Merge tag 'please-pull-mce-bitmap-comment' of git://git.kernel.org/pub/scm/linux/kernel/git/ras/ras into x86/ras

Pull MCE updates from Tony Luck:

 "Better comments so we understand our existing machine check
  bank bitmaps - prelude to adding another bitmap soon."

Signed-off-by: Ingo Molnar <mingo@kernel.org>

16 files changed, 77 insertions, 48 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 685692c94f05..fe120da25625 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2265,6 +2265,7 @@ source "fs/Kconfig.binfmt"
 config IA32_EMULATION
 	bool "IA32 Emulation"
 	depends on X86_64
+	select BINFMT_ELF
 	select COMPAT_BINFMT_ELF
 	select HAVE_UID16
 	---help---
diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S
index 62fe22cd4cba..477e9d75149b 100644
--- a/arch/x86/crypto/aesni-intel_asm.S
+++ b/arch/x86/crypto/aesni-intel_asm.S
@@ -2681,56 +2681,68 @@ ENTRY(aesni_xts_crypt8)
 	addq %rcx, KEYP
 
 	movdqa IV, STATE1
-	pxor 0x00(INP), STATE1
+	movdqu 0x00(INP), INC
+	pxor INC, STATE1
 	movdqu IV, 0x00(OUTP)
 
 	_aesni_gf128mul_x_ble()
 	movdqa IV, STATE2
-	pxor 0x10(INP), STATE2
+	movdqu 0x10(INP), INC
+	pxor INC, STATE2
 	movdqu IV, 0x10(OUTP)
 
 	_aesni_gf128mul_x_ble()
 	movdqa IV, STATE3
-	pxor 0x20(INP), STATE3
+	movdqu 0x20(INP), INC
+	pxor INC, STATE3
 	movdqu IV, 0x20(OUTP)
 
 	_aesni_gf128mul_x_ble()
 	movdqa IV, STATE4
-	pxor 0x30(INP), STATE4
+	movdqu 0x30(INP), INC
+	pxor INC, STATE4
 	movdqu IV, 0x30(OUTP)
 
 	call *%r11
 
-	pxor 0x00(OUTP), STATE1
+	movdqu 0x00(OUTP), INC
+	pxor INC, STATE1
 	movdqu STATE1, 0x00(OUTP)
 
 	_aesni_gf128mul_x_ble()
 	movdqa IV, STATE1
-	pxor 0x40(INP), STATE1
+	movdqu 0x40(INP), INC
+	pxor INC, STATE1
 	movdqu IV, 0x40(OUTP)
 
-	pxor 0x10(OUTP), STATE2
+	movdqu 0x10(OUTP), INC
+	pxor INC, STATE2
 	movdqu STATE2, 0x10(OUTP)
 
 	_aesni_gf128mul_x_ble()
 	movdqa IV, STATE2
-	pxor 0x50(INP), STATE2
+	movdqu 0x50(INP), INC
+	pxor INC, STATE2
 	movdqu IV, 0x50(OUTP)
 
-	pxor 0x20(OUTP), STATE3
+	movdqu 0x20(OUTP), INC
+	pxor INC, STATE3
 	movdqu STATE3, 0x20(OUTP)
 
 	_aesni_gf128mul_x_ble()
 	movdqa IV, STATE3
-	pxor 0x60(INP), STATE3
+	movdqu 0x60(INP), INC
+	pxor INC, STATE3
 	movdqu IV, 0x60(OUTP)
 
-	pxor 0x30(OUTP), STATE4
+	movdqu 0x30(OUTP), INC
+	pxor INC, STATE4
 	movdqu STATE4, 0x30(OUTP)
 
 	_aesni_gf128mul_x_ble()
 	movdqa IV, STATE4
-	pxor 0x70(INP), STATE4
+	movdqu 0x70(INP), INC
+	pxor INC, STATE4
 	movdqu IV, 0x70(OUTP)
 
