Merge branch 'fixes-rc1' into omap-for-v4.2/fixes

author: Tony Lindgren <tony@atomide.com> 2015-07-06 14:33:17 +0200
committer: Tony Lindgren <tony@atomide.com> 2015-07-06 14:33:17 +0200
commit: ae745302c0a3e2b5b768690f631fc14db44467e7 (patch)
tree: 1db4d210a7419286b447dc09fa7400a561d55f42 /arch/x86/kernel/cpu
parent: ARM: OMAP2+: Remove unnessary return statement from the void function, omap2_... (diff)
parent: ARM: dts: am4372.dtsi: disable rfbi (diff)
download: linux-ae745302c0a3e2b5b768690f631fc14db44467e7.tar.xz
linux-ae745302c0a3e2b5b768690f631fc14db44467e7.zip
33 files changed, 1328 insertions, 892 deletions
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index e4cf63301ff4..dd3a4baffe50 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -19,6 +19,13 @@
 
 #include "cpu.h"
 
+/*
+ * nodes_per_socket: Stores the number of nodes per socket.
+ * Refer to Fam15h Models 00-0fh BKDG - CPUID Fn8000_001E_ECX
+ * Node Identifiers[10:8]
+ */
+static u32 nodes_per_socket = 1;
+
 static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p)
 {
 	u32 gprs[8] = { 0 };
@@ -288,10 +295,10 @@ static int nearby_node(int apicid)
  *     Assumption: Number of cores in each internal node is the same.
  * (2) AMD processors supporting compute units
  */
-#ifdef CONFIG_X86_HT
+#ifdef CONFIG_SMP
 static void amd_get_topology(struct cpuinfo_x86 *c)
 {
-	u32 nodes, cores_per_cu = 1;
+	u32 cores_per_cu = 1;
 	u8 node_id;
 	int cpu = smp_processor_id();
 
@@ -300,7 +307,7 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
 		u32 eax, ebx, ecx, edx;
 
 		cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
-		nodes = ((ecx >> 8) & 7) + 1;
+		nodes_per_socket = ((ecx >> 8) & 7) + 1;
 		node_id = ecx & 7;
 
 		/* get compute unit information */
@@ -311,18 +318,18 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
 		u64 value;
 
 		rdmsrl(MSR_FAM10H_NODE_ID, value);
-		nodes = ((value >> 3) & 7) + 1;
+		nodes_per_socket = ((value >> 3) & 7) + 1;
 		node_id = value & 7;
 	} else
 		return;
 
 	/* fixup multi-node processor information */
-	if (nodes > 1) {
+	if (nodes_per_socket > 1) {
 		u32 cores_per_node;
 		u32 cus_per_node;
 
 		set_cpu_cap(c, X86_FEATURE_AMD_DCM);
-		cores_per_node = c->x86_max_cores / nodes;
+		cores_per_node = c->x86_max_cores / nodes_per_socket;
 		cus_per_node = cores_per_node / cores_per_cu;
 
 		/* store NodeID, use llc_shared_map to store sibling info */
@@ -341,7 +348,7 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
  */
 static void amd_detect_cmp(struct cpuinfo_x86 *c)
 {
-#ifdef CONFIG_X86_HT
+#ifdef CONFIG_SMP
 	unsigned bits;
 	int cpu = smp_processor_id();
 
@@ -366,6 +373,12 @@ u16 amd_get_nb_id(int cpu)
 }
 EXPORT_SYMBOL_GPL(amd_get_nb_id);
 
+u32 amd_get_nodes_per_socket(void)
+{
+	return nodes_per_socket;
+}
+EXPORT_SYMBOL_GPL(amd_get_nodes_per_socket);
+
 static void srat_detect_node(struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_NUMA
@@ -420,7 +433,7 @@ static void srat_detect_node(struct cpuinfo_x86 *c)
 
 static void early_init_amd_mc(struct cpuinfo_x86 *c)
 {
-#ifdef CONFIG_X86_HT
+#ifdef CONFIG_SMP
 	unsigned bits, ecx;
 
 	/* Multi core CPU? */
@@ -520,8 +533,16 @@ static void early_init_amd(struct cpuinfo_x86 *c)
 			set_cpu_cap(c, X86_FEATURE_K6_MTRR);
 #endif
 #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_PCI)
-	/* check CPU config space for extended APIC ID */
-	if (cpu_has_apic && c->x86 >= 0xf) {
+	/*
+	 * ApicID can always be treated as an 8-bit value for AMD APIC versions
+	 * >= 0x10, but even old K8s came out of reset with version 0x10. So, we
+	 * can safely set X86_FEATURE_EXTD_APICID unconditionally for families
+	 * after 16h.
+	 */
+	if (cpu_has_apic && c->x86 > 0x16) {
+		set_cpu_cap(c, X86_FEATURE_EXTD_APICID);
+	} else if (cpu_has_apic && c->x86 >= 0xf) {
+		/* check CPU config space for extended APIC ID */
 		unsigned int val;
 		val = read_pci_config(0, 24, 0, 0x68);
 		if ((val & ((1 << 17) | (1 << 18))) == ((1 << 17) | (1 << 18)))
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 03445346ee0a..bd17db15a2c1 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -12,57 +12,11 @@
 #include <asm/bugs.h>
 #include <asm/processor.h>
 #include <asm/processor-flags.h>
-#include <asm/i387.h>
+#include <asm/fpu/internal.h>
 #include <asm/msr.h>
 #include <asm/paravirt.h>
 #include <asm/alternative.h>
 
-static double __initdata x = 4195835.0;
-static double __initdata y = 3145727.0;
-
-/*
- * This used to check for exceptions..
- * However, it turns out that to support that,
- * the XMM trap handlers basically had to
- * be buggy. So let's have a correct XMM trap
- * handler, and forget about printing out
- * some status at boot.
- *
- * We should really only care about bugs here
- * anyway. Not features.
- */
-static void __init check_fpu(void)
-{
-	s32 fdiv_bug;
-
-	kernel_fpu_begin();
-
-	/*
-	 * trap_init() enabled FXSR and company _before_ testing for FP
-	 * problems here.
-	 *
-	 * Test for the divl bug: http://en.wikipedia.org/wiki/Fdiv_bug
-	 */
-	__asm__("fninit\n\t"
-		"fldl %1\n\t"
-		"fdivl %2\n\t"
-		"fmull %2\n\t"
-		"fldl %1\n\t"
-		"fsubp %%st,%%st(1)\n\t"
-		"fistpl %0\n\t"
-		"fwait\n\t"
-		"fninit"
-		: "=m" (*&fdiv_bug)
-		: "m" (*&x), "m" (*&y));
-
-	kernel_fpu_end();
-
-	if (fdiv_bug) {
-		set_cpu_bug(&boot_cpu_data, X86_BUG_FDIV);
-		pr_warn("Hmm, FPU with FDIV bug\n");
-	}
-}
-
 void __init check_bugs(void)
 {
 	identify_boot_cpu();
@@ -85,10 +39,5 @@ void __init check_bugs(void)
 		'0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86);
 	alternative_instructions();
 
-	/*
-	 * kernel_fpu_begin/end() in check_fpu() relies on the patched
-	 * alternative instructions.
-	 */
-	if (cpu_has_fpu)
-		check_fpu();
+	fpu__init_check_bugs();
 }
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index a62cf04dac8a..922c5e0cea4c 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -5,6 +5,7 @@
 #include <linux/module.h>
 #include <linux/percpu.h>
 #include <linux/string.h>
+#include <linux/ctype.h>
 #include <linux/delay.h>
 #include <linux/sched.h>
 #include <linux/init.h>
@@ -31,8 +32,7 @@
 #include <asm/setup.h>
 #include <asm/apic.h>
 #include <asm/desc.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
 #include <asm/mtrr.h>
 #include <linux/numa.h>
 #include <asm/asm.h>
@@ -145,32 +145,21 @@ DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = {
 } };
 EXPORT_PER_CPU_SYMBOL_GPL(gdt_page);
 
-static int __init x86_xsave_setup(char *s)
+static int __init x86_mpx_setup(char *s)
 {
+	/* require an exact match without trailing characters */
 	if (strlen(s))
 		return 0;
-	setup_clear_cpu_cap(X86_FEATURE_XSAVE);
-	setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
-	setup_clear_cpu_cap(X86_FEATURE_XSAVES);
-	setup_clear_cpu_cap(X86_FEATURE_AVX);
-	setup_clear_cpu_cap(X86_FEATURE_AVX2);
-	return 1;
-}
-__setup("noxsave", x86_xsave_setup);
 
-static int __init x86_xsaveopt_setup(char *s)
-{
-	setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
-	return 1;
-}
-__setup("noxsaveopt", x86_xsaveopt_setup);
+	/* do not emit a message if the feature is not present */
+	if (!boot_cpu_has(X86_FEATURE_MPX))
+		return 1;
 
-static int __init x86_xsaves_setup(char *s)
-{
-	setup_clear_cpu_cap(X86_FEATURE_XSAVES);
+	setup_clear_cpu_cap(X86_FEATURE_MPX);
+	pr_info("nompx: Intel Memory Protection Extensions (MPX) disabled\n");
 	return 1;
 }
-__setup("noxsaves", x86_xsaves_setup);
+__setup("nompx", x86_mpx_setup);
 
 #ifdef CONFIG_X86_32
 static int cachesize_override = -1;
@@ -183,14 +172,6 @@ static int __init cachesize_setup(char *str)
 }
 __setup("cachesize=", cachesize_setup);
 
-static int __init x86_fxsr_setup(char *s)
-{
-	setup_clear_cpu_cap(X86_FEATURE_FXSR);
-	setup_clear_cpu_cap(X86_FEATURE_XMM);
-	return 1;
-}
-__setup("nofxsr", x86_fxsr_setup);
-
 static int __init x86_sep_setup(char *s)
 {
 	setup_clear_cpu_cap(X86_FEATURE_SEP);
@@ -419,7 +400,7 @@ static const struct cpu_dev *cpu_devs[X86_VENDOR_NUM] = {};
 static void get_model_name(struct cpuinfo_x86 *c)
 {
 	unsigned int *v;
-	char *p, *q;
+	char *p, *q, *s;
 
 	if (c->extended_cpuid_level < 0x80000004)
 		return;
@@ -430,19 +411,21 @@ static void get_model_name(struct cpuinfo_x86 *c)
 	cpuid(0x80000004, &v[8], &v[9], &v[10], &v[11]);
 	c->x86_model_id[48] = 0;
 
-	/*
-	 * Intel chips right-justify this string for some dumb reason;
-	 * undo that brain damage:
-	 */
-	p = q = &c->x86_model_id[0];
+	/* Trim whitespace */
+	p = q = s = &c->x86_model_id[0];
+
 	while (*p == ' ')
 		p++;
-	if (p != q) {
-		while (*p)
-			*q++ = *p++;
-		while (q <= &c->x86_model_id[48])
-			*q++ = '\0';	/* Zero-pad the rest */
+
+	while (*p) {
+		/* Note the last non-whitespace index */
+		if (!isspace(*p))
+			s = q;
+
+		*q++ = *p++;
 	}
+
+	*(s + 1) = '\0';
 }
 
 void cpu_detect_cache_sizes(struct cpuinfo_x86 *c)
@@ -508,7 +491,7 @@ static void cpu_detect_tlb(struct cpuinfo_x86 *c)
 
 void detect_ht(struct cpuinfo_x86 *c)
 {
-#ifdef CONFIG_X86_HT
+#ifdef CONFIG_SMP
 	u32 eax, ebx, ecx, edx;
 	int index_msb, core_bits;
 	static bool printed;
@@ -759,7 +742,6 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 	cpu_detect(c);
 	get_cpu_vendor(c);
 	get_cpu_cap(c);
-	fpu_detect(c);
 
 	if (this_cpu->c_early_init)
 		this_cpu->c_early_init(c);
@@ -771,6 +753,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 		this_cpu->c_bsp_init(c);
 
 	setup_force_cpu_cap(X86_FEATURE_ALWAYS);
+	fpu__init_system(c);
 }
 
 void __init early_cpu_init(void)
@@ -844,7 +827,7 @@ static void generic_identify(struct cpuinfo_x86 *c)
 	if (c->cpuid_level >= 0x00000001) {
 		c->initial_apicid = (cpuid_ebx(1) >> 24) & 0xFF;
 #ifdef CONFIG_X86_32
-# ifdef CONFIG_X86_HT
+# ifdef CONFIG_SMP
 		c->apicid = apic->phys_pkg_id(c->initial_apicid, 0);
 # else
 		c->apicid = c->initial_apicid;
@@ -1026,7 +1009,7 @@ void enable_sep_cpu(void)
 	      (unsigned long)tss + offsetofend(struct tss_struct, SYSENTER_stack),
 	      0);
 
-	wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long)ia32_sysenter_target, 0);
+	wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long)entry_SYSENTER_32, 0);
 
 out:
 	put_cpu();
@@ -1122,7 +1105,7 @@ void print_cpu_info(struct cpuinfo_x86 *c)
 		printk(KERN_CONT "%s ", vendor);
 
 	if (c->x86_model_id[0])
-		printk(KERN_CONT "%s", strim(c->x86_model_id));
+		printk(KERN_CONT "%s", c->x86_model_id);
 	else
 		printk(KERN_CONT "%d86", c->x86);
 
@@ -1155,10 +1138,6 @@ static __init int setup_disablecpuid(char *arg)
 }
 __setup("clearcpuid=", setup_disablecpuid);
 
-DEFINE_PER_CPU(unsigned long, kernel_stack) =
-	(unsigned long)&init_thread_union + THREAD_SIZE;
-EXPORT_PER_CPU_SYMBOL(kernel_stack);
-
 #ifdef CONFIG_X86_64
 struct desc_ptr idt_descr = { NR_VECTORS * 16 - 1, (unsigned long) idt_table };
 struct desc_ptr debug_idt_descr = { NR_VECTORS * 16 - 1,
@@ -1183,8 +1162,6 @@ DEFINE_PER_CPU(unsigned int, irq_count) __visible = -1;
 DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT;
 EXPORT_PER_CPU_SYMBOL(__preempt_count);
 
-DEFINE_PER_CPU(struct task_struct *, fpu_owner_task);
-
 /*
  * Special IST stacks which the CPU switches to when it calls
  * an IST-marked descriptor entry. Up to 7 stacks (hardware
@@ -1208,10 +1185,10 @@ void syscall_init(void)
 	 * set CS/DS but only a 32bit target. LSTAR sets the 64bit rip.
 	 */
 	wrmsrl(MSR_STAR,  ((u64)__USER32_CS)<<48  | ((u64)__KERNEL_CS)<<32);
-	wrmsrl(MSR_LSTAR, system_call);
+	wrmsrl(MSR_LSTAR, entry_SYSCALL_64);
 
 #ifdef CONFIG_IA32_EMULATION
-	wrmsrl(MSR_CSTAR, ia32_cstar_target);
+	wrmsrl(MSR_CSTAR, entry_SYSCALL_compat);
 	/*
 	 * This only works on Intel CPUs.
 	 * On AMD CPUs these MSRs are 32-bit, CPU truncates MSR_IA32_SYSENTER_EIP.
@@ -1220,7 +1197,7 @@ void syscall_init(void)
 	 */
 	wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS);
 	wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL);
-	wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)ia32_sysenter_target);
+	wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat);
 #else
 	wrmsrl(MSR_CSTAR, ignore_sysret);
 	wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)GDT_ENTRY_INVALID_SEG);
@@ -1275,7 +1252,6 @@ DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task;
 EXPORT_PER_CPU_SYMBOL(current_task);
 DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT;
 EXPORT_PER_CPU_SYMBOL(__preempt_count);
-DEFINE_PER_CPU(struct task_struct *, fpu_owner_task);
 
 /*
  * On x86_32, vm86 modifies tss.sp0, so sp0 isn't a reliable way to find
@@ -1439,7 +1415,7 @@ void cpu_init(void)
 	clear_all_debug_regs();
 	dbg_restore_debug_regs();
 
-	fpu_init();
+	fpu__init_cpu();
 
 	if (is_uv_system())
 		uv_cpu_init();
@@ -1495,7 +1471,7 @@ void cpu_init(void)
 	clear_all_debug_regs();
 	dbg_restore_debug_regs();
 
-	fpu_init();
+	fpu__init_cpu();
 }
 #endif
 
diff --git a/arch/x86/kernel/cpu/hypervisor.c b/arch/x86/kernel/cpu/hypervisor.c
index 36ce402a3fa5..d820d8eae96b 100644
--- a/arch/x86/kernel/cpu/hypervisor.c
+++ b/arch/x86/kernel/cpu/hypervisor.c
@@ -27,8 +27,8 @@
 
 static const __initconst struct hypervisor_x86 * const hypervisors[] =
 {
-#ifdef CONFIG_XEN_PVHVM
-	&x86_hyper_xen_hvm,
+#ifdef CONFIG_XEN
+	&x86_hyper_xen,
 #endif
 	&x86_hyper_vmware,
 	&x86_hyper_ms_hyperv,
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index edcb0e28c336..be4febc58b94 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -654,7 +654,7 @@ unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c)
 	unsigned int new_l1d = 0, new_l1i = 0; /* Cache sizes from cpuid(4) */
 	unsigned int new_l2 = 0, new_l3 = 0, i; /* Cache sizes from cpuid(4) */
 	unsigned int l2_id = 0, l3_id = 0, num_threads_sharing, index_msb;
-#ifdef CONFIG_X86_HT
+#ifdef CONFIG_SMP
 	unsigned int cpu = c->cpu_index;
 #endif
 
@@ -773,19 +773,19 @@ unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c)
 
 	if (new_l2) {
 		l2 = new_l2;
-#ifdef CONFIG_X86_HT
+#ifdef CONFIG_SMP
 		per_cpu(cpu_llc_id, cpu) = l2_id;
 #endif
 	}
 
 	if (new_l3) {
 		l3 = new_l3;
-#ifdef CONFIG_X86_HT
+#ifdef CONFIG_SMP
 		per_cpu(cpu_llc_id, cpu) = l3_id;
 #endif
 	}
 
-#ifdef CONFIG_X86_HT
+#ifdef CONFIG_SMP
 	/*
 	 * If cpu_llc_id is not yet set, this means cpuid_level < 4 which in
 	 * turns means that the only possibility is SMT (as indicated in
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index e535533d5ab8..df919ff103c3 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -53,9 +53,12 @@
 static DEFINE_MUTEX(mce_chrdev_read_mutex);
 
 #define rcu_dereference_check_mce(p) \
-	rcu_dereference_index_check((p), \
-			      rcu_read_lock_sched_held() || \
-			      lockdep_is_held(&mce_chrdev_read_mutex))
+({ \
+	rcu_lockdep_assert(rcu_read_lock_sched_held() || \
+			   lockdep_is_held(&mce_chrdev_read_mutex), \
+			   "suspicious rcu_dereference_check_mce() usage"); \
+	smp_load_acquire(&(p)); \
+})
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/mce.h>
@@ -708,6 +711,7 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp,
 			  struct pt_regs *regs)
 {
 	int i, ret = 0;
+	char *tmp;
 
 	for (i = 0; i < mca_cfg.banks; i++) {
 		m->status = mce_rdmsrl(MSR_IA32_MCx_STATUS(i));
@@ -716,9 +720,11 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp,
 			if (quirk_no_way_out)
 				quirk_no_way_out(i, m, regs);
 		}
-		if (mce_severity(m, mca_cfg.tolerant, msg, true) >=
-		    MCE_PANIC_SEVERITY)
+
+		if (mce_severity(m, mca_cfg.tolerant, &tmp, true) >= MCE_PANIC_SEVERITY) {
+			*msg = tmp;
 			ret = 1;
+		}
 	}
 	return ret;
 }
@@ -1047,6 +1053,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 	char *msg = "Unknown";
 	u64 recover_paddr = ~0ull;
 	int flags = MF_ACTION_REQUIRED;
+	int lmce = 0;
 
 	prev_state = ist_enter(regs);
 
@@ -1074,11 +1081,20 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 		kill_it = 1;
 
 	/*
-	 * Go through all the banks in exclusion of the other CPUs.
-	 * This way we don't report duplicated events on shared banks
-	 * because the first one to see it will clear it.
+	 * Check if this MCE is signaled to only this logical processor
 	 */
-	order = mce_start(&no_way_out);
+	if (m.mcgstatus & MCG_STATUS_LMCES)
+		lmce = 1;
+	else {
+		/*
+		 * Go through all the banks in exclusion of the other CPUs.
+		 * This way we don't report duplicated events on shared banks
+		 * because the first one to see it will clear it.
+		 * If this is a Local MCE, then no need to perform rendezvous.
+		 */
+		order = mce_start(&no_way_out);
+	}
+
 	for (i = 0; i < cfg->banks; i++) {
 		__clear_bit(i, toclear);
 		if (!test_bit(i, valid_banks))
@@ -1155,8 +1171,18 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 	 * Do most of the synchronization with other CPUs.
 	 * When there's any problem use only local no_way_out state.
 	 */
-	if (mce_end(order) < 0)
-		no_way_out = worst >= MCE_PANIC_SEVERITY;
+	if (!lmce) {
+		if (mce_end(order) < 0)
+			no_way_out = worst >= MCE_PANIC_SEVERITY;
+	} else {
+		/*
+		 * Local MCE skipped calling mce_reign()
+		 * If we found a fatal error, we need to panic here.
+		 */
+		 if (worst >= MCE_PANIC_SEVERITY && mca_cfg.tolerant < 3)
+			mce_panic("Machine check from unknown source",
+				NULL, NULL);
+	}
 
