diff options
author | Scott Wood <scottwood@freescale.com> | 2013-11-01 21:17:16 (GMT) |
---|---|---|
committer | Scott Wood <scottwood@freescale.com> | 2013-11-03 22:47:10 (GMT) |
commit | 31110de40dca4d4aeff4f253b3def948b88fa590 (patch) | |
tree | 0d811783836d52f15e37b4244de54f44ed4f93ad /arch/powerpc/perf/core-book3s.c | |
parent | ae60d5d27c429b13cf28a09ab8b9d30682433c5a (diff) | |
parent | 8bb495e3f02401ee6f76d1b1d77f3ac9f079e376 (diff) | |
download | linux-fsl-qoriq-31110de40dca4d4aeff4f253b3def948b88fa590.tar.xz |
Merge tag 'v3.10' into sdk-kernel-3.10
git rebase --continue
Linux 3.10
Conflicts:
Documentation/virtual/kvm/api.txt
arch/ia64/kvm/Makefile
arch/powerpc/Kconfig
arch/powerpc/Makefile
arch/powerpc/boot/dts/b4420qds.dts
arch/powerpc/boot/dts/b4860qds.dts
arch/powerpc/boot/dts/b4qds.dts
arch/powerpc/boot/dts/fsl/b4420si-post.dtsi
arch/powerpc/boot/dts/fsl/b4420si-pre.dtsi
arch/powerpc/boot/dts/fsl/b4860si-post.dtsi
arch/powerpc/boot/dts/fsl/b4860si-pre.dtsi
arch/powerpc/boot/dts/fsl/b4si-post.dtsi
arch/powerpc/boot/dts/fsl/p1010si-post.dtsi
arch/powerpc/boot/dts/fsl/p2041si-post.dtsi
arch/powerpc/boot/dts/fsl/p3041si-post.dtsi
arch/powerpc/boot/dts/fsl/p4080si-post.dtsi
arch/powerpc/boot/dts/fsl/p5020si-post.dtsi
arch/powerpc/boot/dts/fsl/p5040si-post.dtsi
arch/powerpc/boot/dts/fsl/qonverge-usb2-dr-0.dtsi
arch/powerpc/boot/dts/fsl/qoriq-sec5.0-0.dtsi
arch/powerpc/boot/dts/fsl/t4240si-post.dtsi
arch/powerpc/boot/dts/fsl/t4240si-pre.dtsi
arch/powerpc/boot/dts/p1025rdb_36b.dts
arch/powerpc/boot/dts/t4240qds.dts
arch/powerpc/configs/corenet64_smp_defconfig
arch/powerpc/configs/mpc85xx_defconfig
arch/powerpc/configs/mpc85xx_smp_defconfig
arch/powerpc/include/asm/cputable.h
arch/powerpc/include/asm/kvm_host.h
arch/powerpc/include/asm/kvm_ppc.h
arch/powerpc/include/asm/machdep.h
arch/powerpc/include/uapi/asm/kvm.h
arch/powerpc/kernel/cpu_setup_fsl_booke.S
arch/powerpc/kernel/cputable.c
arch/powerpc/kernel/idle.c
arch/powerpc/kernel/pci-common.c
arch/powerpc/kvm/Kconfig
arch/powerpc/kvm/book3s.c
arch/powerpc/kvm/booke.c
arch/powerpc/kvm/e500.c
arch/powerpc/kvm/e500_mmu.c
arch/powerpc/kvm/e500_mmu_host.c
arch/powerpc/kvm/e500mc.c
arch/powerpc/kvm/emulate.c
arch/powerpc/kvm/irq.h
arch/powerpc/kvm/mpic.c
arch/powerpc/kvm/powerpc.c
arch/powerpc/mm/tlb_nohash.c
arch/powerpc/platforms/85xx/Kconfig
arch/powerpc/platforms/85xx/b4_qds.c
arch/powerpc/platforms/85xx/t4240_qds.c
arch/powerpc/platforms/pseries/smp.c
arch/powerpc/sysdev/fsl_85xx_l2ctlr.c
arch/powerpc/sysdev/fsl_msi.c
arch/powerpc/sysdev/fsl_pci.c
arch/powerpc/sysdev/fsl_pci.h
arch/powerpc/sysdev/mpic.c
arch/x86/kvm/Makefile
arch/x86/kvm/x86.c
drivers/Kconfig
drivers/clk/Kconfig
drivers/cpufreq/Makefile
drivers/crypto/caam/caamalg.c
drivers/crypto/caam/intern.h
drivers/crypto/caam/jr.c
drivers/crypto/caam/regs.h
drivers/infiniband/ulp/ipoib/ipoib_ethtool.c
drivers/iommu/Makefile
drivers/iommu/amd_iommu.c
drivers/iommu/exynos-iommu.c
drivers/iommu/intel-iommu.c
drivers/iommu/iommu.c
drivers/iommu/msm_iommu.c
drivers/iommu/omap-iommu.c
drivers/iommu/tegra-gart.c
drivers/iommu/tegra-smmu.c
drivers/misc/Makefile
drivers/mmc/card/block.c
drivers/mmc/card/queue.c
drivers/mmc/core/core.c
drivers/mtd/nand/fsl_ifc_nand.c
drivers/net/ethernet/3com/3c501.c
drivers/net/ethernet/8390/3c503.c
drivers/net/ethernet/dec/ewrk3.c
drivers/net/ethernet/freescale/fec.c
drivers/net/ethernet/freescale/gianfar.c
drivers/net/ethernet/freescale/gianfar.h
drivers/net/ethernet/i825xx/3c505.c
