From 4be2c7ff4f362e41706e84a3d6726bdcda9ab65f Mon Sep 17 00:00:00 2001
From: Jaswinder Singh Rajput
Date: Sat, 31 Jan 2009 11:41:04 +0530
Subject: headers_check fix: powerpc, bootx.h

fix the following 'make headers_check' warnings:

  usr/include/asm-powerpc/bootx.h:12: include of <linux/types.h> is preferred over <asm/types.h>
  usr/include/asm-powerpc/bootx.h:57: found __[us]{8,16,32,64} type without #include <linux/types.h>

Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
---
 arch/powerpc/include/asm/bootx.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/bootx.h b/arch/powerpc/include/asm/bootx.h
index 57b82e3f89ce..60a3c9ef3017 100644
--- a/arch/powerpc/include/asm/bootx.h
+++ b/arch/powerpc/include/asm/bootx.h
@@ -9,7 +9,7 @@
 #ifndef __ASM_BOOTX_H__
 #define __ASM_BOOTX_H__
 
-#include <asm/types.h>
+#include <linux/types.h>
 
 #ifdef macintosh
 #include <Types.h>
-- 
cgit v1.2.3


From 785857f5f0b7fbeed934e39af24edec471637375 Mon Sep 17 00:00:00 2001
From: Jaswinder Singh Rajput
Date: Sat, 31 Jan 2009 11:42:29 +0530
Subject: headers_check fix: powerpc, elf.h

fix the following 'make headers_check' warning:

  usr/include/asm-powerpc/elf.h:5: include of <linux/types.h> is preferred over <asm/types.h>

Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
---
 arch/powerpc/include/asm/elf.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/elf.h b/arch/powerpc/include/asm/elf.h
index cd46f023ec6d..b5600ce6055e 100644
--- a/arch/powerpc/include/asm/elf.h
+++ b/arch/powerpc/include/asm/elf.h
@@ -7,7 +7,7 @@
 #include <asm/string.h>
 #endif
 
-#include <asm/types.h>
+#include <linux/types.h>
 #include <asm/ptrace.h>
 #include <asm/cputable.h>
 #include <asm/auxvec.h>
-- 
cgit v1.2.3


From 9f2cd967b7f029ebe2c74969709ff9c745344dba Mon Sep 17 00:00:00 2001
From: Jaswinder Singh Rajput
Date: Sat, 31 Jan 2009 11:44:45 +0530
Subject: headers_check fix: powerpc, kvm.h

fix the following 'make headers_check' warnings:

  usr/include/asm-powerpc/kvm.h:23: include of <linux/types.h> is preferred over <asm/types.h>
  usr/include/asm-powerpc/kvm.h:26: found __[us]{8,16,32,64} type without #include <linux/types.h>

Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
---
 arch/powerpc/include/asm/kvm.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/kvm.h b/arch/powerpc/include/asm/kvm.h
index f993e4198d5c..4e0cf65f7f5a 100644
--- a/arch/powerpc/include/asm/kvm.h
+++ b/arch/powerpc/include/asm/kvm.h
@@ -20,7 +20,7 @@
 #ifndef __LINUX_KVM_POWERPC_H
 #define __LINUX_KVM_POWERPC_H
 
-#include <asm/types.h>
+#include <linux/types.h>
 
 struct kvm_regs {
 	__u64 pc;
-- 
cgit v1.2.3


From 122bb2207b8107ce117d10fcfd3a2f6c3804a362 Mon Sep 17 00:00:00 2001
From: Jaswinder Singh Rajput
Date: Sat, 31 Jan 2009 11:46:23 +0530
Subject: headers_check fix: powerpc, ps3fb.h

fix the following 'make headers_check' warning:

  usr/include/asm-powerpc/ps3fb.h:33: found __[us]{8,16,32,64} type without #include <linux/types.h>

Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
---
 arch/powerpc/include/asm/ps3fb.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/ps3fb.h b/arch/powerpc/include/asm/ps3fb.h
index 3f121fe4010d..e7233a849680 100644
--- a/arch/powerpc/include/asm/ps3fb.h
+++ b/arch/powerpc/include/asm/ps3fb.h
@@ -19,6 +19,7 @@
 #ifndef _ASM_POWERPC_PS3FB_H_
 #define _ASM_POWERPC_PS3FB_H_
 
+#include <linux/types.h>
 #include <linux/ioctl.h>
 
 /* ioctl */
-- 
cgit v1.2.3


From 1a16bc4590fcc94630571c541c8fef7a0845c2c0 Mon Sep 17 00:00:00 2001
From: Jaswinder Singh Rajput
Date: Sat, 31 Jan 2009 11:52:05 +0530
Subject: headers_check fix: powerpc, spu_info.h

fix the following 'make headers_check' warning:

  usr/include/asm-powerpc/spu_info.h:27: found __[us]{8,16,32,64} type without #include <linux/types.h>

Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
---
 arch/powerpc/include/asm/spu_info.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/spu_info.h b/arch/powerpc/include/asm/spu_info.h
index 3545efbf9891..1286c823f0d8 100644
--- a/arch/powerpc/include/asm/spu_info.h
+++ b/arch/powerpc/include/asm/spu_info.h
@@ -23,9 +23,10 @@
 #ifndef _SPU_INFO_H
 #define _SPU_INFO_H
 
+#include <linux/types.h>
+
 #ifdef __KERNEL__
 #include <asm/spu.h>
-#include <linux/types.h>
 #else
 struct mfc_cq_sr {
 	__u64 mfc_cq_data0_RW;
-- 
cgit v1.2.3


From 48109870bab7e66f30f933cd218258368024cd9f Mon Sep 17 00:00:00 2001
From: Jaswinder Singh Rajput
Date: Sat, 31 Jan 2009 11:54:05 +0530
Subject: headers_check fix: powerpc, swab.h

fix the following 'make headers_check' warning:

  usr/include/asm-powerpc/swab.h:11: include of <linux/types.h> is preferred over <asm/types.h>

Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
---
 arch/powerpc/include/asm/swab.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/swab.h b/arch/powerpc/include/asm/swab.h
index ef824ae4b79c..c581e3ef73ed 100644
--- a/arch/powerpc/include/asm/swab.h
+++ b/arch/powerpc/include/asm/swab.h
@@ -8,7 +8,7 @@
  * 2 of the License, or (at your option) any later version.
  */
 
-#include <asm/types.h>
+#include <linux/types.h>
 #include <linux/compiler.h>
 
 #ifdef __GNUC__
-- 
cgit v1.2.3


From cb9eff097831007afb30d64373f29d99825d0068 Mon Sep 17 00:00:00 2001
From: Patrick Ohly
Date: Thu, 12 Feb 2009 05:03:36 +0000
Subject: net: new user space API for time stamping of incoming and outgoing
 packets

User space can request hardware and/or software time stamping.
Reporting of the result(s) via a new control message is enabled
separately for each field in the message because some of the
fields may require additional computation and thus cause overhead.
User space can tell the different kinds of time stamps apart
and choose what suits its needs.

When a TX timestamp operation is requested, the TX skb will be cloned
and the clone will be time stamped (in hardware or software) and added
to the socket error queue of the skb, if the skb has a socket
associated with it.

The actual TX timestamp will reach userspace as a RX timestamp on the
cloned packet. If timestamping is requested and no timestamping is
done in the device driver (potentially this may use hardware
timestamping), it will be done in software after the device's
start_hard_xmit routine.

Signed-off-by: Patrick Ohly <patrick.ohly@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/timestamping.txt          | 178 +++++++
 Documentation/networking/timestamping/.gitignore   |   1 +
 Documentation/networking/timestamping/Makefile     |   6 +
 .../networking/timestamping/timestamping.c         | 533 +++++++++++++++++++++
 arch/alpha/include/asm/socket.h                    |   3 +
 arch/arm/include/asm/socket.h                      |   3 +
 arch/avr32/include/asm/socket.h                    |   3 +
 arch/blackfin/include/asm/socket.h                 |   3 +
 arch/cris/include/asm/socket.h                     |   3 +
 arch/h8300/include/asm/socket.h                    |   3 +
 arch/ia64/include/asm/socket.h                     |   3 +
 arch/m68k/include/asm/socket.h                     |   3 +
 arch/mips/include/asm/socket.h                     |   3 +
 arch/parisc/include/asm/socket.h                   |   3 +
 arch/powerpc/include/asm/socket.h                  |   3 +
 arch/s390/include/asm/socket.h                     |   3 +
 arch/sh/include/asm/socket.h                       |   3 +
 arch/sparc/include/asm/socket.h                    |   3 +
 arch/x86/include/asm/socket.h                      |   3 +
 arch/xtensa/include/asm/socket.h                   |   3 +
 include/asm-frv/socket.h                           |   3 +
 include/asm-m32r/socket.h                          |   3 +
 include/asm-mn10300/socket.h                       |   3 +
 include/linux/errqueue.h                           |   1 +
 include/linux/net_tstamp.h                         | 104 ++++
 include/linux/sockios.h                            |   3 +
 26 files changed, 883 insertions(+)
 create mode 100644 Documentation/networking/timestamping.txt
 create mode 100644 Documentation/networking/timestamping/.gitignore
 create mode 100644 Documentation/networking/timestamping/Makefile
 create mode 100644 Documentation/networking/timestamping/timestamping.c
 create mode 100644 include/linux/net_tstamp.h

(limited to 'arch/powerpc/include')

