From fbbe07011581990ef74dfac06dc8511b1a14badb Mon Sep 17 00:00:00 2001 From: Sukadev Bhattiprolu Date: Thu, 3 Sep 2015 20:07:45 -0700 Subject: perf/core: Add a 'flags' parameter to the PMU transactional interfaces Currently, the PMU interface allows reading only one counter at a time. But some PMUs like the 24x7 counters in Power, support reading several counters at once. To leveage this functionality, extend the transaction interface to support a "transaction type". The first type, PERF_PMU_TXN_ADD, refers to the existing transactions, i.e. used to _schedule_ all the events on the PMU as a group. A second transaction type, PERF_PMU_TXN_READ, will be used in a follow-on patch, by the 24x7 counters to read several counters at once. Extend the transaction interfaces to the PMU to accept a 'txn_flags' parameter and use this parameter to ignore any transactions that are not of type PERF_PMU_TXN_ADD. Thanks to Peter Zijlstra for his input. Signed-off-by: Sukadev Bhattiprolu [peterz: s390 compile fix] Signed-off-by: Peter Zijlstra (Intel) Acked-by: Michael Ellerman Cc: Arnaldo Carvalho de Melo Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Link: http://lkml.kernel.org/r/1441336073-22750-3-git-send-email-sukadev@linux.vnet.ibm.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event.c | 32 +++++++++++++++++++++++++++++++- 1 file changed, 31 insertions(+), 1 deletion(-) (limited to 'arch/x86/kernel/cpu/perf_event.c') diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 66dd3fe99b82..dc77ef470e0e 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1748,9 +1748,21 @@ static inline void x86_pmu_read(struct perf_event *event) * Start group events scheduling transaction * Set the flag to make pmu::enable() not perform the * schedulability test, it will be performed at commit time + * + * We only support PERF_PMU_TXN_ADD transactions. Save the + * transaction flags but otherwise ignore non-PERF_PMU_TXN_ADD + * transactions. */ -static void x86_pmu_start_txn(struct pmu *pmu) +static void x86_pmu_start_txn(struct pmu *pmu, unsigned int txn_flags) { + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + + WARN_ON_ONCE(cpuc->txn_flags); /* txn already in flight */ + + cpuc->txn_flags = txn_flags; + if (txn_flags & ~PERF_PMU_TXN_ADD) + return; + perf_pmu_disable(pmu); __this_cpu_or(cpu_hw_events.group_flag, PERF_EVENT_TXN); __this_cpu_write(cpu_hw_events.n_txn, 0); @@ -1763,6 +1775,16 @@ static void x86_pmu_start_txn(struct pmu *pmu) */ static void x86_pmu_cancel_txn(struct pmu *pmu) { + unsigned int txn_flags; + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + + WARN_ON_ONCE(!cpuc->txn_flags); /* no txn in flight */ + + txn_flags = cpuc->txn_flags; + cpuc->txn_flags = 0; + if (txn_flags & ~PERF_PMU_TXN_ADD) + return; + __this_cpu_and(cpu_hw_events.group_flag, ~PERF_EVENT_TXN); /* * Truncate collected array by the number of events added in this @@ -1786,6 +1808,13 @@ static int x86_pmu_commit_txn(struct pmu *pmu) int assign[X86_PMC_IDX_MAX]; int n, ret; + WARN_ON_ONCE(!cpuc->txn_flags); /* no txn in flight */ + + if (cpuc->txn_flags & ~PERF_PMU_TXN_ADD) { + cpuc->txn_flags = 0; + return 0; + } + n = cpuc->n_events; if (!x86_pmu_initialized()) @@ -1802,6 +1831,7 @@ static int x86_pmu_commit_txn(struct pmu *pmu) memcpy(cpuc->assign, assign, n*sizeof(int)); cpuc->group_flag &= ~PERF_EVENT_TXN; + cpuc->txn_flags = 0; perf_pmu_enable(pmu); return 0; } -- cgit v1.2.3 From 8f3e5684d3fbd91ead283916676fa3dac22615e5 Mon Sep 17 00:00:00 2001 From: Sukadev Bhattiprolu Date: Thu, 3 Sep 2015 20:07:53 -0700 Subject: perf/core: Drop PERF_EVENT_TXN We