 	/*
 	 * At insane "tolerant" levels we take no action. Otherwise
@@ -1637,10 +1663,16 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
 		mce_intel_feature_init(c);
 		mce_adjust_timer = cmci_intel_adjust_timer;
 		break;
-	case X86_VENDOR_AMD:
+
+	case X86_VENDOR_AMD: {
+		u32 ebx = cpuid_ebx(0x80000007);
+
 		mce_amd_feature_init(c);
-		mce_flags.overflow_recov = cpuid_ebx(0x80000007) & 0x1;
+		mce_flags.overflow_recov = !!(ebx & BIT(0));
+		mce_flags.succor	 = !!(ebx & BIT(1));
 		break;
+		}
+
 	default:
 		break;
 	}
@@ -1884,7 +1916,7 @@ out:
 static unsigned int mce_chrdev_poll(struct file *file, poll_table *wait)
 {
 	poll_wait(file, &mce_chrdev_wait, wait);
-	if (rcu_access_index(mcelog.next))
+	if (READ_ONCE(mcelog.next))
 		return POLLIN | POLLRDNORM;
 	if (!mce_apei_read_done && apei_check_mce())
 		return POLLIN | POLLRDNORM;
@@ -1929,8 +1961,8 @@ void register_mce_write_callback(ssize_t (*fn)(struct file *filp,
 }
 EXPORT_SYMBOL_GPL(register_mce_write_callback);
 
-ssize_t mce_chrdev_write(struct file *filp, const char __user *ubuf,
-			 size_t usize, loff_t *off)
+static ssize_t mce_chrdev_write(struct file *filp, const char __user *ubuf,
+				size_t usize, loff_t *off)
 {
 	if (mce_write)
 		return mce_write(filp, ubuf, usize, off);
@@ -1976,6 +2008,7 @@ void mce_disable_bank(int bank)
 /*
  * mce=off Disables machine check
  * mce=no_cmci Disables CMCI
+ * mce=no_lmce Disables LMCE
  * mce=dont_log_ce Clears corrected events silently, no log created for CEs.
  * mce=ignore_ce Disables polling and CMCI, corrected events are not cleared.
  * mce=TOLERANCELEVEL[,monarchtimeout] (number, see above)
@@ -1999,6 +2032,8 @@ static int __init mcheck_enable(char *str)
 		cfg->disabled = true;
 	else if (!strcmp(str, "no_cmci"))
 		cfg->cmci_disabled = true;
+	else if (!strcmp(str, "no_lmce"))
+		cfg->lmce_disabled = true;
 	else if (!strcmp(str, "dont_log_ce"))
 		cfg->dont_log_ce = true;
 	else if (!strcmp(str, "ignore_ce"))
@@ -2008,11 +2043,8 @@ static int __init mcheck_enable(char *str)
 	else if (!strcmp(str, "bios_cmci_threshold"))
 		cfg->bios_cmci_threshold = true;
 	else if (isdigit(str[0])) {
-		get_option(&str, &(cfg->tolerant));
-		if (*str == ',') {
-			++str;
+		if (get_option(&str, &cfg->tolerant) == 2)
 			get_option(&str, &(cfg->monarch_timeout));
-		}
 	} else {
 		pr_info("mce argument %s ignored. Please use /sys\n", str);
 		return 0;
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 55ad9b37cae8..e99b15077e94 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -1,19 +1,13 @@
 /*
- *  (c) 2005-2012 Advanced Micro Devices, Inc.
+ *  (c) 2005-2015 Advanced Micro Devices, Inc.
  *  Your use of this code is subject to the terms and conditions of the
  *  GNU general public license version 2. See "COPYING" or
  *  http://www.gnu.org/licenses/gpl.html
  *
  *  Written by Jacob Shin - AMD, Inc.
- *
  *  Maintained by: Borislav Petkov <bp@alien8.de>
  *
- *  April 2006
- *     - added support for AMD Family 0x10 processors
- *  May 2012
- *     - major scrubbing
- *
- *  All MC4_MISCi registers are shared between multi-cores
+ *  All MC4_MISCi registers are shared between cores on a node.
  */
 #include <linux/interrupt.h>
 #include <linux/notifier.h>
@@ -32,6 +26,7 @@
 #include <asm/idle.h>
 #include <asm/mce.h>
 #include <asm/msr.h>
+#include <asm/trace/irq_vectors.h>
 
 #define NR_BLOCKS         9
 #define THRESHOLD_MAX     0xFFF
@@ -47,6 +42,13 @@
 #define MASK_BLKPTR_LO    0xFF000000
 #define MCG_XBLK_ADDR     0xC0000400
 
+/* Deferred error settings */
+#define MSR_CU_DEF_ERR		0xC0000410
+#define MASK_DEF_LVTOFF		0x000000F0
+#define MASK_DEF_INT_TYPE	0x00000006
+#define DEF_LVT_OFF		0x2
+#define DEF_INT_TYPE_APIC	0x2
+
 static const char * const th_names[] = {
 	"load_store",
 	"insn_fetch",
@@ -60,6 +62,13 @@ static DEFINE_PER_CPU(struct threshold_bank **, threshold_banks);
 static DEFINE_PER_CPU(unsigned char, bank_map);	/* see which banks are on */
 
 static void amd_threshold_interrupt(void);
+static void amd_deferred_error_interrupt(void);
+
+static void default_deferred_error_interrupt(void)
+{
+	pr_err("Unexpected deferred interrupt at vector %x\n", DEFERRED_ERROR_VECTOR);
+}
+void (*deferred_error_int_vector)(void) = default_deferred_error_interrupt;
 
 /*
  * CPU Initialization
@@ -196,7 +205,7 @@ static void mce_threshold_block_init(struct threshold_block *b, int offset)
 	threshold_restart_bank(&tr);
 };
 
-static int setup_APIC_mce(int reserved, int new)
+static int setup_APIC_mce_threshold(int reserved, int new)
 {
 	if (reserved < 0 && !setup_APIC_eilvt(new, THRESHOLD_APIC_VECTOR,
 					      APIC_EILVT_MSG_FIX, 0))
@@ -205,6 +214,39 @@ static int setup_APIC_mce(int reserved, int new)
 	return reserved;
 }
 
+static int setup_APIC_deferred_error(int reserved, int new)
+{
+	if (reserved < 0 && !setup_APIC_eilvt(new, DEFERRED_ERROR_VECTOR,
+					      APIC_EILVT_MSG_FIX, 0))
+		return new;
+
+	return reserved;
+}
+
+static void deferred_error_interrupt_enable(struct cpuinfo_x86 *c)
+{
+	u32 low = 0, high = 0;
+	int def_offset = -1, def_new;
+
+	if (rdmsr_safe(MSR_CU_DEF_ERR, &low, &high))
+		return;
+
+	def_new = (low & MASK_DEF_LVTOFF) >> 4;
+	if (!(low & MASK_DEF_LVTOFF)) {
+		pr_err(FW_BUG "Your BIOS is not setting up LVT offset 0x2 for deferred error IRQs correctly.\n");
+		def_new = DEF_LVT_OFF;
+		low = (low & ~MASK_DEF_LVTOFF) | (DEF_LVT_OFF << 4);
+	}
+
+	def_offset = setup_APIC_deferred_error(def_offset, def_new);
+	if ((def_offset == def_new) &&
+	    (deferred_error_int_vector != amd_deferred_error_interrupt))
+		deferred_error_int_vector = amd_deferred_error_interrupt;
+
+	low = (low & ~MASK_DEF_INT_TYPE) | DEF_INT_TYPE_APIC;
+	wrmsr(MSR_CU_DEF_ERR, low, high);
+}
+
 /* cpu init entry point, called from mce.c with preempt off */
 void mce_amd_feature_init(struct cpuinfo_x86 *c)
 {
@@ -252,7 +294,7 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
 
 			b.interrupt_enable = 1;
 			new	= (high & MASK_LVTOFF_HI) >> 20;
-			offset  = setup_APIC_mce(offset, new);
+			offset  = setup_APIC_mce_threshold(offset, new);
 
 			if ((offset == new) &&
 			    (mce_threshold_vector != amd_threshold_interrupt))
@@ -262,6 +304,73 @@ init:
 			mce_threshold_block_init(&b, offset);
 		}
 	}
+
+	if (mce_flags.succor)
+		deferred_error_interrupt_enable(c);
+}
+
+static void __log_error(unsigned int bank, bool threshold_err, u64 misc)
+{
+	struct mce m;
+	u64 status;
+
+	rdmsrl(MSR_IA32_MCx_STATUS(bank), status);
+	if (!(status & MCI_STATUS_VAL))
+		return;
+
+	mce_setup(&m);
+
+	m.status = status;
+	m.bank = bank;
+
+	if (threshold_err)
+		m.misc = misc;
+
+	if (m.status & MCI_STATUS_ADDRV)
+		rdmsrl(MSR_IA32_MCx_ADDR(bank), m.addr);
+
+	mce_log(&m);
+	wrmsrl(MSR_IA32_MCx_STATUS(bank), 0);
+}
+
+static inline void __smp_deferred_error_interrupt(void)
+{
+	inc_irq_stat(irq_deferred_error_count);
+	deferred_error_int_vector();
+}
+
+asmlinkage __visible void smp_deferred_error_interrupt(void)
+{
+	entering_irq();
+	__smp_deferred_error_interrupt();
+	exiting_ack_irq();
+}
+
+asmlinkage __visible void smp_trace_deferred_error_interrupt(void)
+{
+	entering_irq();
+	trace_deferred_error_apic_entry(DEFERRED_ERROR_VECTOR);
+	__smp_deferred_error_interrupt();
+	trace_deferred_error_apic_exit(DEFERRED_ERROR_VECTOR);
+	exiting_ack_irq();
+}
+
+/* APIC interrupt handler for deferred errors */
+static void amd_deferred_error_interrupt(void)
+{
+	u64 status;
+	unsigned int bank;
+
+	for (bank = 0; bank < mca_cfg.banks; ++bank) {
+		rdmsrl(MSR_IA32_MCx_STATUS(bank), status);
+
+		if (!(status & MCI_STATUS_VAL) ||
+		    !(status & MCI_STATUS_DEFERRED))
+			continue;
+
+		__log_error(bank, false, 0);
+		break;
+	}
 }
 
 /*
@@ -273,12 +382,12 @@ init:
  * the interrupt goes off when error_count reaches threshold_limit.
  * the handler will simply log mcelog w/ software defined bank number.
  */
+
 static void amd_threshold_interrupt(void)
 {
 	u32 low = 0, high = 0, address = 0;
 	int cpu = smp_processor_id();
 	unsigned int bank, block;
-	struct mce m;
 
 	/* assume first bank caused it */
 	for (bank = 0; bank < mca_cfg.banks; ++bank) {
@@ -321,15 +430,7 @@ static void amd_threshold_interrupt(void)
 	return;
 
 log:
-	mce_setup(&m);
-	rdmsrl(MSR_IA32_MCx_STATUS(bank), m.status);
-	if (!(m.status & MCI_STATUS_VAL))
-		return;
-	m.misc = ((u64)high << 32) | low;
-	m.bank = bank;
-	mce_log(&m);
-
-	wrmsrl(MSR_IA32_MCx_STATUS(bank), 0);
+	__log_error(bank, true, ((u64)high << 32) | low);
 }
 
 /*
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index b4a41cf030ed..844f56c5616d 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -91,6 +91,36 @@ static int cmci_supported(int *banks)
 	return !!(cap & MCG_CMCI_P);
 }
 
+static bool lmce_supported(void)
+{
+	u64 tmp;
+
+	if (mca_cfg.lmce_disabled)
+		return false;
+
+	rdmsrl(MSR_IA32_MCG_CAP, tmp);
+
+	/*
+	 * LMCE depends on recovery support in the processor. Hence both
+	 * MCG_SER_P and MCG_LMCE_P should be present in MCG_CAP.
+	 */
+	if ((tmp & (MCG_SER_P | MCG_LMCE_P)) !=
+		   (MCG_SER_P | MCG_LMCE_P))
+		return false;
+
+	/*
+	 * BIOS should indicate support for LMCE by setting bit 20 in
+	 * IA32_FEATURE_CONTROL without which touching MCG_EXT_CTL will
+	 * generate a #GP fault.
+	 */
+	rdmsrl(MSR_IA32_FEATURE_CONTROL, tmp);
+	if ((tmp & (FEATURE_CONTROL_LOCKED | FEATURE_CONTROL_LMCE)) ==
+		   (FEATURE_CONTROL_LOCKED | FEATURE_CONTROL_LMCE))
+		return true;
+
+	return false;
+}
+
 bool mce_intel_cmci_poll(void)
 {
 	if (__this_cpu_read(cmci_storm_state) == CMCI_STORM_NONE)
@@ -405,8 +435,22 @@ static void intel_init_cmci(void)
 	cmci_recheck();
 }
 
+void intel_init_lmce(void)
+{
+	u64 val;
+
+	if (!lmce_supported())
+		return;
+
+	rdmsrl(MSR_IA32_MCG_EXT_CTL, val);
+
+	if (!(val & MCG_EXT_CTL_LMCE_EN))
+		wrmsrl(MSR_IA32_MCG_EXT_CTL, val | MCG_EXT_CTL_LMCE_EN);
+}
+
 void mce_intel_feature_init(struct cpuinfo_x86 *c)
 {
 	intel_init_thermal(c);
 	intel_init_cmci();
+	intel_init_lmce();
 }
diff --git a/arch/x86/kernel/cpu/microcode/amd_early.c b/arch/x86/kernel/cpu/microcode/amd_early.c
index 737737edbd1e..e8a215a9a345 100644
--- a/arch/x86/kernel/cpu/microcode/amd_early.c
+++ b/arch/x86/kernel/cpu/microcode/amd_early.c
@@ -228,7 +228,23 @@ static void apply_ucode_in_initrd(void *ucode, size_t size, bool save_patch)
 	}
 }
 
-void __init load_ucode_amd_bsp(void)
+static bool __init load_builtin_amd_microcode(struct cpio_data *cp,
+					      unsigned int family)
+{
+#ifdef CONFIG_X86_64
+	char fw_name[36] = "amd-ucode/microcode_amd.bin";
+
+	if (family >= 0x15)
+		snprintf(fw_name, sizeof(fw_name),
+			 "amd-ucode/microcode_amd_fam%.2xh.bin", family);
+
+	return get_builtin_firmware(cp, fw_name);
+#else
+	return false;
+#endif
+}
+
+void __init load_ucode_amd_bsp(unsigned int family)
 {
 	struct cpio_data cp;
 	void **data;
@@ -243,8 +259,10 @@ void __init load_ucode_amd_bsp(void)
 #endif
 
 	cp = find_ucode_in_initrd();
-	if (!cp.data)
-		return;
+	if (!cp.data) {
+		if (!load_builtin_amd_microcode(&cp, family))
+			return;
+	}
 
 	*data = cp.data;
 	*size = cp.size;
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 36a83617eb21..6236a54a63f4 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -1,74 +1,16 @@
 /*
- *	Intel CPU Microcode Update Driver for Linux
+ * CPU Microcode Update Driver for Linux
  *
- *	Copyright (C) 2000-2006 Tigran Aivazian <tigran@aivazian.fsnet.co.uk>
- *		      2006	Shaohua Li <shaohua.li@intel.com>
+ * Copyright (C) 2000-2006 Tigran Aivazian <tigran@aivazian.fsnet.co.uk>
+ *	      2006	Shaohua Li <shaohua.li@intel.com>
+ *	      2013-2015	Borislav Petkov <bp@alien8.de>
  *
- *	This driver allows to upgrade microcode on Intel processors
- *	belonging to IA-32 family - PentiumPro, Pentium II,
- *	Pentium III, Xeon, Pentium 4, etc.
+ * This driver allows to upgrade microcode on x86 processors.
  *
- *	Reference: Section 8.11 of Volume 3a, IA-32 Intel? Architecture
- *	Software Developer's Manual
- *	Order Number 253668 or free download from:
- *
- *	http://developer.intel.com/Assets/PDF/manual/253668.pdf	
- *
- *	For more information, go to http://www.urbanmyth.org/microcode
- *
- *	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; either version
- *	2 of the License, or (at your option) any later version.
- *
- *	1.0	16 Feb 2000, Tigran Aivazian <tigran@sco.com>
- *		Initial release.
- *	1.01	18 Feb 2000, Tigran Aivazian <tigran@sco.com>
- *		Added read() support + cleanups.
- *	1.02	21 Feb 2000, Tigran Aivazian <tigran@sco.com>
- *		Added 'device trimming' support. open(O_WRONLY) zeroes
- *		and frees the saved copy of applied microcode.
- *	1.03	29 Feb 2000, Tigran Aivazian <tigran@sco.com>
- *		Made to use devfs (/dev/cpu/microcode) + cleanups.
- *	1.04	06 Jun 2000, Simon Trimmer <simon@veritas.com>
- *		Added misc device support (now uses both devfs and misc).
- *		Added MICROCODE_IOCFREE ioctl to clear memory.
- *	1.05	09 Jun 2000, Simon Trimmer <simon@veritas.com>
- *		Messages for error cases (non Intel & no suitable microcode).
- *	1.06	03 Aug 2000, Tigran Aivazian <tigran@veritas.com>
- *		Removed ->release(). Removed exclusive open and status bitmap.
- *		Added microcode_rwsem to serialize read()/write()/ioctl().
- *		Removed global kernel lock usage.
- *	1.07	07 Sep 2000, Tigran Aivazian <tigran@veritas.com>
- *		Write 0 to 0x8B msr and then cpuid before reading revision,
- *		so that it works even if there were no update done by the
- *		BIOS. Otherwise, reading from 0x8B gives junk (which happened
- *		to be 0 on my machine which is why it worked even when I
- *		disabled update by the BIOS)
- *		Thanks to Eric W. Biederman <ebiederman@lnxi.com> for the fix.
- *	1.08	11 Dec 2000, Richard Schaal <richard.schaal@intel.com> and
- *			     Tigran Aivazian <tigran@veritas.com>
- *		Intel Pentium 4 processor support and bugfixes.
- *	1.09	30 Oct 2001, Tigran Aivazian <tigran@veritas.com>
- *		Bugfix for HT (Hyper-Threading) enabled processors
- *		whereby processor resources are shared by all logical processors
- *		in a single CPU package.
- *	1.10	28 Feb 2002 Asit K Mallick <asit.k.mallick@intel.com> and
- *		Tigran Aivazian <tigran@veritas.com>,
- *		Serialize updates as required on HT processors due to
- *		speculative nature of implementation.
- *	1.11	22 Mar 2002 Tigran Aivazian <tigran@veritas.com>
- *		Fix the panic when writing zero-length microcode chunk.
- *	1.12	29 Sep 2003 Nitin Kamble <nitin.a.kamble@intel.com>,
- *		Jun Nakajima <jun.nakajima@intel.com>
- *		Support for the microcode updates in the new format.
- *	1.13	10 Oct 2003 Tigran Aivazian <tigran@veritas.com>
- *		Removed ->read() method and obsoleted MICROCODE_IOCFREE ioctl
- *		because we no longer hold a copy of applied microcode
- *		in kernel memory.
- *	1.14	25 Jun 2004 Tigran Aivazian <tigran@veritas.com>
- *		Fix sigmatch() macro to handle old CPUs with pf == 0.
- *		Thanks to Stuart Swales for pointing out this bug.
+ * 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; either version
+ * 2 of the License, or (at your option) any later version.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
diff --git a/arch/x86/kernel/cpu/microcode/core_early.c b/arch/x86/kernel/cpu/microcode/core_early.c
index a413a69cbd74..8ebc421d6299 100644
--- a/arch/x86/kernel/cpu/microcode/core_early.c
+++ b/arch/x86/kernel/cpu/microcode/core_early.c
@@ -3,6 +3,7 @@
  *
  *	Copyright (C) 2012 Fenghua Yu <fenghua.yu@intel.com>
  *			   H Peter Anvin" <hpa@zytor.com>
+ *		  (C) 2015 Borislav Petkov <bp@alien8.de>
  *
  *	This driver allows to early upgrade microcode on Intel processors
  *	belonging to IA-32 family - PentiumPro, Pentium II,
@@ -17,6 +18,7 @@
  *	2 of the License, or (at your option) any later version.
  */
 #include <linux/module.h>
+#include <linux/firmware.h>
 #include <asm/microcode.h>
 #include <asm/microcode_intel.h>
 #include <asm/microcode_amd.h>
@@ -43,9 +45,29 @@ static bool __init check_loader_disabled_bsp(void)
 	return *res;
 }
 
