Merge branch 'perf/urgent' into perf/core

Pick up the latest fixes, refresh the development tree.

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

14 files changed, 130 insertions, 33 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index e903c71f7e69..0952ecd60eca 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -26,6 +26,7 @@ config X86
 	select HAVE_AOUT if X86_32
 	select HAVE_UNSTABLE_SCHED_CLOCK
 	select ARCH_SUPPORTS_NUMA_BALANCING
+	select ARCH_SUPPORTS_INT128 if X86_64
 	select ARCH_WANTS_PROT_NUMA_PROT_NONE
 	select HAVE_IDE
 	select HAVE_OPROFILE
diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h
index c49a613c6452..cea1c76d49bf 100644
--- a/arch/x86/include/asm/fpu-internal.h
+++ b/arch/x86/include/asm/fpu-internal.h
@@ -293,12 +293,13 @@ static inline int restore_fpu_checking(struct task_struct *tsk)
 	/* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception
 	   is pending.  Clear the x87 state here by setting it to fixed
 	   values. "m" is a random variable that should be in L1 */
-	alternative_input(
-		ASM_NOP8 ASM_NOP2,
-		"emms\n\t"		/* clear stack tags */
-		"fildl %P[addr]",	/* set F?P to defined value */
-		X86_FEATURE_FXSAVE_LEAK,
-		[addr] "m" (tsk->thread.fpu.has_fpu));
+	if (unlikely(static_cpu_has(X86_FEATURE_FXSAVE_LEAK))) {
+		asm volatile(
+			"fnclex\n\t"
+			"emms\n\t"
+			"fildl %P[addr]"	/* set F?P to defined value */
+			: : [addr] "m" (tsk->thread.fpu.has_fpu));
+	}
 
 	return fpu_restore_checking(&tsk->thread.fpu);
 }
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 3d1999458709..bbc8b12fa443 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -452,9 +452,16 @@ static inline int pte_present(pte_t a)
 }
 
 #define pte_accessible pte_accessible
-static inline int pte_accessible(pte_t a)
+static inline bool pte_accessible(struct mm_struct *mm, pte_t a)
 {
-	return pte_flags(a) & _PAGE_PRESENT;
+	if (pte_flags(a) & _PAGE_PRESENT)
+		return true;
+
+	if ((pte_flags(a) & (_PAGE_PROTNONE | _PAGE_NUMA)) &&
+			mm_tlb_flush_pending(mm))
+		return true;
+
+	return false;
 }
 
 static inline int pte_hidden(pte_t pte)
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index 8729723636fd..c8b051933b1b 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -8,6 +8,12 @@
 DECLARE_PER_CPU(int, __preempt_count);
 
 /*
+ * We use the PREEMPT_NEED_RESCHED bit as an inverted NEED_RESCHED such
+ * that a decrement hitting 0 means we can and should reschedule.
+ */
+#define PREEMPT_ENABLED	(0 + PREEMPT_NEED_RESCHED)
+
+/*
  * We mask the PREEMPT_NEED_RESCHED bit so as not to confuse all current users
  * that think a non-zero value indicates we cannot preempt.
  */
@@ -74,6 +80,11 @@ static __always_inline void __preempt_count_sub(int val)
 	__this_cpu_add_4(__preempt_count, -val);
 }
 
+/*
+ * Because we keep PREEMPT_NEED_RESCHED set when we do _not_ need to reschedule
+ * a decrement which hits zero means we have no preempt_count and should
+ * reschedule.
+ */
 static __always_inline bool __preempt_count_dec_and_test(void)
 {
 	GEN_UNARY_RMWcc("decl", __preempt_count, __percpu_arg(0), "e");
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index dc1ec0dff939..ea04b342c026 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -387,7 +387,8 @@ static void init_intel(struct cpuinfo_x86 *c)
 			set_cpu_cap(c, X86_FEATURE_PEBS);
 	}
 
-	if (c->x86 == 6 && c->x86_model == 29 && cpu_has_clflush)
+	if (c->x86 == 6 && cpu_has_clflush &&
+	    (c->x86_model == 29 || c->x86_model == 46 || c->x86_model == 47))
 		set_cpu_cap(c, X86_FEATURE_CLFLUSH_MONITOR);
 
 #ifdef CONFIG_X86_64
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index fd00bb29425d..c1a861829d81 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -262,11 +262,20 @@ struct cpu_hw_events {
 	__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \
 			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST_HSW)
 
-#define EVENT_CONSTRAINT_END		\
-	EVENT_CONSTRAINT(0, 0, 0)
+/*
+ * We define the end marker as having a weight of -1
+ * to enable blacklisting of events using a counter bitmask
+ * of zero and thus a weight of zero.
+ * The end marker has a weight that cannot possibly be
+ * obtained from counting the bits in the bitmask.
+ */
+#define EVENT_CONSTRAINT_END { .weight = -1 }
 
+/*
+ * Check for end marker with weight == -1
+ */
 #define for_each_event_constraint(e, c)	\
-	for ((e) = (c); (e)->weight; (e)++)
+	for ((e) = (c); (e)->weight != -1; (e)++)
 