drivers/net/ethernet/i825xx/3c507.c
drivers/rtc/rtc-ds3232.c
drivers/s390/net/qeth_core_main.c
drivers/staging/Kconfig
drivers/staging/Makefile
drivers/staging/ccg/u_ether.c
drivers/usb/gadget/fsl_udc_core.c
drivers/usb/otg/fsl_otg.c
drivers/vfio/vfio.c
drivers/watchdog/Kconfig
include/linux/iommu.h
include/linux/kvm_host.h
include/linux/mmc/sdhci.h
include/linux/msi.h
include/linux/netdev_features.h
include/linux/pci.h
include/linux/skbuff.h
include/net/ip6_route.h
include/net/sch_generic.h
include/net/xfrm.h
include/uapi/linux/kvm.h
net/core/netpoll.c
virt/kvm/irqchip.c
virt/kvm/kvm_main.c
Diffstat (limited to 'arch/powerpc/perf/core-book3s.c')
-rw-r--r-- | arch/powerpc/perf/core-book3s.c | 391 |
1 files changed, 334 insertions, 57 deletions
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index aa2465e..29c6482 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -13,11 +13,18 @@ #include <linux/perf_event.h> #include <linux/percpu.h> #include <linux/hardirq.h> +#include <linux/uaccess.h> #include <asm/reg.h> #include <asm/pmc.h> #include <asm/machdep.h> #include <asm/firmware.h> #include <asm/ptrace.h> +#include <asm/code-patching.h> + +#define BHRB_MAX_ENTRIES 32 +#define BHRB_TARGET 0x0000000000000002 +#define BHRB_PREDICTION 0x0000000000000001 +#define BHRB_EA 0xFFFFFFFFFFFFFFFC struct cpu_hw_events { int n_events; @@ -38,7 +45,15 @@ struct cpu_hw_events { unsigned int group_flag; int n_txn_start; + + /* BHRB bits */ + u64 bhrb_filter; /* BHRB HW branch filter */ + int bhrb_users; + void *bhrb_context; + struct perf_branch_stack bhrb_stack; + struct perf_branch_entry bhrb_entries[BHRB_MAX_ENTRIES]; }; + DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events); struct power_pmu *ppmu; @@ -87,8 +102,17 @@ static inline int siar_valid(struct pt_regs *regs) return 1; } +static inline void power_pmu_bhrb_enable(struct perf_event *event) {} +static inline void power_pmu_bhrb_disable(struct perf_event *event) {} +void power_pmu_flush_branch_stack(void) {} +static inline void power_pmu_bhrb_read(struct cpu_hw_events *cpuhw) {} #endif /* CONFIG_PPC32 */ +static bool regs_use_siar(struct pt_regs *regs) +{ + return !!regs->result; +} + /* * Things that are specific to 64-bit implementations. */ @@ -98,11 +122,12 @@ static inline unsigned long perf_ip_adjust(struct pt_regs *regs) { unsigned long mmcra = regs->dsisr; - if ((mmcra & MMCRA_SAMPLE_ENABLE) && !(ppmu->flags & PPMU_ALT_SIPR)) { + if ((ppmu->flags & PPMU_HAS_SSLOT) && (mmcra & MMCRA_SAMPLE_ENABLE)) { unsigned long slot = (mmcra & MMCRA_SLOT) >> MMCRA_SLOT_SHIFT; if (slot > 1) return 4 * (slot - 1); } + return 0; } @@ -111,43 +136,57 @@ static inline unsigned long perf_ip_adjust(struct pt_regs *regs) * If we're not doing instruction sampling, give them the SDAR * (sampled data address). If we are doing instruction sampling, then * only give them the SDAR if it corresponds to the instruction - * pointed to by SIAR; this is indicated by the [POWER6_]MMCRA_SDSYNC or - * the [POWER7P_]MMCRA_SDAR_VALID bit in MMCRA. + * pointed to by SIAR; this is indicated by the [POWER6_]MMCRA_SDSYNC, the + * [POWER7P_]MMCRA_SDAR_VALID bit in MMCRA, or the SDAR_VALID bit in SIER. */ static inline void perf_get_data_addr(struct pt_regs *regs, u64 *addrp) { unsigned long mmcra = regs->dsisr; - unsigned long sdsync; + bool sdar_valid; - if (ppmu->flags & PPMU_SIAR_VALID) - sdsync = POWER7P_MMCRA_SDAR_VALID; - else if (ppmu->flags & PPMU_ALT_SIPR) - sdsync = POWER6_MMCRA_SDSYNC; - else - sdsync = MMCRA_SDSYNC; + if (ppmu->flags & PPMU_HAS_SIER) + sdar_valid = regs->dar & SIER_SDAR_VALID; + else { + unsigned long sdsync; - if (!