Merge tag 'v4.11-rc5' into x86/mm, to refresh the branch

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

34 files changed, 269 insertions, 101 deletions

diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 2d449337a360..a94a4d10f2df 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -120,10 +120,6 @@ else
         # -funit-at-a-time shrinks the kernel .text considerably
         # unfortunately it makes reading oopses harder.
         KBUILD_CFLAGS += $(call cc-option,-funit-at-a-time)
-
-        # this works around some issues with generating unwind tables in older gccs
-        # newer gccs do it by default
-        KBUILD_CFLAGS += $(call cc-option,-maccumulate-outgoing-args)
 endif
 
 ifdef CONFIG_X86_X32
@@ -147,6 +143,37 @@ ifeq ($(CONFIG_KMEMCHECK),y)
 	KBUILD_CFLAGS += $(call cc-option,-fno-builtin-memcpy)
 endif
 
+#
+# If the function graph tracer is used with mcount instead of fentry,
+# '-maccumulate-outgoing-args' is needed to prevent a GCC bug
+# (https://gcc.gnu.org/bugzilla/show_bug.cgi?id=42109)
+#
+ifdef CONFIG_FUNCTION_GRAPH_TRACER
+  ifndef CONFIG_HAVE_FENTRY
+	ACCUMULATE_OUTGOING_ARGS := 1
+  else
+    ifeq ($(call cc-option-yn, -mfentry), n)
+	ACCUMULATE_OUTGOING_ARGS := 1
+    endif
+  endif
+endif
+
+#
+# Jump labels need '-maccumulate-outgoing-args' for gcc < 4.5.2 to prevent a
+# GCC bug (https://gcc.gnu.org/bugzilla/show_bug.cgi?id=46226).  There's no way
+# to test for this bug at compile-time because the test case needs to execute,
+# which is a no-go for cross compilers.  So check the GCC version instead.
+#
+ifdef CONFIG_JUMP_LABEL
+  ifneq ($(ACCUMULATE_OUTGOING_ARGS), 1)
+	ACCUMULATE_OUTGOING_ARGS = $(call cc-if-fullversion, -lt, 040502, 1)
+  endif
+endif
+
+ifeq ($(ACCUMULATE_OUTGOING_ARGS), 1)
+	KBUILD_CFLAGS += -maccumulate-outgoing-args
+endif
+
 # Stackpointer is addressed different for 32 bit and 64 bit x86
 sp-$(CONFIG_X86_32) := esp
 sp-$(CONFIG_X86_64) := rsp
diff --git a/arch/x86/Makefile_32.cpu b/arch/x86/Makefile_32.cpu
index 6647ed49c66c..a45eb15b7cf2 100644
--- a/arch/x86/Makefile_32.cpu
+++ b/arch/x86/Makefile_32.cpu
@@ -45,24 +45,6 @@ cflags-$(CONFIG_MGEODE_LX)	+= $(call cc-option,-march=geode,-march=pentium-mmx)
 # cpu entries
 cflags-$(CONFIG_X86_GENERIC) 	+= $(call tune,generic,$(call tune,i686))
 
-# Work around the pentium-mmx code generator madness of gcc4.4.x which
-# does stack alignment by generating horrible code _before_ the mcount
-# prologue (push %ebp, mov %esp, %ebp) which breaks the function graph
-# tracer assumptions. For i686, generic, core2 this is set by the
-# compiler anyway
-ifeq ($(CONFIG_FUNCTION_GRAPH_TRACER), y)
-ADD_ACCUMULATE_OUTGOING_ARGS := y
-endif
-
-# Work around to a bug with asm goto with first implementations of it
-# in gcc causing gcc to mess up the push and pop of the stack in some
-# uses of asm goto.
-ifeq ($(CONFIG_JUMP_LABEL), y)
-ADD_ACCUMULATE_OUTGOING_ARGS := y
-endif
-
-cflags-$(ADD_ACCUMULATE_OUTGOING_ARGS) += $(call cc-option,-maccumulate-outgoing-args)
-
 # Bug fix for binutils: this option is required in order to keep
 # binutils from generating NOPL instructions against our will.
 ifneq ($(CONFIG_X86_P6_NOP),y)
diff --git a/arch/x86/boot/compressed/error.c b/arch/x86/boot/compressed/error.c
index 6248740b68b5..31922023de49 100644
--- a/arch/x86/boot/compressed/error.c
+++ b/arch/x86/boot/compressed/error.c
@@ -4,6 +4,7 @@
  * memcpy() and memmove() are defined for the compressed boot environment.
  */
 #include "misc.h"
+#include "error.h"
 
 void warn(char *m)
 {
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 349d4d17aa7f..580b60f5ac83 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2101,8 +2101,8 @@ static int x86_pmu_event_init(struct perf_event *event)
 
 static void refresh_pce(void *ignored)
 {
-	if (current->mm)
-		load_mm_cr4(current->mm);
+	if (current->active_mm)
+		load_mm_cr4(current->active_mm);
 }
 
 static void x86_pmu_event_mapped(struct perf_event *event)
@@ -2110,6 +2110,18 @@ static void x86_pmu_event_mapped(struct perf_event *event)
 	if (!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED))
 		return;
 