diff --git a/Documentation/networking/timestamping.txt b/Documentation/networking/timestamping.txt
new file mode 100644
index 000000000000..a681a65b5bc7
--- /dev/null
+++ b/Documentation/networking/timestamping.txt
@@ -0,0 +1,178 @@
+The existing interfaces for getting network packages time stamped are:
+
+* SO_TIMESTAMP
+  Generate time stamp for each incoming packet using the (not necessarily
+  monotonous!) system time. Result is returned via recv_msg() in a
+  control message as timeval (usec resolution).
+
+* SO_TIMESTAMPNS
+  Same time stamping mechanism as SO_TIMESTAMP, but returns result as
+  timespec (nsec resolution).
+
+* IP_MULTICAST_LOOP + SO_TIMESTAMP[NS]
+  Only for multicasts: approximate send time stamp by receiving the looped
+  packet and using its receive time stamp.
+
+The following interface complements the existing ones: receive time
+stamps can be generated and returned for arbitrary packets and much
+closer to the point where the packet is really sent. Time stamps can
+be generated in software (as before) or in hardware (if the hardware
+has such a feature).
+
+SO_TIMESTAMPING:
+
+Instructs the socket layer which kind of information is wanted. The
+parameter is an integer with some of the following bits set. Setting
+other bits is an error and doesn't change the current state.
+
+SOF_TIMESTAMPING_TX_HARDWARE:  try to obtain send time stamp in hardware
+SOF_TIMESTAMPING_TX_SOFTWARE:  if SOF_TIMESTAMPING_TX_HARDWARE is off or
+                               fails, then do it in software
+SOF_TIMESTAMPING_RX_HARDWARE:  return the original, unmodified time stamp
+                               as generated by the hardware
+SOF_TIMESTAMPING_RX_SOFTWARE:  if SOF_TIMESTAMPING_RX_HARDWARE is off or
+                               fails, then do it in software
+SOF_TIMESTAMPING_RAW_HARDWARE: return original raw hardware time stamp
+SOF_TIMESTAMPING_SYS_HARDWARE: return hardware time stamp transformed to
+                               the system time base
+SOF_TIMESTAMPING_SOFTWARE:     return system time stamp generated in
+                               software
+
+SOF_TIMESTAMPING_TX/RX determine how time stamps are generated.
+SOF_TIMESTAMPING_RAW/SYS determine how they are reported in the
+following control message:
+    struct scm_timestamping {
+           struct timespec systime;
+           struct timespec hwtimetrans;
+           struct timespec hwtimeraw;
+    };
+
+recvmsg() can be used to get this control message for regular incoming
+packets. For send time stamps the outgoing packet is looped back to
+the socket's error queue with the send time stamp(s) attached. It can
+be received with recvmsg(flags=MSG_ERRQUEUE). The call returns the
+original outgoing packet data including all headers preprended down to
+and including the link layer, the scm_timestamping control message and
+a sock_extended_err control message with ee_errno==ENOMSG and
+ee_origin==SO_EE_ORIGIN_TIMESTAMPING. A socket with such a pending
+bounced packet is ready for reading as far as select() is concerned.
+
+All three values correspond to the same event in time, but were
+generated in different ways. Each of these values may be empty (= all
+zero), in which case no such value was available. If the application
+is not interested in some of these values, they can be left blank to
+avoid the potential overhead of calculating them.
+
+systime is the value of the system time at that moment. This
+corresponds to the value also returned via SO_TIMESTAMP[NS]. If the
+time stamp was generated by hardware, then this field is
+empty. Otherwise it is filled in if SOF_TIMESTAMPING_SOFTWARE is
+set.
+
+hwtimeraw is the original hardware time stamp. Filled in if
+SOF_TIMESTAMPING_RAW_HARDWARE is set. No assumptions about its
+relation to system time should be made.
+
+hwtimetrans is the hardware time stamp transformed so that it
+corresponds as good as possible to system time. This correlation is
+not perfect; as a consequence, sorting packets received via different
+NICs by their hwtimetrans may differ from the order in which they were
+received. hwtimetrans may be non-monotonic even for the same NIC.
+Filled in if SOF_TIMESTAMPING_SYS_HARDWARE is set. Requires support
+by the network device and will be empty without that support.
+
+
+SIOCSHWTSTAMP:
+
+Hardware time stamping must also be initialized for each device driver
+that is expected to do hardware time stamping. The parameter is:
+
+struct hwtstamp_config {
+    int flags;           /* no flags defined right now, must be zero */
+    int tx_type;         /* HWTSTAMP_TX_* */
+    int rx_filter;       /* HWTSTAMP_FILTER_* */
+};
+
+Desired behavior is passed into the kernel and to a specific device by
+calling ioctl(SIOCSHWTSTAMP) with a pointer to a struct ifreq whose
+ifr_data points to a struct hwtstamp_config. The tx_type and
+rx_filter are hints to the driver what it is expected to do. If
+the requested fine-grained filtering for incoming packets is not
+supported, the driver may time stamp more than just the requested types
+of packets.
+
+A driver which supports hardware time stamping shall update the struct
+with the actual, possibly more permissive configuration. If the
+requested packets cannot be time stamped, then nothing should be
+changed and ERANGE shall be returned (in contrast to EINVAL, which
+indicates that SIOCSHWTSTAMP is not supported at all).
+
+Only a processes with admin rights may change the configuration. User
+space is responsible to ensure that multiple processes don't interfere
+with each other and that the settings are reset.
+
+/* possible values for hwtstamp_config->tx_type */
+enum {
+	/*
+	 * no outgoing packet will need hardware time stamping;
+	 * should a packet arrive which asks for it, no hardware
+	 * time stamping will be done
+	 */
+	HWTSTAMP_TX_OFF,
+
+	/*
+	 * enables hardware time stamping for outgoing packets;
+	 * the sender of the packet decides which are to be
+	 * time stamped by setting SOF_TIMESTAMPING_TX_SOFTWARE
+	 * before sending the packet
+	 */
+	HWTSTAMP_TX_ON,
+};
+
+/* possible values for hwtstamp_config->rx_filter */
+enum {
+	/* time stamp no incoming packet at all */
+	HWTSTAMP_FILTER_NONE,
+
+	/* time stamp any incoming packet */
+	HWTSTAMP_FILTER_ALL,
+
+        /* return value: time stamp all packets requested plus some others */
+        HWTSTAMP_FILTER_SOME,
+
+	/* PTP v1, UDP, any kind of event packet */
+	HWTSTAMP_FILTER_PTP_V1_L4_EVENT,
+
+        ...
+};
+
+
+DEVICE IMPLEMENTATION
+
+A driver which supports hardware time stamping must support the
+SIOCSHWTSTAMP ioctl. Time stamps for received packets must be stored
+in the skb with skb_hwtstamp_set().
+
+Time stamps for outgoing packets are to be generated as follows:
+- In hard_start_xmit(), check if skb_hwtstamp_check_tx_hardware()
+  returns non-zero. If yes, then the driver is expected
+  to do hardware time stamping.
+- If this is possible for the skb and requested, then declare
+  that the driver is doing the time stamping by calling
+  skb_hwtstamp_tx_in_progress(). A driver not supporting
+  hardware time stamping doesn't do that. A driver must never
+  touch sk_buff::tstamp! It is used to store how time stamping
+  for an outgoing packets is to be done.
+- As soon as the driver has sent the packet and/or obtained a
+  hardware time stamp for it, it passes the time stamp back by
+  calling skb_hwtstamp_tx() with the original skb, the raw
+  hardware time stamp and a handle to the device (necessary
+  to convert the hardware time stamp to system time). If obtaining
+  the hardware time stamp somehow fails, then the driver should
+  not fall back to software time stamping. The rationale is that
+  this would occur at a later time in the processing pipeline
+  than other software time stamping and therefore could lead
+  to unexpected deltas between time stamps.
+- If the driver did not call skb_hwtstamp_tx_in_progress(), then
+  dev_hard_start_xmit() checks whether software time stamping
+  is wanted as fallback and potentially generates the time stamp.
diff --git a/Documentation/networking/timestamping/.gitignore b/Documentation/networking/timestamping/.gitignore
new file mode 100644
index 000000000000..71e81eb2e22f
--- /dev/null
+++ b/Documentation/networking/timestamping/.gitignore
@@ -0,0 +1 @@
+timestamping
diff --git a/Documentation/networking/timestamping/Makefile b/Documentation/networking/timestamping/Makefile
new file mode 100644
index 000000000000..2a1489fdc036
--- /dev/null
+++ b/Documentation/networking/timestamping/Makefile
@@ -0,0 +1,6 @@
+CPPFLAGS = -I../../../include
+
+timestamping: timestamping.c
+
+clean:
+	rm -f timestamping
diff --git a/Documentation/networking/timestamping/timestamping.c b/Documentation/networking/timestamping/timestamping.c
new file mode 100644
index 000000000000..43d143104210
--- /dev/null
+++ b/Documentation/networking/timestamping/timestamping.c
@@ -0,0 +1,533 @@
+/*
+ * This program demonstrates how the various time stamping features in
+ * the Linux kernel work. It emulates the behavior of a PTP
+ * implementation in stand-alone master mode by sending PTPv1 Sync
+ * multicasts once every second. It looks for similar packets, but
+ * beyond that doesn't actually implement PTP.
+ *
+ * Outgoing packets are time stamped with SO_TIMESTAMPING with or
+ * without hardware support.
+ *
+ * Incoming packets are time stamped with SO_TIMESTAMPING with or
+ * without hardware support, SIOCGSTAMP[NS] (per-socket time stamp) and
+ * SO_TIMESTAMP[NS].
+ *
+ * Copyright (C) 2009 Intel Corporation.
+ * Author: Patrick Ohly <patrick.ohly@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope 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.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <errno.h>
+#include <string.h>
+
+#include <sys/time.h>
+#include <sys/socket.h>
+#include <sys/select.h>
+#include <sys/ioctl.h>
+#include <arpa/inet.h>
+#include <net/if.h>
+
+#include "asm/types.h"
+#include "linux/net_tstamp.h"
+#include "linux/errqueue.h"
+
+#ifndef SO_TIMESTAMPING
+# define SO_TIMESTAMPING         37
+# define SCM_TIMESTAMPING        SO_TIMESTAMPING
+#endif
+
+#ifndef SO_TIMESTAMPNS
+# define SO_TIMESTAMPNS 35
+#endif
+
+#ifndef SIOCGSTAMPNS
+# define SIOCGSTAMPNS 0x8907
+#endif
+
+#ifndef SIOCSHWTSTAMP
+# define SIOCSHWTSTAMP 0x89b0
+#endif
+
+static void usage(const char *error)
+{
+	if (error)
+		printf("invalid option: %s\n", error);
+	printf("timestamping interface option*\n\n"
+	       "Options:\n"
+	       "  IP_MULTICAST_LOOP - looping outgoing multicasts\n"
+	       "  SO_TIMESTAMP - normal software time stamping, ms resolution\n"
+	       "  SO_TIMESTAMPNS - more accurate software time stamping\n"
+	       "  SOF_TIMESTAMPING_TX_HARDWARE - hardware time stamping of outgoing packets\n"
+	       "  SOF_TIMESTAMPING_TX_SOFTWARE - software fallback for outgoing packets\n"
+	       "  SOF_TIMESTAMPING_RX_HARDWARE - hardware time stamping of incoming packets\n"
+	       "  SOF_TIMESTAMPING_RX_SOFTWARE - software fallback for incoming packets\n"
+	       "  SOF_TIMESTAMPING_SOFTWARE - request reporting of software time stamps\n"
+	       "  SOF_TIMESTAMPING_SYS_HARDWARE - request reporting of transformed HW time stamps\n"
+	       "  SOF_TIMESTAMPING_RAW_HARDWARE - request reporting of raw HW time stamps\n"
+	       "  SIOCGSTAMP - check last socket time stamp\n"
+	       "  SIOCGSTAMPNS - more accurate socket time stamp\n");
+	exit(1);
+}
+
+static void bail(const char *error)
+{
+	printf("%s: %s\n", error, strerror(errno));
+	exit(1);
+}
+
+static const unsigned char sync[] = {
+	0x00, 0x01, 0x00, 0x01,
+	0x5f, 0x44, 0x46, 0x4c,
+	0x54, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+	0x01, 0x01,
+
+	/* fake uuid */
+	0x00, 0x01,
+	0x02, 0x03, 0x04, 0x05,
+
+	0x00, 0x01, 0x00, 0x37,
+	0x00, 0x00, 0x00, 0x08,
+	0x00, 0x00, 0x00, 0x00,
+	0x49, 0x05, 0xcd, 0x01,
+	0x29, 0xb1, 0x8d, 0xb0,
+	0x00, 0x00, 0x00, 0x00,
+	0x00, 0x01,
+
+	/* fake uuid */
+	0x00, 0x01,
+	0x02, 0x03, 0x04, 0x05,
+
+	0x00, 0x00, 0x00, 0x37,
+	0x00, 0x00, 0x00, 0x04,
+	0x44, 0x46, 0x4c, 0x54,
+	0x00, 0x00, 0xf0, 0x60,
+	0x00, 0x01, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x01,
+	0x00, 0x00, 0xf0, 0x60,
+	0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x04,
+	0x44, 0x46, 0x4c, 0x54,
+	0x00, 0x01,
+
+	/* fake uuid */
+	0x00, 0x01,
+	0x02, 0x03, 0x04, 0x05,
+
+	0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00
+};
+
+static void sendpacket(int sock, struct sockaddr *addr, socklen_t addr_len)
+{
+	struct timeval now;
+	int res;
+
+	res = sendto(sock, sync, sizeof(sync), 0,
+		addr, addr_len);
+	gettimeofday(&now, 0);
+	if (res < 0)
+		printf("%s: %s\n", "send", strerror(errno));
+	else
+		printf("%ld.%06ld: sent %d bytes\n",
+		       (long)now.tv_sec, (long)now.tv_usec,
+		       res);
+}
+
+static void printpacket(struct msghdr *msg, int res,
+			char *data,
+			int sock, int recvmsg_flags,
+			int siocgstamp, int siocgstampns)
+{
+	struct sockaddr_in *from_addr = (struct sockaddr_in *)msg->msg_name;
+	struct cmsghdr *cmsg;
+	struct timeval tv;
+	struct timespec ts;
+	struct timeval now;
+
+	gettimeofday(&now, 0);
+
+	printf("%ld.%06ld: received %s data, %d bytes from %s, %d bytes control messages\n",
+	       (long)now.tv_sec, (long)now.tv_usec,
+	       (recvmsg_flags & MSG_ERRQUEUE) ? "error" : "regular",
+	       res,
+	       inet_ntoa(from_addr->sin_addr),
+	       msg->msg_controllen);
+	for (cmsg = CMSG_FIRSTHDR(msg);
+	     cmsg;
+	     cmsg = CMSG_NXTHDR(msg, cmsg)) {
+		printf("   cmsg len %d: ", cmsg->cmsg_len);
+		switch (cmsg->cmsg_level) {
+		case SOL_SOCKET:
+			printf("SOL_SOCKET ");
+			switch (cmsg->cmsg_type) {
+			case SO_TIMESTAMP: {
+				struct timeval *stamp =
+					(struct timeval *)CMSG_DATA(cmsg);
+				printf("SO_TIMESTAMP %ld.%06ld",
+				       (long)stamp->tv_sec,
+				       (long)stamp->tv_usec);
+				break;
+			}
+			case SO_TIMESTAMPNS: {
+				struct timespec *stamp =
+					(struct timespec *)CMSG_DATA(cmsg);
+				printf("SO_TIMESTAMPNS %ld.%09ld",
+				       (long)stamp->tv_sec,
+				       (long)stamp->tv_nsec);
+				break;
+			}
+			case SO_TIMESTAMPING: {
+				struct timespec *stamp =
+					(struct timespec *)CMSG_DATA(cmsg);
+				printf("SO_TIMESTAMPING ");
+				printf("SW %ld.%09ld ",
+				       (long)stamp->tv_sec,
+				       (long)stamp->tv_nsec);
+				stamp++;
+				printf("HW transformed %ld.%09ld ",
+				       (long)stamp->tv_sec,
+				       (long)stamp->tv_nsec);
+				stamp++;
+				printf("HW raw %ld.%09ld",
+				       (long)stamp->tv_sec,
+				       (long)stamp->tv_nsec);
+				break;
+			}
+			default:
+				printf("type %d", cmsg->cmsg_type);
+				break;
+			}
+			break;
+		case IPPROTO_IP:
+			printf("IPPROTO_IP ");
+			switch (cmsg->cmsg_type) {
+			case IP_RECVERR: {
+				struct sock_extended_err *err =
+					(struct sock_extended_err *)CMSG_DATA(cmsg);
+				printf("IP_RECVERR ee_errno '%s' ee_origin %d => %s",
+					strerror(err->ee_errno),
+					err->ee_origin,
+#ifdef SO_EE_ORIGIN_TIMESTAMPING
+					err->ee_origin == SO_EE_ORIGIN_TIMESTAMPING ?
+					"bounced packet" : "unexpected origin"
+#else
+					"probably SO_EE_ORIGIN_TIMESTAMPING"
+#endif
+					);
+				if (res < sizeof(sync))
+					printf(" => truncated data?!");
+				else if (!memcmp(sync, data + res - sizeof(sync),
+							sizeof(sync)))
+					printf(" => GOT OUR DATA BACK (HURRAY!)");
+				break;
+			}
+			case IP_PKTINFO: {
+				struct in_pktinfo *pktinfo =
+					(struct in_pktinfo *)CMSG_DATA(cmsg);
+				printf("IP_PKTINFO interface index %u",
+					pktinfo->ipi_ifindex);
+				break;
+			}
+			default:
+				printf("type %d", cmsg->cmsg_type);
+				break;
+			}
+			break;
+		default:
+			printf("level %d type %d",
+				cmsg->cmsg_level,
+				cmsg->cmsg_type);
+			break;
+		}
+		printf("\n");
+	}
+
+	if (siocgstamp) {
+		if (ioctl(sock, SIOCGSTAMP, &tv))
+			printf("   %s: %s\n", "SIOCGSTAMP", strerror(errno));
+		else
+			printf("SIOCGSTAMP %ld.%06ld\n",
+			       (long)tv.tv_sec,
+			       (long)tv.tv_usec);
+	}
+	if (siocgstampns) {
+		if (ioctl(sock, SIOCGSTAMPNS, &ts))
+			printf("   %s: %s\n", "SIOCGSTAMPNS", strerror(errno));
+		else
+			printf("SIOCGSTAMPNS %ld.%09ld\n",
+			       (long)ts.tv_sec,
+			       (long)ts.tv_nsec);
+	}
+}
+
+static void recvpacket(int sock, int recvmsg_flags,
+		       int siocgstamp, int siocgstampns)
+{
+	char data[256];
+	struct msghdr msg;
+	struct iovec entry;
+	struct sockaddr_in from_addr;
+	struct {
+		struct cmsghdr cm;
+		char control[512];
+	} control;
+	int res;
+
+	memset(&msg, 0, sizeof(msg));
+	msg.msg_iov = &entry;
+	msg.msg_iovlen = 1;
+	entry.iov_base = data;
+	entry.iov_len = sizeof(data);
+	msg.msg_name = (caddr_t)&from_addr;
+	msg.msg_namelen = sizeof(from_addr);
+	msg.msg_control = &control;
+	msg.msg_controllen = sizeof(control);
+
+	res = recvmsg(sock, &msg, recvmsg_flags|MSG_DONTWAIT);
+	if (res < 0) {
+		printf("%s %s: %s\n",
+		       "recvmsg",
+		       (recvmsg_flags & MSG_ERRQUEUE) ? "error" : "regular",
+		       strerror(errno));
+	} else {
+		printpacket(&msg, res, data,
+			    sock, recvmsg_flags,
+			    siocgstamp, siocgstampns);
+	}
+}
+
+int main(int argc, char **argv)
+{
+	int so_timestamping_flags = 0;
+	int so_timestamp = 0;
+	int so_timestampns = 0;
+	int siocgstamp = 0;
+	int siocgstampns = 0;
+	int ip_multicast_loop = 0;
+	char *interface;
+	int i;
+	int enabled = 1;
+	int sock;
+	struct ifreq device;
+	struct ifreq hwtstamp;
+	struct hwtstamp_config hwconfig, hwconfig_requested;
+	struct sockaddr_in addr;
+	struct ip_mreq imr;
+	struct in_addr iaddr;
+	int val;
+	socklen_t len;
+	struct timeval next;
+
+	if (argc < 2)
+		usage(0);
+	interface = argv[1];
+
+	for (i = 2; i < argc; i++) {
+		if (!strcasecmp(argv[i], "SO_TIMESTAMP"))
+			so_timestamp = 1;
+		else if (!strcasecmp(argv[i], "SO_TIMESTAMPNS"))
+			so_timestampns = 1;
+		else if (!strcasecmp(argv[i], "SIOCGSTAMP"))
+			siocgstamp = 1;
+		else if (!strcasecmp(argv[i], "SIOCGSTAMPNS"))
+			siocgstampns = 1;
+		else if (!strcasecmp(argv[i], "IP_MULTICAST_LOOP"))
+			ip_multicast_loop = 1;
+		else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_TX_HARDWARE"))
+			so_timestamping_flags |= SOF_TIMESTAMPING_TX_HARDWARE;
+		else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_TX_SOFTWARE"))
+			so_timestamping_flags |= SOF_TIMESTAMPING_TX_SOFTWARE;
+		else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_RX_HARDWARE"))
+			so_timestamping_flags |= SOF_TIMESTAMPING_RX_HARDWARE;
+		else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_RX_SOFTWARE"))
+			so_timestamping_flags |= SOF_TIMESTAMPING_RX_SOFTWARE;
+		else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_SOFTWARE"))
+			so_timestamping_flags |= SOF_TIMESTAMPING_SOFTWARE;
+		else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_SYS_HARDWARE"))
+			so_timestamping_flags |= SOF_TIMESTAMPING_SYS_HARDWARE;
+		else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_RAW_HARDWARE"))
+			so_timestamping_flags |= SOF_TIMESTAMPING_RAW_HARDWARE;
+		else
+			usage(argv[i]);
+	}
+
+	sock = socket(PF_INET, SOCK_DGRAM, IPPROTO_UDP);
+	if (socket < 0)
+		bail("socket");
+
+	memset(&device, 0, sizeof(device));
+	strncpy(device.ifr_name, interface, sizeof(device.ifr_name));
+	if (ioctl(sock, SIOCGIFADDR, &device) < 0)
+		bail("getting interface IP address");
+
+	memset(&hwtstamp, 0, sizeof(hwtstamp));
+	strncpy(hwtstamp.ifr_name, interface, sizeof(hwtstamp.ifr_name));
+	hwtstamp.ifr_data = (void *)&hwconfig;
+	memset(&hwconfig, 0, sizeof(&hwconfig));
+	hwconfig.tx_type =
+		(so_timestamping_flags & SOF_TIMESTAMPING_TX_HARDWARE) ?
+		HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF;
+	hwconfig.rx_filter =
+		(so_timestamping_flags & SOF_TIMESTAMPING_RX_HARDWARE) ?
+		HWTSTAMP_FILTER_PTP_V1_L4_SYNC : HWTSTAMP_FILTER_NONE;
+	hwconfig_requested = hwconfig;
+	if (ioctl(sock, SIOCSHWTSTAMP, &hwtstamp) < 0) {
+		if ((errno == EINVAL || errno == ENOTSUP) &&
+		    hwconfig_requested.tx_type == HWTSTAMP_TX_OFF &&
+		    hwconfig_requested.rx_filter == HWTSTAMP_FILTER_NONE)
+			printf("SIOCSHWTSTAMP: disabling hardware time stamping not possible\n");
+		else
+			bail("SIOCSHWTSTAMP");
+	}
+	printf("SIOCSHWTSTAMP: tx_type %d requested, got %d; rx_filter %d requested, got %d\n",
+	       hwconfig_requested.tx_type, hwconfig.tx_type,
+	       hwconfig_requested.rx_filter, hwconfig.rx_filter);
+
+	/* bind to PTP port */
+	addr.sin_family = AF_INET;
+	addr.sin_addr.s_addr = htonl(INADDR_ANY);
+	addr.sin_port = htons(319 /* PTP event port */);
+	if (bind(sock,
+		 (struct sockaddr *)&addr,
+		 sizeof(struct sockaddr_in)) < 0)
+		bail("bind");
+
+	/* set multicast group for outgoing packets */
+	inet_aton("224.0.1.130", &iaddr); /* alternate PTP domain 1 */
+	addr.sin_addr = iaddr;
+	imr.imr_multiaddr.s_addr = iaddr.s_addr;
+	imr.imr_interface.s_addr =
+		((struct sockaddr_in *)&device.ifr_addr)->sin_addr.s_addr;
+	if (setsockopt(sock, IPPROTO_IP, IP_MULTICAST_IF,
+		       &imr.imr_interface.s_addr, sizeof(struct in_addr)) < 0)
+		bail("set multicast");
+
+	/* join multicast group, loop our own packet */
+	if (setsockopt(sock, IPPROTO_IP, IP_ADD_MEMBERSHIP,
+		       &imr, sizeof(struct ip_mreq)) < 0)
+		bail("join multicast group");
+
+	if (setsockopt(sock, IPPROTO_IP, IP_MULTICAST_LOOP,
+		       &ip_multicast_loop, sizeof(enabled)) < 0) {
+		bail("loop multicast");
+	}
+
+	/* set socket options for time stamping */
+	if (so_timestamp &&
+		setsockopt(sock, SOL_SOCKET, SO_TIMESTAMP,
+			   &enabled, sizeof(enabled)) < 0)
+		bail("setsockopt SO_TIMESTAMP");
+
+	if (so_timestampns &&
+		setsockopt(sock, SOL_SOCKET, SO_TIMESTAMPNS,
+			   &enabled, sizeof(enabled)) < 0)
+		bail("setsockopt SO_TIMESTAMPNS");
+
+	if (so_timestamping_flags &&
+		setsockopt(sock, SOL_SOCKET, SO_TIMESTAMPING,
+			   &so_timestamping_flags,
+			   sizeof(so_timestamping_flags)) < 0)
+		bail("setsockopt SO_TIMESTAMPING");
+
+	/* request IP_PKTINFO for debugging purposes */
+	if (setsockopt(sock, SOL_IP, IP_PKTINFO,
+		       &enabled, sizeof(enabled)) < 0)
+		printf("%s: %s\n", "setsockopt IP_PKTINFO", strerror(errno));
+
+	/* verify socket options */
+	len = sizeof(val);
+	if (getsockopt(sock, SOL_SOCKET, SO_TIMESTAMP, &val, &len) < 0)
+		printf("%s: %s\n", "getsockopt SO_TIMESTAMP", strerror(errno));
+	else
+		printf("SO_TIMESTAMP %d\n", val);
+
+	if (getsockopt(sock, SOL_SOCKET, SO_TIMESTAMPNS, &val, &len) < 0)
+		printf("%s: %s\n", "getsockopt SO_TIMESTAMPNS",
+		       strerror(errno));
+	else
+		printf("SO_TIMESTAMPNS %d\n", val);
+
+	if (getsockopt(sock, SOL_SOCKET, SO_TIMESTAMPING, &val, &len) < 0) {
+		printf("%s: %s\n", "getsockopt SO_TIMESTAMPING",
+		       strerror(errno));
+	} else {
+		printf("SO_TIMESTAMPING %d\n", val);
+		if (val != so_timestamping_flags)
+			printf("   not the expected value %d\n",
+			       so_timestamping_flags);
+	}
+
+	/* send packets forever every five seconds */
+	gettimeofday(&next, 0);
+	next.tv_sec = (next.tv_sec + 1) / 5 * 5;
+	next.tv_usec = 0;
+	while (1) {
+		struct timeval now;
+		struct timeval delta;
+		long delta_us;
+		int res;
+		fd_set readfs, errorfs;
+
+		gettimeofday(&now, 0);
+		delta_us = (long)(next.tv_sec - now.tv_sec) * 1000000 +
+			(long)(next.tv_usec - now.tv_usec);
+		if (delta_us > 0) {
+			/* continue waiting for timeout or data */
+			delta.tv_sec = delta_us / 1000000;
+			delta.tv_usec = delta_us % 1000000;
+
+			FD_ZERO(&readfs);
+			FD_ZERO(&errorfs);
+			FD_SET(sock, &readfs);
+			FD_SET(sock, &errorfs);
+			printf("%ld.%06ld: select %ldus\n",
+			       (long)now.tv_sec, (long)now.tv_usec,
+			       delta_us);
+			res = select(sock + 1, &readfs, 0, &errorfs, &delta);
+			gettimeofday(&now, 0);
+			printf("%ld.%06ld: select returned: %d, %s\n",
+			       (long)now.tv_sec, (long)now.tv_usec,
+			       res,
+			       res < 0 ? strerror(errno) : "success");
+			if (res > 0) {
+				if (FD_ISSET(sock, &readfs))
+					printf("ready for reading\n");
+				if (FD_ISSET(sock, &errorfs))
+					printf("has error\n");
+				recvpacket(sock, 0,
+					   siocgstamp,
+					   siocgstampns);
+				recvpacket(sock, MSG_ERRQUEUE,
+					   siocgstamp,
+					   siocgstampns);
+			}
+		} else {
+			/* write one packet */
+			sendpacket(sock,
+				   (struct sockaddr *)&addr,
+				   sizeof(addr));
+			next.tv_sec += 5;
+			continue;
+		}
+	}
+
+	return 0;
+}
diff --git a/arch/alpha/include/asm/socket.h b/arch/alpha/include/asm/socket.h
index a1057c2d95e7..3641ec1452f4 100644
--- a/arch/alpha/include/asm/socket.h
+++ b/arch/alpha/include/asm/socket.h
@@ -62,6 +62,9 @@
 
 #define SO_MARK			36
 
+#define SO_TIMESTAMPING		37
+#define SCM_TIMESTAMPING	SO_TIMESTAMPING
+
 /* O_NONBLOCK clashes with the bits used for socket types.  Therefore we
  * have to define SOCK_NONBLOCK to a different value here.
  */
diff --git a/arch/arm/include/asm/socket.h b/arch/arm/include/asm/socket.h
index 6817be9573a6..537de4e0ef50 100644
--- a/arch/arm/include/asm/socket.h
+++ b/arch/arm/include/asm/socket.h
@@ -54,4 +54,7 @@
 
 #define SO_MARK			36
 
+#define SO_TIMESTAMPING		37
+#define SCM_TIMESTAMPING	SO_TIMESTAMPING
+
 #endif /* _ASM_SOCKET_H */
diff --git a/arch/avr32/include/asm/socket.h b/arch/avr32/include/asm/socket.h
index 35863f260929..04c860619700 100644
--- a/arch/avr32/include/asm/socket.h
+++ b/arch/avr32/include/asm/socket.h
@@ -54,4 +54,7 @@
 
 #define SO_MARK			36
 
+#define SO_TIMESTAMPING		37
+#define SCM_TIMESTAMPING	SO_TIMESTAMPING
+
 #endif /* __ASM_AVR32_SOCKET_H */
diff --git a/arch/blackfin/include/asm/socket.h b/arch/blackfin/include/asm/socket.h
index 2ca702e44d47..fac7fe9e1f8a 100644
--- a/arch/blackfin/include/asm/socket.h
+++ b/arch/blackfin/include/asm/socket.h
@@ -53,4 +53,7 @@
 
 #define SO_MARK			36
 
+#define SO_TIMESTAMPING		37
+#define SCM_TIMESTAMPING	SO_TIMESTAMPING
+
 #endif				/* _ASM_SOCKET_H */
diff --git a/arch/cris/include/asm/socket.h b/arch/cris/include/asm/socket.h
index 9df0ca82f5de..d5cf74005408 100644
--- a/arch/cris/include/asm/socket.h
+++ b/arch/cris/include/asm/socket.h
@@ -56,6 +56,9 @@
 
 #define SO_MARK			36
 
+#define SO_TIMESTAMPING		37
+#define SCM_TIMESTAMPING	SO_TIMESTAMPING
+
 #endif /* _ASM_SOCKET_H */
 
 
diff --git a/arch/h8300/include/asm/socket.h b/arch/h8300/include/asm/socket.h
index da2520dbf254..602518a70a1a 100644
--- a/arch/h8300/include/asm/socket.h
+++ b/arch/h8300/include/asm/socket.h
@@ -54,4 +54,7 @@
 
 #define SO_MARK			36
 
+#define SO_TIMESTAMPING		37
+#define SCM_TIMESTAMPING	SO_TIMESTAMPING
+
 #endif /* _ASM_SOCKET_H */
diff --git a/arch/ia64/include/asm/socket.h b/arch/ia64/include/asm/socket.h
index d5ef0aa3e312..745421225ec6 100644
--- a/arch/ia64/include/asm/socket.h
+++ b/arch/ia64/include/asm/socket.h
@@ -63,4 +63,7 @@
 
 #define SO_MARK			36
 
+#define SO_TIMESTAMPING		37
+#define SCM_TIMESTAMPING	SO_TIMESTAMPING
+
 #endif /* _ASM_IA64_SOCKET_H */
diff --git a/arch/m68k/include/asm/socket.h b/arch/m68k/include/asm/socket.h
index dbc64e92c41a..ca87f938b03f 100644
--- a/arch/m68k/include/asm/socket.h
+++ b/arch/m68k/include/asm/socket.h
@@ -54,4 +54,7 @@
 
 #define SO_MARK			36
 
+#define SO_TIMESTAMPING		37
+#define SCM_TIMESTAMPING	SO_TIMESTAMPING
+
 #endif /* _ASM_SOCKET_H */
diff --git a/arch/mips/include/asm/socket.h b/arch/mips/include/asm/socket.h
index facc2d7a87ca..2abca1780169 100644
--- a/arch/mips/include/asm/socket.h
+++ b/arch/mips/include/asm/socket.h
@@ -75,6 +75,9 @@ To add: #define SO_REUSEPORT 0x0200	/* Allow local address and port reuse.  */
 
 #define SO_MARK			36
 
+#define SO_TIMESTAMPING		37
+#define SCM_TIMESTAMPING	SO_TIMESTAMPING
+
 #ifdef __KERNEL__
 
 /** sock_type - Socket types
diff --git a/arch/parisc/include/asm/socket.h b/arch/parisc/include/asm/socket.h
index fba402c95ac2..885472bf7b78 100644
--- a/arch/parisc/include/asm/socket.h
+++ b/arch/parisc/include/asm/socket.h
@@ -54,6 +54,9 @@
 
 #define SO_MARK			0x401f
 
+#define SO_TIMESTAMPING		0x4020
+#define SCM_TIMESTAMPING	SO_TIMESTAMPING
+
 /* O_NONBLOCK clashes with the bits used for socket types.  Therefore we
  * have to define SOCK_NONBLOCK to a different value here.
  */
diff --git a/arch/powerpc/include/asm/socket.h b/arch/powerpc/include/asm/socket.h
index f5a4e168e498..1e5cfad0e3f7 100644
--- a/arch/powerpc/include/asm/socket.h
+++ b/arch/powerpc/include/asm/socket.h
@@ -61,4 +61,7 @@
 
 #define SO_MARK			36
 
+#define SO_TIMESTAMPING		37
+#define SCM_TIMESTAMPING	SO_TIMESTAMPING
+
 #endif	/* _ASM_POWERPC_SOCKET_H */
diff --git a/arch/s390/include/asm/socket.h b/arch/s390/include/asm/socket.h
index c786ab623b2d..02330c50241b 100644
--- a/arch/s390/include/asm/socket.h
+++ b/arch/s390/include/asm/socket.h
@@ -62,4 +62,7 @@
 
 #define SO_MARK			36
 
+#define SO_TIMESTAMPING		37
+#define SCM_TIMESTAMPING	SO_TIMESTAMPING
+
 #endif /* _ASM_SOCKET_H */
diff --git a/arch/sh/include/asm/socket.h b/arch/sh/include/asm/socket.h
index 6d4bf6512959..345653b96826 100644
--- a/arch/sh/include/asm/socket.h
+++ b/arch/sh/include/asm/socket.h
@@ -54,4 +54,7 @@
 
 #define SO_MARK			36
 
+#define SO_TIMESTAMPING		37
+#define SCM_TIMESTAMPING	SO_TIMESTAMPING
+
 #endif /* __ASM_SH_SOCKET_H */
diff --git a/arch/sparc/include/asm/socket.h b/arch/sparc/include/asm/socket.h
index bf50d0c2d583..982a12f959f4 100644
--- a/arch/sparc/include/asm/socket.h
+++ b/arch/sparc/include/asm/socket.h
@@ -50,6 +50,9 @@
 
 #define SO_MARK			0x0022
 
+#define SO_TIMESTAMPING		0x0023
+#define SCM_TIMESTAMPING	SO_TIMESTAMPING
+
 /* Security levels - as per NRL IPv6 - don't actually do anything */
 #define SO_SECURITY_AUTHENTICATION		0x5001
 #define SO_SECURITY_ENCRYPTION_TRANSPORT	0x5002
diff --git a/arch/x86/include/asm/socket.h b/arch/x86/include/asm/socket.h
index 8ab9cc8b2ecc..ca8bf2cd0ba9 100644
--- a/arch/x86/include/asm/socket.h
+++ b/arch/x86/include/asm/socket.h
@@ -54,4 +54,7 @@
 
 #define SO_MARK			36
 
+#define SO_TIMESTAMPING		37
+#define SCM_TIMESTAMPING	SO_TIMESTAMPING
+
 #endif /* _ASM_X86_SOCKET_H */
diff --git a/arch/xtensa/include/asm/socket.h b/arch/xtensa/include/asm/socket.h
index 6100682b1da2..dd1a7a4a1cea 100644
--- a/arch/xtensa/include/asm/socket.h
+++ b/arch/xtensa/include/asm/socket.h
@@ -65,4 +65,7 @@
 
