Merge tag 'v4.3-rc4' into locking/core, to pick up fixes before applying new changes

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

24 files changed, 242 insertions, 202 deletions

diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index d3033183ed70..055a01de7c8d 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1128,7 +1128,18 @@ END(error_exit)
 
 /* Runs on exception stack */
 ENTRY(nmi)
+	/*
+	 * Fix up the exception frame if we're on Xen.
+	 * PARAVIRT_ADJUST_EXCEPTION_FRAME is guaranteed to push at most
+	 * one value to the stack on native, so it may clobber the rdx
+	 * scratch slot, but it won't clobber any of the important
+	 * slots past it.
+	 *
+	 * Xen is a different story, because the Xen frame itself overlaps
+	 * the "NMI executing" variable.
+	 */
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
+
 	/*
 	 * We allow breakpoints in NMIs. If a breakpoint occurs, then
 	 * the iretq it performs will take us out of NMI context.
@@ -1179,9 +1190,12 @@ ENTRY(nmi)
 	 * we don't want to enable interrupts, because then we'll end
 	 * up in an awkward situation in which IRQs are on but NMIs
 	 * are off.
+	 *
+	 * We also must not push anything to the stack before switching
+	 * stacks lest we corrupt the "NMI executing" variable.
 	 */
 
-	SWAPGS
+	SWAPGS_UNSAFE_STACK
 	cld
 	movq	%rsp, %rdx
 	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index e6cf2ad350d1..9727b3b48bd1 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -193,7 +193,7 @@
 #define X86_FEATURE_HW_PSTATE	( 7*32+ 8) /* AMD HW-PState */
 #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
 #define X86_FEATURE_HWP		( 7*32+ 10) /* "hwp" Intel HWP */
-#define X86_FEATURE_HWP_NOITFY	( 7*32+ 11) /* Intel HWP_NOTIFY */
+#define X86_FEATURE_HWP_NOTIFY	( 7*32+ 11) /* Intel HWP_NOTIFY */
 #define X86_FEATURE_HWP_ACT_WINDOW ( 7*32+ 12) /* Intel HWP_ACT_WINDOW */
 #define X86_FEATURE_HWP_EPP	( 7*32+13) /* Intel HWP_EPP */
 #define X86_FEATURE_HWP_PKG_REQ ( 7*32+14) /* Intel HWP_PKG_REQ */
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 155162ea0e00..ae68be92f755 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -86,6 +86,18 @@ extern u64 asmlinkage efi_call(void *fp, ...);
 extern void __iomem *__init efi_ioremap(unsigned long addr, unsigned long size,
 					u32 type, u64 attribute);
 
+#ifdef CONFIG_KASAN
+/*
+ * CONFIG_KASAN may redefine memset to __memset.  __memset function is present
+ * only in kernel binary.  Since the EFI stub linked into a separate binary it
+ * doesn't have __memset().  So we should use standard memset from
+ * arch/x86/boot/compressed/string.c.  The same applies to memcpy and memmove.
+ */
+#undef memcpy
+#undef memset
+#undef memmove
+#endif
+
 #endif /* CONFIG_X86_32 */
 
 extern struct efi_scratch efi_scratch;
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 349f80a82b82..2beee0382088 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -40,6 +40,7 @@
 
 #define KVM_PIO_PAGE_OFFSET 1
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 2
+#define KVM_HALT_POLL_NS_DEFAULT 500000
 
 #define KVM_IRQCHIP_NUM_PINS  KVM_IOAPIC_NUM_PINS
 
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index c1c0a1c14344..b8c14bb7fc8f 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -141,6 +141,8 @@
 #define DEBUGCTLMSR_BTS_OFF_USR		(1UL << 10)
 #define DEBUGCTLMSR_FREEZE_LBRS_ON_PMI	(1UL << 11)
 
+#define MSR_PEBS_FRONTEND		0x000003f7
+
 #define MSR_IA32_POWER_CTL		0x000001fc
 
 #define MSR_IA32_MC0_CTL		0x00000400
@@ -331,6 +333,7 @@
 /* C1E active bits in int pending message */
 #define K8_INTP_C1E_ACTIVE_MASK		0x18000000
 #define MSR_K8_TSEG_ADDR		0xc0010112
+#define MSR_K8_TSEG_MASK		0xc0010113
 #define K8_MTRRFIXRANGE_DRAM_ENABLE	0x00040000 /* MtrrFixDramEn bit    */
 #define K8_MTRRFIXRANGE_DRAM_MODIFY	0x00080000 /* MtrrFixDramModEn bit */
 #define K8_MTRR_RDMEM_WRMEM_MASK	0x18181818 /* Mask: RdMem|WrMem    */
diff --git a/arch/x86/include/asm/pvclock-abi.h b/arch/x86/include/asm/pvclock-abi.h
index 655e07a48f6c..67f08230103a 100644
--- a/arch/x86/include/asm/pvclock-abi.h
+++ b/arch/x86/include/asm/pvclock-abi.h
@@ -41,6 +41,7 @@ struct pvclock_wall_clock {
 