 	_aesni_gf128mul_x_ble()
@@ -2738,16 +2750,20 @@ ENTRY(aesni_xts_crypt8)
 
 	call *%r11
 
-	pxor 0x40(OUTP), STATE1
+	movdqu 0x40(OUTP), INC
+	pxor INC, STATE1
 	movdqu STATE1, 0x40(OUTP)
 
-	pxor 0x50(OUTP), STATE2
+	movdqu 0x50(OUTP), INC
+	pxor INC, STATE2
 	movdqu STATE2, 0x50(OUTP)
 
-	pxor 0x60(OUTP), STATE3
+	movdqu 0x60(OUTP), INC
+	pxor INC, STATE3
 	movdqu STATE3, 0x60(OUTP)
 
-	pxor 0x70(OUTP), STATE4
+	movdqu 0x70(OUTP), INC
+	pxor INC, STATE4
 	movdqu STATE4, 0x70(OUTP)
 
 	ret
diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c
index 805078e08013..52ff81cce008 100644
--- a/arch/x86/ia32/ia32_aout.c
+++ b/arch/x86/ia32/ia32_aout.c
@@ -192,7 +192,7 @@ static int aout_core_dump(long signr, struct pt_regs *regs, struct file *file,
 	/* struct user */
 	DUMP_WRITE(&dump, sizeof(dump));
 	/* Now dump all of the user data.  Include malloced stuff as well */
-	DUMP_SEEK(PAGE_SIZE);
+	DUMP_SEEK(PAGE_SIZE - sizeof(dump));
 	/* now we start writing out the user space info */
 	set_fs(USER_DS);
 	/* Dump the data area */
diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h
index ba870bb6dd8e..57873beb3292 100644
--- a/arch/x86/include/asm/irq.h
+++ b/arch/x86/include/asm/irq.h
@@ -41,4 +41,9 @@ extern int vector_used_by_percpu_irq(unsigned int vector);
 
 extern void init_ISA_irqs(void);
 
+#ifdef CONFIG_X86_LOCAL_APIC
+void arch_trigger_all_cpu_backtrace(void);
+#define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace
+#endif
+
 #endif /* _ASM_X86_IRQ_H */
diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h
index 6825e2efd1b4..6bc3985ee473 100644
--- a/arch/x86/include/asm/microcode.h
+++ b/arch/x86/include/asm/microcode.h
@@ -60,11 +60,11 @@ static inline void __exit exit_amd_microcode(void) {}
 #ifdef CONFIG_MICROCODE_EARLY
 #define MAX_UCODE_COUNT 128
 extern void __init load_ucode_bsp(void);
-extern __init void load_ucode_ap(void);
+extern void __cpuinit load_ucode_ap(void);
 extern int __init save_microcode_in_initrd(void);
 #else
 static inline void __init load_ucode_bsp(void) {}
-static inline __init void load_ucode_ap(void) {}
+static inline void __cpuinit load_ucode_ap(void) {}
 static inline int __init save_microcode_in_initrd(void)
 {
 	return 0;
diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h
index c0fa356e90de..86f9301903c8 100644
--- a/arch/x86/include/asm/nmi.h
+++ b/arch/x86/include/asm/nmi.h
@@ -18,9 +18,7 @@ extern int proc_nmi_enabled(struct ctl_table *, int ,
 			void __user *, size_t *, loff_t *);
 extern int unknown_nmi_panic;
 
-void arch_trigger_all_cpu_backtrace(void);
-#define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace
-#endif
+#endif /* CONFIG_X86_LOCAL_APIC */
 
 #define NMI_FLAG_FIRST	1
 
diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c
index 31cb9ae992b7..a698d7165c96 100644
--- a/arch/x86/kernel/apic/hw_nmi.c
+++ b/arch/x86/kernel/apic/hw_nmi.c
@@ -9,6 +9,7 @@
  *
  */
 #include <asm/apic.h>
+#include <asm/nmi.h>
 
