Merge tag 'v3.16-rc7' into perf/core, to merge in the latest fixes before applying new changes

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

arch/x86/kernel/apic/hw_nmi.c

@@ -33,31 +33,41 @@ static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly;
 /* "in progress" flag of arch_trigger_all_cpu_backtrace */
 static unsigned long backtrace_flag;
 
-void arch_trigger_all_cpu_backtrace(void)
+void arch_trigger_all_cpu_backtrace(bool include_self)
 {
 	int i;
+	int cpu = get_cpu();
 
-	if (test_and_set_bit(0, &backtrace_flag))
+	if (test_and_set_bit(0, &backtrace_flag)) {
 		/*
 		 * If there is already a trigger_all_cpu_backtrace() in progress
 		 * (backtrace_flag == 1), don't output double cpu dump infos.
 		 */
+		put_cpu();
 		return;
+	}
 
 	cpumask_copy(to_cpumask(backtrace_mask), cpu_online_mask);
+	if (!include_self)
+		cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask));
 
-	printk(KERN_INFO "sending NMI to all CPUs:\n");
-	apic->send_IPI_all(NMI_VECTOR);
+	if (!cpumask_empty(to_cpumask(backtrace_mask))) {
+		pr_info("sending NMI to %s CPUs:\n",
+			(include_self ? "all" : "other"));
+		apic->send_IPI_mask(to_cpumask(backtrace_mask), NMI_VECTOR);
+	}
 
 	/* Wait for up to 10 seconds for all CPUs to do the backtrace */
 	for (i = 0; i < 10 * 1000; i++) {
 		if (cpumask_empty(to_cpumask(backtrace_mask)))
 			break;
 		mdelay(1);
+		touch_softlockup_watchdog();
 	}
 
 	clear_bit(0, &backtrace_flag);
 	smp_mb__after_atomic();
+	put_cpu();
 }
 
 static int

arch/x86/kernel/apm_32.c

@@ -841,7 +841,6 @@ static int apm_do_idle(void)
 	u32 eax;
 	u8 ret = 0;
 	int idled = 0;
-	int polling;
 	int err = 0;
 
 	if (!need_resched()) {

arch/x86/kernel/cpu/intel.c

@@ -370,6 +370,17 @@ static void init_intel(struct cpuinfo_x86 *c)
 	 */
 	detect_extended_topology(c);
 
+	if (!cpu_has(c, X86_FEATURE_XTOPOLOGY)) {
+		/*
+		 * let's use the legacy cpuid vector 0x1 and 0x4 for topology
+		 * detection.
+		 */
+		c->x86_max_cores = intel_num_cpu_cores(c);
+#ifdef CONFIG_X86_32
+		detect_ht(c);
+#endif
+	}
+
 	l2 = init_intel_cacheinfo(c);
 	if (c->cpuid_level > 9) {
 		unsigned eax = cpuid_eax(10);
@@ -438,17 +449,6 @@ static void init_intel(struct cpuinfo_x86 *c)
 		set_cpu_cap(c, X86_FEATURE_P3);
 #endif
 
-	if (!cpu_has(c, X86_FEATURE_XTOPOLOGY)) {
-		/*
-		 * let's use the legacy cpuid vector 0x1 and 0x4 for topology
-		 * detection.
-		 */
-		c->x86_max_cores = intel_num_cpu_cores(c);
-#ifdef CONFIG_X86_32
-		detect_ht(c);
-#endif
-	}
-
 	/* Work around errata */
 	srat_detect_node(c);
 

arch/x86/kernel/cpu/intel_cacheinfo.c

@@ -730,6 +730,18 @@ unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c)
 #endif
 	}
 
+#ifdef CONFIG_X86_HT
+	/*
+	 * 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
+	 * cpuid1). Since cpuid2 doesn't specify shared caches, and we know
+	 * that SMT shares all caches, we can unconditionally set cpu_llc_id to
+	 * c->phys_proc_id.
+	 */
+	if (per_cpu(cpu_llc_id, cpu) == BAD_APICID)
+		per_cpu(cpu_llc_id, cpu) = c->phys_proc_id;
+#endif
+
 	c->x86_cache_size = l3 ? l3 : (l2 ? l2 : (l1i+l1d));
 
 	return l2;

arch/x86/kernel/cpu/mcheck/mce.c

@@ -2451,6 +2451,12 @@ static __init int mcheck_init_device(void)
 	for_each_online_cpu(i) {
 		err = mce_device_create(i);
 		if (err) {
+			/*
+			 * Register notifier anyway (and do not unreg it) so
+			 * that we don't leave undeleted timers, see notifier
+			 * callback above.
+			 */
+			__register_hotcpu_notifier(&mce_cpu_notifier);
 			cpu_notifier_register_done();
 			goto err_device_create;
 		}
@@ -2471,10 +2477,6 @@ static __init int mcheck_init_device(void)
 err_register:
 	unregister_syscore_ops(&mce_syscore_ops);
 