+	/*
+	 * This function relies on not being called concurrently in two
+	 * tasks in the same mm.  Otherwise one task could observe
+	 * perf_rdpmc_allowed > 1 and return all the way back to
+	 * userspace with CR4.PCE clear while another task is still
+	 * doing on_each_cpu_mask() to propagate CR4.PCE.
+	 *
+	 * For now, this can't happen because all callers hold mmap_sem
+	 * for write.  If this changes, we'll need a different solution.
+	 */
+	lockdep_assert_held_exclusive(&current->mm->mmap_sem);
+
 	if (atomic_inc_return(&current->mm->context.perf_rdpmc_allowed) == 1)
 		on_each_cpu_mask(mm_cpumask(current->mm), refresh_pce, NULL, 1);
 }
@@ -2244,6 +2256,7 @@ void arch_perf_update_userpage(struct perf_event *event,
 			       struct perf_event_mmap_page *userpg, u64 now)
 {
 	struct cyc2ns_data *data;
+	u64 offset;
 
 	userpg->cap_user_time = 0;
 	userpg->cap_user_time_zero = 0;
@@ -2251,11 +2264,13 @@ void arch_perf_update_userpage(struct perf_event *event,
 		!!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED);
 	userpg->pmc_width = x86_pmu.cntval_bits;
 
-	if (!sched_clock_stable())
+	if (!using_native_sched_clock() || !sched_clock_stable())
 		return;
 
 	data = cyc2ns_read_begin();
 
+	offset = data->cyc2ns_offset + __sched_clock_offset;
+
 	/*
 	 * Internal timekeeping for enabled/running/stopped times
 	 * is always in the local_clock domain.
@@ -2263,7 +2278,7 @@ void arch_perf_update_userpage(struct perf_event *event,
 	userpg->cap_user_time = 1;
 	userpg->time_mult = data->cyc2ns_mul;
 	userpg->time_shift = data->cyc2ns_shift;
-	userpg->time_offset = data->cyc2ns_offset - now;
+	userpg->time_offset = offset - now;
 
 	/*
 	 * cap_user_time_zero doesn't make sense when we're using a different
@@ -2271,7 +2286,7 @@ void arch_perf_update_userpage(struct perf_event *event,
 	 */
 	if (!event->attr.use_clockid) {
 		userpg->cap_user_time_zero = 1;
-		userpg->time_zero = data->cyc2ns_offset;
+		userpg->time_zero = offset;
 	}
 
 	cyc2ns_read_end(data);
diff --git a/arch/x86/include/asm/kvm_page_track.h b/arch/x86/include/asm/kvm_page_track.h
index d74747b031ec..c4eda791f877 100644
--- a/arch/x86/include/asm/kvm_page_track.h
+++ b/arch/x86/include/asm/kvm_page_track.h
@@ -46,6 +46,7 @@ struct kvm_page_track_notifier_node {
 };
 
 void kvm_page_track_init(struct kvm *kvm);
+void kvm_page_track_cleanup(struct kvm *kvm);
 
 void kvm_page_track_free_memslot(struct kvm_memory_slot *free,
 				 struct kvm_memory_slot *dont);
diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h
index 29eb5778019c..c8821bab938f 100644
--- a/arch/x86/include/asm/pgtable-3level.h
+++ b/arch/x86/include/asm/pgtable-3level.h
@@ -121,12 +121,9 @@ static inline void native_pmd_clear(pmd_t *pmd)
 	*(tmp + 1) = 0;
 }
 
-#if !defined(CONFIG_SMP) || (defined(CONFIG_HIGHMEM64G) && \
-		defined(CONFIG_PARAVIRT))
 static inline void native_pud_clear(pud_t *pudp)
 {
 }
-#endif
 
 static inline void pud_clear(pud_t *pudp)
 {
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index bf51e6054577..473293a681e0 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -70,7 +70,7 @@ extern struct mm_struct *pgd_page_get_mm(struct page *page);
 # define set_pud(pudp, pud)		native_set_pud(pudp, pud)
 #endif
 
-#ifndef __PAGETABLE_PMD_FOLDED
+#ifndef __PAGETABLE_PUD_FOLDED
 #define pud_clear(pud)			native_pud_clear(pud)
 #endif
 
diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h
index a04eabd43d06..27e9f9d769b8 100644
--- a/arch/x86/include/asm/timer.h
+++ b/arch/x86/include/asm/timer.h
@@ -12,6 +12,8 @@ extern int recalibrate_cpu_khz(void);
 
 extern int no_timer_check;
 
