_mutex_deadlock_account_lock(lock, task);
 		return 1;
 	}
 
 	ret = task_blocks_on_rt_mutex(lock, waiter, task, detect_deadlock);
 
-	if (ret && !waiter->task) {
+	if (ret && !rt_mutex_owner(lock)) {
 		/*
 		 * Reset the return value. We might have
 		 * returned with -EDEADLK and the owner
@@ -1056,6 +969,10 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 		 */
 		ret = 0;
 	}
+
+	if (unlikely(ret))
+		remove_waiter(lock, waiter);
+
 	raw_spin_unlock(&lock->wait_lock);
 
 	debug_rt_mutex_print_deadlock(waiter);
@@ -1110,12 +1027,11 @@ int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
 
 	set_current_state(TASK_INTERRUPTIBLE);
 
-	ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter,
-				  detect_deadlock);
+	ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter);
 
 	set_current_state(TASK_RUNNING);
 
-	if (unlikely(waiter->task))
+	if (unlikely(ret))
 		remove_waiter(lock, waiter);
 
 	/*
@@ -1126,13 +1042,5 @@ int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
 
 	raw_spin_unlock(&lock->wait_lock);
 
-	/*
-	 * Readjust priority, when we did not get the lock. We might have been
-	 * the pending owner and boosted. Since we did not take the lock, the
-	 * PI boost has to go.
-	 */
-	if (unlikely(ret))
-		rt_mutex_adjust_prio(current);
-
 	return ret;
 }
diff --git a/kernel/rtmutex_common.h b/kernel/rtmutex_common.h
index 97a2f81866af..53a66c85261b 100644
--- a/kernel/rtmutex_common.h
+++ b/kernel/rtmutex_common.h
@@ -91,9 +91,8 @@ task_top_pi_waiter(struct task_struct *p)
 /*
  * lock->owner state tracking:
  */
-#define RT_MUTEX_OWNER_PENDING	1UL
-#define RT_MUTEX_HAS_WAITERS	2UL
-#define RT_MUTEX_OWNER_MASKALL	3UL
+#define RT_MUTEX_HAS_WAITERS	1UL
+#define RT_MUTEX_OWNER_MASKALL	1UL
 
 static inline struct task_struct *rt_mutex_owner(struct rt_mutex *lock)
 {
@@ -101,17 +100,6 @@ static inline struct task_struct *rt_mutex_owner(struct rt_mutex *lock)
 		((unsigned long)lock->owner & ~RT_MUTEX_OWNER_MASKALL);
 }
 
-static inline struct task_struct *rt_mutex_real_owner(struct rt_mutex *lock)
-{
-	return (struct task_struct *)
-		((unsigned long)lock->owner & ~RT_MUTEX_HAS_WAITERS);
-}
-
-static inline unsigned long rt_mutex_owner_pending(struct rt_mutex *lock)
-{
-	return (unsigned long)lock->owner & RT_MUTEX_OWNER_PENDING;
-}
-
 /*
  * PI-futex support (proxy locking functions, etc.):
  */
diff --git a/kernel/sched.c b/kernel/sched.c
index 42eab5a8437d..c8e40b7005c0 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -324,7 +324,7 @@ struct cfs_rq {
 	 * 'curr' points to currently running entity on this cfs_rq.
 	 * It is set to NULL otherwise (i.e when none are currently running).
 	 */
-	struct sched_entity *curr, *next, *last;
+	struct sched_entity *curr, *next, *last, *skip;
 
 	unsigned int nr_spread_over;
 
@@ -606,9 +606,6 @@ static inline struct task_group *task_group(struct task_struct *p)
 	struct task_group *tg;
 	struct cgroup_subsys_state *css;
 
-	if (p->flags & PF_EXITING)
-		return &root_task_group;
-
 	css = task_subsys_state_check(p, cpu_cgroup_subsys_id,
 			lockdep_is_held(&task_rq(p)->lock));
 	tg = container_of(css, struct task_group, css);
@@ -1686,6 +1683,39 @@ static void double_rq_unlock(struct rq *rq1, struct rq *rq2)
 		__release(rq2->lock);
 }
 
+#else /* CONFIG_SMP */
+
+/*
+ * double_rq_lock - safely lock two runqueues
+ *
+ * Note this does not disable interrupts like task_rq_lock,
+ * you need to do so manually before calling.
+ */
+static void double_rq_lock(struct rq *rq1, struct rq *rq2)
+	__acquires(rq1->lock)
+	__acquires(rq2->lock)
+{
+	BUG_ON(!irqs_disabled());
+	BUG_ON(rq1 != rq2);
+	raw_spin_lock(&rq1->lock);
+	__acquire(rq2->lock);	/* Fake it out ;) */
+}
+
+/*
+ * double_rq_unlock - safely unlock two runqueues
+ *
+ * Note this does not restore interrupts like task_rq_unlock,
+ * you need to do so manually after calling.
+ */
+static void double_rq_unlock(struct rq *rq1, struct rq *rq2)
+	__releases(rq1->lock)
+	__releases(rq2->lock)
+{
+	BUG_ON(rq1 != rq2);
+	raw_spin_unlock(&rq1->lock);
+	__release(rq2->lock);
+}
+
 #endif
 
 static void calc_load_account_idle(struct rq *this_rq);
@@ -1880,7 +1910,7 @@ void account_system_vtime(struct task_struct *curr)
 	 */
 	if (hardirq_count())
 		__this_cpu_add(cpu_hardirq_time, delta);
-	else if (in_serving_softirq() && !(curr->flags & PF_KSOFTIRQD))
+	else if (in_serving_softirq() && curr != this_cpu_ksoftirqd())
 		__this_cpu_add(cpu_softirq_time, delta);
 
 	irq_time_write_end();
@@ -1920,8 +1950,40 @@ static void update_rq_clock_task(struct rq *rq, s64 delta)
 		sched_rt_avg_update(rq, irq_delta);
 }
 
+static int irqtime_account_hi_update(void)
+{
+	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
+	unsigned long flags;
+	u64 latest_ns;
+	int ret = 0;
+
+	local_irq_save(flags);
+	latest_ns = this_cpu_read(cpu_hardirq_time);
+	if (cputime64_gt(nsecs_to_cputime64(latest_ns), cpustat->irq))
+		ret = 1;
+	local_irq_restore(flags);
+	return ret;
+}
+
+static int irqtime_account_si_update(void)
+{
+	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
+	unsigned long flags;
+	u64 latest_ns;
+	int ret = 0;
+
+	local_irq_save(flags);
+	latest_ns = this_cpu_read(cpu_softirq_time);
+	if (cputime64_gt(nsecs_to_cputime64(latest_ns), cpustat->softirq))
+		ret = 1;
+	local_irq_restore(flags);
+	return ret;
+}
+
 #else /* CONFIG_IRQ_TIME_ACCOUNTING */
 
+#define sched_clock_irqtime	(0)
+
 static void update_rq_clock_task(struct rq *rq, s64 delta)
 {
 	rq->clock_task += delta;
@@ -2025,14 +2087,14 @@ inline int task_curr(const struct task_struct *p)
 
 static inline void check_class_changed(struct rq *rq, struct task_struct *p,
 				       const struct sched_class *prev_class,
-				       int oldprio, int running)
+				       int oldprio)
 {
 	if (prev_class != p->sched_class) {
 		if (prev_class->switched_from)
-			prev_class->switched_from(rq, p, running);
-		p->sched_class->switched_to(rq, p, running);
-	} else
-		p->sched_class->prio_changed(rq, p, oldprio, running);
+			prev_class->switched_from(rq, p);
+		p->sched_class->switched_to(rq, p);
+	} else if (oldprio != p->prio)
+		p->sched_class->prio_changed(rq, p, oldprio);
 }
 
 static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
@@ -2224,7 +2286,10 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state)
 		 * yield - it could be a while.
 		 */
 		if (unlikely(on_rq)) {
-			schedule_timeout_uninterruptible(1);
+			ktime_t to = ktime_set(0, NSEC_PER_SEC/HZ);
+
+			set_current_state(TASK_UNINTERRUPTIBLE);
+			schedule_hrtimeout(&to, HRTIMER_MODE_REL);
 			continue;
 		}
 
@@ -2265,27 +2330,6 @@ void kick_process(struct task_struct *p)
 EXPORT_SYMBOL_GPL(kick_process);
 #endif /* CONFIG_SMP */
 
-/**
- * task_oncpu_function_call - call a function on the cpu on which a task runs
- * @p:		the task to evaluate
- * @func:	the function to be called
- * @info:	the function call argument
- *
- * Calls the function @func when the task is currently running. This might
- * be on the current CPU, which just calls the function directly
- */
-void task_oncpu_function_call(struct task_struct *p,
-			      void (*func) (void *info), void *info)
-{
-	int cpu;
-
-	preempt_disable();
-	cpu = task_cpu(p);
-	if (task_curr(p))
-		smp_call_function_single(cpu, func, info, 1);
-	preempt_enable();
-}
-
 #ifdef CONFIG_SMP
 /*
  * ->cpus_allowed is protected by either TASK_WAKING or rq->lock held.
@@ -2566,6 +2610,7 @@ static void __sched_fork(struct task_struct *p)
 	p->se.sum_exec_runtime		= 0;
 	p->se.prev_sum_exec_runtime	= 0;
 	p->se.nr_migrations		= 0;
+	p->se.vruntime			= 0;
 
 #ifdef CONFIG_SCHEDSTATS
 	memset(&p->se.statistics, 0, sizeof(p->se.statistics));
@@ -2776,9 +2821,12 @@ static inline void
 prepare_task_switch(struct rq *rq, struct task_struct *prev,
 		    struct task_struct *next)
 {
+	sched_info_switch(prev, next);
+	perf_event_task_sched_out(prev, next);
 	fire_sched_out_preempt_notifiers(prev, next);
 	prepare_lock_switch(rq, next);
 	prepare_arch_switch(next);
+	trace_sched_switch(prev, next);
 }
 
 /**
@@ -2911,7 +2959,7 @@ context_switch(struct rq *rq, struct task_struct *prev,
 	struct mm_struct *mm, *oldmm;
 
 	prepare_task_switch(rq, prev, next);
-	trace_sched_switch(prev, next);
+
 	mm = next->mm;
 	oldmm = prev->active_mm;
 	/*
@@ -3568,6 +3616,32 @@ static void account_guest_time(struct task_struct *p, cputime_t cputime,
 }
 
 /*
+ * Account system cpu time to a process and desired cpustat field
+ * @p: the process that the cpu time gets accounted to
+ * @cputime: the cpu time spent in kernel space since the last update
+ * @cputime_scaled: cputime scaled by cpu frequency
+ * @target_cputime64: pointer to cpustat field that has to be updated
+ */
+static inline
+void __account_system_time(struct task_struct *p, cputime_t cputime,
+			cputime_t cputime_scaled, cputime64_t *target_cputime64)
+{
+	cputime64_t tmp = cputime_to_cputime64(cputime);
+
+	/* Add system time to process. */
+	p->stime = cputime_add(p->stime, cputime);
+	p->stimescaled = cputime_add(p->stimescaled, cputime_scaled);
+	account_group_system_time(p, cputime);
+
+	/* Add system time to cpustat. */
+	*target_cputime64 = cputime64_add(*target_cputime64, tmp);
+	cpuacct_update_stats(p, CPUACCT_STAT_SYSTEM, cputime);
+
+	/* Account for system time used */
+	acct_update_integrals(p);
+}
+
+/*
  * Account system cpu time to a process.
  * @p: the process that the cpu time gets accounted to
  * @hardirq_offset: the offset to subtract from hardirq_count()
@@ -3578,36 +3652,26 @@ void account_system_time(struct task_struct *p, int hardirq_offset,
 			 cputime_t cputime, cputime_t cputime_scaled)
 {
 	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
-	cputime64_t tmp;
+	cputime64_t *target_cputime64;
 
 	if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0)) {
 		account_guest_time(p, cputime, cputime_scaled);
 		return;
 	}
 
-	/* Add system time to process. */
-	p->stime = cputime_add(p->stime, cputime);
-	p->stimescaled = cputime_add(p->stimescaled, cputime_scaled);
-	account_group_system_time(p, cputime);
-
-	/* Add system time to cpustat. */
-	tmp = cputime_to_cputime64(cputime);
 	if (hardirq_count() - hardirq_offset)
-		cpustat->irq = cputime64_add(cpustat->irq, tmp);
+		target_cputime64 = &cpustat->irq;
 	else if (in_serving_softirq())
-		cpustat->softirq = cputime64_add(cpustat->softirq, tmp);
+		target_cputime64 = &cpustat->softirq;
 	else
-		cpustat->system = cputime64_add(cpustat->system, tmp);
+		target_cputime64 = &cpustat->system;
 
-	cpuacct_update_stats(p, CPUACCT_STAT_SYSTEM, cputime);
-
-	/* Account for system time used */
-	acct_update_integrals(p);
+	__account_system_time(p, cputime, cputime_scaled, target_cputime64);
 }
 
 /*
  * Account for involuntary wait time.
- * @steal: the cpu time spent in involuntary wait
+ * @cputime: the cpu time spent in involuntary wait
  */
 void account_steal_time(cputime_t cputime)
 {
@@ -3635,6 +3699,73 @@ void account_idle_time(cputime_t cputime)
 
 #ifndef CONFIG_VIRT_CPU_ACCOUNTING
 
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+/*
+ * Account a tick to a process and cpustat
+ * @p: the process that the cpu time gets accounted to
+ * @user_tick: is the tick from userspace
+ * @rq: the pointer to rq
+ *
+ * Tick demultiplexing follows the order
+ * - pending hardirq update
+ * - pending softirq update
+ * - user_time
+ * - idle_time
+ * - system time
+ *   - check for guest_time
+ *   - else account as system_time
+ *
+ * Check for hardirq is done both for system and user time as there is
+ * no timer going off while we are on hardirq and hence we may never get an
+ * opportunity to update it solely in system time.
+ * p->stime and friends are only updated on system time and not on irq
+ * softirq as those do not count in task exec_runtime any more.
+ */
+static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
+						struct rq *rq)
+{
+	cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
+	cputime64_t tmp = cputime_to_cputime64(cputime_one_jiffy);
+	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
+
+	if (irqtime_account_hi_update()) {
+		cpustat->irq = cputime64_add(cpustat->irq, tmp);
+	} else if (irqtime_account_si_update()) {
+		cpustat->softirq = cputime64_add(cpustat->softirq, tmp);
+	} else if (this_cpu_ksoftirqd() == p) {
+		/*
+		 * ksoftirqd time do not get accounted in cpu_softirq_time.
+		 * So, we have to handle it separately here.
+		 * Also, p->stime needs to be updated for ksoftirqd.
+		 */
+		__account_system_time(p, cputime_one_jiffy, one_jiffy_scaled,
+					&cpustat->softirq);
+	} else if (user_tick) {
+		account_user_time(p, cputime_one_jiffy, one_jiffy_scaled);
+	} else if (p == rq->idle) {
+		account_idle_time(cputime_one_jiffy);
+	} else if (p->flags & PF_VCPU) { /* System time or guest time */
+		account_guest_time(p, cputime_one_jiffy, one_jiffy_scaled);
+	} else {
+		__account_system_time(p, cputime_one_jiffy, one_jiffy_scaled,
+					&cpustat->system);
+	}
+}
+
+static void irqtime_account_idle_ticks(int ticks)
+{
+	int i;
+	struct rq *rq = this_rq();
+
+	for (i = 0; i < ticks; i++)
+		irqtime_account_process_tick(current, 0, rq);
+}
+#else /* CONFIG_IRQ_TIME_ACCOUNTING */
+static void irqtime_account_idle_ticks(int ticks) {}
+static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
+						struct rq *rq) {}
+#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
+
 /*
  * Account a single tick of cpu time.
  * @p: the process that the cpu time gets accounted to
@@ -3645,6 +3776,11 @@ void account_process_tick(struct task_struct *p, int user_tick)
 	cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
 	struct rq *rq = this_rq();
 
+	if (sched_clock_irqtime) {
+		irqtime_account_process_tick(p, user_tick, rq);
+		return;
+	}
+
 	if (user_tick)
 		account_user_time(p, cputime_one_jiffy, one_jiffy_scaled);
 	else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET))
@@ -3670,6 +3806,12 @@ void account_steal_ticks(unsigned long ticks)
  */
 void account_idle_ticks(unsigned long ticks)
 {
+
+	if (sched_clock_irqtime) {
+		irqtime_account_idle_ticks(ticks);
+		return;
+	}
+
 	account_idle_time(jiffies_to_cputime(ticks));
 }
 
@@ -3989,9 +4131,6 @@ need_resched_nonpreemptible:
 	rq->skip_clock_update = 0;
 
 	if (likely(prev != next)) {
-		sched_info_switch(prev, next);
-		perf_event_task_sched_out(prev, next);
-
 		rq->nr_switches++;
 		rq->curr = next;
 		++*switch_count;
@@ -4571,11 +4710,10 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 
 	if (running)
 		p->sched_class->set_curr_task(rq);
-	if (on_rq) {
+	if (on_rq)
 		enqueue_task(rq, p, oldprio < prio ? ENQUEUE_HEAD : 0);
 
-		check_class_changed(rq, p, prev_class, oldprio, running);
-	}
+	check_class_changed(rq, p, prev_class, oldprio);
 	task_rq_unlock(rq, &flags);
 }
 
@@ -4823,12 +4961,15 @@ recheck:
 			    param->sched_priority > rlim_rtprio)
 				return -EPERM;
 		}
+
 		/*
-		 * Like positive nice levels, dont allow tasks to
-		 * move out of SCHED_IDLE either:
+		 * Treat SCHED_IDLE as nice 20. Only allow a switch to
+		 * SCHED_NORMAL if the RLIMIT_NICE would normally permit it.
 		 */
-		if (p->policy == SCHED_IDLE && policy != SCHED_IDLE)
-			return -EPERM;
+		if (p->policy == SCHED_IDLE && policy != SCHED_IDLE) {
+			if (!can_nice(p, TASK_NICE(p)))
+				return -EPERM;
+		}
 
 		/* can't change other user's priorities */
 		if (!check_same_owner(p))
@@ -4903,11 +5044,10 @@ recheck:
 
 	if (running)
 		p->sched_class->set_curr_task(rq);
-	if (on_rq) {
+	if (on_rq)
 		activate_task(rq, p, 0);
 
-		check_class_changed(rq, p, prev_class, oldprio, running);
-	}
+	check_class_changed(rq, p, prev_class, oldprio);
 	__task_rq_unlock(rq);
 	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
 
@@ -5324,6 +5464,65 @@ void __sched yield(void)
 }
 EXPORT_SYMBOL(yield);
 
+/**
+ * yield_to - yield the current processor to another thread in
+ * your thread group, or accelerate that thread toward the
+ * processor it's on.
+ *
+ * It's the caller's job to ensure that the target task struct
+ * can't go away on us before we can do any checks.
+ *
+ * Returns true if we indeed boosted the target task.
+ */
+bool __sched yield_to(struct task_struct *p, bool preempt)
+{
+	struct task_struct *curr = current;
+	struct rq *rq, *p_rq;
+	unsigned long flags;
+	bool yielded = 0;
+
+	local_irq_save(flags);
+	rq = this_rq();
+
+again:
+	p_rq = task_rq(p);
+	double_rq_lock(rq, p_rq);
+	while (task_rq(p) != p_rq) {
+		double_rq_unlock(rq, p_rq);
+		goto again;
+	}
+
+	if (!curr->sched_class->yield_to_task)
+		goto out;
+
+	if (curr->sched_class != p->sched_class)
+		goto out;
+
+	if (task_running(p_rq, p) || p->state)
+		goto out;
+
+	yielded = curr->sched_class->yield_to_task(rq, p, preempt);
+	if (yielded) {
+		schedstat_inc(rq, yld_count);
+		/*
+		 * Make p's CPU reschedule; pick_next_entity takes care of
+		 * fairness.
+		 */
+		if (preempt && rq != p_rq)
+			resched_task(p_rq->curr);
+	}
+
+out:
+	double_rq_unlock(rq, p_rq);
+	local_irq_restore(flags);
+
+	if (yielded)
+		schedule();
+
+	return yielded;
+}
+EXPORT_SYMBOL_GPL(yield_to);
+
 /*
  * This task is about to go to sleep on IO. Increment rq->nr_iowait so
  * that process accounting knows that this is a task in IO wait state.
@@ -5572,7 +5771,7 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu)
 	 * The idle tasks have their own, simple scheduling class:
 	 */
 	idle->sched_class = &idle_sched_class;
-	ftrace_graph_init_task(idle);
+	ftrace_graph_init_idle_task(idle, cpu);
 }
 
 /*
@@ -7797,6 +7996,10 @@ static void init_cfs_rq(struct cfs_rq *cfs_rq, struct rq *rq)
 	INIT_LIST_HEAD(&cfs_rq->tasks);
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	cfs_rq->rq = rq;
+	/* allow initial update_cfs_load() to truncate */
+#ifdef CONFIG_SMP
+	cfs_rq->load_stamp = 1;
+#endif
 #endif
 	cfs_rq->min_vruntime = (u64)(-(1LL << 20));
 }
@@ -8110,6 +8313,8 @@ EXPORT_SYMBOL(__might_sleep);
 #ifdef CONFIG_MAGIC_SYSRQ
 static void normalize_task(struct rq *rq, struct task_struct *p)
 {
+	const struct sched_class *prev_class = p->sched_class;
+	int old_prio = p->prio;
 	int on_rq;
 
 	on_rq = p->se.on_rq;
@@ -8120,6 +8325,8 @@ static void normalize_task(struct rq *rq, struct task_struct *p)
 		activate_task(rq, p, 0);
 		resched_task(rq->curr);
 	}
+
+	check_class_changed(rq, p, prev_class, old_prio);
 }
 
 void normalize_rt_tasks(void)
@@ -8511,7 +8718,7 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares)
 		/* Propagate contribution to hierarchy */
 		raw_spin_lock_irqsave(&rq->lock, flags);
 		for_each_sched_entity(se)
-			update_cfs_shares(group_cfs_rq(se), 0);
+			update_cfs_shares(group_cfs_rq(se));
 		raw_spin_unlock_irqrestore(&rq->lock, flags);
 	}
 
@@ -8885,7 +9092,8 @@ cpu_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
 }
 
 static void
-cpu_cgroup_exit(struct cgroup_subsys *ss, struct task_struct *task)
+cpu_cgroup_exit(struct cgroup_subsys *ss, struct cgroup *cgrp,
+		struct cgroup *old_cgrp, struct task_struct *task)
 {
 	/*
 	 * cgroup_exit() is called in the copy_process() failure path.
diff --git a/kernel/sched_autogroup.c b/kernel/sched_autogroup.c
index 9fb656283157..5946ac515602 100644
--- a/kernel/sched_autogroup.c
+++ b/kernel/sched_autogroup.c
@@ -12,7 +12,6 @@ static atomic_t autogroup_seq_nr;
 static void __init autogroup_init(struct task_struct *init_task)
 {
 	autogroup_default.tg = &root_task_group;
-	root_task_group.autogroup = &autogroup_default;
 	kref_init(&autogroup_default.kref);
 	init_rwsem(&autogroup_default.lock);
 	init_task->signal->autogroup = &autogroup_default;
@@ -130,7 +129,7 @@ task_wants_autogroup(struct task_struct *p, struct task_group *tg)
 
 static inline bool task_group_is_autogroup(struct task_group *tg)
 {
-	return tg != &root_task_group && tg->autogroup;
+	return !!tg->autogroup;
 }
 
 static inline struct task_group *
@@ -161,11 +160,15 @@ autogroup_move_group(struct task_struct *p, struct autogroup *ag)
 
 	p->signal->autogroup = autogroup_kref_get(ag);
 
+	if (!ACCESS_ONCE(sysctl_sched_autogroup_enabled))
+		goto out;
+
 	t = p;
 	do {
 		sched_move_task(t);
 	} while_each_thread(p, t);
 
+out:
 	unlock_task_sighand(p, &flags);
 	autogroup_kref_put(prev);
 }
@@ -247,10 +250,14 @@ void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m)
 {
 	struct autogroup *ag = autogroup_task_get(p);
 
+	if (!task_group_is_autogroup(ag->tg))
+		goto out;
+
 	down_read(&ag->lock);
 	seq_printf(m, "/autogroup-%ld nice %d\n", ag->id, ag->nice);
 	up_read(&ag->lock);
 
+out:
 	autogroup_kref_put(ag);
 }
 #endif /* CONFIG_PROC_FS */
@@ -258,9 +265,7 @@ void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m)
 #ifdef CONFIG_SCHED_DEBUG
 static inline int autogroup_path(struct task_group *tg, char *buf, int buflen)
 {
-	int enabled = ACCESS_ONCE(sysctl_sched_autogroup_enabled);
-
-	if (!enabled || !tg->autogroup)
+	if (!task_group_is_autogroup(tg))
 		return 0;
 
 	return snprintf(buf, buflen, "%s-%ld", "/autogroup", tg->autogroup->id);
diff --git a/kernel/sched_autogroup.h b/kernel/sched_autogroup.h
index 7b859ffe5dad..05577055cfca 100644
--- a/kernel/sched_autogroup.h
+++ b/kernel/sched_autogroup.h
@@ -1,6 +1,11 @@
 #ifdef CONFIG_SCHED_AUTOGROUP
 
 struct autogroup {
+	/*
+	 * reference doesn't mean how many thread attach to this
+	 * autogroup now. It just stands for the number of task
+	 * could use this autogroup.
+	 */
 	struct kref		kref;
 	struct task_group	*tg;
 	struct rw_semaphore	lock;
diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index eb6cb8edd075..7bacd83a4158 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -179,7 +179,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 
 	raw_spin_lock_irqsave(&rq->lock, flags);
 	if (cfs_rq->rb_leftmost)
-		MIN_vruntime = (__pick_next_entity(cfs_rq))->vruntime;
+		MIN_vruntime = (__pick_first_entity(cfs_rq))->vruntime;
 	last = __pick_last_entity(cfs_rq);
 	if (last)
 		max_vruntime = last->vruntime;
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 0c26e2df450e..3f7ec9e27ee1 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -69,14 +69,6 @@ static unsigned int sched_nr_latency = 8;
 unsigned int sysctl_sched_child_runs_first __read_mostly;
 
 /*
- * sys_sched_yield() compat mode
- *
- * This option switches the agressive yield implementation of the
- * old scheduler back on.
- */
-unsigned int __read_mostly sysctl_sched_compat_yield;
-
-/*
  * SCHED_OTHER wake-up granularity.
  * (default: 1 msec * (1 + ilog(ncpus)), units: nanoseconds)
  *
@@ -419,7 +411,7 @@ static void __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	rb_erase(&se->run_node, &cfs_rq->tasks_timeline);
 }
 
-static struct sched_entity *__pick_next_entity(struct cfs_rq *cfs_rq)
+static struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq)
 {
 	struct rb_node *left = cfs_rq->rb_leftmost;
 
@@ -429,6 +421,17 @@ static struct sched_entity *__pick_next_entity(struct cfs_rq *cfs_rq)
 	return rb_entry(left, struct sched_entity, run_node);
 }
 
+static struct sched_entity *__pick_next_entity(struct sched_entity *se)
+{
+	struct rb_node *next = rb_next(&se->run_node);
+
+	if (!next)
+		return NULL;
+
+	return rb_entry(next, struct sched_entity, run_node);
+}
+
+#ifdef CONFIG_SCHED_DEBUG
 static struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq)
 {
 	struct rb_node *last = rb_last(&cfs_rq->tasks_timeline);
@@ -443,7 +446,6 @@ static struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq)
  * Scheduling class statistics methods:
  */
 
-#ifdef CONFIG_SCHED_DEBUG
 int sched_proc_update_handler(struct ctl_table *table, int write,
 		void __user *buffer, size_t *lenp,
 		loff_t *ppos)
@@ -540,7 +542,7 @@ static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 }
 
 static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update);
-static void update_cfs_shares(struct cfs_rq *cfs_rq, long weight_delta);
+static void update_cfs_shares(struct cfs_rq *cfs_rq);
 
 /*
  * Update the current task's runtime statistics. Skip current tasks that
@@ -733,6 +735,7 @@ static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update)
 	    now - cfs_rq->load_last > 4 * period) {
 		cfs_rq->load_period = 0;
 		cfs_rq->load_avg = 0;
+		delta = period - 1;
 	}
 
 	cfs_rq->load_stamp = now;
@@ -763,16 +766,15 @@ static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update)
 		list_del_leaf_cfs_rq(cfs_rq);
 }
 
-static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg,
-				long weight_delta)
+static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
 {
 	long load_weight, load, shares;
 
-	load = cfs_rq->load.weight + weight_delta;
+	load = cfs_rq->load.weight;
 
 	load_weight = atomic_read(&tg->load_weight);
-	load_weight -= cfs_rq->load_contribution;
 	load_weight += load;
+	load_weight -= cfs_rq->load_contribution;
 
 	shares = (tg->shares * load);
 	if (load_weight)
@@ -790,7 +792,7 @@ static void update_entity_shares_tick(struct cfs_rq *cfs_rq)
 {
 	if (cfs_rq->load_unacc_exec_time > sysctl_sched_shares_window) {
 		update_cfs_load(cfs_rq, 0);
-		update_cfs_shares(cfs_rq, 0);
+		update_cfs_shares(cfs_rq);
 	}
 }
 # else /* CONFIG_SMP */
@@ -798,8 +800,7 @@ static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update)
 {
 }
 
-static inline long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg,
-				long weight_delta)
+static inline long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
 {
 	return tg->shares;
 }
@@ -824,7 +825,7 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
 		account_entity_enqueue(cfs_rq, se);
 }
 
-static void update_cfs_shares(struct cfs_rq *cfs_rq, long weight_delta)
+static void update_cfs_shares(struct cfs_rq *cfs_rq)
 {
 	struct task_group *tg;
 	struct sched_entity *se;
@@ -838,7 +839,7 @@ static void update_cfs_shares(struct cfs_rq *cfs_rq, long weight_delta)
 	if (likely(se->load.weight == tg->shares))
 		return;
 #endif
-	shares = calc_cfs_shares(cfs_rq, tg, weight_delta);
+	shares = calc_cfs_shares(cfs_rq, tg);
 
 	reweight_entity(cfs_rq_of(se), se, shares);
 }
@@ -847,7 +848,7 @@ static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update)
 {
 }
 
-static inline void update_cfs_shares(struct cfs_rq *cfs_rq, long weight_delta)
+static inline void update_cfs_shares(struct cfs_rq *cfs_rq)
 {
 }
 
@@ -978,8 +979,8 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	 */
 	update_curr(cfs_rq);
 	update_cfs_load(cfs_rq, 0);
-	update_cfs_shares(cfs_rq, se->load.weight);
 	account_entity_enqueue(cfs_rq, se);
+	update_cfs_shares(cfs_rq);
 
 	if (flags & ENQUEUE_WAKEUP) {
 		place_entity(cfs_rq, se, 0);
@@ -996,19 +997,49 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 		list_add_leaf_cfs_rq(cfs_rq);
 }
 
-static void __clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
+static void __clear_buddies_last(struct sched_entity *se)
+{
+	for_each_sched_entity(se) {
+		struct cfs_rq *cfs_rq = cfs_rq_of(se);
+		if (cfs_rq->last == se)
+			cfs_rq->last = NULL;
+		else
+			break;
+	}
+}
+
+static void __clear_buddies_next(struct sched_entity *se)
 {
-	if (!se || cfs_rq->last == se)
-		cfs_rq->last = NULL;
+	for_each_sched_entity(se) {
+		struct cfs_rq *cfs_rq = cfs_rq_of(se);
+		if (cfs_rq->next == se)
+			cfs_rq->next = NULL;
+		else
+			break;
+	}
+}
 
-	if (!se || cfs_rq->next == se)
-		cfs_rq->next = NULL;
+static void __clear_buddies_skip(struct sched_entity *se)
+{
+	for_each_sched_entity(se) {
+		struct cfs_rq *cfs_rq = cfs_rq_of(se);
+		if (cfs_rq->skip == se)
+			cfs_rq->skip = NULL;
+		else
+			break;
+	}
 }
 
 static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	for_each_sched_entity(se)
-		__clear_buddies(cfs_rq_of(se), se);
+	if (cfs_rq->last == se)
+		__clear_buddies_last(se);
+
+	if (cfs_rq->next == se)
+		__clear_buddies_next(se);
+
+	if (cfs_rq->skip == se)
+		__clear_buddies_skip(se);
 }
 
 static void
@@ -1041,7 +1072,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	update_cfs_load(cfs_rq, 0);
 	account_entity_dequeue(cfs_rq, se);
 	update_min_vruntime(cfs_rq);
-	update_cfs_shares(cfs_rq, 0);
+	update_cfs_shares(cfs_rq);
 
 	/*
 	 * Normalize the entity after updating the min_vruntime because the
@@ -1084,7 +1115,7 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
 		return;
 
 	if (cfs_rq->nr_running > 1) {
-		struct sched_entity *se = __pick_next_entity(cfs_rq);
+		struct sched_entity *se = __pick_first_entity(cfs_rq);
 		s64 delta = curr->vruntime - se->vruntime;
 
 		if (delta < 0)
@@ -1128,13 +1159,27 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 static int
 wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se);
 
+/*
+ * Pick the next process, keeping these things in mind, in this order:
+ * 1) keep things fair between processes/task groups
+ * 2) pick the "next" process, since someone really wants that to run
+ * 3) pick the "last" process, for cache locality
+ * 4) do not run the "skip" process, if something else is available
+ */
 static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
 {
-	struct sched_entity *se = __pick_next_entity(cfs_rq);
+	struct sched_entity *se = __pick_first_entity(cfs_rq);
 	struct sched_entity *left = se;
 
-	if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1)
-		se = cfs_rq->next;
+	/*
+	 * Avoid running the skip buddy, if running something else can
+	 * be done without getting too unfair.
+	 */
+	if (cfs_rq->skip == se) {
+		struct sched_entity *second = __pick_next_entity(se);
+		if (second && wakeup_preempt_entity(second, left) < 1)
+			se = second;
+	}
 
 	/*
 	 * Prefer last buddy, try to return the CPU to a preempted task.
@@ -1142,6 +1187,12 @@ static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
 	if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, left) < 1)
 		se = cfs_rq->last;
 
+	/*
+	 * Someone really wants this to run. If it's not unfair, run it.
+	 */
+	if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1)
+		se = cfs_rq->next;
+
 	clear_buddies(cfs_rq, se);
 
 	return se;
@@ -1282,7 +1333,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 		struct cfs_rq *cfs_rq = cfs_rq_of(se);
 
 		update_cfs_load(cfs_rq, 0);
-		update_cfs_shares(cfs_rq, 0);
+		update_cfs_shares(cfs_rq);
 	}
 
 	hrtick_update(rq);
@@ -1312,58 +1363,12 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 		struct cfs_rq *cfs_rq = cfs_rq_of(se);
 
 		update_cfs_load(cfs_rq, 0);
-		update_cfs_shares(cfs_rq, 0);
+		update_cfs_shares(cfs_rq);
 	}
 
 	hrtick_update(rq);
 }
 
-/*
- * sched_yield() support is very simple - we dequeue and enqueue.
- *
- * If compat_yield is turned on then we requeue to the end of the tree.
- */
-static void yield_task_fair(struct rq *rq)
-{
-	struct task_struct *curr = rq->curr;
-	struct cfs_rq *cfs_rq = task_cfs_rq(curr);
-	struct sched_entity *rightmost, *se = &curr->se;
-
-	/*
-	 * Are we the only task in the tree?
-	 */
-	if (unlikely(cfs_rq->nr_running == 1))
-		return;
-
-	clear_buddies(cfs_rq, se);
-
-	if (likely(!sysctl_sched_compat_yield) && curr->policy != SCHED_BATCH) {
-		update_rq_clock(rq);
-		/*
-		 * Update run-time statistics of the 'current'.
-		 */
-		update_curr(cfs_rq);
-
-		return;
-	}
-	/*
-	 * Find the rightmost entry in the rbtree:
-	 */
-	rightmost = __pick_last_entity(cfs_rq);
-	/*
-	 * Already in the rightmost position?
-	 */
-	if (unlikely(!rightmost || entity_before(rightmost, se)))
-		return;
-
-	/*
-	 * Minimally necessary key value to be last in the tree:
-	 * Upon rescheduling, sched_class::put_prev_task() will place
-	 * 'current' within the tree based on its new key value.
-	 */
-	se->vruntime = rightmost->vruntime + 1;
-}
-
 #ifdef CONFIG_SMP
 
 static void task_waking_fair(struct rq *rq, struct task_struct *p)
@@ -1834,6 +1839,14 @@ static void set_next_buddy(struct sched_entity *se)
 	}
 }
 
+static void set_skip_buddy(struct sched_entity *se)
+{
+	if (likely(task_of(se)->policy != SCHED_IDLE)) {
+		for_each_sched_entity(se)
+			cfs_rq_of(se)->skip = se;
+	}
+}
+
 /*
  * Preempt the current task with a newly woken task if needed:
  */
@@ -1857,16 +1870,18 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
 	if (test_tsk_need_resched(curr))
 		return;
 
+	/* Idle tasks are by definition preempted by non-idle tasks. */
+	if (unlikely(curr->policy == SCHED_IDLE) &&
+	    likely(p->policy != SCHED_IDLE))
+		goto preempt;
+
 	/*
-	 * Batch and idle tasks do not preempt (their preemption is driven by
-	 * the tick):
+	 * Batch and idle tasks do not preempt non-idle tasks (their preemption
+	 * is driven by the tick):
 	 */
 	if (unlikely(p->policy != SCHED_NORMAL))
 		return;
 
-	/* Idle tasks are by definition preempted by everybody. */
-	if (unlikely(curr->policy == SCHED_IDLE))
-		goto preempt;
 
 	if (!sched_feat(WAKEUP_PREEMPT))
 		return;
@@ -1932,6 +1947,51 @@ static void put_prev_task_fair(struct rq *rq, struct task_struct *prev)
 	}
 }
 
+/*
+ * sched_yield() is very simple
+ *
+ * The magic of dealing with the ->skip buddy is in pick_next_entity.
+ */
+static void yield_task_fair(struct rq *rq)
+{
+	struct task_struct *curr = rq->curr;
+	struct cfs_rq *cfs_rq = task_cfs_rq(curr);
+	struct sched_entity *se = &curr->se;
+
+	/*
+	 * Are we the only task in the tree?
+	 */
+	if (unlikely(rq->nr_running == 1))
+		return;
+
+	clear_buddies(cfs_rq, se);
+
+	if (curr->policy != SCHED_BATCH) {
+		update_rq_clock(rq);
+		/*
+		 * Update run-time statistics of the 'current'.
+		 */
+		update_curr(cfs_rq);
+	}
+
+	set_skip_buddy(se);
+}
+
+static bool yield_to_task_fair(struct rq *rq, struct task_struct *p, bool preempt)
+{
+	struct sched_entity *se = &p->se;
+
+	if (!se->on_rq)
+		return false;
+
+	/* Tell the scheduler that we'd really like pse to run next. */
+	set_next_buddy(se);
+
+	yield_task_fair(rq);
+
+	return true;
+}
+
 #ifdef CONFIG_SMP
 /**************************************************
  * Fair scheduling class load-balancing methods:
@@ -2123,7 +2183,7 @@ static int update_shares_cpu(struct task_group *tg, int cpu)
 	 * We need to update shares after updating tg->load_weight in
 	 * order to adjust the weight of groups with long running tasks.
 	 */
-	update_cfs_shares(cfs_rq, 0);
+	update_cfs_shares(cfs_rq);
 
 	raw_spin_unlock_irqrestore(&rq->lock, flags);
 
@@ -2610,7 +2670,6 @@ fix_small_capacity(struct sched_domain *sd, struct sched_group *group)
  * @this_cpu: Cpu for which load balance is currently performed.
  * @idle: Idle status of this_cpu
  * @load_idx: Load index of sched_domain of this_cpu for load calc.
- * @sd_idle: Idle status of the sched_domain containing group.
  * @local_group: Does group contain this_cpu.
  * @cpus: Set of cpus considered for load balancing.
  * @balance: Should we balance.
@@ -2618,7 +2677,7 @@ fix_small_capacity(struct sched_domain *sd, struct sched_group *group)
  */
 static inline void update_sg_lb_stats(struct sched_domain *sd,
 			struct sched_group *group, int this_cpu,
-			enum cpu_idle_type idle, int load_idx, int *sd_idle,
+			enum cpu_idle_type idle, int load_idx,
 			int local_group, const struct cpumask *cpus,
 			int *balance, struct sg_lb_stats *sgs)
 {
@@ -2638,9 +2697,6 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
 	for_each_cpu_and(i, sched_group_cpus(group), cpus) {
 		struct rq *rq = cpu_rq(i);
 
-		if (*sd_idle && rq->nr_running)
-			*sd_idle = 0;
-
 		/* Bias balancing toward cpus of our domain */
 		if (local_group) {
 			if (idle_cpu(i) && !first_idle_cpu) {
@@ -2685,7 +2741,7 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
 
 	/*
 	 * Consider the group unbalanced when the imbalance is larger
-	 * than the average weight of two tasks.
+	 * than the average weight of a task.
 	 *
 	 * APZ: with cgroup the avg task weight can vary wildly and
 	 *      might not be a suitable number - should we keep a
@@ -2695,7 +2751,7 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
 	if (sgs->sum_nr_running)
 		avg_load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running;
 
-	if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task && max_nr_running > 1)
+	if ((max_cpu_load - min_cpu_load) >= avg_load_per_task && max_nr_running > 1)
 		sgs->group_imb = 1;
 
 	sgs->group_capacity = DIV_ROUND_CLOSEST(group->cpu_power, SCHED_LOAD_SCALE);
@@ -2755,15 +2811,13 @@ static bool update_sd_pick_busiest(struct sched_domain *sd,
  * @sd: sched_domain whose statistics are to be updated.
  * @this_cpu: Cpu for which load balance is currently performed.
  * @idle: Idle status of this_cpu
- * @sd_idle: Idle status of the sched_domain containing sg.
  * @cpus: Set of cpus considered for load balancing.
  * @balance: Should we balance.
  * @sds: variable to hold the statistics for this sched_domain.
  */
 static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
-			enum cpu_idle_type idle, int *sd_idle,
-			const struct cpumask *cpus, int *balance,
-			struct sd_lb_stats *sds)
+			enum cpu_idle_type idle, const struct cpumask *cpus,
+			int *balance, struct sd_lb_stats *sds)
 {
 	struct sched_domain *child = sd->child;
 	struct sched_group *sg = sd->groups;
@@ -2781,7 +2835,7 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
 
 		local_group = cpumask_test_cpu(this_cpu, sched_group_cpus(sg));
 		memset(&sgs, 0, sizeof(sgs));
-		update_sg_lb_stats(sd, sg, this_cpu, idle, load_idx, sd_idle,
+		update_sg_lb_stats(sd, sg, this_cpu, idle, load_idx,
 				local_group, cpus, balance, &sgs);
 
 		if (local_group && !(*balance))
@@ -3033,7 +3087,6 @@ static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu,
  * @imbalance: Variable which stores amount of weighted load which should
  *		be moved to restore balance/put a group to idle.
  * @idle: The idle status of this_cpu.
- * @sd_idle: The idleness of sd
  * @cpus: The set of CPUs under consideration for load-balancing.
  * @balance: Pointer to a variable indicating if this_cpu
  *	is the appropriate cpu to perform load balancing at this_level.
@@ -3046,7 +3099,7 @@ static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu,
 static struct sched_group *
 find_busiest_group(struct sched_domain *sd, int this_cpu,
 		   unsigned long *imbalance, enum cpu_idle_type idle,
-		   int *sd_idle, const struct cpumask *cpus, int *balance)
+		   const struct cpumask *cpus, int *balance)
 {
 	struct sd_lb_stats sds;
 
@@ -3056,22 +3109,11 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
 	 * Compute the various statistics relavent for load balancing at
 	 * this level.
 	 */
-	update_sd_lb_stats(sd, this_cpu, idle, sd_idle, cpus,
-					balance, &sds);
-
-	/* Cases where imbalance does not exist from POV of this_cpu */
-	/* 1) this_cpu is not the appropriate cpu to perform load balancing
-	 *    at this level.
-	 * 2) There is no busy sibling group to pull from.
-	 * 3) This group is the busiest group.
-	 * 4) This group is more busy than the avg busieness at this
-	 *    sched_domain.
-	 * 5) The imbalance is within the specified limit.
-	 *
-	 * Note: when doing newidle balance, if the local group has excess
-	 * capacity (i.e. nr_running < group_capacity) and the busiest group
-	 * does not have any capacity, we force a load balance to pull tasks
-	 * to the local group. In this case, we skip past checks 3, 4 and 5.
+	update_sd_lb_stats(sd, this_cpu, idle, cpus, balance, &sds);
+
+	/*
+	 * this_cpu is not the appropriate cpu to perform load balancing at
+	 * this level.
 	 */
 	if (!(*balance))
 		goto ret;
@@ -3080,41 +3122,55 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
 	    check_asym_packing(sd, &sds, this_cpu, imbalance))
 		return sds.busiest;
 
+	/* There is no busy sibling group to pull tasks from */
 	if (!sds.busiest || sds.busiest_nr_running == 0)
 		goto out_balanced;
 
-	/*  SD_BALANCE_NEWIDLE trumps SMP nice when underutilized */
+	/*
+	 * If the busiest group is imbalanced the below checks don't
+	 * work because they assumes all things are equal, which typically
+	 * isn't true due to cpus_allowed constraints and the like.
+	 */
+	if (sds.group_imb)
+		goto force_balance;
+
+	/* SD_BALANCE_NEWIDLE trumps SMP nice when underutilized */
 	if (idle == CPU_NEWLY_IDLE && sds.this_has_capacity &&
 			!sds.busiest_has_capacity)
 		goto force_balance;
 
+	/*
+	 * If the local group is more busy than the selected busiest group
+	 * don't try and pull any tasks.
+	 */
 	if (sds.this_load >= sds.max_load)
 		goto out_balanced;
 
+	/*
+	 * Don't pull any tasks if this group is already above the domain
+	 * average load.
+	 */
 	sds.avg_load = (SCHED_LOAD_SCALE * sds.total_load) / sds.total_pwr;
-
 	if (sds.this_load >= sds.avg_load)
 		goto out_balanced;
 
-	/*
-	 * In the CPU_NEWLY_IDLE, use imbalance_pct to be conservative.
-	 * And to check for busy balance use !idle_cpu instead of
-	 * CPU_NOT_IDLE. This is because HT siblings will use CPU_NOT_IDLE
-	 * even when they are idle.
-	 */
-	if (idle == CPU_NEWLY_IDLE || !idle_cpu(this_cpu)) {
-		if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load)
-			goto out_balanced;
-	} else {
+	if (idle == CPU_IDLE) {
 		/*
 		 * This cpu is idle. If the busiest group load doesn't
 		 * have more tasks than the number of available cpu's and
 		 * there is no imbalance between this and busiest group
 		 * wrt to idle cpu's, it is balanced.
 		 */
-		if ((sds.this_idle_cpus  <= sds.busiest_idle_cpus + 1) &&
+		if ((sds.this_idle_cpus <= sds.busiest_idle_cpus + 1) &&
 		    sds.busiest_nr_running <= sds.busiest_group_weight)
 			goto out_balanced;
+	} else {
+		/*
+		 * In the CPU_NEWLY_IDLE, CPU_NOT_IDLE cases, use
+		 * imbalance_pct to be conservative.
+		 */
+		if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load)
+			goto out_balanced;
 	}
 
 force_balance:
@@ -3193,7 +3249,7 @@ find_busiest_queue(struct sched_domain *sd, struct sched_group *group,
 /* Working cpumask for load_balance and load_balance_newidle. */
 static DEFINE_PER_CPU(cpumask_var_t, load_balance_tmpmask);
 
-static int need_active_balance(struct sched_domain *sd, int sd_idle, int idle,
+static int need_active_balance(struct sched_domain *sd, int idle,
 			       int busiest_cpu, int this_cpu)
 {
 	if (idle == CPU_NEWLY_IDLE) {
@@ -3225,10 +3281,6 @@ static int need_active_balance(struct sched_domain *sd, int sd_idle, int idle,
 		 * move_tasks() will succeed.  ld_moved will be true and this
 		 * active balance code will not be triggered.
 		 */
-		if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
-		    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
-			return 0;
-
 		if (sched_mc_power_savings < POWERSAVINGS_BALANCE_WAKEUP)
 			return 0;
 	}
@@ -3246,7 +3298,7 @@ static int load_balance(int this_cpu, struct rq *this_rq,
 			struct sched_domain *sd, enum cpu_idle_type idle,
 			int *balance)
 {
-	int ld_moved, all_pinned = 0, active_balance = 0, sd_idle = 0;
+	int ld_moved, all_pinned = 0, active_balance = 0;
 	struct sched_group *group;
 	unsigned long imbalance;
 	struct rq *busiest;
@@ -3255,20 +3307,10 @@ static int load_balance(int this_cpu, struct rq *this_rq,
 
 	cpumask_copy(cpus, cpu_active_mask);
 
-	/*
-	 * When power savings policy is enabled for the parent domain, idle
-	 * sibling can pick up load irrespective of busy siblings. In this case,
-	 * let the state of idle sibling percolate up as CPU_IDLE, instead of
-	 * portraying it as CPU_NOT_IDLE.
-	 */
-	if (idle != CPU_NOT_IDLE && sd->flags & SD_SHARE_CPUPOWER &&
-	    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
-		sd_idle = 1;
-
 	schedstat_inc(sd, lb_count[idle]);
 
 redo:
-	group = find_busiest_group(sd, this_cpu, &imbalance, idle, &sd_idle,
+	group = find_busiest_group(sd, this_cpu, &imbalance, idle,
 				   cpus, balance);
 
 	if (*balance == 0)
@@ -3330,8 +3372,7 @@ redo:
 		if (idle != CPU_NEWLY_IDLE)
 			sd->nr_balance_failed++;
 
-		if (need_active_balance(sd, sd_idle, idle, cpu_of(busiest),
-					this_cpu)) {
+		if (need_active_balance(sd, idle, cpu_of(busiest), this_cpu)) {
 			raw_spin_lock_irqsave(&busiest->lock, flags);
 
 			/* don't kick the active_load_balance_cpu_stop,
@@ -3386,10 +3427,6 @@ redo:
 			sd->balance_interval *= 2;
 	}
 
-	if (!ld_moved && !sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
-	    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
-		ld_moved = -1;
-
 	goto out;
 
 out_balanced:
@@ -3403,11 +3440,7 @@ out_one_pinned:
 			(sd->balance_interval < sd->max_interval))
 		sd->balance_interval *= 2;
 
-	if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
-	    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
-		ld_moved = -1;
-	else
-		ld_moved = 0;
+	ld_moved = 0;
 out:
 	return ld_moved;
 }
@@ -3831,8 +3864,7 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle)
 			if (load_balance(cpu, rq, sd, idle, &balance)) {
 				/*
 				 * We've pulled tasks over so either we're no
-				 * longer idle, or one of our SMT siblings is
-				 * not idle.
+				 * longer idle.
 				 */
 				idle = CPU_NOT_IDLE;
 			}
@@ -4079,33 +4111,62 @@ static void task_fork_fair(struct task_struct *p)
  * Priority of the task has changed. Check to see if we preempt
  * the current task.
  */
-static void prio_changed_fair(struct rq *rq, struct task_struct *p,
-			      int oldprio, int running)
+static void
+prio_changed_fair(struct rq *rq, struct task_struct *p, int oldprio)
 {
+	if (!p->se.on_rq)
+		return;
+
 	/*
 	 * Reschedule if we are currently running on this runqueue and
 	 * our priority decreased, or if we are not currently running on
 	 * this runqueue and our priority is higher than the current's
 	 */
-	if (running) {
+	if (rq->curr == p) {
 		if (p->prio > oldprio)
 			resched_task(rq->curr);
 	} else
 		check_preempt_curr(rq, p, 0);
 }
 
+static void switched_from_fair(struct rq *rq, struct task_struct *p)
+{
+	struct sched_entity *se = &p->se;
+	struct cfs_rq *cfs_rq = cfs_rq_of(se);
+
+	/*
+	 * Ensure the task's vruntime is normalized, so that when its
+	 * switched back to the fair class the enqueue_entity(.flags=0) will
+	 * do the right thing.
+	 *
+	 * If it was on_rq, then the dequeue_entity(.flags=0) will already
+	 * have normalized the vruntime, if it was !on_rq, then only when
+	 * the task is sleeping will it still have non-normalized vruntime.
+	 */
+	if (!se->on_rq && p->state != TASK_RUNNING) {
+		/*
+		 * Fix up our vruntime so that the current sleep doesn't
+		 * cause 'unlimited' sleep bonus.
+		 */
+		place_entity(cfs_rq, se, 0);
+		se->vruntime -= cfs_rq->min_vruntime;
+	}
+}
+
 /*
  * We switched to the sched_fair class.
  */
-static void switched_to_fair(struct rq *rq, struct task_struct *p,
-			     int running)
+static void switched_to_fair(struct rq *rq, struct task_struct *p)
 {
+	if (!p->se.on_rq)
+		return;
+
 	/*
 	 * We were most likely switched from sched_rt, so
 	 * kick off the schedule if running, otherwise just see
 	 * if we can still preempt the current task.
 	 */
-	if (running)
+	if (rq->curr == p)
 		resched_task(rq->curr);
 	else
 		check_preempt_curr(rq, p, 0);
@@ -4171,6 +4232,7 @@ static const struct sched_class fair_sched_class = {
 	.enqueue_task		= enqueue_task_fair,
 	.dequeue_task		= dequeue_task_fair,
 	.yield_task		= yield_task_fair,
+	.yield_to_task		= yield_to_task_fair,
 
 	.check_preempt_curr	= check_preempt_wakeup,
 
@@ -4191,6 +4253,7 @@ static const struct sched_class fair_sched_class = {
 	.task_fork		= task_fork_fair,
 
 	.prio_changed		= prio_changed_fair,
+	.switched_from		= switched_from_fair,
 	.switched_to		= switched_to_fair,
 
 	.get_rr_interval	= get_rr_interval_fair,
diff --git a/kernel/sched_idletask.c b/kernel/sched_idletask.c
index 9fa0f402c87c..c82f26c1b7c3 100644
--- a/kernel/sched_idletask.c
+++ b/kernel/sched_idletask.c
@@ -52,31 +52,15 @@ static void set_curr_task_idle(struct rq *rq)
 {
 }
 
-static void switched_to_idle(struct rq *rq, struct task_struct *p,
-			     int running)
+static void switched_to_idle(struct rq *rq, struct task_struct *p)
 {
-	/* Can this actually happen?? */
-	if (running)
-		resched_task(rq->curr);
-	else
-		check_preempt_curr(rq, p, 0);
+	BUG();
 }
 
-static void prio_changed_idle(struct rq *rq, struct task_struct *p,
-			      int oldprio, int running)
+static void
+prio_changed_idle(struct rq *rq, struct task_struct *p, int oldprio)
 {
-	/* This can happen for hot plug CPUS */
-
-	/*
-	 * Reschedule if we are currently running on this runqueue and
-	 * our priority decreased, or if we are not currently running on
-	 * this runqueue and our priority is higher than the current's
-	 */
-	if (running) {
-		if (p->prio > oldprio)
-			resched_task(rq->curr);
-	} else
-		check_preempt_curr(rq, p, 0);
+	BUG();
 }
 
 static unsigned int get_rr_interval_idle(struct rq *rq, struct task_struct *task)
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index 01f75a5f17af..db308cb08b75 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -1599,8 +1599,7 @@ static void rq_offline_rt(struct rq *rq)
  * When switch from the rt queue, we bring ourselves to a position
  * that we might want to pull RT tasks from other runqueues.
  */
-static void switched_from_rt(struct rq *rq, struct task_struct *p,
-			   int running)
+static void switched_from_rt(struct rq *rq, struct task_struct *p)
 {
 	/*
 	 * If there are other RT tasks then we will reschedule
@@ -1609,7 +1608,7 @@ static void switched_from_rt(struct rq *rq, struct task_struct *p,
 	 * we may need to handle the pulling of RT tasks
 	 * now.
 	 */
-	if (!rq->rt.rt_nr_running)
+	if (p->se.on_rq && !rq->rt.rt_nr_running)
 		pull_rt_task(rq);
 }
 
@@ -1628,8 +1627,7 @@ static inline void init_sched_rt_class(void)
  * with RT tasks. In this case we try to push them off to
  * other runqueues.
  */
-static void switched_to_rt(struct rq *rq, struct task_struct *p,
-			   int running)
+static void switched_to_rt(struct rq *rq, struct task_struct *p)
 {
 	int check_resched = 1;
 
@@ -1640,7 +1638,7 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p,
 	 * If that current running task is also an RT task
 	 * then see if we can move to another run queue.
 	 */
-	if (!running) {
+	if (p->se.on_rq && rq->curr != p) {
 #ifdef CONFIG_SMP
 		if (rq->rt.overloaded && push_rt_task(rq) &&
 		    /* Don't resched if we changed runqueues */
@@ -1656,10 +1654,13 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p,
  * Priority of the task has changed. This may cause
  * us to initiate a push or pull.
  */
-static void prio_changed_rt(struct rq *rq, struct task_struct *p,
-			    int oldprio, int running)
+static void
+prio_changed_rt(struct rq *rq, struct task_struct *p, int oldprio)
 {
-	if (running) {
+	if (!p->se.on_rq)
+		return;
+
+	if (rq->curr == p) {
 #ifdef CONFIG_SMP
 		/*
 		 * If our priority decreases while running, we
diff --git a/kernel/sched_stoptask.c b/kernel/sched_stoptask.c
index 2bf6b47058c1..84ec9bcf82d9 100644
--- a/kernel/sched_stoptask.c
+++ b/kernel/sched_stoptask.c
@@ -59,14 +59,13 @@ static void set_curr_task_stop(struct rq *rq)
 {
 }
 
-static void switched_to_stop(struct rq *rq, struct task_struct *p,
-			     int running)
+static void switched_to_stop(struct rq *rq, struct task_struct *p)
 {
 	BUG(); /* its impossible to change to this class */
 }
 
-static void prio_changed_stop(struct rq *rq, struct task_struct *p,
-			      int oldprio, int running)
+static void
+prio_changed_stop(struct rq *rq, struct task_struct *p, int oldprio)
 {
 	BUG(); /* how!?, what priority? */
 }
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 68eb5efec388..56e5dec837f0 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -54,7 +54,7 @@ EXPORT_SYMBOL(irq_stat);
 
 static struct softirq_action softirq_vec[NR_SOFTIRQS] __cacheline_aligned_in_smp;
 
-static DEFINE_PER_CPU(struct task_struct *, ksoftirqd);
+DEFINE_PER_CPU(struct task_struct *, ksoftirqd);
 
 char *softirq_to_name[NR_SOFTIRQS] = {
 	"HI", "TIMER", "NET_TX", "NET_RX", "BLOCK", "BLOCK_IOPOLL",
@@ -311,9 +311,21 @@ void irq_enter(void)
 }
 
 #ifdef __ARCH_IRQ_EXIT_IRQS_DISABLED
-# define invoke_softirq()	__do_softirq()
+static inline void invoke_softirq(void)
+{
+	if (!force_irqthreads)
+		__do_softirq();
+	else
+		wakeup_softirqd();
+}
 #else
-# define invoke_softirq()	do_softirq()
+static inline void invoke_softirq(void)
+{
+	if (!force_irqthreads)
+		do_softirq();
+	else
+		wakeup_softirqd();
+}
 #endif
 
 /*
@@ -721,7 +733,6 @@ static int run_ksoftirqd(void * __bind_cpu)
 {
 	set_current_state(TASK_INTERRUPTIBLE);
 
-	current->flags |= PF_KSOFTIRQD;
 	while (!kthread_should_stop()) {
 		preempt_disable();
 		if (!local_softirq_pending()) {
@@ -738,7 +749,10 @@ static int run_ksoftirqd(void * __bind_cpu)
 			   don't process */
 			if (cpu_is_offline((long)__bind_cpu))
 				goto wait_to_die;
-			do_softirq();
+			local_irq_disable();
+			if (local_softirq_pending())
+				__do_softirq();
+			local_irq_enable();
 			preempt_enable_no_resched();
 			cond_resched();
 			preempt_disable();
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index c782fe9924c7..25cc41cd8f33 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -186,3 +186,8 @@ cond_syscall(sys_perf_event_open);
 /* fanotify! */
 cond_syscall(sys_fanotify_init);
 cond_syscall(sys_fanotify_mark);
+
+/* open by handle */
+cond_syscall(sys_name_to_handle_at);
+cond_syscall(sys_open_by_handle_at);
+cond_syscall(compat_sys_open_by_handle_at);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 4eed0af5d144..51054fea5d99 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -361,20 +361,13 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= sched_rt_handler,
 	},
-	{
-		.procname	= "sched_compat_yield",
-		.data		= &sysctl_sched_compat_yield,
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
 #ifdef CONFIG_SCHED_AUTOGROUP
 	{
 		.procname	= "sched_autogroup_enabled",
 		.data		= &sysctl_sched_autogroup_enabled,
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= &zero,
 		.extra2		= &one,
 	},
@@ -948,7 +941,7 @@ static struct ctl_table kern_table[] = {
 		.data		= &sysctl_perf_event_sample_rate,
 		.maxlen		= sizeof(sysctl_perf_event_sample_rate),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= perf_proc_update_handler,
 	},
 #endif
 #ifdef CONFIG_KMEMCHECK
diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c
index b875bedf7c9a..3b8e028b9601 100644
--- a/kernel/sysctl_binary.c
+++ b/kernel/sysctl_binary.c
@@ -1321,13 +1321,11 @@ static ssize_t binary_sysctl(const int *name, int nlen,
 	void __user *oldval, size_t oldlen, void __user *newval, size_t newlen)
 {
 	const struct bin_table *table = NULL;
-	struct nameidata nd;
 	struct vfsmount *mnt;
 	struct file *file;
 	ssize_t result;
 	char *pathname;
 	int flags;
-	int acc_mode;
 
 	pathname = sysctl_getname(name, nlen, &table);
 	result = PTR_ERR(pathname);
@@ -1337,28 +1335,17 @@ static ssize_t binary_sysctl(const int *name, int nlen,
 	/* How should the sysctl be accessed? */
 	if (oldval && oldlen && newval && newlen) {
 		flags = O_RDWR;
-		acc_mode = MAY_READ | MAY_WRITE;
 	} else if (newval && newlen) {
 		flags = O_WRONLY;
-		acc_mode = MAY_WRITE;
 	} else if (oldval && oldlen) {
 		flags = O_RDONLY;
-		acc_mode = MAY_READ;
 	} else {
 		result = 0;
 		goto out_putname;
 	}
 
 	mnt = current->nsproxy->pid_ns->proc_mnt;
-	result = vfs_path_lookup(mnt->mnt_root, mnt, pathname, 0, &nd);
-	if (result)
-		goto out_putname;
-
-	result = may_open(&nd.path, acc_mode, flags);
-	if (result)
-		goto out_putpath;
-
-	file = dentry_open(nd.path.dentry, nd.path.mnt, flags, current_cred());
+	file = file_open_root(mnt->mnt_root, mnt, pathname, flags);
 	result = PTR_ERR(file);
 	if (IS_ERR(file))
 		goto out_putname;
@@ -1370,10 +1357,6 @@ out_putname:
 	putname(pathname);
 out:
 	return result;
-
-out_putpath:
-	path_put(&nd.path);
-	goto out_putname;
 }
 
 
diff --git a/kernel/time.c b/kernel/time.c
index 32174359576f..8e8dc6d705c9 100644
--- a/kernel/time.c
+++ b/kernel/time.c
@@ -150,7 +150,7 @@ static inline void warp_clock(void)
  * various programs will get confused when the clock gets warped.
  */
 
-int do_sys_settimeofday(struct timespec *tv, struct timezone *tz)
+int do_sys_settimeofday(const struct timespec *tv, const struct timezone *tz)
 {
 	static int firsttime = 1;
 	int error = 0;
@@ -645,7 +645,7 @@ u64 nsec_to_clock_t(u64 x)
 }
 
 /**
- * nsecs_to_jiffies - Convert nsecs in u64 to jiffies
+ * nsecs_to_jiffies64 - Convert nsecs in u64 to jiffies64
  *
  * @n:	nsecs in u64
  *
@@ -657,7 +657,7 @@ u64 nsec_to_clock_t(u64 x)
  *   NSEC_PER_SEC = 10^9 = (5^9 * 2^9) = (1953125 * 512)
  *   ULLONG_MAX ns = 18446744073.709551615 secs = about 584 years
  */
-unsigned long nsecs_to_jiffies(u64 n)
+u64 nsecs_to_jiffies64(u64 n)
 {
 #if (NSEC_PER_SEC % HZ) == 0
 	/* Common case, HZ = 100, 128, 200, 250, 256, 500, 512, 1000 etc. */
@@ -674,22 +674,23 @@ unsigned long nsecs_to_jiffies(u64 n)
 #endif
 }
 
-#if (BITS_PER_LONG < 64)
-u64 get_jiffies_64(void)
+/**
+ * nsecs_to_jiffies - Convert nsecs in u64 to jiffies
+ *
+ * @n:	nsecs in u64
+ *
+ * Unlike {m,u}secs_to_jiffies, type of input is not unsigned int but u64.
+ * And this doesn't return MAX_JIFFY_OFFSET since this function is designed
+ * for scheduler, not for use in device drivers to calculate timeout value.
+ *
+ * note:
+ *   NSEC_PER_SEC = 10^9 = (5^9 * 2^9) = (1953125 * 512)
+ *   ULLONG_MAX ns = 18446744073.709551615 secs = about 584 years
+ */
+unsigned long nsecs_to_jiffies(u64 n)
 {
-	unsigned long seq;
-	u64 ret;
-
-	do {
-		seq = read_seqbegin(&xtime_lock);
-		ret = jiffies_64;
-	} while (read_seqretry(&xtime_lock, seq));
-	return ret;
+	return (unsigned long)nsecs_to_jiffies64(n);
 }
-EXPORT_SYMBOL(get_jiffies_64);
-#endif
-
-EXPORT_SYMBOL(jiffies);
 
 /*
  * Add two timespec values and do a safety check for overflow.
diff --git a/kernel/time/Makefile b/kernel/time/Makefile
index ee266620b06c..b0425991e9ac 100644
--- a/kernel/time/Makefile
+++ b/kernel/time/Makefile
@@ -1,4 +1,5 @@
-obj-y += timekeeping.o ntp.o clocksource.o jiffies.o timer_list.o timecompare.o timeconv.o
+obj-y += timekeeping.o ntp.o clocksource.o jiffies.o timer_list.o timecompare.o
+obj-y += timeconv.o posix-clock.o
 
 obj-$(CONFIG_GENERIC_CLOCKEVENTS_BUILD)		+= clockevents.o
 obj-$(CONFIG_GENERIC_CLOCKEVENTS)		+= tick-common.o
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index d7395fdfb9f3..0d74b9ba90c8 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -18,7 +18,6 @@
 #include <linux/notifier.h>
 #include <linux/smp.h>
 #include <linux/sysdev.h>
-#include <linux/tick.h>
 
 #include "tick-internal.h"
 
diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index 5404a8456909..b2fa506667c0 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -22,8 +22,11 @@
 ************************************************************************/
 #include <linux/clocksource.h>
 #include <linux/jiffies.h>
+#include <linux/module.h>
 #include <linux/init.h>
 
+#include "tick-internal.h"
+
 /* The Jiffies based clocksource is the lowest common
  * denominator clock source which should function on
  * all systems. It has the same coarse resolution as
@@ -64,6 +67,23 @@ struct clocksource clocksource_jiffies = {
 	.shift		= JIFFIES_SHIFT,
 };
 
+#if (BITS_PER_LONG < 64)
+u64 get_jiffies_64(void)
+{
+	unsigned long seq;
+	u64 ret;
+
+	do {
+		seq = read_seqbegin(&xtime_lock);
+		ret = jiffies_64;
+	} while (read_seqretry(&xtime_lock, seq));
+	return ret;
+}
+EXPORT_SYMBOL(get_jiffies_64);
+#endif
+
+EXPORT_SYMBOL(jiffies);
+
 static int __init init_jiffies_clocksource(void)
 {
 	return clocksource_register(&clocksource_jiffies);
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 5c00242fa921..5f1bb8e2008f 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -16,6 +16,8 @@
 #include <linux/mm.h>
 #include <linux/module.h>
 
+#include "tick-internal.h"
+
 /*
  * NTP timekeeping variables:
  */
@@ -646,6 +648,17 @@ int do_adjtimex(struct timex *txc)
 			hrtimer_cancel(&leap_timer);
 	}
 
+	if (txc->modes & ADJ_SETOFFSET) {
+		struct timespec delta;
+		delta.tv_sec  = txc->time.tv_sec;
+		delta.tv_nsec = txc->time.tv_usec;
+		if (!(txc->modes & ADJ_NANO))
+			delta.tv_nsec *= 1000;
+		result = timekeeping_inject_offset(&delta);
+		if (result)
+			return result;
+	}
+
 	getnstimeofday(&ts);
 
 	write_seqlock_irq(&xtime_lock);
diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c
new file mode 100644
index 000000000000..25028dd4fa18
--- /dev/null
+++ b/kernel/time/posix-clock.c
@@ -0,0 +1,451 @@
+/*
+ * posix-clock.c - support for dynamic clock devices
+ *
+ * Copyright (C) 2010 OMICRON electronics GmbH
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to the Free Software
+ *  Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+#include <linux/device.h>
+#include <linux/file.h>
+#include <linux/mutex.h>
+#include <linux/posix-clock.h>
+#include <linux/slab.h>
+#include <linux/syscalls.h>
+#include <linux/uaccess.h>
+
+static void delete_clock(struct kref *kref);
+
+/*
+ * Returns NULL if the posix_clock instance attached to 'fp' is old and stale.
+ */
+static struct posix_clock *get_posix_clock(struct file *fp)
+{
+	struct posix_clock *clk = fp->private_data;
+
+	mutex_lock(&clk->mutex);
+
+	if (!clk->zombie)
+		return clk;
+
+	mutex_unlock(&clk->mutex);
+
+	return NULL;
+}
+
+static void put_posix_clock(struct posix_clock *clk)
+{
+	mutex_unlock(&clk->mutex);
+}
+
+static ssize_t posix_clock_read(struct file *fp, char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	struct posix_clock *clk = get_posix_clock(fp);
+	int err = -EINVAL;
+
+	if (!clk)
+		return -ENODEV;
+
+	if (clk->ops.read)
+		err = clk->ops.read(clk, fp->f_flags, buf, count);
+
+	put_posix_clock(clk);
+
+	return err;
+}
+
+static unsigned int posix_clock_poll(struct file *fp, poll_table *wait)
+{
+	struct posix_clock *clk = get_posix_clock(fp);
+	int result = 0;
+
+	if (!clk)
+		return -ENODEV;
+
+	if (clk->ops.poll)
+		result = clk->ops.poll(clk, fp, wait);
+
+	put_posix_clock(clk);
+
+	return result;
+}
+
+static int posix_clock_fasync(int fd, struct file *fp, int on)
+{
+	struct posix_clock *clk = get_posix_clock(fp);
+	int err = 0;
+
+	if (!clk)
+		return -ENODEV;
+
+	if (clk->ops.fasync)
+		err = clk->ops.fasync(clk, fd, fp, on);
+
+	put_posix_clock(clk);
+
+	return err;
+}
+
+static int posix_clock_mmap(struct file *fp, struct vm_area_struct *vma)
+{
+	struct posix_clock *clk = get_posix_clock(fp);
+	int err = -ENODEV;
+
+	if (!clk)
+		return -ENODEV;
+
+	if (clk->ops.mmap)
+		err = clk->ops.mmap(clk, vma);
+
+	put_posix_clock(clk);
+
+	return err;
+}
+
+static long posix_clock_ioctl(struct file *fp,
+			      unsigned int cmd, unsigned long arg)
+{
+	struct posix_clock *clk = get_posix_clock(fp);
+	int err = -ENOTTY;
+
+	if (!clk)
+		return -ENODEV;
+
+	if (clk->ops.ioctl)
+		err = clk->ops.ioctl(clk, cmd, arg);
+
+	put_posix_clock(clk);
+
+	return err;
+}
+
+#ifdef CONFIG_COMPAT
+static long posix_clock_compat_ioctl(struct file *fp,
+				     unsigned int cmd, unsigned long arg)
+{
+	struct posix_clock *clk = get_posix_clock(fp);
+	int err = -ENOTTY;
+
+	if (!clk)
+		return -ENODEV;
+
+	if (clk->ops.ioctl)
+		err = clk->ops.ioctl(clk, cmd, arg);
+
+	put_posix_clock(clk);
+
+	return err;
+}
+#endif
+
+static int posix_clock_open(struct inode *inode, struct file *fp)
+{
+	int err;
+	struct posix_clock *clk =
+		container_of(inode->i_cdev, struct posix_clock, cdev);
+
+	mutex_lock(&clk->mutex);
+
+	if (clk->zombie) {
+		err = -ENODEV;
+		goto out;
+	}
+	if (clk->ops.open)
+		err = clk->ops.open(clk, fp->f_mode);
+	else
+		err = 0;
+
+	if (!err) {
+		kref_get(&clk->kref);
+		fp->private_data = clk;
+	}
+out:
+	mutex_unlock(&clk->mutex);
+	return err;
+}
+
+static int posix_clock_release(struct inode *inode, struct file *fp)
+{
+	struct posix_clock *clk = fp->private_data;
+	int err = 0;
+
+	if (clk->ops.release)
+		err = clk->ops.release(clk);
+
+	kref_put(&clk->kref, delete_clock);
+
+	fp->private_data = NULL;
+
+	return err;
+}
+
+static const struct file_operations posix_clock_file_operations = {
+	.owner		= THIS_MODULE,
+	.llseek		= no_llseek,
+	.read		= posix_clock_read,
+	.poll		= posix_clock_poll,
+	.unlocked_ioctl	= posix_clock_ioctl,
+	.open		= posix_clock_open,
+	.release	= posix_clock_release,
+	.fasync		= posix_clock_fasync,
+	.mmap		= posix_clock_mmap,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= posix_clock_compat_ioctl,
+#endif
+};
+
+int posix_clock_register(struct posix_clock *clk, dev_t devid)
+{
+	int err;
+
+	kref_init(&clk->kref);
+	mutex_init(&clk->mutex);
+
+	cdev_init(&clk->cdev, &posix_clock_file_operations);
+	clk->cdev.owner = clk->ops.owner;
+	err = cdev_add(&clk->cdev, devid, 1);
+	if (err)
+		goto no_cdev;
+
+	return err;
+no_cdev:
+	mutex_destroy(&clk->mutex);
+	return err;
+}
+EXPORT_SYMBOL_GPL(posix_clock_register);
+
+static void delete_clock(struct kref *kref)
+{
+	struct posix_clock *clk = container_of(kref, struct posix_clock, kref);
+	mutex_destroy(&clk->mutex);
+	if (clk->release)
+		clk->release(clk);
+}
+
+void posix_clock_unregister(struct posix_clock *clk)
+{
+	cdev_del(&clk->cdev);
+
+	mutex_lock(&clk->mutex);
+	clk->zombie = true;
+	mutex_unlock(&clk->mutex);
+
+	kref_put(&clk->kref, delete_clock);
+}
+EXPORT_SYMBOL_GPL(posix_clock_unregister);
+
+struct posix_clock_desc {
+	struct file *fp;
+	struct posix_clock *clk;
+};
+
+static int get_clock_desc(const clockid_t id, struct posix_clock_desc *cd)
+{
+	struct file *fp = fget(CLOCKID_TO_FD(id));
+	int err = -EINVAL;
+
+	if (!fp)
+		return err;
+
+	if (fp->f_op->open != posix_clock_open || !fp->private_data)
+		goto out;
+
+	cd->fp = fp;
+	cd->clk = get_posix_clock(fp);
+
+	err = cd->clk ? 0 : -ENODEV;
+out:
+	if (err)
+		fput(fp);
+	return err;
+}
+
+static void put_clock_desc(struct posix_clock_desc *cd)
+{
+	put_posix_clock(cd->clk);
+	fput(cd->fp);
+}
+
+static int pc_clock_adjtime(clockid_t id, struct timex *tx)
+{
+	struct posix_clock_desc cd;
+	int err;
+
+	err = get_clock_desc(id, &cd);
+	if (err)
+		return err;
+
+	if ((cd.fp->f_mode & FMODE_WRITE) == 0) {
+		err = -EACCES;
+		goto out;
+	}
+
+	if (cd.clk->ops.clock_adjtime)
+		err = cd.clk->ops.clock_adjtime(cd.clk, tx);
+	else
+		err = -EOPNOTSUPP;
+out:
+	put_clock_desc(&cd);
+
+	return err;
+}
+
+static int pc_clock_gettime(clockid_t id, struct timespec *ts)
+{
+	struct posix_clock_desc cd;
+	int err;
+
+	err = get_clock_desc(id, &cd);
+	if (err)
+		return err;
+
+	if (cd.clk->ops.clock_gettime)
+		err = cd.clk->ops.clock_gettime(cd.clk, ts);
+	else
+		err = -EOPNOTSUPP;
+
+	put_clock_desc(&cd);
+
+	return err;
+}
+
+static int pc_clock_getres(clockid_t id, struct timespec *ts)
+{
+	struct posix_clock_desc cd;
+	int err;
+
+	err = get_clock_desc(id, &cd);
+	if (err)
+		return err;
+
+	if (cd.clk->ops.clock_getres)
+		err = cd.clk->ops.clock_getres(cd.clk, ts);
+	else
+		err = -EOPNOTSUPP;
+
+	put_clock_desc(&cd);
+
+	return err;
+}
+
+static int pc_clock_settime(clockid_t id, const struct timespec *ts)
+{
+	struct posix_clock_desc cd;
+	int err;
+
+	err = get_clock_desc(id, &cd);
+	if (err)
+		return err;
+
+	if ((cd.fp->f_mode & FMODE_WRITE) == 0) {
+		err = -EACCES;
+		goto out;
+	}
+
+	if (cd.clk->ops.clock_settime)
+		err = cd.clk->ops.clock_settime(cd.clk, ts);
+	else
+		err = -EOPNOTSUPP;
+out:
+	put_clock_desc(&cd);
+
+	return err;
+}
+
+static int pc_timer_create(struct k_itimer *kit)
+{
+	clockid_t id = kit->it_clock;
+	struct posix_clock_desc cd;
+	int err;
+
+	err = get_clock_desc(id, &cd);
+	if (err)
+		return err;
+
+	if (cd.clk->ops.timer_create)
+		err = cd.clk->ops.timer_create(cd.clk, kit);
+	else
+		err = -EOPNOTSUPP;
+
+	put_clock_desc(&cd);
+
+	return err;
+}
+
+static int pc_timer_delete(struct k_itimer *kit)
+{
+	clockid_t id = kit->it_clock;
+	struct posix_clock_desc cd;
+	int err;
+
+	err = get_clock_desc(id, &cd);
+	if (err)
+		return err;
+
+	if (cd.clk->ops.timer_delete)
+		err = cd.clk->ops.timer_delete(cd.clk, kit);
+	else
+		err = -EOPNOTSUPP;
+
+	put_clock_desc(&cd);
+
+	return err;
+}
+
+static void pc_timer_gettime(struct k_itimer *kit, struct itimerspec *ts)
+{
+	clockid_t id = kit->it_clock;
+	struct posix_clock_desc cd;
+
+	if (get_clock_desc(id, &cd))
+		return;
+
+	if (cd.clk->ops.timer_gettime)
+		cd.clk->ops.timer_gettime(cd.clk, kit, ts);
+
+	put_clock_desc(&cd);
+}
+
+static int pc_timer_settime(struct k_itimer *kit, int flags,
+			    struct itimerspec *ts, struct itimerspec *old)
+{
+	clockid_t id = kit->it_clock;
+	struct posix_clock_desc cd;
+	int err;
+
+	err = get_clock_desc(id, &cd);
+	if (err)
+		return err;
+
+	if (cd.clk->ops.timer_settime)
+		err = cd.clk->ops.timer_settime(cd.clk, kit, flags, ts, old);
+	else
+		err = -EOPNOTSUPP;
+
+	put_clock_desc(&cd);
+
+	return err;
+}
+
+struct k_clock clock_posix_dynamic = {
+	.clock_getres	= pc_clock_getres,
+	.clock_set	= pc_clock_settime,
+	.clock_get	= pc_clock_gettime,
+	.clock_adj	= pc_clock_adjtime,
+	.timer_create	= pc_timer_create,
+	.timer_set	= pc_timer_settime,
+	.timer_del	= pc_timer_delete,
+	.timer_get	= pc_timer_gettime,
+};
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index a3b5aff62606..da800ffa810c 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -18,7 +18,6 @@
 #include <linux/percpu.h>
 #include <linux/profile.h>
 #include <linux/sched.h>
-#include <linux/tick.h>
 
 #include "tick-internal.h"
 
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index ed228ef6f6b8..119528de8235 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -18,7 +18,6 @@
 #include <linux/percpu.h>
 #include <linux/profile.h>
 #include <linux/sched.h>
-#include <linux/tick.h>
 
 #include <asm/irq_regs.h>
 
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index f65d3a723a64..1009b06d6f89 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -1,6 +1,10 @@
 /*
  * tick internal variable and functions used by low/high res code
  */
+#include <linux/hrtimer.h>
+#include <linux/tick.h>
+
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_BUILD
 
 #define TICK_DO_TIMER_NONE	-1
 #define TICK_DO_TIMER_BOOT	-2
@@ -135,3 +139,8 @@ static inline int tick_device_is_functional(struct clock_event_device *dev)
 {
 	return !(dev->features & CLOCK_EVT_FEAT_DUMMY);
 }
+
+#endif
+
+extern void do_timer(unsigned long ticks);
+extern seqlock_t xtime_lock;
diff --git a/kernel/time/tick-oneshot.c b/kernel/time/tick-oneshot.c
index 5cbc101f908b..2d04411a5f05 100644
--- a/kernel/time/tick-oneshot.c
+++ b/kernel/time/tick-oneshot.c
@@ -18,7 +18,6 @@
 #include <linux/percpu.h>
 #include <linux/profile.h>
 #include <linux/sched.h>
-#include <linux/tick.h>
 
 #include "tick-internal.h"
 
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index c55ea2433471..d5097c44b407 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -19,7 +19,6 @@
 #include <linux/percpu.h>
 #include <linux/profile.h>
 #include <linux/sched.h>
-#include <linux/tick.h>
 #include <linux/module.h>
 
 #include <asm/irq_regs.h>
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index d27c7562902c..3bd7e3d5c632 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -353,7 +353,7 @@ EXPORT_SYMBOL(do_gettimeofday);
  *
  * Sets the time of day to the new time and update NTP and notify hrtimers
  */
-int do_settimeofday(struct timespec *tv)
+int do_settimeofday(const struct timespec *tv)
 {
 	struct timespec ts_delta;
 	unsigned long flags;
@@ -387,6 +387,42 @@ int do_settimeofday(struct timespec *tv)
 
 EXPORT_SYMBOL(do_settimeofday);
 
+
+/**
+ * timekeeping_inject_offset - Adds or subtracts from the current time.
+ * @tv:		pointer to the timespec variable containing the offset
+ *
+ * Adds or subtracts an offset value from the current time.
+ */
+int timekeeping_inject_offset(struct timespec *ts)
+{
+	unsigned long flags;
+
+	if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC)
+		return -EINVAL;
+
+	write_seqlock_irqsave(&xtime_lock, flags);
+
+	timekeeping_forward_now();
+
+	xtime = timespec_add(xtime, *ts);
+	wall_to_monotonic = timespec_sub(wall_to_monotonic, *ts);
+
+	timekeeper.ntp_error = 0;
+	ntp_clear();
+
+	update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock,
+				timekeeper.mult);
+
+	write_sequnlock_irqrestore(&xtime_lock, flags);
+
+	/* signal hrtimers about time change */
+	clock_was_set();
+
+	return 0;
+}
+EXPORT_SYMBOL(timekeeping_inject_offset);
+
 /**
  * change_clocksource - Swaps clocksources if a new one is available
  *
@@ -779,7 +815,7 @@ static cycle_t logarithmic_accumulation(cycle_t offset, int shift)
  *
  * Called from the timer interrupt, must hold a write on xtime_lock.
  */
-void update_wall_time(void)
+static void update_wall_time(void)
 {
 	struct clocksource *clock;
 	cycle_t offset;
@@ -871,7 +907,7 @@ void update_wall_time(void)
  * getboottime - Return the real time of system boot.
  * @ts:		pointer to the timespec to be set
  *
- * Returns the time of day in a timespec.
+ * Returns the wall-time of boot in a timespec.
  *
  * This is based on the wall_to_monotonic offset and the total suspend
  * time. Calls to settimeofday will affect the value returned (which
@@ -889,6 +925,55 @@ void getboottime(struct timespec *ts)
 }
 EXPORT_SYMBOL_GPL(getboottime);
 
+
+/**
+ * get_monotonic_boottime - Returns monotonic time since boot
+ * @ts:		pointer to the timespec to be set
+ *
+ * Returns the monotonic time since boot in a timespec.
+ *
+ * This is similar to CLOCK_MONTONIC/ktime_get_ts, but also
+ * includes the time spent in suspend.
+ */
+void get_monotonic_boottime(struct timespec *ts)
+{
+	struct timespec tomono, sleep;
+	unsigned int seq;
+	s64 nsecs;
+
+	WARN_ON(timekeeping_suspended);
+
+	do {
+		seq = read_seqbegin(&xtime_lock);
+		*ts = xtime;
+		tomono = wall_to_monotonic;
+		sleep = total_sleep_time;
+		nsecs = timekeeping_get_ns();
+
+	} while (read_seqretry(&xtime_lock, seq));
+
+	set_normalized_timespec(ts, ts->tv_sec + tomono.tv_sec + sleep.tv_sec,
+			ts->tv_nsec + tomono.tv_nsec + sleep.tv_nsec + nsecs);
+}
+EXPORT_SYMBOL_GPL(get_monotonic_boottime);
+
+/**
+ * ktime_get_boottime - Returns monotonic time since boot in a ktime
+ *
+ * Returns the monotonic time since boot in a ktime
+ *
+ * This is similar to CLOCK_MONTONIC/ktime_get, but also
+ * includes the time spent in suspend.
+ */
+ktime_t ktime_get_boottime(void)
+{
+	struct timespec ts;
+
+	get_monotonic_boottime(&ts);
+	return timespec_to_ktime(ts);
+}
+EXPORT_SYMBOL_GPL(ktime_get_boottime);
+
 /**
  * monotonic_to_bootbased - Convert the monotonic time to boot based.
  * @ts:		pointer to the timespec to be converted
@@ -910,11 +995,6 @@ struct timespec __current_kernel_time(void)
 	return xtime;
 }
 
-struct timespec __get_wall_to_monotonic(void)
-{
-	return wall_to_monotonic;
-}
-
 struct timespec current_kernel_time(void)
 {
 	struct timespec now;
@@ -946,3 +1026,48 @@ struct timespec get_monotonic_coarse(void)
 				now.tv_nsec + mono.tv_nsec);
 	return now;
 }
+
+/*
+ * The 64-bit jiffies value is not atomic - you MUST NOT read it
+ * without sampling the sequence number in xtime_lock.
+ * jiffies is defined in the linker script...
+ */
+void do_timer(unsigned long ticks)
+{
+	jiffies_64 += ticks;
+	update_wall_time();
+	calc_global_load(ticks);
+}
+
+/**
+ * get_xtime_and_monotonic_and_sleep_offset() - get xtime, wall_to_monotonic,
+ *    and sleep offsets.
+ * @xtim:	pointer to timespec to be set with xtime
+ * @wtom:	pointer to timespec to be set with wall_to_monotonic
+ * @sleep:	pointer to timespec to be set with time in suspend
+ */
+void get_xtime_and_monotonic_and_sleep_offset(struct timespec *xtim,
+				struct timespec *wtom, struct timespec *sleep)
+{
+	unsigned long seq;
+
+	do {
+		seq = read_seqbegin(&xtime_lock);
+		*xtim = xtime;
+		*wtom = wall_to_monotonic;
+		*sleep = total_sleep_time;
+	} while (read_seqretry(&xtime_lock, seq));
+}
+
+/**
+ * xtime_update() - advances the timekeeping infrastructure
+ * @ticks:	number of ticks, that have elapsed since the last call.
+ *
+ * Must be called with interrupts disabled.
+ */
+void xtime_update(unsigned long ticks)
+{
+	write_seqlock(&xtime_lock);
+	do_timer(ticks);
+	write_sequnlock(&xtime_lock);
+}
diff --git a/kernel/timer.c b/kernel/timer.c
index d6459923d245..fd6198692b57 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -404,6 +404,11 @@ static void timer_stats_account_timer(struct timer_list *timer) {}
 
 static struct debug_obj_descr timer_debug_descr;
 
+static void *timer_debug_hint(void *addr)
+{
+	return ((struct timer_list *) addr)->function;
+}
+
 /*
  * fixup_init is called when:
  * - an active object is initialized
@@ -477,6 +482,7 @@ static int timer_fixup_free(void *addr, enum debug_obj_state state)
 
 static struct debug_obj_descr timer_debug_descr = {
 	.name		= "timer_list",
+	.debug_hint	= timer_debug_hint,
 	.fixup_init	= timer_fixup_init,
 	.fixup_activate	= timer_fixup_activate,
 	.fixup_free	= timer_fixup_free,
@@ -964,6 +970,25 @@ EXPORT_SYMBOL(try_to_del_timer_sync);
  * add_timer_on(). Upon exit the timer is not queued and the handler is
  * not running on any CPU.
  *
+ * Note: You must not hold locks that are held in interrupt context
+ *   while calling this function. Even if the lock has nothing to do
+ *   with the timer in question.  Here's why:
+ *
+ *    CPU0                             CPU1
+ *    ----                             ----
+ *                                   <SOFTIRQ>
+ *                                   call_timer_fn();
+ *                                     base->running_timer = mytimer;
+ *  spin_lock_irq(somelock);
+ *                                     <IRQ>
+ *                                        spin_lock(somelock);
+ *  del_timer_sync(mytimer);
+ *   while (base->running_timer == mytimer);
+ *
+ * Now del_timer_sync() will never return and never release somelock.
+ * The interrupt on the other CPU is waiting to grab somelock but
+ * it has interrupted the softirq that CPU0 is waiting to finish.
+ *
  * The function returns whether it has deactivated a pending timer or not.
  */
 int del_timer_sync(struct timer_list *timer)
@@ -971,6 +996,10 @@ int del_timer_sync(struct timer_list *timer)
 #ifdef CONFIG_LOCKDEP
 	unsigned long flags;
 
+	/*
+	 * If lockdep gives a backtrace here, please reference
+	 * the synchronization rules above.
+	 */
 	local_irq_save(flags);
 	lock_map_acquire(&timer->lockdep_map);
 	lock_map_release(&timer->lockdep_map);
@@ -1295,19 +1324,6 @@ void run_local_timers(void)
 	raise_softirq(TIMER_SOFTIRQ);
 }
 
-/*
- * The 64-bit jiffies value is not atomic - you MUST NOT read it
- * without sampling the sequence number in xtime_lock.
- * jiffies is defined in the linker script...
- */
-
-void do_timer(unsigned long ticks)
-{
-	jiffies_64 += ticks;
-	update_wall_time();
-	calc_global_load(ticks);
-}
-
 #ifdef __ARCH_WANT_SYS_ALARM
 
 /*
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index f3dadae83883..888b611897d3 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -3328,7 +3328,7 @@ static int start_graph_tracing(void)
 	/* The cpu_boot init_task->ret_stack will never be freed */
 	for_each_online_cpu(cpu) {
 		if (!idle_task(cpu)->ret_stack)
-			ftrace_graph_init_task(idle_task(cpu));
+			ftrace_graph_init_idle_task(idle_task(cpu), cpu);
 	}
 
 	do {
@@ -3418,6 +3418,49 @@ void unregister_ftrace_graph(void)
 	mutex_unlock(&ftrace_lock);
 }
 
+static DEFINE_PER_CPU(struct ftrace_ret_stack *, idle_ret_stack);
+
+static void
+graph_init_task(struct task_struct *t, struct ftrace_ret_stack *ret_stack)
+{
+	atomic_set(&t->tracing_graph_pause, 0);
+	atomic_set(&t->trace_overrun, 0);
+	t->ftrace_timestamp = 0;
+	/* make curr_ret_stack visable before we add the ret_stack */
+	smp_wmb();
+	t->ret_stack = ret_stack;
+}
+
+/*
+ * Allocate a return stack for the idle task. May be the first
+ * time through, or it may be done by CPU hotplug online.
+ */
+void ftrace_graph_init_idle_task(struct task_struct *t, int cpu)
+{
+	t->curr_ret_stack = -1;
+	/*
+	 * The idle task has no parent, it either has its own
+	 * stack or no stack at all.
+	 */
+	if (t->ret_stack)
+		WARN_ON(t->ret_stack != per_cpu(idle_ret_stack, cpu));
+
+	if (ftrace_graph_active) {
+		struct ftrace_ret_stack *ret_stack;
+
+		ret_stack = per_cpu(idle_ret_stack, cpu);
+		if (!ret_stack) {
+			ret_stack = kmalloc(FTRACE_RETFUNC_DEPTH
+					    * sizeof(struct ftrace_ret_stack),
+					    GFP_KERNEL);
+			if (!ret_stack)
+				return;
+			per_cpu(idle_ret_stack, cpu) = ret_stack;
+		}
+		graph_init_task(t, ret_stack);
+	}
+}
+
 /* Allocate a return stack for newly created task */
 void ftrace_graph_init_task(struct task_struct *t)
 {
@@ -3433,12 +3476,7 @@ void ftrace_graph_init_task(struct task_struct *t)
 				GFP_KERNEL);
 		if (!ret_stack)
 			return;
-		atomic_set(&t->tracing_graph_pause, 0);
-		atomic_set(&t->trace_overrun, 0);
-		t->ftrace_timestamp = 0;
-		/* make curr_ret_stack visable before we add the ret_stack */
-		smp_wmb();
-		t->ret_stack = ret_stack;
+		graph_init_task(t, ret_stack);
 	}
 }
 
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index bd1c35a4fbcc..db7b439d23ee 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -5,7 +5,6 @@
  */
 #include <linux/ring_buffer.h>
 #include <linux/trace_clock.h>
-#include <linux/ftrace_irq.h>
 #include <linux/spinlock.h>
 #include <linux/debugfs.h>
 #include <linux/uaccess.h>
@@ -1429,6 +1428,17 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
 }
 EXPORT_SYMBOL_GPL(ring_buffer_resize);
 
+void ring_buffer_change_overwrite(struct ring_buffer *buffer, int val)
+{
+	mutex_lock(&buffer->mutex);
+	if (val)
+		buffer->flags |= RB_FL_OVERWRITE;
+	else
+		buffer->flags &= ~RB_FL_OVERWRITE;
+	mutex_unlock(&buffer->mutex);
+}
+EXPORT_SYMBOL_GPL(ring_buffer_change_overwrite);
+
 static inline void *
 __rb_data_page_index(struct buffer_data_page *bpage, unsigned index)
 {
@@ -2162,11 +2172,19 @@ rb_reserve_next_event(struct ring_buffer *buffer,
 	if (likely(ts >= cpu_buffer->write_stamp)) {
 		delta = diff;
 		if (unlikely(test_time_stamp(delta))) {
+			int local_clock_stable = 1;
+#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
+			local_clock_stable = sched_clock_stable;
+#endif
 			WARN_ONCE(delta > (1ULL << 59),
-				  KERN_WARNING "Delta way too big! %llu ts=%llu write stamp = %llu\n",
+				  KERN_WARNING "Delta way too big! %llu ts=%llu write stamp = %llu\n%s",
 				  (unsigned long long)delta,
 				  (unsigned long long)ts,
-				  (unsigned long long)cpu_buffer->write_stamp);
+				  (unsigned long long)cpu_buffer->write_stamp,
+				  local_clock_stable ? "" :
+				  "If you just came from a suspend/resume,\n"
+				  "please switch to the trace global clock:\n"
+				  "  echo global > /sys/kernel/debug/tracing/trace_clock\n");
 			add_timestamp = 1;
 		}
 	}
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index dc53ecb80589..9541c27c1cf2 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -41,8 +41,6 @@
 #include "trace.h"
 #include "trace_output.h"
 