+extern struct builtin_fw __start_builtin_fw[];
+extern struct builtin_fw __end_builtin_fw[];
+
+bool get_builtin_firmware(struct cpio_data *cd, const char *name)
+{
+#ifdef CONFIG_FW_LOADER
+	struct builtin_fw *b_fw;
+
+	for (b_fw = __start_builtin_fw; b_fw != __end_builtin_fw; b_fw++) {
+		if (!strcmp(name, b_fw->name)) {
+			cd->size = b_fw->size;
+			cd->data = b_fw->data;
+			return true;
+		}
+	}
+#endif
+	return false;
+}
+
 void __init load_ucode_bsp(void)
 {
-	int vendor, family;
+	int vendor;
+	unsigned int family;
 
 	if (check_loader_disabled_bsp())
 		return;
@@ -63,7 +85,7 @@ void __init load_ucode_bsp(void)
 		break;
 	case X86_VENDOR_AMD:
 		if (family >= 0x10)
-			load_ucode_amd_bsp();
+			load_ucode_amd_bsp(family);
 		break;
 	default:
 		break;
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index a41beadb3db9..969dc17eb1b4 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -1,74 +1,13 @@
 /*
- *	Intel CPU Microcode Update Driver for Linux
+ * Intel CPU Microcode Update Driver for Linux
  *
- *	Copyright (C) 2000-2006 Tigran Aivazian <tigran@aivazian.fsnet.co.uk>
- *		      2006	Shaohua Li <shaohua.li@intel.com>
+ * Copyright (C) 2000-2006 Tigran Aivazian <tigran@aivazian.fsnet.co.uk>
+ *		 2006 Shaohua Li <shaohua.li@intel.com>
  *
- *	This driver allows to upgrade microcode on Intel processors
- *	belonging to IA-32 family - PentiumPro, Pentium II,
- *	Pentium III, Xeon, Pentium 4, etc.
- *
- *	Reference: Section 8.11 of Volume 3a, IA-32 Intel? Architecture
- *	Software Developer's Manual
- *	Order Number 253668 or free download from:
- *
- *	http://developer.intel.com/Assets/PDF/manual/253668.pdf	
- *
- *	For more information, go to http://www.urbanmyth.org/microcode
- *
- *	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; either version
- *	2 of the License, or (at your option) any later version.
- *
- *	1.0	16 Feb 2000, Tigran Aivazian <tigran@sco.com>
- *		Initial release.
- *	1.01	18 Feb 2000, Tigran Aivazian <tigran@sco.com>
- *		Added read() support + cleanups.
- *	1.02	21 Feb 2000, Tigran Aivazian <tigran@sco.com>
- *		Added 'device trimming' support. open(O_WRONLY) zeroes
- *		and frees the saved copy of applied microcode.
- *	1.03	29 Feb 2000, Tigran Aivazian <tigran@sco.com>
- *		Made to use devfs (/dev/cpu/microcode) + cleanups.
- *	1.04	06 Jun 2000, Simon Trimmer <simon@veritas.com>
- *		Added misc device support (now uses both devfs and misc).
- *		Added MICROCODE_IOCFREE ioctl to clear memory.
- *	1.05	09 Jun 2000, Simon Trimmer <simon@veritas.com>
- *		Messages for error cases (non Intel & no suitable microcode).
- *	1.06	03 Aug 2000, Tigran Aivazian <tigran@veritas.com>
- *		Removed ->release(). Removed exclusive open and status bitmap.
- *		Added microcode_rwsem to serialize read()/write()/ioctl().
- *		Removed global kernel lock usage.
- *	1.07	07 Sep 2000, Tigran Aivazian <tigran@veritas.com>
- *		Write 0 to 0x8B msr and then cpuid before reading revision,
- *		so that it works even if there were no update done by the
- *		BIOS. Otherwise, reading from 0x8B gives junk (which happened
- *		to be 0 on my machine which is why it worked even when I
- *		disabled update by the BIOS)
- *		Thanks to Eric W. Biederman <ebiederman@lnxi.com> for the fix.
- *	1.08	11 Dec 2000, Richard Schaal <richard.schaal@intel.com> and
- *			     Tigran Aivazian <tigran@veritas.com>
- *		Intel Pentium 4 processor support and bugfixes.
- *	1.09	30 Oct 2001, Tigran Aivazian <tigran@veritas.com>
- *		Bugfix for HT (Hyper-Threading) enabled processors
- *		whereby processor resources are shared by all logical processors
- *		in a single CPU package.
- *	1.10	28 Feb 2002 Asit K Mallick <asit.k.mallick@intel.com> and
- *		Tigran Aivazian <tigran@veritas.com>,
- *		Serialize updates as required on HT processors due to
- *		speculative nature of implementation.
- *	1.11	22 Mar 2002 Tigran Aivazian <tigran@veritas.com>
- *		Fix the panic when writing zero-length microcode chunk.
- *	1.12	29 Sep 2003 Nitin Kamble <nitin.a.kamble@intel.com>,
- *		Jun Nakajima <jun.nakajima@intel.com>
- *		Support for the microcode updates in the new format.
- *	1.13	10 Oct 2003 Tigran Aivazian <tigran@veritas.com>
- *		Removed ->read() method and obsoleted MICROCODE_IOCFREE ioctl
- *		because we no longer hold a copy of applied microcode
- *		in kernel memory.
- *	1.14	25 Jun 2004 Tigran Aivazian <tigran@veritas.com>
- *		Fix sigmatch() macro to handle old CPUs with pf == 0.
- *		Thanks to Stuart Swales for pointing out this bug.
+ * 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; either version
+ * 2 of the License, or (at your option) any later version.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -124,7 +63,7 @@ static int get_matching_mc(struct microcode_intel *mc_intel, int cpu)
 	cpf = cpu_sig.pf;
 	crev = cpu_sig.rev;
 
-	return get_matching_microcode(csig, cpf, crev, mc_intel);
+	return has_newer_microcode(mc_intel, csig, cpf, crev);
 }
 
 static int apply_microcode_intel(int cpu)
@@ -226,7 +165,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
 
 		csig = uci->cpu_sig.sig;
 		cpf = uci->cpu_sig.pf;
-		if (get_matching_microcode(csig, cpf, new_rev, mc)) {
+		if (has_newer_microcode(mc, csig, cpf, new_rev)) {
 			vfree(new_mc);
 			new_rev = mc_header.rev;
 			new_mc  = mc;
diff --git a/arch/x86/kernel/cpu/microcode/intel_early.c b/arch/x86/kernel/cpu/microcode/intel_early.c
index 2f49ab4ac0ae..8187b7247d1c 100644
--- a/arch/x86/kernel/cpu/microcode/intel_early.c
+++ b/arch/x86/kernel/cpu/microcode/intel_early.c
@@ -59,10 +59,10 @@ load_microcode_early(struct microcode_intel **saved,
 		ucode_ptr = saved[i];
 		mc_hdr	  = (struct microcode_header_intel *)ucode_ptr;
 
-		ret = get_matching_microcode(uci->cpu_sig.sig,
-					     uci->cpu_sig.pf,
-					     new_rev,
-					     ucode_ptr);
+		ret = has_newer_microcode(ucode_ptr,
+					  uci->cpu_sig.sig,
+					  uci->cpu_sig.pf,
+					  new_rev);
 		if (!ret)
 			continue;
 
@@ -246,7 +246,7 @@ static unsigned int _save_mc(struct microcode_intel **mc_saved,
 			     u8 *ucode_ptr, unsigned int num_saved)
 {
 	struct microcode_header_intel *mc_hdr, *mc_saved_hdr;
-	unsigned int sig, pf, new_rev;
+	unsigned int sig, pf;
 	int found = 0, i;
 
 	mc_hdr = (struct microcode_header_intel *)ucode_ptr;
@@ -255,14 +255,13 @@ static unsigned int _save_mc(struct microcode_intel **mc_saved,
 		mc_saved_hdr = (struct microcode_header_intel *)mc_saved[i];
 		sig	     = mc_saved_hdr->sig;
 		pf	     = mc_saved_hdr->pf;
-		new_rev	     = mc_hdr->rev;
 
-		if (!get_matching_sig(sig, pf, new_rev, ucode_ptr))
+		if (!find_matching_signature(ucode_ptr, sig, pf))
 			continue;
 
 		found = 1;
 
-		if (!revision_is_newer(mc_hdr, new_rev))
+		if (mc_hdr->rev <= mc_saved_hdr->rev)
 			continue;
 
 		/*
@@ -522,6 +521,27 @@ out:
 EXPORT_SYMBOL_GPL(save_mc_for_early);
 #endif
 
+static bool __init load_builtin_intel_microcode(struct cpio_data *cp)
+{
+#ifdef CONFIG_X86_64
+	unsigned int eax = 0x00000001, ebx, ecx = 0, edx;
+	unsigned int family, model, stepping;
+	char name[30];
+
+	native_cpuid(&eax, &ebx, &ecx, &edx);
+
+	family   = __x86_family(eax);
+	model    = x86_model(eax);
+	stepping = eax & 0xf;
+
+	sprintf(name, "intel-ucode/%02x-%02x-%02x", family, model, stepping);
+
+	return get_builtin_firmware(cp, name);
+#else
+	return false;
+#endif
+}
+
 static __initdata char ucode_name[] = "kernel/x86/microcode/GenuineIntel.bin";
 static __init enum ucode_state
 scan_microcode(struct mc_saved_data *mc_saved_data, unsigned long *initrd,
@@ -540,8 +560,10 @@ scan_microcode(struct mc_saved_data *mc_saved_data, unsigned long *initrd,
 	cd.size = 0;
 
 	cd = find_cpio_data(p, (void *)start, size, &offset);
-	if (!cd.data)
-		return UCODE_ERROR;
+	if (!cd.data) {
+		if (!load_builtin_intel_microcode(&cd))
+			return UCODE_ERROR;
+	}
 
 	return get_matching_model_microcode(0, start, cd.data, cd.size,
 					    mc_saved_data, initrd, uci);
diff --git a/arch/x86/kernel/cpu/microcode/intel_lib.c b/arch/x86/kernel/cpu/microcode/intel_lib.c
index cd47a510a3f1..1883d252ff7d 100644
--- a/arch/x86/kernel/cpu/microcode/intel_lib.c
+++ b/arch/x86/kernel/cpu/microcode/intel_lib.c
@@ -31,11 +31,18 @@
 #include <asm/processor.h>
 #include <asm/msr.h>
 
-static inline int
-update_match_cpu(unsigned int csig, unsigned int cpf,
-		 unsigned int sig, unsigned int pf)
+static inline bool cpu_signatures_match(unsigned int s1, unsigned int p1,
+					unsigned int s2, unsigned int p2)
 {
-	return (!sigmatch(sig, csig, pf, cpf)) ? 0 : 1;
+	if (s1 != s2)
+		return false;
+
+	/* Processor flags are either both 0 ... */
+	if (!p1 && !p2)
+		return true;
+
+	/* ... or they intersect. */
+	return p1 & p2;
 }
 
 int microcode_sanity_check(void *mc, int print_err)
@@ -124,27 +131,25 @@ EXPORT_SYMBOL_GPL(microcode_sanity_check);
 /*
  * Returns 1 if update has been found, 0 otherwise.
  */
-int get_matching_sig(unsigned int csig, int cpf, int rev, void *mc)
+int find_matching_signature(void *mc, unsigned int csig, int cpf)
 {
-	struct microcode_header_intel *mc_header = mc;
-	struct extended_sigtable *ext_header;
-	unsigned long total_size = get_totalsize(mc_header);
-	int ext_sigcount, i;
+	struct microcode_header_intel *mc_hdr = mc;
+	struct extended_sigtable *ext_hdr;
 	struct extended_signature *ext_sig;
+	int i;
 
-	if (update_match_cpu(csig, cpf, mc_header->sig, mc_header->pf))
+	if (cpu_signatures_match(csig, cpf, mc_hdr->sig, mc_hdr->pf))
 		return 1;
 
 	/* Look for ext. headers: */
-	if (total_size <= get_datasize(mc_header) + MC_HEADER_SIZE)
+	if (get_totalsize(mc_hdr) <= get_datasize(mc_hdr) + MC_HEADER_SIZE)
 		return 0;
 
-	ext_header = mc + get_datasize(mc_header) + MC_HEADER_SIZE;
-	ext_sigcount = ext_header->count;
-	ext_sig = (void *)ext_header + EXT_HEADER_SIZE;
+	ext_hdr = mc + get_datasize(mc_hdr) + MC_HEADER_SIZE;
+	ext_sig = (void *)ext_hdr + EXT_HEADER_SIZE;
 
-	for (i = 0; i < ext_sigcount; i++) {
-		if (update_match_cpu(csig, cpf, ext_sig->sig, ext_sig->pf))
+	for (i = 0; i < ext_hdr->count; i++) {
+		if (cpu_signatures_match(csig, cpf, ext_sig->sig, ext_sig->pf))
 			return 1;
 		ext_sig++;
 	}
@@ -154,13 +159,13 @@ int get_matching_sig(unsigned int csig, int cpf, int rev, void *mc)
 /*
  * Returns 1 if update has been found, 0 otherwise.
  */
-int get_matching_microcode(unsigned int csig, int cpf, int rev, void *mc)
+int has_newer_microcode(void *mc, unsigned int csig, int cpf, int new_rev)
 {
 	struct microcode_header_intel *mc_hdr = mc;
 
-	if (!revision_is_newer(mc_hdr, rev))
+	if (mc_hdr->rev <= new_rev)
 		return 0;
 
-	return get_matching_sig(csig, cpf, rev, mc);
+	return find_matching_signature(mc, csig, cpf);
 }
-EXPORT_SYMBOL_GPL(get_matching_microcode);
+EXPORT_SYMBOL_GPL(has_newer_microcode);
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 939155ffdece..aad4bd84b475 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -39,14 +39,12 @@ void hyperv_vector_handler(struct pt_regs *regs)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
 
-	irq_enter();
-	exit_idle();
-
+	entering_irq();
 	inc_irq_stat(irq_hv_callback_count);
 	if (vmbus_handler)
 		vmbus_handler();
 
-	irq_exit();
+	exiting_irq();
 	set_irq_regs(old_regs);
 }
 
diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c
index 5f90b85ff22e..70d7c93f4550 100644
--- a/arch/x86/kernel/cpu/mtrr/cleanup.c
+++ b/arch/x86/kernel/cpu/mtrr/cleanup.c
@@ -98,7 +98,8 @@ x86_get_mtrr_mem_range(struct range *range, int nr_range,
 			continue;
 		base = range_state[i].base_pfn;
 		if (base < (1<<(20-PAGE_SHIFT)) && mtrr_state.have_fixed &&
-		    (mtrr_state.enabled & 1)) {
+		    (mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED) &&
+		    (mtrr_state.enabled & MTRR_STATE_MTRR_FIXED_ENABLED)) {
 			/* Var MTRR contains UC entry below 1M? Skip it: */
 			printk(BIOS_BUG_MSG, i);
 			if (base + size <= (1<<(20-PAGE_SHIFT)))
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 7d74f7b3c6ba..3b533cf37c74 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -102,59 +102,76 @@ static int check_type_overlap(u8 *prev, u8 *curr)
 	return 0;
 }
 
-/*
- * Error/Semi-error returns:
- * 0xFF - when MTRR is not enabled
- * *repeat == 1 implies [start:end] spanned across MTRR range and type returned
- *		corresponds only to [start:*partial_end].
- *		Caller has to lookup again for [*partial_end:end].
+/**
+ * mtrr_type_lookup_fixed - look up memory type in MTRR fixed entries
+ *
+ * Return the MTRR fixed memory type of 'start'.
+ *
+ * MTRR fixed entries are divided into the following ways:
+ *  0x00000 - 0x7FFFF : This range is divided into eight 64KB sub-ranges
+ *  0x80000 - 0xBFFFF : This range is divided into sixteen 16KB sub-ranges
+ *  0xC0000 - 0xFFFFF : This range is divided into sixty-four 4KB sub-ranges
+ *
+ * Return Values:
+ * MTRR_TYPE_(type)  - Matched memory type
+ * MTRR_TYPE_INVALID - Unmatched
+ */
+static u8 mtrr_type_lookup_fixed(u64 start, u64 end)
+{
+	int idx;
+
+	if (start >= 0x100000)
+		return MTRR_TYPE_INVALID;
+
+	/* 0x0 - 0x7FFFF */
+	if (start < 0x80000) {
+		idx = 0;
+		idx += (start >> 16);
+		return mtrr_state.fixed_ranges[idx];
+	/* 0x80000 - 0xBFFFF */
+	} else if (start < 0xC0000) {
+		idx = 1 * 8;
+		idx += ((start - 0x80000) >> 14);
+		return mtrr_state.fixed_ranges[idx];
+	}
+
+	/* 0xC0000 - 0xFFFFF */
+	idx = 3 * 8;
+	idx += ((start - 0xC0000) >> 12);
+	return mtrr_state.fixed_ranges[idx];
+}
+
+/**
+ * mtrr_type_lookup_variable - look up memory type in MTRR variable entries
+ *
+ * Return Value:
+ * MTRR_TYPE_(type) - Matched memory type or default memory type (unmatched)
+ *
+ * Output Arguments:
+ * repeat - Set to 1 when [start:end] spanned across MTRR range and type
+ *	    returned corresponds only to [start:*partial_end].  Caller has
+ *	    to lookup again for [*partial_end:end].
+ *
+ * uniform - Set to 1 when an MTRR covers the region uniformly, i.e. the
+ *	     region is fully covered by a single MTRR entry or the default
+ *	     type.
  */
-static u8 __mtrr_type_lookup(u64 start, u64 end, u64 *partial_end, int *repeat)
+static u8 mtrr_type_lookup_variable(u64 start, u64 end, u64 *partial_end,
+				    int *repeat, u8 *uniform)
 {
 	int i;
 	u64 base, mask;
 	u8 prev_match, curr_match;
 
 	*repeat = 0;
-	if (!mtrr_state_set)
-		return 0xFF;
-
-	if (!mtrr_state.enabled)
-		return 0xFF;
+	*uniform = 1;
 
-	/* Make end inclusive end, instead of exclusive */
+	/* Make end inclusive instead of exclusive */
 	end--;
 
-	/* Look in fixed ranges. Just return the type as per start */
-	if (mtrr_state.have_fixed && (start < 0x100000)) {
-		int idx;
-
-		if (start < 0x80000) {
-			idx = 0;
-			idx += (start >> 16);
-			return mtrr_state.fixed_ranges[idx];
-		} else if (start < 0xC0000) {
-			idx = 1 * 8;
-			idx += ((start - 0x80000) >> 14);
-			return mtrr_state.fixed_ranges[idx];
-		} else if (start < 0x1000000) {
-			idx = 3 * 8;
-			idx += ((start - 0xC0000) >> 12);
-			return mtrr_state.fixed_ranges[idx];
-		}
-	}
-
-	/*
-	 * Look in variable ranges
-	 * Look of multiple ranges matching this address and pick type
-	 * as per MTRR precedence
-	 */
-	if (!(mtrr_state.enabled & 2))
-		return mtrr_state.def_type;
-
-	prev_match = 0xFF;
+	prev_match = MTRR_TYPE_INVALID;
 	for (i = 0; i < num_var_ranges; ++i) {
-		unsigned short start_state, end_state;
+		unsigned short start_state, end_state, inclusive;
 
 		if (!(mtrr_state.var_ranges[i].mask_lo & (1 << 11)))
 			continue;
@@ -166,20 +183,29 @@ static u8 __mtrr_type_lookup(u64 start, u64 end, u64 *partial_end, int *repeat)
 
 		start_state = ((start & mask) == (base & mask));
 		end_state = ((end & mask) == (base & mask));
+		inclusive = ((start < base) && (end > base));
 
-		if (start_state != end_state) {
+		if ((start_state != end_state) || inclusive) {
 			/*
 			 * We have start:end spanning across an MTRR.
-			 * We split the region into
-			 * either
-			 * (start:mtrr_end) (mtrr_end:end)
-			 * or
-			 * (start:mtrr_start) (mtrr_start:end)
+			 * We split the region into either
+			 *
+			 * - start_state:1
+			 * (start:mtrr_end)(mtrr_end:end)
+			 * - end_state:1
+			 * (start:mtrr_start)(mtrr_start:end)
+			 * - inclusive:1
+			 * (start:mtrr_start)(mtrr_start:mtrr_end)(mtrr_end:end)
+			 *
 			 * depending on kind of overlap.
-			 * Return the type for first region and a pointer to
-			 * the start of second region so that caller will
-			 * lookup again on the second region.
-			 * Note: This way we handle multiple overlaps as well.
+			 *
+			 * Return the type of the first region and a pointer
+			 * to the start of next region so that caller will be
+			 * advised to lookup again after having adjusted start
+			 * and end.
+			 *
+			 * Note: This way we handle overlaps with multiple
+			 * entries and the default type properly.
 			 */
 			if (start_state)
 				*partial_end = base + get_mtrr_size(mask);
@@ -193,59 +219,94 @@ static u8 __mtrr_type_lookup(u64 start, u64 end, u64 *partial_end, int *repeat)
 
 			end = *partial_end - 1; /* end is inclusive */
 			*repeat = 1;
+			*uniform = 0;
 		}
 
 		if ((start & mask) != (base & mask))
 			continue;
 
 		curr_match = mtrr_state.var_ranges[i].base_lo & 0xff;
-		if (prev_match == 0xFF) {
+		if (prev_match == MTRR_TYPE_INVALID) {
 			prev_match = curr_match;
 			continue;
 		}
 
+		*uniform = 0;
 		if (check_type_overlap(&prev_match, &curr_match))
 			return curr_match;
 	}
 