+extern bool using_native_sched_clock(void);
+
 /*
  * We use the full linear equation: f(x) = a + b*x, in order to allow
  * a continuous function in the face of dynamic freq changes.
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index 72e8300b1e8a..9cffb44a3cf5 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -485,15 +485,17 @@ static inline unsigned long uv_soc_phys_ram_to_gpa(unsigned long paddr)
 
 	if (paddr < uv_hub_info->lowmem_remap_top)
 		paddr |= uv_hub_info->lowmem_remap_base;
-	paddr |= uv_hub_info->gnode_upper;
-	if (m_val)
+
+	if (m_val) {
+		paddr |= uv_hub_info->gnode_upper;
 		paddr = ((paddr << uv_hub_info->m_shift)
 						>> uv_hub_info->m_shift) |
 			((paddr >> uv_hub_info->m_val)
 						<< uv_hub_info->n_lshift);
-	else
+	} else {
 		paddr |= uv_soc_phys_ram_to_nasid(paddr)
 						<< uv_hub_info->gpa_shift;
+	}
 	return paddr;
 }
 
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index ae32838cac5f..b2879cc23db4 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -179,10 +179,15 @@ static int acpi_register_lapic(int id, u32 acpiid, u8 enabled)
 		return -EINVAL;
 	}
 
+	if (!enabled) {
+		++disabled_cpus;
+		return -EINVAL;
+	}
+
 	if (boot_cpu_physical_apicid != -1U)
 		ver = boot_cpu_apic_version;
 
-	cpu = __generic_processor_info(id, ver, enabled);
+	cpu = generic_processor_info(id, ver);
 	if (cpu >= 0)
 		early_per_cpu(x86_cpu_to_acpiid, cpu) = acpiid;
 
@@ -710,7 +715,7 @@ static void __init acpi_set_irq_model_ioapic(void)
 #ifdef CONFIG_ACPI_HOTPLUG_CPU
 #include <acpi/processor.h>
 
-int acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)
+static int acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)
 {
 #ifdef CONFIG_ACPI_NUMA
 	int nid;
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index aee7deddabd0..8ccb7ef512e0 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -2063,7 +2063,7 @@ static int allocate_logical_cpuid(int apicid)
 	return nr_logical_cpuids++;
 }
 
-int __generic_processor_info(int apicid, int version, bool enabled)
+int generic_processor_info(int apicid, int version)
 {
 	int cpu, max = nr_cpu_ids;
 	bool boot_cpu_detected = physid_isset(boot_cpu_physical_apicid,
@@ -2121,11 +2121,9 @@ int __generic_processor_info(int apicid, int version, bool enabled)
 	if (num_processors >= nr_cpu_ids) {
 		int thiscpu = max + disabled_cpus;
 
-		if (enabled) {
-			pr_warning("APIC: NR_CPUS/possible_cpus limit of %i "
-				   "reached. Processor %d/0x%x ignored.\n",
-				   max, thiscpu, apicid);
-		}
+		pr_warning("APIC: NR_CPUS/possible_cpus limit of %i "
+			   "reached. Processor %d/0x%x ignored.\n",
+			   max, thiscpu, apicid);
 
 		disabled_cpus++;
 		return -EINVAL;
@@ -2177,23 +2175,13 @@ int __generic_processor_info(int apicid, int version, bool enabled)
 		apic->x86_32_early_logical_apicid(cpu);
 #endif
 	set_cpu_possible(cpu, true);
-
-	if (enabled) {
-		num_processors++;
-		physid_set(apicid, phys_cpu_present_map);
-		set_cpu_present(cpu, true);
-	} else {
-		disabled_cpus++;
-	}
+	physid_set(apicid, phys_cpu_present_map);
+	set_cpu_present(cpu, true);
+	num_processors++;
 
 	return cpu;
 }
 
-int generic_processor_info(int apicid, int version)
-{
-	return __generic_processor_info(apicid, version, true);
-}
-
 int hard_smp_processor_id(void)
 {
 	return read_apic_id();
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index e9f8f8cdd570..86f20cc0a65e 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -1105,7 +1105,8 @@ void __init uv_init_hub_info(struct uv_hub_info_s *hi)
 	node_id.v		= uv_read_local_mmr(UVH_NODE_ID);
 	uv_cpuid.gnode_shift	= max_t(unsigned int, uv_cpuid.gnode_shift, mn.n_val);
 	hi->gnode_extra		= (node_id.s.node_id & ~((1 << uv_cpuid.gnode_shift) - 1)) >> 1;
-	hi->gnode_upper		= (unsigned long)hi->gnode_extra << mn.m_val;
+	if (mn.m_val)
+		hi->gnode_upper	= (u64)hi->gnode_extra << mn.m_val;
 
 	if (uv_gp_table) {
 		hi->global_mmr_base	= uv_gp_table->mmr_base;
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index c05509d38b1f..9ac2a5cdd9c2 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -727,7 +727,7 @@ void rdtgroup_kn_unlock(struct kernfs_node *kn)
 	if (atomic_dec_and_test(&rdtgrp->waitcount) &&
 	    (rdtgrp->flags & RDT_DELETED)) {
 		kernfs_unbreak_active_protection(kn);
-		kernfs_put(kn);
+		kernfs_put(rdtgrp->kn);
 		kfree(rdtgrp);
 	} else {
 		kernfs_unbreak_active_protection(kn);
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 524cc5780a77..6e4a047e4b68 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -60,7 +60,7 @@ static const char * const th_names[] = {
 	"load_store",
 	"insn_fetch",
 	"combined_unit",
-	"",
+	"decode_unit",
 	"northbridge",
 	"execution_unit",
 };
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 8f3d9cf26ff9..cbd73eb42170 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -29,6 +29,12 @@
 #include <asm/ftrace.h>
 #include <asm/nops.h>
 
