From 1f6a1e2d7d7135280125418b25d35aebd6fa0952 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 14 Mar 2019 12:58:52 +0100 Subject: [PATCH] perf/x86: Remove PERF_X86_EVENT_COMMITTED The flag PERF_X86_EVENT_COMMITTED is used to find uncommitted events for which to call put_event_constraint() when scheduling fails. These are the newly added events to the list, and must form, per definition, the tail of cpuc->event_list[]. By computing the list index of the last successfull schedule, then iteration can start there and the flag is redundant. There are only 3 callers of x86_schedule_events(), notably: - x86_pmu_add() - x86_pmu_commit_txn() - validate_group() For x86_pmu_add(), cpuc->n_events isn't updated until after schedule_events() succeeds, therefore cpuc->n_events points to the desired index. For x86_pmu_commit_txn(), cpuc->n_events is updated, but we can trivially compute the desired value with cpuc->n_txn -- the number of events added in this transaction. For validate_group(), we can make the rule for x86_pmu_add() work by simply setting cpuc->n_events to 0 before calling schedule_events(). Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Stephane Eranian Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Vince Weaver Signed-off-by: Ingo Molnar --- arch/x86/events/core.c | 28 +++++++++++++--------------- arch/x86/events/perf_event.h | 19 +++++++++---------- 2 files changed, 22 insertions(+), 25 deletions(-) diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 508bf5355a5a..9cab5adfa87a 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -925,19 +925,23 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) if (!unsched && assign) { for (i = 0; i < n; i++) { e = cpuc->event_list[i]; - e->hw.flags |= PERF_X86_EVENT_COMMITTED; if (x86_pmu.commit_scheduling) x86_pmu.commit_scheduling(cpuc, i, assign[i]); } } else { - for (i = 0; i < n; i++) { + /* + * Compute the number of events already present; see + * x86_pmu_add(), validate_group() and x86_pmu_commit_txn(). + * For the former two cpuc->n_events hasn't been updated yet, + * while for the latter cpuc->n_txn contains the number of + * events added in the current transaction. + */ + i = cpuc->n_events; + if (cpuc->txn_flags & PERF_PMU_TXN_ADD) + i -= cpuc->n_txn; + + for (; i < n; i++) { e = cpuc->event_list[i]; - /* - * do not put_constraint() on comitted events, - * because they are good to go - */ - if ((e->hw.flags & PERF_X86_EVENT_COMMITTED)) - continue; /* * release events that failed scheduling @@ -1371,11 +1375,6 @@ static void x86_pmu_del(struct perf_event *event, int flags) struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); int i; - /* - * event is descheduled - */ - event->hw.flags &= ~PERF_X86_EVENT_COMMITTED; - /* * If we're called during a txn, we only need to undo x86_pmu.add. * The events never got scheduled and ->cancel_txn will truncate @@ -2079,8 +2078,7 @@ static int validate_group(struct perf_event *event) if (n < 0) goto out; - fake_cpuc->n_events = n; - + fake_cpuc->n_events = 0; ret = x86_pmu.schedule_events(fake_cpuc, n, NULL); out: diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index a75955741c50..b4d41829da4f 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -55,22 +55,21 @@ struct event_constraint { int overlap; int flags; }; + /* * struct hw_perf_event.flags flags */ #define PERF_X86_EVENT_PEBS_LDLAT 0x0001 /* ld+ldlat data address sampling */ #define PERF_X86_EVENT_PEBS_ST 0x0002 /* st data address sampling */ #define PERF_X86_EVENT_PEBS_ST_HSW 0x0004 /* haswell style datala, store */ -#define PERF_X86_EVENT_COMMITTED 0x0008 /* event passed commit_txn */ -#define PERF_X86_EVENT_PEBS_LD_HSW 0x0010 /* haswell style datala, load */ -#define PERF_X86_EVENT_PEBS_NA_HSW 0x0020 /* haswell style datala, unknown */ -#define PERF_X86_EVENT_EXCL 0x0040 /* HT exclusivity on counter */ -#define PERF_X86_EVENT_DYNAMIC 0x0080 /* dynamic alloc'd constraint */ -#define PERF_X86_EVENT_RDPMC_ALLOWED 0x0100 /* grant rdpmc permission */ -#define PERF_X86_EVENT_EXCL_ACCT 0x0200 /* accounted EXCL event */ -#define PERF_X86_EVENT_AUTO_RELOAD 0x0400 /* use PEBS auto-reload */ -#define PERF_X86_EVENT_LARGE_PEBS 0x0800 /* use large PEBS */ - +#define PERF_X86_EVENT_PEBS_LD_HSW 0x0008 /* haswell style datala, load */ +#define PERF_X86_EVENT_PEBS_NA_HSW 0x0010 /* haswell style datala, unknown */ +#define PERF_X86_EVENT_EXCL 0x0020 /* HT exclusivity on counter */ +#define PERF_X86_EVENT_DYNAMIC 0x0040 /* dynamic alloc'd constraint */ +#define PERF_X86_EVENT_RDPMC_ALLOWED 0x0080 /* grant rdpmc permission */ +#define PERF_X86_EVENT_EXCL_ACCT 0x0100 /* accounted EXCL event */ +#define PERF_X86_EVENT_AUTO_RELOAD 0x0200 /* use PEBS auto-reload */ +#define PERF_X86_EVENT_LARGE_PEBS 0x0400 /* use large PEBS */ struct amd_nb { int nb_id; /* NorthBridge id */ -- 2.25.1