 #define PVCLOCK_TSC_STABLE_BIT	(1 << 0)
 #define PVCLOCK_GUEST_STOPPED	(1 << 1)
+/* PVCLOCK_COUNTS_FROM_ZERO broke ABI and can't be used anymore. */
 #define PVCLOCK_COUNTS_FROM_ZERO (1 << 2)
 #endif /* __ASSEMBLY__ */
 #endif /* _ASM_X86_PVCLOCK_ABI_H */
diff --git a/arch/x86/include/uapi/asm/bitsperlong.h b/arch/x86/include/uapi/asm/bitsperlong.h
index b0ae1c4dc791..217909b4d6f5 100644
--- a/arch/x86/include/uapi/asm/bitsperlong.h
+++ b/arch/x86/include/uapi/asm/bitsperlong.h
@@ -1,7 +1,7 @@
 #ifndef __ASM_X86_BITSPERLONG_H
 #define __ASM_X86_BITSPERLONG_H
 
-#ifdef __x86_64__
+#if defined(__x86_64__) && !defined(__ILP32__)
 # define __BITS_PER_LONG 64
 #else
 # define __BITS_PER_LONG 32
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 381c8b9b3a33..20e242ea1bc4 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -34,11 +34,10 @@
 struct ms_hyperv_info ms_hyperv;
 EXPORT_SYMBOL_GPL(ms_hyperv);
 
-static void (*hv_kexec_handler)(void);
-static void (*hv_crash_handler)(struct pt_regs *regs);
-
 #if IS_ENABLED(CONFIG_HYPERV)
 static void (*vmbus_handler)(void);
+static void (*hv_kexec_handler)(void);
+static void (*hv_crash_handler)(struct pt_regs *regs);
 
 void hyperv_vector_handler(struct pt_regs *regs)
 {
@@ -96,8 +95,8 @@ void hv_remove_crash_handler(void)
 	hv_crash_handler = NULL;
 }
 EXPORT_SYMBOL_GPL(hv_remove_crash_handler);
-#endif
 
+#ifdef CONFIG_KEXEC_CORE
 static void hv_machine_shutdown(void)
 {
 	if (kexec_in_progress && hv_kexec_handler)
@@ -111,7 +110,8 @@ static void hv_machine_crash_shutdown(struct pt_regs *regs)
 		hv_crash_handler(regs);
 	native_machine_crash_shutdown(regs);
 }
-
+#endif /* CONFIG_KEXEC_CORE */
+#endif /* CONFIG_HYPERV */
 
 static uint32_t  __init ms_hyperv_platform(void)
 {
@@ -186,8 +186,10 @@ static void __init ms_hyperv_init_platform(void)
 	no_timer_check = 1;
 #endif
 
+#if IS_ENABLED(CONFIG_HYPERV) && defined(CONFIG_KEXEC_CORE)
 	machine_ops.shutdown = hv_machine_shutdown;
 	machine_ops.crash_shutdown = hv_machine_crash_shutdown;
+#endif
 	mark_tsc_unstable("running on Hyper-V");
 }
 
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 5edf6d868fc1..165be83a7fa4 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -47,6 +47,7 @@ enum extra_reg_type {
 	EXTRA_REG_RSP_1 = 1,	/* offcore_response_1 */
 	EXTRA_REG_LBR   = 2,	/* lbr_select */
 	EXTRA_REG_LDLAT = 3,	/* ld_lat_threshold */
+	EXTRA_REG_FE    = 4,    /* fe_* */
 
 	EXTRA_REG_MAX		/* number of entries needed */
 };
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 3fefebfbdf4b..f63360be2238 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -205,6 +205,11 @@ static struct extra_reg intel_skl_extra_regs[] __read_mostly = {
 	INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3fffff8fffull, RSP_0),
 	INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0x3fffff8fffull, RSP_1),
 	INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
+	/*
+	 * Note the low 8 bits eventsel code is not a continuous field, containing
+	 * some #GPing bits. These are masked out.
+	 */
+	INTEL_UEVENT_EXTRA_REG(0x01c6, MSR_PEBS_FRONTEND, 0x7fff17, FE),
 	EVENT_EXTRA_END
 };
 