 #define SO_MARK			36
 
+#define SO_TIMESTAMPING		37
+#define SCM_TIMESTAMPING	SO_TIMESTAMPING
+
 #endif	/* _XTENSA_SOCKET_H */
diff --git a/include/asm-frv/socket.h b/include/asm-frv/socket.h
index e51ca67b9356..57c3d4054e8b 100644
--- a/include/asm-frv/socket.h
+++ b/include/asm-frv/socket.h
@@ -54,5 +54,8 @@
 
 #define SO_MARK			36
 
+#define SO_TIMESTAMPING		37
+#define SCM_TIMESTAMPING	SO_TIMESTAMPING
+
 #endif /* _ASM_SOCKET_H */
 
diff --git a/include/asm-m32r/socket.h b/include/asm-m32r/socket.h
index 9a0e20012224..be7ed589af5c 100644
--- a/include/asm-m32r/socket.h
+++ b/include/asm-m32r/socket.h
@@ -54,4 +54,7 @@
 
 #define SO_MARK			36
 
+#define SO_TIMESTAMPING		37
+#define SCM_TIMESTAMPING	SO_TIMESTAMPING
+
 #endif /* _ASM_M32R_SOCKET_H */
diff --git a/include/asm-mn10300/socket.h b/include/asm-mn10300/socket.h
index 80af9c4ccad7..fb5daf438ec9 100644
--- a/include/asm-mn10300/socket.h
+++ b/include/asm-mn10300/socket.h
@@ -54,4 +54,7 @@
 
 #define SO_MARK			36
 
+#define SO_TIMESTAMPING		37
+#define SCM_TIMESTAMPING	SO_TIMESTAMPING
+
 #endif /* _ASM_SOCKET_H */
diff --git a/include/linux/errqueue.h b/include/linux/errqueue.h
index ceb1454b6977..ec12cc74366f 100644
--- a/include/linux/errqueue.h
+++ b/include/linux/errqueue.h
@@ -18,6 +18,7 @@ struct sock_extended_err
 #define SO_EE_ORIGIN_LOCAL	1
 #define SO_EE_ORIGIN_ICMP	2
 #define SO_EE_ORIGIN_ICMP6	3
+#define SO_EE_ORIGIN_TIMESTAMPING 4
 
 #define SO_EE_OFFENDER(ee)	((struct sockaddr*)((ee)+1))
 
diff --git a/include/linux/net_tstamp.h b/include/linux/net_tstamp.h
new file mode 100644
index 000000000000..a3b8546354ac
--- /dev/null
+++ b/include/linux/net_tstamp.h
@@ -0,0 +1,104 @@
+/*
+ * Userspace API for hardware time stamping of network packets
+ *
+ * Copyright (C) 2008,2009 Intel Corporation
+ * Author: Patrick Ohly <patrick.ohly@intel.com>
+ *
+ */
+
+#ifndef _NET_TIMESTAMPING_H
+#define _NET_TIMESTAMPING_H
+
+#include <linux/socket.h>   /* for SO_TIMESTAMPING */
+
+/* SO_TIMESTAMPING gets an integer bit field comprised of these values */
+enum {
+	SOF_TIMESTAMPING_TX_HARDWARE = (1<<0),
+	SOF_TIMESTAMPING_TX_SOFTWARE = (1<<1),
+	SOF_TIMESTAMPING_RX_HARDWARE = (1<<2),
+	SOF_TIMESTAMPING_RX_SOFTWARE = (1<<3),
+	SOF_TIMESTAMPING_SOFTWARE = (1<<4),
+	SOF_TIMESTAMPING_SYS_HARDWARE = (1<<5),
+	SOF_TIMESTAMPING_RAW_HARDWARE = (1<<6),
+	SOF_TIMESTAMPING_MASK =
+	(SOF_TIMESTAMPING_RAW_HARDWARE - 1) |
+	SOF_TIMESTAMPING_RAW_HARDWARE
+};
+
+/**
+ * struct hwtstamp_config - %SIOCSHWTSTAMP parameter
+ *
+ * @flags:	no flags defined right now, must be zero
+ * @tx_type:	one of HWTSTAMP_TX_*
+ * @rx_type:	one of one of HWTSTAMP_FILTER_*
+ *
+ * %SIOCSHWTSTAMP expects a &struct ifreq with a ifr_data pointer to
+ * this structure. dev_ifsioc() in the kernel takes care of the
+ * translation between 32 bit userspace and 64 bit kernel. The
+ * structure is intentionally chosen so that it has the same layout on
+ * 32 and 64 bit systems, don't break this!
+ */
+struct hwtstamp_config {
+	int flags;
+	int tx_type;
+	int rx_filter;
+};
+
+/* possible values for hwtstamp_config->tx_type */
+enum {
+	/*
+	 * No outgoing packet will need hardware time stamping;
+	 * should a packet arrive which asks for it, no hardware
+	 * time stamping will be done.
+	 */
+	HWTSTAMP_TX_OFF,
+
+	/*
+	 * Enables hardware time stamping for outgoing packets;
+	 * the sender of the packet decides which are to be
+	 * time stamped by setting %SOF_TIMESTAMPING_TX_SOFTWARE
+	 * before sending the packet.
+	 */
+	HWTSTAMP_TX_ON,
+};
+
+/* possible values for hwtstamp_config->rx_filter */
+enum {
+	/* time stamp no incoming packet at all */
+	HWTSTAMP_FILTER_NONE,
+
+	/* time stamp any incoming packet */
+	HWTSTAMP_FILTER_ALL,
+
+	/* return value: time stamp all packets requested plus some others */
+	HWTSTAMP_FILTER_SOME,
+
+	/* PTP v1, UDP, any kind of event packet */
+	HWTSTAMP_FILTER_PTP_V1_L4_EVENT,
+	/* PTP v1, UDP, Sync packet */
+	HWTSTAMP_FILTER_PTP_V1_L4_SYNC,
+	/* PTP v1, UDP, Delay_req packet */
+	HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ,
+	/* PTP v2, UDP, any kind of event packet */
+	HWTSTAMP_FILTER_PTP_V2_L4_EVENT,
+	/* PTP v2, UDP, Sync packet */
+	HWTSTAMP_FILTER_PTP_V2_L4_SYNC,
+	/* PTP v2, UDP, Delay_req packet */
+	HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ,
+
+	/* 802.AS1, Ethernet, any kind of event packet */
+	HWTSTAMP_FILTER_PTP_V2_L2_EVENT,
+	/* 802.AS1, Ethernet, Sync packet */
+	HWTSTAMP_FILTER_PTP_V2_L2_SYNC,
+	/* 802.AS1, Ethernet, Delay_req packet */
+	HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ,
+
+	/* PTP v2/802.AS1, any layer, any kind of event packet */
+	HWTSTAMP_FILTER_PTP_V2_EVENT,
+	/* PTP v2/802.AS1, any layer, Sync packet */
+	HWTSTAMP_FILTER_PTP_V2_SYNC,
+	/* PTP v2/802.AS1, any layer, Delay_req packet */
+	HWTSTAMP_FILTER_PTP_V2_DELAY_REQ,
+};
+
+#endif /* _NET_TIMESTAMPING_H */
diff --git a/include/linux/sockios.h b/include/linux/sockios.h
index abef7596655a..241f179347d9 100644
--- a/include/linux/sockios.h
+++ b/include/linux/sockios.h
@@ -122,6 +122,9 @@
 #define SIOCBRADDIF	0x89a2		/* add interface to bridge      */
 #define SIOCBRDELIF	0x89a3		/* remove interface from bridge */
 
+/* hardware time stamping: parameters in linux/net_tstamp.h */
+#define SIOCSHWTSTAMP   0x89b0
+
 /* Device private ioctl calls */
 
 /*
-- 
cgit v1.2.3


From d0bfb940ecabf0b44fb1fd80d8d60594e569e5ec Mon Sep 17 00:00:00 2001
From: Jan Kiszka
Date: Mon, 15 Dec 2008 13:52:10 +0100
Subject: KVM: New guest debug interface

This rips out the support for KVM_DEBUG_GUEST and introduces a new IOCTL
instead: KVM_SET_GUEST_DEBUG. The IOCTL payload consists of a generic
part, controlling the "main switch" and the single-step feature. The
arch specific part adds an x86 interface for intercepting both types of
debug exceptions separately and re-injecting them when the host was not
interested. Moveover, the foundation for guest debugging via debug
registers is layed.

To signal breakpoint events properly back to userland, an arch-specific
data block is now returned along KVM_EXIT_DEBUG. For x86, the arch block
contains the PC, the debug exception, and relevant debug registers to
tell debug events properly apart.

The availability of this new interface is signaled by
KVM_CAP_SET_GUEST_DEBUG. Empty stubs for not yet supported archs are
provided.

Note that both SVM and VTX are supported, but only the latter was tested
yet. Based on the experience with all those VTX corner case, I would be
fairly surprised if SVM will work out of the box.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/ia64/include/asm/kvm.h     |  7 ++++
 arch/ia64/kvm/kvm-ia64.c        |  4 +-
 arch/powerpc/include/asm/kvm.h  |  7 ++++
 arch/powerpc/kvm/powerpc.c      |  4 +-
 arch/s390/include/asm/kvm.h     |  7 ++++
 arch/s390/kvm/kvm-s390.c        |  4 +-
 arch/x86/include/asm/kvm.h      | 18 ++++++++
 arch/x86/include/asm/kvm_host.h |  9 +---
 arch/x86/kvm/svm.c              | 50 +++++++++++++++++++++-
 arch/x86/kvm/vmx.c              | 93 ++++++++++++++++-------------------------
 arch/x86/kvm/x86.c              | 14 ++++---
 include/linux/kvm.h             | 51 +++++++++++++++-------
 include/linux/kvm_host.h        |  6 +--
 virt/kvm/kvm_main.c             |  6 +--
 14 files changed, 179 insertions(+), 101 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/ia64/include/asm/kvm.h b/arch/ia64/include/asm/kvm.h
index bfa86b6af7cd..be3fdb891214 100644
--- a/arch/ia64/include/asm/kvm.h
+++ b/arch/ia64/include/asm/kvm.h
@@ -214,4 +214,11 @@ struct kvm_sregs {
 struct kvm_fpu {
 };
 
+struct kvm_debug_exit_arch {
+};
+
+/* for KVM_SET_GUEST_DEBUG */
+struct kvm_guest_debug_arch {
+};
+
 #endif
diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c
index 28f982045f29..de47467a0e61 100644
--- a/arch/ia64/kvm/kvm-ia64.c
+++ b/arch/ia64/kvm/kvm-ia64.c
@@ -1303,8 +1303,8 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 	return -EINVAL;
 }
 
-int kvm_arch_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu,
-		struct kvm_debug_guest *dbg)
+int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
+					struct kvm_guest_debug *dbg)
 {
 	return -EINVAL;
 }
diff --git a/arch/powerpc/include/asm/kvm.h b/arch/powerpc/include/asm/kvm.h
index f993e4198d5c..755f1b1948c5 100644
--- a/arch/powerpc/include/asm/kvm.h
+++ b/arch/powerpc/include/asm/kvm.h
@@ -52,4 +52,11 @@ struct kvm_fpu {
 	__u64 fpr[32];
 };
 
+struct kvm_debug_exit_arch {
+};
+
+/* for KVM_SET_GUEST_DEBUG */
+struct kvm_guest_debug_arch {
+};
+
 #endif /* __LINUX_KVM_POWERPC_H */
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 5f81256287f5..7c2ad4017d6a 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -240,8 +240,8 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 	kvmppc_core_vcpu_put(vcpu);
 }
 
-int kvm_arch_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu,
-                                    struct kvm_debug_guest *dbg)
+int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
+					struct kvm_guest_debug *dbg)
 {
 	int i;
 
diff --git a/arch/s390/include/asm/kvm.h b/arch/s390/include/asm/kvm.h
index e1f54654e3ae..0b2f829f6d50 100644
--- a/arch/s390/include/asm/kvm.h
+++ b/arch/s390/include/asm/kvm.h
@@ -42,4 +42,11 @@ struct kvm_fpu {
 	__u64 fprs[16];
 };
 
+struct kvm_debug_exit_arch {
+};
+
+/* for KVM_SET_GUEST_DEBUG */
+struct kvm_guest_debug_arch {
+};
+
 #endif
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 0d33893e1e89..cbfe91e10120 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -422,8 +422,8 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
 	return -EINVAL; /* not implemented yet */
 }
 
-int kvm_arch_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu,
-				    struct kvm_debug_guest *dbg)
+int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
+					struct kvm_guest_debug *dbg)
 {
 	return -EINVAL; /* not implemented yet */
 }
diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h
index 886c9402ec45..32eb96c7ca27 100644
--- a/arch/x86/include/asm/kvm.h
+++ b/arch/x86/include/asm/kvm.h
@@ -212,6 +212,24 @@ struct kvm_pit_channel_state {
 	__s64 count_load_time;
 };
 
+struct kvm_debug_exit_arch {
+	__u32 exception;
+	__u32 pad;
+	__u64 pc;
+	__u64 dr6;
+	__u64 dr7;
+};
+
+#define KVM_GUESTDBG_USE_SW_BP		0x00010000
+#define KVM_GUESTDBG_USE_HW_BP		0x00020000
+#define KVM_GUESTDBG_INJECT_DB		0x00040000
+#define KVM_GUESTDBG_INJECT_BP		0x00080000
+
+/* for KVM_SET_GUEST_DEBUG */
+struct kvm_guest_debug_arch {
+	__u64 debugreg[8];
+};
+
 struct kvm_pit_state {
 	struct kvm_pit_channel_state channels[3];
 };
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 53779309514a..c430cd580ee2 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -135,12 +135,6 @@ enum {
 
 #define KVM_NR_MEM_OBJS 40
 
-struct kvm_guest_debug {
-	int enabled;
-	unsigned long bp[4];
-	int singlestep;
-};
-
 /*
  * We don't want allocation failures within the mmu code, so we preallocate
  * enough memory for a single page fault in a cache.
@@ -448,8 +442,7 @@ struct kvm_x86_ops {
 	void (*vcpu_put)(struct kvm_vcpu *vcpu);
 
 	int (*set_guest_debug)(struct kvm_vcpu *vcpu,
-			       struct kvm_debug_guest *dbg);
-	void (*guest_debug_pre)(struct kvm_vcpu *vcpu);
+			       struct kvm_guest_debug *dbg);
 	int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata);
 	int (*set_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 data);
 	u64 (*get_segment_base)(struct kvm_vcpu *vcpu, int seg);
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 0fbbde54ecae..88d9062f4545 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -968,9 +968,32 @@ static void svm_set_segment(struct kvm_vcpu *vcpu,
 
 }
 
-static int svm_guest_debug(struct kvm_vcpu *vcpu, struct kvm_debug_guest *dbg)
+static int svm_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg)
 {
-	return -EOPNOTSUPP;
+	int old_debug = vcpu->guest_debug;
+	struct vcpu_svm *svm = to_svm(vcpu);
+
+	vcpu->guest_debug = dbg->control;
+
+	svm->vmcb->control.intercept_exceptions &=
+		~((1 << DB_VECTOR) | (1 << BP_VECTOR));
+	if (vcpu->guest_debug & KVM_GUESTDBG_ENABLE) {
+		if (vcpu->guest_debug &
+		    (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))
+			svm->vmcb->control.intercept_exceptions |=
+				1 << DB_VECTOR;
+		if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP)
+			svm->vmcb->control.intercept_exceptions |=
+				1 << BP_VECTOR;
+	} else
+		vcpu->guest_debug = 0;
+
+	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
+		svm->vmcb->save.rflags |= X86_EFLAGS_TF | X86_EFLAGS_RF;
+	else if (old_debug & KVM_GUESTDBG_SINGLESTEP)
+		svm->vmcb->save.rflags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF);
+
+	return 0;
 }
 
 static int svm_get_irq(struct kvm_vcpu *vcpu)
@@ -1094,6 +1117,27 @@ static int pf_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 	return kvm_mmu_page_fault(&svm->vcpu, fault_address, error_code);
 }
 
+static int db_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+{
+	if (!(svm->vcpu.guest_debug &
+	      (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))) {
+		kvm_queue_exception(&svm->vcpu, DB_VECTOR);
+		return 1;
+	}
+	kvm_run->exit_reason = KVM_EXIT_DEBUG;
+	kvm_run->debug.arch.pc = svm->vmcb->save.cs.base + svm->vmcb->save.rip;
+	kvm_run->debug.arch.exception = DB_VECTOR;
+	return 0;
+}
+
+static int bp_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+{
+	kvm_run->exit_reason = KVM_EXIT_DEBUG;
+	kvm_run->debug.arch.pc = svm->vmcb->save.cs.base + svm->vmcb->save.rip;
+	kvm_run->debug.arch.exception = BP_VECTOR;
+	return 0;
+}
+
 static int ud_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 {
 	int er;
@@ -2050,6 +2094,8 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm,
 	[SVM_EXIT_WRITE_DR3]			= emulate_on_interception,
 	[SVM_EXIT_WRITE_DR5]			= emulate_on_interception,
 	[SVM_EXIT_WRITE_DR7]			= emulate_on_interception,
+	[SVM_EXIT_EXCP_BASE + DB_VECTOR]	= db_interception,
+	[SVM_EXIT_EXCP_BASE + BP_VECTOR]	= bp_interception,
 	[SVM_EXIT_EXCP_BASE + UD_VECTOR]	= ud_interception,
 	[SVM_EXIT_EXCP_BASE + PF_VECTOR] 	= pf_interception,
 	[SVM_EXIT_EXCP_BASE + NM_VECTOR] 	= nm_interception,
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 1d974c1eaa7d..f55690ddb3ac 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -480,8 +480,13 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu)
 	eb = (1u << PF_VECTOR) | (1u << UD_VECTOR);
 	if (!vcpu->fpu_active)
 		eb |= 1u << NM_VECTOR;
-	if (vcpu->guest_debug.enabled)
-		eb |= 1u << DB_VECTOR;
+	if (vcpu->guest_debug & KVM_GUESTDBG_ENABLE) {
+		if (vcpu->guest_debug &
+		    (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))
+			eb |= 1u << DB_VECTOR;
+		if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP)
+			eb |= 1u << BP_VECTOR;
+	}
 	if (vcpu->arch.rmode.active)
 		eb = ~0;
 	if (vm_need_ept())
@@ -1003,40 +1008,23 @@ static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg)
 	}
 }
 
-static int set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_debug_guest *dbg)
+static int set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg)
 {
-	unsigned long dr7 = 0x400;
-	int old_singlestep;
-
-	old_singlestep = vcpu->guest_debug.singlestep;
-
-	vcpu->guest_debug.enabled = dbg->enabled;
-	if (vcpu->guest_debug.enabled) {
-		int i;
-
-		dr7 |= 0x200;  /* exact */
-		for (i = 0; i < 4; ++i) {
-			if (!dbg->breakpoints[i].enabled)
-				continue;
-			vcpu->guest_debug.bp[i] = dbg->breakpoints[i].address;
-			dr7 |= 2 << (i*2);    /* global enable */
-			dr7 |= 0 << (i*4+16); /* execution breakpoint */
-		}
-
-		vcpu->guest_debug.singlestep = dbg->singlestep;
-	} else
-		vcpu->guest_debug.singlestep = 0;
+	int old_debug = vcpu->guest_debug;
+	unsigned long flags;
 
-	if (old_singlestep && !vcpu->guest_debug.singlestep) {
-		unsigned long flags;
+	vcpu->guest_debug = dbg->control;
+	if (!(vcpu->guest_debug & KVM_GUESTDBG_ENABLE))
+		vcpu->guest_debug = 0;
 
-		flags = vmcs_readl(GUEST_RFLAGS);
+	flags = vmcs_readl(GUEST_RFLAGS);
+	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
+		flags |= X86_EFLAGS_TF | X86_EFLAGS_RF;
+	else if (old_debug & KVM_GUESTDBG_SINGLESTEP)
 		flags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF);
-		vmcs_writel(GUEST_RFLAGS, flags);
-	}
+	vmcs_writel(GUEST_RFLAGS, flags);
 
 	update_exception_bitmap(vcpu);
-	vmcs_writel(GUEST_DR7, dr7);
 
 	return 0;
 }
@@ -2540,24 +2528,6 @@ static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr)
 	return 0;
 }
 
-static void kvm_guest_debug_pre(struct kvm_vcpu *vcpu)
-{
-	struct kvm_guest_debug *dbg = &vcpu->guest_debug;
-
-	set_debugreg(dbg->bp[0], 0);
-	set_debugreg(dbg->bp[1], 1);
-	set_debugreg(dbg->bp[2], 2);
-	set_debugreg(dbg->bp[3], 3);
-
-	if (dbg->singlestep) {
-		unsigned long flags;
-
-		flags = vmcs_readl(GUEST_RFLAGS);
-		flags |= X86_EFLAGS_TF | X86_EFLAGS_RF;
-		vmcs_writel(GUEST_RFLAGS, flags);
-	}
-}
-
 static int handle_rmode_exception(struct kvm_vcpu *vcpu,
 				  int vec, u32 err_code)
 {
@@ -2574,9 +2544,17 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu,
 	 *        the required debugging infrastructure rework.
 	 */
 	switch (vec) {
-	case DE_VECTOR:
 	case DB_VECTOR:
+		if (vcpu->guest_debug &
+		    (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))
+			return 0;
+		kvm_queue_exception(vcpu, vec);
+		return 1;
 	case BP_VECTOR:
+		if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP)
+			return 0;
+		/* fall through */
+	case DE_VECTOR:
 	case OF_VECTOR:
 	case BR_VECTOR:
 	case UD_VECTOR:
@@ -2593,7 +2571,7 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu,
 static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	u32 intr_info, error_code;
+	u32 intr_info, ex_no, error_code;
 	unsigned long cr2, rip;
 	u32 vect_info;
 	enum emulation_result er;
@@ -2653,14 +2631,16 @@ static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		return 1;
 	}
 
-	if ((intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK)) ==
-	    (INTR_TYPE_HARD_EXCEPTION | 1)) {
+	ex_no = intr_info & INTR_INFO_VECTOR_MASK;
+	if (ex_no == DB_VECTOR || ex_no == BP_VECTOR) {
 		kvm_run->exit_reason = KVM_EXIT_DEBUG;
-		return 0;
+		kvm_run->debug.arch.pc = vmcs_readl(GUEST_CS_BASE) + rip;
+		kvm_run->debug.arch.exception = ex_no;
+	} else {
+		kvm_run->exit_reason = KVM_EXIT_EXCEPTION;
+		kvm_run->ex.exception = ex_no;
+		kvm_run->ex.error_code = error_code;
 	}
-	kvm_run->exit_reason = KVM_EXIT_EXCEPTION;
-	kvm_run->ex.exception = intr_info & INTR_INFO_VECTOR_MASK;
-	kvm_run->ex.error_code = error_code;
 	return 0;
 }
 
@@ -3600,7 +3580,6 @@ static struct kvm_x86_ops vmx_x86_ops = {
 	.vcpu_put = vmx_vcpu_put,
 
 	.set_guest_debug = set_guest_debug,
-	.guest_debug_pre = kvm_guest_debug_pre,
 	.get_msr = vmx_get_msr,
 	.set_msr = vmx_set_msr,
 	.get_segment_base = vmx_get_segment_base,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index b5e9932e0f62..e990d164b56d 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3005,9 +3005,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		goto out;
 	}
 