-#define TRACE_BUFFER_FLAGS	(RB_FL_OVERWRITE)
-
 /*
  * On boot up, the ring buffer is set to the minimum size, so that
  * we do not waste memory on systems that are not using tracing.
@@ -340,7 +338,7 @@ static DECLARE_WAIT_QUEUE_HEAD(trace_wait);
 /* trace_flags holds trace_options default values */
 unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK |
 	TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO | TRACE_ITER_SLEEP_TIME |
-	TRACE_ITER_GRAPH_TIME | TRACE_ITER_RECORD_CMD;
+	TRACE_ITER_GRAPH_TIME | TRACE_ITER_RECORD_CMD | TRACE_ITER_OVERWRITE;
 
 static int trace_stop_count;
 static DEFINE_SPINLOCK(tracing_start_lock);
@@ -425,6 +423,7 @@ static const char *trace_options[] = {
 	"sleep-time",
 	"graph-time",
 	"record-cmd",
+	"overwrite",
 	NULL
 };
 
@@ -780,6 +779,11 @@ __acquires(kernel_lock)
 		tracing_reset_online_cpus(tr);
 
 		current_trace = type;
+
+		/* If we expanded the buffers, make sure the max is expanded too */
+		if (ring_buffer_expanded && type->use_max_tr)
+			ring_buffer_resize(max_tr.buffer, trace_buf_size);
+
 		/* the test is responsible for initializing and enabling */
 		pr_info("Testing tracer %s: ", type->name);
 		ret = type->selftest(type, tr);
@@ -792,6 +796,10 @@ __acquires(kernel_lock)
 		/* Only reset on passing, to avoid touching corrupted buffers */
 		tracing_reset_online_cpus(tr);
 
+		/* Shrink the max buffer again */
+		if (ring_buffer_expanded && type->use_max_tr)
+			ring_buffer_resize(max_tr.buffer, 1);
+
 		printk(KERN_CONT "PASSED\n");
 	}
 #endif
@@ -1102,7 +1110,6 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags,
 
 	entry->preempt_count		= pc & 0xff;
 	entry->pid			= (tsk) ? tsk->pid : 0;
-	entry->lock_depth		= (tsk) ? tsk->lock_depth : 0;
 	entry->flags =
 #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT
 		(irqs_disabled_flags(flags) ? TRACE_FLAG_IRQS_OFF : 0) |
@@ -1749,10 +1756,9 @@ static void print_lat_help_header(struct seq_file *m)
 	seq_puts(m, "#                | / _----=> need-resched    \n");
 	seq_puts(m, "#                || / _---=> hardirq/softirq \n");
 	seq_puts(m, "#                ||| / _--=> preempt-depth   \n");
-	seq_puts(m, "#                |||| /_--=> lock-depth       \n");
-	seq_puts(m, "#                |||||/     delay             \n");
-	seq_puts(m, "#  cmd     pid   |||||| time  |   caller      \n");
-	seq_puts(m, "#     \\   /      ||||||   \\   |   /           \n");
+	seq_puts(m, "#                |||| /     delay             \n");
+	seq_puts(m, "#  cmd     pid   ||||| time  |   caller      \n");
+	seq_puts(m, "#     \\   /      |||||  \\    |   /           \n");
 }
 
 static void print_func_help_header(struct seq_file *m)
@@ -2529,6 +2535,9 @@ static void set_tracer_flags(unsigned int mask, int enabled)
 
 	if (mask == TRACE_ITER_RECORD_CMD)
 		trace_event_enable_cmd_record(enabled);
+
+	if (mask == TRACE_ITER_OVERWRITE)
+		ring_buffer_change_overwrite(global_trace.buffer, enabled);
 }
 
 static ssize_t
@@ -2710,6 +2719,10 @@ tracing_ctrl_write(struct file *filp, const char __user *ubuf,
 
 	mutex_lock(&trace_types_lock);
 	if (tracer_enabled ^ val) {
+
+		/* Only need to warn if this is used to change the state */
+		WARN_ONCE(1, "tracing_enabled is deprecated. Use tracing_on");
+
 		if (val) {
 			tracer_enabled = 1;
 			if (current_trace->start)
@@ -4551,9 +4564,11 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
 __init static int tracer_alloc_buffers(void)
 {
 	int ring_buf_size;
+	enum ring_buffer_flags rb_flags;
 	int i;
 	int ret = -ENOMEM;
 
+
 	if (!alloc_cpumask_var(&tracing_buffer_mask, GFP_KERNEL))
 		goto out;
 
@@ -4566,12 +4581,13 @@ __init static int tracer_alloc_buffers(void)
 	else
 		ring_buf_size = 1;
 
+	rb_flags = trace_flags & TRACE_ITER_OVERWRITE ? RB_FL_OVERWRITE : 0;
+
 	cpumask_copy(tracing_buffer_mask, cpu_possible_mask);
 	cpumask_copy(tracing_cpumask, cpu_all_mask);
 
 	/* TODO: make the number of buffers hot pluggable with CPUS */
-	global_trace.buffer = ring_buffer_alloc(ring_buf_size,
-						   TRACE_BUFFER_FLAGS);
+	global_trace.buffer = ring_buffer_alloc(ring_buf_size, rb_flags);
 	if (!global_trace.buffer) {
 		printk(KERN_ERR "tracer: failed to allocate ring buffer!\n");
 		WARN_ON(1);
@@ -4581,7 +4597,7 @@ __init static int tracer_alloc_buffers(void)
 
 
 #ifdef CONFIG_TRACER_MAX_TRACE
-	max_tr.buffer = ring_buffer_alloc(1, TRACE_BUFFER_FLAGS);
+	max_tr.buffer = ring_buffer_alloc(1, rb_flags);
 	if (!max_tr.buffer) {
 		printk(KERN_ERR "tracer: failed to allocate max ring buffer!\n");
 		WARN_ON(1);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 9021f8c0c0c3..5e9dfc6286dd 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -272,8 +272,8 @@ struct tracer {
 	/* If you handled the flag setting, return 0 */
 	int			(*set_flag)(u32 old_flags, u32 bit, int set);
 	struct tracer		*next;
-	int			print_max;
 	struct tracer_flags	*flags;
+	int			print_max;
 	int			use_max_tr;
 };
 
@@ -606,6 +606,7 @@ enum trace_iterator_flags {
 	TRACE_ITER_SLEEP_TIME		= 0x40000,
 	TRACE_ITER_GRAPH_TIME		= 0x80000,
 	TRACE_ITER_RECORD_CMD		= 0x100000,
+	TRACE_ITER_OVERWRITE		= 0x200000,
 };
 
 /*
@@ -661,8 +662,10 @@ struct ftrace_event_field {
 };
 
 struct event_filter {
-	int			n_preds;
-	struct filter_pred	**preds;
+	int			n_preds;	/* Number assigned */
+	int			a_preds;	/* allocated */
+	struct filter_pred	*preds;
+	struct filter_pred	*root;
 	char			*filter_string;
 };
 
@@ -674,11 +677,23 @@ struct event_subsystem {
 	int			nr_events;
 };
 
+#define FILTER_PRED_INVALID	((unsigned short)-1)
+#define FILTER_PRED_IS_RIGHT	(1 << 15)
+#define FILTER_PRED_FOLD	(1 << 15)
+
+/*
+ * The max preds is the size of unsigned short with
+ * two flags at the MSBs. One bit is used for both the IS_RIGHT
+ * and FOLD flags. The other is reserved.
+ *
+ * 2^14 preds is way more than enough.
+ */
+#define MAX_FILTER_PRED		16384
+
 struct filter_pred;
 struct regex;
 
-typedef int (*filter_pred_fn_t) (struct filter_pred *pred, void *event,
-				 int val1, int val2);
+typedef int (*filter_pred_fn_t) (struct filter_pred *pred, void *event);
 
 typedef int (*regex_match_func)(char *str, struct regex *r, int len);
 
@@ -700,11 +715,23 @@ struct filter_pred {
 	filter_pred_fn_t 	fn;
 	u64 			val;
 	struct regex		regex;
-	char 			*field_name;
+	/*
+	 * Leaf nodes use field_name, ops is used by AND and OR
+	 * nodes. The field_name is always freed when freeing a pred.
+	 * We can overload field_name for ops and have it freed
+	 * as well.
+	 */
+	union {
+		char		*field_name;
+		unsigned short	*ops;
+	};
 	int 			offset;
 	int 			not;
 	int 			op;
-	int 			pop_n;
+	unsigned short		index;
+	unsigned short		parent;
+	unsigned short		left;
+	unsigned short		right;
 };
 
 extern struct list_head ftrace_common_fields;
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index 6cf223764be8..1516cb3ec549 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -109,12 +109,12 @@ FTRACE_ENTRY(funcgraph_exit, ftrace_graph_ret_entry,
  */
 #define FTRACE_CTX_FIELDS					\
 	__field(	unsigned int,	prev_pid	)	\
+	__field(	unsigned int,	next_pid	)	\
+	__field(	unsigned int,	next_cpu	)       \
 	__field(	unsigned char,	prev_prio	)	\
 	__field(	unsigned char,	prev_state	)	\
-	__field(	unsigned int,	next_pid	)	\
 	__field(	unsigned char,	next_prio	)	\
-	__field(	unsigned char,	next_state	)	\
-	__field(	unsigned int,	next_cpu	)
+	__field(	unsigned char,	next_state	)
 
 FTRACE_ENTRY(context_switch, ctx_switch_entry,
 
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 5f499e0438a4..e88f74fe1d4c 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -116,7 +116,6 @@ static int trace_define_common_fields(void)
 	__common_field(unsigned char, flags);
 	__common_field(unsigned char, preempt_count);
 	__common_field(int, pid);
-	__common_field(int, lock_depth);
 
 	return ret;
 }
@@ -326,6 +325,7 @@ int trace_set_clr_event(const char *system, const char *event, int set)
 {
 	return __ftrace_set_clr_event(NULL, system, event, set);
 }
+EXPORT_SYMBOL_GPL(trace_set_clr_event);
 
 /* 128 should be much more than enough */
 #define EVENT_BUF_SIZE		127
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 36d40104b17f..3249b4f77ef0 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -123,9 +123,13 @@ struct filter_parse_state {
 	} operand;
 };
 
+struct pred_stack {
+	struct filter_pred	**preds;
+	int			index;
+};
+
 #define DEFINE_COMPARISON_PRED(type)					\
-static int filter_pred_##type(struct filter_pred *pred, void *event,	\
-			      int val1, int val2)			\
+static int filter_pred_##type(struct filter_pred *pred, void *event)	\
 {									\
 	type *addr = (type *)(event + pred->offset);			\
 	type val = (type)pred->val;					\
@@ -152,8 +156,7 @@ static int filter_pred_##type(struct filter_pred *pred, void *event,	\
 }
 
 #define DEFINE_EQUALITY_PRED(size)					\
-static int filter_pred_##size(struct filter_pred *pred, void *event,	\
-			      int val1, int val2)			\
+static int filter_pred_##size(struct filter_pred *pred, void *event)	\
 {									\
 	u##size *addr = (u##size *)(event + pred->offset);		\
 	u##size val = (u##size)pred->val;				\
@@ -178,23 +181,8 @@ DEFINE_EQUALITY_PRED(32);
 DEFINE_EQUALITY_PRED(16);
 DEFINE_EQUALITY_PRED(8);
 
-static int filter_pred_and(struct filter_pred *pred __attribute((unused)),
-			   void *event __attribute((unused)),
-			   int val1, int val2)
-{
-	return val1 && val2;
-}
-
-static int filter_pred_or(struct filter_pred *pred __attribute((unused)),
-			  void *event __attribute((unused)),
-			  int val1, int val2)
-{
-	return val1 || val2;
-}
-
 /* Filter predicate for fixed sized arrays of characters */
-static int filter_pred_string(struct filter_pred *pred, void *event,
-			      int val1, int val2)
+static int filter_pred_string(struct filter_pred *pred, void *event)
 {
 	char *addr = (char *)(event + pred->offset);
 	int cmp, match;
@@ -207,8 +195,7 @@ static int filter_pred_string(struct filter_pred *pred, void *event,
 }
 
 /* Filter predicate for char * pointers */
-static int filter_pred_pchar(struct filter_pred *pred, void *event,
-			     int val1, int val2)
+static int filter_pred_pchar(struct filter_pred *pred, void *event)
 {
 	char **addr = (char **)(event + pred->offset);
 	int cmp, match;
@@ -231,8 +218,7 @@ static int filter_pred_pchar(struct filter_pred *pred, void *event,
  * and add it to the address of the entry, and at last we have
  * the address of the string.
  */
-static int filter_pred_strloc(struct filter_pred *pred, void *event,
-			      int val1, int val2)
+static int filter_pred_strloc(struct filter_pred *pred, void *event)
 {
 	u32 str_item = *(u32 *)(event + pred->offset);
 	int str_loc = str_item & 0xffff;
@@ -247,8 +233,7 @@ static int filter_pred_strloc(struct filter_pred *pred, void *event,
 	return match;
 }
 
-static int filter_pred_none(struct filter_pred *pred, void *event,
-			    int val1, int val2)
+static int filter_pred_none(struct filter_pred *pred, void *event)
 {
 	return 0;
 }
@@ -377,32 +362,147 @@ static void filter_build_regex(struct filter_pred *pred)
 	pred->not ^= not;
 }
 
+enum move_type {
+	MOVE_DOWN,
+	MOVE_UP_FROM_LEFT,
+	MOVE_UP_FROM_RIGHT
+};
+
+static struct filter_pred *
+get_pred_parent(struct filter_pred *pred, struct filter_pred *preds,
+		int index, enum move_type *move)
+{
+	if (pred->parent & FILTER_PRED_IS_RIGHT)
+		*move = MOVE_UP_FROM_RIGHT;
+	else
+		*move = MOVE_UP_FROM_LEFT;
+	pred = &preds[pred->parent & ~FILTER_PRED_IS_RIGHT];
+
+	return pred;
+}
+
+/*
+ * A series of AND or ORs where found together. Instead of
+ * climbing up and down the tree branches, an array of the
+ * ops were made in order of checks. We can just move across
+ * the array and short circuit if needed.
+ */
+static int process_ops(struct filter_pred *preds,
+		       struct filter_pred *op, void *rec)
+{
+	struct filter_pred *pred;
+	int type;
+	int match;
+	int i;
+
+	/*
+	 * Micro-optimization: We set type to true if op
+	 * is an OR and false otherwise (AND). Then we
+	 * just need to test if the match is equal to
+	 * the type, and if it is, we can short circuit the
+	 * rest of the checks:
+	 *
+	 * if ((match && op->op == OP_OR) ||
+	 *     (!match && op->op == OP_AND))
+	 *	  return match;
+	 */
+	type = op->op == OP_OR;
+
+	for (i = 0; i < op->val; i++) {
+		pred = &preds[op->ops[i]];
+		match = pred->fn(pred, rec);
+		if (!!match == type)
+			return match;
+	}
+	return match;
+}
+
 /* return 1 if event matches, 0 otherwise (discard) */
 int filter_match_preds(struct event_filter *filter, void *rec)
 {
-	int match, top = 0, val1 = 0, val2 = 0;
-	int stack[MAX_FILTER_PRED];
+	int match = -1;
+	enum move_type move = MOVE_DOWN;
+	struct filter_pred *preds;
 	struct filter_pred *pred;
-	int i;
+	struct filter_pred *root;
+	int n_preds;
+	int done = 0;
+
+	/* no filter is considered a match */
+	if (!filter)
+		return 1;
+
+	n_preds = filter->n_preds;
+
+	if (!n_preds)
+		return 1;
+
+	/*
+	 * n_preds, root and filter->preds are protect with preemption disabled.
+	 */
+	preds = rcu_dereference_sched(filter->preds);
+	root = rcu_dereference_sched(filter->root);
+	if (!root)
+		return 1;
+
+	pred = root;
 
-	for (i = 0; i < filter->n_preds; i++) {
-		pred = filter->preds[i];
-		if (!pred->pop_n) {
-			match = pred->fn(pred, rec, val1, val2);
-			stack[top++] = match;
+	/* match is currently meaningless */
+	match = -1;
+
+	do {
+		switch (move) {
+		case MOVE_DOWN:
+			/* only AND and OR have children */
+			if (pred->left != FILTER_PRED_INVALID) {
+				/* If ops is set, then it was folded. */
+				if (!pred->ops) {
+					/* keep going to down the left side */
+					pred = &preds[pred->left];
+					continue;
+				}
+				/* We can treat folded ops as a leaf node */
+				match = process_ops(preds, pred, rec);
+			} else
+				match = pred->fn(pred, rec);
+			/* If this pred is the only pred */
+			if (pred == root)
+				break;
+			pred = get_pred_parent(pred, preds,
+					       pred->parent, &move);
+			continue;
+		case MOVE_UP_FROM_LEFT:
+			/*
+			 * Check for short circuits.
+			 *
+			 * Optimization: !!match == (pred->op == OP_OR)
+			 *   is the same as:
+			 * if ((match && pred->op == OP_OR) ||
+			 *     (!match && pred->op == OP_AND))
+			 */
+			if (!!match == (pred->op == OP_OR)) {
+				if (pred == root)
+					break;
+				pred = get_pred_parent(pred, preds,
+						       pred->parent, &move);
+				continue;
+			}
+			/* now go down the right side of the tree. */
+			pred = &preds[pred->right];
+			move = MOVE_DOWN;
+			continue;
+		case MOVE_UP_FROM_RIGHT:
+			/* We finished this equation. */
+			if (pred == root)
+				break;
+			pred = get_pred_parent(pred, preds,
+					       pred->parent, &move);
 			continue;
 		}
-		if (pred->pop_n > top) {
-			WARN_ON_ONCE(1);
-			return 0;
-		}
-		val1 = stack[--top];
-		val2 = stack[--top];
-		match = pred->fn(pred, rec, val1, val2);
-		stack[top++] = match;
-	}
+		done = 1;
+	} while (!done);
 
-	return stack[--top];
+	return match;
 }
 EXPORT_SYMBOL_GPL(filter_match_preds);
 
@@ -414,6 +514,9 @@ static void parse_error(struct filter_parse_state *ps, int err, int pos)
 
 static void remove_filter_string(struct event_filter *filter)
 {
+	if (!filter)
+		return;
+
 	kfree(filter->filter_string);
 	filter->filter_string = NULL;
 }
@@ -473,9 +576,10 @@ static void append_filter_err(struct filter_parse_state *ps,
 
 void print_event_filter(struct ftrace_event_call *call, struct trace_seq *s)
 {
-	struct event_filter *filter = call->filter;
+	struct event_filter *filter;
 
 	mutex_lock(&event_mutex);
+	filter = call->filter;
 	if (filter && filter->filter_string)
 		trace_seq_printf(s, "%s\n", filter->filter_string);
 	else
@@ -486,9 +590,10 @@ void print_event_filter(struct ftrace_event_call *call, struct trace_seq *s)
 void print_subsystem_event_filter(struct event_subsystem *system,
 				  struct trace_seq *s)
 {
-	struct event_filter *filter = system->filter;
+	struct event_filter *filter;
 
 	mutex_lock(&event_mutex);
+	filter = system->filter;
 	if (filter && filter->filter_string)
 		trace_seq_printf(s, "%s\n", filter->filter_string);
 	else
@@ -539,10 +644,58 @@ static void filter_clear_pred(struct filter_pred *pred)
 	pred->regex.len = 0;
 }
 
-static int filter_set_pred(struct filter_pred *dest,
+static int __alloc_pred_stack(struct pred_stack *stack, int n_preds)
+{
+	stack->preds = kzalloc(sizeof(*stack->preds)*(n_preds + 1), GFP_KERNEL);
+	if (!stack->preds)
+		return -ENOMEM;
+	stack->index = n_preds;
+	return 0;
+}
+
+static void __free_pred_stack(struct pred_stack *stack)
+{
+	kfree(stack->preds);
+	stack->index = 0;
+}
+
+static int __push_pred_stack(struct pred_stack *stack,
+			     struct filter_pred *pred)
+{
+	int index = stack->index;
+
+	if (WARN_ON(index == 0))
+		return -ENOSPC;
+
+	stack->preds[--index] = pred;
+	stack->index = index;
+	return 0;
+}
+
+static struct filter_pred *
+__pop_pred_stack(struct pred_stack *stack)
+{
+	struct filter_pred *pred;
+	int index = stack->index;
+
+	pred = stack->preds[index++];
+	if (!pred)
+		return NULL;
+
+	stack->index = index;
+	return pred;
+}
+
+static int filter_set_pred(struct event_filter *filter,
+			   int idx,
+			   struct pred_stack *stack,
 			   struct filter_pred *src,
 			   filter_pred_fn_t fn)
 {
+	struct filter_pred *dest = &filter->preds[idx];
+	struct filter_pred *left;
+	struct filter_pred *right;
+
 	*dest = *src;
 	if (src->field_name) {
 		dest->field_name = kstrdup(src->field_name, GFP_KERNEL);
@@ -550,116 +703,140 @@ static int filter_set_pred(struct filter_pred *dest,
 			return -ENOMEM;
 	}
 	dest->fn = fn;
+	dest->index = idx;
 
-	return 0;
+	if (dest->op == OP_OR || dest->op == OP_AND) {
+		right = __pop_pred_stack(stack);
+		left = __pop_pred_stack(stack);
+		if (!left || !right)
+			return -EINVAL;
+		/*
+		 * If both children can be folded
+		 * and they are the same op as this op or a leaf,
+		 * then this op can be folded.
+		 */
+		if (left->index & FILTER_PRED_FOLD &&
+		    (left->op == dest->op ||
+		     left->left == FILTER_PRED_INVALID) &&
+		    right->index & FILTER_PRED_FOLD &&
+		    (right->op == dest->op ||
+		     right->left == FILTER_PRED_INVALID))
+			dest->index |= FILTER_PRED_FOLD;
+
+		dest->left = left->index & ~FILTER_PRED_FOLD;
+		dest->right = right->index & ~FILTER_PRED_FOLD;
+		left->parent = dest->index & ~FILTER_PRED_FOLD;
+		right->parent = dest->index | FILTER_PRED_IS_RIGHT;
+	} else {
+		/*
+		 * Make dest->left invalid to be used as a quick
+		 * way to know this is a leaf node.
+		 */
+		dest->left = FILTER_PRED_INVALID;
+
+		/* All leafs allow folding the parent ops. */
+		dest->index |= FILTER_PRED_FOLD;
+	}
+
+	return __push_pred_stack(stack, dest);
 }
 
-static void filter_disable_preds(struct ftrace_event_call *call)
+static void __free_preds(struct event_filter *filter)
 {
-	struct event_filter *filter = call->filter;
 	int i;
 
-	call->flags &= ~TRACE_EVENT_FL_FILTERED;
+	if (filter->preds) {
+		for (i = 0; i < filter->a_preds; i++)
+			kfree(filter->preds[i].field_name);
+		kfree(filter->preds);
+		filter->preds = NULL;
+	}
+	filter->a_preds = 0;
 	filter->n_preds = 0;
-
-	for (i = 0; i < MAX_FILTER_PRED; i++)
-		filter->preds[i]->fn = filter_pred_none;
 }
 
-static void __free_preds(struct event_filter *filter)
+static void filter_disable(struct ftrace_event_call *call)
 {
-	int i;
+	call->flags &= ~TRACE_EVENT_FL_FILTERED;
+}
 
+static void __free_filter(struct event_filter *filter)
+{
 	if (!filter)
 		return;
 
-	for (i = 0; i < MAX_FILTER_PRED; i++) {
-		if (filter->preds[i])
-			filter_free_pred(filter->preds[i]);
-	}
-	kfree(filter->preds);
+	__free_preds(filter);
 	kfree(filter->filter_string);
 	kfree(filter);
 }
 
+/*
+ * Called when destroying the ftrace_event_call.
+ * The call is being freed, so we do not need to worry about
+ * the call being currently used. This is for module code removing
+ * the tracepoints from within it.
+ */
 void destroy_preds(struct ftrace_event_call *call)
 {
-	__free_preds(call->filter);
+	__free_filter(call->filter);
 	call->filter = NULL;
-	call->flags &= ~TRACE_EVENT_FL_FILTERED;
 }
 
-static struct event_filter *__alloc_preds(void)
+static struct event_filter *__alloc_filter(void)
 {
 	struct event_filter *filter;
+
+	filter = kzalloc(sizeof(*filter), GFP_KERNEL);
+	return filter;
+}
+
+static int __alloc_preds(struct event_filter *filter, int n_preds)
+{
 	struct filter_pred *pred;
 	int i;
 
-	filter = kzalloc(sizeof(*filter), GFP_KERNEL);
-	if (!filter)
-		return ERR_PTR(-ENOMEM);
+	if (filter->preds)
+		__free_preds(filter);
 
-	filter->n_preds = 0;
+	filter->preds =
+		kzalloc(sizeof(*filter->preds) * n_preds, GFP_KERNEL);
 
-	filter->preds = kzalloc(MAX_FILTER_PRED * sizeof(pred), GFP_KERNEL);
 	if (!filter->preds)
-		goto oom;
+		return -ENOMEM;
 
-	for (i = 0; i < MAX_FILTER_PRED; i++) {
-		pred = kzalloc(sizeof(*pred), GFP_KERNEL);
-		if (!pred)
-			goto oom;
+	filter->a_preds = n_preds;
+	filter->n_preds = 0;
+
+	for (i = 0; i < n_preds; i++) {
+		pred = &filter->preds[i];
 		pred->fn = filter_pred_none;
-		filter->preds[i] = pred;
 	}
 
-	return filter;
-
-oom:
-	__free_preds(filter);
-	return ERR_PTR(-ENOMEM);
-}
-
-static int init_preds(struct ftrace_event_call *call)
-{
-	if (call->filter)
-		return 0;
-
-	call->flags &= ~TRACE_EVENT_FL_FILTERED;
-	call->filter = __alloc_preds();
-	if (IS_ERR(call->filter))
-		return PTR_ERR(call->filter);
-
 	return 0;
 }
 
-static int init_subsystem_preds(struct event_subsystem *system)
+static void filter_free_subsystem_preds(struct event_subsystem *system)
 {
 	struct ftrace_event_call *call;
-	int err;
 
 	list_for_each_entry(call, &ftrace_events, list) {
 		if (strcmp(call->class->system, system->name) != 0)
 			continue;
 
-		err = init_preds(call);
-		if (err)
-			return err;
+		filter_disable(call);
+		remove_filter_string(call->filter);
 	}
-
-	return 0;
 }
 
-static void filter_free_subsystem_preds(struct event_subsystem *system)
+static void filter_free_subsystem_filters(struct event_subsystem *system)
 {
 	struct ftrace_event_call *call;
 
 	list_for_each_entry(call, &ftrace_events, list) {
 		if (strcmp(call->class->system, system->name) != 0)
 			continue;
-
-		filter_disable_preds(call);
-		remove_filter_string(call->filter);
+		__free_filter(call->filter);
+		call->filter = NULL;
 	}
 }
 
@@ -667,18 +844,19 @@ static int filter_add_pred_fn(struct filter_parse_state *ps,
 			      struct ftrace_event_call *call,
 			      struct event_filter *filter,
 			      struct filter_pred *pred,
+			      struct pred_stack *stack,
 			      filter_pred_fn_t fn)
 {
 	int idx, err;
 
-	if (filter->n_preds == MAX_FILTER_PRED) {
+	if (WARN_ON(filter->n_preds == filter->a_preds)) {
 		parse_error(ps, FILT_ERR_TOO_MANY_PREDS, 0);
 		return -ENOSPC;
 	}
 
 	idx = filter->n_preds;
-	filter_clear_pred(filter->preds[idx]);
-	err = filter_set_pred(filter->preds[idx], pred, fn);
+	filter_clear_pred(&filter->preds[idx]);
+	err = filter_set_pred(filter, idx, stack, pred, fn);
 	if (err)
 		return err;
 
@@ -763,6 +941,7 @@ static int filter_add_pred(struct filter_parse_state *ps,
 			   struct ftrace_event_call *call,
 			   struct event_filter *filter,
 			   struct filter_pred *pred,
+			   struct pred_stack *stack,
 			   bool dry_run)
 {
 	struct ftrace_event_field *field;
@@ -770,17 +949,12 @@ static int filter_add_pred(struct filter_parse_state *ps,
 	unsigned long long val;
 	int ret;
 
-	pred->fn = filter_pred_none;
+	fn = pred->fn = filter_pred_none;
 
-	if (pred->op == OP_AND) {
-		pred->pop_n = 2;
-		fn = filter_pred_and;
+	if (pred->op == OP_AND)
 		goto add_pred_fn;
-	} else if (pred->op == OP_OR) {
-		pred->pop_n = 2;
-		fn = filter_pred_or;
+	else if (pred->op == OP_OR)
 		goto add_pred_fn;
-	}
 
 	field = find_event_field(call, pred->field_name);
 	if (!field) {
@@ -829,7 +1003,7 @@ static int filter_add_pred(struct filter_parse_state *ps,
 
 add_pred_fn:
 	if (!dry_run)
-		return filter_add_pred_fn(ps, call, filter, pred, fn);
+		return filter_add_pred_fn(ps, call, filter, pred, stack, fn);
 	return 0;
 }
 
@@ -1187,6 +1361,234 @@ static int check_preds(struct filter_parse_state *ps)
 	return 0;
 }
 
+static int count_preds(struct filter_parse_state *ps)
+{
+	struct postfix_elt *elt;
+	int n_preds = 0;
+
+	list_for_each_entry(elt, &ps->postfix, list) {
+		if (elt->op == OP_NONE)
+			continue;
+		n_preds++;
+	}
+
+	return n_preds;
+}
+
+/*
+ * The tree is walked at filtering of an event. If the tree is not correctly
+ * built, it may cause an infinite loop. Check here that the tree does
+ * indeed terminate.
+ */
+static int check_pred_tree(struct event_filter *filter,
+			   struct filter_pred *root)
+{
+	struct filter_pred *preds;
+	struct filter_pred *pred;
+	enum move_type move = MOVE_DOWN;
+	int count = 0;
+	int done = 0;
+	int max;
+
+	/*
+	 * The max that we can hit a node is three times.
+	 * Once going down, once coming up from left, and
+	 * once coming up from right. This is more than enough
+	 * since leafs are only hit a single time.
+	 */
+	max = 3 * filter->n_preds;
+
+	preds = filter->preds;
+	if  (!preds)
+		return -EINVAL;
+	pred = root;
+
+	do {
+		if (WARN_ON(count++ > max))
+			return -EINVAL;
+
+		switch (move) {
+		case MOVE_DOWN:
+			if (pred->left != FILTER_PRED_INVALID) {
+				pred = &preds[pred->left];
+				continue;
+			}
+			/* A leaf at the root is just a leaf in the tree */
+			if (pred == root)
+				break;
+			pred = get_pred_parent(pred, preds,
+					       pred->parent, &move);
+			continue;
+		case MOVE_UP_FROM_LEFT:
+			pred = &preds[pred->right];
+			move = MOVE_DOWN;
+			continue;
+		case MOVE_UP_FROM_RIGHT:
+			if (pred == root)
+				break;
+			pred = get_pred_parent(pred, preds,
+					       pred->parent, &move);
+			continue;
+		}
+		done = 1;
+	} while (!done);
+
+	/* We are fine. */
+	return 0;
+}
+
+static int count_leafs(struct filter_pred *preds, struct filter_pred *root)
+{
+	struct filter_pred *pred;
+	enum move_type move = MOVE_DOWN;
+	int count = 0;
+	int done = 0;
+
+	pred = root;
+
+	do {
+		switch (move) {
+		case MOVE_DOWN:
+			if (pred->left != FILTER_PRED_INVALID) {
+				pred = &preds[pred->left];
+				continue;
+			}
+			/* A leaf at the root is just a leaf in the tree */
+			if (pred == root)
+				return 1;
+			count++;
+			pred = get_pred_parent(pred, preds,
+					       pred->parent, &move);
+			continue;
+		case MOVE_UP_FROM_LEFT:
+			pred = &preds[pred->right];
+			move = MOVE_DOWN;
+			continue;
+		case MOVE_UP_FROM_RIGHT:
+			if (pred == root)
+				break;
+			pred = get_pred_parent(pred, preds,
+					       pred->parent, &move);
+			continue;
+		}
+		done = 1;
+	} while (!done);
+
+	return count;
+}
+
+static int fold_pred(struct filter_pred *preds, struct filter_pred *root)
+{
+	struct filter_pred *pred;
+	enum move_type move = MOVE_DOWN;
+	int count = 0;
+	int children;
+	int done = 0;
+
+	/* No need to keep the fold flag */
+	root->index &= ~FILTER_PRED_FOLD;
+
+	/* If the root is a leaf then do nothing */
+	if (root->left == FILTER_PRED_INVALID)
+		return 0;
+
+	/* count the children */
+	children = count_leafs(preds, &preds[root->left]);
+	children += count_leafs(preds, &preds[root->right]);
+
+	root->ops = kzalloc(sizeof(*root->ops) * children, GFP_KERNEL);
+	if (!root->ops)
+		return -ENOMEM;
+
+	root->val = children;
+
+	pred = root;
+	do {
+		switch (move) {
+		case MOVE_DOWN:
+			if (pred->left != FILTER_PRED_INVALID) {
+				pred = &preds[pred->left];
+				continue;
+			}
+			if (WARN_ON(count == children))
+				return -EINVAL;
+			pred->index &= ~FILTER_PRED_FOLD;
+			root->ops[count++] = pred->index;
+			pred = get_pred_parent(pred, preds,
+					       pred->parent, &move);
+			continue;
+		case MOVE_UP_FROM_LEFT:
+			pred = &preds[pred->right];
+			move = MOVE_DOWN;
+			continue;
+		case MOVE_UP_FROM_RIGHT:
+			if (pred == root)
+				break;
+			pred = get_pred_parent(pred, preds,
+					       pred->parent, &move);
+			continue;
+		}
+		done = 1;
+	} while (!done);
+
+	return 0;
+}
+
+/*
+ * To optimize the processing of the ops, if we have several "ors" or
+ * "ands" together, we can put them in an array and process them all
+ * together speeding up the filter logic.
+ */
+static int fold_pred_tree(struct event_filter *filter,
+			   struct filter_pred *root)
+{
+	struct filter_pred *preds;
+	struct filter_pred *pred;
+	enum move_type move = MOVE_DOWN;
+	int done = 0;
+	int err;
+
+	preds = filter->preds;
+	if  (!preds)
+		return -EINVAL;
+	pred = root;
+
+	do {
+		switch (move) {
+		case MOVE_DOWN:
+			if (pred->index & FILTER_PRED_FOLD) {
+				err = fold_pred(preds, pred);
+				if (err)
+					return err;
+				/* Folded nodes are like leafs */
+			} else if (pred->left != FILTER_PRED_INVALID) {
+				pred = &preds[pred->left];
+				continue;
+			}
+
+			/* A leaf at the root is just a leaf in the tree */
+			if (pred == root)
+				break;
+			pred = get_pred_parent(pred, preds,
+					       pred->parent, &move);
+			continue;
+		case MOVE_UP_FROM_LEFT:
+			pred = &preds[pred->right];
+			move = MOVE_DOWN;
+			continue;
+		case MOVE_UP_FROM_RIGHT:
+			if (pred == root)
+				break;
+			pred = get_pred_parent(pred, preds,
+					       pred->parent, &move);
+			continue;
+		}
+		done = 1;
+	} while (!done);
+
+	return 0;
+}
+
 static int replace_preds(struct ftrace_event_call *call,
 			 struct event_filter *filter,
 			 struct filter_parse_state *ps,
@@ -1195,14 +1597,32 @@ static int replace_preds(struct ftrace_event_call *call,
 {
 	char *operand1 = NULL, *operand2 = NULL;
 	struct filter_pred *pred;
+	struct filter_pred *root;
 	struct postfix_elt *elt;
+	struct pred_stack stack = { }; /* init to NULL */
 	int err;
 	int n_preds = 0;
 
+	n_preds = count_preds(ps);
+	if (n_preds >= MAX_FILTER_PRED) {
+		parse_error(ps, FILT_ERR_TOO_MANY_PREDS, 0);
+		return -ENOSPC;
+	}
+
 	err = check_preds(ps);
 	if (err)
 		return err;
 
+	if (!dry_run) {
+		err = __alloc_pred_stack(&stack, n_preds);
+		if (err)
+			return err;
+		err = __alloc_preds(filter, n_preds);
+		if (err)
+			goto fail;
+	}
+
+	n_preds = 0;
 	list_for_each_entry(elt, &ps->postfix, list) {
 		if (elt->op == OP_NONE) {
 			if (!operand1)
@@ -1211,14 +1631,16 @@ static int replace_preds(struct ftrace_event_call *call,
 				operand2 = elt->operand;
 			else {
 				parse_error(ps, FILT_ERR_TOO_MANY_OPERANDS, 0);
-				return -EINVAL;
+				err = -EINVAL;
+				goto fail;
 			}
 			continue;
 		}
 
-		if (n_preds++ == MAX_FILTER_PRED) {
+		if (WARN_ON(n_preds++ == MAX_FILTER_PRED)) {
 			parse_error(ps, FILT_ERR_TOO_MANY_PREDS, 0);
-			return -ENOSPC;
+			err = -ENOSPC;
+			goto fail;
 		}
 
 		if (elt->op == OP_AND || elt->op == OP_OR) {
@@ -1228,76 +1650,181 @@ static int replace_preds(struct ftrace_event_call *call,
 
 		if (!operand1 || !operand2) {
 			parse_error(ps, FILT_ERR_MISSING_FIELD, 0);
-			return -EINVAL;
+			err = -EINVAL;
+			goto fail;
 		}
 
 		pred = create_pred(elt->op, operand1, operand2);
 add_pred:
-		if (!pred)
-			return -ENOMEM;
-		err = filter_add_pred(ps, call, filter, pred, dry_run);
+		if (!pred) {
+			err = -ENOMEM;
+			goto fail;
+		}
+		err = filter_add_pred(ps, call, filter, pred, &stack, dry_run);
 		filter_free_pred(pred);
 		if (err)
-			return err;
+			goto fail;
 
 		operand1 = operand2 = NULL;
 	}
 
-	return 0;
+	if (!dry_run) {
+		/* We should have one item left on the stack */
+		pred = __pop_pred_stack(&stack);
+		if (!pred)
+			return -EINVAL;
+		/* This item is where we start from in matching */
+		root = pred;
+		/* Make sure the stack is empty */
+		pred = __pop_pred_stack(&stack);
+		if (WARN_ON(pred)) {
+			err = -EINVAL;
+			filter->root = NULL;
+			goto fail;
+		}
+		err = check_pred_tree(filter, root);
+		if (err)
+			goto fail;
+
+		/* Optimize the tree */
+		err = fold_pred_tree(filter, root);
+		if (err)
+			goto fail;
+
+		/* We don't set root until we know it works */
+		barrier();
+		filter->root = root;
+	}
+
+	err = 0;
+fail:
+	__free_pred_stack(&stack);
+	return err;
 }
 
+struct filter_list {
+	struct list_head	list;
+	struct event_filter	*filter;
+};
+
 static int replace_system_preds(struct event_subsystem *system,
 				struct filter_parse_state *ps,
 				char *filter_string)
 {
 	struct ftrace_event_call *call;
+	struct filter_list *filter_item;
+	struct filter_list *tmp;
+	LIST_HEAD(filter_list);
 	bool fail = true;
 	int err;
 
 	list_for_each_entry(call, &ftrace_events, list) {
-		struct event_filter *filter = call->filter;
 
 		if (strcmp(call->class->system, system->name) != 0)
 			continue;
 
-		/* try to see if the filter can be applied */
-		err = replace_preds(call, filter, ps, filter_string, true);
+		/*
+		 * Try to see if the filter can be applied
+		 *  (filter arg is ignored on dry_run)
+		 */
+		err = replace_preds(call, NULL, ps, filter_string, true);
 		if (err)
+			goto fail;
+	}
+
+	list_for_each_entry(call, &ftrace_events, list) {
+		struct event_filter *filter;
+
+		if (strcmp(call->class->system, system->name) != 0)
 			continue;
 
-		/* really apply the filter */
-		filter_disable_preds(call);
-		err = replace_preds(call, filter, ps, filter_string, false);
+		filter_item = kzalloc(sizeof(*filter_item), GFP_KERNEL);
+		if (!filter_item)
+			goto fail_mem;
+
+		list_add_tail(&filter_item->list, &filter_list);
+
+		filter_item->filter = __alloc_filter();
+		if (!filter_item->filter)
+			goto fail_mem;
+		filter = filter_item->filter;
+
+		/* Can only fail on no memory */
+		err = replace_filter_string(filter, filter_string);
 		if (err)
-			filter_disable_preds(call);
-		else {
+			goto fail_mem;
+
+		err = replace_preds(call, filter, ps, filter_string, false);
+		if (err) {
+			filter_disable(call);
+			parse_error(ps, FILT_ERR_BAD_SUBSYS_FILTER, 0);
+			append_filter_err(ps, filter);
+		} else
 			call->flags |= TRACE_EVENT_FL_FILTERED;
-			replace_filter_string(filter, filter_string);
-		}
+		/*
+		 * Regardless of if this returned an error, we still
+		 * replace the filter for the call.
+		 */
+		filter = call->filter;
+		call->filter = filter_item->filter;
+		filter_item->filter = filter;
+
 		fail = false;
 	}
 
-	if (fail) {
-		parse_error(ps, FILT_ERR_BAD_SUBSYS_FILTER, 0);
-		return -EINVAL;
+	if (fail)
+		goto fail;
+
+	/*
+	 * The calls can still be using the old filters.
+	 * Do a synchronize_sched() to ensure all calls are
+	 * done with them before we free them.
+	 */
+	synchronize_sched();
+	list_for_each_entry_safe(filter_item, tmp, &filter_list, list) {
+		__free_filter(filter_item->filter);
+		list_del(&filter_item->list);
+		kfree(filter_item);
 	}
 	return 0;
+ fail:
+	/* No call succeeded */
+	list_for_each_entry_safe(filter_item, tmp, &filter_list, list) {
+		list_del(&filter_item->list);
+		kfree(filter_item);
+	}
+	parse_error(ps, FILT_ERR_BAD_SUBSYS_FILTER, 0);
+	return -EINVAL;
+ fail_mem:
+	/* If any call succeeded, we still need to sync */
+	if (!fail)
+		synchronize_sched();
+	list_for_each_entry_safe(filter_item, tmp, &filter_list, list) {
+		__free_filter(filter_item->filter);
+		list_del(&filter_item->list);
+		kfree(filter_item);
+	}
+	return -ENOMEM;
 }
 
 int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
 {
-	int err;
 	struct filter_parse_state *ps;
+	struct event_filter *filter;
+	struct event_filter *tmp;
+	int err = 0;
 
 	mutex_lock(&event_mutex);
 
-	err = init_preds(call);
-	if (err)
-		goto out_unlock;
-
 	if (!strcmp(strstrip(filter_string), "0")) {
-		filter_disable_preds(call);
-		remove_filter_string(call->filter);
+		filter_disable(call);
+		filter = call->filter;
+		if (!filter)
+			goto out_unlock;
+		call->filter = NULL;
+		/* Make sure the filter is not being used */
+		synchronize_sched();
+		__free_filter(filter);
 		goto out_unlock;
 	}
 
@@ -1306,22 +1833,41 @@ int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
 	if (!ps)
 		goto out_unlock;
 
-	filter_disable_preds(call);
-	replace_filter_string(call->filter, filter_string);
+	filter = __alloc_filter();
+	if (!filter) {
+		kfree(ps);
+		goto out_unlock;
+	}
+
+	replace_filter_string(filter, filter_string);
 
 	parse_init(ps, filter_ops, filter_string);
 	err = filter_parse(ps);
 	if (err) {
-		append_filter_err(ps, call->filter);
+		append_filter_err(ps, filter);
 		goto out;
 	}
 
-	err = replace_preds(call, call->filter, ps, filter_string, false);
-	if (err)
-		append_filter_err(ps, call->filter);
-	else
+	err = replace_preds(call, filter, ps, filter_string, false);
+	if (err) {
+		filter_disable(call);
+		append_filter_err(ps, filter);
+	} else
 		call->flags |= TRACE_EVENT_FL_FILTERED;
 out:
+	/*
+	 * Always swap the call filter with the new filter
+	 * even if there was an error. If there was an error
+	 * in the filter, we disable the filter and show the error
+	 * string
+	 */
+	tmp = call->filter;
+	call->filter = filter;
+	if (tmp) {
+		/* Make sure the call is done with the filter */
+		synchronize_sched();
+		__free_filter(tmp);
+	}
 	filter_opstack_clear(ps);
 	postfix_clear(ps);
 	kfree(ps);
@@ -1334,18 +1880,21 @@ out_unlock:
 int apply_subsystem_event_filter(struct event_subsystem *system,
 				 char *filter_string)
 {
-	int err;
 	struct filter_parse_state *ps;
+	struct event_filter *filter;
+	int err = 0;
 
 	mutex_lock(&event_mutex);
 
-	err = init_subsystem_preds(system);
-	if (err)
-		goto out_unlock;
-
 	if (!strcmp(strstrip(filter_string), "0")) {
 		filter_free_subsystem_preds(system);
 		remove_filter_string(system->filter);
+		filter = system->filter;
+		system->filter = NULL;
+		/* Ensure all filters are no longer used */
+		synchronize_sched();
+		filter_free_subsystem_filters(system);
+		__free_filter(filter);
 		goto out_unlock;
 	}
 
@@ -1354,7 +1903,17 @@ int apply_subsystem_event_filter(struct event_subsystem *system,
 	if (!ps)
 		goto out_unlock;
 
-	replace_filter_string(system->filter, filter_string);
+	filter = __alloc_filter();
+	if (!filter)
+		goto out;
+
+	replace_filter_string(filter, filter_string);
+	/*
+	 * No event actually uses the system filter
+	 * we can free it without synchronize_sched().
+	 */
+	__free_filter(system->filter);
+	system->filter = filter;
 
 	parse_init(ps, filter_ops, filter_string);
 	err = filter_parse(ps);
@@ -1384,7 +1943,7 @@ void ftrace_profile_free_filter(struct perf_event *event)
 	struct event_filter *filter = event->filter;
 
 	event->filter = NULL;
-	__free_preds(filter);
+	__free_filter(filter);
 }
 
 int ftrace_profile_set_filter(struct perf_event *event, int event_id,
@@ -1410,8 +1969,8 @@ int ftrace_profile_set_filter(struct perf_event *event, int event_id,
 	if (event->filter)
 		goto out_unlock;
 
-	filter = __alloc_preds();
-	if (IS_ERR(filter)) {
+	filter = __alloc_filter();
+	if (!filter) {
 		err = PTR_ERR(filter);
 		goto out_unlock;
 	}
@@ -1419,7 +1978,7 @@ int ftrace_profile_set_filter(struct perf_event *event, int event_id,
 	err = -ENOMEM;
 	ps = kzalloc(sizeof(*ps), GFP_KERNEL);
 	if (!ps)
-		goto free_preds;
+		goto free_filter;
 
 	parse_init(ps, filter_ops, filter_str);
 	err = filter_parse(ps);
@@ -1435,9 +1994,9 @@ free_ps:
 	postfix_clear(ps);
 	kfree(ps);
 
-free_preds:
+free_filter:
 	if (err)
-		__free_preds(filter);
+		__free_filter(filter);
 
 out_unlock:
 	mutex_unlock(&event_mutex);
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 2dec9bcde8b4..8435b43b1782 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -353,6 +353,43 @@ static __kprobes void free_deref_fetch_param(struct deref_fetch_param *data)
 	kfree(data);
 }
 
+/* Bitfield fetch function */
+struct bitfield_fetch_param {
+	struct fetch_param orig;
+	unsigned char hi_shift;
+	unsigned char low_shift;
+};
+
+#define DEFINE_FETCH_bitfield(type)					\
+static __kprobes void FETCH_FUNC_NAME(bitfield, type)(struct pt_regs *regs,\
+					    void *data, void *dest)	\
+{									\
+	struct bitfield_fetch_param *bprm = data;			\
+	type buf = 0;							\
+	call_fetch(&bprm->orig, regs, &buf);				\
+	if (buf) {							\
+		buf <<= bprm->hi_shift;					\
+		buf >>= bprm->low_shift;				\
+	}								\
+	*(type *)dest = buf;						\
+}
+DEFINE_BASIC_FETCH_FUNCS(bitfield)
+#define fetch_bitfield_string NULL
+#define fetch_bitfield_string_size NULL
+
+static __kprobes void
+free_bitfield_fetch_param(struct bitfield_fetch_param *data)
+{
+	/*
+	 * Don't check the bitfield itself, because this must be the
+	 * last fetch function.
+	 */
+	if (CHECK_FETCH_FUNCS(deref, data->orig.fn))
+		free_deref_fetch_param(data->orig.data);
+	else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn))
+		free_symbol_cache(data->orig.data);
+	kfree(data);
+}
 /* Default (unsigned long) fetch type */
 #define __DEFAULT_FETCH_TYPE(t) u##t
 #define _DEFAULT_FETCH_TYPE(t) __DEFAULT_FETCH_TYPE(t)
@@ -367,6 +404,7 @@ enum {
 	FETCH_MTD_memory,
 	FETCH_MTD_symbol,
 	FETCH_MTD_deref,
+	FETCH_MTD_bitfield,
 	FETCH_MTD_END,
 };
 
@@ -387,6 +425,7 @@ ASSIGN_FETCH_FUNC(retval, ftype),			\
 ASSIGN_FETCH_FUNC(memory, ftype),			\
 ASSIGN_FETCH_FUNC(symbol, ftype),			\
 ASSIGN_FETCH_FUNC(deref, ftype),			\
+ASSIGN_FETCH_FUNC(bitfield, ftype),			\
 	  }						\
 	}
 
@@ -430,9 +469,33 @@ static const struct fetch_type *find_fetch_type(const char *type)
 	if (!type)
 		type = DEFAULT_FETCH_TYPE_STR;
 
+	/* Special case: bitfield */
+	if (*type == 'b') {
+		unsigned long bs;
+		type = strchr(type, '/');
+		if (!type)
+			goto fail;
+		type++;
+		if (strict_strtoul(type, 0, &bs))
+			goto fail;
+		switch (bs) {
+		case 8:
+			return find_fetch_type("u8");
+		case 16:
+			return find_fetch_type("u16");
+		case 32:
+			return find_fetch_type("u32");
+		case 64:
+			return find_fetch_type("u64");
+		default:
+			goto fail;
+		}
+	}
+
 	for (i = 0; i < ARRAY_SIZE(fetch_type_table); i++)
 		if (strcmp(type, fetch_type_table[i].name) == 0)
 			return &fetch_type_table[i];
+fail:
 	return NULL;
 }
 
@@ -586,7 +649,9 @@ error:
 
 static void free_probe_arg(struct probe_arg *arg)
 {
-	if (CHECK_FETCH_FUNCS(deref, arg->fetch.fn))
+	if (CHECK_FETCH_FUNCS(bitfield, arg->fetch.fn))
+		free_bitfield_fetch_param(arg->fetch.data);
+	else if (CHECK_FETCH_FUNCS(deref, arg->fetch.fn))
 		free_deref_fetch_param(arg->fetch.data);
 	else if (CHECK_FETCH_FUNCS(symbol, arg->fetch.fn))
 		free_symbol_cache(arg->fetch.data);
@@ -767,16 +832,15 @@ static int __parse_probe_arg(char *arg, const struct fetch_type *t,
 		}
 		break;
 	case '+':	/* deref memory */
+		arg++;	/* Skip '+', because strict_strtol() rejects it. */
 	case '-':
 		tmp = strchr(arg, '(');
 		if (!tmp)
 			break;
 		*tmp = '\0';
-		ret = strict_strtol(arg + 1, 0, &offset);
+		ret = strict_strtol(arg, 0, &offset);
 		if (ret)
 			break;
-		if (arg[0] == '-')
-			offset = -offset;
 		arg = tmp + 1;
 		tmp = strrchr(arg, ')');
 		if (tmp) {
@@ -807,6 +871,41 @@ static int __parse_probe_arg(char *arg, const struct fetch_type *t,
 	return ret;
 }
 
+#define BYTES_TO_BITS(nb)	((BITS_PER_LONG * (nb)) / sizeof(long))
+
+/* Bitfield type needs to be parsed into a fetch function */
+static int __parse_bitfield_probe_arg(const char *bf,
+				      const struct fetch_type *t,
+				      struct fetch_param *f)
+{
+	struct bitfield_fetch_param *bprm;
+	unsigned long bw, bo;
+	char *tail;
+
+	if (*bf != 'b')
+		return 0;
+
+	bprm = kzalloc(sizeof(*bprm), GFP_KERNEL);
+	if (!bprm)
+		return -ENOMEM;
+	bprm->orig = *f;
+	f->fn = t->fetch[FETCH_MTD_bitfield];
+	f->data = (void *)bprm;
+
+	bw = simple_strtoul(bf + 1, &tail, 0);	/* Use simple one */
+	if (bw == 0 || *tail != '@')
+		return -EINVAL;
+
+	bf = tail + 1;
+	bo = simple_strtoul(bf, &tail, 0);
+	if (tail == bf || *tail != '/')
+		return -EINVAL;
+
+	bprm->hi_shift = BYTES_TO_BITS(t->size) - (bw + bo);
+	bprm->low_shift = bprm->hi_shift + bo;
+	return (BYTES_TO_BITS(t->size) < (bw + bo)) ? -EINVAL : 0;
+}
+
 /* String length checking wrapper */
 static int parse_probe_arg(char *arg, struct trace_probe *tp,
 			   struct probe_arg *parg, int is_return)
@@ -836,6 +935,8 @@ static int parse_probe_arg(char *arg, struct trace_probe *tp,
 	parg->offset = tp->size;
 	tp->size += parg->type->size;
 	ret = __parse_probe_arg(arg, parg->type, &parg->fetch, is_return);
+	if (ret >= 0 && t != NULL)
+		ret = __parse_bitfield_probe_arg(t, parg->type, &parg->fetch);
 	if (ret >= 0) {
 		parg->fetch_size.fn = get_fetch_size_function(parg->type,
 							      parg->fetch.fn);
@@ -1130,7 +1231,7 @@ static int command_trace_probe(const char *buf)
 	return ret;
 }
 
-#define WRITE_BUFSIZE 128
+#define WRITE_BUFSIZE 4096
 
 static ssize_t probes_write(struct file *file, const char __user *buffer,
 			    size_t count, loff_t *ppos)
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 02272baa2206..456be9063c2d 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -529,24 +529,34 @@ seq_print_ip_sym(struct trace_seq *s, unsigned long ip, unsigned long sym_flags)
  * @entry: The trace entry field from the ring buffer
  *
  * Prints the generic fields of irqs off, in hard or softirq, preempt
- * count and lock depth.
+ * count.
  */
 int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry)
 {
-	int hardirq, softirq;
+	char hardsoft_irq;
+	char need_resched;
+	char irqs_off;
+	int hardirq;
+	int softirq;
 	int ret;
 
 	hardirq = entry->flags & TRACE_FLAG_HARDIRQ;
 	softirq = entry->flags & TRACE_FLAG_SOFTIRQ;
 
+	irqs_off =
+		(entry->flags & TRACE_FLAG_IRQS_OFF) ? 'd' :
+		(entry->flags & TRACE_FLAG_IRQS_NOSUPPORT) ? 'X' :
+		'.';
+	need_resched =
+		(entry->flags & TRACE_FLAG_NEED_RESCHED) ? 'N' : '.';
+	hardsoft_irq =
+		(hardirq && softirq) ? 'H' :
+		hardirq ? 'h' :
+		softirq ? 's' :
+		'.';
+
 	if (!trace_seq_printf(s, "%c%c%c",
-			      (entry->flags & TRACE_FLAG_IRQS_OFF) ? 'd' :
-				(entry->flags & TRACE_FLAG_IRQS_NOSUPPORT) ?
-				  'X' : '.',
-			      (entry->flags & TRACE_FLAG_NEED_RESCHED) ?
-				'N' : '.',
-			      (hardirq && softirq) ? 'H' :
-				hardirq ? 'h' : softirq ? 's' : '.'))
+			      irqs_off, need_resched, hardsoft_irq))
 		return 0;
 
 	if (entry->preempt_count)
@@ -554,13 +564,7 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry)
 	else
 		ret = trace_seq_putc(s, '.');
 
-	if (!ret)
-		return 0;
-
-	if (entry->lock_depth < 0)
-		return trace_seq_putc(s, '.');
-
-	return trace_seq_printf(s, "%d", entry->lock_depth);
+	return ret;
 }
 
 static int
diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
index 8f758d070c43..7e62c0a18456 100644
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -247,51 +247,3 @@ void tracing_sched_switch_assign_trace(struct trace_array *tr)
 	ctx_trace = tr;
 }
 
-static void stop_sched_trace(struct trace_array *tr)
-{
-	tracing_stop_sched_switch_record();
-}
-
-static int sched_switch_trace_init(struct trace_array *tr)
-{
-	ctx_trace = tr;
-	tracing_reset_online_cpus(tr);
-	tracing_start_sched_switch_record();
-	return 0;
-}
-
-static void sched_switch_trace_reset(struct trace_array *tr)
-{
-	if (sched_ref)
-		stop_sched_trace(tr);
-}
-
-static void sched_switch_trace_start(struct trace_array *tr)
-{
-	sched_stopped = 0;
-}
-
-static void sched_switch_trace_stop(struct trace_array *tr)
-{
-	sched_stopped = 1;
-}
-
-static struct tracer sched_switch_trace __read_mostly =
-{
-	.name		= "sched_switch",
-	.init		= sched_switch_trace_init,
-	.reset		= sched_switch_trace_reset,
-	.start		= sched_switch_trace_start,
-	.stop		= sched_switch_trace_stop,
-	.wait_pipe	= poll_wait_pipe,
-#ifdef CONFIG_FTRACE_SELFTEST
-	.selftest    = trace_selftest_startup_sched_switch,
-#endif
-};
-
-__init static int init_sched_switch_trace(void)
-{
-	return register_tracer(&sched_switch_trace);
-}
-device_initcall(init_sched_switch_trace);
-
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 5c9fe08d2093..ee7b5a0bb9f8 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -60,6 +60,19 @@ extern struct syscall_metadata *__stop_syscalls_metadata[];
 
 static struct syscall_metadata **syscalls_metadata;
 
+#ifndef ARCH_HAS_SYSCALL_MATCH_SYM_NAME
+static inline bool arch_syscall_match_sym_name(const char *sym, const char *name)
+{
+	/*
+	 * Only compare after the "sys" prefix. Archs that use
+	 * syscall wrappers may have syscalls symbols aliases prefixed
+	 * with "SyS" instead of "sys", leading to an unwanted
+	 * mismatch.
+	 */
+	return !strcmp(sym + 3, name + 3);
+}
+#endif
+
 static __init struct syscall_metadata *
 find_syscall_meta(unsigned long syscall)
 {
@@ -72,14 +85,11 @@ find_syscall_meta(unsigned long syscall)
 	stop = __stop_syscalls_metadata;
 	kallsyms_lookup(syscall, NULL, NULL, NULL, str);
 
+	if (arch_syscall_match_sym_name(str, "sys_ni_syscall"))
+		return NULL;
+
 	for ( ; start < stop; start++) {
-		/*
-		 * Only compare after the "sys" prefix. Archs that use
-		 * syscall wrappers may have syscalls symbols aliases prefixed
-		 * with "SyS" instead of "sys", leading to an unwanted
-		 * mismatch.
-		 */
-		if ((*start)->name && !strcmp((*start)->name + 3, str + 3))
+		if ((*start)->name && arch_syscall_match_sym_name(str, (*start)->name))
 			return *start;
 	}
 	return NULL;
@@ -359,7 +369,7 @@ int reg_event_syscall_enter(struct ftrace_event_call *call)
 	int num;
 
 	num = ((struct syscall_metadata *)call->data)->syscall_nr;
-	if (num < 0 || num >= NR_syscalls)
+	if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls))
 		return -ENOSYS;
 	mutex_lock(&syscall_trace_lock);
 	if (!sys_refcount_enter)
@@ -377,7 +387,7 @@ void unreg_event_syscall_enter(struct ftrace_event_call *call)
 	int num;
 
 	num = ((struct syscall_metadata *)call->data)->syscall_nr;
-	if (num < 0 || num >= NR_syscalls)
+	if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls))
 		return;
 	mutex_lock(&syscall_trace_lock);
 	sys_refcount_enter--;
@@ -393,7 +403,7 @@ int reg_event_syscall_exit(struct ftrace_event_call *call)
 	int num;
 
 	num = ((struct syscall_metadata *)call->data)->syscall_nr;
-	if (num < 0 || num >= NR_syscalls)
+	if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls))
 		return -ENOSYS;
 	mutex_lock(&syscall_trace_lock);
 	if (!sys_refcount_exit)
@@ -411,7 +421,7 @@ void unreg_event_syscall_exit(struct ftrace_event_call *call)
 	int num;
 
 	num = ((struct syscall_metadata *)call->data)->syscall_nr;
-	if (num < 0 || num >= NR_syscalls)
+	if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls))
 		return;
 	mutex_lock(&syscall_trace_lock);
 	sys_refcount_exit--;
@@ -424,6 +434,14 @@ void unreg_event_syscall_exit(struct ftrace_event_call *call)
 int init_syscall_trace(struct ftrace_event_call *call)
 {
 	int id;
+	int num;
+
+	num = ((struct syscall_metadata *)call->data)->syscall_nr;
+	if (num < 0 || num >= NR_syscalls) {
+		pr_debug("syscall %s metadata not mapped, disabling ftrace event\n",
+				((struct syscall_metadata *)call->data)->name);
+		return -ENOSYS;
+	}
 
 	if (set_syscall_print_fmt(call) < 0)
 		return -ENOMEM;
@@ -438,7 +456,7 @@ int init_syscall_trace(struct ftrace_event_call *call)
 	return id;
 }
 
-unsigned long __init arch_syscall_addr(int nr)
+unsigned long __init __weak arch_syscall_addr(int nr)
 {
 	return (unsigned long)sys_call_table[nr];
 }
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index ee6578b578ad..b5fe4c00eb3c 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -316,6 +316,11 @@ static inline int __next_wq_cpu(int cpu, const struct cpumask *mask,
 
 static struct debug_obj_descr work_debug_descr;
 
+static void *work_debug_hint(void *addr)
+{
+	return ((struct work_struct *) addr)->func;
+}
+
 /*
  * fixup_init is called when:
  * - an active object is initialized
@@ -387,6 +392,7 @@ static int work_fixup_free(void *addr, enum debug_obj_state state)
 
 static struct debug_obj_descr work_debug_descr = {
 	.name		= "work_struct",
+	.debug_hint	= work_debug_hint,
 	.fixup_init	= work_fixup_init,
 	.fixup_activate	= work_fixup_activate,
 	.fixup_free	= work_fixup_free,
diff --git a/lib/debugobjects.c b/lib/debugobjects.c
index deebcc57d4e6..9d86e45086f5 100644
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -249,14 +249,17 @@ static struct debug_bucket *get_bucket(unsigned long addr)
 
 static void debug_print_object(struct debug_obj *obj, char *msg)
 {
+	struct debug_obj_descr *descr = obj->descr;
 	static int limit;
 
-	if (limit < 5 && obj->descr != descr_test) {
+	if (limit < 5 && descr != descr_test) {
+		void *hint = descr->debug_hint ?
+			descr->debug_hint(obj->object) : NULL;
 		limit++;
 		WARN(1, KERN_ERR "ODEBUG: %s %s (active state %u) "
-				 "object type: %s\n",
+				 "object type: %s hint: %pS\n",
 			msg, obj_states[obj->state], obj->astate,
-			obj->descr->name);
+			descr->name, hint);
 	}
 	debug_objects_warnings++;
 }
diff --git a/lib/plist.c b/lib/plist.c
index 1471988d9190..0ae7e6431726 100644
--- a/lib/plist.c
+++ b/lib/plist.c
@@ -28,6 +28,8 @@
 
 #ifdef CONFIG_DEBUG_PI_LIST
 
+static struct plist_head test_head;
+
 static void plist_check_prev_next(struct list_head *t, struct list_head *p,
 				  struct list_head *n)
 {
@@ -54,12 +56,13 @@ static void plist_check_list(struct list_head *top)
 
 static void plist_check_head(struct plist_head *head)
 {
-	WARN_ON(!head->rawlock && !head->spinlock);
+	WARN_ON(head != &test_head && !head->rawlock && !head->spinlock);
 	if (head->rawlock)
 		WARN_ON_SMP(!raw_spin_is_locked(head->rawlock));
 	if (head->spinlock)
 		WARN_ON_SMP(!spin_is_locked(head->spinlock));
-	plist_check_list(&head->prio_list);
+	if (!plist_head_empty(head))
+		plist_check_list(&plist_first(head)->prio_list);
 	plist_check_list(&head->node_list);
 }
 
@@ -75,25 +78,33 @@ static void plist_check_head(struct plist_head *head)
  */
 void plist_add(struct plist_node *node, struct plist_head *head)
 {
-	struct plist_node *iter;
+	struct plist_node *first, *iter, *prev = NULL;
+	struct list_head *node_next = &head->node_list;
 
 	plist_check_head(head);
 	WARN_ON(!plist_node_empty(node));
+	WARN_ON(!list_empty(&node->prio_list));
+
+	if (plist_head_empty(head))
+		goto ins_node;
 
-	list_for_each_entry(iter, &head->prio_list, plist.prio_list) {
-		if (node->prio < iter->prio)
-			goto lt_prio;
-		else if (node->prio == iter->prio) {
-			iter = list_entry(iter->plist.prio_list.next,
-					struct plist_node, plist.prio_list);
-			goto eq_prio;
+	first = iter = plist_first(head);
+
+	do {
+		if (node->prio < iter->prio) {
+			node_next = &iter->node_list;
+			break;
 		}
-	}
 
-lt_prio:
-	list_add_tail(&node->plist.prio_list, &iter->plist.prio_list);
-eq_prio:
-	list_add_tail(&node->plist.node_list, &iter->plist.node_list);
+		prev = iter;
+		iter = list_entry(iter->prio_list.next,
+				struct plist_node, prio_list);
+	} while (iter != first);
+
+	if (!prev || prev->prio != node->prio)
+		list_add_tail(&node->prio_list, &iter->prio_list);
+ins_node:
+	list_add_tail(&node->node_list, node_next);
 
 	plist_check_head(head);
 }
@@ -108,14 +119,98 @@ void plist_del(struct plist_node *node, struct plist_head *head)
 {
 	plist_check_head(head);
 
-	if (!list_empty(&node->plist.prio_list)) {
-		struct plist_node *next = plist_first(&node->plist);
+	if (!list_empty(&node->prio_list)) {
+		if (node->node_list.next != &head->node_list) {
+			struct plist_node *next;
+
+			next = list_entry(node->node_list.next,
+					struct plist_node, node_list);
 
-		list_move_tail(&next->plist.prio_list, &node->plist.prio_list);
-		list_del_init(&node->plist.prio_list);
+			/* add the next plist_node into prio_list */
+			if (list_empty(&next->prio_list))
+				list_add(&next->prio_list, &node->prio_list);
+		}
+		list_del_init(&node->prio_list);
 	}
 
-	list_del_init(&node->plist.node_list);
+	list_del_init(&node->node_list);
 
 	plist_check_head(head);
 }
+
+#ifdef CONFIG_DEBUG_PI_LIST
+#include <linux/sched.h>
+#include <linux/module.h>
+#include <linux/init.h>
+
+static struct plist_node __initdata test_node[241];
+
+static void __init plist_test_check(int nr_expect)
+{
+	struct plist_node *first, *prio_pos, *node_pos;
+
+	if (plist_head_empty(&test_head)) {
+		BUG_ON(nr_expect != 0);
+		return;
+	}
+
+	prio_pos = first = plist_first(&test_head);
+	plist_for_each(node_pos, &test_head) {
+		if (nr_expect-- < 0)
+			break;
+		if (node_pos == first)
+			continue;
+		if (node_pos->prio == prio_pos->prio) {
+			BUG_ON(!list_empty(&node_pos->prio_list));
+			continue;
+		}
+
+		BUG_ON(prio_pos->prio > node_pos->prio);
+		BUG_ON(prio_pos->prio_list.next != &node_pos->prio_list);
+		prio_pos = node_pos;
+	}
+
+	BUG_ON(nr_expect != 0);
+	BUG_ON(prio_pos->prio_list.next != &first->prio_list);
+}
+
+static int  __init plist_test(void)
+{
+	int nr_expect = 0, i, loop;
+	unsigned int r = local_clock();
+
+	printk(KERN_INFO "start plist test\n");
+	plist_head_init(&test_head, NULL);
+	for (i = 0; i < ARRAY_SIZE(test_node); i++)
+		plist_node_init(test_node + i, 0);
+
+	for (loop = 0; loop < 1000; loop++) {
+		r = r * 193939 % 47629;
+		i = r % ARRAY_SIZE(test_node);
+		if (plist_node_empty(test_node + i)) {
+			r = r * 193939 % 47629;
+			test_node[i].prio = r % 99;
+			plist_add(test_node + i, &test_head);
+			nr_expect++;
+		} else {
+			plist_del(test_node + i, &test_head);
+			nr_expect--;
+		}
+		plist_test_check(nr_expect);
+	}
+
+	for (i = 0; i < ARRAY_SIZE(test_node); i++) {
+		if (plist_node_empty(test_node + i))
+			continue;
+		plist_del(test_node + i, &test_head);
+		nr_expect--;
+		plist_test_check(nr_expect);
+	}
+
+	printk(KERN_INFO "end plist test\n");
+	return 0;
+}
+
+module_init(plist_test);
+
+#endif
diff --git a/lib/rwsem.c b/lib/rwsem.c
index f236d7cd5cf3..aa7c3052261f 100644
--- a/lib/rwsem.c
+++ b/lib/rwsem.c
@@ -222,8 +222,7 @@ rwsem_down_failed_common(struct rw_semaphore *sem,
 /*
  * wait for the read lock to be granted
  */
-asmregparm struct rw_semaphore __sched *
-rwsem_down_read_failed(struct rw_semaphore *sem)
+struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem)
 {
 	return rwsem_down_failed_common(sem, RWSEM_WAITING_FOR_READ,
 					-RWSEM_ACTIVE_READ_BIAS);
@@ -232,8 +231,7 @@ rwsem_down_read_failed(struct rw_semaphore *sem)
 /*
  * wait for the write lock to be granted
  */
-asmregparm struct rw_semaphore __sched *
-rwsem_down_write_failed(struct rw_semaphore *sem)
+struct rw_semaphore __sched *rwsem_down_write_failed(struct rw_semaphore *sem)
 {
 	return rwsem_down_failed_common(sem, RWSEM_WAITING_FOR_WRITE,
 					-RWSEM_ACTIVE_WRITE_BIAS);
@@ -243,7 +241,7 @@ rwsem_down_write_failed(struct rw_semaphore *sem)
  * handle waking up a waiter on the semaphore
  * - up_read/up_write has decremented the active part of count if we come here
  */
-asmregparm struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem)
+struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem)
 {
 	unsigned long flags;
 
@@ -263,7 +261,7 @@ asmregparm struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem)
  * - caller incremented waiting part of count and discovered it still negative
  * - just wake up any readers at the front of the queue
  */
-asmregparm struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem)
+struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem)
 {
 	unsigned long flags;
 
diff --git a/mm/Makefile b/mm/Makefile
index 2b1b575ae712..42a8326c3e3d 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -7,7 +7,7 @@ mmu-$(CONFIG_MMU)	:= fremap.o highmem.o madvise.o memory.o mincore.o \
 			   mlock.o mmap.o mprotect.o mremap.o msync.o rmap.o \
 			   vmalloc.o pagewalk.o pgtable-generic.o
 
-obj-y			:= bootmem.o filemap.o mempool.o oom_kill.o fadvise.o \
+obj-y			:= filemap.o mempool.o oom_kill.o fadvise.o \
 			   maccess.o page_alloc.o page-writeback.o \
 			   readahead.o swap.o truncate.o vmscan.o shmem.o \
 			   prio_tree.o util.o mmzone.o vmstat.o backing-dev.o \
@@ -15,6 +15,12 @@ obj-y			:= bootmem.o filemap.o mempool.o oom_kill.o fadvise.o \
 			   $(mmu-y)
 obj-y += init-mm.o
 
+ifdef CONFIG_NO_BOOTMEM
+	obj-y		+= nobootmem.o
+else
+	obj-y		+= bootmem.o
+endif
+
 obj-$(CONFIG_HAVE_MEMBLOCK) += memblock.o
 
 obj-$(CONFIG_BOUNCE)	+= bounce.o
diff --git a/mm/bootmem.c b/mm/bootmem.c
index 13b0caa9793c..07aeb89e396e 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -23,6 +23,13 @@
 
 #include "internal.h"
 
+#ifndef CONFIG_NEED_MULTIPLE_NODES
+struct pglist_data __refdata contig_page_data = {
+	.bdata = &bootmem_node_data[0]
+};
+EXPORT_SYMBOL(contig_page_data);
+#endif
+
 unsigned long max_low_pfn;
 unsigned long min_low_pfn;
 unsigned long max_pfn;
@@ -35,7 +42,6 @@ unsigned long max_pfn;
 unsigned long saved_max_pfn;
 #endif
 
-#ifndef CONFIG_NO_BOOTMEM
 bootmem_data_t bootmem_node_data[MAX_NUMNODES] __initdata;
 
 static struct list_head bdata_list __initdata = LIST_HEAD_INIT(bdata_list);
@@ -146,7 +152,7 @@ unsigned long __init init_bootmem(unsigned long start, unsigned long pages)
 	min_low_pfn = start;
 	return init_bootmem_core(NODE_DATA(0)->bdata, start, 0, pages);
 }
-#endif
+
 /*
  * free_bootmem_late - free bootmem pages directly to page allocator
  * @addr: starting address of the range
@@ -171,53 +177,6 @@ void __init free_bootmem_late(unsigned long addr, unsigned long size)
 	}
 }
 
-#ifdef CONFIG_NO_BOOTMEM
-static void __init __free_pages_memory(unsigned long start, unsigned long end)
-{
-	int i;
-	unsigned long start_aligned, end_aligned;
-	int order = ilog2(BITS_PER_LONG);
-
-	start_aligned = (start + (BITS_PER_LONG - 1)) & ~(BITS_PER_LONG - 1);
-	end_aligned = end & ~(BITS_PER_LONG - 1);
-
-	if (end_aligned <= start_aligned) {
-		for (i = start; i < end; i++)
-			__free_pages_bootmem(pfn_to_page(i), 0);
-
-		return;
-	}
-
-	for (i = start; i < start_aligned; i++)
-		__free_pages_bootmem(pfn_to_page(i), 0);
-
-	for (i = start_aligned; i < end_aligned; i += BITS_PER_LONG)
-		__free_pages_bootmem(pfn_to_page(i), order);
-
-	for (i = end_aligned; i < end; i++)
-		__free_pages_bootmem(pfn_to_page(i), 0);
-}
-
-unsigned long __init free_all_memory_core_early(int nodeid)
-{
-	int i;
-	u64 start, end;
-	unsigned long count = 0;
-	struct range *range = NULL;
-	int nr_range;
-
-	nr_range = get_free_all_memory_range(&range, nodeid);
-
-	for (i = 0; i < nr_range; i++) {
-		start = range[i].start;
-		end = range[i].end;
-		count += end - start;
-		__free_pages_memory(start, end);
-	}
-
-	return count;
-}
-#else
 static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
 {
 	int aligned;
@@ -278,7 +237,6 @@ static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
 
 	return count;
 }
-#endif
 
 /**
  * free_all_bootmem_node - release a node's free pages to the buddy allocator
@@ -289,12 +247,7 @@ static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
 unsigned long __init free_all_bootmem_node(pg_data_t *pgdat)
 {
 	register_page_bootmem_info_node(pgdat);
-#ifdef CONFIG_NO_BOOTMEM
-	/* free_all_memory_core_early(MAX_NUMNODES) will be called later */
-	return 0;
-#else
 	return free_all_bootmem_core(pgdat->bdata);
-#endif
 }
 
 /**
@@ -304,16 +257,6 @@ unsigned long __init free_all_bootmem_node(pg_data_t *pgdat)
  */
 unsigned long __init free_all_bootmem(void)
 {
-#ifdef CONFIG_NO_BOOTMEM
-	/*
-	 * We need to use MAX_NUMNODES instead of NODE_DATA(0)->node_id
-	 *  because in some case like Node0 doesnt have RAM installed
-	 *  low ram will be on Node1
-	 * Use MAX_NUMNODES will make sure all ranges in early_node_map[]
-	 *  will be used instead of only Node0 related
-	 */
-	return free_all_memory_core_early(MAX_NUMNODES);
-#else
 	unsigned long total_pages = 0;
 	bootmem_data_t *bdata;
 
@@ -321,10 +264,8 @@ unsigned long __init free_all_bootmem(void)
 		total_pages += free_all_bootmem_core(bdata);
 
 	return total_pages;
-#endif
 }
 
-#ifndef CONFIG_NO_BOOTMEM
 static void __init __free(bootmem_data_t *bdata,
 			unsigned long sidx, unsigned long eidx)
 {
@@ -419,7 +360,6 @@ static int __init mark_bootmem(unsigned long start, unsigned long end,
 	}
 	BUG();
 }
-#endif
 
 /**
  * free_bootmem_node - mark a page range as usable
@@ -434,10 +374,6 @@ static int __init mark_bootmem(unsigned long start, unsigned long end,
 void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
 			      unsigned long size)
 {
-#ifdef CONFIG_NO_BOOTMEM
-	kmemleak_free_part(__va(physaddr), size);
-	memblock_x86_free_range(physaddr, physaddr + size);
-#else
 	unsigned long start, end;
 
 	kmemleak_free_part(__va(physaddr), size);
@@ -446,7 +382,6 @@ void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
 	end = PFN_DOWN(physaddr + size);
 
 	mark_bootmem_node(pgdat->bdata, start, end, 0, 0);
-#endif
 }
 
 /**
@@ -460,10 +395,6 @@ void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
  */
 void __init free_bootmem(unsigned long addr, unsigned long size)
 {
-#ifdef CONFIG_NO_BOOTMEM
-	kmemleak_free_part(__va(addr), size);
-	memblock_x86_free_range(addr, addr + size);
-#else
 	unsigned long start, end;
 
 	kmemleak_free_part(__va(addr), size);
@@ -472,7 +403,6 @@ void __init free_bootmem(unsigned long addr, unsigned long size)
 	end = PFN_DOWN(addr + size);
 
 	mark_bootmem(start, end, 0, 0);
-#endif
 }
 
 /**
@@ -489,17 +419,12 @@ void __init free_bootmem(unsigned long addr, unsigned long size)
 int __init reserve_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
 				 unsigned long size, int flags)
 {
-#ifdef CONFIG_NO_BOOTMEM
-	panic("no bootmem");
-	return 0;
-#else
 	unsigned long start, end;
 
 	start = PFN_DOWN(physaddr);
 	end = PFN_UP(physaddr + size);
 
 	return mark_bootmem_node(pgdat->bdata, start, end, 1, flags);
-#endif
 }
 
 /**
@@ -515,20 +440,14 @@ int __init reserve_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
 int __init reserve_bootmem(unsigned long addr, unsigned long size,
 			    int flags)
 {
-#ifdef CONFIG_NO_BOOTMEM
-	panic("no bootmem");
-	return 0;
-#else
 	unsigned long start, end;
 
 	start = PFN_DOWN(addr);
 	end = PFN_UP(addr + size);
 
 	return mark_bootmem(start, end, 1, flags);
-#endif
 }
 
-#ifndef CONFIG_NO_BOOTMEM
 int __weak __init reserve_bootmem_generic(unsigned long phys, unsigned long len,
 				   int flags)
 {
@@ -685,33 +604,12 @@ static void * __init alloc_arch_preferred_bootmem(bootmem_data_t *bdata,
 #endif
 	return NULL;
 }
-#endif
 
 static void * __init ___alloc_bootmem_nopanic(unsigned long size,
 					unsigned long align,
 					unsigned long goal,
 					unsigned long limit)
 {
-#ifdef CONFIG_NO_BOOTMEM
-	void *ptr;
-
-	if (WARN_ON_ONCE(slab_is_available()))
-		return kzalloc(size, GFP_NOWAIT);
-
-restart:
-
-	ptr = __alloc_memory_core_early(MAX_NUMNODES, size, align, goal, limit);
-
-	if (ptr)
-		return ptr;
-
-	if (goal != 0) {
-		goal = 0;
-		goto restart;
-	}
-
-	return NULL;
-#else
 	bootmem_data_t *bdata;
 	void *region;
 
@@ -737,7 +635,6 @@ restart:
 	}
 
 	return NULL;
-#endif
 }
 
 /**
@@ -758,10 +655,6 @@ void * __init __alloc_bootmem_nopanic(unsigned long size, unsigned long align,
 {
 	unsigned long limit = 0;
 
-#ifdef CONFIG_NO_BOOTMEM
-	limit = -1UL;
-#endif
-
 	return ___alloc_bootmem_nopanic(size, align, goal, limit);
 }
 
@@ -798,14 +691,9 @@ void * __init __alloc_bootmem(unsigned long size, unsigned long align,
 {
 	unsigned long limit = 0;
 
-#ifdef CONFIG_NO_BOOTMEM
-	limit = -1UL;
-#endif
-
 	return ___alloc_bootmem(size, align, goal, limit);
 }
 
-#ifndef CONFIG_NO_BOOTMEM
 static void * __init ___alloc_bootmem_node(bootmem_data_t *bdata,
 				unsigned long size, unsigned long align,
 				unsigned long goal, unsigned long limit)
@@ -822,7 +710,6 @@ static void * __init ___alloc_bootmem_node(bootmem_data_t *bdata,
 
 	return ___alloc_bootmem(size, align, goal, limit);
 }
-#endif
 
 /**
  * __alloc_bootmem_node - allocate boot memory from a specific node
@@ -842,24 +729,10 @@ static void * __init ___alloc_bootmem_node(bootmem_data_t *bdata,
 void * __init __alloc_bootmem_node(pg_data_t *pgdat, unsigned long size,
 				   unsigned long align, unsigned long goal)
 {
-	void *ptr;
-
 	if (WARN_ON_ONCE(slab_is_available()))
 		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
 
-#ifdef CONFIG_NO_BOOTMEM
-	ptr = __alloc_memory_core_early(pgdat->node_id, size, align,
-					 goal, -1ULL);
-	if (ptr)
-		return ptr;
-
-	ptr = __alloc_memory_core_early(MAX_NUMNODES, size, align,
-					 goal, -1ULL);
-#else
-	ptr = ___alloc_bootmem_node(pgdat->bdata, size, align, goal, 0);
-#endif
-
-	return ptr;
+	return  ___alloc_bootmem_node(pgdat->bdata, size, align, goal, 0);
 }
 
 void * __init __alloc_bootmem_node_high(pg_data_t *pgdat, unsigned long size,
@@ -880,13 +753,8 @@ void * __init __alloc_bootmem_node_high(pg_data_t *pgdat, unsigned long size,
 		unsigned long new_goal;
 
 		new_goal = MAX_DMA32_PFN << PAGE_SHIFT;
-#ifdef CONFIG_NO_BOOTMEM
-		ptr =  __alloc_memory_core_early(pgdat->node_id, size, align,
-						 new_goal, -1ULL);
-#else
 		ptr = alloc_bootmem_core(pgdat->bdata, size, align,
 						 new_goal, 0);
-#endif
 		if (ptr)
 			return ptr;
 	}
@@ -907,16 +775,6 @@ void * __init __alloc_bootmem_node_high(pg_data_t *pgdat, unsigned long size,
 void * __init alloc_bootmem_section(unsigned long size,
 				    unsigned long section_nr)
 {
-#ifdef CONFIG_NO_BOOTMEM
-	unsigned long pfn, goal, limit;
-
-	pfn = section_nr_to_pfn(section_nr);
-	goal = pfn << PAGE_SHIFT;
-	limit = section_nr_to_pfn(section_nr + 1) << PAGE_SHIFT;
-
-	return __alloc_memory_core_early(early_pfn_to_nid(pfn), size,
-					 SMP_CACHE_BYTES, goal, limit);
-#else
 	bootmem_data_t *bdata;
 	unsigned long pfn, goal, limit;
 
@@ -926,7 +784,6 @@ void * __init alloc_bootmem_section(unsigned long size,
 	bdata = &bootmem_node_data[early_pfn_to_nid(pfn)];
 
 	return alloc_bootmem_core(bdata, size, SMP_CACHE_BYTES, goal, limit);
-#endif
 }
 #endif
 
@@ -938,16 +795,11 @@ void * __init __alloc_bootmem_node_nopanic(pg_data_t *pgdat, unsigned long size,
 	if (WARN_ON_ONCE(slab_is_available()))
 		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
 
-#ifdef CONFIG_NO_BOOTMEM
-	ptr =  __alloc_memory_core_early(pgdat->node_id, size, align,
-						 goal, -1ULL);
-#else
 	ptr = alloc_arch_preferred_bootmem(pgdat->bdata, size, align, goal, 0);
 	if (ptr)
 		return ptr;
 
 	ptr = alloc_bootmem_core(pgdat->bdata, size, align, goal, 0);
-#endif
 	if (ptr)
 		return ptr;
 
@@ -995,21 +847,9 @@ void * __init __alloc_bootmem_low(unsigned long size, unsigned long align,
 void * __init __alloc_bootmem_low_node(pg_data_t *pgdat, unsigned long size,
 				       unsigned long align, unsigned long goal)
 {
-	void *ptr;
-
 	if (WARN_ON_ONCE(slab_is_available()))
 		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
 
-#ifdef CONFIG_NO_BOOTMEM
-	ptr = __alloc_memory_core_early(pgdat->node_id, size, align,
+	return ___alloc_bootmem_node(pgdat->bdata, size, align,
 				goal, ARCH_LOW_ADDRESS_LIMIT);
-	if (ptr)
-		return ptr;
-	ptr = __alloc_memory_core_early(MAX_NUMNODES, size, align,
-				goal, ARCH_LOW_ADDRESS_LIMIT);
-#else
-	ptr = ___alloc_bootmem_node(pgdat->bdata, size, align,
-				goal, ARCH_LOW_ADDRESS_LIMIT);
-#endif
-	return ptr;
 }
diff --git a/mm/nobootmem.c b/mm/nobootmem.c
new file mode 100644
index 000000000000..e2bdb07079ce
--- /dev/null
+++ b/mm/nobootmem.c
@@ -0,0 +1,435 @@
+/*
+ *  bootmem - A boot-time physical memory allocator and configurator
+ *
+ *  Copyright (C) 1999 Ingo Molnar
+ *                1999 Kanoj Sarcar, SGI
+ *                2008 Johannes Weiner
+ *
+ * Access to this subsystem has to be serialized externally (which is true
+ * for the boot process anyway).
+ */
+#include <linux/init.h>
+#include <linux/pfn.h>
+#include <linux/slab.h>
+#include <linux/bootmem.h>
+#include <linux/module.h>
+#include <linux/kmemleak.h>
+#include <linux/range.h>
+#include <linux/memblock.h>
+
+#include <asm/bug.h>
+#include <asm/io.h>
+#include <asm/processor.h>
+
+#include "internal.h"
+
+#ifndef CONFIG_NEED_MULTIPLE_NODES
+struct pglist_data __refdata contig_page_data;
+EXPORT_SYMBOL(contig_page_data);
+#endif
+
+unsigned long max_low_pfn;
+unsigned long min_low_pfn;
+unsigned long max_pfn;
+
+#ifdef CONFIG_CRASH_DUMP
+/*
+ * If we have booted due to a crash, max_pfn will be a very low value. We need
+ * to know the amount of memory that the previous kernel used.
+ */
+unsigned long saved_max_pfn;
+#endif
+
+static void * __init __alloc_memory_core_early(int nid, u64 size, u64 align,
+					u64 goal, u64 limit)
+{
+	void *ptr;
+	u64 addr;
+
+	if (limit > memblock.current_limit)
+		limit = memblock.current_limit;
+
+	addr = find_memory_core_early(nid, size, align, goal, limit);
+
+	if (addr == MEMBLOCK_ERROR)
+		return NULL;
+
+	ptr = phys_to_virt(addr);
+	memset(ptr, 0, size);
+	memblock_x86_reserve_range(addr, addr + size, "BOOTMEM");
+	/*
+	 * The min_count is set to 0 so that bootmem allocated blocks
+	 * are never reported as leaks.
+	 */
+	kmemleak_alloc(ptr, size, 0, 0);
+	return ptr;
+}
+
+/*
+ * free_bootmem_late - free bootmem pages directly to page allocator
+ * @addr: starting address of the range
+ * @size: size of the range in bytes
+ *
+ * This is only useful when the bootmem allocator has already been torn
+ * down, but we are still initializing the system.  Pages are given directly
+ * to the page allocator, no bootmem metadata is updated because it is gone.
+ */
+void __init free_bootmem_late(unsigned long addr, unsigned long size)
+{
+	unsigned long cursor, end;
+
+	kmemleak_free_part(__va(addr), size);
+
+	cursor = PFN_UP(addr);
+	end = PFN_DOWN(addr + size);
+
+	for (; cursor < end; cursor++) {
+		__free_pages_bootmem(pfn_to_page(cursor), 0);
+		totalram_pages++;
+	}
+}
+
+static void __init __free_pages_memory(unsigned long start, unsigned long end)
+{
+	int i;
+	unsigned long start_aligned, end_aligned;
+	int order = ilog2(BITS_PER_LONG);
+
+	start_aligned = (start + (BITS_PER_LONG - 1)) & ~(BITS_PER_LONG - 1);
+	end_aligned = end & ~(BITS_PER_LONG - 1);
+
+	if (end_aligned <= start_aligned) {
+		for (i = start; i < end; i++)
+			__free_pages_bootmem(pfn_to_page(i), 0);
+
+		return;
+	}
+
+	for (i = start; i < start_aligned; i++)
+		__free_pages_bootmem(pfn_to_page(i), 0);
+
+	for (i = start_aligned; i < end_aligned; i += BITS_PER_LONG)
+		__free_pages_bootmem(pfn_to_page(i), order);
+
+	for (i = end_aligned; i < end; i++)
+		__free_pages_bootmem(pfn_to_page(i), 0);
+}
+
+unsigned long __init free_all_memory_core_early(int nodeid)
+{
+	int i;
+	u64 start, end;
+	unsigned long count = 0;
+	struct range *range = NULL;
+	int nr_range;
+
+	nr_range = get_free_all_memory_range(&range, nodeid);
+
+	for (i = 0; i < nr_range; i++) {
+		start = range[i].start;
+		end = range[i].end;
+		count += end - start;
+		__free_pages_memory(start, end);
+	}
+
+	return count;
+}
+
+/**
+ * free_all_bootmem_node - release a node's free pages to the buddy allocator
+ * @pgdat: node to be released
+ *
+ * Returns the number of pages actually released.
+ */
+unsigned long __init free_all_bootmem_node(pg_data_t *pgdat)
+{
+	register_page_bootmem_info_node(pgdat);
+
+	/* free_all_memory_core_early(MAX_NUMNODES) will be called later */
+	return 0;
+}
+
+/**
+ * free_all_bootmem - release free pages to the buddy allocator
+ *
+ * Returns the number of pages actually released.
+ */
+unsigned long __init free_all_bootmem(void)
+{
+	/*
+	 * We need to use MAX_NUMNODES instead of NODE_DATA(0)->node_id
+	 *  because in some case like Node0 doesnt have RAM installed
+	 *  low ram will be on Node1
+	 * Use MAX_NUMNODES will make sure all ranges in early_node_map[]
+	 *  will be used instead of only Node0 related
+	 */
+	return free_all_memory_core_early(MAX_NUMNODES);
+}
+
+/**
+ * free_bootmem_node - mark a page range as usable
+ * @pgdat: node the range resides on
+ * @physaddr: starting address of the range
+ * @size: size of the range in bytes
+ *
+ * Partial pages will be considered reserved and left as they are.
+ *
+ * The range must reside completely on the specified node.
+ */
+void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
+			      unsigned long size)
+{
+	kmemleak_free_part(__va(physaddr), size);
+	memblock_x86_free_range(physaddr, physaddr + size);
+}
+
+/**
+ * free_bootmem - mark a page range as usable
+ * @addr: starting address of the range
+ * @size: size of the range in bytes
+ *
+ * Partial pages will be considered reserved and left as they are.
+ *
+ * The range must be contiguous but may span node boundaries.
+ */
+void __init free_bootmem(unsigned long addr, unsigned long size)
+{
+	kmemleak_free_part(__va(addr), size);
+	memblock_x86_free_range(addr, addr + size);
+}
+
+static void * __init ___alloc_bootmem_nopanic(unsigned long size,
+					unsigned long align,
+					unsigned long goal,
+					unsigned long limit)
+{
+	void *ptr;
+
+	if (WARN_ON_ONCE(slab_is_available()))
+		return kzalloc(size, GFP_NOWAIT);
+
+restart:
+
+	ptr = __alloc_memory_core_early(MAX_NUMNODES, size, align, goal, limit);
+
+	if (ptr)
+		return ptr;
+
+	if (goal != 0) {
+		goal = 0;
+		goto restart;
+	}
+
+	return NULL;
+}
+
+/**
+ * __alloc_bootmem_nopanic - allocate boot memory without panicking
+ * @size: size of the request in bytes
+ * @align: alignment of the region
+ * @goal: preferred starting address of the region
+ *
+ * The goal is dropped if it can not be satisfied and the allocation will
+ * fall back to memory below @goal.
+ *
+ * Allocation may happen on any node in the system.
+ *
+ * Returns NULL on failure.
+ */
+void * __init __alloc_bootmem_nopanic(unsigned long size, unsigned long align,
+					unsigned long goal)
+{
+	unsigned long limit = -1UL;
+
+	return ___alloc_bootmem_nopanic(size, align, goal, limit);
+}
+
+static void * __init ___alloc_bootmem(unsigned long size, unsigned long align,
+					unsigned long goal, unsigned long limit)
+{
+	void *mem = ___alloc_bootmem_nopanic(size, align, goal, limit);
+
+	if (mem)
+		return mem;
+	/*
+	 * Whoops, we cannot satisfy the allocation request.
+	 */
+	printk(KERN_ALERT "bootmem alloc of %lu bytes failed!\n", size);
+	panic("Out of memory");
+	return NULL;
+}
+
+/**
+ * __alloc_bootmem - allocate boot memory
+ * @size: size of the request in bytes
+ * @align: alignment of the region
+ * @goal: preferred starting address of the region
+ *
+ * The goal is dropped if it can not be satisfied and the allocation will
+ * fall back to memory below @goal.
+ *
+ * Allocation may happen on any node in the system.
+ *
+ * The function panics if the request can not be satisfied.
+ */
+void * __init __alloc_bootmem(unsigned long size, unsigned long align,
+			      unsigned long goal)
+{
+	unsigned long limit = -1UL;
+
+	return ___alloc_bootmem(size, align, goal, limit);
+}
+
+/**
+ * __alloc_bootmem_node - allocate boot memory from a specific node
+ * @pgdat: node to allocate from
+ * @size: size of the request in bytes
+ * @align: alignment of the region
+ * @goal: preferred starting address of the region
+ *
+ * The goal is dropped if it can not be satisfied and the allocation will
+ * fall back to memory below @goal.
+ *
+ * Allocation may fall back to any node in the system if the specified node
+ * can not hold the requested memory.
+ *
+ * The function panics if the request can not be satisfied.
+ */
+void * __init __alloc_bootmem_node(pg_data_t *pgdat, unsigned long size,
+				   unsigned long align, unsigned long goal)
+{
+	void *ptr;
+
+	if (WARN_ON_ONCE(slab_is_available()))
+		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
+
+	ptr = __alloc_memory_core_early(pgdat->node_id, size, align,
+					 goal, -1ULL);
+	if (ptr)
+		return ptr;
+
+	return __alloc_memory_core_early(MAX_NUMNODES, size, align,
+					 goal, -1ULL);
+}
+
+void * __init __alloc_bootmem_node_high(pg_data_t *pgdat, unsigned long size,
+				   unsigned long align, unsigned long goal)
+{
+#ifdef MAX_DMA32_PFN
+	unsigned long end_pfn;
+
+	if (WARN_ON_ONCE(slab_is_available()))
+		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
+
+	/* update goal according ...MAX_DMA32_PFN */
+	end_pfn = pgdat->node_start_pfn + pgdat->node_spanned_pages;
+
+	if (end_pfn > MAX_DMA32_PFN + (128 >> (20 - PAGE_SHIFT)) &&
+	    (goal >> PAGE_SHIFT) < MAX_DMA32_PFN) {
+		void *ptr;
+		unsigned long new_goal;
+
+		new_goal = MAX_DMA32_PFN << PAGE_SHIFT;
+		ptr =  __alloc_memory_core_early(pgdat->node_id, size, align,
+						 new_goal, -1ULL);
+		if (ptr)
+			return ptr;
+	}
+#endif
+
+	return __alloc_bootmem_node(pgdat, size, align, goal);
+
+}
+
+#ifdef CONFIG_SPARSEMEM
+/**
+ * alloc_bootmem_section - allocate boot memory from a specific section
+ * @size: size of the request in bytes
+ * @section_nr: sparse map section to allocate from
+ *
+ * Return NULL on failure.
+ */
+void * __init alloc_bootmem_section(unsigned long size,
+				    unsigned long section_nr)
+{
+	unsigned long pfn, goal, limit;
+
+	pfn = section_nr_to_pfn(section_nr);
+	goal = pfn << PAGE_SHIFT;
+	limit = section_nr_to_pfn(section_nr + 1) << PAGE_SHIFT;
+
+	return __alloc_memory_core_early(early_pfn_to_nid(pfn), size,
+					 SMP_CACHE_BYTES, goal, limit);
+}
+#endif
+
+void * __init __alloc_bootmem_node_nopanic(pg_data_t *pgdat, unsigned long size,
+				   unsigned long align, unsigned long goal)
+{
+	void *ptr;
+
+	if (WARN_ON_ONCE(slab_is_available()))
+		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
+
+	ptr =  __alloc_memory_core_early(pgdat->node_id, size, align,
+						 goal, -1ULL);
+	if (ptr)
+		return ptr;
+
+	return __alloc_bootmem_nopanic(size, align, goal);
+}
+
+#ifndef ARCH_LOW_ADDRESS_LIMIT
+#define ARCH_LOW_ADDRESS_LIMIT	0xffffffffUL
+#endif
+
+/**
+ * __alloc_bootmem_low - allocate low boot memory
+ * @size: size of the request in bytes
+ * @align: alignment of the region
+ * @goal: preferred starting address of the region
+ *
+ * The goal is dropped if it can not be satisfied and the allocation will
+ * fall back to memory below @goal.
+ *
+ * Allocation may happen on any node in the system.
+ *
+ * The function panics if the request can not be satisfied.
+ */
+void * __init __alloc_bootmem_low(unsigned long size, unsigned long align,
+				  unsigned long goal)
+{
+	return ___alloc_bootmem(size, align, goal, ARCH_LOW_ADDRESS_LIMIT);
+}
+
+/**
+ * __alloc_bootmem_low_node - allocate low boot memory from a specific node
+ * @pgdat: node to allocate from
+ * @size: size of the request in bytes
+ * @align: alignment of the region
+ * @goal: preferred starting address of the region
+ *
+ * The goal is dropped if it can not be satisfied and the allocation will
+ * fall back to memory below @goal.
+ *
+ * Allocation may fall back to any node in the system if the specified node
+ * can not hold the requested memory.
+ *
+ * The function panics if the request can not be satisfied.
+ */
+void * __init __alloc_bootmem_low_node(pg_data_t *pgdat, unsigned long size,
+				       unsigned long align, unsigned long goal)
+{
+	void *ptr;
+
+	if (WARN_ON_ONCE(slab_is_available()))
+		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
+
+	ptr = __alloc_memory_core_early(pgdat->node_id, size, align,
+				goal, ARCH_LOW_ADDRESS_LIMIT);
+	if (ptr)
+		return ptr;
+
+	return  __alloc_memory_core_early(MAX_NUMNODES, size, align,
+				goal, ARCH_LOW_ADDRESS_LIMIT);
+}
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index cdef1d4b4e47..bd7625676a64 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3699,13 +3699,45 @@ void __init free_bootmem_with_active_regions(int nid,
 }
 
