Merge branch 'master' into queue

* master: (15791 commits)
  Linux 3.9-rc1
  btrfs/raid56: Add missing #include <linux/vmalloc.h>
  fix compat_sys_rt_sigprocmask()
  SUNRPC: One line comment fix
  ext4: enable quotas before orphan cleanup
  ext4: don't allow quota mount options when quota feature enabled
  ext4: fix a warning from sparse check for ext4_dir_llseek
  ext4: convert number of blocks to clusters properly
  ext4: fix possible memory leak in ext4_remount()
  jbd2: fix ERR_PTR dereference in jbd2__journal_start
  metag: Provide dma_get_sgtable()
  metag: prom.h: remove declaration of metag_dt_memblock_reserve()
  metag: copy devicetree to non-init memory
  metag: cleanup metag_ksyms.c includes
  metag: move mm/init.c exports out of metag_ksyms.c
  metag: move usercopy.c exports out of metag_ksyms.c
  metag: move setup.c exports out of metag_ksyms.c
  metag: move kick.c exports out of metag_ksyms.c
  metag: move traps.c exports out of metag_ksyms.c
  metag: move irq enable out of irqflags.h on SMP
  ...

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

Conflicts:
	arch/x86/kernel/kvmclock.c

3 files changed, 164 insertions, 40 deletions

diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index aa2465e21f1a..65362e98eb26 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -880,8 +880,16 @@ static int power_pmu_add(struct perf_event *event, int ef_flags)
 	cpuhw->events[n0] = event->hw.config;
 	cpuhw->flags[n0] = event->hw.event_base;
 
+	/*
+	 * This event may have been disabled/stopped in record_and_restart()
+	 * because we exceeded the ->event_limit. If re-starting the event,
+	 * clear the ->hw.state (STOPPED and UPTODATE flags), so the user
+	 * notification is re-enabled.
+	 */
 	if (!(ef_flags & PERF_EF_START))
 		event->hw.state = PERF_HES_STOPPED | PERF_HES_UPTODATE;
+	else
+		event->hw.state = 0;
 
 	/*
 	 * If group events scheduling transaction was started,
@@ -1305,6 +1313,16 @@ static int power_pmu_event_idx(struct perf_event *event)
 	return event->hw.idx;
 }
 
+ssize_t power_events_sysfs_show(struct device *dev,
+				struct device_attribute *attr, char *page)
+{
+	struct perf_pmu_events_attr *pmu_attr;
+
+	pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr);
+
+	return sprintf(page, "event=0x%02llx\n", pmu_attr->id);
+}
+
 struct pmu power_pmu = {
 	.pmu_enable	= power_pmu_enable,
 	.pmu_disable	= power_pmu_disable,
@@ -1349,6 +1367,8 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 	 */
 	val = 0;
 	left = local64_read(&event->hw.period_left) - delta;
+	if (delta == 0)
+		left++;
 	if (period) {
 		if (left <= 0) {
 			left += period;
@@ -1412,11 +1432,8 @@ unsigned long perf_instruction_pointer(struct pt_regs *regs)
 		return regs->nip;
 }
 
-static bool pmc_overflow(unsigned long val)
+static bool pmc_overflow_power7(unsigned long val)
 {
-	if ((int)val < 0)
-		return true;
-
 	/*
 	 * Events on POWER7 can roll back if a speculative event doesn't
 	 * eventually complete. Unfortunately in some rare cases they will
@@ -1428,7 +1445,15 @@ static bool pmc_overflow(unsigned long val)
 	 * PMCs because a user might set a period of less than 256 and we
 	 * don't want to mistakenly reset them.
 	 */
-	if (pvr_version_is(PVR_POWER7) && ((0x80000000 - val) <= 256))
+	if ((0x80000000 - val) <= 256)
+		return true;
+
+	return false;
+}
+
+static bool pmc_overflow(unsigned long val)
+{
+	if ((int)val < 0)
 		return true;
 
 	return false;
@@ -1439,11 +1464,11 @@ static bool pmc_overflow(unsigned long val)
  */
 static void perf_event_interrupt(struct pt_regs *regs)
 {
-	int i;
+	int i, j;
 	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
 	struct perf_event *event;
-	unsigned long val;
-	int found = 0;
+	unsigned long val[8];
+	int found, active;
 	int nmi;
 
 	if (cpuhw->n_limited)
@@ -1458,33 +1483,53 @@ static void perf_event_interrupt(struct pt_regs *regs)
 	else
 		irq_enter();
 