-	if (vcpu->guest_debug.enabled)
-		kvm_x86_ops->guest_debug_pre(vcpu);
-
 	vcpu->guest_mode = 1;
 	/*
 	 * Make sure that guest_mode assignment won't happen after
@@ -3218,7 +3215,7 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	/*
 	 * Don't leak debug flags in case they were set for guest debugging
 	 */
-	if (vcpu->guest_debug.enabled && vcpu->guest_debug.singlestep)
+	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
 		regs->rflags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF);
 
 	vcpu_put(vcpu);
@@ -3837,8 +3834,8 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
-int kvm_arch_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu,
-				    struct kvm_debug_guest *dbg)
+int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
+					struct kvm_guest_debug *dbg)
 {
 	int r;
 
@@ -3846,6 +3843,11 @@ int kvm_arch_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu,
 
 	r = kvm_x86_ops->set_guest_debug(vcpu, dbg);
 
+	if (dbg->control & KVM_GUESTDBG_INJECT_DB)
+		kvm_queue_exception(vcpu, DB_VECTOR);
+	else if (dbg->control & KVM_GUESTDBG_INJECT_BP)
+		kvm_queue_exception(vcpu, BP_VECTOR);
+
 	vcpu_put(vcpu);
 
 	return r;
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index 0424326f1679..429a2ce202f9 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -126,6 +126,7 @@ struct kvm_run {
 			__u64 data_offset; /* relative to kvm_run start */
 		} io;
 		struct {
+			struct kvm_debug_exit_arch arch;
 		} debug;
 		/* KVM_EXIT_MMIO */
 		struct {
@@ -217,21 +218,6 @@ struct kvm_interrupt {
 	__u32 irq;
 };
 
-struct kvm_breakpoint {
-	__u32 enabled;
-	__u32 padding;
-	__u64 address;
-};
-
-/* for KVM_DEBUG_GUEST */
-struct kvm_debug_guest {
-	/* int */
-	__u32 enabled;
-	__u32 pad;
-	struct kvm_breakpoint breakpoints[4];
-	__u32 singlestep;
-};
-
 /* for KVM_GET_DIRTY_LOG */
 struct kvm_dirty_log {
 	__u32 slot;
@@ -292,6 +278,17 @@ struct kvm_s390_interrupt {
 	__u64 parm64;
 };
 
+/* for KVM_SET_GUEST_DEBUG */
+
+#define KVM_GUESTDBG_ENABLE		0x00000001
+#define KVM_GUESTDBG_SINGLESTEP		0x00000002
+
+struct kvm_guest_debug {
+	__u32 control;
+	__u32 pad;
+	struct kvm_guest_debug_arch arch;
+};
+
 #define KVM_TRC_SHIFT           16
 /*
  * kvm trace categories
@@ -396,6 +393,7 @@ struct kvm_trace_rec {
 #ifdef __KVM_HAVE_USER_NMI
 #define KVM_CAP_USER_NMI 22
 #endif
+#define KVM_CAP_SET_GUEST_DEBUG 23
 
 /*
  * ioctls for VM fds
@@ -440,7 +438,8 @@ struct kvm_trace_rec {
 #define KVM_SET_SREGS             _IOW(KVMIO,  0x84, struct kvm_sregs)
 #define KVM_TRANSLATE             _IOWR(KVMIO, 0x85, struct kvm_translation)
 #define KVM_INTERRUPT             _IOW(KVMIO,  0x86, struct kvm_interrupt)
-#define KVM_DEBUG_GUEST           _IOW(KVMIO,  0x87, struct kvm_debug_guest)
+/* KVM_DEBUG_GUEST is no longer supported, use KVM_SET_GUEST_DEBUG instead */
+#define KVM_DEBUG_GUEST           __KVM_DEPRECATED_DEBUG_GUEST
 #define KVM_GET_MSRS              _IOWR(KVMIO, 0x88, struct kvm_msrs)
 #define KVM_SET_MSRS              _IOW(KVMIO,  0x89, struct kvm_msrs)
 #define KVM_SET_CPUID             _IOW(KVMIO,  0x8a, struct kvm_cpuid)
@@ -469,6 +468,26 @@ struct kvm_trace_rec {
 #define KVM_SET_MP_STATE          _IOW(KVMIO,  0x99, struct kvm_mp_state)
 /* Available with KVM_CAP_NMI */
 #define KVM_NMI                   _IO(KVMIO,  0x9a)
+/* Available with KVM_CAP_SET_GUEST_DEBUG */
+#define KVM_SET_GUEST_DEBUG       _IOW(KVMIO,  0x9b, struct kvm_guest_debug)
+
+/*
+ * Deprecated interfaces
+ */
+struct kvm_breakpoint {
+	__u32 enabled;
+	__u32 padding;
+	__u64 address;
+};
+
+struct kvm_debug_guest {
+	__u32 enabled;
+	__u32 pad;
+	struct kvm_breakpoint breakpoints[4];
+	__u32 singlestep;
+};
+
+#define __KVM_DEPRECATED_DEBUG_GUEST _IOW(KVMIO,  0x87, struct kvm_debug_guest)
 
 #define KVM_TRC_INJ_VIRQ         (KVM_TRC_HANDLER + 0x02)
 #define KVM_TRC_REDELIVER_EVT    (KVM_TRC_HANDLER + 0x03)
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index bf6f703642fc..e92212f970db 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -73,7 +73,7 @@ struct kvm_vcpu {
 	struct kvm_run *run;
 	int guest_mode;
 	unsigned long requests;
-	struct kvm_guest_debug guest_debug;
+	unsigned long guest_debug;
 	int fpu_active;
 	int guest_fpu_loaded;
 	wait_queue_head_t wq;
@@ -255,8 +255,8 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
 				    struct kvm_mp_state *mp_state);
 int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
 				    struct kvm_mp_state *mp_state);
-int kvm_arch_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu,
-				    struct kvm_debug_guest *dbg);
+int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
+					struct kvm_guest_debug *dbg);
 int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run);
 
 int kvm_arch_init(void *opaque);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 29a667ce35b0..f83ef9c7e89b 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1755,13 +1755,13 @@ out_free2:
 		r = 0;
 		break;
 	}
-	case KVM_DEBUG_GUEST: {
-		struct kvm_debug_guest dbg;
+	case KVM_SET_GUEST_DEBUG: {
+		struct kvm_guest_debug dbg;
 
 		r = -EFAULT;
 		if (copy_from_user(&dbg, argp, sizeof dbg))
 			goto out;
-		r = kvm_arch_vcpu_ioctl_debug_guest(vcpu, &dbg);
+		r = kvm_arch_vcpu_ioctl_set_guest_debug(vcpu, &dbg);
 		if (r)
 			goto out;
 		r = 0;
-- 
cgit v1.2.3


From 989c0f0ed56468a4aa48711cef5acf122a40d1dd Mon Sep 17 00:00:00 2001
From: Jan Kiszka
Date: Thu, 18 Dec 2008 12:33:18 +0100
Subject: KVM: Remove old kvm_guest_debug structs

Remove the remaining arch fragments of the old guest debug interface
that now break non-x86 builds.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/ia64/include/asm/kvm_host.h    | 2 --
 arch/powerpc/include/asm/kvm_host.h | 6 ------
 arch/s390/include/asm/kvm_host.h    | 3 ---
 3 files changed, 11 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/ia64/include/asm/kvm_host.h b/arch/ia64/include/asm/kvm_host.h
index 7da0c0963226..46f8b0eb5684 100644
--- a/arch/ia64/include/asm/kvm_host.h
+++ b/arch/ia64/include/asm/kvm_host.h
@@ -239,8 +239,6 @@ struct kvm_vm_data {
 
 struct kvm;
 struct kvm_vcpu;
-struct kvm_guest_debug{
-};
 
 struct kvm_mmio_req {
 	uint64_t addr;          /*  physical address		*/
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index c1e436fe7738..a22600537a8c 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -200,10 +200,4 @@ struct kvm_vcpu_arch {
 	unsigned long pending_exceptions;
 };
 
-struct kvm_guest_debug {
-	int enabled;
-	unsigned long bp[4];
-	int singlestep;
-};
-
 #endif /* __POWERPC_KVM_HOST_H__ */
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 3c55e4107dcc..c6e674f5fca9 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -21,9 +21,6 @@
 /* memory slots that does not exposed to userspace */
 #define KVM_PRIVATE_MEM_SLOTS 4
 
-struct kvm_guest_debug {
-};
-
 struct sca_entry {
 	atomic_t scn;
 	__u64	reserved;
-- 
cgit v1.2.3


From c46fb0211f8b93de45400bff814c0f29335af5fc Mon Sep 17 00:00:00 2001
From: Hollis Blanchard
Date: Sat, 3 Jan 2009 16:22:58 -0600
Subject: KVM: ppc: move struct kvmppc_44x_tlbe into 44x-specific header

Signed-off-by: Hollis Blanchard <hollisb@us.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/include/asm/kvm_44x.h  | 7 +++++++
 arch/powerpc/include/asm/kvm_host.h | 7 -------
 2 files changed, 7 insertions(+), 7 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/kvm_44x.h b/arch/powerpc/include/asm/kvm_44x.h
index f49031b632ca..d22d39942a92 100644
--- a/arch/powerpc/include/asm/kvm_44x.h
+++ b/arch/powerpc/include/asm/kvm_44x.h
@@ -28,6 +28,13 @@
  * need to find some way of advertising it. */
 #define KVM44x_GUEST_TLB_SIZE 64
 
+struct kvmppc_44x_tlbe {
+	u32 tid; /* Only the low 8 bits are used. */
+	u32 word0;
+	u32 word1;
+	u32 word2;
+};
+
 struct kvmppc_44x_shadow_ref {
 	struct page *page;
 	u16 gtlb_index;
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index a22600537a8c..65c4d492d722 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -64,13 +64,6 @@ struct kvm_vcpu_stat {
 	u32 halt_wakeup;
 };
 
-struct kvmppc_44x_tlbe {
-	u32 tid; /* Only the low 8 bits are used. */
-	u32 word0;
-	u32 word1;
-	u32 word2;
-};
-
 enum kvm_exit_types {
 	MMIO_EXITS,
 	DCR_EXITS,
-- 
cgit v1.2.3


From ecc0981ff07cbe7cdf95de20be5b24fee8e49cb5 Mon Sep 17 00:00:00 2001
From: Hollis Blanchard
Date: Sat, 3 Jan 2009 16:22:59 -0600
Subject: KVM: ppc: cosmetic changes to mmu hook names

Signed-off-by: Hollis Blanchard <hollisb@us.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/include/asm/kvm_ppc.h | 5 +++--
 arch/powerpc/kvm/44x_tlb.c         | 2 +-
 arch/powerpc/kvm/powerpc.c         | 2 +-
 3 files changed, 5 insertions(+), 4 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 36d2a50a8487..7ba95d28b837 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -52,13 +52,14 @@ extern int kvmppc_emulate_instruction(struct kvm_run *run,
 extern int kvmppc_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu);
 extern void kvmppc_emulate_dec(struct kvm_vcpu *vcpu);
 
+/* Core-specific hooks */
+
 extern void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 gvaddr, gpa_t gpaddr,
                            u64 asid, u32 flags, u32 max_bytes,
                            unsigned int gtlb_idx);
 extern void kvmppc_mmu_priv_switch(struct kvm_vcpu *vcpu, int usermode);
 extern void kvmppc_mmu_switch_pid(struct kvm_vcpu *vcpu, u32 pid);
-
-/* Core-specific hooks */
+extern void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu);
 
 extern struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm,
                                                 unsigned int id);
diff --git a/arch/powerpc/kvm/44x_tlb.c b/arch/powerpc/kvm/44x_tlb.c
index 9a34b8edb9e2..8f9c09cbb833 100644
--- a/arch/powerpc/kvm/44x_tlb.c
+++ b/arch/powerpc/kvm/44x_tlb.c
@@ -248,7 +248,7 @@ static void kvmppc_44x_shadow_release(struct kvmppc_vcpu_44x *vcpu_44x,
 	KVMTRACE_1D(STLB_INVAL, &vcpu_44x->vcpu, stlb_index, handler);
 }
 
-void kvmppc_core_destroy_mmu(struct kvm_vcpu *vcpu)
+void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_vcpu_44x *vcpu_44x = to_44x(vcpu);
 	int i;
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 7c2ad4017d6a..f30be9ef2314 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -216,7 +216,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 
 void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
 {
-	kvmppc_core_destroy_mmu(vcpu);
+	kvmppc_mmu_destroy(vcpu);
 }
 
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
-- 
cgit v1.2.3


From 58a96214a306fc7fc66105097eea9c4f3bfa35bc Mon Sep 17 00:00:00 2001
From: Hollis Blanchard
Date: Sat, 3 Jan 2009 16:23:01 -0600
Subject: KVM: ppc: change kvmppc_mmu_map() parameters

Passing just the TLB index will ease an e500 implementation.

Signed-off-by: Hollis Blanchard <hollisb@us.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/include/asm/kvm_ppc.h |  1 -
 arch/powerpc/kvm/44x_tlb.c         | 15 +++++++--------
 arch/powerpc/kvm/booke.c           |  6 ++----
 3 files changed, 9 insertions(+), 13 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 7ba95d28b837..f661f8ba3ab8 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -55,7 +55,6 @@ extern void kvmppc_emulate_dec(struct kvm_vcpu *vcpu);
 /* Core-specific hooks */
 
 extern void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 gvaddr, gpa_t gpaddr,
-                           u64 asid, u32 flags, u32 max_bytes,
                            unsigned int gtlb_idx);
 extern void kvmppc_mmu_priv_switch(struct kvm_vcpu *vcpu, int usermode);
 extern void kvmppc_mmu_switch_pid(struct kvm_vcpu *vcpu, u32 pid);
diff --git a/arch/powerpc/kvm/44x_tlb.c b/arch/powerpc/kvm/44x_tlb.c
index 8f9c09cbb833..e8ed22f28eae 100644
--- a/arch/powerpc/kvm/44x_tlb.c
+++ b/arch/powerpc/kvm/44x_tlb.c
@@ -269,15 +269,19 @@ void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)
  * Caller must ensure that the specified guest TLB entry is safe to insert into
  * the shadow TLB.
  */
-void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 gvaddr, gpa_t gpaddr, u64 asid,
-                    u32 flags, u32 max_bytes, unsigned int gtlb_index)
+void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 gvaddr, gpa_t gpaddr,
+                    unsigned int gtlb_index)
 {
 	struct kvmppc_44x_tlbe stlbe;
 	struct kvmppc_vcpu_44x *vcpu_44x = to_44x(vcpu);
+	struct kvmppc_44x_tlbe *gtlbe = &vcpu_44x->guest_tlb[gtlb_index];
 	struct kvmppc_44x_shadow_ref *ref;
 	struct page *new_page;
 	hpa_t hpaddr;
 	gfn_t gfn;
+	u32 asid = gtlbe->tid;
+	u32 flags = gtlbe->word2;
+	u32 max_bytes = get_tlb_bytes(gtlbe);
 	unsigned int victim;
 
 	/* Select TLB entry to clobber. Indirectly guard against races with the TLB
@@ -448,10 +452,8 @@ int kvmppc_44x_emul_tlbwe(struct kvm_vcpu *vcpu, u8 ra, u8 rs, u8 ws)
 	}
 
 	if (tlbe_is_host_safe(vcpu, tlbe)) {
-		u64 asid;
 		gva_t eaddr;
 		gpa_t gpaddr;
-		u32 flags;
 		u32 bytes;
 
 		eaddr = get_tlb_eaddr(tlbe);
@@ -462,10 +464,7 @@ int kvmppc_44x_emul_tlbwe(struct kvm_vcpu *vcpu, u8 ra, u8 rs, u8 ws)
 		eaddr &= ~(bytes - 1);
 		gpaddr &= ~(bytes - 1);
 
-		asid = (tlbe->word0 & PPC44x_TLB_TS) | tlbe->tid;
-		flags = tlbe->word2 & 0xffff;
-
-		kvmppc_mmu_map(vcpu, eaddr, gpaddr, asid, flags, bytes, gtlb_index);
+		kvmppc_mmu_map(vcpu, eaddr, gpaddr, gtlb_index);
 	}
 
 	KVMTRACE_5D(GTLB_WRITE, vcpu, gtlb_index, tlbe->tid, tlbe->word0,
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index d196ae619303..85b9e2fc6c6b 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -316,8 +316,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			 * b) the guest used a large mapping which we're faking
 			 * Either way, we need to satisfy the fault without
 			 * invoking the guest. */
-			kvmppc_mmu_map(vcpu, eaddr, gpaddr, gtlbe->tid,
-			               gtlbe->word2, get_tlb_bytes(gtlbe), gtlb_index);
+			kvmppc_mmu_map(vcpu, eaddr, gpaddr, gtlb_index);
 			kvmppc_account_exit(vcpu, DTLB_VIRT_MISS_EXITS);
 			r = RESUME_GUEST;
 		} else {
@@ -364,8 +363,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			 * b) the guest used a large mapping which we're faking
 			 * Either way, we need to satisfy the fault without
 			 * invoking the guest. */
-			kvmppc_mmu_map(vcpu, eaddr, gpaddr, gtlbe->tid,
-			               gtlbe->word2, get_tlb_bytes(gtlbe), gtlb_index);
+			kvmppc_mmu_map(vcpu, eaddr, gpaddr, gtlb_index);
 		} else {
 			/* Guest mapped and leaped at non-RAM! */
 			kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_MACHINE_CHECK);
-- 
cgit v1.2.3


From be8d1cae07d5acf4a61046d7def5eda40f0981e1 Mon Sep 17 00:00:00 2001
From: Hollis Blanchard
Date: Sat, 3 Jan 2009 16:23:02 -0600
Subject: KVM: ppc: turn tlb_xlate() into a per-core hook (and give it a better
 name)

Signed-off-by: Hollis Blanchard <hollisb@us.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/include/asm/kvm_ppc.h |  2 ++
 arch/powerpc/kvm/44x.c             |  6 +-----
 arch/powerpc/kvm/44x_tlb.c         | 10 ++++++++++
 arch/powerpc/kvm/44x_tlb.h         |  7 -------
 arch/powerpc/kvm/booke.c           | 10 ++--------
 5 files changed, 15 insertions(+), 20 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index f661f8ba3ab8..9fd70aa916d9 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -59,6 +59,8 @@ extern void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 gvaddr, gpa_t gpaddr,
 extern void kvmppc_mmu_priv_switch(struct kvm_vcpu *vcpu, int usermode);
 extern void kvmppc_mmu_switch_pid(struct kvm_vcpu *vcpu, u32 pid);
 extern void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu);
+extern gpa_t kvmppc_mmu_xlate(struct kvm_vcpu *vcpu, unsigned int gtlb_index,
+                              gva_t eaddr);
 
 extern struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm,
                                                 unsigned int id);
diff --git a/arch/powerpc/kvm/44x.c b/arch/powerpc/kvm/44x.c
index a66bec57265a..8383603dd8a4 100644
--- a/arch/powerpc/kvm/44x.c
+++ b/arch/powerpc/kvm/44x.c
@@ -149,8 +149,6 @@ int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu)
 int kvmppc_core_vcpu_translate(struct kvm_vcpu *vcpu,
                                struct kvm_translation *tr)
 {
-	struct kvmppc_vcpu_44x *vcpu_44x = to_44x(vcpu);
-	struct kvmppc_44x_tlbe *gtlbe;
 	int index;
 	gva_t eaddr;
 	u8 pid;
@@ -166,9 +164,7 @@ int kvmppc_core_vcpu_translate(struct kvm_vcpu *vcpu,
 		return 0;
 	}
 
-	gtlbe = &vcpu_44x->guest_tlb[index];
-
-	tr->physical_address = tlb_xlate(gtlbe, eaddr);
+	tr->physical_address = kvmppc_mmu_xlate(vcpu, index, eaddr);
 	/* XXX what does "writeable" and "usermode" even mean? */
 	tr->valid = 1;
 
diff --git a/arch/powerpc/kvm/44x_tlb.c b/arch/powerpc/kvm/44x_tlb.c
index e8ed22f28eae..2f14671e8a15 100644
--- a/arch/powerpc/kvm/44x_tlb.c
+++ b/arch/powerpc/kvm/44x_tlb.c
@@ -208,6 +208,16 @@ int kvmppc_44x_tlb_index(struct kvm_vcpu *vcpu, gva_t eaddr, unsigned int pid,
 	return -1;
 }
 
+gpa_t kvmppc_mmu_xlate(struct kvm_vcpu *vcpu, unsigned int gtlb_index,
+                       gva_t eaddr)
+{
+	struct kvmppc_vcpu_44x *vcpu_44x = to_44x(vcpu);
+	struct kvmppc_44x_tlbe *gtlbe = &vcpu_44x->guest_tlb[gtlb_index];
+	unsigned int pgmask = get_tlb_bytes(gtlbe) - 1;
+
+	return get_tlb_raddr(gtlbe) | (eaddr & pgmask);
+}
+
 int kvmppc_44x_itlb_index(struct kvm_vcpu *vcpu, gva_t eaddr)
 {
 	unsigned int as = !!(vcpu->arch.msr & MSR_IS);
diff --git a/arch/powerpc/kvm/44x_tlb.h b/arch/powerpc/kvm/44x_tlb.h
index 772191f29e62..05b6f7eef5b6 100644
--- a/arch/powerpc/kvm/44x_tlb.h
+++ b/arch/powerpc/kvm/44x_tlb.h
@@ -85,11 +85,4 @@ static inline unsigned int get_mmucr_sts(const struct kvm_vcpu *vcpu)
 	return (vcpu->arch.mmucr >> 16) & 0x1;
 }
 
-static inline gpa_t tlb_xlate(struct kvmppc_44x_tlbe *tlbe, gva_t eaddr)
-{
-	unsigned int pgmask = get_tlb_bytes(tlbe) - 1;
-
-	return get_tlb_raddr(tlbe) | (eaddr & pgmask);
-}
-
 #endif /* __KVM_POWERPC_TLB_H__ */
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 85b9e2fc6c6b..56d6ed69ed60 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -286,8 +286,6 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 
 	/* XXX move to a 440-specific file. */
 	case BOOKE_INTERRUPT_DTLB_MISS: {
-		struct kvmppc_vcpu_44x *vcpu_44x = to_44x(vcpu);
-		struct kvmppc_44x_tlbe *gtlbe;
 		unsigned long eaddr = vcpu->arch.fault_dear;
 		int gtlb_index;
 		gpa_t gpaddr;
@@ -305,8 +303,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			break;
 		}
 
-		gtlbe = &vcpu_44x->guest_tlb[gtlb_index];
-		gpaddr = tlb_xlate(gtlbe, eaddr);
+		gpaddr = kvmppc_mmu_xlate(vcpu, gtlb_index, eaddr);
 		gfn = gpaddr >> PAGE_SHIFT;
 
 		if (kvm_is_visible_gfn(vcpu->kvm, gfn)) {
@@ -332,8 +329,6 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 
 	/* XXX move to a 440-specific file. */
 	case BOOKE_INTERRUPT_ITLB_MISS: {
-		struct kvmppc_vcpu_44x *vcpu_44x = to_44x(vcpu);
-		struct kvmppc_44x_tlbe *gtlbe;
 		unsigned long eaddr = vcpu->arch.pc;
 		gpa_t gpaddr;
 		gfn_t gfn;
@@ -352,8 +347,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 
 		kvmppc_account_exit(vcpu, ITLB_VIRT_MISS_EXITS);
 
-		gtlbe = &vcpu_44x->guest_tlb[gtlb_index];
-		gpaddr = tlb_xlate(gtlbe, eaddr);
+		gpaddr = kvmppc_mmu_xlate(vcpu, gtlb_index, eaddr);
 		gfn = gpaddr >> PAGE_SHIFT;
 
 		if (kvm_is_visible_gfn(vcpu->kvm, gfn)) {
-- 
cgit v1.2.3


From fa86b8dda2e0faccefbeda61edc02a50bd588f4f Mon Sep 17 00:00:00 2001
From: Hollis Blanchard
Date: Sat, 3 Jan 2009 16:23:03 -0600
Subject: KVM: ppc: rename 44x MMU functions used in booke.c

e500 will provide its own implementation of these.

