From: Peter Zijlstra peterz@infradead.org
mainline inclusion from mainline-v5.2-rc1 commit 63b79f6ebc464afb730bc45762c820795e276da1 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I47H3V CVE: NA
--------------------------------
Icelake extended the general counters to 8, even when SMT is enabled. However only a (large) subset of the events can be used on all 8 counters.
The events that can or cannot be used on all counters are organized in ranges.
A lot of scheduler constraints are required to handle all this.
To avoid blowing up the tables add event code ranges to the constraint tables, and a new inline function to match them.
Originally-by: Andi Kleen ak@linux.intel.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org # developer hat on Signed-off-by: Kan Liang kan.liang@linux.intel.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org # maintainer hat on Cc: Alexander Shishkin alexander.shishkin@linux.intel.com Cc: Arnaldo Carvalho de Melo acme@redhat.com Cc: Jiri Olsa jolsa@redhat.com Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Peter Zijlstra peterz@infradead.org Cc: Stephane Eranian eranian@google.com Cc: Thomas Gleixner tglx@linutronix.de Cc: Vince Weaver vincent.weaver@maine.edu Cc: acme@kernel.org Cc: jolsa@kernel.org Link: https://lkml.kernel.org/r/20190402194509.2832-8-kan.liang@linux.intel.com Signed-off-by: Ingo Molnar mingo@kernel.org Signed-off-by: Jackie Liu liuyun01@kylinos.cn Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Reviewed-by: Yang Jihong yangjihong1@huawei.com Reviewed-by: Xie XiuQi xiexiuqi@huawei.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- arch/x86/events/intel/core.c | 2 +- arch/x86/events/intel/ds.c | 2 +- arch/x86/events/perf_event.h | 44 +++++++++++++++++++++++++++++++----- 3 files changed, 40 insertions(+), 8 deletions(-)
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 2dd8b0d64295a..710c24846df24 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2573,7 +2573,7 @@ x86_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
if (x86_pmu.event_constraints) { for_each_event_constraint(c, x86_pmu.event_constraints) { - if ((event->hw.config & c->cmask) == c->code) { + if (constraint_match(c, event->hw.config)) { event->hw.flags |= c->flags; return c; } diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index b3279feff458b..0405ed81a791d 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -858,7 +858,7 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event)
if (x86_pmu.pebs_constraints) { for_each_event_constraint(c, x86_pmu.pebs_constraints) { - if ((event->hw.config & c->cmask) == c->code) { + if (constraint_match(c, event->hw.config)) { event->hw.flags |= c->flags; return c; } diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 66e99a7c3f956..aec00e9f263e6 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -49,12 +49,19 @@ struct event_constraint { unsigned long idxmsk[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; u64 idxmsk64; }; - u64 code; - u64 cmask; - int weight; - int overlap; - int flags; + u64 code; + u64 cmask; + int weight; + int overlap; + int flags; + unsigned int size; }; + +static inline bool constraint_match(struct event_constraint *c, u64 ecode) +{ + return ((ecode & c->cmask) - c->code) <= (u64)c->size; +} + /* * struct hw_perf_event.flags flags */ @@ -257,18 +264,29 @@ struct cpu_hw_events { void *kfree_on_online[X86_PERF_KFREE_MAX]; };
-#define __EVENT_CONSTRAINT(c, n, m, w, o, f) {\ +#define __EVENT_CONSTRAINT_RANGE(c, e, n, m, w, o, f) { \ { .idxmsk64 = (n) }, \ .code = (c), \ + .size = (e) - (c), \ .cmask = (m), \ .weight = (w), \ .overlap = (o), \ .flags = f, \ }
+#define __EVENT_CONSTRAINT(c, n, m, w, o, f) \ + __EVENT_CONSTRAINT_RANGE(c, c, n, m, w, o, f) + #define EVENT_CONSTRAINT(c, n, m) \ __EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 0, 0)
+/* + * The constraint_match() function only works for 'simple' event codes + * and not for extended (AMD64_EVENTSEL_EVENT) events codes. + */ +#define EVENT_CONSTRAINT_RANGE(c, e, n, m) \ + __EVENT_CONSTRAINT_RANGE(c, e, n, m, HWEIGHT(n), 0, 0) + #define INTEL_EXCLEVT_CONSTRAINT(c, n) \ __EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT, HWEIGHT(n),\ 0, PERF_X86_EVENT_EXCL) @@ -303,6 +321,12 @@ struct cpu_hw_events { #define INTEL_EVENT_CONSTRAINT(c, n) \ EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT)
+/* + * Constraint on a range of Event codes + */ +#define INTEL_EVENT_CONSTRAINT_RANGE(c, e, n) \ + EVENT_CONSTRAINT_RANGE(c, e, n, ARCH_PERFMON_EVENTSEL_EVENT) + /* * Constraint on the Event code + UMask + fixed-mask * @@ -350,6 +374,9 @@ struct cpu_hw_events { #define INTEL_FLAGS_EVENT_CONSTRAINT(c, n) \ EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS)
+#define INTEL_FLAGS_EVENT_CONSTRAINT_RANGE(c, e, n) \ + EVENT_CONSTRAINT_RANGE(c, e, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS) + /* Check only flags, but allow all event/umask */ #define INTEL_ALL_EVENT_CONSTRAINT(code, n) \ EVENT_CONSTRAINT(code, n, X86_ALL_EVENT_FLAGS) @@ -366,6 +393,11 @@ struct cpu_hw_events { ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \ HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW)
+#define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(code, end, n) \ + __EVENT_CONSTRAINT_RANGE(code, end, n, \ + ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \ + HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW) + #define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_XLD(code, n) \ __EVENT_CONSTRAINT(code, n, \ ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \