| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <166201997029.401.15207678182540811754.tip-bot2@tip-bot2>
Date: Thu, 01 Sep 2022 08:12:50 -0000
From: "tip-bot2 for Marco Elver" <tip-bot2@...utronix.de>
To: linux-tip-commits@...r.kernel.org
Cc: Marco Elver <elver@...gle.com>,
"Peter Zijlstra (Intel)" <peterz@...radead.org>,
Dmitry Vyukov <dvyukov@...gle.com>,
Ian Rogers <irogers@...gle.com>, x86@...nel.org,
linux-kernel@...r.kernel.org
Subject: [tip: perf/core] perf/hw_breakpoint: Optimize list of per-task breakpoints
The following commit has been merged into the perf/core branch of tip:
Commit-ID: 0370dc314df35579b751d1b77c9169f071444962
Gitweb: https://git.kernel.org/tip/0370dc314df35579b751d1b77c9169f071444962
Author: Marco Elver <elver@...gle.com>
AuthorDate: Mon, 29 Aug 2022 14:47:09 +02:00
Committer: Peter Zijlstra <peterz@...radead.org>
CommitterDate: Tue, 30 Aug 2022 10:56:21 +02:00
perf/hw_breakpoint: Optimize list of per-task breakpoints
On a machine with 256 CPUs, running the recently added perf breakpoint
benchmark results in:
| $> perf bench -r 30 breakpoint thread -b 4 -p 64 -t 64
| # Running 'breakpoint/thread' benchmark:
| # Created/joined 30 threads with 4 breakpoints and 64 parallelism
| Total time: 236.418 [sec]
|
| 123134.794271 usecs/op
| 7880626.833333 usecs/op/cpu
The benchmark tests inherited breakpoint perf events across many
threads.
Looking at a perf profile, we can see that the majority of the time is
spent in various hw_breakpoint.c functions, which execute within the
'nr_bp_mutex' critical sections which then results in contention on that
mutex as well:
37.27% [kernel] [k] osq_lock
34.92% [kernel] [k] mutex_spin_on_owner
12.15% [kernel] [k] toggle_bp_slot
11.90% [kernel] [k] __reserve_bp_slot
The culprit here is task_bp_pinned(), which has a runtime complexity of
O(#tasks) due to storing all task breakpoints in the same list and
iterating through that list looking for a matching task. Clearly, this
does not scale to thousands of tasks.
Instead, make use of the "rhashtable" variant "rhltable" which stores
multiple items with the same key in a list. This results in average
runtime complexity of O(1) for task_bp_pinned().
With the optimization, the benchmark shows:
| $> perf bench -r 30 breakpoint thread -b 4 -p 64 -t 64
| # Running 'breakpoint/thread' benchmark:
| # Created/joined 30 threads with 4 breakpoints and 64 parallelism
| Total time: 0.208 [sec]
|
| 108.422396 usecs/op
| 6939.033333 usecs/op/cpu
On this particular setup that's a speedup of ~1135x.
While one option would be to make task_struct a breakpoint list node,
this would only further bloat task_struct for infrequently used data.
Furthermore, after all optimizations in this series, there's no evidence
it would result in better performance: later optimizations make the time
spent looking up entries in the hash table negligible (we'll reach the
theoretical ideal performance i.e. no constraints).
Signed-off-by: Marco Elver <elver@...gle.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@...radead.org>
Reviewed-by: Dmitry Vyukov <dvyukov@...gle.com>
Acked-by: Ian Rogers <irogers@...gle.com>
Link: https://lore.kernel.org/r/20220829124719.675715-5-elver@google.com
---
include/linux/perf_event.h | 3 +-
kernel/events/hw_breakpoint.c | 56 +++++++++++++++++++++-------------
2 files changed, 37 insertions(+), 22 deletions(-)
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index ae30c61..1999408 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -36,6 +36,7 @@ struct perf_guest_info_callbacks {
};
#ifdef CONFIG_HAVE_HW_BREAKPOINT
+#include <linux/rhashtable-types.h>
#include <asm/hw_breakpoint.h>
#endif
@@ -178,7 +179,7 @@ struct hw_perf_event {
* creation and event initalization.
