From: mark.rutland@arm.com (Mark Rutland)
To: linux-arm-kernel@lists.infradead.org
Subject: [RFC PATCH 09/15] ARM: perf: lock PMU registers per-CPU
Date: Mon, 15 Aug 2011 14:55:10 +0100 [thread overview]
Message-ID: <1313416516-8006-10-git-send-email-mark.rutland@arm.com> (raw)
In-Reply-To: <1313416516-8006-1-git-send-email-mark.rutland@arm.com>
Currently, a single lock serialises access to CPU PMU registers. This
global locking is unnecessary as PMU registers are local to the CPU
they monitor.
This patch replaces the global lock with a per-CPU lock. As the lock is
in struct cpu_hw_events, PMUs providing a single cpu_hw_events instance
can be locked globally.
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Will Deacon <will.deacon@arm.com>
---
arch/arm/kernel/perf_event.c | 17 +++++++++-----
arch/arm/kernel/perf_event_v6.c | 25 +++++++++++++--------
arch/arm/kernel/perf_event_v7.c | 20 ++++++++++-------
arch/arm/kernel/perf_event_xscale.c | 40 +++++++++++++++++++++--------------
4 files changed, 62 insertions(+), 40 deletions(-)
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index 5ce6c33..9331d57 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -27,12 +27,6 @@
#include <asm/stacktrace.h>
/*
- * Hardware lock to serialize accesses to PMU registers. Needed for the
- * read/modify/write sequences.
- */
-static DEFINE_RAW_SPINLOCK(pmu_lock);
-
-/*
* ARMv6 supports a maximum of 3 events, starting from index 0. If we add
* another platform that supports more, we need to increase this to be the
* largest of all platforms.
@@ -55,6 +49,12 @@ struct cpu_hw_events {
* an event. A 0 means that the counter can be used.
*/
unsigned long used_mask[BITS_TO_LONGS(ARMPMU_MAX_HWEVENTS)];
+
+ /*
+ * Hardware lock to serialize accesses to PMU registers. Needed for the
+ * read/modify/write sequences.
+ */
+ raw_spinlock_t pmu_lock;
};
static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events);
@@ -685,6 +685,11 @@ static struct cpu_hw_events *armpmu_get_cpu_events(void)
static void __init cpu_pmu_init(struct arm_pmu *armpmu)
{
+ int cpu;
+ for_each_possible_cpu(cpu) {
+ struct cpu_hw_events *events = &per_cpu(cpu_hw_events, cpu);
+ raw_spin_lock_init(&events->pmu_lock);
+ }
armpmu->get_hw_events = armpmu_get_cpu_events;
}
diff --git a/arch/arm/kernel/perf_event_v6.c b/arch/arm/kernel/perf_event_v6.c
index 8390128..68cf704 100644
--- a/arch/arm/kernel/perf_event_v6.c
+++ b/arch/arm/kernel/perf_event_v6.c
@@ -433,6 +433,7 @@ armv6pmu_enable_event(struct hw_perf_event *hwc,
int idx)
{
unsigned long val, mask, evt, flags;
+ struct cpu_hw_events *events = armpmu->get_hw_events();
if (ARMV6_CYCLE_COUNTER == idx) {
mask = 0;
@@ -454,12 +455,12 @@ armv6pmu_enable_event(struct hw_perf_event *hwc,
* Mask out the current event and set the counter to count the event
* that we're interested in.
*/
- raw_spin_lock_irqsave(&pmu_lock, flags);
+ raw_spin_lock_irqsave(&events->pmu_lock, flags);
val = armv6_pmcr_read();
val &= ~mask;
val |= evt;
armv6_pmcr_write(val);
- raw_spin_unlock_irqrestore(&pmu_lock, flags);
+ raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
}
static int counter_is_active(unsigned long pmcr, int idx)
@@ -544,24 +545,26 @@ static void
armv6pmu_start(void)
{
unsigned long flags, val;
+ struct cpu_hw_events *events = armpmu->get_hw_events();
- raw_spin_lock_irqsave(&pmu_lock, flags);
+ raw_spin_lock_irqsave(&events->pmu_lock, flags);
val = armv6_pmcr_read();
val |= ARMV6_PMCR_ENABLE;
armv6_pmcr_write(val);
- raw_spin_unlock_irqrestore(&pmu_lock, flags);
+ raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
}
static void
armv6pmu_stop(void)
{
unsigned long flags, val;
+ struct cpu_hw_events *events = armpmu->get_hw_events();
- raw_spin_lock_irqsave(&pmu_lock, flags);
+ raw_spin_lock_irqsave(&events->pmu_lock, flags);
val = armv6_pmcr_read();
val &= ~ARMV6_PMCR_ENABLE;
armv6_pmcr_write(val);
- raw_spin_unlock_irqrestore(&pmu_lock, flags);
+ raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
}
static int
@@ -595,6 +598,7 @@ armv6pmu_disable_event(struct hw_perf_event *hwc,
int idx)
{
unsigned long val, mask, evt, flags;
+ struct cpu_hw_events *events = armpmu->get_hw_events();
if (ARMV6_CYCLE_COUNTER == idx) {
mask = ARMV6_PMCR_CCOUNT_IEN;
@@ -615,12 +619,12 @@ armv6pmu_disable_event(struct hw_perf_event *hwc,
* of ETM bus signal assertion cycles. The external reporting should
* be disabled and so this should never increment.