Signed-off-by: Hollis Blanchard <hollisb@us.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/include/asm/kvm_ppc.h | 2 ++
 arch/powerpc/kvm/44x_tlb.c         | 4 ++--
 arch/powerpc/kvm/44x_tlb.h         | 2 --
 arch/powerpc/kvm/booke.c           | 4 ++--
 4 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 9fd70aa916d9..5e80a20f32b8 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -59,6 +59,8 @@ extern void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 gvaddr, gpa_t gpaddr,
 extern void kvmppc_mmu_priv_switch(struct kvm_vcpu *vcpu, int usermode);
 extern void kvmppc_mmu_switch_pid(struct kvm_vcpu *vcpu, u32 pid);
 extern void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu);
+extern int kvmppc_mmu_dtlb_index(struct kvm_vcpu *vcpu, gva_t eaddr);
+extern int kvmppc_mmu_itlb_index(struct kvm_vcpu *vcpu, gva_t eaddr);
 extern gpa_t kvmppc_mmu_xlate(struct kvm_vcpu *vcpu, unsigned int gtlb_index,
                               gva_t eaddr);
 
diff --git a/arch/powerpc/kvm/44x_tlb.c b/arch/powerpc/kvm/44x_tlb.c
index 2f14671e8a15..e67b7313ffc3 100644
--- a/arch/powerpc/kvm/44x_tlb.c
+++ b/arch/powerpc/kvm/44x_tlb.c
@@ -218,14 +218,14 @@ gpa_t kvmppc_mmu_xlate(struct kvm_vcpu *vcpu, unsigned int gtlb_index,
 	return get_tlb_raddr(gtlbe) | (eaddr & pgmask);
 }
 
-int kvmppc_44x_itlb_index(struct kvm_vcpu *vcpu, gva_t eaddr)
+int kvmppc_mmu_itlb_index(struct kvm_vcpu *vcpu, gva_t eaddr)
 {
 	unsigned int as = !!(vcpu->arch.msr & MSR_IS);
 
 	return kvmppc_44x_tlb_index(vcpu, eaddr, vcpu->arch.pid, as);
 }
 
-int kvmppc_44x_dtlb_index(struct kvm_vcpu *vcpu, gva_t eaddr)
+int kvmppc_mmu_dtlb_index(struct kvm_vcpu *vcpu, gva_t eaddr)
 {
 	unsigned int as = !!(vcpu->arch.msr & MSR_DS);
 
diff --git a/arch/powerpc/kvm/44x_tlb.h b/arch/powerpc/kvm/44x_tlb.h
index 05b6f7eef5b6..a9ff80e51526 100644
--- a/arch/powerpc/kvm/44x_tlb.h
+++ b/arch/powerpc/kvm/44x_tlb.h
@@ -25,8 +25,6 @@
 
 extern int kvmppc_44x_tlb_index(struct kvm_vcpu *vcpu, gva_t eaddr,
                                 unsigned int pid, unsigned int as);
-extern int kvmppc_44x_dtlb_index(struct kvm_vcpu *vcpu, gva_t eaddr);
-extern int kvmppc_44x_itlb_index(struct kvm_vcpu *vcpu, gva_t eaddr);
 
 extern int kvmppc_44x_emul_tlbsx(struct kvm_vcpu *vcpu, u8 rt, u8 ra, u8 rb,
                                  u8 rc);
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 56d6ed69ed60..1e692ac16e99 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -292,7 +292,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		gfn_t gfn;
 
 		/* Check the guest TLB. */
-		gtlb_index = kvmppc_44x_dtlb_index(vcpu, eaddr);
+		gtlb_index = kvmppc_mmu_dtlb_index(vcpu, eaddr);
 		if (gtlb_index < 0) {
 			/* The guest didn't have a mapping for it. */
 			kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_DTLB_MISS);
@@ -337,7 +337,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		r = RESUME_GUEST;
 
 		/* Check the guest TLB. */
-		gtlb_index = kvmppc_44x_itlb_index(vcpu, eaddr);
+		gtlb_index = kvmppc_mmu_itlb_index(vcpu, eaddr);
 		if (gtlb_index < 0) {
 			/* The guest didn't have a mapping for it. */
 			kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_ITLB_MISS);
-- 
cgit v1.2.3


From f7b200af8f1da748cc67993caeff3923d6014070 Mon Sep 17 00:00:00 2001
From: Hollis Blanchard
Date: Sat, 3 Jan 2009 16:23:07 -0600
Subject: KVM: ppc: Add dbsr in kvm_vcpu_arch

Kernel for E500 need clear dbsr when startup.
So add dbsr register in kvm_vcpu_arch for BOOKE.

Signed-off-by: Liu Yu <yu.liu@freescale.com>
Signed-off-by: Hollis Blanchard <hollisb@us.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/include/asm/kvm_host.h | 1 +
 arch/powerpc/kvm/booke_emulate.c    | 4 ++++
 2 files changed, 5 insertions(+)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 65c4d492d722..50e5ce1b400a 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -163,6 +163,7 @@ struct kvm_vcpu_arch {
 	u32 ccr1;
 	u32 dbcr0;
 	u32 dbcr1;
+	u32 dbsr;
 
 #ifdef CONFIG_KVM_EXIT_TIMING
 	struct kvmppc_exit_timing timing_exit;
diff --git a/arch/powerpc/kvm/booke_emulate.c b/arch/powerpc/kvm/booke_emulate.c
index 8aa78f1a1f87..aebc65e93f4b 100644
--- a/arch/powerpc/kvm/booke_emulate.c
+++ b/arch/powerpc/kvm/booke_emulate.c
@@ -111,6 +111,8 @@ int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
 		vcpu->arch.dbcr0 = vcpu->arch.gpr[rs]; break;
 	case SPRN_DBCR1:
 		vcpu->arch.dbcr1 = vcpu->arch.gpr[rs]; break;
+	case SPRN_DBSR:
+		vcpu->arch.dbsr &= ~vcpu->arch.gpr[rs]; break;
 	case SPRN_TSR:
 		vcpu->arch.tsr &= ~vcpu->arch.gpr[rs]; break;
 	case SPRN_TCR:
@@ -204,6 +206,8 @@ int kvmppc_booke_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
 		vcpu->arch.gpr[rt] = vcpu->arch.dbcr0; break;
 	case SPRN_DBCR1:
 		vcpu->arch.gpr[rt] = vcpu->arch.dbcr1; break;
+	case SPRN_DBSR:
+		vcpu->arch.gpr[rt] = vcpu->arch.dbsr; break;
 
 	case SPRN_IVOR0:
 		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_CRITICAL];
-- 
cgit v1.2.3


From bc8080cbcc8870178f0910edd537d0cb5706d703 Mon Sep 17 00:00:00 2001
From: Hollis Blanchard
Date: Sat, 3 Jan 2009 16:23:10 -0600
Subject: KVM: ppc: E500 core-specific code

Signed-off-by: Liu Yu <yu.liu@freescale.com>
Signed-off-by: Hollis Blanchard <hollisb@us.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/include/asm/kvm_e500.h |  67 ++++
 arch/powerpc/kvm/Kconfig            |  13 +
 arch/powerpc/kvm/Makefile           |   9 +
 arch/powerpc/kvm/e500.c             | 151 ++++++++
 arch/powerpc/kvm/e500_emulate.c     | 169 +++++++++
 arch/powerpc/kvm/e500_tlb.c         | 737 ++++++++++++++++++++++++++++++++++++
 arch/powerpc/kvm/e500_tlb.h         | 184 +++++++++
 7 files changed, 1330 insertions(+)
 create mode 100644 arch/powerpc/include/asm/kvm_e500.h
 create mode 100644 arch/powerpc/kvm/e500.c
 create mode 100644 arch/powerpc/kvm/e500_emulate.c
 create mode 100644 arch/powerpc/kvm/e500_tlb.c
 create mode 100644 arch/powerpc/kvm/e500_tlb.h

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/kvm_e500.h b/arch/powerpc/include/asm/kvm_e500.h
new file mode 100644
index 000000000000..9d497ce49726
--- /dev/null
+++ b/arch/powerpc/include/asm/kvm_e500.h
@@ -0,0 +1,67 @@
+/*
+ * Copyright (C) 2008 Freescale Semiconductor, Inc. All rights reserved.
+ *
+ * Author: Yu Liu, <yu.liu@freescale.com>
+ *
+ * Description:
+ * This file is derived from arch/powerpc/include/asm/kvm_44x.h,
+ * by Hollis Blanchard <hollisb@us.ibm.com>.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __ASM_KVM_E500_H__
+#define __ASM_KVM_E500_H__
+
+#include <linux/kvm_host.h>
+
+#define BOOKE_INTERRUPT_SIZE 36
+
+#define E500_PID_NUM   3
+#define E500_TLB_NUM   2
+
+struct tlbe{
+	u32 mas1;
+	u32 mas2;
+	u32 mas3;
+	u32 mas7;
+};
+
+struct kvmppc_vcpu_e500 {
+	/* Unmodified copy of the guest's TLB. */
+	struct tlbe *guest_tlb[E500_TLB_NUM];
+	/* TLB that's actually used when the guest is running. */
+	struct tlbe *shadow_tlb[E500_TLB_NUM];
+	/* Pages which are referenced in the shadow TLB. */
+	struct page **shadow_pages[E500_TLB_NUM];
+
+	unsigned int guest_tlb_size[E500_TLB_NUM];
+	unsigned int shadow_tlb_size[E500_TLB_NUM];
+	unsigned int guest_tlb_nv[E500_TLB_NUM];
+
+	u32 host_pid[E500_PID_NUM];
+	u32 pid[E500_PID_NUM];
+
+	u32 mas0;
+	u32 mas1;
+	u32 mas2;
+	u32 mas3;
+	u32 mas4;
+	u32 mas5;
+	u32 mas6;
+	u32 mas7;
+	u32 l1csr1;
+	u32 hid0;
+	u32 hid1;
+
+	struct kvm_vcpu vcpu;
+};
+
+static inline struct kvmppc_vcpu_e500 *to_e500(struct kvm_vcpu *vcpu)
+{
+	return container_of(vcpu, struct kvmppc_vcpu_e500, vcpu);
+}
+
+#endif /* __ASM_KVM_E500_H__ */
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index 6dbdc4817d80..146570550142 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -43,6 +43,19 @@ config KVM_EXIT_TIMING
 
 	  If unsure, say N.
 
