From 4d9690dd56b0d18f2af8a9d4a279cb205aae3345 Mon Sep 17 00:00:00 2001 From: Joel Stanley Date: Tue, 8 Jul 2014 16:08:21 +0930 Subject: powerpc/perf: Add PPMU_ARCH_207S define Instead of separate bits for every POWER8 PMU feature, have a single one for v2.07 of the architecture. This saves us adding a MMCR2 define for a future patch. Cc: stable@vger.kernel.org Signed-off-by: Joel Stanley Acked-by: Michael Ellerman Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/perf/core-book3s.c | 6 +++--- arch/powerpc/perf/power8-pmu.c | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'arch/powerpc/perf') diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 4520c9356b54..a2ff1bda706a 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -485,7 +485,7 @@ static bool is_ebb_event(struct perf_event *event) * check that the PMU supports EBB, meaning those that don't can still * use bit 63 of the event code for something else if they wish. */ - return (ppmu->flags & PPMU_EBB) && + return (ppmu->flags & PPMU_ARCH_207S) && ((event->attr.config >> PERF_EVENT_CONFIG_EBB_SHIFT) & 1); } @@ -777,7 +777,7 @@ void perf_event_print_debug(void) if (ppmu->flags & PPMU_HAS_SIER) sier = mfspr(SPRN_SIER); - if (ppmu->flags & PPMU_EBB) { + if (ppmu->flags & PPMU_ARCH_207S) { pr_info("MMCR2: %016lx EBBHR: %016lx\n", mfspr(SPRN_MMCR2), mfspr(SPRN_EBBHR)); pr_info("EBBRR: %016lx BESCR: %016lx\n", @@ -1696,7 +1696,7 @@ static int power_pmu_event_init(struct perf_event *event) if (has_branch_stack(event)) { /* PMU has BHRB enabled */ - if (!(ppmu->flags & PPMU_BHRB)) + if (!(ppmu->flags & PPMU_ARCH_207S)) return -EOPNOTSUPP; } diff --git a/arch/powerpc/perf/power8-pmu.c b/arch/powerpc/perf/power8-pmu.c index fe2763b6e039..639cd9156585 100644 --- a/arch/powerpc/perf/power8-pmu.c +++ b/arch/powerpc/perf/power8-pmu.c @@ -792,7 +792,7 @@ static struct power_pmu power8_pmu = { .get_constraint = power8_get_constraint, .get_alternatives = power8_get_alternatives, .disable_pmc = power8_disable_pmc, - .flags = PPMU_HAS_SSLOT | PPMU_HAS_SIER | PPMU_BHRB | PPMU_EBB, + .flags = PPMU_HAS_SSLOT | PPMU_HAS_SIER | PPMU_ARCH_207S, .n_generic = ARRAY_SIZE(power8_generic_events), .generic_events = power8_generic_events, .cache_events = &power8_cache_events, -- cgit v1.2.1 From b50a6c584bb47b370f84bfd746770c0bbe7129b7 Mon Sep 17 00:00:00 2001 From: Joel Stanley Date: Tue, 8 Jul 2014 16:08:22 +0930 Subject: powerpc/perf: Clear MMCR2 when enabling PMU On POWER8 when switching to a KVM guest we set bits in MMCR2 to freeze the PMU counters. Aside from on boot they are then never reset, resulting in stuck perf counters for any user in the guest or host. We now set MMCR2 to 0 whenever enabling the PMU, which provides a sane state for perf to use the PMU counters under either the guest or the host. This was manifesting as a bug with ppc64_cpu --frequency: $ sudo ppc64_cpu --frequency WARNING: couldn't run on cpu 0 WARNING: couldn't run on cpu 8 ... WARNING: couldn't run on cpu 144 WARNING: couldn't run on cpu 152 min: 18446744073.710 GHz (cpu -1) max: 0.000 GHz (cpu -1) avg: 0.000 GHz The command uses a perf counter to measure CPU cycles over a fixed amount of time, in order to approximate the frequency of the machine. The counters were returning zero once a guest was started, regardless of weather it was still running or had been shut down. By dumping the value of MMCR2, it was observed that once a guest is running MMCR2 is set to 1s - which stops counters from running: $ sudo sh -c 'echo p > /proc/sysrq-trigger' CPU: 0 PMU registers, ppmu = POWER8 n_counters = 6 PMC1: 5b635e38 PMC2: 00000000 PMC3: 00000000 PMC4: 00000000 PMC5: 1bf5a646 PMC6: 5793d378 PMC7: deadbeef PMC8: deadbeef MMCR0: 0000000080000000 MMCR1: 000000001e000000 MMCRA: 0000040000000000 MMCR2: fffffffffffffc00 EBBHR: 0000000000000000 EBBRR: 0000000000000000 BESCR: 0000000000000000 SIAR: 00000000000a51cc SDAR: c00000000fc40000 SIER: 0000000001000000 This is done unconditionally in book3s_hv_interrupts.S upon entering the guest, and the original value is only save/restored if the host has indicated it was using the PMU. This is okay, however the user of the PMU needs to ensure that it is in a defined state when it starts using it. Fixes: e05b9b9e5c10 ("powerpc/perf: Power8 PMU support") Cc: stable@vger.kernel.org Signed-off-by: Joel Stanley Acked-by: Michael Ellerman Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/perf/core-book3s.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch/powerpc/perf') diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index a2ff1bda706a..bae697cd5925 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -1300,6 +1300,9 @@ static void power_pmu_enable(struct pmu *pmu) write_mmcr0(cpuhw, mmcr0); + if (ppmu->flags & PPMU_ARCH_207S) + mtspr(SPRN_MMCR2, 0); + /* * Enable instruction sampling if necessary */ -- cgit v1.2.1 From f56029410a13cae3652d1f34788045c40a13ffc7 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Thu, 29 May 2014 08:15:38 +1000 Subject: powerpc/perf: Never program book3s PMCs with values >= 0x80000000 We are seeing a lot of PMU warnings on POWER8: Can't find PMC that caused IRQ Looking closer, the active PMC is 0 at this point and we took a PMU exception on the transition from negative to 0. Some versions of POWER8 have an issue where they edge detect and not level detect PMC overflows. A number of places program the PMC with (0x80000000 - period_left), where period_left can be negative. We can either fix all of these or just ensure that period_left is always >= 1. This patch takes the second option. Cc: Signed-off-by: Anton Blanchard Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/perf/core-book3s.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/perf') diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index bae697cd5925..6b0641c3f03f 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -996,7 +996,22 @@ static void power_pmu_read(struct perf_event *event) } while (local64_cmpxchg(&event->hw.prev_count, prev, val) != prev); local64_add(delta, &event->count); - local64_sub(delta, &event->hw.period_left); + + /* + * A number of places program the PMC with (0x80000000 - period_left). + * We never want period_left to be less than 1 because we will program + * the PMC with a value >= 0x800000000 and an edge detected PMC will + * roll around to 0 before taking an exception. We have seen this + * on POWER8. + * + * To fix this, clamp the minimum value of period_left to 1. + */ + do { + prev = local64_read(&event->hw.period_left); + val = prev - delta; + if (val < 1) + val = 1; + } while (local64_cmpxchg(&event->hw.period_left, prev, val) != prev); } /* -- cgit v1.2.1