-	cpu_notifier_register_begin();
-	__unregister_hotcpu_notifier(&mce_cpu_notifier);
-	cpu_notifier_register_done();
-
 err_device_create:
 	/*
 	 * We didn't keep track of which devices were created above, but

arch/x86/kernel/cpu/perf_event.c

@@ -118,6 +118,9 @@ static int x86_pmu_extra_regs(u64 config, struct perf_event *event)
 			continue;
 		if (event->attr.config1 & ~er->valid_mask)
 			return -EINVAL;
+		/* Check if the extra msrs can be safely accessed*/
+		if (!er->extra_msr_access)
+			return -ENXIO;
 
 		reg->idx = er->idx;
 		reg->config = event->attr.config1;

arch/x86/kernel/cpu/perf_event.h

@@ -295,14 +295,16 @@ struct extra_reg {
 	u64			config_mask;
 	u64			valid_mask;
 	int			idx;  /* per_xxx->regs[] reg index */
+	bool			extra_msr_access;
 };
 
 #define EVENT_EXTRA_REG(e, ms, m, vm, i) {	\
-	.event = (e),		\
-	.msr = (ms),		\
-	.config_mask = (m),	\
-	.valid_mask = (vm),	\
-	.idx = EXTRA_REG_##i,	\
+	.event = (e),			\
+	.msr = (ms),			\
+	.config_mask = (m),		\
+	.valid_mask = (vm),		\
+	.idx = EXTRA_REG_##i,		\
+	.extra_msr_access = true,	\
 	}
 
 #define INTEL_EVENT_EXTRA_REG(event, msr, vm, idx)	\

arch/x86/kernel/cpu/perf_event_intel.c

@@ -1381,6 +1381,15 @@ again:
 
 	intel_pmu_lbr_read();
 
+	/*
+	 * CondChgd bit 63 doesn't mean any overflow status. Ignore
+	 * and clear the bit.
+	 */
+	if (__test_and_clear_bit(63, (unsigned long *)&status)) {
+		if (!status)
+			goto done;
+	}
+
 	/*
 	 * PEBS overflow sets bit 62 in the global status register
 	 */
@@ -2173,6 +2182,41 @@ static void intel_snb_check_microcode(void)
 	}
 }
 
+/*
+ * Under certain circumstances, access certain MSR may cause #GP.
+ * The function tests if the input MSR can be safely accessed.
+ */
+static bool check_msr(unsigned long msr, u64 mask)
+{
+	u64 val_old, val_new, val_tmp;
+
+	/*
+	 * 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.
+	 */
+	if (rdmsrl_safe(msr, &val_old))
+		return false;
+
+	/*
+	 * Only change the bits which can be updated by wrmsrl.
+	 */
+	val_tmp = val_old ^ mask;
+	if (wrmsrl_safe(msr, val_tmp) ||
+	    rdmsrl_safe(msr, &val_new))
+		return false;
+
+	if (val_new != val_tmp)
+		return false;
+
+	/* Here it's sure that the MSR can be safely accessed.
+	 * Restore the old value and return.
+	 */
+	wrmsrl(msr, val_old);
+
+	return true;
+}
+
 static __init void intel_sandybridge_quirk(void)
 {
 	x86_pmu.check_microcode = intel_snb_check_microcode;
@@ -2262,7 +2306,8 @@ __init int intel_pmu_init(void)
 	union cpuid10_ebx ebx;
 	struct event_constraint *c;
 	unsigned int unused;
-	int version;
+	struct extra_reg *er;
+	int version, i;
 
 	if (!cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) {
 		switch (boot_cpu_data.x86) {
@@ -2465,6 +2510,9 @@ __init int intel_pmu_init(void)
 	case 62: /* IvyBridge EP */
 		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
+		/* dTLB-load-misses on IVB is different than SNB */
+		hw_cache_event_ids[C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = 0x8108; /* DTLB_LOAD_MISSES.DEMAND_LD_MISS_CAUSES_A_WALK */
+
 		memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs,
 		       sizeof(hw_cache_extra_regs));
 