+#if defined(CONFIG_FUNCTION_GRAPH_TRACER) && \
+	!defined(CC_USING_FENTRY) && \
+	!defined(CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE)
+# error The following combination is not supported: ((compiler missing -mfentry) || (CONFIG_X86_32 and !CONFIG_DYNAMIC_FTRACE)) && CONFIG_FUNCTION_GRAPH_TRACER && CONFIG_CC_OPTIMIZE_FOR_SIZE
+#endif
+
 #ifdef CONFIG_DYNAMIC_FTRACE
 
 int ftrace_arch_code_modify_prepare(void)
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 54a2372f5dbb..b5785c197e53 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -4,6 +4,7 @@
  *  Copyright (C) 2000 Andrea Arcangeli <andrea@suse.de> SuSE
  */
 
+#define DISABLE_BRANCH_PROFILING
 #include <linux/init.h>
 #include <linux/linkage.h>
 #include <linux/types.h>
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index f088ea4c66e7..a723ae9440ab 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -166,11 +166,9 @@ int __register_nmi_handler(unsigned int type, struct nmiaction *action)
 	spin_lock_irqsave(&desc->lock, flags);
 
 	/*
-	 * most handlers of type NMI_UNKNOWN never return because
-	 * they just assume the NMI is theirs.  Just a sanity check
-	 * to manage expectations
+	 * Indicate if there are multiple registrations on the
+	 * internal NMI handler call chains (SERR and IO_CHECK).
 	 */
-	WARN_ON_ONCE(type == NMI_UNKNOWN && !list_empty(&desc->head));
 	WARN_ON_ONCE(type == NMI_SERR && !list_empty(&desc->head));
 	WARN_ON_ONCE(type == NMI_IO_CHECK && !list_empty(&desc->head));
 
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 4f7a9833d8e5..714dfba6a1e7 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -328,7 +328,7 @@ unsigned long long sched_clock(void)
 	return paravirt_sched_clock();
 }
 
-static inline bool using_native_sched_clock(void)
+bool using_native_sched_clock(void)
 {
 	return pv_time_ops.sched_clock == native_sched_clock;
 }
@@ -336,7 +336,7 @@ static inline bool using_native_sched_clock(void)
 unsigned long long
 sched_clock(void) __attribute__((alias("native_sched_clock")));
 
-static inline bool using_native_sched_clock(void) { return true; }
+bool using_native_sched_clock(void) { return true; }
 #endif
 
 int check_tsc_unstable(void)
@@ -1333,6 +1333,8 @@ static int __init init_tsc_clocksource(void)
 	 * the refined calibration and directly register it as a clocksource.
 	 */
 	if (boot_cpu_has(X86_FEATURE_TSC_KNOWN_FREQ)) {
+		if (boot_cpu_has(X86_FEATURE_ART))
+			art_related_clocksource = &clocksource_tsc;
 		clocksource_register_khz(&clocksource_tsc, tsc_khz);
 		return 0;
 	}
diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c
index 478d15dbaee4..08339262b666 100644
--- a/arch/x86/kernel/unwind_frame.c
+++ b/arch/x86/kernel/unwind_frame.c
@@ -82,19 +82,43 @@ static size_t regs_size(struct pt_regs *regs)
 	return sizeof(*regs);
 }
 
+#ifdef CONFIG_X86_32
+#define GCC_REALIGN_WORDS 3
+#else
+#define GCC_REALIGN_WORDS 1
+#endif
+
 static bool is_last_task_frame(struct unwind_state *state)
 {
-	unsigned long bp = (unsigned long)state->bp;
-	unsigned long regs = (unsigned long)task_pt_regs(state->task);
+	unsigned long *last_bp = (unsigned long *)task_pt_regs(state->task) - 2;
+	unsigned long *aligned_bp = last_bp - GCC_REALIGN_WORDS;
 
