Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc

Pull powerpc updates from Benjamin Herrenschmidt:
 "So from the depth of frozen Minnesota, here's the powerpc pull request
  for 3.9.  It has a few interesting highlights, in addition to the
  usual bunch of bug fixes, minor updates, embedded device tree updates
  and new boards:

   - Hand tuned asm implementation of SHA1 (by Paulus & Michael
     Ellerman)

   - Support for Doorbell interrupts on Power8 (kind of fast
     thread-thread IPIs) by Ian Munsie

   - Long overdue cleanup of the way we handle relocation of our open
     firmware trampoline (prom_init.c) on 64-bit by Anton Blanchard

   - Support for saving/restoring & context switching the PPR (Processor
     Priority Register) on server processors that support it.  This
     allows the kernel to preserve thread priorities established by
     userspace.  By Haren Myneni.

   - DAWR (new watchpoint facility) support on Power8 by Michael Neuling

   - Ability to change the DSCR (Data Stream Control Register) which
     controls cache prefetching on a running process via ptrace by
     Alexey Kardashevskiy

   - Support for context switching the TAR register on Power8 (new
     branch target register meant to be used by some new specific
     userspace perf event interrupt facility which is yet to be enabled)
     by Ian Munsie.

   - Improve preservation of the CFAR register (which captures the
     origin of a branch) on various exception conditions by Paulus.

   - Move the Bestcomm DMA driver from arch powerpc to drivers/dma where
     it belongs by Philippe De Muyter

   - Support for Transactional Memory on Power8 by Michael Neuling
     (based on original work by Matt Evans).  For those curious about
     the feature, the patch contains a pretty good description."

(See commit db8ff907027b: "powerpc: Documentation for transactional
memory on powerpc" for the mentioned description added to the file
Documentation/powerpc/transactional_memory.txt)

* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc: (140 commits)
  powerpc/kexec: Disable hard IRQ before kexec
  powerpc/85xx: l2sram - Add compatible string for BSC9131 platform
  powerpc/85xx: bsc9131 - Correct typo in SDHC device node
  powerpc/e500/qemu-e500: enable coreint
  powerpc/mpic: allow coreint to be determined by MPIC version
  powerpc/fsl_pci: Store the pci ctlr device ptr in the pci ctlr struct
  powerpc/85xx: Board support for ppa8548
  powerpc/fsl: remove extraneous DIU platform functions
  arch/powerpc/platforms/85xx/p1022_ds.c: adjust duplicate test
  powerpc: Documentation for transactional memory on powerpc
  powerpc: Add transactional memory to pseries and ppc64 defconfigs
  powerpc: Add config option for transactional memory
  powerpc: Add transactional memory to POWER8 cpu features
  powerpc: Add new transactional memory state to the signal context
  powerpc: Hook in new transactional memory code
  powerpc: Routines for FP/VSX/VMX unavailable during a transaction
  powerpc: Add transactional memory unavaliable execption handler
  powerpc: Add reclaim and recheckpoint functions for context switching transactional memory processes
  powerpc: Add FP/VSX and VMX register load functions for transactional memory
  powerpc: Add helper functions for transactional memory context switching
  ...

2 files changed, 66 insertions, 29 deletions

diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index fa476d50791..65362e98eb2 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,
@@ -1359,6 +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;
@@ -1422,11 +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
@@ -1438,7 +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;
@@ -1449,11 +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)
@@ -1468,33 +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
diff --git a/arch/powerpc/perf/e500-pmu.c b/arch/powerpc/perf/e500-pmu.c
index cb2e2949c8d..fb664929f5d 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