Merge branch 'linus' into timers/core

Reason: Get upstream fixes before adding conflicting code.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

8 files changed, 137 insertions, 61 deletions

diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index a7d26d83fb70..8f4be53ea04b 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -35,13 +35,6 @@ static bool __init ms_hyperv_platform(void)
 	if (!boot_cpu_has(X86_FEATURE_HYPERVISOR))
 		return false;
 
-	/*
-	 * Xen emulates Hyper-V to support enlightened Windows.
-	 * Check to see first if we are on a Xen Hypervisor.
-	 */
-	if (xen_cpuid_base())
-		return false;
-
 	cpuid(HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS,
 	      &eax, &hyp_signature[0], &hyp_signature[1], &hyp_signature[2]);
 
@@ -82,12 +75,6 @@ static void __init ms_hyperv_init_platform(void)
 
 	if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE)
 		clocksource_register_hz(&hyperv_cs, NSEC_PER_SEC/100);
-#if IS_ENABLED(CONFIG_HYPERV)
-	/*
-	 * Setup the IDT for hypervisor callback.
-	 */
-	alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, hyperv_callback_vector);
-#endif
 }
 
 const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = {
@@ -103,6 +90,11 @@ static irq_handler_t vmbus_isr;
 
 void hv_register_vmbus_handler(int irq, irq_handler_t handler)
 {
+	/*
+	 * Setup the IDT for hypervisor callback.
+	 */
+	alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, hyperv_callback_vector);
+
 	vmbus_irq = irq;
 	vmbus_isr = handler;
 }
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 529c8931fc02..cc45deb791b0 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -101,6 +101,10 @@ static struct event_constraint intel_snb_event_constraints[] __read_mostly =
 	FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
 	FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
 	FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */
+	INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf), /* CYCLE_ACTIVITY.CYCLES_NO_DISPATCH */
+	INTEL_UEVENT_CONSTRAINT(0x05a3, 0xf), /* CYCLE_ACTIVITY.STALLS_L2_PENDING */
+	INTEL_UEVENT_CONSTRAINT(0x02a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */
+	INTEL_UEVENT_CONSTRAINT(0x06a3, 0x4), /* CYCLE_ACTIVITY.STALLS_L1D_PENDING */
 	INTEL_EVENT_CONSTRAINT(0x48, 0x4), /* L1D_PEND_MISS.PENDING */
 	INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */
 	INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.LOAD_LATENCY */
@@ -149,8 +153,14 @@ static struct event_constraint intel_gen_event_constraints[] __read_mostly =
 };
 
 static struct extra_reg intel_snb_extra_regs[] __read_mostly = {
-	INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3fffffffffull, RSP_0),
-	INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3fffffffffull, RSP_1),
+	INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3f807f8fffull, RSP_0),
+	INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3f807f8fffull, RSP_1),
+	EVENT_EXTRA_END
+};
+
+static struct extra_reg intel_snbep_extra_regs[] __read_mostly = {
+	INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3fffff8fffull, RSP_0),
+	INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3fffff8fffull, RSP_1),
 	EVENT_EXTRA_END
 };
 
@@ -2093,7 +2103,10 @@ __init int intel_pmu_init(void)
 		x86_pmu.event_constraints = intel_snb_event_constraints;
 		x86_pmu.pebs_constraints = intel_snb_pebs_event_constraints;
 		x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
-		x86_pmu.extra_regs = intel_snb_extra_regs;
+		if (boot_cpu_data.x86_model == 45)
+			x86_pmu.extra_regs = intel_snbep_extra_regs;
+		else
+			x86_pmu.extra_regs = intel_snb_extra_regs;
 		/* all extra regs are per-cpu when HT is on */
 		x86_pmu.er_flags |= ERF_HAS_RSP_1;
 		x86_pmu.er_flags |= ERF_NO_HT_SHARING;
@@ -2119,7 +2132,10 @@ __init int intel_pmu_init(void)
 		x86_pmu.event_constraints = intel_ivb_event_constraints;
 		x86_pmu.pebs_constraints = intel_ivb_pebs_event_constraints;
 		x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
-		x86_pmu.extra_regs = intel_snb_extra_regs;
+		if (boot_cpu_data.x86_model == 62)
+			x86_pmu.extra_regs = intel_snbep_extra_regs;
+		else
+			x86_pmu.extra_regs = intel_snb_extra_regs;
 		/* all extra regs are per-cpu when HT is on */
 		x86_pmu.er_flags |= ERF_HAS_RSP_1;
 		x86_pmu.er_flags |= ERF_NO_HT_SHARING;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 826054a4f2ee..26830f3af0df 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -314,10 +314,11 @@ int intel_pmu_drain_bts_buffer(void)
 	if (top <= at)
 		return 0;
 
+	memset(&regs, 0, sizeof(regs));
+
 	ds->bts_index = ds->bts_buffer_base;
 
 	perf_sample_data_init(&data, 0, event->hw.last_period);
-	regs.ip     = 0;
 
 	/*
 	 * Prepare a generic sample, i.e. fill in the invariant fields.
@@ -729,3 +730,13 @@ void intel_ds_init(void)
 		}
 	}
 }
+
+void perf_restore_debug_store(void)
+{
+	struct debug_store *ds = __this_cpu_read(cpu_hw_events.ds);
+
+	if (!x86_pmu.bts && !x86_pmu.pebs)
+		return;
+
+	wrmsrl(MSR_IA32_DS_AREA, (unsigned long)ds);
+}
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 3f06e6149981..7bfe318d3d8a 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -375,6 +375,9 @@ static void __kprobes arch_copy_kprobe(struct kprobe *p)
 	else
 		p->ainsn.boostable = -1;
 
+	/* Check whether the instruction modifies Interrupt Flag or not */
+	p->ainsn.if_modifier = is_IF_modifier(p->ainsn.insn);
+
 	/* Also, displacement change doesn't affect the first byte */
 	p->opcode = p->ainsn.insn[0];
 }
@@ -434,7 +437,7 @@ static void __kprobes set_current_kprobe(struct kprobe *p, struct pt_regs *regs,
 	__this_cpu_write(current_kprobe, p);
 	kcb->kprobe_saved_flags = kcb->kprobe_old_flags
 		= (regs->flags & (X86_EFLAGS_TF | X86_EFLAGS_IF));
-	if (is_IF_modifier(p->ainsn.insn))
+	if (p->ainsn.if_modifier)
 		kcb->kprobe_saved_flags &= ~X86_EFLAGS_IF;
 }
 
diff --git a/arch/x86/kernel/microcode_core_early.c b/arch/x86/kernel/microcode_core_early.c
index 577db8417d15..833d51d6ee06 100644
--- a/arch/x86/kernel/microcode_core_early.c
+++ b/arch/x86/kernel/microcode_core_early.c
@@ -45,9 +45,6 @@ static int __cpuinit x86_vendor(void)
 	u32 eax = 0x00000000;
 	u32 ebx, ecx = 0, edx;
 
-	if (!have_cpuid_p())
-		return X86_VENDOR_UNKNOWN;
-
 	native_cpuid(&eax, &ebx, &ecx, &edx);
 
 	if (CPUID_IS(CPUID_INTEL1, CPUID_INTEL2, CPUID_INTEL3, ebx, ecx, edx))
@@ -59,18 +56,45 @@ static int __cpuinit x86_vendor(void)
 	return X86_VENDOR_UNKNOWN;
 }
 
+static int __cpuinit x86_family(void)
+{
+	u32 eax = 0x00000001;
+	u32 ebx, ecx = 0, edx;
+	int x86;
+
+	native_cpuid(&eax, &ebx, &ecx, &edx);
+
+	x86 = (eax >> 8) & 0xf;
+	if (x86 == 15)
+		x86 += (eax >> 20) & 0xff;
+
+	return x86;
+}
+
 void __init load_ucode_bsp(void)
 {
-	int vendor = x86_vendor();
+	int vendor, x86;
+
+	if (!have_cpuid_p())
+		return;
 
-	if (vendor == X86_VENDOR_INTEL)
+	vendor = x86_vendor();
+	x86 = x86_family();
+
+	if (vendor == X86_VENDOR_INTEL && x86 >= 6)
 		load_ucode_intel_bsp();
 }
 
 void __cpuinit load_ucode_ap(void)
 {
-	int vendor = x86_vendor();
+	int vendor, x86;
+
+	if (!have_cpuid_p())
+		return;
+
+	vendor = x86_vendor();
+	x86 = x86_family();
 
-	if (vendor == X86_VENDOR_INTEL)
+	if (vendor == X86_VENDOR_INTEL && x86 >= 6)
 		load_ucode_intel_ap();
 }
diff --git a/arch/x86/kernel/microcode_intel_early.c b/arch/x86/kernel/microcode_intel_early.c
index 7890bc838952..d893e8ed8ac9 100644
--- a/arch/x86/kernel/microcode_intel_early.c
+++ b/arch/x86/kernel/microcode_intel_early.c
@@ -90,13 +90,13 @@ microcode_phys(struct microcode_intel **mc_saved_tmp,
 	struct microcode_intel ***mc_saved;
 
 	mc_saved = (struct microcode_intel ***)
-		   __pa_symbol(&mc_saved_data->mc_saved);
+		   __pa_nodebug(&mc_saved_data->mc_saved);
 	for (i = 0; i < mc_saved_data->mc_saved_count; i++) {
 		struct microcode_intel *p;
 
 		p = *(struct microcode_intel **)
-			__pa(mc_saved_data->mc_saved + i);
-		mc_saved_tmp[i] = (struct microcode_intel *)__pa(p);
+			__pa_nodebug(mc_saved_data->mc_saved + i);
+		mc_saved_tmp[i] = (struct microcode_intel *)__pa_nodebug(p);
 	}
 }
 #endif
@@ -562,7 +562,7 @@ scan_microcode(unsigned long start, unsigned long end,
 	struct cpio_data cd;
 	long offset = 0;
 #ifdef CONFIG_X86_32
-	char *p = (char *)__pa_symbol(ucode_name);
+	char *p = (char *)__pa_nodebug(ucode_name);
 #else
 	char *p = ucode_name;
 #endif
@@ -630,8 +630,8 @@ static void __cpuinit print_ucode(struct ucode_cpu_info *uci)
 	if (mc_intel == NULL)
 		return;
 
-	delay_ucode_info_p = (int *)__pa_symbol(&delay_ucode_info);
-	current_mc_date_p = (int *)__pa_symbol(&current_mc_date);
+	delay_ucode_info_p = (int *)__pa_nodebug(&delay_ucode_info);
+	current_mc_date_p = (int *)__pa_nodebug(&current_mc_date);
 
 	*delay_ucode_info_p = 1;
 	*current_mc_date_p = mc_intel->hdr.date;
@@ -659,8 +659,8 @@ static inline void __cpuinit print_ucode(struct ucode_cpu_info *uci)
 }
 #endif
 
-static int apply_microcode_early(struct mc_saved_data *mc_saved_data,
-				 struct ucode_cpu_info *uci)
+static int __cpuinit apply_microcode_early(struct mc_saved_data *mc_saved_data,
+					   struct ucode_cpu_info *uci)
 {
 	struct microcode_intel *mc_intel;
 	unsigned int val[2];
@@ -741,15 +741,15 @@ load_ucode_intel_bsp(void)
 #ifdef CONFIG_X86_32
 	struct boot_params *boot_params_p;
 
-	boot_params_p = (struct boot_params *)__pa_symbol(&boot_params);
+	boot_params_p = (struct boot_params *)__pa_nodebug(&boot_params);
 	ramdisk_image = boot_params_p->hdr.ramdisk_image;
 	ramdisk_size  = boot_params_p->hdr.ramdisk_size;
 	initrd_start_early = ramdisk_image;
 	initrd_end_early = initrd_start_early + ramdisk_size;
 
 	_load_ucode_intel_bsp(
-		(struct mc_saved_data *)__pa_symbol(&mc_saved_data),
-		(unsigned long *)__pa_symbol(&mc_saved_in_initrd),
+		(struct mc_saved_data *)__pa_nodebug(&mc_saved_data),
+		(unsigned long *)__pa_nodebug(&mc_saved_in_initrd),
 		initrd_start_early, initrd_end_early, &uci);
 #else
 	ramdisk_image = boot_params.hdr.ramdisk_image;
@@ -772,10 +772,10 @@ void __cpuinit load_ucode_intel_ap(void)
 	unsigned long *initrd_start_p;
 
 	mc_saved_in_initrd_p =
-		(unsigned long *)__pa_symbol(mc_saved_in_initrd);
-	mc_saved_data_p = (struct mc_saved_data *)__pa_symbol(&mc_saved_data);
-	initrd_start_p = (unsigned long *)__pa_symbol(&initrd_start);
-	initrd_start_addr = (unsigned long)__pa_symbol(*initrd_start_p);
+		(unsigned long *)__pa_nodebug(mc_saved_in_initrd);
+	mc_saved_data_p = (struct mc_saved_data *)__pa_nodebug(&mc_saved_data);
+	initrd_start_p = (unsigned long *)__pa_nodebug(&initrd_start);
+	initrd_start_addr = (unsigned long)__pa_nodebug(*initrd_start_p);
 #else
 	mc_saved_data_p = &mc_saved_data;
 	mc_saved_in_initrd_p = mc_saved_in_initrd;
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 17fff18a1031..8bfb335f74bb 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -263,6 +263,18 @@ void paravirt_leave_lazy_mmu(void)
 	leave_lazy(PARAVIRT_LAZY_MMU);
 }
 
+void paravirt_flush_lazy_mmu(void)
+{
+	preempt_disable();
+
+	if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) {
+		arch_leave_lazy_mmu_mode();
+		arch_enter_lazy_mmu_mode();
+	}
+
+	preempt_enable();
+}
+
 void paravirt_start_context_switch(struct task_struct *prev)
 {
 	BUG_ON(preemptible());
@@ -292,18 +304,6 @@ enum paravirt_lazy_mode paravirt_get_lazy_mode(void)
 	return this_cpu_read(paravirt_lazy_mode);
 }
 
