LKML Archive on lore.kernel.org
 help / color / Atom feed
From: Peter Zijlstra <peterz@infradead.org>
To: mingo@kernel.org, tglx@linutronix.de, rostedt@goodmis.org
Cc: linux-kernel@vger.kernel.org, kan.liang@linux.intel.com,
	acme@kernel.org, mark.rutland@arm.com,
	alexander.shishkin@linux.intel.com, jolsa@redhat.com,
	namhyung@kernel.org, ak@linux.intel.com, eranian@google.com,
	peterz@infradead.org
Subject: [PATCH 2/6] perf/x86: Reduce stack usage for x86_pmu::drain_pebs()
Date: Fri, 30 Oct 2020 16:13:47 +0100
Message-ID: <20201030151955.054099690@infradead.org> (raw)
In-Reply-To: <20201030151345.540479897@infradead.org>

intel_pmu_drain_pebs_*() is typically called from handle_pmi_common(),
both have an on-stack struct perf_sample_data, which is *big*. Rewire
things so that drain_pebs() can use the one handle_pmi_common() has.

Reported-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 arch/x86/events/intel/core.c |    2 -
 arch/x86/events/intel/ds.c   |   47 ++++++++++++++++++++++---------------------
 arch/x86/events/perf_event.h |    2 -
 3 files changed, 27 insertions(+), 24 deletions(-)

--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2630,7 +2630,7 @@ static int handle_pmi_common(struct pt_r
 		u64 pebs_enabled = cpuc->pebs_enabled;
 
 		handled++;
-		x86_pmu.drain_pebs(regs);
+		x86_pmu.drain_pebs(regs, &data);
 		status &= x86_pmu.intel_ctrl | GLOBAL_STATUS_TRACE_TOPAPMI;
 
 		/*
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -670,7 +670,9 @@ int intel_pmu_drain_bts_buffer(void)
 
 static inline void intel_pmu_drain_pebs_buffer(void)
 {
-	x86_pmu.drain_pebs(NULL);
+	struct perf_sample_data data;
+
+	x86_pmu.drain_pebs(NULL, &data);
 }
 
 /*
@@ -1719,19 +1721,20 @@ intel_pmu_save_and_restart_reload(struct
 	return 0;
 }
 
-static void __intel_pmu_pebs_event(struct perf_event *event,
-				   struct pt_regs *iregs,
-				   void *base, void *top,
-				   int bit, int count,
-				   void (*setup_sample)(struct perf_event *,
-						struct pt_regs *,
-						void *,
-						struct perf_sample_data *,
-						struct pt_regs *))
+static __always_inline void
+__intel_pmu_pebs_event(struct perf_event *event,
+		       struct pt_regs *iregs,
+		       struct perf_sample_data *data,
+		       void *base, void *top,
+		       int bit, int count,
+		       void (*setup_sample)(struct perf_event *,
+					    struct pt_regs *,
+					    void *,
+					    struct perf_sample_data *,
+					    struct pt_regs *))
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
-	struct perf_sample_data data;
 	struct x86_perf_regs perf_regs;
 	struct pt_regs *regs = &perf_regs.regs;
 	void *at = get_next_pebs_record_by_bit(base, top, bit);
@@ -1752,14 +1755,14 @@ static void __intel_pmu_pebs_event(struc
 		iregs = &dummy_iregs;
 
 	while (count > 1) {
-		setup_sample(event, iregs, at, &data, regs);
-		perf_event_output(event, &data, regs);
+		setup_sample(event, iregs, at, data, regs);
+		perf_event_output(event, data, regs);
 		at += cpuc->pebs_record_size;
 		at = get_next_pebs_record_by_bit(at, top, bit);
 		count--;
 	}
 
-	setup_sample(event, iregs, at, &data, regs);
+	setup_sample(event, iregs, at, data, regs);
 	if (iregs == &dummy_iregs) {
 		/*
 		 * The PEBS records may be drained in the non-overflow context,
@@ -1767,18 +1770,18 @@ static void __intel_pmu_pebs_event(struc
 		 * last record the same as other PEBS records, and doesn't
 		 * invoke the generic overflow handler.
 		 */
-		perf_event_output(event, &data, regs);
+		perf_event_output(event, data, regs);
 	} else {
 		/*
 		 * All but the last records are processed.
 		 * The last one is left to be able to call the overflow handler.
 		 */
-		if (perf_event_overflow(event, &data, regs))
+		if (perf_event_overflow(event, data, regs))
 			x86_pmu_stop(event, 0);
 	}
 }
 
-static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
+static void intel_pmu_drain_pebs_core(struct pt_regs *iregs, struct perf_sample_data *data)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct debug_store *ds = cpuc->ds;
@@ -1812,7 +1815,7 @@ static void intel_pmu_drain_pebs_core(st
 		return;
 	}
 
-	__intel_pmu_pebs_event(event, iregs, at, top, 0, n,
+	__intel_pmu_pebs_event(event, iregs, data, at, top, 0, n,
 			       setup_pebs_fixed_sample_data);
 }
 