+config KVM_E500
+	bool "KVM support for PowerPC E500 processors"
+	depends on EXPERIMENTAL && E500
+	select KVM
+	---help---
+	  Support running unmodified E500 guest kernels in virtual machines on
+	  E500 host processors.
+
+	  This module provides access to the hardware capabilities through
+	  a character device node named /dev/kvm.
+
+	  If unsure, say N.
+
 config KVM_TRACE
 	bool "KVM trace support"
 	depends on KVM && MARKERS && SYSFS
diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile
index 3ef5261828e2..4b2df66c79d8 100644
--- a/arch/powerpc/kvm/Makefile
+++ b/arch/powerpc/kvm/Makefile
@@ -22,3 +22,12 @@ kvm-440-objs := \
 	44x_tlb.o \
 	44x_emulate.o
 obj-$(CONFIG_KVM_440) += kvm-440.o
+
+kvm-e500-objs := \
+	booke.o \
+	booke_emulate.o \
+	booke_interrupts.o \
+	e500.o \
+	e500_tlb.o \
+	e500_emulate.o
+obj-$(CONFIG_KVM_E500) += kvm-e500.o
diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c
new file mode 100644
index 000000000000..7992da497cd4
--- /dev/null
+++ b/arch/powerpc/kvm/e500.c
@@ -0,0 +1,151 @@
+/*
+ * Copyright (C) 2008 Freescale Semiconductor, Inc. All rights reserved.
+ *
+ * Author: Yu Liu, <yu.liu@freescale.com>
+ *
+ * Description:
+ * This file is derived from arch/powerpc/kvm/44x.c,
+ * by Hollis Blanchard <hollisb@us.ibm.com>.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kvm_host.h>
+#include <linux/err.h>
+
+#include <asm/reg.h>
+#include <asm/cputable.h>
+#include <asm/tlbflush.h>
+#include <asm/kvm_e500.h>
+#include <asm/kvm_ppc.h>
+
+#include "e500_tlb.h"
+
+void kvmppc_core_load_host_debugstate(struct kvm_vcpu *vcpu)
+{
+}
+
+void kvmppc_core_load_guest_debugstate(struct kvm_vcpu *vcpu)
+{
+}
+
+void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+{
+	kvmppc_e500_tlb_load(vcpu, cpu);
+}
+
+void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
+{
+	kvmppc_e500_tlb_put(vcpu);
+}
+
+int kvmppc_core_check_processor_compat(void)
+{
+	int r;
+
+	if (strcmp(cur_cpu_spec->cpu_name, "e500v2") == 0)
+		r = 0;
+	else
+		r = -ENOTSUPP;
+
+	return r;
+}
+
+int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+
+	kvmppc_e500_tlb_setup(vcpu_e500);
+
+	/* Use the same core vertion as host's */
+	vcpu->arch.pvr = mfspr(SPRN_PVR);
+
+	return 0;
+}
+
+/* 'linear_address' is actually an encoding of AS|PID|EADDR . */
+int kvmppc_core_vcpu_translate(struct kvm_vcpu *vcpu,
+                               struct kvm_translation *tr)
+{
+	int index;
+	gva_t eaddr;
+	u8 pid;
+	u8 as;
+
+	eaddr = tr->linear_address;
+	pid = (tr->linear_address >> 32) & 0xff;
+	as = (tr->linear_address >> 40) & 0x1;
+
+	index = kvmppc_e500_tlb_search(vcpu, eaddr, pid, as);
+	if (index < 0) {
+		tr->valid = 0;
+		return 0;
+	}
+
+	tr->physical_address = kvmppc_mmu_xlate(vcpu, index, eaddr);
+	/* XXX what does "writeable" and "usermode" even mean? */
+	tr->valid = 1;
+
+	return 0;
+}
+
+struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500;
+	struct kvm_vcpu *vcpu;
+	int err;
+
+	vcpu_e500 = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
+	if (!vcpu_e500) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	vcpu = &vcpu_e500->vcpu;
+	err = kvm_vcpu_init(vcpu, kvm, id);
+	if (err)
+		goto free_vcpu;
+
+	err = kvmppc_e500_tlb_init(vcpu_e500);
+	if (err)
+		goto uninit_vcpu;
+
+	return vcpu;
+
+uninit_vcpu:
+	kvm_vcpu_uninit(vcpu);
+free_vcpu:
+	kmem_cache_free(kvm_vcpu_cache, vcpu_e500);
+out:
+	return ERR_PTR(err);
+}
+
+void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+
+	kvmppc_e500_tlb_uninit(vcpu_e500);
+	kvm_vcpu_uninit(vcpu);
+	kmem_cache_free(kvm_vcpu_cache, vcpu_e500);
+}
+
+static int kvmppc_e500_init(void)
+{
+	int r;
+
+	r = kvmppc_booke_init();
+	if (r)
+		return r;
+
+	return kvm_init(NULL, sizeof(struct kvmppc_vcpu_e500), THIS_MODULE);
+}
+
+static void kvmppc_e500_exit(void)
+{
+	kvmppc_booke_exit();
+}
+
+module_init(kvmppc_e500_init);
+module_exit(kvmppc_e500_exit);
diff --git a/arch/powerpc/kvm/e500_emulate.c b/arch/powerpc/kvm/e500_emulate.c
new file mode 100644
index 000000000000..a47f44cd2cfd
--- /dev/null
+++ b/arch/powerpc/kvm/e500_emulate.c
@@ -0,0 +1,169 @@
+/*
+ * Copyright (C) 2008 Freescale Semiconductor, Inc. All rights reserved.
+ *
+ * Author: Yu Liu, <yu.liu@freescale.com>
+ *
+ * Description:
+ * This file is derived from arch/powerpc/kvm/44x_emulate.c,
+ * by Hollis Blanchard <hollisb@us.ibm.com>.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ */
+
+#include <asm/kvm_ppc.h>
+#include <asm/disassemble.h>
+#include <asm/kvm_e500.h>
+
+#include "booke.h"
+#include "e500_tlb.h"
+
+#define XOP_TLBIVAX 786
+#define XOP_TLBSX   914
+#define XOP_TLBRE   946
+#define XOP_TLBWE   978
+
+int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
+                           unsigned int inst, int *advance)
+{
+	int emulated = EMULATE_DONE;
+	int ra;
+	int rb;
+	int rs;
+	int rt;
+
+	switch (get_op(inst)) {
+	case 31:
+		switch (get_xop(inst)) {
+
+		case XOP_TLBRE:
+			emulated = kvmppc_e500_emul_tlbre(vcpu);
+			break;
+
+		case XOP_TLBWE:
+			emulated = kvmppc_e500_emul_tlbwe(vcpu);
+			break;
+
+		case XOP_TLBSX:
+			rb = get_rb(inst);
+			emulated = kvmppc_e500_emul_tlbsx(vcpu,rb);
+			break;
+
+		case XOP_TLBIVAX:
+			ra = get_ra(inst);
+			rb = get_rb(inst);
+			emulated = kvmppc_e500_emul_tlbivax(vcpu, ra, rb);
+			break;
+
+		default:
+			emulated = EMULATE_FAIL;
+		}
+
+		break;
+
+	default:
+		emulated = EMULATE_FAIL;
+	}
+
+	if (emulated == EMULATE_FAIL)
+		emulated = kvmppc_booke_emulate_op(run, vcpu, inst, advance);
+
+	return emulated;
+}
+
+int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+	int emulated = EMULATE_DONE;
+
+	switch (sprn) {
+	case SPRN_PID:
+		vcpu_e500->pid[0] = vcpu->arch.shadow_pid =
+			vcpu->arch.pid = vcpu->arch.gpr[rs];
+		break;
+	case SPRN_PID1:
+		vcpu_e500->pid[1] = vcpu->arch.gpr[rs]; break;
+	case SPRN_PID2:
+		vcpu_e500->pid[2] = vcpu->arch.gpr[rs]; break;
+	case SPRN_MAS0:
+		vcpu_e500->mas0 = vcpu->arch.gpr[rs]; break;
+	case SPRN_MAS1:
+		vcpu_e500->mas1 = vcpu->arch.gpr[rs]; break;
+	case SPRN_MAS2:
+		vcpu_e500->mas2 = vcpu->arch.gpr[rs]; break;
+	case SPRN_MAS3:
+		vcpu_e500->mas3 = vcpu->arch.gpr[rs]; break;
+	case SPRN_MAS4:
+		vcpu_e500->mas4 = vcpu->arch.gpr[rs]; break;
+	case SPRN_MAS6:
+		vcpu_e500->mas6 = vcpu->arch.gpr[rs]; break;
+	case SPRN_MAS7:
+		vcpu_e500->mas7 = vcpu->arch.gpr[rs]; break;
+	case SPRN_L1CSR1:
+		vcpu_e500->l1csr1 = vcpu->arch.gpr[rs]; break;
+	case SPRN_HID0:
+		vcpu_e500->hid0 = vcpu->arch.gpr[rs]; break;
+	case SPRN_HID1:
+		vcpu_e500->hid1 = vcpu->arch.gpr[rs]; break;
+
+	default:
+		emulated = kvmppc_booke_emulate_mtspr(vcpu, sprn, rs);
+	}
+
+	return emulated;
+}
+
+int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+	int emulated = EMULATE_DONE;
+
+	switch (sprn) {
+	case SPRN_PID:
+		vcpu->arch.gpr[rt] = vcpu_e500->pid[0]; break;
+	case SPRN_PID1:
+		vcpu->arch.gpr[rt] = vcpu_e500->pid[1]; break;
+	case SPRN_PID2:
+		vcpu->arch.gpr[rt] = vcpu_e500->pid[2]; break;
+	case SPRN_MAS0:
+		vcpu->arch.gpr[rt] = vcpu_e500->mas0; break;
+	case SPRN_MAS1:
+		vcpu->arch.gpr[rt] = vcpu_e500->mas1; break;
+	case SPRN_MAS2:
+		vcpu->arch.gpr[rt] = vcpu_e500->mas2; break;
+	case SPRN_MAS3:
+		vcpu->arch.gpr[rt] = vcpu_e500->mas3; break;
+	case SPRN_MAS4:
+		vcpu->arch.gpr[rt] = vcpu_e500->mas4; break;
+	case SPRN_MAS6:
+		vcpu->arch.gpr[rt] = vcpu_e500->mas6; break;
+	case SPRN_MAS7:
+		vcpu->arch.gpr[rt] = vcpu_e500->mas7; break;
+
+	case SPRN_TLB0CFG:
+		vcpu->arch.gpr[rt] = mfspr(SPRN_TLB0CFG);
+		vcpu->arch.gpr[rt] &= ~0xfffUL;
+		vcpu->arch.gpr[rt] |= vcpu_e500->guest_tlb_size[0];
+		break;
+
+	case SPRN_TLB1CFG:
+		vcpu->arch.gpr[rt] = mfspr(SPRN_TLB1CFG);
+		vcpu->arch.gpr[rt] &= ~0xfffUL;
+		vcpu->arch.gpr[rt] |= vcpu_e500->guest_tlb_size[1];
+		break;
+
+	case SPRN_L1CSR1:
+		vcpu->arch.gpr[rt] = vcpu_e500->l1csr1; break;
+	case SPRN_HID0:
+		vcpu->arch.gpr[rt] = vcpu_e500->hid0; break;
+	case SPRN_HID1:
+		vcpu->arch.gpr[rt] = vcpu_e500->hid1; break;
+
+	default:
+		emulated = kvmppc_booke_emulate_mfspr(vcpu, sprn, rt);
+	}
+
+	return emulated;
+}
+
diff --git a/arch/powerpc/kvm/e500_tlb.c b/arch/powerpc/kvm/e500_tlb.c
new file mode 100644
index 000000000000..6a50340f575e
--- /dev/null
+++ b/arch/powerpc/kvm/e500_tlb.c
@@ -0,0 +1,737 @@
+/*
+ * Copyright (C) 2008 Freescale Semiconductor, Inc. All rights reserved.
+ *
+ * Author: Yu Liu, yu.liu@freescale.com
+ *
+ * Description:
+ * This file is based on arch/powerpc/kvm/44x_tlb.c,
+ * by Hollis Blanchard <hollisb@us.ibm.com>.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include <linux/highmem.h>
+#include <asm/kvm_ppc.h>
+#include <asm/kvm_e500.h>
+
+#include "e500_tlb.h"
+
+#define to_htlb1_esel(esel) (tlb1_entry_num - (esel) - 1)
+
+static unsigned int tlb1_entry_num;
+
+void kvmppc_dump_tlbs(struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+	struct tlbe *tlbe;
+	int i, tlbsel;
+
+	printk("| %8s | %8s | %8s | %8s | %8s |\n",
+			"nr", "mas1", "mas2", "mas3", "mas7");
+
+	for (tlbsel = 0; tlbsel < 2; tlbsel++) {
+		printk("Guest TLB%d:\n", tlbsel);
+		for (i = 0; i < vcpu_e500->guest_tlb_size[tlbsel]; i++) {
+			tlbe = &vcpu_e500->guest_tlb[tlbsel][i];
+			if (tlbe->mas1 & MAS1_VALID)
+				printk(" G[%d][%3d] |  %08X | %08X | %08X | %08X |\n",
+					tlbsel, i, tlbe->mas1, tlbe->mas2,
+					tlbe->mas3, tlbe->mas7);
+		}
+	}
+
+	for (tlbsel = 0; tlbsel < 2; tlbsel++) {
+		printk("Shadow TLB%d:\n", tlbsel);
+		for (i = 0; i < vcpu_e500->shadow_tlb_size[tlbsel]; i++) {
+			tlbe = &vcpu_e500->shadow_tlb[tlbsel][i];
+			if (tlbe->mas1 & MAS1_VALID)
+				printk(" S[%d][%3d] |  %08X | %08X | %08X | %08X |\n",
+					tlbsel, i, tlbe->mas1, tlbe->mas2,
+					tlbe->mas3, tlbe->mas7);
+		}
+	}
+}
+
+static inline unsigned int tlb0_get_next_victim(
+		struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	unsigned int victim;
+
+	victim = vcpu_e500->guest_tlb_nv[0]++;
+	if (unlikely(vcpu_e500->guest_tlb_nv[0] >= KVM_E500_TLB0_WAY_NUM))
+		vcpu_e500->guest_tlb_nv[0] = 0;
+
+	return victim;
+}
+
+static inline unsigned int tlb1_max_shadow_size(void)
+{
+	return tlb1_entry_num - tlbcam_index;
+}
+
+static inline int tlbe_is_writable(struct tlbe *tlbe)
+{
+	return tlbe->mas3 & (MAS3_SW|MAS3_UW);
+}
+
+static inline u32 e500_shadow_mas3_attrib(u32 mas3, int usermode)
+{
+	/* Mask off reserved bits. */
+	mas3 &= MAS3_ATTRIB_MASK;
+
+	if (!usermode) {
+		/* Guest is in supervisor mode,
+		 * so we need to translate guest
+		 * supervisor permissions into user permissions. */
+		mas3 &= ~E500_TLB_USER_PERM_MASK;
+		mas3 |= (mas3 & E500_TLB_SUPER_PERM_MASK) << 1;
+	}
+
+	return mas3 | E500_TLB_SUPER_PERM_MASK;
+}
+
+static inline u32 e500_shadow_mas2_attrib(u32 mas2, int usermode)
+{
+	return mas2 & MAS2_ATTRIB_MASK;
+}
+
+/*
+ * writing shadow tlb entry to host TLB
+ */
+static inline void __write_host_tlbe(struct tlbe *stlbe)
+{
+	mtspr(SPRN_MAS1, stlbe->mas1);
+	mtspr(SPRN_MAS2, stlbe->mas2);
+	mtspr(SPRN_MAS3, stlbe->mas3);
+	mtspr(SPRN_MAS7, stlbe->mas7);
+	__asm__ __volatile__ ("tlbwe\n" : : );
+}
+
+static inline void write_host_tlbe(struct kvmppc_vcpu_e500 *vcpu_e500,
+		int tlbsel, int esel)
+{
+	struct tlbe *stlbe = &vcpu_e500->shadow_tlb[tlbsel][esel];
+
+	local_irq_disable();
+	if (tlbsel == 0) {
+		__write_host_tlbe(stlbe);
+	} else {
+		unsigned register mas0;
+
+		mas0 = mfspr(SPRN_MAS0);
+
+		mtspr(SPRN_MAS0, MAS0_TLBSEL(1) | MAS0_ESEL(to_htlb1_esel(esel)));
+		__write_host_tlbe(stlbe);
+
+		mtspr(SPRN_MAS0, mas0);
+	}
+	local_irq_enable();
+}
+
+void kvmppc_e500_tlb_load(struct kvm_vcpu *vcpu, int cpu)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+	int i;
+	unsigned register mas0;
+
+	/* Load all valid TLB1 entries to reduce guest tlb miss fault */
+	local_irq_disable();
+	mas0 = mfspr(SPRN_MAS0);
+	for (i = 0; i < tlb1_max_shadow_size(); i++) {
+		struct tlbe *stlbe = &vcpu_e500->shadow_tlb[1][i];
+
+		if (get_tlb_v(stlbe)) {
+			mtspr(SPRN_MAS0, MAS0_TLBSEL(1)
+					| MAS0_ESEL(to_htlb1_esel(i)));
+			__write_host_tlbe(stlbe);
+		}
+	}
+	mtspr(SPRN_MAS0, mas0);
+	local_irq_enable();
+}
+
+void kvmppc_e500_tlb_put(struct kvm_vcpu *vcpu)
+{
+	_tlbia();
+}
+
+/* Search the guest TLB for a matching entry. */
+static int kvmppc_e500_tlb_index(struct kvmppc_vcpu_e500 *vcpu_e500,
+		gva_t eaddr, int tlbsel, unsigned int pid, int as)
+{
+	int i;
+
+	/* XXX Replace loop with fancy data structures. */
+	for (i = 0; i < vcpu_e500->guest_tlb_size[tlbsel]; i++) {
+		struct tlbe *tlbe = &vcpu_e500->guest_tlb[tlbsel][i];
+		unsigned int tid;
+
+		if (eaddr < get_tlb_eaddr(tlbe))
+			continue;
+
+		if (eaddr > get_tlb_end(tlbe))
+			continue;
+
+		tid = get_tlb_tid(tlbe);
+		if (tid && (tid != pid))
+			continue;
+
+		if (!get_tlb_v(tlbe))
+			continue;
+
+		if (get_tlb_ts(tlbe) != as && as != -1)
+			continue;
+
+		return i;
+	}
+
+	return -1;
+}
+
+static void kvmppc_e500_shadow_release(struct kvmppc_vcpu_e500 *vcpu_e500,
+		int tlbsel, int esel)
+{
+	struct tlbe *stlbe = &vcpu_e500->shadow_tlb[tlbsel][esel];
+	struct page *page = vcpu_e500->shadow_pages[tlbsel][esel];
+
+	if (page) {
+		vcpu_e500->shadow_pages[tlbsel][esel] = NULL;
+
+		if (get_tlb_v(stlbe)) {
+			if (tlbe_is_writable(stlbe))
+				kvm_release_page_dirty(page);
+			else
+				kvm_release_page_clean(page);
+		}
+	}
+}
+
+static void kvmppc_e500_stlbe_invalidate(struct kvmppc_vcpu_e500 *vcpu_e500,
+		int tlbsel, int esel)
+{
+	struct tlbe *stlbe = &vcpu_e500->shadow_tlb[tlbsel][esel];
+
+	kvmppc_e500_shadow_release(vcpu_e500, tlbsel, esel);
+	stlbe->mas1 = 0;
+	KVMTRACE_5D(STLB_INVAL, &vcpu_e500->vcpu, index_of(tlbsel, esel),
+			stlbe->mas1, stlbe->mas2, stlbe->mas3, stlbe->mas7,
+			handler);
+}
+
+static void kvmppc_e500_tlb1_invalidate(struct kvmppc_vcpu_e500 *vcpu_e500,
+		gva_t eaddr, gva_t eend, u32 tid)
+{
+	unsigned int pid = tid & 0xff;
+	unsigned int i;
+
+	/* XXX Replace loop with fancy data structures. */
+	for (i = 0; i < vcpu_e500->guest_tlb_size[1]; i++) {
+		struct tlbe *stlbe = &vcpu_e500->shadow_tlb[1][i];
+		unsigned int tid;
+
+		if (!get_tlb_v(stlbe))
+			continue;
+
+		if (eend < get_tlb_eaddr(stlbe))
+			continue;
+
+		if (eaddr > get_tlb_end(stlbe))
+			continue;
+
+		tid = get_tlb_tid(stlbe);
+		if (tid && (tid != pid))
+			continue;
+
+		kvmppc_e500_stlbe_invalidate(vcpu_e500, 1, i);
+		write_host_tlbe(vcpu_e500, 1, i);
+	}
+}
+
+static inline void kvmppc_e500_deliver_tlb_miss(struct kvm_vcpu *vcpu,
+		unsigned int eaddr, int as)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+	unsigned int victim, pidsel, tsized;
+	int tlbsel;
+
+	/* since we only have tow TLBs, only lower bit is used. */
+	tlbsel = (vcpu_e500->mas4 >> 28) & 0x1;
+	victim = (tlbsel == 0) ? tlb0_get_next_victim(vcpu_e500) : 0;
+	pidsel = (vcpu_e500->mas4 >> 16) & 0xf;
+	tsized = (vcpu_e500->mas4 >> 8) & 0xf;
+
+	vcpu_e500->mas0 = MAS0_TLBSEL(tlbsel) | MAS0_ESEL(victim)
+		| MAS0_NV(vcpu_e500->guest_tlb_nv[tlbsel]);
+	vcpu_e500->mas1 = MAS1_VALID | (as ? MAS1_TS : 0)
+		| MAS1_TID(vcpu_e500->pid[pidsel])
+		| MAS1_TSIZE(tsized);
+	vcpu_e500->mas2 = (eaddr & MAS2_EPN)
+		| (vcpu_e500->mas4 & MAS2_ATTRIB_MASK);
+	vcpu_e500->mas3 &= MAS3_U0 | MAS3_U1 | MAS3_U2 | MAS3_U3;
+	vcpu_e500->mas6 = (vcpu_e500->mas6 & MAS6_SPID1)
+		| (get_cur_pid(vcpu) << 16)
+		| (as ? MAS6_SAS : 0);
+	vcpu_e500->mas7 = 0;
+}
+
+static inline void kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
+	u64 gvaddr, gfn_t gfn, struct tlbe *gtlbe, int tlbsel, int esel)
+{
+	struct page *new_page;
+	struct tlbe *stlbe;
+	hpa_t hpaddr;
+
+	stlbe = &vcpu_e500->shadow_tlb[tlbsel][esel];
+
+	/* Get reference to new page. */
+	new_page = gfn_to_page(vcpu_e500->vcpu.kvm, gfn);
+	if (is_error_page(new_page)) {
+		printk(KERN_ERR "Couldn't get guest page for gfn %lx!\n", gfn);
+		kvm_release_page_clean(new_page);
+		return;
+	}
+	hpaddr = page_to_phys(new_page);
+
+	/* Drop reference to old page. */
+	kvmppc_e500_shadow_release(vcpu_e500, tlbsel, esel);
+
+	vcpu_e500->shadow_pages[tlbsel][esel] = new_page;
+
+	/* Force TS=1 IPROT=0 TSIZE=4KB for all guest mappings. */
+	stlbe->mas1 = MAS1_TSIZE(BOOKE_PAGESZ_4K)
+		| MAS1_TID(get_tlb_tid(gtlbe)) | MAS1_TS | MAS1_VALID;
+	stlbe->mas2 = (gvaddr & MAS2_EPN)
+		| e500_shadow_mas2_attrib(gtlbe->mas2,
+				vcpu_e500->vcpu.arch.msr & MSR_PR);
+	stlbe->mas3 = (hpaddr & MAS3_RPN)
+		| e500_shadow_mas3_attrib(gtlbe->mas3,
+				vcpu_e500->vcpu.arch.msr & MSR_PR);
+	stlbe->mas7 = (hpaddr >> 32) & MAS7_RPN;
+
+	KVMTRACE_5D(STLB_WRITE, &vcpu_e500->vcpu, index_of(tlbsel, esel),
+			stlbe->mas1, stlbe->mas2, stlbe->mas3, stlbe->mas7,
+			handler);
+}
+
+/* XXX only map the one-one case, for now use TLB0 */
+static int kvmppc_e500_stlbe_map(struct kvmppc_vcpu_e500 *vcpu_e500,
+		int tlbsel, int esel)
+{
+	struct tlbe *gtlbe;
+
+	gtlbe = &vcpu_e500->guest_tlb[tlbsel][esel];
+
+	kvmppc_e500_shadow_map(vcpu_e500, get_tlb_eaddr(gtlbe),
+			get_tlb_raddr(gtlbe) >> PAGE_SHIFT,
+			gtlbe, tlbsel, esel);
+
+	return esel;
+}
+
+/* Caller must ensure that the specified guest TLB entry is safe to insert into
+ * the shadow TLB. */
+/* XXX for both one-one and one-to-many , for now use TLB1 */
+static int kvmppc_e500_tlb1_map(struct kvmppc_vcpu_e500 *vcpu_e500,
+		u64 gvaddr, gfn_t gfn, struct tlbe *gtlbe)
+{
+	unsigned int victim;
+
+	victim = vcpu_e500->guest_tlb_nv[1]++;
+
+	if (unlikely(vcpu_e500->guest_tlb_nv[1] >= tlb1_max_shadow_size()))
+		vcpu_e500->guest_tlb_nv[1] = 0;
+
+	kvmppc_e500_shadow_map(vcpu_e500, gvaddr, gfn, gtlbe, 1, victim);
+
+	return victim;
+}
+
+/* Invalidate all guest kernel mappings when enter usermode,
+ * so that when they fault back in they will get the
+ * proper permission bits. */
+void kvmppc_mmu_priv_switch(struct kvm_vcpu *vcpu, int usermode)
+{
+	if (usermode) {
+		struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+		int i;
+
+		/* XXX Replace loop with fancy data structures. */
+		/* needn't set modified since tlbia will make TLB1 coherent */
+		for (i = 0; i < tlb1_max_shadow_size(); i++)
+			kvmppc_e500_stlbe_invalidate(vcpu_e500, 1, i);
+
+		_tlbia();
+	}
+}
+
+static int kvmppc_e500_gtlbe_invalidate(struct kvmppc_vcpu_e500 *vcpu_e500,
+		int tlbsel, int esel)
+{
+	struct tlbe *gtlbe = &vcpu_e500->guest_tlb[tlbsel][esel];
+
+	if (unlikely(get_tlb_iprot(gtlbe)))
+		return -1;
+
+	if (tlbsel == 1) {
+		kvmppc_e500_tlb1_invalidate(vcpu_e500, get_tlb_eaddr(gtlbe),
+				get_tlb_end(gtlbe),
+				get_tlb_tid(gtlbe));
+	} else {
+		kvmppc_e500_stlbe_invalidate(vcpu_e500, tlbsel, esel);
+	}
+
+	gtlbe->mas1 = 0;
+
+	return 0;
+}
+
+int kvmppc_e500_emul_tlbivax(struct kvm_vcpu *vcpu, int ra, int rb)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+	unsigned int ia;
+	int esel, tlbsel;
+	gva_t ea;
+
+	ea = ((ra) ? vcpu->arch.gpr[ra] : 0) + vcpu->arch.gpr[rb];
+
+	ia = (ea >> 2) & 0x1;
+
+	/* since we only have tow TLBs, only lower bit is used. */
+	tlbsel = (ea >> 3) & 0x1;
+
+	if (ia) {
+		/* invalidate all entries */
+		for (esel = 0; esel < vcpu_e500->guest_tlb_size[tlbsel]; esel++)
+			kvmppc_e500_gtlbe_invalidate(vcpu_e500, tlbsel, esel);
+	} else {
+		ea &= 0xfffff000;
+		esel = kvmppc_e500_tlb_index(vcpu_e500, ea, tlbsel,
+				get_cur_pid(vcpu), -1);
+		if (esel >= 0)
+			kvmppc_e500_gtlbe_invalidate(vcpu_e500, tlbsel, esel);
+	}
+
+	_tlbia();
+
+	return EMULATE_DONE;
+}
+
+int kvmppc_e500_emul_tlbre(struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+	int tlbsel, esel;
+	struct tlbe *gtlbe;
+
+	tlbsel = get_tlb_tlbsel(vcpu_e500);
+	esel = get_tlb_esel(vcpu_e500, tlbsel);
+
+	gtlbe = &vcpu_e500->guest_tlb[tlbsel][esel];
+	vcpu_e500->mas0 &= MAS0_NV(0);
+	vcpu_e500->mas0 |= MAS0_NV(vcpu_e500->guest_tlb_nv[tlbsel]);
+	vcpu_e500->mas1 = gtlbe->mas1;
+	vcpu_e500->mas2 = gtlbe->mas2;
+	vcpu_e500->mas3 = gtlbe->mas3;
+	vcpu_e500->mas7 = gtlbe->mas7;
+
+	return EMULATE_DONE;
+}
+
+int kvmppc_e500_emul_tlbsx(struct kvm_vcpu *vcpu, int rb)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+	int as = !!get_cur_sas(vcpu_e500);
+	unsigned int pid = get_cur_spid(vcpu_e500);
+	int esel, tlbsel;
+	struct tlbe *gtlbe = NULL;
+	gva_t ea;
+
+	ea = vcpu->arch.gpr[rb];
+
+	for (tlbsel = 0; tlbsel < 2; tlbsel++) {
+		esel = kvmppc_e500_tlb_index(vcpu_e500, ea, tlbsel, pid, as);
+		if (esel >= 0) {
+			gtlbe = &vcpu_e500->guest_tlb[tlbsel][esel];
+			break;
+		}
+	}
+
+	if (gtlbe) {
+		vcpu_e500->mas0 = MAS0_TLBSEL(tlbsel) | MAS0_ESEL(esel)
+			| MAS0_NV(vcpu_e500->guest_tlb_nv[tlbsel]);
+		vcpu_e500->mas1 = gtlbe->mas1;
+		vcpu_e500->mas2 = gtlbe->mas2;
+		vcpu_e500->mas3 = gtlbe->mas3;
+		vcpu_e500->mas7 = gtlbe->mas7;
+	} else {
+		int victim;
+
+		/* since we only have tow TLBs, only lower bit is used. */
+		tlbsel = vcpu_e500->mas4 >> 28 & 0x1;
+		victim = (tlbsel == 0) ? tlb0_get_next_victim(vcpu_e500) : 0;
+
+		vcpu_e500->mas0 = MAS0_TLBSEL(tlbsel) | MAS0_ESEL(victim)
+			| MAS0_NV(vcpu_e500->guest_tlb_nv[tlbsel]);
+		vcpu_e500->mas1 = (vcpu_e500->mas6 & MAS6_SPID0)
+			| (vcpu_e500->mas6 & (MAS6_SAS ? MAS1_TS : 0))
+			| (vcpu_e500->mas4 & MAS4_TSIZED(~0));
+		vcpu_e500->mas2 &= MAS2_EPN;
+		vcpu_e500->mas2 |= vcpu_e500->mas4 & MAS2_ATTRIB_MASK;
+		vcpu_e500->mas3 &= MAS3_U0 | MAS3_U1 | MAS3_U2 | MAS3_U3;
+		vcpu_e500->mas7 = 0;
+	}
+
+	return EMULATE_DONE;
+}
+
+int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+	u64 eaddr;
+	u64 raddr;
+	u32 tid;
+	struct tlbe *gtlbe;
+	int tlbsel, esel, stlbsel, sesel;
+
+	tlbsel = get_tlb_tlbsel(vcpu_e500);
+	esel = get_tlb_esel(vcpu_e500, tlbsel);
+
+	gtlbe = &vcpu_e500->guest_tlb[tlbsel][esel];
+
+	if (get_tlb_v(gtlbe) && tlbsel == 1) {
+		eaddr = get_tlb_eaddr(gtlbe);
+		tid = get_tlb_tid(gtlbe);
+		kvmppc_e500_tlb1_invalidate(vcpu_e500, eaddr,
+				get_tlb_end(gtlbe), tid);
+	}
+
+	gtlbe->mas1 = vcpu_e500->mas1;
+	gtlbe->mas2 = vcpu_e500->mas2;
+	gtlbe->mas3 = vcpu_e500->mas3;
+	gtlbe->mas7 = vcpu_e500->mas7;
+
+	KVMTRACE_5D(GTLB_WRITE, vcpu, vcpu_e500->mas0,
+			gtlbe->mas1, gtlbe->mas2, gtlbe->mas3, gtlbe->mas7,
+			handler);
+
+	/* Invalidate shadow mappings for the about-to-be-clobbered TLBE. */
+	if (tlbe_is_host_safe(vcpu, gtlbe)) {
+		switch (tlbsel) {
+		case 0:
+			/* TLB0 */
+			gtlbe->mas1 &= ~MAS1_TSIZE(~0);
+			gtlbe->mas1 |= MAS1_TSIZE(BOOKE_PAGESZ_4K);
+
+			stlbsel = 0;
+			sesel = kvmppc_e500_stlbe_map(vcpu_e500, 0, esel);
+
+			break;
+
+		case 1:
+			/* TLB1 */
+			eaddr = get_tlb_eaddr(gtlbe);
+			raddr = get_tlb_raddr(gtlbe);
+
+			/* Create a 4KB mapping on the host.
+			 * If the guest wanted a large page,
+			 * only the first 4KB is mapped here and the rest
+			 * are mapped on the fly. */
+			stlbsel = 1;
+			sesel = kvmppc_e500_tlb1_map(vcpu_e500, eaddr,
+					raddr >> PAGE_SHIFT, gtlbe);
+			break;
+
+		default:
+			BUG();
+		}
+		write_host_tlbe(vcpu_e500, stlbsel, sesel);
+	}
+
+	return EMULATE_DONE;
+}
+
+int kvmppc_mmu_itlb_index(struct kvm_vcpu *vcpu, gva_t eaddr)
+{
+	unsigned int as = !!(vcpu->arch.msr & MSR_IS);
+
+	return kvmppc_e500_tlb_search(vcpu, eaddr, get_cur_pid(vcpu), as);
+}
+
+int kvmppc_mmu_dtlb_index(struct kvm_vcpu *vcpu, gva_t eaddr)
+{
+	unsigned int as = !!(vcpu->arch.msr & MSR_DS);
+
+	return kvmppc_e500_tlb_search(vcpu, eaddr, get_cur_pid(vcpu), as);
+}
+
+void kvmppc_mmu_itlb_miss(struct kvm_vcpu *vcpu)
+{
+	unsigned int as = !!(vcpu->arch.msr & MSR_IS);
+
+	kvmppc_e500_deliver_tlb_miss(vcpu, vcpu->arch.pc, as);
+}
+
+void kvmppc_mmu_dtlb_miss(struct kvm_vcpu *vcpu)
+{
+	unsigned int as = !!(vcpu->arch.msr & MSR_DS);
+
+	kvmppc_e500_deliver_tlb_miss(vcpu, vcpu->arch.fault_dear, as);
+}
+
+gpa_t kvmppc_mmu_xlate(struct kvm_vcpu *vcpu, unsigned int index,
+			gva_t eaddr)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+	struct tlbe *gtlbe =
+		&vcpu_e500->guest_tlb[tlbsel_of(index)][esel_of(index)];
+	u64 pgmask = get_tlb_bytes(gtlbe) - 1;
+
+	return get_tlb_raddr(gtlbe) | (eaddr & pgmask);
+}
+
+void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+	int tlbsel, i;
+
+	for (tlbsel = 0; tlbsel < 2; tlbsel++)
+		for (i = 0; i < vcpu_e500->guest_tlb_size[tlbsel]; i++)
+			kvmppc_e500_shadow_release(vcpu_e500, tlbsel, i);
+
+	/* discard all guest mapping */
+	_tlbia();
+}
+
+void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 eaddr, gpa_t gpaddr,
+			unsigned int index)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+	int tlbsel = tlbsel_of(index);
+	int esel = esel_of(index);
+	int stlbsel, sesel;
+
+	switch (tlbsel) {
+	case 0:
+		stlbsel = 0;
+		sesel = esel;
+		break;
+
+	case 1: {
+		gfn_t gfn = gpaddr >> PAGE_SHIFT;
+		struct tlbe *gtlbe
+			= &vcpu_e500->guest_tlb[tlbsel][esel];
+
+		stlbsel = 1;
+		sesel = kvmppc_e500_tlb1_map(vcpu_e500, eaddr, gfn, gtlbe);
+		break;
+	}
+
+	default:
+		BUG();
+		break;
+	}
+	write_host_tlbe(vcpu_e500, stlbsel, sesel);
+}
+
+int kvmppc_e500_tlb_search(struct kvm_vcpu *vcpu,
+				gva_t eaddr, unsigned int pid, int as)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+	int esel, tlbsel;
+
+	for (tlbsel = 0; tlbsel < 2; tlbsel++) {
+		esel = kvmppc_e500_tlb_index(vcpu_e500, eaddr, tlbsel, pid, as);
+		if (esel >= 0)
+			return index_of(tlbsel, esel);
+	}
+
+	return -1;
+}
+
+void kvmppc_e500_tlb_setup(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	struct tlbe *tlbe;
+
+	/* Insert large initial mapping for guest. */
+	tlbe = &vcpu_e500->guest_tlb[1][0];
+	tlbe->mas1 = MAS1_VALID | MAS1_TSIZE(BOOKE_PAGESZ_256M);
+	tlbe->mas2 = 0;
+	tlbe->mas3 = E500_TLB_SUPER_PERM_MASK;
+	tlbe->mas7 = 0;
+
+	/* 4K map for serial output. Used by kernel wrapper. */
+	tlbe = &vcpu_e500->guest_tlb[1][1];
+	tlbe->mas1 = MAS1_VALID | MAS1_TSIZE(BOOKE_PAGESZ_4K);
+	tlbe->mas2 = (0xe0004500 & 0xFFFFF000) | MAS2_I | MAS2_G;
+	tlbe->mas3 = (0xe0004500 & 0xFFFFF000) | E500_TLB_SUPER_PERM_MASK;
+	tlbe->mas7 = 0;
+}
+
+int kvmppc_e500_tlb_init(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	tlb1_entry_num = mfspr(SPRN_TLB1CFG) & 0xFFF;
+
+	vcpu_e500->guest_tlb_size[0] = KVM_E500_TLB0_SIZE;
+	vcpu_e500->guest_tlb[0] =
+		kzalloc(sizeof(struct tlbe) * KVM_E500_TLB0_SIZE, GFP_KERNEL);
+	if (vcpu_e500->guest_tlb[0] == NULL)
+		goto err_out;
+
+	vcpu_e500->shadow_tlb_size[0] = KVM_E500_TLB0_SIZE;
+	vcpu_e500->shadow_tlb[0] =
+		kzalloc(sizeof(struct tlbe) * KVM_E500_TLB0_SIZE, GFP_KERNEL);
+	if (vcpu_e500->shadow_tlb[0] == NULL)
+		goto err_out_guest0;
+
+	vcpu_e500->guest_tlb_size[1] = KVM_E500_TLB1_SIZE;
+	vcpu_e500->guest_tlb[1] =
+		kzalloc(sizeof(struct tlbe) * KVM_E500_TLB1_SIZE, GFP_KERNEL);
+	if (vcpu_e500->guest_tlb[1] == NULL)
+		goto err_out_shadow0;
+
+	vcpu_e500->shadow_tlb_size[1] = tlb1_entry_num;
+	vcpu_e500->shadow_tlb[1] =
+		kzalloc(sizeof(struct tlbe) * tlb1_entry_num, GFP_KERNEL);
+	if (vcpu_e500->shadow_tlb[1] == NULL)
+		goto err_out_guest1;
+
+	vcpu_e500->shadow_pages[0] = (struct page **)
+		kzalloc(sizeof(struct page *) * KVM_E500_TLB0_SIZE, GFP_KERNEL);
+	if (vcpu_e500->shadow_pages[0] == NULL)
+		goto err_out_shadow1;
+
+	vcpu_e500->shadow_pages[1] = (struct page **)
+		kzalloc(sizeof(struct page *) * tlb1_entry_num, GFP_KERNEL);
+	if (vcpu_e500->shadow_pages[1] == NULL)
+		goto err_out_page0;
+
+	return 0;
+
+err_out_page0:
+	kfree(vcpu_e500->shadow_pages[0]);
+err_out_shadow1:
+	kfree(vcpu_e500->shadow_tlb[1]);
+err_out_guest1:
+	kfree(vcpu_e500->guest_tlb[1]);
+err_out_shadow0:
+	kfree(vcpu_e500->shadow_tlb[0]);
+err_out_guest0:
+	kfree(vcpu_e500->guest_tlb[0]);
+err_out:
+	return -1;
+}
+
+void kvmppc_e500_tlb_uninit(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	kfree(vcpu_e500->shadow_pages[1]);
+	kfree(vcpu_e500->shadow_pages[0]);
+	kfree(vcpu_e500->shadow_tlb[1]);
+	kfree(vcpu_e500->guest_tlb[1]);
+	kfree(vcpu_e500->shadow_tlb[0]);
+	kfree(vcpu_e500->guest_tlb[0]);
+}
diff --git a/arch/powerpc/kvm/e500_tlb.h b/arch/powerpc/kvm/e500_tlb.h
new file mode 100644
index 000000000000..d8833f955163
--- /dev/null
+++ b/arch/powerpc/kvm/e500_tlb.h
@@ -0,0 +1,184 @@
+/*
+ * Copyright (C) 2008 Freescale Semiconductor, Inc. All rights reserved.
+ *
+ * Author: Yu Liu, yu.liu@freescale.com
+ *
+ * Description:
+ * This file is based on arch/powerpc/kvm/44x_tlb.h,
+ * by Hollis Blanchard <hollisb@us.ibm.com>.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __KVM_E500_TLB_H__
+#define __KVM_E500_TLB_H__
+
+#include <linux/kvm_host.h>
+#include <asm/mmu-fsl-booke.h>
+#include <asm/tlb.h>
+#include <asm/kvm_e500.h>
+
+#define KVM_E500_TLB0_WAY_SIZE_BIT	7	/* Fixed */
+#define KVM_E500_TLB0_WAY_SIZE		(1UL << KVM_E500_TLB0_WAY_SIZE_BIT)
+#define KVM_E500_TLB0_WAY_SIZE_MASK	(KVM_E500_TLB0_WAY_SIZE - 1)
+
+#define KVM_E500_TLB0_WAY_NUM_BIT	1	/* No greater than 7 */
+#define KVM_E500_TLB0_WAY_NUM		(1UL << KVM_E500_TLB0_WAY_NUM_BIT)
+#define KVM_E500_TLB0_WAY_NUM_MASK	(KVM_E500_TLB0_WAY_NUM - 1)
+
+#define KVM_E500_TLB0_SIZE  (KVM_E500_TLB0_WAY_SIZE * KVM_E500_TLB0_WAY_NUM)
+#define KVM_E500_TLB1_SIZE  16
+
+#define index_of(tlbsel, esel)	(((tlbsel) << 16) | ((esel) & 0xFFFF))
+#define tlbsel_of(index)	((index) >> 16)
+#define esel_of(index)		((index) & 0xFFFF)
+
+#define E500_TLB_USER_PERM_MASK (MAS3_UX|MAS3_UR|MAS3_UW)
+#define E500_TLB_SUPER_PERM_MASK (MAS3_SX|MAS3_SR|MAS3_SW)
+#define MAS2_ATTRIB_MASK \
+	  (MAS2_X0 | MAS2_X1 | MAS2_W | MAS2_I | MAS2_M | MAS2_G | MAS2_E)
+#define MAS3_ATTRIB_MASK \
+	  (MAS3_U0 | MAS3_U1 | MAS3_U2 | MAS3_U3 \
+	   | E500_TLB_USER_PERM_MASK | E500_TLB_SUPER_PERM_MASK)
+
+extern void kvmppc_dump_tlbs(struct kvm_vcpu *);
+extern int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *);
+extern int kvmppc_e500_emul_tlbre(struct kvm_vcpu *);
+extern int kvmppc_e500_emul_tlbivax(struct kvm_vcpu *, int, int);
+extern int kvmppc_e500_emul_tlbsx(struct kvm_vcpu *, int);
+extern int kvmppc_e500_tlb_search(struct kvm_vcpu *, gva_t, unsigned int, int);
+extern void kvmppc_e500_tlb_put(struct kvm_vcpu *);
+extern void kvmppc_e500_tlb_load(struct kvm_vcpu *, int);
+extern int kvmppc_e500_tlb_init(struct kvmppc_vcpu_e500 *);
+extern void kvmppc_e500_tlb_uninit(struct kvmppc_vcpu_e500 *);
+extern void kvmppc_e500_tlb_setup(struct kvmppc_vcpu_e500 *);
+
+/* TLB helper functions */
+static inline unsigned int get_tlb_size(const struct tlbe *tlbe)
+{
+	return (tlbe->mas1 >> 8) & 0xf;
+}
+
+static inline gva_t get_tlb_eaddr(const struct tlbe *tlbe)
+{
+	return tlbe->mas2 & 0xfffff000;
+}
+
+static inline u64 get_tlb_bytes(const struct tlbe *tlbe)
+{
+	unsigned int pgsize = get_tlb_size(tlbe);
+	return 1ULL << 10 << (pgsize << 1);
+}
+
+static inline gva_t get_tlb_end(const struct tlbe *tlbe)
+{
+	u64 bytes = get_tlb_bytes(tlbe);
+	return get_tlb_eaddr(tlbe) + bytes - 1;
+}
+
+static inline u64 get_tlb_raddr(const struct tlbe *tlbe)
+{
+	u64 rpn = tlbe->mas7;
+	return (rpn << 32) | (tlbe->mas3 & 0xfffff000);
+}
+
+static inline unsigned int get_tlb_tid(const struct tlbe *tlbe)
+{
+	return (tlbe->mas1 >> 16) & 0xff;
+}
+
+static inline unsigned int get_tlb_ts(const struct tlbe *tlbe)
+{
+	return (tlbe->mas1 >> 12) & 0x1;
+}
+
+static inline unsigned int get_tlb_v(const struct tlbe *tlbe)
+{
+	return (tlbe->mas1 >> 31) & 0x1;
+}
+
+static inline unsigned int get_tlb_iprot(const struct tlbe *tlbe)
+{
+	return (tlbe->mas1 >> 30) & 0x1;
+}
+
+static inline unsigned int get_cur_pid(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.pid & 0xff;
+}
+
+static inline unsigned int get_cur_spid(
+		const struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	return (vcpu_e500->mas6 >> 16) & 0xff;
+}
+
+static inline unsigned int get_cur_sas(
+		const struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	return vcpu_e500->mas6 & 0x1;
+}
+
+static inline unsigned int get_tlb_tlbsel(
+		const struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	/*
+	 * Manual says that tlbsel has 2 bits wide.
+	 * Since we only have tow TLBs, only lower bit is used.
+	 */
+	return (vcpu_e500->mas0 >> 28) & 0x1;
+}
+
+static inline unsigned int get_tlb_nv_bit(
+		const struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	return vcpu_e500->mas0 & 0xfff;
+}
+
+static inline unsigned int get_tlb_esel_bit(
+		const struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	return (vcpu_e500->mas0 >> 16) & 0xfff;
+}
+
+static inline unsigned int get_tlb_esel(
+		const struct kvmppc_vcpu_e500 *vcpu_e500,
+		int tlbsel)
+{
+	unsigned int esel = get_tlb_esel_bit(vcpu_e500);
+
+	if (tlbsel == 0) {
+		esel &= KVM_E500_TLB0_WAY_NUM_MASK;
+		esel |= ((vcpu_e500->mas2 >> 12) & KVM_E500_TLB0_WAY_SIZE_MASK)
+				<< KVM_E500_TLB0_WAY_NUM_BIT;
+	} else {
+		esel &= KVM_E500_TLB1_SIZE - 1;
+	}
+
+	return esel;
+}
+
+static inline int tlbe_is_host_safe(const struct kvm_vcpu *vcpu,
+			const struct tlbe *tlbe)
+{
+	gpa_t gpa;
+
+	if (!get_tlb_v(tlbe))
+		return 0;
+
+	/* Does it match current guest AS? */
+	/* XXX what about IS != DS? */
+	if (get_tlb_ts(tlbe) != !!(vcpu->arch.msr & MSR_IS))
+		return 0;
+
+	gpa = get_tlb_raddr(tlbe);
+	if (!gfn_to_memslot(vcpu->kvm, gpa >> PAGE_SHIFT))
+		/* Mapping is not for RAM. */
+		return 0;
+
+	return 1;
+}
+
+#endif /* __KVM_E500_TLB_H__ */
-- 
cgit v1.2.3