@@ -2565,6 +2613,34 @@ __init int intel_pmu_init(void)
 		}
 	}
 
+	/*
+	 * Access LBR MSR may cause #GP under certain circumstances.
+	 * E.g. KVM doesn't support LBR MSR
+	 * Check all LBT MSR here.
+	 * Disable LBR access if any LBR MSRs can not be accessed.
+	 */
+	if (x86_pmu.lbr_nr && !check_msr(x86_pmu.lbr_tos, 0x3UL))
+		x86_pmu.lbr_nr = 0;
+	for (i = 0; i < x86_pmu.lbr_nr; i++) {
+		if (!(check_msr(x86_pmu.lbr_from + i, 0xffffUL) &&
+		      check_msr(x86_pmu.lbr_to + i, 0xffffUL)))
+			x86_pmu.lbr_nr = 0;
+	}
+
+	/*
+	 * Access extra MSR may cause #GP under certain circumstances.
+	 * E.g. KVM doesn't support offcore event
+	 * Check all extra_regs here.
+	 */
+	if (x86_pmu.extra_regs) {
+		for (er = x86_pmu.extra_regs; er->msr; er++) {
+			er->extra_msr_access = check_msr(er->msr, 0x1ffUL);
+			/* Disable LBR select mapping */
+			if ((er->idx == EXTRA_REG_LBR) && !er->extra_msr_access)
+				x86_pmu.lbr_sel_map = NULL;
+		}
+	}
+
 	/* Support full width counters using alternative MSR range */
 	if (x86_pmu.intel_cap.full_width_write) {
 		x86_pmu.max_period = x86_pmu.cntval_mask;

arch/x86/kernel/cpu/perf_event_intel_ds.c

@@ -311,9 +311,11 @@ static int alloc_bts_buffer(int cpu)
 	if (!x86_pmu.bts)
 		return 0;
 
-	buffer = kzalloc_node(BTS_BUFFER_SIZE, GFP_KERNEL, node);
-	if (unlikely(!buffer))
+	buffer = kzalloc_node(BTS_BUFFER_SIZE, GFP_KERNEL | __GFP_NOWARN, node);
+	if (unlikely(!buffer)) {
+		WARN_ONCE(1, "%s: BTS buffer allocation failure\n", __func__);
 		return -ENOMEM;
+	}
 
 	max = BTS_BUFFER_SIZE / BTS_RECORD_SIZE;
 	thresh = max / 16;

arch/x86/kernel/cpu/perf_event_intel_uncore.c

@@ -550,16 +550,16 @@ static struct extra_reg snbep_uncore_cbox_extra_regs[] = {
 	SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0x6),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x8),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x8),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4135, 0xffff, 0xc),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4335, 0xffff, 0xc),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4135, 0xffff, 0xa),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4335, 0xffff, 0xa),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x4435, 0xffff, 0x2),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x4835, 0xffff, 0x2),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x4a35, 0xffff, 0x2),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x5035, 0xffff, 0x2),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x0136, 0xffff, 0x8),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x0336, 0xffff, 0x8),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0xc),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0xc),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0xa),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0xa),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x4436, 0xffff, 0x2),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x4836, 0xffff, 0x2),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x4a36, 0xffff, 0x2),
@@ -1222,6 +1222,7 @@ static struct extra_reg ivt_uncore_cbox_extra_regs[] = {
 	SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN,
 				  SNBEP_CBO_PMON_CTL_TID_EN, 0x1),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x1031, 0x10ff, 0x2),
+
 	SNBEP_CBO_EVENT_EXTRA_REG(0x1134, 0xffff, 0x4),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0xc),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x5134, 0xffff, 0xc),
@@ -1245,7 +1246,7 @@ static struct extra_reg ivt_uncore_cbox_extra_regs[] = {
 	SNBEP_CBO_EVENT_EXTRA_REG(0x8335, 0xffff, 0x10),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x0136, 0xffff, 0x10),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x0336, 0xffff, 0x10),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x2336, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x2136, 0xffff, 0x10),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x2336, 0xffff, 0x10),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0x18),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0x18),