-	for (i = 0; i < cpuhw->n_events; ++i) {
-		event = cpuhw->event[i];
-		if (!event->hw.idx || is_limited_pmc(event->hw.idx))
+	/* Read all the PMCs since we'll need them a bunch of times */
+	for (i = 0; i < ppmu->n_counter; ++i)
+		val[i] = read_pmc(i + 1);
+
+	/* Try to find what caused the IRQ */
+	found = 0;
+	for (i = 0; i < ppmu->n_counter; ++i) {
+		if (!pmc_overflow(val[i]))
 			continue;
-		val = read_pmc(event->hw.idx);
-		if ((int)val < 0) {
-			/* event has overflowed */
-			found = 1;
-			record_and_restart(event, val, regs);
+		if (is_limited_pmc(i + 1))
+			continue; /* these won't generate IRQs */
+		/*
+		 * We've found one that's overflowed.  For active
+		 * counters we need to log this.  For inactive
+		 * counters, we need to reset it anyway
+		 */
+		found = 1;
+		active = 0;
+		for (j = 0; j < cpuhw->n_events; ++j) {
+			event = cpuhw->event[j];
+			if (event->hw.idx == (i + 1)) {
+				active = 1;
+				record_and_restart(event, val[i], regs);
+				break;
+			}
 		}
+		if (!active)
+			/* reset non active counters that have overflowed */
+			write_pmc(i + 1, 0);
 	}
-
-	/*
-	 * In case we didn't find and reset the event that caused
-	 * the interrupt, scan all events and reset any that are
-	 * negative, to avoid getting continual interrupts.
-	 * Any that we processed in the previous loop will not be negative.
-	 */
-	if (!found) {
-		for (i = 0; i < ppmu->n_counter; ++i) {
-			if (is_limited_pmc(i + 1))
+	if (!found && pvr_version_is(PVR_POWER7)) {
+		/* check active counters for special buggy p7 overflow */
+		for (i = 0; i < cpuhw->n_events; ++i) {
+			event = cpuhw->event[i];
+			if (!event->hw.idx || is_limited_pmc(event->hw.idx))
 				continue;
-			val = read_pmc(i + 1);
-			if (pmc_overflow(val))
-				write_pmc(i + 1, 0);
+			if (pmc_overflow_power7(val[event->hw.idx - 1])) {
+				/* event has overflowed in a buggy way*/
+				found = 1;
+				record_and_restart(event,
+						   val[event->hw.idx - 1],
+						   regs);
+			}
 		}
 	}
+	if ((!found) && printk_ratelimit())
+		printk(KERN_WARNING "Can't find PMC that caused IRQ\n");
 
 	/*
 	 * Reset MMCR0 to its normal value.  This will set PMXE and
@@ -1537,6 +1582,8 @@ int __cpuinit register_power_pmu(struct power_pmu *pmu)
 	pr_info("%s performance monitor hardware support registered\n",
 		pmu->name);
 
+	power_pmu.attr_groups = ppmu->attr_groups;
+
 #ifdef MSR_HV
 	/*
 	 * Use FCHV to ignore kernel events if MSR.HV is set.
diff --git a/arch/powerpc/perf/e500-pmu.c b/arch/powerpc/perf/e500-pmu.c
index cb2e2949c8d1..fb664929f5da 100644
--- a/arch/powerpc/perf/e500-pmu.c
+++ b/arch/powerpc/perf/e500-pmu.c
@@ -24,6 +24,8 @@ static int e500_generic_events[] = {
 	[PERF_COUNT_HW_CACHE_MISSES] = 41, /* Data L1 cache reloads */
 	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 12,
 	[PERF_COUNT_HW_BRANCH_MISSES] = 15,
+	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 18,
+	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 19,
 };
 