*/
struct arch_hw_breakpoint info;
- struct list_head bp_list;
+ struct rhlist_head bp_list;
};
#endif
struct { /* amd_iommu */
diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index 6076c63..6d09edc 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
@@ -26,10 +26,10 @@
#include <linux/irqflags.h>
#include <linux/kdebug.h>
#include <linux/kernel.h>
-#include <linux/list.h>
#include <linux/mutex.h>
#include <linux/notifier.h>
#include <linux/percpu.h>
+#include <linux/rhashtable.h>
#include <linux/sched.h>
#include <linux/slab.h>
@@ -54,7 +54,13 @@ static struct bp_cpuinfo *get_bp_info(int cpu, enum bp_type_idx type)
}
/* Keep track of the breakpoints attached to tasks */
-static LIST_HEAD(bp_task_head);
+static struct rhltable task_bps_ht;
+static const struct rhashtable_params task_bps_ht_params = {
+ .head_offset = offsetof(struct hw_perf_event, bp_list),
+ .key_offset = offsetof(struct hw_perf_event, target),
+ .key_len = sizeof_field(struct hw_perf_event, target),
+ .automatic_shrinking = true,
+};
static int constraints_initialized;
@@ -103,17 +109,23 @@ static unsigned int max_task_bp_pinned(int cpu, enum bp_type_idx type)
*/
static int task_bp_pinned(int cpu, struct perf_event *bp, enum bp_type_idx type)
{
- struct task_struct *tsk = bp->hw.target;
+ struct rhlist_head *head, *pos;
struct perf_event *iter;
int count = 0;
- list_for_each_entry(iter, &bp_task_head, hw.bp_list) {
- if (iter->hw.target == tsk &&
- find_slot_idx(iter->attr.bp_type) == type &&
+ rcu_read_lock();
+ head = rhltable_lookup(&task_bps_ht, &bp->hw.target, task_bps_ht_params);
+ if (!head)
+ goto out;
+
+ rhl_for_each_entry_rcu(iter, pos, head, hw.bp_list) {
+ if (find_slot_idx(iter->attr.bp_type) == type &&
(iter->cpu < 0 || cpu == iter->cpu))
count += hw_breakpoint_weight(iter);
}
+out:
+ rcu_read_unlock();
return count;
}
@@ -186,7 +198,7 @@ static void toggle_bp_task_slot(struct perf_event *bp, int cpu,
/*
* Add/remove the given breakpoint in our constraint table
*/
-static void
+static int
toggle_bp_slot(struct perf_event *bp, bool enable, enum bp_type_idx type,
int weight)
{
@@ -199,7 +211,7 @@ toggle_bp_slot(struct perf_event *bp, bool enable, enum bp_type_idx type,
/* Pinned counter cpu profiling */
if (!bp->hw.target) {
get_bp_info(bp->cpu, type)->cpu_pinned += weight;
- return;
+ return 0;
}
/* Pinned counter task profiling */
@@ -207,9 +219,9 @@ toggle_bp_slot(struct perf_event *bp, bool enable, enum bp_type_idx type,
toggle_bp_task_slot(bp, cpu, type, weight);
if (enable)
- list_add_tail(&bp->hw.bp_list, &bp_task_head);
+ return rhltable_insert(&task_bps_ht, &bp->hw.bp_list, task_bps_ht_params);
else
- list_del(&bp->hw.bp_list);
+ return rhltable_remove(&task_bps_ht, &bp->hw.bp_list, task_bps_ht_params);
}
__weak int arch_reserve_bp_slot(struct perf_event *bp)
@@ -307,9 +319,7 @@ static int __reserve_bp_slot(struct perf_event *bp, u64 bp_type)
if (ret)
return ret;
- toggle_bp_slot(bp, true, type, weight);
-
- return 0;
+ return toggle_bp_slot(bp, true, type, weight);
}
int reserve_bp_slot(struct perf_event *bp)
@@ -334,7 +344,7 @@ static void __release_bp_slot(struct perf_event *bp, u64 bp_type)
type = find_slot_idx(bp_type);
weight = hw_breakpoint_weight(bp);
- toggle_bp_slot(bp, false, type, weight);
+ WARN_ON(toggle_bp_slot(bp, false, type, weight));
}
void release_bp_slot(struct perf_event *bp)
@@ -707,7 +717,7 @@ static struct pmu perf_breakpoint = {
int __init init_hw_breakpoint(void)
{
int cpu, err_cpu;
- int i;
+ int i, ret;
for (i = 0; i < TYPE_MAX; i++)
nr_slots[i] = hw_breakpoint_slots(i);
@@ -718,18 +728,24 @@ int __init init_hw_breakpoint(void)
info->tsk_pinned = kcalloc(nr_slots[i], sizeof(int),
GFP_KERNEL);
- if (!info->tsk_pinned)
- goto err_alloc;
+ if (!info->tsk_pinned) {
+ ret = -ENOMEM;
+ goto err;
+ }
}
}
+ ret = rhltable_init(&task_bps_ht, &task_bps_ht_params);
+ if (ret)
+ goto err;
+
constraints_initialized = 1;
perf_pmu_register(&perf_breakpoint, "breakpoint", PERF_TYPE_BREAKPOINT);
return register_die_notifier(&hw_breakpoint_exceptions_nb);
- err_alloc:
+err:
for_each_possible_cpu(err_cpu) {
for (i = 0; i < TYPE_MAX; i++)
kfree(get_bp_info(err_cpu, i)->tsk_pinned);
@@ -737,7 +753,5 @@ int __init init_hw_breakpoint(void)
break;
}
- return -ENOMEM;
+ return ret;
}
-
-
Powered by blists - more mailing lists