-	if (mtrr_tom2) {
-		if (start >= (1ULL<<32) && (end < mtrr_tom2))
-			return MTRR_TYPE_WRBACK;
-	}
-
-	if (prev_match != 0xFF)
+	if (prev_match != MTRR_TYPE_INVALID)
 		return prev_match;
 
 	return mtrr_state.def_type;
 }
 
-/*
- * Returns the effective MTRR type for the region
- * Error return:
- * 0xFF - when MTRR is not enabled
+/**
+ * mtrr_type_lookup - look up memory type in MTRR
+ *
+ * Return Values:
+ * MTRR_TYPE_(type)  - The effective MTRR type for the region
+ * MTRR_TYPE_INVALID - MTRR is disabled
+ *
+ * Output Argument:
+ * uniform - Set to 1 when an MTRR covers the region uniformly, i.e. the
+ *	     region is fully covered by a single MTRR entry or the default
+ *	     type.
  */
-u8 mtrr_type_lookup(u64 start, u64 end)
+u8 mtrr_type_lookup(u64 start, u64 end, u8 *uniform)
 {
-	u8 type, prev_type;
+	u8 type, prev_type, is_uniform = 1, dummy;
 	int repeat;
 	u64 partial_end;
 
-	type = __mtrr_type_lookup(start, end, &partial_end, &repeat);
+	if (!mtrr_state_set)
+		return MTRR_TYPE_INVALID;
+
+	if (!(mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED))
+		return MTRR_TYPE_INVALID;
+
+	/*
+	 * Look up the fixed ranges first, which take priority over
+	 * the variable ranges.
+	 */
+	if ((start < 0x100000) &&
+	    (mtrr_state.have_fixed) &&
+	    (mtrr_state.enabled & MTRR_STATE_MTRR_FIXED_ENABLED)) {
+		is_uniform = 0;
+		type = mtrr_type_lookup_fixed(start, end);
+		goto out;
+	}
+
+	/*
+	 * Look up the variable ranges.  Look of multiple ranges matching
+	 * this address and pick type as per MTRR precedence.
+	 */
+	type = mtrr_type_lookup_variable(start, end, &partial_end,
+					 &repeat, &is_uniform);
 
 	/*
 	 * Common path is with repeat = 0.
 	 * However, we can have cases where [start:end] spans across some
-	 * MTRR range. Do repeated lookups for that case here.
+	 * MTRR ranges and/or the default type.  Do repeated lookups for
+	 * that case here.
 	 */
 	while (repeat) {
 		prev_type = type;
 		start = partial_end;
-		type = __mtrr_type_lookup(start, end, &partial_end, &repeat);
+		is_uniform = 0;
+		type = mtrr_type_lookup_variable(start, end, &partial_end,
+						 &repeat, &dummy);
 
 		if (check_type_overlap(&prev_type, &type))
-			return type;
+			goto out;
 	}
 
+	if (mtrr_tom2 && (start >= (1ULL<<32)) && (end < mtrr_tom2))
+		type = MTRR_TYPE_WRBACK;
+
+out:
+	*uniform = is_uniform;
 	return type;
 }
 
@@ -347,7 +408,9 @@ static void __init print_mtrr_state(void)
 		 mtrr_attrib_to_str(mtrr_state.def_type));
 	if (mtrr_state.have_fixed) {
 		pr_debug("MTRR fixed ranges %sabled:\n",
-			 mtrr_state.enabled & 1 ? "en" : "dis");
+			((mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED) &&
+			 (mtrr_state.enabled & MTRR_STATE_MTRR_FIXED_ENABLED)) ?
+			 "en" : "dis");
 		print_fixed(0x00000, 0x10000, mtrr_state.fixed_ranges + 0);
 		for (i = 0; i < 2; ++i)
 			print_fixed(0x80000 + i * 0x20000, 0x04000,
@@ -360,7 +423,7 @@ static void __init print_mtrr_state(void)
 		print_fixed_last();
 	}
 	pr_debug("MTRR variable ranges %sabled:\n",
-		 mtrr_state.enabled & 2 ? "en" : "dis");
+		 mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED ? "en" : "dis");
 	high_width = (__ffs64(size_or_mask) - (32 - PAGE_SHIFT) + 3) / 4;
 
 	for (i = 0; i < num_var_ranges; ++i) {
@@ -382,7 +445,7 @@ static void __init print_mtrr_state(void)
 }
 
 /* Grab all of the MTRR state for this CPU into *state */
-void __init get_mtrr_state(void)
+bool __init get_mtrr_state(void)
 {
 	struct mtrr_var_range *vrs;
 	unsigned long flags;
@@ -426,6 +489,8 @@ void __init get_mtrr_state(void)
 
 	post_set();
 	local_irq_restore(flags);
+
+	return !!(mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED);
 }
 
 /* Some BIOS's are messed up and don't set all MTRRs the same! */
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index ea5f363a1948..e7ed0d8ebacb 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -59,6 +59,12 @@
 #define MTRR_TO_PHYS_WC_OFFSET 1000
 
 u32 num_var_ranges;
+static bool __mtrr_enabled;
+
+static bool mtrr_enabled(void)
+{
+	return __mtrr_enabled;
+}
 
 unsigned int mtrr_usage_table[MTRR_MAX_VAR_RANGES];
 static DEFINE_MUTEX(mtrr_mutex);
@@ -286,7 +292,7 @@ int mtrr_add_page(unsigned long base, unsigned long size,
 	int i, replace, error;
 	mtrr_type ltype;
 
-	if (!mtrr_if)
+	if (!mtrr_enabled())
 		return -ENXIO;
 
 	error = mtrr_if->validate_add_page(base, size, type);
@@ -435,6 +441,8 @@ static int mtrr_check(unsigned long base, unsigned long size)
 int mtrr_add(unsigned long base, unsigned long size, unsigned int type,
 	     bool increment)
 {
+	if (!mtrr_enabled())
+		return -ENODEV;
 	if (mtrr_check(base, size))
 		return -EINVAL;
 	return mtrr_add_page(base >> PAGE_SHIFT, size >> PAGE_SHIFT, type,
@@ -463,8 +471,8 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size)
 	unsigned long lbase, lsize;
 	int error = -EINVAL;
 
-	if (!mtrr_if)
-		return -ENXIO;
+	if (!mtrr_enabled())
+		return -ENODEV;
 
 	max = num_var_ranges;
 	/* No CPU hotplug when we change MTRR entries */
@@ -523,6 +531,8 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size)
  */
 int mtrr_del(int reg, unsigned long base, unsigned long size)
 {
+	if (!mtrr_enabled())
+		return -ENODEV;
 	if (mtrr_check(base, size))
 		return -EINVAL;
 	return mtrr_del_page(reg, base >> PAGE_SHIFT, size >> PAGE_SHIFT);
@@ -538,6 +548,9 @@ EXPORT_SYMBOL(mtrr_del);
  * attempts to add a WC MTRR covering size bytes starting at base and
  * logs an error if this fails.
  *
+ * The called should provide a power of two size on an equivalent
+ * power of two boundary.
+ *
  * Drivers must store the return value to pass to mtrr_del_wc_if_needed,
  * but drivers should not try to interpret that return value.
  */
@@ -545,7 +558,7 @@ int arch_phys_wc_add(unsigned long base, unsigned long size)
 {
 	int ret;
 
-	if (pat_enabled)
+	if (pat_enabled() || !mtrr_enabled())
 		return 0;  /* Success!  (We don't need to do anything.) */
 
 	ret = mtrr_add(base, size, MTRR_TYPE_WRCOMB, true);
@@ -577,7 +590,7 @@ void arch_phys_wc_del(int handle)
 EXPORT_SYMBOL(arch_phys_wc_del);
 
 /*
- * phys_wc_to_mtrr_index - translates arch_phys_wc_add's return value
+ * arch_phys_wc_index - translates arch_phys_wc_add's return value
  * @handle: Return value from arch_phys_wc_add
  *
  * This will turn the return value from arch_phys_wc_add into an mtrr
@@ -587,14 +600,14 @@ EXPORT_SYMBOL(arch_phys_wc_del);
  * in printk line.  Alas there is an illegitimate use in some ancient
  * drm ioctls.
  */
-int phys_wc_to_mtrr_index(int handle)
+int arch_phys_wc_index(int handle)
 {
 	if (handle < MTRR_TO_PHYS_WC_OFFSET)
 		return -1;
 	else
 		return handle - MTRR_TO_PHYS_WC_OFFSET;
 }
-EXPORT_SYMBOL_GPL(phys_wc_to_mtrr_index);
+EXPORT_SYMBOL_GPL(arch_phys_wc_index);
 
 /*
  * HACK ALERT!
@@ -734,10 +747,12 @@ void __init mtrr_bp_init(void)
 	}
 
 	if (mtrr_if) {
+		__mtrr_enabled = true;
 		set_num_var_ranges();
 		init_table();
 		if (use_intel()) {
-			get_mtrr_state();
+			/* BIOS may override */
+			__mtrr_enabled = get_mtrr_state();
 
 			if (mtrr_cleanup(phys_addr)) {
 				changed_by_mtrr_cleanup = 1;
@@ -745,10 +760,16 @@ void __init mtrr_bp_init(void)
 			}
 		}
 	}
+
+	if (!mtrr_enabled())
+		pr_info("MTRR: Disabled\n");
 }
 
 void mtrr_ap_init(void)
 {
+	if (!mtrr_enabled())
+		return;
+
 	if (!use_intel() || mtrr_aps_delayed_init)
 		return;
 	/*
@@ -774,6 +795,9 @@ void mtrr_save_state(void)
 {
 	int first_cpu;
 
+	if (!mtrr_enabled())
+		return;
+
 	get_online_cpus();
 	first_cpu = cpumask_first(cpu_online_mask);
 	smp_call_function_single(first_cpu, mtrr_save_fixed_ranges, NULL, 1);
@@ -782,6 +806,8 @@ void mtrr_save_state(void)
 
 void set_mtrr_aps_delayed_init(void)
 {
+	if (!mtrr_enabled())
+		return;
 	if (!use_intel())
 		return;
 
@@ -793,7 +819,7 @@ void set_mtrr_aps_delayed_init(void)
  */
 void mtrr_aps_init(void)
 {
-	if (!use_intel())
+	if (!use_intel() || !mtrr_enabled())
 		return;
 
 	/*
@@ -810,7 +836,7 @@ void mtrr_aps_init(void)
 
 void mtrr_bp_restore(void)
 {
-	if (!use_intel())
+	if (!use_intel() || !mtrr_enabled())
 		return;
 
 	mtrr_if->set_all();
@@ -818,7 +844,7 @@ void mtrr_bp_restore(void)
 
 static int __init mtrr_init_finialize(void)
 {
-	if (!mtrr_if)
+	if (!mtrr_enabled())
 		return 0;
 
 	if (use_intel()) {
diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.h b/arch/x86/kernel/cpu/mtrr/mtrr.h
index df5e41f31a27..951884dcc433 100644
--- a/arch/x86/kernel/cpu/mtrr/mtrr.h
+++ b/arch/x86/kernel/cpu/mtrr/mtrr.h
@@ -51,7 +51,7 @@ void set_mtrr_prepare_save(struct set_mtrr_context *ctxt);
 
 void fill_mtrr_var_range(unsigned int index,
 		u32 base_lo, u32 base_hi, u32 mask_lo, u32 mask_hi);
-void get_mtrr_state(void);
+bool get_mtrr_state(void);
 
 extern void set_mtrr_ops(const struct mtrr_ops *ops);
 
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 87848ebe2bb7..3658de47900f 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -135,6 +135,7 @@ static int x86_pmu_extra_regs(u64 config, struct perf_event *event)
 }
 
 static atomic_t active_events;
+static atomic_t pmc_refcount;
 static DEFINE_MUTEX(pmc_reserve_mutex);
 
 #ifdef CONFIG_X86_LOCAL_APIC
@@ -190,6 +191,7 @@ static bool check_hw_exists(void)
 	u64 val, val_fail, val_new= ~0;
 	int i, reg, reg_fail, ret = 0;
 	int bios_fail = 0;
+	int reg_safe = -1;
 
 	/*
 	 * Check to see if the BIOS enabled any of the counters, if so
@@ -204,6 +206,8 @@ static bool check_hw_exists(void)
 			bios_fail = 1;
 			val_fail = val;
 			reg_fail = reg;
+		} else {
+			reg_safe = i;
 		}
 	}
 
@@ -222,11 +226,22 @@ static bool check_hw_exists(void)
 	}
 
 	/*
+	 * If all the counters are enabled, the below test will always
+	 * fail.  The tools will also become useless in this scenario.
+	 * Just fail and disable the hardware counters.
+	 */
+
+	if (reg_safe == -1) {
+		reg = reg_safe;
+		goto msr_fail;
+	}
+
+	/*
 	 * Read the current value, change it and read it back to see if it
 	 * matches, this is needed to detect certain hardware emulators
 	 * (qemu/kvm) that don't trap on the MSR access and always return 0s.
 	 */
-	reg = x86_pmu_event_addr(0);
+	reg = x86_pmu_event_addr(reg_safe);
 	if (rdmsrl_safe(reg, &val))
 		goto msr_fail;
 	val ^= 0xffffUL;
@@ -256,11 +271,8 @@ msr_fail:
 
 static void hw_perf_event_destroy(struct perf_event *event)
 {
-	if (atomic_dec_and_mutex_lock(&active_events, &pmc_reserve_mutex)) {
-		release_pmc_hardware();
-		release_ds_buffers();
-		mutex_unlock(&pmc_reserve_mutex);
-	}
+	x86_release_hardware();
+	atomic_dec(&active_events);
 }
 
 void hw_perf_lbr_event_destroy(struct perf_event *event)
@@ -310,33 +322,65 @@ set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event *event)
 	return x86_pmu_extra_regs(val, event);
 }
 
+int x86_reserve_hardware(void)
+{
+	int err = 0;
+
+	if (!atomic_inc_not_zero(&pmc_refcount)) {
+		mutex_lock(&pmc_reserve_mutex);
+		if (atomic_read(&pmc_refcount) == 0) {
+			if (!reserve_pmc_hardware())
+				err = -EBUSY;
+			else
+				reserve_ds_buffers();
+		}
+		if (!err)
+			atomic_inc(&pmc_refcount);
+		mutex_unlock(&pmc_reserve_mutex);
+	}
+
+	return err;
+}
+
+void x86_release_hardware(void)
+{
+	if (atomic_dec_and_mutex_lock(&pmc_refcount, &pmc_reserve_mutex)) {
+		release_pmc_hardware();
+		release_ds_buffers();
+		mutex_unlock(&pmc_reserve_mutex);
+	}
+}
+
 /*
  * Check if we can create event of a certain type (that no conflicting events
  * are present).
  */
 int x86_add_exclusive(unsigned int what)
 {
-	int ret = -EBUSY, i;
-
-	if (atomic_inc_not_zero(&x86_pmu.lbr_exclusive[what]))
-		return 0;
+	int i;
 
-	mutex_lock(&pmc_reserve_mutex);
-	for (i = 0; i < ARRAY_SIZE(x86_pmu.lbr_exclusive); i++)
-		if (i != what && atomic_read(&x86_pmu.lbr_exclusive[i]))
-			goto out;
+	if (!atomic_inc_not_zero(&x86_pmu.lbr_exclusive[what])) {
+		mutex_lock(&pmc_reserve_mutex);
+		for (i = 0; i < ARRAY_SIZE(x86_pmu.lbr_exclusive); i++) {
+			if (i != what && atomic_read(&x86_pmu.lbr_exclusive[i]))
+				goto fail_unlock;
+		}
+		atomic_inc(&x86_pmu.lbr_exclusive[what]);
+		mutex_unlock(&pmc_reserve_mutex);
+	}
 
-	atomic_inc(&x86_pmu.lbr_exclusive[what]);
-	ret = 0;
+	atomic_inc(&active_events);
+	return 0;
 
-out:
+fail_unlock:
 	mutex_unlock(&pmc_reserve_mutex);
-	return ret;
+	return -EBUSY;
 }
 
 void x86_del_exclusive(unsigned int what)
 {
 	atomic_dec(&x86_pmu.lbr_exclusive[what]);
+	atomic_dec(&active_events);
 }
 
 int x86_setup_perfctr(struct perf_event *event)
@@ -513,22 +557,11 @@ static int __x86_pmu_event_init(struct perf_event *event)
 	if (!x86_pmu_initialized())
 		return -ENODEV;
 
-	err = 0;
-	if (!atomic_inc_not_zero(&active_events)) {
-		mutex_lock(&pmc_reserve_mutex);
-		if (atomic_read(&active_events) == 0) {
-			if (!reserve_pmc_hardware())
-				err = -EBUSY;
-			else
-				reserve_ds_buffers();
-		}
-		if (!err)
-			atomic_inc(&active_events);
-		mutex_unlock(&pmc_reserve_mutex);
-	}
+	err = x86_reserve_hardware();
 	if (err)
 		return err;
 
+	atomic_inc(&active_events);
 	event->destroy = hw_perf_event_destroy;
 
 	event->hw.idx = -1;
@@ -611,6 +644,7 @@ struct sched_state {
 	int	event;		/* event index */
 	int	counter;	/* counter index */
 	int	unassigned;	/* number of events to be assigned left */
+	int	nr_gp;		/* number of GP counters used */
 	unsigned long used[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
 };
 
@@ -620,27 +654,29 @@ struct sched_state {
 struct perf_sched {
 	int			max_weight;
 	int			max_events;
-	struct perf_event	**events;
-	struct sched_state	state;
+	int			max_gp;
 	int			saved_states;
+	struct event_constraint	**constraints;
+	struct sched_state	state;
 	struct sched_state	saved[SCHED_STATES_MAX];
 };
 
 /*
  * Initialize interator that runs through all events and counters.
  */
-static void perf_sched_init(struct perf_sched *sched, struct perf_event **events,
-			    int num, int wmin, int wmax)
+static void perf_sched_init(struct perf_sched *sched, struct event_constraint **constraints,
+			    int num, int wmin, int wmax, int gpmax)
 {
 	int idx;
 
 	memset(sched, 0, sizeof(*sched));
 	sched->max_events	= num;
 	sched->max_weight	= wmax;
-	sched->events		= events;
+	sched->max_gp		= gpmax;
+	sched->constraints	= constraints;
 
 	for (idx = 0; idx < num; idx++) {
-		if (events[idx]->hw.constraint->weight == wmin)
+		if (constraints[idx]->weight == wmin)
 			break;
 	}
 
@@ -687,7 +723,7 @@ static bool __perf_sched_find_counter(struct perf_sched *sched)
 	if (sched->state.event >= sched->max_events)
 		return false;
 
-	c = sched->events[sched->state.event]->hw.constraint;
+	c = sched->constraints[sched->state.event];
 	/* Prefer fixed purpose counters */
 	if (c->idxmsk64 & (~0ULL << INTEL_PMC_IDX_FIXED)) {
 		idx = INTEL_PMC_IDX_FIXED;
@@ -696,11 +732,16 @@ static bool __perf_sched_find_counter(struct perf_sched *sched)
 				goto done;
 		}
 	}
+
 	/* Grab the first unused counter starting with idx */
 	idx = sched->state.counter;
 	for_each_set_bit_from(idx, c->idxmsk, INTEL_PMC_IDX_FIXED) {
-		if (!__test_and_set_bit(idx, sched->state.used))
+		if (!__test_and_set_bit(idx, sched->state.used)) {
+			if (sched->state.nr_gp++ >= sched->max_gp)
+				return false;
+
 			goto done;
+		}
 	}
 
 	return false;
@@ -745,7 +786,7 @@ static bool perf_sched_next_event(struct perf_sched *sched)
 			if (sched->state.weight > sched->max_weight)
 				return false;
 		}
-		c = sched->events[sched->state.event]->hw.constraint;
+		c = sched->constraints[sched->state.event];
 	} while (c->weight != sched->state.weight);
 
 	sched->state.counter = 0;	/* start with first counter */
@@ -756,12 +797,12 @@ static bool perf_sched_next_event(struct perf_sched *sched)
 /*
  * Assign a counter for each event.
  */
-int perf_assign_events(struct perf_event **events, int n,
-			int wmin, int wmax, int *assign)
+int perf_assign_events(struct event_constraint **constraints, int n,
+			int wmin, int wmax, int gpmax, int *assign)
 {
 	struct perf_sched sched;
 
-	perf_sched_init(&sched, events, n, wmin, wmax);
+	perf_sched_init(&sched, constraints, n, wmin, wmax, gpmax);
 
 	do {
 		if (!perf_sched_find_counter(&sched))
@@ -788,9 +829,9 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
 		x86_pmu.start_scheduling(cpuc);
 
 	for (i = 0, wmin = X86_PMC_IDX_MAX, wmax = 0; i < n; i++) {
-		hwc = &cpuc->event_list[i]->hw;
+		cpuc->event_constraint[i] = NULL;
 		c = x86_pmu.get_event_constraints(cpuc, i, cpuc->event_list[i]);
-		hwc->constraint = c;
+		cpuc->event_constraint[i] = c;
 
 		wmin = min(wmin, c->weight);
 		wmax = max(wmax, c->weight);
@@ -801,7 +842,7 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
 	 */
 	for (i = 0; i < n; i++) {
 		hwc = &cpuc->event_list[i]->hw;
-		c = hwc->constraint;
+		c = cpuc->event_constraint[i];
 
