Merge tag 'v4.0-rc2' into x86/asm, to refresh the tree

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

40 files changed, 658 insertions, 185 deletions

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 62fbe7177cdd..c887cd944f0c 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -16,6 +16,10 @@ CFLAGS_REMOVE_ftrace.o = -pg
 CFLAGS_REMOVE_early_printk.o = -pg
 endif
 
+KASAN_SANITIZE_head$(BITS).o := n
+KASAN_SANITIZE_dumpstack.o := n
+KASAN_SANITIZE_dumpstack_$(BITS).o := n
+
 CFLAGS_irq.o := -I$(src)/../include/asm/trace
 
 obj-y			:= process_$(BITS).o signal.o entry_$(BITS).o
@@ -64,6 +68,7 @@ obj-$(CONFIG_X86_MPPARSE)	+= mpparse.o
 obj-y				+= apic/
 obj-$(CONFIG_X86_REBOOTFIXUPS)	+= reboot_fixups_32.o
 obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
+obj-$(CONFIG_LIVEPATCH)		+= livepatch.o
 obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o
 obj-$(CONFIG_FTRACE_SYSCALLS)	+= ftrace.o
 obj-$(CONFIG_X86_TSC)		+= trace_clock.o
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index a18fff361c7f..3d525c6124f6 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -613,6 +613,11 @@ int acpi_gsi_to_irq(u32 gsi, unsigned int *irqp)
 {
 	int rc, irq, trigger, polarity;
 
+	if (acpi_irq_model == ACPI_IRQ_MODEL_PIC) {
+		*irqp = gsi;
+		return 0;
+	}
+
 	rc = acpi_get_override_irq(gsi, &trigger, &polarity);
 	if (rc == 0) {
 		trigger = trigger ? ACPI_LEVEL_SENSITIVE : ACPI_EDGE_SENSITIVE;
@@ -845,13 +850,7 @@ int acpi_ioapic_registered(acpi_handle handle, u32 gsi_base)
 
 static int __init acpi_parse_sbf(struct acpi_table_header *table)
 {
-	struct acpi_table_boot *sb;
-
-	sb = (struct acpi_table_boot *)table;
-	if (!sb) {
-		printk(KERN_WARNING PREFIX "Unable to map SBF\n");
-		return -ENODEV;
-	}
+	struct acpi_table_boot *sb = (struct acpi_table_boot *)table;
 
 	sbf_port = sb->cmos_index;	/* Save CMOS port */
 
@@ -865,13 +864,7 @@ static struct resource *hpet_res __initdata;
 
 static int __init acpi_parse_hpet(struct acpi_table_header *table)
 {
-	struct acpi_table_hpet *hpet_tbl;
-
-	hpet_tbl = (struct acpi_table_hpet *)table;
-	if (!hpet_tbl) {
-		printk(KERN_WARNING PREFIX "Unable to map HPET\n");
-		return -ENODEV;
-	}
+	struct acpi_table_hpet *hpet_tbl = (struct acpi_table_hpet *)table;
 
 	if (hpet_tbl->address.space_id != ACPI_SPACE_MEM) {
 		printk(KERN_WARNING PREFIX "HPET timers must be located in "
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 31368207837c..d1daead5fcdd 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -78,7 +78,7 @@ int x86_acpi_suspend_lowlevel(void)
 
 	header->pmode_cr0 = read_cr0();
 	if (__this_cpu_read(cpu_info.cpuid_level) >= 0) {
-		header->pmode_cr4 = read_cr4();
+		header->pmode_cr4 = __read_cr4();
 		header->pmode_behavior |= (1 << WAKEUP_BEHAVIOR_RESTORE_CR4);
 	}
 	if (!rdmsr_safe(MSR_IA32_MISC_ENABLE,
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index b665d241efad..ad3639ae1b9b 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1580,8 +1580,7 @@ static __init void try_to_enable_x2apic(int remap_mode)
 		 * under KVM
 		 */
 		if (max_physical_apicid > 255 ||
-		    (IS_ENABLED(CONFIG_HYPERVISOR_GUEST) &&
-		     !hypervisor_x2apic_available())) {
+		    !hypervisor_x2apic_available()) {
 			pr_info("x2apic: IRQ remapping doesn't support X2APIC mode\n");
 			x2apic_disable();
 			return;
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index b15bffcaba6d..2346c95c6ab1 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -19,6 +19,7 @@
 #include <asm/archrandom.h>
 #include <asm/hypervisor.h>
 #include <asm/processor.h>
+#include <asm/tlbflush.h>
 #include <asm/debugreg.h>
 #include <asm/sections.h>
 #include <asm/vsyscall.h>
@@ -278,7 +279,7 @@ __setup("nosmep", setup_disable_smep);
 static __always_inline void setup_smep(struct cpuinfo_x86 *c)
 {
 	if (cpu_has(c, X86_FEATURE_SMEP))
-		set_in_cr4(X86_CR4_SMEP);
+		cr4_set_bits(X86_CR4_SMEP);
 }
 