 /*
  * Extra registers for specific events.
diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
index e09f0bfb7b8f..4b8e4d3cd6ea 100644
--- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c
+++ b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
@@ -10,6 +10,7 @@
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/ptrace.h>
+#include <linux/syscore_ops.h>
 
 #include <asm/apic.h>
 
@@ -816,6 +817,18 @@ out:
 	return ret;
 }
 
+static void ibs_eilvt_setup(void)
+{
+	/*
+	 * Force LVT offset assignment for family 10h: The offsets are
+	 * not assigned by the BIOS for this family, so the OS is
+	 * responsible for doing it. If the OS assignment fails, fall
+	 * back to BIOS settings and try to setup this.
+	 */
+	if (boot_cpu_data.x86 == 0x10)
+		force_ibs_eilvt_setup();
+}
+
 static inline int get_ibs_lvt_offset(void)
 {
 	u64 val;
@@ -851,6 +864,36 @@ static void clear_APIC_ibs(void *dummy)
 		setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_FIX, 1);
 }
 
+#ifdef CONFIG_PM
+
+static int perf_ibs_suspend(void)
+{
+	clear_APIC_ibs(NULL);
+	return 0;
+}
+
+static void perf_ibs_resume(void)
+{
+	ibs_eilvt_setup();
+	setup_APIC_ibs(NULL);
+}
+
+static struct syscore_ops perf_ibs_syscore_ops = {
+	.resume		= perf_ibs_resume,
+	.suspend	= perf_ibs_suspend,
+};
+
+static void perf_ibs_pm_init(void)
+{
+	register_syscore_ops(&perf_ibs_syscore_ops);
+}
+
+#else
+
+static inline void perf_ibs_pm_init(void) { }
+
+#endif
+
 static int
 perf_ibs_cpu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
 {
@@ -877,18 +920,12 @@ static __init int amd_ibs_init(void)
 	if (!caps)
 		return -ENODEV;	/* ibs not supported by the cpu */
 
-	/*
-	 * Force LVT offset assignment for family 10h: The offsets are
-	 * not assigned by the BIOS for this family, so the OS is
-	 * responsible for doing it. If the OS assignment fails, fall
-	 * back to BIOS settings and try to setup this.
-	 */
-	if (boot_cpu_data.x86 == 0x10)
-		force_ibs_eilvt_setup();
+	ibs_eilvt_setup();
 
 	if (!ibs_eilvt_valid())
 		goto out;
 
+	perf_ibs_pm_init();
 	get_online_cpus();
 	ibs_caps = caps;
 	/* make ibs_caps visible to other cpus: */
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 51e2988c5728..a2a4f4697889 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -1082,7 +1082,7 @@ ENTRY(ftrace_caller)
 	pushl $0	/* Pass NULL as regs pointer */
 	movl 4*4(%esp), %eax
 	movl 0x4(%ebp), %edx
-	leal function_trace_op, %ecx
+	movl function_trace_op, %ecx
 	subl $MCOUNT_INSN_SIZE, %eax
 
 .globl ftrace_call
@@ -1140,7 +1140,7 @@ ENTRY(ftrace_regs_caller)
 	movl 12*4(%esp), %eax	/* Load ip (1st parameter) */
 	subl $MCOUNT_INSN_SIZE, %eax	/* Adjust ip */
 	movl 0x4(%ebp), %edx	/* Load parent ip (2nd parameter) */
-	leal function_trace_op, %ecx /* Save ftrace_pos in 3rd parameter */
+	movl function_trace_op, %ecx /* Save ftrace_pos in 3rd parameter */
 	pushl %esp		/* Save pt_regs as 4th parameter */
 
 GLOBAL(ftrace_regs_call)
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index e21b0785a85b..1e96c3628bf2 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -88,7 +88,7 @@ END(function_hook)
 	MCOUNT_SAVE_FRAME \skip
 
 	/* Load the ftrace_ops into the 3rd parameter */
-	leaq function_trace_op, %rdx
+	movq function_trace_op(%rip), %rdx
 
 	/* Load ip into the first parameter */
 	movq RIP(%rsp), %rdi
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index dec48bfaddb8..1673940cf9c3 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1350,6 +1350,10 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
 		return;
 	}
 
+	if (!kvm_vcpu_is_bsp(apic->vcpu))
+		value &= ~MSR_IA32_APICBASE_BSP;
+	vcpu->arch.apic_base = value;
+
 	/* update jump label if enable bit changes */
 	if ((vcpu->arch.apic_base ^ value) & MSR_IA32_APICBASE_ENABLE) {
 		if (value & MSR_IA32_APICBASE_ENABLE)
@@ -1359,10 +1363,6 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
 		recalculate_apic_map(vcpu->kvm);
 	}
 
-	if (!kvm_vcpu_is_bsp(apic->vcpu))
-		value &= ~MSR_IA32_APICBASE_BSP;
-
-	vcpu->arch.apic_base = value;
 	if ((old_value ^ value) & X2APIC_ENABLE) {
 		if (value & X2APIC_ENABLE) {
 			u32 id = kvm_apic_id(apic);
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index b2fe1c252f35..da7837e1349d 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -8283,8 +8283,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 	vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK);
 	kvm_set_cr4(vcpu, vmcs12->host_cr4);
 