@@ -1835,7 +1838,7 @@ static void intel_pmu_pebs_event_update_
 	}
 }
 
-static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
+static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_data *data)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct debug_store *ds = cpuc->ds;
@@ -1942,14 +1945,14 @@ static void intel_pmu_drain_pebs_nhm(str
 		}
 
 		if (counts[bit]) {
-			__intel_pmu_pebs_event(event, iregs, base,
+			__intel_pmu_pebs_event(event, iregs, data, base,
 					       top, bit, counts[bit],
 					       setup_pebs_fixed_sample_data);
 		}
 	}
 }
 
-static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs)
+static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_data *data)
 {
 	short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {};
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
@@ -1997,7 +2000,7 @@ static void intel_pmu_drain_pebs_icl(str
 		if (WARN_ON_ONCE(!event->attr.precise_ip))
 			continue;
 
-		__intel_pmu_pebs_event(event, iregs, base,
+		__intel_pmu_pebs_event(event, iregs, data, base,
 				       top, bit, counts[bit],
 				       setup_pebs_adaptive_sample_data);
 	}
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -727,7 +727,7 @@ struct x86_pmu {
 	int		pebs_record_size;
 	int		pebs_buffer_size;
 	int		max_pebs_events;
-	void		(*drain_pebs)(struct pt_regs *regs);
+	void		(*drain_pebs)(struct pt_regs *regs, struct perf_sample_data *data);
 	struct event_constraint *pebs_constraints;
 	void		(*pebs_aliases)(struct perf_event *event);
 	unsigned long	large_pebs_flags;



  parent reply index

Thread overview: 23+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-10-30 15:13 [PATCH 0/6] perf: Reduce stack usage (and misc bits) Peter Zijlstra
2020-10-30 15:13 ` [PATCH 1/6] perf: Reduce stack usage of perf_output_begin() Peter Zijlstra
2020-11-10 12:45   ` [tip: perf/urgent] " tip-bot2 for Peter Zijlstra
2020-10-30 15:13 ` Peter Zijlstra [this message]
2020-11-10 12:45   ` [tip: perf/urgent] perf/x86: Reduce stack usage for x86_pmu::drain_pebs() tip-bot2 for Peter Zijlstra
2020-10-30 15:13 ` [PATCH 3/6] perf: Fix get_recursion_context() Peter Zijlstra
2020-11-10 12:45   ` [tip: perf/urgent] " tip-bot2 for Peter Zijlstra
2020-10-30 15:13 ` [PATCH 4/6] perf: Optimize get_recursion_context() Peter Zijlstra
2020-10-30 17:11   ` Jesper Dangaard Brouer
2020-10-30 20:22     ` Steven Rostedt
2020-10-30 22:14       ` Thomas Gleixner
2020-10-30 23:31         ` Steven Rostedt
2020-10-31 11:23           ` Peter Zijlstra
2020-10-30 23:01       ` Peter Zijlstra
2020-10-31 12:11         ` David Laight
2020-10-31 13:18           ` David Laight
2020-11-09 12:12           ` Peter Zijlstra
2020-11-09 14:14             ` David Laight
2020-11-10 12:45   ` [tip: perf/urgent] " tip-bot2 for Peter Zijlstra
2020-10-30 15:13 ` [PATCH 5/6] perf/arch: Remove perf_sample_data::regs_user_copy Peter Zijlstra
2020-11-10 12:45   ` [tip: perf/urgent] " tip-bot2 for Peter Zijlstra
2020-10-30 15:13 ` [PATCH 6/6] perf/x86: Make dummy_iregs static Peter Zijlstra
2020-11-10 12:45   ` [tip: perf/urgent] " tip-bot2 for Peter Zijlstra

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20201030151955.054099690@infradead.org \
    --to=peterz@infradead.org \
    --cc=acme@kernel.org \
    --cc=ak@linux.intel.com \
    --cc=alexander.shishkin@linux.intel.com \
    --cc=eranian@google.com \
    --cc=jolsa@redhat.com \
    --cc=kan.liang@linux.intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mark.rutland@arm.com \
    --cc=mingo@kernel.org \
    --cc=namhyung@kernel.org \
    --cc=rostedt@goodmis.org \
    --cc=tglx@linutronix.de \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

LKML Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/lkml/0 lkml/git/0.git
	git clone --mirror https://lore.kernel.org/lkml/1 lkml/git/1.git
	git clone --mirror https://lore.kernel.org/lkml/2 lkml/git/2.git
	git clone --mirror https://lore.kernel.org/lkml/3 lkml/git/3.git
	git clone --mirror https://lore.kernel.org/lkml/4 lkml/git/4.git
	git clone --mirror https://lore.kernel.org/lkml/5 lkml/git/5.git
	git clone --mirror https://lore.kernel.org/lkml/6 lkml/git/6.git
	git clone --mirror https://lore.kernel.org/lkml/7 lkml/git/7.git
	git clone --mirror https://lore.kernel.org/lkml/8 lkml/git/8.git
	git clone --mirror https://lore.kernel.org/lkml/9 lkml/git/9.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 lkml lkml/ https://lore.kernel.org/lkml \
		linux-kernel@vger.kernel.org
	public-inbox-index lkml

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-kernel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git