@@ -250,7 +255,7 @@ struct event_constraint intel_bdw_event_constraints[] = {
 	FIXED_EVENT_CONSTRAINT(0x003c, 1),	/* CPU_CLK_UNHALTED.CORE */
 	FIXED_EVENT_CONSTRAINT(0x0300, 2),	/* CPU_CLK_UNHALTED.REF */
 	INTEL_UEVENT_CONSTRAINT(0x148, 0x4),	/* L1D_PEND_MISS.PENDING */
-	INTEL_EVENT_CONSTRAINT(0xa3, 0x4),	/* CYCLE_ACTIVITY.* */
+	INTEL_UEVENT_CONSTRAINT(0x8a3, 0x4),	/* CYCLE_ACTIVITY.CYCLES_L1D_MISS */
 	EVENT_CONSTRAINT_END
 };
 
@@ -2891,6 +2896,8 @@ PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63");
 
 PMU_FORMAT_ATTR(ldlat, "config1:0-15");
 
+PMU_FORMAT_ATTR(frontend, "config1:0-23");
+
 static struct attribute *intel_arch3_formats_attr[] = {
 	&format_attr_event.attr,
 	&format_attr_umask.attr,
@@ -2907,6 +2914,11 @@ static struct attribute *intel_arch3_formats_attr[] = {
 	NULL,
 };
 
+static struct attribute *skl_format_attr[] = {
+	&format_attr_frontend.attr,
+	NULL,
+};
+
 static __initconst const struct x86_pmu core_pmu = {
 	.name			= "core",
 	.handle_irq		= x86_pmu_handle_irq,
@@ -3516,7 +3528,8 @@ __init int intel_pmu_init(void)
 
 		x86_pmu.hw_config = hsw_hw_config;
 		x86_pmu.get_event_constraints = hsw_get_event_constraints;
-		x86_pmu.cpu_events = hsw_events_attrs;
+		x86_pmu.format_attrs = merge_attr(intel_arch3_formats_attr,
+						  skl_format_attr);
 		WARN_ON(!x86_pmu.format_attrs);
 		x86_pmu.cpu_events = hsw_events_attrs;
 		pr_cont("Skylake events, ");
diff --git a/arch/x86/kernel/cpu/perf_event_msr.c b/arch/x86/kernel/cpu/perf_event_msr.c
index 086b12eae794..f32ac13934f2 100644
--- a/arch/x86/kernel/cpu/perf_event_msr.c
+++ b/arch/x86/kernel/cpu/perf_event_msr.c
@@ -10,12 +10,12 @@ enum perf_msr_id {
 	PERF_MSR_EVENT_MAX,
 };
 
-bool test_aperfmperf(int idx)
+static bool test_aperfmperf(int idx)
 {
 	return boot_cpu_has(X86_FEATURE_APERFMPERF);
 }
 
-bool test_intel(int idx)
+static bool test_intel(int idx)
 {
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL ||
 	    boot_cpu_data.x86 != 6)
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index 3d423a101fae..608fb26c7254 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -37,7 +37,7 @@ void init_scattered_cpuid_features(struct cpuinfo_x86 *c)
 		{ X86_FEATURE_PLN,		CR_EAX, 4, 0x00000006, 0 },
 		{ X86_FEATURE_PTS,		CR_EAX, 6, 0x00000006, 0 },
 		{ X86_FEATURE_HWP,		CR_EAX, 7, 0x00000006, 0 },
-		{ X86_FEATURE_HWP_NOITFY,	CR_EAX, 8, 0x00000006, 0 },
+		{ X86_FEATURE_HWP_NOTIFY,	CR_EAX, 8, 0x00000006, 0 },
 		{ X86_FEATURE_HWP_ACT_WINDOW,	CR_EAX, 9, 0x00000006, 0 },
 		{ X86_FEATURE_HWP_EPP,		CR_EAX,10, 0x00000006, 0 },
 		{ X86_FEATURE_HWP_PKG_REQ,	CR_EAX,11, 0x00000006, 0 },
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index e068d6683dba..74ca2fe7a0b3 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -185,10 +185,9 @@ void native_machine_crash_shutdown(struct pt_regs *regs)
 }
 
 #ifdef CONFIG_KEXEC_FILE
-static int get_nr_ram_ranges_callback(unsigned long start_pfn,
-				unsigned long nr_pfn, void *arg)
+static int get_nr_ram_ranges_callback(u64 start, u64 end, void *arg)
 {
-	int *nr_ranges = arg;
+	unsigned int *nr_ranges = arg;
 