*/
- raw_spin_lock_irqsave(&pmu_lock, flags);
+ raw_spin_lock_irqsave(&events->pmu_lock, flags);
val = armv6_pmcr_read();
val &= ~mask;
val |= evt;
armv6_pmcr_write(val);
- raw_spin_unlock_irqrestore(&pmu_lock, flags);
+ raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
}
static void
@@ -628,6 +632,7 @@ armv6mpcore_pmu_disable_event(struct hw_perf_event *hwc,
int idx)
{
unsigned long val, mask, flags, evt = 0;
+ struct cpu_hw_events *events = armpmu->get_hw_events();
if (ARMV6_CYCLE_COUNTER == idx) {
mask = ARMV6_PMCR_CCOUNT_IEN;
@@ -644,12 +649,12 @@ armv6mpcore_pmu_disable_event(struct hw_perf_event *hwc,
* Unlike UP ARMv6, we don't have a way of stopping the counters. We
* simply disable the interrupt reporting.
*/
- raw_spin_lock_irqsave(&pmu_lock, flags);
+ raw_spin_lock_irqsave(&events->pmu_lock, flags);
val = armv6_pmcr_read();
val &= ~mask;
val |= evt;
armv6_pmcr_write(val);
- raw_spin_unlock_irqrestore(&pmu_lock, flags);
+ raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
}
static struct arm_pmu armv6pmu = {
diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index f4170fc..68ac522 100644
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -936,12 +936,13 @@ static void armv7_pmnc_dump_regs(void)
static void armv7pmu_enable_event(struct hw_perf_event *hwc, int idx)
{
unsigned long flags;
+ struct cpu_hw_events *events = armpmu->get_hw_events();
/*
* Enable counter and interrupt, and set the counter to count
* the event that we're interested in.
*/
- raw_spin_lock_irqsave(&pmu_lock, flags);
+ raw_spin_lock_irqsave(&events->pmu_lock, flags);
/*
* Disable counter
@@ -966,17 +967,18 @@ static void armv7pmu_enable_event(struct hw_perf_event *hwc, int idx)
*/
armv7_pmnc_enable_counter(idx);
- raw_spin_unlock_irqrestore(&pmu_lock, flags);
+ raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
}
static void armv7pmu_disable_event(struct hw_perf_event *hwc, int idx)
{
unsigned long flags;
+ struct cpu_hw_events *events = armpmu->get_hw_events();
/*
* Disable counter and interrupt
*/
- raw_spin_lock_irqsave(&pmu_lock, flags);
+ raw_spin_lock_irqsave(&events->pmu_lock, flags);
/*
* Disable counter
@@ -988,7 +990,7 @@ static void armv7pmu_disable_event(struct hw_perf_event *hwc, int idx)
*/
armv7_pmnc_disable_intens(idx);
- raw_spin_unlock_irqrestore(&pmu_lock, flags);
+ raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
}
static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev)
@@ -1054,21 +1056,23 @@ static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev)
static void armv7pmu_start(void)
{
unsigned long flags;
+ struct cpu_hw_events *events = armpmu->get_hw_events();
- raw_spin_lock_irqsave(&pmu_lock, flags);
+ raw_spin_lock_irqsave(&events->pmu_lock, flags);
/* Enable all counters */
armv7_pmnc_write(armv7_pmnc_read() | ARMV7_PMNC_E);
- raw_spin_unlock_irqrestore(&pmu_lock, flags);
+ raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
}
static void armv7pmu_stop(void)
{
unsigned long flags;
+ struct cpu_hw_events *events = armpmu->get_hw_events();
- raw_spin_lock_irqsave(&pmu_lock, flags);
+ raw_spin_lock_irqsave(&events->pmu_lock, flags);
/* Disable all counters */
armv7_pmnc_write(armv7_pmnc_read() & ~ARMV7_PMNC_E);
- raw_spin_unlock_irqrestore(&pmu_lock, flags);
+ raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
}
static int armv7pmu_get_event_idx(struct cpu_hw_events *cpuc,
diff --git a/arch/arm/kernel/perf_event_xscale.c b/arch/arm/kernel/perf_event_xscale.c
index ca89a06..18e4823 100644
--- a/arch/arm/kernel/perf_event_xscale.c
+++ b/arch/arm/kernel/perf_event_xscale.c
@@ -281,6 +281,7 @@ static void
xscale1pmu_enable_event(struct hw_perf_event *hwc, int idx)
{
unsigned long val, mask, evt, flags;
+ struct cpu_hw_events *events = armpmu->get_hw_events();
switch (idx) {
case XSCALE_CYCLE_COUNTER:
@@ -302,18 +303,19 @@ xscale1pmu_enable_event(struct hw_perf_event *hwc, int idx)
return;
}
- raw_spin_lock_irqsave(&pmu_lock, flags);
+ raw_spin_lock_irqsave(&events->pmu_lock, flags);
val = xscale1pmu_read_pmnc();
val &= ~mask;
val |= evt;
xscale1pmu_write_pmnc(val);
- raw_spin_unlock_irqrestore(&pmu_lock, flags);
+ raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
}
static void
xscale1pmu_disable_event(struct hw_perf_event *hwc, int idx)
{
unsigned long val, mask, evt, flags;
+ struct cpu_hw_events *events = armpmu->get_hw_events();
switch (idx) {
case XSCALE_CYCLE_COUNTER:
@@ -333,12 +335,12 @@ xscale1pmu_disable_event(struct hw_perf_event *hwc, int idx)
return;
}
- raw_spin_lock_irqsave(&pmu_lock, flags);
+ raw_spin_lock_irqsave(&events->pmu_lock, flags);
val = xscale1pmu_read_pmnc();
val &= ~mask;
val |= evt;
xscale1pmu_write_pmnc(val);
- raw_spin_unlock_irqrestore(&pmu_lock, flags);
+ raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
}
static int
@@ -365,24 +367,26 @@ static void
xscale1pmu_start(void)
{
unsigned long flags, val;
+ struct cpu_hw_events *events = armpmu->get_hw_events();
- raw_spin_lock_irqsave(&pmu_lock, flags);
+ raw_spin_lock_irqsave(&events->pmu_lock, flags);
val = xscale1pmu_read_pmnc();
val |= XSCALE_PMU_ENABLE;
xscale1pmu_write_pmnc(val);
- raw_spin_unlock_irqrestore(&pmu_lock, flags);
+ raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
}
static void
xscale1pmu_stop(void)
{
unsigned long flags, val;
+ struct cpu_hw_events *events = armpmu->get_hw_events();
- raw_spin_lock_irqsave(&pmu_lock, flags);
+ raw_spin_lock_irqsave(&events->pmu_lock, flags);
val = xscale1pmu_read_pmnc();
val &= ~XSCALE_PMU_ENABLE;
xscale1pmu_write_pmnc(val);
- raw_spin_unlock_irqrestore(&pmu_lock, flags);
+ raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
}
static inline u32
@@ -610,6 +614,7 @@ static void
xscale2pmu_enable_event(struct hw_perf_event *hwc, int idx)
{
unsigned long flags, ien, evtsel;
+ struct cpu_hw_events *events = armpmu->get_hw_events();
ien = xscale2pmu_read_int_enable();
evtsel = xscale2pmu_read_event_select();
@@ -643,16 +648,17 @@ xscale2pmu_enable_event(struct hw_perf_event *hwc, int idx)
return;
}
- raw_spin_lock_irqsave(&pmu_lock, flags);
+ raw_spin_lock_irqsave(&events->pmu_lock, flags);
xscale2pmu_write_event_select(evtsel);
xscale2pmu_write_int_enable(ien);
- raw_spin_unlock_irqrestore(&pmu_lock, flags);
+ raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
}
static void
xscale2pmu_disable_event(struct hw_perf_event *hwc, int idx)
{
unsigned long flags, ien, evtsel;
+ struct cpu_hw_events *events = armpmu->get_hw_events();
ien = xscale2pmu_read_int_enable();
evtsel = xscale2pmu_read_event_select();
