| Message ID | 20220704150514.48816-10-elver@google.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | perf/hw_breakpoint: Optimize for thousands of tasks | expand |
On Mon, Jul 4, 2022 at 8:07 AM Marco Elver <elver@google.com> wrote: > > Internal data structures (cpu_bps, task_bps) of powerpc's hw_breakpoint > implementation have relied on nr_bp_mutex serializing access to them. > > Before overhauling synchronization of kernel/events/hw_breakpoint.c, > introduce 2 spinlocks to synchronize cpu_bps and task_bps respectively, > thus avoiding reliance on callers synchronizing powerpc's hw_breakpoint. > > Reported-by: Dmitry Vyukov <dvyukov@google.com> > Signed-off-by: Marco Elver <elver@google.com> > Acked-by: Dmitry Vyukov <dvyukov@google.com> Acked-by: Ian Rogers <irogers@google.com> Thanks, Ian > --- > v2: > * New patch. > --- > arch/powerpc/kernel/hw_breakpoint.c | 53 ++++++++++++++++++++++------- > 1 file changed, 40 insertions(+), 13 deletions(-) > > diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c > index 2669f80b3a49..8db1a15d7acb 100644 > --- a/arch/powerpc/kernel/hw_breakpoint.c > +++ b/arch/powerpc/kernel/hw_breakpoint.c > @@ -15,6 +15,7 @@ > #include <linux/kernel.h> > #include <linux/sched.h> > #include <linux/smp.h> > +#include <linux/spinlock.h> > #include <linux/debugfs.h> > #include <linux/init.h> > > @@ -129,7 +130,14 @@ struct breakpoint { > bool ptrace_bp; > }; > > +/* > + * While kernel/events/hw_breakpoint.c does its own synchronization, we cannot > + * rely on it safely synchronizing internals here; however, we can rely on it > + * not requesting more breakpoints than available. > + */ > +static DEFINE_SPINLOCK(cpu_bps_lock); > static DEFINE_PER_CPU(struct breakpoint *, cpu_bps[HBP_NUM_MAX]); > +static DEFINE_SPINLOCK(task_bps_lock); > static LIST_HEAD(task_bps); > > static struct breakpoint *alloc_breakpoint(struct perf_event *bp) > @@ -174,7 +182,9 @@ static int task_bps_add(struct perf_event *bp) > if (IS_ERR(tmp)) > return PTR_ERR(tmp); > > + spin_lock(&task_bps_lock); > list_add(&tmp->list, &task_bps); > + spin_unlock(&task_bps_lock); > return 0; > } > > @@ -182,6 +192,7 @@ static void task_bps_remove(struct perf_event *bp) > { > struct list_head *pos, *q; > > + spin_lock(&task_bps_lock); > list_for_each_safe(pos, q, &task_bps) { > struct breakpoint *tmp = list_entry(pos, struct breakpoint, list); > > @@ -191,6 +202,7 @@ static void task_bps_remove(struct perf_event *bp) > break; > } > } > + spin_unlock(&task_bps_lock); > } > > /* > @@ -200,12 +212,17 @@ static void task_bps_remove(struct perf_event *bp) > static bool all_task_bps_check(struct perf_event *bp) > { > struct breakpoint *tmp; > + bool ret = false; > > + spin_lock(&task_bps_lock); > list_for_each_entry(tmp, &task_bps, list) { > - if (!can_co_exist(tmp, bp)) > - return true; > + if (!can_co_exist(tmp, bp)) { > + ret = true; > + break; > + } > } > - return false; > + spin_unlock(&task_bps_lock); > + return ret; > } > > /* > @@ -215,13 +232,18 @@ static bool all_task_bps_check(struct perf_event *bp) > static bool same_task_bps_check(struct perf_event *bp) > { > struct breakpoint *tmp; > + bool ret = false; > > + spin_lock(&task_bps_lock); > list_for_each_entry(tmp, &task_bps, list) { > if (tmp->bp->hw.target == bp->hw.target && > - !can_co_exist(tmp, bp)) > - return true; > + !can_co_exist(tmp, bp)) { > + ret = true; > + break; > + } > } > - return false; > + spin_unlock(&task_bps_lock); > + return ret; > } > > static int cpu_bps_add(struct perf_event *bp) > @@ -234,6 +256,7 @@ static int cpu_bps_add(struct perf_event *bp) > if (IS_ERR(tmp)) > return PTR_ERR(tmp); > > + spin_lock(&cpu_bps_lock); > cpu_bp = per_cpu_ptr(cpu_bps, bp->cpu); > for (i = 0; i < nr_wp_slots(); i++) { > if (!cpu_bp[i]) { > @@ -241,6 +264,7 @@ static int cpu_bps_add(struct perf_event *bp) > break; > } > } > + spin_unlock(&cpu_bps_lock); > return 0; > } > > @@ -249,6 +273,7 @@ static void cpu_bps_remove(struct perf_event *bp) > struct breakpoint **cpu_bp; > int i = 0; > > + spin_lock(&cpu_bps_lock); > cpu_bp = per_cpu_ptr(cpu_bps, bp->cpu); > for (i = 0; i < nr_wp_slots(); i++) { > if (!cpu_bp[i]) > @@ -260,19 +285,25 @@ static void cpu_bps_remove(struct perf_event *bp) > break; > } > } > + spin_unlock(&cpu_bps_lock); > } > > static bool cpu_bps_check(int cpu, struct perf_event *bp) > { > struct breakpoint **cpu_bp; > + bool ret = false; > int i; > > + spin_lock(&cpu_bps_lock); > cpu_bp = per_cpu_ptr(cpu_bps, cpu); > for (i = 0; i < nr_wp_slots(); i++) { > - if (cpu_bp[i] && !can_co_exist(cpu_bp[i], bp)) > - return true; > + if (cpu_bp[i] && !can_co_exist(cpu_bp[i], bp)) { > + ret = true; > + break; > + } > } > - return false; > + spin_unlock(&cpu_bps_lock); > + return ret; > } > > static bool all_cpu_bps_check(struct perf_event *bp) > @@ -286,10 +317,6 @@ static bool all_cpu_bps_check(struct perf_event *bp) > return false; > } > > -/* > - * We don't use any locks to serialize accesses to cpu_bps or task_bps > - * because are already inside nr_bp_mutex. > - */ > int arch_reserve_bp_slot(struct perf_event *bp) > { > int ret; > -- > 2.37.0.rc0.161.g10f37bed90-goog >
diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index 2669f80b3a49..8db1a15d7acb 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -15,6 +15,7 @@ #include <linux/kernel.h> #include <linux/sched.h> #include <linux/smp.h> +#include <linux/spinlock.h> #include <linux/debugfs.h> #include <linux/init.h> @@ -129,7 +130,14 @@ struct breakpoint { bool ptrace_bp; }; +/* + * While kernel/events/hw_breakpoint.c does its own synchronization, we cannot + * rely on it safely synchronizing internals here; however, we can rely on it + * not requesting more breakpoints than available. + */ +static DEFINE_SPINLOCK(cpu_bps_lock); static DEFINE_PER_CPU(struct breakpoint *, cpu_bps[HBP_NUM_MAX]); +static DEFINE_SPINLOCK(task_bps_lock); static LIST_HEAD(task_bps); static struct breakpoint *alloc_breakpoint(struct perf_event *bp) @@ -174,7 +182,9 @@ static int task_bps_add(struct perf_event *bp) if (IS_ERR(tmp)) return PTR_ERR(tmp); + spin_lock(&task_bps_lock); list_add(&tmp->list, &task_bps); + spin_unlock(&task_bps_lock); return 0; } @@ -182,6 +192,7 @@ static void task_bps_remove(struct perf_event *bp) { struct list_head *pos, *q; + spin_lock(&task_bps_lock); list_for_each_safe(pos, q, &task_bps) { struct breakpoint *tmp = list_entry(pos, struct breakpoint, list); @@ -191,6 +202,7 @@ static void task_bps_remove(struct perf_event *bp) break; } } + spin_unlock(&task_bps_lock); } /* @@ -200,12 +212,17 @@ static void task_bps_remove(struct perf_event *bp) static bool all_task_bps_check(struct perf_event *bp) { struct breakpoint *tmp; + bool ret = false; + spin_lock(&task_bps_lock); list_for_each_entry(tmp, &task_bps, list) { - if (!can_co_exist(tmp, bp)) - return true; + if (!can_co_exist(tmp, bp)) { + ret = true; + break; + } } - return false; + spin_unlock(&task_bps_lock); + return ret; } /* @@ -215,13 +232,18 @@ static bool all_task_bps_check(struct perf_event *bp) static bool same_task_bps_check(struct perf_event *bp) { struct breakpoint *tmp; + bool ret = false; + spin_lock(&task_bps_lock); list_for_each_entry(tmp, &task_bps, list) { if (tmp->bp->hw.target == bp->hw.target && - !can_co_exist(tmp, bp)) - return true; + !can_co_exist(tmp, bp)) { + ret = true; + break; + } } - return false; + spin_unlock(&task_bps_lock); + return ret; } static int cpu_bps_add(struct perf_event *bp) @@ -234,6 +256,7 @@ static int cpu_bps_add(struct perf_event *bp) if (IS_ERR(tmp)) return PTR_ERR(tmp); + spin_lock(&cpu_bps_lock); cpu_bp = per_cpu_ptr(cpu_bps, bp->cpu); for (i = 0; i < nr_wp_slots(); i++) { if (!cpu_bp[i]) { @@ -241,6 +264,7 @@ static int cpu_bps_add(struct perf_event *bp) break; } } + spin_unlock(&cpu_bps_lock); return 0; } @@ -249,6 +273,7 @@ static void cpu_bps_remove(struct perf_event *bp) struct breakpoint **cpu_bp; int i = 0; + spin_lock(&cpu_bps_lock); cpu_bp = per_cpu_ptr(cpu_bps, bp->cpu); for (i = 0; i < nr_wp_slots(); i++) { if (!cpu_bp[i]) @@ -260,19 +285,25 @@ static void cpu_bps_remove(struct perf_event *bp) break; } } + spin_unlock(&cpu_bps_lock); } static bool cpu_bps_check(int cpu, struct perf_event *bp) { struct breakpoint **cpu_bp; + bool ret = false; int i; + spin_lock(&cpu_bps_lock); cpu_bp = per_cpu_ptr(cpu_bps, cpu); for (i = 0; i < nr_wp_slots(); i++) { - if (cpu_bp[i] && !can_co_exist(cpu_bp[i], bp)) - return true; + if (cpu_bp[i] && !can_co_exist(cpu_bp[i], bp)) { + ret = true; + break; + } } - return false; + spin_unlock(&cpu_bps_lock); + return ret; } static bool all_cpu_bps_check(struct perf_event *bp) @@ -286,10 +317,6 @@ static bool all_cpu_bps_check(struct perf_event *bp) return false; } -/* - * We don't use any locks to serialize accesses to cpu_bps or task_bps - * because are already inside nr_bp_mutex. - */ int arch_reserve_bp_slot(struct perf_event *bp) { int ret;