 	(*nr_ranges)++;
 	return 0;
@@ -214,7 +213,7 @@ static void fill_up_crash_elf_data(struct crash_elf_data *ced,
 
 	ced->image = image;
 
-	walk_system_ram_range(0, -1, &nr_ranges,
+	walk_system_ram_res(0, -1, &nr_ranges,
 				get_nr_ram_ranges_callback);
 
 	ced->max_nr_ranges = nr_ranges;
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index f68e48f5f6c2..c2130aef3f9d 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -41,10 +41,18 @@
 #include <asm/timer.h>
 #include <asm/special_insns.h>
 
-/* nop stub */
-void _paravirt_nop(void)
-{
-}
+/*
+ * nop stub, which must not clobber anything *including the stack* to
+ * avoid confusing the entry prologues.
+ */
+extern void _paravirt_nop(void);
+asm (".pushsection .entry.text, \"ax\"\n"
+     ".global _paravirt_nop\n"
+     "_paravirt_nop:\n\t"
+     "ret\n\t"
+     ".size _paravirt_nop, . - _paravirt_nop\n\t"
+     ".type _paravirt_nop, @function\n\t"
+     ".popsection");
 
 /* identity function, which can be inlined */
 u32 _paravirt_ident_32(u32 x)
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 6d0e62ae8516..39e585a554b7 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -506,3 +506,58 @@ unsigned long arch_randomize_brk(struct mm_struct *mm)
 	return randomize_range(mm->brk, range_end, 0) ? : mm->brk;
 }
 
+/*
+ * Called from fs/proc with a reference on @p to find the function
+ * which called into schedule(). This needs to be done carefully
+ * because the task might wake up and we might look at a stack
+ * changing under us.
+ */
+unsigned long get_wchan(struct task_struct *p)
+{
+	unsigned long start, bottom, top, sp, fp, ip;
+	int count = 0;
+
+	if (!p || p == current || p->state == TASK_RUNNING)
+		return 0;
+
+	start = (unsigned long)task_stack_page(p);
+	if (!start)
+		return 0;
+
+	/*
+	 * Layout of the stack page:
+	 *
+	 * ----------- topmax = start + THREAD_SIZE - sizeof(unsigned long)
+	 * PADDING
+	 * ----------- top = topmax - TOP_OF_KERNEL_STACK_PADDING
+	 * stack
+	 * ----------- bottom = start + sizeof(thread_info)
+	 * thread_info
+	 * ----------- start
+	 *
+	 * The tasks stack pointer points at the location where the
+	 * framepointer is stored. The data on the stack is:
+	 * ... IP FP ... IP FP
+	 *
+	 * We need to read FP and IP, so we need to adjust the upper
+	 * bound by another unsigned long.
+	 */
+	top = start + THREAD_SIZE - TOP_OF_KERNEL_STACK_PADDING;
+	top -= 2 * sizeof(unsigned long);
+	bottom = start + sizeof(struct thread_info);
+
+	sp = READ_ONCE(p->thread.sp);
+	if (sp < bottom || sp > top)
+		return 0;
+
+	fp = READ_ONCE(*(unsigned long *)sp);
+	do {
+		if (fp < bottom || fp > top)
+			return 0;
+		ip = READ_ONCE(*(unsigned long *)(fp + sizeof(unsigned long)));
+		if (!in_sched_functions(ip))
+			return ip;
+		fp = READ_ONCE(*(unsigned long *)fp);
+	} while (count++ < 16 && p->state != TASK_RUNNING);
+	return 0;
+}
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index c13df2c735f8..737527b40e5b 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -324,31 +324,3 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 
 	return prev_p;
 }
-
-#define top_esp                (THREAD_SIZE - sizeof(unsigned long))
-#define top_ebp                (THREAD_SIZE - 2*sizeof(unsigned long))
-
-unsigned long get_wchan(struct task_struct *p)
-{
-	unsigned long bp, sp, ip;
-	unsigned long stack_page;
-	int count = 0;
-	if (!p || p == current || p->state == TASK_RUNNING)
-		return 0;
-	stack_page = (unsigned long)task_stack_page(p);
-	sp = p->thread.sp;
-	if (!stack_page || sp < stack_page || sp > top_esp+stack_page)
-		return 0;
-	/* include/asm-i386/system.h:switch_to() pushes bp last. */
-	bp = *(unsigned long *) sp;
-	do {
-		if (bp < stack_page || bp > top_ebp+stack_page)
-			return 0;
-		ip = *(unsigned long *) (bp+4);
-		if (!in_sched_functions(ip))
-			return ip;
-		bp = *(unsigned long *) bp;
-	} while (count++ < 16);
-	return 0;
-}
-
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 3c1bbcf12924..b35921a670b2 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -499,30 +499,6 @@ void set_personality_ia32(bool x32)
 }
 EXPORT_SYMBOL_GPL(set_personality_ia32);
 