arch/x86/kernel/entry_32.S

@@ -423,8 +423,9 @@ sysenter_past_esp:
 	jnz sysenter_audit
 sysenter_do_call:
 	cmpl $(NR_syscalls), %eax
-	jae syscall_badsys
+	jae sysenter_badsys
 	call *sys_call_table(,%eax,4)
+sysenter_after_call:
 	movl %eax,PT_EAX(%esp)
 	LOCKDEP_SYS_EXIT
 	DISABLE_INTERRUPTS(CLBR_ANY)
@@ -501,6 +502,7 @@ ENTRY(system_call)
 	jae syscall_badsys
 syscall_call:
 	call *sys_call_table(,%eax,4)
+syscall_after_call:
 	movl %eax,PT_EAX(%esp)		# store the return value
 syscall_exit:
 	LOCKDEP_SYS_EXIT
@@ -674,8 +676,13 @@ syscall_fault:
 END(syscall_fault)
 
 syscall_badsys:
-	movl $-ENOSYS,PT_EAX(%esp)
-	jmp resume_userspace
+	movl $-ENOSYS,%eax
+	jmp syscall_after_call
+END(syscall_badsys)
+
+sysenter_badsys:
+	movl $-ENOSYS,%eax
+	jmp sysenter_after_call
 END(syscall_badsys)
 	CFI_ENDPROC
 

arch/x86/kernel/espfix_64.c

@@ -175,7 +175,7 @@ void init_espfix_ap(void)
 	if (!pud_present(pud)) {
 		pmd_p = (pmd_t *)__get_free_page(PGALLOC_GFP);
 		pud = __pud(__pa(pmd_p) | (PGTABLE_PROT & ptemask));
-		paravirt_alloc_pud(&init_mm, __pa(pmd_p) >> PAGE_SHIFT);
+		paravirt_alloc_pmd(&init_mm, __pa(pmd_p) >> PAGE_SHIFT);
 		for (n = 0; n < ESPFIX_PUD_CLONES; n++)
 			set_pud(&pud_p[n], pud);
 	}
@@ -185,7 +185,7 @@ void init_espfix_ap(void)
 	if (!pmd_present(pmd)) {
 		pte_p = (pte_t *)__get_free_page(PGALLOC_GFP);
 		pmd = __pmd(__pa(pte_p) | (PGTABLE_PROT & ptemask));
-		paravirt_alloc_pmd(&init_mm, __pa(pte_p) >> PAGE_SHIFT);
+		paravirt_alloc_pte(&init_mm, __pa(pte_p) >> PAGE_SHIFT);
 		for (n = 0; n < ESPFIX_PMD_CLONES; n++)
 			set_pmd(&pmd_p[n], pmd);
 	}
@@ -193,7 +193,6 @@ void init_espfix_ap(void)
 	pte_p = pte_offset_kernel(&pmd, addr);
 	stack_page = (void *)__get_free_page(GFP_KERNEL);
 	pte = __pte(__pa(stack_page) | (__PAGE_KERNEL_RO & ptemask));
-	paravirt_alloc_pte(&init_mm, __pa(stack_page) >> PAGE_SHIFT);
 	for (n = 0; n < ESPFIX_PTE_CLONES; n++)
 		set_pte(&pte_p[n*PTE_STRIDE], pte);
 

arch/x86/kernel/kprobes/core.c

@@ -574,6 +574,9 @@ int kprobe_int3_handler(struct pt_regs *regs)
 	struct kprobe *p;
 	struct kprobe_ctlblk *kcb;
 
+	if (user_mode_vm(regs))
+		return 0;
+
 	addr = (kprobe_opcode_t *)(regs->ip - sizeof(kprobe_opcode_t));
 	/*
 	 * We don't want to be preempted for the entire

arch/x86/kernel/signal.c

@@ -363,7 +363,7 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig,
 
 		/* Set up to return from userspace.  */
 		restorer = current->mm->context.vdso +
-			selected_vdso32->sym___kernel_sigreturn;
+			selected_vdso32->sym___kernel_rt_sigreturn;
 		if (ksig->ka.sa.sa_flags & SA_RESTORER)
 			restorer = ksig->ka.sa.sa_restorer;
 		put_user_ex(restorer, &frame->pretcode);

arch/x86/kernel/tsc.c

@@ -920,9 +920,9 @@ static int time_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
 		tsc_khz = cpufreq_scale(tsc_khz_ref, ref_freq, freq->new);
 		if (!(freq->flags & CPUFREQ_CONST_LOOPS))
 			mark_tsc_unstable("cpufreq changes");
-	}
 
-	set_cyc2ns_scale(tsc_khz, freq->cpu);
+		set_cyc2ns_scale(tsc_khz, freq->cpu);
+	}
 
 	return 0;
 }