Merge branch 'perf-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'perf-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (28 commits)
  perf session: Fix infinite loop in __perf_session__process_events
  perf evsel: Support perf_evsel__open(cpus > 1 && threads > 1)
  perf sched: Use PTHREAD_STACK_MIN to avoid pthread_attr_setstacksize() fail
  perf tools: Emit clearer message for sys_perf_event_open ENOENT return
  perf stat: better error message for unsupported events
  perf sched: Fix allocation result check
  perf, x86: P4 PMU - Fix unflagged overflows handling
  dynamic debug: Fix build issue with older gcc
  tracing: Fix TRACE_EVENT power tracepoint creation
  tracing: Fix preempt count leak
  tracepoint: Add __rcu annotation
  tracing: remove duplicate null-pointer check in skb tracepoint
  tracing/trivial: Add missing comma in TRACE_EVENT comment
  tracing: Include module.h in define_trace.h
  x86: Save rbp in pt_regs on irq entry
  x86, dumpstack: Fix unused variable warning
  x86, NMI: Clean-up default_do_nmi()
  x86, NMI: Allow NMI reason io port (0x61) to be processed on any CPU
  x86, NMI: Remove DIE_NMI_IPI
  x86, NMI: Add priorities to handlers
  ...

10 files changed, 101 insertions, 96 deletions

diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c
index 72ec29e..79fd43c 100644
--- a/arch/x86/kernel/apic/hw_nmi.c
+++ b/arch/x86/kernel/apic/hw_nmi.c
@@ -68,7 +68,6 @@ arch_trigger_all_cpu_backtrace_handler(struct notifier_block *self,
 
 	switch (cmd) {
 	case DIE_NMI:
-	case DIE_NMI_IPI:
 		break;
 
 	default:
@@ -96,7 +95,7 @@ arch_trigger_all_cpu_backtrace_handler(struct notifier_block *self,
 static __read_mostly struct notifier_block backtrace_notifier = {
 	.notifier_call          = arch_trigger_all_cpu_backtrace_handler,
 	.next                   = NULL,
-	.priority               = 1
+	.priority               = NMI_LOCAL_LOW_PRIOR,
 };
 
 static int __init register_trigger_all_cpu_backtrace(void)
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index ecca5f4..89b9f56 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -641,7 +641,7 @@ void __cpuinit uv_cpu_init(void)
  */
 int uv_handle_nmi(struct notifier_block *self, unsigned long reason, void *data)
 {
-	if (reason != DIE_NMI_IPI)
+	if (reason != DIE_NMIUNKNOWN)
 		return NOTIFY_OK;
 
 	if (in_crash_kexec)
diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c
index e7dbde7..a779719 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-inject.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c
@@ -25,6 +25,7 @@
 #include <linux/gfp.h>
 #include <asm/mce.h>
 #include <asm/apic.h>
+#include <asm/nmi.h>
 
 /* Update fake mce registers on current CPU. */
 static void inject_mce(struct mce *m)
@@ -83,7 +84,7 @@ static int mce_raise_notify(struct notifier_block *self,
 	struct die_args *args = (struct die_args *)data;
 	int cpu = smp_processor_id();
 	struct mce *m = &__get_cpu_var(injectm);
-	if (val != DIE_NMI_IPI || !cpumask_test_cpu(cpu, mce_inject_cpumask))
+	if (val != DIE_NMI || !cpumask_test_cpu(cpu, mce_inject_cpumask))
 		return NOTIFY_DONE;
 	cpumask_clear_cpu(cpu, mce_inject_cpumask);
 	if (m->inject_flags & MCJ_EXCEPTION)
@@ -95,7 +96,7 @@ static int mce_raise_notify(struct notifier_block *self,
 
 static struct notifier_block mce_raise_nb = {
 	.notifier_call = mce_raise_notify,
-	.priority = 1000,
+	.priority = NMI_LOCAL_NORMAL_PRIOR,
 };
 
 /* Inject mce on current CPU */
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 0492101..9d977a2 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1267,7 +1267,6 @@ perf_event_nmi_handler(struct notifier_block *self,
 
 	switch (cmd) {
 	case DIE_NMI:
-	case DIE_NMI_IPI:
 		break;
 	case DIE_NMIUNKNOWN:
 		this_nmi = percpu_read(irq_stat.__nmi_count);
@@ -1317,7 +1316,7 @@ perf_event_nmi_handler(struct notifier_block *self,
 static __read_mostly struct notifier_block perf_event_nmi_notifier = {
 	.notifier_call		= perf_event_nmi_handler,
 	.next			= NULL,
-	.priority		= 1
+	.priority		= NMI_LOCAL_LOW_PRIOR,
 };
 
 static struct event_constraint unconstrained;
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index 81400b9..e56b9bf 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -753,19 +753,21 @@ out:
 
 static inline int p4_pmu_clear_cccr_ovf(struct hw_perf_event *hwc)
 {
-	int overflow = 0;
-	u32 low, high;
+	u64 v;
 