 static __init int setup_disable_smap(char *arg)
@@ -298,9 +299,9 @@ static __always_inline void setup_smap(struct cpuinfo_x86 *c)
 
 	if (cpu_has(c, X86_FEATURE_SMAP)) {
 #ifdef CONFIG_X86_SMAP
-		set_in_cr4(X86_CR4_SMAP);
+		cr4_set_bits(X86_CR4_SMAP);
 #else
-		clear_in_cr4(X86_CR4_SMAP);
+		cr4_clear_bits(X86_CR4_SMAP);
 #endif
 	}
 }
@@ -1295,6 +1296,12 @@ void cpu_init(void)
 	wait_for_master_cpu(cpu);
 
 	/*
+	 * Initialize the CR4 shadow before doing anything that could
+	 * try to read it.
+	 */
+	cr4_init_shadow();
+
+	/*
 	 * Load microcode on this cpu if a valid microcode is available.
 	 * This is early microcode loading procedure.
 	 */
@@ -1313,7 +1320,7 @@ void cpu_init(void)
 
 	pr_debug("Initializing CPU#%d\n", cpu);
 
-	clear_in_cr4(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE);
+	cr4_clear_bits(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE);
 
 	/*
 	 * Initialize the per-CPU GDT with the boot GDT,
@@ -1389,12 +1396,18 @@ void cpu_init(void)
 
 	wait_for_master_cpu(cpu);
 
+	/*
+	 * Initialize the CR4 shadow before doing anything that could
+	 * try to read it.
+	 */
+	cr4_init_shadow();
+
 	show_ucode_info_early();
 
 	printk(KERN_INFO "Initializing CPU#%d\n", cpu);
 
 	if (cpu_feature_enabled(X86_FEATURE_VME) || cpu_has_tsc || cpu_has_de)
-		clear_in_cr4(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE);
+		cr4_clear_bits(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE);
 
 	load_current_idt();
 	switch_to_new_gdt(cpu);
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 94d7dcb12145..50163fa9034f 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -565,8 +565,8 @@ static const struct _tlb_table intel_tlb_table[] = {
 	{ 0xb2, TLB_INST_4K,		64,	" TLB_INST 4KByte pages, 4-way set associative" },
 	{ 0xb3, TLB_DATA_4K,		128,	" TLB_DATA 4 KByte pages, 4-way set associative" },
 	{ 0xb4, TLB_DATA_4K,		256,	" TLB_DATA 4 KByte pages, 4-way associative" },
-	{ 0xb5, TLB_INST_4K,		64,	" TLB_INST 4 KByte pages, 8-way set ssociative" },
-	{ 0xb6, TLB_INST_4K,		128,	" TLB_INST 4 KByte pages, 8-way set ssociative" },
+	{ 0xb5, TLB_INST_4K,		64,	" TLB_INST 4 KByte pages, 8-way set associative" },
+	{ 0xb6, TLB_INST_4K,		128,	" TLB_INST 4 KByte pages, 8-way set associative" },
 	{ 0xba, TLB_DATA_4K,		64,	" TLB_DATA 4 KByte pages, 4-way associative" },
 	{ 0xc0, TLB_DATA_4K_4M,		8,	" TLB_DATA 4 KByte and 4 MByte pages, 4-way associative" },
 	{ 0xc1, STLB_4K_2M,		1024,	" STLB 4 KByte and 2 MByte pages, 8-way associative" },
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index c7035073dfc1..659643376dbf 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -952,20 +952,18 @@ static ssize_t show_size(struct _cpuid4_info *this_leaf, char *buf,
 static ssize_t show_shared_cpu_map_func(struct _cpuid4_info *this_leaf,
 					int type, char *buf)
 {
-	ptrdiff_t len = PTR_ALIGN(buf + PAGE_SIZE - 1, PAGE_SIZE) - buf;
-	int n = 0;
-
-	if (len > 1) {
-		const struct cpumask *mask;
-
-		mask = to_cpumask(this_leaf->shared_cpu_map);
-		n = type ?
-			cpulist_scnprintf(buf, len-2, mask) :
-			cpumask_scnprintf(buf, len-2, mask);
-		buf[n++] = '\n';
-		buf[n] = '\0';
-	}
-	return n;
+	const struct cpumask *mask = to_cpumask(this_leaf->shared_cpu_map);
+	int ret;
+
+	if (type)
+		ret = scnprintf(buf, PAGE_SIZE - 1, "%*pbl",
+				cpumask_pr_args(mask));
+	else
+		ret = scnprintf(buf, PAGE_SIZE - 1, "%*pb",
+				cpumask_pr_args(mask));
+	buf[ret++] = '\n';
+	buf[ret] = '\0';
+	return ret;
 }
 