From b52a638c391c5c7b013180f5374274698b8535c8 Mon Sep 17 00:00:00 2001
From: Hollis Blanchard
Date: Sat, 3 Jan 2009 16:23:11 -0600
Subject: KVM: ppc: Add kvmppc_mmu_dtlb/itlb_miss for booke

When itlb or dtlb miss happens, E500 needs to update some mmu registers.
So that the auto-load mechanism can work on E500 when write a tlb entry.

Signed-off-by: Liu Yu <yu.liu@freescale.com>
Signed-off-by: Hollis Blanchard <hollisb@us.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/include/asm/kvm_ppc.h | 2 ++
 arch/powerpc/kvm/44x_tlb.c         | 8 ++++++++
 arch/powerpc/kvm/booke.c           | 2 ++
 3 files changed, 12 insertions(+)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 5e80a20f32b8..6052779dbb56 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -63,6 +63,8 @@ extern int kvmppc_mmu_dtlb_index(struct kvm_vcpu *vcpu, gva_t eaddr);
 extern int kvmppc_mmu_itlb_index(struct kvm_vcpu *vcpu, gva_t eaddr);
 extern gpa_t kvmppc_mmu_xlate(struct kvm_vcpu *vcpu, unsigned int gtlb_index,
                               gva_t eaddr);
+extern void kvmppc_mmu_dtlb_miss(struct kvm_vcpu *vcpu);
+extern void kvmppc_mmu_itlb_miss(struct kvm_vcpu *vcpu);
 
 extern struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm,
                                                 unsigned int id);
diff --git a/arch/powerpc/kvm/44x_tlb.c b/arch/powerpc/kvm/44x_tlb.c
index e67b7313ffc3..4a16f472cc18 100644
--- a/arch/powerpc/kvm/44x_tlb.c
+++ b/arch/powerpc/kvm/44x_tlb.c
@@ -232,6 +232,14 @@ int kvmppc_mmu_dtlb_index(struct kvm_vcpu *vcpu, gva_t eaddr)
 	return kvmppc_44x_tlb_index(vcpu, eaddr, vcpu->arch.pid, as);
 }
 
+void kvmppc_mmu_itlb_miss(struct kvm_vcpu *vcpu)
+{
+}
+
+void kvmppc_mmu_dtlb_miss(struct kvm_vcpu *vcpu)
+{
+}
+
 static void kvmppc_44x_shadow_release(struct kvmppc_vcpu_44x *vcpu_44x,
                                       unsigned int stlb_index)
 {
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index a73b3959e41c..933c406c7915 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -295,6 +295,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_DTLB_MISS);
 			vcpu->arch.dear = vcpu->arch.fault_dear;
 			vcpu->arch.esr = vcpu->arch.fault_esr;
+			kvmppc_mmu_dtlb_miss(vcpu);
 			kvmppc_account_exit(vcpu, DTLB_REAL_MISS_EXITS);
 			r = RESUME_GUEST;
 			break;
@@ -337,6 +338,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		if (gtlb_index < 0) {
 			/* The guest didn't have a mapping for it. */
 			kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_ITLB_MISS);
+			kvmppc_mmu_itlb_miss(vcpu);
 			kvmppc_account_exit(vcpu, ITLB_REAL_MISS_EXITS);
 			break;
 		}
-- 
cgit v1.2.3


From bb3a8a178dec1e46df3138a30f76acf67fe12397 Mon Sep 17 00:00:00 2001
From: Hollis Blanchard
Date: Sat, 3 Jan 2009 16:23:13 -0600
Subject: KVM: ppc: Add extra E500 exceptions

e500 has additional interrupt vectors (and corresponding IVORs) for SPE and
performance monitoring interrupts.

Signed-off-by: Liu Yu <yu.liu@freescale.com>
Signed-off-by: Hollis Blanchard <hollisb@us.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/include/asm/kvm_asm.h  |  7 ++++++-
 arch/powerpc/include/asm/kvm_host.h |  2 +-
 arch/powerpc/kvm/booke.c            | 18 ++++++++++++++++++
 arch/powerpc/kvm/booke.h            | 30 ++++++++++++++++++------------
 arch/powerpc/kvm/booke_interrupts.S |  3 +++
 arch/powerpc/kvm/e500.c             | 20 +++++++++++++++++++-
 arch/powerpc/kvm/e500_emulate.c     | 27 +++++++++++++++++++++++++++
 7 files changed, 92 insertions(+), 15 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h
index 2197764796d9..56bfae59837f 100644
--- a/arch/powerpc/include/asm/kvm_asm.h
+++ b/arch/powerpc/include/asm/kvm_asm.h
@@ -42,7 +42,12 @@
 #define BOOKE_INTERRUPT_DTLB_MISS 13
 #define BOOKE_INTERRUPT_ITLB_MISS 14
 #define BOOKE_INTERRUPT_DEBUG 15
-#define BOOKE_MAX_INTERRUPT 15
+
+/* E500 */
+#define BOOKE_INTERRUPT_SPE_UNAVAIL 32
+#define BOOKE_INTERRUPT_SPE_FP_DATA 33
+#define BOOKE_INTERRUPT_SPE_FP_ROUND 34
+#define BOOKE_INTERRUPT_PERFORMANCE_MONITOR 35
 
 #define RESUME_FLAG_NV          (1<<0)  /* Reload guest nonvolatile state? */
 #define RESUME_FLAG_HOST        (1<<1)  /* Resume host? */
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 50e5ce1b400a..1c6187697520 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -150,7 +150,7 @@ struct kvm_vcpu_arch {
 	u32 tbu;
 	u32 tcr;
 	u32 tsr;
-	u32 ivor[16];
+	u32 ivor[64];
 	ulong ivpr;
 	u32 pir;
 
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index f192fbee2f29..642e4204cf25 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -118,6 +118,9 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
 	case BOOKE_IRQPRIO_DATA_STORAGE:
 	case BOOKE_IRQPRIO_INST_STORAGE:
 	case BOOKE_IRQPRIO_FP_UNAVAIL:
+	case BOOKE_IRQPRIO_SPE_UNAVAIL:
+	case BOOKE_IRQPRIO_SPE_FP_DATA:
+	case BOOKE_IRQPRIO_SPE_FP_ROUND:
 	case BOOKE_IRQPRIO_AP_UNAVAIL:
 	case BOOKE_IRQPRIO_ALIGNMENT:
 		allowed = 1;
@@ -261,6 +264,21 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		r = RESUME_GUEST;
 		break;
 
+	case BOOKE_INTERRUPT_SPE_UNAVAIL:
+		kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_SPE_UNAVAIL);
+		r = RESUME_GUEST;
+		break;
+
+	case BOOKE_INTERRUPT_SPE_FP_DATA:
+		kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_SPE_FP_DATA);
+		r = RESUME_GUEST;
+		break;
+
+	case BOOKE_INTERRUPT_SPE_FP_ROUND:
+		kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_SPE_FP_ROUND);
+		r = RESUME_GUEST;
+		break;
+
 	case BOOKE_INTERRUPT_DATA_STORAGE:
 		vcpu->arch.dear = vcpu->arch.fault_dear;
 		vcpu->arch.esr = vcpu->arch.fault_esr;
diff --git a/arch/powerpc/kvm/booke.h b/arch/powerpc/kvm/booke.h
index 7ceeb3e739b4..d59bcca1f9d8 100644
--- a/arch/powerpc/kvm/booke.h
+++ b/arch/powerpc/kvm/booke.h
@@ -31,18 +31,24 @@
 #define BOOKE_IRQPRIO_ALIGNMENT 2
 #define BOOKE_IRQPRIO_PROGRAM 3
 #define BOOKE_IRQPRIO_FP_UNAVAIL 4
-#define BOOKE_IRQPRIO_SYSCALL 5
-#define BOOKE_IRQPRIO_AP_UNAVAIL 6
-#define BOOKE_IRQPRIO_DTLB_MISS 7
-#define BOOKE_IRQPRIO_ITLB_MISS 8
-#define BOOKE_IRQPRIO_MACHINE_CHECK 9
-#define BOOKE_IRQPRIO_DEBUG 10
-#define BOOKE_IRQPRIO_CRITICAL 11
-#define BOOKE_IRQPRIO_WATCHDOG 12
-#define BOOKE_IRQPRIO_EXTERNAL 13
-#define BOOKE_IRQPRIO_FIT 14
-#define BOOKE_IRQPRIO_DECREMENTER 15
-#define BOOKE_IRQPRIO_MAX 15
+#define BOOKE_IRQPRIO_SPE_UNAVAIL 5
+#define BOOKE_IRQPRIO_SPE_FP_DATA 6
+#define BOOKE_IRQPRIO_SPE_FP_ROUND 7
+#define BOOKE_IRQPRIO_SYSCALL 8
+#define BOOKE_IRQPRIO_AP_UNAVAIL 9
+#define BOOKE_IRQPRIO_DTLB_MISS 10
+#define BOOKE_IRQPRIO_ITLB_MISS 11
+#define BOOKE_IRQPRIO_MACHINE_CHECK 12
+#define BOOKE_IRQPRIO_DEBUG 13
+#define BOOKE_IRQPRIO_CRITICAL 14
+#define BOOKE_IRQPRIO_WATCHDOG 15
+#define BOOKE_IRQPRIO_EXTERNAL 16
+#define BOOKE_IRQPRIO_FIT 17
+#define BOOKE_IRQPRIO_DECREMENTER 18
+#define BOOKE_IRQPRIO_PERFORMANCE_MONITOR 19
+#define BOOKE_IRQPRIO_MAX 19
+
+extern unsigned long kvmppc_booke_handlers;
 
 /* Helper function for "full" MSR writes. No need to call this if only EE is
  * changing. */
diff --git a/arch/powerpc/kvm/booke_interrupts.S b/arch/powerpc/kvm/booke_interrupts.S
index 4679ec287e62..d0c6f841bbd1 100644
--- a/arch/powerpc/kvm/booke_interrupts.S
+++ b/arch/powerpc/kvm/booke_interrupts.S
@@ -86,6 +86,9 @@ KVM_HANDLER BOOKE_INTERRUPT_WATCHDOG
 KVM_HANDLER BOOKE_INTERRUPT_DTLB_MISS
 KVM_HANDLER BOOKE_INTERRUPT_ITLB_MISS
 KVM_HANDLER BOOKE_INTERRUPT_DEBUG
+KVM_HANDLER BOOKE_INTERRUPT_SPE_UNAVAIL
+KVM_HANDLER BOOKE_INTERRUPT_SPE_FP_DATA
+KVM_HANDLER BOOKE_INTERRUPT_SPE_FP_ROUND
 
 _GLOBAL(kvmppc_handler_len)
 	.long kvmppc_handler_1 - kvmppc_handler_0
diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c
index 7992da497cd4..d8067fd81cdd 100644
--- a/arch/powerpc/kvm/e500.c
+++ b/arch/powerpc/kvm/e500.c
@@ -21,6 +21,7 @@
 #include <asm/kvm_e500.h>
 #include <asm/kvm_ppc.h>
 
+#include "booke.h"
 #include "e500_tlb.h"
 
 void kvmppc_core_load_host_debugstate(struct kvm_vcpu *vcpu)
@@ -133,12 +134,29 @@ void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
 
 static int kvmppc_e500_init(void)
 {
-	int r;
+	int r, i;
+	unsigned long ivor[3];
+	unsigned long max_ivor = 0;
 
 	r = kvmppc_booke_init();
 	if (r)
 		return r;
 
+	/* copy extra E500 exception handlers */
+	ivor[0] = mfspr(SPRN_IVOR32);
+	ivor[1] = mfspr(SPRN_IVOR33);
+	ivor[2] = mfspr(SPRN_IVOR34);
+	for (i = 0; i < 3; i++) {
+		if (ivor[i] > max_ivor)
+			max_ivor = ivor[i];
+
+		memcpy((void *)kvmppc_booke_handlers + ivor[i],
+		       kvmppc_handlers_start + (i + 16) * kvmppc_handler_len,
+		       kvmppc_handler_len);
+	}
+	flush_icache_range(kvmppc_booke_handlers,
+			kvmppc_booke_handlers + max_ivor + kvmppc_handler_len);
+
 	return kvm_init(NULL, sizeof(struct kvmppc_vcpu_e500), THIS_MODULE);
 }
 
diff --git a/arch/powerpc/kvm/e500_emulate.c b/arch/powerpc/kvm/e500_emulate.c
index a47f44cd2cfd..d3c0c7c7f209 100644
--- a/arch/powerpc/kvm/e500_emulate.c
+++ b/arch/powerpc/kvm/e500_emulate.c
@@ -107,6 +107,20 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
 	case SPRN_HID1:
 		vcpu_e500->hid1 = vcpu->arch.gpr[rs]; break;
 
+	/* extra exceptions */
+	case SPRN_IVOR32:
+		vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_UNAVAIL] = vcpu->arch.gpr[rs];
+		break;
+	case SPRN_IVOR33:
+		vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_DATA] = vcpu->arch.gpr[rs];
+		break;
+	case SPRN_IVOR34:
+		vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_ROUND] = vcpu->arch.gpr[rs];
+		break;
+	case SPRN_IVOR35:
+		vcpu->arch.ivor[BOOKE_IRQPRIO_PERFORMANCE_MONITOR] = vcpu->arch.gpr[rs];
+		break;
+
 	default:
 		emulated = kvmppc_booke_emulate_mtspr(vcpu, sprn, rs);
 	}
@@ -160,6 +174,19 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
 	case SPRN_HID1:
 		vcpu->arch.gpr[rt] = vcpu_e500->hid1; break;
 
+	/* extra exceptions */
+	case SPRN_IVOR32:
+		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_UNAVAIL];
+		break;
+	case SPRN_IVOR33:
+		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_DATA];
+		break;
+	case SPRN_IVOR34:
+		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_ROUND];
+		break;
+	case SPRN_IVOR35:
+		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_PERFORMANCE_MONITOR];
+		break;
 	default:
 		emulated = kvmppc_booke_emulate_mfspr(vcpu, sprn, rt);
 	}
-- 
cgit v1.2.3


From f5d0906b5bafd7faea553ed1cc92bd06755b66b9 Mon Sep 17 00:00:00 2001
From: Hollis Blanchard
Date: Sun, 4 Jan 2009 13:51:09 -0600
Subject: KVM: ppc: remove debug support broken by KVM debug rewrite

After the rewrite of KVM's debug support, this code doesn't even build any
more.