-void arch_flush_lazy_mmu_mode(void)
-{
-	preempt_disable();
-
-	if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) {
-		arch_leave_lazy_mmu_mode();
-		arch_enter_lazy_mmu_mode();
-	}
-
-	preempt_enable();
-}
-
 struct pv_info pv_info = {
 	.name = "bare hardware",
 	.paravirt_enabled = 0,
@@ -475,6 +475,7 @@ struct pv_mmu_ops pv_mmu_ops = {
 	.lazy_mode = {
 		.enter = paravirt_nop,
 		.leave = paravirt_nop,
+		.flush = paravirt_nop,
 	},
 
 	.set_fixmap = native_set_fixmap,
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 90d8cc930f5e..fae9134a2de9 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -507,11 +507,14 @@ static void __init memblock_x86_reserve_range_setup_data(void)
 /*
  * Keep the crash kernel below this limit.  On 32 bits earlier kernels
  * would limit the kernel to the low 512 MiB due to mapping restrictions.
+ * On 64bit, old kexec-tools need to under 896MiB.
  */
 #ifdef CONFIG_X86_32
-# define CRASH_KERNEL_ADDR_MAX	(512 << 20)
+# define CRASH_KERNEL_ADDR_LOW_MAX	(512 << 20)
+# define CRASH_KERNEL_ADDR_HIGH_MAX	(512 << 20)
 #else
-# define CRASH_KERNEL_ADDR_MAX	MAXMEM
+# define CRASH_KERNEL_ADDR_LOW_MAX	(896UL<<20)
+# define CRASH_KERNEL_ADDR_HIGH_MAX	MAXMEM
 #endif
 
 static void __init reserve_crashkernel_low(void)
@@ -521,19 +524,35 @@ static void __init reserve_crashkernel_low(void)
 	unsigned long long low_base = 0, low_size = 0;
 	unsigned long total_low_mem;
 	unsigned long long base;
+	bool auto_set = false;
 	int ret;
 
 	total_low_mem = memblock_mem_size(1UL<<(32-PAGE_SHIFT));
+	/* crashkernel=Y,low */
 	ret = parse_crashkernel_low(boot_command_line, total_low_mem,
 						&low_size, &base);
-	if (ret != 0 || low_size <= 0)
-		return;
+	if (ret != 0) {
+		/*
+		 * two parts from lib/swiotlb.c:
+		 *	swiotlb size: user specified with swiotlb= or default.
+		 *	swiotlb overflow buffer: now is hardcoded to 32k.
+		 *		We round it to 8M for other buffers that
+		 *		may need to stay low too.
+		 */
+		low_size = swiotlb_size_or_default() + (8UL<<20);
+		auto_set = true;
+	} else {
+		/* passed with crashkernel=0,low ? */
+		if (!low_size)
+			return;
+	}
 
 	low_base = memblock_find_in_range(low_size, (1ULL<<32),
 					low_size, alignment);
 
 	if (!low_base) {
-		pr_info("crashkernel low reservation failed - No suitable area found.\n");
+		if (!auto_set)
+			pr_info("crashkernel low reservation failed - No suitable area found.\n");
 
 		return;
 	}
@@ -554,14 +573,22 @@ static void __init reserve_crashkernel(void)
 	const unsigned long long alignment = 16<<20;	/* 16M */
 	unsigned long long total_mem;
 	unsigned long long crash_size, crash_base;
+	bool high = false;
 	int ret;
 
 	total_mem = memblock_phys_mem_size();
 
+	/* crashkernel=XM */
 	ret = parse_crashkernel(boot_command_line, total_mem,
 			&crash_size, &crash_base);
-	if (ret != 0 || crash_size <= 0)
-		return;
+	if (ret != 0 || crash_size <= 0) {
+		/* crashkernel=X,high */
+		ret = parse_crashkernel_high(boot_command_line, total_mem,
+				&crash_size, &crash_base);
+		if (ret != 0 || crash_size <= 0)
+			return;
+		high = true;
+	}
 
 	/* 0 means: find the address automatically */
 	if (crash_base <= 0) {
@@ -569,7 +596,9 @@ static void __init reserve_crashkernel(void)
 		 *  kexec want bzImage is below CRASH_KERNEL_ADDR_MAX
 		 */
 		crash_base = memblock_find_in_range(alignment,
-			       CRASH_KERNEL_ADDR_MAX, crash_size, alignment);
+					high ? CRASH_KERNEL_ADDR_HIGH_MAX :
+					       CRASH_KERNEL_ADDR_LOW_MAX,
+					crash_size, alignment);
 
 		if (!crash_base) {
 			pr_info("crashkernel reservation failed - No suitable area found.\n");