 	/*
 	 * We have to check for the last task frame at two different locations
 	 * because gcc can occasionally decide to realign the stack pointer and
-	 * change the offset of the stack frame by a word in the prologue of a
-	 * function called by head/entry code.
+	 * change the offset of the stack frame in the prologue of a function
+	 * called by head/entry code.  Examples:
+	 *
+	 * <start_secondary>:
+	 *      push   %edi
+	 *      lea    0x8(%esp),%edi
+	 *      and    $0xfffffff8,%esp
+	 *      pushl  -0x4(%edi)
+	 *      push   %ebp
+	 *      mov    %esp,%ebp
+	 *
+	 * <x86_64_start_kernel>:
+	 *      lea    0x8(%rsp),%r10
+	 *      and    $0xfffffffffffffff0,%rsp
+	 *      pushq  -0x8(%r10)
+	 *      push   %rbp
+	 *      mov    %rsp,%rbp
+	 *
+	 * Note that after aligning the stack, it pushes a duplicate copy of
+	 * the return address before pushing the frame pointer.
 	 */
-	return bp == regs - FRAME_HEADER_SIZE ||
-	       bp == regs - FRAME_HEADER_SIZE - sizeof(long);
+	return (state->bp == last_bp ||
+		(state->bp == aligned_bp && *(aligned_bp+1) == *(last_bp+1)));
 }
 
 /*
diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c
index 73ea24d4f119..047b17a26269 100644
--- a/arch/x86/kvm/i8259.c
+++ b/arch/x86/kvm/i8259.c
@@ -657,6 +657,9 @@ void kvm_pic_destroy(struct kvm *kvm)
 {
 	struct kvm_pic *vpic = kvm->arch.vpic;
 
+	if (!vpic)
+		return;
+
 	kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_master);
 	kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_slave);
 	kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_eclr);
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index 6e219e5c07d2..289270a6aecb 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -635,6 +635,9 @@ void kvm_ioapic_destroy(struct kvm *kvm)
 {
 	struct kvm_ioapic *ioapic = kvm->arch.vioapic;
 
+	if (!ioapic)
+		return;
+
 	cancel_delayed_work_sync(&ioapic->eoi_inject);
 	kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &ioapic->dev);
 	kvm->arch.vioapic = NULL;
diff --git a/arch/x86/kvm/page_track.c b/arch/x86/kvm/page_track.c
index 37942e419c32..60168cdd0546 100644
--- a/arch/x86/kvm/page_track.c
+++ b/arch/x86/kvm/page_track.c
@@ -160,6 +160,14 @@ bool kvm_page_track_is_active(struct kvm_vcpu *vcpu, gfn_t gfn,
 	return !!ACCESS_ONCE(slot->arch.gfn_track[mode][index]);
 }
 
+void kvm_page_track_cleanup(struct kvm *kvm)
+{
+	struct kvm_page_track_notifier_head *head;
+
+	head = &kvm->arch.track_notifier_head;
+	cleanup_srcu_struct(&head->track_srcu);
+}
+
 void kvm_page_track_init(struct kvm *kvm)
 {
 	struct kvm_page_track_notifier_head *head;
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index c02b9af2056a..5f48f62b8dc2 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1377,6 +1377,9 @@ static void avic_vm_destroy(struct kvm *kvm)
 	unsigned long flags;
 	struct kvm_arch *vm_data = &kvm->arch;
 
+	if (!avic)
+		return;
+
 	avic_free_vm_id(vm_data->avic_vm_id);
 
 	if (vm_data->avic_logical_id_table_page)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 3acde663dc58..535cc065b844 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -1238,6 +1238,11 @@ static inline bool cpu_has_vmx_invvpid_global(void)
 	return vmx_capability.vpid & VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT;
 }
 
+static inline bool cpu_has_vmx_invvpid(void)
+{
+	return vmx_capability.vpid & VMX_VPID_INVVPID_BIT;
+}
+
 static inline bool cpu_has_vmx_ept(void)
 {
 	return vmcs_config.cpu_based_2nd_exec_ctrl &
@@ -2751,7 +2756,6 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
 		SECONDARY_EXEC_RDTSCP |
 		SECONDARY_EXEC_DESC |
 		SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE |
-		SECONDARY_EXEC_ENABLE_VPID |
 		SECONDARY_EXEC_APIC_REGISTER_VIRT |
 		SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
 		SECONDARY_EXEC_WBINVD_EXITING |
@@ -2779,10 +2783,12 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
 	 * though it is treated as global context.  The alternative is
 	 * not failing the single-context invvpid, and it is worse.
 	 */
-	if (enable_vpid)
+	if (enable_vpid) {
+		vmx->nested.nested_vmx_secondary_ctls_high |=
+			SECONDARY_EXEC_ENABLE_VPID;
 		vmx->nested.nested_vmx_vpid_caps = VMX_VPID_INVVPID_BIT |
 			VMX_VPID_EXTENT_SUPPORTED_MASK;
-	else
+	} else
 		vmx->nested.nested_vmx_vpid_caps = 0;
 
 	if (enable_unrestricted_guest)
@@ -4020,6 +4026,12 @@ static void vmx_flush_tlb(struct kvm_vcpu *vcpu)
 	__vmx_flush_tlb(vcpu, to_vmx(vcpu)->vpid);
 }
 