 static inline ssize_t show_shared_cpu_map(struct _cpuid4_info *leaf, char *buf,
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index cdfed7953963..3c036cb4a370 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -44,6 +44,7 @@
 
 #include <asm/processor.h>
 #include <asm/traps.h>
+#include <asm/tlbflush.h>
 #include <asm/mce.h>
 #include <asm/msr.h>
 
@@ -151,14 +152,11 @@ static struct mce_log mcelog = {
 void mce_log(struct mce *mce)
 {
 	unsigned next, entry;
-	int ret = 0;
 
 	/* Emit the trace record: */
 	trace_mce_record(mce);
 
-	ret = atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, mce);
-	if (ret == NOTIFY_STOP)
-		return;
+	atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, mce);
 
 	mce->finished = 0;
 	wmb();
@@ -1452,7 +1450,7 @@ static void __mcheck_cpu_init_generic(void)
 	bitmap_fill(all_banks, MAX_NR_BANKS);
 	machine_check_poll(MCP_UC | m_fl, &all_banks);
 
-	set_in_cr4(X86_CR4_MCE);
+	cr4_set_bits(X86_CR4_MCE);
 
 	rdmsrl(MSR_IA32_MCG_CAP, cap);
 	if (cap & MCG_CTL_P)
diff --git a/arch/x86/kernel/cpu/mcheck/p5.c b/arch/x86/kernel/cpu/mcheck/p5.c
index ec2663a708e4..737b0ad4e61a 100644
--- a/arch/x86/kernel/cpu/mcheck/p5.c
+++ b/arch/x86/kernel/cpu/mcheck/p5.c
@@ -9,6 +9,7 @@
 
 #include <asm/processor.h>
 #include <asm/traps.h>
+#include <asm/tlbflush.h>
 #include <asm/mce.h>
 #include <asm/msr.h>
 
@@ -65,7 +66,7 @@ void intel_p5_mcheck_init(struct cpuinfo_x86 *c)
 	       "Intel old style machine check architecture supported.\n");
 
 	/* Enable MCE: */
-	set_in_cr4(X86_CR4_MCE);
+	cr4_set_bits(X86_CR4_MCE);
 	printk(KERN_INFO
 	       "Intel old style machine check reporting enabled on CPU#%d.\n",
 	       smp_processor_id());
diff --git a/arch/x86/kernel/cpu/mcheck/winchip.c b/arch/x86/kernel/cpu/mcheck/winchip.c
index bd5d46a32210..44f138296fbe 100644
--- a/arch/x86/kernel/cpu/mcheck/winchip.c
+++ b/arch/x86/kernel/cpu/mcheck/winchip.c
@@ -8,6 +8,7 @@
 
 #include <asm/processor.h>
 #include <asm/traps.h>
+#include <asm/tlbflush.h>
 #include <asm/mce.h>
 #include <asm/msr.h>
 