 		/* never assigned */
 		if (hwc->idx == -1)
@@ -821,9 +862,26 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
 	}
 
 	/* slow path */
-	if (i != n)
-		unsched = perf_assign_events(cpuc->event_list, n, wmin,
-					     wmax, assign);
+	if (i != n) {
+		int gpmax = x86_pmu.num_counters;
+
+		/*
+		 * Do not allow scheduling of more than half the available
+		 * generic counters.
+		 *
+		 * This helps avoid counter starvation of sibling thread by
+		 * ensuring at most half the counters cannot be in exclusive
+		 * mode. There is no designated counters for the limits. Any
+		 * N/2 counters can be used. This helps with events with
+		 * specific counter constraints.
+		 */
+		if (is_ht_workaround_enabled() && !cpuc->is_fake &&
+		    READ_ONCE(cpuc->excl_cntrs->exclusive_present))
+			gpmax /= 2;
+
+		unsched = perf_assign_events(cpuc->event_constraint, n, wmin,
+					     wmax, gpmax, assign);
+	}
 
 	/*
 	 * In case of success (unsched = 0), mark events as committed,
@@ -840,12 +898,9 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
 			e = cpuc->event_list[i];
 			e->hw.flags |= PERF_X86_EVENT_COMMITTED;
 			if (x86_pmu.commit_scheduling)
-				x86_pmu.commit_scheduling(cpuc, e, assign[i]);
+				x86_pmu.commit_scheduling(cpuc, i, assign[i]);
 		}
-	}
-
-	if (!assign || unsched) {
-
+	} else {
 		for (i = 0; i < n; i++) {
 			e = cpuc->event_list[i];
 			/*
@@ -1058,13 +1113,16 @@ int x86_perf_event_set_period(struct perf_event *event)
 
 	per_cpu(pmc_prev_left[idx], smp_processor_id()) = left;
 
-	/*
-	 * The hw event starts counting from this event offset,
-	 * mark it to be able to extra future deltas:
-	 */
-	local64_set(&hwc->prev_count, (u64)-left);
+	if (!(hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) ||
+	    local64_read(&hwc->prev_count) != (u64)-left) {
+		/*
+		 * The hw event starts counting from this event offset,
+		 * mark it to be able to extra future deltas:
+		 */
+		local64_set(&hwc->prev_count, (u64)-left);
 
-	wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask);
+		wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask);
+	}
 
 	/*
 	 * Due to erratum on certan cpu we need
@@ -1292,8 +1350,10 @@ static void x86_pmu_del(struct perf_event *event, int flags)
 		x86_pmu.put_event_constraints(cpuc, event);
 
 	/* Delete the array entry. */
-	while (++i < cpuc->n_events)
+	while (++i < cpuc->n_events) {
 		cpuc->event_list[i-1] = cpuc->event_list[i];
+		cpuc->event_constraint[i-1] = cpuc->event_constraint[i];
+	}
 	--cpuc->n_events;
 
 	perf_event_update_userpage(event);
@@ -1374,6 +1434,10 @@ perf_event_nmi_handler(unsigned int cmd, struct pt_regs *regs)
 	u64 finish_clock;
 	int ret;
 
+	/*
+	 * All PMUs/events that share this PMI handler should make sure to
+	 * increment active_events for their events.
+	 */
 	if (!atomic_read(&active_events))
 		return NMI_DONE;
 
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 6ac5cb7a9e14..3e7fd27dfe20 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -74,6 +74,9 @@ struct event_constraint {
 #define PERF_X86_EVENT_EXCL		0x0040 /* HT exclusivity on counter */
 #define PERF_X86_EVENT_DYNAMIC		0x0080 /* dynamic alloc'd constraint */
 #define PERF_X86_EVENT_RDPMC_ALLOWED	0x0100 /* grant rdpmc permission */
+#define PERF_X86_EVENT_EXCL_ACCT	0x0200 /* accounted EXCL event */
+#define PERF_X86_EVENT_AUTO_RELOAD	0x0400 /* use PEBS auto-reload */
+#define PERF_X86_EVENT_FREERUNNING	0x0800 /* use freerunning PEBS */
 
 
 struct amd_nb {
@@ -87,6 +90,18 @@ struct amd_nb {
 #define MAX_PEBS_EVENTS		8
 
 /*
+ * Flags PEBS can handle without an PMI.
+ *
+ * TID can only be handled by flushing at context switch.
+ *
+ */
+#define PEBS_FREERUNNING_FLAGS \
+	(PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_ADDR | \
+	PERF_SAMPLE_ID | PERF_SAMPLE_CPU | PERF_SAMPLE_STREAM_ID | \
+	PERF_SAMPLE_DATA_SRC | PERF_SAMPLE_IDENTIFIER | \
+	PERF_SAMPLE_TRANSACTION)
+
+/*
  * A debug store configuration.
  *
  * We only support architectures that use 64bit fields.
@@ -132,10 +147,7 @@ enum intel_excl_state_type {
 };
 
 struct intel_excl_states {
-	enum intel_excl_state_type init_state[X86_PMC_IDX_MAX];
 	enum intel_excl_state_type state[X86_PMC_IDX_MAX];
-	int  num_alloc_cntrs;/* #counters allocated */
-	int  max_alloc_cntrs;/* max #counters allowed */
 	bool sched_started; /* true if scheduling has started */
 };
 
@@ -144,6 +156,11 @@ struct intel_excl_cntrs {
 
 	struct intel_excl_states states[2];
 
+	union {
+		u16	has_exclusive[2];
+		u32	exclusive_present;
+	};
+
 	int		refcnt;		/* per-core: #HT threads */
 	unsigned	core_id;	/* per-core: core id */
 };
@@ -172,7 +189,11 @@ struct cpu_hw_events {
 					     added in the current transaction */
 	int			assign[X86_PMC_IDX_MAX]; /* event to counter assignment */
 	u64			tags[X86_PMC_IDX_MAX];
+
 	struct perf_event	*event_list[X86_PMC_IDX_MAX]; /* in enabled order */
+	struct event_constraint	*event_constraint[X86_PMC_IDX_MAX];
+
+	int			n_excl; /* the number of exclusive events */
 
 	unsigned int		group_flag;
 	int			is_fake;
@@ -519,12 +540,10 @@ struct x86_pmu {
 	void		(*put_event_constraints)(struct cpu_hw_events *cpuc,
 						 struct perf_event *event);
 
-	void		(*commit_scheduling)(struct cpu_hw_events *cpuc,
-					     struct perf_event *event,
-					     int cntr);
-
 	void		(*start_scheduling)(struct cpu_hw_events *cpuc);
 
+	void		(*commit_scheduling)(struct cpu_hw_events *cpuc, int idx, int cntr);
+
 	void		(*stop_scheduling)(struct cpu_hw_events *cpuc);
 
 	struct event_constraint *event_constraints;
@@ -697,6 +716,10 @@ int x86_add_exclusive(unsigned int what);
 
 void x86_del_exclusive(unsigned int what);
 
+int x86_reserve_hardware(void);
+
+void x86_release_hardware(void);
+
 void hw_perf_lbr_event_destroy(struct perf_event *event);
 
 int x86_setup_perfctr(struct perf_event *event);
@@ -717,8 +740,8 @@ static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc,
 
 void x86_pmu_enable_all(int added);
 
-int perf_assign_events(struct perf_event **events, int n,
-			int wmin, int wmax, int *assign);
+int perf_assign_events(struct event_constraint **constraints, int n,
+			int wmin, int wmax, int gpmax, int *assign);
 int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign);
 
 void x86_pmu_stop(struct perf_event *event, int flags);
@@ -860,6 +883,8 @@ void intel_pmu_pebs_enable_all(void);
 
 void intel_pmu_pebs_disable_all(void);
 
+void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in);
+
 void intel_ds_init(void);
 
 void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in);
@@ -929,4 +954,8 @@ static inline struct intel_shared_regs *allocate_shared_regs(int cpu)
 	return NULL;
 }
 
+static inline int is_ht_workaround_enabled(void)
+{
+	return 0;
+}
 #endif /* CONFIG_CPU_SUP_INTEL */
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 219d3fb423a1..b9826a981fb2 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1134,7 +1134,7 @@ static __initconst const u64 slm_hw_cache_extra_regs
  [ C(LL  ) ] = {
 	[ C(OP_READ) ] = {
 		[ C(RESULT_ACCESS) ] = SLM_DMND_READ|SLM_LLC_ACCESS,
-		[ C(RESULT_MISS)   ] = SLM_DMND_READ|SLM_LLC_MISS,
+		[ C(RESULT_MISS)   ] = 0,
 	},
 	[ C(OP_WRITE) ] = {
 		[ C(RESULT_ACCESS) ] = SLM_DMND_WRITE|SLM_LLC_ACCESS,
@@ -1184,8 +1184,7 @@ static __initconst const u64 slm_hw_cache_event_ids
 	[ C(OP_READ) ] = {
 		/* OFFCORE_RESPONSE.ANY_DATA.LOCAL_CACHE */
 		[ C(RESULT_ACCESS) ] = 0x01b7,
-		/* OFFCORE_RESPONSE.ANY_DATA.ANY_LLC_MISS */
-		[ C(RESULT_MISS)   ] = 0x01b7,
+		[ C(RESULT_MISS)   ] = 0,
 	},
 	[ C(OP_WRITE) ] = {
 		/* OFFCORE_RESPONSE.ANY_RFO.LOCAL_CACHE */
@@ -1217,7 +1216,7 @@ static __initconst const u64 slm_hw_cache_event_ids
  [ C(ITLB) ] = {
 	[ C(OP_READ) ] = {
 		[ C(RESULT_ACCESS) ] = 0x00c0, /* INST_RETIRED.ANY_P */
-		[ C(RESULT_MISS)   ] = 0x0282, /* ITLB.MISSES */
+		[ C(RESULT_MISS)   ] = 0x40205, /* PAGE_WALKS.I_SIDE_WALKS */
 	},
 	[ C(OP_WRITE) ] = {
 		[ C(RESULT_ACCESS) ] = -1,
@@ -1904,9 +1903,8 @@ static void
 intel_start_scheduling(struct cpu_hw_events *cpuc)
 {
 	struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs;
-	struct intel_excl_states *xl, *xlo;
+	struct intel_excl_states *xl;
 	int tid = cpuc->excl_thread_id;
-	int o_tid = 1 - tid; /* sibling thread */
 
 	/*
 	 * nothing needed if in group validation mode
@@ -1917,35 +1915,52 @@ intel_start_scheduling(struct cpu_hw_events *cpuc)
 	/*
 	 * no exclusion needed
 	 */
-	if (!excl_cntrs)
+	if (WARN_ON_ONCE(!excl_cntrs))
 		return;
 
-	xlo = &excl_cntrs->states[o_tid];
 	xl = &excl_cntrs->states[tid];
 
 	xl->sched_started = true;
-	xl->num_alloc_cntrs = 0;
 	/*
 	 * lock shared state until we are done scheduling
 	 * in stop_event_scheduling()
 	 * makes scheduling appear as a transaction
 	 */
-	WARN_ON_ONCE(!irqs_disabled());
 	raw_spin_lock(&excl_cntrs->lock);
+}
 
-	/*
-	 * save initial state of sibling thread
-	 */
-	memcpy(xlo->init_state, xlo->state, sizeof(xlo->init_state));
+static void intel_commit_scheduling(struct cpu_hw_events *cpuc, int idx, int cntr)
+{
+	struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs;
+	struct event_constraint *c = cpuc->event_constraint[idx];
+	struct intel_excl_states *xl;
+	int tid = cpuc->excl_thread_id;
+
+	if (cpuc->is_fake || !is_ht_workaround_enabled())
+		return;
+
+	if (WARN_ON_ONCE(!excl_cntrs))
+		return;
+
+	if (!(c->flags & PERF_X86_EVENT_DYNAMIC))
+		return;
+
+	xl = &excl_cntrs->states[tid];
+
+	lockdep_assert_held(&excl_cntrs->lock);
+
+	if (c->flags & PERF_X86_EVENT_EXCL)
+		xl->state[cntr] = INTEL_EXCL_EXCLUSIVE;
+	else
+		xl->state[cntr] = INTEL_EXCL_SHARED;
 }
 
 static void
 intel_stop_scheduling(struct cpu_hw_events *cpuc)
 {
 	struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs;
-	struct intel_excl_states *xl, *xlo;
+	struct intel_excl_states *xl;
 	int tid = cpuc->excl_thread_id;
-	int o_tid = 1 - tid; /* sibling thread */
 
 	/*
 	 * nothing needed if in group validation mode
@@ -1955,17 +1970,11 @@ intel_stop_scheduling(struct cpu_hw_events *cpuc)
 	/*
 	 * no exclusion needed
 	 */
-	if (!excl_cntrs)
+	if (WARN_ON_ONCE(!excl_cntrs))
 		return;
 
-	xlo = &excl_cntrs->states[o_tid];
 	xl = &excl_cntrs->states[tid];
 
-	/*
-	 * make new sibling thread state visible
-	 */
-	memcpy(xlo->state, xlo->init_state, sizeof(xlo->state));
-
 	xl->sched_started = false;
 	/*
 	 * release shared state lock (acquired in intel_start_scheduling())
@@ -1977,12 +1986,10 @@ static struct event_constraint *
 intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event,
 			   int idx, struct event_constraint *c)
 {
-	struct event_constraint *cx;
 	struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs;
-	struct intel_excl_states *xl, *xlo;
-	int is_excl, i;
+	struct intel_excl_states *xlo;
 	int tid = cpuc->excl_thread_id;
-	int o_tid = 1 - tid; /* alternate */
+	int is_excl, i;
 
 	/*
 	 * validating a group does not require
@@ -1994,34 +2001,8 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event,
 	/*
 	 * no exclusion needed
 	 */
-	if (!excl_cntrs)
+	if (WARN_ON_ONCE(!excl_cntrs))
 		return c;
-	/*
-	 * event requires exclusive counter access
-	 * across HT threads
-	 */
-	is_excl = c->flags & PERF_X86_EVENT_EXCL;
-
-	/*
-	 * xl = state of current HT
-	 * xlo = state of sibling HT
-	 */
-	xl = &excl_cntrs->states[tid];
-	xlo = &excl_cntrs->states[o_tid];
-
-	/*
-	 * do not allow scheduling of more than max_alloc_cntrs
-	 * which is set to half the available generic counters.
-	 * this helps avoid counter starvation of sibling thread
-	 * by ensuring at most half the counters cannot be in
-	 * exclusive mode. There is not designated counters for the
-	 * limits. Any N/2 counters can be used. This helps with
-	 * events with specifix counter constraints
-	 */
-	if (xl->num_alloc_cntrs++ == xl->max_alloc_cntrs)
-		return &emptyconstraint;
-
-	cx = c;
 
 	/*
 	 * because we modify the constraint, we need
@@ -2032,10 +2013,7 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event,
 	 * been cloned (marked dynamic)
 	 */
 	if (!(c->flags & PERF_X86_EVENT_DYNAMIC)) {
-
-		/* sanity check */
-		if (idx < 0)
-			return &emptyconstraint;
+		struct event_constraint *cx;
 
 		/*
 		 * grab pre-allocated constraint entry
@@ -2046,13 +2024,14 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event,
 		 * initialize dynamic constraint
 		 * with static constraint
 		 */
-		memcpy(cx, c, sizeof(*cx));
+		*cx = *c;
 
 		/*
 		 * mark constraint as dynamic, so we
 		 * can free it later on
 		 */
 		cx->flags |= PERF_X86_EVENT_DYNAMIC;
+		c = cx;
 	}
 
 	/*
@@ -2063,6 +2042,22 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event,
 	 */
 
 	/*
+	 * state of sibling HT
+	 */
+	xlo = &excl_cntrs->states[tid ^ 1];
+
+	/*
+	 * event requires exclusive counter access
+	 * across HT threads
+	 */
+	is_excl = c->flags & PERF_X86_EVENT_EXCL;
+	if (is_excl && !(event->hw.flags & PERF_X86_EVENT_EXCL_ACCT)) {
+		event->hw.flags |= PERF_X86_EVENT_EXCL_ACCT;
+		if (!cpuc->n_excl++)
+			WRITE_ONCE(excl_cntrs->has_exclusive[tid], 1);
+	}
+
+	/*
 	 * Modify static constraint with current dynamic
 	 * state of thread
 	 *
@@ -2070,44 +2065,44 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event,
 	 * SHARED   : sibling counter measuring non-exclusive event
 	 * UNUSED   : sibling counter unused
 	 */
-	for_each_set_bit(i, cx->idxmsk, X86_PMC_IDX_MAX) {
+	for_each_set_bit(i, c->idxmsk, X86_PMC_IDX_MAX) {
 		/*
 		 * exclusive event in sibling counter
 		 * our corresponding counter cannot be used
 		 * regardless of our event
 		 */
-		if (xl->state[i] == INTEL_EXCL_EXCLUSIVE)
-			__clear_bit(i, cx->idxmsk);
+		if (xlo->state[i] == INTEL_EXCL_EXCLUSIVE)
+			__clear_bit(i, c->idxmsk);
 		/*
 		 * if measuring an exclusive event, sibling
 		 * measuring non-exclusive, then counter cannot
 		 * be used
 		 */
-		if (is_excl && xl->state[i] == INTEL_EXCL_SHARED)
-			__clear_bit(i, cx->idxmsk);
+		if (is_excl && xlo->state[i] == INTEL_EXCL_SHARED)
+			__clear_bit(i, c->idxmsk);
 	}
 
 	/*
 	 * recompute actual bit weight for scheduling algorithm
 	 */
-	cx->weight = hweight64(cx->idxmsk64);
+	c->weight = hweight64(c->idxmsk64);
 
 	/*
 	 * if we return an empty mask, then switch
 	 * back to static empty constraint to avoid
 	 * the cost of freeing later on
 	 */
-	if (cx->weight == 0)
-		cx = &emptyconstraint;
+	if (c->weight == 0)
+		c = &emptyconstraint;
 
-	return cx;
+	return c;
 }
 
 static struct event_constraint *
 intel_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 			    struct perf_event *event)
 {
-	struct event_constraint *c1 = event->hw.constraint;
+	struct event_constraint *c1 = cpuc->event_constraint[idx];
 	struct event_constraint *c2;
 
 	/*
@@ -2133,10 +2128,8 @@ static void intel_put_excl_constraints(struct cpu_hw_events *cpuc,
 {
 	struct hw_perf_event *hwc = &event->hw;
 	struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs;
-	struct intel_excl_states *xlo, *xl;
-	unsigned long flags = 0; /* keep compiler happy */
 	int tid = cpuc->excl_thread_id;
-	int o_tid = 1 - tid;
+	struct intel_excl_states *xl;
 
 	/*
 	 * nothing needed if in group validation mode
@@ -2144,31 +2137,35 @@ static void intel_put_excl_constraints(struct cpu_hw_events *cpuc,
 	if (cpuc->is_fake)
 		return;
 
-	WARN_ON_ONCE(!excl_cntrs);
-
-	if (!excl_cntrs)
+	if (WARN_ON_ONCE(!excl_cntrs))
 		return;
 
-	xl = &excl_cntrs->states[tid];
-	xlo = &excl_cntrs->states[o_tid];
+	if (hwc->flags & PERF_X86_EVENT_EXCL_ACCT) {
+		hwc->flags &= ~PERF_X86_EVENT_EXCL_ACCT;
+		if (!--cpuc->n_excl)
+			WRITE_ONCE(excl_cntrs->has_exclusive[tid], 0);
+	}
 
 	/*
-	 * put_constraint may be called from x86_schedule_events()
-	 * which already has the lock held so here make locking
-	 * conditional
+	 * If event was actually assigned, then mark the counter state as
+	 * unused now.
 	 */
-	if (!xl->sched_started)
-		raw_spin_lock_irqsave(&excl_cntrs->lock, flags);
+	if (hwc->idx >= 0) {
+		xl = &excl_cntrs->states[tid];
 
-	/*
-	 * if event was actually assigned, then mark the
-	 * counter state as unused now
-	 */
-	if (hwc->idx >= 0)
-		xlo->state[hwc->idx] = INTEL_EXCL_UNUSED;
+		/*
+		 * put_constraint may be called from x86_schedule_events()
+		 * which already has the lock held so here make locking
+		 * conditional.
+		 */
+		if (!xl->sched_started)
+			raw_spin_lock(&excl_cntrs->lock);
+
+		xl->state[hwc->idx] = INTEL_EXCL_UNUSED;
 
-	if (!xl->sched_started)
-		raw_spin_unlock_irqrestore(&excl_cntrs->lock, flags);
+		if (!xl->sched_started)
+			raw_spin_unlock(&excl_cntrs->lock);
+	}
 }
 
 static void
@@ -2189,8 +2186,6 @@ intel_put_shared_regs_event_constraints(struct cpu_hw_events *cpuc,
 static void intel_put_event_constraints(struct cpu_hw_events *cpuc,
 					struct perf_event *event)
 {
-	struct event_constraint *c = event->hw.constraint;
-
 	intel_put_shared_regs_event_constraints(cpuc, event);
 