(mmcra & MMCRA_SAMPLE_ENABLE) || (mmcra & sdsync)) + if (ppmu->flags & PPMU_SIAR_VALID) + sdsync = POWER7P_MMCRA_SDAR_VALID; + else if (ppmu->flags & PPMU_ALT_SIPR) + sdsync = POWER6_MMCRA_SDSYNC; + else + sdsync = MMCRA_SDSYNC; + + sdar_valid = mmcra & sdsync; + } + + if (!(mmcra & MMCRA_SAMPLE_ENABLE) || sdar_valid) *addrp = mfspr(SPRN_SDAR); } -static bool mmcra_sihv(unsigned long mmcra) +static bool regs_sihv(struct pt_regs *regs) { unsigned long sihv = MMCRA_SIHV; + if (ppmu->flags & PPMU_HAS_SIER) + return !!(regs->dar & SIER_SIHV); + if (ppmu->flags & PPMU_ALT_SIPR) sihv = POWER6_MMCRA_SIHV; - return !!(mmcra & sihv); + return !!(regs->dsisr & sihv); } -static bool mmcra_sipr(unsigned long mmcra) +static bool regs_sipr(struct pt_regs *regs) { unsigned long sipr = MMCRA_SIPR; + if (ppmu->flags & PPMU_HAS_SIER) + return !!(regs->dar & SIER_SIPR); + if (ppmu->flags & PPMU_ALT_SIPR) sipr = POWER6_MMCRA_SIPR; - return !!(mmcra & sipr); + return !!(regs->dsisr & sipr); } static inline u32 perf_flags_from_msr(struct pt_regs *regs) @@ -161,8 +200,7 @@ static inline u32 perf_flags_from_msr(struct pt_regs *regs) static inline u32 perf_get_misc_flags(struct pt_regs *regs) { - unsigned long mmcra = regs->dsisr; - unsigned long use_siar = regs->result; + bool use_siar = regs_use_siar(regs); if (!use_siar) return perf_flags_from_msr(regs); @@ -181,16 +219,19 @@ static inline u32 perf_get_misc_flags(struct pt_regs *regs) } /* PR has priority over HV, so order below is important */ - if (mmcra_sipr(mmcra)) + if (regs_sipr(regs)) return PERF_RECORD_MISC_USER; - if (mmcra_sihv(mmcra) && (freeze_events_kernel != MMCR0_FCHV)) + + if (regs_sihv(regs) && (freeze_events_kernel != MMCR0_FCHV)) return PERF_RECORD_MISC_HYPERVISOR; + return PERF_RECORD_MISC_KERNEL; } /* * Overload regs->dsisr to store MMCRA so we only need to read it once * on each interrupt. + * Overload regs->dar to store SIER if we have it. * Overload regs->result to specify whether we should use the MSR (result * is zero) or the SIAR (result is non zero). */ @@ -200,6 +241,11 @@ static inline void perf_read_regs(struct pt_regs *regs) int marked = mmcra & MMCRA_SAMPLE_ENABLE; int use_siar; + regs->dsisr = mmcra; + + if (ppmu->flags & PPMU_HAS_SIER) + regs->dar = mfspr(SPRN_SIER); + /* * If this isn't a PMU exception (eg a software event) the SIAR is * not valid. Use pt_regs. @@ -223,12 +269,11 @@ static inline void perf_read_regs(struct pt_regs *regs) use_siar = 1; else if ((ppmu->flags & PPMU_NO_CONT_SAMPLING)) use_siar = 0; - else if (!(ppmu->flags & PPMU_NO_SIPR) && mmcra_sipr(mmcra)) + else if (!(ppmu->flags & PPMU_NO_SIPR) && regs_sipr(regs)) use_siar = 0; else use_siar = 1; - regs->dsisr = mmcra; regs->result = use_siar; } @@ -253,12 +298,170 @@ static inline int siar_valid(struct pt_regs *regs) unsigned long mmcra = regs->dsisr; int marked = mmcra & MMCRA_SAMPLE_ENABLE; - if ((ppmu->flags & PPMU_SIAR_VALID) && marked) - return mmcra & POWER7P_MMCRA_SIAR_VALID; + if (marked) { + if (ppmu->flags & PPMU_HAS_SIER) + return regs->dar & SIER_SIAR_VALID; + + if (ppmu->flags & PPMU_SIAR_VALID) + return mmcra & POWER7P_MMCRA_SIAR_VALID; + } return 1; } + +/* Reset all possible BHRB entries */ +static void power_pmu_bhrb_reset(void) +{ + asm volatile(PPC_CLRBHRB); +} + +static void power_pmu_bhrb_enable(struct perf_event *event) +{ + struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events); + + if (!ppmu->bhrb_nr) + return; + + /* Clear BHRB if we changed task context to avoid data leaks */ + if (event->ctx->task && cpuhw->bhrb_context != event->ctx) { + power_pmu_bhrb_reset(); + cpuhw->bhrb_context = event->ctx; + } + cpuhw->bhrb_users++; +} + +static void power_pmu_bhrb_disable(struct perf_event *event) +{ + struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events); + + if (!ppmu->bhrb_nr) + return; + + cpuhw->bhrb_users--; + WARN_ON_ONCE(cpuhw->bhrb_users < 0); + + if (!cpuhw->disabled && !cpuhw->bhrb_users) { + /* BHRB cannot be turned off when other + * events are active on the PMU. + */ + + /* avoid stale pointer */ + cpuhw->bhrb_context = NULL; + } +} + +/* Called from ctxsw to prevent one process's branch entries to + * mingle with the other process's entries during context switch. + */ +void power_pmu_flush_branch_stack(void) +{ + if (ppmu->bhrb_nr) + power_pmu_bhrb_reset(); +} +/* Calculate the to address for a branch */ +static __u64 power_pmu_bhrb_to(u64 addr) +{ + unsigned int instr; + int ret; + __u64 target; + + if (is_kernel_addr(addr)) + return branch_target((unsigned int *)addr); + + /* Userspace: need copy instruction here then translate it */ + pagefault_disable(); + ret = __get_user_inatomic(instr, (unsigned int __user *)addr); + if (ret) { + pagefault_enable(); + return 0; + } + pagefault_enable(); + + target = branch_target(&instr); + if ((!target) || (instr & BRANCH_ABSOLUTE)) + return target; + + /* Translate relative branch target from kernel to user address */ + return target - (unsigned long)&instr + addr; +} + +/* Processing BHRB entries */ +void power_pmu_bhrb_read(struct cpu_hw_events *cpuhw) +{ + u64 val; + u64 addr; + int r_index, u_index, pred; + + r_index = 0; + u_index = 0; + while (r_index < ppmu->bhrb_nr) { + /* Assembly read function */ + val = read_bhrb(r_index++); + if (!val) + /* Terminal marker: End of valid BHRB entries */ + break; + else { + addr = val & BHRB_EA; + pred = val & BHRB_PREDICTION; + + if (!addr) + /* invalid entry */ + continue; + + /* Branches are read most recent first (ie. mfbhrb 0 is + * the most recent branch). + * There are two types of valid entries: + * 1) a target entry which is the to address of a + * computed goto like a blr,bctr,btar. The next + * entry read from the bhrb will be branch + * corresponding to this target (ie. the actual + * blr/bctr/btar instruction). + * 2) a from address which is an actual branch. If a + * target entry proceeds this, then this is the + * matching branch for that target. If this is not + * following a target entry, then this is a branch + * where the target is given as an immediate field + * in the instruction (ie. an i or b form branch). + * In this case we need to read the instruction from + * memory to determine the target/to address. + */ + + if (val & BHRB_TARGET) { + /* Target branches use two entries + * (ie. computed gotos/XL form) + */ + cpuhw->bhrb_entries[u_index].to = addr; + cpuhw->bhrb_entries[u_index].mispred = pred; + cpuhw->bhrb_entries[u_index].predicted = ~pred; + + /* Get from address in next entry */ + val = read_bhrb(r_index++); + addr = val & BHRB_EA; + if (val & BHRB_TARGET) { + /* Shouldn't have two targets in a + row.. Reset index and try again */ + r_index--; + addr = 0; + } + cpuhw->bhrb_entries[u_index].from = addr; + } else { + /* Branches to immediate field + (ie I or B form) */ + cpuhw->bhrb_entries[u_index].from = addr; + cpuhw->bhrb_entries[u_index].to = + power_pmu_bhrb_to(addr); + cpuhw->bhrb_entries[u_index].mispred = pred; + cpuhw->bhrb_entries[u_index].predicted = ~pred; + } + u_index++; + + } + } + cpuhw->bhrb_stack.nr = u_index; + return; +} + #endif /* CONFIG_PPC64 */ static void perf_event_interrupt(struct pt_regs *regs); @@ -822,6 +1025,9 @@ static void power_pmu_enable(struct pmu *pmu) } out: + if (cpuhw->bhrb_users) + ppmu->config_bhrb(cpuhw->bhrb_filter); + local_irq_restore(flags); } @@ -880,8 +1086,16 @@ 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, @@ -903,6 +1117,9 @@ nocheck: ret = 0; out: + if (has_branch_stack(event)) + power_pmu_bhrb_enable(event); + perf_pmu_enable(event->pmu); local_irq_restore(flags); return ret; @@ -955,6 +1172,9 @@ static void power_pmu_del(struct perf_event *event, int ef_flags) cpuhw->mmcr[0] &= ~(MMCR0_PMXE | MMCR0_FCECE); } + if (has_branch_stack(event)) + power_pmu_bhrb_disable(event); + perf_pmu_enable(event->pmu); local_irq_restore(flags); } @@ -1187,9 +1407,11 @@ static int power_pmu_event_init(struct perf_event *event) if (!ppmu) return -ENOENT; - /* does not support taken branch sampling */ - if (has_branch_stack(event)) - return -EOPNOTSUPP; + if (has_branch_stack(event)) { + /* PMU has BHRB enabled */ + if (!(ppmu->flags & PPMU_BHRB)) + return -EOPNOTSUPP; + } switch (event->attr.type) { case PERF_TYPE_HARDWARE: @@ -1270,6 +1492,15 @@ static int power_pmu_event_init(struct perf_event *event) cpuhw = &get_cpu_var(cpu_hw_events); err = power_check_constraints(cpuhw, events, cflags, n + 1); + + if (has_branch_stack(event)) { + cpuhw->bhrb_filter = ppmu->bhrb_filter_map( + event->attr.branch_sample_type); + + if(cpuhw->bhrb_filter == -1) + return -EOPNOTSUPP; + } + put_cpu_var(cpu_hw_events); if (err) return -EINVAL; @@ -1305,6 +1536,16 @@ 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, @@ -1318,9 +1559,9 @@ struct pmu power_pmu = { .cancel_txn = power_pmu_cancel_txn, .commit_txn = power_pmu_commit_txn, .event_idx = power_pmu_event_idx, + .flush_branch_stack = power_pmu_flush_branch_stack, }; - /* * A counter has overflowed; update its count and record * things if requested. Note that interrupts are hard-disabled @@ -1349,6 +1590,8 @@ 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; @@ -1377,6 +1620,13 @@ static void record_and_restart(struct perf_event *event, unsigned long val, if (event->attr.sample_type & PERF_SAMPLE_ADDR) perf_get_data_addr(regs, &data.addr); + if (event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK) { + struct cpu_hw_events *cpuhw; + cpuhw = &__get_cpu_var(cpu_hw_events); + power_pmu_bhrb_read(cpuhw); + data.br_stack = &cpuhw->bhrb_stack; + } + if (perf_event_overflow(event, &data, regs)) power_pmu_stop(event, 0); } @@ -1402,7 +1652,7 @@ unsigned long perf_misc_flags(struct pt_regs *regs) */ unsigned long perf_instruction_pointer(struct pt_regs *regs) { - unsigned long use_siar = regs->result; + bool use_siar = regs_use_siar(regs); if (use_siar && siar_valid(regs)) return mfspr(SPRN_SIAR) + perf_ip_adjust(regs); @@ -1412,11 +1662,8 @@ 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 +1675,15 @@ 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 +1694,11 @@ 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 +1713,53 @@ 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 && !nmi && 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 +1812,8 @@ 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. |