@@ -686,10 +692,10 @@ xscale2pmu_disable_event(struct hw_perf_event *hwc, int idx)
return;
}
- raw_spin_lock_irqsave(&pmu_lock, flags);
+ raw_spin_lock_irqsave(&events->pmu_lock, flags);
xscale2pmu_write_event_select(evtsel);
xscale2pmu_write_int_enable(ien);
- raw_spin_unlock_irqrestore(&pmu_lock, flags);
+ raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
}
static int
@@ -712,24 +718,26 @@ static void
xscale2pmu_start(void)
{
unsigned long flags, val;
+ struct cpu_hw_events *events = armpmu->get_hw_events();
- raw_spin_lock_irqsave(&pmu_lock, flags);
+ raw_spin_lock_irqsave(&events->pmu_lock, flags);
val = xscale2pmu_read_pmnc() & ~XSCALE_PMU_CNT64;
val |= XSCALE_PMU_ENABLE;
xscale2pmu_write_pmnc(val);
- raw_spin_unlock_irqrestore(&pmu_lock, flags);
+ raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
}
static void
xscale2pmu_stop(void)
{
unsigned long flags, val;
+ struct cpu_hw_events *events = armpmu->get_hw_events();
- raw_spin_lock_irqsave(&pmu_lock, flags);
+ raw_spin_lock_irqsave(&events->pmu_lock, flags);
val = xscale2pmu_read_pmnc();
val &= ~XSCALE_PMU_ENABLE;
xscale2pmu_write_pmnc(val);
- raw_spin_unlock_irqrestore(&pmu_lock, flags);
+ raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
}
static inline u32
--
1.7.0.4
next prev parent reply other threads:[~2011-08-15 13:55 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-08-15 13:55 [RFC PATCH 00/15] ARM: perf: support multiple PMUs Mark Rutland
2011-08-15 13:55 ` [RFC PATCH 01/15] perf: provide PMU when initing events Mark Rutland
2011-08-15 13:55 ` [RFC PATCH 02/15] ARM: perf: only register a CPU PMU when present Mark Rutland
2011-08-15 13:55 ` [RFC PATCH 03/15] ARM: perf: clean up event group validation Mark Rutland
2011-08-15 13:55 ` [RFC PATCH 04/15] ARM: perf: remove active_mask Mark Rutland
2011-08-15 13:55 ` [RFC PATCH 05/15] ARM: perf: move active_events into struct arm_pmu Mark Rutland
2011-08-15 13:55 ` [RFC PATCH 06/15] ARM: perf: move platform device to " Mark Rutland
2011-08-15 13:55 ` [RFC PATCH 07/15] ARM: perf: indirect access to cpu_hw_events Mark Rutland
2011-08-15 13:55 ` [RFC PATCH 08/15] ARM: perf: remove unnecessary armpmu->stop Mark Rutland
2011-08-15 13:55 ` Mark Rutland [this message]
2011-08-15 13:55 ` [RFC PATCH 10/15] ARM: perf: add type field to struct arm_pmu Mark Rutland
2011-08-15 13:55 ` [RFC PATCH 11/15] ARM: perf: refactor event mapping Mark Rutland
2011-08-15 13:55 ` [RFC PATCH 12/15] ARM: perf: add support for multiple PMUs Mark Rutland
2011-08-15 13:55 ` [RFC PATCH 13/15] ARM: perf: remove event limit from pmu_hw_events Mark Rutland
2011-08-15 13:55 ` [RFC PATCH 14/15] ARM: perf: remove cpu-related misnomers Mark Rutland
2011-08-15 13:55 ` [RFC PATCH 15/15] ARM: perf: move arm_pmu into <asm/pmu.h> Mark Rutland
2011-08-17 14:12 ` [RFC PATCH 00/15] ARM: perf: support multiple PMUs Jamie Iles
-- strict thread matches above, loose matches on Subject: below --
2011-04-28 9:17 [RFC PATCH 09/15] ARM: perf: lock PMU registers per-CPU Mark Rutland
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=1313416516-8006-10-git-send-email-mark.rutland@arm.com \
--to=mark.rutland@arm.com \
--cc=linux-arm-kernel@lists.infradead.org \
/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
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.