+static void vmx_flush_tlb_ept_only(struct kvm_vcpu *vcpu)
+{
+	if (enable_ept)
+		vmx_flush_tlb(vcpu);
+}
+
 static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu)
 {
 	ulong cr0_guest_owned_bits = vcpu->arch.cr0_guest_owned_bits;
@@ -6513,8 +6525,10 @@ static __init int hardware_setup(void)
 	if (boot_cpu_has(X86_FEATURE_NX))
 		kvm_enable_efer_bits(EFER_NX);
 
-	if (!cpu_has_vmx_vpid())
+	if (!cpu_has_vmx_vpid() || !cpu_has_vmx_invvpid() ||
+		!(cpu_has_vmx_invvpid_single() || cpu_has_vmx_invvpid_global()))
 		enable_vpid = 0;
+
 	if (!cpu_has_vmx_shadow_vmcs())
 		enable_shadow_vmcs = 0;
 	if (enable_shadow_vmcs)
@@ -8497,7 +8511,8 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
 	    && kvm_vmx_exit_handlers[exit_reason])
 		return kvm_vmx_exit_handlers[exit_reason](vcpu);
 	else {
-		WARN_ONCE(1, "vmx: unexpected exit reason 0x%x\n", exit_reason);
+		vcpu_unimpl(vcpu, "vmx: unexpected exit reason 0x%x\n",
+				exit_reason);
 		kvm_queue_exception(vcpu, UD_VECTOR);
 		return 1;
 	}
@@ -8543,6 +8558,7 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set)
 	} else {
 		sec_exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE;
 		sec_exec_control |= SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
+		vmx_flush_tlb_ept_only(vcpu);
 	}
 	vmcs_write32(SECONDARY_VM_EXEC_CONTROL, sec_exec_control);
 
@@ -8568,8 +8584,10 @@ static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu, hpa_t hpa)
 	 */
 	if (!is_guest_mode(vcpu) ||
 	    !nested_cpu_has2(get_vmcs12(&vmx->vcpu),
-			     SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES))
+			     SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
 		vmcs_write64(APIC_ACCESS_ADDR, hpa);
+		vmx_flush_tlb_ept_only(vcpu);
+	}
 }
 
 static void vmx_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr)
@@ -9970,7 +9988,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	u32 exec_control;
-	bool nested_ept_enabled = false;
 
 	vmcs_write16(GUEST_ES_SELECTOR, vmcs12->guest_es_selector);
 	vmcs_write16(GUEST_CS_SELECTOR, vmcs12->guest_cs_selector);
@@ -10117,8 +10134,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 				vmcs12->guest_intr_status);
 		}
 
-		nested_ept_enabled = (exec_control & SECONDARY_EXEC_ENABLE_EPT) != 0;
-
 		/*
 		 * Write an illegal value to APIC_ACCESS_ADDR. Later,
 		 * nested_get_vmcs12_pages will either fix it up or
@@ -10251,6 +10266,9 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 	if (nested_cpu_has_ept(vmcs12)) {
 		kvm_mmu_unload(vcpu);
 		nested_ept_init_mmu_context(vcpu);
+	} else if (nested_cpu_has2(vmcs12,
+				   SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
+		vmx_flush_tlb_ept_only(vcpu);
 	}
 
 	/*
@@ -10278,12 +10296,10 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 	vmx_set_efer(vcpu, vcpu->arch.efer);
 
 	/* Shadow page tables on either EPT or shadow page tables. */
-	if (nested_vmx_load_cr3(vcpu, vmcs12->guest_cr3, nested_ept_enabled,
+	if (nested_vmx_load_cr3(vcpu, vmcs12->guest_cr3, nested_cpu_has_ept(vmcs12),
 				entry_failure_code))
 		return 1;
 
-	kvm_mmu_reset_context(vcpu);
-
 	if (!enable_ept)
 		vcpu->arch.walk_mmu->inject_page_fault = vmx_inject_page_fault_nested;
 
@@ -11052,6 +11068,10 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 		vmx->nested.change_vmcs01_virtual_x2apic_mode = false;
 		vmx_set_virtual_x2apic_mode(vcpu,
 				vcpu->arch.apic_base & X2APIC_ENABLE);
+	} else if (!nested_cpu_has_ept(vmcs12) &&
+		   nested_cpu_has2(vmcs12,
+				   SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
+		vmx_flush_tlb_ept_only(vcpu);
 	}
 
 	/* This is needed for same reason as it was needed in prepare_vmcs02 */
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 1faf620a6fdc..ccbd45ecd41a 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -8153,11 +8153,12 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	if (kvm_x86_ops->vm_destroy)
 		kvm_x86_ops->vm_destroy(kvm);
 	kvm_iommu_unmap_guest(kvm);
-	kfree(kvm->arch.vpic);
-	kfree(kvm->arch.vioapic);
+	kvm_pic_destroy(kvm);
+	kvm_ioapic_destroy(kvm);
 	kvm_free_vcpus(kvm);
 	kvfree(rcu_dereference_check(kvm->arch.apic_map, 1));
 	kvm_mmu_uninit_vm(kvm);
+	kvm_page_track_cleanup(kvm);
 }
 
 void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
@@ -8566,11 +8567,11 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
 {
 	struct x86_exception fault;
 