@@ -36,7 +37,7 @@ void winchip_mcheck_init(struct cpuinfo_x86 *c)
 	lo &= ~(1<<4);	/* Enable MCE */
 	wrmsr(MSR_IDT_FCR1, lo, hi);
 
-	set_in_cr4(X86_CR4_MCE);
+	cr4_set_bits(X86_CR4_MCE);
 
 	printk(KERN_INFO
 	       "Winchip machine check reporting enabled on CPU#0.\n");
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index c6826d1e8082..746e7fd08aad 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -196,6 +196,11 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
 		struct microcode_header_intel mc_header;
 		unsigned int mc_size;
 
+		if (leftover < sizeof(mc_header)) {
+			pr_err("error! Truncated header in microcode data file\n");
+			break;
+		}
+
 		if (get_ucode_data(&mc_header, ucode_ptr, sizeof(mc_header)))
 			break;
 
diff --git a/arch/x86/kernel/cpu/microcode/intel_early.c b/arch/x86/kernel/cpu/microcode/intel_early.c
index ec9df6f9cd47..420eb933189c 100644
--- a/arch/x86/kernel/cpu/microcode/intel_early.c
+++ b/arch/x86/kernel/cpu/microcode/intel_early.c
@@ -321,7 +321,11 @@ get_matching_model_microcode(int cpu, unsigned long start,
 	unsigned int mc_saved_count = mc_saved_data->mc_saved_count;
 	int i;
 
-	while (leftover) {
+	while (leftover && mc_saved_count < ARRAY_SIZE(mc_saved_tmp)) {
+
+		if (leftover < sizeof(mc_header))
+			break;
+
 		mc_header = (struct microcode_header_intel *)ucode_ptr;
 
 		mc_size = get_totalsize(mc_header);
diff --git a/arch/x86/kernel/cpu/mtrr/cyrix.c b/arch/x86/kernel/cpu/mtrr/cyrix.c
index 9e451b0876b5..f8c81ba0b465 100644
--- a/arch/x86/kernel/cpu/mtrr/cyrix.c
+++ b/arch/x86/kernel/cpu/mtrr/cyrix.c
@@ -138,8 +138,8 @@ static void prepare_set(void)
 
 	/*  Save value of CR4 and clear Page Global Enable (bit 7)  */
 	if (cpu_has_pge) {
-		cr4 = read_cr4();
-		write_cr4(cr4 & ~X86_CR4_PGE);
+		cr4 = __read_cr4();
+		__write_cr4(cr4 & ~X86_CR4_PGE);
 	}
 
 	/*
@@ -171,7 +171,7 @@ static void post_set(void)
 
 	/* Restore value of CR4 */
 	if (cpu_has_pge)
-		write_cr4(cr4);
+		__write_cr4(cr4);
 }
 
 static void cyrix_set_arr(unsigned int reg, unsigned long base,
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 0e25a1bc5ab5..7d74f7b3c6ba 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -678,8 +678,8 @@ static void prepare_set(void) __acquires(set_atomicity_lock)
 
 	/* Save value of CR4 and clear Page Global Enable (bit 7) */
 	if (cpu_has_pge) {
-		cr4 = read_cr4();
-		write_cr4(cr4 & ~X86_CR4_PGE);
+		cr4 = __read_cr4();
+		__write_cr4(cr4 & ~X86_CR4_PGE);
 	}
 
 	/* Flush all TLBs via a mov %cr3, %reg; mov %reg, %cr3 */
@@ -708,7 +708,7 @@ static void post_set(void) __releases(set_atomicity_lock)
 
 	/* Restore value of CR4 */
 	if (cpu_has_pge)
-		write_cr4(cr4);
+		__write_cr4(cr4);
 	raw_spin_unlock(&set_atomicity_lock);
 }
 
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 143e5f5dc855..b71a7f86d68a 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -31,6 +31,8 @@
 #include <asm/nmi.h>
 #include <asm/smp.h>
 #include <asm/alternative.h>
+#include <asm/mmu_context.h>
+#include <asm/tlbflush.h>
 #include <asm/timer.h>
 #include <asm/desc.h>
 #include <asm/ldt.h>
@@ -43,6 +45,8 @@ DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = {
 	.enabled = 1,
 };
 