-	rdmsr(hwc->config_base + hwc->idx, low, high);
-
-	/* we need to check high bit for unflagged overflows */
-	if ((low & P4_CCCR_OVF) || !(high & (1 << 31))) {
-		overflow = 1;
-		(void)checking_wrmsrl(hwc->config_base + hwc->idx,
-			((u64)low) & ~P4_CCCR_OVF);
+	/* an official way for overflow indication */
+	rdmsrl(hwc->config_base + hwc->idx, v);
+	if (v & P4_CCCR_OVF) {
+		wrmsrl(hwc->config_base + hwc->idx, v & ~P4_CCCR_OVF);
+		return 1;
 	}
 
-	return overflow;
+	/* it might be unflagged overflow */
+	rdmsrl(hwc->event_base + hwc->idx, v);
+	if (!(v & ARCH_P4_CNTRVAL_MASK))
+		return 1;
+
+	return 0;
 }
 
 static void p4_pmu_disable_pebs(void)
@@ -1152,9 +1154,9 @@ static __initconst const struct x86_pmu p4_pmu = {
 	 */
 	.num_counters		= ARCH_P4_MAX_CCCR,
 	.apic			= 1,
-	.cntval_bits		= 40,
-	.cntval_mask		= (1ULL << 40) - 1,
-	.max_period		= (1ULL << 39) - 1,
+	.cntval_bits		= ARCH_P4_CNTRVAL_BITS,
+	.cntval_mask		= ARCH_P4_CNTRVAL_MASK,
+	.max_period		= (1ULL << (ARCH_P4_CNTRVAL_BITS - 1)) - 1,
 	.hw_config		= p4_hw_config,
 	.schedule_events	= p4_pmu_schedule_events,
 	/*
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 8474c99..d6fb146 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -197,14 +197,8 @@ void show_stack(struct task_struct *task, unsigned long *sp)
  */
 void dump_stack(void)
 {
-	unsigned long bp = 0;
 	unsigned long stack;
 
-#ifdef CONFIG_FRAME_POINTER
-	if (!bp)
-		get_bp(bp);
-#endif
-
 	printk("Pid: %d, comm: %.20s %s %s %.*s\n",
 		current->pid, current->comm, print_tainted(),
 		init_utsname()->release,
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index e3ba417..d3b895f 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -299,17 +299,21 @@ ENDPROC(native_usergs_sysret64)
 ENTRY(save_args)
 	XCPT_FRAME
 	cld
-	movq_cfi rdi, RDI+16-ARGOFFSET
-	movq_cfi rsi, RSI+16-ARGOFFSET
-	movq_cfi rdx, RDX+16-ARGOFFSET
-	movq_cfi rcx, RCX+16-ARGOFFSET
-	movq_cfi rax, RAX+16-ARGOFFSET
-	movq_cfi  r8,  R8+16-ARGOFFSET
-	movq_cfi  r9,  R9+16-ARGOFFSET
-	movq_cfi r10, R10+16-ARGOFFSET
-	movq_cfi r11, R11+16-ARGOFFSET
-
-	leaq -ARGOFFSET+16(%rsp),%rdi	/* arg1 for handler */
+	/*
+	 * start from rbp in pt_regs and jump over
+	 * return address.
+	 */
+	movq_cfi rdi, RDI+8-RBP
+	movq_cfi rsi, RSI+8-RBP
+	movq_cfi rdx, RDX+8-RBP
+	movq_cfi rcx, RCX+8-RBP
+	movq_cfi rax, RAX+8-RBP
+	movq_cfi  r8,  R8+8-RBP
+	movq_cfi  r9,  R9+8-RBP
+	movq_cfi r10, R10+8-RBP
+	movq_cfi r11, R11+8-RBP
+
+	leaq -RBP+8(%rsp),%rdi	/* arg1 for handler */
 	movq_cfi rbp, 8		/* push %rbp */
 	leaq 8(%rsp), %rbp		/* mov %rsp, %ebp */
 	testl $3, CS(%rdi)
@@ -782,8 +786,9 @@ END(interrupt)
 