 #define C(x)	PERF_COUNT_HW_CACHE_##x
diff --git a/arch/powerpc/perf/power7-pmu.c b/arch/powerpc/perf/power7-pmu.c
index 441af08edf43..b554879bd31e 100644
--- a/arch/powerpc/perf/power7-pmu.c
+++ b/arch/powerpc/perf/power7-pmu.c
@@ -51,11 +51,25 @@
 #define MMCR1_PMCSEL_MSK	0xff
 
 /*
+ * Power7 event codes.
+ */
+#define	PME_PM_CYC			0x1e
+#define	PME_PM_GCT_NOSLOT_CYC		0x100f8
+#define	PME_PM_CMPLU_STALL		0x4000a
+#define	PME_PM_INST_CMPL		0x2
+#define	PME_PM_LD_REF_L1		0xc880
+#define	PME_PM_LD_MISS_L1		0x400f0
+#define	PME_PM_BRU_FIN			0x10068
+#define	PME_PM_BRU_MPRED		0x400f6
+
+/*
  * Layout of constraint bits:
  * 6666555555555544444444443333333333222222222211111111110000000000
  * 3210987654321098765432109876543210987654321098765432109876543210
- *                                                 [  ><><><><><><>
- *                                                  NC P6P5P4P3P2P1
+ *                                              < ><  ><><><><><><>
+ *                                              L2  NC P6P5P4P3P2P1
+ *
+ * L2 - 16-18 - Required L2SEL value (select field)
  *
  * NC - number of counters
  *     15: NC error 0x8000
@@ -72,7 +86,7 @@
 static int power7_get_constraint(u64 event, unsigned long *maskp,
 				 unsigned long *valp)
 {
-	int pmc, sh;
+	int pmc, sh, unit;
 	unsigned long mask = 0, value = 0;
 
 	pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
@@ -90,6 +104,15 @@ static int power7_get_constraint(u64 event, unsigned long *maskp,
 		mask  |= 0x8000;
 		value |= 0x1000;
 	}
+
+	unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK;
+	if (unit == 6) {
+		/* L2SEL must be identical across events */
+		int l2sel = (event >> PM_L2SEL_SH) & PM_L2SEL_MSK;
+		mask  |= 0x7 << 16;
+		value |= l2sel << 16;
+	}
+
 	*maskp = mask;
 	*valp = value;
 	return 0;
@@ -296,14 +319,14 @@ static void power7_disable_pmc(unsigned int pmc, unsigned long mmcr[])
 }
 
 static int power7_generic_events[] = {
-	[PERF_COUNT_HW_CPU_CYCLES] = 0x1e,
-	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x100f8, /* GCT_NOSLOT_CYC */
-	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x4000a,  /* CMPLU_STALL */
-	[PERF_COUNT_HW_INSTRUCTIONS] = 2,
-	[PERF_COUNT_HW_CACHE_REFERENCES] = 0xc880,	/* LD_REF_L1_LSU*/
-	[PERF_COUNT_HW_CACHE_MISSES] = 0x400f0,		/* LD_MISS_L1	*/
-	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x10068,	/* BRU_FIN	*/
-	[PERF_COUNT_HW_BRANCH_MISSES] = 0x400f6,	/* BR_MPRED	*/
+	[PERF_COUNT_HW_CPU_CYCLES] =			PME_PM_CYC,
+	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =	PME_PM_GCT_NOSLOT_CYC,
+	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] =	PME_PM_CMPLU_STALL,
+	[PERF_COUNT_HW_INSTRUCTIONS] =			PME_PM_INST_CMPL,
+	[PERF_COUNT_HW_CACHE_REFERENCES] =		PME_PM_LD_REF_L1,
+	[PERF_COUNT_HW_CACHE_MISSES] =			PME_PM_LD_MISS_L1,
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] =		PME_PM_BRU_FIN,
+	[PERF_COUNT_HW_BRANCH_MISSES] =			PME_PM_BRU_MPRED,
 };
 