 	/*
@@ -2198,48 +2193,8 @@ static void intel_put_event_constraints(struct cpu_hw_events *cpuc,
 	 * all events are subject to and must call the
 	 * put_excl_constraints() routine
 	 */
-	if (c && cpuc->excl_cntrs)
+	if (cpuc->excl_cntrs)
 		intel_put_excl_constraints(cpuc, event);
-
-	/* cleanup dynamic constraint */
-	if (c && (c->flags & PERF_X86_EVENT_DYNAMIC))
-		event->hw.constraint = NULL;
-}
-
-static void intel_commit_scheduling(struct cpu_hw_events *cpuc,
-				    struct perf_event *event, int cntr)
-{
-	struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs;
-	struct event_constraint *c = event->hw.constraint;
-	struct intel_excl_states *xlo, *xl;
-	int tid = cpuc->excl_thread_id;
-	int o_tid = 1 - tid;
-	int is_excl;
-
-	if (cpuc->is_fake || !c)
-		return;
-
-	is_excl = c->flags & PERF_X86_EVENT_EXCL;
-
-	if (!(c->flags & PERF_X86_EVENT_DYNAMIC))
-		return;
-
-	WARN_ON_ONCE(!excl_cntrs);
-
-	if (!excl_cntrs)
-		return;
-
-	xl = &excl_cntrs->states[tid];
-	xlo = &excl_cntrs->states[o_tid];
-
-	WARN_ON_ONCE(!raw_spin_is_locked(&excl_cntrs->lock));
-
-	if (cntr >= 0) {
-		if (is_excl)
-			xlo->init_state[cntr] = INTEL_EXCL_EXCLUSIVE;
-		else
-			xlo->init_state[cntr] = INTEL_EXCL_SHARED;
-	}
 }
 
 static void intel_pebs_aliases_core2(struct perf_event *event)
@@ -2305,8 +2260,15 @@ static int intel_pmu_hw_config(struct perf_event *event)
 	if (ret)
 		return ret;
 
-	if (event->attr.precise_ip && x86_pmu.pebs_aliases)
-		x86_pmu.pebs_aliases(event);
+	if (event->attr.precise_ip) {
+		if (!event->attr.freq) {
+			event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD;
+			if (!(event->attr.sample_type & ~PEBS_FREERUNNING_FLAGS))
+				event->hw.flags |= PERF_X86_EVENT_FREERUNNING;
+		}
+		if (x86_pmu.pebs_aliases)
+			x86_pmu.pebs_aliases(event);
+	}
 
 	if (needs_branch_stack(event)) {
 		ret = intel_pmu_setup_lbr_filter(event);
@@ -2533,34 +2495,6 @@ ssize_t intel_event_sysfs_show(char *page, u64 config)
 	return x86_event_sysfs_show(page, config, event);
 }
 
-static __initconst const struct x86_pmu core_pmu = {
-	.name			= "core",
-	.handle_irq		= x86_pmu_handle_irq,
-	.disable_all		= x86_pmu_disable_all,
-	.enable_all		= core_pmu_enable_all,
-	.enable			= core_pmu_enable_event,
-	.disable		= x86_pmu_disable_event,
-	.hw_config		= x86_pmu_hw_config,
-	.schedule_events	= x86_schedule_events,
-	.eventsel		= MSR_ARCH_PERFMON_EVENTSEL0,
-	.perfctr		= MSR_ARCH_PERFMON_PERFCTR0,
-	.event_map		= intel_pmu_event_map,
-	.max_events		= ARRAY_SIZE(intel_perfmon_event_map),
-	.apic			= 1,
-	/*
-	 * Intel PMCs cannot be accessed sanely above 32 bit width,
-	 * so we install an artificial 1<<31 period regardless of
-	 * the generic event period:
-	 */
-	.max_period		= (1ULL << 31) - 1,
-	.get_event_constraints	= intel_get_event_constraints,
-	.put_event_constraints	= intel_put_event_constraints,
-	.event_constraints	= intel_core_event_constraints,
-	.guest_get_msrs		= core_guest_get_msrs,
-	.format_attrs		= intel_arch_formats_attr,
-	.events_sysfs_show	= intel_event_sysfs_show,
-};
-
 struct intel_shared_regs *allocate_shared_regs(int cpu)
 {
 	struct intel_shared_regs *regs;
@@ -2583,19 +2517,11 @@ struct intel_shared_regs *allocate_shared_regs(int cpu)
 static struct intel_excl_cntrs *allocate_excl_cntrs(int cpu)
 {
 	struct intel_excl_cntrs *c;
-	int i;
 
 	c = kzalloc_node(sizeof(struct intel_excl_cntrs),
 			 GFP_KERNEL, cpu_to_node(cpu));
 	if (c) {
 		raw_spin_lock_init(&c->lock);
-		for (i = 0; i < X86_PMC_IDX_MAX; i++) {
-			c->states[0].state[i] = INTEL_EXCL_UNUSED;
-			c->states[0].init_state[i] = INTEL_EXCL_UNUSED;
-
-			c->states[1].state[i] = INTEL_EXCL_UNUSED;
-			c->states[1].init_state[i] = INTEL_EXCL_UNUSED;
-		}
 		c->core_id = -1;
 	}
 	return c;
@@ -2650,7 +2576,7 @@ static void intel_pmu_cpu_starting(int cpu)
 	if (!(x86_pmu.flags & PMU_FL_NO_HT_SHARING)) {
 		void **onln = &cpuc->kfree_on_online[X86_PERF_KFREE_SHARED];
 
-		for_each_cpu(i, topology_thread_cpumask(cpu)) {
+		for_each_cpu(i, topology_sibling_cpumask(cpu)) {
 			struct intel_shared_regs *pc;
 
 			pc = per_cpu(cpu_hw_events, i).shared_regs;
@@ -2668,9 +2594,7 @@ static void intel_pmu_cpu_starting(int cpu)
 		cpuc->lbr_sel = &cpuc->shared_regs->regs[EXTRA_REG_LBR];
 
 	if (x86_pmu.flags & PMU_FL_EXCL_CNTRS) {
-		int h = x86_pmu.num_counters >> 1;
-
-		for_each_cpu(i, topology_thread_cpumask(cpu)) {
+		for_each_cpu(i, topology_sibling_cpumask(cpu)) {
 			struct intel_excl_cntrs *c;
 
 			c = per_cpu(cpu_hw_events, i).excl_cntrs;
@@ -2683,11 +2607,6 @@ static void intel_pmu_cpu_starting(int cpu)
 		}
 		cpuc->excl_cntrs->core_id = core_id;
 		cpuc->excl_cntrs->refcnt++;
-		/*
-		 * set hard limit to half the number of generic counters
-		 */
-		cpuc->excl_cntrs->states[0].max_alloc_cntrs = h;
-		cpuc->excl_cntrs->states[1].max_alloc_cntrs = h;
 	}
 }
 
@@ -2723,6 +2642,15 @@ static void intel_pmu_cpu_dying(int cpu)
 	fini_debug_store_on_cpu(cpu);
 }
 
+static void intel_pmu_sched_task(struct perf_event_context *ctx,
+				 bool sched_in)
+{
+	if (x86_pmu.pebs_active)
+		intel_pmu_pebs_sched_task(ctx, sched_in);
+	if (x86_pmu.lbr_nr)
+		intel_pmu_lbr_sched_task(ctx, sched_in);
+}
+
 PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63");
 
 PMU_FORMAT_ATTR(ldlat, "config1:0-15");
@@ -2743,6 +2671,44 @@ static struct attribute *intel_arch3_formats_attr[] = {
 	NULL,
 };
 
+static __initconst const struct x86_pmu core_pmu = {
+	.name			= "core",
+	.handle_irq		= x86_pmu_handle_irq,
+	.disable_all		= x86_pmu_disable_all,
+	.enable_all		= core_pmu_enable_all,
+	.enable			= core_pmu_enable_event,
+	.disable		= x86_pmu_disable_event,
+	.hw_config		= x86_pmu_hw_config,
+	.schedule_events	= x86_schedule_events,
+	.eventsel		= MSR_ARCH_PERFMON_EVENTSEL0,
+	.perfctr		= MSR_ARCH_PERFMON_PERFCTR0,
+	.event_map		= intel_pmu_event_map,
+	.max_events		= ARRAY_SIZE(intel_perfmon_event_map),
+	.apic			= 1,
+	/*
+	 * Intel PMCs cannot be accessed sanely above 32-bit width,
+	 * so we install an artificial 1<<31 period regardless of
+	 * the generic event period:
+	 */
+	.max_period		= (1ULL<<31) - 1,
+	.get_event_constraints	= intel_get_event_constraints,
+	.put_event_constraints	= intel_put_event_constraints,
+	.event_constraints	= intel_core_event_constraints,
+	.guest_get_msrs		= core_guest_get_msrs,
+	.format_attrs		= intel_arch_formats_attr,
+	.events_sysfs_show	= intel_event_sysfs_show,
+
+	/*
+	 * Virtual (or funny metal) CPU can define x86_pmu.extra_regs
+	 * together with PMU version 1 and thus be using core_pmu with
+	 * shared_regs. We need following callbacks here to allocate
+	 * it properly.
+	 */
+	.cpu_prepare		= intel_pmu_cpu_prepare,
+	.cpu_starting		= intel_pmu_cpu_starting,
+	.cpu_dying		= intel_pmu_cpu_dying,
+};
+
 static __initconst const struct x86_pmu intel_pmu = {
 	.name			= "Intel",
 	.handle_irq		= intel_pmu_handle_irq,
@@ -2774,7 +2740,7 @@ static __initconst const struct x86_pmu intel_pmu = {
 	.cpu_starting		= intel_pmu_cpu_starting,
 	.cpu_dying		= intel_pmu_cpu_dying,
 	.guest_get_msrs		= intel_guest_get_msrs,
-	.sched_task		= intel_pmu_lbr_sched_task,
+	.sched_task		= intel_pmu_sched_task,
 };
 
 static __init void intel_clovertown_quirk(void)
@@ -2947,8 +2913,8 @@ static __init void intel_ht_bug(void)
 {
 	x86_pmu.flags |= PMU_FL_EXCL_CNTRS | PMU_FL_EXCL_ENABLED;
 
-	x86_pmu.commit_scheduling = intel_commit_scheduling;
 	x86_pmu.start_scheduling = intel_start_scheduling;
+	x86_pmu.commit_scheduling = intel_commit_scheduling;
 	x86_pmu.stop_scheduling = intel_stop_scheduling;
 }
 
@@ -3261,6 +3227,8 @@ __init int intel_pmu_init(void)
 
 	case 61: /* 14nm Broadwell Core-M */
 	case 86: /* 14nm Broadwell Xeon D */
+	case 71: /* 14nm Broadwell + GT3e (Intel Iris Pro graphics) */
+	case 79: /* 14nm Broadwell Server */
 		x86_pmu.late_ack = true;
 		memcpy(hw_cache_event_ids, hsw_hw_cache_event_ids, sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, hsw_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
@@ -3330,13 +3298,13 @@ __init int intel_pmu_init(void)
 		 * counter, so do not extend mask to generic counters
 		 */
 		for_each_event_constraint(c, x86_pmu.event_constraints) {
-			if (c->cmask != FIXED_EVENT_FLAGS
-			    || c->idxmsk64 == INTEL_PMC_MSK_FIXED_REF_CYCLES) {
-				continue;
+			if (c->cmask == FIXED_EVENT_FLAGS
+			    && c->idxmsk64 != INTEL_PMC_MSK_FIXED_REF_CYCLES) {
+				c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1;
 			}
-
-			c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1;
-			c->weight += x86_pmu.num_counters;
+			c->idxmsk64 &=
+				~(~0UL << (INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed));
+			c->weight = hweight64(c->idxmsk64);
 		}
 	}
 
@@ -3394,7 +3362,7 @@ static __init int fixup_ht_bug(void)
 	if (!(x86_pmu.flags & PMU_FL_EXCL_ENABLED))
 		return 0;
 
-	w = cpumask_weight(topology_thread_cpumask(cpu));
+	w = cpumask_weight(topology_sibling_cpumask(cpu));
 	if (w > 1) {
 		pr_info("PMU erratum BJ122, BV98, HSD29 worked around, HT is on\n");
 		return 0;
@@ -3404,8 +3372,8 @@ static __init int fixup_ht_bug(void)
 
 	x86_pmu.flags &= ~(PMU_FL_EXCL_CNTRS | PMU_FL_EXCL_ENABLED);
 
-	x86_pmu.commit_scheduling = NULL;
 	x86_pmu.start_scheduling = NULL;
+	x86_pmu.commit_scheduling = NULL;
 	x86_pmu.stop_scheduling = NULL;
 
 	watchdog_nmi_enable_all();
diff --git a/arch/x86/kernel/cpu/perf_event_intel_bts.c b/arch/x86/kernel/cpu/perf_event_intel_bts.c
index ac1f0c55f379..43dd672d788b 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_bts.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_bts.c
@@ -483,17 +483,26 @@ static int bts_event_add(struct perf_event *event, int mode)
 
 static void bts_event_destroy(struct perf_event *event)
 {
+	x86_release_hardware();
 	x86_del_exclusive(x86_lbr_exclusive_bts);
 }
 
 static int bts_event_init(struct perf_event *event)
 {
+	int ret;
+
 	if (event->attr.type != bts_pmu.type)
 		return -ENOENT;
 
 	if (x86_add_exclusive(x86_lbr_exclusive_bts))
 		return -EBUSY;
 
+	ret = x86_reserve_hardware();
+	if (ret) {
+		x86_del_exclusive(x86_lbr_exclusive_bts);
+		return ret;
+	}
+
 	event->destroy = bts_event_destroy;
 
 	return 0;
@@ -521,5 +530,4 @@ static __init int bts_init(void)
 
 	return perf_pmu_register(&bts_pmu, "intel_bts", -1);
 }
-
-module_init(bts_init);
+arch_initcall(bts_init);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_cqm.c b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
index e4d1b8b738fa..188076161c1b 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_cqm.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
@@ -13,16 +13,35 @@
 #define MSR_IA32_QM_CTR		0x0c8e
 #define MSR_IA32_QM_EVTSEL	0x0c8d
 
-static unsigned int cqm_max_rmid = -1;
+static u32 cqm_max_rmid = -1;
 static unsigned int cqm_l3_scale; /* supposedly cacheline size */
 
-struct intel_cqm_state {
-	raw_spinlock_t		lock;
-	int			rmid;
-	int			cnt;
+/**
+ * struct intel_pqr_state - State cache for the PQR MSR
+ * @rmid:		The cached Resource Monitoring ID
+ * @closid:		The cached Class Of Service ID
+ * @rmid_usecnt:	The usage counter for rmid
+ *
+ * The upper 32 bits of MSR_IA32_PQR_ASSOC contain closid and the
+ * lower 10 bits rmid. The update to MSR_IA32_PQR_ASSOC always
+ * contains both parts, so we need to cache them.
+ *
+ * The cache also helps to avoid pointless updates if the value does
+ * not change.
+ */
+struct intel_pqr_state {
+	u32			rmid;
+	u32			closid;
+	int			rmid_usecnt;
 };
 
-static DEFINE_PER_CPU(struct intel_cqm_state, cqm_state);
+/*
+ * The cached intel_pqr_state is strictly per CPU and can never be
+ * updated from a remote CPU. Both functions which modify the state
+ * (intel_cqm_event_start and intel_cqm_event_stop) are called with
+ * interrupts disabled, which is sufficient for the protection.
+ */
+static DEFINE_PER_CPU(struct intel_pqr_state, pqr_state);
 
 /*
  * Protects cache_cgroups and cqm_rmid_free_lru and cqm_rmid_limbo_lru.
@@ -57,7 +76,7 @@ static cpumask_t cqm_cpumask;
  * near-zero occupancy value, i.e. no cachelines are tagged with this
  * RMID, once __intel_cqm_rmid_rotate() returns.
  */
-static unsigned int intel_cqm_rotation_rmid;
+static u32 intel_cqm_rotation_rmid;
 
 #define INVALID_RMID		(-1)
 
@@ -69,7 +88,7 @@ static unsigned int intel_cqm_rotation_rmid;
  * Likewise, an rmid value of -1 is used to indicate "no rmid currently
  * assigned" and is used as part of the rotation code.
  */
-static inline bool __rmid_valid(unsigned int rmid)
+static inline bool __rmid_valid(u32 rmid)
 {
 	if (!rmid || rmid == INVALID_RMID)
 		return false;
@@ -77,7 +96,7 @@ static inline bool __rmid_valid(unsigned int rmid)
 	return true;
 }
 
-static u64 __rmid_read(unsigned int rmid)
+static u64 __rmid_read(u32 rmid)
 {
 	u64 val;
 
@@ -102,7 +121,7 @@ enum rmid_recycle_state {
 };
 
 struct cqm_rmid_entry {
-	unsigned int rmid;
+	u32 rmid;
 	enum rmid_recycle_state state;
 	struct list_head list;
 	unsigned long queue_time;
@@ -147,7 +166,7 @@ static LIST_HEAD(cqm_rmid_limbo_lru);
  */
 static struct cqm_rmid_entry **cqm_rmid_ptrs;
 
-static inline struct cqm_rmid_entry *__rmid_entry(int rmid)
+static inline struct cqm_rmid_entry *__rmid_entry(u32 rmid)
 {
 	struct cqm_rmid_entry *entry;
 
@@ -162,7 +181,7 @@ static inline struct cqm_rmid_entry *__rmid_entry(int rmid)
  *
  * We expect to be called with cache_mutex held.
  */
-static int __get_rmid(void)
+static u32 __get_rmid(void)
 {
 	struct cqm_rmid_entry *entry;
 
@@ -177,7 +196,7 @@ static int __get_rmid(void)
 	return entry->rmid;
 }
 
-static void __put_rmid(unsigned int rmid)
+static void __put_rmid(u32 rmid)
 {
 	struct cqm_rmid_entry *entry;
 
@@ -372,7 +391,7 @@ static bool __conflict_event(struct perf_event *a, struct perf_event *b)
 }
 
 struct rmid_read {
-	unsigned int rmid;
+	u32 rmid;
 	atomic64_t value;
 };
 
@@ -381,12 +400,11 @@ static void __intel_cqm_event_count(void *info);
 /*
  * Exchange the RMID of a group of events.
  */
-static unsigned int
-intel_cqm_xchg_rmid(struct perf_event *group, unsigned int rmid)
+static u32 intel_cqm_xchg_rmid(struct perf_event *group, u32 rmid)
 {
 	struct perf_event *event;
-	unsigned int old_rmid = group->hw.cqm_rmid;
 	struct list_head *head = &group->hw.cqm_group_entry;
+	u32 old_rmid = group->hw.cqm_rmid;
 
 	lockdep_assert_held(&cache_mutex);
 
@@ -451,7 +469,7 @@ static void intel_cqm_stable(void *arg)
  * If we have group events waiting for an RMID that don't conflict with
  * events already running, assign @rmid.
  */
-static bool intel_cqm_sched_in_event(unsigned int rmid)
+static bool intel_cqm_sched_in_event(u32 rmid)
 {
 	struct perf_event *leader, *event;
 
@@ -598,7 +616,7 @@ static bool intel_cqm_rmid_stabilize(unsigned int *available)
 static void __intel_cqm_pick_and_rotate(struct perf_event *next)
 {
 	struct perf_event *rotor;
-	unsigned int rmid;
+	u32 rmid;
 
 	lockdep_assert_held(&cache_mutex);
 
@@ -626,7 +644,7 @@ static void __intel_cqm_pick_and_rotate(struct perf_event *next)
 static void intel_cqm_sched_out_conflicting_events(struct perf_event *event)
 {
 	struct perf_event *group, *g;
-	unsigned int rmid;
+	u32 rmid;
 
 	lockdep_assert_held(&cache_mutex);
 
@@ -828,8 +846,8 @@ static void intel_cqm_setup_event(struct perf_event *event,
 				  struct perf_event **group)
 {
 	struct perf_event *iter;
-	unsigned int rmid;
 	bool conflict = false;
+	u32 rmid;
 
 	list_for_each_entry(iter, &cache_groups, hw.cqm_groups_entry) {
 		rmid = iter->hw.cqm_rmid;
@@ -860,7 +878,7 @@ static void intel_cqm_setup_event(struct perf_event *event,
 static void intel_cqm_event_read(struct perf_event *event)
 {
 	unsigned long flags;
-	unsigned int rmid;
+	u32 rmid;
 	u64 val;
 
 	/*
@@ -961,55 +979,48 @@ out:
 
 static void intel_cqm_event_start(struct perf_event *event, int mode)
 {
-	struct intel_cqm_state *state = this_cpu_ptr(&cqm_state);
-	unsigned int rmid = event->hw.cqm_rmid;
-	unsigned long flags;
+	struct intel_pqr_state *state = this_cpu_ptr(&pqr_state);
+	u32 rmid = event->hw.cqm_rmid;
 
 	if (!(event->hw.cqm_state & PERF_HES_STOPPED))
 		return;
 
 	event->hw.cqm_state &= ~PERF_HES_STOPPED;
 