-	if (nested_cpu_has_ept(vmcs12))
-		nested_ept_uninit_mmu_context(vcpu);
+	nested_ept_uninit_mmu_context(vcpu);
 
 	kvm_set_cr3(vcpu, vmcs12->host_cr3);
 	kvm_mmu_reset_context(vcpu);
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 9ff85bb8dd69..9d591c895803 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -641,6 +641,20 @@ no_context(struct pt_regs *regs, unsigned long error_code,
 
 	/* Are we prepared to handle this kernel fault? */
 	if (fixup_exception(regs)) {
+		/*
+		 * Any interrupt that takes a fault gets the fixup. This makes
+		 * the below recursive fault logic only apply to a faults from
+		 * task context.
+		 */
+		if (in_interrupt())
+			return;
+
+		/*
+		 * Per the above we're !in_interrupt(), aka. task context.
+		 *
+		 * In this case we need to make sure we're not recursively
+		 * faulting through the emulate_vsyscall() logic.
+		 */
 		if (current_thread_info()->sig_on_uaccess_error && signal) {
 			tsk->thread.trap_nr = X86_TRAP_PF;
 			tsk->thread.error_code = error_code | PF_USER;
@@ -649,6 +663,10 @@ no_context(struct pt_regs *regs, unsigned long error_code,
 			/* XXX: hwpoison faults will set the wrong code. */
 			force_sig_info_fault(signal, si_code, address, tsk, 0);
 		}
+
+		/*
+		 * Barring that, we can do the fixup and be happy.
+		 */
 		return;
 	}
 
diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
index dd74e46828c0..0596e8e0cc19 100644
--- a/arch/x86/mm/gup.c
+++ b/arch/x86/mm/gup.c
@@ -83,6 +83,12 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
 		pte_t pte = gup_get_pte(ptep);
 		struct page *page;
 
+		/* Similar to the PMD case, NUMA hinting must take slow path */
+		if (pte_numa(pte)) {
+			pte_unmap(ptep);
+			return 0;
+		}
+
 		if ((pte_flags(pte) & (mask | _PAGE_SPECIAL)) != mask) {
 			pte_unmap(ptep);
 			return 0;
@@ -167,6 +173,13 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
 		if (pmd_none(pmd) || pmd_trans_splitting(pmd))
 			return 0;
 		if (unlikely(pmd_large(pmd))) {
+			/*
+			 * NUMA hinting faults need to be handled in the GUP
+			 * slowpath for accounting purposes and so that they
+			 * can be serialised against THP migration.
+			 */
+			if (pmd_numa(pmd))
+				return 0;
 			if (!gup_huge_pmd(pmd, addr, next, write, pages, nr))
 				return 0;
 		} else {
diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c
index 2ada505067cc..eb5d7a56f8d4 100644
--- a/arch/x86/vdso/vclock_gettime.c
+++ b/arch/x86/vdso/vclock_gettime.c
@@ -178,7 +178,7 @@ notrace static int __always_inline do_realtime(struct timespec *ts)
 
 	ts->tv_nsec = 0;
 	do {
-		seq = read_seqcount_begin_no_lockdep(&gtod->seq);
+		seq = raw_read_seqcount_begin(&gtod->seq);
 		mode = gtod->clock.vclock_mode;
 		ts->tv_sec = gtod->wall_time_sec;
 		ns = gtod->wall_time_snsec;
@@ -198,7 +198,7 @@ notrace static int do_monotonic(struct timespec *ts)
 
 	ts->tv_nsec = 0;
 	do {
-		seq = read_seqcount_begin_no_lockdep(&gtod->seq);
+		seq = raw_read_seqcount_begin(&gtod->seq);
 		mode = gtod->clock.vclock_mode;
 		ts->tv_sec = gtod->monotonic_time_sec;
 		ns = gtod->monotonic_time_snsec;
@@ -214,7 +214,7 @@ notrace static int do_realtime_coarse(struct timespec *ts)
 {
 	unsigned long seq;
 	do {
-		seq = read_seqcount_begin_no_lockdep(&gtod->seq);
+		seq = raw_read_seqcount_begin(&gtod->seq);
 		ts->tv_sec = gtod->wall_time_coarse.tv_sec;
 		ts->tv_nsec = gtod->wall_time_coarse.tv_nsec;
 	} while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
@@ -225,7 +225,7 @@ notrace static int do_monotonic_coarse(struct timespec *ts)
 {
 	unsigned long seq;
 	do {
-		seq = read_seqcount_begin_no_lockdep(&gtod->seq);
+		seq = raw_read_seqcount_begin(&gtod->seq);
 		ts->tv_sec = gtod->monotonic_time_coarse.tv_sec;
 		ts->tv_nsec = gtod->monotonic_time_coarse.tv_nsec;
 	} while (unlikely(read_seqcount_retry(&gtod->seq, seq)));