-unsigned long get_wchan(struct task_struct *p)
-{
-	unsigned long stack;
-	u64 fp, ip;
-	int count = 0;
-
-	if (!p || p == current || p->state == TASK_RUNNING)
-		return 0;
-	stack = (unsigned long)task_stack_page(p);
-	if (p->thread.sp < stack || p->thread.sp >= stack+THREAD_SIZE)
-		return 0;
-	fp = *(u64 *)(p->thread.sp);
-	do {
-		if (fp < (unsigned long)stack ||
-		    fp >= (unsigned long)stack+THREAD_SIZE)
-			return 0;
-		ip = *(u64 *)(fp+8);
-		if (!in_sched_functions(ip))
-			return ip;
-		fp = *(u64 *)fp;
-	} while (count++ < 16);
-	return 0;
-}
-
 long do_arch_prctl(struct task_struct *task, int code, unsigned long addr)
 {
 	int ret = 0;
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 69088a1ba509..ff606f507913 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3322,7 +3322,7 @@ walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep)
 			break;
 
 		reserved |= is_shadow_zero_bits_set(&vcpu->arch.mmu, spte,
-						    leaf);
+						    iterator.level);
 	}
 
 	walk_shadow_page_lockless_end(vcpu);
@@ -3614,7 +3614,7 @@ static void
 __reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
 			struct rsvd_bits_validate *rsvd_check,
 			int maxphyaddr, int level, bool nx, bool gbpages,
-			bool pse)
+			bool pse, bool amd)
 {
 	u64 exb_bit_rsvd = 0;
 	u64 gbpages_bit_rsvd = 0;
@@ -3631,7 +3631,7 @@ __reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
 	 * Non-leaf PML4Es and PDPEs reserve bit 8 (which would be the G bit for
 	 * leaf entries) on AMD CPUs only.
 	 */
-	if (guest_cpuid_is_amd(vcpu))
+	if (amd)
 		nonleaf_bit8_rsvd = rsvd_bits(8, 8);
 
 	switch (level) {
@@ -3699,7 +3699,7 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
 	__reset_rsvds_bits_mask(vcpu, &context->guest_rsvd_check,
 				cpuid_maxphyaddr(vcpu), context->root_level,
 				context->nx, guest_cpuid_has_gbpages(vcpu),
-				is_pse(vcpu));
+				is_pse(vcpu), guest_cpuid_is_amd(vcpu));
 }
 
 static void
@@ -3749,13 +3749,24 @@ static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu,
 void
 reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context)
 {
+	/*
+	 * Passing "true" to the last argument is okay; it adds a check
+	 * on bit 8 of the SPTEs which KVM doesn't use anyway.
+	 */
 	__reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check,
 				boot_cpu_data.x86_phys_bits,
 				context->shadow_root_level, context->nx,
-				guest_cpuid_has_gbpages(vcpu), is_pse(vcpu));
+				guest_cpuid_has_gbpages(vcpu), is_pse(vcpu),
+				true);
 }
 EXPORT_SYMBOL_GPL(reset_shadow_zero_bits_mask);
 
+static inline bool boot_cpu_is_amd(void)
+{
+	WARN_ON_ONCE(!tdp_enabled);
+	return shadow_x_mask == 0;
+}
+
 /*
  * the direct page table on host, use as much mmu features as
  * possible, however, kvm currently does not do execution-protection.
@@ -3764,11 +3775,11 @@ static void
 reset_tdp_shadow_zero_bits_mask(struct kvm_vcpu *vcpu,
 				struct kvm_mmu *context)
 {
-	if (guest_cpuid_is_amd(vcpu))
+	if (boot_cpu_is_amd())
 		__reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check,
 					boot_cpu_data.x86_phys_bits,
 					context->shadow_root_level, false,
-					cpu_has_gbpages, true);
+					cpu_has_gbpages, true, true);
 	else
 		__reset_rsvds_bits_mask_ept(&context->shadow_zero_check,
 					    boot_cpu_data.x86_phys_bits,
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index fdb8cb63a6c0..2f9ed1ff0632 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -202,6 +202,7 @@ module_param(npt, int, S_IRUGO);
 static int nested = true;
 module_param(nested, int, S_IRUGO);
 