+struct static_key rdpmc_always_available = STATIC_KEY_INIT_FALSE;
+
 u64 __read_mostly hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
 				[PERF_COUNT_HW_CACHE_OP_MAX]
@@ -1327,8 +1331,6 @@ x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
 		break;
 
 	case CPU_STARTING:
-		if (x86_pmu.attr_rdpmc)
-			set_in_cr4(X86_CR4_PCE);
 		if (x86_pmu.cpu_starting)
 			x86_pmu.cpu_starting(cpu);
 		break;
@@ -1804,14 +1806,44 @@ static int x86_pmu_event_init(struct perf_event *event)
 			event->destroy(event);
 	}
 
+	if (ACCESS_ONCE(x86_pmu.attr_rdpmc))
+		event->hw.flags |= PERF_X86_EVENT_RDPMC_ALLOWED;
+
 	return err;
 }
 
+static void refresh_pce(void *ignored)
+{
+	if (current->mm)
+		load_mm_cr4(current->mm);
+}
+
+static void x86_pmu_event_mapped(struct perf_event *event)
+{
+	if (!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED))
+		return;
+
+	if (atomic_inc_return(&current->mm->context.perf_rdpmc_allowed) == 1)
+		on_each_cpu_mask(mm_cpumask(current->mm), refresh_pce, NULL, 1);
+}
+
+static void x86_pmu_event_unmapped(struct perf_event *event)
+{
+	if (!current->mm)
+		return;
+
+	if (!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED))
+		return;
+
+	if (atomic_dec_and_test(&current->mm->context.perf_rdpmc_allowed))
+		on_each_cpu_mask(mm_cpumask(current->mm), refresh_pce, NULL, 1);
+}
+
 static int x86_pmu_event_idx(struct perf_event *event)
 {
 	int idx = event->hw.idx;
 
-	if (!x86_pmu.attr_rdpmc)
+	if (!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED))
 		return 0;
 
 	if (x86_pmu.num_counters_fixed && idx >= INTEL_PMC_IDX_FIXED) {
@@ -1829,16 +1861,6 @@ static ssize_t get_attr_rdpmc(struct device *cdev,
 	return snprintf(buf, 40, "%d\n", x86_pmu.attr_rdpmc);
 }
 
-static void change_rdpmc(void *info)
-{
-	bool enable = !!(unsigned long)info;
-
-	if (enable)
-		set_in_cr4(X86_CR4_PCE);
-	else
-		clear_in_cr4(X86_CR4_PCE);
-}
-
 static ssize_t set_attr_rdpmc(struct device *cdev,
 			      struct device_attribute *attr,
 			      const char *buf, size_t count)
@@ -1850,14 +1872,27 @@ static ssize_t set_attr_rdpmc(struct device *cdev,
 	if (ret)
 		return ret;
 
+	if (val > 2)
+		return -EINVAL;
+
 	if (x86_pmu.attr_rdpmc_broken)
 		return -ENOTSUPP;
 
-	if (!!val != !!x86_pmu.attr_rdpmc) {
-		x86_pmu.attr_rdpmc = !!val;
-		on_each_cpu(change_rdpmc, (void *)val, 1);
+	if ((val == 2) != (x86_pmu.attr_rdpmc == 2)) {
+		/*
+		 * Changing into or out of always available, aka
+		 * perf-event-bypassing mode.  This path is extremely slow,
+		 * but only root can trigger it, so it's okay.
+		 */
+		if (val == 2)
+			static_key_slow_inc(&rdpmc_always_available);
+		else
+			static_key_slow_dec(&rdpmc_always_available);
+		on_each_cpu(refresh_pce, NULL, 1);
 	}
 
+	x86_pmu.attr_rdpmc = val;
+
 	return count;
 }
 
@@ -1900,6 +1935,9 @@ static struct pmu pmu = {
 
 	.event_init		= x86_pmu_event_init,
 
+	.event_mapped		= x86_pmu_event_mapped,
+	.event_unmapped		= x86_pmu_event_unmapped,
+
 	.add			= x86_pmu_add,
 	.del			= x86_pmu_del,
 	.start			= x86_pmu_start,
@@ -1914,13 +1952,15 @@ static struct pmu pmu = {
 	.flush_branch_stack	= x86_pmu_flush_branch_stack,
 };
 