 #include <linux/cpumask.h>
 #include <linux/kdebug.h>
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 9239504b41cb..bf49cdbb010f 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -89,7 +89,10 @@ static DECLARE_WAIT_QUEUE_HEAD(mce_chrdev_wait);
 static DEFINE_PER_CPU(struct mce, mces_seen);
 static int			cpu_missing;
 
-/* MCA banks polled by the period polling timer for corrected events */
+/*
+ * MCA banks polled by the period polling timer for corrected events.
+ * With Intel CMCI, this only has MCA banks which do not support CMCI (if any).
+ */
 DEFINE_PER_CPU(mce_banks_t, mce_poll_banks) = {
 	[0 ... BITS_TO_LONGS(MAX_NR_BANKS)-1] = ~0UL
 };
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index ae1697c2afe3..d56405309dc1 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -24,6 +24,18 @@
  * Also supports reliable discovery of shared banks.
  */
 
+/*
+ * CMCI can be delivered to multiple cpus that share a machine check bank
+ * so we need to designate a single cpu to process errors logged in each bank
+ * in the interrupt handler (otherwise we would have many races and potential
+ * double reporting of the same error).
+ * Note that this can change when a cpu is offlined or brought online since
+ * some MCA banks are shared across cpus. When a cpu is offlined, cmci_clear()
+ * disables CMCI on all banks owned by the cpu and clears this bitfield. At
+ * this point, cmci_rediscover() kicks in and a different cpu may end up
+ * taking ownership of some of the shared MCA banks that were previously
+ * owned by the offlined cpu.
+ */
 static DEFINE_PER_CPU(mce_banks_t, mce_banks_owned);
 
 /*
diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c
index 35ffda5d0727..5f90b85ff22e 100644
--- a/arch/x86/kernel/cpu/mtrr/cleanup.c
+++ b/arch/x86/kernel/cpu/mtrr/cleanup.c
@@ -714,15 +714,15 @@ int __init mtrr_cleanup(unsigned address_bits)
 	if (mtrr_tom2)
 		x_remove_size = (mtrr_tom2 >> PAGE_SHIFT) - x_remove_base;
 
-	nr_range = x86_get_mtrr_mem_range(range, 0, x_remove_base, x_remove_size);
 	/*
 	 * [0, 1M) should always be covered by var mtrr with WB
 	 * and fixed mtrrs should take effect before var mtrr for it:
 	 */
-	nr_range = add_range_with_merge(range, RANGE_NUM, nr_range, 0,
+	nr_range = add_range_with_merge(range, RANGE_NUM, 0, 0,
 					1ULL<<(20 - PAGE_SHIFT));
-	/* Sort the ranges: */
-	sort_range(range, nr_range);
+	/* add from var mtrr at last */
+	nr_range = x86_get_mtrr_mem_range(range, nr_range,
+					  x_remove_base, x_remove_size);
 
 	range_sums = sum_ranges(range, nr_range);
 	printk(KERN_INFO "total RAM covered: %ldM\n",
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index f60d41ff9a97..a9e22073bd56 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -165,13 +165,13 @@ static struct extra_reg intel_snb_extra_regs[] __read_mostly = {
 	INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3f807f8fffull, RSP_0),
 	INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3f807f8fffull, RSP_1),
 	INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
-	INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
 	EVENT_EXTRA_END
 };
 
 static struct extra_reg intel_snbep_extra_regs[] __read_mostly = {
 	INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3fffff8fffull, RSP_0),
 	INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3fffff8fffull, RSP_1),
+	INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
 	EVENT_EXTRA_END
 };
 
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index d2c381280e3c..3dd37ebd591b 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -242,6 +242,7 @@ void __init kvmclock_init(void)
 	if (!mem)
 		return;
 	hv_clock = __va(mem);
+	memset(hv_clock, 0, size);
 
 	if (kvm_register_clock("boot clock")) {
 		hv_clock = NULL;
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 4e7a37ff03ab..81a5f5e8f142 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -277,18 +277,6 @@ void exit_idle(void)
 }
 #endif
 
-void arch_cpu_idle_prepare(void)
-{
-	/*
-	 * If we're the non-boot CPU, nothing set the stack canary up
-	 * for us.  CPU0 already has it initialized but no harm in
-	 * doing it again.  This is a good place for updating it, as
-	 * we wont ever return from this function (so the invalid
-	 * canaries already on the stack wont ever trigger).
-	 */
-	boot_init_stack_canary();
-}
-
 void arch_cpu_idle_enter(void)
 {
 	local_touch_nmi();
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 9c73b51817e4..bfd348e99369 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -372,15 +372,15 @@ static bool __cpuinit match_mc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 
 void __cpuinit set_cpu_sibling_map(int cpu)
 {
-	bool has_mc = boot_cpu_data.x86_max_cores > 1;
 	bool has_smt = smp_num_siblings > 1;
+	bool has_mp = has_smt || boot_cpu_data.x86_max_cores > 1;
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 	struct cpuinfo_x86 *o;
 	int i;
 
 	cpumask_set_cpu(cpu, cpu_sibling_setup_mask);
 
-	if (!has_smt && !has_mc) {
+	if (!has_mp) {
 		cpumask_set_cpu(cpu, cpu_sibling_mask(cpu));
 		cpumask_set_cpu(cpu, cpu_llc_shared_mask(cpu));
 		cpumask_set_cpu(cpu, cpu_core_mask(cpu));
@@ -394,7 +394,7 @@ void __cpuinit set_cpu_sibling_map(int cpu)
 		if ((i == cpu) || (has_smt && match_smt(c, o)))
 			link_mask(sibling, cpu, i);
 
-		if ((i == cpu) || (has_mc && match_llc(c, o)))
+		if ((i == cpu) || (has_mp && match_llc(c, o)))
 			link_mask(llc_shared, cpu, i);
 
 	}
@@ -406,7 +406,7 @@ void __cpuinit set_cpu_sibling_map(int cpu)
 	for_each_cpu(i, cpu_sibling_setup_mask) {
 		o = &cpu_data(i);
 
-		if ((i == cpu) || (has_mc && match_mc(c, o))) {
+		if ((i == cpu) || (has_mp && match_mc(c, o))) {
 			link_mask(core, cpu, i);
 
 			/*
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 094b5d96ab14..e8ba99c34180 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -582,8 +582,6 @@ int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
 	if (index != XCR_XFEATURE_ENABLED_MASK)
 		return 1;
 	xcr0 = xcr;
-	if (kvm_x86_ops->get_cpl(vcpu) != 0)
-		return 1;
 	if (!(xcr0 & XSTATE_FP))
 		return 1;
 	if ((xcr0 & XSTATE_YMM) && !(xcr0 & XSTATE_SSE))
@@ -597,7 +595,8 @@ int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
 
 int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
 {
-	if (__kvm_set_xcr(vcpu, index, xcr)) {
+	if (kvm_x86_ops->get_cpl(vcpu) != 0 ||
+	    __kvm_set_xcr(vcpu, index, xcr)) {
 		kvm_inject_gp(vcpu, 0);
 		return 1;
 	}
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 5ae2eb09419e..d2fbcedcf6ea 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -1069,7 +1069,10 @@ efi_status_t efi_query_variable_store(u32 attributes, unsigned long size)
 		 * that by attempting to use more space than is available.
 		 */
 		unsigned long dummy_size = remaining_size + 1024;
-		void *dummy = kmalloc(dummy_size, GFP_ATOMIC);
+		void *dummy = kzalloc(dummy_size, GFP_ATOMIC);
+
+		if (!dummy)
+			return EFI_OUT_OF_RESOURCES;
 
 		status = efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID,
 					  EFI_VARIABLE_NON_VOLATILE |
@@ -1089,6 +1092,8 @@ efi_status_t efi_query_variable_store(u32 attributes, unsigned long size)
 					 0, dummy);
 		}
 
+		kfree(dummy);
+
 		/*
 		 * The runtime code may now have triggered a garbage collection
 		 * run, so check the variable info again