+static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
 static void svm_flush_tlb(struct kvm_vcpu *vcpu);
 static void svm_complete_interrupts(struct vcpu_svm *svm);
 
@@ -513,7 +514,7 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
 	struct vcpu_svm *svm = to_svm(vcpu);
 
 	if (svm->vmcb->control.next_rip != 0) {
-		WARN_ON(!static_cpu_has(X86_FEATURE_NRIPS));
+		WARN_ON_ONCE(!static_cpu_has(X86_FEATURE_NRIPS));
 		svm->next_rip = svm->vmcb->control.next_rip;
 	}
 
@@ -865,64 +866,6 @@ static void svm_disable_lbrv(struct vcpu_svm *svm)
 	set_msr_interception(msrpm, MSR_IA32_LASTINTTOIP, 0, 0);
 }
 
-#define MTRR_TYPE_UC_MINUS	7
-#define MTRR2PROTVAL_INVALID 0xff
-
-static u8 mtrr2protval[8];
-
-static u8 fallback_mtrr_type(int mtrr)
-{
-	/*
-	 * WT and WP aren't always available in the host PAT.  Treat
-	 * them as UC and UC- respectively.  Everything else should be
-	 * there.
-	 */
-	switch (mtrr)
-	{
-	case MTRR_TYPE_WRTHROUGH:
-		return MTRR_TYPE_UNCACHABLE;
-	case MTRR_TYPE_WRPROT:
-		return MTRR_TYPE_UC_MINUS;
-	default:
-		BUG();
-	}
-}
-
-static void build_mtrr2protval(void)
-{
-	int i;
-	u64 pat;
-
-	for (i = 0; i < 8; i++)
-		mtrr2protval[i] = MTRR2PROTVAL_INVALID;
-
-	/* Ignore the invalid MTRR types.  */
-	mtrr2protval[2] = 0;
-	mtrr2protval[3] = 0;
-
-	/*
-	 * Use host PAT value to figure out the mapping from guest MTRR
-	 * values to nested page table PAT/PCD/PWT values.  We do not
-	 * want to change the host PAT value every time we enter the
-	 * guest.
-	 */
-	rdmsrl(MSR_IA32_CR_PAT, pat);
-	for (i = 0; i < 8; i++) {
-		u8 mtrr = pat >> (8 * i);
-
-		if (mtrr2protval[mtrr] == MTRR2PROTVAL_INVALID)
-			mtrr2protval[mtrr] = __cm_idx2pte(i);
-	}
-
-	for (i = 0; i < 8; i++) {
-		if (mtrr2protval[i] == MTRR2PROTVAL_INVALID) {
-			u8 fallback = fallback_mtrr_type(i);
-			mtrr2protval[i] = mtrr2protval[fallback];
-			BUG_ON(mtrr2protval[i] == MTRR2PROTVAL_INVALID);
-		}
-	}
-}
-
 static __init int svm_hardware_setup(void)
 {
 	int cpu;
@@ -989,7 +932,6 @@ static __init int svm_hardware_setup(void)
 	} else
 		kvm_disable_tdp();
 
-	build_mtrr2protval();
 	return 0;
 
 err:
@@ -1144,43 +1086,6 @@ static u64 svm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc)
 	return target_tsc - tsc;
 }
 
-static void svm_set_guest_pat(struct vcpu_svm *svm, u64 *g_pat)
-{
-	struct kvm_vcpu *vcpu = &svm->vcpu;
-
-	/* Unlike Intel, AMD takes the guest's CR0.CD into account.
-	 *
-	 * AMD does not have IPAT.  To emulate it for the case of guests
-	 * with no assigned devices, just set everything to WB.  If guests
-	 * have assigned devices, however, we cannot force WB for RAM
-	 * pages only, so use the guest PAT directly.
-	 */
-	if (!kvm_arch_has_assigned_device(vcpu->kvm))
-		*g_pat = 0x0606060606060606;
-	else
-		*g_pat = vcpu->arch.pat;
-}
-
-static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
-{
-	u8 mtrr;
-
-	/*
-	 * 1. MMIO: trust guest MTRR, so same as item 3.
-	 * 2. No passthrough: always map as WB, and force guest PAT to WB as well
-	 * 3. Passthrough: can't guarantee the result, try to trust guest.
-	 */
-	if (!is_mmio && !kvm_arch_has_assigned_device(vcpu->kvm))
-		return 0;
-
-	if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED) &&
-	    kvm_read_cr0(vcpu) & X86_CR0_CD)
-		return _PAGE_NOCACHE;
-
-	mtrr = kvm_mtrr_get_guest_memory_type(vcpu, gfn);
-	return mtrr2protval[mtrr];
-}
-
 static void init_vmcb(struct vcpu_svm *svm, bool init_event)
 {
 	struct vmcb_control_area *control = &svm->vmcb->control;
@@ -1263,7 +1168,8 @@ static void init_vmcb(struct vcpu_svm *svm, bool init_event)
 	 * svm_set_cr0() sets PG and WP and clears NW and CD on save->cr0.
 	 * It also updates the guest-visible cr0 value.
 	 */
-	(void)kvm_set_cr0(&svm->vcpu, X86_CR0_NW | X86_CR0_CD | X86_CR0_ET);
+	svm_set_cr0(&svm->vcpu, X86_CR0_NW | X86_CR0_CD | X86_CR0_ET);
+	kvm_mmu_reset_context(&svm->vcpu);
 