Signed-off-by: Hollis Blanchard <hollisb@us.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/include/asm/kvm_host.h |  5 ---
 arch/powerpc/include/asm/kvm_ppc.h  |  3 --
 arch/powerpc/kvm/44x.c              | 66 -------------------------------------
 arch/powerpc/kvm/powerpc.c          | 27 ++-------------
 4 files changed, 2 insertions(+), 99 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 1c6187697520..dfdf13c9fefd 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -111,11 +111,6 @@ struct kvm_arch {
 struct kvm_vcpu_arch {
 	u32 host_stack;
 	u32 host_pid;
-	u32 host_dbcr0;
-	u32 host_dbcr1;
-	u32 host_dbcr2;
-	u32 host_iac[4];
-	u32 host_msr;
 
 	u64 fpr[32];
 	ulong gpr[32];
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 6052779dbb56..2c6ee349df5e 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -77,9 +77,6 @@ extern int kvmppc_core_vcpu_translate(struct kvm_vcpu *vcpu,
 extern void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
 extern void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu);
 
-extern void kvmppc_core_load_guest_debugstate(struct kvm_vcpu *vcpu);
-extern void kvmppc_core_load_host_debugstate(struct kvm_vcpu *vcpu);
-
 extern void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu);
 extern int kvmppc_core_pending_dec(struct kvm_vcpu *vcpu);
 extern void kvmppc_core_queue_program(struct kvm_vcpu *vcpu);
diff --git a/arch/powerpc/kvm/44x.c b/arch/powerpc/kvm/44x.c
index 8383603dd8a4..0cef809cec21 100644
--- a/arch/powerpc/kvm/44x.c
+++ b/arch/powerpc/kvm/44x.c
@@ -28,72 +28,6 @@
 
 #include "44x_tlb.h"
 
-/* Note: clearing MSR[DE] just means that the debug interrupt will not be
- * delivered *immediately*. Instead, it simply sets the appropriate DBSR bits.
- * If those DBSR bits are still set when MSR[DE] is re-enabled, the interrupt
- * will be delivered as an "imprecise debug event" (which is indicated by
- * DBSR[IDE].
- */
-static void kvm44x_disable_debug_interrupts(void)
-{
-	mtmsr(mfmsr() & ~MSR_DE);
-}
-
-void kvmppc_core_load_host_debugstate(struct kvm_vcpu *vcpu)
-{
-	kvm44x_disable_debug_interrupts();
-
-	mtspr(SPRN_IAC1, vcpu->arch.host_iac[0]);
-	mtspr(SPRN_IAC2, vcpu->arch.host_iac[1]);
-	mtspr(SPRN_IAC3, vcpu->arch.host_iac[2]);
-	mtspr(SPRN_IAC4, vcpu->arch.host_iac[3]);
-	mtspr(SPRN_DBCR1, vcpu->arch.host_dbcr1);
-	mtspr(SPRN_DBCR2, vcpu->arch.host_dbcr2);
-	mtspr(SPRN_DBCR0, vcpu->arch.host_dbcr0);
-	mtmsr(vcpu->arch.host_msr);
-}
-
-void kvmppc_core_load_guest_debugstate(struct kvm_vcpu *vcpu)
-{
-	struct kvm_guest_debug *dbg = &vcpu->guest_debug;
-	u32 dbcr0 = 0;
-
-	vcpu->arch.host_msr = mfmsr();
-	kvm44x_disable_debug_interrupts();
-
-	/* Save host debug register state. */
-	vcpu->arch.host_iac[0] = mfspr(SPRN_IAC1);
-	vcpu->arch.host_iac[1] = mfspr(SPRN_IAC2);
-	vcpu->arch.host_iac[2] = mfspr(SPRN_IAC3);
-	vcpu->arch.host_iac[3] = mfspr(SPRN_IAC4);
-	vcpu->arch.host_dbcr0 = mfspr(SPRN_DBCR0);
-	vcpu->arch.host_dbcr1 = mfspr(SPRN_DBCR1);
-	vcpu->arch.host_dbcr2 = mfspr(SPRN_DBCR2);
-
-	/* set registers up for guest */
-
-	if (dbg->bp[0]) {
-		mtspr(SPRN_IAC1, dbg->bp[0]);
-		dbcr0 |= DBCR0_IAC1 | DBCR0_IDM;
-	}
-	if (dbg->bp[1]) {
-		mtspr(SPRN_IAC2, dbg->bp[1]);
-		dbcr0 |= DBCR0_IAC2 | DBCR0_IDM;
-	}
-	if (dbg->bp[2]) {
-		mtspr(SPRN_IAC3, dbg->bp[2]);
-		dbcr0 |= DBCR0_IAC3 | DBCR0_IDM;
-	}
-	if (dbg->bp[3]) {
-		mtspr(SPRN_IAC4, dbg->bp[3]);
-		dbcr0 |= DBCR0_IAC4 | DBCR0_IDM;
-	}
-
-	mtspr(SPRN_DBCR0, dbcr0);
-	mtspr(SPRN_DBCR1, 0);
-	mtspr(SPRN_DBCR2, 0);
-}
-
 void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	kvmppc_44x_tlb_load(vcpu);
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index f30be9ef2314..9057335fdc61 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -221,41 +221,18 @@ void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
 
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
-	if (vcpu->guest_debug.enabled)
-		kvmppc_core_load_guest_debugstate(vcpu);
-
 	kvmppc_core_vcpu_load(vcpu, cpu);
 }
 
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 {
-	if (vcpu->guest_debug.enabled)
-		kvmppc_core_load_host_debugstate(vcpu);
-
-	/* Don't leave guest TLB entries resident when being de-scheduled. */
-	/* XXX It would be nice to differentiate between heavyweight exit and
-	 * sched_out here, since we could avoid the TLB flush for heavyweight
-	 * exits. */
-	_tlbil_all();
 	kvmppc_core_vcpu_put(vcpu);
 }
 
 int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
-					struct kvm_guest_debug *dbg)
+                                        struct kvm_guest_debug *dbg)
 {
-	int i;
-
-	vcpu->guest_debug.enabled = dbg->enabled;
-	if (vcpu->guest_debug.enabled) {
-		for (i=0; i < ARRAY_SIZE(vcpu->guest_debug.bp); i++) {
-			if (dbg->breakpoints[i].enabled)
-				vcpu->guest_debug.bp[i] = dbg->breakpoints[i].address;
-			else
-				vcpu->guest_debug.bp[i] = 0;
-		}
-	}
-
-	return 0;
+	return -EINVAL;
 }
 
 static void kvmppc_complete_dcr_load(struct kvm_vcpu *vcpu,
-- 
cgit v1.2.3


From 87c656b4147cd08c6efba95d8d70c12cba181255 Mon Sep 17 00:00:00 2001
From: Liu Yu
Date: Wed, 14 Jan 2009 10:47:36 -0600
Subject: powerpc/fsl-booke: declare tlbcam_index for use in c

So, KVM needs to read tlbcam_index to know exactly
which TLB1 entry is unused by host.

Signed-off-by: Liu Yu <yu.liu@freescale.com>
Acked-by: Kumar Gala <galak@kernel.crashing.org>
Signed-off-by: Hollis Blanchard <hollisb@us.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/include/asm/mmu-fsl-booke.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/mmu-fsl-booke.h b/arch/powerpc/include/asm/mmu-fsl-booke.h
index 3f941c0f7e8e..4285b64a65e0 100644
--- a/arch/powerpc/include/asm/mmu-fsl-booke.h
+++ b/arch/powerpc/include/asm/mmu-fsl-booke.h
@@ -75,6 +75,8 @@
 
 #ifndef __ASSEMBLY__
 
+extern unsigned int tlbcam_index;
+
 typedef struct {
 	unsigned int	id;
 	unsigned int	active;
-- 
cgit v1.2.3


From 2b1c6bd77d4e6a727ffac8630cd154b2144b751a Mon Sep 17 00:00:00 2001
From: Christoph Hellwig
Date: Fri, 28 Nov 2008 10:09:09 +0100
Subject: generic compat_sys_ustat

Due to a different size of ino_t ustat needs a compat handler, but
currently only x86 and mips provide one.  Add a generic compat_sys_ustat
and switch all architectures over to it.  Instead of doing various
user copy hacks compat_sys_ustat just reimplements sys_ustat as
it's trivial.  This was suggested by Arnd Bergmann.

Found by Eric Sandeen when running xfstests/017 on ppc64, which causes
stack smashing warnings on RHEL/Fedora due to the too large amount of
data writen by the syscall.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/ia64/ia32/ia32_entry.S        |  2 +-
 arch/mips/kernel/linux32.c         | 34 ----------------------------------
 arch/mips/kernel/scall64-n32.S     |  2 +-
 arch/mips/kernel/scall64-o32.S     |  2 +-
 arch/parisc/kernel/syscall_table.S |  2 +-
 arch/powerpc/include/asm/systbl.h  |  2 +-
 arch/s390/kernel/compat_wrapper.S  |  2 +-
 arch/x86/ia32/ia32entry.S          |  2 +-
 arch/x86/ia32/sys_ia32.c           | 22 ----------------------
 arch/x86/include/asm/ia32.h        |  7 -------
 arch/x86/include/asm/sys_ia32.h    |  2 --
 fs/compat.c                        | 28 ++++++++++++++++++++++++++++
 include/linux/compat.h             |  8 ++++++++
 13 files changed, 43 insertions(+), 72 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/ia64/ia32/ia32_entry.S b/arch/ia64/ia32/ia32_entry.S
index a46f8395e9a5..af9405cd70e5 100644
--- a/arch/ia64/ia32/ia32_entry.S
+++ b/arch/ia64/ia32/ia32_entry.S
@@ -240,7 +240,7 @@ ia32_syscall_table:
 	data8 sys_ni_syscall
 	data8 sys_umask		  /* 60 */
 	data8 sys_chroot
-	data8 sys_ustat
+	data8 compat_sys_ustat
 	data8 sys_dup2
 	data8 sys_getppid
 	data8 sys_getpgrp	  /* 65 */
diff --git a/arch/mips/kernel/linux32.c b/arch/mips/kernel/linux32.c
index 1a86f84fa947..784859cedef7 100644
--- a/arch/mips/kernel/linux32.c
+++ b/arch/mips/kernel/linux32.c
@@ -356,40 +356,6 @@ SYSCALL_DEFINE1(32_personality, unsigned long, personality)
 	return ret;
 }
 
-/* ustat compatibility */
-struct ustat32 {
-	compat_daddr_t	f_tfree;
-	compat_ino_t	f_tinode;
-	char		f_fname[6];
-	char		f_fpack[6];
-};
-
-extern asmlinkage long sys_ustat(dev_t dev, struct ustat __user * ubuf);
-
-SYSCALL_DEFINE2(32_ustat, dev_t, dev, struct ustat32 __user *, ubuf32)
-{
-	int err;
-	struct ustat tmp;
-	struct ustat32 tmp32;
-	mm_segment_t old_fs = get_fs();
-
-	set_fs(KERNEL_DS);
-	err = sys_ustat(dev, (struct ustat __user *)&tmp);
-	set_fs(old_fs);
-
-	if (err)
-		goto out;
-
-	memset(&tmp32, 0, sizeof(struct ustat32));
-	tmp32.f_tfree = tmp.f_tfree;
-	tmp32.f_tinode = tmp.f_tinode;
-
-	err = copy_to_user(ubuf32, &tmp32, sizeof(struct ustat32)) ? -EFAULT : 0;
-
-out:
-	return err;
-}
-
 SYSCALL_DEFINE4(32_sendfile, long, out_fd, long, in_fd,
 	compat_off_t __user *, offset, s32, count)
 {
diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S
index 7438e92f8a01..f61d6b0e5731 100644
--- a/arch/mips/kernel/scall64-n32.S
+++ b/arch/mips/kernel/scall64-n32.S
@@ -253,7 +253,7 @@ EXPORT(sysn32_call_table)
 	PTR	compat_sys_utime		/* 6130 */
 	PTR	sys_mknod
 	PTR	sys_32_personality
-	PTR	sys_32_ustat
+	PTR	compat_sys_ustat
 	PTR	compat_sys_statfs
 	PTR	compat_sys_fstatfs		/* 6135 */
 	PTR	sys_sysfs
diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
index b0fef4ff9827..60997f1f69d4 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -265,7 +265,7 @@ sys_call_table:
 	PTR	sys_olduname
 	PTR	sys_umask			/* 4060 */
 	PTR	sys_chroot
-	PTR	sys_32_ustat
+	PTR	compat_sys_ustat
 	PTR	sys_dup2
 	PTR	sys_getppid
 	PTR	sys_getpgrp			/* 4065 */
diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S
index 303d2b647e41..03b9a01bc16c 100644
--- a/arch/parisc/kernel/syscall_table.S
+++ b/arch/parisc/kernel/syscall_table.S
@@ -130,7 +130,7 @@
 	ENTRY_OURS(newuname)
 	ENTRY_SAME(umask)		/* 60 */
 	ENTRY_SAME(chroot)
-	ENTRY_SAME(ustat)
+	ENTRY_COMP(ustat)
 	ENTRY_SAME(dup2)
 	ENTRY_SAME(getppid)
 	ENTRY_SAME(getpgrp)		/* 65 */
diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h
index 72353f6070a4..fe166491e9dc 100644
--- a/arch/powerpc/include/asm/systbl.h
+++ b/arch/powerpc/include/asm/systbl.h
@@ -65,7 +65,7 @@ SYSCALL(ni_syscall)
 SYSX(sys_ni_syscall,sys_olduname, sys_olduname)
 COMPAT_SYS_SPU(umask)
 SYSCALL_SPU(chroot)
-SYSCALL(ustat)
+COMPAT_SYS(ustat)
 SYSCALL_SPU(dup2)
 SYSCALL_SPU(getppid)
 SYSCALL_SPU(getpgrp)
diff --git a/arch/s390/kernel/compat_wrapper.S b/arch/s390/kernel/compat_wrapper.S
index 62c706eb0de6..87cf5a79a351 100644
--- a/arch/s390/kernel/compat_wrapper.S
+++ b/arch/s390/kernel/compat_wrapper.S
@@ -252,7 +252,7 @@ sys32_chroot_wrapper:
 sys32_ustat_wrapper:
 	llgfr	%r2,%r2			# dev_t
 	llgtr	%r3,%r3			# struct ustat *
-	jg	sys_ustat
+	jg	compat_sys_ustat
 
 	.globl	sys32_dup2_wrapper
 sys32_dup2_wrapper:
diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 5a0d76dc56a4..8ef8876666b2 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -557,7 +557,7 @@ ia32_sys_call_table:
 	.quad sys32_olduname
 	.quad sys_umask		/* 60 */
 	.quad sys_chroot
-	.quad sys32_ustat
+	.quad compat_sys_ustat
 	.quad sys_dup2
 	.quad sys_getppid
 	.quad sys_getpgrp		/* 65 */
diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c
index 6c0d7f6231af..efac92fd1efb 100644
--- a/arch/x86/ia32/sys_ia32.c
+++ b/arch/x86/ia32/sys_ia32.c
@@ -638,28 +638,6 @@ long sys32_uname(struct old_utsname __user *name)
 	return err ? -EFAULT : 0;
 }
 
-long sys32_ustat(unsigned dev, struct ustat32 __user *u32p)
-{
-	struct ustat u;
-	mm_segment_t seg;
-	int ret;
-
-	seg = get_fs();
-	set_fs(KERNEL_DS);
-	ret = sys_ustat(dev, (struct ustat __user *)&u);
-	set_fs(seg);
-	if (ret < 0)
-		return ret;
-
-	if (!access_ok(VERIFY_WRITE, u32p, sizeof(struct ustat32)) ||
-	    __put_user((__u32) u.f_tfree, &u32p->f_tfree) ||
-	    __put_user((__u32) u.f_tinode, &u32p->f_tfree) ||
-	    __copy_to_user(&u32p->f_fname, u.f_fname, sizeof(u.f_fname)) ||
-	    __copy_to_user(&u32p->f_fpack, u.f_fpack, sizeof(u.f_fpack)))
-		ret = -EFAULT;
-	return ret;
-}
-
 asmlinkage long sys32_execve(char __user *name, compat_uptr_t __user *argv,
 			     compat_uptr_t __user *envp, struct pt_regs *regs)
 {
diff --git a/arch/x86/include/asm/ia32.h b/arch/x86/include/asm/ia32.h
index 50ca486fd88c..1f7e62517284 100644
--- a/arch/x86/include/asm/ia32.h
+++ b/arch/x86/include/asm/ia32.h
@@ -129,13 +129,6 @@ typedef struct compat_siginfo {
 	} _sifields;
 } compat_siginfo_t;
 
-struct ustat32 {
-	__u32			f_tfree;
-	compat_ino_t		f_tinode;
-	char			f_fname[6];
-	char			f_fpack[6];
-};
-
 #define IA32_STACK_TOP IA32_PAGE_OFFSET
 
 #ifdef __KERNEL__
diff --git a/arch/x86/include/asm/sys_ia32.h b/arch/x86/include/asm/sys_ia32.h
index ffb08be2a530..72a6dcd1299b 100644
--- a/arch/x86/include/asm/sys_ia32.h
+++ b/arch/x86/include/asm/sys_ia32.h
@@ -70,8 +70,6 @@ struct old_utsname;
 asmlinkage long sys32_olduname(struct oldold_utsname __user *);
 long sys32_uname(struct old_utsname __user *);
 
-long sys32_ustat(unsigned, struct ustat32 __user *);
-
 asmlinkage long sys32_execve(char __user *, compat_uptr_t __user *,
 			     compat_uptr_t __user *, struct pt_regs *);
 asmlinkage long sys32_clone(unsigned int, unsigned int, struct pt_regs *);
diff --git a/fs/compat.c b/fs/compat.c
index d0145ca27572..4e0db94b5353 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -378,6 +378,34 @@ out:
 	return error;
 }
 
+/*
+ * This is a copy of sys_ustat, just dealing with a structure layout.
+ * Given how simple this syscall is that apporach is more maintainable
+ * than the various conversion hacks.
+ */
+asmlinkage long compat_sys_ustat(unsigned dev, struct compat_ustat __user *u)
+{
+	struct super_block *sb;
+	struct compat_ustat tmp;
+	struct kstatfs sbuf;
+	int err;
+
+	sb = user_get_super(new_decode_dev(dev));
+	if (!sb)
+		return -EINVAL;
+	err = vfs_statfs(sb->s_root, &sbuf);
+	drop_super(sb);
+	if (err)
+		return err;
+
+	memset(&tmp, 0, sizeof(struct compat_ustat));
+	tmp.f_tfree = sbuf.f_bfree;
+	tmp.f_tinode = sbuf.f_ffree;
+	if (copy_to_user(u, &tmp, sizeof(struct compat_ustat)))
+		return -EFAULT;
+	return 0;
+}
+
 static int get_compat_flock(struct flock *kfl, struct compat_flock __user *ufl)
 {
 	if (!access_ok(VERIFY_READ, ufl, sizeof(*ufl)) ||
diff --git a/include/linux/compat.h b/include/linux/compat.h
index 3fd2194ff573..b880864672de 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -125,6 +125,13 @@ struct compat_dirent {
 	char		d_name[256];
 };
 
+struct compat_ustat {
+	compat_daddr_t		f_tfree;
+	compat_ino_t		f_tinode;
+	char			f_fname[6];
+	char			f_fpack[6];
+};
+
 typedef union compat_sigval {
 	compat_int_t	sival_int;
 	compat_uptr_t	sival_ptr;
@@ -178,6 +185,7 @@ long compat_sys_semtimedop(int semid, struct sembuf __user *tsems,
 		unsigned nsems, const struct compat_timespec __user *timeout);
 asmlinkage long compat_sys_keyctl(u32 option,
 			      u32 arg2, u32 arg3, u32 arg4, u32 arg5);
+asmlinkage long compat_sys_ustat(unsigned dev, struct compat_ustat __user *u32);
 
 asmlinkage ssize_t compat_sys_readv(unsigned long fd,
 		const struct compat_iovec __user *vec, unsigned long vlen);
-- 
cgit v1.2.3