-	trace_kvm_async_pf_ready(work->arch.token, work->gva);
 	if (work->wakeup_all)
 		work->arch.token = ~0; /* broadcast wakeup */
 	else
 		kvm_del_async_pf_gfn(vcpu, work->arch.gfn);
+	trace_kvm_async_pf_ready(work->arch.token, work->gva);
 
 	if ((vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED) &&
 	    !apf_put_user(vcpu, KVM_PV_REASON_PAGE_READY)) {
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index 779782f58324..9a53a06e5a3e 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -290,7 +290,7 @@ EXPORT_SYMBOL_GPL(memcpy_mcsafe_unrolled)
 	_ASM_EXTABLE_FAULT(.L_copy_leading_bytes, .L_memcpy_mcsafe_fail)
 	_ASM_EXTABLE_FAULT(.L_cache_w0, .L_memcpy_mcsafe_fail)
 	_ASM_EXTABLE_FAULT(.L_cache_w1, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_cache_w3, .L_memcpy_mcsafe_fail)
+	_ASM_EXTABLE_FAULT(.L_cache_w2, .L_memcpy_mcsafe_fail)
 	_ASM_EXTABLE_FAULT(.L_cache_w3, .L_memcpy_mcsafe_fail)
 	_ASM_EXTABLE_FAULT(.L_cache_w4, .L_memcpy_mcsafe_fail)
 	_ASM_EXTABLE_FAULT(.L_cache_w5, .L_memcpy_mcsafe_fail)
diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c
index 7b81f01067f2..3d1059db6bf6 100644
--- a/arch/x86/mm/kasan_init_64.c
+++ b/arch/x86/mm/kasan_init_64.c
@@ -1,3 +1,4 @@
+#define DISABLE_BRANCH_PROFILING
 #define pr_fmt(fmt) "kasan: " fmt
 #include <linux/bootmem.h>
 #include <linux/kasan.h>
diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c
index 887e57182716..aed206475aa7 100644
--- a/arch/x86/mm/kaslr.c
+++ b/arch/x86/mm/kaslr.c
@@ -48,7 +48,7 @@ static const unsigned long vaddr_start = __PAGE_OFFSET_BASE;
 #if defined(CONFIG_X86_ESPFIX64)
 static const unsigned long vaddr_end = ESPFIX_BASE_ADDR;
 #elif defined(CONFIG_EFI)
-static const unsigned long vaddr_end = EFI_VA_START;
+static const unsigned long vaddr_end = EFI_VA_END;
 #else
 static const unsigned long vaddr_end = __START_KERNEL_map;
 #endif
@@ -105,7 +105,7 @@ void __init kernel_randomize_memory(void)
 	 */
 	BUILD_BUG_ON(vaddr_start >= vaddr_end);
 	BUILD_BUG_ON(IS_ENABLED(CONFIG_X86_ESPFIX64) &&
-		     vaddr_end >= EFI_VA_START);
+		     vaddr_end >= EFI_VA_END);
 	BUILD_BUG_ON((IS_ENABLED(CONFIG_X86_ESPFIX64) ||
 		      IS_ENABLED(CONFIG_EFI)) &&
 		     vaddr_end >= __START_KERNEL_map);
diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c
index 5126dfd52b18..cd44ae727df7 100644
--- a/arch/x86/mm/mpx.c
+++ b/arch/x86/mm/mpx.c
@@ -590,7 +590,7 @@ static unsigned long mpx_bd_entry_to_bt_addr(struct mm_struct *mm,
  * we might run off the end of the bounds table if we are on
  * a 64-bit kernel and try to get 8 bytes.
  */
-int get_user_bd_entry(struct mm_struct *mm, unsigned long *bd_entry_ret,
+static int get_user_bd_entry(struct mm_struct *mm, unsigned long *bd_entry_ret,
 		long __user *bd_entry_ptr)
 {
 	u32 bd_entry_32;
diff --git a/arch/x86/platform/intel-mid/device_libs/Makefile b/arch/x86/platform/intel-mid/device_libs/Makefile
index a7dbec4dce27..3dbde04febdc 100644
--- a/arch/x86/platform/intel-mid/device_libs/Makefile
+++ b/arch/x86/platform/intel-mid/device_libs/Makefile
@@ -26,5 +26,6 @@ obj-$(subst m,y,$(CONFIG_GPIO_PCA953X)) += platform_pcal9555a.o
 obj-$(subst m,y,$(CONFIG_GPIO_PCA953X)) += platform_tca6416.o
 # MISC Devices
 obj-$(subst m,y,$(CONFIG_KEYBOARD_GPIO)) += platform_gpio_keys.o
+obj-$(subst m,y,$(CONFIG_INTEL_MID_POWER_BUTTON)) += platform_mrfld_power_btn.o
 obj-$(subst m,y,$(CONFIG_RTC_DRV_CMOS)) += platform_mrfld_rtc.o
 obj-$(subst m,y,$(CONFIG_INTEL_MID_WATCHDOG)) += platform_mrfld_wdt.o
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_power_btn.c b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_power_btn.c
new file mode 100644
index 000000000000..a6c3705a28ad
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_power_btn.c
@@ -0,0 +1,82 @@
+/*
+ * Intel Merrifield power button support
+ *
+ * (C) Copyright 2017 Intel Corporation
+ *
+ * Author: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+#include <linux/init.h>
+#include <linux/ioport.h>
+#include <linux/platform_device.h>
+#include <linux/sfi.h>
+
+#include <asm/intel-mid.h>
+#include <asm/intel_scu_ipc.h>
+
+static struct resource mrfld_power_btn_resources[] = {
+	{
+		.flags		= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device mrfld_power_btn_dev = {
+	.name		= "msic_power_btn",
+	.id		= PLATFORM_DEVID_NONE,
+	.num_resources	= ARRAY_SIZE(mrfld_power_btn_resources),
+	.resource	= mrfld_power_btn_resources,
+};
+
+static int mrfld_power_btn_scu_status_change(struct notifier_block *nb,
+					     unsigned long code, void *data)
+{
+	if (code == SCU_DOWN) {
+		platform_device_unregister(&mrfld_power_btn_dev);
+		return 0;
+	}
+
+	return platform_device_register(&mrfld_power_btn_dev);
+}
+
+static struct notifier_block mrfld_power_btn_scu_notifier = {
+	.notifier_call	= mrfld_power_btn_scu_status_change,
+};
+
+static int __init register_mrfld_power_btn(void)
+{
+	if (intel_mid_identify_cpu() != INTEL_MID_CPU_CHIP_TANGIER)
+		return -ENODEV;
+
+	/*
+	 * We need to be sure that the SCU IPC is ready before
+	 * PMIC power button device can be registered:
+	 */
+	intel_scu_notifier_add(&mrfld_power_btn_scu_notifier);
+
+	return 0;
+}
+arch_initcall(register_mrfld_power_btn);
+
+static void __init *mrfld_power_btn_platform_data(void *info)
+{
+	struct resource *res = mrfld_power_btn_resources;
+	struct sfi_device_table_entry *pentry = info;
+
+	res->start = res->end = pentry->irq;
+	return NULL;
+}
+
+static const struct devs_id mrfld_power_btn_dev_id __initconst = {
+	.name			= "bcove_power_btn",
+	.type			= SFI_DEV_TYPE_IPC,
+	.delay			= 1,
+	.msic			= 1,
+	.get_platform_data	= &mrfld_power_btn_platform_data,
+};
+
+sfi_device(mrfld_power_btn_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c
index 86edd1e941eb..9e304e2ea4f5 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c
@@ -19,7 +19,7 @@
 #include <asm/intel_scu_ipc.h>
 #include <asm/io_apic.h>
 