 	save->cr4 = X86_CR4_PAE;
 	/* rdx = ?? */
@@ -1276,7 +1182,6 @@ static void init_vmcb(struct vcpu_svm *svm, bool init_event)
 		clr_cr_intercept(svm, INTERCEPT_CR3_READ);
 		clr_cr_intercept(svm, INTERCEPT_CR3_WRITE);
 		save->g_pat = svm->vcpu.arch.pat;
-		svm_set_guest_pat(svm, &save->g_pat);
 		save->cr3 = 0;
 		save->cr4 = 0;
 	}
@@ -1671,10 +1576,13 @@ static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 
 	if (!vcpu->fpu_active)
 		cr0 |= X86_CR0_TS;
-
-	/* These are emulated via page tables.  */
-	cr0 &= ~(X86_CR0_CD | X86_CR0_NW);
-
+	/*
+	 * re-enable caching here because the QEMU bios
+	 * does not do it - this results in some delay at
+	 * reboot
+	 */
+	if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED))
+		cr0 &= ~(X86_CR0_CD | X86_CR0_NW);
 	svm->vmcb->save.cr0 = cr0;
 	mark_dirty(svm->vmcb, VMCB_CR);
 	update_cr0_intercept(svm);
@@ -3349,16 +3257,6 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 	case MSR_VM_IGNNE:
 		vcpu_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data);
 		break;
-	case MSR_IA32_CR_PAT:
-		if (npt_enabled) {
-			if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data))
-				return 1;
-			vcpu->arch.pat = data;
-			svm_set_guest_pat(svm, &svm->vmcb->save.g_pat);
-			mark_dirty(svm->vmcb, VMCB_NPT);
-			break;
-		}
-		/* fall through */
 	default:
 		return kvm_set_msr_common(vcpu, msr);
 	}
@@ -4193,6 +4091,11 @@ static bool svm_has_high_real_mode_segbase(void)
 	return true;
 }
 
+static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
+{
+	return 0;
+}
+
 static void svm_cpuid_update(struct kvm_vcpu *vcpu)
 {
 }
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 64076740251e..06ef4908ba61 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -8617,17 +8617,22 @@ static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
 	u64 ipat = 0;
 
 	/* For VT-d and EPT combination
-	 * 1. MMIO: guest may want to apply WC, trust it.
+	 * 1. MMIO: always map as UC
 	 * 2. EPT with VT-d:
 	 *   a. VT-d without snooping control feature: can't guarantee the
-	 *	result, try to trust guest.  So the same as item 1.
+	 *	result, try to trust guest.
 	 *   b. VT-d with snooping control feature: snooping control feature of
 	 *	VT-d engine can guarantee the cache correctness. Just set it
 	 *	to WB to keep consistent with host. So the same as item 3.
 	 * 3. EPT without VT-d: always map as WB and set IPAT=1 to keep
 	 *    consistent with host MTRR
 	 */
-	if (!is_mmio && !kvm_arch_has_noncoherent_dma(vcpu->kvm)) {
+	if (is_mmio) {
+		cache = MTRR_TYPE_UNCACHABLE;
+		goto exit;
+	}
+
+	if (!kvm_arch_has_noncoherent_dma(vcpu->kvm)) {
 		ipat = VMX_EPT_IPAT_BIT;
 		cache = MTRR_TYPE_WRBACK;
 		goto exit;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 6bbb0dfb99d0..92511d4b7236 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1708,8 +1708,6 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 		vcpu->pvclock_set_guest_stopped_request = false;
 	}
 