-	raw_spin_lock_irqsave(&state->lock, flags);
-
-	if (state->cnt++)
-		WARN_ON_ONCE(state->rmid != rmid);
-	else
+	if (state->rmid_usecnt++) {
+		if (!WARN_ON_ONCE(state->rmid != rmid))
+			return;
+	} else {
 		WARN_ON_ONCE(state->rmid);
+	}
 
 	state->rmid = rmid;
-	wrmsrl(MSR_IA32_PQR_ASSOC, state->rmid);
-
-	raw_spin_unlock_irqrestore(&state->lock, flags);
+	wrmsr(MSR_IA32_PQR_ASSOC, rmid, state->closid);
 }
 
 static void intel_cqm_event_stop(struct perf_event *event, int mode)
 {
-	struct intel_cqm_state *state = this_cpu_ptr(&cqm_state);
-	unsigned long flags;
+	struct intel_pqr_state *state = this_cpu_ptr(&pqr_state);
 
 	if (event->hw.cqm_state & PERF_HES_STOPPED)
 		return;
 
 	event->hw.cqm_state |= PERF_HES_STOPPED;
 
-	raw_spin_lock_irqsave(&state->lock, flags);
 	intel_cqm_event_read(event);
 
-	if (!--state->cnt) {
+	if (!--state->rmid_usecnt) {
 		state->rmid = 0;
-		wrmsrl(MSR_IA32_PQR_ASSOC, 0);
+		wrmsr(MSR_IA32_PQR_ASSOC, 0, state->closid);
 	} else {
 		WARN_ON_ONCE(!state->rmid);
 	}
-
-	raw_spin_unlock_irqrestore(&state->lock, flags);
 }
 
 static int intel_cqm_event_add(struct perf_event *event, int mode)
 {
 	unsigned long flags;
-	unsigned int rmid;
+	u32 rmid;
 
 	raw_spin_lock_irqsave(&cache_lock, flags);
 
@@ -1024,11 +1035,6 @@ static int intel_cqm_event_add(struct perf_event *event, int mode)
 	return 0;
 }
 
-static void intel_cqm_event_del(struct perf_event *event, int mode)
-{
-	intel_cqm_event_stop(event, mode);
-}
-
 static void intel_cqm_event_destroy(struct perf_event *event)
 {
 	struct perf_event *group_other = NULL;
@@ -1057,7 +1063,7 @@ static void intel_cqm_event_destroy(struct perf_event *event)
 			list_replace(&event->hw.cqm_groups_entry,
 				     &group_other->hw.cqm_groups_entry);
 		} else {
-			unsigned int rmid = event->hw.cqm_rmid;
+			u32 rmid = event->hw.cqm_rmid;
 
 			if (__rmid_valid(rmid))
 				__put_rmid(rmid);
@@ -1221,7 +1227,7 @@ static struct pmu intel_cqm_pmu = {
 	.task_ctx_nr	     = perf_sw_context,
 	.event_init	     = intel_cqm_event_init,
 	.add		     = intel_cqm_event_add,
-	.del		     = intel_cqm_event_del,
+	.del		     = intel_cqm_event_stop,
 	.start		     = intel_cqm_event_start,
 	.stop		     = intel_cqm_event_stop,
 	.read		     = intel_cqm_event_read,
@@ -1243,12 +1249,12 @@ static inline void cqm_pick_event_reader(int cpu)
 
 static void intel_cqm_cpu_prepare(unsigned int cpu)
 {
-	struct intel_cqm_state *state = &per_cpu(cqm_state, cpu);
+	struct intel_pqr_state *state = &per_cpu(pqr_state, cpu);
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 
-	raw_spin_lock_init(&state->lock);
 	state->rmid = 0;
-	state->cnt  = 0;
+	state->closid = 0;
+	state->rmid_usecnt = 0;
 
 	WARN_ON(c->x86_cache_max_rmid != cqm_max_rmid);
 	WARN_ON(c->x86_cache_occ_scale != cqm_l3_scale);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 813f75d71175..71fc40238843 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -11,7 +11,7 @@
 #define BTS_RECORD_SIZE		24
 
 #define BTS_BUFFER_SIZE		(PAGE_SIZE << 4)
-#define PEBS_BUFFER_SIZE	PAGE_SIZE
+#define PEBS_BUFFER_SIZE	(PAGE_SIZE << 4)
 #define PEBS_FIXUP_SIZE		PAGE_SIZE
 
 /*
@@ -250,7 +250,7 @@ static int alloc_pebs_buffer(int cpu)
 {
 	struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
 	int node = cpu_to_node(cpu);
-	int max, thresh = 1; /* always use a single PEBS record */
+	int max;
 	void *buffer, *ibuffer;
 
 	if (!x86_pmu.pebs)
@@ -280,9 +280,6 @@ static int alloc_pebs_buffer(int cpu)
 	ds->pebs_absolute_maximum = ds->pebs_buffer_base +
 		max * x86_pmu.pebs_record_size;
 
-	ds->pebs_interrupt_threshold = ds->pebs_buffer_base +
-		thresh * x86_pmu.pebs_record_size;
-
 	return 0;
 }
 
@@ -549,6 +546,19 @@ int intel_pmu_drain_bts_buffer(void)
 	return 1;
 }
 
+static inline void intel_pmu_drain_pebs_buffer(void)
+{
+	struct pt_regs regs;
+
+	x86_pmu.drain_pebs(&regs);
+}
+
+void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in)
+{
+	if (!sched_in)
+		intel_pmu_drain_pebs_buffer();
+}
+
 /*
  * PEBS
  */
@@ -684,33 +694,81 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event)
 	return &emptyconstraint;
 }
 
+static inline bool pebs_is_enabled(struct cpu_hw_events *cpuc)
+{
+	return (cpuc->pebs_enabled & ((1ULL << MAX_PEBS_EVENTS) - 1));
+}
+
 void intel_pmu_pebs_enable(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
+	struct debug_store *ds = cpuc->ds;
+	bool first_pebs;
+	u64 threshold;
 
 	hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT;
 
+	first_pebs = !pebs_is_enabled(cpuc);
 	cpuc->pebs_enabled |= 1ULL << hwc->idx;
 
 	if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT)
 		cpuc->pebs_enabled |= 1ULL << (hwc->idx + 32);
 	else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
 		cpuc->pebs_enabled |= 1ULL << 63;
+
+	/*
+	 * When the event is constrained enough we can use a larger
+	 * threshold and run the event with less frequent PMI.
+	 */
+	if (hwc->flags & PERF_X86_EVENT_FREERUNNING) {
+		threshold = ds->pebs_absolute_maximum -
+			x86_pmu.max_pebs_events * x86_pmu.pebs_record_size;
+
+		if (first_pebs)
+			perf_sched_cb_inc(event->ctx->pmu);
+	} else {
+		threshold = ds->pebs_buffer_base + x86_pmu.pebs_record_size;
+
+		/*
+		 * If not all events can use larger buffer,
+		 * roll back to threshold = 1
+		 */
+		if (!first_pebs &&
+		    (ds->pebs_interrupt_threshold > threshold))
+			perf_sched_cb_dec(event->ctx->pmu);
+	}
+
+	/* Use auto-reload if possible to save a MSR write in the PMI */
+	if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) {
+		ds->pebs_event_reset[hwc->idx] =
+			(u64)(-hwc->sample_period) & x86_pmu.cntval_mask;
+	}
+
+	if (first_pebs || ds->pebs_interrupt_threshold > threshold)
+		ds->pebs_interrupt_threshold = threshold;
 }
 
 void intel_pmu_pebs_disable(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
+	struct debug_store *ds = cpuc->ds;
 
 	cpuc->pebs_enabled &= ~(1ULL << hwc->idx);
 
-	if (event->hw.constraint->flags & PERF_X86_EVENT_PEBS_LDLAT)
+	if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT)
 		cpuc->pebs_enabled &= ~(1ULL << (hwc->idx + 32));
-	else if (event->hw.constraint->flags & PERF_X86_EVENT_PEBS_ST)
+	else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
 		cpuc->pebs_enabled &= ~(1ULL << 63);
 
+	if (ds->pebs_interrupt_threshold >
+	    ds->pebs_buffer_base + x86_pmu.pebs_record_size) {
+		intel_pmu_drain_pebs_buffer();
+		if (!pebs_is_enabled(cpuc))
+			perf_sched_cb_dec(event->ctx->pmu);
+	}
+
 	if (cpuc->enabled)
 		wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
 
@@ -846,8 +904,10 @@ static inline u64 intel_hsw_transaction(struct pebs_record_hsw *pebs)
 	return txn;
 }
 
-static void __intel_pmu_pebs_event(struct perf_event *event,
-				   struct pt_regs *iregs, void *__pebs)
+static void setup_pebs_sample_data(struct perf_event *event,
+				   struct pt_regs *iregs, void *__pebs,
+				   struct perf_sample_data *data,
+				   struct pt_regs *regs)
 {
 #define PERF_X86_EVENT_PEBS_HSW_PREC \
 		(PERF_X86_EVENT_PEBS_ST_HSW | \
@@ -859,13 +919,11 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 	 */
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct pebs_record_hsw *pebs = __pebs;
-	struct perf_sample_data data;
-	struct pt_regs regs;
 	u64 sample_type;
 	int fll, fst, dsrc;
 	int fl = event->hw.flags;
 
-	if (!intel_pmu_save_and_restart(event))
+	if (pebs == NULL)
 		return;
 
 	sample_type = event->attr.sample_type;
@@ -874,15 +932,15 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 	fll = fl & PERF_X86_EVENT_PEBS_LDLAT;
 	fst = fl & (PERF_X86_EVENT_PEBS_ST | PERF_X86_EVENT_PEBS_HSW_PREC);
 
-	perf_sample_data_init(&data, 0, event->hw.last_period);
+	perf_sample_data_init(data, 0, event->hw.last_period);
 
-	data.period = event->hw.last_period;
+	data->period = event->hw.last_period;
 
 	/*
 	 * Use latency for weight (only avail with PEBS-LL)
 	 */
 	if (fll && (sample_type & PERF_SAMPLE_WEIGHT))
-		data.weight = pebs->lat;
+		data->weight = pebs->lat;
 
 	/*
 	 * data.data_src encodes the data source
@@ -895,7 +953,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 			val = precise_datala_hsw(event, pebs->dse);
 		else if (fst)
 			val = precise_store_data(pebs->dse);
-		data.data_src.val = val;
+		data->data_src.val = val;
 	}
 
 	/*
@@ -908,61 +966,123 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 	 * PERF_SAMPLE_IP and PERF_SAMPLE_CALLCHAIN to function properly.
 	 * A possible PERF_SAMPLE_REGS will have to transfer all regs.
 	 */
-	regs = *iregs;
-	regs.flags = pebs->flags;
-	set_linear_ip(&regs, pebs->ip);
-	regs.bp = pebs->bp;
-	regs.sp = pebs->sp;
+	*regs = *iregs;
+	regs->flags = pebs->flags;
+	set_linear_ip(regs, pebs->ip);
+	regs->bp = pebs->bp;
+	regs->sp = pebs->sp;
 
 	if (sample_type & PERF_SAMPLE_REGS_INTR) {
-		regs.ax = pebs->ax;
-		regs.bx = pebs->bx;
-		regs.cx = pebs->cx;
-		regs.dx = pebs->dx;
-		regs.si = pebs->si;
-		regs.di = pebs->di;
-		regs.bp = pebs->bp;
-		regs.sp = pebs->sp;
-
-		regs.flags = pebs->flags;
+		regs->ax = pebs->ax;
+		regs->bx = pebs->bx;
+		regs->cx = pebs->cx;
+		regs->dx = pebs->dx;
+		regs->si = pebs->si;
+		regs->di = pebs->di;
+		regs->bp = pebs->bp;
+		regs->sp = pebs->sp;
+
+		regs->flags = pebs->flags;
 #ifndef CONFIG_X86_32
-		regs.r8 = pebs->r8;
-		regs.r9 = pebs->r9;
-		regs.r10 = pebs->r10;
-		regs.r11 = pebs->r11;
-		regs.r12 = pebs->r12;
-		regs.r13 = pebs->r13;
-		regs.r14 = pebs->r14;
-		regs.r15 = pebs->r15;
+		regs->r8 = pebs->r8;
+		regs->r9 = pebs->r9;
+		regs->r10 = pebs->r10;
+		regs->r11 = pebs->r11;
+		regs->r12 = pebs->r12;
+		regs->r13 = pebs->r13;
+		regs->r14 = pebs->r14;
+		regs->r15 = pebs->r15;
 #endif
 	}
 
 	if (event->attr.precise_ip > 1 && x86_pmu.intel_cap.pebs_format >= 2) {
-		regs.ip = pebs->real_ip;
-		regs.flags |= PERF_EFLAGS_EXACT;
-	} else if (event->attr.precise_ip > 1 && intel_pmu_pebs_fixup_ip(&regs))
-		regs.flags |= PERF_EFLAGS_EXACT;
+		regs->ip = pebs->real_ip;
+		regs->flags |= PERF_EFLAGS_EXACT;
+	} else if (event->attr.precise_ip > 1 && intel_pmu_pebs_fixup_ip(regs))
+		regs->flags |= PERF_EFLAGS_EXACT;
 	else
-		regs.flags &= ~PERF_EFLAGS_EXACT;
+		regs->flags &= ~PERF_EFLAGS_EXACT;
 
 	if ((sample_type & PERF_SAMPLE_ADDR) &&
 	    x86_pmu.intel_cap.pebs_format >= 1)
-		data.addr = pebs->dla;
+		data->addr = pebs->dla;
 
 	if (x86_pmu.intel_cap.pebs_format >= 2) {
 		/* Only set the TSX weight when no memory weight. */
 		if ((sample_type & PERF_SAMPLE_WEIGHT) && !fll)
-			data.weight = intel_hsw_weight(pebs);
+			data->weight = intel_hsw_weight(pebs);
 
 		if (sample_type & PERF_SAMPLE_TRANSACTION)
-			data.txn = intel_hsw_transaction(pebs);
+			data->txn = intel_hsw_transaction(pebs);
 	}
 
 	if (has_branch_stack(event))
-		data.br_stack = &cpuc->lbr_stack;
+		data->br_stack = &cpuc->lbr_stack;
+}
+
+static inline void *
+get_next_pebs_record_by_bit(void *base, void *top, int bit)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	void *at;
+	u64 pebs_status;
+
+	if (base == NULL)
+		return NULL;
+
+	for (at = base; at < top; at += x86_pmu.pebs_record_size) {
+		struct pebs_record_nhm *p = at;
 
-	if (perf_event_overflow(event, &data, &regs))
+		if (test_bit(bit, (unsigned long *)&p->status)) {
+			/* PEBS v3 has accurate status bits */
+			if (x86_pmu.intel_cap.pebs_format >= 3)
+				return at;
+
+			if (p->status == (1 << bit))
+				return at;
+
+			/* clear non-PEBS bit and re-check */
+			pebs_status = p->status & cpuc->pebs_enabled;
+			pebs_status &= (1ULL << MAX_PEBS_EVENTS) - 1;
+			if (pebs_status == (1 << bit))
+				return at;
+		}
+	}
+	return NULL;
+}
+
+static void __intel_pmu_pebs_event(struct perf_event *event,
+				   struct pt_regs *iregs,
+				   void *base, void *top,
+				   int bit, int count)
+{
+	struct perf_sample_data data;
+	struct pt_regs regs;
+	void *at = get_next_pebs_record_by_bit(base, top, bit);
+
+	if (!intel_pmu_save_and_restart(event) &&
+	    !(event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD))
+		return;
+
+	while (count > 1) {
+		setup_pebs_sample_data(event, iregs, at, &data, &regs);
+		perf_event_output(event, &data, &regs);
+		at += x86_pmu.pebs_record_size;
+		at = get_next_pebs_record_by_bit(at, top, bit);
+		count--;
+	}
+
+	setup_pebs_sample_data(event, iregs, at, &data, &regs);
+
+	/*
+	 * All but the last records are processed.
+	 * The last one is left to be able to call the overflow handler.
+	 */
+	if (perf_event_overflow(event, &data, &regs)) {
 		x86_pmu_stop(event, 0);
+		return;
+	}
+
 }
 
 static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
@@ -992,72 +1112,99 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
 	if (!event->attr.precise_ip)
 		return;
 
-	n = top - at;
+	n = (top - at) / x86_pmu.pebs_record_size;
 	if (n <= 0)
 		return;
 
-	/*
-	 * Should not happen, we program the threshold at 1 and do not
-	 * set a reset value.
-	 */
-	WARN_ONCE(n > 1, "bad leftover pebs %d\n", n);
-	at += n - 1;
-
-	__intel_pmu_pebs_event(event, iregs, at);
+	__intel_pmu_pebs_event(event, iregs, at, top, 0, n);
 }
 
 static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct debug_store *ds = cpuc->ds;
-	struct perf_event *event = NULL;
-	void *at, *top;
-	u64 status = 0;
-	int bit;
+	struct perf_event *event;
+	void *base, *at, *top;
+	short counts[MAX_PEBS_EVENTS] = {};
+	short error[MAX_PEBS_EVENTS] = {};
+	int bit, i;
 
 	if (!x86_pmu.pebs_active)
 		return;
 
-	at  = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base;
+	base = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base;
 	top = (struct pebs_record_nhm *)(unsigned long)ds->pebs_index;
 
 	ds->pebs_index = ds->pebs_buffer_base;
 
-	if (unlikely(at > top))
+	if (unlikely(base >= top))
 		return;
 
-	/*
-	 * Should not happen, we program the threshold at 1 and do not
-	 * set a reset value.
-	 */
-	WARN_ONCE(top - at > x86_pmu.max_pebs_events * x86_pmu.pebs_record_size,
-		  "Unexpected number of pebs records %ld\n",
-		  (long)(top - at) / x86_pmu.pebs_record_size);
-
-	for (; at < top; at += x86_pmu.pebs_record_size) {
+	for (at = base; at < top; at += x86_pmu.pebs_record_size) {
 		struct pebs_record_nhm *p = at;
 
-		for_each_set_bit(bit, (unsigned long *)&p->status,
-				 x86_pmu.max_pebs_events) {
-			event = cpuc->events[bit];
-			if (!test_bit(bit, cpuc->active_mask))
-				continue;
-
-			WARN_ON_ONCE(!event);
+		/* PEBS v3 has accurate status bits */
+		if (x86_pmu.intel_cap.pebs_format >= 3) {
+			for_each_set_bit(bit, (unsigned long *)&p->status,
+					 MAX_PEBS_EVENTS)
+				counts[bit]++;
 
-			if (!event->attr.precise_ip)
-				continue;
+			continue;
+		}
 
-			if (__test_and_set_bit(bit, (unsigned long *)&status))
+		bit = find_first_bit((unsigned long *)&p->status,
+					x86_pmu.max_pebs_events);
+		if (bit >= x86_pmu.max_pebs_events)
+			continue;
+		if (!test_bit(bit, cpuc->active_mask))
+			continue;
+		/*
+		 * The PEBS hardware does not deal well with the situation
+		 * when events happen near to each other and multiple bits
+		 * are set. But it should happen rarely.
+		 *
+		 * If these events include one PEBS and multiple non-PEBS
+		 * events, it doesn't impact PEBS record. The record will
+		 * be handled normally. (slow path)
+		 *
+		 * If these events include two or more PEBS events, the
+		 * records for the events can be collapsed into a single
+		 * one, and it's not possible to reconstruct all events
+		 * that caused the PEBS record. It's called collision.
+		 * If collision happened, the record will be dropped.
+		 *
+		 */
+		if (p->status != (1 << bit)) {
+			u64 pebs_status;
+
+			/* slow path */
+			pebs_status = p->status & cpuc->pebs_enabled;
+			pebs_status &= (1ULL << MAX_PEBS_EVENTS) - 1;
+			if (pebs_status != (1 << bit)) {
+				for_each_set_bit(i, (unsigned long *)&pebs_status,
+						 MAX_PEBS_EVENTS)
+					error[i]++;
 				continue;
-
-			break;
+			}
 		}
+		counts[bit]++;
+	}
 
-		if (!event || bit >= x86_pmu.max_pebs_events)
+	for (bit = 0; bit < x86_pmu.max_pebs_events; bit++) {
+		if ((counts[bit] == 0) && (error[bit] == 0))
 			continue;
+		event = cpuc->events[bit];
+		WARN_ON_ONCE(!event);
+		WARN_ON_ONCE(!event->attr.precise_ip);
 
-		__intel_pmu_pebs_event(event, iregs, at);
+		/* log dropped samples number */
+		if (error[bit])
+			perf_log_lost_samples(event, error[bit]);
+
+		if (counts[bit]) {
+			__intel_pmu_pebs_event(event, iregs, base,
+					       top, bit, counts[bit]);
+		}
 	}
 }
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index 94e5b506caa6..452a7bd2dedb 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -96,6 +96,7 @@ enum {
 	X86_BR_NO_TX		= 1 << 14,/* not in transaction */
 	X86_BR_ZERO_CALL	= 1 << 15,/* zero length call */
 	X86_BR_CALL_STACK	= 1 << 16,/* call stack */
+	X86_BR_IND_JMP		= 1 << 17,/* indirect jump */
 };
 
 #define X86_BR_PLM (X86_BR_USER | X86_BR_KERNEL)
@@ -113,6 +114,7 @@ enum {
 	 X86_BR_IRQ	 |\
 	 X86_BR_ABORT	 |\
 	 X86_BR_IND_CALL |\
+	 X86_BR_IND_JMP  |\
 	 X86_BR_ZERO_CALL)
 
 #define X86_BR_ALL (X86_BR_PLM | X86_BR_ANY)
@@ -262,9 +264,6 @@ void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in)
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct x86_perf_task_context *task_ctx;
 