-#define TANGIER_EXT_TIMER0_MSI 15
+#define TANGIER_EXT_TIMER0_MSI 12
 
 static struct platform_device wdt_dev = {
 	.name = "intel_mid_wdt",
diff --git a/arch/x86/platform/intel-mid/mfld.c b/arch/x86/platform/intel-mid/mfld.c
index e793fe509971..e42978d4deaf 100644
--- a/arch/x86/platform/intel-mid/mfld.c
+++ b/arch/x86/platform/intel-mid/mfld.c
@@ -17,16 +17,6 @@
 
 #include "intel_mid_weak_decls.h"
 
-static void penwell_arch_setup(void);
-/* penwell arch ops */
-static struct intel_mid_ops penwell_ops = {
-	.arch_setup = penwell_arch_setup,
-};
-
-static void mfld_power_off(void)
-{
-}
-
 static unsigned long __init mfld_calibrate_tsc(void)
 {
 	unsigned long fast_calibrate;
@@ -63,9 +53,12 @@ static unsigned long __init mfld_calibrate_tsc(void)
 static void __init penwell_arch_setup(void)
 {
 	x86_platform.calibrate_tsc = mfld_calibrate_tsc;
-	pm_power_off = mfld_power_off;
 }
 
+static struct intel_mid_ops penwell_ops = {
+	.arch_setup = penwell_arch_setup,
+};
+
 void *get_penwell_ops(void)
 {
 	return &penwell_ops;
diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile
index 555b9fa0ad43..7dbdb780264d 100644
--- a/arch/x86/purgatory/Makefile
+++ b/arch/x86/purgatory/Makefile
@@ -8,6 +8,7 @@ PURGATORY_OBJS = $(addprefix $(obj)/,$(purgatory-y))
 LDFLAGS_purgatory.ro := -e purgatory_start -r --no-undefined -nostdlib -z nodefaultlib
 targets += purgatory.ro
 
+KASAN_SANITIZE	:= n
 KCOV_INSTRUMENT := n
 
 # Default KBUILD_CFLAGS can have -pg option set when FTRACE is enabled. That