-	pvclock_flags |= PVCLOCK_COUNTS_FROM_ZERO;
-
 	/* If the host uses TSC clocksource, then it is stable */
 	if (use_master_clock)
 		pvclock_flags |= PVCLOCK_TSC_STABLE_BIT;
@@ -2007,8 +2005,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 					&vcpu->requests);
 
 			ka->boot_vcpu_runs_old_kvmclock = tmp;
-
-			ka->kvmclock_offset = -get_kernel_ns();
 		}
 
 		vcpu->arch.time = data;
@@ -2190,6 +2186,8 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_IA32_LASTINTFROMIP:
 	case MSR_IA32_LASTINTTOIP:
 	case MSR_K8_SYSCFG:
+	case MSR_K8_TSEG_ADDR:
+	case MSR_K8_TSEG_MASK:
 	case MSR_K7_HWCR:
 	case MSR_VM_HSAVE_PA:
 	case MSR_K8_INT_PENDING_MSG:
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 30564e2752d3..df48430c279b 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1132,7 +1132,7 @@ void mark_rodata_ro(void)
 	 * has been zapped already via cleanup_highmem().
 	 */
 	all_end = roundup((unsigned long)_brk_end, PMD_SIZE);
-	set_memory_nx(rodata_start, (all_end - rodata_start) >> PAGE_SHIFT);
+	set_memory_nx(text_end, (all_end - text_end) >> PAGE_SHIFT);
 
 	rodata_test();
 
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 09d3afc0a181..dc78a4a9a466 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -166,6 +166,7 @@ void pcibios_fixup_bus(struct pci_bus *b)
 {
 	struct pci_dev *dev;
 
+	pci_read_bridge_bases(b);
 	list_for_each_entry(dev, &b->devices, bus_list)
 		pcibios_fixup_device_resources(dev);
 }
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 1db84c0758b7..6a28ded74211 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -705,6 +705,70 @@ out:
 }
 
 /*
+ * Iterate the EFI memory map in reverse order because the regions
+ * will be mapped top-down. The end result is the same as if we had
+ * mapped things forward, but doesn't require us to change the
+ * existing implementation of efi_map_region().
+ */
+static inline void *efi_map_next_entry_reverse(void *entry)
+{
+	/* Initial call */
+	if (!entry)
+		return memmap.map_end - memmap.desc_size;
+
+	entry -= memmap.desc_size;
+	if (entry < memmap.map)
+		return NULL;
+
+	return entry;
+}
+
+/*
+ * efi_map_next_entry - Return the next EFI memory map descriptor
+ * @entry: Previous EFI memory map descriptor
+ *
+ * This is a helper function to iterate over the EFI memory map, which
+ * we do in different orders depending on the current configuration.
+ *
+ * To begin traversing the memory map @entry must be %NULL.
+ *
+ * Returns %NULL when we reach the end of the memory map.
+ */
+static void *efi_map_next_entry(void *entry)
+{
+	if (!efi_enabled(EFI_OLD_MEMMAP) && efi_enabled(EFI_64BIT)) {
+		/*
+		 * Starting in UEFI v2.5 the EFI_PROPERTIES_TABLE
+		 * config table feature requires us to map all entries
+		 * in the same order as they appear in the EFI memory
+		 * map. That is to say, entry N must have a lower
+		 * virtual address than entry N+1. This is because the
+		 * firmware toolchain leaves relative references in
+		 * the code/data sections, which are split and become
+		 * separate EFI memory regions. Mapping things
+		 * out-of-order leads to the firmware accessing
+		 * unmapped addresses.
+		 *
+		 * Since we need to map things this way whether or not
+		 * the kernel actually makes use of
+		 * EFI_PROPERTIES_TABLE, let's just switch to this
+		 * scheme by default for 64-bit.
+		 */
+		return efi_map_next_entry_reverse(entry);
+	}
+
+	/* Initial call */
+	if (!entry)
+		return memmap.map;
+
+	entry += memmap.desc_size;
+	if (entry >= memmap.map_end)
+		return NULL;
+
+	return entry;
+}
+
+/*
  * Map the efi memory ranges of the runtime services and update new_mmap with
  * virtual addresses.
  */
@@ -714,7 +778,8 @@ static void * __init efi_map_regions(int *count, int *pg_shift)
 	unsigned long left = 0;
 	efi_memory_desc_t *md;
 
-	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
+	p = NULL;
+	while ((p = efi_map_next_entry(p))) {
 		md = p;
 		if (!(md->attribute & EFI_MEMORY_RUNTIME)) {
 #ifdef CONFIG_X86_64