currently use PERF_EVENT_TXN flag to determine if we are in the middle of a transaction. If in a transaction, we defer the schedulability checks from pmu->add() operation to the pmu->commit() operation. Now that we have "transaction types" (PERF_PMU_TXN_ADD, PERF_PMU_TXN_READ) we can use the type to determine if we are in a transaction and drop the PERF_EVENT_TXN flag. When PERF_EVENT_TXN is dropped, the cpuhw->group_flag on some architectures becomes unused, so drop that field as well. This is an extension of the Powerpc patch from Peter Zijlstra to s390, Sparc and x86 architectures. Signed-off-by: Sukadev Bhattiprolu Signed-off-by: Peter Zijlstra (Intel) Cc: Arnaldo Carvalho de Melo Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Michael Ellerman Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Link: http://lkml.kernel.org/r/1441336073-22750-11-git-send-email-sukadev@linux.vnet.ibm.com Signed-off-by: Ingo Molnar --- arch/powerpc/perf/core-book3s.c | 6 +----- arch/s390/kernel/perf_cpum_cf.c | 5 +---- arch/sparc/kernel/perf_event.c | 6 +----- arch/x86/kernel/cpu/perf_event.c | 7 ++----- arch/x86/kernel/cpu/perf_event.h | 1 - include/linux/perf_event.h | 2 -- 6 files changed, 5 insertions(+), 22 deletions(-) (limited to 'arch/x86/kernel/cpu/perf_event.c') diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index c84074185c80..d1e65ce545b3 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -48,7 +48,6 @@ struct cpu_hw_events { unsigned long amasks[MAX_HWEVENTS][MAX_EVENT_ALTERNATIVES]; unsigned long avalues[MAX_HWEVENTS][MAX_EVENT_ALTERNATIVES]; - unsigned int group_flag; unsigned int txn_flags; int n_txn_start; @@ -1442,7 +1441,7 @@ static int power_pmu_add(struct perf_event *event, int ef_flags) * skip the schedulability test here, it will be performed * at commit time(->commit_txn) as a whole */ - if (cpuhw->group_flag & PERF_EVENT_TXN) + if (cpuhw->txn_flags & PERF_PMU_TXN_ADD) goto nocheck; if (check_excludes(cpuhw->event, cpuhw->flags, n0, 1)) @@ -1603,7 +1602,6 @@ static void power_pmu_start_txn(struct pmu *pmu, unsigned int txn_flags) return; perf_pmu_disable(pmu); - cpuhw->group_flag |= PERF_EVENT_TXN; cpuhw->n_txn_start = cpuhw->n_events; } @@ -1624,7 +1622,6 @@ static void power_pmu_cancel_txn(struct pmu *pmu) if (txn_flags & ~PERF_PMU_TXN_ADD) return; - cpuhw->group_flag &= ~PERF_EVENT_TXN; perf_pmu_enable(pmu); } @@ -1659,7 +1656,6 @@ static int power_pmu_commit_txn(struct pmu *pmu) for (i = cpuhw->n_txn_start; i < n; ++i) cpuhw->event[i]->hw.config = cpuhw->events[i]; - cpuhw->group_flag &= ~PERF_EVENT_TXN; cpuhw->txn_flags = 0; perf_pmu_enable(pmu); return 0; diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c index 19138be412d6..cb774ff6e749 100644 --- a/arch/s390/kernel/perf_cpum_cf.c +++ b/arch/s390/kernel/perf_cpum_cf.c @@ -536,7 +536,7 @@ static int cpumf_pmu_add(struct perf_event *event, int flags) * For group events transaction, the authorization check is * done in cpumf_pmu_commit_txn(). */ - if (!(cpuhw->flags & PERF_EVENT_TXN)) + if (!(cpuhw->txn_flags & PERF_PMU_TXN_ADD)) if (validate_ctr_auth(&event->hw)) return -EPERM; @@ -590,7 +590,6 @@ static void cpumf_pmu_start_txn(struct pmu *pmu, unsigned int txn_flags) return; perf_pmu_disable(pmu); - cpuhw->flags |= PERF_EVENT_TXN; cpuhw->tx_state = cpuhw->state; } @@ -613,7 +612,6 @@ static void cpumf_pmu_cancel_txn(struct pmu *pmu) WARN_ON(cpuhw->tx_state != cpuhw->state); - cpuhw->flags &= ~PERF_EVENT_TXN; perf_pmu_enable(pmu); } @@ -640,7 +638,6 @@ static int cpumf_pmu_commit_txn(struct pmu *pmu) if ((state & cpuhw->info.auth_ctl) != state) return -EPERM; - cpuhw->flags &= ~PERF_EVENT_TXN; cpuhw->txn_flags = 0; perf_pmu_enable(pmu); return 0; diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c index 2c0984d146ec..b0da5aedb336 100644 --- a/arch/sparc/kernel/perf_event.c +++ b/arch/sparc/kernel/perf_event.c @@ -108,7 +108,6 @@ struct cpu_hw_events { /* Enabled/disable state. */ int enabled; - unsigned int group_flag; unsigned int txn_flags; }; static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = { .enabled = 1, }; @@ -1380,7 +1379,7 @@ static int sparc_pmu_add(struct perf_event *event, int ef_flags) * skip the schedulability test here, it will be performed * at commit time(->commit_txn) as a whole */ - if (cpuc->group_flag & PERF_EVENT_TXN) + if (cpuc->txn_flags & PERF_PMU_TXN_ADD) goto nocheck; if (check_excludes(cpuc->event, n0, 1)) @@ -1506,7 +1505,6 @@ static void sparc_pmu_start_txn(struct pmu *pmu, unsigned int txn_flags) return; perf_pmu_disable(pmu); - cpuhw->group_flag |= PERF_EVENT_TXN; } /* @@ -1526,7 +1524,6 @@ static void sparc_pmu_cancel_txn(struct pmu *pmu) if (txn_flags & ~PERF_PMU_TXN_ADD) return; - cpuhw->group_flag &= ~PERF_EVENT_TXN; perf_pmu_enable(pmu); } @@ -1556,7 +1553,6 @@ static int sparc_pmu_commit_txn(struct pmu *pmu) if (sparc_check_constraints(cpuc->event, cpuc->events, n)) return -EAGAIN; - cpuc->group_flag &= ~PERF_EVENT_TXN; cpuc->txn_flags = 0; perf_pmu_enable(pmu); return 0; diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index dc77ef470e0e..4562cf070c27 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1175,7 +1175,7 @@ static int x86_pmu_add(struct perf_event *event, int flags) * skip the schedulability test here, it will be performed * at commit time (->commit_txn) as a whole. */ - if (cpuc->group_flag & PERF_EVENT_TXN) + if (cpuc->txn_flags & PERF_PMU_TXN_ADD) goto done_collect; ret = x86_pmu.schedule_events(cpuc, n, assign); @@ -1326,7 +1326,7 @@ static void x86_pmu_del(struct perf_event *event, int flags) * XXX assumes any ->del() called during a TXN will only be on * an event added during that same TXN. */ - if (cpuc->group_flag & PERF_EVENT_TXN) + if (cpuc->txn_flags & PERF_PMU_TXN_ADD) return; /* @@ -1764,7 +1764,6 @@ static void x86_pmu_start_txn(struct pmu *pmu, unsigned int txn_flags) return; perf_pmu_disable(pmu); - __this_cpu_or(cpu_hw_events.group_flag, PERF_EVENT_TXN); __this_cpu_write(cpu_hw_events.n_txn, 0); } @@ -1785,7 +1784,6 @@ static void x86_pmu_cancel_txn(struct pmu *pmu) if (txn_flags & ~PERF_PMU_TXN_ADD) return; - __this_cpu_and(cpu_hw_events.group_flag, ~PERF_EVENT_TXN); /* * Truncate collected array by the number of events added in this * transaction. See x86_pmu_add() and x86_pmu_*_txn(). @@ -1830,7 +1828,6 @@ static int x86_pmu_commit_txn(struct pmu *pmu) */ memcpy(cpuc->assign, assign, n*sizeof(int)); - cpuc->group_flag &= ~PERF_EVENT_TXN; cpuc->txn_flags = 0; perf_pmu_enable(pmu); return 0; diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index c99c93b9e348..953a0e4e3284 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -195,7 +195,6 @@ struct cpu_hw_events { int n_excl; /* the number of exclusive events */ - unsigned int group_flag; unsigned int txn_flags; int is_fake; diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index b83cea932f74..d841d33bcdc9 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -199,8 +199,6 @@ struct perf_event; /* * Common implementation detail of pmu::{start,commit,cancel}_txn */ -#define PERF_EVENT_TXN 0x1 - #define PERF_PMU_TXN_ADD 0x1 /* txn to add/schedule event on PMU */ #define PERF_PMU_TXN_READ 0x2 /* txn to read event group from PMU */ -- cgit v1.2.3