 #ifdef CONFIG_HAVE_MEMBLOCK
+/*
+ * Basic iterator support. Return the last range of PFNs for a node
+ * Note: nid == MAX_NUMNODES returns last region regardless of node
+ */
+static int __meminit last_active_region_index_in_nid(int nid)
+{
+	int i;
+
+	for (i = nr_nodemap_entries - 1; i >= 0; i--)
+		if (nid == MAX_NUMNODES || early_node_map[i].nid == nid)
+			return i;
+
+	return -1;
+}
+
+/*
+ * Basic iterator support. Return the previous active range of PFNs for a node
+ * Note: nid == MAX_NUMNODES returns next region regardless of node
+ */
+static int __meminit previous_active_region_index_in_nid(int index, int nid)
+{
+	for (index = index - 1; index >= 0; index--)
+		if (nid == MAX_NUMNODES || early_node_map[index].nid == nid)
+			return index;
+
+	return -1;
+}
+
+#define for_each_active_range_index_in_nid_reverse(i, nid) \
+	for (i = last_active_region_index_in_nid(nid); i != -1; \
+				i = previous_active_region_index_in_nid(i, nid))
+
 u64 __init find_memory_core_early(int nid, u64 size, u64 align,
 					u64 goal, u64 limit)
 {
 	int i;
 
 	/* Need to go over early_node_map to find out good range for node */
-	for_each_active_range_index_in_nid(i, nid) {
+	for_each_active_range_index_in_nid_reverse(i, nid) {
 		u64 addr;
 		u64 ei_start, ei_last;
 		u64 final_start, final_end;
@@ -3748,34 +3780,6 @@ int __init add_from_early_node_map(struct range *range, int az,
 	return nr_range;
 }
 
-#ifdef CONFIG_NO_BOOTMEM
-void * __init __alloc_memory_core_early(int nid, u64 size, u64 align,
-					u64 goal, u64 limit)
-{
-	void *ptr;
-	u64 addr;
-
-	if (limit > memblock.current_limit)
-		limit = memblock.current_limit;
-
-	addr = find_memory_core_early(nid, size, align, goal, limit);
-
-	if (addr == MEMBLOCK_ERROR)
-		return NULL;
-
-	ptr = phys_to_virt(addr);
-	memset(ptr, 0, size);
-	memblock_x86_reserve_range(addr, addr + size, "BOOTMEM");
-	/*
-	 * The min_count is set to 0 so that bootmem allocated blocks
-	 * are never reported as leaks.
-	 */
-	kmemleak_alloc(ptr, size, 0, 0);
-	return ptr;
-}
-#endif
-
-
 void __init work_with_active_regions(int nid, work_fn_t work_fn, void *data)
 {
 	int i;
@@ -4809,15 +4813,6 @@ void __init set_dma_reserve(unsigned long new_dma_reserve)
 	dma_reserve = new_dma_reserve;
 }
 
-#ifndef CONFIG_NEED_MULTIPLE_NODES
-struct pglist_data __refdata contig_page_data = {
-#ifndef CONFIG_NO_BOOTMEM
- .bdata = &bootmem_node_data[0]
-#endif
- };
-EXPORT_SYMBOL(contig_page_data);
-#endif
-
 void __init free_area_init(unsigned long *zones_size)
 {
 	free_area_init_node(0, zones_size,
diff --git a/mm/shmem.c b/mm/shmem.c
index 5ee67c990602..3437b65d6d6e 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2144,8 +2144,10 @@ static int shmem_encode_fh(struct dentry *dentry, __u32 *fh, int *len,
 {
 	struct inode *inode = dentry->d_inode;
 
-	if (*len < 3)
+	if (*len < 3) {
+		*len = 3;
 		return 255;
+	}
 
 	if (inode_unhashed(inode)) {
 		/* Unfortunately insert_inode_hash is not idempotent,
diff --git a/net/core/scm.c b/net/core/scm.c
index bbe454450801..4c1ef026d695 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -95,7 +95,7 @@ static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp)
 		int fd = fdp[i];
 		struct file *file;
 
-		if (fd < 0 || !(file = fget(fd)))
+		if (fd < 0 || !(file = fget_raw(fd)))
 			return -EBADF;
 		*fpp++ = file;
 		fpl->count++;
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 437a99e560e1..ba5b8c208498 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -850,7 +850,7 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 		 * Get the parent directory, calculate the hash for last
 		 * component.
 		 */
-		err = path_lookup(sunaddr->sun_path, LOOKUP_PARENT, &nd);
+		err = kern_path_parent(sunaddr->sun_path, &nd);
 		if (err)
 			goto out_mknod_parent;
 
diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index f89f83bf828e..b6f4b994eb35 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -104,7 +104,7 @@ struct sock *unix_get_socket(struct file *filp)
 	/*
 	 *	Socket ?
 	 */
-	if (S_ISSOCK(inode->i_mode)) {
+	if (S_ISSOCK(inode->i_mode) && !(filp->f_mode & FMODE_PATH)) {
 		struct socket *sock = SOCKET_I(inode);
 		struct sock *s = sock->sk;
 
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 4c0383da1c9a..58848e3e392c 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -2654,11 +2654,6 @@ sub process {
 			WARN("Use of volatile is usually wrong: see Documentation/volatile-considered-harmful.txt\n" . $herecurr);
 		}
 
-# SPIN_LOCK_UNLOCKED & RW_LOCK_UNLOCKED are deprecated
-		if ($line =~ /\b(SPIN_LOCK_UNLOCKED|RW_LOCK_UNLOCKED)/) {
-			ERROR("Use of $1 is deprecated: see Documentation/spinlocks.txt\n" . $herecurr);
-		}
-
 # warn about #if 0
 		if ($line =~ /^.\s*\#\s*if\s+0\b/) {
 			CHK("if this code is redundant consider removing it\n" .
diff --git a/scripts/kconfig/streamline_config.pl b/scripts/kconfig/streamline_config.pl
index fd81fc33d633..a4fe923c0131 100644
--- a/scripts/kconfig/streamline_config.pl
+++ b/scripts/kconfig/streamline_config.pl
@@ -1,6 +1,6 @@
 #!/usr/bin/perl -w
 #
-# Copywrite 2005-2009 - Steven Rostedt
+# Copyright 2005-2009 - Steven Rostedt
 # Licensed under the terms of the GNU GPL License version 2
 #
 #  It's simple enough to figure out how this works.
diff --git a/scripts/recordmcount.c b/scripts/recordmcount.c
index 038b3d1e2981..f9f6f52db772 100644
--- a/scripts/recordmcount.c
+++ b/scripts/recordmcount.c
@@ -206,7 +206,8 @@ static uint32_t (*w2)(uint16_t);
 static int
 is_mcounted_section_name(char const *const txtname)
 {
-	return 0 == strcmp(".text",          txtname) ||
+	return 0 == strcmp(".text",           txtname) ||
+		0 == strcmp(".ref.text",      txtname) ||
 		0 == strcmp(".sched.text",    txtname) ||
 		0 == strcmp(".spinlock.text", txtname) ||
 		0 == strcmp(".irqentry.text", txtname) ||
diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl
index 1d7963f4ee79..4be0deea71ca 100755
--- a/scripts/recordmcount.pl
+++ b/scripts/recordmcount.pl
@@ -130,6 +130,7 @@ if ($inputfile =~ m,kernel/trace/ftrace\.o$,) {
 # Acceptable sections to record.
 my %text_sections = (
      ".text" => 1,
+     ".ref.text" => 1,
      ".sched.text" => 1,
      ".spinlock.text" => 1,
      ".irqentry.text" => 1,
diff --git a/scripts/rt-tester/rt-tester.py b/scripts/rt-tester/rt-tester.py
index 44423b4dcb82..8c81d76959ee 100644
--- a/scripts/rt-tester/rt-tester.py
+++ b/scripts/rt-tester/rt-tester.py
@@ -33,8 +33,6 @@ cmd_opcodes = {
     "lockintnowait" : "6",
     "lockcont"      : "7",
     "unlock"        : "8",
-    "lockbkl"       : "9",
-    "unlockbkl"     : "10",
     "signal"        : "11",
     "resetevent"    : "98",
     "reset"         : "99",
diff --git a/scripts/rt-tester/t2-l1-2rt-sameprio.tst b/scripts/rt-tester/t2-l1-2rt-sameprio.tst
index 8821f27cc8be..3710c8b2090d 100644
--- a/scripts/rt-tester/t2-l1-2rt-sameprio.tst
+++ b/scripts/rt-tester/t2-l1-2rt-sameprio.tst
@@ -19,8 +19,6 @@
 # lockintnowait	lock nr (0-7)
 # lockcont	lock nr (0-7)
 # unlock	lock nr (0-7)
-# lockbkl	lock nr (0-7)
-# unlockbkl	lock nr (0-7)
 # signal	0
 # reset		0
 # resetevent	0
@@ -39,9 +37,6 @@
 # blocked	lock nr (0-7)
 # blockedwake	lock nr (0-7)
 # unlocked	lock nr (0-7)
-# lockedbkl	dont care
-# blockedbkl	dont care
-# unlockedbkl	dont care
 # opcodeeq	command opcode or number
 # opcodelt	number
 # opcodegt	number
diff --git a/scripts/rt-tester/t2-l1-pi.tst b/scripts/rt-tester/t2-l1-pi.tst
index cde1f189a02b..b4cc95975adb 100644
--- a/scripts/rt-tester/t2-l1-pi.tst
+++ b/scripts/rt-tester/t2-l1-pi.tst
@@ -19,8 +19,6 @@
 # lockintnowait	lock nr (0-7)
 # lockcont	lock nr (0-7)
 # unlock	lock nr (0-7)
-# lockbkl	lock nr (0-7)
-# unlockbkl	lock nr (0-7)
 # signal	0
 # reset		0
 # resetevent	0
@@ -39,9 +37,6 @@
 # blocked	lock nr (0-7)
 # blockedwake	lock nr (0-7)
 # unlocked	lock nr (0-7)
-# lockedbkl	dont care
-# blockedbkl	dont care
-# unlockedbkl	dont care
 # opcodeeq	command opcode or number
 # opcodelt	number
 # opcodegt	number
diff --git a/scripts/rt-tester/t2-l1-signal.tst b/scripts/rt-tester/t2-l1-signal.tst
index 3ab0bfc49950..1b57376cc1f7 100644
--- a/scripts/rt-tester/t2-l1-signal.tst
+++ b/scripts/rt-tester/t2-l1-signal.tst
@@ -19,8 +19,6 @@
 # lockintnowait	lock nr (0-7)
 # lockcont	lock nr (0-7)
 # unlock	lock nr (0-7)
-# lockbkl	lock nr (0-7)
-# unlockbkl	lock nr (0-7)
 # signal	0
 # reset		0
 # resetevent	0
@@ -39,9 +37,6 @@
 # blocked	lock nr (0-7)
 # blockedwake	lock nr (0-7)
 # unlocked	lock nr (0-7)
-# lockedbkl	dont care
-# blockedbkl	dont care
-# unlockedbkl	dont care
 # opcodeeq	command opcode or number
 # opcodelt	number
 # opcodegt	number
diff --git a/scripts/rt-tester/t2-l2-2rt-deadlock.tst b/scripts/rt-tester/t2-l2-2rt-deadlock.tst
index f4b5d5d6215f..68b10629b6f4 100644
--- a/scripts/rt-tester/t2-l2-2rt-deadlock.tst
+++ b/scripts/rt-tester/t2-l2-2rt-deadlock.tst
@@ -19,8 +19,6 @@
 # lockintnowait	lock nr (0-7)
 # lockcont	lock nr (0-7)
 # unlock	lock nr (0-7)
-# lockbkl	lock nr (0-7)
-# unlockbkl	lock nr (0-7)
 # signal	0
 # reset		0
 # resetevent	0
@@ -39,9 +37,6 @@
 # blocked	lock nr (0-7)
 # blockedwake	lock nr (0-7)
 # unlocked	lock nr (0-7)
-# lockedbkl	dont care
-# blockedbkl	dont care
-# unlockedbkl	dont care
 # opcodeeq	command opcode or number
 # opcodelt	number
 # opcodegt	number
diff --git a/scripts/rt-tester/t3-l1-pi-1rt.tst b/scripts/rt-tester/t3-l1-pi-1rt.tst
index 63440ca2cce9..8e6c8b11ae56 100644
--- a/scripts/rt-tester/t3-l1-pi-1rt.tst
+++ b/scripts/rt-tester/t3-l1-pi-1rt.tst
@@ -19,8 +19,6 @@
 # lockintnowait	lock nr (0-7)
 # lockcont	lock nr (0-7)
 # unlock	lock nr (0-7)
-# lockbkl	lock nr (0-7)
-# unlockbkl	lock nr (0-7)
 # signal	thread to signal (0-7)
 # reset		0
 # resetevent	0
@@ -39,9 +37,6 @@
 # blocked	lock nr (0-7)
 # blockedwake	lock nr (0-7)
 # unlocked	lock nr (0-7)
-# lockedbkl	dont care
-# blockedbkl	dont care
-# unlockedbkl	dont care
 # opcodeeq	command opcode or number
 # opcodelt	number
 # opcodegt	number
diff --git a/scripts/rt-tester/t3-l1-pi-2rt.tst b/scripts/rt-tester/t3-l1-pi-2rt.tst
index e5816fe67df3..69c2212fc520 100644
--- a/scripts/rt-tester/t3-l1-pi-2rt.tst
+++ b/scripts/rt-tester/t3-l1-pi-2rt.tst
@@ -19,8 +19,6 @@
 # lockintnowait	lock nr (0-7)
 # lockcont	lock nr (0-7)
 # unlock	lock nr (0-7)
-# lockbkl	lock nr (0-7)
-# unlockbkl	lock nr (0-7)
 # signal	thread to signal (0-7)
 # reset		0
 # resetevent	0
@@ -39,9 +37,6 @@
 # blocked	lock nr (0-7)
 # blockedwake	lock nr (0-7)
 # unlocked	lock nr (0-7)
-# lockedbkl	dont care
-# blockedbkl	dont care
-# unlockedbkl	dont care
 # opcodeeq	command opcode or number
 # opcodelt	number
 # opcodegt	number
diff --git a/scripts/rt-tester/t3-l1-pi-3rt.tst b/scripts/rt-tester/t3-l1-pi-3rt.tst
index 718b82b5d3bb..9b0f1eb26a88 100644
--- a/scripts/rt-tester/t3-l1-pi-3rt.tst
+++ b/scripts/rt-tester/t3-l1-pi-3rt.tst
@@ -19,8 +19,6 @@
 # lockintnowait	lock nr (0-7)
 # lockcont	lock nr (0-7)
 # unlock	lock nr (0-7)
-# lockbkl	lock nr (0-7)
-# unlockbkl	lock nr (0-7)
 # signal	thread to signal (0-7)
 # reset		0
 # resetevent	0
@@ -39,9 +37,6 @@
 # blocked	lock nr (0-7)
 # blockedwake	lock nr (0-7)
 # unlocked	lock nr (0-7)
-# lockedbkl	dont care
-# blockedbkl	dont care
-# unlockedbkl	dont care
 # opcodeeq	command opcode or number
 # opcodelt	number
 # opcodegt	number
diff --git a/scripts/rt-tester/t3-l1-pi-signal.tst b/scripts/rt-tester/t3-l1-pi-signal.tst
index c6e213563498..39ec74ab06ee 100644
--- a/scripts/rt-tester/t3-l1-pi-signal.tst
+++ b/scripts/rt-tester/t3-l1-pi-signal.tst
@@ -19,8 +19,6 @@
 # lockintnowait	lock nr (0-7)
 # lockcont	lock nr (0-7)
 # unlock	lock nr (0-7)
-# lockbkl	lock nr (0-7)
-# unlockbkl	lock nr (0-7)
 # signal	thread to signal (0-7)
 # reset		0
 # resetevent	0
@@ -39,9 +37,6 @@
 # blocked	lock nr (0-7)
 # blockedwake	lock nr (0-7)
 # unlocked	lock nr (0-7)
-# lockedbkl	dont care
-# blockedbkl	dont care
-# unlockedbkl	dont care
 # opcodeeq	command opcode or number
 # opcodelt	number
 # opcodegt	number
diff --git a/scripts/rt-tester/t3-l1-pi-steal.tst b/scripts/rt-tester/t3-l1-pi-steal.tst
index f53749d59d79..e03db7e010fa 100644
--- a/scripts/rt-tester/t3-l1-pi-steal.tst
+++ b/scripts/rt-tester/t3-l1-pi-steal.tst
@@ -19,8 +19,6 @@
 # lockintnowait	lock nr (0-7)
 # lockcont	lock nr (0-7)
 # unlock	lock nr (0-7)
-# lockbkl	lock nr (0-7)
-# unlockbkl	lock nr (0-7)
 # signal	thread to signal (0-7)
 # reset		0
 # resetevent	0
@@ -39,9 +37,6 @@
 # blocked	lock nr (0-7)
 # blockedwake	lock nr (0-7)
 # unlocked	lock nr (0-7)
-# lockedbkl	dont care
-# blockedbkl	dont care
-# unlockedbkl	dont care
 # opcodeeq	command opcode or number
 # opcodelt	number
 # opcodegt	number
diff --git a/scripts/rt-tester/t3-l2-pi.tst b/scripts/rt-tester/t3-l2-pi.tst
index cdc3e4fd7bac..7b59100d3e48 100644
--- a/scripts/rt-tester/t3-l2-pi.tst
+++ b/scripts/rt-tester/t3-l2-pi.tst
@@ -19,8 +19,6 @@
 # lockintnowait	lock nr (0-7)
 # lockcont	lock nr (0-7)
 # unlock	lock nr (0-7)
-# lockbkl	lock nr (0-7)
-# unlockbkl	lock nr (0-7)
 # signal	thread to signal (0-7)
 # reset		0
 # resetevent	0
@@ -39,9 +37,6 @@
 # blocked	lock nr (0-7)
 # blockedwake	lock nr (0-7)
 # unlocked	lock nr (0-7)
-# lockedbkl	dont care
-# blockedbkl	dont care
-# unlockedbkl	dont care
 # opcodeeq	command opcode or number
 # opcodelt	number
 # opcodegt	number
diff --git a/scripts/rt-tester/t4-l2-pi-deboost.tst b/scripts/rt-tester/t4-l2-pi-deboost.tst
index baa14137f473..2f0e049d6443 100644
--- a/scripts/rt-tester/t4-l2-pi-deboost.tst
+++ b/scripts/rt-tester/t4-l2-pi-deboost.tst
@@ -19,8 +19,6 @@
 # lockintnowait	lock nr (0-7)
 # lockcont	lock nr (0-7)
 # unlock	lock nr (0-7)
-# lockbkl	lock nr (0-7)
-# unlockbkl	lock nr (0-7)
 # signal	thread to signal (0-7)
 # reset		0
 # resetevent	0
@@ -39,9 +37,6 @@
 # blocked	lock nr (0-7)
 # blockedwake	lock nr (0-7)
 # unlocked	lock nr (0-7)
-# lockedbkl	dont care
-# blockedbkl	dont care
-# unlockedbkl	dont care
 # opcodeeq	command opcode or number
 # opcodelt	number
 # opcodegt	number
diff --git a/scripts/rt-tester/t5-l4-pi-boost-deboost-setsched.tst b/scripts/rt-tester/t5-l4-pi-boost-deboost-setsched.tst
index e6ec0c81b54d..04f4034ff895 100644
--- a/scripts/rt-tester/t5-l4-pi-boost-deboost-setsched.tst
+++ b/scripts/rt-tester/t5-l4-pi-boost-deboost-setsched.tst
@@ -19,8 +19,6 @@
 # lockintnowait	lock nr (0-7)
 # lockcont	lock nr (0-7)
 # unlock	lock nr (0-7)
-# lockbkl	lock nr (0-7)
-# unlockbkl	lock nr (0-7)
 # signal	thread to signal (0-7)
 # reset		0
 # resetevent	0
@@ -39,9 +37,6 @@
 # blocked	lock nr (0-7)
 # blockedwake	lock nr (0-7)
 # unlocked	lock nr (0-7)
-# lockedbkl	dont care
-# blockedbkl	dont care
-# unlockedbkl	dont care
 # opcodeeq	command opcode or number
 # opcodelt	number
 # opcodegt	number
diff --git a/scripts/rt-tester/t5-l4-pi-boost-deboost.tst b/scripts/rt-tester/t5-l4-pi-boost-deboost.tst
index ca64f8bbf4bc..a48a6ee29ddc 100644
--- a/scripts/rt-tester/t5-l4-pi-boost-deboost.tst
+++ b/scripts/rt-tester/t5-l4-pi-boost-deboost.tst
@@ -19,8 +19,6 @@
 # lockintnowait	lock nr (0-7)
 # lockcont	lock nr (0-7)
 # unlock	lock nr (0-7)
-# lockbkl	lock nr (0-7)
-# unlockbkl	lock nr (0-7)
 # signal	thread to signal (0-7)
 # reset		0
 # resetevent	0
@@ -39,9 +37,6 @@
 # blocked	lock nr (0-7)
 # blockedwake	lock nr (0-7)
 # unlocked	lock nr (0-7)
-# lockedbkl	dont care
-# blockedbkl	dont care
-# unlockedbkl	dont care
 # opcodeeq	command opcode or number
 # opcodelt	number
 # opcodegt	number
diff --git a/security/commoncap.c b/security/commoncap.c
index 64c2ed9c9015..dbfdaed4cc66 100644
--- a/security/commoncap.c
+++ b/security/commoncap.c
@@ -93,7 +93,7 @@ int cap_capable(struct task_struct *tsk, const struct cred *cred, int cap,
  * Determine whether the current process may set the system clock and timezone
  * information, returning 0 if permission granted, -ve if denied.
  */
-int cap_settime(struct timespec *ts, struct timezone *tz)
+int cap_settime(const struct timespec *ts, const struct timezone *tz)
 {
 	if (!capable(CAP_SYS_TIME))
 		return -EPERM;
diff --git a/security/security.c b/security/security.c
index 7b7308ace8c5..bb33ecadcf95 100644
--- a/security/security.c
+++ b/security/security.c
@@ -201,7 +201,7 @@ int security_syslog(int type)
 	return security_ops->syslog(type);
 }
 
-int security_settime(struct timespec *ts, struct timezone *tz)
+int security_settime(const struct timespec *ts, const struct timezone *tz)
 {
 	return security_ops->settime(ts, tz);
 }
diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore
index cb43289e447f..416684be0ad3 100644
--- a/tools/perf/.gitignore
+++ b/tools/perf/.gitignore
@@ -1,4 +1,3 @@
-PERF-BUILD-OPTIONS
 PERF-CFLAGS
 PERF-GUI-VARS
 PERF-VERSION-FILE
diff --git a/tools/perf/Documentation/Makefile b/tools/perf/Documentation/Makefile
index bd498d496952..4626a398836a 100644
--- a/tools/perf/Documentation/Makefile
+++ b/tools/perf/Documentation/Makefile
@@ -178,8 +178,8 @@ install-pdf: pdf
 	$(INSTALL) -d -m 755 $(DESTDIR)$(pdfdir)
 	$(INSTALL) -m 644 user-manual.pdf $(DESTDIR)$(pdfdir)
 
-install-html: html
-	'$(SHELL_PATH_SQ)' ./install-webdoc.sh $(DESTDIR)$(htmldir)
+#install-html: html
+#	'$(SHELL_PATH_SQ)' ./install-webdoc.sh $(DESTDIR)$(htmldir)
 
 ../PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE
 	$(QUIET_SUBDIR0)../ $(QUIET_SUBDIR1) PERF-VERSION-FILE
@@ -288,15 +288,16 @@ $(patsubst %.txt,%.html,$(wildcard howto/*.txt)): %.html : %.txt
 	sed -e '1,/^$$/d' $< | $(ASCIIDOC) -b xhtml11 - >$@+ && \
 	mv $@+ $@
 
-install-webdoc : html
-	'$(SHELL_PATH_SQ)' ./install-webdoc.sh $(WEBDOC_DEST)
+# UNIMPLEMENTED
+#install-webdoc : html
+#	'$(SHELL_PATH_SQ)' ./install-webdoc.sh $(WEBDOC_DEST)
 
-quick-install: quick-install-man
+# quick-install: quick-install-man
 
-quick-install-man:
-	'$(SHELL_PATH_SQ)' ./install-doc-quick.sh $(DOC_REF) $(DESTDIR)$(mandir)
+# quick-install-man:
+#	'$(SHELL_PATH_SQ)' ./install-doc-quick.sh $(DOC_REF) $(DESTDIR)$(mandir)
 
-quick-install-html:
-	'$(SHELL_PATH_SQ)' ./install-doc-quick.sh $(HTML_REF) $(DESTDIR)$(htmldir)
+#quick-install-html:
+#	'$(SHELL_PATH_SQ)' ./install-doc-quick.sh $(HTML_REF) $(DESTDIR)$(htmldir)
 
 .PHONY: .FORCE-PERF-VERSION-FILE
diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index 399751befeed..7a527f7e9da9 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -8,7 +8,7 @@ perf-list - List all symbolic event types
 SYNOPSIS
 --------
 [verse]
-'perf list'
+'perf list' [hw|sw|cache|tracepoint|event_glob]
 
 DESCRIPTION
 -----------
@@ -63,7 +63,26 @@ details. Some of them are referenced in the SEE ALSO section below.
 
 OPTIONS
 -------
-None
+
+Without options all known events will be listed.
+
+To limit the list use:
+
+. 'hw' or 'hardware' to list hardware events such as cache-misses, etc.
+
+. 'sw' or 'software' to list software events such as context switches, etc.
+
+. 'cache' or 'hwcache' to list hardware cache events such as L1-dcache-loads, etc.
+
+. 'tracepoint' to list all tracepoint events, alternatively use
+  'subsys_glob:event_glob' to filter by tracepoint subsystems such as sched,
+  block, etc.
+
+. If none of the above is matched, it will apply the supplied glob to all
+  events, printing the ones that match.
+
+One or more types can be used at the same time, listing the events for the
+types specified.
 
 SEE ALSO
 --------
diff --git a/tools/perf/Documentation/perf-lock.txt b/tools/perf/Documentation/perf-lock.txt
index 921de259ea10..4a26a2f3a6a3 100644
--- a/tools/perf/Documentation/perf-lock.txt
+++ b/tools/perf/Documentation/perf-lock.txt
@@ -24,8 +24,8 @@ and statistics with this 'perf lock' command.
 
   'perf lock report' reports statistical data.
 
-OPTIONS
--------
+COMMON OPTIONS
+--------------
 
 -i::
 --input=<file>::
@@ -39,6 +39,14 @@ OPTIONS
 --dump-raw-trace::
         Dump raw trace in ASCII.
 
+REPORT OPTIONS
+--------------
+
+-k::
+--key=<value>::
+        Sorting key. Possible values: acquired (default), contended,
+        wait_total, wait_max, wait_min.
+
 SEE ALSO
 --------
 linkperf:perf[1]
diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt
index 86b797a35aa6..02bafce4b341 100644
--- a/tools/perf/Documentation/perf-probe.txt
+++ b/tools/perf/Documentation/perf-probe.txt
@@ -16,7 +16,7 @@ or
 or
 'perf probe' --list
 or
-'perf probe' [options] --line='FUNC[:RLN[+NUM|:RLN2]]|SRC:ALN[+NUM|:ALN2]'
+'perf probe' [options] --line='LINE'
 or
 'perf probe' [options] --vars='PROBEPOINT'
 
@@ -73,6 +73,17 @@ OPTIONS
 	(Only for --vars) Show external defined variables in addition to local
 	variables.
 
+-F::
+--funcs::
+	Show available functions in given module or kernel.
+
+--filter=FILTER::
+	(Only for --vars and --funcs) Set filter. FILTER is a combination of glob
+	pattern, see FILTER PATTERN for detail.
+	Default FILTER is "!__k???tab_* & !__crc_*" for --vars, and "!_*"
+	for --funcs.
+	If several filters are specified, only the last filter is used.
+
 -f::
 --force::
 	Forcibly add events with existing name.
@@ -117,13 +128,14 @@ LINE SYNTAX
 -----------
 Line range is described by following syntax.
 
- "FUNC[:RLN[+NUM|-RLN2]]|SRC[:ALN[+NUM|-ALN2]]"
+ "FUNC[@SRC][:RLN[+NUM|-RLN2]]|SRC[:ALN[+NUM|-ALN2]]"
 
 FUNC specifies the function name of showing lines. 'RLN' is the start line
 number from function entry line, and 'RLN2' is the end line number. As same as
 probe syntax, 'SRC' means the source file path, 'ALN' is start line number,
 and 'ALN2' is end line number in the file. It is also possible to specify how
-many lines to show by using 'NUM'.
+many lines to show by using 'NUM'. Moreover, 'FUNC@SRC' combination is good
+for searching a specific function when several functions share same name.
 So, "source.c:100-120" shows lines between 100th to l20th in source.c file. And "func:10+20" shows 20 lines from 10th line of func function.
 
 LAZY MATCHING
@@ -135,6 +147,14 @@ e.g.
 
 This provides some sort of flexibility and robustness to probe point definitions against minor code changes. For example, actual 10th line of schedule() can be moved easily by modifying schedule(), but the same line matching 'rq=cpu_rq*' may still exist in the function.)
 
+FILTER PATTERN
+--------------
+ The filter pattern is a glob matching pattern(s) to filter variables.
+ In addition, you can use "!" for specifying filter-out rule. You also can give several rules combined with "&" or "|", and fold those rules as one rule by using "(" ")".
+
+e.g.
+ With --filter "foo* | bar*", perf probe -V shows variables which start with "foo" or "bar".
+ With --filter "!foo* & *bar", perf probe -V shows variables which don't start with "foo" and end with "bar", like "fizzbar". But "foobar" is filtered out.
 
 EXAMPLES
 --------
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index e032716c839b..5a520f825295 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -137,6 +137,17 @@ Do not update the builid cache. This saves some overhead in situations
 where the information in the perf.data file (which includes buildids)
 is sufficient.
 
+-G name,...::
+--cgroup name,...::
+monitor only in the container (cgroup) called "name". This option is available only
+in per-cpu mode. The cgroup filesystem must be mounted. All threads belonging to
+container "name" are monitored when they run on the monitored CPUs. Multiple cgroups
+can be provided. Each cgroup is applied to the corresponding event, i.e., first cgroup
+to first event, second cgroup to second event and so on. It is possible to provide
+an empty cgroup (monitor all the time) using, e.g., -G foo,,bar. Cgroups must have
+corresponding events, i.e., they always refer to events defined earlier on the command
+line.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-list[1]
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index b6da7affbbee..918cc38ee6d1 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -83,6 +83,17 @@ This option is only valid in system-wide mode.
 print counts using a CSV-style output to make it easy to import directly into
 spreadsheets. Columns are separated by the string specified in SEP.
 
+-G name::
+--cgroup name::
+monitor only in the container (cgroup) called "name". This option is available only
+in per-cpu mode. The cgroup filesystem must be mounted. All threads belonging to
+container "name" are monitored when they run on the monitored CPUs. Multiple cgroups
+can be provided. Each cgroup is applied to the corresponding event, i.e., first cgroup
+to first event, second cgroup to second event and so on. It is possible to provide
+an empty cgroup (monitor all the time) using, e.g., -G foo,,bar. Cgroups must have
+corresponding events, i.e., they always refer to events defined earlier on the command
+line.
+
 EXAMPLES
 --------
 
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 7141c42e1469..9b8421805c5c 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -3,7 +3,7 @@ ifeq ("$(origin O)", "command line")
 endif
 
 # The default target of this Makefile is...
-all::
+all:
 
 ifneq ($(OUTPUT),)
 # check that the output directory actually exists
@@ -11,152 +11,12 @@ OUTDIR := $(shell cd $(OUTPUT) && /bin/pwd)
 $(if $(OUTDIR),, $(error output directory "$(OUTPUT)" does not exist))
 endif
 
-# Define V=1 to have a more verbose compile.
-# Define V=2 to have an even more verbose compile.
-#
-# Define SNPRINTF_RETURNS_BOGUS if your are on a system which snprintf()
-# or vsnprintf() return -1 instead of number of characters which would
-# have been written to the final string if enough space had been available.
-#
-# Define FREAD_READS_DIRECTORIES if your are on a system which succeeds
-# when attempting to read from an fopen'ed directory.
-#
-# Define NO_OPENSSL environment variable if you do not have OpenSSL.
-# This also implies MOZILLA_SHA1.
-#
-# Define CURLDIR=/foo/bar if your curl header and library files are in
-# /foo/bar/include and /foo/bar/lib directories.
-#
-# Define EXPATDIR=/foo/bar if your expat header and library files are in
-# /foo/bar/include and /foo/bar/lib directories.
-#
-# Define NO_D_INO_IN_DIRENT if you don't have d_ino in your struct dirent.
-#
-# Define NO_D_TYPE_IN_DIRENT if your platform defines DT_UNKNOWN but lacks
-# d_type in struct dirent (latest Cygwin -- will be fixed soonish).
-#
-# Define NO_C99_FORMAT if your formatted IO functions (printf/scanf et.al.)
-# do not support the 'size specifiers' introduced by C99, namely ll, hh,
-# j, z, t. (representing long long int, char, intmax_t, size_t, ptrdiff_t).
-# some C compilers supported these specifiers prior to C99 as an extension.
-#
-# Define NO_STRCASESTR if you don't have strcasestr.
-#
-# Define NO_MEMMEM if you don't have memmem.
-#
-# Define NO_STRTOUMAX if you don't have strtoumax in the C library.
-# If your compiler also does not support long long or does not have
-# strtoull, define NO_STRTOULL.
-#
-# Define NO_SETENV if you don't have setenv in the C library.
-#
-# Define NO_UNSETENV if you don't have unsetenv in the C library.
-#
-# Define NO_MKDTEMP if you don't have mkdtemp in the C library.
-#
-# Define NO_SYS_SELECT_H if you don't have sys/select.h.
-#
-# Define NO_SYMLINK_HEAD if you never want .perf/HEAD to be a symbolic link.
-# Enable it on Windows.  By default, symrefs are still used.
-#
-# Define NO_SVN_TESTS if you want to skip time-consuming SVN interoperability
-# tests.  These tests take up a significant amount of the total test time
-# but are not needed unless you plan to talk to SVN repos.
-#
-# Define NO_FINK if you are building on Darwin/Mac OS X, have Fink
-# installed in /sw, but don't want PERF to link against any libraries
-# installed there.  If defined you may specify your own (or Fink's)
-# include directories and library directories by defining CFLAGS
-# and LDFLAGS appropriately.
-#
-# Define NO_DARWIN_PORTS if you are building on Darwin/Mac OS X,
-# have DarwinPorts installed in /opt/local, but don't want PERF to
-# link against any libraries installed there.  If defined you may
-# specify your own (or DarwinPort's) include directories and
-# library directories by defining CFLAGS and LDFLAGS appropriately.
-#
-# Define PPC_SHA1 environment variable when running make to make use of
-# a bundled SHA1 routine optimized for PowerPC.
-#
-# Define ARM_SHA1 environment variable when running make to make use of
-# a bundled SHA1 routine optimized for ARM.
-#
-# Define MOZILLA_SHA1 environment variable when running make to make use of
-# a bundled SHA1 routine coming from Mozilla. It is GPL'd and should be fast
-# on non-x86 architectures (e.g. PowerPC), while the OpenSSL version (default
-# choice) has very fast version optimized for i586.
-#
-# Define NEEDS_SSL_WITH_CRYPTO if you need -lcrypto with -lssl (Darwin).
-#
-# Define NEEDS_LIBICONV if linking with libc is not enough (Darwin).
-#
-# Define NEEDS_SOCKET if linking with libc is not enough (SunOS,
-# Patrick Mauritz).
-#
-# Define NO_MMAP if you want to avoid mmap.
-#
-# Define NO_PTHREADS if you do not have or do not want to use Pthreads.
-#
-# Define NO_PREAD if you have a problem with pread() system call (e.g.
-# cygwin.dll before v1.5.22).
-#
-# Define NO_FAST_WORKING_DIRECTORY if accessing objects in pack files is
-# generally faster on your platform than accessing the working directory.
-#
-# Define NO_TRUSTABLE_FILEMODE if your filesystem may claim to support
-# the executable mode bit, but doesn't really do so.
-#
-# Define NO_IPV6 if you lack IPv6 support and getaddrinfo().
-#
-# Define NO_SOCKADDR_STORAGE if your platform does not have struct
-# sockaddr_storage.
-#
-# Define NO_ICONV if your libc does not properly support iconv.
-#
-# Define OLD_ICONV if your library has an old iconv(), where the second
-# (input buffer pointer) parameter is declared with type (const char **).
-#
-# Define NO_DEFLATE_BOUND if your zlib does not have deflateBound.
-#
-# Define NO_R_TO_GCC_LINKER if your gcc does not like "-R/path/lib"
-# that tells runtime paths to dynamic libraries;
-# "-Wl,-rpath=/path/lib" is used instead.
-#
-# Define USE_NSEC below if you want perf to care about sub-second file mtimes
-# and ctimes. Note that you need recent glibc (at least 2.2.4) for this, and
-# it will BREAK YOUR LOCAL DIFFS! show-diff and anything using it will likely
-# randomly break unless your underlying filesystem supports those sub-second
-# times (my ext3 doesn't).
-#
-# Define USE_ST_TIMESPEC if your "struct stat" uses "st_ctimespec" instead of
-# "st_ctim"
-#
-# Define NO_NSEC if your "struct stat" does not have "st_ctim.tv_nsec"
-# available.  This automatically turns USE_NSEC off.
-#
-# Define USE_STDEV below if you want perf to care about the underlying device
-# change being considered an inode change from the update-index perspective.
-#
-# Define NO_ST_BLOCKS_IN_STRUCT_STAT if your platform does not have st_blocks
-# field that counts the on-disk footprint in 512-byte blocks.
+# Define V to have a more verbose compile.
 #
 # Define ASCIIDOC8 if you want to format documentation with AsciiDoc 8
 #
 # Define DOCBOOK_XSL_172 if you want to format man pages with DocBook XSL v1.72.
 #
-# Define NO_PERL_MAKEMAKER if you cannot use Makefiles generated by perl's
-# MakeMaker (e.g. using ActiveState under Cygwin).
-#
-# Define NO_PERL if you do not want Perl scripts or libraries at all.
-#
-# Define INTERNAL_QSORT to use Git's implementation of qsort(), which
-# is a simplified version of the merge sort used in glibc. This is
-# recommended if Git triggers O(n^2) behavior in your platform's qsort().
-#
-# Define NO_EXTERNAL_GREP if you don't want "perf grep" to ever call
-# your external grep (e.g., if your system lacks grep, if its grep is
-# broken, or spawning external process is slower than built-in grep perf has).
-#
 # Define LDFLAGS=-static to build a static binary.
 #
 # Define EXTRA_CFLAGS=-m64 or EXTRA_CFLAGS=-m32 as appropriate for cross-builds.
@@ -167,12 +27,7 @@ $(OUTPUT)PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE
 	@$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT)
 -include $(OUTPUT)PERF-VERSION-FILE
 
-uname_S := $(shell sh -c 'uname -s 2>/dev/null || echo not')
-uname_M := $(shell sh -c 'uname -m 2>/dev/null || echo not')
-uname_O := $(shell sh -c 'uname -o 2>/dev/null || echo not')
-uname_R := $(shell sh -c 'uname -r 2>/dev/null || echo not')
-uname_P := $(shell sh -c 'uname -p 2>/dev/null || echo not')
-uname_V := $(shell sh -c 'uname -v 2>/dev/null || echo not')
+uname_M := $(shell uname -m 2>/dev/null || echo not)
 
 ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \
 				  -e s/arm.*/arm/ -e s/sa110/arm/ \
@@ -191,8 +46,6 @@ ifeq ($(ARCH),x86_64)
 	ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S
 endif
 
-# CFLAGS and LDFLAGS are for the users to override from the command line.
-
 #
 # Include saner warnings here, which can catch bugs:
 #
@@ -270,22 +123,13 @@ CC = $(CROSS_COMPILE)gcc
 AR = $(CROSS_COMPILE)ar
 RM = rm -f
 MKDIR = mkdir
-TAR = tar
 FIND = find
 INSTALL = install
-RPMBUILD = rpmbuild
-PTHREAD_LIBS = -lpthread
 
 # sparse is architecture-neutral, which means that we need to tell it
 # explicitly what architecture to check for. Fix this up for yours..
 SPARSE_FLAGS = -D__BIG_ENDIAN__ -D__powerpc__
 
-ifeq ($(V), 2)
-	QUIET_STDERR = ">/dev/null"
-else
-	QUIET_STDERR = ">/dev/null 2>&1"
-endif
-
 -include feature-tests.mak
 
 ifeq ($(call try-cc,$(SOURCE_HELLO),-Werror -fstack-protector-all),y)
@@ -310,49 +154,37 @@ BASIC_LDFLAGS =
 
 # Guard against environment variables
 BUILTIN_OBJS =
-BUILT_INS =
-COMPAT_CFLAGS =
-COMPAT_OBJS =
 LIB_H =
 LIB_OBJS =
-SCRIPT_PERL =
+PYRF_OBJS =
 SCRIPT_SH =
-TEST_PROGRAMS =
 
 SCRIPT_SH += perf-archive.sh
 
 grep-libs = $(filter -l%,$(1))
 strip-libs = $(filter-out -l%,$(1))
 
+$(OUTPUT)python/perf.so: $(PYRF_OBJS)
+	$(QUIET_GEN)python util/setup.py --quiet  build_ext --build-lib='$(OUTPUT)python' \
+						--build-temp='$(OUTPUT)python/temp'
 #
 # No Perl scripts right now:
 #
 
-# SCRIPT_PERL += perf-add--interactive.perl
-
-SCRIPTS = $(patsubst %.sh,%,$(SCRIPT_SH)) \
-	  $(patsubst %.perl,%,$(SCRIPT_PERL))
-
-# Empty...
-EXTRA_PROGRAMS =
-
-# ... and all the rest that could be moved out of bindir to perfexecdir
-PROGRAMS += $(EXTRA_PROGRAMS)
+SCRIPTS = $(patsubst %.sh,%,$(SCRIPT_SH))
 
 #
 # Single 'perf' binary right now:
 #
 PROGRAMS += $(OUTPUT)perf
 
-# List built-in command $C whose implementation cmd_$C() is not in
-# builtin-$C.o but is linked in as part of some other command.
-#
+LANG_BINDINGS =
 
 # what 'all' will build and 'install' will install, in perfexecdir
 ALL_PROGRAMS = $(PROGRAMS) $(SCRIPTS)
 
 # what 'all' will build but not install in perfexecdir
-OTHER_PROGRAMS = $(OUTPUT)perf$X
+OTHER_PROGRAMS = $(OUTPUT)perf
 
 # Set paths to tools early so that they can be used for version tests.
 ifndef SHELL_PATH
@@ -395,6 +227,7 @@ LIB_H += util/include/dwarf-regs.h
 LIB_H += util/include/asm/dwarf2.h
 LIB_H += util/include/asm/cpufeature.h
 LIB_H += perf.h
+LIB_H += util/annotate.h
 LIB_H += util/cache.h
 LIB_H += util/callchain.h
 LIB_H += util/build-id.h
@@ -402,6 +235,7 @@ LIB_H += util/debug.h
 LIB_H += util/debugfs.h
 LIB_H += util/event.h
 LIB_H += util/evsel.h
+LIB_H += util/evlist.h
 LIB_H += util/exec_cmd.h
 LIB_H += util/types.h
 LIB_H += util/levenshtein.h
@@ -416,6 +250,7 @@ LIB_H += util/help.h
 LIB_H += util/session.h
 LIB_H += util/strbuf.h
 LIB_H += util/strlist.h
+LIB_H += util/strfilter.h
 LIB_H += util/svghelper.h
 LIB_H += util/run-command.h
 LIB_H += util/sigchain.h
@@ -425,21 +260,26 @@ LIB_H += util/values.h
 LIB_H += util/sort.h
 LIB_H += util/hist.h
 LIB_H += util/thread.h
+LIB_H += util/thread_map.h
 LIB_H += util/trace-event.h
 LIB_H += util/probe-finder.h
 LIB_H += util/probe-event.h
 LIB_H += util/pstack.h
 LIB_H += util/cpumap.h
+LIB_H += util/top.h
 LIB_H += $(ARCH_INCLUDE)
+LIB_H += util/cgroup.h
 
 LIB_OBJS += $(OUTPUT)util/abspath.o
 LIB_OBJS += $(OUTPUT)util/alias.o
+LIB_OBJS += $(OUTPUT)util/annotate.o
 LIB_OBJS += $(OUTPUT)util/build-id.o
 LIB_OBJS += $(OUTPUT)util/config.o
 LIB_OBJS += $(OUTPUT)util/ctype.o
 LIB_OBJS += $(OUTPUT)util/debugfs.o
 LIB_OBJS += $(OUTPUT)util/environment.o
 LIB_OBJS += $(OUTPUT)util/event.o
+LIB_OBJS += $(OUTPUT)util/evlist.o
 LIB_OBJS += $(OUTPUT)util/evsel.o
 LIB_OBJS += $(OUTPUT)util/exec_cmd.o
 LIB_OBJS += $(OUTPUT)util/help.o
@@ -455,6 +295,8 @@ LIB_OBJS += $(OUTPUT)util/quote.o
 LIB_OBJS += $(OUTPUT)util/strbuf.o
 LIB_OBJS += $(OUTPUT)util/string.o
 LIB_OBJS += $(OUTPUT)util/strlist.o
+LIB_OBJS += $(OUTPUT)util/strfilter.o
+LIB_OBJS += $(OUTPUT)util/top.o
 LIB_OBJS += $(OUTPUT)util/usage.o
 LIB_OBJS += $(OUTPUT)util/wrapper.o
 LIB_OBJS += $(OUTPUT)util/sigchain.o
@@ -469,6 +311,7 @@ LIB_OBJS += $(OUTPUT)util/map.o
 LIB_OBJS += $(OUTPUT)util/pstack.o
 LIB_OBJS += $(OUTPUT)util/session.o
 LIB_OBJS += $(OUTPUT)util/thread.o
+LIB_OBJS += $(OUTPUT)util/thread_map.o
 LIB_OBJS += $(OUTPUT)util/trace-event-parse.o
 LIB_OBJS += $(OUTPUT)util/trace-event-read.o
 LIB_OBJS += $(OUTPUT)util/trace-event-info.o
@@ -480,6 +323,7 @@ LIB_OBJS += $(OUTPUT)util/probe-event.o
 LIB_OBJS += $(OUTPUT)util/util.o
 LIB_OBJS += $(OUTPUT)util/xyarray.o
 LIB_OBJS += $(OUTPUT)util/cpumap.o
+LIB_OBJS += $(OUTPUT)util/cgroup.o
 
 BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o
 
@@ -514,6 +358,20 @@ BUILTIN_OBJS += $(OUTPUT)builtin-inject.o
 
 PERFLIBS = $(LIB_FILE)
 
+# Files needed for the python binding, perf.so
+# pyrf is just an internal name needed for all those wrappers.
+# This has to be in sync with what is in the 'sources' variable in
+# tools/perf/util/setup.py
+
+PYRF_OBJS += $(OUTPUT)util/cpumap.o
+PYRF_OBJS += $(OUTPUT)util/ctype.o
+PYRF_OBJS += $(OUTPUT)util/evlist.o
+PYRF_OBJS += $(OUTPUT)util/evsel.o
+PYRF_OBJS += $(OUTPUT)util/python.o
+PYRF_OBJS += $(OUTPUT)util/thread_map.o
+PYRF_OBJS += $(OUTPUT)util/util.o
+PYRF_OBJS += $(OUTPUT)util/xyarray.o
+
 #
 # Platform specific tweaks
 #
@@ -535,22 +393,6 @@ endif # NO_DWARF
 
 -include arch/$(ARCH)/Makefile
 
-ifeq ($(uname_S),Darwin)
-	ifndef NO_FINK
-		ifeq ($(shell test -d /sw/lib && echo y),y)
-			BASIC_CFLAGS += -I/sw/include
-			BASIC_LDFLAGS += -L/sw/lib
-		endif
-	endif
-	ifndef NO_DARWIN_PORTS
-		ifeq ($(shell test -d /opt/local/lib && echo y),y)
-			BASIC_CFLAGS += -I/opt/local/include
-			BASIC_LDFLAGS += -L/opt/local/lib
-		endif
-	endif
-	PTHREAD_LIBS =
-endif
-
 ifneq ($(OUTPUT),)
 	BASIC_CFLAGS += -I$(OUTPUT)
 endif
@@ -595,6 +437,7 @@ else
 		LIB_OBJS += $(OUTPUT)util/ui/browsers/annotate.o
 		LIB_OBJS += $(OUTPUT)util/ui/browsers/hists.o
 		LIB_OBJS += $(OUTPUT)util/ui/browsers/map.o
+		LIB_OBJS += $(OUTPUT)util/ui/browsers/top.o
 		LIB_OBJS += $(OUTPUT)util/ui/helpline.o
 		LIB_OBJS += $(OUTPUT)util/ui/progress.o
 		LIB_OBJS += $(OUTPUT)util/ui/util.o
@@ -604,6 +447,7 @@ else
 		LIB_H += util/ui/libslang.h
 		LIB_H += util/ui/progress.h
 		LIB_H += util/ui/util.h
+		LIB_H += util/ui/ui.h
 	endif
 endif
 
@@ -635,12 +479,14 @@ else
 	PYTHON_EMBED_CCOPTS = `python-config --cflags 2>/dev/null`
 	FLAGS_PYTHON_EMBED=$(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)
 	ifneq ($(call try-cc,$(SOURCE_PYTHON_EMBED),$(FLAGS_PYTHON_EMBED)),y)
+		msg := $(warning No Python.h found, install python-dev[el] to have python support in 'perf script' and to build the python bindings)
 		BASIC_CFLAGS += -DNO_LIBPYTHON
 	else
                ALL_LDFLAGS += $(PYTHON_EMBED_LDFLAGS)
                EXTLIBS += $(PYTHON_EMBED_LIBADD)
 		LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-python.o
 		LIB_OBJS += $(OUTPUT)scripts/python/Perf-Trace-Util/Context.o
+		LANG_BINDINGS += $(OUTPUT)python/perf.so
 	endif
 endif
 
@@ -690,201 +536,13 @@ else
 	endif
 endif
 
-ifndef CC_LD_DYNPATH
-	ifdef NO_R_TO_GCC_LINKER
-		# Some gcc does not accept and pass -R to the linker to specify
-		# the runtime dynamic library path.
-		CC_LD_DYNPATH = -Wl,-rpath,
-	else
-		CC_LD_DYNPATH = -R
-	endif
-endif
-
-ifdef NEEDS_SOCKET
-	EXTLIBS += -lsocket
-endif
-ifdef NEEDS_NSL
-	EXTLIBS += -lnsl
-endif
-ifdef NO_D_TYPE_IN_DIRENT
-	BASIC_CFLAGS += -DNO_D_TYPE_IN_DIRENT
-endif
-ifdef NO_D_INO_IN_DIRENT
-	BASIC_CFLAGS += -DNO_D_INO_IN_DIRENT
-endif
-ifdef NO_ST_BLOCKS_IN_STRUCT_STAT
-	BASIC_CFLAGS += -DNO_ST_BLOCKS_IN_STRUCT_STAT
-endif
-ifdef USE_NSEC
-	BASIC_CFLAGS += -DUSE_NSEC
-endif
-ifdef USE_ST_TIMESPEC
-	BASIC_CFLAGS += -DUSE_ST_TIMESPEC
-endif
-ifdef NO_NSEC
-	BASIC_CFLAGS += -DNO_NSEC
-endif
-ifdef NO_C99_FORMAT
-	BASIC_CFLAGS += -DNO_C99_FORMAT
-endif
-ifdef SNPRINTF_RETURNS_BOGUS
-	COMPAT_CFLAGS += -DSNPRINTF_RETURNS_BOGUS
-	COMPAT_OBJS += $(OUTPUT)compat/snprintf.o
-endif
-ifdef FREAD_READS_DIRECTORIES
-	COMPAT_CFLAGS += -DFREAD_READS_DIRECTORIES
-	COMPAT_OBJS += $(OUTPUT)compat/fopen.o
-endif
-ifdef NO_SYMLINK_HEAD
-	BASIC_CFLAGS += -DNO_SYMLINK_HEAD
-endif
-ifdef NO_STRCASESTR
-	COMPAT_CFLAGS += -DNO_STRCASESTR
-	COMPAT_OBJS += $(OUTPUT)compat/strcasestr.o
-endif
-ifdef NO_STRTOUMAX
-	COMPAT_CFLAGS += -DNO_STRTOUMAX
-	COMPAT_OBJS += $(OUTPUT)compat/strtoumax.o
-endif
-ifdef NO_STRTOULL
-	COMPAT_CFLAGS += -DNO_STRTOULL
-endif
-ifdef NO_SETENV
-	COMPAT_CFLAGS += -DNO_SETENV
-	COMPAT_OBJS += $(OUTPUT)compat/setenv.o
-endif
-ifdef NO_MKDTEMP
-	COMPAT_CFLAGS += -DNO_MKDTEMP
-	COMPAT_OBJS += $(OUTPUT)compat/mkdtemp.o
-endif
-ifdef NO_UNSETENV
-	COMPAT_CFLAGS += -DNO_UNSETENV
-	COMPAT_OBJS += $(OUTPUT)compat/unsetenv.o
-endif
-ifdef NO_SYS_SELECT_H
-	BASIC_CFLAGS += -DNO_SYS_SELECT_H
-endif
-ifdef NO_MMAP
-	COMPAT_CFLAGS += -DNO_MMAP
-	COMPAT_OBJS += $(OUTPUT)compat/mmap.o
-else
-	ifdef USE_WIN32_MMAP
-		COMPAT_CFLAGS += -DUSE_WIN32_MMAP
-		COMPAT_OBJS += $(OUTPUT)compat/win32mmap.o
-	endif
-endif
-ifdef NO_PREAD
-	COMPAT_CFLAGS += -DNO_PREAD
-	COMPAT_OBJS += $(OUTPUT)compat/pread.o
-endif
-ifdef NO_FAST_WORKING_DIRECTORY
-	BASIC_CFLAGS += -DNO_FAST_WORKING_DIRECTORY
-endif
-ifdef NO_TRUSTABLE_FILEMODE
-	BASIC_CFLAGS += -DNO_TRUSTABLE_FILEMODE
-endif
-ifdef NO_IPV6
-	BASIC_CFLAGS += -DNO_IPV6
-endif
-ifdef NO_UINTMAX_T
-	BASIC_CFLAGS += -Duintmax_t=uint32_t
-endif
-ifdef NO_SOCKADDR_STORAGE
-ifdef NO_IPV6
-	BASIC_CFLAGS += -Dsockaddr_storage=sockaddr_in
-else
-	BASIC_CFLAGS += -Dsockaddr_storage=sockaddr_in6
-endif
-endif
-ifdef NO_INET_NTOP
-	LIB_OBJS += $(OUTPUT)compat/inet_ntop.o
-endif
-ifdef NO_INET_PTON
-	LIB_OBJS += $(OUTPUT)compat/inet_pton.o
-endif
-
-ifdef NO_ICONV
-	BASIC_CFLAGS += -DNO_ICONV
-endif
-
-ifdef OLD_ICONV
-	BASIC_CFLAGS += -DOLD_ICONV
-endif
-
-ifdef NO_DEFLATE_BOUND
-	BASIC_CFLAGS += -DNO_DEFLATE_BOUND
-endif
-
-ifdef PPC_SHA1
-	SHA1_HEADER = "ppc/sha1.h"
-	LIB_OBJS += $(OUTPUT)ppc/sha1.o ppc/sha1ppc.o
-else
-ifdef ARM_SHA1
-	SHA1_HEADER = "arm/sha1.h"
-	LIB_OBJS += $(OUTPUT)arm/sha1.o $(OUTPUT)arm/sha1_arm.o
-else
-ifdef MOZILLA_SHA1
-	SHA1_HEADER = "mozilla-sha1/sha1.h"
-	LIB_OBJS += $(OUTPUT)mozilla-sha1/sha1.o
-else
-	SHA1_HEADER = <openssl/sha.h>
-	EXTLIBS += $(LIB_4_CRYPTO)
-endif
-endif
-endif
-ifdef NO_PERL_MAKEMAKER
-	export NO_PERL_MAKEMAKER
-endif
-ifdef NO_HSTRERROR
-	COMPAT_CFLAGS += -DNO_HSTRERROR
-	COMPAT_OBJS += $(OUTPUT)compat/hstrerror.o
-endif
-ifdef NO_MEMMEM
-	COMPAT_CFLAGS += -DNO_MEMMEM
-	COMPAT_OBJS += $(OUTPUT)compat/memmem.o
-endif
-ifdef INTERNAL_QSORT
-	COMPAT_CFLAGS += -DINTERNAL_QSORT
-	COMPAT_OBJS += $(OUTPUT)compat/qsort.o
-endif
-ifdef RUNTIME_PREFIX
-	COMPAT_CFLAGS += -DRUNTIME_PREFIX
-endif
-
-ifdef DIR_HAS_BSD_GROUP_SEMANTICS
-	COMPAT_CFLAGS += -DDIR_HAS_BSD_GROUP_SEMANTICS
-endif
-ifdef NO_EXTERNAL_GREP
-	BASIC_CFLAGS += -DNO_EXTERNAL_GREP
-endif
-
-ifeq ($(PERL_PATH),)
-NO_PERL=NoThanks
-endif
-
-QUIET_SUBDIR0  = +$(MAKE) -C # space to separate -C and subdir
-QUIET_SUBDIR1  =
-
-ifneq ($(findstring $(MAKEFLAGS),w),w)
-PRINT_DIR = --no-print-directory
-else # "make -w"
-NO_SUBDIR = :
-endif
-
 ifneq ($(findstring $(MAKEFLAGS),s),s)
 ifndef V
 	QUIET_CC       = @echo '   ' CC $@;
 	QUIET_AR       = @echo '   ' AR $@;
 	QUIET_LINK     = @echo '   ' LINK $@;
 	QUIET_MKDIR    = @echo '   ' MKDIR $@;
-	QUIET_BUILT_IN = @echo '   ' BUILTIN $@;
 	QUIET_GEN      = @echo '   ' GEN $@;
-	QUIET_SUBDIR0  = +@subdir=
-	QUIET_SUBDIR1  = ;$(NO_SUBDIR) echo '   ' SUBDIR $$subdir; \
-			 $(MAKE) $(PRINT_DIR) -C $$subdir
-	export V
-	export QUIET_GEN
-	export QUIET_BUILT_IN
 endif
 endif
 
@@ -894,7 +552,6 @@ endif
 
 # Shell quote (do not use $(call) to accommodate ancient setups);
 
-SHA1_HEADER_SQ = $(subst ','\'',$(SHA1_HEADER))
 ETC_PERFCONFIG_SQ = $(subst ','\'',$(ETC_PERFCONFIG))
 
 DESTDIR_SQ = $(subst ','\'',$(DESTDIR))
@@ -908,46 +565,36 @@ htmldir_SQ = $(subst ','\'',$(htmldir))
 prefix_SQ = $(subst ','\'',$(prefix))
 
 SHELL_PATH_SQ = $(subst ','\'',$(SHELL_PATH))
-PERL_PATH_SQ = $(subst ','\'',$(PERL_PATH))
 
 LIBS = -Wl,--whole-archive $(PERFLIBS) -Wl,--no-whole-archive $(EXTLIBS)
 
-BASIC_CFLAGS += -DSHA1_HEADER='$(SHA1_HEADER_SQ)' \
-	$(COMPAT_CFLAGS)
-LIB_OBJS += $(COMPAT_OBJS)
-
 ALL_CFLAGS += $(BASIC_CFLAGS)
 ALL_CFLAGS += $(ARCH_CFLAGS)
 ALL_LDFLAGS += $(BASIC_LDFLAGS)
 
-export TAR INSTALL DESTDIR SHELL_PATH
+export INSTALL SHELL_PATH
 
 
 ### Build rules
 
 SHELL = $(SHELL_PATH)
 
-all:: shell_compatibility_test $(ALL_PROGRAMS) $(BUILT_INS) $(OTHER_PROGRAMS) $(OUTPUT)PERF-BUILD-OPTIONS
-ifneq (,$X)
-	$(foreach p,$(patsubst %$X,%,$(filter %$X,$(ALL_PROGRAMS) $(BUILT_INS) perf$X)), test '$p' -ef '$p$X' || $(RM) '$p';)
-endif
-
-all::
+all: shell_compatibility_test $(ALL_PROGRAMS) $(LANG_BINDINGS) $(OTHER_PROGRAMS)
 
 please_set_SHELL_PATH_to_a_more_modern_shell:
 	@$$(:)
 
 shell_compatibility_test: please_set_SHELL_PATH_to_a_more_modern_shell
 
-strip: $(PROGRAMS) $(OUTPUT)perf$X
-	$(STRIP) $(STRIP_OPTS) $(PROGRAMS) $(OUTPUT)perf$X
+strip: $(PROGRAMS) $(OUTPUT)perf
+	$(STRIP) $(STRIP_OPTS) $(PROGRAMS) $(OUTPUT)perf
 
 $(OUTPUT)perf.o: perf.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-CFLAGS
 	$(QUIET_CC)$(CC) -DPERF_VERSION='"$(PERF_VERSION)"' \
 		'-DPERF_HTML_PATH="$(htmldir_SQ)"' \
 		$(ALL_CFLAGS) -c $(filter %.c,$^) -o $@
 
-$(OUTPUT)perf$X: $(OUTPUT)perf.o $(BUILTIN_OBJS) $(PERFLIBS)
+$(OUTPUT)perf: $(OUTPUT)perf.o $(BUILTIN_OBJS) $(PERFLIBS)
 	$(QUIET_LINK)$(CC) $(ALL_CFLAGS) $(ALL_LDFLAGS) $(OUTPUT)perf.o \
                $(BUILTIN_OBJS) $(LIBS) -o $@
 
@@ -963,39 +610,17 @@ $(OUTPUT)builtin-timechart.o: builtin-timechart.c $(OUTPUT)common-cmds.h $(OUTPU
 		'-DPERF_MAN_PATH="$(mandir_SQ)"' \
 		'-DPERF_INFO_PATH="$(infodir_SQ)"' $<
 
-$(BUILT_INS): $(OUTPUT)perf$X
-	$(QUIET_BUILT_IN)$(RM) $@ && \
-	ln perf$X $@ 2>/dev/null || \
-	ln -s perf$X $@ 2>/dev/null || \
-	cp perf$X $@
-
 $(OUTPUT)common-cmds.h: util/generate-cmdlist.sh command-list.txt
 
 $(OUTPUT)common-cmds.h: $(wildcard Documentation/perf-*.txt)
 	$(QUIET_GEN). util/generate-cmdlist.sh > $@+ && mv $@+ $@
 
-$(patsubst %.sh,%,$(SCRIPT_SH)) : % : %.sh
-	$(QUIET_GEN)$(RM) $(OUTPUT)$@ $(OUTPUT)$@+ && \
-	sed -e '1s|#!.*/sh|#!$(SHELL_PATH_SQ)|' \
-	    -e 's|@SHELL_PATH@|$(SHELL_PATH_SQ)|' \
-	    -e 's|@@PERL@@|$(PERL_PATH_SQ)|g' \
-	    -e 's/@@PERF_VERSION@@/$(PERF_VERSION)/g' \
-	    -e 's/@@NO_CURL@@/$(NO_CURL)/g' \
-	    $@.sh > $(OUTPUT)$@+ && \
-	chmod +x $(OUTPUT)$@+ && \
-	mv $(OUTPUT)$@+ $(OUTPUT)$@
-
-configure: configure.ac
-	$(QUIET_GEN)$(RM) $@ $<+ && \
-	sed -e 's/@@PERF_VERSION@@/$(PERF_VERSION)/g' \
-	    $< > $<+ && \
-	autoconf -o $@ $<+ && \
-	$(RM) $<+
+$(SCRIPTS) : % : %.sh
+	$(QUIET_GEN)$(INSTALL) '$@.sh' '$(OUTPUT)$@'
 
 # These can record PERF_VERSION
 $(OUTPUT)perf.o perf.spec \
-	$(patsubst %.sh,%,$(SCRIPT_SH)) \
-	$(patsubst %.perl,%,$(SCRIPT_PERL)) \
+	$(SCRIPTS) \
 	: $(OUTPUT)PERF-VERSION-FILE
 
 $(OUTPUT)%.o: %.c $(OUTPUT)PERF-CFLAGS
@@ -1012,9 +637,6 @@ $(OUTPUT)util/exec_cmd.o: util/exec_cmd.c $(OUTPUT)PERF-CFLAGS
 		'-DPREFIX="$(prefix_SQ)"' \
 		$<
 
-$(OUTPUT)builtin-init-db.o: builtin-init-db.c $(OUTPUT)PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DDEFAULT_PERF_TEMPLATE_DIR='"$(template_dir_SQ)"' $<
-
 $(OUTPUT)util/config.o: util/config.c $(OUTPUT)PERF-CFLAGS
 	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
 
@@ -1024,6 +646,9 @@ $(OUTPUT)util/ui/browser.o: util/ui/browser.c $(OUTPUT)PERF-CFLAGS
 $(OUTPUT)util/ui/browsers/annotate.o: util/ui/browsers/annotate.c $(OUTPUT)PERF-CFLAGS
 	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DENABLE_SLFUTURE_CONST $<
 
+$(OUTPUT)util/ui/browsers/top.o: util/ui/browsers/top.c $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DENABLE_SLFUTURE_CONST $<
+
 $(OUTPUT)util/ui/browsers/hists.o: util/ui/browsers/hists.c $(OUTPUT)PERF-CFLAGS
 	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DENABLE_SLFUTURE_CONST $<
 
@@ -1045,12 +670,11 @@ $(OUTPUT)util/scripting-engines/trace-event-python.o: util/scripting-engines/tra
 $(OUTPUT)scripts/python/Perf-Trace-Util/Context.o: scripts/python/Perf-Trace-Util/Context.c $(OUTPUT)PERF-CFLAGS
 	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs $<
 
-$(OUTPUT)perf-%$X: %.o $(PERFLIBS)
+$(OUTPUT)perf-%: %.o $(PERFLIBS)
 	$(QUIET_LINK)$(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) $(LIBS)
 
 $(LIB_OBJS) $(BUILTIN_OBJS): $(LIB_H)
-$(patsubst perf-%$X,%.o,$(PROGRAMS)): $(LIB_H) $(wildcard */*.h)
-builtin-revert.o wt-status.o: wt-status.h
+$(patsubst perf-%,%.o,$(PROGRAMS)): $(LIB_H) $(wildcard */*.h)
 
 # we compile into subdirectories. if the target directory is not the source directory, they might not exists. So
 # we depend the various files onto their directories.
@@ -1063,6 +687,36 @@ $(sort $(dir $(DIRECTORY_DEPS))):
 $(LIB_FILE): $(LIB_OBJS)
 	$(QUIET_AR)$(RM) $@ && $(AR) rcs $@ $(LIB_OBJS)
 
+help:
+	@echo 'Perf make targets:'
+	@echo '  doc		- make *all* documentation (see below)'
+	@echo '  man		- make manpage documentation (access with man <foo>)'
+	@echo '  html		- make html documentation'
+	@echo '  info		- make GNU info documentation (access with info <foo>)'
+	@echo '  pdf		- make pdf documentation'
+	@echo '  TAGS		- use etags to make tag information for source browsing'
+	@echo '  tags		- use ctags to make tag information for source browsing'
+	@echo '  cscope	- use cscope to make interactive browsing database'
+	@echo ''
+	@echo 'Perf install targets:'
+	@echo '  NOTE: documentation build requires asciidoc, xmlto packages to be installed'
+	@echo '  HINT: use "make prefix=<path> <install target>" to install to a particular'
+	@echo '        path like make prefix=/usr/local install install-doc'
+	@echo '  install	- install compiled binaries'
+	@echo '  install-doc	- install *all* documentation'
+	@echo '  install-man	- install manpage documentation'
+	@echo '  install-html	- install html documentation'
+	@echo '  install-info	- install GNU info documentation'
+	@echo '  install-pdf	- install pdf documentation'
+	@echo ''
+	@echo '  quick-install-doc	- alias for quick-install-man'
+	@echo '  quick-install-man	- install the documentation quickly'
+	@echo '  quick-install-html	- install the html documentation quickly'
+	@echo ''
+	@echo 'Perf maintainer targets:'
+	@echo '  distclean		- alias to clean'
+	@echo '  clean			- clean all binary objects and build output'
+
 doc:
 	$(MAKE) -C Documentation all
 
@@ -1101,30 +755,12 @@ $(OUTPUT)PERF-CFLAGS: .FORCE-PERF-CFLAGS
 		echo "$$FLAGS" >$(OUTPUT)PERF-CFLAGS; \
             fi
 
-# We need to apply sq twice, once to protect from the shell
-# that runs $(OUTPUT)PERF-BUILD-OPTIONS, and then again to protect it
-# and the first level quoting from the shell that runs "echo".
-$(OUTPUT)PERF-BUILD-OPTIONS: .FORCE-PERF-BUILD-OPTIONS
-	@echo SHELL_PATH=\''$(subst ','\'',$(SHELL_PATH_SQ))'\' >$@
-	@echo TAR=\''$(subst ','\'',$(subst ','\'',$(TAR)))'\' >>$@
-	@echo NO_CURL=\''$(subst ','\'',$(subst ','\'',$(NO_CURL)))'\' >>$@
-	@echo NO_PERL=\''$(subst ','\'',$(subst ','\'',$(NO_PERL)))'\' >>$@
-
 ### Testing rules
 
-#
-# None right now:
-#
-# TEST_PROGRAMS += test-something$X
-
-all:: $(TEST_PROGRAMS)
-
 # GNU make supports exporting all variables by "export" without parameters.
 # However, the environment gets quite big, and some programs have problems
 # with that.
 
-export NO_SVN_TESTS
-
 check: $(OUTPUT)common-cmds.h
 	if sparse; \
 	then \
@@ -1133,33 +769,21 @@ check: $(OUTPUT)common-cmds.h
 			sparse $(ALL_CFLAGS) $(SPARSE_FLAGS) $$i || exit; \
 		done; \
 	else \
-		echo 2>&1 "Did you mean 'make test'?"; \
 		exit 1; \
 	fi
 
-remove-dashes:
-	./fixup-builtins $(BUILT_INS) $(PROGRAMS) $(SCRIPTS)
-
 ### Installation rules
 
-ifneq ($(filter /%,$(firstword $(template_dir))),)
-template_instdir = $(template_dir)
-else
-template_instdir = $(prefix)/$(template_dir)
-endif
-export template_instdir
-
 ifneq ($(filter /%,$(firstword $(perfexecdir))),)
 perfexec_instdir = $(perfexecdir)
 else
 perfexec_instdir = $(prefix)/$(perfexecdir)
 endif
 perfexec_instdir_SQ = $(subst ','\'',$(perfexec_instdir))
-export perfexec_instdir
 
 install: all
 	$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(bindir_SQ)'
-	$(INSTALL) $(OUTPUT)perf$X '$(DESTDIR_SQ)$(bindir_SQ)'
+	$(INSTALL) $(OUTPUT)perf '$(DESTDIR_SQ)$(bindir_SQ)'
 	$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace'
 	$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/bin'
 	$(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
@@ -1172,14 +796,6 @@ install: all
 	$(INSTALL) scripts/python/*.py -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python'
 	$(INSTALL) scripts/python/bin/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/bin'
 
-ifdef BUILT_INS
-	$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
-	$(INSTALL) $(BUILT_INS) '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
-ifneq (,$X)
-	$(foreach p,$(patsubst %$X,%,$(filter %$X,$(ALL_PROGRAMS) $(BUILT_INS) $(OUTPUT)perf$X)), $(RM) '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/$p';)
-endif
-endif
-
 install-doc:
 	$(MAKE) -C Documentation install
 
@@ -1204,104 +820,17 @@ quick-install-man:
 quick-install-html:
 	$(MAKE) -C Documentation quick-install-html
 
-
-### Maintainer's dist rules
-#
-# None right now
-#
-#
-# perf.spec: perf.spec.in
-#	sed -e 's/@@VERSION@@/$(PERF_VERSION)/g' < $< > $@+
-#	mv $@+ $@
-#
-# PERF_TARNAME=perf-$(PERF_VERSION)
-# dist: perf.spec perf-archive$(X) configure
-#	./perf-archive --format=tar \
-#		--prefix=$(PERF_TARNAME)/ HEAD^{tree} > $(PERF_TARNAME).tar
-#	@mkdir -p $(PERF_TARNAME)
-#	@cp perf.spec configure $(PERF_TARNAME)
-#	@echo $(PERF_VERSION) > $(PERF_TARNAME)/version
-#	$(TAR) rf $(PERF_TARNAME).tar \
-#		$(PERF_TARNAME)/perf.spec \
-#		$(PERF_TARNAME)/configure \
-#		$(PERF_TARNAME)/version
-#	@$(RM) -r $(PERF_TARNAME)
-#	gzip -f -9 $(PERF_TARNAME).tar
-#
-# htmldocs = perf-htmldocs-$(PERF_VERSION)
-# manpages = perf-manpages-$(PERF_VERSION)
-# dist-doc:
-#	$(RM) -r .doc-tmp-dir
-#	mkdir .doc-tmp-dir
-#	$(MAKE) -C Documentation WEBDOC_DEST=../.doc-tmp-dir install-webdoc
-#	cd .doc-tmp-dir && $(TAR) cf ../$(htmldocs).tar .
-#	gzip -n -9 -f $(htmldocs).tar
-#	:
-#	$(RM) -r .doc-tmp-dir
-#	mkdir -p .doc-tmp-dir/man1 .doc-tmp-dir/man5 .doc-tmp-dir/man7
-#	$(MAKE) -C Documentation DESTDIR=./ \
-#		man1dir=../.doc-tmp-dir/man1 \
-#		man5dir=../.doc-tmp-dir/man5 \
-#		man7dir=../.doc-tmp-dir/man7 \
-#		install
-#	cd .doc-tmp-dir && $(TAR) cf ../$(manpages).tar .
-#	gzip -n -9 -f $(manpages).tar
-#	$(RM) -r .doc-tmp-dir
-#
-# rpm: dist
-#	$(RPMBUILD) -ta $(PERF_TARNAME).tar.gz
-
 ### Cleaning rules
 
-distclean: clean
-#	$(RM) configure
-
 clean:
-	$(RM) *.o */*.o */*/*.o */*/*/*.o $(LIB_FILE)
-	$(RM) $(ALL_PROGRAMS) $(BUILT_INS) perf$X
-	$(RM) $(TEST_PROGRAMS)
+	$(RM) $(OUTPUT){*.o,*/*.o,*/*/*.o,*/*/*/*.o,$(LIB_FILE),perf-archive}
+	$(RM) $(ALL_PROGRAMS) perf
 	$(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope*
-	$(RM) -r autom4te.cache
-	$(RM) config.log config.mak.autogen config.mak.append config.status config.cache
-	$(RM) -r $(PERF_TARNAME) .doc-tmp-dir
-	$(RM) $(PERF_TARNAME).tar.gz perf-core_$(PERF_VERSION)-*.tar.gz
-	$(RM) $(htmldocs).tar.gz $(manpages).tar.gz
 	$(MAKE) -C Documentation/ clean
-	$(RM) $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)PERF-CFLAGS $(OUTPUT)PERF-BUILD-OPTIONS
+	$(RM) $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)PERF-CFLAGS
+	@python util/setup.py clean --build-lib='$(OUTPUT)python' \
+				   --build-temp='$(OUTPUT)python/temp'
 
 .PHONY: all install clean strip
 .PHONY: shell_compatibility_test please_set_SHELL_PATH_to_a_more_modern_shell
 .PHONY: .FORCE-PERF-VERSION-FILE TAGS tags cscope .FORCE-PERF-CFLAGS
-.PHONY: .FORCE-PERF-BUILD-OPTIONS
-
-### Make sure built-ins do not have dups and listed in perf.c
-#
-check-builtins::
-	./check-builtins.sh
-
-### Test suite coverage testing
-#
-# None right now
-#
-# .PHONY: coverage coverage-clean coverage-build coverage-report
-#
-# coverage:
-#	$(MAKE) coverage-build
-#	$(MAKE) coverage-report
-#
-# coverage-clean:
-#	rm -f *.gcda *.gcno
-#
-# COVERAGE_CFLAGS = $(CFLAGS) -O0 -ftest-coverage -fprofile-arcs
-# COVERAGE_LDFLAGS = $(CFLAGS)  -O0 -lgcov
-#
-# coverage-build: coverage-clean
-#	$(MAKE) CFLAGS="$(COVERAGE_CFLAGS)" LDFLAGS="$(COVERAGE_LDFLAGS)" all
-#	$(MAKE) CFLAGS="$(COVERAGE_CFLAGS)" LDFLAGS="$(COVERAGE_LDFLAGS)" \
-#		-j1 test
-#
-# coverage-report:
-#	gcov -b *.c */*.c
-#	grep '^function.*called 0 ' *.c.gcov */*.c.gcov \
-#		| sed -e 's/\([^:]*\)\.gcov: *function \([^ ]*\) called.*/\1: \2/' \
-#		| tee coverage-untested-functions
diff --git a/tools/perf/bench/sched-pipe.c b/tools/perf/bench/sched-pipe.c
index d9ab3ce446ac..0c7454f8b8a9 100644
--- a/tools/perf/bench/sched-pipe.c
+++ b/tools/perf/bench/sched-pipe.c
@@ -55,7 +55,7 @@ int bench_sched_pipe(int argc, const char **argv,
 	 * discarding returned value of read(), write()
 	 * causes error in building environment for perf
 	 */
-	int ret, wait_stat;
+	int __used ret, wait_stat;
 	pid_t pid, retpid;
 
 	argc = parse_options(argc, argv, options,
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 8879463807e4..695de4b5ae63 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -9,6 +9,7 @@
 
 #include "util/util.h"
 
+#include "util/util.h"
 #include "util/color.h"
 #include <linux/list.h>
 #include "util/cache.h"
@@ -18,6 +19,9 @@
 #include "perf.h"
 #include "util/debug.h"
 
+#include "util/evlist.h"
+#include "util/evsel.h"
+#include "util/annotate.h"
 #include "util/event.h"
 #include "util/parse-options.h"
 #include "util/parse-events.h"
@@ -36,9 +40,13 @@ static bool		print_line;
 
 static const char *sym_hist_filter;
 
-static int hists__add_entry(struct hists *self, struct addr_location *al)
+static int perf_evlist__add_sample(struct perf_evlist *evlist,
+				   struct perf_sample *sample,
+				   struct addr_location *al)
 {
+	struct perf_evsel *evsel;
 	struct hist_entry *he;
+	int ret;
 
 	if (sym_hist_filter != NULL &&
 	    (al->sym == NULL || strcmp(sym_hist_filter, al->sym->name) != 0)) {
@@ -51,25 +59,51 @@ static int hists__add_entry(struct hists *self, struct addr_location *al)
 		return 0;
 	}
 
-	he = __hists__add_entry(self, al, NULL, 1);
+	evsel = perf_evlist__id2evsel(evlist, sample->id);
+	if (evsel == NULL) {
+		/*
+		 * FIXME: Propagate this back, but at least we're in a builtin,
+		 * where exit() is allowed. ;-)
+		 */
+		ui__warning("Invalid %s file, contains samples with id not in "
+			    "its header!\n", input_name);
+		exit_browser(0);
+		exit(1);
+	}
+
+	he = __hists__add_entry(&evsel->hists, al, NULL, 1);
 	if (he == NULL)
 		return -ENOMEM;
 
-	return hist_entry__inc_addr_samples(he, al->addr);
+	ret = 0;
+	if (he->ms.sym != NULL) {
+		struct annotation *notes = symbol__annotation(he->ms.sym);
+		if (notes->src == NULL &&
+		    symbol__alloc_hist(he->ms.sym, evlist->nr_entries) < 0)
+			return -ENOMEM;
+
+		ret = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
+	}
+
+	evsel->hists.stats.total_period += sample->period;
+	hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
+	return ret;
 }
 
-static int process_sample_event(event_t *event, struct sample_data *sample,
+static int process_sample_event(union perf_event *event,
+				struct perf_sample *sample,
 				struct perf_session *session)
 {
 	struct addr_location al;
 
-	if (event__preprocess_sample(event, session, &al, sample, NULL) < 0) {
+	if (perf_event__preprocess_sample(event, session, &al, sample,
+					  symbol__annotate_init) < 0) {
 		pr_warning("problem processing %d event, skipping it.\n",
 			   event->header.type);
 		return -1;
 	}
 
-	if (!al.filtered && hists__add_entry(&session->hists, &al)) {
+	if (!al.filtered && perf_evlist__add_sample(session->evlist, sample, &al)) {
 		pr_warning("problem incrementing symbol count, "
 			   "skipping event\n");
 		return -1;
@@ -78,261 +112,26 @@ static int process_sample_event(event_t *event, struct sample_data *sample,
 	return 0;
 }
 
-static int objdump_line__print(struct objdump_line *self,
-			       struct list_head *head,
-			       struct hist_entry *he, u64 len)
-{
-	struct symbol *sym = he->ms.sym;
-	static const char *prev_line;
-	static const char *prev_color;
-
-	if (self->offset != -1) {
-		const char *path = NULL;
-		unsigned int hits = 0;
-		double percent = 0.0;
-		const char *color;
-		struct sym_priv *priv = symbol__priv(sym);
-		struct sym_ext *sym_ext = priv->ext;
-		struct sym_hist *h = priv->hist;
-		s64 offset = self->offset;
-		struct objdump_line *next = objdump__get_next_ip_line(head, self);
-
-		while (offset < (s64)len &&
-		       (next == NULL || offset < next->offset)) {
-			if (sym_ext) {
-				if (path == NULL)
-					path = sym_ext[offset].path;
-				percent += sym_ext[offset].percent;
-			} else
-				hits += h->ip[offset];
-
-			++offset;
-		}
-
-		if (sym_ext == NULL && h->sum)
-			percent = 100.0 * hits / h->sum;
-
-		color = get_percent_color(percent);
-
-		/*
-		 * Also color the filename and line if needed, with
-		 * the same color than the percentage. Don't print it
-		 * twice for close colored ip with the same filename:line
-		 */
-		if (path) {
-			if (!prev_line || strcmp(prev_line, path)
-				       || color != prev_color) {
-				color_fprintf(stdout, color, " %s", path);
-				prev_line = path;
-				prev_color = color;
-			}
-		}
-
-		color_fprintf(stdout, color, " %7.2f", percent);
-		printf(" :	");
-		color_fprintf(stdout, PERF_COLOR_BLUE, "%s\n", self->line);
-	} else {
-		if (!*self->line)
-			printf("         :\n");
-		else
-			printf("         :	%s\n", self->line);
-	}
-
-	return 0;
-}
-
-static struct rb_root root_sym_ext;
-
-static void insert_source_line(struct sym_ext *sym_ext)
-{
-	struct sym_ext *iter;
-	struct rb_node **p = &root_sym_ext.rb_node;
-	struct rb_node *parent = NULL;
-
-	while (*p != NULL) {
-		parent = *p;
-		iter = rb_entry(parent, struct sym_ext, node);
-
-		if (sym_ext->percent > iter->percent)
-			p = &(*p)->rb_left;
-		else
-			p = &(*p)->rb_right;
-	}
-
-	rb_link_node(&sym_ext->node, parent, p);
-	rb_insert_color(&sym_ext->node, &root_sym_ext);
-}
-
-static void free_source_line(struct hist_entry *he, int len)
-{
-	struct sym_priv *priv = symbol__priv(he->ms.sym);
-	struct sym_ext *sym_ext = priv->ext;
-	int i;
-
-	if (!sym_ext)
-		return;
-
-	for (i = 0; i < len; i++)
-		free(sym_ext[i].path);
-	free(sym_ext);
-
-	priv->ext = NULL;
-	root_sym_ext = RB_ROOT;
-}
-
-/* Get the filename:line for the colored entries */
-static void
-get_source_line(struct hist_entry *he, int len, const char *filename)
-{
-	struct symbol *sym = he->ms.sym;
-	u64 start;
-	int i;
-	char cmd[PATH_MAX * 2];
-	struct sym_ext *sym_ext;
-	struct sym_priv *priv = symbol__priv(sym);
-	struct sym_hist *h = priv->hist;
-
-	if (!h->sum)
-		return;
-
-	sym_ext = priv->ext = calloc(len, sizeof(struct sym_ext));
-	if (!priv->ext)
-		return;
-
-	start = he->ms.map->unmap_ip(he->ms.map, sym->start);
-
-	for (i = 0; i < len; i++) {
-		char *path = NULL;
-		size_t line_len;
-		u64 offset;
-		FILE *fp;
-
-		sym_ext[i].percent = 100.0 * h->ip[i] / h->sum;
-		if (sym_ext[i].percent <= 0.5)
-			continue;
-
-		offset = start + i;
-		sprintf(cmd, "addr2line -e %s %016" PRIx64, filename, offset);
-		fp = popen(cmd, "r");
-		if (!fp)
-			continue;
-
-		if (getline(&path, &line_len, fp) < 0 || !line_len)
-			goto next;
-
-		sym_ext[i].path = malloc(sizeof(char) * line_len + 1);
-		if (!sym_ext[i].path)
-			goto next;
-
-		strcpy(sym_ext[i].path, path);
-		insert_source_line(&sym_ext[i]);
-
-	next:
-		pclose(fp);
-	}
-}
-
-static void print_summary(const char *filename)
-{
-	struct sym_ext *sym_ext;
-	struct rb_node *node;
-
-	printf("\nSorted summary for file %s\n", filename);
-	printf("----------------------------------------------\n\n");
-
-	if (RB_EMPTY_ROOT(&root_sym_ext)) {
-		printf(" Nothing higher than %1.1f%%\n", MIN_GREEN);
-		return;
-	}
-
-	node = rb_first(&root_sym_ext);
-	while (node) {
-		double percent;
-		const char *color;
-		char *path;
-
-		sym_ext = rb_entry(node, struct sym_ext, node);
-		percent = sym_ext->percent;
-		color = get_percent_color(percent);
-		path = sym_ext->path;
-
-		color_fprintf(stdout, color, " %7.2f %s", percent, path);
-		node = rb_next(node);
-	}
-}
-
-static void hist_entry__print_hits(struct hist_entry *self)
-{
-	struct symbol *sym = self->ms.sym;
-	struct sym_priv *priv = symbol__priv(sym);
-	struct sym_hist *h = priv->hist;
-	u64 len = sym->end - sym->start, offset;
-
-	for (offset = 0; offset < len; ++offset)
-		if (h->ip[offset] != 0)
-			printf("%*" PRIx64 ": %" PRIu64 "\n", BITS_PER_LONG / 2,
-			       sym->start + offset, h->ip[offset]);
-	printf("%*s: %" PRIu64 "\n", BITS_PER_LONG / 2, "h->sum", h->sum);
-}
-
-static int hist_entry__tty_annotate(struct hist_entry *he)
+static int hist_entry__tty_annotate(struct hist_entry *he, int evidx)
 {
-	struct map *map = he->ms.map;
-	struct dso *dso = map->dso;
-	struct symbol *sym = he->ms.sym;
-	const char *filename = dso->long_name, *d_filename;
-	u64 len;
-	LIST_HEAD(head);
-	struct objdump_line *pos, *n;
-
-	if (hist_entry__annotate(he, &head, 0) < 0)
-		return -1;
-
-	if (full_paths)
-		d_filename = filename;
-	else
-		d_filename = basename(filename);
-
-	len = sym->end - sym->start;
-
-	if (print_line) {
-		get_source_line(he, len, filename);
-		print_summary(filename);
-	}
-
-	printf("\n\n------------------------------------------------\n");
-	printf(" Percent |	Source code & Disassembly of %s\n", d_filename);
-	printf("------------------------------------------------\n");
-
-	if (verbose)
-		hist_entry__print_hits(he);
-
-	list_for_each_entry_safe(pos, n, &head, node) {
-		objdump_line__print(pos, &head, he, len);
-		list_del(&pos->node);
-		objdump_line__free(pos);
-	}
-
-	if (print_line)
-		free_source_line(he, len);
-
-	return 0;
+	return symbol__tty_annotate(he->ms.sym, he->ms.map, evidx,
+				    print_line, full_paths, 0, 0);
 }
 
-static void hists__find_annotations(struct hists *self)
+static void hists__find_annotations(struct hists *self, int evidx)
 {
 	struct rb_node *nd = rb_first(&self->entries), *next;
 	int key = KEY_RIGHT;
 
 	while (nd) {
 		struct hist_entry *he = rb_entry(nd, struct hist_entry, rb_node);
-		struct sym_priv *priv;
+		struct annotation *notes;
 
 		if (he->ms.sym == NULL || he->ms.map->dso->annotate_warned)
 			goto find_next;
 
-		priv = symbol__priv(he->ms.sym);
-		if (priv->hist == NULL) {
+		notes = symbol__annotation(he->ms.sym);
+		if (notes->src == NULL) {
 find_next:
 			if (key == KEY_LEFT)
 				nd = rb_prev(nd);
@@ -342,7 +141,7 @@ find_next:
 		}
 
 		if (use_browser > 0) {
-			key = hist_entry__tui_annotate(he);
+			key = hist_entry__tui_annotate(he, evidx);
 			switch (key) {
 			case KEY_RIGHT:
 				next = rb_next(nd);
@@ -357,24 +156,24 @@ find_next:
 			if (next != NULL)
 				nd = next;
 		} else {
-			hist_entry__tty_annotate(he);
+			hist_entry__tty_annotate(he, evidx);
 			nd = rb_next(nd);
 			/*
 			 * Since we have a hist_entry per IP for the same
-			 * symbol, free he->ms.sym->hist to signal we already
+			 * symbol, free he->ms.sym->src to signal we already
 			 * processed this symbol.
 			 */
-			free(priv->hist);
-			priv->hist = NULL;
+			free(notes->src);
+			notes->src = NULL;
 		}
 	}
 }
 
 static struct perf_event_ops event_ops = {
 	.sample	= process_sample_event,
-	.mmap	= event__process_mmap,
-	.comm	= event__process_comm,
-	.fork	= event__process_task,
+	.mmap	= perf_event__process_mmap,
+	.comm	= perf_event__process_comm,
+	.fork	= perf_event__process_task,
 	.ordered_samples = true,
 	.ordering_requires_timestamps = true,
 };
@@ -383,6 +182,8 @@ static int __cmd_annotate(void)
 {
 	int ret;
 	struct perf_session *session;
+	struct perf_evsel *pos;
+	u64 total_nr_samples;
 
 	session = perf_session__new(input_name, O_RDONLY, force, false, &event_ops);
 	if (session == NULL)
@@ -403,12 +204,36 @@ static int __cmd_annotate(void)
 	if (verbose > 2)
 		perf_session__fprintf_dsos(session, stdout);
 
-	hists__collapse_resort(&session->hists);
-	hists__output_resort(&session->hists);
-	hists__find_annotations(&session->hists);
-out_delete:
-	perf_session__delete(session);
+	total_nr_samples = 0;
+	list_for_each_entry(pos, &session->evlist->entries, node) {
+		struct hists *hists = &pos->hists;
+		u32 nr_samples = hists->stats.nr_events[PERF_RECORD_SAMPLE];
+
+		if (nr_samples > 0) {
+			total_nr_samples += nr_samples;
+			hists__collapse_resort(hists);
+			hists__output_resort(hists);
+			hists__find_annotations(hists, pos->idx);
+		}
+	}
 
+	if (total_nr_samples == 0) {
+		ui__warning("The %s file has no samples!\n", input_name);
+		goto out_delete;
+	}
+out_delete:
+	/*
+	 * Speed up the exit process, for large files this can
+	 * take quite a while.
+	 *
+	 * XXX Enable this when using valgrind or if we ever
+	 * librarize this command.
+	 *
+	 * Also experiment with obstacks to see how much speed
+	 * up we'll get here.
+	 *
+	 * perf_session__delete(session);
+	 */
 	return ret;
 }
 
@@ -451,9 +276,9 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __used)
 	else if (use_tui)
 		use_browser = 1;
 
-	setup_browser();
+	setup_browser(true);
 
-	symbol_conf.priv_size = sizeof(struct sym_priv);
+	symbol_conf.priv_size = sizeof(struct annotation);
 	symbol_conf.try_vmlinux_path = true;
 
 	if (symbol__init() < 0)
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 3153e492dbcc..6b7d91160ecb 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -30,13 +30,13 @@ static int hists__add_entry(struct hists *self,
 	return -ENOMEM;
 }
 
-static int diff__process_sample_event(event_t *event,
-				      struct sample_data *sample,
+static int diff__process_sample_event(union perf_event *event,
+				      struct perf_sample *sample,
 				      struct perf_session *session)
 {
 	struct addr_location al;
 
-	if (event__preprocess_sample(event, session, &al, sample, NULL) < 0) {
+	if (perf_event__preprocess_sample(event, session, &al, sample, NULL) < 0) {
 		pr_warning("problem processing %d event, skipping it.\n",
 			   event->header.type);
 		return -1;
@@ -56,11 +56,11 @@ static int diff__process_sample_event(event_t *event,
 
 static struct perf_event_ops event_ops = {
 	.sample	= diff__process_sample_event,
-	.mmap	= event__process_mmap,
-	.comm	= event__process_comm,
-	.exit	= event__process_task,
-	.fork	= event__process_task,
-	.lost	= event__process_lost,
+	.mmap	= perf_event__process_mmap,
+	.comm	= perf_event__process_comm,
+	.exit	= perf_event__process_task,
+	.fork	= perf_event__process_task,
+	.lost	= perf_event__process_lost,
 	.ordered_samples = true,
 	.ordering_requires_timestamps = true,
 };
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 0c78ffa7bf67..e29f04ed3396 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -16,8 +16,8 @@
 static char		const *input_name = "-";
 static bool		inject_build_ids;
 
-static int event__repipe_synth(event_t *event,
-			       struct perf_session *session __used)
+static int perf_event__repipe_synth(union perf_event *event,
+				    struct perf_session *session __used)
 {
 	uint32_t size;
 	void *buf = event;
@@ -36,41 +36,44 @@ static int event__repipe_synth(event_t *event,
 	return 0;
 }
 
-static int event__repipe(event_t *event, struct sample_data *sample __used,
-			 struct perf_session *session)
+static int perf_event__repipe(union perf_event *event,
+			      struct perf_sample *sample __used,
+			      struct perf_session *session)
 {
-	return event__repipe_synth(event, session);
+	return perf_event__repipe_synth(event, session);
 }
 
-static int event__repipe_mmap(event_t *self, struct sample_data *sample,
-			      struct perf_session *session)
+static int perf_event__repipe_mmap(union perf_event *event,
+				   struct perf_sample *sample,
+				   struct perf_session *session)
 {
 	int err;
 
-	err = event__process_mmap(self, sample, session);
-	event__repipe(self, sample, session);
+	err = perf_event__process_mmap(event, sample, session);
+	perf_event__repipe(event, sample, session);
 
 	return err;
 }
 
-static int event__repipe_task(event_t *self, struct sample_data *sample,
-			      struct perf_session *session)
+static int perf_event__repipe_task(union perf_event *event,
+				   struct perf_sample *sample,
+				   struct perf_session *session)
 {
 	int err;
 
-	err = event__process_task(self, sample, session);
-	event__repipe(self, sample, session);
+	err = perf_event__process_task(event, sample, session);
+	perf_event__repipe(event, sample, session);
 
 	return err;
 }
 
-static int event__repipe_tracing_data(event_t *self,
-				      struct perf_session *session)
+static int perf_event__repipe_tracing_data(union perf_event *event,
+					   struct perf_session *session)
 {
 	int err;
 
-	event__repipe_synth(self, session);
-	err = event__process_tracing_data(self, session);
+	perf_event__repipe_synth(event, session);
+	err = perf_event__process_tracing_data(event, session);
 
 	return err;
 }
@@ -109,8 +112,8 @@ static int dso__inject_build_id(struct dso *self, struct perf_session *session)
 	if (self->kernel)
 		misc = PERF_RECORD_MISC_KERNEL;
 
-	err = event__synthesize_build_id(self, misc, event__repipe,
-					 machine, session);
+	err = perf_event__synthesize_build_id(self, misc, perf_event__repipe,
+					      machine, session);
 	if (err) {
 		pr_err("Can't synthesize build_id event for %s\n", self->long_name);
 		return -1;
@@ -119,8 +122,9 @@ static int dso__inject_build_id(struct dso *self, struct perf_session *session)
 	return 0;
 }
 
-static int event__inject_buildid(event_t *event, struct sample_data *sample,
-				 struct perf_session *session)
+static int perf_event__inject_buildid(union perf_event *event,
+				      struct perf_sample *sample,
+				      struct perf_session *session)
 {
 	struct addr_location al;
 	struct thread *thread;
@@ -155,24 +159,24 @@ static int event__inject_buildid(event_t *event, struct sample_data *sample,
 	}
 
 repipe:
-	event__repipe(event, sample, session);
+	perf_event__repipe(event, sample, session);
 	return 0;
 }
 
 struct perf_event_ops inject_ops = {
-	.sample		= event__repipe,
-	.mmap		= event__repipe,
-	.comm		= event__repipe,
-	.fork		= event__repipe,
-	.exit		= event__repipe,
-	.lost		= event__repipe,
-	.read		= event__repipe,
-	.throttle	= event__repipe,
-	.unthrottle	= event__repipe,
-	.attr		= event__repipe_synth,
-	.event_type 	= event__repipe_synth,
-	.tracing_data 	= event__repipe_synth,
-	.build_id 	= event__repipe_synth,
+	.sample		= perf_event__repipe,
+	.mmap		= perf_event__repipe,
+	.comm		= perf_event__repipe,
+	.fork		= perf_event__repipe,
+	.exit		= perf_event__repipe,
+	.lost		= perf_event__repipe,
+	.read		= perf_event__repipe,
+	.throttle	= perf_event__repipe,
+	.unthrottle	= perf_event__repipe,
+	.attr		= perf_event__repipe_synth,
+	.event_type 	= perf_event__repipe_synth,
+	.tracing_data 	= perf_event__repipe_synth,
+	.build_id 	= perf_event__repipe_synth,
 };
 
 extern volatile int session_done;
@@ -190,10 +194,10 @@ static int __cmd_inject(void)
 	signal(SIGINT, sig_handler);
 
 	if (inject_build_ids) {
-		inject_ops.sample	= event__inject_buildid;
-		inject_ops.mmap		= event__repipe_mmap;
-		inject_ops.fork		= event__repipe_task;
-		inject_ops.tracing_data	= event__repipe_tracing_data;
+		inject_ops.sample	= perf_event__inject_buildid;
+		inject_ops.mmap		= perf_event__repipe_mmap;
+		inject_ops.fork		= perf_event__repipe_task;
+		inject_ops.tracing_data	= perf_event__repipe_tracing_data;
 	}
 
 	session = perf_session__new(input_name, O_RDONLY, false, true, &inject_ops);
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index d97256d65980..7f618f4e7b79 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -275,9 +275,8 @@ static void process_free_event(void *data,
 	s_alloc->alloc_cpu = -1;
 }
 
-static void
-process_raw_event(event_t *raw_event __used, void *data,
-		  int cpu, u64 timestamp, struct thread *thread)
+static void process_raw_event(union perf_event *raw_event __used, void *data,
+			      int cpu, u64 timestamp, struct thread *thread)
 {
 	struct event *event;
 	int type;
@@ -304,7 +303,8 @@ process_raw_event(event_t *raw_event __used, void *data,
 	}
 }
 
-static int process_sample_event(event_t *event, struct sample_data *sample,
+static int process_sample_event(union perf_event *event,
+				struct perf_sample *sample,
 				struct perf_session *session)
 {
 	struct thread *thread = perf_session__findnew(session, event->ip.pid);
@@ -325,7 +325,7 @@ static int process_sample_event(event_t *event, struct sample_data *sample,
 
 static struct perf_event_ops event_ops = {
 	.sample			= process_sample_event,
-	.comm			= event__process_comm,
+	.comm			= perf_event__process_comm,
 	.ordered_samples	= true,
 };
 
diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
index d88c6961274c..6313b6eb3ebb 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -5,6 +5,7 @@
  *
  * Copyright (C) 2009, Thomas Gleixner <tglx@linutronix.de>
  * Copyright (C) 2008-2009, Red Hat Inc, Ingo Molnar <mingo@redhat.com>
+ * Copyright (C) 2011, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
  */
 #include "builtin.h"
 
@@ -13,9 +14,47 @@
 #include "util/parse-events.h"
 #include "util/cache.h"
 
-int cmd_list(int argc __used, const char **argv __used, const char *prefix __used)
+int cmd_list(int argc, const char **argv, const char *prefix __used)
 {
 	setup_pager();
-	print_events();
+
+	if (argc == 1)
+		print_events(NULL);
+	else {
+		int i;
+
+		for (i = 1; i < argc; ++i) {
+			if (i > 1)
+				putchar('\n');
+			if (strncmp(argv[i], "tracepoint", 10) == 0)
+				print_tracepoint_events(NULL, NULL);
+			else if (strcmp(argv[i], "hw") == 0 ||
+				 strcmp(argv[i], "hardware") == 0)
+				print_events_type(PERF_TYPE_HARDWARE);
+			else if (strcmp(argv[i], "sw") == 0 ||
+				 strcmp(argv[i], "software") == 0)
+				print_events_type(PERF_TYPE_SOFTWARE);
+			else if (strcmp(argv[i], "cache") == 0 ||
+				 strcmp(argv[i], "hwcache") == 0)
+				print_hwcache_events(NULL);
+			else {
+				char *sep = strchr(argv[i], ':'), *s;
+				int sep_idx;
+
+				if (sep == NULL) {
+					print_events(argv[i]);
+					continue;
+				}
+				sep_idx = sep - argv[i];
+				s = strdup(argv[i]);
+				if (s == NULL)
+					return -1;
+
+				s[sep_idx] = '\0';
+				print_tracepoint_events(s, s + sep_idx + 1);
+				free(s);
+			}
+		}
+	}
 	return 0;
 }
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index 2b36defc5d73..2e93f99b1480 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -834,14 +834,14 @@ static void dump_info(void)
 		die("Unknown type of information\n");
 }
 
-static int process_sample_event(event_t *self, struct sample_data *sample,
+static int process_sample_event(union perf_event *event, struct perf_sample *sample,
 				struct perf_session *s)
 {
 	struct thread *thread = perf_session__findnew(s, sample->tid);
 
 	if (thread == NULL) {
 		pr_debug("problem processing %d event, skipping it.\n",
-			self->header.type);
+			event->header.type);
 		return -1;
 	}
 
@@ -852,7 +852,7 @@ static int process_sample_event(event_t *self, struct sample_data *sample,
 
 static struct perf_event_ops eops = {
 	.sample			= process_sample_event,
-	.comm			= event__process_comm,
+	.comm			= perf_event__process_comm,
 	.ordered_samples	= true,
 };
 
@@ -893,7 +893,7 @@ static const char * const report_usage[] = {
 
 static const struct option report_options[] = {
 	OPT_STRING('k', "key", &sort_key, "acquired",
-		    "key for sorting"),
+		    "key for sorting (acquired / contended / wait_total / wait_max / wait_min)"),
 	/* TODO: type */
 	OPT_END()
 };
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index add163c9f0e7..2c0e64d0b4aa 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -36,6 +36,7 @@
 #include "builtin.h"
 #include "util/util.h"
 #include "util/strlist.h"
+#include "util/strfilter.h"
 #include "util/symbol.h"
 #include "util/debug.h"
 #include "util/debugfs.h"
@@ -43,6 +44,8 @@
 #include "util/probe-finder.h"
 #include "util/probe-event.h"
 
+#define DEFAULT_VAR_FILTER "!__k???tab_* & !__crc_*"
+#define DEFAULT_FUNC_FILTER "!_*"
 #define MAX_PATH_LEN 256
 
 /* Session management structure */
@@ -52,6 +55,7 @@ static struct {
 	bool show_lines;
 	bool show_vars;
 	bool show_ext_vars;
+	bool show_funcs;
 	bool mod_events;
 	int nevents;
 	struct perf_probe_event events[MAX_PROBES];
@@ -59,6 +63,7 @@ static struct {
 	struct line_range line_range;
 	const char *target_module;
 	int max_probe_points;
+	struct strfilter *filter;
 } params;
 
 /* Parse an event definition. Note that any error must die. */
@@ -157,6 +162,27 @@ static int opt_show_vars(const struct option *opt __used,
 }
 #endif
 
+static int opt_set_filter(const struct option *opt __used,
+			  const char *str, int unset __used)
+{
+	const char *err;
+
+	if (str) {
+		pr_debug2("Set filter: %s\n", str);
+		if (params.filter)
+			strfilter__delete(params.filter);
+		params.filter = strfilter__new(str, &err);
+		if (!params.filter) {
+			pr_err("Filter parse error at %td.\n", err - str + 1);
+			pr_err("Source: \"%s\"\n", str);
+			pr_err("         %*c\n", (int)(err - str + 1), '^');
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
 static const char * const probe_usage[] = {
 	"perf probe [<options>] 'PROBEDEF' ['PROBEDEF' ...]",
 	"perf probe [<options>] --add 'PROBEDEF' [--add 'PROBEDEF' ...]",
@@ -221,6 +247,13 @@ static const struct option options[] = {
 	OPT__DRY_RUN(&probe_event_dry_run),
 	OPT_INTEGER('\0', "max-probes", &params.max_probe_points,
 		 "Set how many probe points can be found for a probe."),
+	OPT_BOOLEAN('F', "funcs", &params.show_funcs,
+		    "Show potential probe-able functions."),
+	OPT_CALLBACK('\0', "filter", NULL,
+		     "[!]FILTER", "Set a filter (with --vars/funcs only)\n"
+		     "\t\t\t(default: \"" DEFAULT_VAR_FILTER "\" for --vars,\n"
+		     "\t\t\t \"" DEFAULT_FUNC_FILTER "\" for --funcs)",
+		     opt_set_filter),
 	OPT_END()
 };
 
@@ -246,7 +279,7 @@ int cmd_probe(int argc, const char **argv, const char *prefix __used)
 		params.max_probe_points = MAX_PROBES;
 
 	if ((!params.nevents && !params.dellist && !params.list_events &&
-	     !params.show_lines))
+	     !params.show_lines && !params.show_funcs))
 		usage_with_options(probe_usage, options);
 
 	/*
@@ -267,12 +300,41 @@ int cmd_probe(int argc, const char **argv, const char *prefix __used)
 			pr_err(" Error: Don't use --list with --vars.\n");
 			usage_with_options(probe_usage, options);
 		}
+		if (params.show_funcs) {
+			pr_err("  Error: Don't use --list with --funcs.\n");
+			usage_with_options(probe_usage, options);
+		}
 		ret = show_perf_probe_events();
 		if (ret < 0)
 			pr_err("  Error: Failed to show event list. (%d)\n",
 			       ret);
 		return ret;
 	}
+	if (params.show_funcs) {
+		if (params.nevents != 0 || params.dellist) {
+			pr_err("  Error: Don't use --funcs with"
+			       " --add/--del.\n");
+			usage_with_options(probe_usage, options);
+		}
+		if (params.show_lines) {
+			pr_err("  Error: Don't use --funcs with --line.\n");
+			usage_with_options(probe_usage, options);
+		}
+		if (params.show_vars) {
+			pr_err("  Error: Don't use --funcs with --vars.\n");
+			usage_with_options(probe_usage, options);
+		}
+		if (!params.filter)
+			params.filter = strfilter__new(DEFAULT_FUNC_FILTER,
+						       NULL);
+		ret = show_available_funcs(params.target_module,
+					   params.filter);
+		strfilter__delete(params.filter);
+		if (ret < 0)
+			pr_err("  Error: Failed to show functions."
+			       " (%d)\n", ret);
+		return ret;
+	}
 
 #ifdef DWARF_SUPPORT
 	if (params.show_lines) {
@@ -297,10 +359,16 @@ int cmd_probe(int argc, const char **argv, const char *prefix __used)
 			       " --add/--del.\n");
 			usage_with_options(probe_usage, options);
 		}
+		if (!params.filter)
+			params.filter = strfilter__new(DEFAULT_VAR_FILTER,
+						       NULL);
+
 		ret = show_available_vars(params.events, params.nevents,
 					  params.max_probe_points,
 					  params.target_module,
+					  params.filter,
 					  params.show_ext_vars);
+		strfilter__delete(params.filter);
 		if (ret < 0)
 			pr_err("  Error: Failed to show vars. (%d)\n", ret);
 		return ret;
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 60cac6f92e8b..6febcc168a8c 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -18,11 +18,13 @@
 
 #include "util/header.h"
 #include "util/event.h"
+#include "util/evlist.h"
 #include "util/evsel.h"
 #include "util/debug.h"
 #include "util/session.h"
 #include "util/symbol.h"
 #include "util/cpumap.h"
+#include "util/thread_map.h"
 
 #include <unistd.h>
 #include <sched.h>
@@ -37,16 +39,14 @@ enum write_mode_t {
 
 static u64			user_interval			= ULLONG_MAX;
 static u64			default_interval		=      0;
-static u64			sample_type;
 
-static struct cpu_map		*cpus;
 static unsigned int		page_size;
 static unsigned int		mmap_pages			=    128;
 static unsigned int		user_freq 			= UINT_MAX;
 static int			freq				=   1000;
 static int			output;
 static int			pipe_output			=      0;
-static const char		*output_name			= "perf.data";
+static const char		*output_name			= NULL;
 static int			group				=      0;
 static int			realtime_prio			=      0;
 static bool			nodelay				=  false;
@@ -55,7 +55,6 @@ static bool			sample_id_all_avail		=   true;
 static bool			system_wide			=  false;
 static pid_t			target_pid			=     -1;
 static pid_t			target_tid			=     -1;
-static struct thread_map	*threads;
 static pid_t			child_pid			=     -1;
 static bool			no_inherit			=  false;
 static enum write_mode_t	write_mode			= WRITE_FORCE;
@@ -66,51 +65,17 @@ static bool			sample_address			=  false;
 static bool			sample_time			=  false;
 static bool			no_buildid			=  false;
 static bool			no_buildid_cache		=  false;
+static struct perf_evlist	*evsel_list;
 
 static long			samples				=      0;
 static u64			bytes_written			=      0;
 
-static struct pollfd		*event_array;
-
-static int			nr_poll				=      0;
-static int			nr_cpu				=      0;
-
 static int			file_new			=      1;
 static off_t			post_processing_offset;
 
 static struct perf_session	*session;
 static const char		*cpu_list;
 
-struct mmap_data {
-	void			*base;
-	unsigned int		mask;
-	unsigned int		prev;
-};
-
-static struct mmap_data		mmap_array[MAX_NR_CPUS];
-
-static unsigned long mmap_read_head(struct mmap_data *md)
-{
-	struct perf_event_mmap_page *pc = md->base;
-	long head;
-
-	head = pc->data_head;
-	rmb();
-
-	return head;
-}
-
-static void mmap_write_tail(struct mmap_data *md, unsigned long tail)
-{
-	struct perf_event_mmap_page *pc = md->base;
-
-	/*
-	 * ensure all reads are done before we write the tail out.
-	 */
-	/* mb(); */
-	pc->data_tail = tail;
-}
-
 static void advance_output(size_t size)
 {
 	bytes_written += size;
@@ -131,42 +96,26 @@ static void write_output(void *buf, size_t size)
 	}
 }
 
-static int process_synthesized_event(event_t *event,
-				     struct sample_data *sample __used,
+static int process_synthesized_event(union perf_event *event,
+				     struct perf_sample *sample __used,
 				     struct perf_session *self __used)
 {
 	write_output(event, event->header.size);
 	return 0;
 }
 
-static void mmap_read(struct mmap_data *md)
+static void mmap_read(struct perf_mmap *md)
 {
-	unsigned int head = mmap_read_head(md);
+	unsigned int head = perf_mmap__read_head(md);
 	unsigned int old = md->prev;
 	unsigned char *data = md->base + page_size;
 	unsigned long size;
 	void *buf;
-	int diff;
 
-	/*
-	 * If we're further behind than half the buffer, there's a chance
-	 * the writer will bite our tail and mess up the samples under us.
-	 *
-	 * If we somehow ended up ahead of the head, we got messed up.
-	 *
-	 * In either case, truncate and restart at head.
-	 */
-	diff = head - old;
-	if (diff < 0) {
-		fprintf(stderr, "WARNING: failed to keep up with mmap data\n");
-		/*
-		 * head points to a known good entry, start there.
-		 */
-		old = head;
-	}
+	if (old == head)
+		return;
 
-	if (old != head)
-		samples++;
+	samples++;
 
 	size = head - old;
 
@@ -185,7 +134,7 @@ static void mmap_read(struct mmap_data *md)
 	write_output(buf, size);
 
 	md->prev = old;
-	mmap_write_tail(md, old);
+	perf_mmap__write_tail(md, old);
 }
 
 static volatile int done = 0;
@@ -209,53 +158,10 @@ static void sig_atexit(void)
 	kill(getpid(), signr);
 }
 
-static int group_fd;
-
-static struct perf_header_attr *get_header_attr(struct perf_event_attr *a, int nr)
-{
-	struct perf_header_attr *h_attr;
-
-	if (nr < session->header.attrs) {
-		h_attr = session->header.attr[nr];
-	} else {
-		h_attr = perf_header_attr__new(a);
-		if (h_attr != NULL)
-			if (perf_header__add_attr(&session->header, h_attr) < 0) {
-				perf_header_attr__delete(h_attr);
-				h_attr = NULL;
-			}
-	}
-
-	return h_attr;
-}
-
-static void create_counter(struct perf_evsel *evsel, int cpu)
+static void config_attr(struct perf_evsel *evsel, struct perf_evlist *evlist)
 {
-	char *filter = evsel->filter;
 	struct perf_event_attr *attr = &evsel->attr;
-	struct perf_header_attr *h_attr;
 	int track = !evsel->idx; /* only the first counter needs these */
-	int thread_index;
-	int ret;
-	struct {
-		u64 count;
-		u64 time_enabled;
-		u64 time_running;
-		u64 id;
-	} read_data;
-	/*
- 	 * Check if parse_single_tracepoint_event has already asked for
- 	 * PERF_SAMPLE_TIME.
- 	 *
-	 * XXX this is kludgy but short term fix for problems introduced by
-	 * eac23d1c that broke 'perf script' by having different sample_types
-	 * when using multiple tracepoint events when we use a perf binary
-	 * that tries to use sample_id_all on an older kernel.
- 	 *
- 	 * We need to move counter creation to perf_session, support
- 	 * different sample_types, etc.
- 	 */
-	bool time_needed = attr->sample_type & PERF_SAMPLE_TIME;
 
 	attr->read_format	= PERF_FORMAT_TOTAL_TIME_ENABLED |
 				  PERF_FORMAT_TOTAL_TIME_RUNNING |
@@ -263,7 +169,7 @@ static void create_counter(struct perf_evsel *evsel, int cpu)
 
 	attr->sample_type	|= PERF_SAMPLE_IP | PERF_SAMPLE_TID;
 
-	if (nr_counters > 1)
+	if (evlist->nr_entries > 1)
 		attr->sample_type |= PERF_SAMPLE_ID;
 
 	/*
@@ -315,19 +221,58 @@ static void create_counter(struct perf_evsel *evsel, int cpu)
 
 	attr->mmap		= track;
 	attr->comm		= track;
-	attr->inherit		= !no_inherit;
+
 	if (target_pid == -1 && target_tid == -1 && !system_wide) {
 		attr->disabled = 1;
 		attr->enable_on_exec = 1;
 	}
-retry_sample_id:
-	attr->sample_id_all = sample_id_all_avail ? 1 : 0;
+}
 
-	for (thread_index = 0; thread_index < threads->nr; thread_index++) {
-try_again:
-		FD(evsel, nr_cpu, thread_index) = sys_perf_event_open(attr, threads->map[thread_index], cpu, group_fd, 0);
+static bool perf_evlist__equal(struct perf_evlist *evlist,
+			       struct perf_evlist *other)
+{
+	struct perf_evsel *pos, *pair;
+
+	if (evlist->nr_entries != other->nr_entries)
+		return false;
+
+	pair = list_entry(other->entries.next, struct perf_evsel, node);
 
-		if (FD(evsel, nr_cpu, thread_index) < 0) {
+	list_for_each_entry(pos, &evlist->entries, node) {
+		if (memcmp(&pos->attr, &pair->attr, sizeof(pos->attr) != 0))
+			return false;
+		pair = list_entry(pair->node.next, struct perf_evsel, node);
+	}
+
+	return true;
+}
+
+static void open_counters(struct perf_evlist *evlist)
+{
+	struct perf_evsel *pos;
+
+	list_for_each_entry(pos, &evlist->entries, node) {
+		struct perf_event_attr *attr = &pos->attr;
+		/*
+		 * Check if parse_single_tracepoint_event has already asked for
+		 * PERF_SAMPLE_TIME.
+		 *
+		 * XXX this is kludgy but short term fix for problems introduced by
+		 * eac23d1c that broke 'perf script' by having different sample_types
+		 * when using multiple tracepoint events when we use a perf binary
+		 * that tries to use sample_id_all on an older kernel.
+		 *
+		 * We need to move counter creation to perf_session, support
+		 * different sample_types, etc.
+		 */
+		bool time_needed = attr->sample_type & PERF_SAMPLE_TIME;
+
+		config_attr(pos, evlist);
+retry_sample_id:
+		attr->sample_id_all = sample_id_all_avail ? 1 : 0;
+try_again:
+		if (perf_evsel__open(pos, evlist->cpus, evlist->threads, group,
+				     !no_inherit) < 0) {
 			int err = errno;
 
 			if (err == EPERM || err == EACCES)
@@ -364,7 +309,7 @@ try_again:
 			}
 			printf("\n");
 			error("sys_perf_event_open() syscall returned with %d (%s).  /bin/dmesg may provide additional information.\n",
-			      FD(evsel, nr_cpu, thread_index), strerror(err));
+			      err, strerror(err));
 
 #if defined(__i386__) || defined(__x86_64__)
 			if (attr->type == PERF_TYPE_HARDWARE && err == EOPNOTSUPP)
@@ -375,90 +320,28 @@ try_again:
 #endif
 
 			die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
-			exit(-1);
 		}
+	}
 
-		h_attr = get_header_attr(attr, evsel->idx);
-		if (h_attr == NULL)
-			die("nomem\n");
+	if (perf_evlist__set_filters(evlist)) {
+		error("failed to set filter with %d (%s)\n", errno,
+			strerror(errno));
+		exit(-1);
+	}
 
-		if (!file_new) {
-			if (memcmp(&h_attr->attr, attr, sizeof(*attr))) {
-				fprintf(stderr, "incompatible append\n");
-				exit(-1);
-			}
-		}
+	if (perf_evlist__mmap(evlist, mmap_pages, false) < 0)
+		die("failed to mmap with %d (%s)\n", errno, strerror(errno));
 
-		if (read(FD(evsel, nr_cpu, thread_index), &read_data, sizeof(read_data)) == -1) {
-			perror("Unable to read perf file descriptor");
+	if (file_new)
+		session->evlist = evlist;
+	else {
+		if (!perf_evlist__equal(session->evlist, evlist)) {
+			fprintf(stderr, "incompatible append\n");
 			exit(-1);
 		}
+ 	}
 
-		if (perf_header_attr__add_id(h_attr, read_data.id) < 0) {
-			pr_warning("Not enough memory to add id\n");
-			exit(-1);
-		}
-
-		assert(FD(evsel, nr_cpu, thread_index) >= 0);
-		fcntl(FD(evsel, nr_cpu, thread_index), F_SETFL, O_NONBLOCK);
-
-		/*
-		 * First counter acts as the group leader:
-		 */
-		if (group && group_fd == -1)
-			group_fd = FD(evsel, nr_cpu, thread_index);
-
-		if (evsel->idx || thread_index) {
-			struct perf_evsel *first;
-			first = list_entry(evsel_list.next, struct perf_evsel, node);
-			ret = ioctl(FD(evsel, nr_cpu, thread_index),
-				    PERF_EVENT_IOC_SET_OUTPUT,
-				    FD(first, nr_cpu, 0));
-			if (ret) {
-				error("failed to set output: %d (%s)\n", errno,
-						strerror(errno));
-				exit(-1);
-			}
-		} else {
-			mmap_array[nr_cpu].prev = 0;
-			mmap_array[nr_cpu].mask = mmap_pages*page_size - 1;
-			mmap_array[nr_cpu].base = mmap(NULL, (mmap_pages+1)*page_size,
-				PROT_READ | PROT_WRITE, MAP_SHARED, FD(evsel, nr_cpu, thread_index), 0);
-			if (mmap_array[nr_cpu].base == MAP_FAILED) {
-				error("failed to mmap with %d (%s)\n", errno, strerror(errno));
-				exit(-1);
-			}
-
-			event_array[nr_poll].fd = FD(evsel, nr_cpu, thread_index);
-			event_array[nr_poll].events = POLLIN;
-			nr_poll++;
-		}
-
-		if (filter != NULL) {
-			ret = ioctl(FD(evsel, nr_cpu, thread_index),
-				    PERF_EVENT_IOC_SET_FILTER, filter);
-			if (ret) {
-				error("failed to set filter with %d (%s)\n", errno,
-						strerror(errno));
-				exit(-1);
-			}
-		}
-	}
-
-	if (!sample_type)
-		sample_type = attr->sample_type;
-}
-
-static void open_counters(int cpu)
-{
-	struct perf_evsel *pos;
-
-	group_fd = -1;
-
-	list_for_each_entry(pos, &evsel_list, node)
-		create_counter(pos, cpu);
-
-	nr_cpu++;
+	perf_session__update_sample_type(session);
 }
 
 static int process_buildids(void)
@@ -481,14 +364,14 @@ static void atexit_header(void)
 
 		if (!no_buildid)
 			process_buildids();
-		perf_header__write(&session->header, output, true);
+		perf_session__write_header(session, evsel_list, output, true);
 		perf_session__delete(session);
-		perf_evsel_list__delete();
+		perf_evlist__delete(evsel_list);
 		symbol__exit();
 	}
 }
 
-static void event__synthesize_guest_os(struct machine *machine, void *data)
+static void perf_event__synthesize_guest_os(struct machine *machine, void *data)
 {
 	int err;
 	struct perf_session *psession = data;
@@ -504,8 +387,8 @@ static void event__synthesize_guest_os(struct machine *machine, void *data)
 	 *method is used to avoid symbol missing when the first addr is
 	 *in module instead of in guest kernel.
 	 */
-	err = event__synthesize_modules(process_synthesized_event,
-					psession, machine);
+	err = perf_event__synthesize_modules(process_synthesized_event,
+					     psession, machine);
 	if (err < 0)
 		pr_err("Couldn't record guest kernel [%d]'s reference"
 		       " relocation symbol.\n", machine->pid);
@@ -514,11 +397,12 @@ static void event__synthesize_guest_os(struct machine *machine, void *data)
 	 * We use _stext for guest kernel because guest kernel's /proc/kallsyms
 	 * have no _text sometimes.
 	 */
-	err = event__synthesize_kernel_mmap(process_synthesized_event,
-					    psession, machine, "_text");
+	err = perf_event__synthesize_kernel_mmap(process_synthesized_event,
+						 psession, machine, "_text");
 	if (err < 0)
-		err = event__synthesize_kernel_mmap(process_synthesized_event,
-						    psession, machine, "_stext");
+		err = perf_event__synthesize_kernel_mmap(process_synthesized_event,
+							 psession, machine,
+							 "_stext");
 	if (err < 0)
 		pr_err("Couldn't record guest kernel [%d]'s reference"
 		       " relocation symbol.\n", machine->pid);
@@ -533,9 +417,9 @@ static void mmap_read_all(void)
 {
 	int i;
 
-	for (i = 0; i < nr_cpu; i++) {
-		if (mmap_array[i].base)
-			mmap_read(&mmap_array[i]);
+	for (i = 0; i < evsel_list->cpus->nr; i++) {
+		if (evsel_list->mmap[i].base)
+			mmap_read(&evsel_list->mmap[i]);
 	}
 
 	if (perf_header__has_feat(&session->header, HEADER_TRACE_INFO))
@@ -566,18 +450,26 @@ static int __cmd_record(int argc, const char **argv)
 		exit(-1);
 	}
 
-	if (!strcmp(output_name, "-"))
-		pipe_output = 1;
-	else if (!stat(output_name, &st) && st.st_size) {
-		if (write_mode == WRITE_FORCE) {
-			char oldname[PATH_MAX];
-			snprintf(oldname, sizeof(oldname), "%s.old",
-				 output_name);
-			unlink(oldname);
-			rename(output_name, oldname);
+	if (!output_name) {
+		if (!fstat(STDOUT_FILENO, &st) && S_ISFIFO(st.st_mode))
+			pipe_output = 1;
+		else
+			output_name = "perf.data";
+	}
+	if (output_name) {
+		if (!strcmp(output_name, "-"))
+			pipe_output = 1;
+		else if (!stat(output_name, &st) && st.st_size) {
+			if (write_mode == WRITE_FORCE) {
+				char oldname[PATH_MAX];
+				snprintf(oldname, sizeof(oldname), "%s.old",
+					 output_name);
+				unlink(oldname);
+				rename(output_name, oldname);
+			}
+		} else if (write_mode == WRITE_APPEND) {
+			write_mode = WRITE_FORCE;
 		}
-	} else if (write_mode == WRITE_APPEND) {
-		write_mode = WRITE_FORCE;
 	}
 
 	flags = O_CREAT|O_RDWR;
@@ -606,19 +498,14 @@ static int __cmd_record(int argc, const char **argv)
 		perf_header__set_feat(&session->header, HEADER_BUILD_ID);
 
 	if (!file_new) {
-		err = perf_header__read(session, output);
+		err = perf_session__read_header(session, output);
 		if (err < 0)
 			goto out_delete_session;
 	}
 
-	if (have_tracepoints(&evsel_list))
+	if (have_tracepoints(&evsel_list->entries))
 		perf_header__set_feat(&session->header, HEADER_TRACE_INFO);
 
-	/*
- 	 * perf_session__delete(session) will be called at atexit_header()
-	 */
-	atexit(atexit_header);
-
 	if (forks) {
 		child_pid = fork();
 		if (child_pid < 0) {
@@ -659,7 +546,7 @@ static int __cmd_record(int argc, const char **argv)
 		}
 
 		if (!system_wide && target_tid == -1 && target_pid == -1)
-			threads->map[0] = child_pid;
+			evsel_list->threads->map[0] = child_pid;
 
 		close(child_ready_pipe[1]);
 		close(go_pipe[0]);
@@ -673,46 +560,42 @@ static int __cmd_record(int argc, const char **argv)
 		close(child_ready_pipe[0]);
 	}
 
-	if (!system_wide && no_inherit && !cpu_list) {
-		open_counters(-1);
-	} else {
-		for (i = 0; i < cpus->nr; i++)
-			open_counters(cpus->map[i]);
-	}
+	open_counters(evsel_list);
 
-	perf_session__set_sample_type(session, sample_type);
+	/*
+	 * perf_session__delete(session) will be called at atexit_header()
+	 */
+	atexit(atexit_header);
 
 	if (pipe_output) {
 		err = perf_header__write_pipe(output);
 		if (err < 0)
 			return err;
 	} else if (file_new) {
-		err = perf_header__write(&session->header, output, false);
+		err = perf_session__write_header(session, evsel_list,
+						 output, false);
 		if (err < 0)
 			return err;
 	}
 
 	post_processing_offset = lseek(output, 0, SEEK_CUR);
 
-	perf_session__set_sample_id_all(session, sample_id_all_avail);
-
 	if (pipe_output) {
-		err = event__synthesize_attrs(&session->header,
-					      process_synthesized_event,
-					      session);
+		err = perf_session__synthesize_attrs(session,
+						     process_synthesized_event);
 		if (err < 0) {
 			pr_err("Couldn't synthesize attrs.\n");
 			return err;
 		}
 
-		err = event__synthesize_event_types(process_synthesized_event,
-						    session);
+		err = perf_event__synthesize_event_types(process_synthesized_event,
+							 session);
 		if (err < 0) {
 			pr_err("Couldn't synthesize event_types.\n");
 			return err;
 		}
 
-		if (have_tracepoints(&evsel_list)) {
+		if (have_tracepoints(&evsel_list->entries)) {
 			/*
 			 * FIXME err <= 0 here actually means that
 			 * there were no tracepoints so its not really
@@ -721,9 +604,9 @@ static int __cmd_record(int argc, const char **argv)
 			 * return this more properly and also
 			 * propagate errors that now are calling die()
 			 */
-			err = event__synthesize_tracing_data(output, &evsel_list,
-							     process_synthesized_event,
-							     session);
+			err = perf_event__synthesize_tracing_data(output, evsel_list,
+								  process_synthesized_event,
+								  session);
 			if (err <= 0) {
 				pr_err("Couldn't record tracing data.\n");
 				return err;
@@ -738,31 +621,34 @@ static int __cmd_record(int argc, const char **argv)
 		return -1;
 	}
 
-	err = event__synthesize_kernel_mmap(process_synthesized_event,
-					    session, machine, "_text");
+	err = perf_event__synthesize_kernel_mmap(process_synthesized_event,
+						 session, machine, "_text");
 	if (err < 0)
-		err = event__synthesize_kernel_mmap(process_synthesized_event,
-						    session, machine, "_stext");
+		err = perf_event__synthesize_kernel_mmap(process_synthesized_event,
+							 session, machine, "_stext");
 	if (err < 0)
 		pr_err("Couldn't record kernel reference relocation symbol\n"
 		       "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
 		       "Check /proc/kallsyms permission or run as root.\n");
 
-	err = event__synthesize_modules(process_synthesized_event,
-					session, machine);
+	err = perf_event__synthesize_modules(process_synthesized_event,
+					     session, machine);
 	if (err < 0)
 		pr_err("Couldn't record kernel module information.\n"
 		       "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
 		       "Check /proc/modules permission or run as root.\n");
 
 	if (perf_guest)
-		perf_session__process_machines(session, event__synthesize_guest_os);
+		perf_session__process_machines(session,
+					       perf_event__synthesize_guest_os);
 
 	if (!system_wide)
-		event__synthesize_thread_map(threads, process_synthesized_event,
-					     session);
+		perf_event__synthesize_thread_map(evsel_list->threads,
+						  process_synthesized_event,
+						  session);
 	else
-		event__synthesize_threads(process_synthesized_event, session);
+		perf_event__synthesize_threads(process_synthesized_event,
+					       session);
 
 	if (realtime_prio) {
 		struct sched_param param;
@@ -789,17 +675,17 @@ static int __cmd_record(int argc, const char **argv)
 		if (hits == samples) {
 			if (done)
 				break;
-			err = poll(event_array, nr_poll, -1);
+			err = poll(evsel_list->pollfd, evsel_list->nr_fds, -1);
 			waking++;
 		}
 
 		if (done) {
-			for (i = 0; i < nr_cpu; i++) {
+			for (i = 0; i < evsel_list->cpus->nr; i++) {
 				struct perf_evsel *pos;
 
-				list_for_each_entry(pos, &evsel_list, node) {
+				list_for_each_entry(pos, &evsel_list->entries, node) {
 					for (thread = 0;
-						thread < threads->nr;
+						thread < evsel_list->threads->nr;
 						thread++)
 						ioctl(FD(pos, i, thread),
 							PERF_EVENT_IOC_DISABLE);
@@ -838,10 +724,10 @@ static const char * const record_usage[] = {
 static bool force, append_file;
 
 const struct option record_options[] = {
-	OPT_CALLBACK('e', "event", NULL, "event",
+	OPT_CALLBACK('e', "event", &evsel_list, "event",
 		     "event selector. use 'perf list' to list available events",
 		     parse_events),
-	OPT_CALLBACK(0, "filter", NULL, "filter",
+	OPT_CALLBACK(0, "filter", &evsel_list, "filter",
 		     "event filter", parse_filter),
 	OPT_INTEGER('p', "pid", &target_pid,
 		    "record events on existing process id"),
@@ -884,6 +770,9 @@ const struct option record_options[] = {
 		    "do not update the buildid cache"),
 	OPT_BOOLEAN('B', "no-buildid", &no_buildid,
 		    "do not collect buildids in perf.data"),
+	OPT_CALLBACK('G', "cgroup", &evsel_list, "name",
+		     "monitor event in cgroup name only",
+		     parse_cgroups),
 	OPT_END()
 };
 
@@ -892,6 +781,10 @@ int cmd_record(int argc, const char **argv, const char *prefix __used)
 	int err = -ENOMEM;
 	struct perf_evsel *pos;
 
+	evsel_list = perf_evlist__new(NULL, NULL);
+	if (evsel_list == NULL)
+		return -ENOMEM;
+
 	argc = parse_options(argc, argv, record_options, record_usage,
 			    PARSE_OPT_STOP_AT_NON_OPTION);
 	if (!argc && target_pid == -1 && target_tid == -1 &&
@@ -908,12 +801,19 @@ int cmd_record(int argc, const char **argv, const char *prefix __used)
 		write_mode = WRITE_FORCE;
 	}
 
+	if (nr_cgroups && !system_wide) {
+		fprintf(stderr, "cgroup monitoring only available in"
+			" system-wide mode\n");
+		usage_with_options(record_usage, record_options);
+	}
+
 	symbol__init();
 
 	if (no_buildid_cache || no_buildid)
 		disable_buildid_cache();
 
-	if (list_empty(&evsel_list) && perf_evsel_list__create_default() < 0) {
+	if (evsel_list->nr_entries == 0 &&
+	    perf_evlist__add_default(evsel_list) < 0) {
 		pr_err("Not enough memory for event selector list\n");
 		goto out_symbol_exit;
 	}
@@ -921,27 +821,19 @@ int cmd_record(int argc, const char **argv, const char *prefix __used)
 	if (target_pid != -1)
 		target_tid = target_pid;
 
-	threads = thread_map__new(target_pid, target_tid);
-	if (threads == NULL) {
-		pr_err("Problems finding threads of monitor\n");
+	if (perf_evlist__create_maps(evsel_list, target_pid,
+				     target_tid, cpu_list) < 0)
 		usage_with_options(record_usage, record_options);
-	}
 
-	cpus = cpu_map__new(cpu_list);
-	if (cpus == NULL) {
-		perror("failed to parse CPUs map");
-		return -1;
-	}
-
-	list_for_each_entry(pos, &evsel_list, node) {
-		if (perf_evsel__alloc_fd(pos, cpus->nr, threads->nr) < 0)
+	list_for_each_entry(pos, &evsel_list->entries, node) {
+		if (perf_evsel__alloc_fd(pos, evsel_list->cpus->nr,
+					 evsel_list->threads->nr) < 0)
 			goto out_free_fd;
 		if (perf_header__push_event(pos->attr.config, event_name(pos)))
 			goto out_free_fd;
 	}
-	event_array = malloc((sizeof(struct pollfd) * MAX_NR_CPUS *
-			      MAX_COUNTERS * threads->nr));
-	if (!event_array)
+
+	if (perf_evlist__alloc_pollfd(evsel_list) < 0)
 		goto out_free_fd;
 
 	if (user_interval != ULLONG_MAX)
@@ -959,16 +851,12 @@ int cmd_record(int argc, const char **argv, const char *prefix __used)
 	} else {
 		fprintf(stderr, "frequency and count are zero, aborting\n");
 		err = -EINVAL;
-		goto out_free_event_array;
+		goto out_free_fd;
 	}
 
 	err = __cmd_record(argc, argv);
-
-out_free_event_array:
-	free(event_array);
 out_free_fd:
-	thread_map__delete(threads);
-	threads = NULL;
+	perf_evlist__delete_maps(evsel_list);
 out_symbol_exit:
 	symbol__exit();
 	return err;
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index c27e31f289e6..b1b82009ab9b 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -9,6 +9,7 @@
 
 #include "util/util.h"
 
+#include "util/annotate.h"
 #include "util/color.h"
 #include <linux/list.h>
 #include "util/cache.h"
@@ -20,6 +21,8 @@
 
 #include "perf.h"
 #include "util/debug.h"
+#include "util/evlist.h"
+#include "util/evsel.h"
 #include "util/header.h"
 #include "util/session.h"
 
@@ -43,120 +46,79 @@ static const char	default_pretty_printing_style[] = "normal";
 static const char	*pretty_printing_style = default_pretty_printing_style;
 
 static char		callchain_default_opt[] = "fractal,0.5";
+static symbol_filter_t	annotate_init;
 
-static struct hists *perf_session__hists_findnew(struct perf_session *self,
-						 u64 event_stream, u32 type,
-						 u64 config)
-{
-	struct rb_node **p = &self->hists_tree.rb_node;
-	struct rb_node *parent = NULL;
-	struct hists *iter, *new;
-
-	while (*p != NULL) {
-		parent = *p;
-		iter = rb_entry(parent, struct hists, rb_node);
-		if (iter->config == config)
-			return iter;
-
-
-		if (config > iter->config)
-			p = &(*p)->rb_right;
-		else
-			p = &(*p)->rb_left;
-	}
-
-	new = malloc(sizeof(struct hists));
-	if (new == NULL)
-		return NULL;
-	memset(new, 0, sizeof(struct hists));
-	new->event_stream = event_stream;
-	new->config = config;
-	new->type = type;
-	rb_link_node(&new->rb_node, parent, p);
-	rb_insert_color(&new->rb_node, &self->hists_tree);
-	return new;
-}
-
-static int perf_session__add_hist_entry(struct perf_session *self,
+static int perf_session__add_hist_entry(struct perf_session *session,
 					struct addr_location *al,
-					struct sample_data *data)
+					struct perf_sample *sample)
 {
-	struct map_symbol *syms = NULL;
 	struct symbol *parent = NULL;
-	int err = -ENOMEM;
+	int err = 0;
 	struct hist_entry *he;
-	struct hists *hists;
-	struct perf_event_attr *attr;
-
-	if ((sort__has_parent || symbol_conf.use_callchain) && data->callchain) {
-		syms = perf_session__resolve_callchain(self, al->thread,
-						       data->callchain, &parent);
-		if (syms == NULL)
-			return -ENOMEM;
+	struct perf_evsel *evsel;
+
+	if ((sort__has_parent || symbol_conf.use_callchain) && sample->callchain) {
+		err = perf_session__resolve_callchain(session, al->thread,
+						      sample->callchain, &parent);
+		if (err)
+			return err;
 	}
 
-	attr = perf_header__find_attr(data->id, &self->header);
-	if (attr)
-		hists = perf_session__hists_findnew(self, data->id, attr->type, attr->config);
-	else
-		hists = perf_session__hists_findnew(self, data->id, 0, 0);
-	if (hists == NULL)
-		goto out_free_syms;
-	he = __hists__add_entry(hists, al, parent, data->period);
+	evsel = perf_evlist__id2evsel(session->evlist, sample->id);
+	if (evsel == NULL) {
+		/*
+		 * FIXME: Propagate this back, but at least we're in a builtin,
+		 * where exit() is allowed. ;-)
+		 */
+		ui__warning("Invalid %s file, contains samples with id %" PRIu64 " not in "
+			    "its header!\n", input_name, sample->id);
+		exit_browser(0);
+		exit(1);
+	}
+
+	he = __hists__add_entry(&evsel->hists, al, parent, sample->period);
 	if (he == NULL)
-		goto out_free_syms;
-	err = 0;
+		return -ENOMEM;
+
 	if (symbol_conf.use_callchain) {
-		err = callchain_append(he->callchain, data->callchain, syms,
-				       data->period);
+		err = callchain_append(he->callchain, &session->callchain_cursor,
+				       sample->period);
 		if (err)
-			goto out_free_syms;
+			return err;
 	}
 	/*
 	 * Only in the newt browser we are doing integrated annotation,
 	 * so we don't allocated the extra space needed because the stdio
 	 * code will not use it.
 	 */
-	if (use_browser > 0)
-		err = hist_entry__inc_addr_samples(he, al->addr);
-out_free_syms:
-	free(syms);
-	return err;
-}
+	if (al->sym != NULL && use_browser > 0) {
+		struct annotation *notes = symbol__annotation(he->ms.sym);
 
-static int add_event_total(struct perf_session *session,
-			   struct sample_data *data,
-			   struct perf_event_attr *attr)
-{
-	struct hists *hists;
+		assert(evsel != NULL);
 
-	if (attr)
-		hists = perf_session__hists_findnew(session, data->id,
-						    attr->type, attr->config);
-	else
-		hists = perf_session__hists_findnew(session, data->id, 0, 0);
+		err = -ENOMEM;
+		if (notes->src == NULL &&
+		    symbol__alloc_hist(he->ms.sym, session->evlist->nr_entries) < 0)
+			goto out;
 
-	if (!hists)
-		return -ENOMEM;
+		err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
+	}
 
-	hists->stats.total_period += data->period;
-	/*
-	 * FIXME: add_event_total should be moved from here to
-	 * perf_session__process_event so that the proper hist is passed to
-	 * the event_op methods.
-	 */
-	hists__inc_nr_events(hists, PERF_RECORD_SAMPLE);
-	session->hists.stats.total_period += data->period;
-	return 0;
+	evsel->hists.stats.total_period += sample->period;
+	hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
+out:
+	return err;
 }
 
-static int process_sample_event(event_t *event, struct sample_data *sample,
+
+static int process_sample_event(union perf_event *event,
+				struct perf_sample *sample,
 				struct perf_session *session)
 {
 	struct addr_location al;
-	struct perf_event_attr *attr;
 
-	if (event__preprocess_sample(event, session, &al, sample, NULL) < 0) {
+	if (perf_event__preprocess_sample(event, session, &al, sample,
+					  annotate_init) < 0) {
 		fprintf(stderr, "problem processing %d event, skipping it.\n",
 			event->header.type);
 		return -1;
@@ -170,26 +132,17 @@ static int process_sample_event(event_t *event, struct sample_data *sample,
 		return -1;
 	}
 
-	attr = perf_header__find_attr(sample->id, &session->header);
-
-	if (add_event_total(session, sample, attr)) {
-		pr_debug("problem adding event period\n");
-		return -1;
-	}
-
 	return 0;
 }
 
-static int process_read_event(event_t *event, struct sample_data *sample __used,
-			      struct perf_session *session __used)
+static int process_read_event(union perf_event *event,
+			      struct perf_sample *sample __used,
+			      struct perf_session *session)
 {
-	struct perf_event_attr *attr;
-
-	attr = perf_header__find_attr(event->read.id, &session->header);
-
+	struct perf_evsel *evsel = perf_evlist__id2evsel(session->evlist,
+							 event->read.id);
 	if (show_threads) {
-		const char *name = attr ? __event_name(attr->type, attr->config)
-				   : "unknown";
+		const char *name = evsel ? event_name(evsel) : "unknown";
 		perf_read_values_add_value(&show_threads_values,
 					   event->read.pid, event->read.tid,
 					   event->read.id,
@@ -198,7 +151,7 @@ static int process_read_event(event_t *event, struct sample_data *sample __used,
 	}
 
 	dump_printf(": %d %d %s %" PRIu64 "\n", event->read.pid, event->read.tid,
-		    attr ? __event_name(attr->type, attr->config) : "FAIL",
+		    evsel ? event_name(evsel) : "FAIL",
 		    event->read.value);
 
 	return 0;
@@ -222,7 +175,7 @@ static int perf_session__setup_sample_type(struct perf_session *self)
 	} else if (!dont_use_callchains && callchain_param.mode != CHAIN_NONE &&
 		   !symbol_conf.use_callchain) {
 			symbol_conf.use_callchain = true;
-			if (register_callchain_param(&callchain_param) < 0) {
+			if (callchain_register_param(&callchain_param) < 0) {
 				fprintf(stderr, "Can't register callchain"
 						" params\n");
 				return -EINVAL;
@@ -233,17 +186,17 @@ static int perf_session__setup_sample_type(struct perf_session *self)
 }
 
 static struct perf_event_ops event_ops = {
-	.sample	= process_sample_event,
-	.mmap	= event__process_mmap,
-	.comm	= event__process_comm,
-	.exit	= event__process_task,
-	.fork	= event__process_task,
-	.lost	= event__process_lost,
-	.read	= process_read_event,
-	.attr	= event__process_attr,
-	.event_type = event__process_event_type,
-	.tracing_data = event__process_tracing_data,
-	.build_id = event__process_build_id,
+	.sample		 = process_sample_event,
+	.mmap		 = perf_event__process_mmap,
+	.comm		 = perf_event__process_comm,
+	.exit		 = perf_event__process_task,
+	.fork		 = perf_event__process_task,
+	.lost		 = perf_event__process_lost,
+	.read		 = process_read_event,
+	.attr		 = perf_event__process_attr,
+	.event_type	 = perf_event__process_event_type,
+	.tracing_data	 = perf_event__process_tracing_data,
+	.build_id	 = perf_event__process_build_id,
 	.ordered_samples = true,
 	.ordering_requires_timestamps = true,
 };
@@ -269,21 +222,21 @@ static size_t hists__fprintf_nr_sample_events(struct hists *self,
 	return ret + fprintf(fp, "\n#\n");
 }
 
-static int hists__tty_browse_tree(struct rb_root *tree, const char *help)
+static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
+					 const char *help)
 {
-	struct rb_node *next = rb_first(tree);
+	struct perf_evsel *pos;
 
-	while (next) {
-		struct hists *hists = rb_entry(next, struct hists, rb_node);
+	list_for_each_entry(pos, &evlist->entries, node) {
+		struct hists *hists = &pos->hists;
 		const char *evname = NULL;
 
 		if (rb_first(&hists->entries) != rb_last(&hists->entries))
-			evname = __event_name(hists->type, hists->config);
+			evname = event_name(pos);
 
 		hists__fprintf_nr_sample_events(hists, evname, stdout);
 		hists__fprintf(hists, NULL, false, stdout);
 		fprintf(stdout, "\n\n");
-		next = rb_next(&hists->rb_node);
 	}
 
 	if (sort_order == default_sort_order &&
@@ -304,8 +257,9 @@ static int hists__tty_browse_tree(struct rb_root *tree, const char *help)
 static int __cmd_report(void)
 {
 	int ret = -EINVAL;
+	u64 nr_samples;
 	struct perf_session *session;
-	struct rb_node *next;
+	struct perf_evsel *pos;
 	const char *help = "For a higher level overview, try: perf report --sort comm,dso";
 
 	signal(SIGINT, sig_handler);
@@ -336,20 +290,24 @@ static int __cmd_report(void)
 	if (verbose > 2)
 		perf_session__fprintf_dsos(session, stdout);
 
-	next = rb_first(&session->hists_tree);
-	while (next) {
-		struct hists *hists;
+	nr_samples = 0;
+	list_for_each_entry(pos, &session->evlist->entries, node) {
+		struct hists *hists = &pos->hists;
 
-		hists = rb_entry(next, struct hists, rb_node);
 		hists__collapse_resort(hists);
 		hists__output_resort(hists);
-		next = rb_next(&hists->rb_node);
+		nr_samples += hists->stats.nr_events[PERF_RECORD_SAMPLE];
+	}
+
+	if (nr_samples == 0) {
+		ui__warning("The %s file has no samples!\n", input_name);
+		goto out_delete;
 	}
 
 	if (use_browser > 0)
-		hists__tui_browse_tree(&session->hists_tree, help);
+		perf_evlist__tui_browse_hists(session->evlist, help);
 	else
-		hists__tty_browse_tree(&session->hists_tree, help);
+		perf_evlist__tty_browse_hists(session->evlist, help);
 
 out_delete:
 	/*
@@ -424,7 +382,7 @@ parse_callchain_opt(const struct option *opt __used, const char *arg,
 	if (tok2)
 		callchain_param.print_limit = strtod(tok2, &endptr);
 setup:
-	if (register_callchain_param(&callchain_param) < 0) {
+	if (callchain_register_param(&callchain_param) < 0) {
 		fprintf(stderr, "Can't register callchain params\n");
 		return -1;
 	}
@@ -498,7 +456,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __used)
 		use_browser = 1;
 
 	if (strcmp(input_name, "-") != 0)
-		setup_browser();
+		setup_browser(true);
 	else
 		use_browser = 0;
 	/*
@@ -507,7 +465,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __used)
 	 * implementation.
 	 */
 	if (use_browser > 0) {
-		symbol_conf.priv_size = sizeof(struct sym_priv);
+		symbol_conf.priv_size = sizeof(struct annotation);
+		annotate_init	      = symbol__annotate_init;
 		/*
  		 * For searching by name on the "Browse map details".
  		 * providing it only in verbose mode not to bloat too
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 29acb894e035..a32f411faeac 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -369,11 +369,6 @@ static void
 process_sched_event(struct task_desc *this_task __used, struct sched_atom *atom)
 {
 	int ret = 0;
-	u64 now;
-	long long delta;
-
-	now = get_nsecs();
-	delta = start_time + atom->timestamp - now;
 
 	switch (atom->type) {
 		case SCHED_EVENT_RUN:
@@ -562,7 +557,7 @@ static void wait_for_tasks(void)
 
 static void run_one_test(void)
 {
-	u64 T0, T1, delta, avg_delta, fluct, std_dev;
+	u64 T0, T1, delta, avg_delta, fluct;
 
 	T0 = get_nsecs();
 	wait_for_tasks();
@@ -578,7 +573,6 @@ static void run_one_test(void)
 	else
 		fluct = delta - avg_delta;
 	sum_fluct += fluct;
-	std_dev = sum_fluct / nr_runs / sqrt(nr_runs);
 	if (!run_avg)
 		run_avg = delta;
 	run_avg = (run_avg*9 + delta)/10;
@@ -799,7 +793,7 @@ replay_switch_event(struct trace_switch_event *switch_event,
 		    u64 timestamp,
 		    struct thread *thread __used)
 {
-	struct task_desc *prev, *next;
+	struct task_desc *prev, __used *next;
 	u64 timestamp0;
 	s64 delta;
 
@@ -1404,7 +1398,7 @@ map_switch_event(struct trace_switch_event *switch_event,
 		 u64 timestamp,
 		 struct thread *thread __used)
 {
-	struct thread *sched_out, *sched_in;
+	struct thread *sched_out __used, *sched_in;
 	int new_shortname;
 	u64 timestamp0;
 	s64 delta;
@@ -1580,9 +1574,9 @@ process_sched_migrate_task_event(void *data, struct perf_session *session,
 						 event, cpu, timestamp, thread);
 }
 
-static void
-process_raw_event(event_t *raw_event __used, struct perf_session *session,
-		  void *data, int cpu, u64 timestamp, struct thread *thread)
+static void process_raw_event(union perf_event *raw_event __used,
+			      struct perf_session *session, void *data, int cpu,
+			      u64 timestamp, struct thread *thread)
 {
 	struct event *event;
 	int type;
@@ -1607,7 +1601,8 @@ process_raw_event(event_t *raw_event __used, struct perf_session *session,
 		process_sched_migrate_task_event(data, session, event, cpu, timestamp, thread);
 }
 
-static int process_sample_event(event_t *event, struct sample_data *sample,
+static int process_sample_event(union perf_event *event,
+				struct perf_sample *sample,
 				struct perf_session *session)
 {
 	struct thread *thread;
@@ -1635,9 +1630,9 @@ static int process_sample_event(event_t *event, struct sample_data *sample,
 
 static struct perf_event_ops event_ops = {
 	.sample			= process_sample_event,
-	.comm			= event__process_comm,
-	.lost			= event__process_lost,
-	.fork			= event__process_task,
+	.comm			= perf_event__process_comm,
+	.lost			= perf_event__process_lost,
+	.fork			= perf_event__process_task,
 	.ordered_samples	= true,
 };
 
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index b766c2a9ac97..5f40df635dcb 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -63,7 +63,8 @@ static int cleanup_scripting(void)
 
 static char const		*input_name = "perf.data";
 
-static int process_sample_event(event_t *event, struct sample_data *sample,
+static int process_sample_event(union perf_event *event,
+				struct perf_sample *sample,
 				struct perf_session *session)
 {
 	struct thread *thread = perf_session__findnew(session, event->ip.pid);
@@ -100,14 +101,14 @@ static int process_sample_event(event_t *event, struct sample_data *sample,
 }
 
 static struct perf_event_ops event_ops = {
-	.sample	= process_sample_event,
-	.comm	= event__process_comm,
-	.attr	= event__process_attr,
-	.event_type = event__process_event_type,
-	.tracing_data = event__process_tracing_data,
-	.build_id = event__process_build_id,
-	.ordering_requires_timestamps = true,
+	.sample		 = process_sample_event,
+	.comm		 = perf_event__process_comm,
+	.attr		 = perf_event__process_attr,
+	.event_type	 = perf_event__process_event_type,
+	.tracing_data	 = perf_event__process_tracing_data,
+	.build_id	 = perf_event__process_build_id,
 	.ordered_samples = true,
+	.ordering_requires_timestamps = true,
 };
 
 extern volatile int session_done;
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index a482a191a0ca..21c025222496 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -43,11 +43,13 @@
 #include "util/parse-options.h"
 #include "util/parse-events.h"
 #include "util/event.h"
+#include "util/evlist.h"
 #include "util/evsel.h"
 #include "util/debug.h"
 #include "util/header.h"
 #include "util/cpumap.h"
 #include "util/thread.h"
+#include "util/thread_map.h"
 
 #include <sys/prctl.h>
 #include <math.h>
@@ -71,8 +73,9 @@ static struct perf_event_attr default_attrs[] = {
 
 };
 
+struct perf_evlist		*evsel_list;
+
 static bool			system_wide			=  false;
-static struct cpu_map		*cpus;
 static int			run_idx				=  0;
 
 static int			run_count			=  1;
@@ -81,7 +84,6 @@ static bool			scale				=  true;
 static bool			no_aggr				= false;
 static pid_t			target_pid			= -1;
 static pid_t			target_tid			= -1;
-static struct thread_map	*threads;
 static pid_t			child_pid			= -1;
 static bool			null_run			=  false;
 static bool			big_num				=  true;
@@ -166,7 +168,7 @@ static int create_perf_stat_counter(struct perf_evsel *evsel)
 				    PERF_FORMAT_TOTAL_TIME_RUNNING;
 
 	if (system_wide)
-		return perf_evsel__open_per_cpu(evsel, cpus);
+		return perf_evsel__open_per_cpu(evsel, evsel_list->cpus, false, false);
 
 	attr->inherit = !no_inherit;
 	if (target_pid == -1 && target_tid == -1) {
@@ -174,7 +176,7 @@ static int create_perf_stat_counter(struct perf_evsel *evsel)
 		attr->enable_on_exec = 1;
 	}
 
-	return perf_evsel__open_per_thread(evsel, threads);
+	return perf_evsel__open_per_thread(evsel, evsel_list->threads, false, false);
 }
 
 /*
@@ -199,7 +201,8 @@ static int read_counter_aggr(struct perf_evsel *counter)
 	u64 *count = counter->counts->aggr.values;
 	int i;
 
-	if (__perf_evsel__read(counter, cpus->nr, threads->nr, scale) < 0)
+	if (__perf_evsel__read(counter, evsel_list->cpus->nr,
+			       evsel_list->threads->nr, scale) < 0)
 		return -1;
 
 	for (i = 0; i < 3; i++)
@@ -232,7 +235,7 @@ static int read_counter(struct perf_evsel *counter)
 	u64 *count;
 	int cpu;
 
-	for (cpu = 0; cpu < cpus->nr; cpu++) {
+	for (cpu = 0; cpu < evsel_list->cpus->nr; cpu++) {
 		if (__perf_evsel__read_on_cpu(counter, cpu, 0, scale) < 0)
 			return -1;
 
@@ -297,7 +300,7 @@ static int run_perf_stat(int argc __used, const char **argv)
 		}
 
 		if (target_tid == -1 && target_pid == -1 && !system_wide)
-			threads->map[0] = child_pid;
+			evsel_list->threads->map[0] = child_pid;
 
 		/*
 		 * Wait for the child to be ready to exec.
@@ -309,7 +312,7 @@ static int run_perf_stat(int argc __used, const char **argv)
 		close(child_ready_pipe[0]);
 	}
 
-	list_for_each_entry(counter, &evsel_list, node) {
+	list_for_each_entry(counter, &evsel_list->entries, node) {
 		if (create_perf_stat_counter(counter) < 0) {
 			if (errno == -EPERM || errno == -EACCES) {
 				error("You may not have permission to collect %sstats.\n"
@@ -347,14 +350,15 @@ static int run_perf_stat(int argc __used, const char **argv)
 	update_stats(&walltime_nsecs_stats, t1 - t0);
 
 	if (no_aggr) {
-		list_for_each_entry(counter, &evsel_list, node) {
+		list_for_each_entry(counter, &evsel_list->entries, node) {
 			read_counter(counter);
-			perf_evsel__close_fd(counter, cpus->nr, 1);
+			perf_evsel__close_fd(counter, evsel_list->cpus->nr, 1);
 		}
 	} else {
-		list_for_each_entry(counter, &evsel_list, node) {
+		list_for_each_entry(counter, &evsel_list->entries, node) {
 			read_counter_aggr(counter);
-			perf_evsel__close_fd(counter, cpus->nr, threads->nr);
+			perf_evsel__close_fd(counter, evsel_list->cpus->nr,
+					     evsel_list->threads->nr);
 		}
 	}
 
@@ -382,10 +386,13 @@ static void nsec_printout(int cpu, struct perf_evsel *evsel, double avg)
 	if (no_aggr)
 		sprintf(cpustr, "CPU%*d%s",
 			csv_output ? 0 : -4,
-			cpus->map[cpu], csv_sep);
+			evsel_list->cpus->map[cpu], csv_sep);
 
 	fprintf(stderr, fmt, cpustr, msecs, csv_sep, event_name(evsel));
 
+	if (evsel->cgrp)
+		fprintf(stderr, "%s%s", csv_sep, evsel->cgrp->name);
+
 	if (csv_output)
 		return;
 
@@ -410,12 +417,15 @@ static void abs_printout(int cpu, struct perf_evsel *evsel, double avg)
 	if (no_aggr)
 		sprintf(cpustr, "CPU%*d%s",
 			csv_output ? 0 : -4,
-			cpus->map[cpu], csv_sep);
+			evsel_list->cpus->map[cpu], csv_sep);
 	else
 		cpu = 0;
 
 	fprintf(stderr, fmt, cpustr, avg, csv_sep, event_name(evsel));
 
+	if (evsel->cgrp)
+		fprintf(stderr, "%s%s", csv_sep, evsel->cgrp->name);
+
 	if (csv_output)
 		return;
 
@@ -456,9 +466,17 @@ static void print_counter_aggr(struct perf_evsel *counter)
 	int scaled = counter->counts->scaled;
 
 	if (scaled == -1) {
-		fprintf(stderr, "%*s%s%-24s\n",
+		fprintf(stderr, "%*s%s%*s",
 			csv_output ? 0 : 18,
-			"<not counted>", csv_sep, event_name(counter));
+			"<not counted>",
+			csv_sep,
+			csv_output ? 0 : -24,
+			event_name(counter));
+
+		if (counter->cgrp)
+			fprintf(stderr, "%s%s", csv_sep, counter->cgrp->name);
+
+		fputc('\n', stderr);
 		return;
 	}
 
@@ -483,7 +501,6 @@ static void print_counter_aggr(struct perf_evsel *counter)
 		fprintf(stderr, "  (scaled from %.2f%%)",
 				100 * avg_running / avg_enabled);
 	}
-
 	fprintf(stderr, "\n");
 }
 
@@ -496,19 +513,23 @@ static void print_counter(struct perf_evsel *counter)
 	u64 ena, run, val;
 	int cpu;
 
-	for (cpu = 0; cpu < cpus->nr; cpu++) {
+	for (cpu = 0; cpu < evsel_list->cpus->nr; cpu++) {
 		val = counter->counts->cpu[cpu].val;
 		ena = counter->counts->cpu[cpu].ena;
 		run = counter->counts->cpu[cpu].run;
 		if (run == 0 || ena == 0) {
-			fprintf(stderr, "CPU%*d%s%*s%s%-24s",
+			fprintf(stderr, "CPU%*d%s%*s%s%*s",
 				csv_output ? 0 : -4,
-				cpus->map[cpu], csv_sep,
+				evsel_list->cpus->map[cpu], csv_sep,
 				csv_output ? 0 : 18,
 				"<not counted>", csv_sep,
+				csv_output ? 0 : -24,
 				event_name(counter));
 
-			fprintf(stderr, "\n");
+			if (counter->cgrp)
+				fprintf(stderr, "%s%s", csv_sep, counter->cgrp->name);
+
+			fputc('\n', stderr);
 			continue;
 		}
 
@@ -525,7 +546,7 @@ static void print_counter(struct perf_evsel *counter)
 					100.0 * run / ena);
 			}
 		}
-		fprintf(stderr, "\n");
+		fputc('\n', stderr);
 	}
 }
 
@@ -555,10 +576,10 @@ static void print_stat(int argc, const char **argv)
 	}
 
 	if (no_aggr) {
-		list_for_each_entry(counter, &evsel_list, node)
+		list_for_each_entry(counter, &evsel_list->entries, node)
 			print_counter(counter);
 	} else {
-		list_for_each_entry(counter, &evsel_list, node)
+		list_for_each_entry(counter, &evsel_list->entries, node)
 			print_counter_aggr(counter);
 	}
 
@@ -610,7 +631,7 @@ static int stat__set_big_num(const struct option *opt __used,
 }
 
 static const struct option options[] = {
-	OPT_CALLBACK('e', "event", NULL, "event",
+	OPT_CALLBACK('e', "event", &evsel_list, "event",
 		     "event selector. use 'perf list' to list available events",
 		     parse_events),
 	OPT_BOOLEAN('i', "no-inherit", &no_inherit,
@@ -638,6 +659,9 @@ static const struct option options[] = {
 		    "disable CPU count aggregation"),
 	OPT_STRING('x', "field-separator", &csv_sep, "separator",
 		   "print counts with custom separator"),
+	OPT_CALLBACK('G', "cgroup", &evsel_list, "name",
+		     "monitor event in cgroup name only",
+		     parse_cgroups),
 	OPT_END()
 };
 
@@ -648,6 +672,10 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
 
 	setlocale(LC_ALL, "");
 
+	evsel_list = perf_evlist__new(NULL, NULL);
+	if (evsel_list == NULL)
+		return -ENOMEM;
+
 	argc = parse_options(argc, argv, options, stat_usage,
 		PARSE_OPT_STOP_AT_NON_OPTION);
 
@@ -674,49 +702,50 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
 	if (run_count <= 0)
 		usage_with_options(stat_usage, options);
 
-	/* no_aggr is for system-wide only */
-	if (no_aggr && !system_wide)
+	/* no_aggr, cgroup are for system-wide only */
+	if ((no_aggr || nr_cgroups) && !system_wide) {
+		fprintf(stderr, "both cgroup and no-aggregation "
+			"modes only available in system-wide mode\n");
+
 		usage_with_options(stat_usage, options);
+	}
 
 	/* Set attrs and nr_counters if no event is selected and !null_run */
-	if (!null_run && !nr_counters) {
+	if (!null_run && !evsel_list->nr_entries) {
 		size_t c;
 
-		nr_counters = ARRAY_SIZE(default_attrs);
-
 		for (c = 0; c < ARRAY_SIZE(default_attrs); ++c) {
-			pos = perf_evsel__new(&default_attrs[c],
-					      nr_counters);
+			pos = perf_evsel__new(&default_attrs[c], c);
 			if (pos == NULL)
 				goto out;
-			list_add(&pos->node, &evsel_list);
+			perf_evlist__add(evsel_list, pos);
 		}
 	}
 
 	if (target_pid != -1)
 		target_tid = target_pid;
 
-	threads = thread_map__new(target_pid, target_tid);
-	if (threads == NULL) {
+	evsel_list->threads = thread_map__new(target_pid, target_tid);
+	if (evsel_list->threads == NULL) {
 		pr_err("Problems finding threads of monitor\n");
 		usage_with_options(stat_usage, options);
 	}
 
 	if (system_wide)
-		cpus = cpu_map__new(cpu_list);
+		evsel_list->cpus = cpu_map__new(cpu_list);
 	else
-		cpus = cpu_map__dummy_new();
+		evsel_list->cpus = cpu_map__dummy_new();
 
-	if (cpus == NULL) {
+	if (evsel_list->cpus == NULL) {
 		perror("failed to parse CPUs map");
 		usage_with_options(stat_usage, options);
 		return -1;
 	}
 
-	list_for_each_entry(pos, &evsel_list, node) {
+	list_for_each_entry(pos, &evsel_list->entries, node) {
 		if (perf_evsel__alloc_stat_priv(pos) < 0 ||
-		    perf_evsel__alloc_counts(pos, cpus->nr) < 0 ||
-		    perf_evsel__alloc_fd(pos, cpus->nr, threads->nr) < 0)
+		    perf_evsel__alloc_counts(pos, evsel_list->cpus->nr) < 0 ||
+		    perf_evsel__alloc_fd(pos, evsel_list->cpus->nr, evsel_list->threads->nr) < 0)
 			goto out_free_fd;
 	}
 
@@ -741,11 +770,10 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
 	if (status != -1)
 		print_stat(argc, argv);
 out_free_fd:
-	list_for_each_entry(pos, &evsel_list, node)
+	list_for_each_entry(pos, &evsel_list->entries, node)
 		perf_evsel__free_stat_priv(pos);
-	perf_evsel_list__delete();
+	perf_evlist__delete_maps(evsel_list);
 out:
-	thread_map__delete(threads);
-	threads = NULL;
+	perf_evlist__delete(evsel_list);
 	return status;
 }
diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c
index 5dcdba653d70..1b2106c58f66 100644
--- a/tools/perf/builtin-test.c
+++ b/tools/perf/builtin-test.c
@@ -7,10 +7,11 @@
 
 #include "util/cache.h"
 #include "util/debug.h"
+#include "util/evlist.h"
 #include "util/parse-options.h"
-#include "util/session.h"
+#include "util/parse-events.h"
 #include "util/symbol.h"
-#include "util/thread.h"
+#include "util/thread_map.h"
 
 static long page_size;
 
@@ -238,14 +239,14 @@ out:
 #include "util/evsel.h"
 #include <sys/types.h>
 
-static int trace_event__id(const char *event_name)
+static int trace_event__id(const char *evname)
 {
 	char *filename;
 	int err = -1, fd;
 
 	if (asprintf(&filename,
 		     "/sys/kernel/debug/tracing/events/syscalls/%s/id",
-		     event_name) < 0)
+		     evname) < 0)
 		return -1;
 
 	fd = open(filename, O_RDONLY);
@@ -289,7 +290,7 @@ static int test__open_syscall_event(void)
 		goto out_thread_map_delete;
 	}
 
-	if (perf_evsel__open_per_thread(evsel, threads) < 0) {
+	if (perf_evsel__open_per_thread(evsel, threads, false, false) < 0) {
 		pr_debug("failed to open counter: %s, "
 			 "tweak /proc/sys/kernel/perf_event_paranoid?\n",
 			 strerror(errno));
@@ -347,9 +348,9 @@ static int test__open_syscall_event_on_all_cpus(void)
 	}
 
 	cpus = cpu_map__new(NULL);
-	if (threads == NULL) {
-		pr_debug("thread_map__new\n");
-		return -1;
+	if (cpus == NULL) {
+		pr_debug("cpu_map__new\n");
+		goto out_thread_map_delete;
 	}
 
 
@@ -364,7 +365,7 @@ static int test__open_syscall_event_on_all_cpus(void)
 		goto out_thread_map_delete;
 	}
 
-	if (perf_evsel__open(evsel, cpus, threads) < 0) {
+	if (perf_evsel__open(evsel, cpus, threads, false, false) < 0) {
 		pr_debug("failed to open counter: %s, "
 			 "tweak /proc/sys/kernel/perf_event_paranoid?\n",
 			 strerror(errno));
@@ -408,6 +409,8 @@ static int test__open_syscall_event_on_all_cpus(void)
 		goto out_close_fd;
 	}
 
+	err = 0;
+
 	for (cpu = 0; cpu < cpus->nr; ++cpu) {
 		unsigned int expected;
 
@@ -416,18 +419,18 @@ static int test__open_syscall_event_on_all_cpus(void)
 
 		if (perf_evsel__read_on_cpu(evsel, cpu, 0) < 0) {
 			pr_debug("perf_evsel__open_read_on_cpu\n");
-			goto out_close_fd;
+			err = -1;
+			break;
 		}
 
 		expected = nr_open_calls + cpu;
 		if (evsel->counts->cpu[cpu].val != expected) {
 			pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls on cpu %d, got %" PRIu64 "\n",
 				 expected, cpus->map[cpu], evsel->counts->cpu[cpu].val);
-			goto out_close_fd;
+			err = -1;
 		}
 	}
 
-	err = 0;
 out_close_fd:
 	perf_evsel__close_fd(evsel, 1, threads->nr);
 out_evsel_delete:
@@ -437,6 +440,159 @@ out_thread_map_delete:
 	return err;
 }
 
+/*
+ * This test will generate random numbers of calls to some getpid syscalls,
+ * then establish an mmap for a group of events that are created to monitor
+ * the syscalls.
+ *
+ * It will receive the events, using mmap, use its PERF_SAMPLE_ID generated
+ * sample.id field to map back to its respective perf_evsel instance.
+ *
+ * Then it checks if the number of syscalls reported as perf events by
+ * the kernel corresponds to the number of syscalls made.
+ */
+static int test__basic_mmap(void)
+{
+	int err = -1;
+	union perf_event *event;
+	struct thread_map *threads;
+	struct cpu_map *cpus;
+	struct perf_evlist *evlist;
+	struct perf_event_attr attr = {
+		.type		= PERF_TYPE_TRACEPOINT,
+		.read_format	= PERF_FORMAT_ID,
+		.sample_type	= PERF_SAMPLE_ID,
+		.watermark	= 0,
+	};
+	cpu_set_t cpu_set;
+	const char *syscall_names[] = { "getsid", "getppid", "getpgrp",
+					"getpgid", };
+	pid_t (*syscalls[])(void) = { (void *)getsid, getppid, getpgrp,
+				      (void*)getpgid };
+#define nsyscalls ARRAY_SIZE(syscall_names)
+	int ids[nsyscalls];
+	unsigned int nr_events[nsyscalls],
+		     expected_nr_events[nsyscalls], i, j;
+	struct perf_evsel *evsels[nsyscalls], *evsel;
+
+	for (i = 0; i < nsyscalls; ++i) {
+		char name[64];
+
+		snprintf(name, sizeof(name), "sys_enter_%s", syscall_names[i]);
+		ids[i] = trace_event__id(name);
+		if (ids[i] < 0) {
+			pr_debug("Is debugfs mounted on /sys/kernel/debug?\n");
+			return -1;
+		}
+		nr_events[i] = 0;
+		expected_nr_events[i] = random() % 257;
+	}
+
+	threads = thread_map__new(-1, getpid());
+	if (threads == NULL) {
+		pr_debug("thread_map__new\n");
+		return -1;
+	}
+
+	cpus = cpu_map__new(NULL);
+	if (cpus == NULL) {
+		pr_debug("cpu_map__new\n");
+		goto out_free_threads;
+	}
+
+	CPU_ZERO(&cpu_set);
+	CPU_SET(cpus->map[0], &cpu_set);
+	sched_setaffinity(0, sizeof(cpu_set), &cpu_set);
+	if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0) {
+		pr_debug("sched_setaffinity() failed on CPU %d: %s ",
+			 cpus->map[0], strerror(errno));
+		goto out_free_cpus;
+	}
+
+	evlist = perf_evlist__new(cpus, threads);
+	if (evlist == NULL) {
+		pr_debug("perf_evlist__new\n");
+		goto out_free_cpus;
+	}
+
+	/* anonymous union fields, can't be initialized above */
+	attr.wakeup_events = 1;
+	attr.sample_period = 1;
+
+	for (i = 0; i < nsyscalls; ++i) {
+		attr.config = ids[i];
+		evsels[i] = perf_evsel__new(&attr, i);
+		if (evsels[i] == NULL) {
+			pr_debug("perf_evsel__new\n");
+			goto out_free_evlist;
+		}
+
+		perf_evlist__add(evlist, evsels[i]);
+
+		if (perf_evsel__open(evsels[i], cpus, threads, false, false) < 0) {
+			pr_debug("failed to open counter: %s, "
+				 "tweak /proc/sys/kernel/perf_event_paranoid?\n",
+				 strerror(errno));
+			goto out_close_fd;
+		}
+	}
+
+	if (perf_evlist__mmap(evlist, 128, true) < 0) {
+		pr_debug("failed to mmap events: %d (%s)\n", errno,
+			 strerror(errno));
+		goto out_close_fd;
+	}
+
+	for (i = 0; i < nsyscalls; ++i)
+		for (j = 0; j < expected_nr_events[i]; ++j) {
+			int foo = syscalls[i]();
+			++foo;
+		}
+
+	while ((event = perf_evlist__read_on_cpu(evlist, 0)) != NULL) {
+		struct perf_sample sample;
+
+		if (event->header.type != PERF_RECORD_SAMPLE) {
+			pr_debug("unexpected %s event\n",
+				 perf_event__name(event->header.type));
+			goto out_munmap;
+		}
+
+		perf_event__parse_sample(event, attr.sample_type, false, &sample);
+		evsel = perf_evlist__id2evsel(evlist, sample.id);
+		if (evsel == NULL) {
+			pr_debug("event with id %" PRIu64
+				 " doesn't map to an evsel\n", sample.id);
+			goto out_munmap;
+		}
+		nr_events[evsel->idx]++;
+	}
+
+	list_for_each_entry(evsel, &evlist->entries, node) {
+		if (nr_events[evsel->idx] != expected_nr_events[evsel->idx]) {
+			pr_debug("expected %d %s events, got %d\n",
+				 expected_nr_events[evsel->idx],
+				 event_name(evsel), nr_events[evsel->idx]);
+			goto out_munmap;
+		}
+	}
+
+	err = 0;
+out_munmap:
+	perf_evlist__munmap(evlist);
+out_close_fd:
+	for (i = 0; i < nsyscalls; ++i)
+		perf_evsel__close_fd(evsels[i], 1, threads->nr);
+out_free_evlist:
+	perf_evlist__delete(evlist);
+out_free_cpus:
+	cpu_map__delete(cpus);
+out_free_threads:
+	thread_map__delete(threads);
+	return err;
+#undef nsyscalls
+}
+
 static struct test {
 	const char *desc;
 	int (*func)(void);
@@ -454,6 +610,10 @@ static struct test {
 		.func = test__open_syscall_event_on_all_cpus,
 	},
 	{
+		.desc = "read samples using the mmap interface",
+		.func = test__basic_mmap,
+	},
+	{
 		.func = NULL,
 	},
 };
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 0ace786e83e0..67c0459dc325 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -273,21 +273,24 @@ static int cpus_cstate_state[MAX_CPUS];
 static u64 cpus_pstate_start_times[MAX_CPUS];
 static u64 cpus_pstate_state[MAX_CPUS];
 
-static int process_comm_event(event_t *event, struct sample_data *sample __used,
+static int process_comm_event(union perf_event *event,
+			      struct perf_sample *sample __used,
 			      struct perf_session *session __used)
 {
 	pid_set_comm(event->comm.tid, event->comm.comm);
 	return 0;
 }
 
-static int process_fork_event(event_t *event, struct sample_data *sample __used,
+static int process_fork_event(union perf_event *event,
+			      struct perf_sample *sample __used,
 			      struct perf_session *session __used)
 {
 	pid_fork(event->fork.pid, event->fork.ppid, event->fork.time);
 	return 0;
 }
 
-static int process_exit_event(event_t *event, struct sample_data *sample __used,
+static int process_exit_event(union perf_event *event,
+			      struct perf_sample *sample __used,
 			      struct perf_session *session __used)
 {
 	pid_exit(event->fork.pid, event->fork.time);
@@ -483,8 +486,8 @@ static void sched_switch(int cpu, u64 timestamp, struct trace_entry *te)
 }
 
 
-static int process_sample_event(event_t *event __used,
-				struct sample_data *sample,
+static int process_sample_event(union perf_event *event __used,
+				struct perf_sample *sample,
 				struct perf_session *session)
 {
 	struct trace_entry *te;
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 5a29d9cd9486..80c9e062bd5b 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -20,11 +20,16 @@
 
 #include "perf.h"
 
+#include "util/annotate.h"
+#include "util/cache.h"
 #include "util/color.h"
+#include "util/evlist.h"
 #include "util/evsel.h"
 #include "util/session.h"
 #include "util/symbol.h"
 #include "util/thread.h"
+#include "util/thread_map.h"
+#include "util/top.h"
 #include "util/util.h"
 #include <linux/rbtree.h>
 #include "util/parse-options.h"
@@ -45,7 +50,6 @@
 #include <errno.h>
 #include <time.h>
 #include <sched.h>
-#include <pthread.h>
 
 #include <sys/syscall.h>
 #include <sys/ioctl.h>
@@ -60,85 +64,42 @@
 
 #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
 
+static struct perf_top top = {
+	.count_filter		= 5,
+	.delay_secs		= 2,
+	.display_weighted	= -1,
+	.target_pid		= -1,
+	.target_tid		= -1,
+	.active_symbols		= LIST_HEAD_INIT(top.active_symbols),
+	.active_symbols_lock	= PTHREAD_MUTEX_INITIALIZER,
+	.active_symbols_cond	= PTHREAD_COND_INITIALIZER,
+	.freq			= 1000, /* 1 KHz */
+};
+
 static bool			system_wide			=  false;
 
-static int			default_interval		=      0;
+static bool			use_tui, use_stdio;
 
-static int			count_filter			=      5;
-static int			print_entries;
+static int			default_interval		=      0;
 
-static int			target_pid			=     -1;
-static int			target_tid			=     -1;
-static struct thread_map	*threads;
 static bool			inherit				=  false;
-static struct cpu_map		*cpus;
 static int			realtime_prio			=      0;
 static bool			group				=  false;
 static unsigned int		page_size;
-static unsigned int		mmap_pages			=     16;
-static int			freq				=   1000; /* 1 KHz */
+static unsigned int		mmap_pages			=    128;
 
-static int			delay_secs			=      2;
-static bool			zero                            =  false;
 static bool			dump_symtab                     =  false;
 
-static bool			hide_kernel_symbols		=  false;
-static bool			hide_user_symbols		=  false;
 static struct winsize		winsize;
 
-/*
- * Source
- */
-
-struct source_line {
-	u64			eip;
-	unsigned long		count[MAX_COUNTERS];
-	char			*line;
-	struct source_line	*next;
-};
-
 static const char		*sym_filter			=   NULL;
-struct sym_entry		*sym_filter_entry		=   NULL;
 struct sym_entry		*sym_filter_entry_sched		=   NULL;
 static int			sym_pcnt_filter			=      5;
-static int			sym_counter			=      0;
-static struct perf_evsel	*sym_evsel			=   NULL;
-static int			display_weighted		=     -1;
-static const char		*cpu_list;
-
-/*
- * Symbols
- */
-
-struct sym_entry_source {
-	struct source_line	*source;
-	struct source_line	*lines;
-	struct source_line	**lines_tail;
-	pthread_mutex_t		lock;
-};
-
-struct sym_entry {
-	struct rb_node		rb_node;
-	struct list_head	node;
-	unsigned long		snap_count;
-	double			weight;
-	int			skip;
-	u16			name_len;
-	u8			origin;
-	struct map		*map;
-	struct sym_entry_source	*src;
-	unsigned long		count[0];
-};
 
 /*
  * Source functions
  */
 
-static inline struct symbol *sym_entry__symbol(struct sym_entry *self)
-{
-       return ((void *)self) + symbol_conf.priv_size;
-}
-
 void get_term_dimensions(struct winsize *ws)
 {
 	char *s = getenv("LINES");
@@ -163,10 +124,10 @@ void get_term_dimensions(struct winsize *ws)
 
 static void update_print_entries(struct winsize *ws)
 {
-	print_entries = ws->ws_row;
+	top.print_entries = ws->ws_row;
 
-	if (print_entries > 9)
-		print_entries -= 9;
+	if (top.print_entries > 9)
+		top.print_entries -= 9;
 }
 
 static void sig_winch_handler(int sig __used)
@@ -178,12 +139,9 @@ static void sig_winch_handler(int sig __used)
 static int parse_source(struct sym_entry *syme)
 {
 	struct symbol *sym;
-	struct sym_entry_source *source;
+	struct annotation *notes;
 	struct map *map;
-	FILE *file;
-	char command[PATH_MAX*2];
-	const char *path;
-	u64 len;
+	int err = -1;
 
 	if (!syme)
 		return -1;
@@ -194,411 +152,137 @@ static int parse_source(struct sym_entry *syme)
 	/*
 	 * We can't annotate with just /proc/kallsyms
 	 */
-	if (map->dso->origin == DSO__ORIG_KERNEL)
+	if (map->dso->origin == DSO__ORIG_KERNEL) {
+		pr_err("Can't annotate %s: No vmlinux file was found in the "
+		       "path\n", sym->name);
+		sleep(1);
 		return -1;
-
-	if (syme->src == NULL) {
-		syme->src = zalloc(sizeof(*source));
-		if (syme->src == NULL)
-			return -1;
-		pthread_mutex_init(&syme->src->lock, NULL);
 	}
 
-	source = syme->src;
-
-	if (source->lines) {
-		pthread_mutex_lock(&source->lock);
+	notes = symbol__annotation(sym);
+	if (notes->src != NULL) {
+		pthread_mutex_lock(&notes->lock);
 		goto out_assign;
 	}
-	path = map->dso->long_name;
-
-	len = sym->end - sym->start;
-
-	sprintf(command,
-		"objdump --start-address=%#0*" PRIx64 " --stop-address=%#0*" PRIx64 " -dS %s",
-		BITS_PER_LONG / 4, map__rip_2objdump(map, sym->start),
-		BITS_PER_LONG / 4, map__rip_2objdump(map, sym->end), path);
-
-	file = popen(command, "r");
-	if (!file)
-		return -1;
-
-	pthread_mutex_lock(&source->lock);
-	source->lines_tail = &source->lines;
-	while (!feof(file)) {
-		struct source_line *src;
-		size_t dummy = 0;
-		char *c, *sep;
 
-		src = malloc(sizeof(struct source_line));
-		assert(src != NULL);
-		memset(src, 0, sizeof(struct source_line));
+	pthread_mutex_lock(&notes->lock);
 
-		if (getline(&src->line, &dummy, file) < 0)
-			break;
-		if (!src->line)
-			break;
-
-		c = strchr(src->line, '\n');
-		if (c)
-			*c = 0;
-
-		src->next = NULL;
-		*source->lines_tail = src;
-		source->lines_tail = &src->next;
-
-		src->eip = strtoull(src->line, &sep, 16);
-		if (*sep == ':')
-			src->eip = map__objdump_2ip(map, src->eip);
-		else /* this line has no ip info (e.g. source line) */
-			src->eip = 0;
+	if (symbol__alloc_hist(sym, top.evlist->nr_entries) < 0) {
+		pthread_mutex_unlock(&notes->lock);
+		pr_err("Not enough memory for annotating '%s' symbol!\n",
+		       sym->name);
+		sleep(1);
+		return err;
 	}
-	pclose(file);
+
+	err = symbol__annotate(sym, syme->map, 0);
+	if (err == 0) {
 out_assign:
-	sym_filter_entry = syme;
-	pthread_mutex_unlock(&source->lock);
-	return 0;
+		top.sym_filter_entry = syme;
+	}
+
+	pthread_mutex_unlock(&notes->lock);
+	return err;
 }
 
 static void __zero_source_counters(struct sym_entry *syme)
 {
-	int i;
-	struct source_line *line;
-
-	line = syme->src->lines;
-	while (line) {
-		for (i = 0; i < nr_counters; i++)
-			line->count[i] = 0;
-		line = line->next;
-	}
+	struct symbol *sym = sym_entry__symbol(syme);
+	symbol__annotate_zero_histograms(sym);
 }
 
 static void record_precise_ip(struct sym_entry *syme, int counter, u64 ip)
 {
-	struct source_line *line;
-
-	if (syme != sym_filter_entry)
-		return;
+	struct annotation *notes;
+	struct symbol *sym;
 
-	if (pthread_mutex_trylock(&syme->src->lock))
+	if (syme != top.sym_filter_entry)
 		return;
 
-	if (syme->src == NULL || syme->src->source == NULL)
-		goto out_unlock;
-
-	for (line = syme->src->lines; line; line = line->next) {
-		/* skip lines without IP info */
-		if (line->eip == 0)
-			continue;
-		if (line->eip == ip) {
-			line->count[counter]++;
-			break;
-		}
-		if (line->eip > ip)
-			break;
-	}
-out_unlock:
-	pthread_mutex_unlock(&syme->src->lock);
-}
-
-#define PATTERN_LEN		(BITS_PER_LONG / 4 + 2)
-
-static void lookup_sym_source(struct sym_entry *syme)
-{
-	struct symbol *symbol = sym_entry__symbol(syme);
-	struct source_line *line;
-	char pattern[PATTERN_LEN + 1];
-
-	sprintf(pattern, "%0*" PRIx64 " <", BITS_PER_LONG / 4,
-		map__rip_2objdump(syme->map, symbol->start));
-
-	pthread_mutex_lock(&syme->src->lock);
-	for (line = syme->src->lines; line; line = line->next) {
-		if (memcmp(line->line, pattern, PATTERN_LEN) == 0) {
-			syme->src->source = line;
-			break;
-		}
-	}
-	pthread_mutex_unlock(&syme->src->lock);
-}
+	sym = sym_entry__symbol(syme);
+	notes = symbol__annotation(sym);
 
-static void show_lines(struct source_line *queue, int count, int total)
-{
-	int i;
-	struct source_line *line;
+	if (pthread_mutex_trylock(&notes->lock))
+		return;
 
-	line = queue;
-	for (i = 0; i < count; i++) {
-		float pcnt = 100.0*(float)line->count[sym_counter]/(float)total;
+	ip = syme->map->map_ip(syme->map, ip);
+	symbol__inc_addr_samples(sym, syme->map, counter, ip);
 
-		printf("%8li %4.1f%%\t%s\n", line->count[sym_counter], pcnt, line->line);
-		line = line->next;
-	}
+	pthread_mutex_unlock(&notes->lock);
 }
 
-#define TRACE_COUNT     3
-
 static void show_details(struct sym_entry *syme)
 {
+	struct annotation *notes;
 	struct symbol *symbol;
-	struct source_line *line;
-	struct source_line *line_queue = NULL;
-	int displayed = 0;
-	int line_queue_count = 0, total = 0, more = 0;
+	int more;
 
 	if (!syme)
 		return;
 
-	if (!syme->src->source)
-		lookup_sym_source(syme);
-
-	if (!syme->src->source)
-		return;
-
 	symbol = sym_entry__symbol(syme);
-	printf("Showing %s for %s\n", event_name(sym_evsel), symbol->name);
-	printf("  Events  Pcnt (>=%d%%)\n", sym_pcnt_filter);
-
-	pthread_mutex_lock(&syme->src->lock);
-	line = syme->src->source;
-	while (line) {
-		total += line->count[sym_counter];
-		line = line->next;
-	}
-
-	line = syme->src->source;
-	while (line) {
-		float pcnt = 0.0;
-
-		if (!line_queue_count)
-			line_queue = line;
-		line_queue_count++;
-
-		if (line->count[sym_counter])
-			pcnt = 100.0 * line->count[sym_counter] / (float)total;
-		if (pcnt >= (float)sym_pcnt_filter) {
-			if (displayed <= print_entries)
-				show_lines(line_queue, line_queue_count, total);
-			else more++;
-			displayed += line_queue_count;
-			line_queue_count = 0;
-			line_queue = NULL;
-		} else if (line_queue_count > TRACE_COUNT) {
-			line_queue = line_queue->next;
-			line_queue_count--;
-		}
-
-		line->count[sym_counter] = zero ? 0 : line->count[sym_counter] * 7 / 8;
-		line = line->next;
-	}
-	pthread_mutex_unlock(&syme->src->lock);
-	if (more)
-		printf("%d lines not displayed, maybe increase display entries [e]\n", more);
-}
+	notes = symbol__annotation(symbol);
 