 /* 0(%rsp): ~(interrupt number) */
 	.macro interrupt func
-	subq $ORIG_RAX-ARGOFFSET+8, %rsp
-	CFI_ADJUST_CFA_OFFSET ORIG_RAX-ARGOFFSET+8
+	/* reserve pt_regs for scratch regs and rbp */
+	subq $ORIG_RAX-RBP, %rsp
+	CFI_ADJUST_CFA_OFFSET ORIG_RAX-RBP
 	call save_args
 	PARTIAL_FRAME 0
 	call \func
@@ -808,9 +813,14 @@ ret_from_intr:
 	TRACE_IRQS_OFF
 	decl PER_CPU_VAR(irq_count)
 	leaveq
+
 	CFI_RESTORE		rbp
 	CFI_DEF_CFA_REGISTER	rsp
 	CFI_ADJUST_CFA_OFFSET	-8
+
+	/* we did not save rbx, restore only from ARGOFFSET */
+	addq $8, %rsp
+	CFI_ADJUST_CFA_OFFSET	-8
 exit_intr:
 	GET_THREAD_INFO(%rcx)
 	testl $3,CS-ARGOFFSET(%rsp)
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index cd21b65..a413000 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -48,6 +48,7 @@
 #include <asm/apicdef.h>
 #include <asm/system.h>
 #include <asm/apic.h>
+#include <asm/nmi.h>
 
 struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] =
 {
@@ -525,10 +526,6 @@ static int __kgdb_notify(struct die_args *args, unsigned long cmd)
 		}
 		return NOTIFY_DONE;
 
-	case DIE_NMI_IPI:
-		/* Just ignore, we will handle the roundup on DIE_NMI. */
-		return NOTIFY_DONE;
-
 	case DIE_NMIUNKNOWN:
 		if (was_in_debug_nmi[raw_smp_processor_id()]) {
 			was_in_debug_nmi[raw_smp_processor_id()] = 0;
@@ -606,7 +603,7 @@ static struct notifier_block kgdb_notifier = {
 	/*
 	 * Lowest-prio notifier priority, we want to be notified last:
 	 */
-	.priority	= -INT_MAX,
+	.priority	= NMI_LOCAL_LOW_PRIOR,
 };
 
 /**
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index c495aa8..fc7aae1 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -18,6 +18,7 @@
 #include <asm/pci_x86.h>
 #include <asm/virtext.h>
 #include <asm/cpu.h>
+#include <asm/nmi.h>
 
 #ifdef CONFIG_X86_32
 # include <linux/ctype.h>
@@ -747,7 +748,7 @@ static int crash_nmi_callback(struct notifier_block *self,
 {
 	int cpu;
 
-	if (val != DIE_NMI_IPI)
+	if (val != DIE_NMI)
 		return NOTIFY_OK;
 
 	cpu = raw_smp_processor_id();
@@ -778,6 +779,8 @@ static void smp_send_nmi_allbutself(void)
 
 static struct notifier_block crash_nmi_nb = {
 	.notifier_call = crash_nmi_callback,
+	/* we want to be the first one called */
+	.priority = NMI_LOCAL_HIGH_PRIOR+1,
 };
 
 /* Halt all other CPUs, calling the specified function on each of them
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index c76aaca..b9b6716 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -84,6 +84,11 @@ EXPORT_SYMBOL_GPL(used_vectors);
 static int ignore_nmis;
 
 int unknown_nmi_panic;
+/*
+ * Prevent NMI reason port (0x61) being accessed simultaneously, can
+ * only be used in NMI handler.
+ */
+static DEFINE_RAW_SPINLOCK(nmi_reason_lock);
 
 static inline void conditional_sti(struct pt_regs *regs)
 {
@@ -310,15 +315,15 @@ static int __init setup_unknown_nmi_panic(char *str)
 __setup("unknown_nmi_panic", setup_unknown_nmi_panic);
 
 static notrace __kprobes void
-mem_parity_error(unsigned char reason, struct pt_regs *regs)
+pci_serr_error(unsigned char reason, struct pt_regs *regs)
 {
-	printk(KERN_EMERG
-		"Uhhuh. NMI received for unknown reason %02x on CPU %d.\n",
-			reason, smp_processor_id());
-
-	printk(KERN_EMERG
-		"You have some hardware problem, likely on the PCI bus.\n");
+	pr_emerg("NMI: PCI system error (SERR) for reason %02x on CPU %d.\n",
+		 reason, smp_processor_id());
 
+	/*
+	 * On some machines, PCI SERR line is used to report memory
+	 * errors. EDAC makes use of it.
+	 */
 #if defined(CONFIG_EDAC)
 	if (edac_handler_set()) {
 		edac_atomic_assert_error();
@@ -329,11 +334,11 @@ mem_parity_error(unsigned char reason, struct pt_regs *regs)
 	if (panic_on_unrecovered_nmi)
 		panic("NMI: Not continuing");
 
-	printk(KERN_EMERG "Dazed and confused, but trying to continue\n");
+	pr_emerg("Dazed and confused, but trying to continue\n");
 
