| Message ID | 20240712102029.3697965-18-james.clark@linaro.org (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | coresight: Use per-sink trace ID maps for Perf sessions | expand |
Reviewed-by: Mike Leach <mike.leach@linaro.org> On Fri, 12 Jul 2024 at 11:23, James Clark <james.clark@linaro.org> wrote: > > From: James Clark <james.clark@arm.com> > > Reduce contention on the lock by replacing the global lock with one for > each map. > > Signed-off-by: James Clark <james.clark@arm.com> > Signed-off-by: James Clark <james.clark@linaro.org> > --- > drivers/hwtracing/coresight/coresight-core.c | 1 + > .../hwtracing/coresight/coresight-trace-id.c | 26 +++++++++---------- > include/linux/coresight.h | 1 + > 3 files changed, 14 insertions(+), 14 deletions(-) > > diff --git a/drivers/hwtracing/coresight/coresight-core.c b/drivers/hwtracing/coresight/coresight-core.c > index c427e9344a84..ea38ecf26fcb 100644 > --- a/drivers/hwtracing/coresight/coresight-core.c > +++ b/drivers/hwtracing/coresight/coresight-core.c > @@ -1164,6 +1164,7 @@ struct coresight_device *coresight_register(struct coresight_desc *desc) > > if (csdev->type == CORESIGHT_DEV_TYPE_SINK || > csdev->type == CORESIGHT_DEV_TYPE_LINKSINK) { > + spin_lock_init(&csdev->perf_sink_id_map.lock); > csdev->perf_sink_id_map.cpu_map = alloc_percpu(atomic_t); > if (!csdev->perf_sink_id_map.cpu_map) { > kfree(csdev); > diff --git a/drivers/hwtracing/coresight/coresight-trace-id.c b/drivers/hwtracing/coresight/coresight-trace-id.c > index bddaed3e5cf8..d98e12cb30ec 100644 > --- a/drivers/hwtracing/coresight/coresight-trace-id.c > +++ b/drivers/hwtracing/coresight/coresight-trace-id.c > @@ -15,12 +15,10 @@ > /* Default trace ID map. Used in sysfs mode and for system sources */ > static DEFINE_PER_CPU(atomic_t, id_map_default_cpu_ids) = ATOMIC_INIT(0); > static struct coresight_trace_id_map id_map_default = { > - .cpu_map = &id_map_default_cpu_ids > + .cpu_map = &id_map_default_cpu_ids, > + .lock = __SPIN_LOCK_UNLOCKED(id_map_default.lock) > }; > > -/* lock to protect id_map and cpu data */ > -static DEFINE_SPINLOCK(id_map_lock); > - > /* #define TRACE_ID_DEBUG 1 */ > #if defined(TRACE_ID_DEBUG) || defined(CONFIG_COMPILE_TEST) > > @@ -123,11 +121,11 @@ static void coresight_trace_id_release_all(struct coresight_trace_id_map *id_map > unsigned long flags; > int cpu; > > - spin_lock_irqsave(&id_map_lock, flags); > + spin_lock_irqsave(&id_map->lock, flags); > bitmap_zero(id_map->used_ids, CORESIGHT_TRACE_IDS_MAX); > for_each_possible_cpu(cpu) > atomic_set(per_cpu_ptr(id_map->cpu_map, cpu), 0); > - spin_unlock_irqrestore(&id_map_lock, flags); > + spin_unlock_irqrestore(&id_map->lock, flags); > DUMP_ID_MAP(id_map); > } > > @@ -136,7 +134,7 @@ static int _coresight_trace_id_get_cpu_id(int cpu, struct coresight_trace_id_map > unsigned long flags; > int id; > > - spin_lock_irqsave(&id_map_lock, flags); > + spin_lock_irqsave(&id_map->lock, flags); > > /* check for existing allocation for this CPU */ > id = _coresight_trace_id_read_cpu_id(cpu, id_map); > @@ -163,7 +161,7 @@ static int _coresight_trace_id_get_cpu_id(int cpu, struct coresight_trace_id_map > atomic_set(per_cpu_ptr(id_map->cpu_map, cpu), id); > > get_cpu_id_out_unlock: > - spin_unlock_irqrestore(&id_map_lock, flags); > + spin_unlock_irqrestore(&id_map->lock, flags); > > DUMP_ID_CPU(cpu, id); > DUMP_ID_MAP(id_map); > @@ -180,12 +178,12 @@ static void _coresight_trace_id_put_cpu_id(int cpu, struct coresight_trace_id_ma > if (!id) > return; > > - spin_lock_irqsave(&id_map_lock, flags); > + spin_lock_irqsave(&id_map->lock, flags); > > coresight_trace_id_free(id, id_map); > atomic_set(per_cpu_ptr(id_map->cpu_map, cpu), 0); > > - spin_unlock_irqrestore(&id_map_lock, flags); > + spin_unlock_irqrestore(&id_map->lock, flags); > DUMP_ID_CPU(cpu, id); > DUMP_ID_MAP(id_map); > } > @@ -195,10 +193,10 @@ static int coresight_trace_id_map_get_system_id(struct coresight_trace_id_map *i > unsigned long flags; > int id; > > - spin_lock_irqsave(&id_map_lock, flags); > + spin_lock_irqsave(&id_map->lock, flags); > /* prefer odd IDs for system components to avoid legacy CPU IDS */ > id = coresight_trace_id_alloc_new_id(id_map, 0, true); > - spin_unlock_irqrestore(&id_map_lock, flags); > + spin_unlock_irqrestore(&id_map->lock, flags); > > DUMP_ID(id); > DUMP_ID_MAP(id_map); > @@ -209,9 +207,9 @@ static void coresight_trace_id_map_put_system_id(struct coresight_trace_id_map * > { > unsigned long flags; > > - spin_lock_irqsave(&id_map_lock, flags); > + spin_lock_irqsave(&id_map->lock, flags); > coresight_trace_id_free(id, id_map); > - spin_unlock_irqrestore(&id_map_lock, flags); > + spin_unlock_irqrestore(&id_map->lock, flags); > > DUMP_ID(id); > DUMP_ID_MAP(id_map); > diff --git a/include/linux/coresight.h b/include/linux/coresight.h > index 197949fd2c35..c13342594278 100644 > --- a/include/linux/coresight.h > +++ b/include/linux/coresight.h > @@ -233,6 +233,7 @@ struct coresight_trace_id_map { > DECLARE_BITMAP(used_ids, CORESIGHT_TRACE_IDS_MAX); > atomic_t __percpu *cpu_map; > atomic_t perf_cs_etm_session_active; > + spinlock_t lock; > }; > > /** > -- > 2.34.1 > -- Mike Leach Principal Engineer, ARM Ltd. Manchester Design Centre. UK
diff --git a/drivers/hwtracing/coresight/coresight-core.c b/drivers/hwtracing/coresight/coresight-core.c index c427e9344a84..ea38ecf26fcb 100644 --- a/drivers/hwtracing/coresight/coresight-core.c +++ b/drivers/hwtracing/coresight/coresight-core.c @@ -1164,6 +1164,7 @@ struct coresight_device *coresight_register(struct coresight_desc *desc) if (csdev->type == CORESIGHT_DEV_TYPE_SINK || csdev->type == CORESIGHT_DEV_TYPE_LINKSINK) { + spin_lock_init(&csdev->perf_sink_id_map.lock); csdev->perf_sink_id_map.cpu_map = alloc_percpu(atomic_t); if (!csdev->perf_sink_id_map.cpu_map) { kfree(csdev); diff --git a/drivers/hwtracing/coresight/coresight-trace-id.c b/drivers/hwtracing/coresight/coresight-trace-id.c index bddaed3e5cf8..d98e12cb30ec 100644 --- a/drivers/hwtracing/coresight/coresight-trace-id.c +++ b/drivers/hwtracing/coresight/coresight-trace-id.c @@ -15,12 +15,10 @@ /* Default trace ID map. Used in sysfs mode and for system sources */ static