-/*
- * Symbols will be added here in event__process_sample and will get out
- * after decayed.
- */
-static LIST_HEAD(active_symbols);
-static pthread_mutex_t active_symbols_lock = PTHREAD_MUTEX_INITIALIZER;
-
-/*
- * Ordering weight: count-1 * count-2 * ... / count-n
- */
-static double sym_weight(const struct sym_entry *sym)
-{
-	double weight = sym->snap_count;
-	int counter;
-
-	if (!display_weighted)
-		return weight;
+	pthread_mutex_lock(&notes->lock);
 
-	for (counter = 1; counter < nr_counters-1; counter++)
-		weight *= sym->count[counter];
+	if (notes->src == NULL)
+		goto out_unlock;
 
-	weight /= (sym->count[counter] + 1);
+	printf("Showing %s for %s\n", event_name(top.sym_evsel), symbol->name);
+	printf("  Events  Pcnt (>=%d%%)\n", sym_pcnt_filter);
 
-	return weight;
+	more = symbol__annotate_printf(symbol, syme->map, top.sym_evsel->idx,
+				       0, sym_pcnt_filter, top.print_entries, 4);
+	if (top.zero)
+		symbol__annotate_zero_histogram(symbol, top.sym_evsel->idx);
+	else
+		symbol__annotate_decay_histogram(symbol, top.sym_evsel->idx);
+	if (more != 0)
+		printf("%d lines not displayed, maybe increase display entries [e]\n", more);
+out_unlock:
+	pthread_mutex_unlock(&notes->lock);
 }
 
-static long			samples;
-static long			kernel_samples, us_samples;
-static long			exact_samples;
-static long			guest_us_samples, guest_kernel_samples;
 static const char		CONSOLE_CLEAR[] = "";
 
 static void __list_insert_active_sym(struct sym_entry *syme)
 {
-	list_add(&syme->node, &active_symbols);
-}
-
-static void list_remove_active_sym(struct sym_entry *syme)
-{
-	pthread_mutex_lock(&active_symbols_lock);
-	list_del_init(&syme->node);
-	pthread_mutex_unlock(&active_symbols_lock);
+	list_add(&syme->node, &top.active_symbols);
 }
 
-static void rb_insert_active_sym(struct rb_root *tree, struct sym_entry *se)
+static void print_sym_table(struct perf_session *session)
 {
-	struct rb_node **p = &tree->rb_node;
-	struct rb_node *parent = NULL;
-	struct sym_entry *iter;
-
-	while (*p != NULL) {
-		parent = *p;
-		iter = rb_entry(parent, struct sym_entry, rb_node);
-
-		if (se->weight > iter->weight)
-			p = &(*p)->rb_left;
-		else
-			p = &(*p)->rb_right;
-	}
-
-	rb_link_node(&se->rb_node, parent, p);
-	rb_insert_color(&se->rb_node, tree);
-}
-
-static void print_sym_table(void)
-{
-	int printed = 0, j;
-	struct perf_evsel *counter;
-	int snap = !display_weighted ? sym_counter : 0;
-	float samples_per_sec = samples/delay_secs;
-	float ksamples_per_sec = kernel_samples/delay_secs;
-	float us_samples_per_sec = (us_samples)/delay_secs;
-	float guest_kernel_samples_per_sec = (guest_kernel_samples)/delay_secs;
-	float guest_us_samples_per_sec = (guest_us_samples)/delay_secs;
-	float esamples_percent = (100.0*exact_samples)/samples;
-	float sum_ksamples = 0.0;
-	struct sym_entry *syme, *n;
-	struct rb_root tmp = RB_ROOT;
+	char bf[160];
+	int printed = 0;
 	struct rb_node *nd;
-	int sym_width = 0, dso_width = 0, dso_short_width = 0;
+	struct sym_entry *syme;
+	struct rb_root tmp = RB_ROOT;
 	const int win_width = winsize.ws_col - 1;
-
-	samples = us_samples = kernel_samples = exact_samples = 0;
-	guest_kernel_samples = guest_us_samples = 0;
-
-	/* Sort the active symbols */
-	pthread_mutex_lock(&active_symbols_lock);
-	syme = list_entry(active_symbols.next, struct sym_entry, node);
-	pthread_mutex_unlock(&active_symbols_lock);
-
-	list_for_each_entry_safe_from(syme, n, &active_symbols, node) {
-		syme->snap_count = syme->count[snap];
-		if (syme->snap_count != 0) {
-
-			if ((hide_user_symbols &&
-			     syme->origin == PERF_RECORD_MISC_USER) ||
-			    (hide_kernel_symbols &&
-			     syme->origin == PERF_RECORD_MISC_KERNEL)) {
-				list_remove_active_sym(syme);
-				continue;
-			}
-			syme->weight = sym_weight(syme);
-			rb_insert_active_sym(&tmp, syme);
-			sum_ksamples += syme->snap_count;
-
-			for (j = 0; j < nr_counters; j++)
-				syme->count[j] = zero ? 0 : syme->count[j] * 7 / 8;
-		} else
-			list_remove_active_sym(syme);
-	}
+	int sym_width, dso_width, dso_short_width;
+	float sum_ksamples = perf_top__decay_samples(&top, &tmp);
 
 	puts(CONSOLE_CLEAR);
 
-	printf("%-*.*s\n", win_width, win_width, graph_dotted_line);
-	if (!perf_guest) {
-		printf("   PerfTop:%8.0f irqs/sec  kernel:%4.1f%%"
-			"  exact: %4.1f%% [",
-			samples_per_sec,
-			100.0 - (100.0 * ((samples_per_sec - ksamples_per_sec) /
-					 samples_per_sec)),
-			esamples_percent);
-	} else {
-		printf("   PerfTop:%8.0f irqs/sec  kernel:%4.1f%% us:%4.1f%%"
-			" guest kernel:%4.1f%% guest us:%4.1f%%"
-			" exact: %4.1f%% [",
-			samples_per_sec,
-			100.0 - (100.0 * ((samples_per_sec-ksamples_per_sec) /
-					  samples_per_sec)),
-			100.0 - (100.0 * ((samples_per_sec-us_samples_per_sec) /
-					  samples_per_sec)),
-			100.0 - (100.0 * ((samples_per_sec -
-						guest_kernel_samples_per_sec) /
-					  samples_per_sec)),
-			100.0 - (100.0 * ((samples_per_sec -
-					   guest_us_samples_per_sec) /
-					  samples_per_sec)),
-			esamples_percent);
-	}
-
-	if (nr_counters == 1 || !display_weighted) {
-		struct perf_evsel *first;
-		first = list_entry(evsel_list.next, struct perf_evsel, node);
-		printf("%" PRIu64, (uint64_t)first->attr.sample_period);
-		if (freq)
-			printf("Hz ");
-		else
-			printf(" ");
-	}
-
-	if (!display_weighted)
-		printf("%s", event_name(sym_evsel));
-	else list_for_each_entry(counter, &evsel_list, node) {
-		if (counter->idx)
-			printf("/");
-
-		printf("%s", event_name(counter));
-	}
+	perf_top__header_snprintf(&top, bf, sizeof(bf));
+	printf("%s\n", bf);
 
-	printf( "], ");
-
-	if (target_pid != -1)
-		printf(" (target_pid: %d", target_pid);
-	else if (target_tid != -1)
-		printf(" (target_tid: %d", target_tid);
-	else
-		printf(" (all");
-
-	if (cpu_list)
-		printf(", CPU%s: %s)\n", cpus->nr > 1 ? "s" : "", cpu_list);
-	else {
-		if (target_tid != -1)
-			printf(")\n");
-		else
-			printf(", %d CPU%s)\n", cpus->nr, cpus->nr > 1 ? "s" : "");
-	}
+	perf_top__reset_sample_counters(&top);
 
 	printf("%-*.*s\n", win_width, win_width, graph_dotted_line);
 
-	if (sym_filter_entry) {
-		show_details(sym_filter_entry);
-		return;
+	if (session->hists.stats.total_lost != 0) {
+		color_fprintf(stdout, PERF_COLOR_RED, "WARNING:");
+		printf(" LOST %" PRIu64 " events, Check IO/CPU overload\n",
+		       session->hists.stats.total_lost);
 	}
 
-	/*
-	 * Find the longest symbol name that will be displayed
-	 */
-	for (nd = rb_first(&tmp); nd; nd = rb_next(nd)) {
-		syme = rb_entry(nd, struct sym_entry, rb_node);
-		if (++printed > print_entries ||
-		    (int)syme->snap_count < count_filter)
-			continue;
-
-		if (syme->map->dso->long_name_len > dso_width)
-			dso_width = syme->map->dso->long_name_len;
-
-		if (syme->map->dso->short_name_len > dso_short_width)
-			dso_short_width = syme->map->dso->short_name_len;
-
-		if (syme->name_len > sym_width)
-			sym_width = syme->name_len;
+	if (top.sym_filter_entry) {
+		show_details(top.sym_filter_entry);
+		return;
 	}
 
-	printed = 0;
+	perf_top__find_widths(&top, &tmp, &dso_width, &dso_short_width,
+			      &sym_width);
 
 	if (sym_width + dso_width > winsize.ws_col - 29) {
 		dso_width = dso_short_width;
@@ -606,7 +290,7 @@ static void print_sym_table(void)
 			sym_width = winsize.ws_col - dso_width - 29;
 	}
 	putchar('\n');
-	if (nr_counters == 1)
+	if (top.evlist->nr_entries == 1)
 		printf("             samples  pcnt");
 	else
 		printf("   weight    samples  pcnt");
@@ -615,7 +299,7 @@ static void print_sym_table(void)
 		printf("         RIP       ");
 	printf(" %-*.*s DSO\n", sym_width, sym_width, "function");
 	printf("   %s    _______ _____",
-	       nr_counters == 1 ? "      " : "______");
+	       top.evlist->nr_entries == 1 ? "      " : "______");
 	if (verbose)
 		printf(" ________________");
 	printf(" %-*.*s", sym_width, sym_width, graph_line);
@@ -628,13 +312,14 @@ static void print_sym_table(void)
 
 		syme = rb_entry(nd, struct sym_entry, rb_node);
 		sym = sym_entry__symbol(syme);
-		if (++printed > print_entries || (int)syme->snap_count < count_filter)
+		if (++printed > top.print_entries ||
+		    (int)syme->snap_count < top.count_filter)
 			continue;
 
 		pcnt = 100.0 - (100.0 * ((sum_ksamples - syme->snap_count) /
 					 sum_ksamples));
 
-		if (nr_counters == 1 || !display_weighted)
+		if (top.evlist->nr_entries == 1 || !top.display_weighted)
 			printf("%20.2f ", syme->weight);
 		else
 			printf("%9.1f %10ld ", syme->weight, syme->snap_count);
@@ -693,10 +378,8 @@ static void prompt_symbol(struct sym_entry **target, const char *msg)
 
 	/* zero counters of active symbol */
 	if (syme) {
-		pthread_mutex_lock(&syme->src->lock);
 		__zero_source_counters(syme);
 		*target = NULL;
-		pthread_mutex_unlock(&syme->src->lock);
 	}
 
 	fprintf(stdout, "\n%s: ", msg);
@@ -707,11 +390,11 @@ static void prompt_symbol(struct sym_entry **target, const char *msg)
 	if (p)
 		*p = 0;
 
-	pthread_mutex_lock(&active_symbols_lock);
-	syme = list_entry(active_symbols.next, struct sym_entry, node);
-	pthread_mutex_unlock(&active_symbols_lock);
+	pthread_mutex_lock(&top.active_symbols_lock);
+	syme = list_entry(top.active_symbols.next, struct sym_entry, node);
+	pthread_mutex_unlock(&top.active_symbols_lock);
 
-	list_for_each_entry_safe_from(syme, n, &active_symbols, node) {
+	list_for_each_entry_safe_from(syme, n, &top.active_symbols, node) {
 		struct symbol *sym = sym_entry__symbol(syme);
 
 		if (!strcmp(buf, sym->name)) {
@@ -735,34 +418,34 @@ static void print_mapped_keys(void)
 {
 	char *name = NULL;
 
-	if (sym_filter_entry) {
-		struct symbol *sym = sym_entry__symbol(sym_filter_entry);
+	if (top.sym_filter_entry) {
+		struct symbol *sym = sym_entry__symbol(top.sym_filter_entry);
 		name = sym->name;
 	}
 
 	fprintf(stdout, "\nMapped keys:\n");
-	fprintf(stdout, "\t[d]     display refresh delay.             \t(%d)\n", delay_secs);
-	fprintf(stdout, "\t[e]     display entries (lines).           \t(%d)\n", print_entries);
+	fprintf(stdout, "\t[d]     display refresh delay.             \t(%d)\n", top.delay_secs);
+	fprintf(stdout, "\t[e]     display entries (lines).           \t(%d)\n", top.print_entries);
 
-	if (nr_counters > 1)
-		fprintf(stdout, "\t[E]     active event counter.              \t(%s)\n", event_name(sym_evsel));
+	if (top.evlist->nr_entries > 1)
+		fprintf(stdout, "\t[E]     active event counter.              \t(%s)\n", event_name(top.sym_evsel));
 
-	fprintf(stdout, "\t[f]     profile display filter (count).    \t(%d)\n", count_filter);
+	fprintf(stdout, "\t[f]     profile display filter (count).    \t(%d)\n", top.count_filter);
 
 	fprintf(stdout, "\t[F]     annotate display filter (percent). \t(%d%%)\n", sym_pcnt_filter);
 	fprintf(stdout, "\t[s]     annotate symbol.                   \t(%s)\n", name?: "NULL");
 	fprintf(stdout, "\t[S]     stop annotation.\n");
 
-	if (nr_counters > 1)
-		fprintf(stdout, "\t[w]     toggle display weighted/count[E]r. \t(%d)\n", display_weighted ? 1 : 0);
+	if (top.evlist->nr_entries > 1)
+		fprintf(stdout, "\t[w]     toggle display weighted/count[E]r. \t(%d)\n", top.display_weighted ? 1 : 0);
 
 	fprintf(stdout,
 		"\t[K]     hide kernel_symbols symbols.     \t(%s)\n",
-		hide_kernel_symbols ? "yes" : "no");
+		top.hide_kernel_symbols ? "yes" : "no");
 	fprintf(stdout,
 		"\t[U]     hide user symbols.               \t(%s)\n",
-		hide_user_symbols ? "yes" : "no");
-	fprintf(stdout, "\t[z]     toggle sample zeroing.             \t(%d)\n", zero ? 1 : 0);
+		top.hide_user_symbols ? "yes" : "no");
+	fprintf(stdout, "\t[z]     toggle sample zeroing.             \t(%d)\n", top.zero ? 1 : 0);
 	fprintf(stdout, "\t[qQ]    quit.\n");
 }
 
@@ -783,7 +466,7 @@ static int key_mapped(int c)
 			return 1;
 		case 'E':
 		case 'w':
-			return nr_counters > 1 ? 1 : 0;
+			return top.evlist->nr_entries > 1 ? 1 : 0;
 		default:
 			break;
 	}
@@ -818,47 +501,47 @@ static void handle_keypress(struct perf_session *session, int c)
 
 	switch (c) {
 		case 'd':
-			prompt_integer(&delay_secs, "Enter display delay");
-			if (delay_secs < 1)
-				delay_secs = 1;
+			prompt_integer(&top.delay_secs, "Enter display delay");
+			if (top.delay_secs < 1)
+				top.delay_secs = 1;
 			break;
 		case 'e':
-			prompt_integer(&print_entries, "Enter display entries (lines)");
-			if (print_entries == 0) {
+			prompt_integer(&top.print_entries, "Enter display entries (lines)");
+			if (top.print_entries == 0) {
 				sig_winch_handler(SIGWINCH);
 				signal(SIGWINCH, sig_winch_handler);
 			} else
 				signal(SIGWINCH, SIG_DFL);
 			break;
 		case 'E':
-			if (nr_counters > 1) {
+			if (top.evlist->nr_entries > 1) {
 				fprintf(stderr, "\nAvailable events:");
 
-				list_for_each_entry(sym_evsel, &evsel_list, node)
-					fprintf(stderr, "\n\t%d %s", sym_evsel->idx, event_name(sym_evsel));
+				list_for_each_entry(top.sym_evsel, &top.evlist->entries, node)
+					fprintf(stderr, "\n\t%d %s", top.sym_evsel->idx, event_name(top.sym_evsel));
 
-				prompt_integer(&sym_counter, "Enter details event counter");
+				prompt_integer(&top.sym_counter, "Enter details event counter");
 
-				if (sym_counter >= nr_counters) {
-					sym_evsel = list_entry(evsel_list.next, struct perf_evsel, node);
-					sym_counter = 0;
-					fprintf(stderr, "Sorry, no such event, using %s.\n", event_name(sym_evsel));
+				if (top.sym_counter >= top.evlist->nr_entries) {
+					top.sym_evsel = list_entry(top.evlist->entries.next, struct perf_evsel, node);
+					top.sym_counter = 0;
+					fprintf(stderr, "Sorry, no such event, using %s.\n", event_name(top.sym_evsel));
 					sleep(1);
 					break;
 				}
-				list_for_each_entry(sym_evsel, &evsel_list, node)
-					if (sym_evsel->idx == sym_counter)
+				list_for_each_entry(top.sym_evsel, &top.evlist->entries, node)
+					if (top.sym_evsel->idx == top.sym_counter)
 						break;
-			} else sym_counter = 0;
+			} else top.sym_counter = 0;
 			break;
 		case 'f':
-			prompt_integer(&count_filter, "Enter display event count filter");
+			prompt_integer(&top.count_filter, "Enter display event count filter");
 			break;
 		case 'F':
 			prompt_percent(&sym_pcnt_filter, "Enter details display event filter (percent)");
 			break;
 		case 'K':
-			hide_kernel_symbols = !hide_kernel_symbols;
+			top.hide_kernel_symbols = !top.hide_kernel_symbols;
 			break;
 		case 'q':
 		case 'Q':
@@ -867,34 +550,50 @@ static void handle_keypress(struct perf_session *session, int c)
 				perf_session__fprintf_dsos(session, stderr);
 			exit(0);
 		case 's':
-			prompt_symbol(&sym_filter_entry, "Enter details symbol");
+			prompt_symbol(&top.sym_filter_entry, "Enter details symbol");
 			break;
 		case 'S':
-			if (!sym_filter_entry)
+			if (!top.sym_filter_entry)
 				break;
 			else {
-				struct sym_entry *syme = sym_filter_entry;
+				struct sym_entry *syme = top.sym_filter_entry;
 
-				pthread_mutex_lock(&syme->src->lock);
-				sym_filter_entry = NULL;
+				top.sym_filter_entry = NULL;
 				__zero_source_counters(syme);
-				pthread_mutex_unlock(&syme->src->lock);
 			}
 			break;
 		case 'U':
-			hide_user_symbols = !hide_user_symbols;
+			top.hide_user_symbols = !top.hide_user_symbols;
 			break;
 		case 'w':
-			display_weighted = ~display_weighted;
+			top.display_weighted = ~top.display_weighted;
 			break;
 		case 'z':
-			zero = !zero;
+			top.zero = !top.zero;
 			break;
 		default:
 			break;
 	}
 }
 
+static void *display_thread_tui(void *arg __used)
+{
+	int err = 0;
+	pthread_mutex_lock(&top.active_symbols_lock);
+	while (list_empty(&top.active_symbols)) {
+		err = pthread_cond_wait(&top.active_symbols_cond,
+					&top.active_symbols_lock);
+		if (err)
+			break;
+	}
+	pthread_mutex_unlock(&top.active_symbols_lock);
+	if (!err)
+		perf_top__tui_browser(&top);
+	exit_browser(0);
+	exit(0);
+	return NULL;
+}
+
 static void *display_thread(void *arg __used)
 {
 	struct pollfd stdin_poll = { .fd = 0, .events = POLLIN };
@@ -909,13 +608,13 @@ static void *display_thread(void *arg __used)
 	tc.c_cc[VTIME] = 0;
 
 repeat:
-	delay_msecs = delay_secs * 1000;
+	delay_msecs = top.delay_secs * 1000;
 	tcsetattr(0, TCSANOW, &tc);
 	/* trash return*/
 	getc(stdin);
 
 	do {
-		print_sym_table();
+		print_sym_table(session);
 	} while (!poll(&stdin_poll, 1, delay_msecs) == 1);
 
 	c = getc(stdin);
@@ -930,6 +629,7 @@ repeat:
 /* Tag samples to be skipped. */
 static const char *skip_symbols[] = {
 	"default_idle",
+	"native_safe_halt",
 	"cpu_idle",
 	"enter_idle",
 	"exit_idle",
@@ -965,9 +665,9 @@ static int symbol_filter(struct map *map, struct symbol *sym)
 
 	syme = symbol__priv(sym);
 	syme->map = map;
-	syme->src = NULL;
+	symbol__annotate_init(map, sym);
 
-	if (!sym_filter_entry && sym_filter && !strcmp(name, sym_filter)) {
+	if (!top.sym_filter_entry && sym_filter && !strcmp(name, sym_filter)) {
 		/* schedule initial sym_filter_entry setup */
 		sym_filter_entry_sched = syme;
 		sym_filter = NULL;
@@ -980,44 +680,40 @@ static int symbol_filter(struct map *map, struct symbol *sym)
 		}
 	}
 
-	if (!syme->skip)
-		syme->name_len = strlen(sym->name);
-
 	return 0;
 }
 
-static void event__process_sample(const event_t *self,
-				  struct sample_data *sample,
-				  struct perf_session *session,
-				  struct perf_evsel *evsel)
+static void perf_event__process_sample(const union perf_event *event,
+				       struct perf_sample *sample,
+				       struct perf_session *session)
 {
-	u64 ip = self->ip.ip;
+	u64 ip = event->ip.ip;
 	struct sym_entry *syme;
 	struct addr_location al;
 	struct machine *machine;
-	u8 origin = self->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+	u8 origin = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
-	++samples;
+	++top.samples;
 
 	switch (origin) {
 	case PERF_RECORD_MISC_USER:
-		++us_samples;
-		if (hide_user_symbols)
+		++top.us_samples;
+		if (top.hide_user_symbols)
 			return;
 		machine = perf_session__find_host_machine(session);
 		break;
 	case PERF_RECORD_MISC_KERNEL:
-		++kernel_samples;
-		if (hide_kernel_symbols)
+		++top.kernel_samples;
+		if (top.hide_kernel_symbols)
 			return;
 		machine = perf_session__find_host_machine(session);
 		break;
 	case PERF_RECORD_MISC_GUEST_KERNEL:
-		++guest_kernel_samples;
-		machine = perf_session__find_machine(session, self->ip.pid);
+		++top.guest_kernel_samples;
+		machine = perf_session__find_machine(session, event->ip.pid);
 		break;
 	case PERF_RECORD_MISC_GUEST_USER:
-		++guest_us_samples;
+		++top.guest_us_samples;
 		/*
 		 * TODO: we don't process guest user from host side
 		 * except simple counting.
@@ -1029,15 +725,15 @@ static void event__process_sample(const event_t *self,
 
 	if (!machine && perf_guest) {
 		pr_err("Can't find guest [%d]'s kernel information\n",
-			self->ip.pid);
+			event->ip.pid);
 		return;
 	}
 
-	if (self->header.misc & PERF_RECORD_MISC_EXACT_IP)
-		exact_samples++;
+	if (event->header.misc & PERF_RECORD_MISC_EXACT_IP)
+		top.exact_samples++;
 
-	if (event__preprocess_sample(self, session, &al, sample,
-				     symbol_filter) < 0 ||
+	if (perf_event__preprocess_sample(event, session, &al, sample,
+					  symbol_filter) < 0 ||
 	    al.filtered)
 		return;
 
@@ -1055,8 +751,9 @@ static void event__process_sample(const event_t *self,
 		 */
 		if (al.map == machine->vmlinux_maps[MAP__FUNCTION] &&
 		    RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION])) {
-			pr_err("The %s file can't be used\n",
-			       symbol_conf.vmlinux_name);
+			ui__warning("The %s file can't be used\n",
+				    symbol_conf.vmlinux_name);
+			exit_browser(0);
 			exit(1);
 		}
 
@@ -1065,13 +762,13 @@ static void event__process_sample(const event_t *self,
 
 	/* let's see, whether we need to install initial sym_filter_entry */
 	if (sym_filter_entry_sched) {
-		sym_filter_entry = sym_filter_entry_sched;
+		top.sym_filter_entry = sym_filter_entry_sched;
 		sym_filter_entry_sched = NULL;
-		if (parse_source(sym_filter_entry) < 0) {
-			struct symbol *sym = sym_entry__symbol(sym_filter_entry);
+		if (parse_source(top.sym_filter_entry) < 0) {
+			struct symbol *sym = sym_entry__symbol(top.sym_filter_entry);
 
 			pr_err("Can't annotate %s", sym->name);
-			if (sym_filter_entry->map->dso->origin == DSO__ORIG_KERNEL) {
+			if (top.sym_filter_entry->map->dso->origin == DSO__ORIG_KERNEL) {
 				pr_err(": No vmlinux file was found in the path:\n");
 				machine__fprintf_vmlinux_path(machine, stderr);
 			} else
@@ -1082,166 +779,73 @@ static void event__process_sample(const event_t *self,
 
 	syme = symbol__priv(al.sym);
 	if (!syme->skip) {
-		syme->count[evsel->idx]++;
+		struct perf_evsel *evsel;
+
 		syme->origin = origin;
+		evsel = perf_evlist__id2evsel(top.evlist, sample->id);
+		assert(evsel != NULL);
+		syme->count[evsel->idx]++;
 		record_precise_ip(syme, evsel->idx, ip);
-		pthread_mutex_lock(&active_symbols_lock);
-		if (list_empty(&syme->node) || !syme->node.next)
+		pthread_mutex_lock(&top.active_symbols_lock);
+		if (list_empty(&syme->node) || !syme->node.next) {
+			static bool first = true;
 			__list_insert_active_sym(syme);
-		pthread_mutex_unlock(&active_symbols_lock);
+			if (first) {
+				pthread_cond_broadcast(&top.active_symbols_cond);
+				first = false;
+			}
+		}
+		pthread_mutex_unlock(&top.active_symbols_lock);
 	}
 }
 
-struct mmap_data {
-	void			*base;
-	int			mask;
-	unsigned int		prev;
-};
-
-static int perf_evsel__alloc_mmap_per_thread(struct perf_evsel *evsel,
-					     int ncpus, int nthreads)
-{
-	evsel->priv = xyarray__new(ncpus, nthreads, sizeof(struct mmap_data));
-	return evsel->priv != NULL ? 0 : -ENOMEM;
-}
-
-static void perf_evsel__free_mmap(struct perf_evsel *evsel)
-{
-	xyarray__delete(evsel->priv);
-	evsel->priv = NULL;
-}
-
-static unsigned int mmap_read_head(struct mmap_data *md)
-{
-	struct perf_event_mmap_page *pc = md->base;
-	int head;
-
-	head = pc->data_head;
-	rmb();
-
-	return head;
-}
-
-static void perf_session__mmap_read_counter(struct perf_session *self,
-					    struct perf_evsel *evsel,
-					    int cpu, int thread_idx)
+static void perf_session__mmap_read_cpu(struct perf_session *self, int cpu)
 {
-	struct xyarray *mmap_array = evsel->priv;
-	struct mmap_data *md = xyarray__entry(mmap_array, cpu, thread_idx);
-	unsigned int head = mmap_read_head(md);
-	unsigned int old = md->prev;
-	unsigned char *data = md->base + page_size;
-	struct sample_data sample;
-	int diff;
-
-	/*
-	 * If we're further behind than half the buffer, there's a chance
-	 * the writer will bite our tail and mess up the samples under us.
-	 *
-	 * If we somehow ended up ahead of the head, we got messed up.
-	 *
-	 * In either case, truncate and restart at head.
-	 */
-	diff = head - old;
-	if (diff > md->mask / 2 || diff < 0) {
-		fprintf(stderr, "WARNING: failed to keep up with mmap data.\n");
-
-		/*
-		 * head points to a known good entry, start there.
-		 */
-		old = head;
-	}
-
-	for (; old != head;) {
-		event_t *event = (event_t *)&data[old & md->mask];
-
-		event_t event_copy;
+	struct perf_sample sample;
+	union perf_event *event;
 
-		size_t size = event->header.size;
+	while ((event = perf_evlist__read_on_cpu(top.evlist, cpu)) != NULL) {
+		perf_session__parse_sample(self, event, &sample);
 
-		/*
-		 * Event straddles the mmap boundary -- header should always
-		 * be inside due to u64 alignment of output.
-		 */
-		if ((old & md->mask) + size != ((old + size) & md->mask)) {
-			unsigned int offset = old;
-			unsigned int len = min(sizeof(*event), size), cpy;
-			void *dst = &event_copy;
-
-			do {
-				cpy = min(md->mask + 1 - (offset & md->mask), len);
-				memcpy(dst, &data[offset & md->mask], cpy);
-				offset += cpy;
-				dst += cpy;
-				len -= cpy;
-			} while (len);
-
-			event = &event_copy;
-		}
-
-		event__parse_sample(event, self, &sample);
 		if (event->header.type == PERF_RECORD_SAMPLE)
-			event__process_sample(event, &sample, self, evsel);
+			perf_event__process_sample(event, &sample, self);
 		else
-			event__process(event, &sample, self);
-		old += size;
+			perf_event__process(event, &sample, self);
 	}
-
-	md->prev = old;
 }
 
-static struct pollfd *event_array;
-
 static void perf_session__mmap_read(struct perf_session *self)
 {
-	struct perf_evsel *counter;
-	int i, thread_index;
-
-	for (i = 0; i < cpus->nr; i++) {
-		list_for_each_entry(counter, &evsel_list, node) {
-			for (thread_index = 0;
-				thread_index < threads->nr;
-				thread_index++) {
-				perf_session__mmap_read_counter(self,
-					counter, i, thread_index);
-			}
-		}
-	}
-}
+	int i;
 
-int nr_poll;
-int group_fd;
+	for (i = 0; i < top.evlist->cpus->nr; i++)
+		perf_session__mmap_read_cpu(self, i);
+}
 
-static void start_counter(int i, struct perf_evsel *evsel)
+static void start_counters(struct perf_evlist *evlist)
 {
-	struct xyarray *mmap_array = evsel->priv;
-	struct mmap_data *mm;
-	struct perf_event_attr *attr;
-	int cpu = -1;
-	int thread_index;
-
-	if (target_tid == -1)
-		cpu = cpus->map[i];
+	struct perf_evsel *counter;
 
-	attr = &evsel->attr;
+	list_for_each_entry(counter, &evlist->entries, node) {
+		struct perf_event_attr *attr = &counter->attr;
 
-	attr->sample_type	= PERF_SAMPLE_IP | PERF_SAMPLE_TID;
+		attr->sample_type = PERF_SAMPLE_IP | PERF_SAMPLE_TID;
 
-	if (freq) {
-		attr->sample_type	|= PERF_SAMPLE_PERIOD;
-		attr->freq		= 1;
-		attr->sample_freq	= freq;
-	}
+		if (top.freq) {
+			attr->sample_type |= PERF_SAMPLE_PERIOD;
+			attr->freq	  = 1;
+			attr->sample_freq = top.freq;
+		}
 
-	attr->inherit		= (cpu < 0) && inherit;
-	attr->mmap		= 1;
+		if (evlist->nr_entries > 1) {
+			attr->sample_type |= PERF_SAMPLE_ID;
+			attr->read_format |= PERF_FORMAT_ID;
+		}
 
-	for (thread_index = 0; thread_index < threads->nr; thread_index++) {
+		attr->mmap = 1;
 try_again:
-		FD(evsel, i, thread_index) = sys_perf_event_open(attr,
-				threads->map[thread_index], cpu, group_fd, 0);
-
-		if (FD(evsel, i, thread_index) < 0) {
+		if (perf_evsel__open(counter, top.evlist->cpus,
+				     top.evlist->threads, group, inherit) < 0) {
 			int err = errno;
 
 			if (err == EPERM || err == EACCES)
@@ -1253,8 +857,8 @@ try_again:
 			 * based cpu-clock-tick sw counter, which
 			 * is always available even if no PMU support:
 			 */
-			if (attr->type == PERF_TYPE_HARDWARE
-					&& attr->config == PERF_COUNT_HW_CPU_CYCLES) {
+			if (attr->type == PERF_TYPE_HARDWARE &&
+			    attr->config == PERF_COUNT_HW_CPU_CYCLES) {
 
 				if (verbose)
 					warning(" ... trying to fall back to cpu-clock-ticks\n");
@@ -1264,39 +868,22 @@ try_again:
 				goto try_again;
 			}
 			printf("\n");
-			error("sys_perf_event_open() syscall returned with %d (%s).  /bin/dmesg may provide additional information.\n",
-					FD(evsel, i, thread_index), strerror(err));
+			error("sys_perf_event_open() syscall returned with %d "
+			      "(%s).  /bin/dmesg may provide additional information.\n",
+			      err, strerror(err));
 			die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
 			exit(-1);
 		}
-		assert(FD(evsel, i, thread_index) >= 0);
-		fcntl(FD(evsel, i, thread_index), F_SETFL, O_NONBLOCK);
-
-		/*
-		 * First counter acts as the group leader:
-		 */
-		if (group && group_fd == -1)
-			group_fd = FD(evsel, i, thread_index);
-
-		event_array[nr_poll].fd = FD(evsel, i, thread_index);
-		event_array[nr_poll].events = POLLIN;
-		nr_poll++;
-
-		mm = xyarray__entry(mmap_array, i, thread_index);
-		mm->prev = 0;
-		mm->mask = mmap_pages*page_size - 1;
-		mm->base = mmap(NULL, (mmap_pages+1)*page_size,
-				PROT_READ, MAP_SHARED, FD(evsel, i, thread_index), 0);
-		if (mm->base == MAP_FAILED)
-			die("failed to mmap with %d (%s)\n", errno, strerror(errno));
 	}
+
+	if (perf_evlist__mmap(evlist, mmap_pages, false) < 0)
+		die("failed to mmap with %d (%s)\n", errno, strerror(errno));
 }
 
 static int __cmd_top(void)
 {
 	pthread_t thread;
-	struct perf_evsel *counter;
-	int i, ret;
+	int ret __used;
 	/*
 	 * FIXME: perf_session__new should allow passing a O_MMAP, so that all this
 	 * mmap reading, etc is encapsulated in it. Use O_WRONLY for now.
@@ -1305,23 +892,23 @@ static int __cmd_top(void)
 	if (session == NULL)
 		return -ENOMEM;
 
-	if (target_tid != -1)
-		event__synthesize_thread_map(threads, event__process, session);
+	if (top.target_tid != -1)
+		perf_event__synthesize_thread_map(top.evlist->threads,
+						  perf_event__process, session);
 	else
-		event__synthesize_threads(event__process, session);
+		perf_event__synthesize_threads(perf_event__process, session);
 
-	for (i = 0; i < cpus->nr; i++) {
-		group_fd = -1;
-		list_for_each_entry(counter, &evsel_list, node)
-			start_counter(i, counter);
-	}
+	start_counters(top.evlist);
+	session->evlist = top.evlist;
+	perf_session__update_sample_type(session);
 
 	/* Wait for a minimal set of events before starting the snapshot */
-	poll(&event_array[0], nr_poll, 100);
+	poll(top.evlist->pollfd, top.evlist->nr_fds, 100);
 
 	perf_session__mmap_read(session);
 
-	if (pthread_create(&thread, NULL, display_thread, session)) {
+	if (pthread_create(&thread, NULL, (use_browser > 0 ? display_thread_tui :
+							     display_thread), session)) {
 		printf("Could not create display thread.\n");
 		exit(-1);
 	}
@@ -1337,12 +924,12 @@ static int __cmd_top(void)
 	}
 
 	while (1) {
-		int hits = samples;
+		u64 hits = top.samples;
 
 		perf_session__mmap_read(session);
 
-		if (hits == samples)
-			ret = poll(event_array, nr_poll, 100);
+		if (hits == top.samples)
+			ret = poll(top.evlist->pollfd, top.evlist->nr_fds, 100);
 	}
 
 	return 0;
@@ -1354,31 +941,31 @@ static const char * const top_usage[] = {
 };
 
 static const struct option options[] = {
-	OPT_CALLBACK('e', "event", NULL, "event",
+	OPT_CALLBACK('e', "event", &top.evlist, "event",
 		     "event selector. use 'perf list' to list available events",
 		     parse_events),
 	OPT_INTEGER('c', "count", &default_interval,
 		    "event period to sample"),
-	OPT_INTEGER('p', "pid", &target_pid,
+	OPT_INTEGER('p', "pid", &top.target_pid,
 		    "profile events on existing process id"),
-	OPT_INTEGER('t', "tid", &target_tid,
+	OPT_INTEGER('t', "tid", &top.target_tid,
 		    "profile events on existing thread id"),
 	OPT_BOOLEAN('a', "all-cpus", &system_wide,
 			    "system-wide collection from all CPUs"),
-	OPT_STRING('C', "cpu", &cpu_list, "cpu",
+	OPT_STRING('C', "cpu", &top.cpu_list, "cpu",
 		    "list of cpus to monitor"),
 	OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
 		   "file", "vmlinux pathname"),
-	OPT_BOOLEAN('K', "hide_kernel_symbols", &hide_kernel_symbols,
+	OPT_BOOLEAN('K', "hide_kernel_symbols", &top.hide_kernel_symbols,
 		    "hide kernel symbols"),
 	OPT_UINTEGER('m', "mmap-pages", &mmap_pages, "number of mmap data pages"),
 	OPT_INTEGER('r', "realtime", &realtime_prio,
 		    "collect data with this RT SCHED_FIFO priority"),
-	OPT_INTEGER('d', "delay", &delay_secs,
+	OPT_INTEGER('d', "delay", &top.delay_secs,
 		    "number of seconds to delay between refreshes"),
 	OPT_BOOLEAN('D', "dump-symtab", &dump_symtab,
 			    "dump the symbol table used for profiling"),
-	OPT_INTEGER('f', "count-filter", &count_filter,
+	OPT_INTEGER('f', "count-filter", &top.count_filter,
 		    "only display functions with more events than this"),
 	OPT_BOOLEAN('g', "group", &group,
 			    "put the counters into a counter group"),
@@ -1386,14 +973,16 @@ static const struct option options[] = {
 		    "child tasks inherit counters"),
 	OPT_STRING('s', "sym-annotate", &sym_filter, "symbol name",
 		    "symbol to annotate"),
-	OPT_BOOLEAN('z', "zero", &zero,
+	OPT_BOOLEAN('z', "zero", &top.zero,
 		    "zero history across updates"),
-	OPT_INTEGER('F', "freq", &freq,
+	OPT_INTEGER('F', "freq", &top.freq,
 		    "profile at this frequency"),
-	OPT_INTEGER('E', "entries", &print_entries,
+	OPT_INTEGER('E', "entries", &top.print_entries,
 		    "display this many functions"),
-	OPT_BOOLEAN('U', "hide_user_symbols", &hide_user_symbols,
+	OPT_BOOLEAN('U', "hide_user_symbols", &top.hide_user_symbols,
 		    "hide user symbols"),
+	OPT_BOOLEAN(0, "tui", &use_tui, "Use the TUI interface"),
+	OPT_BOOLEAN(0, "stdio", &use_stdio, "Use the stdio interface"),
 	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose (show counter open errors, etc)"),
 	OPT_END()
@@ -1404,64 +993,68 @@ int cmd_top(int argc, const char **argv, const char *prefix __used)
 	struct perf_evsel *pos;
 	int status = -ENOMEM;
 
+	top.evlist = perf_evlist__new(NULL, NULL);
+	if (top.evlist == NULL)
+		return -ENOMEM;
+
 	page_size = sysconf(_SC_PAGE_SIZE);
 
 	argc = parse_options(argc, argv, options, top_usage, 0);
 	if (argc)
 		usage_with_options(top_usage, options);
 
-	if (target_pid != -1)
-		target_tid = target_pid;
+	/*
+ 	 * XXX For now start disabled, only using TUI if explicitely asked for.
+ 	 * Change that when handle_keys equivalent gets written, live annotation
+ 	 * done, etc.
+ 	 */
+	use_browser = 0;
 
-	threads = thread_map__new(target_pid, target_tid);
-	if (threads == NULL) {
-		pr_err("Problems finding threads of monitor\n");
-		usage_with_options(top_usage, options);
-	}
+	if (use_stdio)
+		use_browser = 0;
+	else if (use_tui)
+		use_browser = 1;
 
-	event_array = malloc((sizeof(struct pollfd) *
-			      MAX_NR_CPUS * MAX_COUNTERS * threads->nr));
-	if (!event_array)
-		return -ENOMEM;
+	setup_browser(false);
 
 	/* CPU and PID are mutually exclusive */
-	if (target_tid > 0 && cpu_list) {
+	if (top.target_tid > 0 && top.cpu_list) {
 		printf("WARNING: PID switch overriding CPU\n");
 		sleep(1);
-		cpu_list = NULL;
+		top.cpu_list = NULL;
 	}
 
-	if (!nr_counters && perf_evsel_list__create_default() < 0) {
+	if (top.target_pid != -1)
+		top.target_tid = top.target_pid;
+
+	if (perf_evlist__create_maps(top.evlist, top.target_pid,
+				     top.target_tid, top.cpu_list) < 0)
+		usage_with_options(top_usage, options);
+
+	if (!top.evlist->nr_entries &&
+	    perf_evlist__add_default(top.evlist) < 0) {
 		pr_err("Not enough memory for event selector list\n");
 		return -ENOMEM;
 	}
 
-	if (delay_secs < 1)
-		delay_secs = 1;
+	if (top.delay_secs < 1)
+		top.delay_secs = 1;
 
 	/*
 	 * User specified count overrides default frequency.
 	 */
 	if (default_interval)
-		freq = 0;
-	else if (freq) {
-		default_interval = freq;
+		top.freq = 0;
+	else if (top.freq) {
+		default_interval = top.freq;
 	} else {
 		fprintf(stderr, "frequency and count are zero, aborting\n");
 		exit(EXIT_FAILURE);
 	}
 
-	if (target_tid != -1)
-		cpus = cpu_map__dummy_new();
-	else
-		cpus = cpu_map__new(cpu_list);
-
-	if (cpus == NULL)
-		usage_with_options(top_usage, options);
-
-	list_for_each_entry(pos, &evsel_list, node) {
-		if (perf_evsel__alloc_mmap_per_thread(pos, cpus->nr, threads->nr) < 0 ||
-		    perf_evsel__alloc_fd(pos, cpus->nr, threads->nr) < 0)
+	list_for_each_entry(pos, &top.evlist->entries, node) {
+		if (perf_evsel__alloc_fd(pos, top.evlist->cpus->nr,
+					 top.evlist->threads->nr) < 0)
 			goto out_free_fd;
 		/*
 		 * Fill in the ones not specifically initialized via -c:
@@ -1472,26 +1065,28 @@ int cmd_top(int argc, const char **argv, const char *prefix __used)
 		pos->attr.sample_period = default_interval;
 	}
 
-	sym_evsel = list_entry(evsel_list.next, struct perf_evsel, node);
+	if (perf_evlist__alloc_pollfd(top.evlist) < 0 ||
+	    perf_evlist__alloc_mmap(top.evlist) < 0)
+		goto out_free_fd;
+
+	top.sym_evsel = list_entry(top.evlist->entries.next, struct perf_evsel, node);
 
-	symbol_conf.priv_size = (sizeof(struct sym_entry) +
-				 (nr_counters + 1) * sizeof(unsigned long));
+	symbol_conf.priv_size = (sizeof(struct sym_entry) + sizeof(struct annotation) +
+				 (top.evlist->nr_entries + 1) * sizeof(unsigned long));
 
 	symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
 	if (symbol__init() < 0)
 		return -1;
 
 	get_term_dimensions(&winsize);
-	if (print_entries == 0) {
+	if (top.print_entries == 0) {
 		update_print_entries(&winsize);
 		signal(SIGWINCH, sig_winch_handler);
 	}
 
 	status = __cmd_top();
 out_free_fd:
-	list_for_each_entry(pos, &evsel_list, node)
-		perf_evsel__free_mmap(pos);
-	perf_evsel_list__delete();
+	perf_evlist__delete(top.evlist);
 
 	return status;
 }
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 95aaf565c704..a5fc660c1f12 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -94,6 +94,32 @@ void get_term_dimensions(struct winsize *ws);
 #include "util/types.h"
 #include <stdbool.h>
 
+struct perf_mmap {
+	void			*base;
+	int			mask;
+	unsigned int		prev;
+};
+
+static inline unsigned int perf_mmap__read_head(struct perf_mmap *mm)
+{
+	struct perf_event_mmap_page *pc = mm->base;
+	int head = pc->data_head;
+	rmb();
+	return head;
+}
+
+static inline void perf_mmap__write_tail(struct perf_mmap *md,
+					 unsigned long tail)
+{
+	struct perf_event_mmap_page *pc = md->base;
+
+	/*
+	 * ensure all reads are done before we write the tail out.
+	 */
+	/* mb(); */
+	pc->data_tail = tail;
+}
+
 /*
  * prctl(PR_TASK_PERF_EVENTS_DISABLE) will (cheaply) disable all
  * counters in the current task.
diff --git a/tools/perf/python/twatch.py b/tools/perf/python/twatch.py
new file mode 100755
index 000000000000..df638c438a9f
--- /dev/null
+++ b/tools/perf/python/twatch.py
@@ -0,0 +1,41 @@
+#! /usr/bin/python
+# -*- python -*-
+# -*- coding: utf-8 -*-
+#   twatch - Experimental use of the perf python interface
+#   Copyright (C) 2011 Arnaldo Carvalho de Melo <acme@redhat.com>
+#
+#   This application is free software; you can redistribute it and/or
+#   modify it under the terms of the GNU General Public License
+#   as published by the Free Software Foundation; version 2.
+#
+#   This application is distributed in the hope that it will be useful,
+#   but WITHOUT ANY WARRANTY; without even the implied warranty of
+#   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+#   General Public License for more details.
+
+import perf
+
+def main():
+	cpus = perf.cpu_map()
+	threads = perf.thread_map()
+	evsel = perf.evsel(task = 1, comm = 1, mmap = 0,
+			   wakeup_events = 1, sample_period = 1,
+			   sample_id_all = 1,
+			   sample_type = perf.SAMPLE_PERIOD | perf.SAMPLE_TID | perf.SAMPLE_CPU | perf.SAMPLE_TID)
+	evsel.open(cpus = cpus, threads = threads);
+	evlist = perf.evlist(cpus, threads)
+	evlist.add(evsel)
+	evlist.mmap()
+	while True:
+		evlist.poll(timeout = -1)
+		for cpu in cpus:
+			event = evlist.read_on_cpu(cpu)
+			if not event:
+				continue
+			print "cpu: %2d, pid: %4d, tid: %4d" % (event.sample_cpu,
+								event.sample_pid,
+								event.sample_tid),
+			print event
+
+if __name__ == '__main__':
+    main()
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
new file mode 100644
index 000000000000..0d0830c98cd7
--- /dev/null
+++ b/tools/perf/util/annotate.c
@@ -0,0 +1,605 @@
+/*
+ * Copyright (C) 2011, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Parts came from builtin-annotate.c, see those files for further
+ * copyright notes.
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+
+#include "util.h"
+#include "build-id.h"
+#include "color.h"
+#include "cache.h"
+#include "symbol.h"
+#include "debug.h"
+#include "annotate.h"
+#include <pthread.h>
+
+int symbol__annotate_init(struct map *map __used, struct symbol *sym)
+{
+	struct annotation *notes = symbol__annotation(sym);
+	pthread_mutex_init(&notes->lock, NULL);
+	return 0;
+}
+
+int symbol__alloc_hist(struct symbol *sym, int nevents)
+{
+	struct annotation *notes = symbol__annotation(sym);
+	size_t sizeof_sym_hist = (sizeof(struct sym_hist) +
+				  (sym->end - sym->start) * sizeof(u64));
+
+	notes->src = zalloc(sizeof(*notes->src) + nevents * sizeof_sym_hist);
+	if (notes->src == NULL)
+		return -1;
+	notes->src->sizeof_sym_hist = sizeof_sym_hist;
+	notes->src->nr_histograms   = nevents;
+	INIT_LIST_HEAD(&notes->src->source);
+	return 0;
+}
+
+void symbol__annotate_zero_histograms(struct symbol *sym)
+{
+	struct annotation *notes = symbol__annotation(sym);
+
+	pthread_mutex_lock(&notes->lock);
+	if (notes->src != NULL)
+		memset(notes->src->histograms, 0,
+		       notes->src->nr_histograms * notes->src->sizeof_sym_hist);
+	pthread_mutex_unlock(&notes->lock);
+}
+
+int symbol__inc_addr_samples(struct symbol *sym, struct map *map,
+			     int evidx, u64 addr)
+{
+	unsigned offset;
+	struct annotation *notes;
+	struct sym_hist *h;
+
+	notes = symbol__annotation(sym);
+	if (notes->src == NULL)
+		return -ENOMEM;
+
+	pr_debug3("%s: addr=%#" PRIx64 "\n", __func__, map->unmap_ip(map, addr));
+
+	if (addr >= sym->end)
+		return 0;
+
+	offset = addr - sym->start;
+	h = annotation__histogram(notes, evidx);
+	h->sum++;
+	h->addr[offset]++;
+
+	pr_debug3("%#" PRIx64 " %s: period++ [addr: %#" PRIx64 ", %#" PRIx64
+		  ", evidx=%d] => %" PRIu64 "\n", sym->start, sym->name,
+		  addr, addr - sym->start, evidx, h->addr[offset]);
+	return 0;
+}
+
+static struct objdump_line *objdump_line__new(s64 offset, char *line, size_t privsize)
+{
+	struct objdump_line *self = malloc(sizeof(*self) + privsize);
+
+	if (self != NULL) {
+		self->offset = offset;
+		self->line = line;
+	}
+
+	return self;
+}
+
+void objdump_line__free(struct objdump_line *self)
+{
+	free(self->line);
+	free(self);
+}
+
+static void objdump__add_line(struct list_head *head, struct objdump_line *line)
+{
+	list_add_tail(&line->node, head);
+}
+
+struct objdump_line *objdump__get_next_ip_line(struct list_head *head,
+					       struct objdump_line *pos)
+{
+	list_for_each_entry_continue(pos, head, node)
+		if (pos->offset >= 0)
+			return pos;
+
+	return NULL;
+}
+
+static int objdump_line__print(struct objdump_line *oline, struct symbol *sym,
+			       int evidx, u64 len, int min_pcnt,
+			       int printed, int max_lines,
+			       struct objdump_line *queue)
+{
+	static const char *prev_line;
+	static const char *prev_color;
+
+	if (oline->offset != -1) {
+		const char *path = NULL;
+		unsigned int hits = 0;
+		double percent = 0.0;
+		const char *color;
+		struct annotation *notes = symbol__annotation(sym);
+		struct source_line *src_line = notes->src->lines;
+		struct sym_hist *h = annotation__histogram(notes, evidx);
+		s64 offset = oline->offset;
+		struct objdump_line *next;
+
+		next = objdump__get_next_ip_line(&notes->src->source, oline);
+
+		while (offset < (s64)len &&
+		       (next == NULL || offset < next->offset)) {
+			if (src_line) {
+				if (path == NULL)
+					path = src_line[offset].path;
+				percent += src_line[offset].percent;
+			} else
+				hits += h->addr[offset];
+
+			++offset;
+		}
+
+		if (src_line == NULL && h->sum)
+			percent = 100.0 * hits / h->sum;
+
+		if (percent < min_pcnt)
+			return -1;
+
+		if (max_lines && printed >= max_lines)
+			return 1;
+
+		if (queue != NULL) {
+			list_for_each_entry_from(queue, &notes->src->source, node) {
+				if (queue == oline)
+					break;
+				objdump_line__print(queue, sym, evidx, len,
+						    0, 0, 1, NULL);
+			}
+		}
+
+		color = get_percent_color(percent);
+
+		/*
+		 * Also color the filename and line if needed, with
+		 * the same color than the percentage. Don't print it
+		 * twice for close colored addr with the same filename:line
+		 */
+		if (path) {
+			if (!prev_line || strcmp(prev_line, path)
+				       || color != prev_color) {
+				color_fprintf(stdout, color, " %s", path);
+				prev_line = path;
+				prev_color = color;
+			}
+		}
+
+		color_fprintf(stdout, color, " %7.2f", percent);
+		printf(" :	");
+		color_fprintf(stdout, PERF_COLOR_BLUE, "%s\n", oline->line);
+	} else if (max_lines && printed >= max_lines)
+		return 1;
+	else {
+		if (queue)
+			return -1;
+
+		if (!*oline->line)
+			printf("         :\n");
+		else
+			printf("         :	%s\n", oline->line);
+	}
+
+	return 0;
+}
+
+static int symbol__parse_objdump_line(struct symbol *sym, struct map *map,
+				      FILE *file, size_t privsize)
+{
+	struct annotation *notes = symbol__annotation(sym);
+	struct objdump_line *objdump_line;
+	char *line = NULL, *tmp, *tmp2, *c;
+	size_t line_len;
+	s64 line_ip, offset = -1;
+
+	if (getline(&line, &line_len, file) < 0)
+		return -1;
+
+	if (!line)
+		return -1;
+
+	while (line_len != 0 && isspace(line[line_len - 1]))
+		line[--line_len] = '\0';
+
+	c = strchr(line, '\n');
+	if (c)
+		*c = 0;
+
+	line_ip = -1;
+
+	/*
+	 * Strip leading spaces:
+	 */
+	tmp = line;
+	while (*tmp) {
+		if (*tmp != ' ')
+			break;
+		tmp++;
+	}
+
+	if (*tmp) {
+		/*
+		 * Parse hexa addresses followed by ':'
+		 */
+		line_ip = strtoull(tmp, &tmp2, 16);
+		if (*tmp2 != ':' || tmp == tmp2 || tmp2[1] == '\0')
+			line_ip = -1;
+	}
+
+	if (line_ip != -1) {
+		u64 start = map__rip_2objdump(map, sym->start),
+		    end = map__rip_2objdump(map, sym->end);
+
+		offset = line_ip - start;
+		if (offset < 0 || (u64)line_ip > end)
+			offset = -1;
+	}
+
+	objdump_line = objdump_line__new(offset, line, privsize);
+	if (objdump_line == NULL) {
+		free(line);
+		return -1;
+	}
+	objdump__add_line(&notes->src->source, objdump_line);
+
+	return 0;
+}
+
+int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize)
+{
+	struct dso *dso = map->dso;
+	char *filename = dso__build_id_filename(dso, NULL, 0);
+	bool free_filename = true;
+	char command[PATH_MAX * 2];
+	FILE *file;
+	int err = 0;
+	char symfs_filename[PATH_MAX];
+
+	if (filename) {
+		snprintf(symfs_filename, sizeof(symfs_filename), "%s%s",
+			 symbol_conf.symfs, filename);
+	}
+
+	if (filename == NULL) {
+		if (dso->has_build_id) {
+			pr_err("Can't annotate %s: not enough memory\n",
+			       sym->name);
+			return -ENOMEM;
+		}
+		goto fallback;
+	} else if (readlink(symfs_filename, command, sizeof(command)) < 0 ||
+		   strstr(command, "[kernel.kallsyms]") ||
+		   access(symfs_filename, R_OK)) {
+		free(filename);
+fallback:
+		/*
+		 * If we don't have build-ids or the build-id file isn't in the
+		 * cache, or is just a kallsyms file, well, lets hope that this
+		 * DSO is the same as when 'perf record' ran.
+		 */
+		filename = dso->long_name;
+		snprintf(symfs_filename, sizeof(symfs_filename), "%s%s",
+			 symbol_conf.symfs, filename);
+		free_filename = false;
+	}
+
+	if (dso->origin == DSO__ORIG_KERNEL) {
+		char bf[BUILD_ID_SIZE * 2 + 16] = " with build id ";
+		char *build_id_msg = NULL;
+
+		if (dso->annotate_warned)
+			goto out_free_filename;
+
+		if (dso->has_build_id) {
+			build_id__sprintf(dso->build_id,
+					  sizeof(dso->build_id), bf + 15);
+			build_id_msg = bf;
+		}
+		err = -ENOENT;
+		dso->annotate_warned = 1;
+		pr_err("Can't annotate %s: No vmlinux file%s was found in the "
+		       "path.\nPlease use 'perf buildid-cache -av vmlinux' or "
+		       "--vmlinux vmlinux.\n",
+		       sym->name, build_id_msg ?: "");
+		goto out_free_filename;
+	}
+
+	pr_debug("%s: filename=%s, sym=%s, start=%#" PRIx64 ", end=%#" PRIx64 "\n", __func__,
+		 filename, sym->name, map->unmap_ip(map, sym->start),
+		 map->unmap_ip(map, sym->end));
+
+	pr_debug("annotating [%p] %30s : [%p] %30s\n",
+		 dso, dso->long_name, sym, sym->name);
+
+	snprintf(command, sizeof(command),
+		 "objdump --start-address=0x%016" PRIx64
+		 " --stop-address=0x%016" PRIx64 " -dS -C %s|grep -v %s|expand",
+		 map__rip_2objdump(map, sym->start),
+		 map__rip_2objdump(map, sym->end),
+		 symfs_filename, filename);
+
+	pr_debug("Executing: %s\n", command);
+
+	file = popen(command, "r");
+	if (!file)
+		goto out_free_filename;
+
+	while (!feof(file))
+		if (symbol__parse_objdump_line(sym, map, file, privsize) < 0)
+			break;
+
+	pclose(file);
+out_free_filename:
+	if (free_filename)
+		free(filename);
+	return err;
+}
+
+static void insert_source_line(struct rb_root *root, struct source_line *src_line)
+{
+	struct source_line *iter;
+	struct rb_node **p = &root->rb_node;
+	struct rb_node *parent = NULL;
+
+	while (*p != NULL) {
+		parent = *p;
+		iter = rb_entry(parent, struct source_line, node);
+
+		if (src_line->percent > iter->percent)
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
+	}
+
+	rb_link_node(&src_line->node, parent, p);
+	rb_insert_color(&src_line->node, root);
+}
+
+static void symbol__free_source_line(struct symbol *sym, int len)
+{
+	struct annotation *notes = symbol__annotation(sym);
+	struct source_line *src_line = notes->src->lines;
+	int i;
+
+	for (i = 0; i < len; i++)
+		free(src_line[i].path);
+
+	free(src_line);
+	notes->src->lines = NULL;
+}
+
+/* Get the filename:line for the colored entries */
+static int symbol__get_source_line(struct symbol *sym, struct map *map,
+				   int evidx, struct rb_root *root, int len,
+				   const char *filename)
+{
+	u64 start;
+	int i;
+	char cmd[PATH_MAX * 2];
+	struct source_line *src_line;
+	struct annotation *notes = symbol__annotation(sym);
+	struct sym_hist *h = annotation__histogram(notes, evidx);
+
+	if (!h->sum)
+		return 0;
+
+	src_line = notes->src->lines = calloc(len, sizeof(struct source_line));
+	if (!notes->src->lines)
+		return -1;
+
+	start = map->unmap_ip(map, sym->start);
+
+	for (i = 0; i < len; i++) {
+		char *path = NULL;
+		size_t line_len;
+		u64 offset;
+		FILE *fp;
+
+		src_line[i].percent = 100.0 * h->addr[i] / h->sum;
+		if (src_line[i].percent <= 0.5)
+			continue;
+
+		offset = start + i;
+		sprintf(cmd, "addr2line -e %s %016" PRIx64, filename, offset);
+		fp = popen(cmd, "r");
+		if (!fp)
+			continue;
+
+		if (getline(&path, &line_len, fp) < 0 || !line_len)
+			goto next;
+
+		src_line[i].path = malloc(sizeof(char) * line_len + 1);
+		if (!src_line[i].path)
+			goto next;
+
+		strcpy(src_line[i].path, path);
+		insert_source_line(root, &src_line[i]);
+
+	next:
+		pclose(fp);
+	}
+
+	return 0;
+}
+
+static void print_summary(struct rb_root *root, const char *filename)
+{
+	struct source_line *src_line;
+	struct rb_node *node;
+
+	printf("\nSorted summary for file %s\n", filename);
+	printf("----------------------------------------------\n\n");
+
+	if (RB_EMPTY_ROOT(root)) {
+		printf(" Nothing higher than %1.1f%%\n", MIN_GREEN);
+		return;
+	}
+
+	node = rb_first(root);
+	while (node) {
+		double percent;
+		const char *color;
+		char *path;
+
+		src_line = rb_entry(node, struct source_line, node);
+		percent = src_line->percent;
+		color = get_percent_color(percent);
+		path = src_line->path;
+
+		color_fprintf(stdout, color, " %7.2f %s", percent, path);
+		node = rb_next(node);
+	}
+}
+
+static void symbol__annotate_hits(struct symbol *sym, int evidx)
+{
+	struct annotation *notes = symbol__annotation(sym);
+	struct sym_hist *h = annotation__histogram(notes, evidx);
+	u64 len = sym->end - sym->start, offset;
+
+	for (offset = 0; offset < len; ++offset)
+		if (h->addr[offset] != 0)
+			printf("%*" PRIx64 ": %" PRIu64 "\n", BITS_PER_LONG / 2,
+			       sym->start + offset, h->addr[offset]);
+	printf("%*s: %" PRIu64 "\n", BITS_PER_LONG / 2, "h->sum", h->sum);
+}
+
+int symbol__annotate_printf(struct symbol *sym, struct map *map, int evidx,
+			    bool full_paths, int min_pcnt, int max_lines,
+			    int context)
+{
+	struct dso *dso = map->dso;
+	const char *filename = dso->long_name, *d_filename;
+	struct annotation *notes = symbol__annotation(sym);
+	struct objdump_line *pos, *queue = NULL;
+	int printed = 2, queue_len = 0;
+	int more = 0;
+	u64 len;
+
+	if (full_paths)
+		d_filename = filename;
+	else
+		d_filename = basename(filename);
+
+	len = sym->end - sym->start;
+
+	printf(" Percent |	Source code & Disassembly of %s\n", d_filename);
+	printf("------------------------------------------------\n");
+
+	if (verbose)
+		symbol__annotate_hits(sym, evidx);
+
+	list_for_each_entry(pos, &notes->src->source, node) {
+		if (context && queue == NULL) {
+			queue = pos;
+			queue_len = 0;
+		}
+
+		switch (objdump_line__print(pos, sym, evidx, len, min_pcnt,
+					    printed, max_lines, queue)) {
+		case 0:
+			++printed;
+			if (context) {
+				printed += queue_len;
+				queue = NULL;
+				queue_len = 0;
+			}
+			break;
+		case 1:
+			/* filtered by max_lines */
+			++more;
+			break;
+		case -1:
+		default:
+			/*
+			 * Filtered by min_pcnt or non IP lines when
+			 * context != 0
+			 */
+			if (!context)
+				break;
+			if (queue_len == context)
+				queue = list_entry(queue->node.next, typeof(*queue), node);
+			else
+				++queue_len;
+			break;
+		}
+	}
+
+	return more;
+}
+
+void symbol__annotate_zero_histogram(struct symbol *sym, int evidx)
+{
+	struct annotation *notes = symbol__annotation(sym);
+	struct sym_hist *h = annotation__histogram(notes, evidx);
+
+	memset(h, 0, notes->src->sizeof_sym_hist);
+}
+
+void symbol__annotate_decay_histogram(struct symbol *sym, int evidx)
+{
+	struct annotation *notes = symbol__annotation(sym);
+	struct sym_hist *h = annotation__histogram(notes, evidx);
+	struct objdump_line *pos;
+	int len = sym->end - sym->start;
+
+	h->sum = 0;
+
+	list_for_each_entry(pos, &notes->src->source, node) {
+		if (pos->offset != -1 && pos->offset < len) {
+			h->addr[pos->offset] = h->addr[pos->offset] * 7 / 8;
+			h->sum += h->addr[pos->offset];
+		}
+	}
+}
+
+void objdump_line_list__purge(struct list_head *head)
+{
+	struct objdump_line *pos, *n;
+
+	list_for_each_entry_safe(pos, n, head, node) {
+		list_del(&pos->node);
+		objdump_line__free(pos);
+	}
+}
+
+int symbol__tty_annotate(struct symbol *sym, struct map *map, int evidx,
+			 bool print_lines, bool full_paths, int min_pcnt,
+			 int max_lines)
+{
+	struct dso *dso = map->dso;
+	const char *filename = dso->long_name;
+	struct rb_root source_line = RB_ROOT;
+	u64 len;
+
+	if (symbol__annotate(sym, map, 0) < 0)
+		return -1;
+
+	len = sym->end - sym->start;
+
+	if (print_lines) {
+		symbol__get_source_line(sym, map, evidx, &source_line,
+					len, filename);
+		print_summary(&source_line, filename);
+	}
+
+	symbol__annotate_printf(sym, map, evidx, full_paths,
+				min_pcnt, max_lines, 0);
+	if (print_lines)
+		symbol__free_source_line(sym, len);
+
+	objdump_line_list__purge(&symbol__annotation(sym)->src->source);
+
+	return 0;
+}
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
new file mode 100644
index 000000000000..c2c286896801
--- /dev/null
+++ b/tools/perf/util/annotate.h
@@ -0,0 +1,103 @@
+#ifndef __PERF_ANNOTATE_H
+#define __PERF_ANNOTATE_H
+
+#include <stdbool.h>
+#include "types.h"
+#include "symbol.h"
+#include <linux/list.h>
+#include <linux/rbtree.h>
+
+struct objdump_line {
+	struct list_head node;
+	s64		 offset;
+	char		 *line;
+};
+
+void objdump_line__free(struct objdump_line *self);
+struct objdump_line *objdump__get_next_ip_line(struct list_head *head,
+					       struct objdump_line *pos);
+
+struct sym_hist {
+	u64		sum;
+	u64		addr[0];
+};
+
+struct source_line {
+	struct rb_node	node;
+	double		percent;
+	char		*path;
+};
+
+/** struct annotated_source - symbols with hits have this attached as in sannotation
+ *
+ * @histogram: Array of addr hit histograms per event being monitored
+ * @lines: If 'print_lines' is specified, per source code line percentages
+ * @source: source parsed from objdump -dS
+ *
+ * lines is allocated, percentages calculated and all sorted by percentage
+ * when the annotation is about to be presented, so the percentages are for
+ * one of the entries in the histogram array, i.e. for the event/counter being
+ * presented. It is deallocated right after symbol__{tui,tty,etc}_annotate
+ * returns.
+ */
+struct annotated_source {
+	struct list_head   source;
+	struct source_line *lines;
+	int    		   nr_histograms;
+	int    		   sizeof_sym_hist;
+	struct sym_hist	   histograms[0];
+};
+
+struct annotation {
+	pthread_mutex_t		lock;
+	struct annotated_source *src;
+};
+
+struct sannotation {
+	struct annotation annotation;
+	struct symbol	  symbol;
+};
+
+static inline struct sym_hist *annotation__histogram(struct annotation *notes, int idx)
+{
+	return (((void *)&notes->src->histograms) +
+	 	(notes->src->sizeof_sym_hist * idx));
+}
+
+static inline struct annotation *symbol__annotation(struct symbol *sym)
+{
+	struct sannotation *a = container_of(sym, struct sannotation, symbol);
+	return &a->annotation;
+}
+
+int symbol__inc_addr_samples(struct symbol *sym, struct map *map,
+			     int evidx, u64 addr);
+int symbol__alloc_hist(struct symbol *sym, int nevents);
+void symbol__annotate_zero_histograms(struct symbol *sym);
+
+int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize);
+int symbol__annotate_init(struct map *map __used, struct symbol *sym);
+int symbol__annotate_printf(struct symbol *sym, struct map *map, int evidx,
+			    bool full_paths, int min_pcnt, int max_lines,
+			    int context);
+void symbol__annotate_zero_histogram(struct symbol *sym, int evidx);
+void symbol__annotate_decay_histogram(struct symbol *sym, int evidx);
+void objdump_line_list__purge(struct list_head *head);
+
+int symbol__tty_annotate(struct symbol *sym, struct map *map, int evidx,
+			 bool print_lines, bool full_paths, int min_pcnt,
+			 int max_lines);
+
+#ifdef NO_NEWT_SUPPORT
+static inline int symbol__tui_annotate(struct symbol *sym __used,
+				       struct map *map __used,
+				       int evidx __used, int refresh __used)
+{
+	return 0;
+}
+#else
+int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx,
+			 int refresh);
+#endif
+
+#endif	/* __PERF_ANNOTATE_H */
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index deffb8c96071..31f934af9861 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -14,8 +14,8 @@
 #include <linux/kernel.h>
 #include "debug.h"
 
-static int build_id__mark_dso_hit(event_t *event,
-				  struct sample_data *sample __used,
+static int build_id__mark_dso_hit(union perf_event *event,
+				  struct perf_sample *sample __used,
 				  struct perf_session *session)
 {
 	struct addr_location al;
@@ -37,13 +37,14 @@ static int build_id__mark_dso_hit(event_t *event,
 	return 0;
 }
 
-static int event__exit_del_thread(event_t *self, struct sample_data *sample __used,
-				  struct perf_session *session)
+static int perf_event__exit_del_thread(union perf_event *event,
+				       struct perf_sample *sample __used,
+				       struct perf_session *session)
 {
-	struct thread *thread = perf_session__findnew(session, self->fork.tid);
+	struct thread *thread = perf_session__findnew(session, event->fork.tid);
 
-	dump_printf("(%d:%d):(%d:%d)\n", self->fork.pid, self->fork.tid,
-		    self->fork.ppid, self->fork.ptid);
+	dump_printf("(%d:%d):(%d:%d)\n", event->fork.pid, event->fork.tid,
+		    event->fork.ppid, event->fork.ptid);
 
 	if (thread) {
 		rb_erase(&thread->rb_node, &session->threads);
@@ -56,9 +57,9 @@ static int event__exit_del_thread(event_t *self, struct sample_data *sample __us
 
 struct perf_event_ops build_id__mark_dso_hit_ops = {
 	.sample	= build_id__mark_dso_hit,
-	.mmap	= event__process_mmap,
-	.fork	= event__process_task,
-	.exit	= event__exit_del_thread,
+	.mmap	= perf_event__process_mmap,
+	.fork	= perf_event__process_task,
+	.exit	= perf_event__exit_del_thread,
 };
 
 char *dso__build_id_filename(struct dso *self, char *bf, size_t size)
diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
index a7729797fd96..fc5e5a09d5b9 100644
--- a/tools/perf/util/cache.h
+++ b/tools/perf/util/cache.h
@@ -34,13 +34,14 @@ extern int pager_use_color;
 extern int use_browser;
 
 #ifdef NO_NEWT_SUPPORT
-static inline void setup_browser(void)
+static inline void setup_browser(bool fallback_to_pager)
 {
-	setup_pager();
+	if (fallback_to_pager)
+		setup_pager();
 }
 static inline void exit_browser(bool wait_for_ok __used) {}
 #else
-void setup_browser(void);
+void setup_browser(bool fallback_to_pager);
 void exit_browser(bool wait_for_ok);
 #endif
 
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index e12d539417b2..9f7106a8d9a4 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2009-2010, Frederic Weisbecker <fweisbec@gmail.com>
+ * Copyright (C) 2009-2011, Frederic Weisbecker <fweisbec@gmail.com>
  *
  * Handle the callchains from the stream in an ad-hoc radix tree and then
  * sort them in an rbtree.
@@ -18,7 +18,8 @@
 #include "util.h"
 #include "callchain.h"
 
-bool ip_callchain__valid(struct ip_callchain *chain, const event_t *event)
+bool ip_callchain__valid(struct ip_callchain *chain,
+			 const union perf_event *event)
 {
 	unsigned int chain_size = event->header.size;
 	chain_size -= (unsigned long)&event->ip.__more_data - (unsigned long)event;
@@ -26,10 +27,10 @@ bool ip_callchain__valid(struct ip_callchain *chain, const event_t *event)
 }
 
 #define chain_for_each_child(child, parent)	\
-	list_for_each_entry(child, &parent->children, brothers)
+	list_for_each_entry(child, &parent->children, siblings)
 
 #define chain_for_each_child_safe(child, next, parent)	\
-	list_for_each_entry_safe(child, next, &parent->children, brothers)
+	list_for_each_entry_safe(child, next, &parent->children, siblings)
 
 static void
 rb_insert_callchain(struct rb_root *root, struct callchain_node *chain,
@@ -38,14 +39,14 @@ rb_insert_callchain(struct rb_root *root, struct callchain_node *chain,
 	struct rb_node **p = &root->rb_node;
 	struct rb_node *parent = NULL;
 	struct callchain_node *rnode;
-	u64 chain_cumul = cumul_hits(chain);
+	u64 chain_cumul = callchain_cumul_hits(chain);
 
 	while (*p) {
 		u64 rnode_cumul;
 
 		parent = *p;
 		rnode = rb_entry(parent, struct callchain_node, rb_node);
-		rnode_cumul = cumul_hits(rnode);
+		rnode_cumul = callchain_cumul_hits(rnode);
 
 		switch (mode) {
 		case CHAIN_FLAT:
@@ -104,7 +105,7 @@ static void __sort_chain_graph_abs(struct callchain_node *node,
 
 	chain_for_each_child(child, node) {
 		__sort_chain_graph_abs(child, min_hit);
-		if (cumul_hits(child) >= min_hit)
+		if (callchain_cumul_hits(child) >= min_hit)
 			rb_insert_callchain(&node->rb_root, child,
 					    CHAIN_GRAPH_ABS);
 	}
@@ -129,7 +130,7 @@ static void __sort_chain_graph_rel(struct callchain_node *node,
 
 	chain_for_each_child(child, node) {
 		__sort_chain_graph_rel(child, min_percent);
-		if (cumul_hits(child) >= min_hit)
+		if (callchain_cumul_hits(child) >= min_hit)
 			rb_insert_callchain(&node->rb_root, child,
 					    CHAIN_GRAPH_REL);
 	}
@@ -143,7 +144,7 @@ sort_chain_graph_rel(struct rb_root *rb_root, struct callchain_root *chain_root,
 	rb_root->rb_node = chain_root->node.rb_root.rb_node;
 }
 
-int register_callchain_param(struct callchain_param *param)
+int callchain_register_param(struct callchain_param *param)
 {
 	switch (param->mode) {
 	case CHAIN_GRAPH_ABS:
@@ -189,32 +190,27 @@ create_child(struct callchain_node *parent, bool inherit_children)
 		chain_for_each_child(next, new)
 			next->parent = new;
 	}
-	list_add_tail(&new->brothers, &parent->children);
+	list_add_tail(&new->siblings, &parent->children);
 
 	return new;
 }
 
 
-struct resolved_ip {
-	u64		  ip;
-	struct map_symbol ms;
-};
-
-struct resolved_chain {
-	u64			nr;
-	struct resolved_ip	ips[0];
-};
-
-
 /*
  * Fill the node with callchain values
  */
 static void
-fill_node(struct callchain_node *node, struct resolved_chain *chain, int start)
+fill_node(struct callchain_node *node, struct callchain_cursor *cursor)
 {
-	unsigned int i;
+	struct callchain_cursor_node *cursor_node;
+
+	node->val_nr = cursor->nr - cursor->pos;
+	if (!node->val_nr)
+		pr_warning("Warning: empty node in callchain tree\n");
 
-	for (i = start; i < chain->nr; i++) {
+	cursor_node = callchain_cursor_current(cursor);
+
+	while (cursor_node) {
 		struct callchain_list *call;
 
 		call = zalloc(sizeof(*call));
@@ -222,23 +218,25 @@ fill_node(struct callchain_node *node, struct resolved_chain *chain, int start)
 			perror("not enough memory for the code path tree");
 			return;
 		}
-		call->ip = chain->ips[i].ip;
-		call->ms = chain->ips[i].ms;
+		call->ip = cursor_node->ip;
+		call->ms.sym = cursor_node->sym;
+		call->ms.map = cursor_node->map;
 		list_add_tail(&call->list, &node->val);
+
+		callchain_cursor_advance(cursor);
+		cursor_node = callchain_cursor_current(cursor);
 	}
-	node->val_nr = chain->nr - start;
-	if (!node->val_nr)
-		pr_warning("Warning: empty node in callchain tree\n");
 }
 
 static void
-add_child(struct callchain_node *parent, struct resolved_chain *chain,
-	  int start, u64 period)
+add_child(struct callchain_node *parent,
+	  struct callchain_cursor *cursor,
+	  u64 period)
 {
 	struct callchain_node *new;
 
 	new = create_child(parent, false);
-	fill_node(new, chain, start);
+	fill_node(new, cursor);
 
 	new->children_hit = 0;
 	new->hit = period;
@@ -250,9 +248,10 @@ add_child(struct callchain_node *parent, struct resolved_chain *chain,
  * Then create another child to host the given callchain of new branch
  */
 static void
-split_add_child(struct callchain_node *parent, struct resolved_chain *chain,
-		struct callchain_list *to_split, int idx_parents, int idx_local,
-		u64 period)
+split_add_child(struct callchain_node *parent,
+		struct callchain_cursor *cursor,
+		struct callchain_list *to_split,
+		u64 idx_parents, u64 idx_local, u64 period)
 {
 	struct callchain_node *new;
 	struct list_head *old_tail;
@@ -272,14 +271,14 @@ split_add_child(struct callchain_node *parent, struct resolved_chain *chain,
 	/* split the hits */
 	new->hit = parent->hit;
 	new->children_hit = parent->children_hit;
-	parent->children_hit = cumul_hits(new);
+	parent->children_hit = callchain_cumul_hits(new);
 	new->val_nr = parent->val_nr - idx_local;
 	parent->val_nr = idx_local;
 
 	/* create a new child for the new branch if any */
-	if (idx_total < chain->nr) {
+	if (idx_total < cursor->nr) {
 		parent->hit = 0;
-		add_child(parent, chain, idx_total, period);
+		add_child(parent, cursor, period);
 		parent->children_hit += period;
 	} else {
 		parent->hit = period;
@@ -287,36 +286,41 @@ split_add_child(struct callchain_node *parent, struct resolved_chain *chain,
 }
 
 static int
-append_chain(struct callchain_node *root, struct resolved_chain *chain,
-	     unsigned int start, u64 period);
+append_chain(struct callchain_node *root,
+	     struct callchain_cursor *cursor,
+	     u64 period);
 
 static void
-append_chain_children(struct callchain_node *root, struct resolved_chain *chain,
-		      unsigned int start, u64 period)
+append_chain_children(struct callchain_node *root,
+		      struct callchain_cursor *cursor,
+		      u64 period)
 {
 	struct callchain_node *rnode;
 
 	/* lookup in childrens */
 	chain_for_each_child(rnode, root) {
-		unsigned int ret = append_chain(rnode, chain, start, period);
+		unsigned int ret = append_chain(rnode, cursor, period);
 
 		if (!ret)
 			goto inc_children_hit;
 	}
 	/* nothing in children, add to the current node */
-	add_child(root, chain, start, period);
+	add_child(root, cursor, period);
 
 inc_children_hit:
 	root->children_hit += period;
 }
 
 static int
-append_chain(struct callchain_node *root, struct resolved_chain *chain,
-	     unsigned int start, u64 period)
+append_chain(struct callchain_node *root,
+	     struct callchain_cursor *cursor,
+	     u64 period)
 {
+	struct callchain_cursor_node *curr_snap = cursor->curr;
 	struct callchain_list *cnode;
-	unsigned int i = start;
+	u64 start = cursor->pos;
 	bool found = false;
+	u64 matches;
 
 	/*
 	 * Lookup in the current node
@@ -324,141 +328,134 @@ append_chain(struct callchain_node *root, struct resolved_chain *chain,
 	 * anywhere inside a function.
 	 */
 	list_for_each_entry(cnode, &root->val, list) {
+		struct callchain_cursor_node *node;
 		struct symbol *sym;
 
-		if (i == chain->nr)
+		node = callchain_cursor_current(cursor);
+		if (!node)
 			break;
 
-		sym = chain->ips[i].ms.sym;
+		sym = node->sym;
 
 		if (cnode->ms.sym && sym) {
 			if (cnode->ms.sym->start != sym->start)
 				break;
-		} else if (cnode->ip != chain->ips[i].ip)
+		} else if (cnode->ip != node->ip)
 			break;
 
 		if (!found)
 			found = true;
-		i++;
+
+		callchain_cursor_advance(cursor);
 	}
 
 	/* matches not, relay on the parent */
-	if (!found)
+	if (!found) {
+		cursor->curr = curr_snap;
+		cursor->pos = start;
 		return -1;
+	}
+
+	matches = cursor->pos - start;
 
 	/* we match only a part of the node. Split it and add the new chain */
-	if (i - start < root->val_nr) {
-		split_add_child(root, chain, cnode, start, i - start, period);
+	if (matches < root->val_nr) {
+		split_add_child(root, cursor, cnode, start, matches, period);
 		return 0;
 	}
 
 	/* we match 100% of the path, increment the hit */
-	if (i - start == root->val_nr && i == chain->nr) {
+	if (matches == root->val_nr && cursor->pos == cursor->nr) {
 		root->hit += period;
 		return 0;
 	}
 
 	/* We match the node and still have a part remaining */
-	append_chain_children(root, chain, i, period);
+	append_chain_children(root, cursor, period);
 
 	return 0;
 }
 
-static void filter_context(struct ip_callchain *old, struct resolved_chain *new,
-			   struct map_symbol *syms)
-{
-	int i, j = 0;
-
-	for (i = 0; i < (int)old->nr; i++) {
-		if (old->ips[i] >= PERF_CONTEXT_MAX)
-			continue;
-
-		new->ips[j].ip = old->ips[i];
-		new->ips[j].ms = syms[i];
-		j++;
-	}
-
-	new->nr = j;
-}
-
-
-int callchain_append(struct callchain_root *root, struct ip_callchain *chain,
-		     struct map_symbol *syms, u64 period)
+int callchain_append(struct callchain_root *root,
+		     struct callchain_cursor *cursor,
+		     u64 period)
 {
-	struct resolved_chain *filtered;
-
-	if (!chain->nr)
+	if (!cursor->nr)
 		return 0;
 
-	filtered = zalloc(sizeof(*filtered) +
-			  chain->nr * sizeof(struct resolved_ip));
-	if (!filtered)
-		return -ENOMEM;
-
-	filter_context(chain, filtered, syms);
-
-	if (!filtered->nr)
-		goto end;
+	callchain_cursor_commit(cursor);
 
-	append_chain_children(&root->node, filtered, 0, period);
+	append_chain_children(&root->node, cursor, period);
 
-	if (filtered->nr > root->max_depth)
-		root->max_depth = filtered->nr;
-end:
-	free(filtered);
+	if (cursor->nr > root->max_depth)
+		root->max_depth = cursor->nr;
 
 	return 0;
 }
 
 static int
-merge_chain_branch(struct callchain_node *dst, struct callchain_node *src,
-		   struct resolved_chain *chain)
+merge_chain_branch(struct callchain_cursor *cursor,
+		   struct callchain_node *dst, struct callchain_node *src)
 {
+	struct callchain_cursor_node **old_last = cursor->last;
 	struct callchain_node *child, *next_child;
 	struct callchain_list *list, *next_list;
-	int old_pos = chain->nr;
+	int old_pos = cursor->nr;
 	int err = 0;
 
 	list_for_each_entry_safe(list, next_list, &src->val, list) {
-		chain->ips[chain->nr].ip = list->ip;
-		chain->ips[chain->nr].ms = list->ms;
-		chain->nr++;
+		callchain_cursor_append(cursor, list->ip,
+					list->ms.map, list->ms.sym);
 		list_del(&list->list);
 		free(list);
 	}
 
-	if (src->hit)
-		append_chain_children(dst, chain, 0, src->hit);
+	if (src->hit) {
+		callchain_cursor_commit(cursor);
+		append_chain_children(dst, cursor, src->hit);
+	}
 
 	chain_for_each_child_safe(child, next_child, src) {
-		err = merge_chain_branch(dst, child, chain);
+		err = merge_chain_branch(cursor, dst, child);
 		if (err)
 			break;
 
-		list_del(&child->brothers);
+		list_del(&child->siblings);
 		free(child);
 	}
 
-	chain->nr = old_pos;
+	cursor->nr = old_pos;
+	cursor->last = old_last;
 
 	return err;
 }
 
-int callchain_merge(struct callchain_root *dst, struct callchain_root *src)
+int callchain_merge(struct callchain_cursor *cursor,
+		    struct callchain_root *dst, struct callchain_root *src)
+{
+	return merge_chain_branch(cursor, &dst->node, &src->node);
+}
+
+int callchain_cursor_append(struct callchain_cursor *cursor,
+			    u64 ip, struct map *map, struct symbol *sym)
 {
-	struct resolved_chain *chain;
-	int err;
+	struct callchain_cursor_node *node = *cursor->last;
 
-	chain = malloc(sizeof(*chain) +
-		       src->max_depth * sizeof(struct resolved_ip));
-	if (!chain)
-		return -ENOMEM;
+	if (!node) {
+		node = calloc(sizeof(*node), 1);
+		if (!node)
+			return -ENOMEM;
 
-	chain->nr = 0;
+		*cursor->last = node;
+	}
 
-	err = merge_chain_branch(&dst->node, &src->node, chain);
+	node->ip = ip;
+	node->map = map;
+	node->sym = sym;
 
-	free(chain);
+	cursor->nr++;
 
-	return err;
+	cursor->last = &node->next;
+
+	return 0;
 }
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index c15fb8c24ad2..1a79df9f739f 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -16,7 +16,7 @@ enum chain_mode {
 
 struct callchain_node {
 	struct callchain_node	*parent;
-	struct list_head	brothers;
+	struct list_head	siblings;
 	struct list_head	children;
 	struct list_head	val;
 	struct rb_node		rb_node; /* to sort nodes in an rbtree */
@@ -49,9 +49,30 @@ struct callchain_list {
 	struct list_head	list;
 };
 
+/*
+ * A callchain cursor is a single linked list that
+ * let one feed a callchain progressively.
+ * It keeps persitent allocated entries to minimize
+ * allocations.
+ */
+struct callchain_cursor_node {
+	u64				ip;
+	struct map			*map;
+	struct symbol			*sym;
+	struct callchain_cursor_node	*next;
+};
+
+struct callchain_cursor {
+	u64				nr;
+	struct callchain_cursor_node	*first;
+	struct callchain_cursor_node	**last;
+	u64				pos;
+	struct callchain_cursor_node	*curr;
+};
+
 static inline void callchain_init(struct callchain_root *root)
 {
-	INIT_LIST_HEAD(&root->node.brothers);
+	INIT_LIST_HEAD(&root->node.siblings);
 	INIT_LIST_HEAD(&root->node.children);
 	INIT_LIST_HEAD(&root->node.val);
 
@@ -61,15 +82,54 @@ static inline void callchain_init(struct callchain_root *root)
 	root->max_depth = 0;
 }
 
-static inline u64 cumul_hits(struct callchain_node *node)
+static inline u64 callchain_cumul_hits(struct callchain_node *node)
 {
 	return node->hit + node->children_hit;
 }
 
-int register_callchain_param(struct callchain_param *param);
-int callchain_append(struct callchain_root *root, struct ip_callchain *chain,
-		     struct map_symbol *syms, u64 period);
-int callchain_merge(struct callchain_root *dst, struct callchain_root *src);
+int callchain_register_param(struct callchain_param *param);
+int callchain_append(struct callchain_root *root,
+		     struct callchain_cursor *cursor,
+		     u64 period);
+
+int callchain_merge(struct callchain_cursor *cursor,
+		    struct callchain_root *dst, struct callchain_root *src);
+
+bool ip_callchain__valid(struct ip_callchain *chain,
+			 const union perf_event *event);
+/*
+ * Initialize a cursor before adding entries inside, but keep
+ * the previously allocated entries as a cache.
+ */
+static inline void callchain_cursor_reset(struct callchain_cursor *cursor)
+{
+	cursor->nr = 0;
+	cursor->last = &cursor->first;
+}
+
+int callchain_cursor_append(struct callchain_cursor *cursor, u64 ip,
+			    struct map *map, struct symbol *sym);
 
-bool ip_callchain__valid(struct ip_callchain *chain, const event_t *event);
+/* Close a cursor writing session. Initialize for the reader */
+static inline void callchain_cursor_commit(struct callchain_cursor *cursor)
+{
+	cursor->curr = cursor->first;
+	cursor->pos = 0;
+}
+
+/* Cursor reading iteration helpers */
+static inline struct callchain_cursor_node *
+callchain_cursor_current(struct callchain_cursor *cursor)
+{
+	if (cursor->pos == cursor->nr)
+		return NULL;
+
+	return cursor->curr;
+}
+
+static inline void callchain_cursor_advance(struct callchain_cursor *cursor)
+{
+	cursor->curr = cursor->curr->next;
+	cursor->pos++;
+}
 #endif	/* __PERF_CALLCHAIN_H */
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
new file mode 100644
index 000000000000..9fea75535221
--- /dev/null
+++ b/tools/perf/util/cgroup.c
@@ -0,0 +1,178 @@
+#include "util.h"
+#include "../perf.h"
+#include "parse-options.h"
+#include "evsel.h"
+#include "cgroup.h"
+#include "debugfs.h" /* MAX_PATH, STR() */
+#include "evlist.h"
+
+int nr_cgroups;
+
+static int
+cgroupfs_find_mountpoint(char *buf, size_t maxlen)
+{
+	FILE *fp;
+	char mountpoint[MAX_PATH+1], tokens[MAX_PATH+1], type[MAX_PATH+1];
+	char *token, *saved_ptr;
+	int found = 0;
+
+	fp = fopen("/proc/mounts", "r");
+	if (!fp)
+		return -1;
+
+	/*
+	 * in order to handle split hierarchy, we need to scan /proc/mounts
+	 * and inspect every cgroupfs mount point to find one that has
+	 * perf_event subsystem
+	 */
+	while (fscanf(fp, "%*s %"STR(MAX_PATH)"s %"STR(MAX_PATH)"s %"
+				STR(MAX_PATH)"s %*d %*d\n",
+				mountpoint, type, tokens) == 3) {
+
+		if (!strcmp(type, "cgroup")) {
+
+			token = strtok_r(tokens, ",", &saved_ptr);
+
+			while (token != NULL) {
+				if (!strcmp(token, "perf_event")) {
+					found = 1;
+					break;
+				}
+				token = strtok_r(NULL, ",", &saved_ptr);
+			}
+		}
+		if (found)
+			break;
+	}
+	fclose(fp);
+	if (!found)
+		return -1;
+
+	if (strlen(mountpoint) < maxlen) {
+		strcpy(buf, mountpoint);
+		return 0;
+	}
+	return -1;
+}
+
+static int open_cgroup(char *name)
+{
+	char path[MAX_PATH+1];
+	char mnt[MAX_PATH+1];
+	int fd;
+
+
+	if (cgroupfs_find_mountpoint(mnt, MAX_PATH+1))
+		return -1;
+
+	snprintf(path, MAX_PATH, "%s/%s", mnt, name);
+
+	fd = open(path, O_RDONLY);
+	if (fd == -1)
+		fprintf(stderr, "no access to cgroup %s\n", path);
+
+	return fd;
+}
+
+static int add_cgroup(struct perf_evlist *evlist, char *str)
+{
+	struct perf_evsel *counter;
+	struct cgroup_sel *cgrp = NULL;
+	int n;
+	/*
+	 * check if cgrp is already defined, if so we reuse it
+	 */
+	list_for_each_entry(counter, &evlist->entries, node) {
+		cgrp = counter->cgrp;
+		if (!cgrp)
+			continue;
+		if (!strcmp(cgrp->name, str))
+			break;
+
+		cgrp = NULL;
+	}
+
+	if (!cgrp) {
+		cgrp = zalloc(sizeof(*cgrp));
+		if (!cgrp)
+			return -1;
+
+		cgrp->name = str;
+
+		cgrp->fd = open_cgroup(str);
+		if (cgrp->fd == -1) {
+			free(cgrp);
+			return -1;
+		}
+	}
+
+	/*
+	 * find corresponding event
+	 * if add cgroup N, then need to find event N
+	 */
+	n = 0;
+	list_for_each_entry(counter, &evlist->entries, node) {
+		if (n == nr_cgroups)
+			goto found;
+		n++;
+	}
+	if (cgrp->refcnt == 0)
+		free(cgrp);
+
+	return -1;
+found:
+	cgrp->refcnt++;
+	counter->cgrp = cgrp;
+	return 0;
+}
+
+void close_cgroup(struct cgroup_sel *cgrp)
+{
+	if (!cgrp)
+		return;
+
+	/* XXX: not reentrant */
+	if (--cgrp->refcnt == 0) {
+		close(cgrp->fd);
+		free(cgrp->name);
+		free(cgrp);
+	}
+}
+
+int parse_cgroups(const struct option *opt __used, const char *str,
+		  int unset __used)
+{
+	struct perf_evlist *evlist = *(struct perf_evlist **)opt->value;
+	const char *p, *e, *eos = str + strlen(str);
+	char *s;
+	int ret;
+
+	if (list_empty(&evlist->entries)) {
+		fprintf(stderr, "must define events before cgroups\n");
+		return -1;
+	}
+
+	for (;;) {
+		p = strchr(str, ',');
+		e = p ? p : eos;
+
+		/* allow empty cgroups, i.e., skip */
+		if (e - str) {
+			/* termination added */
+			s = strndup(str, e - str);
+			if (!s)
+				return -1;
+			ret = add_cgroup(evlist, s);
+			if (ret) {
+				free(s);
+				return -1;
+			}
+		}
+		/* nr_cgroups is increased een for empty cgroups */
+		nr_cgroups++;
+		if (!p)
+			break;
+		str = p+1;
+	}
+	return 0;
+}
diff --git a/tools/perf/util/cgroup.h b/tools/perf/util/cgroup.h
new file mode 100644
index 000000000000..89acd6debdc5
--- /dev/null
+++ b/tools/perf/util/cgroup.h
@@ -0,0 +1,17 @@
+#ifndef __CGROUP_H__
+#define __CGROUP_H__
+
+struct option;
+
+struct cgroup_sel {
+	char *name;
+	int fd;
+	int refcnt;
+};
+
+
+extern int nr_cgroups; /* number of explicit cgroups defined */
+extern void close_cgroup(struct cgroup_sel *cgrp);
+extern int parse_cgroups(const struct option *opt, const char *str, int unset);
+
+#endif /* __CGROUP_H__ */
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 3ccaa1043383..6893eec693ab 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -177,3 +177,8 @@ struct cpu_map *cpu_map__dummy_new(void)
 
 	return cpus;
 }
+
+void cpu_map__delete(struct cpu_map *map)
+{
+	free(map);
+}
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index f7a4f42f6307..072c0a374794 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -8,6 +8,6 @@ struct cpu_map {
 
 struct cpu_map *cpu_map__new(const char *cpu_list);
 struct cpu_map *cpu_map__dummy_new(void);
-void *cpu_map__delete(struct cpu_map *map);
+void cpu_map__delete(struct cpu_map *map);
 
 #endif /* __PERF_CPUMAP_H */
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index 01bbe8ecec3f..d4536a9e0d8c 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -57,7 +57,7 @@ void ui__warning(const char *format, ...)
 }
 #endif
 
-void trace_event(event_t *event)
+void trace_event(union perf_event *event)
 {
 	unsigned char *raw_event = (void *)event;
 	const char *color = PERF_COLOR_BLUE;
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index ca35fd66b5df..93516cf4682c 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -9,7 +9,7 @@ extern int verbose;
 extern bool quiet, dump_trace;
 
 int dump_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2)));
-void trace_event(event_t *event);
+void trace_event(union perf_event *event);
 
 struct ui_progress;
 