-void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
+void arch_perf_update_userpage(struct perf_event *event,
+			       struct perf_event_mmap_page *userpg, u64 now)
 {
 	struct cyc2ns_data *data;
 
 	userpg->cap_user_time = 0;
 	userpg->cap_user_time_zero = 0;
-	userpg->cap_user_rdpmc = x86_pmu.attr_rdpmc;
+	userpg->cap_user_rdpmc =
+		!!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED);
 	userpg->pmc_width = x86_pmu.cntval_bits;
 
 	if (!sched_clock_stable())
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 4e6cdb0ddc70..df525d2be1e8 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -71,6 +71,8 @@ struct event_constraint {
 #define PERF_X86_EVENT_COMMITTED	0x8 /* event passed commit_txn */
 #define PERF_X86_EVENT_PEBS_LD_HSW	0x10 /* haswell style datala, load */
 #define PERF_X86_EVENT_PEBS_NA_HSW	0x20 /* haswell style datala, unknown */
+#define PERF_X86_EVENT_RDPMC_ALLOWED	0x40 /* grant rdpmc permission */
+
 
 struct amd_nb {
 	int nb_id;  /* NorthBridge id */
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index b74ebc7c4402..cf3df1d8d039 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -265,7 +265,10 @@ int __die(const char *str, struct pt_regs *regs, long err)
 	printk("SMP ");
 #endif
 #ifdef CONFIG_DEBUG_PAGEALLOC
-	printk("DEBUG_PAGEALLOC");
+	printk("DEBUG_PAGEALLOC ");
+#endif
+#ifdef CONFIG_KASAN
+	printk("KASAN");
 #endif
 	printk("\n");
 	if (notify_die(DIE_OOPS, str, regs, err,
diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c
index 01d1c187c9f9..a62536a1be88 100644
--- a/arch/x86/kernel/early_printk.c
+++ b/arch/x86/kernel/early_printk.c
@@ -19,6 +19,7 @@
 #include <linux/usb/ehci_def.h>
 #include <linux/efi.h>
 #include <asm/efi.h>
+#include <asm/pci_x86.h>
 
 /* Simple VGA output */
 #define VGABASE		(__ISA_IO_base + 0xb8000)
@@ -76,7 +77,7 @@ static struct console early_vga_console = {
 
 /* Serial functions loosely based on a similar package from Klaus P. Gerlicher */
 
-static int early_serial_base = 0x3f8;  /* ttyS0 */
+static unsigned long early_serial_base = 0x3f8;  /* ttyS0 */
 
 #define XMTRDY          0x20
 
@@ -94,13 +95,40 @@ static int early_serial_base = 0x3f8;  /* ttyS0 */
 #define DLL             0       /*  Divisor Latch Low         */
 #define DLH             1       /*  Divisor latch High        */
 
+static void mem32_serial_out(unsigned long addr, int offset, int value)
+{
+	uint32_t *vaddr = (uint32_t *)addr;
+	/* shift implied by pointer type */
+	writel(value, vaddr + offset);
+}
+
+static unsigned int mem32_serial_in(unsigned long addr, int offset)
+{
+	uint32_t *vaddr = (uint32_t *)addr;
+	/* shift implied by pointer type */
+	return readl(vaddr + offset);
+}
+
+static unsigned int io_serial_in(unsigned long addr, int offset)
+{
+	return inb(addr + offset);
+}
+
+static void io_serial_out(unsigned long addr, int offset, int value)
+{
+	outb(value, addr + offset);
+}
+
+static unsigned int (*serial_in)(unsigned long addr, int offset) = io_serial_in;
+static void (*serial_out)(unsigned long addr, int offset, int value) = io_serial_out;
+
 static int early_serial_putc(unsigned char ch)
 {
 	unsigned timeout = 0xffff;
 
-	while ((inb(early_serial_base + LSR) & XMTRDY) == 0 && --timeout)
+	while ((serial_in(early_serial_base, LSR) & XMTRDY) == 0 && --timeout)
 		cpu_relax();
-	outb(ch, early_serial_base + TXR);
+	serial_out(early_serial_base, TXR, ch);
 	return timeout ? 0 : -1;
 }
 