DEFINE_PER_CPU(atomic_t, id_map_default_cpu_ids) = ATOMIC_INIT(0); static struct coresight_trace_id_map id_map_default = { - .cpu_map = &id_map_default_cpu_ids + .cpu_map = &id_map_default_cpu_ids, + .lock = __SPIN_LOCK_UNLOCKED(id_map_default.lock) }; -/* lock to protect id_map and cpu data */ -static DEFINE_SPINLOCK(id_map_lock); - /* #define TRACE_ID_DEBUG 1 */ #if defined(TRACE_ID_DEBUG) || defined(CONFIG_COMPILE_TEST) @@ -123,11 +121,11 @@ static void coresight_trace_id_release_all(struct coresight_trace_id_map *id_map unsigned long flags; int cpu; - spin_lock_irqsave(&id_map_lock, flags); + spin_lock_irqsave(&id_map->lock, flags); bitmap_zero(id_map->used_ids, CORESIGHT_TRACE_IDS_MAX); for_each_possible_cpu(cpu) atomic_set(per_cpu_ptr(id_map->cpu_map, cpu), 0); - spin_unlock_irqrestore(&id_map_lock, flags); + spin_unlock_irqrestore(&id_map->lock, flags); DUMP_ID_MAP(id_map); } @@ -136,7 +134,7 @@ static int _coresight_trace_id_get_cpu_id(int cpu, struct coresight_trace_id_map unsigned long flags; int id; - spin_lock_irqsave(&id_map_lock, flags); + spin_lock_irqsave(&id_map->lock, flags); /* check for existing allocation for this CPU */ id = _coresight_trace_id_read_cpu_id(cpu, id_map); @@ -163,7 +161,7 @@ static int _coresight_trace_id_get_cpu_id(int cpu, struct coresight_trace_id_map atomic_set(per_cpu_ptr(id_map->cpu_map, cpu), id); get_cpu_id_out_unlock: - spin_unlock_irqrestore(&id_map_lock, flags); + spin_unlock_irqrestore(&id_map->lock, flags); DUMP_ID_CPU(cpu, id); DUMP_ID_MAP(id_map); @@ -180,12 +178,12 @@ static void _coresight_trace_id_put_cpu_id(int cpu, struct coresight_trace_id_ma if (!id) return; - spin_lock_irqsave(&id_map_lock, flags); + spin_lock_irqsave(&id_map->lock, flags); coresight_trace_id_free(id, id_map); atomic_set(per_cpu_ptr(id_map->cpu_map, cpu), 0); - spin_unlock_irqrestore(&id_map_lock, flags); + spin_unlock_irqrestore(&id_map->lock, flags); DUMP_ID_CPU(cpu, id); DUMP_ID_MAP(id_map); } @@ -195,10 +193,10 @@ static int coresight_trace_id_map_get_system_id(struct coresight_trace_id_map *i unsigned long flags; int id; - spin_lock_irqsave(&id_map_lock, flags); + spin_lock_irqsave(&id_map->lock, flags); /* prefer odd IDs for system components to avoid legacy CPU IDS */ id = coresight_trace_id_alloc_new_id(id_map, 0, true); - spin_unlock_irqrestore(&id_map_lock, flags); + spin_unlock_irqrestore(&id_map->lock, flags); DUMP_ID(id); DUMP_ID_MAP(id_map); @@ -209,9 +207,9 @@ static void coresight_trace_id_map_put_system_id(struct coresight_trace_id_map * { unsigned long flags; - spin_lock_irqsave(&id_map_lock, flags); + spin_lock_irqsave(&id_map->lock, flags); coresight_trace_id_free(id, id_map); - spin_unlock_irqrestore(&id_map_lock, flags); + spin_unlock_irqrestore(&id_map->lock, flags); DUMP_ID(id); DUMP_ID_MAP(id_map); diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 197949fd2c35..c13342594278 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -233,6 +233,7 @@ struct coresight_trace_id_map { DECLARE_BITMAP(used_ids, CORESIGHT_TRACE_IDS_MAX); atomic_t __percpu *cpu_map; atomic_t perf_cs_etm_session_active; + spinlock_t lock; }; /**