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 50d0a931497a..2b15c362ef56 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -6,8 +6,9 @@
 #include "string.h"
 #include "strlist.h"
 #include "thread.h"
+#include "thread_map.h"
 
-static const char *event__name[] = {
+static const char *perf_event__names[] = {
 	[0]			 = "TOTAL",
 	[PERF_RECORD_MMAP]	 = "MMAP",
 	[PERF_RECORD_LOST]	 = "LOST",
@@ -25,16 +26,16 @@ static const char *event__name[] = {
 	[PERF_RECORD_FINISHED_ROUND]	 = "FINISHED_ROUND",
 };
 
-const char *event__get_event_name(unsigned int id)
+const char *perf_event__name(unsigned int id)
 {
-	if (id >= ARRAY_SIZE(event__name))
+	if (id >= ARRAY_SIZE(perf_event__names))
 		return "INVALID";
-	if (!event__name[id])
+	if (!perf_event__names[id])
 		return "UNKNOWN";
-	return event__name[id];
+	return perf_event__names[id];
 }
 
-static struct sample_data synth_sample = {
+static struct perf_sample synth_sample = {
 	.pid	   = -1,
 	.tid	   = -1,
 	.time	   = -1,
@@ -43,9 +44,9 @@ static struct sample_data synth_sample = {
 	.period	   = 1,
 };
 
-static pid_t event__synthesize_comm(event_t *event, pid_t pid, int full,
-				    event__handler_t process,
-				    struct perf_session *session)
+static pid_t perf_event__synthesize_comm(union perf_event *event, pid_t pid,
+					 int full, perf_event__handler_t process,
+					 struct perf_session *session)
 {
 	char filename[PATH_MAX];
 	char bf[BUFSIZ];
@@ -126,9 +127,10 @@ out:
 	return tgid;
 }
 
-static int event__synthesize_mmap_events(event_t *event, pid_t pid, pid_t tgid,
-					 event__handler_t process,
-					 struct perf_session *session)
+static int perf_event__synthesize_mmap_events(union perf_event *event,
+					      pid_t pid, pid_t tgid,
+					      perf_event__handler_t process,
+					      struct perf_session *session)
 {
 	char filename[PATH_MAX];
 	FILE *fp;
@@ -199,14 +201,14 @@ static int event__synthesize_mmap_events(event_t *event, pid_t pid, pid_t tgid,
 	return 0;
 }
 
-int event__synthesize_modules(event__handler_t process,
-			      struct perf_session *session,
-			      struct machine *machine)
+int perf_event__synthesize_modules(perf_event__handler_t process,
+				   struct perf_session *session,
+				   struct machine *machine)
 {
 	struct rb_node *nd;
 	struct map_groups *kmaps = &machine->kmaps;
-	event_t *event = zalloc(sizeof(event->mmap) + session->id_hdr_size);
-
+	union perf_event *event = zalloc((sizeof(event->mmap) +
+					  session->id_hdr_size));
 	if (event == NULL) {
 		pr_debug("Not enough memory synthesizing mmap event "
 			 "for kernel modules\n");
@@ -251,23 +253,24 @@ int event__synthesize_modules(event__handler_t process,
 	return 0;
 }
 
-static int __event__synthesize_thread(event_t *comm_event, event_t *mmap_event,
-				      pid_t pid, event__handler_t process,
+static int __event__synthesize_thread(union perf_event *comm_event,
+				      union perf_event *mmap_event,
+				      pid_t pid, perf_event__handler_t process,
 				      struct perf_session *session)
 {
-	pid_t tgid = event__synthesize_comm(comm_event, pid, 1, process,
+	pid_t tgid = perf_event__synthesize_comm(comm_event, pid, 1, process,
 					    session);
 	if (tgid == -1)
 		return -1;
-	return event__synthesize_mmap_events(mmap_event, pid, tgid,
+	return perf_event__synthesize_mmap_events(mmap_event, pid, tgid,
 					     process, session);
 }
 
-int event__synthesize_thread_map(struct thread_map *threads,
-				 event__handler_t process,
-				 struct perf_session *session)
+int perf_event__synthesize_thread_map(struct thread_map *threads,
+				      perf_event__handler_t process,
+				      struct perf_session *session)
 {
-	event_t *comm_event, *mmap_event;
+	union perf_event *comm_event, *mmap_event;
 	int err = -1, thread;
 
 	comm_event = malloc(sizeof(comm_event->comm) + session->id_hdr_size);
@@ -294,12 +297,12 @@ out:
 	return err;
 }
 
-int event__synthesize_threads(event__handler_t process,
-			      struct perf_session *session)
+int perf_event__synthesize_threads(perf_event__handler_t process,
+				   struct perf_session *session)
 {
 	DIR *proc;
 	struct dirent dirent, *next;
-	event_t *comm_event, *mmap_event;
+	union perf_event *comm_event, *mmap_event;
 	int err = -1;
 
 	comm_event = malloc(sizeof(comm_event->comm) + session->id_hdr_size);
@@ -357,10 +360,10 @@ static int find_symbol_cb(void *arg, const char *name, char type,
 	return 1;
 }
 
-int event__synthesize_kernel_mmap(event__handler_t process,
-				  struct perf_session *session,
-				  struct machine *machine,
-				  const char *symbol_name)
+int perf_event__synthesize_kernel_mmap(perf_event__handler_t process,
+				       struct perf_session *session,
+				       struct machine *machine,
+				       const char *symbol_name)
 {
 	size_t size;
 	const char *filename, *mmap_name;
@@ -374,8 +377,8 @@ int event__synthesize_kernel_mmap(event__handler_t process,
 	 * kernels.
 	 */
 	struct process_symbol_args args = { .name = symbol_name, };
-	event_t *event = zalloc(sizeof(event->mmap) + session->id_hdr_size);
-
+	union perf_event *event = zalloc((sizeof(event->mmap) +
+					  session->id_hdr_size));
 	if (event == NULL) {
 		pr_debug("Not enough memory synthesizing mmap event "
 			 "for kernel modules\n");
@@ -421,42 +424,15 @@ int event__synthesize_kernel_mmap(event__handler_t process,
 	return err;
 }
 
-static void thread__comm_adjust(struct thread *self, struct hists *hists)
-{
-	char *comm = self->comm;
-
-	if (!symbol_conf.col_width_list_str && !symbol_conf.field_sep &&
-	    (!symbol_conf.comm_list ||
-	     strlist__has_entry(symbol_conf.comm_list, comm))) {
-		u16 slen = strlen(comm);
-
-		if (hists__new_col_len(hists, HISTC_COMM, slen))
-			hists__set_col_len(hists, HISTC_THREAD, slen + 6);
-	}
-}
-
-static int thread__set_comm_adjust(struct thread *self, const char *comm,
-				   struct hists *hists)
+int perf_event__process_comm(union perf_event *event,
+			     struct perf_sample *sample __used,
+			     struct perf_session *session)
 {
-	int ret = thread__set_comm(self, comm);
-
-	if (ret)
-		return ret;
-
-	thread__comm_adjust(self, hists);
+	struct thread *thread = perf_session__findnew(session, event->comm.tid);
 
-	return 0;
-}
+	dump_printf(": %s:%d\n", event->comm.comm, event->comm.tid);
 
-int event__process_comm(event_t *self, struct sample_data *sample __used,
-			struct perf_session *session)
-{
-	struct thread *thread = perf_session__findnew(session, self->comm.tid);
-
-	dump_printf(": %s:%d\n", self->comm.comm, self->comm.tid);
-
-	if (thread == NULL || thread__set_comm_adjust(thread, self->comm.comm,
-						      &session->hists)) {
+	if (thread == NULL || thread__set_comm(thread, event->comm.comm)) {
 		dump_printf("problem processing PERF_RECORD_COMM, skipping event.\n");
 		return -1;
 	}
@@ -464,19 +440,21 @@ int event__process_comm(event_t *self, struct sample_data *sample __used,
 	return 0;
 }
 
-int event__process_lost(event_t *self, struct sample_data *sample __used,
-			struct perf_session *session)
+int perf_event__process_lost(union perf_event *event,
+			     struct perf_sample *sample __used,
+			     struct perf_session *session)
 {
 	dump_printf(": id:%" PRIu64 ": lost:%" PRIu64 "\n",
-		    self->lost.id, self->lost.lost);
-	session->hists.stats.total_lost += self->lost.lost;
+		    event->lost.id, event->lost.lost);
+	session->hists.stats.total_lost += event->lost.lost;
 	return 0;
 }
 
-static void event_set_kernel_mmap_len(struct map **maps, event_t *self)
+static void perf_event__set_kernel_mmap_len(union perf_event *event,
+					    struct map **maps)
 {
-	maps[MAP__FUNCTION]->start = self->mmap.start;
-	maps[MAP__FUNCTION]->end   = self->mmap.start + self->mmap.len;
+	maps[MAP__FUNCTION]->start = event->mmap.start;
+	maps[MAP__FUNCTION]->end   = event->mmap.start + event->mmap.len;
 	/*
 	 * Be a bit paranoid here, some perf.data file came with
 	 * a zero sized synthesized MMAP event for the kernel.
@@ -485,8 +463,8 @@ static void event_set_kernel_mmap_len(struct map **maps, event_t *self)
 		maps[MAP__FUNCTION]->end = ~0ULL;
 }
 
-static int event__process_kernel_mmap(event_t *self,
-			struct perf_session *session)
+static int perf_event__process_kernel_mmap(union perf_event *event,
+					   struct perf_session *session)
 {
 	struct map *map;
 	char kmmap_prefix[PATH_MAX];
@@ -494,9 +472,9 @@ static int event__process_kernel_mmap(event_t *self,
 	enum dso_kernel_type kernel_type;
 	bool is_kernel_mmap;
 
-	machine = perf_session__findnew_machine(session, self->mmap.pid);
+	machine = perf_session__findnew_machine(session, event->mmap.pid);
 	if (!machine) {
-		pr_err("Can't find id %d's machine\n", self->mmap.pid);
+		pr_err("Can't find id %d's machine\n", event->mmap.pid);
 		goto out_problem;
 	}
 
@@ -506,17 +484,17 @@ static int event__process_kernel_mmap(event_t *self,
 	else
 		kernel_type = DSO_TYPE_GUEST_KERNEL;
 
-	is_kernel_mmap = memcmp(self->mmap.filename,
+	is_kernel_mmap = memcmp(event->mmap.filename,
 				kmmap_prefix,
 				strlen(kmmap_prefix)) == 0;
-	if (self->mmap.filename[0] == '/' ||
-	    (!is_kernel_mmap && self->mmap.filename[0] == '[')) {
+	if (event->mmap.filename[0] == '/' ||
+	    (!is_kernel_mmap && event->mmap.filename[0] == '[')) {
 
 		char short_module_name[1024];
 		char *name, *dot;
 
-		if (self->mmap.filename[0] == '/') {
-			name = strrchr(self->mmap.filename, '/');
+		if (event->mmap.filename[0] == '/') {
+			name = strrchr(event->mmap.filename, '/');
 			if (name == NULL)
 				goto out_problem;
 
@@ -528,10 +506,10 @@ static int event__process_kernel_mmap(event_t *self,
 					"[%.*s]", (int)(dot - name), name);
 			strxfrchar(short_module_name, '-', '_');
 		} else
-			strcpy(short_module_name, self->mmap.filename);
+			strcpy(short_module_name, event->mmap.filename);
 
-		map = machine__new_module(machine, self->mmap.start,
-					  self->mmap.filename);
+		map = machine__new_module(machine, event->mmap.start,
+					  event->mmap.filename);
 		if (map == NULL)
 			goto out_problem;
 
@@ -541,9 +519,9 @@ static int event__process_kernel_mmap(event_t *self,
 
 		map->dso->short_name = name;
 		map->dso->sname_alloc = 1;
-		map->end = map->start + self->mmap.len;
+		map->end = map->start + event->mmap.len;
 	} else if (is_kernel_mmap) {
-		const char *symbol_name = (self->mmap.filename +
+		const char *symbol_name = (event->mmap.filename +
 				strlen(kmmap_prefix));
 		/*
 		 * Should be there already, from the build-id table in
@@ -558,10 +536,10 @@ static int event__process_kernel_mmap(event_t *self,
 		if (__machine__create_kernel_maps(machine, kernel) < 0)
 			goto out_problem;
 
-		event_set_kernel_mmap_len(machine->vmlinux_maps, self);
+		perf_event__set_kernel_mmap_len(event, machine->vmlinux_maps);
 		perf_session__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps,
 							 symbol_name,
-							 self->mmap.pgoff);
+							 event->mmap.pgoff);
 		if (machine__is_default_guest(machine)) {
 			/*
 			 * preload dso of guest kernel and modules
@@ -575,22 +553,23 @@ out_problem:
 	return -1;
 }
 
-int event__process_mmap(event_t *self, struct sample_data *sample __used,
-			struct perf_session *session)
+int perf_event__process_mmap(union perf_event *event,
+			     struct perf_sample *sample __used,
+			     struct perf_session *session)
 {
 	struct machine *machine;
 	struct thread *thread;
 	struct map *map;
-	u8 cpumode = self->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 	int ret = 0;
 
 	dump_printf(" %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64 "]: %s\n",
-			self->mmap.pid, self->mmap.tid, self->mmap.start,
-			self->mmap.len, self->mmap.pgoff, self->mmap.filename);
+			event->mmap.pid, event->mmap.tid, event->mmap.start,
+			event->mmap.len, event->mmap.pgoff, event->mmap.filename);
 
 	if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL ||
 	    cpumode == PERF_RECORD_MISC_KERNEL) {
-		ret = event__process_kernel_mmap(self, session);
+		ret = perf_event__process_kernel_mmap(event, session);
 		if (ret < 0)
 			goto out_problem;
 		return 0;
@@ -599,12 +578,12 @@ int event__process_mmap(event_t *self, struct sample_data *sample __used,
 	machine = perf_session__find_host_machine(session);
 	if (machine == NULL)
 		goto out_problem;
-	thread = perf_session__findnew(session, self->mmap.pid);
+	thread = perf_session__findnew(session, event->mmap.pid);
 	if (thread == NULL)
 		goto out_problem;
-	map = map__new(&machine->user_dsos, self->mmap.start,
-			self->mmap.len, self->mmap.pgoff,
-			self->mmap.pid, self->mmap.filename,
+	map = map__new(&machine->user_dsos, event->mmap.start,
+			event->mmap.len, event->mmap.pgoff,
+			event->mmap.pid, event->mmap.filename,
 			MAP__FUNCTION);
 	if (map == NULL)
 		goto out_problem;
@@ -617,16 +596,17 @@ out_problem:
 	return 0;
 }
 
-int event__process_task(event_t *self, struct sample_data *sample __used,
-			struct perf_session *session)
+int perf_event__process_task(union perf_event *event,
+			     struct perf_sample *sample __used,
+			     struct perf_session *session)
 {
-	struct thread *thread = perf_session__findnew(session, self->fork.tid);
-	struct thread *parent = perf_session__findnew(session, self->fork.ptid);
+	struct thread *thread = perf_session__findnew(session, event->fork.tid);
+	struct thread *parent = perf_session__findnew(session, event->fork.ptid);
 
-	dump_printf("(%d:%d):(%d:%d)\n", self->fork.pid, self->fork.tid,
-		    self->fork.ppid, self->fork.ptid);
+	dump_printf("(%d:%d):(%d:%d)\n", event->fork.pid, event->fork.tid,
+		    event->fork.ppid, event->fork.ptid);
 
-	if (self->header.type == PERF_RECORD_EXIT) {
+	if (event->header.type == PERF_RECORD_EXIT) {
 		perf_session__remove_thread(session, thread);
 		return 0;
 	}
@@ -640,20 +620,22 @@ int event__process_task(event_t *self, struct sample_data *sample __used,
 	return 0;
 }
 
-int event__process(event_t *event, struct sample_data *sample,
-		   struct perf_session *session)
+int perf_event__process(union perf_event *event, struct perf_sample *sample,
+			struct perf_session *session)
 {
 	switch (event->header.type) {
 	case PERF_RECORD_COMM:
-		event__process_comm(event, sample, session);
+		perf_event__process_comm(event, sample, session);
 		break;
 	case PERF_RECORD_MMAP:
-		event__process_mmap(event, sample, session);
+		perf_event__process_mmap(event, sample, session);
 		break;
 	case PERF_RECORD_FORK:
 	case PERF_RECORD_EXIT:
-		event__process_task(event, sample, session);
+		perf_event__process_task(event, sample, session);
 		break;
+	case PERF_RECORD_LOST:
+		perf_event__process_lost(event, sample, session);
 	default:
 		break;
 	}
@@ -750,24 +732,14 @@ void thread__find_addr_location(struct thread *self,
 		al->sym = NULL;
 }
 
-static void dso__calc_col_width(struct dso *self, struct hists *hists)
-{
-	if (!symbol_conf.col_width_list_str && !symbol_conf.field_sep &&
-	    (!symbol_conf.dso_list ||
-	     strlist__has_entry(symbol_conf.dso_list, self->name))) {
-		u16 slen = dso__name_len(self);
-		hists__new_col_len(hists, HISTC_DSO, slen);
-	}
-
-	self->slen_calculated = 1;
-}
-
-int event__preprocess_sample(const event_t *self, struct perf_session *session,
-			     struct addr_location *al, struct sample_data *data,
-			     symbol_filter_t filter)
+int perf_event__preprocess_sample(const union perf_event *event,
+				  struct perf_session *session,
+				  struct addr_location *al,
+				  struct perf_sample *sample,
+				  symbol_filter_t filter)
 {
-	u8 cpumode = self->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
-	struct thread *thread = perf_session__findnew(session, self->ip.pid);
+	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+	struct thread *thread = perf_session__findnew(session, event->ip.pid);
 
 	if (thread == NULL)
 		return -1;
@@ -789,12 +761,12 @@ int event__preprocess_sample(const event_t *self, struct perf_session *session,
 		machine__create_kernel_maps(&session->host_machine);
 
 	thread__find_addr_map(thread, session, cpumode, MAP__FUNCTION,
-			      self->ip.pid, self->ip.ip, al);
+			      event->ip.pid, event->ip.ip, al);
 	dump_printf(" ...... dso: %s\n",
 		    al->map ? al->map->dso->long_name :
 			al->level == 'H' ? "[hypervisor]" : "<not found>");
 	al->sym = NULL;
-	al->cpu = data->cpu;
+	al->cpu = sample->cpu;
 
 	if (al->map) {
 		if (symbol_conf.dso_list &&
@@ -805,23 +777,8 @@ int event__preprocess_sample(const event_t *self, struct perf_session *session,
 			strlist__has_entry(symbol_conf.dso_list,
 					   al->map->dso->long_name)))))
 			goto out_filtered;
-		/*
-		 * We have to do this here as we may have a dso with no symbol
-		 * hit that has a name longer than the ones with symbols
-		 * sampled.
-		 */
-		if (!sort_dso.elide && !al->map->dso->slen_calculated)
-			dso__calc_col_width(al->map->dso, &session->hists);
 
 		al->sym = map__find_symbol(al->map, al->addr, filter);
-	} else {
-		const unsigned int unresolved_col_width = BITS_PER_LONG / 4;
-
-		if (hists__col_len(&session->hists, HISTC_DSO) < unresolved_col_width &&
-		    !symbol_conf.col_width_list_str && !symbol_conf.field_sep &&
-		    !symbol_conf.dso_list)
-			hists__set_col_len(&session->hists, HISTC_DSO,
-					   unresolved_col_width);
 	}
 
 	if (symbol_conf.sym_list && al->sym &&
@@ -834,128 +791,3 @@ out_filtered:
 	al->filtered = true;
 	return 0;
 }
-
-static int event__parse_id_sample(const event_t *event,
-				  struct perf_session *session,
-				  struct sample_data *sample)
-{
-	const u64 *array;
-	u64 type;
-
-	sample->cpu = sample->pid = sample->tid = -1;
-	sample->stream_id = sample->id = sample->time = -1ULL;
-
-	if (!session->sample_id_all)
-		return 0;
-
-	array = event->sample.array;
-	array += ((event->header.size -
-		   sizeof(event->header)) / sizeof(u64)) - 1;
-	type = session->sample_type;
-
-	if (type & PERF_SAMPLE_CPU) {
-		u32 *p = (u32 *)array;
-		sample->cpu = *p;
-		array--;
-	}
-
-	if (type & PERF_SAMPLE_STREAM_ID) {
-		sample->stream_id = *array;
-		array--;
-	}
-
-	if (type & PERF_SAMPLE_ID) {
-		sample->id = *array;
-		array--;
-	}
-
-	if (type & PERF_SAMPLE_TIME) {
-		sample->time = *array;
-		array--;
-	}
-
-	if (type & PERF_SAMPLE_TID) {
-		u32 *p = (u32 *)array;
-		sample->pid = p[0];
-		sample->tid = p[1];
-	}
-
-	return 0;
-}
-
-int event__parse_sample(const event_t *event, struct perf_session *session,
-			struct sample_data *data)
-{
-	const u64 *array;
-	u64 type;
-
-	if (event->header.type != PERF_RECORD_SAMPLE)
-		return event__parse_id_sample(event, session, data);
-
-	array = event->sample.array;
-	type = session->sample_type;
-
-	if (type & PERF_SAMPLE_IP) {
-		data->ip = event->ip.ip;
-		array++;
-	}
-
-	if (type & PERF_SAMPLE_TID) {
-		u32 *p = (u32 *)array;
-		data->pid = p[0];
-		data->tid = p[1];
-		array++;
-	}
-
-	if (type & PERF_SAMPLE_TIME) {
-		data->time = *array;
-		array++;
-	}
-
-	if (type & PERF_SAMPLE_ADDR) {
-		data->addr = *array;
-		array++;
-	}
-
-	data->id = -1ULL;
-	if (type & PERF_SAMPLE_ID) {
-		data->id = *array;
-		array++;
-	}
-
-	if (type & PERF_SAMPLE_STREAM_ID) {
-		data->stream_id = *array;
-		array++;
-	}
-
-	if (type & PERF_SAMPLE_CPU) {
-		u32 *p = (u32 *)array;
-		data->cpu = *p;
-		array++;
-	} else
-		data->cpu = -1;
-
-	if (type & PERF_SAMPLE_PERIOD) {
-		data->period = *array;
-		array++;
-	}
-
-	if (type & PERF_SAMPLE_READ) {
-		pr_debug("PERF_SAMPLE_READ is unsuported for now\n");
-		return -1;
-	}
-
-	if (type & PERF_SAMPLE_CALLCHAIN) {
-		data->callchain = (struct ip_callchain *)array;
-		array += 1 + data->callchain->nr;
-	}
-
-	if (type & PERF_SAMPLE_RAW) {
-		u32 *p = (u32 *)array;
-		data->raw_size = *p;
-		p++;
-		data->raw_data = p;
-	}
-
-	return 0;
-}
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index cc7b52f9b492..9c35170fb379 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -61,7 +61,7 @@ struct sample_event {
 	u64 array[];
 };
 
-struct sample_data {
+struct perf_sample {
 	u64 ip;
 	u32 pid, tid;
 	u64 time;
@@ -117,7 +117,7 @@ struct tracing_data_event {
 	u32 size;
 };
 
-typedef union event_union {
+union perf_event {
 	struct perf_event_header	header;
 	struct ip_event			ip;
 	struct mmap_event		mmap;
@@ -130,50 +130,54 @@ typedef union event_union {
 	struct event_type_event		event_type;
 	struct tracing_data_event	tracing_data;
 	struct build_id_event		build_id;
-} event_t;
+};
 
-void event__print_totals(void);
+void perf_event__print_totals(void);
 
 struct perf_session;
 struct thread_map;
 
-typedef int (*event__handler_synth_t)(event_t *event, 
+typedef int (*perf_event__handler_synth_t)(union perf_event *event, 
+					   struct perf_session *session);
+typedef int (*perf_event__handler_t)(union perf_event *event,
+				     struct perf_sample *sample,
 				      struct perf_session *session);
-typedef int (*event__handler_t)(event_t *event, struct sample_data *sample,
-				struct perf_session *session);
-
-int event__synthesize_thread_map(struct thread_map *threads,
-				 event__handler_t process,
-				 struct perf_session *session);
-int event__synthesize_threads(event__handler_t process,
-			      struct perf_session *session);
-int event__synthesize_kernel_mmap(event__handler_t process,
-				struct perf_session *session,
-				struct machine *machine,
-				const char *symbol_name);
-
-int event__synthesize_modules(event__handler_t process,
-			      struct perf_session *session,
-			      struct machine *machine);
-
-int event__process_comm(event_t *self, struct sample_data *sample,
-			struct perf_session *session);
-int event__process_lost(event_t *self, struct sample_data *sample,
-			struct perf_session *session);
-int event__process_mmap(event_t *self, struct sample_data *sample,
-			struct perf_session *session);
-int event__process_task(event_t *self, struct sample_data *sample,
+
+int perf_event__synthesize_thread_map(struct thread_map *threads,
+				      perf_event__handler_t process,
+				      struct perf_session *session);
+int perf_event__synthesize_threads(perf_event__handler_t process,
+				   struct perf_session *session);
+int perf_event__synthesize_kernel_mmap(perf_event__handler_t process,
+				       struct perf_session *session,
+				       struct machine *machine,
+				       const char *symbol_name);
+
+int perf_event__synthesize_modules(perf_event__handler_t process,
+				   struct perf_session *session,
+				   struct machine *machine);
+
+int perf_event__process_comm(union perf_event *event, struct perf_sample *sample,
+			     struct perf_session *session);
+int perf_event__process_lost(union perf_event *event, struct perf_sample *sample,
+			     struct perf_session *session);
+int perf_event__process_mmap(union perf_event *event, struct perf_sample *sample,
+			     struct perf_session *session);
+int perf_event__process_task(union perf_event *event, struct perf_sample *sample,
+			     struct perf_session *session);
+int perf_event__process(union perf_event *event, struct perf_sample *sample,
 			struct perf_session *session);
-int event__process(event_t *event, struct sample_data *sample,
-		   struct perf_session *session);
 
 struct addr_location;
-int event__preprocess_sample(const event_t *self, struct perf_session *session,
-			     struct addr_location *al, struct sample_data *data,
-			     symbol_filter_t filter);
-int event__parse_sample(const event_t *event, struct perf_session *session,
-			struct sample_data *sample);
+int perf_event__preprocess_sample(const union perf_event *self,
+				  struct perf_session *session,
+				  struct addr_location *al,
+				  struct perf_sample *sample,
+				  symbol_filter_t filter);
+
+const char *perf_event__name(unsigned int id);
 
-const char *event__get_event_name(unsigned int id);
+int perf_event__parse_sample(const union perf_event *event, u64 type,
+			     bool sample_id_all, struct perf_sample *sample);
 
 #endif /* __PERF_RECORD_H */
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
new file mode 100644
index 000000000000..d852cefa20de
--- /dev/null
+++ b/tools/perf/util/evlist.c
@@ -0,0 +1,394 @@
+/*
+ * Copyright (C) 2011, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Parts came from builtin-{top,stat,record}.c, see those files for further
+ * copyright notes.
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+#include <poll.h>
+#include "cpumap.h"
+#include "thread_map.h"
+#include "evlist.h"
+#include "evsel.h"
+#include "util.h"
+
+#include <sys/mman.h>
+
+#include <linux/bitops.h>
+#include <linux/hash.h>
+
+#define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
+#define SID(e, x, y) xyarray__entry(e->sample_id, x, y)
+
+void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus,
+		       struct thread_map *threads)
+{
+	int i;
+
+	for (i = 0; i < PERF_EVLIST__HLIST_SIZE; ++i)
+		INIT_HLIST_HEAD(&evlist->heads[i]);
+	INIT_LIST_HEAD(&evlist->entries);
+	perf_evlist__set_maps(evlist, cpus, threads);
+}
+
+struct perf_evlist *perf_evlist__new(struct cpu_map *cpus,
+				     struct thread_map *threads)
+{
+	struct perf_evlist *evlist = zalloc(sizeof(*evlist));
+
+	if (evlist != NULL)
+		perf_evlist__init(evlist, cpus, threads);
+
+	return evlist;
+}
+
+static void perf_evlist__purge(struct perf_evlist *evlist)
+{
+	struct perf_evsel *pos, *n;
+
+	list_for_each_entry_safe(pos, n, &evlist->entries, node) {
+		list_del_init(&pos->node);
+		perf_evsel__delete(pos);
+	}
+
+	evlist->nr_entries = 0;
+}
+
+void perf_evlist__exit(struct perf_evlist *evlist)
+{
+	free(evlist->mmap);
+	free(evlist->pollfd);
+	evlist->mmap = NULL;
+	evlist->pollfd = NULL;
+}
+
+void perf_evlist__delete(struct perf_evlist *evlist)
+{
+	perf_evlist__purge(evlist);
+	perf_evlist__exit(evlist);
+	free(evlist);
+}
+
+void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry)
+{
+	list_add_tail(&entry->node, &evlist->entries);
+	++evlist->nr_entries;
+}
+
+int perf_evlist__add_default(struct perf_evlist *evlist)
+{
+	struct perf_event_attr attr = {
+		.type = PERF_TYPE_HARDWARE,
+		.config = PERF_COUNT_HW_CPU_CYCLES,
+	};
+	struct perf_evsel *evsel = perf_evsel__new(&attr, 0);
+
+	if (evsel == NULL)
+		return -ENOMEM;
+
+	perf_evlist__add(evlist, evsel);
+	return 0;
+}
+
+int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
+{
+	int nfds = evlist->cpus->nr * evlist->threads->nr * evlist->nr_entries;
+	evlist->pollfd = malloc(sizeof(struct pollfd) * nfds);
+	return evlist->pollfd != NULL ? 0 : -ENOMEM;
+}
+
+void perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd)
+{
+	fcntl(fd, F_SETFL, O_NONBLOCK);
+	evlist->pollfd[evlist->nr_fds].fd = fd;
+	evlist->pollfd[evlist->nr_fds].events = POLLIN;
+	evlist->nr_fds++;
+}
+
+static void perf_evlist__id_hash(struct perf_evlist *evlist,
+				 struct perf_evsel *evsel,
+				 int cpu, int thread, u64 id)
+{
+	int hash;
+	struct perf_sample_id *sid = SID(evsel, cpu, thread);
+
+	sid->id = id;
+	sid->evsel = evsel;
+	hash = hash_64(sid->id, PERF_EVLIST__HLIST_BITS);
+	hlist_add_head(&sid->node, &evlist->heads[hash]);
+}
+
+void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel,
+			 int cpu, int thread, u64 id)
+{
+	perf_evlist__id_hash(evlist, evsel, cpu, thread, id);
+	evsel->id[evsel->ids++] = id;
+}
+
+static int perf_evlist__id_add_fd(struct perf_evlist *evlist,
+				  struct perf_evsel *evsel,
+				  int cpu, int thread, int fd)
+{
+	u64 read_data[4] = { 0, };
+	int id_idx = 1; /* The first entry is the counter value */
+
+	if (!(evsel->attr.read_format & PERF_FORMAT_ID) ||
+	    read(fd, &read_data, sizeof(read_data)) == -1)
+		return -1;
+
+	if (evsel->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+		++id_idx;
+	if (evsel->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+		++id_idx;
+
+	perf_evlist__id_add(evlist, evsel, cpu, thread, read_data[id_idx]);
+	return 0;
+}
+
+struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id)
+{
+	struct hlist_head *head;
+	struct hlist_node *pos;
+	struct perf_sample_id *sid;
+	int hash;
+
+	if (evlist->nr_entries == 1)
+		return list_entry(evlist->entries.next, struct perf_evsel, node);
+
+	hash = hash_64(id, PERF_EVLIST__HLIST_BITS);
+	head = &evlist->heads[hash];
+
+	hlist_for_each_entry(sid, pos, head, node)
+		if (sid->id == id)
+			return sid->evsel;
+	return NULL;
+}
+
+union perf_event *perf_evlist__read_on_cpu(struct perf_evlist *evlist, int cpu)
+{
+	/* XXX Move this to perf.c, making it generally available */
+	unsigned int page_size = sysconf(_SC_PAGE_SIZE);
+	struct perf_mmap *md = &evlist->mmap[cpu];
+	unsigned int head = perf_mmap__read_head(md);
+	unsigned int old = md->prev;
+	unsigned char *data = md->base + page_size;
+	union perf_event *event = NULL;
+
+	if (evlist->overwrite) {
+		/*
+		 * If we're further behind than half the buffer, there's a chance
+		 * the writer will bite our tail and mess up the samples under us.
+		 *
+		 * If we somehow ended up ahead of the head, we got messed up.
+		 *
+		 * In either case, truncate and restart at head.
+		 */
+		int diff = head - old;
+		if (diff > md->mask / 2 || diff < 0) {
+			fprintf(stderr, "WARNING: failed to keep up with mmap data.\n");
+
+			/*
+			 * head points to a known good entry, start there.
+			 */
+			old = head;
+		}
+	}
+
+	if (old != head) {
+		size_t size;
+
+		event = (union perf_event *)&data[old & md->mask];
+		size = event->header.size;
+
+		/*
+		 * Event straddles the mmap boundary -- header should always
+		 * be inside due to u64 alignment of output.
+		 */
+		if ((old & md->mask) + size != ((old + size) & md->mask)) {
+			unsigned int offset = old;
+			unsigned int len = min(sizeof(*event), size), cpy;
+			void *dst = &evlist->event_copy;
+
+			do {
+				cpy = min(md->mask + 1 - (offset & md->mask), len);
+				memcpy(dst, &data[offset & md->mask], cpy);
+				offset += cpy;
+				dst += cpy;
+				len -= cpy;
+			} while (len);
+
+			event = &evlist->event_copy;
+		}
+
+		old += size;
+	}
+
+	md->prev = old;
+
+	if (!evlist->overwrite)
+		perf_mmap__write_tail(md, old);
+
+	return event;
+}
+
+void perf_evlist__munmap(struct perf_evlist *evlist)
+{
+	int cpu;
+
+	for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
+		if (evlist->mmap[cpu].base != NULL) {
+			munmap(evlist->mmap[cpu].base, evlist->mmap_len);
+			evlist->mmap[cpu].base = NULL;
+		}
+	}
+}
+
+int perf_evlist__alloc_mmap(struct perf_evlist *evlist)
+{
+	evlist->mmap = zalloc(evlist->cpus->nr * sizeof(struct perf_mmap));
+	return evlist->mmap != NULL ? 0 : -ENOMEM;
+}
+
+static int __perf_evlist__mmap(struct perf_evlist *evlist, int cpu, int prot,
+			       int mask, int fd)
+{
+	evlist->mmap[cpu].prev = 0;
+	evlist->mmap[cpu].mask = mask;
+	evlist->mmap[cpu].base = mmap(NULL, evlist->mmap_len, prot,
+				      MAP_SHARED, fd, 0);
+	if (evlist->mmap[cpu].base == MAP_FAILED)
+		return -1;
+
+	perf_evlist__add_pollfd(evlist, fd);
+	return 0;
+}
+
+/** perf_evlist__mmap - Create per cpu maps to receive events
+ *
+ * @evlist - list of events
+ * @pages - map length in pages
+ * @overwrite - overwrite older events?
+ *
+ * If overwrite is false the user needs to signal event consuption using:
+ *
+ *	struct perf_mmap *m = &evlist->mmap[cpu];
+ *	unsigned int head = perf_mmap__read_head(m);
+ *
+ *	perf_mmap__write_tail(m, head)
+ *
+ * Using perf_evlist__read_on_cpu does this automatically.
+ */
+int perf_evlist__mmap(struct perf_evlist *evlist, int pages, bool overwrite)
+{
+	unsigned int page_size = sysconf(_SC_PAGE_SIZE);
+	int mask = pages * page_size - 1, cpu;
+	struct perf_evsel *first_evsel, *evsel;
+	const struct cpu_map *cpus = evlist->cpus;
+	const struct thread_map *threads = evlist->threads;
+	int thread, prot = PROT_READ | (overwrite ? 0 : PROT_WRITE);
+
+	if (evlist->mmap == NULL && perf_evlist__alloc_mmap(evlist) < 0)
+		return -ENOMEM;
+
+	if (evlist->pollfd == NULL && perf_evlist__alloc_pollfd(evlist) < 0)
+		return -ENOMEM;
+
+	evlist->overwrite = overwrite;
+	evlist->mmap_len = (pages + 1) * page_size;
+	first_evsel = list_entry(evlist->entries.next, struct perf_evsel, node);
+
+	list_for_each_entry(evsel, &evlist->entries, node) {
+		if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
+		    evsel->sample_id == NULL &&
+		    perf_evsel__alloc_id(evsel, cpus->nr, threads->nr) < 0)
+			return -ENOMEM;
+
+		for (cpu = 0; cpu < cpus->nr; cpu++) {
+			for (thread = 0; thread < threads->nr; thread++) {
+				int fd = FD(evsel, cpu, thread);
+
+				if (evsel->idx || thread) {
+					if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT,
+						  FD(first_evsel, cpu, 0)) != 0)
+						goto out_unmap;
+				} else if (__perf_evlist__mmap(evlist, cpu, prot, mask, fd) < 0)
+					goto out_unmap;
+
+				if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
+				    perf_evlist__id_add_fd(evlist, evsel, cpu, thread, fd) < 0)
+					goto out_unmap;
+			}
+		}
+	}
+
+	return 0;
+
+out_unmap:
+	for (cpu = 0; cpu < cpus->nr; cpu++) {
+		if (evlist->mmap[cpu].base != NULL) {
+			munmap(evlist->mmap[cpu].base, evlist->mmap_len);
+			evlist->mmap[cpu].base = NULL;
+		}
+	}
+	return -1;
+}
+
+int perf_evlist__create_maps(struct perf_evlist *evlist, pid_t target_pid,
+			     pid_t target_tid, const char *cpu_list)
+{
+	evlist->threads = thread_map__new(target_pid, target_tid);
+
+	if (evlist->threads == NULL)
+		return -1;
+
+	if (target_tid != -1)
+		evlist->cpus = cpu_map__dummy_new();
+	else
+		evlist->cpus = cpu_map__new(cpu_list);
+
+	if (evlist->cpus == NULL)
+		goto out_delete_threads;
+
+	return 0;
+
+out_delete_threads:
+	thread_map__delete(evlist->threads);
+	return -1;
+}
+
+void perf_evlist__delete_maps(struct perf_evlist *evlist)
+{
+	cpu_map__delete(evlist->cpus);
+	thread_map__delete(evlist->threads);
+	evlist->cpus	= NULL;
+	evlist->threads = NULL;
+}
+
+int perf_evlist__set_filters(struct perf_evlist *evlist)
+{
+	const struct thread_map *threads = evlist->threads;
+	const struct cpu_map *cpus = evlist->cpus;
+	struct perf_evsel *evsel;
+	char *filter;
+	int thread;
+	int cpu;
+	int err;
+	int fd;
+
+	list_for_each_entry(evsel, &evlist->entries, node) {
+		filter = evsel->filter;
+		if (!filter)
+			continue;
+		for (cpu = 0; cpu < cpus->nr; cpu++) {
+			for (thread = 0; thread < threads->nr; thread++) {
+				fd = FD(evsel, cpu, thread);
+				err = ioctl(fd, PERF_EVENT_IOC_SET_FILTER, filter);
+				if (err)
+					return err;
+			}
+		}
+	}
+
+	return 0;
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
new file mode 100644
index 000000000000..8b1cb7a4c5f1
--- /dev/null
+++ b/tools/perf/util/evlist.h
@@ -0,0 +1,68 @@
+#ifndef __PERF_EVLIST_H
+#define __PERF_EVLIST_H 1
+
+#include <linux/list.h>
+#include "../perf.h"
+#include "event.h"
+
+struct pollfd;
+struct thread_map;
+struct cpu_map;
+
+#define PERF_EVLIST__HLIST_BITS 8
+#define PERF_EVLIST__HLIST_SIZE (1 << PERF_EVLIST__HLIST_BITS)
+
+struct perf_evlist {
+	struct list_head entries;
+	struct hlist_head heads[PERF_EVLIST__HLIST_SIZE];
+	int		 nr_entries;
+	int		 nr_fds;
+	int		 mmap_len;
+	bool		 overwrite;
+	union perf_event event_copy;
+	struct perf_mmap *mmap;
+	struct pollfd	 *pollfd;
+	struct thread_map *threads;
+	struct cpu_map	  *cpus;
+};
+
+struct perf_evsel;
+
+struct perf_evlist *perf_evlist__new(struct cpu_map *cpus,
+				     struct thread_map *threads);
+void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus,
+		       struct thread_map *threads);
+void perf_evlist__exit(struct perf_evlist *evlist);
+void perf_evlist__delete(struct perf_evlist *evlist);
+
+void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry);
+int perf_evlist__add_default(struct perf_evlist *evlist);
+
+void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel,
+			 int cpu, int thread, u64 id);
+
+int perf_evlist__alloc_pollfd(struct perf_evlist *evlist);
+void perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd);
+
+struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id);
+
+union perf_event *perf_evlist__read_on_cpu(struct perf_evlist *self, int cpu);
+
+int perf_evlist__alloc_mmap(struct perf_evlist *evlist);
+int perf_evlist__mmap(struct perf_evlist *evlist, int pages, bool overwrite);
+void perf_evlist__munmap(struct perf_evlist *evlist);
+
+static inline void perf_evlist__set_maps(struct perf_evlist *evlist,
+					 struct cpu_map *cpus,
+					 struct thread_map *threads)
+{
+	evlist->cpus	= cpus;
+	evlist->threads	= threads;
+}
+
+int perf_evlist__create_maps(struct perf_evlist *evlist, pid_t target_pid,
+			     pid_t target_tid, const char *cpu_list);
+void perf_evlist__delete_maps(struct perf_evlist *evlist);
+int perf_evlist__set_filters(struct perf_evlist *evlist);
+
+#endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index d8575d31ee6c..662596afd7f1 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1,20 +1,34 @@
+/*
+ * Copyright (C) 2011, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Parts came from builtin-{top,stat,record}.c, see those files for further
+ * copyright notes.
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+
 #include "evsel.h"
-#include "../perf.h"
+#include "evlist.h"
 #include "util.h"
 #include "cpumap.h"
-#include "thread.h"
+#include "thread_map.h"
 
 #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
 
+void perf_evsel__init(struct perf_evsel *evsel,
+		      struct perf_event_attr *attr, int idx)
+{
+	evsel->idx	   = idx;
+	evsel->attr	   = *attr;
+	INIT_LIST_HEAD(&evsel->node);
+}
+
 struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx)
 {
 	struct perf_evsel *evsel = zalloc(sizeof(*evsel));
 
-	if (evsel != NULL) {
-		evsel->idx	   = idx;
-		evsel->attr	   = *attr;
-		INIT_LIST_HEAD(&evsel->node);
-	}
+	if (evsel != NULL)
+		perf_evsel__init(evsel, attr, idx);
 
 	return evsel;
 }
@@ -25,6 +39,22 @@ int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
 	return evsel->fd != NULL ? 0 : -ENOMEM;
 }
 
+int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads)
+{
+	evsel->sample_id = xyarray__new(ncpus, nthreads, sizeof(struct perf_sample_id));
+	if (evsel->sample_id == NULL)
+		return -ENOMEM;
+
+	evsel->id = zalloc(ncpus * nthreads * sizeof(u64));
+	if (evsel->id == NULL) {
+		xyarray__delete(evsel->sample_id);
+		evsel->sample_id = NULL;
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
 int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus)
 {
 	evsel->counts = zalloc((sizeof(*evsel->counts) +
@@ -38,6 +68,14 @@ void perf_evsel__free_fd(struct perf_evsel *evsel)
 	evsel->fd = NULL;
 }
 
+void perf_evsel__free_id(struct perf_evsel *evsel)
+{
+	xyarray__delete(evsel->sample_id);
+	evsel->sample_id = NULL;
+	free(evsel->id);
+	evsel->id = NULL;
+}
+
 void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
 {
 	int cpu, thread;
@@ -49,10 +87,19 @@ void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
 		}
 }
 
-void perf_evsel__delete(struct perf_evsel *evsel)
+void perf_evsel__exit(struct perf_evsel *evsel)
 {
 	assert(list_empty(&evsel->node));
 	xyarray__delete(evsel->fd);
+	xyarray__delete(evsel->sample_id);
+	free(evsel->id);
+}
+
+void perf_evsel__delete(struct perf_evsel *evsel)
+{
+	perf_evsel__exit(evsel);
+	close_cgroup(evsel->cgrp);
+	free(evsel->name);
 	free(evsel);
 }
 
@@ -128,21 +175,51 @@ int __perf_evsel__read(struct perf_evsel *evsel,
 }
 
 static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
-			      struct thread_map *threads)
+			      struct thread_map *threads, bool group, bool inherit)
 {
 	int cpu, thread;
+	unsigned long flags = 0;
+	int pid = -1;
 
 	if (evsel->fd == NULL &&
 	    perf_evsel__alloc_fd(evsel, cpus->nr, threads->nr) < 0)
 		return -1;
 
+	if (evsel->cgrp) {
+		flags = PERF_FLAG_PID_CGROUP;
+		pid = evsel->cgrp->fd;
+	}
+
 	for (cpu = 0; cpu < cpus->nr; cpu++) {
+		int group_fd = -1;
+		/*
+		 * Don't allow mmap() of inherited per-task counters. This
+		 * would create a performance issue due to all children writing
+		 * to the same buffer.
+		 *
+		 * FIXME:
+		 * Proper fix is not to pass 'inherit' to perf_evsel__open*,
+		 * but a 'flags' parameter, with 'group' folded there as well,
+		 * then introduce a PERF_O_{MMAP,GROUP,INHERIT} enum, and if
+		 * O_MMAP is set, emit a warning if cpu < 0 and O_INHERIT is
+		 * set. Lets go for the minimal fix first tho.
+		 */
+		evsel->attr.inherit = (cpus->map[cpu] >= 0) && inherit;
+
 		for (thread = 0; thread < threads->nr; thread++) {
+
+			if (!evsel->cgrp)
+				pid = threads->map[thread];
+
 			FD(evsel, cpu, thread) = sys_perf_event_open(&evsel->attr,
-								     threads->map[thread],
-								     cpus->map[cpu], -1, 0);
+								     pid,
+								     cpus->map[cpu],
+								     group_fd, flags);
 			if (FD(evsel, cpu, thread) < 0)
 				goto out_close;
+
+			if (group && group_fd == -1)
+				group_fd = FD(evsel, cpu, thread);
 		}
 	}
 
@@ -175,10 +252,9 @@ static struct {
 	.threads = { -1, },
 };
 
-int perf_evsel__open(struct perf_evsel *evsel,
-		     struct cpu_map *cpus, struct thread_map *threads)
+int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
+		     struct thread_map *threads, bool group, bool inherit)
 {
-
 	if (cpus == NULL) {
 		/* Work around old compiler warnings about strict aliasing */
 		cpus = &empty_cpu_map.map;
@@ -187,15 +263,135 @@ int perf_evsel__open(struct perf_evsel *evsel,
 	if (threads == NULL)
 		threads = &empty_thread_map.map;
 
-	return __perf_evsel__open(evsel, cpus, threads);
+	return __perf_evsel__open(evsel, cpus, threads, group, inherit);
 }
 
-int perf_evsel__open_per_cpu(struct perf_evsel *evsel, struct cpu_map *cpus)
+int perf_evsel__open_per_cpu(struct perf_evsel *evsel,
+			     struct cpu_map *cpus, bool group, bool inherit)
 {
-	return __perf_evsel__open(evsel, cpus, &empty_thread_map.map);
+	return __perf_evsel__open(evsel, cpus, &empty_thread_map.map, group, inherit);
+}
+
+int perf_evsel__open_per_thread(struct perf_evsel *evsel,
+				struct thread_map *threads, bool group, bool inherit)
+{
+	return __perf_evsel__open(evsel, &empty_cpu_map.map, threads, group, inherit);
+}
+
+static int perf_event__parse_id_sample(const union perf_event *event, u64 type,
+				       struct perf_sample *sample)
+{
+	const u64 *array = event->sample.array;
+
+	array += ((event->header.size -
+		   sizeof(event->header)) / sizeof(u64)) - 1;
+
+	if (type & PERF_SAMPLE_CPU) {
+		u32 *p = (u32 *)array;
+		sample->cpu = *p;
+		array--;
+	}
+
+	if (type & PERF_SAMPLE_STREAM_ID) {
+		sample->stream_id = *array;
+		array--;
+	}
+
+	if (type & PERF_SAMPLE_ID) {
+		sample->id = *array;
+		array--;
+	}
+
+	if (type & PERF_SAMPLE_TIME) {
+		sample->time = *array;
+		array--;
+	}
+
+	if (type & PERF_SAMPLE_TID) {
+		u32 *p = (u32 *)array;
+		sample->pid = p[0];
+		sample->tid = p[1];
+	}
+
+	return 0;
 }
 
-int perf_evsel__open_per_thread(struct perf_evsel *evsel, struct thread_map *threads)
+int perf_event__parse_sample(const union perf_event *event, u64 type,
+			     bool sample_id_all, struct perf_sample *data)
 {
-	return __perf_evsel__open(evsel, &empty_cpu_map.map, threads);
+	const u64 *array;
+
+	data->cpu = data->pid = data->tid = -1;
+	data->stream_id = data->id = data->time = -1ULL;
+
+	if (event->header.type != PERF_RECORD_SAMPLE) {
+		if (!sample_id_all)
+			return 0;
+		return perf_event__parse_id_sample(event, type, data);
+	}
+
+	array = event->sample.array;
+
+	if (type & PERF_SAMPLE_IP) {
+		data->ip = event->ip.ip;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_TID) {
+		u32 *p = (u32 *)array;
+		data->pid = p[0];
+		data->tid = p[1];
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_TIME) {
+		data->time = *array;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_ADDR) {
+		data->addr = *array;
+		array++;
+	}
+
+	data->id = -1ULL;
+	if (type & PERF_SAMPLE_ID) {
+		data->id = *array;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_STREAM_ID) {
+		data->stream_id = *array;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_CPU) {
+		u32 *p = (u32 *)array;
+		data->cpu = *p;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_PERIOD) {
+		data->period = *array;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_READ) {
+		fprintf(stderr, "PERF_SAMPLE_READ is unsuported for now\n");
+		return -1;
+	}
+
+	if (type & PERF_SAMPLE_CALLCHAIN) {
+		data->callchain = (struct ip_callchain *)array;
+		array += 1 + data->callchain->nr;
+	}
+
+	if (type & PERF_SAMPLE_RAW) {
+		u32 *p = (u32 *)array;
+		data->raw_size = *p;
+		p++;
+		data->raw_data = p;
+	}
+
+	return 0;
 }
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index b2d755fe88a5..6710ab538342 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -6,6 +6,8 @@
 #include "../../../include/linux/perf_event.h"
 #include "types.h"
 #include "xyarray.h"
+#include "cgroup.h"
+#include "hist.h"
  
 struct perf_counts_values {
 	union {
@@ -24,31 +26,66 @@ struct perf_counts {
 	struct perf_counts_values cpu[];
 };
 
+struct perf_evsel;
+
+/*
+ * Per fd, to map back from PERF_SAMPLE_ID to evsel, only used when there are
+ * more than one entry in the evlist.
+ */
+struct perf_sample_id {
+	struct hlist_node 	node;
+	u64		 	id;
+	struct perf_evsel	*evsel;
+};
+
+/** struct perf_evsel - event selector
+ *
+ * @name - Can be set to retain the original event name passed by the user,
+ *         so that when showing results in tools such as 'perf stat', we
+ *         show the name used, not some alias.
+ */
 struct perf_evsel {
 	struct list_head	node;
 	struct perf_event_attr	attr;
 	char			*filter;
 	struct xyarray		*fd;
+	struct xyarray		*sample_id;
+	u64			*id;
 	struct perf_counts	*counts;
 	int			idx;
-	void			*priv;
+	int			ids;
+	struct hists		hists;
+	char			*name;
+	union {
+		void		*priv;
+		off_t		id_offset;
+	};
+	struct cgroup_sel	*cgrp;
 };
 
 struct cpu_map;
 struct thread_map;
+struct perf_evlist;
 
 struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx);
+void perf_evsel__init(struct perf_evsel *evsel,
+		      struct perf_event_attr *attr, int idx);
+void perf_evsel__exit(struct perf_evsel *evsel);
 void perf_evsel__delete(struct perf_evsel *evsel);
 
 int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
+int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads);
 int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus);
 void perf_evsel__free_fd(struct perf_evsel *evsel);
+void perf_evsel__free_id(struct perf_evsel *evsel);
 void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
 
-int perf_evsel__open_per_cpu(struct perf_evsel *evsel, struct cpu_map *cpus);
-int perf_evsel__open_per_thread(struct perf_evsel *evsel, struct thread_map *threads);
-int perf_evsel__open(struct perf_evsel *evsel, 
-		     struct cpu_map *cpus, struct thread_map *threads);
+int perf_evsel__open_per_cpu(struct perf_evsel *evsel,
+			     struct cpu_map *cpus, bool group, bool inherit);
+int perf_evsel__open_per_thread(struct perf_evsel *evsel,
+				struct thread_map *threads, bool group, bool inherit);
+int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
+		     struct thread_map *threads, bool group, bool inherit);
 
 #define perf_evsel__match(evsel, t, c)		\
 	(evsel->attr.type == PERF_TYPE_##t &&	\
diff --git a/tools/perf/util/exec_cmd.c b/tools/perf/util/exec_cmd.c
index 67eeff571568..7adf4ad15d8f 100644
--- a/tools/perf/util/exec_cmd.c
+++ b/tools/perf/util/exec_cmd.c
@@ -11,31 +11,12 @@ static const char *argv0_path;
 
 const char *system_path(const char *path)
 {
-#ifdef RUNTIME_PREFIX
-	static const char *prefix;
-#else
 	static const char *prefix = PREFIX;
-#endif
 	struct strbuf d = STRBUF_INIT;
 
 	if (is_absolute_path(path))
 		return path;
 
-#ifdef RUNTIME_PREFIX
-	assert(argv0_path);
-	assert(is_absolute_path(argv0_path));
-
-	if (!prefix &&
-	    !(prefix = strip_path_suffix(argv0_path, PERF_EXEC_PATH)) &&
-	    !(prefix = strip_path_suffix(argv0_path, BINDIR)) &&
-	    !(prefix = strip_path_suffix(argv0_path, "perf"))) {
-		prefix = PREFIX;
-		fprintf(stderr, "RUNTIME_PREFIX requested, "
-				"but prefix computation failed.  "
-				"Using static fallback '%s'.\n", prefix);
-	}
-#endif
-
 	strbuf_addf(&d, "%s/%s", prefix, path);
 	path = strbuf_detach(&d, NULL);
 	return path;
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 0866bcdb5e8e..e5230c0ef95b 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -8,6 +8,8 @@
 #include <linux/list.h>
 #include <linux/kernel.h>
 
+#include "evlist.h"
+#include "evsel.h"
 #include "util.h"
 #include "header.h"
 #include "../perf.h"
@@ -18,89 +20,6 @@
 
 static bool no_buildid_cache = false;
 
-/*
- * Create new perf.data header attribute:
- */
-struct perf_header_attr *perf_header_attr__new(struct perf_event_attr *attr)
-{
-	struct perf_header_attr *self = malloc(sizeof(*self));
-
-	if (self != NULL) {
-		self->attr = *attr;
-		self->ids  = 0;
-		self->size = 1;
-		self->id   = malloc(sizeof(u64));
-		if (self->id == NULL) {
-			free(self);
-			self = NULL;
-		}
-	}
-
-	return self;
-}
-
-void perf_header_attr__delete(struct perf_header_attr *self)
-{
-	free(self->id);
-	free(self);
-}
-
-int perf_header_attr__add_id(struct perf_header_attr *self, u64 id)
-{
-	int pos = self->ids;
-
-	self->ids++;
-	if (self->ids > self->size) {
-		int nsize = self->size * 2;
-		u64 *nid = realloc(self->id, nsize * sizeof(u64));
-
-		if (nid == NULL)
-			return -1;
-
-		self->size = nsize;
-		self->id = nid;
-	}
-	self->id[pos] = id;
-	return 0;
-}
-
-int perf_header__init(struct perf_header *self)
-{
-	self->size = 1;
-	self->attr = malloc(sizeof(void *));
-	return self->attr == NULL ? -ENOMEM : 0;
-}
-
-void perf_header__exit(struct perf_header *self)
-{
-	int i;
-	for (i = 0; i < self->attrs; ++i)
-                perf_header_attr__delete(self->attr[i]);
-	free(self->attr);
-}
-
-int perf_header__add_attr(struct perf_header *self,
-			  struct perf_header_attr *attr)
-{
-	if (self->frozen)
-		return -1;
-
-	if (self->attrs == self->size) {
-		int nsize = self->size * 2;
-		struct perf_header_attr **nattr;
-
-		nattr = realloc(self->attr, nsize * sizeof(void *));
-		if (nattr == NULL)
-			return -1;
-
-		self->size = nsize;
-		self->attr = nattr;
-	}
-
-	self->attr[self->attrs++] = attr;
-	return 0;
-}
-
 static int event_count;
 static struct perf_trace_event_type *events;
 
@@ -147,19 +66,19 @@ struct perf_file_attr {
 	struct perf_file_section	ids;
 };
 
-void perf_header__set_feat(struct perf_header *self, int feat)
+void perf_header__set_feat(struct perf_header *header, int feat)
 {
-	set_bit(feat, self->adds_features);
+	set_bit(feat, header->adds_features);
 }
 
-void perf_header__clear_feat(struct perf_header *self, int feat)
+void perf_header__clear_feat(struct perf_header *header, int feat)
 {
-	clear_bit(feat, self->adds_features);
+	clear_bit(feat, header->adds_features);
 }
 
-bool perf_header__has_feat(const struct perf_header *self, int feat)
+bool perf_header__has_feat(const struct perf_header *header, int feat)
 {
-	return test_bit(feat, self->adds_features);
+	return test_bit(feat, header->adds_features);
 }
 
 static int do_write(int fd, const void *buf, size_t size)
@@ -228,22 +147,22 @@ static int __dsos__write_buildid_table(struct list_head *head, pid_t pid,
 	return 0;
 }
 
-static int machine__write_buildid_table(struct machine *self, int fd)
+static int machine__write_buildid_table(struct machine *machine, int fd)
 {
 	int err;
 	u16 kmisc = PERF_RECORD_MISC_KERNEL,
 	    umisc = PERF_RECORD_MISC_USER;
 
-	if (!machine__is_host(self)) {
+	if (!machine__is_host(machine)) {
 		kmisc = PERF_RECORD_MISC_GUEST_KERNEL;
 		umisc = PERF_RECORD_MISC_GUEST_USER;
 	}
 
-	err = __dsos__write_buildid_table(&self->kernel_dsos, self->pid,
+	err = __dsos__write_buildid_table(&machine->kernel_dsos, machine->pid,
 					  kmisc, fd);
 	if (err == 0)
-		err = __dsos__write_buildid_table(&self->user_dsos,
-						  self->pid, umisc, fd);
+		err = __dsos__write_buildid_table(&machine->user_dsos,
+						  machine->pid, umisc, fd);
 	return err;
 }
 
@@ -366,12 +285,12 @@ out_free:
 	return err;
 }
 
-static int dso__cache_build_id(struct dso *self, const char *debugdir)
+static int dso__cache_build_id(struct dso *dso, const char *debugdir)
 {
-	bool is_kallsyms = self->kernel && self->long_name[0] != '/';
+	bool is_kallsyms = dso->kernel && dso->long_name[0] != '/';
 
-	return build_id_cache__add_b(self->build_id, sizeof(self->build_id),
-				     self->long_name, debugdir, is_kallsyms);
+	return build_id_cache__add_b(dso->build_id, sizeof(dso->build_id),
+				     dso->long_name, debugdir, is_kallsyms);
 }
 
 static int __dsos__cache_build_ids(struct list_head *head, const char *debugdir)
@@ -386,14 +305,14 @@ static int __dsos__cache_build_ids(struct list_head *head, const char *debugdir)
 	return err;
 }
 
-static int machine__cache_build_ids(struct machine *self, const char *debugdir)
+static int machine__cache_build_ids(struct machine *machine, const char *debugdir)
 {
-	int ret = __dsos__cache_build_ids(&self->kernel_dsos, debugdir);
-	ret |= __dsos__cache_build_ids(&self->user_dsos, debugdir);
+	int ret = __dsos__cache_build_ids(&machine->kernel_dsos, debugdir);
+	ret |= __dsos__cache_build_ids(&machine->user_dsos, debugdir);
 	return ret;
 }
 
-static int perf_session__cache_build_ids(struct perf_session *self)
+static int perf_session__cache_build_ids(struct perf_session *session)
 {
 	struct rb_node *nd;
 	int ret;
@@ -404,28 +323,28 @@ static int perf_session__cache_build_ids(struct perf_session *self)
 	if (mkdir(debugdir, 0755) != 0 && errno != EEXIST)
 		return -1;
 
-	ret = machine__cache_build_ids(&self->host_machine, debugdir);
+	ret = machine__cache_build_ids(&session->host_machine, debugdir);
 
-	for (nd = rb_first(&self->machines); nd; nd = rb_next(nd)) {
+	for (nd = rb_first(&session->machines); nd; nd = rb_next(nd)) {
 		struct machine *pos = rb_entry(nd, struct machine, rb_node);
 		ret |= machine__cache_build_ids(pos, debugdir);
 	}
 	return ret ? -1 : 0;
 }
 
-static bool machine__read_build_ids(struct machine *self, bool with_hits)
+static bool machine__read_build_ids(struct machine *machine, bool with_hits)
 {
-	bool ret = __dsos__read_build_ids(&self->kernel_dsos, with_hits);
-	ret |= __dsos__read_build_ids(&self->user_dsos, with_hits);
+	bool ret = __dsos__read_build_ids(&machine->kernel_dsos, with_hits);
+	ret |= __dsos__read_build_ids(&machine->user_dsos, with_hits);
 	return ret;
 }
 
-static bool perf_session__read_build_ids(struct perf_session *self, bool with_hits)
+static bool perf_session__read_build_ids(struct perf_session *session, bool with_hits)
 {
 	struct rb_node *nd;
-	bool ret = machine__read_build_ids(&self->host_machine, with_hits);
+	bool ret = machine__read_build_ids(&session->host_machine, with_hits);
 
-	for (nd = rb_first(&self->machines); nd; nd = rb_next(nd)) {
+	for (nd = rb_first(&session->machines); nd; nd = rb_next(nd)) {
 		struct machine *pos = rb_entry(nd, struct machine, rb_node);
 		ret |= machine__read_build_ids(pos, with_hits);
 	}
@@ -433,7 +352,8 @@ static bool perf_session__read_build_ids(struct perf_session *self, bool with_hi
 	return ret;
 }
 
-static int perf_header__adds_write(struct perf_header *self, int fd)
+static int perf_header__adds_write(struct perf_header *header,
+				   struct perf_evlist *evlist, int fd)
 {
 	int nr_sections;
 	struct perf_session *session;
@@ -442,13 +362,13 @@ static int perf_header__adds_write(struct perf_header *self, int fd)
 	u64 sec_start;
 	int idx = 0, err;
 
-	session = container_of(self, struct perf_session, header);
+	session = container_of(header, struct perf_session, header);
 
-	if (perf_header__has_feat(self, HEADER_BUILD_ID &&
+	if (perf_header__has_feat(header, HEADER_BUILD_ID &&
 	    !perf_session__read_build_ids(session, true)))
-		perf_header__clear_feat(self, HEADER_BUILD_ID);
+		perf_header__clear_feat(header, HEADER_BUILD_ID);
 
-	nr_sections = bitmap_weight(self->adds_features, HEADER_FEAT_BITS);
+	nr_sections = bitmap_weight(header->adds_features, HEADER_FEAT_BITS);
 	if (!nr_sections)
 		return 0;
 
@@ -458,28 +378,28 @@ static int perf_header__adds_write(struct perf_header *self, int fd)
 
 	sec_size = sizeof(*feat_sec) * nr_sections;
 
-	sec_start = self->data_offset + self->data_size;
+	sec_start = header->data_offset + header->data_size;
 	lseek(fd, sec_start + sec_size, SEEK_SET);
 
-	if (perf_header__has_feat(self, HEADER_TRACE_INFO)) {
+	if (perf_header__has_feat(header, HEADER_TRACE_INFO)) {
 		struct perf_file_section *trace_sec;
 
 		trace_sec = &feat_sec[idx++];
 
 		/* Write trace info */
 		trace_sec->offset = lseek(fd, 0, SEEK_CUR);
-		read_tracing_data(fd, &evsel_list);
+		read_tracing_data(fd, &evlist->entries);
 		trace_sec->size = lseek(fd, 0, SEEK_CUR) - trace_sec->offset;
 	}
 
-	if (perf_header__has_feat(self, HEADER_BUILD_ID)) {
+	if (perf_header__has_feat(header, HEADER_BUILD_ID)) {
 		struct perf_file_section *buildid_sec;
 
 		buildid_sec = &feat_sec[idx++];
 
 		/* Write build-ids */
 		buildid_sec->offset = lseek(fd, 0, SEEK_CUR);
-		err = dsos__write_buildid_table(self, fd);
+		err = dsos__write_buildid_table(header, fd);
 		if (err < 0) {
 			pr_debug("failed to write buildid table\n");
 			goto out_free;
@@ -518,32 +438,41 @@ int perf_header__write_pipe(int fd)
 	return 0;
 }
 
-int perf_header__write(struct perf_header *self, int fd, bool at_exit)
+int perf_session__write_header(struct perf_session *session,
+			       struct perf_evlist *evlist,
+			       int fd, bool at_exit)
 {
 	struct perf_file_header f_header;
 	struct perf_file_attr   f_attr;
-	struct perf_header_attr	*attr;
-	int i, err;
+	struct perf_header *header = &session->header;
+	struct perf_evsel *attr, *pair = NULL;
+	int err;
 
 	lseek(fd, sizeof(f_header), SEEK_SET);
 
-	for (i = 0; i < self->attrs; i++) {
-		attr = self->attr[i];
+	if (session->evlist != evlist)
+		pair = list_entry(session->evlist->entries.next, struct perf_evsel, node);
 
+	list_for_each_entry(attr, &evlist->entries, node) {
 		attr->id_offset = lseek(fd, 0, SEEK_CUR);
 		err = do_write(fd, attr->id, attr->ids * sizeof(u64));
 		if (err < 0) {
+out_err_write:
 			pr_debug("failed to write perf header\n");
 			return err;
 		}
+		if (session->evlist != evlist) {
+			err = do_write(fd, pair->id, pair->ids * sizeof(u64));
+			if (err < 0)
+				goto out_err_write;
+			attr->ids += pair->ids;
+			pair = list_entry(pair->node.next, struct perf_evsel, node);
+		}
 	}
 
+	header->attr_offset = lseek(fd, 0, SEEK_CUR);
 
-	self->attr_offset = lseek(fd, 0, SEEK_CUR);
-
-	for (i = 0; i < self->attrs; i++) {
-		attr = self->attr[i];
-
+	list_for_each_entry(attr, &evlist->entries, node) {
 		f_attr = (struct perf_file_attr){
 			.attr = attr->attr,
 			.ids  = {
@@ -558,20 +487,20 @@ int perf_header__write(struct perf_header *self, int fd, bool at_exit)
 		}
 	}
 
-	self->event_offset = lseek(fd, 0, SEEK_CUR);
-	self->event_size = event_count * sizeof(struct perf_trace_event_type);
+	header->event_offset = lseek(fd, 0, SEEK_CUR);
+	header->event_size = event_count * sizeof(struct perf_trace_event_type);
 	if (events) {
-		err = do_write(fd, events, self->event_size);
+		err = do_write(fd, events, header->event_size);
 		if (err < 0) {
 			pr_debug("failed to write perf header events\n");
 			return err;
 		}
 	}
 
-	self->data_offset = lseek(fd, 0, SEEK_CUR);
+	header->data_offset = lseek(fd, 0, SEEK_CUR);
 
 	if (at_exit) {
-		err = perf_header__adds_write(self, fd);
+		err = perf_header__adds_write(header, evlist, fd);
 		if (err < 0)
 			return err;
 	}
@@ -581,20 +510,20 @@ int perf_header__write(struct perf_header *self, int fd, bool at_exit)
 		.size	   = sizeof(f_header),
 		.attr_size = sizeof(f_attr),
 		.attrs = {
-			.offset = self->attr_offset,
-			.size   = self->attrs * sizeof(f_attr),
+			.offset = header->attr_offset,
+			.size   = evlist->nr_entries * sizeof(f_attr),
 		},
 		.data = {
-			.offset = self->data_offset,
-			.size	= self->data_size,
+			.offset = header->data_offset,
+			.size	= header->data_size,
 		},
 		.event_types = {
-			.offset = self->event_offset,
-			.size	= self->event_size,
+			.offset = header->event_offset,
+			.size	= header->event_size,
 		},
 	};
 
-	memcpy(&f_header.adds_features, &self->adds_features, sizeof(self->adds_features));
+	memcpy(&f_header.adds_features, &header->adds_features, sizeof(header->adds_features));
 
 	lseek(fd, 0, SEEK_SET);
 	err = do_write(fd, &f_header, sizeof(f_header));
@@ -602,26 +531,26 @@ int perf_header__write(struct perf_header *self, int fd, bool at_exit)
 		pr_debug("failed to write perf header\n");
 		return err;
 	}
-	lseek(fd, self->data_offset + self->data_size, SEEK_SET);
+	lseek(fd, header->data_offset + header->data_size, SEEK_SET);
 
-	self->frozen = 1;
+	header->frozen = 1;
 	return 0;
 }
 
-static int perf_header__getbuffer64(struct perf_header *self,
+static int perf_header__getbuffer64(struct perf_header *header,
 				    int fd, void *buf, size_t size)
 {
 	if (readn(fd, buf, size) <= 0)
 		return -1;
 
-	if (self->needs_swap)
+	if (header->needs_swap)
 		mem_bswap_64(buf, size);
 
 	return 0;
 }
 
-int perf_header__process_sections(struct perf_header *self, int fd,
-				  int (*process)(struct perf_file_section *self,
+int perf_header__process_sections(struct perf_header *header, int fd,
+				  int (*process)(struct perf_file_section *section,
 						 struct perf_header *ph,
 						 int feat, int fd))
 {
@@ -631,7 +560,7 @@ int perf_header__process_sections(struct perf_header *self, int fd,
 	int idx = 0;
 	int err = -1, feat = 1;
 
-	nr_sections = bitmap_weight(self->adds_features, HEADER_FEAT_BITS);
+	nr_sections = bitmap_weight(header->adds_features, HEADER_FEAT_BITS);
 	if (!nr_sections)
 		return 0;
 
@@ -641,17 +570,17 @@ int perf_header__process_sections(struct perf_header *self, int fd,
 
 	sec_size = sizeof(*feat_sec) * nr_sections;
 
-	lseek(fd, self->data_offset + self->data_size, SEEK_SET);
+	lseek(fd, header->data_offset + header->data_size, SEEK_SET);
 
-	if (perf_header__getbuffer64(self, fd, feat_sec, sec_size))
+	if (perf_header__getbuffer64(header, fd, feat_sec, sec_size))
 		goto out_free;
 
 	err = 0;
 	while (idx < nr_sections && feat < HEADER_LAST_FEATURE) {
-		if (perf_header__has_feat(self, feat)) {
+		if (perf_header__has_feat(header, feat)) {
 			struct perf_file_section *sec = &feat_sec[idx++];
 
-			err = process(sec, self, feat, fd);
+			err = process(sec, header, feat, fd);
 			if (err < 0)
 				break;
 		}
@@ -662,35 +591,35 @@ out_free:
 	return err;
 }
 
-int perf_file_header__read(struct perf_file_header *self,
+int perf_file_header__read(struct perf_file_header *header,
 			   struct perf_header *ph, int fd)
 {
 	lseek(fd, 0, SEEK_SET);
 
-	if (readn(fd, self, sizeof(*self)) <= 0 ||
-	    memcmp(&self->magic, __perf_magic, sizeof(self->magic)))
+	if (readn(fd, header, sizeof(*header)) <= 0 ||
+	    memcmp(&header->magic, __perf_magic, sizeof(header->magic)))
 		return -1;
 
-	if (self->attr_size != sizeof(struct perf_file_attr)) {
-		u64 attr_size = bswap_64(self->attr_size);
+	if (header->attr_size != sizeof(struct perf_file_attr)) {
+		u64 attr_size = bswap_64(header->attr_size);
 
 		if (attr_size != sizeof(struct perf_file_attr))
 			return -1;
 
-		mem_bswap_64(self, offsetof(struct perf_file_header,
+		mem_bswap_64(header, offsetof(struct perf_file_header,
 					    adds_features));
 		ph->needs_swap = true;
 	}
 
-	if (self->size != sizeof(*self)) {
+	if (header->size != sizeof(*header)) {
 		/* Support the previous format */
-		if (self->size == offsetof(typeof(*self), adds_features))
-			bitmap_zero(self->adds_features, HEADER_FEAT_BITS);
+		if (header->size == offsetof(typeof(*header), adds_features))
+			bitmap_zero(header->adds_features, HEADER_FEAT_BITS);
 		else
 			return -1;
 	}
 
-	memcpy(&ph->adds_features, &self->adds_features,
+	memcpy(&ph->adds_features, &header->adds_features,
 	       sizeof(ph->adds_features));
 	/*
 	 * FIXME: hack that assumes that if we need swap the perf.data file
@@ -704,10 +633,10 @@ int perf_file_header__read(struct perf_file_header *self,
 		perf_header__set_feat(ph, HEADER_BUILD_ID);
 	}
 
-	ph->event_offset = self->event_types.offset;
-	ph->event_size   = self->event_types.size;
-	ph->data_offset  = self->data.offset;
-	ph->data_size	 = self->data.size;
+	ph->event_offset = header->event_types.offset;
+	ph->event_size   = header->event_types.size;
+	ph->data_offset  = header->data.offset;
+	ph->data_size	 = header->data.size;
 	return 0;
 }
 
@@ -766,11 +695,10 @@ out:
 	return err;
 }
 
-static int perf_header__read_build_ids(struct perf_header *self,
-			int input, u64 offset, u64 size)
+static int perf_header__read_build_ids(struct perf_header *header,
+				       int input, u64 offset, u64 size)
 {
-	struct perf_session *session = container_of(self,
-			struct perf_session, header);
+	struct perf_session *session = container_of(header, struct perf_session, header);
 	struct build_id_event bev;
 	char filename[PATH_MAX];
 	u64 limit = offset + size;
@@ -782,7 +710,7 @@ static int perf_header__read_build_ids(struct perf_header *self,
 		if (read(input, &bev, sizeof(bev)) != sizeof(bev))
 			goto out;
 
-		if (self->needs_swap)
+		if (header->needs_swap)
 			perf_event_header__bswap(&bev.header);
 
 		len = bev.header.size - sizeof(bev);
@@ -798,13 +726,13 @@ out:
 	return err;
 }
 
-static int perf_file_section__process(struct perf_file_section *self,
+static int perf_file_section__process(struct perf_file_section *section,
 				      struct perf_header *ph,
 				      int feat, int fd)
 {
-	if (lseek(fd, self->offset, SEEK_SET) == (off_t)-1) {
+	if (lseek(fd, section->offset, SEEK_SET) == (off_t)-1) {
 		pr_debug("Failed to lseek to %" PRIu64 " offset for feature "
-			  "%d, continuing...\n", self->offset, feat);
+			  "%d, continuing...\n", section->offset, feat);
 		return 0;
 	}
 
@@ -814,7 +742,7 @@ static int perf_file_section__process(struct perf_file_section *self,
 		break;
 
 	case HEADER_BUILD_ID:
-		if (perf_header__read_build_ids(ph, fd, self->offset, self->size))
+		if (perf_header__read_build_ids(ph, fd, section->offset, section->size))
 			pr_debug("Failed to read buildids, continuing...\n");
 		break;
 	default:
@@ -824,21 +752,21 @@ static int perf_file_section__process(struct perf_file_section *self,
 	return 0;
 }
 
-static int perf_file_header__read_pipe(struct perf_pipe_file_header *self,
+static int perf_file_header__read_pipe(struct perf_pipe_file_header *header,
 				       struct perf_header *ph, int fd,
 				       bool repipe)
 {
-	if (readn(fd, self, sizeof(*self)) <= 0 ||
-	    memcmp(&self->magic, __perf_magic, sizeof(self->magic)))
+	if (readn(fd, header, sizeof(*header)) <= 0 ||
+	    memcmp(&header->magic, __perf_magic, sizeof(header->magic)))
 		return -1;
 
-	if (repipe && do_write(STDOUT_FILENO, self, sizeof(*self)) < 0)
+	if (repipe && do_write(STDOUT_FILENO, header, sizeof(*header)) < 0)
 		return -1;
 
-	if (self->size != sizeof(*self)) {
-		u64 size = bswap_64(self->size);
+	if (header->size != sizeof(*header)) {
+		u64 size = bswap_64(header->size);
 
-		if (size != sizeof(*self))
+		if (size != sizeof(*header))
 			return -1;
 
 		ph->needs_swap = true;
@@ -849,10 +777,10 @@ static int perf_file_header__read_pipe(struct perf_pipe_file_header *self,
 
 static int perf_header__read_pipe(struct perf_session *session, int fd)
 {
-	struct perf_header *self = &session->header;
+	struct perf_header *header = &session->header;
 	struct perf_pipe_file_header f_header;
 
-	if (perf_file_header__read_pipe(&f_header, self, fd,
+	if (perf_file_header__read_pipe(&f_header, header, fd,
 					session->repipe) < 0) {
 		pr_debug("incompatible file format\n");
 		return -EINVAL;
@@ -863,18 +791,22 @@ static int perf_header__read_pipe(struct perf_session *session, int fd)
 	return 0;
 }
 
-int perf_header__read(struct perf_session *session, int fd)
+int perf_session__read_header(struct perf_session *session, int fd)
 {
-	struct perf_header *self = &session->header;
+	struct perf_header *header = &session->header;
 	struct perf_file_header	f_header;
 	struct perf_file_attr	f_attr;
 	u64			f_id;
 	int nr_attrs, nr_ids, i, j;
 
+	session->evlist = perf_evlist__new(NULL, NULL);
+	if (session->evlist == NULL)
+		return -ENOMEM;
+
 	if (session->fd_pipe)
 		return perf_header__read_pipe(session, fd);
 
-	if (perf_file_header__read(&f_header, self, fd) < 0) {
+	if (perf_file_header__read(&f_header, header, fd) < 0) {
 		pr_debug("incompatible file format\n");
 		return -EINVAL;
 	}
@@ -883,33 +815,39 @@ int perf_header__read(struct perf_session *session, int fd)
 	lseek(fd, f_header.attrs.offset, SEEK_SET);
 
 	for (i = 0; i < nr_attrs; i++) {
-		struct perf_header_attr *attr;
+		struct perf_evsel *evsel;
 		off_t tmp;
 
-		if (perf_header__getbuffer64(self, fd, &f_attr, sizeof(f_attr)))
+		if (perf_header__getbuffer64(header, fd, &f_attr, sizeof(f_attr)))
 			goto out_errno;
 
 		tmp = lseek(fd, 0, SEEK_CUR);
+		evsel = perf_evsel__new(&f_attr.attr, i);
 
-		attr = perf_header_attr__new(&f_attr.attr);
-		if (attr == NULL)
-			 return -ENOMEM;
+		if (evsel == NULL)
+			goto out_delete_evlist;
+		/*
+		 * Do it before so that if perf_evsel__alloc_id fails, this
+		 * entry gets purged too at perf_evlist__delete().
+		 */
+		perf_evlist__add(session->evlist, evsel);
 
 		nr_ids = f_attr.ids.size / sizeof(u64);
+		/*
+		 * We don't have the cpu and thread maps on the header, so
+		 * for allocating the perf_sample_id table we fake 1 cpu and
+		 * hattr->ids threads.
+		 */
+		if (perf_evsel__alloc_id(evsel, 1, nr_ids))
+			goto out_delete_evlist;
+
 		lseek(fd, f_attr.ids.offset, SEEK_SET);
 
 		for (j = 0; j < nr_ids; j++) {
-			if (perf_header__getbuffer64(self, fd, &f_id, sizeof(f_id)))
+			if (perf_header__getbuffer64(header, fd, &f_id, sizeof(f_id)))
 				goto out_errno;
 
-			if (perf_header_attr__add_id(attr, f_id) < 0) {
-				perf_header_attr__delete(attr);
-				return -ENOMEM;
-			}
-		}
-		if (perf_header__add_attr(self, attr) < 0) {
-			perf_header_attr__delete(attr);
-			return -ENOMEM;
+			perf_evlist__id_add(session->evlist, evsel, 0, j, f_id);
 		}
 
 		lseek(fd, tmp, SEEK_SET);
@@ -920,93 +858,63 @@ int perf_header__read(struct perf_session *session, int fd)
 		events = malloc(f_header.event_types.size);
 		if (events == NULL)
 			return -ENOMEM;
-		if (perf_header__getbuffer64(self, fd, events,
+		if (perf_header__getbuffer64(header, fd, events,
 					     f_header.event_types.size))
 			goto out_errno;
 		event_count =  f_header.event_types.size / sizeof(struct perf_trace_event_type);
 	}
 
-	perf_header__process_sections(self, fd, perf_file_section__process);
+	perf_header__process_sections(header, fd, perf_file_section__process);
 
-	lseek(fd, self->data_offset, SEEK_SET);
+	lseek(fd, header->data_offset, SEEK_SET);
 
-	self->frozen = 1;
+	header->frozen = 1;
 	return 0;
 out_errno:
 	return -errno;
+
+out_delete_evlist:
+	perf_evlist__delete(session->evlist);
+	session->evlist = NULL;
+	return -ENOMEM;
 }
 
-u64 perf_header__sample_type(struct perf_header *header)
+u64 perf_evlist__sample_type(struct perf_evlist *evlist)
 {
+	struct perf_evsel *pos;
 	u64 type = 0;
-	int i;
-
-	for (i = 0; i < header->attrs; i++) {
-		struct perf_header_attr *attr = header->attr[i];
 
+	list_for_each_entry(pos, &evlist->entries, node) {
 		if (!type)
-			type = attr->attr.sample_type;
-		else if (type != attr->attr.sample_type)
+			type = pos->attr.sample_type;
+		else if (type != pos->attr.sample_type)
 			die("non matching sample_type");
 	}
 
 	return type;
 }
 
-bool perf_header__sample_id_all(const struct perf_header *header)
+bool perf_evlist__sample_id_all(const struct perf_evlist *evlist)
 {
 	bool value = false, first = true;
-	int i;
-
-	for (i = 0; i < header->attrs; i++) {
-		struct perf_header_attr *attr = header->attr[i];
+	struct perf_evsel *pos;
 
+	list_for_each_entry(pos, &evlist->entries, node) {
 		if (first) {
-			value = attr->attr.sample_id_all;
+			value = pos->attr.sample_id_all;
 			first = false;
-		} else if (value != attr->attr.sample_id_all)
+		} else if (value != pos->attr.sample_id_all)
 			die("non matching sample_id_all");
 	}
 
 	return value;
 }
 
-struct perf_event_attr *
-perf_header__find_attr(u64 id, struct perf_header *header)
-{
-	int i;
-
-	/*
-	 * We set id to -1 if the data file doesn't contain sample
-	 * ids. This can happen when the data file contains one type
-	 * of event and in that case, the header can still store the
-	 * event attribute information. Check for this and avoid
-	 * walking through the entire list of ids which may be large.
-	 */
-	if (id == -1ULL) {
-		if (header->attrs > 0)
-			return &header->attr[0]->attr;
-		return NULL;
-	}
-
-	for (i = 0; i < header->attrs; i++) {
-		struct perf_header_attr *attr = header->attr[i];
-		int j;
-
-		for (j = 0; j < attr->ids; j++) {
-			if (attr->id[j] == id)
-				return &attr->attr;
-		}
-	}
-
-	return NULL;
-}
-
-int event__synthesize_attr(struct perf_event_attr *attr, u16 ids, u64 *id,
-			   event__handler_t process,
-			   struct perf_session *session)
+int perf_event__synthesize_attr(struct perf_event_attr *attr, u16 ids, u64 *id,
+				perf_event__handler_t process,
+				struct perf_session *session)
 {
-	event_t *ev;
+	union perf_event *ev;
 	size_t size;
 	int err;
 
@@ -1033,17 +941,15 @@ int event__synthesize_attr(struct perf_event_attr *attr, u16 ids, u64 *id,
 	return err;
 }
 
-int event__synthesize_attrs(struct perf_header *self, event__handler_t process,
-			    struct perf_session *session)
+int perf_session__synthesize_attrs(struct perf_session *session,
+				   perf_event__handler_t process)
 {
-	struct perf_header_attr	*attr;
-	int i, err = 0;
-
-	for (i = 0; i < self->attrs; i++) {
-		attr = self->attr[i];
+	struct perf_evsel *attr;
+	int err = 0;
 
-		err = event__synthesize_attr(&attr->attr, attr->ids, attr->id,
-					     process, session);
+	list_for_each_entry(attr, &session->evlist->entries, node) {
+		err = perf_event__synthesize_attr(&attr->attr, attr->ids,
+						  attr->id, process, session);
 		if (err) {
 			pr_debug("failed to create perf header attribute\n");
 			return err;
@@ -1053,29 +959,39 @@ int event__synthesize_attrs(struct perf_header *self, event__handler_t process,
 	return err;
 }
 
-int event__process_attr(event_t *self, struct perf_session *session)
+int perf_event__process_attr(union perf_event *event,
+			     struct perf_session *session)
 {
-	struct perf_header_attr *attr;
 	unsigned int i, ids, n_ids;
+	struct perf_evsel *evsel;
 
-	attr = perf_header_attr__new(&self->attr.attr);
-	if (attr == NULL)
+	if (session->evlist == NULL) {
+		session->evlist = perf_evlist__new(NULL, NULL);
+		if (session->evlist == NULL)
+			return -ENOMEM;
+	}
+
+	evsel = perf_evsel__new(&event->attr.attr,
+				session->evlist->nr_entries);
+	if (evsel == NULL)
 		return -ENOMEM;
 
-	ids = self->header.size;
-	ids -= (void *)&self->attr.id - (void *)self;
+	perf_evlist__add(session->evlist, evsel);
+
+	ids = event->header.size;
+	ids -= (void *)&event->attr.id - (void *)event;
 	n_ids = ids / sizeof(u64);
+	/*
+	 * We don't have the cpu and thread maps on the header, so
+	 * for allocating the perf_sample_id table we fake 1 cpu and
+	 * hattr->ids threads.
+	 */
+	if (perf_evsel__alloc_id(evsel, 1, n_ids))
+		return -ENOMEM;
 
 	for (i = 0; i < n_ids; i++) {
-		if (perf_header_attr__add_id(attr, self->attr.id[i]) < 0) {
-			perf_header_attr__delete(attr);
-			return -ENOMEM;
-		}
-	}
-
-	if (perf_header__add_attr(&session->header, attr) < 0) {
-		perf_header_attr__delete(attr);
-		return -ENOMEM;
+		perf_evlist__id_add(session->evlist, evsel, 0, i,
+				    event->attr.id[i]);
 	}
 
 	perf_session__update_sample_type(session);
@@ -1083,11 +999,11 @@ int event__process_attr(event_t *self, struct perf_session *session)
 	return 0;
 }
 
-int event__synthesize_event_type(u64 event_id, char *name,
-				 event__handler_t process,
-				 struct perf_session *session)
+int perf_event__synthesize_event_type(u64 event_id, char *name,
+				      perf_event__handler_t process,
+				      struct perf_session *session)
 {
-	event_t ev;
+	union perf_event ev;
 	size_t size = 0;
 	int err = 0;
 
@@ -1108,8 +1024,8 @@ int event__synthesize_event_type(u64 event_id, char *name,
 	return err;
 }
 
-int event__synthesize_event_types(event__handler_t process,
-				  struct perf_session *session)
+int perf_event__synthesize_event_types(perf_event__handler_t process,
+				       struct perf_session *session)
 {
 	struct perf_trace_event_type *type;
 	int i, err = 0;
@@ -1117,8 +1033,9 @@ int event__synthesize_event_types(event__handler_t process,
 	for (i = 0; i < event_count; i++) {
 		type = &events[i];
 
-		err = event__synthesize_event_type(type->event_id, type->name,
-						   process, session);
+		err = perf_event__synthesize_event_type(type->event_id,
+							type->name, process,
+							session);
 		if (err) {
 			pr_debug("failed to create perf header event type\n");
 			return err;
@@ -1128,28 +1045,28 @@ int event__synthesize_event_types(event__handler_t process,
 	return err;
 }
 
-int event__process_event_type(event_t *self,
-			      struct perf_session *session __unused)
+int perf_event__process_event_type(union perf_event *event,
+				   struct perf_session *session __unused)
 {
-	if (perf_header__push_event(self->event_type.event_type.event_id,
-				    self->event_type.event_type.name) < 0)
+	if (perf_header__push_event(event->event_type.event_type.event_id,
+				    event->event_type.event_type.name) < 0)
 		return -ENOMEM;
 
 	return 0;
 }
 
-int event__synthesize_tracing_data(int fd, struct list_head *pattrs,
-				   event__handler_t process,
+int perf_event__synthesize_tracing_data(int fd, struct perf_evlist *evlist,
+					 perf_event__handler_t process,
 				   struct perf_session *session __unused)
 {
-	event_t ev;
+	union perf_event ev;
 	ssize_t size = 0, aligned_size = 0, padding;
-	int err = 0;
+	int err __used = 0;
 
 	memset(&ev, 0, sizeof(ev));
 
 	ev.tracing_data.header.type = PERF_RECORD_HEADER_TRACING_DATA;
-	size = read_tracing_data_size(fd, pattrs);
+	size = read_tracing_data_size(fd, &evlist->entries);
 	if (size <= 0)
 		return size;
 	aligned_size = ALIGN(size, sizeof(u64));
@@ -1159,16 +1076,16 @@ int event__synthesize_tracing_data(int fd, struct list_head *pattrs,
 
 	process(&ev, NULL, session);
 
-	err = read_tracing_data(fd, pattrs);
+	err = read_tracing_data(fd, &evlist->entries);
 	write_padded(fd, NULL, 0, padding);
 
 	return aligned_size;
 }
 
-int event__process_tracing_data(event_t *self,
-				struct perf_session *session)
+int perf_event__process_tracing_data(union perf_event *event,
+				     struct perf_session *session)
 {
-	ssize_t size_read, padding, size = self->tracing_data.size;
+	ssize_t size_read, padding, size = event->tracing_data.size;
 	off_t offset = lseek(session->fd, 0, SEEK_CUR);
 	char buf[BUFSIZ];
 
@@ -1194,12 +1111,12 @@ int event__process_tracing_data(event_t *self,
 	return size_read + padding;
 }
 
-int event__synthesize_build_id(struct dso *pos, u16 misc,
-			       event__handler_t process,
-			       struct machine *machine,
-			       struct perf_session *session)
+int perf_event__synthesize_build_id(struct dso *pos, u16 misc,
+				    perf_event__handler_t process,
+				    struct machine *machine,
+				    struct perf_session *session)
 {
-	event_t ev;
+	union perf_event ev;
 	size_t len;
 	int err = 0;
 
@@ -1222,11 +1139,11 @@ int event__synthesize_build_id(struct dso *pos, u16 misc,
 	return err;
 }
 
-int event__process_build_id(event_t *self,
-			    struct perf_session *session)
+int perf_event__process_build_id(union perf_event *event,
+				 struct perf_session *session)
 {
-	__event_process_build_id(&self->build_id,
-				 self->build_id.filename,
+	__event_process_build_id(&event->build_id,
+				 event->build_id.filename,
 				 session);
 	return 0;
 }
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 33f16be7b72f..456661d7f10e 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -9,13 +9,6 @@
 
 #include <linux/bitmap.h>
 
-struct perf_header_attr {
-	struct perf_event_attr attr;
-	int ids, size;
-	u64 *id;
-	off_t id_offset;
-};
-
 enum {
 	HEADER_TRACE_INFO = 1,
 	HEADER_BUILD_ID,
@@ -46,14 +39,12 @@ struct perf_pipe_file_header {
 
 struct perf_header;
 
-int perf_file_header__read(struct perf_file_header *self,
+int perf_file_header__read(struct perf_file_header *header,
 			   struct perf_header *ph, int fd);
 
 struct perf_header {
 	int			frozen;
-	int			attrs, size;
 	bool			needs_swap;
-	struct perf_header_attr **attr;
 	s64			attr_offset;
 	u64			data_offset;
 	u64			data_size;
@@ -62,34 +53,25 @@ struct perf_header {
 	DECLARE_BITMAP(adds_features, HEADER_FEAT_BITS);
 };
 
-int perf_header__init(struct perf_header *self);
-void perf_header__exit(struct perf_header *self);
+struct perf_evlist;
 
-int perf_header__read(struct perf_session *session, int fd);
-int perf_header__write(struct perf_header *self, int fd, bool at_exit);
+int perf_session__read_header(struct perf_session *session, int fd);
+int perf_session__write_header(struct perf_session *session,
+			       struct perf_evlist *evlist,
+			       int fd, bool at_exit);
 int perf_header__write_pipe(int fd);
 
-int perf_header__add_attr(struct perf_header *self,
-			  struct perf_header_attr *attr);
-
 int perf_header__push_event(u64 id, const char *name);
 char *perf_header__find_event(u64 id);
 
-struct perf_header_attr *perf_header_attr__new(struct perf_event_attr *attr);
-void perf_header_attr__delete(struct perf_header_attr *self);
+u64 perf_evlist__sample_type(struct perf_evlist *evlist);
+bool perf_evlist__sample_id_all(const struct perf_evlist *evlist);
+void perf_header__set_feat(struct perf_header *header, int feat);
+void perf_header__clear_feat(struct perf_header *header, int feat);
+bool perf_header__has_feat(const struct perf_header *header, int feat);
 
-int perf_header_attr__add_id(struct perf_header_attr *self, u64 id);
-
-u64 perf_header__sample_type(struct perf_header *header);
-bool perf_header__sample_id_all(const struct perf_header *header);
-struct perf_event_attr *
-perf_header__find_attr(u64 id, struct perf_header *header);
-void perf_header__set_feat(struct perf_header *self, int feat);
-void perf_header__clear_feat(struct perf_header *self, int feat);
-bool perf_header__has_feat(const struct perf_header *self, int feat);
-
-int perf_header__process_sections(struct perf_header *self, int fd,
-				  int (*process)(struct perf_file_section *self,
+int perf_header__process_sections(struct perf_header *header, int fd,
+				  int (*process)(struct perf_file_section *section,
 						 struct perf_header *ph,
 						 int feat, int fd));
 
@@ -97,32 +79,31 @@ int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
 			  const char *name, bool is_kallsyms);
 int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir);
 
-int event__synthesize_attr(struct perf_event_attr *attr, u16 ids, u64 *id,
-			   event__handler_t process,
-			   struct perf_session *session);
-int event__synthesize_attrs(struct perf_header *self,
-			    event__handler_t process,
-			    struct perf_session *session);
-int event__process_attr(event_t *self, struct perf_session *session);
-
-int event__synthesize_event_type(u64 event_id, char *name,
-				 event__handler_t process,
-				 struct perf_session *session);
-int event__synthesize_event_types(event__handler_t process,
-				  struct perf_session *session);
-int event__process_event_type(event_t *self,
-			      struct perf_session *session);
-
-int event__synthesize_tracing_data(int fd, struct list_head *pattrs,
-				   event__handler_t process,
-				   struct perf_session *session);
-int event__process_tracing_data(event_t *self,
+int perf_event__synthesize_attr(struct perf_event_attr *attr, u16 ids, u64 *id,
+				perf_event__handler_t process,
 				struct perf_session *session);
+int perf_session__synthesize_attrs(struct perf_session *session,
+				   perf_event__handler_t process);
+int perf_event__process_attr(union perf_event *event, struct perf_session *session);
+
+int perf_event__synthesize_event_type(u64 event_id, char *name,
+				      perf_event__handler_t process,
+				      struct perf_session *session);
+int perf_event__synthesize_event_types(perf_event__handler_t process,
+				       struct perf_session *session);
+int perf_event__process_event_type(union perf_event *event,
+				   struct perf_session *session);
 