@@ -114,13 +142,28 @@ static void early_serial_write(struct console *con, const char *s, unsigned n)
 	}
 }
 
+static __init void early_serial_hw_init(unsigned divisor)
+{
+	unsigned char c;
+
+	serial_out(early_serial_base, LCR, 0x3);	/* 8n1 */
+	serial_out(early_serial_base, IER, 0);	/* no interrupt */
+	serial_out(early_serial_base, FCR, 0);	/* no fifo */
+	serial_out(early_serial_base, MCR, 0x3);	/* DTR + RTS */
+
+	c = serial_in(early_serial_base, LCR);
+	serial_out(early_serial_base, LCR, c | DLAB);
+	serial_out(early_serial_base, DLL, divisor & 0xff);
+	serial_out(early_serial_base, DLH, (divisor >> 8) & 0xff);
+	serial_out(early_serial_base, LCR, c & ~DLAB);
+}
+
 #define DEFAULT_BAUD 9600
 
 static __init void early_serial_init(char *s)
 {
-	unsigned char c;
 	unsigned divisor;
-	unsigned baud = DEFAULT_BAUD;
+	unsigned long baud = DEFAULT_BAUD;
 	char *e;
 
 	if (*s == ',')
@@ -145,24 +188,124 @@ static __init void early_serial_init(char *s)
 			s++;
 	}
 
-	outb(0x3, early_serial_base + LCR);	/* 8n1 */
-	outb(0, early_serial_base + IER);	/* no interrupt */
-	outb(0, early_serial_base + FCR);	/* no fifo */
-	outb(0x3, early_serial_base + MCR);	/* DTR + RTS */
+	if (*s) {
+		if (kstrtoul(s, 0, &baud) < 0 || baud == 0)
+			baud = DEFAULT_BAUD;
+	}
+
+	/* Convert from baud to divisor value */
+	divisor = 115200 / baud;
+
+	/* These will always be IO based ports */
+	serial_in = io_serial_in;
+	serial_out = io_serial_out;
+
+	/* Set up the HW */
+	early_serial_hw_init(divisor);
+}
+
+#ifdef CONFIG_PCI
+/*
+ * early_pci_serial_init()
+ *
+ * This function is invoked when the early_printk param starts with "pciserial"
+ * The rest of the param should be ",B:D.F,baud" where B, D & F describe the
+ * location of a PCI device that must be a UART device.
+ */
+static __init void early_pci_serial_init(char *s)
+{
+	unsigned divisor;
+	unsigned long baud = DEFAULT_BAUD;
+	u8 bus, slot, func;
+	uint32_t classcode, bar0;
+	uint16_t cmdreg;
+	char *e;
+
+
+	/*
+	 * First, part the param to get the BDF values
+	 */
+	if (*s == ',')
+		++s;
+
+	if (*s == 0)
+		return;
+
+	bus = (u8)simple_strtoul(s, &e, 16);
+	s = e;
+	if (*s != ':')
+		return;
+	++s;
+	slot = (u8)simple_strtoul(s, &e, 16);
+	s = e;
+	if (*s != '.')
+		return;
+	++s;
+	func = (u8)simple_strtoul(s, &e, 16);
+	s = e;
+
+	/* A baud might be following */
+	if (*s == ',')
+		s++;
+
+	/*
+	 * Second, find the device from the BDF
+	 */
+	cmdreg = read_pci_config(bus, slot, func, PCI_COMMAND);
+	classcode = read_pci_config(bus, slot, func, PCI_CLASS_REVISION);
+	bar0 = read_pci_config(bus, slot, func, PCI_BASE_ADDRESS_0);
+
+	/*
+	 * Verify it is a UART type device
+	 */
+	if (((classcode >> 16 != PCI_CLASS_COMMUNICATION_MODEM) &&
+	     (classcode >> 16 != PCI_CLASS_COMMUNICATION_SERIAL)) ||
+	   (((classcode >> 8) & 0xff) != 0x02)) /* 16550 I/F at BAR0 */
+		return;
+
+	/*
+	 * Determine if it is IO or memory mapped
+	 */
+	if (bar0 & 0x01) {
+		/* it is IO mapped */