-	/* Clear and disable the memory parity error line. */
-	reason = (reason & 0xf) | 4;
-	outb(reason, 0x61);
+	/* Clear and disable the PCI SERR error line. */
+	reason = (reason & NMI_REASON_CLEAR_MASK) | NMI_REASON_CLEAR_SERR;
+	outb(reason, NMI_REASON_PORT);
 }
 
 static notrace __kprobes void
@@ -341,15 +346,17 @@ io_check_error(unsigned char reason, struct pt_regs *regs)
 {
 	unsigned long i;
 
-	printk(KERN_EMERG "NMI: IOCK error (debug interrupt?)\n");
+	pr_emerg(
+	"NMI: IOCK error (debug interrupt?) for reason %02x on CPU %d.\n",
+		 reason, smp_processor_id());
 	show_registers(regs);
 
 	if (panic_on_io_nmi)
 		panic("NMI IOCK error: Not continuing");
 
 	/* Re-enable the IOCK line, wait for a few seconds */
-	reason = (reason & 0xf) | 8;
-	outb(reason, 0x61);
+	reason = (reason & NMI_REASON_CLEAR_MASK) | NMI_REASON_CLEAR_IOCHK;
+	outb(reason, NMI_REASON_PORT);
 
 	i = 20000;
 	while (--i) {
@@ -357,8 +364,8 @@ io_check_error(unsigned char reason, struct pt_regs *regs)
 		udelay(100);
 	}
 
-	reason &= ~8;
-	outb(reason, 0x61);
+	reason &= ~NMI_REASON_CLEAR_IOCHK;
+	outb(reason, NMI_REASON_PORT);
 }
 
 static notrace __kprobes void
@@ -377,57 +384,50 @@ unknown_nmi_error(unsigned char reason, struct pt_regs *regs)
 		return;
 	}
 #endif
-	printk(KERN_EMERG
-		"Uhhuh. NMI received for unknown reason %02x on CPU %d.\n",
-			reason, smp_processor_id());
+	pr_emerg("Uhhuh. NMI received for unknown reason %02x on CPU %d.\n",
+		 reason, smp_processor_id());
 
-	printk(KERN_EMERG "Do you have a strange power saving mode enabled?\n");
+	pr_emerg("Do you have a strange power saving mode enabled?\n");
 	if (unknown_nmi_panic || panic_on_unrecovered_nmi)
 		panic("NMI: Not continuing");
 
-	printk(KERN_EMERG "Dazed and confused, but trying to continue\n");
+	pr_emerg("Dazed and confused, but trying to continue\n");
 }
 
 static notrace __kprobes void default_do_nmi(struct pt_regs *regs)
 {
 	unsigned char reason = 0;
-	int cpu;
 
-	cpu = smp_processor_id();
-
-	/* Only the BSP gets external NMIs from the system. */
-	if (!cpu)
-		reason = get_nmi_reason();
+	/*
+	 * CPU-specific NMI must be processed before non-CPU-specific
+	 * NMI, otherwise we may lose it, because the CPU-specific
+	 * NMI can not be detected/processed on other CPUs.
+	 */
+	if (notify_die(DIE_NMI, "nmi", regs, 0, 2, SIGINT) == NOTIFY_STOP)
+		return;
 
-	if (!(reason & 0xc0)) {
-		if (notify_die(DIE_NMI_IPI, "nmi_ipi", regs, reason, 2, SIGINT)
-								== NOTIFY_STOP)
-			return;
+	/* Non-CPU-specific NMI: NMI sources can be processed on any CPU */
+	raw_spin_lock(&nmi_reason_lock);
+	reason = get_nmi_reason();
 
-#ifdef CONFIG_X86_LOCAL_APIC
-		if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT)
-							== NOTIFY_STOP)
-			return;
+	if (reason & NMI_REASON_MASK) {
+		if (reason & NMI_REASON_SERR)
+			pci_serr_error(reason, regs);
+		else if (reason & NMI_REASON_IOCHK)
+			io_check_error(reason, regs);
+#ifdef CONFIG_X86_32
+		/*
+		 * Reassert NMI in case it became active
+		 * meanwhile as it's edge-triggered:
+		 */
+		reassert_nmi();
 #endif
-		unknown_nmi_error(reason, regs);
-
+		raw_spin_unlock(&nmi_reason_lock);
 		return;
 	}
-	if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT) == NOTIFY_STOP)
-		return;
+	raw_spin_unlock(&nmi_reason_lock);
 
-	/* AK: following checks seem to be broken on modern chipsets. FIXME */
-	if (reason & 0x80)
-		mem_parity_error(reason, regs);
-	if (reason & 0x40)
-		io_check_error(reason, regs);
-#ifdef CONFIG_X86_32
-	/*
-	 * Reassert NMI in case it became active meanwhile
-	 * as it's edge-triggered:
-	 */
-	reassert_nmi();
-#endif
+	unknown_nmi_error(reason, regs);
 }
 
 dotraplinkage notrace __kprobes void