-int event__synthesize_build_id(struct dso *pos, u16 misc,
-			       event__handler_t process,
-			       struct machine *machine,
-			       struct perf_session *session);
-int event__process_build_id(event_t *self, struct perf_session *session);
-
+int perf_event__synthesize_tracing_data(int fd, struct perf_evlist *evlist,
+					perf_event__handler_t process,
+					struct perf_session *session);
+int perf_event__process_tracing_data(union perf_event *event,
+				     struct perf_session *session);
+
+int perf_event__synthesize_build_id(struct dso *pos, u16 misc,
+				    perf_event__handler_t process,
+				    struct machine *machine,
+				    struct perf_session *session);
+int perf_event__process_build_id(union perf_event *event,
+				 struct perf_session *session);
 #endif /* __PERF_HEADER_H */
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index df51560f16f7..627a02e03c57 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -1,3 +1,4 @@
+#include "annotate.h"
 #include "util.h"
 #include "build-id.h"
 #include "hist.h"
@@ -49,6 +50,15 @@ static void hists__calc_col_len(struct hists *self, struct hist_entry *h)
 
 	if (h->ms.sym)
 		hists__new_col_len(self, HISTC_SYMBOL, h->ms.sym->namelen);
+	else {
+		const unsigned int unresolved_col_width = BITS_PER_LONG / 4;
+
+		if (hists__col_len(self, HISTC_DSO) < unresolved_col_width &&
+		    !symbol_conf.col_width_list_str && !symbol_conf.field_sep &&
+		    !symbol_conf.dso_list)
+			hists__set_col_len(self, HISTC_DSO,
+					   unresolved_col_width);
+	}
 
 	len = thread__comm_len(h->thread);
 	if (hists__new_col_len(self, HISTC_COMM, len))
@@ -211,7 +221,9 @@ void hist_entry__free(struct hist_entry *he)
  * collapse the histogram
  */
 
-static bool collapse__insert_entry(struct rb_root *root, struct hist_entry *he)
+static bool hists__collapse_insert_entry(struct hists *self,
+					 struct rb_root *root,
+					 struct hist_entry *he)
 {
 	struct rb_node **p = &root->rb_node;
 	struct rb_node *parent = NULL;
@@ -226,8 +238,11 @@ static bool collapse__insert_entry(struct rb_root *root, struct hist_entry *he)
 
 		if (!cmp) {
 			iter->period += he->period;
-			if (symbol_conf.use_callchain)
-				callchain_merge(iter->callchain, he->callchain);
+			if (symbol_conf.use_callchain) {
+				callchain_cursor_reset(&self->callchain_cursor);
+				callchain_merge(&self->callchain_cursor, iter->callchain,
+						he->callchain);
+			}
 			hist_entry__free(he);
 			return false;
 		}
@@ -262,7 +277,7 @@ void hists__collapse_resort(struct hists *self)
 		next = rb_next(&n->rb_node);
 
 		rb_erase(&n->rb_node, &self->entries);
-		if (collapse__insert_entry(&tmp, n))
+		if (hists__collapse_insert_entry(self, &tmp, n))
 			hists__inc_nr_entries(self, n);
 	}
 
@@ -425,7 +440,7 @@ static size_t __callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
 		u64 cumul;
 
 		child = rb_entry(node, struct callchain_node, rb_node);
-		cumul = cumul_hits(child);
+		cumul = callchain_cumul_hits(child);
 		remaining -= cumul;
 
 		/*
@@ -947,225 +962,14 @@ void hists__filter_by_thread(struct hists *self, const struct thread *thread)
 	}
 }
 
-static int symbol__alloc_hist(struct symbol *self)
-{
-	struct sym_priv *priv = symbol__priv(self);
-	const int size = (sizeof(*priv->hist) +
-			  (self->end - self->start) * sizeof(u64));
-
-	priv->hist = zalloc(size);
-	return priv->hist == NULL ? -1 : 0;
-}
-
-int hist_entry__inc_addr_samples(struct hist_entry *self, u64 ip)
-{
-	unsigned int sym_size, offset;
-	struct symbol *sym = self->ms.sym;
-	struct sym_priv *priv;
-	struct sym_hist *h;
-
-	if (!sym || !self->ms.map)
-		return 0;
-
-	priv = symbol__priv(sym);
-	if (priv->hist == NULL && symbol__alloc_hist(sym) < 0)
-		return -ENOMEM;
-
-	sym_size = sym->end - sym->start;
-	offset = ip - sym->start;
-
-	pr_debug3("%s: ip=%#" PRIx64 "\n", __func__, self->ms.map->unmap_ip(self->ms.map, ip));
-
-	if (offset >= sym_size)
-		return 0;
-
-	h = priv->hist;
-	h->sum++;
-	h->ip[offset]++;
-
-	pr_debug3("%#" PRIx64 " %s: period++ [ip: %#" PRIx64 ", %#" PRIx64
-		  "] => %" PRIu64 "\n", self->ms.sym->start, self->ms.sym->name,
-		  ip, ip - self->ms.sym->start, h->ip[offset]);
-	return 0;
-}
-
-static struct objdump_line *objdump_line__new(s64 offset, char *line, size_t privsize)
-{
-	struct objdump_line *self = malloc(sizeof(*self) + privsize);
-
-	if (self != NULL) {
-		self->offset = offset;
-		self->line = line;
-	}
-
-	return self;
-}
-
-void objdump_line__free(struct objdump_line *self)
-{
-	free(self->line);
-	free(self);
-}
-
-static void objdump__add_line(struct list_head *head, struct objdump_line *line)
-{
-	list_add_tail(&line->node, head);
-}
-
-struct objdump_line *objdump__get_next_ip_line(struct list_head *head,
-					       struct objdump_line *pos)
-{
-	list_for_each_entry_continue(pos, head, node)
-		if (pos->offset >= 0)
-			return pos;
-
-	return NULL;
-}
-
-static int hist_entry__parse_objdump_line(struct hist_entry *self, FILE *file,
-					  struct list_head *head, size_t privsize)
+int hist_entry__inc_addr_samples(struct hist_entry *he, int evidx, u64 ip)
 {
-	struct symbol *sym = self->ms.sym;
-	struct objdump_line *objdump_line;
-	char *line = NULL, *tmp, *tmp2, *c;
-	size_t line_len;
-	s64 line_ip, offset = -1;
-
-	if (getline(&line, &line_len, file) < 0)
-		return -1;
-
-	if (!line)
-		return -1;
-
-	while (line_len != 0 && isspace(line[line_len - 1]))
-		line[--line_len] = '\0';
-
-	c = strchr(line, '\n');
-	if (c)
-		*c = 0;
-
-	line_ip = -1;
-
-	/*
-	 * Strip leading spaces:
-	 */
-	tmp = line;
-	while (*tmp) {
-		if (*tmp != ' ')
-			break;
-		tmp++;
-	}
-
-	if (*tmp) {
-		/*
-		 * Parse hexa addresses followed by ':'
-		 */
-		line_ip = strtoull(tmp, &tmp2, 16);
-		if (*tmp2 != ':' || tmp == tmp2 || tmp2[1] == '\0')
-			line_ip = -1;
-	}
-
-	if (line_ip != -1) {
-		u64 start = map__rip_2objdump(self->ms.map, sym->start),
-		    end = map__rip_2objdump(self->ms.map, sym->end);
-
-		offset = line_ip - start;
-		if (offset < 0 || (u64)line_ip > end)
-			offset = -1;
-	}
-
-	objdump_line = objdump_line__new(offset, line, privsize);
-	if (objdump_line == NULL) {
-		free(line);
-		return -1;
-	}
-	objdump__add_line(head, objdump_line);
-
-	return 0;
+	return symbol__inc_addr_samples(he->ms.sym, he->ms.map, evidx, ip);
 }
 
-int hist_entry__annotate(struct hist_entry *self, struct list_head *head,
-			 size_t privsize)
+int hist_entry__annotate(struct hist_entry *he, size_t privsize)
 {
-	struct symbol *sym = self->ms.sym;
-	struct map *map = self->ms.map;
-	struct dso *dso = map->dso;
-	char *filename = dso__build_id_filename(dso, NULL, 0);
-	bool free_filename = true;
-	char command[PATH_MAX * 2];
-	FILE *file;
-	int err = 0;
-	u64 len;
-	char symfs_filename[PATH_MAX];
-
-	if (filename) {
-		snprintf(symfs_filename, sizeof(symfs_filename), "%s%s",
-			 symbol_conf.symfs, filename);
-	}
-
-	if (filename == NULL) {
-		if (dso->has_build_id) {
-			pr_err("Can't annotate %s: not enough memory\n",
-			       sym->name);
-			return -ENOMEM;
-		}
-		goto fallback;
-	} else if (readlink(symfs_filename, command, sizeof(command)) < 0 ||
-		   strstr(command, "[kernel.kallsyms]") ||
-		   access(symfs_filename, R_OK)) {
-		free(filename);
-fallback:
-		/*
-		 * If we don't have build-ids or the build-id file isn't in the
-		 * cache, or is just a kallsyms file, well, lets hope that this
-		 * DSO is the same as when 'perf record' ran.
-		 */
-		filename = dso->long_name;
-		snprintf(symfs_filename, sizeof(symfs_filename), "%s%s",
-			 symbol_conf.symfs, filename);
-		free_filename = false;
-	}
-
-	if (dso->origin == DSO__ORIG_KERNEL) {
-		if (dso->annotate_warned)
-			goto out_free_filename;
-		err = -ENOENT;
-		dso->annotate_warned = 1;
-		pr_err("Can't annotate %s: No vmlinux file was found in the "
-		       "path\n", sym->name);
-		goto out_free_filename;
-	}
-
-	pr_debug("%s: filename=%s, sym=%s, start=%#" PRIx64 ", end=%#" PRIx64 "\n", __func__,
-		 filename, sym->name, map->unmap_ip(map, sym->start),
-		 map->unmap_ip(map, sym->end));
-
-	len = sym->end - sym->start;
-
-	pr_debug("annotating [%p] %30s : [%p] %30s\n",
-		 dso, dso->long_name, sym, sym->name);
-
-	snprintf(command, sizeof(command),
-		 "objdump --start-address=0x%016" PRIx64 " --stop-address=0x%016" PRIx64 " -dS -C %s|grep -v %s|expand",
-		 map__rip_2objdump(map, sym->start),
-		 map__rip_2objdump(map, sym->end),
-		 symfs_filename, filename);
-
-	pr_debug("Executing: %s\n", command);
-
-	file = popen(command, "r");
-	if (!file)
-		goto out_free_filename;
-
-	while (!feof(file))
-		if (hist_entry__parse_objdump_line(self, file, head, privsize) < 0)
-			break;
-
-	pclose(file);
-out_free_filename:
-	if (free_filename)
-		free(filename);
-	return err;
+	return symbol__annotate(he->ms.sym, he->ms.map, privsize);
 }
 
 void hists__inc_nr_events(struct hists *self, u32 type)
@@ -1180,8 +984,12 @@ size_t hists__fprintf_nr_events(struct hists *self, FILE *fp)
 	size_t ret = 0;
 
 	for (i = 0; i < PERF_RECORD_HEADER_MAX; ++i) {
-		const char *name = event__get_event_name(i);
+		const char *name;
+
+		if (self->stats.nr_events[i] == 0)
+			continue;
 
+		name = perf_event__name(i);
 		if (!strcmp(name, "UNKNOWN"))
 			continue;
 
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index ee789856a8c9..cb6858a2f9a3 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -9,33 +9,6 @@ extern struct callchain_param callchain_param;
 struct hist_entry;
 struct addr_location;
 struct symbol;
-struct rb_root;
-
-struct objdump_line {
-	struct list_head node;
-	s64		 offset;
-	char		 *line;
-};
-
-void objdump_line__free(struct objdump_line *self);
-struct objdump_line *objdump__get_next_ip_line(struct list_head *head,
-					       struct objdump_line *pos);
-
-struct sym_hist {
-	u64		sum;
-	u64		ip[0];
-};
-
-struct sym_ext {
-	struct rb_node	node;
-	double		percent;
-	char		*path;
-};
-
-struct sym_priv {
-	struct sym_hist	*hist;
-	struct sym_ext	*ext;
-};
 
 /*
  * The kernel collects the number of events it couldn't send in a stretch and
@@ -69,14 +42,13 @@ enum hist_column {
 };
 
 struct hists {
-	struct rb_node		rb_node;
 	struct rb_root		entries;
 	u64			nr_entries;
 	struct events_stats	stats;
-	u64			config;
 	u64			event_stream;
-	u32			type;
 	u16			col_len[HISTC_NR_COLS];
+	/* Best would be to reuse the session callchain cursor */
+	struct callchain_cursor	callchain_cursor;
 };
 
 struct hist_entry *__hists__add_entry(struct hists *self,
@@ -102,9 +74,8 @@ size_t hists__fprintf_nr_events(struct hists *self, FILE *fp);
 size_t hists__fprintf(struct hists *self, struct hists *pair,
 		      bool show_displacement, FILE *fp);
 
-int hist_entry__inc_addr_samples(struct hist_entry *self, u64 ip);
-int hist_entry__annotate(struct hist_entry *self, struct list_head *head,
-			 size_t privsize);
+int hist_entry__inc_addr_samples(struct hist_entry *self, int evidx, u64 addr);
+int hist_entry__annotate(struct hist_entry *self, size_t privsize);
 
 void hists__filter_by_dso(struct hists *self, const struct dso *dso);
 void hists__filter_by_thread(struct hists *self, const struct thread *thread);
@@ -113,21 +84,18 @@ u16 hists__col_len(struct hists *self, enum hist_column col);
 void hists__set_col_len(struct hists *self, enum hist_column col, u16 len);
 bool hists__new_col_len(struct hists *self, enum hist_column col, u16 len);
 
-#ifdef NO_NEWT_SUPPORT
-static inline int hists__browse(struct hists *self __used,
-				const char *helpline __used,
-				const char *ev_name __used)
-{
-	return 0;
-}
+struct perf_evlist;
 
-static inline int hists__tui_browse_tree(struct rb_root *self __used,
-					 const char *help __used)
+#ifdef NO_NEWT_SUPPORT
+static inline
+int perf_evlist__tui_browse_hists(struct perf_evlist *evlist __used,
+				  const char *help __used)
 {
 	return 0;
 }
 
-static inline int hist_entry__tui_annotate(struct hist_entry *self __used)
+static inline int hist_entry__tui_annotate(struct hist_entry *self __used,
+					   int evidx __used)
 {
 	return 0;
 }
@@ -135,14 +103,12 @@ static inline int hist_entry__tui_annotate(struct hist_entry *self __used)
 #define KEY_RIGHT -2
 #else
 #include <newt.h>
-int hists__browse(struct hists *self, const char *helpline,
-		  const char *ev_name);
-int hist_entry__tui_annotate(struct hist_entry *self);
+int hist_entry__tui_annotate(struct hist_entry *self, int evidx);
 
 #define KEY_LEFT NEWT_KEY_LEFT
 #define KEY_RIGHT NEWT_KEY_RIGHT
 
-int hists__tui_browse_tree(struct rb_root *self, const char *help);
+int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help);
 #endif
 
 unsigned int hists__sort_list_width(struct hists *self);
diff --git a/tools/perf/util/include/linux/list.h b/tools/perf/util/include/linux/list.h
index f5ca26e53fbb..356c7e467b83 100644
--- a/tools/perf/util/include/linux/list.h
+++ b/tools/perf/util/include/linux/list.h
@@ -1,3 +1,4 @@
+#include <linux/kernel.h>
 #include "../../../../include/linux/list.h"
 
 #ifndef PERF_LIST_H
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 135f69baf966..54a7e2634d58 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1,6 +1,7 @@
 #include "../../../include/linux/hw_breakpoint.h"
 #include "util.h"
 #include "../perf.h"
+#include "evlist.h"
 #include "evsel.h"
 #include "parse-options.h"
 #include "parse-events.h"
@@ -11,10 +12,6 @@
 #include "header.h"
 #include "debugfs.h"
 
-int				nr_counters;
-
-LIST_HEAD(evsel_list);
-
 struct event_symbol {
 	u8		type;
 	u64		config;
@@ -271,6 +268,9 @@ const char *event_name(struct perf_evsel *evsel)
 	u64 config = evsel->attr.config;
 	int type = evsel->attr.type;
 
+	if (evsel->name)
+		return evsel->name;
+
 	return __event_name(type, config);
 }
 
@@ -449,8 +449,8 @@ parse_single_tracepoint_event(char *sys_name,
 /* sys + ':' + event + ':' + flags*/
 #define MAX_EVOPT_LEN	(MAX_EVENT_LENGTH * 2 + 2 + 128)
 static enum event_result
-parse_multiple_tracepoint_event(char *sys_name, const char *evt_exp,
-				char *flags)
+parse_multiple_tracepoint_event(const struct option *opt, char *sys_name,
+				const char *evt_exp, char *flags)
 {
 	char evt_path[MAXPATHLEN];
 	struct dirent *evt_ent;
@@ -483,15 +483,16 @@ parse_multiple_tracepoint_event(char *sys_name, const char *evt_exp,
 		if (len < 0)
 			return EVT_FAILED;
 
-		if (parse_events(NULL, event_opt, 0))
+		if (parse_events(opt, event_opt, 0))
 			return EVT_FAILED;
 	}
 
 	return EVT_HANDLED_ALL;
 }
 
-static enum event_result parse_tracepoint_event(const char **strp,
-				    struct perf_event_attr *attr)
+static enum event_result
+parse_tracepoint_event(const struct option *opt, const char **strp,
+		       struct perf_event_attr *attr)
 {
 	const char *evt_name;
 	char *flags = NULL, *comma_loc;
@@ -530,7 +531,7 @@ static enum event_result parse_tracepoint_event(const char **strp,
 		return EVT_FAILED;
 	if (strpbrk(evt_name, "*?")) {
 		*strp += strlen(sys_name) + evt_length + 1; /* 1 == the ':' */
-		return parse_multiple_tracepoint_event(sys_name, evt_name,
+		return parse_multiple_tracepoint_event(opt, sys_name, evt_name,
 						       flags);
 	} else {
 		return parse_single_tracepoint_event(sys_name, evt_name,
@@ -740,11 +741,12 @@ parse_event_modifier(const char **strp, struct perf_event_attr *attr)
  * Symbolic names are (almost) exactly matched.
  */
 static enum event_result
-parse_event_symbols(const char **str, struct perf_event_attr *attr)
+parse_event_symbols(const struct option *opt, const char **str,
+		    struct perf_event_attr *attr)
 {
 	enum event_result ret;
 
-	ret = parse_tracepoint_event(str, attr);
+	ret = parse_tracepoint_event(opt, str, attr);
 	if (ret != EVT_FAILED)
 		goto modifier;
 
@@ -778,14 +780,17 @@ modifier:
 	return ret;
 }
 
-int parse_events(const struct option *opt __used, const char *str, int unset __used)
+int parse_events(const struct option *opt, const char *str, int unset __used)
 {
+	struct perf_evlist *evlist = *(struct perf_evlist **)opt->value;
 	struct perf_event_attr attr;
 	enum event_result ret;
+	const char *ostr;
 
 	for (;;) {
+		ostr = str;
 		memset(&attr, 0, sizeof(attr));
-		ret = parse_event_symbols(&str, &attr);
+		ret = parse_event_symbols(opt, &str, &attr);
 		if (ret == EVT_FAILED)
 			return -1;
 
@@ -794,12 +799,15 @@ int parse_events(const struct option *opt __used, const char *str, int unset __u
 
 		if (ret != EVT_HANDLED_ALL) {
 			struct perf_evsel *evsel;
-			evsel = perf_evsel__new(&attr,
-						nr_counters);
+			evsel = perf_evsel__new(&attr, evlist->nr_entries);
 			if (evsel == NULL)
 				return -1;
-			list_add_tail(&evsel->node, &evsel_list);
-			++nr_counters;
+			perf_evlist__add(evlist, evsel);
+
+			evsel->name = calloc(str - ostr + 1, 1);
+			if (!evsel->name)
+				return -1;
+			strncpy(evsel->name, ostr, str - ostr);
 		}
 
 		if (*str == 0)
@@ -813,13 +821,14 @@ int parse_events(const struct option *opt __used, const char *str, int unset __u
 	return 0;
 }
 
-int parse_filter(const struct option *opt __used, const char *str,
+int parse_filter(const struct option *opt, const char *str,
 		 int unset __used)
 {
+	struct perf_evlist *evlist = *(struct perf_evlist **)opt->value;
 	struct perf_evsel *last = NULL;
 
-	if (!list_empty(&evsel_list))
-		last = list_entry(evsel_list.prev, struct perf_evsel, node);
+	if (evlist->nr_entries > 0)
+		last = list_entry(evlist->entries.prev, struct perf_evsel, node);
 
 	if (last == NULL || last->attr.type != PERF_TYPE_TRACEPOINT) {
 		fprintf(stderr,
@@ -849,7 +858,7 @@ static const char * const event_type_descriptors[] = {
  * Print the events from <debugfs_mount_point>/tracing/events
  */
 
-static void print_tracepoint_events(void)
+void print_tracepoint_events(const char *subsys_glob, const char *event_glob)
 {
 	DIR *sys_dir, *evt_dir;
 	struct dirent *sys_next, *evt_next, sys_dirent, evt_dirent;
@@ -864,6 +873,9 @@ static void print_tracepoint_events(void)
 		return;
 
 	for_each_subsystem(sys_dir, sys_dirent, sys_next) {
+		if (subsys_glob != NULL && 
+		    !strglobmatch(sys_dirent.d_name, subsys_glob))
+			continue;
 
 		snprintf(dir_path, MAXPATHLEN, "%s/%s", debugfs_path,
 			 sys_dirent.d_name);
@@ -872,6 +884,10 @@ static void print_tracepoint_events(void)
 			continue;
 
 		for_each_event(sys_dirent, evt_dir, evt_dirent, evt_next) {
+			if (event_glob != NULL && 
+			    !strglobmatch(evt_dirent.d_name, event_glob))
+				continue;
+
 			snprintf(evt_path, MAXPATHLEN, "%s:%s",
 				 sys_dirent.d_name, evt_dirent.d_name);
 			printf("  %-42s [%s]\n", evt_path,
@@ -923,13 +939,61 @@ int is_valid_tracepoint(const char *event_string)
 	return 0;
 }
 
+void print_events_type(u8 type)
+{
+	struct event_symbol *syms = event_symbols;
+	unsigned int i;
+	char name[64];
+
+	for (i = 0; i < ARRAY_SIZE(event_symbols); i++, syms++) {
+		if (type != syms->type)
+			continue;
+
+		if (strlen(syms->alias))
+			snprintf(name, sizeof(name),  "%s OR %s",
+				 syms->symbol, syms->alias);
+		else
+			snprintf(name, sizeof(name), "%s", syms->symbol);
+
+		printf("  %-42s [%s]\n", name,
+			event_type_descriptors[type]);
+	}
+}
+
+int print_hwcache_events(const char *event_glob)
+{
+	unsigned int type, op, i, printed = 0;
+
+	for (type = 0; type < PERF_COUNT_HW_CACHE_MAX; type++) {
+		for (op = 0; op < PERF_COUNT_HW_CACHE_OP_MAX; op++) {
+			/* skip invalid cache type */
+			if (!is_cache_op_valid(type, op))
+				continue;
+
+			for (i = 0; i < PERF_COUNT_HW_CACHE_RESULT_MAX; i++) {
+				char *name = event_cache_name(type, op, i);
+
+				if (event_glob != NULL && 
+				    !strglobmatch(name, event_glob))
+					continue;
+
+				printf("  %-42s [%s]\n", name,
+					event_type_descriptors[PERF_TYPE_HW_CACHE]);
+				++printed;
+			}
+		}
+	}
+
+	return printed;
+}
+
 /*
  * Print the help text for the event symbols:
  */
-void print_events(void)
+void print_events(const char *event_glob)
 {
 	struct event_symbol *syms = event_symbols;
-	unsigned int i, type, op, prev_type = -1;
+	unsigned int i, type, prev_type = -1, printed = 0, ntypes_printed = 0;
 	char name[40];
 
 	printf("\n");
@@ -938,8 +1002,16 @@ void print_events(void)
 	for (i = 0; i < ARRAY_SIZE(event_symbols); i++, syms++) {
 		type = syms->type;
 
-		if (type != prev_type)
+		if (type != prev_type && printed) {
 			printf("\n");
+			printed = 0;
+			ntypes_printed++;
+		}
+
+		if (event_glob != NULL && 
+		    !(strglobmatch(syms->symbol, event_glob) ||
+		      (syms->alias && strglobmatch(syms->alias, event_glob))))
+			continue;
 
 		if (strlen(syms->alias))
 			sprintf(name, "%s OR %s", syms->symbol, syms->alias);
@@ -949,22 +1021,17 @@ void print_events(void)
 			event_type_descriptors[type]);
 
 		prev_type = type;
+		++printed;
 	}
 
-	printf("\n");
-	for (type = 0; type < PERF_COUNT_HW_CACHE_MAX; type++) {
-		for (op = 0; op < PERF_COUNT_HW_CACHE_OP_MAX; op++) {
-			/* skip invalid cache type */
-			if (!is_cache_op_valid(type, op))
-				continue;
-
-			for (i = 0; i < PERF_COUNT_HW_CACHE_RESULT_MAX; i++) {
-				printf("  %-42s [%s]\n",
-					event_cache_name(type, op, i),
-					event_type_descriptors[PERF_TYPE_HW_CACHE]);
-			}
-		}
+	if (ntypes_printed) {
+		printed = 0;
+		printf("\n");
 	}
+	print_hwcache_events(event_glob);
+
+	if (event_glob != NULL)
+		return;
 
 	printf("\n");
 	printf("  %-42s [%s]\n",
@@ -977,37 +1044,7 @@ void print_events(void)
 			event_type_descriptors[PERF_TYPE_BREAKPOINT]);
 	printf("\n");
 
-	print_tracepoint_events();
+	print_tracepoint_events(NULL, NULL);
 
 	exit(129);
 }
-
-int perf_evsel_list__create_default(void)
-{
-	struct perf_evsel *evsel;
-	struct perf_event_attr attr;
-
-	memset(&attr, 0, sizeof(attr));
-	attr.type = PERF_TYPE_HARDWARE;
-	attr.config = PERF_COUNT_HW_CPU_CYCLES;
-
-	evsel = perf_evsel__new(&attr, 0);
-
-	if (evsel == NULL)
-		return -ENOMEM;
-
-	list_add(&evsel->node, &evsel_list);
-	++nr_counters;
-	return 0;
-}
-
-void perf_evsel_list__delete(void)
-{
-	struct perf_evsel *pos, *n;
-
-	list_for_each_entry_safe(pos, n, &evsel_list, node) {
-		list_del_init(&pos->node);
-		perf_evsel__delete(pos);
-	}
-	nr_counters = 0;
-}
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 458e3ecf17af..212f88e07a9c 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -9,11 +9,6 @@
 struct list_head;
 struct perf_evsel;
 
-extern struct list_head evsel_list;
-
-int perf_evsel_list__create_default(void);
-void perf_evsel_list__delete(void);
-
 struct option;
 
 struct tracepoint_path {
@@ -25,8 +20,6 @@ struct tracepoint_path {
 extern struct tracepoint_path *tracepoint_id_to_path(u64 config);
 extern bool have_tracepoints(struct list_head *evlist);
 
-extern int			nr_counters;
-
 const char *event_name(struct perf_evsel *event);
 extern const char *__event_name(int type, u64 config);
 
@@ -35,7 +28,10 @@ extern int parse_filter(const struct option *opt, const char *str, int unset);
 
 #define EVENTS_HELP_MAX (128*1024)
 
-extern void print_events(void);
+void print_events(const char *event_glob);
+void print_events_type(u8 type);
+void print_tracepoint_events(const char *subsys_glob, const char *event_glob);
+int print_hwcache_events(const char *event_glob);
 extern int is_valid_tracepoint(const char *event_string);
 
 extern char debugfs_path[];
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 6e29d9c9dccc..5ddee66020a7 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -31,6 +31,7 @@
 #include <string.h>
 #include <stdarg.h>
 #include <limits.h>
+#include <elf.h>
 
 #undef _GNU_SOURCE
 #include "util.h"
@@ -111,7 +112,25 @@ static struct symbol *__find_kernel_function_by_name(const char *name,
 						     NULL);
 }
 
-const char *kernel_get_module_path(const char *module)
+static struct map *kernel_get_module_map(const char *module)
+{
+	struct rb_node *nd;
+	struct map_groups *grp = &machine.kmaps;
+
+	if (!module)
+		module = "kernel";
+
+	for (nd = rb_first(&grp->maps[MAP__FUNCTION]); nd; nd = rb_next(nd)) {
+		struct map *pos = rb_entry(nd, struct map, rb_node);
+		if (strncmp(pos->dso->short_name + 1, module,
+			    pos->dso->short_name_len - 2) == 0) {
+			return pos;
+		}
+	}
+	return NULL;
+}
+
+static struct dso *kernel_get_module_dso(const char *module)
 {
 	struct dso *dso;
 	struct map *map;
@@ -141,7 +160,13 @@ const char *kernel_get_module_path(const char *module)
 		}
 	}
 found:
-	return dso->long_name;
+	return dso;
+}
+
+const char *kernel_get_module_path(const char *module)
+{
+	struct dso *dso = kernel_get_module_dso(module);
+	return (dso) ? dso->long_name : NULL;
 }
 
 #ifdef DWARF_SUPPORT
@@ -384,7 +409,7 @@ int show_line_range(struct line_range *lr, const char *module)
 	setup_pager();
 
 	if (lr->function)
-		fprintf(stdout, "<%s:%d>\n", lr->function,
+		fprintf(stdout, "<%s@%s:%d>\n", lr->function, lr->path,
 			lr->start - lr->offset);
 	else
 		fprintf(stdout, "<%s:%d>\n", lr->path, lr->start);
@@ -426,12 +451,14 @@ end:
 }
 
 static int show_available_vars_at(int fd, struct perf_probe_event *pev,
-				  int max_vls, bool externs)
+				  int max_vls, struct strfilter *_filter,
+				  bool externs)
 {
 	char *buf;
-	int ret, i;
+	int ret, i, nvars;
 	struct str_node *node;
 	struct variable_list *vls = NULL, *vl;
+	const char *var;
 
 	buf = synthesize_perf_probe_point(&pev->point);
 	if (!buf)
@@ -439,36 +466,45 @@ static int show_available_vars_at(int fd, struct perf_probe_event *pev,
 	pr_debug("Searching variables at %s\n", buf);
 
 	ret = find_available_vars_at(fd, pev, &vls, max_vls, externs);
-	if (ret > 0) {
-		/* Some variables were found */
-		fprintf(stdout, "Available variables at %s\n", buf);
-		for (i = 0; i < ret; i++) {
-			vl = &vls[i];
-			/*
-			 * A probe point might be converted to
-			 * several trace points.
-			 */
-			fprintf(stdout, "\t@<%s+%lu>\n", vl->point.symbol,
-				vl->point.offset);
-			free(vl->point.symbol);
-			if (vl->vars) {
-				strlist__for_each(node, vl->vars)
+	if (ret <= 0) {
+		pr_err("Failed to find variables at %s (%d)\n", buf, ret);
+		goto end;
+	}
+	/* Some variables are found */
+	fprintf(stdout, "Available variables at %s\n", buf);
+	for (i = 0; i < ret; i++) {
+		vl = &vls[i];
+		/*
+		 * A probe point might be converted to
+		 * several trace points.
+		 */
+		fprintf(stdout, "\t@<%s+%lu>\n", vl->point.symbol,
+			vl->point.offset);
+		free(vl->point.symbol);
+		nvars = 0;
+		if (vl->vars) {
+			strlist__for_each(node, vl->vars) {
+				var = strchr(node->s, '\t') + 1;
+				if (strfilter__compare(_filter, var)) {
 					fprintf(stdout, "\t\t%s\n", node->s);
-				strlist__delete(vl->vars);
-			} else
-				fprintf(stdout, "(No variables)\n");
+					nvars++;
+				}
+			}
+			strlist__delete(vl->vars);
 		}
-		free(vls);
-	} else
-		pr_err("Failed to find variables at %s (%d)\n", buf, ret);
-
+		if (nvars == 0)
+			fprintf(stdout, "\t\t(No matched variables)\n");
+	}
+	free(vls);
+end:
 	free(buf);
 	return ret;
 }
 
 /* Show available variables on given probe point */
 int show_available_vars(struct perf_probe_event *pevs, int npevs,
-			int max_vls, const char *module, bool externs)
+			int max_vls, const char *module,
+			struct strfilter *_filter, bool externs)
 {
 	int i, fd, ret = 0;
 
@@ -485,7 +521,8 @@ int show_available_vars(struct perf_probe_event *pevs, int npevs,
 	setup_pager();
 
 	for (i = 0; i < npevs && ret >= 0; i++)
-		ret = show_available_vars_at(fd, &pevs[i], max_vls, externs);
+		ret = show_available_vars_at(fd, &pevs[i], max_vls, _filter,
+					     externs);
 
 	close(fd);
 	return ret;
@@ -531,7 +568,9 @@ int show_line_range(struct line_range *lr __unused, const char *module __unused)
 
 int show_available_vars(struct perf_probe_event *pevs __unused,
 			int npevs __unused, int max_vls __unused,
-			const char *module __unused, bool externs __unused)
+			const char *module __unused,
+			struct strfilter *filter __unused,
+			bool externs __unused)
 {
 	pr_warning("Debuginfo-analysis is not supported.\n");
 	return -ENOSYS;
@@ -556,11 +595,11 @@ static int parse_line_num(char **ptr, int *val, const char *what)
  * The line range syntax is described by:
  *
  *         SRC[:SLN[+NUM|-ELN]]
- *         FNC[:SLN[+NUM|-ELN]]
+ *         FNC[@SRC][:SLN[+NUM|-ELN]]
  */
 int parse_line_range_desc(const char *arg, struct line_range *lr)
 {
-	char *range, *name = strdup(arg);
+	char *range, *file, *name = strdup(arg);
 	int err;
 
 	if (!name)
@@ -610,7 +649,16 @@ int parse_line_range_desc(const char *arg, struct line_range *lr)
 		}
 	}
 
-	if (strchr(name, '.'))
+	file = strchr(name, '@');
+	if (file) {
+		*file = '\0';
+		lr->file = strdup(++file);
+		if (lr->file == NULL) {
+			err = -ENOMEM;
+			goto err;
+		}
+		lr->function = name;
+	} else if (strchr(name, '.'))
 		lr->file = name;
 	else
 		lr->function = name;
@@ -1784,9 +1832,12 @@ int add_perf_probe_events(struct perf_probe_event *pevs, int npevs,
 	}
 
 	/* Loop 2: add all events */
-	for (i = 0; i < npevs && ret >= 0; i++)
+	for (i = 0; i < npevs; i++) {
 		ret = __add_probe_trace_events(pkgs[i].pev, pkgs[i].tevs,
 						pkgs[i].ntevs, force_add);
+		if (ret < 0)
+			break;
+	}
 end:
 	/* Loop 3: cleanup and free trace events  */
 	for (i = 0; i < npevs; i++) {
@@ -1912,4 +1963,46 @@ int del_perf_probe_events(struct strlist *dellist)
 
 	return ret;
 }
+/* TODO: don't use a global variable for filter ... */
+static struct strfilter *available_func_filter;
+
+/*
+ * If a symbol corresponds to a function with global binding and
+ * matches filter return 0. For all others return 1.
+ */
+static int filter_available_functions(struct map *map __unused,
+				      struct symbol *sym)
+{
+	if (sym->binding == STB_GLOBAL &&
+	    strfilter__compare(available_func_filter, sym->name))
+		return 0;
+	return 1;
+}
+
+int show_available_funcs(const char *module, struct strfilter *_filter)
+{
+	struct map *map;
+	int ret;
+
+	setup_pager();
+
+	ret = init_vmlinux();
+	if (ret < 0)
+		return ret;
 
+	map = kernel_get_module_map(module);
+	if (!map) {
+		pr_err("Failed to find %s map.\n", (module) ? : "kernel");
+		return -EINVAL;
+	}
+	available_func_filter = _filter;
+	if (map__load(map, filter_available_functions)) {
+		pr_err("Failed to load map.\n");
+		return -EINVAL;
+	}
+	if (!dso__sorted_by_name(map->dso, map->type))
+		dso__sort_by_name(map->dso, map->type);
+
+	dso__fprintf_symbols_by_name(map->dso, map->type, stdout);
+	return 0;
+}
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index 5accbedfea37..3434fc9d79d5 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -3,6 +3,7 @@
 
 #include <stdbool.h>
 #include "strlist.h"
+#include "strfilter.h"
 
 extern bool probe_event_dry_run;
 
@@ -126,7 +127,8 @@ extern int show_perf_probe_events(void);
 extern int show_line_range(struct line_range *lr, const char *module);
 extern int show_available_vars(struct perf_probe_event *pevs, int npevs,
 			       int max_probe_points, const char *module,
-			       bool externs);
+			       struct strfilter *filter, bool externs);
+extern int show_available_funcs(const char *module, struct strfilter *filter);
 
 
 /* Maximum index number of event-name postfix */
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index ab83b6ac5d65..194f9e2a3285 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -33,6 +33,7 @@
 #include <ctype.h>
 #include <dwarf-regs.h>
 
+#include <linux/bitops.h>
 #include "event.h"
 #include "debug.h"
 #include "util.h"
@@ -280,6 +281,19 @@ static bool die_compare_name(Dwarf_Die *dw_die, const char *tname)
 	return name ? (strcmp(tname, name) == 0) : false;
 }
 
+/* Get callsite line number of inline-function instance */
+static int die_get_call_lineno(Dwarf_Die *in_die)
+{
+	Dwarf_Attribute attr;
+	Dwarf_Word ret;
+
+	if (!dwarf_attr(in_die, DW_AT_call_line, &attr))
+		return -ENOENT;
+
+	dwarf_formudata(&attr, &ret);
+	return (int)ret;
+}
+
 /* Get type die */
 static Dwarf_Die *die_get_type(Dwarf_Die *vr_die, Dwarf_Die *die_mem)
 {
@@ -320,13 +334,23 @@ static Dwarf_Die *die_get_real_type(Dwarf_Die *vr_die, Dwarf_Die *die_mem)
 	return vr_die;
 }
 
-static bool die_is_signed_type(Dwarf_Die *tp_die)
+static int die_get_attr_udata(Dwarf_Die *tp_die, unsigned int attr_name,
+			      Dwarf_Word *result)
 {
 	Dwarf_Attribute attr;
+
+	if (dwarf_attr(tp_die, attr_name, &attr) == NULL ||
+	    dwarf_formudata(&attr, result) != 0)
+		return -ENOENT;
+
+	return 0;
+}
+
+static bool die_is_signed_type(Dwarf_Die *tp_die)
+{
 	Dwarf_Word ret;
 
-	if (dwarf_attr(tp_die, DW_AT_encoding, &attr) == NULL ||
-	    dwarf_formudata(&attr, &ret) != 0)
+	if (die_get_attr_udata(tp_die, DW_AT_encoding, &ret))
 		return false;
 
 	return (ret == DW_ATE_signed_char || ret == DW_ATE_signed ||
@@ -335,11 +359,29 @@ static bool die_is_signed_type(Dwarf_Die *tp_die)
 
 static int die_get_byte_size(Dwarf_Die *tp_die)
 {
-	Dwarf_Attribute attr;
 	Dwarf_Word ret;
 
-	if (dwarf_attr(tp_die, DW_AT_byte_size, &attr) == NULL ||
-	    dwarf_formudata(&attr, &ret) != 0)
+	if (die_get_attr_udata(tp_die, DW_AT_byte_size, &ret))
+		return 0;
+
+	return (int)ret;
+}
+
+static int die_get_bit_size(Dwarf_Die *tp_die)
+{
+	Dwarf_Word ret;
+
+	if (die_get_attr_udata(tp_die, DW_AT_bit_size, &ret))
+		return 0;
+
+	return (int)ret;
+}
+
+static int die_get_bit_offset(Dwarf_Die *tp_die)
+{
+	Dwarf_Word ret;
+
+	if (die_get_attr_udata(tp_die, DW_AT_bit_offset, &ret))
 		return 0;
 
 	return (int)ret;
@@ -458,6 +500,151 @@ static Dwarf_Die *die_find_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
 	return die_find_child(sp_die, __die_find_inline_cb, &addr, die_mem);
 }
 
+/* Walker on lines (Note: line number will not be sorted) */
+typedef int (* line_walk_handler_t) (const char *fname, int lineno,
+				     Dwarf_Addr addr, void *data);
+
+struct __line_walk_param {
+	const char *fname;
+	line_walk_handler_t handler;
+	void *data;
+	int retval;
+};
+
+static int __die_walk_funclines_cb(Dwarf_Die *in_die, void *data)
+{
+	struct __line_walk_param *lw = data;
+	Dwarf_Addr addr;
+	int lineno;
+
+	if (dwarf_tag(in_die) == DW_TAG_inlined_subroutine) {
+		lineno = die_get_call_lineno(in_die);
+		if (lineno > 0 && dwarf_entrypc(in_die, &addr) == 0) {
+			lw->retval = lw->handler(lw->fname, lineno, addr,
+						 lw->data);
+			if (lw->retval != 0)
+				return DIE_FIND_CB_FOUND;
+		}
+	}
+	return DIE_FIND_CB_SIBLING;
+}
+
+/* Walk on lines of blocks included in given DIE */
+static int __die_walk_funclines(Dwarf_Die *sp_die,
+				line_walk_handler_t handler, void *data)
+{
+	struct __line_walk_param lw = {
+		.handler = handler,
+		.data = data,
+		.retval = 0,
+	};
+	Dwarf_Die die_mem;
+	Dwarf_Addr addr;
+	int lineno;
+
+	/* Handle function declaration line */
+	lw.fname = dwarf_decl_file(sp_die);
+	if (lw.fname && dwarf_decl_line(sp_die, &lineno) == 0 &&
+	    dwarf_entrypc(sp_die, &addr) == 0) {
+		lw.retval = handler(lw.fname, lineno, addr, data);
+		if (lw.retval != 0)
+			goto done;
+	}
+	die_find_child(sp_die, __die_walk_funclines_cb, &lw, &die_mem);
+done:
+	return lw.retval;
+}
+
+static int __die_walk_culines_cb(Dwarf_Die *sp_die, void *data)
+{
+	struct __line_walk_param *lw = data;
+
+	lw->retval = __die_walk_funclines(sp_die, lw->handler, lw->data);
+	if (lw->retval != 0)
+		return DWARF_CB_ABORT;
+
+	return DWARF_CB_OK;
+}
+
+/*
+ * Walk on lines inside given PDIE. If the PDIE is subprogram, walk only on
+ * the lines inside the subprogram, otherwise PDIE must be a CU DIE.
+ */
+static int die_walk_lines(Dwarf_Die *pdie, line_walk_handler_t handler,
+			  void *data)
+{
+	Dwarf_Lines *lines;
+	Dwarf_Line *line;
+	Dwarf_Addr addr;
+	const char *fname;
+	int lineno, ret = 0;
+	Dwarf_Die die_mem, *cu_die;
+	size_t nlines, i;
+
+	/* Get the CU die */
+	if (dwarf_tag(pdie) == DW_TAG_subprogram)
+		cu_die = dwarf_diecu(pdie, &die_mem, NULL, NULL);
+	else
+		cu_die = pdie;
+	if (!cu_die) {
+		pr_debug2("Failed to get CU from subprogram\n");
+		return -EINVAL;
+	}
+
+	/* Get lines list in the CU */
+	if (dwarf_getsrclines(cu_die, &lines, &nlines) != 0) {
+		pr_debug2("Failed to get source lines on this CU.\n");
+		return -ENOENT;
+	}
+	pr_debug2("Get %zd lines from this CU\n", nlines);
+
+	/* Walk on the lines on lines list */
+	for (i = 0; i < nlines; i++) {
+		line = dwarf_onesrcline(lines, i);
+		if (line == NULL ||
+		    dwarf_lineno(line, &lineno) != 0 ||
+		    dwarf_lineaddr(line, &addr) != 0) {
+			pr_debug2("Failed to get line info. "
+				  "Possible error in debuginfo.\n");
+			continue;
+		}
+		/* Filter lines based on address */
+		if (pdie != cu_die)
+			/*
+			 * Address filtering
+			 * The line is included in given function, and
+			 * no inline block includes it.
+			 */
+			if (!dwarf_haspc(pdie, addr) ||
+			    die_find_inlinefunc(pdie, addr, &die_mem))
+				continue;
+		/* Get source line */
+		fname = dwarf_linesrc(line, NULL, NULL);
+
+		ret = handler(fname, lineno, addr, data);
+		if (ret != 0)
+			return ret;
+	}
+
+	/*
+	 * Dwarf lines doesn't include function declarations and inlined
+	 * subroutines. We have to check functions list or given function.
+	 */
+	if (pdie != cu_die)
+		ret = __die_walk_funclines(pdie, handler, data);
+	else {
+		struct __line_walk_param param = {
+			.handler = handler,
+			.data = data,
+			.retval = 0,
+		};
+		dwarf_getfuncs(cu_die, __die_walk_culines_cb, &param, 0);
+		ret = param.retval;
+	}
+
+	return ret;
+}
+
 struct __find_variable_param {
 	const char *name;
 	Dwarf_Addr addr;
@@ -669,6 +856,8 @@ static_var:
 	return 0;
 }
 
+#define BYTES_TO_BITS(nb)	((nb) * BITS_PER_LONG / sizeof(long))
+
 static int convert_variable_type(Dwarf_Die *vr_die,
 				 struct probe_trace_arg *tvar,
 				 const char *cast)
@@ -685,6 +874,14 @@ static int convert_variable_type(Dwarf_Die *vr_die,
 		return (tvar->type == NULL) ? -ENOMEM : 0;
 	}
 
+	if (die_get_bit_size(vr_die) != 0) {
+		/* This is a bitfield */
+		ret = snprintf(buf, 16, "b%d@%d/%zd", die_get_bit_size(vr_die),
+				die_get_bit_offset(vr_die),
+				BYTES_TO_BITS(die_get_byte_size(vr_die)));
+		goto formatted;
+	}
+
 	if (die_get_real_type(vr_die, &type) == NULL) {
 		pr_warning("Failed to get a type information of %s.\n",
 			   dwarf_diename(vr_die));
@@ -729,29 +926,31 @@ static int convert_variable_type(Dwarf_Die *vr_die,
 		return (tvar->type == NULL) ? -ENOMEM : 0;
 	}
 
-	ret = die_get_byte_size(&type) * 8;
-	if (ret) {
-		/* Check the bitwidth */
-		if (ret > MAX_BASIC_TYPE_BITS) {
-			pr_info("%s exceeds max-bitwidth."
-				" Cut down to %d bits.\n",
-				dwarf_diename(&type), MAX_BASIC_TYPE_BITS);
-			ret = MAX_BASIC_TYPE_BITS;
-		}
+	ret = BYTES_TO_BITS(die_get_byte_size(&type));
+	if (!ret)
+		/* No size ... try to use default type */
+		return 0;
 
-		ret = snprintf(buf, 16, "%c%d",
-			       die_is_signed_type(&type) ? 's' : 'u', ret);
-		if (ret < 0 || ret >= 16) {
-			if (ret >= 16)
-				ret = -E2BIG;
-			pr_warning("Failed to convert variable type: %s\n",
-				   strerror(-ret));
-			return ret;
-		}
-		tvar->type = strdup(buf);
-		if (tvar->type == NULL)
-			return -ENOMEM;
+	/* Check the bitwidth */
+	if (ret > MAX_BASIC_TYPE_BITS) {
+		pr_info("%s exceeds max-bitwidth. Cut down to %d bits.\n",
+			dwarf_diename(&type), MAX_BASIC_TYPE_BITS);
+		ret = MAX_BASIC_TYPE_BITS;
+	}
+	ret = snprintf(buf, 16, "%c%d",
+		       die_is_signed_type(&type) ? 's' : 'u', ret);
+
+formatted:
+	if (ret < 0 || ret >= 16) {
+		if (ret >= 16)
+			ret = -E2BIG;
+		pr_warning("Failed to convert variable type: %s\n",
+			   strerror(-ret));
+		return ret;
 	}
+	tvar->type = strdup(buf);
+	if (tvar->type == NULL)
+		return -ENOMEM;
 	return 0;
 }
 
@@ -1050,157 +1249,102 @@ static int call_probe_finder(Dwarf_Die *sp_die, struct probe_finder *pf)
 	return ret;
 }
 
-/* Find probe point from its line number */
-static int find_probe_point_by_line(struct probe_finder *pf)
+static int probe_point_line_walker(const char *fname, int lineno,
+				   Dwarf_Addr addr, void *data)
 {
-	Dwarf_Lines *lines;
-	Dwarf_Line *line;
-	size_t nlines, i;
-	Dwarf_Addr addr;
-	int lineno;
-	int ret = 0;
-
-	if (dwarf_getsrclines(&pf->cu_die, &lines, &nlines) != 0) {
-		pr_warning("No source lines found.\n");
-		return -ENOENT;
-	}
+	struct probe_finder *pf = data;
+	int ret;
 
-	for (i = 0; i < nlines && ret == 0; i++) {
-		line = dwarf_onesrcline(lines, i);
-		if (dwarf_lineno(line, &lineno) != 0 ||
-		    lineno != pf->lno)
-			continue;
+	if (lineno != pf->lno || strtailcmp(fname, pf->fname) != 0)
+		return 0;
 
-		/* TODO: Get fileno from line, but how? */
-		if (strtailcmp(dwarf_linesrc(line, NULL, NULL), pf->fname) != 0)
-			continue;
+	pf->addr = addr;
+	ret = call_probe_finder(NULL, pf);
 
-		if (dwarf_lineaddr(line, &addr) != 0) {
-			pr_warning("Failed to get the address of the line.\n");
-			return -ENOENT;
-		}
-		pr_debug("Probe line found: line[%d]:%d addr:0x%jx\n",
-			 (int)i, lineno, (uintmax_t)addr);
-		pf->addr = addr;
+	/* Continue if no error, because the line will be in inline function */
+	return ret < 0 ? ret : 0;
+}
 
-		ret = call_probe_finder(NULL, pf);
-		/* Continuing, because target line might be inlined. */
-	}
-	return ret;
+/* Find probe point from its line number */
+static int find_probe_point_by_line(struct probe_finder *pf)
+{
+	return die_walk_lines(&pf->cu_die, probe_point_line_walker, pf);
 }
 
 /* Find lines which match lazy pattern */
 static int find_lazy_match_lines(struct list_head *head,
 				 const char *fname, const char *pat)
 {
-	char *fbuf, *p1, *p2;
-	int fd, line, nlines = -1;
-	struct stat st;
-
-	fd = open(fname, O_RDONLY);
-	if (fd < 0) {
-		pr_warning("Failed to open %s: %s\n", fname, strerror(-fd));
+	FILE *fp;
+	char *line = NULL;
+	size_t line_len;
+	ssize_t len;
+	int count = 0, linenum = 1;
+
+	fp = fopen(fname, "r");
+	if (!fp) {
+		pr_warning("Failed to open %s: %s\n", fname, strerror(errno));
 		return -errno;
 	}
 
-	if (fstat(fd, &st) < 0) {
-		pr_warning("Failed to get the size of %s: %s\n",
-			   fname, strerror(errno));
-		nlines = -errno;
-		goto out_close;
-	}
-
-	nlines = -ENOMEM;
-	fbuf = malloc(st.st_size + 2);
-	if (fbuf == NULL)
-		goto out_close;
-	if (read(fd, fbuf, st.st_size) < 0) {
-		pr_warning("Failed to read %s: %s\n", fname, strerror(errno));
-		nlines = -errno;
-		goto out_free_fbuf;
-	}
-	fbuf[st.st_size] = '\n';	/* Dummy line */
-	fbuf[st.st_size + 1] = '\0';
-	p1 = fbuf;
-	line = 1;
-	nlines = 0;
-	while ((p2 = strchr(p1, '\n')) != NULL) {
-		*p2 = '\0';
-		if (strlazymatch(p1, pat)) {
-			line_list__add_line(head, line);
-			nlines++;
+	while ((len = getline(&line, &line_len, fp)) > 0) {
+
+		if (line[len - 1] == '\n')
+			line[len - 1] = '\0';
+
+		if (strlazymatch(line, pat)) {
+			line_list__add_line(head, linenum);
+			count++;
 		}
-		line++;
-		p1 = p2 + 1;
+		linenum++;
 	}
-out_free_fbuf:
-	free(fbuf);
-out_close:
-	close(fd);
-	return nlines;
+
+	if (ferror(fp))
+		count = -errno;
+	free(line);
+	fclose(fp);
+
+	if (count == 0)
+		pr_debug("No matched lines found in %s.\n", fname);
+	return count;
+}
+
+static int probe_point_lazy_walker(const char *fname, int lineno,
+				   Dwarf_Addr addr, void *data)
+{
+	struct probe_finder *pf = data;
+	int ret;
+
+	if (!line_list__has_line(&pf->lcache, lineno) ||
+	    strtailcmp(fname, pf->fname) != 0)
+		return 0;
+
+	pr_debug("Probe line found: line:%d addr:0x%llx\n",
+		 lineno, (unsigned long long)addr);
+	pf->addr = addr;
+	ret = call_probe_finder(NULL, pf);
+
+	/*
+	 * Continue if no error, because the lazy pattern will match
+	 * to other lines
+	 */
+	return ret < 0 ? ret : 0;
 }
 
 /* Find probe points from lazy pattern  */
 static int find_probe_point_lazy(Dwarf_Die *sp_die, struct probe_finder *pf)
 {
-	Dwarf_Lines *lines;
-	Dwarf_Line *line;
-	size_t nlines, i;
-	Dwarf_Addr addr;
-	Dwarf_Die die_mem;
-	int lineno;
 	int ret = 0;
 
 	if (list_empty(&pf->lcache)) {
 		/* Matching lazy line pattern */
 		ret = find_lazy_match_lines(&pf->lcache, pf->fname,
 					    pf->pev->point.lazy_line);
-		if (ret == 0) {
-			pr_debug("No matched lines found in %s.\n", pf->fname);
-			return 0;
-		} else if (ret < 0)
+		if (ret <= 0)
 			return ret;
 	}
 
-	if (dwarf_getsrclines(&pf->cu_die, &lines, &nlines) != 0) {
-		pr_warning("No source lines found.\n");
-		return -ENOENT;
-	}
-
-	for (i = 0; i < nlines && ret >= 0; i++) {
-		line = dwarf_onesrcline(lines, i);
-
-		if (dwarf_lineno(line, &lineno) != 0 ||
-		    !line_list__has_line(&pf->lcache, lineno))
-			continue;
-
-		/* TODO: Get fileno from line, but how? */
-		if (strtailcmp(dwarf_linesrc(line, NULL, NULL), pf->fname) != 0)
-			continue;
-
-		if (dwarf_lineaddr(line, &addr) != 0) {
-			pr_debug("Failed to get the address of line %d.\n",
-				 lineno);
-			continue;
-		}
-		if (sp_die) {
-			/* Address filtering 1: does sp_die include addr? */
-			if (!dwarf_haspc(sp_die, addr))
-				continue;
-			/* Address filtering 2: No child include addr? */
-			if (die_find_inlinefunc(sp_die, addr, &die_mem))
-				continue;
-		}
-
-		pr_debug("Probe line found: line[%d]:%d addr:0x%llx\n",
-			 (int)i, lineno, (unsigned long long)addr);
-		pf->addr = addr;
-
-		ret = call_probe_finder(sp_die, pf);
-		/* Continuing, because target line might be inlined. */
-	}
-	/* TODO: deallocate lines, but how? */
-	return ret;
+	return die_walk_lines(sp_die, probe_point_lazy_walker, pf);
 }
 
 /* Callback parameter with return value */
@@ -1318,8 +1462,7 @@ static int find_probes(int fd, struct probe_finder *pf)
 	off = 0;
 	line_list__init(&pf->lcache);
 	/* Loop on CUs (Compilation Unit) */
-	while (!dwarf_nextcu(dbg, off, &noff, &cuhl, NULL, NULL, NULL) &&
-	       ret >= 0) {
+	while (!dwarf_nextcu(dbg, off, &noff, &cuhl, NULL, NULL, NULL)) {
 		/* Get the DIE(Debugging Information Entry) of this CU */
 		diep = dwarf_offdie(dbg, off + cuhl, &pf->cu_die);
 		if (!diep)
@@ -1340,6 +1483,8 @@ static int find_probes(int fd, struct probe_finder *pf)
 				pf->lno = pp->line;
 				ret = find_probe_point_by_line(pf);
 			}
+			if (ret < 0)
+				break;
 		}
 		off = noff;
 	}
@@ -1644,91 +1789,28 @@ static int line_range_add_line(const char *src, unsigned int lineno,
 	return line_list__add_line(&lr->line_list, lineno);
 }
 
-/* Search function declaration lines */
-static int line_range_funcdecl_cb(Dwarf_Die *sp_die, void *data)
+static int line_range_walk_cb(const char *fname, int lineno,
+			      Dwarf_Addr addr __used,
+			      void *data)
 {
-	struct dwarf_callback_param *param = data;
-	struct line_finder *lf = param->data;
-	const char *src;
-	int lineno;
+	struct line_finder *lf = data;
 
-	src = dwarf_decl_file(sp_die);
-	if (src && strtailcmp(src, lf->fname) != 0)
-		return DWARF_CB_OK;
-
-	if (dwarf_decl_line(sp_die, &lineno) != 0 ||
+	if ((strtailcmp(fname, lf->fname) != 0) ||
 	    (lf->lno_s > lineno || lf->lno_e < lineno))
-		return DWARF_CB_OK;
+		return 0;
 
-	param->retval = line_range_add_line(src, lineno, lf->lr);
-	if (param->retval < 0)
-		return DWARF_CB_ABORT;
-	return DWARF_CB_OK;
-}
+	if (line_range_add_line(fname, lineno, lf->lr) < 0)
+		return -EINVAL;
 
-static int find_line_range_func_decl_lines(struct line_finder *lf)
-{
-	struct dwarf_callback_param param = {.data = (void *)lf, .retval = 0};
-	dwarf_getfuncs(&lf->cu_die, line_range_funcdecl_cb, &param, 0);
-	return param.retval;
+	return 0;
 }
 
 /* Find line range from its line number */
 static int find_line_range_by_line(Dwarf_Die *sp_die, struct line_finder *lf)
 {
-	Dwarf_Lines *lines;
-	Dwarf_Line *line;
-	size_t nlines, i;
-	Dwarf_Addr addr;
-	int lineno, ret = 0;
-	const char *src;
-	Dwarf_Die die_mem;
-
-	line_list__init(&lf->lr->line_list);
-	if (dwarf_getsrclines(&lf->cu_die, &lines, &nlines) != 0) {
-		pr_warning("No source lines found.\n");
-		return -ENOENT;
-	}
-
-	/* Search probable lines on lines list */
-	for (i = 0; i < nlines; i++) {
-		line = dwarf_onesrcline(lines, i);
-		if (dwarf_lineno(line, &lineno) != 0 ||
-		    (lf->lno_s > lineno || lf->lno_e < lineno))
-			continue;
-
-		if (sp_die) {
-			/* Address filtering 1: does sp_die include addr? */
-			if (dwarf_lineaddr(line, &addr) != 0 ||
-			    !dwarf_haspc(sp_die, addr))
-				continue;
-
-			/* Address filtering 2: No child include addr? */
-			if (die_find_inlinefunc(sp_die, addr, &die_mem))
-				continue;
-		}
-
-		/* TODO: Get fileno from line, but how? */
-		src = dwarf_linesrc(line, NULL, NULL);
-		if (strtailcmp(src, lf->fname) != 0)
-			continue;
-
-		ret = line_range_add_line(src, lineno, lf->lr);
-		if (ret < 0)
-			return ret;
-	}
+	int ret;
 
-	/*
-	 * Dwarf lines doesn't include function declarations. We have to
-	 * check functions list or given function.
-	 */
-	if (sp_die) {
-		src = dwarf_decl_file(sp_die);
-		if (src && dwarf_decl_line(sp_die, &lineno) == 0 &&
-		    (lf->lno_s <= lineno && lf->lno_e >= lineno))
-			ret = line_range_add_line(src, lineno, lf->lr);
-	} else
-		ret = find_line_range_func_decl_lines(lf);
+	ret = die_walk_lines(sp_die ?: &lf->cu_die, line_range_walk_cb, lf);
 
 	/* Update status */
 	if (ret >= 0)
@@ -1758,9 +1840,6 @@ static int line_range_search_cb(Dwarf_Die *sp_die, void *data)
 	struct line_finder *lf = param->data;
 	struct line_range *lr = lf->lr;
 
-	pr_debug("find (%llx) %s\n",
-		 (unsigned long long)dwarf_dieoffset(sp_die),
-		 dwarf_diename(sp_die));
 	if (dwarf_tag(sp_die) == DW_TAG_subprogram &&
 	    die_compare_name(sp_die, lr->function)) {
 		lf->fname = dwarf_decl_file(sp_die);
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
new file mode 100644
index 000000000000..a9f2d7e1204d
--- /dev/null
+++ b/tools/perf/util/python.c
@@ -0,0 +1,896 @@
+#include <Python.h>
+#include <structmember.h>
+#include <inttypes.h>
+#include <poll.h>
+#include "evlist.h"
+#include "evsel.h"
+#include "event.h"
+#include "cpumap.h"
+#include "thread_map.h"
+
+/* Define PyVarObject_HEAD_INIT for python 2.5 */
+#ifndef PyVarObject_HEAD_INIT
+# define PyVarObject_HEAD_INIT(type, size) PyObject_HEAD_INIT(type) size,
+#endif
+
+struct throttle_event {
+	struct perf_event_header header;
+	u64			 time;
+	u64			 id;
+	u64			 stream_id;
+};
+
+PyMODINIT_FUNC initperf(void);
+
+#define member_def(type, member, ptype, help) \
+	{ #member, ptype, \
+	  offsetof(struct pyrf_event, event) + offsetof(struct type, member), \
+	  0, help }
+
+#define sample_member_def(name, member, ptype, help) \
+	{ #name, ptype, \
+	  offsetof(struct pyrf_event, sample) + offsetof(struct perf_sample, member), \
+	  0, help }
+
+struct pyrf_event {
+	PyObject_HEAD
+	struct perf_sample sample;
+	union perf_event   event;
+};
+
+#define sample_members \
+	sample_member_def(sample_ip, ip, T_ULONGLONG, "event type"),			 \
+	sample_member_def(sample_pid, pid, T_INT, "event pid"),			 \
+	sample_member_def(sample_tid, tid, T_INT, "event tid"),			 \
+	sample_member_def(sample_time, time, T_ULONGLONG, "event timestamp"),		 \
+	sample_member_def(sample_addr, addr, T_ULONGLONG, "event addr"),		 \
+	sample_member_def(sample_id, id, T_ULONGLONG, "event id"),			 \
+	sample_member_def(sample_stream_id, stream_id, T_ULONGLONG, "event stream id"), \
+	sample_member_def(sample_period, period, T_ULONGLONG, "event period"),		 \
+	sample_member_def(sample_cpu, cpu, T_UINT, "event cpu"),
+
+static char pyrf_mmap_event__doc[] = PyDoc_STR("perf mmap event object.");
+
+static PyMemberDef pyrf_mmap_event__members[] = {
+	sample_members
+	member_def(perf_event_header, type, T_UINT, "event type"),
+	member_def(mmap_event, pid, T_UINT, "event pid"),
+	member_def(mmap_event, tid, T_UINT, "event tid"),
+	member_def(mmap_event, start, T_ULONGLONG, "start of the map"),
+	member_def(mmap_event, len, T_ULONGLONG, "map length"),
+	member_def(mmap_event, pgoff, T_ULONGLONG, "page offset"),
+	member_def(mmap_event, filename, T_STRING_INPLACE, "backing store"),
+	{ .name = NULL, },
+};
+
+static PyObject *pyrf_mmap_event__repr(struct pyrf_event *pevent)
+{
+	PyObject *ret;
+	char *s;
+
+	if (asprintf(&s, "{ type: mmap, pid: %u, tid: %u, start: %#" PRIx64 ", "
+			 "length: %#" PRIx64 ", offset: %#" PRIx64 ", "
+			 "filename: %s }",
+		     pevent->event.mmap.pid, pevent->event.mmap.tid,
+		     pevent->event.mmap.start, pevent->event.mmap.len,
+		     pevent->event.mmap.pgoff, pevent->event.mmap.filename) < 0) {
+		ret = PyErr_NoMemory();
+	} else {
+		ret = PyString_FromString(s);
+		free(s);
+	}
+	return ret;
+}
+
+static PyTypeObject pyrf_mmap_event__type = {
+	PyVarObject_HEAD_INIT(NULL, 0)
+	.tp_name	= "perf.mmap_event",
+	.tp_basicsize	= sizeof(struct pyrf_event),
+	.tp_flags	= Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+	.tp_doc		= pyrf_mmap_event__doc,
+	.tp_members	= pyrf_mmap_event__members,
+	.tp_repr	= (reprfunc)pyrf_mmap_event__repr,
+};
+
+static char pyrf_task_event__doc[] = PyDoc_STR("perf task (fork/exit) event object.");
+
+static PyMemberDef pyrf_task_event__members[] = {
+	sample_members
+	member_def(perf_event_header, type, T_UINT, "event type"),
+	member_def(fork_event, pid, T_UINT, "event pid"),
+	member_def(fork_event, ppid, T_UINT, "event ppid"),
+	member_def(fork_event, tid, T_UINT, "event tid"),
+	member_def(fork_event, ptid, T_UINT, "event ptid"),
+	member_def(fork_event, time, T_ULONGLONG, "timestamp"),
+	{ .name = NULL, },
+};
+
+static PyObject *pyrf_task_event__repr(struct pyrf_event *pevent)
+{
+	return PyString_FromFormat("{ type: %s, pid: %u, ppid: %u, tid: %u, "
+				   "ptid: %u, time: %" PRIu64 "}",
+				   pevent->event.header.type == PERF_RECORD_FORK ? "fork" : "exit",
+				   pevent->event.fork.pid,
+				   pevent->event.fork.ppid,
+				   pevent->event.fork.tid,
+				   pevent->event.fork.ptid,
+				   pevent->event.fork.time);
+}
+
+static PyTypeObject pyrf_task_event__type = {
+	PyVarObject_HEAD_INIT(NULL, 0)
+	.tp_name	= "perf.task_event",
+	.tp_basicsize	= sizeof(struct pyrf_event),
+	.tp_flags	= Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+	.tp_doc		= pyrf_task_event__doc,
+	.tp_members	= pyrf_task_event__members,
+	.tp_repr	= (reprfunc)pyrf_task_event__repr,
+};
+
+static char pyrf_comm_event__doc[] = PyDoc_STR("perf comm event object.");
+
+static PyMemberDef pyrf_comm_event__members[] = {
+	sample_members
+	member_def(perf_event_header, type, T_UINT, "event type"),
+	member_def(comm_event, pid, T_UINT, "event pid"),
+	member_def(comm_event, tid, T_UINT, "event tid"),
+	member_def(comm_event, comm, T_STRING_INPLACE, "process name"),
+	{ .name = NULL, },
+};
+
+static PyObject *pyrf_comm_event__repr(struct pyrf_event *pevent)
+{
+	return PyString_FromFormat("{ type: comm, pid: %u, tid: %u, comm: %s }",
+				   pevent->event.comm.pid,
+				   pevent->event.comm.tid,
+				   pevent->event.comm.comm);
+}
+
+static PyTypeObject pyrf_comm_event__type = {
+	PyVarObject_HEAD_INIT(NULL, 0)
+	.tp_name	= "perf.comm_event",
+	.tp_basicsize	= sizeof(struct pyrf_event),
+	.tp_flags	= Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+	.tp_doc		= pyrf_comm_event__doc,
+	.tp_members	= pyrf_comm_event__members,
+	.tp_repr	= (reprfunc)pyrf_comm_event__repr,
+};
+
+static char pyrf_throttle_event__doc[] = PyDoc_STR("perf throttle event object.");
+
+static PyMemberDef pyrf_throttle_event__members[] = {
+	sample_members
+	member_def(perf_event_header, type, T_UINT, "event type"),
+	member_def(throttle_event, time, T_ULONGLONG, "timestamp"),
+	member_def(throttle_event, id, T_ULONGLONG, "event id"),
+	member_def(throttle_event, stream_id, T_ULONGLONG, "event stream id"),
+	{ .name = NULL, },
+};
+
+static PyObject *pyrf_throttle_event__repr(struct pyrf_event *pevent)
+{
+	struct throttle_event *te = (struct throttle_event *)(&pevent->event.header + 1);
+
+	return PyString_FromFormat("{ type: %sthrottle, time: %" PRIu64 ", id: %" PRIu64
+				   ", stream_id: %" PRIu64 " }",
+				   pevent->event.header.type == PERF_RECORD_THROTTLE ? "" : "un",
+				   te->time, te->id, te->stream_id);
+}
+
+static PyTypeObject pyrf_throttle_event__type = {
+	PyVarObject_HEAD_INIT(NULL, 0)
+	.tp_name	= "perf.throttle_event",
+	.tp_basicsize	= sizeof(struct pyrf_event),
+	.tp_flags	= Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+	.tp_doc		= pyrf_throttle_event__doc,
+	.tp_members	= pyrf_throttle_event__members,
+	.tp_repr	= (reprfunc)pyrf_throttle_event__repr,
+};
+
+static int pyrf_event__setup_types(void)
+{
+	int err;
+	pyrf_mmap_event__type.tp_new =
+	pyrf_task_event__type.tp_new =
+	pyrf_comm_event__type.tp_new =
+	pyrf_throttle_event__type.tp_new = PyType_GenericNew;
+	err = PyType_Ready(&pyrf_mmap_event__type);
+	if (err < 0)
+		goto out;
+	err = PyType_Ready(&pyrf_task_event__type);
+	if (err < 0)
+		goto out;
+	err = PyType_Ready(&pyrf_comm_event__type);
+	if (err < 0)
+		goto out;
+	err = PyType_Ready(&pyrf_throttle_event__type);
+	if (err < 0)
+		goto out;
+out:
+	return err;
+}
+
+static PyTypeObject *pyrf_event__type[] = {
+	[PERF_RECORD_MMAP]	 = &pyrf_mmap_event__type,
+	[PERF_RECORD_LOST]	 = &pyrf_mmap_event__type,
+	[PERF_RECORD_COMM]	 = &pyrf_comm_event__type,
+	[PERF_RECORD_EXIT]	 = &pyrf_task_event__type,
+	[PERF_RECORD_THROTTLE]	 = &pyrf_throttle_event__type,
+	[PERF_RECORD_UNTHROTTLE] = &pyrf_throttle_event__type,
+	[PERF_RECORD_FORK]	 = &pyrf_task_event__type,
+	[PERF_RECORD_READ]	 = &pyrf_mmap_event__type,
+	[PERF_RECORD_SAMPLE]	 = &pyrf_mmap_event__type,
+};
+
+static PyObject *pyrf_event__new(union perf_event *event)
+{
+	struct pyrf_event *pevent;
+	PyTypeObject *ptype;
+
+	if (event->header.type < PERF_RECORD_MMAP ||
+	    event->header.type > PERF_RECORD_SAMPLE)
+		return NULL;
+
+	ptype = pyrf_event__type[event->header.type];
+	pevent = PyObject_New(struct pyrf_event, ptype);
+	if (pevent != NULL)
+		memcpy(&pevent->event, event, event->header.size);
+	return (PyObject *)pevent;
+}
+
+struct pyrf_cpu_map {
+	PyObject_HEAD
+
+	struct cpu_map *cpus;
+};
+
+static int pyrf_cpu_map__init(struct pyrf_cpu_map *pcpus,
+			      PyObject *args, PyObject *kwargs)
+{
+	static char *kwlist[] = { "cpustr", NULL, NULL, };
+	char *cpustr = NULL;
+
+	if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|s",
+					 kwlist, &cpustr))
+		return -1;
+
+	pcpus->cpus = cpu_map__new(cpustr);
+	if (pcpus->cpus == NULL)
+		return -1;
+	return 0;
+}
+
+static void pyrf_cpu_map__delete(struct pyrf_cpu_map *pcpus)
+{
+	cpu_map__delete(pcpus->cpus);
+	pcpus->ob_type->tp_free((PyObject*)pcpus);
+}
+
+static Py_ssize_t pyrf_cpu_map__length(PyObject *obj)
+{
+	struct pyrf_cpu_map *pcpus = (void *)obj;
+
+	return pcpus->cpus->nr;
+}
+
+static PyObject *pyrf_cpu_map__item(PyObject *obj, Py_ssize_t i)
+{
+	struct pyrf_cpu_map *pcpus = (void *)obj;
+
+	if (i >= pcpus->cpus->nr)
+		return NULL;
+
+	return Py_BuildValue("i", pcpus->cpus->map[i]);
+}
+
+static PySequenceMethods pyrf_cpu_map__sequence_methods = {
+	.sq_length = pyrf_cpu_map__length,
+	.sq_item   = pyrf_cpu_map__item,
+};
+
+static char pyrf_cpu_map__doc[] = PyDoc_STR("cpu map object.");
+
+static PyTypeObject pyrf_cpu_map__type = {
+	PyVarObject_HEAD_INIT(NULL, 0)
+	.tp_name	= "perf.cpu_map",
+	.tp_basicsize	= sizeof(struct pyrf_cpu_map),
+	.tp_dealloc	= (destructor)pyrf_cpu_map__delete,
+	.tp_flags	= Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+	.tp_doc		= pyrf_cpu_map__doc,
+	.tp_as_sequence	= &pyrf_cpu_map__sequence_methods,
+	.tp_init	= (initproc)pyrf_cpu_map__init,
+};
+
+static int pyrf_cpu_map__setup_types(void)
+{
+	pyrf_cpu_map__type.tp_new = PyType_GenericNew;
+	return PyType_Ready(&pyrf_cpu_map__type);
+}
+
+struct pyrf_thread_map {
+	PyObject_HEAD
+
+	struct thread_map *threads;
+};
+
+static int pyrf_thread_map__init(struct pyrf_thread_map *pthreads,
+				 PyObject *args, PyObject *kwargs)
+{
+	static char *kwlist[] = { "pid", "tid", NULL, NULL, };
+	int pid = -1, tid = -1;
+
+	if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|ii",
+					 kwlist, &pid, &tid))
+		return -1;
+
+	pthreads->threads = thread_map__new(pid, tid);
+	if (pthreads->threads == NULL)
+		return -1;
+	return 0;
+}
+
+static void pyrf_thread_map__delete(struct pyrf_thread_map *pthreads)
+{
+	thread_map__delete(pthreads->threads);
+	pthreads->ob_type->tp_free((PyObject*)pthreads);
+}
+
+static Py_ssize_t pyrf_thread_map__length(PyObject *obj)
+{
+	struct pyrf_thread_map *pthreads = (void *)obj;
+
+	return pthreads->threads->nr;
+}
+
+static PyObject *pyrf_thread_map__item(PyObject *obj, Py_ssize_t i)
+{
+	struct pyrf_thread_map *pthreads = (void *)obj;
+
+	if (i >= pthreads->threads->nr)
+		return NULL;
+
+	return Py_BuildValue("i", pthreads->threads->map[i]);
+}
+
+static PySequenceMethods pyrf_thread_map__sequence_methods = {
+	.sq_length = pyrf_thread_map__length,
+	.sq_item   = pyrf_thread_map__item,
+};
+
+static char pyrf_thread_map__doc[] = PyDoc_STR("thread map object.");
+
+static PyTypeObject pyrf_thread_map__type = {
+	PyVarObject_HEAD_INIT(NULL, 0)
+	.tp_name	= "perf.thread_map",
+	.tp_basicsize	= sizeof(struct pyrf_thread_map),
+	.tp_dealloc	= (destructor)pyrf_thread_map__delete,
+	.tp_flags	= Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+	.tp_doc		= pyrf_thread_map__doc,
+	.tp_as_sequence	= &pyrf_thread_map__sequence_methods,
+	.tp_init	= (initproc)pyrf_thread_map__init,
+};
+
+static int pyrf_thread_map__setup_types(void)
+{
+	pyrf_thread_map__type.tp_new = PyType_GenericNew;
+	return PyType_Ready(&pyrf_thread_map__type);
+}
+
+struct pyrf_evsel {
+	PyObject_HEAD
+
+	struct perf_evsel evsel;
+};
+
+static int pyrf_evsel__init(struct pyrf_evsel *pevsel,
+			    PyObject *args, PyObject *kwargs)
+{
+	struct perf_event_attr attr = {
+		.type = PERF_TYPE_HARDWARE,
+		.config = PERF_COUNT_HW_CPU_CYCLES,
+		.sample_type = PERF_SAMPLE_PERIOD | PERF_SAMPLE_TID,
+	};
+	static char *kwlist[] = {
+		"type",
+		"config",
+		"sample_freq",
+		"sample_period",
+		"sample_type",
+		"read_format",
+		"disabled",
+		"inherit",
+		"pinned",
+		"exclusive",
+		"exclude_user",
+		"exclude_kernel",
+		"exclude_hv",
+		"exclude_idle",
+		"mmap",
+		"comm",
+		"freq",
+		"inherit_stat",
+		"enable_on_exec",
+		"task",
+		"watermark",
+		"precise_ip",
+		"mmap_data",
+		"sample_id_all",
+		"wakeup_events",
+		"bp_type",
+		"bp_addr",
+		"bp_len", NULL, NULL, };
+	u64 sample_period = 0;
+	u32 disabled = 0,
+	    inherit = 0,
+	    pinned = 0,
+	    exclusive = 0,
+	    exclude_user = 0,
+	    exclude_kernel = 0,
+	    exclude_hv = 0,
+	    exclude_idle = 0,
+	    mmap = 0,
+	    comm = 0,
+	    freq = 1,
+	    inherit_stat = 0,
+	    enable_on_exec = 0,
+	    task = 0,
+	    watermark = 0,
+	    precise_ip = 0,
+	    mmap_data = 0,
+	    sample_id_all = 1;
+	int idx = 0;
+
+	if (!PyArg_ParseTupleAndKeywords(args, kwargs,
+					 "|iKiKKiiiiiiiiiiiiiiiiiiiiiKK", kwlist,
+					 &attr.type, &attr.config, &attr.sample_freq,
+					 &sample_period, &attr.sample_type,
+					 &attr.read_format, &disabled, &inherit,
+					 &pinned, &exclusive, &exclude_user,
+					 &exclude_kernel, &exclude_hv, &exclude_idle,
+					 &mmap, &comm, &freq, &inherit_stat,
+					 &enable_on_exec, &task, &watermark,
+					 &precise_ip, &mmap_data, &sample_id_all,
+					 &attr.wakeup_events, &attr.bp_type,
+					 &attr.bp_addr, &attr.bp_len, &idx))
+		return -1;
+
+	/* union... */
+	if (sample_period != 0) {
+		if (attr.sample_freq != 0)
+			return -1; /* FIXME: throw right exception */
+		attr.sample_period = sample_period;
+	}
+
+	/* Bitfields */
+	attr.disabled	    = disabled;
+	attr.inherit	    = inherit;
+	attr.pinned	    = pinned;
+	attr.exclusive	    = exclusive;
+	attr.exclude_user   = exclude_user;
+	attr.exclude_kernel = exclude_kernel;
+	attr.exclude_hv	    = exclude_hv;
+	attr.exclude_idle   = exclude_idle;
+	attr.mmap	    = mmap;
+	attr.comm	    = comm;
+	attr.freq	    = freq;
+	attr.inherit_stat   = inherit_stat;
+	attr.enable_on_exec = enable_on_exec;
+	attr.task	    = task;
+	attr.watermark	    = watermark;
+	attr.precise_ip	    = precise_ip;
+	attr.mmap_data	    = mmap_data;
+	attr.sample_id_all  = sample_id_all;
+
+	perf_evsel__init(&pevsel->evsel, &attr, idx);
+	return 0;
+}
+
+static void pyrf_evsel__delete(struct pyrf_evsel *pevsel)
+{
+	perf_evsel__exit(&pevsel->evsel);
+	pevsel->ob_type->tp_free((PyObject*)pevsel);
+}
+
+static PyObject *pyrf_evsel__open(struct pyrf_evsel *pevsel,
+				  PyObject *args, PyObject *kwargs)
+{
+	struct perf_evsel *evsel = &pevsel->evsel;
+	struct cpu_map *cpus = NULL;
+	struct thread_map *threads = NULL;
+	PyObject *pcpus = NULL, *pthreads = NULL;
+	int group = 0, overwrite = 0;
+	static char *kwlist[] = {"cpus", "threads", "group", "overwrite", NULL, NULL};
+
+	if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|OOii", kwlist,
+					 &pcpus, &pthreads, &group, &overwrite))
+		return NULL;
+
+	if (pthreads != NULL)
+		threads = ((struct pyrf_thread_map *)pthreads)->threads;
+
+	if (pcpus != NULL)
+		cpus = ((struct pyrf_cpu_map *)pcpus)->cpus;
+
+	if (perf_evsel__open(evsel, cpus, threads, group, overwrite) < 0) {
+		PyErr_SetFromErrno(PyExc_OSError);
+		return NULL;
+	}
+
+	Py_INCREF(Py_None);
+	return Py_None;
+}
+
+static PyMethodDef pyrf_evsel__methods[] = {
+	{
+		.ml_name  = "open",
+		.ml_meth  = (PyCFunction)pyrf_evsel__open,
+		.ml_flags = METH_VARARGS | METH_KEYWORDS,
+		.ml_doc	  = PyDoc_STR("open the event selector file descriptor table.")
+	},
+	{ .ml_name = NULL, }
+};
+
+static char pyrf_evsel__doc[] = PyDoc_STR("perf event selector list object.");
+
+static PyTypeObject pyrf_evsel__type = {
+	PyVarObject_HEAD_INIT(NULL, 0)
+	.tp_name	= "perf.evsel",
+	.tp_basicsize	= sizeof(struct pyrf_evsel),
+	.tp_dealloc	= (destructor)pyrf_evsel__delete,
+	.tp_flags	= Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+	.tp_doc		= pyrf_evsel__doc,
+	.tp_methods	= pyrf_evsel__methods,
+	.tp_init	= (initproc)pyrf_evsel__init,
+};
+
+static int pyrf_evsel__setup_types(void)
+{
+	pyrf_evsel__type.tp_new = PyType_GenericNew;
+	return PyType_Ready(&pyrf_evsel__type);
+}
+
+struct pyrf_evlist {
+	PyObject_HEAD
+
+	struct perf_evlist evlist;
+};
+
+static int pyrf_evlist__init(struct pyrf_evlist *pevlist,
+			     PyObject *args, PyObject *kwargs __used)
+{
+	PyObject *pcpus = NULL, *pthreads = NULL;
+	struct cpu_map *cpus;
+	struct thread_map *threads;
+
+	if (!PyArg_ParseTuple(args, "OO", &pcpus, &pthreads))
+		return -1;
+
+	threads = ((struct pyrf_thread_map *)pthreads)->threads;
+	cpus = ((struct pyrf_cpu_map *)pcpus)->cpus;
+	perf_evlist__init(&pevlist->evlist, cpus, threads);
+	return 0;
+}
+
+static void pyrf_evlist__delete(struct pyrf_evlist *pevlist)
+{
+	perf_evlist__exit(&pevlist->evlist);
+	pevlist->ob_type->tp_free((PyObject*)pevlist);
+}
+
+static PyObject *pyrf_evlist__mmap(struct pyrf_evlist *pevlist,
+				   PyObject *args, PyObject *kwargs)
+{
+	struct perf_evlist *evlist = &pevlist->evlist;
+	static char *kwlist[] = {"pages", "overwrite",
+				  NULL, NULL};
+	int pages = 128, overwrite = false;
+
+	if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|ii", kwlist,
+					 &pages, &overwrite))
+		return NULL;
+
+	if (perf_evlist__mmap(evlist, pages, overwrite) < 0) {
+		PyErr_SetFromErrno(PyExc_OSError);
+		return NULL;
+	}
+
+	Py_INCREF(Py_None);
+	return Py_None;
+}
+
+static PyObject *pyrf_evlist__poll(struct pyrf_evlist *pevlist,
+				   PyObject *args, PyObject *kwargs)
+{
+	struct perf_evlist *evlist = &pevlist->evlist;
+	static char *kwlist[] = {"timeout", NULL, NULL};
+	int timeout = -1, n;
+
+	if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|i", kwlist, &timeout))
+		return NULL;
+
+	n = poll(evlist->pollfd, evlist->nr_fds, timeout);
+	if (n < 0) {
+		PyErr_SetFromErrno(PyExc_OSError);
+		return NULL;
+	}
+
+	return Py_BuildValue("i", n);
+}
+
+static PyObject *pyrf_evlist__get_pollfd(struct pyrf_evlist *pevlist,
+					 PyObject *args __used, PyObject *kwargs __used)
+{
+	struct perf_evlist *evlist = &pevlist->evlist;
+        PyObject *list = PyList_New(0);
+	int i;
+
+	for (i = 0; i < evlist->nr_fds; ++i) {
+		PyObject *file;
+		FILE *fp = fdopen(evlist->pollfd[i].fd, "r");
+
+		if (fp == NULL)
+			goto free_list;
+
+		file = PyFile_FromFile(fp, "perf", "r", NULL);
+		if (file == NULL)
+			goto free_list;
+
+		if (PyList_Append(list, file) != 0) {
+			Py_DECREF(file);
+			goto free_list;
+		}
+			
+		Py_DECREF(file);
+	}
+
+	return list;
+free_list:
+	return PyErr_NoMemory();
+}
+
+
+static PyObject *pyrf_evlist__add(struct pyrf_evlist *pevlist,
+				  PyObject *args, PyObject *kwargs __used)
+{
+	struct perf_evlist *evlist = &pevlist->evlist;
+	PyObject *pevsel;
+	struct perf_evsel *evsel;
+
+	if (!PyArg_ParseTuple(args, "O", &pevsel))
+		return NULL;
+
+	Py_INCREF(pevsel);
+	evsel = &((struct pyrf_evsel *)pevsel)->evsel;
+	evsel->idx = evlist->nr_entries;
+	perf_evlist__add(evlist, evsel);
+
+	return Py_BuildValue("i", evlist->nr_entries);
+}
+
+static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
+					  PyObject *args, PyObject *kwargs)
+{
+	struct perf_evlist *evlist = &pevlist->evlist;
+	union perf_event *event;
+	int sample_id_all = 1, cpu;
+	static char *kwlist[] = {"sample_id_all", NULL, NULL};
+
+	if (!PyArg_ParseTupleAndKeywords(args, kwargs, "i|i", kwlist,
+					 &cpu, &sample_id_all))
+		return NULL;
+
+	event = perf_evlist__read_on_cpu(evlist, cpu);
+	if (event != NULL) {
+		struct perf_evsel *first;
+		PyObject *pyevent = pyrf_event__new(event);
+		struct pyrf_event *pevent = (struct pyrf_event *)pyevent;
+
+		if (pyevent == NULL)
+			return PyErr_NoMemory();
+
+		first = list_entry(evlist->entries.next, struct perf_evsel, node);
+		perf_event__parse_sample(event, first->attr.sample_type, sample_id_all,
+					 &pevent->sample);
+		return pyevent;
+	}
+
+	Py_INCREF(Py_None);
+	return Py_None;
+}
+
+static PyMethodDef pyrf_evlist__methods[] = {
+	{
+		.ml_name  = "mmap",
+		.ml_meth  = (PyCFunction)pyrf_evlist__mmap,
+		.ml_flags = METH_VARARGS | METH_KEYWORDS,
+		.ml_doc	  = PyDoc_STR("mmap the file descriptor table.")
+	},
+	{
+		.ml_name  = "poll",
+		.ml_meth  = (PyCFunction)pyrf_evlist__poll,
+		.ml_flags = METH_VARARGS | METH_KEYWORDS,
+		.ml_doc	  = PyDoc_STR("poll the file descriptor table.")
+	},
+	{
+		.ml_name  = "get_pollfd",
+		.ml_meth  = (PyCFunction)pyrf_evlist__get_pollfd,
+		.ml_flags = METH_VARARGS | METH_KEYWORDS,
+		.ml_doc	  = PyDoc_STR("get the poll file descriptor table.")
+	},
+	{
+		.ml_name  = "add",
+		.ml_meth  = (PyCFunction)pyrf_evlist__add,
+		.ml_flags = METH_VARARGS | METH_KEYWORDS,
+		.ml_doc	  = PyDoc_STR("adds an event selector to the list.")
+	},
+	{
+		.ml_name  = "read_on_cpu",
+		.ml_meth  = (PyCFunction)pyrf_evlist__read_on_cpu,
+		.ml_flags = METH_VARARGS | METH_KEYWORDS,
+		.ml_doc	  = PyDoc_STR("reads an event.")
+	},
+	{ .ml_name = NULL, }
+};
+
+static Py_ssize_t pyrf_evlist__length(PyObject *obj)
+{
+	struct pyrf_evlist *pevlist = (void *)obj;
+
+	return pevlist->evlist.nr_entries;
+}
+
+static PyObject *pyrf_evlist__item(PyObject *obj, Py_ssize_t i)
+{
+	struct pyrf_evlist *pevlist = (void *)obj;
+	struct perf_evsel *pos;
+
+	if (i >= pevlist->evlist.nr_entries)
+		return NULL;
+
+	list_for_each_entry(pos, &pevlist->evlist.entries, node)
+		if (i-- == 0)
+			break;
+
+	return Py_BuildValue("O", container_of(pos, struct pyrf_evsel, evsel));
+}
+
+static PySequenceMethods pyrf_evlist__sequence_methods = {
+	.sq_length = pyrf_evlist__length,
+	.sq_item   = pyrf_evlist__item,
+};
+
+static char pyrf_evlist__doc[] = PyDoc_STR("perf event selector list object.");
+
+static PyTypeObject pyrf_evlist__type = {
+	PyVarObject_HEAD_INIT(NULL, 0)
+	.tp_name	= "perf.evlist",
+	.tp_basicsize	= sizeof(struct pyrf_evlist),
+	.tp_dealloc	= (destructor)pyrf_evlist__delete,
+	.tp_flags	= Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+	.tp_as_sequence	= &pyrf_evlist__sequence_methods,
+	.tp_doc		= pyrf_evlist__doc,
+	.tp_methods	= pyrf_evlist__methods,
+	.tp_init	= (initproc)pyrf_evlist__init,
+};
+
+static int pyrf_evlist__setup_types(void)
+{
+	pyrf_evlist__type.tp_new = PyType_GenericNew;
+	return PyType_Ready(&pyrf_evlist__type);
+}
+
+static struct {
+	const char *name;
+	int	    value;
+} perf__constants[] = {
+	{ "TYPE_HARDWARE",   PERF_TYPE_HARDWARE },
+	{ "TYPE_SOFTWARE",   PERF_TYPE_SOFTWARE },
+	{ "TYPE_TRACEPOINT", PERF_TYPE_TRACEPOINT },
+	{ "TYPE_HW_CACHE",   PERF_TYPE_HW_CACHE },
+	{ "TYPE_RAW",	     PERF_TYPE_RAW },
+	{ "TYPE_BREAKPOINT", PERF_TYPE_BREAKPOINT },
+
+	{ "COUNT_HW_CPU_CYCLES",	  PERF_COUNT_HW_CPU_CYCLES },
+	{ "COUNT_HW_INSTRUCTIONS",	  PERF_COUNT_HW_INSTRUCTIONS },
+	{ "COUNT_HW_CACHE_REFERENCES",	  PERF_COUNT_HW_CACHE_REFERENCES },
+	{ "COUNT_HW_CACHE_MISSES",	  PERF_COUNT_HW_CACHE_MISSES },
+	{ "COUNT_HW_BRANCH_INSTRUCTIONS", PERF_COUNT_HW_BRANCH_INSTRUCTIONS },
+	{ "COUNT_HW_BRANCH_MISSES",	  PERF_COUNT_HW_BRANCH_MISSES },
+	{ "COUNT_HW_BUS_CYCLES",	  PERF_COUNT_HW_BUS_CYCLES },
+	{ "COUNT_HW_CACHE_L1D",		  PERF_COUNT_HW_CACHE_L1D },
+	{ "COUNT_HW_CACHE_L1I",		  PERF_COUNT_HW_CACHE_L1I },
+	{ "COUNT_HW_CACHE_LL",	  	  PERF_COUNT_HW_CACHE_LL },
+	{ "COUNT_HW_CACHE_DTLB",	  PERF_COUNT_HW_CACHE_DTLB },
+	{ "COUNT_HW_CACHE_ITLB",	  PERF_COUNT_HW_CACHE_ITLB },
+	{ "COUNT_HW_CACHE_BPU",		  PERF_COUNT_HW_CACHE_BPU },
+	{ "COUNT_HW_CACHE_OP_READ",	  PERF_COUNT_HW_CACHE_OP_READ },
+	{ "COUNT_HW_CACHE_OP_WRITE",	  PERF_COUNT_HW_CACHE_OP_WRITE },
+	{ "COUNT_HW_CACHE_OP_PREFETCH",	  PERF_COUNT_HW_CACHE_OP_PREFETCH },
+	{ "COUNT_HW_CACHE_RESULT_ACCESS", PERF_COUNT_HW_CACHE_RESULT_ACCESS },
+	{ "COUNT_HW_CACHE_RESULT_MISS",   PERF_COUNT_HW_CACHE_RESULT_MISS },
+
+	{ "COUNT_SW_CPU_CLOCK",	       PERF_COUNT_SW_CPU_CLOCK },
+	{ "COUNT_SW_TASK_CLOCK",       PERF_COUNT_SW_TASK_CLOCK },
+	{ "COUNT_SW_PAGE_FAULTS",      PERF_COUNT_SW_PAGE_FAULTS },
+	{ "COUNT_SW_CONTEXT_SWITCHES", PERF_COUNT_SW_CONTEXT_SWITCHES },
+	{ "COUNT_SW_CPU_MIGRATIONS",   PERF_COUNT_SW_CPU_MIGRATIONS },
+	{ "COUNT_SW_PAGE_FAULTS_MIN",  PERF_COUNT_SW_PAGE_FAULTS_MIN },
+	{ "COUNT_SW_PAGE_FAULTS_MAJ",  PERF_COUNT_SW_PAGE_FAULTS_MAJ },
+	{ "COUNT_SW_ALIGNMENT_FAULTS", PERF_COUNT_SW_ALIGNMENT_FAULTS },
+	{ "COUNT_SW_EMULATION_FAULTS", PERF_COUNT_SW_EMULATION_FAULTS },
+
+	{ "SAMPLE_IP",	      PERF_SAMPLE_IP },
+	{ "SAMPLE_TID",	      PERF_SAMPLE_TID },
+	{ "SAMPLE_TIME",      PERF_SAMPLE_TIME },
+	{ "SAMPLE_ADDR",      PERF_SAMPLE_ADDR },
+	{ "SAMPLE_READ",      PERF_SAMPLE_READ },
+	{ "SAMPLE_CALLCHAIN", PERF_SAMPLE_CALLCHAIN },
+	{ "SAMPLE_ID",	      PERF_SAMPLE_ID },
+	{ "SAMPLE_CPU",	      PERF_SAMPLE_CPU },
+	{ "SAMPLE_PERIOD",    PERF_SAMPLE_PERIOD },
+	{ "SAMPLE_STREAM_ID", PERF_SAMPLE_STREAM_ID },
+	{ "SAMPLE_RAW",	      PERF_SAMPLE_RAW },
+
+	{ "FORMAT_TOTAL_TIME_ENABLED", PERF_FORMAT_TOTAL_TIME_ENABLED },
+	{ "FORMAT_TOTAL_TIME_RUNNING", PERF_FORMAT_TOTAL_TIME_RUNNING },
+	{ "FORMAT_ID",		       PERF_FORMAT_ID },
+	{ "FORMAT_GROUP",	       PERF_FORMAT_GROUP },
+
+	{ "RECORD_MMAP",       PERF_RECORD_MMAP },
+	{ "RECORD_LOST",       PERF_RECORD_LOST },
+	{ "RECORD_COMM",       PERF_RECORD_COMM },
+	{ "RECORD_EXIT",       PERF_RECORD_EXIT },
+	{ "RECORD_THROTTLE",   PERF_RECORD_THROTTLE },
+	{ "RECORD_UNTHROTTLE", PERF_RECORD_UNTHROTTLE },
+	{ "RECORD_FORK",       PERF_RECORD_FORK },
+	{ "RECORD_READ",       PERF_RECORD_READ },
+	{ "RECORD_SAMPLE",     PERF_RECORD_SAMPLE },
+	{ .name = NULL, },
+};
+
+static PyMethodDef perf__methods[] = {
+	{ .ml_name = NULL, }
+};
+
+PyMODINIT_FUNC initperf(void)
+{
+	PyObject *obj;
+	int i;
+	PyObject *dict, *module = Py_InitModule("perf", perf__methods);
+
+	if (module == NULL ||
+	    pyrf_event__setup_types() < 0 ||
+	    pyrf_evlist__setup_types() < 0 ||
+	    pyrf_evsel__setup_types() < 0 ||
+	    pyrf_thread_map__setup_types() < 0 ||
+	    pyrf_cpu_map__setup_types() < 0)
+		return;
+
+	Py_INCREF(&pyrf_evlist__type);
+	PyModule_AddObject(module, "evlist", (PyObject*)&pyrf_evlist__type);
+
+	Py_INCREF(&pyrf_evsel__type);
+	PyModule_AddObject(module, "evsel", (PyObject*)&pyrf_evsel__type);
+
+	Py_INCREF(&pyrf_thread_map__type);
+	PyModule_AddObject(module, "thread_map", (PyObject*)&pyrf_thread_map__type);
+
+	Py_INCREF(&pyrf_cpu_map__type);
+	PyModule_AddObject(module, "cpu_map", (PyObject*)&pyrf_cpu_map__type);
+
+	dict = PyModule_GetDict(module);
+	if (dict == NULL)
+		goto error;
+
+	for (i = 0; perf__constants[i].name != NULL; i++) {
+		obj = PyInt_FromLong(perf__constants[i].value);
+		if (obj == NULL)
+			goto error;
+		PyDict_SetItemString(dict, perf__constants[i].name, obj);
+		Py_DECREF(obj);
+	}
+
+error:
+	if (PyErr_Occurred())
+		PyErr_SetString(PyExc_ImportError, "perf: Init failed!");
+}
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index c6d99334bdfa..2040b8538527 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -248,8 +248,7 @@ static void python_process_event(int cpu, void *data,
 	context = PyCObject_FromVoidPtr(scripting_context, NULL);
 