-	if (!x86_pmu.lbr_nr)
-		return;
-
 	/*
 	 * If LBR callstack feature is enabled and the stack was saved when
 	 * the task was scheduled out, restore the stack. Otherwise flush
@@ -523,6 +522,9 @@ static int intel_pmu_setup_sw_lbr_filter(struct perf_event *event)
 			X86_BR_CALL_STACK;
 	}
 
+	if (br_type & PERF_SAMPLE_BRANCH_IND_JUMP)
+		mask |= X86_BR_IND_JMP;
+
 	/*
 	 * stash actual user request into reg, it may
 	 * be used by fixup code for some CPU
@@ -736,7 +738,7 @@ static int branch_type(unsigned long from, unsigned long to, int abort)
 			break;
 		case 4:
 		case 5:
-			ret = X86_BR_JMP;
+			ret = X86_BR_IND_JMP;
 			break;
 		}
 		break;
@@ -844,6 +846,7 @@ static const int nhm_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = {
 	 */
 	[PERF_SAMPLE_BRANCH_IND_CALL_SHIFT] = LBR_IND_CALL | LBR_IND_JMP,
 	[PERF_SAMPLE_BRANCH_COND_SHIFT]     = LBR_JCC,
+	[PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT] = LBR_IND_JMP,
 };
 
 static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = {
@@ -856,6 +859,7 @@ static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = {
 						| LBR_FAR,
 	[PERF_SAMPLE_BRANCH_IND_CALL_SHIFT]	= LBR_IND_CALL,
 	[PERF_SAMPLE_BRANCH_COND_SHIFT]		= LBR_JCC,
+	[PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT]	= LBR_IND_JMP,
 };
 
 static const int hsw_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = {
@@ -870,6 +874,7 @@ static const int hsw_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = {
 	[PERF_SAMPLE_BRANCH_COND_SHIFT]		= LBR_JCC,
 	[PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT]	= LBR_REL_CALL | LBR_IND_CALL
 						| LBR_RETURN | LBR_CALL_STACK,
+	[PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT]	= LBR_IND_JMP,
 };
 
 /* core */
diff --git a/arch/x86/kernel/cpu/perf_event_intel_pt.c b/arch/x86/kernel/cpu/perf_event_intel_pt.c
index ffe666c2c6b5..183de719628d 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_pt.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_pt.c
@@ -151,7 +151,7 @@ static int __init pt_pmu_hw_init(void)
 
 		de_attr->attr.attr.name = pt_caps[i].name;
 
-		sysfs_attr_init(&de_attrs->attr.attr);
+		sysfs_attr_init(&de_attr->attr.attr);
 
 		de_attr->attr.attr.mode		= S_IRUGO;
 		de_attr->attr.show		= pt_cap_show;
@@ -187,15 +187,6 @@ static bool pt_event_valid(struct perf_event *event)
  * These all are cpu affine and operate on a local PT
  */
 
-static bool pt_is_running(void)
-{
-	u64 ctl;
-
-	rdmsrl(MSR_IA32_RTIT_CTL, ctl);
-
-	return !!(ctl & RTIT_CTL_TRACEEN);
-}
-
 static void pt_config(struct perf_event *event)
 {
 	u64 reg;
@@ -609,16 +600,19 @@ static unsigned int pt_topa_next_entry(struct pt_buffer *buf, unsigned int pg)
  * @handle:	Current output handle.
  *
  * Place INT and STOP marks to prevent overwriting old data that the consumer
- * hasn't yet collected.
+ * hasn't yet collected and waking up the consumer after a certain fraction of
+ * the buffer has filled up. Only needed and sensible for non-snapshot counters.
+ *
+ * This obviously relies on buf::head to figure out buffer markers, so it has
+ * to be called after pt_buffer_reset_offsets() and before the hardware tracing
+ * is enabled.
  */
 static int pt_buffer_reset_markers(struct pt_buffer *buf,
 				   struct perf_output_handle *handle)
 
 {
-	unsigned long idx, npages, end;
-
-	if (buf->snapshot)
-		return 0;
+	unsigned long head = local64_read(&buf->head);
+	unsigned long idx, npages, wakeup;
 
 	/* can't stop in the middle of an output region */
 	if (buf->output_off + handle->size + 1 <
@@ -634,17 +628,26 @@ static int pt_buffer_reset_markers(struct pt_buffer *buf,
 	buf->topa_index[buf->stop_pos]->stop = 0;
 	buf->topa_index[buf->intr_pos]->intr = 0;
 
-	if (pt_cap_get(PT_CAP_topa_multiple_entries)) {
-		npages = (handle->size + 1) >> PAGE_SHIFT;
-		end = (local64_read(&buf->head) >> PAGE_SHIFT) + npages;
-		/*if (end > handle->wakeup >> PAGE_SHIFT)
-		  end = handle->wakeup >> PAGE_SHIFT;*/
-		idx = end & (buf->nr_pages - 1);
-		buf->stop_pos = idx;
-		idx = (local64_read(&buf->head) >> PAGE_SHIFT) + npages - 1;
-		idx &= buf->nr_pages - 1;
-		buf->intr_pos = idx;
-	}
+	/* how many pages till the STOP marker */
+	npages = handle->size >> PAGE_SHIFT;
+
+	/* if it's on a page boundary, fill up one more page */
+	if (!offset_in_page(head + handle->size + 1))
+		npages++;
+
+	idx = (head >> PAGE_SHIFT) + npages;
+	idx &= buf->nr_pages - 1;
+	buf->stop_pos = idx;
+
+	wakeup = handle->wakeup >> PAGE_SHIFT;
+
+	/* in the worst case, wake up the consumer one page before hard stop */
+	idx = (head >> PAGE_SHIFT) + npages - 1;
+	if (idx > wakeup)
+		idx = wakeup;
+
+	idx &= buf->nr_pages - 1;
+	buf->intr_pos = idx;
 
 	buf->topa_index[buf->stop_pos]->stop = 1;
 	buf->topa_index[buf->intr_pos]->intr = 1;
@@ -664,7 +667,7 @@ static void pt_buffer_setup_topa_index(struct pt_buffer *buf)
 	struct topa *cur = buf->first, *prev = buf->last;
 	struct topa_entry *te_cur = TOPA_ENTRY(cur, 0),
 		*te_prev = TOPA_ENTRY(prev, prev->last - 1);
-	int pg = 0, idx = 0, ntopa = 0;
+	int pg = 0, idx = 0;
 
 	while (pg < buf->nr_pages) {
 		int tidx;
@@ -679,9 +682,9 @@ static void pt_buffer_setup_topa_index(struct pt_buffer *buf)
 			/* advance to next topa table */
 			idx = 0;
 			cur = list_entry(cur->list.next, struct topa, list);
-			ntopa++;
-		} else
+		} else {
 			idx++;
+		}
 		te_cur = TOPA_ENTRY(cur, idx);
 	}
 
@@ -693,7 +696,14 @@ static void pt_buffer_setup_topa_index(struct pt_buffer *buf)
  * @head:	Write pointer (aux_head) from AUX buffer.
  *
  * Find the ToPA table and entry corresponding to given @head and set buffer's
- * "current" pointers accordingly.
+ * "current" pointers accordingly. This is done after we have obtained the
+ * current aux_head position from a successful call to perf_aux_output_begin()
+ * to make sure the hardware is writing to the right place.
+ *
+ * This function modifies buf::{cur,cur_idx,output_off} that will be programmed
+ * into PT msrs when the tracing is enabled and buf::head and buf::data_size,
+ * which are used to determine INT and STOP markers' locations by a subsequent
+ * call to pt_buffer_reset_markers().
  */
 static void pt_buffer_reset_offsets(struct pt_buffer *buf, unsigned long head)
 {
@@ -891,6 +901,7 @@ void intel_pt_interrupt(void)
 		}
 
 		pt_buffer_reset_offsets(buf, pt->handle.head);
+		/* snapshot counters don't use PMI, so it's safe */
 		ret = pt_buffer_reset_markers(buf, &pt->handle);
 		if (ret) {
 			perf_aux_output_end(&pt->handle, 0, true);
@@ -913,7 +924,7 @@ static void pt_event_start(struct perf_event *event, int mode)
 	struct pt *pt = this_cpu_ptr(&pt_ctx);
 	struct pt_buffer *buf = perf_get_aux(&pt->handle);
 
-	if (pt_is_running() || !buf || pt_buffer_is_full(buf, pt)) {
+	if (!buf || pt_buffer_is_full(buf, pt)) {
 		event->hw.state = PERF_HES_STOPPED;
 		return;
 	}
@@ -944,7 +955,6 @@ static void pt_event_stop(struct perf_event *event, int mode)
 	event->hw.state = PERF_HES_STOPPED;
 
 	if (mode & PERF_EF_UPDATE) {
-		struct pt *pt = this_cpu_ptr(&pt_ctx);
 		struct pt_buffer *buf = perf_get_aux(&pt->handle);
 
 		if (!buf)
@@ -1096,5 +1106,4 @@ static __init int pt_init(void)
 
 	return ret;
 }
-
-module_init(pt_init);
+arch_initcall(pt_init);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
index 999289b94025..5cbd4e64feb5 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -204,9 +204,8 @@ again:
 
 static void rapl_start_hrtimer(struct rapl_pmu *pmu)
 {
-	__hrtimer_start_range_ns(&pmu->hrtimer,
-			pmu->timer_interval, 0,
-			HRTIMER_MODE_REL_PINNED, 0);
+       hrtimer_start(&pmu->hrtimer, pmu->timer_interval,
+		     HRTIMER_MODE_REL_PINNED);
 }
 
 static void rapl_stop_hrtimer(struct rapl_pmu *pmu)
@@ -722,6 +721,7 @@ static int __init rapl_pmu_init(void)
 		break;
 	case 60: /* Haswell */
 	case 69: /* Haswell-Celeron */
+	case 61: /* Broadwell */
 		rapl_cntr_mask = RAPL_IDX_HSW;
 		rapl_pmu_events_group.attrs = rapl_events_hsw_attr;
 		break;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index c635b8b49e93..21b5e38c921b 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -233,9 +233,8 @@ static enum hrtimer_restart uncore_pmu_hrtimer(struct hrtimer *hrtimer)
 
 void uncore_pmu_start_hrtimer(struct intel_uncore_box *box)
 {
-	__hrtimer_start_range_ns(&box->hrtimer,
-			ns_to_ktime(box->hrtimer_duration), 0,
-			HRTIMER_MODE_REL_PINNED, 0);
+	hrtimer_start(&box->hrtimer, ns_to_ktime(box->hrtimer_duration),
+		      HRTIMER_MODE_REL_PINNED);
 }
 
 void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box)
@@ -365,9 +364,8 @@ static int uncore_assign_events(struct intel_uncore_box *box, int assign[], int
 	bitmap_zero(used_mask, UNCORE_PMC_IDX_MAX);
 
 	for (i = 0, wmin = UNCORE_PMC_IDX_MAX, wmax = 0; i < n; i++) {
-		hwc = &box->event_list[i]->hw;
 		c = uncore_get_event_constraint(box, box->event_list[i]);
-		hwc->constraint = c;
+		box->event_constraint[i] = c;
 		wmin = min(wmin, c->weight);
 		wmax = max(wmax, c->weight);
 	}
@@ -375,7 +373,7 @@ static int uncore_assign_events(struct intel_uncore_box *box, int assign[], int
 	/* fastpath, try to reuse previous register */
 	for (i = 0; i < n; i++) {
 		hwc = &box->event_list[i]->hw;
-		c = hwc->constraint;
+		c = box->event_constraint[i];
 
 		/* never assigned */
 		if (hwc->idx == -1)
@@ -395,8 +393,8 @@ static int uncore_assign_events(struct intel_uncore_box *box, int assign[], int
 	}
 	/* slow path */
 	if (i != n)
-		ret = perf_assign_events(box->event_list, n,
-					 wmin, wmax, assign);
+		ret = perf_assign_events(box->event_constraint, n,
+					 wmin, wmax, n, assign);
 
 	if (!assign || ret) {
 		for (i = 0; i < n; i++)
@@ -840,6 +838,7 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id
 	box->phys_id = phys_id;
 	box->pci_dev = pdev;
 	box->pmu = pmu;
+	uncore_box_init(box);
 	pci_set_drvdata(pdev, box);
 
 	raw_spin_lock(&uncore_box_lock);
@@ -922,6 +921,9 @@ static int __init uncore_pci_init(void)
 	case 69: /* Haswell Celeron */
 		ret = hsw_uncore_pci_init();
 		break;
+	case 61: /* Broadwell */
+		ret = bdw_uncore_pci_init();
+		break;
 	default:
 		return 0;
 	}
@@ -1003,8 +1005,10 @@ static int uncore_cpu_starting(int cpu)
 			pmu = &type->pmus[j];
 			box = *per_cpu_ptr(pmu->box, cpu);
 			/* called by uncore_cpu_init? */
-			if (box && box->phys_id >= 0)
+			if (box && box->phys_id >= 0) {
+				uncore_box_init(box);
 				continue;
+			}
 
 			for_each_online_cpu(k) {
 				exist = *per_cpu_ptr(pmu->box, k);
@@ -1020,8 +1024,10 @@ static int uncore_cpu_starting(int cpu)
 				}
 			}
 
-			if (box)
+			if (box) {
 				box->phys_id = phys_id;
+				uncore_box_init(box);
+			}
 		}
 	}
 	return 0;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
index 6c8c1e7e69d8..0f77f0a196e4 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -97,6 +97,7 @@ struct intel_uncore_box {
 	atomic_t refcnt;
 	struct perf_event *events[UNCORE_PMC_IDX_MAX];
 	struct perf_event *event_list[UNCORE_PMC_IDX_MAX];
+	struct event_constraint *event_constraint[UNCORE_PMC_IDX_MAX];
 	unsigned long active_mask[BITS_TO_LONGS(UNCORE_PMC_IDX_MAX)];
 	u64 tags[UNCORE_PMC_IDX_MAX];
 	struct pci_dev *pci_dev;
@@ -257,14 +258,6 @@ static inline int uncore_num_counters(struct intel_uncore_box *box)
 	return box->pmu->type->num_counters;
 }
 
-static inline void uncore_box_init(struct intel_uncore_box *box)
-{
-	if (!test_and_set_bit(UNCORE_BOX_FLAG_INITIATED, &box->flags)) {
-		if (box->pmu->type->ops->init_box)
-			box->pmu->type->ops->init_box(box);
-	}
-}
-
 static inline void uncore_disable_box(struct intel_uncore_box *box)
 {
 	if (box->pmu->type->ops->disable_box)
@@ -273,8 +266,6 @@ static inline void uncore_disable_box(struct intel_uncore_box *box)
 
 static inline void uncore_enable_box(struct intel_uncore_box *box)
 {
-	uncore_box_init(box);
-
 	if (box->pmu->type->ops->enable_box)
 		box->pmu->type->ops->enable_box(box);
 }
@@ -297,6 +288,14 @@ static inline u64 uncore_read_counter(struct intel_uncore_box *box,
 	return box->pmu->type->ops->read_counter(box, event);
 }
 
+static inline void uncore_box_init(struct intel_uncore_box *box)
+{
+	if (!test_and_set_bit(UNCORE_BOX_FLAG_INITIATED, &box->flags)) {
+		if (box->pmu->type->ops->init_box)
+			box->pmu->type->ops->init_box(box);
+	}
+}
+
 static inline bool uncore_box_is_fake(struct intel_uncore_box *box)
 {
 	return (box->phys_id < 0);
@@ -326,6 +325,7 @@ extern struct event_constraint uncore_constraint_empty;
 int snb_uncore_pci_init(void);
 int ivb_uncore_pci_init(void);
 int hsw_uncore_pci_init(void);
+int bdw_uncore_pci_init(void);
 void snb_uncore_cpu_init(void);
 void nhm_uncore_cpu_init(void);
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
index 3001015b755c..b005a78c7012 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
@@ -1,6 +1,14 @@
 /* Nehalem/SandBridge/Haswell uncore support */
 #include "perf_event_intel_uncore.h"
 
+/* Uncore IMC PCI IDs */
+#define PCI_DEVICE_ID_INTEL_SNB_IMC	0x0100
+#define PCI_DEVICE_ID_INTEL_IVB_IMC	0x0154
+#define PCI_DEVICE_ID_INTEL_IVB_E3_IMC	0x0150
+#define PCI_DEVICE_ID_INTEL_HSW_IMC	0x0c00
+#define PCI_DEVICE_ID_INTEL_HSW_U_IMC	0x0a04
+#define PCI_DEVICE_ID_INTEL_BDW_IMC	0x1604
+
 /* SNB event control */
 #define SNB_UNC_CTL_EV_SEL_MASK			0x000000ff
 #define SNB_UNC_CTL_UMASK_MASK			0x0000ff00
@@ -472,6 +480,18 @@ static const struct pci_device_id hsw_uncore_pci_ids[] = {
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_HSW_IMC),
 		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
 	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_HSW_U_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* end: all zeroes */ },
+};
+
+static const struct pci_device_id bdw_uncore_pci_ids[] = {
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BDW_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
 	{ /* end: all zeroes */ },
 };
 
@@ -490,6 +510,11 @@ static struct pci_driver hsw_uncore_pci_driver = {
 	.id_table	= hsw_uncore_pci_ids,
 };
 
+static struct pci_driver bdw_uncore_pci_driver = {
+	.name		= "bdw_uncore",
+	.id_table	= bdw_uncore_pci_ids,
+};
+
 struct imc_uncore_pci_dev {
 	__u32 pci_id;
 	struct pci_driver *driver;
@@ -502,6 +527,8 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = {
 	IMC_DEV(IVB_IMC, &ivb_uncore_pci_driver),    /* 3rd Gen Core processor */
 	IMC_DEV(IVB_E3_IMC, &ivb_uncore_pci_driver), /* Xeon E3-1200 v2/3rd Gen Core processor */
 	IMC_DEV(HSW_IMC, &hsw_uncore_pci_driver),    /* 4th Gen Core Processor */
+	IMC_DEV(HSW_U_IMC, &hsw_uncore_pci_driver),  /* 4th Gen Core ULT Mobile Processor */
+	IMC_DEV(BDW_IMC, &bdw_uncore_pci_driver),    /* 5th Gen Core U */
 	{  /* end marker */ }
 };
 
@@ -549,6 +576,11 @@ int hsw_uncore_pci_init(void)
 	return imc_uncore_pci_init();
 }
 
+int bdw_uncore_pci_init(void)
+{
+	return imc_uncore_pci_init();
+}
+
 /* end of Sandy Bridge uncore support */
 
 /* Nehalem uncore support */
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
index 12d9548457e7..6d6e85dd5849 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
@@ -164,8 +164,8 @@
 				((1ULL << (n)) - 1)))
 
 /* Haswell-EP Ubox */
-#define HSWEP_U_MSR_PMON_CTR0			0x705
-#define HSWEP_U_MSR_PMON_CTL0			0x709
+#define HSWEP_U_MSR_PMON_CTR0			0x709
+#define HSWEP_U_MSR_PMON_CTL0			0x705
 #define HSWEP_U_MSR_PMON_FILTER			0x707
 
 #define HSWEP_U_MSR_PMON_UCLK_FIXED_CTL		0x703
@@ -1914,7 +1914,7 @@ static struct intel_uncore_type hswep_uncore_cbox = {
 	.name			= "cbox",
 	.num_counters		= 4,
 	.num_boxes		= 18,
-	.perf_ctr_bits		= 44,
+	.perf_ctr_bits		= 48,
 	.event_ctl		= HSWEP_C0_MSR_PMON_CTL0,
 	.perf_ctr		= HSWEP_C0_MSR_PMON_CTR0,
 	.event_mask		= SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK,
diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c
index e7d8c7608471..18ca99f2798b 100644
--- a/arch/x86/kernel/cpu/proc.c
+++ b/arch/x86/kernel/cpu/proc.c
@@ -12,7 +12,8 @@ static void show_cpuinfo_core(struct seq_file *m, struct cpuinfo_x86 *c,
 {
 #ifdef CONFIG_SMP
 	seq_printf(m, "physical id\t: %d\n", c->phys_proc_id);
-	seq_printf(m, "siblings\t: %d\n", cpumask_weight(cpu_core_mask(cpu)));
+	seq_printf(m, "siblings\t: %d\n",
+		   cpumask_weight(topology_core_cpumask(cpu)));
 	seq_printf(m, "core id\t\t: %d\n", c->cpu_core_id);
 	seq_printf(m, "cpu cores\t: %d\n", c->booted_cores);
 	seq_printf(m, "apicid\t\t: %d\n", c->apicid);
author	Tony Lindgren <tony@atomide.com>	2015-07-06 14:33:17 +0200
committer	Tony Lindgren <tony@atomide.com>	2015-07-06 14:33:17 +0200
commit	ae745302c0a3e2b5b768690f631fc14db44467e7 (patch)
tree	1db4d210a7419286b447dc09fa7400a561d55f42 /arch/x86/kernel/cpu
parent	ARM: OMAP2+: Remove unnessary return statement from the void function, omap2_... (diff)
parent	ARM: dts: am4372.dtsi: disable rfbi (diff)
download	linux-ae745302c0a3e2b5b768690f631fc14db44467e7.tar.xz linux-ae745302c0a3e2b5b768690f631fc14db44467e7.zip