 #define C(x)	PERF_COUNT_HW_CACHE_##x
@@ -351,6 +374,57 @@ static int power7_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
 	},
 };
 
+
+GENERIC_EVENT_ATTR(cpu-cycles,			CYC);
+GENERIC_EVENT_ATTR(stalled-cycles-frontend,	GCT_NOSLOT_CYC);
+GENERIC_EVENT_ATTR(stalled-cycles-backend,	CMPLU_STALL);
+GENERIC_EVENT_ATTR(instructions,		INST_CMPL);
+GENERIC_EVENT_ATTR(cache-references,		LD_REF_L1);
+GENERIC_EVENT_ATTR(cache-misses,		LD_MISS_L1);
+GENERIC_EVENT_ATTR(branch-instructions,		BRU_FIN);
+GENERIC_EVENT_ATTR(branch-misses,		BRU_MPRED);
+
+POWER_EVENT_ATTR(CYC,				CYC);
+POWER_EVENT_ATTR(GCT_NOSLOT_CYC,		GCT_NOSLOT_CYC);
+POWER_EVENT_ATTR(CMPLU_STALL,			CMPLU_STALL);
+POWER_EVENT_ATTR(INST_CMPL,			INST_CMPL);
+POWER_EVENT_ATTR(LD_REF_L1,			LD_REF_L1);
+POWER_EVENT_ATTR(LD_MISS_L1,			LD_MISS_L1);
+POWER_EVENT_ATTR(BRU_FIN,			BRU_FIN)
+POWER_EVENT_ATTR(BRU_MPRED,			BRU_MPRED);
+
+static struct attribute *power7_events_attr[] = {
+	GENERIC_EVENT_PTR(CYC),
+	GENERIC_EVENT_PTR(GCT_NOSLOT_CYC),
+	GENERIC_EVENT_PTR(CMPLU_STALL),
+	GENERIC_EVENT_PTR(INST_CMPL),
+	GENERIC_EVENT_PTR(LD_REF_L1),
+	GENERIC_EVENT_PTR(LD_MISS_L1),
+	GENERIC_EVENT_PTR(BRU_FIN),
+	GENERIC_EVENT_PTR(BRU_MPRED),
+
+	POWER_EVENT_PTR(CYC),
+	POWER_EVENT_PTR(GCT_NOSLOT_CYC),
+	POWER_EVENT_PTR(CMPLU_STALL),
+	POWER_EVENT_PTR(INST_CMPL),
+	POWER_EVENT_PTR(LD_REF_L1),
+	POWER_EVENT_PTR(LD_MISS_L1),
+	POWER_EVENT_PTR(BRU_FIN),
+	POWER_EVENT_PTR(BRU_MPRED),
+	NULL
+};
+
+
+static struct attribute_group power7_pmu_events_group = {
+	.name = "events",
+	.attrs = power7_events_attr,
+};
+
+static const struct attribute_group *power7_pmu_attr_groups[] = {
+	&power7_pmu_events_group,
+	NULL,
+};
+
 static struct power_pmu power7_pmu = {
 	.name			= "POWER7",
 	.n_counter		= 6,
@@ -362,6 +436,7 @@ static struct power_pmu power7_pmu = {
 	.get_alternatives	= power7_get_alternatives,
 	.disable_pmc		= power7_disable_pmc,
 	.flags			= PPMU_ALT_SIPR,
+	.attr_groups		= power7_pmu_attr_groups,
 	.n_generic		= ARRAY_SIZE(power7_generic_events),
 	.generic_events		= power7_generic_events,
 	.cache_events		= &power7_cache_events,