 	PyTuple_SetItem(t, n++, PyString_FromString(handler_name));
-	PyTuple_SetItem(t, n++,
-			PyCObject_FromVoidPtr(scripting_context, NULL));
+	PyTuple_SetItem(t, n++, context);
 
 	if (handler) {
 		PyTuple_SetItem(t, n++, PyInt_FromLong(cpu));
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 105f00bfd555..f26639fa0fb3 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -7,6 +7,8 @@
 #include <sys/types.h>
 #include <sys/mman.h>
 
+#include "evlist.h"
+#include "evsel.h"
 #include "session.h"
 #include "sort.h"
 #include "util.h"
@@ -19,7 +21,7 @@ static int perf_session__open(struct perf_session *self, bool force)
 		self->fd_pipe = true;
 		self->fd = STDIN_FILENO;
 
-		if (perf_header__read(self, self->fd) < 0)
+		if (perf_session__read_header(self, self->fd) < 0)
 			pr_err("incompatible file format");
 
 		return 0;
@@ -51,7 +53,7 @@ static int perf_session__open(struct perf_session *self, bool force)
 		goto out_close;
 	}
 
-	if (perf_header__read(self, self->fd) < 0) {
+	if (perf_session__read_header(self, self->fd) < 0) {
 		pr_err("incompatible file format");
 		goto out_close;
 	}
@@ -67,7 +69,7 @@ out_close:
 
 static void perf_session__id_header_size(struct perf_session *session)
 {
-       struct sample_data *data;
+       struct perf_sample *data;
        u64 sample_type = session->sample_type;
        u16 size = 0;
 
@@ -92,21 +94,10 @@ out:
        session->id_hdr_size = size;
 }
 
-void perf_session__set_sample_id_all(struct perf_session *session, bool value)
-{
-	session->sample_id_all = value;
-	perf_session__id_header_size(session);
-}
-
-void perf_session__set_sample_type(struct perf_session *session, u64 type)
-{
-	session->sample_type = type;
-}
-
 void perf_session__update_sample_type(struct perf_session *self)
 {
-	self->sample_type = perf_header__sample_type(&self->header);
-	self->sample_id_all = perf_header__sample_id_all(&self->header);
+	self->sample_type = perf_evlist__sample_type(self->evlist);
+	self->sample_id_all = perf_evlist__sample_id_all(self->evlist);
 	perf_session__id_header_size(self);
 }
 
@@ -135,13 +126,9 @@ struct perf_session *perf_session__new(const char *filename, int mode,
 	if (self == NULL)
 		goto out;
 
-	if (perf_header__init(&self->header) < 0)
-		goto out_free;
-
 	memcpy(self->filename, filename, len);
 	self->threads = RB_ROOT;
 	INIT_LIST_HEAD(&self->dead_threads);
-	self->hists_tree = RB_ROOT;
 	self->last_match = NULL;
 	/*
 	 * On 64bit we can mmap the data file in one go. No need for tiny mmap
@@ -162,17 +149,16 @@ struct perf_session *perf_session__new(const char *filename, int mode,
 	if (mode == O_RDONLY) {
 		if (perf_session__open(self, force) < 0)
 			goto out_delete;
+		perf_session__update_sample_type(self);
 	} else if (mode == O_WRONLY) {
 		/*
 		 * In O_RDONLY mode this will be performed when reading the
-		 * kernel MMAP event, in event__process_mmap().
+		 * kernel MMAP event, in perf_event__process_mmap().
 		 */
 		if (perf_session__create_kernel_maps(self) < 0)
 			goto out_delete;
 	}
 
-	perf_session__update_sample_type(self);
-
 	if (ops && ops->ordering_requires_timestamps &&
 	    ops->ordered_samples && !self->sample_id_all) {
 		dump_printf("WARNING: No sample_id_all support, falling back to unordered processing\n");
@@ -181,9 +167,6 @@ struct perf_session *perf_session__new(const char *filename, int mode,
 
 out:
 	return self;
-out_free:
-	free(self);
-	return NULL;
 out_delete:
 	perf_session__delete(self);
 	return NULL;
@@ -214,7 +197,6 @@ static void perf_session__delete_threads(struct perf_session *self)
 
 void perf_session__delete(struct perf_session *self)
 {
-	perf_header__exit(&self->header);
 	perf_session__destroy_kernel_maps(self);
 	perf_session__delete_dead_threads(self);
 	perf_session__delete_threads(self);
@@ -242,17 +224,16 @@ static bool symbol__match_parent_regex(struct symbol *sym)
 	return 0;
 }
 
-struct map_symbol *perf_session__resolve_callchain(struct perf_session *self,
-						   struct thread *thread,
-						   struct ip_callchain *chain,
-						   struct symbol **parent)
+int perf_session__resolve_callchain(struct perf_session *self,
+				    struct thread *thread,
+				    struct ip_callchain *chain,
+				    struct symbol **parent)
 {
 	u8 cpumode = PERF_RECORD_MISC_USER;
 	unsigned int i;
-	struct map_symbol *syms = calloc(chain->nr, sizeof(*syms));
+	int err;
 
-	if (!syms)
-		return NULL;
+	callchain_cursor_reset(&self->callchain_cursor);
 
 	for (i = 0; i < chain->nr; i++) {
 		u64 ip = chain->ips[i];
@@ -281,30 +262,33 @@ struct map_symbol *perf_session__resolve_callchain(struct perf_session *self,
 				*parent = al.sym;
 			if (!symbol_conf.use_callchain)
 				break;
-			syms[i].map = al.map;
-			syms[i].sym = al.sym;
 		}
+
+		err = callchain_cursor_append(&self->callchain_cursor,
+					      ip, al.map, al.sym);
+		if (err)
+			return err;
 	}
 
-	return syms;
+	return 0;
 }
 
-static int process_event_synth_stub(event_t *event __used,
+static int process_event_synth_stub(union perf_event *event __used,
 				    struct perf_session *session __used)
 {
 	dump_printf(": unhandled!\n");
 	return 0;
 }
 
-static int process_event_stub(event_t *event __used,
-			      struct sample_data *sample __used,
+static int process_event_stub(union perf_event *event __used,
+			      struct perf_sample *sample __used,
 			      struct perf_session *session __used)
 {
 	dump_printf(": unhandled!\n");
 	return 0;
 }
 
-static int process_finished_round_stub(event_t *event __used,
+static int process_finished_round_stub(union perf_event *event __used,
 				       struct perf_session *session __used,
 				       struct perf_event_ops *ops __used)
 {
@@ -312,7 +296,7 @@ static int process_finished_round_stub(event_t *event __used,
 	return 0;
 }
 
-static int process_finished_round(event_t *event,
+static int process_finished_round(union perf_event *event,
 				  struct perf_session *session,
 				  struct perf_event_ops *ops);
 
@@ -329,7 +313,7 @@ static void perf_event_ops__fill_defaults(struct perf_event_ops *handler)
 	if (handler->exit == NULL)
 		handler->exit = process_event_stub;
 	if (handler->lost == NULL)
-		handler->lost = event__process_lost;
+		handler->lost = perf_event__process_lost;
 	if (handler->read == NULL)
 		handler->read = process_event_stub;
 	if (handler->throttle == NULL)
@@ -363,98 +347,98 @@ void mem_bswap_64(void *src, int byte_size)
 	}
 }
 
-static void event__all64_swap(event_t *self)
+static void perf_event__all64_swap(union perf_event *event)
 {
-	struct perf_event_header *hdr = &self->header;
-	mem_bswap_64(hdr + 1, self->header.size - sizeof(*hdr));
+	struct perf_event_header *hdr = &event->header;
+	mem_bswap_64(hdr + 1, event->header.size - sizeof(*hdr));
 }
 
-static void event__comm_swap(event_t *self)
+static void perf_event__comm_swap(union perf_event *event)
 {
-	self->comm.pid = bswap_32(self->comm.pid);
-	self->comm.tid = bswap_32(self->comm.tid);
+	event->comm.pid = bswap_32(event->comm.pid);
+	event->comm.tid = bswap_32(event->comm.tid);
 }
 
-static void event__mmap_swap(event_t *self)
+static void perf_event__mmap_swap(union perf_event *event)
 {
-	self->mmap.pid	 = bswap_32(self->mmap.pid);
-	self->mmap.tid	 = bswap_32(self->mmap.tid);
-	self->mmap.start = bswap_64(self->mmap.start);
-	self->mmap.len	 = bswap_64(self->mmap.len);
-	self->mmap.pgoff = bswap_64(self->mmap.pgoff);
+	event->mmap.pid	  = bswap_32(event->mmap.pid);
+	event->mmap.tid	  = bswap_32(event->mmap.tid);
+	event->mmap.start = bswap_64(event->mmap.start);
+	event->mmap.len	  = bswap_64(event->mmap.len);
+	event->mmap.pgoff = bswap_64(event->mmap.pgoff);
 }
 
-static void event__task_swap(event_t *self)
+static void perf_event__task_swap(union perf_event *event)
 {
-	self->fork.pid	= bswap_32(self->fork.pid);
-	self->fork.tid	= bswap_32(self->fork.tid);
-	self->fork.ppid	= bswap_32(self->fork.ppid);
-	self->fork.ptid	= bswap_32(self->fork.ptid);
-	self->fork.time	= bswap_64(self->fork.time);
+	event->fork.pid	 = bswap_32(event->fork.pid);
+	event->fork.tid	 = bswap_32(event->fork.tid);
+	event->fork.ppid = bswap_32(event->fork.ppid);
+	event->fork.ptid = bswap_32(event->fork.ptid);
+	event->fork.time = bswap_64(event->fork.time);
 }
 
-static void event__read_swap(event_t *self)
+static void perf_event__read_swap(union perf_event *event)
 {
-	self->read.pid		= bswap_32(self->read.pid);
-	self->read.tid		= bswap_32(self->read.tid);
-	self->read.value	= bswap_64(self->read.value);
-	self->read.time_enabled	= bswap_64(self->read.time_enabled);
-	self->read.time_running	= bswap_64(self->read.time_running);
-	self->read.id		= bswap_64(self->read.id);
+	event->read.pid		 = bswap_32(event->read.pid);
+	event->read.tid		 = bswap_32(event->read.tid);
+	event->read.value	 = bswap_64(event->read.value);
+	event->read.time_enabled = bswap_64(event->read.time_enabled);
+	event->read.time_running = bswap_64(event->read.time_running);
+	event->read.id		 = bswap_64(event->read.id);
 }
 
-static void event__attr_swap(event_t *self)
+static void perf_event__attr_swap(union perf_event *event)
 {
 	size_t size;
 
-	self->attr.attr.type		= bswap_32(self->attr.attr.type);
-	self->attr.attr.size		= bswap_32(self->attr.attr.size);
-	self->attr.attr.config		= bswap_64(self->attr.attr.config);
-	self->attr.attr.sample_period	= bswap_64(self->attr.attr.sample_period);
-	self->attr.attr.sample_type	= bswap_64(self->attr.attr.sample_type);
-	self->attr.attr.read_format	= bswap_64(self->attr.attr.read_format);
-	self->attr.attr.wakeup_events	= bswap_32(self->attr.attr.wakeup_events);
-	self->attr.attr.bp_type		= bswap_32(self->attr.attr.bp_type);
-	self->attr.attr.bp_addr		= bswap_64(self->attr.attr.bp_addr);
-	self->attr.attr.bp_len		= bswap_64(self->attr.attr.bp_len);
-
-	size = self->header.size;
-	size -= (void *)&self->attr.id - (void *)self;
-	mem_bswap_64(self->attr.id, size);
+	event->attr.attr.type		= bswap_32(event->attr.attr.type);
+	event->attr.attr.size		= bswap_32(event->attr.attr.size);
+	event->attr.attr.config		= bswap_64(event->attr.attr.config);
+	event->attr.attr.sample_period	= bswap_64(event->attr.attr.sample_period);
+	event->attr.attr.sample_type	= bswap_64(event->attr.attr.sample_type);
+	event->attr.attr.read_format	= bswap_64(event->attr.attr.read_format);
+	event->attr.attr.wakeup_events	= bswap_32(event->attr.attr.wakeup_events);
+	event->attr.attr.bp_type	= bswap_32(event->attr.attr.bp_type);
+	event->attr.attr.bp_addr	= bswap_64(event->attr.attr.bp_addr);
+	event->attr.attr.bp_len		= bswap_64(event->attr.attr.bp_len);
+
+	size = event->header.size;
+	size -= (void *)&event->attr.id - (void *)event;
+	mem_bswap_64(event->attr.id, size);
 }
 
-static void event__event_type_swap(event_t *self)
+static void perf_event__event_type_swap(union perf_event *event)
 {
-	self->event_type.event_type.event_id =
-		bswap_64(self->event_type.event_type.event_id);
+	event->event_type.event_type.event_id =
+		bswap_64(event->event_type.event_type.event_id);
 }
 
-static void event__tracing_data_swap(event_t *self)
+static void perf_event__tracing_data_swap(union perf_event *event)
 {
-	self->tracing_data.size = bswap_32(self->tracing_data.size);
+	event->tracing_data.size = bswap_32(event->tracing_data.size);
 }
 
-typedef void (*event__swap_op)(event_t *self);
-
-static event__swap_op event__swap_ops[] = {
-	[PERF_RECORD_MMAP]   = event__mmap_swap,
-	[PERF_RECORD_COMM]   = event__comm_swap,
-	[PERF_RECORD_FORK]   = event__task_swap,
-	[PERF_RECORD_EXIT]   = event__task_swap,
-	[PERF_RECORD_LOST]   = event__all64_swap,
-	[PERF_RECORD_READ]   = event__read_swap,
-	[PERF_RECORD_SAMPLE] = event__all64_swap,
-	[PERF_RECORD_HEADER_ATTR]   = event__attr_swap,
-	[PERF_RECORD_HEADER_EVENT_TYPE]   = event__event_type_swap,
-	[PERF_RECORD_HEADER_TRACING_DATA]   = event__tracing_data_swap,
-	[PERF_RECORD_HEADER_BUILD_ID]   = NULL,
-	[PERF_RECORD_HEADER_MAX]    = NULL,
+typedef void (*perf_event__swap_op)(union perf_event *event);
+
+static perf_event__swap_op perf_event__swap_ops[] = {
+	[PERF_RECORD_MMAP]		  = perf_event__mmap_swap,
+	[PERF_RECORD_COMM]		  = perf_event__comm_swap,
+	[PERF_RECORD_FORK]		  = perf_event__task_swap,
+	[PERF_RECORD_EXIT]		  = perf_event__task_swap,
+	[PERF_RECORD_LOST]		  = perf_event__all64_swap,
+	[PERF_RECORD_READ]		  = perf_event__read_swap,
+	[PERF_RECORD_SAMPLE]		  = perf_event__all64_swap,
+	[PERF_RECORD_HEADER_ATTR]	  = perf_event__attr_swap,
+	[PERF_RECORD_HEADER_EVENT_TYPE]	  = perf_event__event_type_swap,
+	[PERF_RECORD_HEADER_TRACING_DATA] = perf_event__tracing_data_swap,
+	[PERF_RECORD_HEADER_BUILD_ID]	  = NULL,
+	[PERF_RECORD_HEADER_MAX]	  = NULL,
 };
 
 struct sample_queue {
 	u64			timestamp;
 	u64			file_offset;
-	event_t			*event;
+	union perf_event	*event;
 	struct list_head	list;
 };
 
@@ -472,8 +456,8 @@ static void perf_session_free_sample_buffers(struct perf_session *session)
 }
 
 static int perf_session_deliver_event(struct perf_session *session,
-				      event_t *event,
-				      struct sample_data *sample,
+				      union perf_event *event,
+				      struct perf_sample *sample,
 				      struct perf_event_ops *ops,
 				      u64 file_offset);
 
@@ -483,7 +467,7 @@ static void flush_sample_queue(struct perf_session *s,
 	struct ordered_samples *os = &s->ordered_samples;
 	struct list_head *head = &os->samples;
 	struct sample_queue *tmp, *iter;
-	struct sample_data sample;
+	struct perf_sample sample;
 	u64 limit = os->next_flush;
 	u64 last_ts = os->last_sample ? os->last_sample->timestamp : 0ULL;
 
@@ -494,7 +478,7 @@ static void flush_sample_queue(struct perf_session *s,
 		if (iter->timestamp > limit)
 			break;
 
-		event__parse_sample(iter->event, s, &sample);
+		perf_session__parse_sample(s, iter->event, &sample);
 		perf_session_deliver_event(s, iter->event, &sample, ops,
 					   iter->file_offset);
 
@@ -550,7 +534,7 @@ static void flush_sample_queue(struct perf_session *s,
  *      Flush every events below timestamp 7
  *      etc...
  */
-static int process_finished_round(event_t *event __used,
+static int process_finished_round(union perf_event *event __used,
 				  struct perf_session *session,
 				  struct perf_event_ops *ops)
 {
@@ -607,12 +591,12 @@ static void __queue_event(struct sample_queue *new, struct perf_session *s)
 
 #define MAX_SAMPLE_BUFFER	(64 * 1024 / sizeof(struct sample_queue))
 
-static int perf_session_queue_event(struct perf_session *s, event_t *event,
-				    struct sample_data *data, u64 file_offset)
+static int perf_session_queue_event(struct perf_session *s, union perf_event *event,
+				    struct perf_sample *sample, u64 file_offset)
 {
 	struct ordered_samples *os = &s->ordered_samples;
 	struct list_head *sc = &os->sample_cache;
-	u64 timestamp = data->time;
+	u64 timestamp = sample->time;
 	struct sample_queue *new;
 
 	if (!timestamp || timestamp == ~0ULL)
@@ -648,7 +632,7 @@ static int perf_session_queue_event(struct perf_session *s, event_t *event,
 	return 0;
 }
 
-static void callchain__printf(struct sample_data *sample)
+static void callchain__printf(struct perf_sample *sample)
 {
 	unsigned int i;
 
@@ -660,8 +644,8 @@ static void callchain__printf(struct sample_data *sample)
 }
 
 static void perf_session__print_tstamp(struct perf_session *session,
-				       event_t *event,
-				       struct sample_data *sample)
+				       union perf_event *event,
+				       struct perf_sample *sample)
 {
 	if (event->header.type != PERF_RECORD_SAMPLE &&
 	    !session->sample_id_all) {
@@ -676,8 +660,8 @@ static void perf_session__print_tstamp(struct perf_session *session,
 		printf("%" PRIu64 " ", sample->time);
 }
 
-static void dump_event(struct perf_session *session, event_t *event,
-		       u64 file_offset, struct sample_data *sample)
+static void dump_event(struct perf_session *session, union perf_event *event,
+		       u64 file_offset, struct perf_sample *sample)
 {
 	if (!dump_trace)
 		return;
@@ -691,11 +675,11 @@ static void dump_event(struct perf_session *session, event_t *event,
 		perf_session__print_tstamp(session, event, sample);
 
 	printf("%#" PRIx64 " [%#x]: PERF_RECORD_%s", file_offset,
-	       event->header.size, event__get_event_name(event->header.type));
+	       event->header.size, perf_event__name(event->header.type));
 }
 
-static void dump_sample(struct perf_session *session, event_t *event,
-			struct sample_data *sample)
+static void dump_sample(struct perf_session *session, union perf_event *event,
+			struct perf_sample *sample)
 {
 	if (!dump_trace)
 		return;
@@ -709,8 +693,8 @@ static void dump_sample(struct perf_session *session, event_t *event,
 }
 
 static int perf_session_deliver_event(struct perf_session *session,
-				      event_t *event,
-				      struct sample_data *sample,
+				      union perf_event *event,
+				      struct perf_sample *sample,
 				      struct perf_event_ops *ops,
 				      u64 file_offset)
 {
@@ -743,7 +727,7 @@ static int perf_session_deliver_event(struct perf_session *session,
 }
 
 static int perf_session__preprocess_sample(struct perf_session *session,
-					   event_t *event, struct sample_data *sample)
+					   union perf_event *event, struct perf_sample *sample)
 {
 	if (event->header.type != PERF_RECORD_SAMPLE ||
 	    !(session->sample_type & PERF_SAMPLE_CALLCHAIN))
@@ -758,7 +742,7 @@ static int perf_session__preprocess_sample(struct perf_session *session,
 	return 0;
 }
 
-static int perf_session__process_user_event(struct perf_session *session, event_t *event,
+static int perf_session__process_user_event(struct perf_session *session, union perf_event *event,
 					    struct perf_event_ops *ops, u64 file_offset)
 {
 	dump_event(session, event, file_offset, NULL);
@@ -783,15 +767,16 @@ static int perf_session__process_user_event(struct perf_session *session, event_
 }
 
 static int perf_session__process_event(struct perf_session *session,
-				       event_t *event,
+				       union perf_event *event,
 				       struct perf_event_ops *ops,
 				       u64 file_offset)
 {
-	struct sample_data sample;
+	struct perf_sample sample;
 	int ret;
 
-	if (session->header.needs_swap && event__swap_ops[event->header.type])
-		event__swap_ops[event->header.type](event);
+	if (session->header.needs_swap &&
+	    perf_event__swap_ops[event->header.type])
+		perf_event__swap_ops[event->header.type](event);
 
 	if (event->header.type >= PERF_RECORD_HEADER_MAX)
 		return -EINVAL;
@@ -804,7 +789,7 @@ static int perf_session__process_event(struct perf_session *session,
 	/*
 	 * For all kernel events we get the sample data
 	 */
-	event__parse_sample(event, session, &sample);
+	perf_session__parse_sample(session, event, &sample);
 
 	/* Preprocess sample records - precheck callchains */
 	if (perf_session__preprocess_sample(session, event, &sample))
@@ -843,7 +828,7 @@ static struct thread *perf_session__register_idle_thread(struct perf_session *se
 static void perf_session__warn_about_errors(const struct perf_session *session,
 					    const struct perf_event_ops *ops)
 {
-	if (ops->lost == event__process_lost &&
+	if (ops->lost == perf_event__process_lost &&
 	    session->hists.stats.total_lost != 0) {
 		ui__warning("Processed %" PRIu64 " events and LOST %" PRIu64
 			    "!\n\nCheck IO/CPU overload!\n\n",
@@ -875,7 +860,7 @@ volatile int session_done;
 static int __perf_session__process_pipe_events(struct perf_session *self,
 					       struct perf_event_ops *ops)
 {
-	event_t event;
+	union perf_event event;
 	uint32_t size;
 	int skip = 0;
 	u64 head;
@@ -956,7 +941,7 @@ int __perf_session__process_events(struct perf_session *session,
 	struct ui_progress *progress;
 	size_t	page_size, mmap_size;
 	char *buf, *mmaps[8];
-	event_t *event;
+	union perf_event *event;
 	uint32_t size;
 
 	perf_event_ops__fill_defaults(ops);
@@ -1001,7 +986,7 @@ remap:
 	file_pos = file_offset + head;
 
 more:
-	event = (event_t *)(buf + head);
+	event = (union perf_event *)(buf + head);
 
 	if (session->header.needs_swap)
 		perf_event_header__bswap(&event->header);
@@ -1134,3 +1119,18 @@ size_t perf_session__fprintf_dsos_buildid(struct perf_session *self, FILE *fp,
 	size_t ret = machine__fprintf_dsos_buildid(&self->host_machine, fp, with_hits);
 	return ret + machines__fprintf_dsos_buildid(&self->machines, fp, with_hits);
 }
+
+size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp)
+{
+	struct perf_evsel *pos;
+	size_t ret = fprintf(fp, "Aggregated stats:\n");
+
+	ret += hists__fprintf_nr_events(&session->hists, fp);
+
+	list_for_each_entry(pos, &session->evlist->entries, node) {
+		ret += fprintf(fp, "%s stats:\n", event_name(pos));
+		ret += hists__fprintf_nr_events(&pos->hists, fp);
+	}
+
+	return ret;
+}
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index decd83f274fd..b5b148b0aaca 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -34,12 +34,12 @@ struct perf_session {
 	struct thread		*last_match;
 	struct machine		host_machine;
 	struct rb_root		machines;
-	struct rb_root		hists_tree;
+	struct perf_evlist	*evlist;
 	/*
-	 * FIXME: should point to the first entry in hists_tree and
-	 *        be a hists instance. Right now its only 'report'
-	 *        that is using ->hists_tree while all the rest use
-	 *        ->hists.
+	 * FIXME: Need to split this up further, we need global
+	 *	  stats + per event stats. 'perf diff' also needs
+	 *	  to properly support multiple events in a single
+	 *	  perf.data file.
 	 */
 	struct hists		hists;
 	u64			sample_type;
@@ -51,15 +51,17 @@ struct perf_session {
 	int			cwdlen;
 	char			*cwd;
 	struct ordered_samples	ordered_samples;
-	char filename[0];
+	struct callchain_cursor	callchain_cursor;
+	char			filename[0];
 };
 
 struct perf_event_ops;
 
-typedef int (*event_op)(event_t *self, struct sample_data *sample,
+typedef int (*event_op)(union perf_event *self, struct perf_sample *sample,
 			struct perf_session *session);
-typedef int (*event_synth_op)(event_t *self, struct perf_session *session);
-typedef int (*event_op2)(event_t *self, struct perf_session *session,
+typedef int (*event_synth_op)(union perf_event *self,
+			      struct perf_session *session);
+typedef int (*event_op2)(union perf_event *self, struct perf_session *session,
 			 struct perf_event_ops *ops);
 
 struct perf_event_ops {
@@ -94,10 +96,10 @@ int __perf_session__process_events(struct perf_session *self,
 int perf_session__process_events(struct perf_session *self,
 				 struct perf_event_ops *event_ops);
 
-struct map_symbol *perf_session__resolve_callchain(struct perf_session *self,
-						   struct thread *thread,
-						   struct ip_callchain *chain,
-						   struct symbol **parent);
+int perf_session__resolve_callchain(struct perf_session *self,
+				    struct thread *thread,
+				    struct ip_callchain *chain,
+				    struct symbol **parent);
 
 bool perf_session__has_traces(struct perf_session *self, const char *msg);
 
@@ -110,8 +112,6 @@ void mem_bswap_64(void *src, int byte_size);
 int perf_session__create_kernel_maps(struct perf_session *self);
 
 void perf_session__update_sample_type(struct perf_session *self);
-void perf_session__set_sample_id_all(struct perf_session *session, bool value);
-void perf_session__set_sample_type(struct perf_session *session, u64 type);
 void perf_session__remove_thread(struct perf_session *self, struct thread *th);
 
 static inline
@@ -149,9 +149,14 @@ size_t perf_session__fprintf_dsos(struct perf_session *self, FILE *fp);
 size_t perf_session__fprintf_dsos_buildid(struct perf_session *self,
 					  FILE *fp, bool with_hits);
 
-static inline
-size_t perf_session__fprintf_nr_events(struct perf_session *self, FILE *fp)
+size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp);
+
+static inline int perf_session__parse_sample(struct perf_session *session,
+					     const union perf_event *event,
+					     struct perf_sample *sample)
 {
-	return hists__fprintf_nr_events(&self->hists, fp);
+	return perf_event__parse_sample(event, session->sample_type,
+					session->sample_id_all, sample);
 }
+
 #endif /* __PERF_SESSION_H */
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
new file mode 100644
index 000000000000..e24ffadb20b2
--- /dev/null
+++ b/tools/perf/util/setup.py
@@ -0,0 +1,19 @@
+#!/usr/bin/python2
+
+from distutils.core import setup, Extension
+
+perf = Extension('perf',
+		  sources = ['util/python.c', 'util/ctype.c', 'util/evlist.c',
+			     'util/evsel.c', 'util/cpumap.c', 'util/thread_map.c',
+			     'util/util.c', 'util/xyarray.c', 'util/cgroup.c'],
+		  include_dirs = ['util/include'],
+		  extra_compile_args = ['-fno-strict-aliasing', '-Wno-write-strings'])
+
+setup(name='perf',
+      version='0.1',
+      description='Interface with the Linux profiling infrastructure',
+      author='Arnaldo Carvalho de Melo',
+      author_email='acme@redhat.com',
+      license='GPLv2',
+      url='http://perf.wiki.kernel.org',
+      ext_modules=[perf])
diff --git a/tools/perf/util/strfilter.c b/tools/perf/util/strfilter.c
new file mode 100644
index 000000000000..834c8ebfe38e
--- /dev/null
+++ b/tools/perf/util/strfilter.c
@@ -0,0 +1,199 @@
+#include "util.h"
+#include "string.h"
+#include "strfilter.h"
+
+/* Operators */
+static const char *OP_and	= "&";	/* Logical AND */
+static const char *OP_or	= "|";	/* Logical OR */
+static const char *OP_not	= "!";	/* Logical NOT */
+
+#define is_operator(c)	((c) == '|' || (c) == '&' || (c) == '!')
+#define is_separator(c)	(is_operator(c) || (c) == '(' || (c) == ')')
+
+static void strfilter_node__delete(struct strfilter_node *self)
+{
+	if (self) {
+		if (self->p && !is_operator(*self->p))
+			free((char *)self->p);
+		strfilter_node__delete(self->l);
+		strfilter_node__delete(self->r);
+		free(self);
+	}
+}
+
+void strfilter__delete(struct strfilter *self)
+{
+	if (self) {
+		strfilter_node__delete(self->root);
+		free(self);
+	}
+}
+
+static const char *get_token(const char *s, const char **e)
+{
+	const char *p;
+
+	while (isspace(*s))	/* Skip spaces */
+		s++;
+
+	if (*s == '\0') {
+		p = s;
+		goto end;
+	}
+
+	p = s + 1;
+	if (!is_separator(*s)) {
+		/* End search */
+retry:
+		while (*p && !is_separator(*p) && !isspace(*p))
+			p++;
+		/* Escape and special case: '!' is also used in glob pattern */
+		if (*(p - 1) == '\\' || (*p == '!' && *(p - 1) == '[')) {
+			p++;
+			goto retry;
+		}
+	}
+end:
+	*e = p;
+	return s;
+}
+
+static struct strfilter_node *strfilter_node__alloc(const char *op,
+						    struct strfilter_node *l,
+						    struct strfilter_node *r)
+{
+	struct strfilter_node *ret = zalloc(sizeof(struct strfilter_node));
+
+	if (ret) {
+		ret->p = op;
+		ret->l = l;
+		ret->r = r;
+	}
+
+	return ret;
+}
+
+static struct strfilter_node *strfilter_node__new(const char *s,
+						  const char **ep)
+{
+	struct strfilter_node root, *cur, *last_op;
+	const char *e;
+
+	if (!s)
+		return NULL;
+
+	memset(&root, 0, sizeof(root));
+	last_op = cur = &root;
+
+	s = get_token(s, &e);
+	while (*s != '\0' && *s != ')') {
+		switch (*s) {
+		case '&':	/* Exchg last OP->r with AND */
+			if (!cur->r || !last_op->r)
+				goto error;
+			cur = strfilter_node__alloc(OP_and, last_op->r, NULL);
+			if (!cur)
+				goto nomem;
+			last_op->r = cur;
+			last_op = cur;
+			break;
+		case '|':	/* Exchg the root with OR */
+			if (!cur->r || !root.r)
+				goto error;
+			cur = strfilter_node__alloc(OP_or, root.r, NULL);
+			if (!cur)
+				goto nomem;
+			root.r = cur;
+			last_op = cur;
+			break;
+		case '!':	/* Add NOT as a leaf node */
+			if (cur->r)
+				goto error;
+			cur->r = strfilter_node__alloc(OP_not, NULL, NULL);
+			if (!cur->r)
+				goto nomem;
+			cur = cur->r;
+			break;
+		case '(':	/* Recursively parses inside the parenthesis */
+			if (cur->r)
+				goto error;
+			cur->r = strfilter_node__new(s + 1, &s);
+			if (!s)
+				goto nomem;
+			if (!cur->r || *s != ')')
+				goto error;
+			e = s + 1;
+			break;
+		default:
+			if (cur->r)
+				goto error;
+			cur->r = strfilter_node__alloc(NULL, NULL, NULL);
+			if (!cur->r)
+				goto nomem;
+			cur->r->p = strndup(s, e - s);
+			if (!cur->r->p)
+				goto nomem;
+		}
+		s = get_token(e, &e);
+	}
+	if (!cur->r)
+		goto error;
+	*ep = s;
+	return root.r;
+nomem:
+	s = NULL;
+error:
+	*ep = s;
+	strfilter_node__delete(root.r);
+	return NULL;
+}
+
+/*
+ * Parse filter rule and return new strfilter.
+ * Return NULL if fail, and *ep == NULL if memory allocation failed.
+ */
+struct strfilter *strfilter__new(const char *rules, const char **err)
+{
+	struct strfilter *ret = zalloc(sizeof(struct strfilter));
+	const char *ep = NULL;
+
+	if (ret)
+		ret->root = strfilter_node__new(rules, &ep);
+
+	if (!ret || !ret->root || *ep != '\0') {
+		if (err)
+			*err = ep;
+		strfilter__delete(ret);
+		ret = NULL;
+	}
+
+	return ret;
+}
+
+static bool strfilter_node__compare(struct strfilter_node *self,
+				    const char *str)
+{
+	if (!self || !self->p)
+		return false;
+
+	switch (*self->p) {
+	case '|':	/* OR */
+		return strfilter_node__compare(self->l, str) ||
+			strfilter_node__compare(self->r, str);
+	case '&':	/* AND */
+		return strfilter_node__compare(self->l, str) &&
+			strfilter_node__compare(self->r, str);
+	case '!':	/* NOT */
+		return !strfilter_node__compare(self->r, str);
+	default:
+		return strglobmatch(str, self->p);
+	}
+}
+
+/* Return true if STR matches the filter rules */
+bool strfilter__compare(struct strfilter *self, const char *str)
+{
+	if (!self)
+		return false;
+	return strfilter_node__compare(self->root, str);
+}
diff --git a/tools/perf/util/strfilter.h b/tools/perf/util/strfilter.h
new file mode 100644
index 000000000000..00f58a7506de
--- /dev/null
+++ b/tools/perf/util/strfilter.h
@@ -0,0 +1,48 @@
+#ifndef __PERF_STRFILTER_H
+#define __PERF_STRFILTER_H
+/* General purpose glob matching filter */
+
+#include <linux/list.h>
+#include <stdbool.h>
+
+/* A node of string filter */
+struct strfilter_node {
+	struct strfilter_node *l;	/* Tree left branche (for &,|) */
+	struct strfilter_node *r;	/* Tree right branche (for !,&,|) */
+	const char *p;		/* Operator or rule */
+};
+
+/* String filter */
+struct strfilter {
+	struct strfilter_node *root;
+};
+
+/**
+ * strfilter__new - Create a new string filter
+ * @rules: Filter rule, which is a combination of glob expressions.
+ * @err: Pointer which points an error detected on @rules
+ *
+ * Parse @rules and return new strfilter. Return NULL if an error detected.
+ * In that case, *@err will indicate where it is detected, and *@err is NULL
+ * if a memory allocation is failed.
+ */
+struct strfilter *strfilter__new(const char *rules, const char **err);
+
+/**
+ * strfilter__compare - compare given string and a string filter
+ * @self: String filter
+ * @str: target string
+ *
+ * Compare @str and @self. Return true if the str match the rule
+ */
+bool strfilter__compare(struct strfilter *self, const char *str);
+
+/**
+ * strfilter__delete - delete a string filter
+ * @self: String filter to delete
+ *
+ * Delete @self.
+ */
+void strfilter__delete(struct strfilter *self);
+
+#endif
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index b1bf490aff88..00014e32c288 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -207,7 +207,6 @@ struct dso *dso__new(const char *name)
 		dso__set_short_name(self, self->name);
 		for (i = 0; i < MAP__NR_TYPES; ++i)
 			self->symbols[i] = self->symbol_names[i] = RB_ROOT;
-		self->slen_calculated = 0;
 		self->origin = DSO__ORIG_NOT_FOUND;
 		self->loaded = 0;
 		self->sorted_by_name = 0;
@@ -1525,8 +1524,8 @@ int dso__load(struct dso *self, struct map *map, symbol_filter_t filter)
 			     symbol_conf.symfs, self->long_name);
 			break;
 		case DSO__ORIG_GUEST_KMODULE:
-			if (map->groups && map->groups->machine)
-				root_dir = map->groups->machine->root_dir;
+			if (map->groups && machine)
+				root_dir = machine->root_dir;
 			else
 				root_dir = "";
 			snprintf(name, size, "%s%s%s", symbol_conf.symfs,
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 670cd1c88f54..4d7ed09fe332 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -132,7 +132,6 @@ struct dso {
 	struct rb_root	 symbol_names[MAP__NR_TYPES];
 	enum dso_kernel_type	kernel;
 	u8		 adjust_symbols:1;
-	u8		 slen_calculated:1;
 	u8		 has_build_id:1;
 	u8		 hit:1;
 	u8		 annotate_warned:1;
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 00f4eade2e3e..d5d3b22250f3 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -7,61 +7,6 @@
 #include "util.h"
 #include "debug.h"
 
-/* Skip "." and ".." directories */
-static int filter(const struct dirent *dir)
-{
-	if (dir->d_name[0] == '.')
-		return 0;
-	else
-		return 1;
-}
-
-struct thread_map *thread_map__new_by_pid(pid_t pid)
-{
-	struct thread_map *threads;
-	char name[256];
-	int items;
-	struct dirent **namelist = NULL;
-	int i;
-
-	sprintf(name, "/proc/%d/task", pid);
-	items = scandir(name, &namelist, filter, NULL);
-	if (items <= 0)
-                return NULL;
-
-	threads = malloc(sizeof(*threads) + sizeof(pid_t) * items);
-	if (threads != NULL) {
-		for (i = 0; i < items; i++)
-			threads->map[i] = atoi(namelist[i]->d_name);
-		threads->nr = items;
-	}
-
-	for (i=0; i<items; i++)
-		free(namelist[i]);
-	free(namelist);
-
-	return threads;
-}
-
-struct thread_map *thread_map__new_by_tid(pid_t tid)
-{
-	struct thread_map *threads = malloc(sizeof(*threads) + sizeof(pid_t));
-
-	if (threads != NULL) {
-		threads->map[0] = tid;
-		threads->nr	= 1;
-	}
-
-	return threads;
-}
-
-struct thread_map *thread_map__new(pid_t pid, pid_t tid)
-{
-	if (pid != -1)
-		return thread_map__new_by_pid(pid);
-	return thread_map__new_by_tid(tid);
-}
-
 static struct thread *thread__new(pid_t pid)
 {
 	struct thread *self = zalloc(sizeof(*self));
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index d7574101054a..e5f2401c1b5e 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -18,24 +18,10 @@ struct thread {
 	int			comm_len;
 };
 
-struct thread_map {
-	int nr;
-	int map[];
-};
-
 struct perf_session;
 
 void thread__delete(struct thread *self);
 
-struct thread_map *thread_map__new_by_pid(pid_t pid);
-struct thread_map *thread_map__new_by_tid(pid_t tid);
-struct thread_map *thread_map__new(pid_t pid, pid_t tid);
-
-static inline void thread_map__delete(struct thread_map *threads)
-{
-	free(threads);
-}
-
 int thread__set_comm(struct thread *self, const char *comm);
 int thread__comm_len(struct thread *self);
 struct thread *perf_session__findnew(struct perf_session *self, pid_t pid);
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
new file mode 100644
index 000000000000..a5df131b77c3
--- /dev/null
+++ b/tools/perf/util/thread_map.c
@@ -0,0 +1,64 @@
+#include <dirent.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include "thread_map.h"
+
+/* Skip "." and ".." directories */
+static int filter(const struct dirent *dir)
+{
+	if (dir->d_name[0] == '.')
+		return 0;
+	else
+		return 1;
+}
+
+struct thread_map *thread_map__new_by_pid(pid_t pid)
+{
+	struct thread_map *threads;
+	char name[256];
+	int items;
+	struct dirent **namelist = NULL;
+	int i;
+
+	sprintf(name, "/proc/%d/task", pid);
+	items = scandir(name, &namelist, filter, NULL);
+	if (items <= 0)
+                return NULL;
+
+	threads = malloc(sizeof(*threads) + sizeof(pid_t) * items);
+	if (threads != NULL) {
+		for (i = 0; i < items; i++)
+			threads->map[i] = atoi(namelist[i]->d_name);
+		threads->nr = items;
+	}
+
+	for (i=0; i<items; i++)
+		free(namelist[i]);
+	free(namelist);
+
+	return threads;
+}
+
+struct thread_map *thread_map__new_by_tid(pid_t tid)
+{
+	struct thread_map *threads = malloc(sizeof(*threads) + sizeof(pid_t));
+
+	if (threads != NULL) {
+		threads->map[0] = tid;
+		threads->nr	= 1;
+	}
+
+	return threads;
+}
+
+struct thread_map *thread_map__new(pid_t pid, pid_t tid)
+{
+	if (pid != -1)
+		return thread_map__new_by_pid(pid);
+	return thread_map__new_by_tid(tid);
+}
+
+void thread_map__delete(struct thread_map *threads)
+{
+	free(threads);
+}
diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h
new file mode 100644
index 000000000000..3cb907311409
--- /dev/null
+++ b/tools/perf/util/thread_map.h
@@ -0,0 +1,15 @@
+#ifndef __PERF_THREAD_MAP_H
+#define __PERF_THREAD_MAP_H
+
+#include <sys/types.h>
+
+struct thread_map {
+	int nr;
+	int map[];
+};
+
+struct thread_map *thread_map__new_by_pid(pid_t pid);
+struct thread_map *thread_map__new_by_tid(pid_t tid);
+struct thread_map *thread_map__new(pid_t pid, pid_t tid);
+void thread_map__delete(struct thread_map *threads);
+#endif	/* __PERF_THREAD_MAP_H */
diff --git a/tools/perf/util/top.c b/tools/perf/util/top.c
new file mode 100644
index 000000000000..75cfe4d45119
--- /dev/null
+++ b/tools/perf/util/top.c
@@ -0,0 +1,238 @@
+/*
+ * Copyright (C) 2011, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Refactored from builtin-top.c, see that files for further copyright notes.
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+
+#include "cpumap.h"
+#include "event.h"
+#include "evlist.h"
+#include "evsel.h"
+#include "parse-events.h"
+#include "symbol.h"
+#include "top.h"
+#include <inttypes.h>
+
+/*
+ * Ordering weight: count-1 * count-2 * ... / count-n
+ */
+static double sym_weight(const struct sym_entry *sym, struct perf_top *top)
+{
+	double weight = sym->snap_count;
+	int counter;
+
+	if (!top->display_weighted)
+		return weight;
+
+	for (counter = 1; counter < top->evlist->nr_entries - 1; counter++)
+		weight *= sym->count[counter];
+
+	weight /= (sym->count[counter] + 1);
+
+	return weight;
+}
+
+static void perf_top__remove_active_sym(struct perf_top *top, struct sym_entry *syme)
+{
+	pthread_mutex_lock(&top->active_symbols_lock);
+	list_del_init(&syme->node);
+	pthread_mutex_unlock(&top->active_symbols_lock);
+}
+
+static void rb_insert_active_sym(struct rb_root *tree, struct sym_entry *se)
+{
+	struct rb_node **p = &tree->rb_node;
+	struct rb_node *parent = NULL;
+	struct sym_entry *iter;
+
+	while (*p != NULL) {
+		parent = *p;
+		iter = rb_entry(parent, struct sym_entry, rb_node);
+
+		if (se->weight > iter->weight)
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
+	}
+
+	rb_link_node(&se->rb_node, parent, p);
+	rb_insert_color(&se->rb_node, tree);
+}
+
+#define SNPRINTF(buf, size, fmt, args...) \
+({ \
+	size_t r = snprintf(buf, size, fmt, ## args); \
+	r > size ?  size : r; \
+})
+
+size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size)
+{
+	struct perf_evsel *counter;
+	float samples_per_sec = top->samples / top->delay_secs;
+	float ksamples_per_sec = top->kernel_samples / top->delay_secs;
+	float esamples_percent = (100.0 * top->exact_samples) / top->samples;
+	size_t ret = 0;
+
+	if (!perf_guest) {
+		ret = SNPRINTF(bf, size,
+			       "   PerfTop:%8.0f irqs/sec  kernel:%4.1f%%"
+			       "  exact: %4.1f%% [", samples_per_sec,
+			       100.0 - (100.0 * ((samples_per_sec - ksamples_per_sec) /
+					samples_per_sec)),
+				esamples_percent);
+	} else {
+		float us_samples_per_sec = top->us_samples / top->delay_secs;
+		float guest_kernel_samples_per_sec = top->guest_kernel_samples / top->delay_secs;
+		float guest_us_samples_per_sec = top->guest_us_samples / top->delay_secs;
+
+		ret = SNPRINTF(bf, size,
+			       "   PerfTop:%8.0f irqs/sec  kernel:%4.1f%% us:%4.1f%%"
+			       " guest kernel:%4.1f%% guest us:%4.1f%%"
+			       " exact: %4.1f%% [", samples_per_sec,
+			       100.0 - (100.0 * ((samples_per_sec - ksamples_per_sec) /
+						 samples_per_sec)),
+			       100.0 - (100.0 * ((samples_per_sec - us_samples_per_sec) /
+						 samples_per_sec)),
+			       100.0 - (100.0 * ((samples_per_sec -
+						  guest_kernel_samples_per_sec) /
+						 samples_per_sec)),
+			       100.0 - (100.0 * ((samples_per_sec -
+						  guest_us_samples_per_sec) /
+						 samples_per_sec)),
+			       esamples_percent);
+	}
+
+	if (top->evlist->nr_entries == 1 || !top->display_weighted) {
+		struct perf_evsel *first;
+		first = list_entry(top->evlist->entries.next, struct perf_evsel, node);
+		ret += SNPRINTF(bf + ret, size - ret, "%" PRIu64 "%s ",
+				(uint64_t)first->attr.sample_period,
+				top->freq ? "Hz" : "");
+	}
+
+	if (!top->display_weighted) {
+		ret += SNPRINTF(bf + ret, size - ret, "%s",
+				event_name(top->sym_evsel));
+	} else {
+		/*
+		 * Don't let events eat all the space. Leaving 30 bytes
+		 * for the rest should be enough.
+		 */
+		size_t last_pos = size - 30;
+
+		list_for_each_entry(counter, &top->evlist->entries, node) {
+			ret += SNPRINTF(bf + ret, size - ret, "%s%s",
+					counter->idx ? "/" : "",
+					event_name(counter));
+			if (ret > last_pos) {
+				sprintf(bf + last_pos - 3, "..");
+				ret = last_pos - 1;
+				break;
+			}
+		}
+	}
+
+	ret += SNPRINTF(bf + ret, size - ret, "], ");
+
+	if (top->target_pid != -1)
+		ret += SNPRINTF(bf + ret, size - ret, " (target_pid: %d",
+				top->target_pid);
+	else if (top->target_tid != -1)
+		ret += SNPRINTF(bf + ret, size - ret, " (target_tid: %d",
+				top->target_tid);
+	else
+		ret += SNPRINTF(bf + ret, size - ret, " (all");
+
+	if (top->cpu_list)
+		ret += SNPRINTF(bf + ret, size - ret, ", CPU%s: %s)",
+				top->evlist->cpus->nr > 1 ? "s" : "", top->cpu_list);
+	else {
+		if (top->target_tid != -1)
+			ret += SNPRINTF(bf + ret, size - ret, ")");
+		else
+			ret += SNPRINTF(bf + ret, size - ret, ", %d CPU%s)",
+					top->evlist->cpus->nr,
+					top->evlist->cpus->nr > 1 ? "s" : "");
+	}
+
+	return ret;
+}
+
+void perf_top__reset_sample_counters(struct perf_top *top)
+{
+	top->samples = top->us_samples = top->kernel_samples =
+	top->exact_samples = top->guest_kernel_samples =
+	top->guest_us_samples = 0;
+}
+
+float perf_top__decay_samples(struct perf_top *top, struct rb_root *root)
+{
+	struct sym_entry *syme, *n;
+	float sum_ksamples = 0.0;
+	int snap = !top->display_weighted ? top->sym_counter : 0, j;
+
+	/* Sort the active symbols */
+	pthread_mutex_lock(&top->active_symbols_lock);
+	syme = list_entry(top->active_symbols.next, struct sym_entry, node);
+	pthread_mutex_unlock(&top->active_symbols_lock);
+
+	top->rb_entries = 0;
+	list_for_each_entry_safe_from(syme, n, &top->active_symbols, node) {
+		syme->snap_count = syme->count[snap];
+		if (syme->snap_count != 0) {
+
+			if ((top->hide_user_symbols &&
+			     syme->origin == PERF_RECORD_MISC_USER) ||
+			    (top->hide_kernel_symbols &&
+			     syme->origin == PERF_RECORD_MISC_KERNEL)) {
+				perf_top__remove_active_sym(top, syme);
+				continue;
+			}
+			syme->weight = sym_weight(syme, top);
+
+			if ((int)syme->snap_count >= top->count_filter) {
+				rb_insert_active_sym(root, syme);
+				++top->rb_entries;
+			}
+			sum_ksamples += syme->snap_count;
+
+			for (j = 0; j < top->evlist->nr_entries; j++)
+				syme->count[j] = top->zero ? 0 : syme->count[j] * 7 / 8;
+		} else
+			perf_top__remove_active_sym(top, syme);
+	}
+
+	return sum_ksamples;
+}
+
+/*
+ * Find the longest symbol name that will be displayed
+ */
+void perf_top__find_widths(struct perf_top *top, struct rb_root *root,
+			   int *dso_width, int *dso_short_width, int *sym_width)
+{
+	struct rb_node *nd;
+	int printed = 0;
+
+	*sym_width = *dso_width = *dso_short_width = 0;
+
+	for (nd = rb_first(root); nd; nd = rb_next(nd)) {
+		struct sym_entry *syme = rb_entry(nd, struct sym_entry, rb_node);
+		struct symbol *sym = sym_entry__symbol(syme);
+
+		if (++printed > top->print_entries ||
+		    (int)syme->snap_count < top->count_filter)
+			continue;
+
+		if (syme->map->dso->long_name_len > *dso_width)
+			*dso_width = syme->map->dso->long_name_len;
+
+		if (syme->map->dso->short_name_len > *dso_short_width)
+			*dso_short_width = syme->map->dso->short_name_len;
+
+		if (sym->namelen > *sym_width)
+			*sym_width = sym->namelen;
+	}
+}
diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h
new file mode 100644
index 000000000000..96d1cb78af01
--- /dev/null
+++ b/tools/perf/util/top.h
@@ -0,0 +1,66 @@
+#ifndef __PERF_TOP_H
+#define __PERF_TOP_H 1
+
+#include "types.h"
+#include "../perf.h"
+#include <stddef.h>
+#include <pthread.h>
+#include <linux/list.h>
+#include <linux/rbtree.h>
+
+struct perf_evlist;
+struct perf_evsel;
+
+struct sym_entry {
+	struct rb_node		rb_node;
+	struct list_head	node;
+	unsigned long		snap_count;
+	double			weight;
+	int			skip;
+	u8			origin;
+	struct map		*map;
+	unsigned long		count[0];
+};
+
+static inline struct symbol *sym_entry__symbol(struct sym_entry *self)
+{
+       return ((void *)self) + symbol_conf.priv_size;
+}
+
+struct perf_top {
+	struct perf_evlist *evlist;
+	/*
+	 * Symbols will be added here in perf_event__process_sample and will
+	 * get out after decayed.
+	 */
+	struct list_head   active_symbols;
+	pthread_mutex_t	   active_symbols_lock;
+	pthread_cond_t	   active_symbols_cond;
+	u64		   samples;
+	u64		   kernel_samples, us_samples;
+	u64		   exact_samples;
+	u64		   guest_us_samples, guest_kernel_samples;
+	int		   print_entries, count_filter, delay_secs;
+	int		   display_weighted, freq, rb_entries, sym_counter;
+	pid_t		   target_pid, target_tid;
+	bool		   hide_kernel_symbols, hide_user_symbols, zero;
+	const char	   *cpu_list;
+	struct sym_entry   *sym_filter_entry;
+	struct perf_evsel  *sym_evsel;
+};
+
+size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size);
+void perf_top__reset_sample_counters(struct perf_top *top);
+float perf_top__decay_samples(struct perf_top *top, struct rb_root *root);
+void perf_top__find_widths(struct perf_top *top, struct rb_root *root,
+			   int *dso_width, int *dso_short_width, int *sym_width);
+
+#ifdef NO_NEWT_SUPPORT
+static inline int perf_top__tui_browser(struct perf_top *top __used)
+{
+	return 0;
+}
+#else
+int perf_top__tui_browser(struct perf_top *top);
+#endif
+#endif /* __PERF_TOP_H */
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index 73a02223c629..d8e622dd738a 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -153,7 +153,7 @@ void parse_proc_kallsyms(char *file, unsigned int size __unused)
 	char *next = NULL;
 	char *addr_str;
 	char ch;
-	int ret;
+	int ret __used;
 	int i;
 
 	line = strtok_r(file, "\n", &next);
diff --git a/tools/perf/util/ui/browser.c b/tools/perf/util/ui/browser.c
index 8bc010edca25..611219f80680 100644
--- a/tools/perf/util/ui/browser.c
+++ b/tools/perf/util/ui/browser.c
@@ -1,4 +1,5 @@
 #include "libslang.h"
+#include "ui.h"
 #include <linux/compiler.h>
 #include <linux/list.h>
 #include <linux/rbtree.h>
@@ -156,6 +157,20 @@ void ui_browser__add_exit_keys(struct ui_browser *self, int keys[])
 	}
 }
 
+void __ui_browser__show_title(struct ui_browser *browser, const char *title)
+{
+	SLsmg_gotorc(0, 0);
+	ui_browser__set_color(browser, NEWT_COLORSET_ROOT);
+	slsmg_write_nstring(title, browser->width);
+}
+
+void ui_browser__show_title(struct ui_browser *browser, const char *title)
+{
+	pthread_mutex_lock(&ui__lock);
+	__ui_browser__show_title(browser, title);
+	pthread_mutex_unlock(&ui__lock);
+}
+
 int ui_browser__show(struct ui_browser *self, const char *title,
 		     const char *helpline, ...)
 {
@@ -178,9 +193,8 @@ int ui_browser__show(struct ui_browser *self, const char *title,
 	if (self->sb == NULL)
 		return -1;
 
-	SLsmg_gotorc(0, 0);
-	ui_browser__set_color(self, NEWT_COLORSET_ROOT);
-	slsmg_write_nstring(title, self->width);
+	pthread_mutex_lock(&ui__lock);
+	__ui_browser__show_title(self, title);
 
 	ui_browser__add_exit_keys(self, keys);
 	newtFormAddComponent(self->form, self->sb);
@@ -188,25 +202,30 @@ int ui_browser__show(struct ui_browser *self, const char *title,
 	va_start(ap, helpline);
 	ui_helpline__vpush(helpline, ap);
 	va_end(ap);
+	pthread_mutex_unlock(&ui__lock);
 	return 0;
 }
 
 void ui_browser__hide(struct ui_browser *self)
 {
+	pthread_mutex_lock(&ui__lock);
 	newtFormDestroy(self->form);
 	self->form = NULL;
 	ui_helpline__pop();
+	pthread_mutex_unlock(&ui__lock);
 }
 
 int ui_browser__refresh(struct ui_browser *self)
 {
 	int row;
 
+	pthread_mutex_lock(&ui__lock);
 	newtScrollbarSet(self->sb, self->index, self->nr_entries - 1);
 	row = self->refresh(self);
 	ui_browser__set_color(self, HE_COLORSET_NORMAL);
 	SLsmg_fill_region(self->y + row, self->x,
 			  self->height - row, self->width, ' ');
+	pthread_mutex_unlock(&ui__lock);
 
 	return 0;
 }
diff --git a/tools/perf/util/ui/browser.h b/tools/perf/util/ui/browser.h
index 0dc7e4da36f5..fc63dda10910 100644
--- a/tools/perf/util/ui/browser.h
+++ b/tools/perf/util/ui/browser.h
@@ -24,7 +24,6 @@ struct ui_browser {
 	u32	      nr_entries;
 };
 
-
 void ui_browser__set_color(struct ui_browser *self, int color);
 void ui_browser__set_percent_color(struct ui_browser *self,
 				   double percent, bool current);
@@ -35,6 +34,8 @@ void ui_browser__reset_index(struct ui_browser *self);
 void ui_browser__gotorc(struct ui_browser *self, int y, int x);
 void ui_browser__add_exit_key(struct ui_browser *self, int key);
 void ui_browser__add_exit_keys(struct ui_browser *self, int keys[]);
+void __ui_browser__show_title(struct ui_browser *browser, const char *title);
+void ui_browser__show_title(struct ui_browser *browser, const char *title);
 int ui_browser__show(struct ui_browser *self, const char *title,
 		     const char *helpline, ...);
 void ui_browser__hide(struct ui_browser *self);
diff --git a/tools/perf/util/ui/browsers/annotate.c b/tools/perf/util/ui/browsers/annotate.c
index 82b78f99251b..8c17a8730e4a 100644
--- a/tools/perf/util/ui/browsers/annotate.c
+++ b/tools/perf/util/ui/browsers/annotate.c
@@ -1,9 +1,12 @@
 #include "../browser.h"
 #include "../helpline.h"
 #include "../libslang.h"
+#include "../../annotate.h"
 #include "../../hist.h"
 #include "../../sort.h"
 #include "../../symbol.h"
+#include "../../annotate.h"
+#include <pthread.h>
 
 static void ui__error_window(const char *fmt, ...)
 {
@@ -42,8 +45,6 @@ static void annotate_browser__write(struct ui_browser *self, void *entry, int ro
 		struct objdump_line_rb_node *olrb = objdump_line__rb(ol);
 		ui_browser__set_percent_color(self, olrb->percent, current_entry);
 		slsmg_printf(" %7.2f ", olrb->percent);
-		if (!current_entry)
-			ui_browser__set_color(self, HE_COLORSET_CODE);
 	} else {
 		ui_browser__set_percent_color(self, 0, current_entry);
 		slsmg_write_nstring(" ", 9);
@@ -55,35 +56,40 @@ static void annotate_browser__write(struct ui_browser *self, void *entry, int ro
 		slsmg_write_nstring(" ", width - 18);
 	else
 		slsmg_write_nstring(ol->line, width - 18);
+
+	if (!current_entry)
+		ui_browser__set_color(self, HE_COLORSET_CODE);
 }
 
 static double objdump_line__calc_percent(struct objdump_line *self,
-					 struct list_head *head,
-					 struct symbol *sym)
+					 struct symbol *sym, int evidx)
 {
 	double percent = 0.0;
 
 	if (self->offset != -1) {
 		int len = sym->end - sym->start;
 		unsigned int hits = 0;
-		struct sym_priv *priv = symbol__priv(sym);
-		struct sym_ext *sym_ext = priv->ext;
-		struct sym_hist *h = priv->hist;
+		struct annotation *notes = symbol__annotation(sym);
+		struct source_line *src_line = notes->src->lines;
+		struct sym_hist *h = annotation__histogram(notes, evidx);
 		s64 offset = self->offset;
-		struct objdump_line *next = objdump__get_next_ip_line(head, self);
-
+		struct objdump_line *next;
 
+		next = objdump__get_next_ip_line(&notes->src->source, self);
 		while (offset < (s64)len &&
 		       (next == NULL || offset < next->offset)) {
-			if (sym_ext) {
-				percent += sym_ext[offset].percent;
+			if (src_line) {
+				percent += src_line[offset].percent;
 			} else
-				hits += h->ip[offset];
+				hits += h->addr[offset];
 
 			++offset;
 		}
-
-		if (sym_ext == NULL && h->sum)
+		/*
+ 		 * If the percentage wasn't already calculated in
+ 		 * symbol__get_source_line, do it now:
+ 		 */
+		if (src_line == NULL && h->sum)
 			percent = 100.0 * hits / h->sum;
 	}
 
@@ -133,103 +139,161 @@ static void annotate_browser__set_top(struct annotate_browser *self,
 	self->curr_hot = nd;
 }
 
-static int annotate_browser__run(struct annotate_browser *self)
+static void annotate_browser__calc_percent(struct annotate_browser *browser,
+					   int evidx)
 {
-	struct rb_node *nd;
-	struct hist_entry *he = self->b.priv;
-	int key;
+	struct symbol *sym = browser->b.priv;
+	struct annotation *notes = symbol__annotation(sym);
+	struct objdump_line *pos;
 
-	if (ui_browser__show(&self->b, he->ms.sym->name,
-			     "<-, -> or ESC: exit, TAB/shift+TAB: cycle thru samples") < 0)
-		return -1;
+	browser->entries = RB_ROOT;
+
+	pthread_mutex_lock(&notes->lock);
+
+	list_for_each_entry(pos, &notes->src->source, node) {
+		struct objdump_line_rb_node *rbpos = objdump_line__rb(pos);
+		rbpos->percent = objdump_line__calc_percent(pos, sym, evidx);
+		if (rbpos->percent < 0.01) {
+			RB_CLEAR_NODE(&rbpos->rb_node);
+			continue;
+		}
+		objdump__insert_line(&browser->entries, rbpos);
+	}
+	pthread_mutex_unlock(&notes->lock);
+
+	browser->curr_hot = rb_last(&browser->entries);
+}
+
+static int annotate_browser__run(struct annotate_browser *self, int evidx,
+				 int refresh)
+{
+	struct rb_node *nd = NULL;
+	struct symbol *sym = self->b.priv;
 	/*
-	 * To allow builtin-annotate to cycle thru multiple symbols by
+	 * RIGHT To allow builtin-annotate to cycle thru multiple symbols by
 	 * examining the exit key for this function.
 	 */
-	ui_browser__add_exit_key(&self->b, NEWT_KEY_RIGHT);
+	int exit_keys[] = { 'H', NEWT_KEY_TAB, NEWT_KEY_UNTAB,
+			    NEWT_KEY_RIGHT, 0 };
+	int key;
+
+	if (ui_browser__show(&self->b, sym->name,
+			     "<-, -> or ESC: exit, TAB/shift+TAB: "
+			     "cycle hottest lines, H: Hottest") < 0)
+		return -1;
+
+	ui_browser__add_exit_keys(&self->b, exit_keys);
+	annotate_browser__calc_percent(self, evidx);
+
+	if (self->curr_hot)
+		annotate_browser__set_top(self, self->curr_hot);
 
 	nd = self->curr_hot;
-	if (nd) {
-		int tabs[] = { NEWT_KEY_TAB, NEWT_KEY_UNTAB, 0 };
-		ui_browser__add_exit_keys(&self->b, tabs);
-	}
+
+	if (refresh != 0)
+		newtFormSetTimer(self->b.form, refresh);
 
 	while (1) {
 		key = ui_browser__run(&self->b);
 
+		if (refresh != 0) {
+			annotate_browser__calc_percent(self, evidx);
+			/*
+			 * Current line focus got out of the list of most active
+			 * lines, NULL it so that if TAB|UNTAB is pressed, we
+			 * move to curr_hot (current hottest line).
+			 */
+			if (nd != NULL && RB_EMPTY_NODE(nd))
+				nd = NULL;
+		}
+
 		switch (key) {
+		case -1:
+			/*
+ 			 * FIXME we need to check if it was
+ 			 * es.reason == NEWT_EXIT_TIMER
+ 			 */
+			if (refresh != 0)
+				symbol__annotate_decay_histogram(sym, evidx);
+			continue;
 		case NEWT_KEY_TAB:
-			nd = rb_prev(nd);
-			if (nd == NULL)
-				nd = rb_last(&self->entries);
-			annotate_browser__set_top(self, nd);
+			if (nd != NULL) {
+				nd = rb_prev(nd);
+				if (nd == NULL)
+					nd = rb_last(&self->entries);
+			} else
+				nd = self->curr_hot;
 			break;
 		case NEWT_KEY_UNTAB:
-			nd = rb_next(nd);
-			if (nd == NULL)
-				nd = rb_first(&self->entries);
-			annotate_browser__set_top(self, nd);
+			if (nd != NULL)
+				nd = rb_next(nd);
+				if (nd == NULL)
+					nd = rb_first(&self->entries);
+			else
+				nd = self->curr_hot;
+			break;
+		case 'H':
+			nd = self->curr_hot;
 			break;
 		default:
 			goto out;
 		}
+
+		if (nd != NULL)
+			annotate_browser__set_top(self, nd);
 	}
 out:
 	ui_browser__hide(&self->b);
 	return key;
 }
 
-int hist_entry__tui_annotate(struct hist_entry *self)
+int hist_entry__tui_annotate(struct hist_entry *he, int evidx)
+{
+	return symbol__tui_annotate(he->ms.sym, he->ms.map, evidx, 0);
+}
+
+int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx,
+			 int refresh)
 {
 	struct objdump_line *pos, *n;
-	struct objdump_line_rb_node *rbpos;
-	LIST_HEAD(head);
+	struct annotation *notes = symbol__annotation(sym);
 	struct annotate_browser browser = {
 		.b = {
-			.entries = &head,
+			.entries = &notes->src->source,
 			.refresh = ui_browser__list_head_refresh,
 			.seek	 = ui_browser__list_head_seek,
 			.write	 = annotate_browser__write,
-			.priv	 = self,
+			.priv	 = sym,
 		},
 	};
 	int ret;
 
-	if (self->ms.sym == NULL)
+	if (sym == NULL)
 		return -1;
 
-	if (self->ms.map->dso->annotate_warned)
+	if (map->dso->annotate_warned)
 		return -1;
 
-	if (hist_entry__annotate(self, &head, sizeof(*rbpos)) < 0) {
+	if (symbol__annotate(sym, map, sizeof(struct objdump_line_rb_node)) < 0) {
 		ui__error_window(ui_helpline__last_msg);
 		return -1;
 	}
 
 	ui_helpline__push("Press <- or ESC to exit");
 
-	list_for_each_entry(pos, &head, node) {
+	list_for_each_entry(pos, &notes->src->source, node) {
+		struct objdump_line_rb_node *rbpos;
 		size_t line_len = strlen(pos->line);
+
 		if (browser.b.width < line_len)
 			browser.b.width = line_len;
 		rbpos = objdump_line__rb(pos);
 		rbpos->idx = browser.b.nr_entries++;
-		rbpos->percent = objdump_line__calc_percent(pos, &head, self->ms.sym);
-		if (rbpos->percent < 0.01)
-			continue;
-		objdump__insert_line(&browser.entries, rbpos);
 	}
 
-	/*
-	 * Position the browser at the hottest line.
-	 */
-	browser.curr_hot = rb_last(&browser.entries);
-	if (browser.curr_hot)
-		annotate_browser__set_top(&browser, browser.curr_hot);
-
 	browser.b.width += 18; /* Percentage */
-	ret = annotate_browser__run(&browser);
-	list_for_each_entry_safe(pos, n, &head, node) {
+	ret = annotate_browser__run(&browser, evidx, refresh);
+	list_for_each_entry_safe(pos, n, &notes->src->source, node) {
 		list_del(&pos->node);
 		objdump_line__free(pos);
 	}
diff --git a/tools/perf/util/ui/browsers/hists.c b/tools/perf/util/ui/browsers/hists.c
index 60c463c16028..798efdca3ead 100644
--- a/tools/perf/util/ui/browsers/hists.c
+++ b/tools/perf/util/ui/browsers/hists.c
@@ -7,6 +7,8 @@
 #include <newt.h>
 #include <linux/rbtree.h>
 
+#include "../../evsel.h"
+#include "../../evlist.h"
 #include "../../hist.h"
 #include "../../pstack.h"
 #include "../../sort.h"
@@ -292,7 +294,8 @@ static int hist_browser__run(struct hist_browser *self, const char *title)
 {
 	int key;
 	int exit_keys[] = { 'a', '?', 'h', 'C', 'd', 'D', 'E', 't',
-			    NEWT_KEY_ENTER, NEWT_KEY_RIGHT, NEWT_KEY_LEFT, 0, };
+			    NEWT_KEY_ENTER, NEWT_KEY_RIGHT, NEWT_KEY_LEFT,
+			    NEWT_KEY_TAB, NEWT_KEY_UNTAB, 0, };
 
 	self->b.entries = &self->hists->entries;
 	self->b.nr_entries = self->hists->nr_entries;
@@ -377,7 +380,7 @@ static int hist_browser__show_callchain_node_rb_tree(struct hist_browser *self,
 	while (node) {
 		struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
 		struct rb_node *next = rb_next(node);
-		u64 cumul = cumul_hits(child);
+		u64 cumul = callchain_cumul_hits(child);
 		struct callchain_list *chain;
 		char folded_sign = ' ';
 		int first = true;
@@ -638,6 +641,9 @@ static void ui_browser__hists_seek(struct ui_browser *self,
 	struct rb_node *nd;
 	bool first = true;
 
+	if (self->nr_entries == 0)
+		return;
+
 	switch (whence) {
 	case SEEK_SET:
 		nd = hists__filter_entries(rb_first(self->entries));
@@ -797,8 +803,11 @@ static int hists__browser_title(struct hists *self, char *bf, size_t size,
 	return printed;
 }
 
-int hists__browse(struct hists *self, const char *helpline, const char *ev_name)
+static int perf_evsel__hists_browse(struct perf_evsel *evsel,
+				    const char *helpline, const char *ev_name,
+				    bool left_exits)
 {
+	struct hists *self = &evsel->hists;
 	struct hist_browser *browser = hist_browser__new(self);
 	struct pstack *fstack;
 	const struct thread *thread_filter = NULL;
@@ -818,8 +827,8 @@ int hists__browse(struct hists *self, const char *helpline, const char *ev_name)
 	hists__browser_title(self, msg, sizeof(msg), ev_name,
 			     dso_filter, thread_filter);
 	while (1) {
-		const struct thread *thread;
-		const struct dso *dso;
+		const struct thread *thread = NULL;
+		const struct dso *dso = NULL;
 		char *options[16];
 		int nr_options = 0, choice = 0, i,
 		    annotate = -2, zoom_dso = -2, zoom_thread = -2,
@@ -827,8 +836,10 @@ int hists__browse(struct hists *self, const char *helpline, const char *ev_name)
 
 		key = hist_browser__run(browser, msg);
 
-		thread = hist_browser__selected_thread(browser);
-		dso = browser->selection->map ? browser->selection->map->dso : NULL;
+		if (browser->he_selection != NULL) {
+			thread = hist_browser__selected_thread(browser);
+			dso = browser->selection->map ? browser->selection->map->dso : NULL;
+		}
 
 		switch (key) {
 		case NEWT_KEY_TAB:
@@ -839,7 +850,8 @@ int hists__browse(struct hists *self, const char *helpline, const char *ev_name)
 			 */
 			goto out_free_stack;
 		case 'a':
-			if (browser->selection->map == NULL &&
+			if (browser->selection == NULL ||
+			    browser->selection->map == NULL ||
 			    browser->selection->map->dso->annotate_warned)
 				continue;
 			goto do_annotate;
@@ -858,6 +870,7 @@ int hists__browse(struct hists *self, const char *helpline, const char *ev_name)
 					"E         Expand all callchains\n"
 					"d         Zoom into current DSO\n"
 					"t         Zoom into current Thread\n"
+					"TAB/UNTAB Switch events\n"
 					"q/CTRL+C  Exit browser");
 			continue;
 		case NEWT_KEY_ENTER:
@@ -867,8 +880,14 @@ int hists__browse(struct hists *self, const char *helpline, const char *ev_name)
 		case NEWT_KEY_LEFT: {
 			const void *top;
 
-			if (pstack__empty(fstack))
+			if (pstack__empty(fstack)) {
+				/*
+				 * Go back to the perf_evsel_menu__run or other user
+				 */
+				if (left_exits)
+					goto out_free_stack;
 				continue;
+			}
 			top = pstack__pop(fstack);
 			if (top == &dso_filter)
 				goto zoom_out_dso;
@@ -877,14 +896,16 @@ int hists__browse(struct hists *self, const char *helpline, const char *ev_name)
 			continue;
 		}
 		case NEWT_KEY_ESCAPE:
-			if (!ui__dialog_yesno("Do you really want to exit?"))
+			if (!left_exits &&
+			    !ui__dialog_yesno("Do you really want to exit?"))
 				continue;
 			/* Fall thru */
 		default:
 			goto out_free_stack;
 		}
 
-		if (browser->selection->sym != NULL &&
+		if (browser->selection != NULL &&
+		    browser->selection->sym != NULL &&
 		    !browser->selection->map->dso->annotate_warned &&
 		    asprintf(&options[nr_options], "Annotate %s",
 			     browser->selection->sym->name) > 0)
@@ -903,7 +924,8 @@ int hists__browse(struct hists *self, const char *helpline, const char *ev_name)
 			     (dso->kernel ? "the Kernel" : dso->short_name)) > 0)
 			zoom_dso = nr_options++;
 
-		if (browser->selection->map != NULL &&
+		if (browser->selection != NULL &&
+		    browser->selection->map != NULL &&
 		    asprintf(&options[nr_options], "Browse map details") > 0)
 			browse_map = nr_options++;
 
@@ -923,19 +945,11 @@ int hists__browse(struct hists *self, const char *helpline, const char *ev_name)
 		if (choice == annotate) {
 			struct hist_entry *he;
 do_annotate:
-			if (browser->selection->map->dso->origin == DSO__ORIG_KERNEL) {
-				browser->selection->map->dso->annotate_warned = 1;
-				ui_helpline__puts("No vmlinux file found, can't "
-						 "annotate with just a "
-						 "kallsyms file");
-				continue;
-			}
-
 			he = hist_browser__selected_entry(browser);
 			if (he == NULL)
 				continue;
 
-			hist_entry__tui_annotate(he);
+			hist_entry__tui_annotate(he, evsel->idx);
 		} else if (choice == browse_map)
 			map__browse(browser->selection->map);
 		else if (choice == zoom_dso) {
@@ -984,30 +998,141 @@ out:
 	return key;
 }
 
-int hists__tui_browse_tree(struct rb_root *self, const char *help)
+struct perf_evsel_menu {
+	struct ui_browser b;
+	struct perf_evsel *selection;
+};
+
+static void perf_evsel_menu__write(struct ui_browser *browser,
+				   void *entry, int row)
+{
+	struct perf_evsel_menu *menu = container_of(browser,
+						    struct perf_evsel_menu, b);
+	struct perf_evsel *evsel = list_entry(entry, struct perf_evsel, node);
+	bool current_entry = ui_browser__is_current_entry(browser, row);
+	unsigned long nr_events = evsel->hists.stats.nr_events[PERF_RECORD_SAMPLE];
+	const char *ev_name = event_name(evsel);
+	char bf[256], unit;
+
+	ui_browser__set_color(browser, current_entry ? HE_COLORSET_SELECTED :
+						       HE_COLORSET_NORMAL);
+
+	nr_events = convert_unit(nr_events, &unit);
+	snprintf(bf, sizeof(bf), "%lu%c%s%s", nr_events,
+		 unit, unit == ' ' ? "" : " ", ev_name);
+	slsmg_write_nstring(bf, browser->width);
+
+	if (current_entry)
+		menu->selection = evsel;
+}
+
+static int perf_evsel_menu__run(struct perf_evsel_menu *menu, const char *help)
 {
-	struct rb_node *first = rb_first(self), *nd = first, *next;
-	int key = 0;
+	int exit_keys[] = { NEWT_KEY_ENTER, NEWT_KEY_RIGHT, 0, };
+	struct perf_evlist *evlist = menu->b.priv;
+	struct perf_evsel *pos;
+	const char *ev_name, *title = "Available samples";
+	int key;
+
+	if (ui_browser__show(&menu->b, title,
+			     "ESC: exit, ENTER|->: Browse histograms") < 0)
+		return -1;
+
+	ui_browser__add_exit_keys(&menu->b, exit_keys);
 
-	while (nd) {
-		struct hists *hists = rb_entry(nd, struct hists, rb_node);
-		const char *ev_name = __event_name(hists->type, hists->config);
+	while (1) {
+		key = ui_browser__run(&menu->b);
 
-		key = hists__browse(hists, help, ev_name);
 		switch (key) {
-		case NEWT_KEY_TAB:
-			next = rb_next(nd);
-			if (next)
-				nd = next;
+		case NEWT_KEY_RIGHT:
+		case NEWT_KEY_ENTER:
+			if (!menu->selection)
+				continue;
+			pos = menu->selection;
+browse_hists:
+			ev_name = event_name(pos);
+			key = perf_evsel__hists_browse(pos, help, ev_name, true);
+			ui_browser__show_title(&menu->b, title);
 			break;
-		case NEWT_KEY_UNTAB:
-			if (nd == first)
+		case NEWT_KEY_LEFT:
+			continue;
+		case NEWT_KEY_ESCAPE:
+			if (!ui__dialog_yesno("Do you really want to exit?"))
 				continue;
-			nd = rb_prev(nd);
+			/* Fall thru */
+		default:
+			goto out;
+		}
+
+		switch (key) {
+		case NEWT_KEY_TAB:
+			if (pos->node.next == &evlist->entries)
+				pos = list_entry(evlist->entries.next, struct perf_evsel, node);
+			else
+				pos = list_entry(pos->node.next, struct perf_evsel, node);
+			goto browse_hists;
+		case NEWT_KEY_UNTAB:
+			if (pos->node.prev == &evlist->entries)
+				pos = list_entry(evlist->entries.prev, struct perf_evsel, node);
+			else
+				pos = list_entry(pos->node.prev, struct perf_evsel, node);
+			goto browse_hists;
+		case 'q':
+		case CTRL('c'):
+			goto out;
 		default:
-			return key;
+			break;
 		}
 	}
 
+out:
+	ui_browser__hide(&menu->b);
 	return key;
 }
+
+static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist,
+					   const char *help)
+{
+	struct perf_evsel *pos;
+	struct perf_evsel_menu menu = {
+		.b = {
+			.entries    = &evlist->entries,
+			.refresh    = ui_browser__list_head_refresh,
+			.seek	    = ui_browser__list_head_seek,
+			.write	    = perf_evsel_menu__write,
+			.nr_entries = evlist->nr_entries,
+			.priv	    = evlist,
+		},
+	};
+
+	ui_helpline__push("Press ESC to exit");
+
+	list_for_each_entry(pos, &evlist->entries, node) {
+		const char *ev_name = event_name(pos);
+		size_t line_len = strlen(ev_name) + 7;
+
+		if (menu.b.width < line_len)
+			menu.b.width = line_len;
+		/*
+		 * Cache the evsel name, tracepoints have a _high_ cost per
+		 * event_name() call.
+		 */
+		if (pos->name == NULL)
+			pos->name = strdup(ev_name);
+	}
+
+	return perf_evsel_menu__run(&menu, help);
+}
+
+int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help)
+{
+
+	if (evlist->nr_entries == 1) {
+		struct perf_evsel *first = list_entry(evlist->entries.next,
+						      struct perf_evsel, node);
+		const char *ev_name = event_name(first);
+		return perf_evsel__hists_browse(first, help, ev_name, false);
+	}
+
+	return __perf_evlist__tui_browse_hists(evlist, help);
+}
diff --git a/tools/perf/util/ui/browsers/map.c b/tools/perf/util/ui/browsers/map.c
index e5158369106e..8462bffe20bc 100644
--- a/tools/perf/util/ui/browsers/map.c
+++ b/tools/perf/util/ui/browsers/map.c
@@ -41,7 +41,7 @@ static int ui_entry__read(const char *title, char *bf, size_t size, int width)
 out_free_form:
 	newtPopWindow();
 	newtFormDestroy(form);
-	return 0;
+	return err;
 }
 
 struct map_browser {
diff --git a/tools/perf/util/ui/browsers/top.c b/tools/perf/util/ui/browsers/top.c
new file mode 100644
index 000000000000..5a06538532af
--- /dev/null
+++ b/tools/perf/util/ui/browsers/top.c
@@ -0,0 +1,213 @@
+/*
+ * Copyright (C) 2011, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Parts came from builtin-{top,stat,record}.c, see those files for further
+ * copyright notes.
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+#include "../browser.h"
+#include "../../annotate.h"
+#include "../helpline.h"
+#include "../libslang.h"
+#include "../util.h"
+#include "../../evlist.h"
+#include "../../hist.h"
+#include "../../sort.h"
+#include "../../symbol.h"
+#include "../../top.h"
+
+struct perf_top_browser {
+	struct ui_browser b;
+	struct rb_root	  root;
+	struct sym_entry  *selection;
+	float		  sum_ksamples;
+	int		  dso_width;
+	int		  dso_short_width;
+	int		  sym_width;
+};
+
+static void perf_top_browser__write(struct ui_browser *browser, void *entry, int row)
+{
+	struct perf_top_browser *top_browser = container_of(browser, struct perf_top_browser, b);
+	struct sym_entry *syme = rb_entry(entry, struct sym_entry, rb_node);
+	bool current_entry = ui_browser__is_current_entry(browser, row);
+	struct symbol *symbol = sym_entry__symbol(syme);
+	struct perf_top *top = browser->priv;
+	int width = browser->width;
+	double pcnt;
+
+	pcnt = 100.0 - (100.0 * ((top_browser->sum_ksamples - syme->snap_count) /
+				 top_browser->sum_ksamples));
+	ui_browser__set_percent_color(browser, pcnt, current_entry);
+
+	if (top->evlist->nr_entries == 1 || !top->display_weighted) {
+		slsmg_printf("%20.2f ", syme->weight);
+		width -= 24;
+	} else {
+		slsmg_printf("%9.1f %10ld ", syme->weight, syme->snap_count);
+		width -= 23;
+	}
+
+	slsmg_printf("%4.1f%%", pcnt);
+	width -= 7;
+
+	if (verbose) {
+		slsmg_printf(" %016" PRIx64, symbol->start);
+		width -= 17;
+	}
+
+	slsmg_printf(" %-*.*s ", top_browser->sym_width, top_browser->sym_width,
+		     symbol->name);
+	width -= top_browser->sym_width;
+	slsmg_write_nstring(width >= syme->map->dso->long_name_len ?
+				syme->map->dso->long_name :
+				syme->map->dso->short_name, width);
+
+	if (current_entry)
+		top_browser->selection = syme;
+}
+
+static void perf_top_browser__update_rb_tree(struct perf_top_browser *browser)
+{
+	struct perf_top *top = browser->b.priv;
+	u64 top_idx = browser->b.top_idx;
+
+	browser->root = RB_ROOT;
+	browser->b.top = NULL;
+	browser->sum_ksamples = perf_top__decay_samples(top, &browser->root);
+	/*
+ 	 * No active symbols
+ 	 */
+	if (top->rb_entries == 0)
+		return;
+
+	perf_top__find_widths(top, &browser->root, &browser->dso_width,
+			      &browser->dso_short_width,
+                              &browser->sym_width);
+	if (browser->sym_width + browser->dso_width > browser->b.width - 29) {
+		browser->dso_width = browser->dso_short_width;
+		if (browser->sym_width + browser->dso_width > browser->b.width - 29)
+			browser->sym_width = browser->b.width - browser->dso_width - 29;
+	}
+
+	/*
+	 * Adjust the ui_browser indexes since the entries in the browser->root
+	 * rb_tree may have changed, then seek it from start, so that we get a
+	 * possible new top of the screen.
+ 	 */
+	browser->b.nr_entries = top->rb_entries;
+
+	if (top_idx >= browser->b.nr_entries) {
+		if (browser->b.height >= browser->b.nr_entries)
+			top_idx = browser->b.nr_entries - browser->b.height;
+		else
+			top_idx = 0;
+	}
+
+	if (browser->b.index >= top_idx + browser->b.height)
+		browser->b.index = top_idx + browser->b.index - browser->b.top_idx;
+
+	if (browser->b.index >= browser->b.nr_entries)
+		browser->b.index = browser->b.nr_entries - 1;
+
+	browser->b.top_idx = top_idx;
+	browser->b.seek(&browser->b, top_idx, SEEK_SET);
+}
+
+static void perf_top_browser__annotate(struct perf_top_browser *browser)
+{
+	struct sym_entry *syme = browser->selection;
+	struct symbol *sym = sym_entry__symbol(syme);
+	struct annotation *notes = symbol__annotation(sym);
+	struct perf_top *top = browser->b.priv;
+
+	if (notes->src != NULL)
+		goto do_annotation;
+
+	pthread_mutex_lock(&notes->lock);
+
+	top->sym_filter_entry = NULL;
+
+	if (symbol__alloc_hist(sym, top->evlist->nr_entries) < 0) {
+		pr_err("Not enough memory for annotating '%s' symbol!\n",
+		       sym->name);
+		pthread_mutex_unlock(&notes->lock);
+		return;
+	}
+
+	top->sym_filter_entry = syme;
+
+	pthread_mutex_unlock(&notes->lock);
+do_annotation:
+	symbol__tui_annotate(sym, syme->map, 0, top->delay_secs * 1000);
+}
+
+static int perf_top_browser__run(struct perf_top_browser *browser)
+{
+	int key;
+	char title[160];
+	struct perf_top *top = browser->b.priv;
+	int delay_msecs = top->delay_secs * 1000;
+	int exit_keys[] = { 'a', NEWT_KEY_ENTER, NEWT_KEY_RIGHT, 0, };
+
+	perf_top_browser__update_rb_tree(browser);
+        perf_top__header_snprintf(top, title, sizeof(title));
+        perf_top__reset_sample_counters(top);
+
+	if (ui_browser__show(&browser->b, title,
+			     "ESC: exit, ENTER|->|a: Live Annotate") < 0)
+		return -1;
+
+	newtFormSetTimer(browser->b.form, delay_msecs);
+	ui_browser__add_exit_keys(&browser->b, exit_keys);
+
+	while (1) {
+		key = ui_browser__run(&browser->b);
+
+		switch (key) {
+		case -1:
+			/* FIXME we need to check if it was es.reason == NEWT_EXIT_TIMER */
+			perf_top_browser__update_rb_tree(browser);
+			perf_top__header_snprintf(top, title, sizeof(title));
+			perf_top__reset_sample_counters(top);
+			ui_browser__set_color(&browser->b, NEWT_COLORSET_ROOT);
+			SLsmg_gotorc(0, 0);
+			slsmg_write_nstring(title, browser->b.width);
+			break;
+		case 'a':
+		case NEWT_KEY_RIGHT:
+		case NEWT_KEY_ENTER:
+			if (browser->selection)
+				perf_top_browser__annotate(browser);
+			break;
+		case NEWT_KEY_LEFT:
+			continue;
+		case NEWT_KEY_ESCAPE:
+			if (!ui__dialog_yesno("Do you really want to exit?"))
+				continue;
+			/* Fall thru */
+		default:
+			goto out;
+		}
+	}
+out:
+	ui_browser__hide(&browser->b);
+	return key;
+}
+
+int perf_top__tui_browser(struct perf_top *top)
+{
+	struct perf_top_browser browser = {
+		.b = {
+			.entries = &browser.root,
+			.refresh = ui_browser__rb_tree_refresh,
+			.seek	 = ui_browser__rb_tree_seek,
+			.write	 = perf_top_browser__write,
+			.priv	 = top,
+		},
+	};
+
+	ui_helpline__push("Press <- or ESC to exit");
+	return perf_top_browser__run(&browser);
+}
diff --git a/tools/perf/util/ui/helpline.c b/tools/perf/util/ui/helpline.c
index 8d79daa4458a..f36d2ff509ed 100644
--- a/tools/perf/util/ui/helpline.c
+++ b/tools/perf/util/ui/helpline.c
@@ -5,6 +5,7 @@
 
 #include "../debug.h"
 #include "helpline.h"
+#include "ui.h"
 
 void ui_helpline__pop(void)
 {
@@ -55,7 +56,8 @@ int ui_helpline__show_help(const char *format, va_list ap)
 	int ret;
 	static int backlog;
 
-        ret = vsnprintf(ui_helpline__last_msg + backlog,
+	pthread_mutex_lock(&ui__lock);
+	ret = vsnprintf(ui_helpline__last_msg + backlog,
 			sizeof(ui_helpline__last_msg) - backlog, format, ap);
 	backlog += ret;
 
@@ -64,6 +66,7 @@ int ui_helpline__show_help(const char *format, va_list ap)
 		newtRefresh();
 		backlog = 0;
 	}
+	pthread_mutex_unlock(&ui__lock);
 
 	return ret;
 }
diff --git a/tools/perf/util/ui/libslang.h b/tools/perf/util/ui/libslang.h
index 5623da8e8080..2b63e1c9b181 100644
--- a/tools/perf/util/ui/libslang.h
+++ b/tools/perf/util/ui/libslang.h
@@ -13,11 +13,11 @@
 
 #if SLANG_VERSION < 20104
 #define slsmg_printf(msg, args...) \
-	SLsmg_printf((char *)msg, ##args)
+	SLsmg_printf((char *)(msg), ##args)
 #define slsmg_write_nstring(msg, len) \
-	SLsmg_write_nstring((char *)msg, len)
+	SLsmg_write_nstring((char *)(msg), len)
 #define sltt_set_color(obj, name, fg, bg) \
-	SLtt_set_color(obj,(char *)name, (char *)fg, (char *)bg)
+	SLtt_set_color(obj,(char *)(name), (char *)(fg), (char *)(bg))
 #else
 #define slsmg_printf SLsmg_printf
 #define slsmg_write_nstring SLsmg_write_nstring
diff --git a/tools/perf/util/ui/setup.c b/tools/perf/util/ui/setup.c
index 662085032eb7..ee46d671db59 100644
--- a/tools/perf/util/ui/setup.c
+++ b/tools/perf/util/ui/setup.c
@@ -6,6 +6,9 @@
 #include "../debug.h"
 #include "browser.h"
 #include "helpline.h"
+#include "ui.h"
+
+pthread_mutex_t ui__lock = PTHREAD_MUTEX_INITIALIZER;
 
 static void newt_suspend(void *d __used)
 {
@@ -14,11 +17,12 @@ static void newt_suspend(void *d __used)
 	newtResume();
 }
 
-void setup_browser(void)
+void setup_browser(bool fallback_to_pager)
 {
 	if (!isatty(1) || !use_browser || dump_trace) {
 		use_browser = 0;
-		setup_pager();
+		if (fallback_to_pager)
+			setup_pager();
 		return;
 	}
 
diff --git a/tools/perf/util/ui/ui.h b/tools/perf/util/ui/ui.h
new file mode 100644
index 000000000000..d264e059c829
--- /dev/null
+++ b/tools/perf/util/ui/ui.h
@@ -0,0 +1,8 @@
+#ifndef _PERF_UI_H_
+#define _PERF_UI_H_ 1
+
+#include <pthread.h>
+
+extern pthread_mutex_t ui__lock;
+
+#endif /* _PERF_UI_H_ */
diff --git a/tools/perf/util/ui/util.c b/tools/perf/util/ui/util.c
index 7b5a8926624e..fdf1fc8f08bc 100644
--- a/tools/perf/util/ui/util.c
+++ b/tools/perf/util/ui/util.c
@@ -9,6 +9,7 @@
 #include "../debug.h"
 #include "browser.h"
 #include "helpline.h"
+#include "ui.h"
 #include "util.h"
 
 static void newt_form__set_exit_keys(newtComponent self)
@@ -118,10 +119,12 @@ void ui__warning(const char *format, ...)
 	va_list args;
 
 	va_start(args, format);
-	if (use_browser > 0)
+	if (use_browser > 0) {
+		pthread_mutex_lock(&ui__lock);
 		newtWinMessagev((char *)warning_str, (char *)ok,
 				(char *)format, args);
-	else
+		pthread_mutex_unlock(&ui__lock);
+	} else
 		vfprintf(stderr, format, args);
 	va_end(args);
 }
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index e833f26f3bfc..fc784284ac8b 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -70,9 +70,7 @@
 #include <sys/poll.h>
 #include <sys/socket.h>
 #include <sys/ioctl.h>
-#ifndef NO_SYS_SELECT_H
 #include <sys/select.h>
-#endif
 #include <netinet/in.h>
 #include <netinet/tcp.h>
 #include <arpa/inet.h>
@@ -83,10 +81,6 @@
 #include "types.h"
 #include <sys/ttydefaults.h>
 
-#ifndef NO_ICONV
-#include <iconv.h>
-#endif
-
 extern const char *graph_line;
 extern const char *graph_dotted_line;
 extern char buildid_dir[];
@@ -236,26 +230,6 @@ static inline int sane_case(int x, int high)
 	return x;
 }
 
-#ifndef DIR_HAS_BSD_GROUP_SEMANTICS
-# define FORCE_DIR_SET_GID S_ISGID
-#else
-# define FORCE_DIR_SET_GID 0
-#endif
-
-#ifdef NO_NSEC
-#undef USE_NSEC
-#define ST_CTIME_NSEC(st) 0
-#define ST_MTIME_NSEC(st) 0
-#else
-#ifdef USE_ST_TIMESPEC
-#define ST_CTIME_NSEC(st) ((unsigned int)((st).st_ctimespec.tv_nsec))
-#define ST_MTIME_NSEC(st) ((unsigned int)((st).st_mtimespec.tv_nsec))
-#else
-#define ST_CTIME_NSEC(st) ((unsigned int)((st).st_ctim.tv_nsec))
-#define ST_MTIME_NSEC(st) ((unsigned int)((st).st_mtim.tv_nsec))
-#endif
-#endif
-
 int mkdir_p(char *path, mode_t mode);
 int copyfile(const char *from, const char *to);
 
diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl
index e1c62eeb88f5..ba7c63af6f3b 100755
--- a/tools/testing/ktest/ktest.pl
+++ b/tools/testing/ktest/ktest.pl
@@ -1,6 +1,6 @@
 #!/usr/bin/perl -w
 #
-# Copywrite 2010 - Steven Rostedt <srostedt@redhat.com>, Red Hat Inc.
+# Copyright 2010 - Steven Rostedt <srostedt@redhat.com>, Red Hat Inc.
 # Licensed under the terms of the GNU GPL License version 2
 #