Mark Rutland (1): perf: Fix perf_event_validate_size() lockdep splat
Peter Zijlstra (1): perf: Fix perf_event_validate_size()
kernel/events/core.c | 67 ++++++++++++++++++++++++++++++-------------- 1 file changed, 46 insertions(+), 21 deletions(-)
From: Peter Zijlstra peterz@infradead.org
stable inclusion from stable-v4.19.302 commit f5d6ab016792c9d6d5280fdb7f8962eb3b8c620e category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I8PT55 CVE: CVE-2023-6931
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...
---------------------------
[ Upstream commit 382c27f4ed28f803b1f1473ac2d8db0afc795a1b ]
Budimir noted that perf_event_validate_size() only checks the size of the newly added event, even though the sizes of all existing events can also change due to not all events having the same read_format.
When we attach the new event, perf_group_attach(), we do re-compute the size for all events.
Fixes: a723968c0ed3 ("perf: Fix u16 overflows") Reported-by: Budimir Markovic markovicbudimir@gmail.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Jihong yangjihong1@huawei.com --- kernel/events/core.c | 59 +++++++++++++++++++++++++++----------------- 1 file changed, 37 insertions(+), 22 deletions(-)
diff --git a/kernel/events/core.c b/kernel/events/core.c index a1f12009e5ef..17b59843ae9b 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1705,28 +1705,31 @@ static inline void perf_event__state_init(struct perf_event *event) PERF_EVENT_STATE_INACTIVE; }
-static void __perf_event_read_size(struct perf_event *event, int nr_siblings) +static int __perf_event_read_size(u64 read_format, int nr_siblings) { int entry = sizeof(u64); /* value */ int size = 0; int nr = 1;
- if (event->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) size += sizeof(u64);
- if (event->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) size += sizeof(u64);
- if (event->attr.read_format & PERF_FORMAT_ID) + if (read_format & PERF_FORMAT_ID) entry += sizeof(u64);
- if (event->attr.read_format & PERF_FORMAT_GROUP) { + if (read_format & PERF_FORMAT_GROUP) { nr += nr_siblings; size += sizeof(u64); }
- size += entry * nr; - event->read_size = size; + /* + * Since perf_event_validate_size() limits this to 16k and inhibits + * adding more siblings, this will never overflow. + */ + return size + nr * entry; }
static void __perf_event_header_size(struct perf_event *event, u64 sample_type) @@ -1767,8 +1770,9 @@ static void __perf_event_header_size(struct perf_event *event, u64 sample_type) */ static void perf_event__header_size(struct perf_event *event) { - __perf_event_read_size(event, - event->group_leader->nr_siblings); + event->read_size = + __perf_event_read_size(event->attr.read_format, + event->group_leader->nr_siblings); __perf_event_header_size(event, event->attr.sample_type); }
@@ -1799,24 +1803,35 @@ static void perf_event__id_header_size(struct perf_event *event) event->id_header_size = size; }
+/* + * Check that adding an event to the group does not result in anybody + * overflowing the 64k event limit imposed by the output buffer. + * + * Specifically, check that the read_size for the event does not exceed 16k, + * read_size being the one term that grows with groups size. Since read_size + * depends on per-event read_format, also (re)check the existing events. + * + * This leaves 48k for the constant size fields and things like callchains, + * branch stacks and register sets. + */ static bool perf_event_validate_size(struct perf_event *event) { - /* - * The values computed here will be over-written when we actually - * attach the event. - */ - __perf_event_read_size(event, event->group_leader->nr_siblings + 1); - __perf_event_header_size(event, event->attr.sample_type & ~PERF_SAMPLE_READ); - perf_event__id_header_size(event); + struct perf_event *sibling, *group_leader = event->group_leader;
- /* - * Sum the lot; should not exceed the 64k limit we have on records. - * Conservative limit to allow for callchains and other variable fields. - */ - if (event->read_size + event->header_size + - event->id_header_size + sizeof(struct perf_event_header) >= 16*1024) + if (__perf_event_read_size(event->attr.read_format, + group_leader->nr_siblings + 1) > 16*1024) return false;
+ if (__perf_event_read_size(group_leader->attr.read_format, + group_leader->nr_siblings + 1) > 16*1024) + return false; + + for_each_sibling_event(sibling, group_leader) { + if (__perf_event_read_size(sibling->attr.read_format, + group_leader->nr_siblings + 1) > 16*1024) + return false; + } + return true; }
From: Mark Rutland mark.rutland@arm.com
stable inclusion from stable-v4.19.303 commit 46f677826f01758cf04e266a7950ed1881aace30 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I8PT55 CVE: NA
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...
---------------------------
commit 7e2c1e4b34f07d9aa8937fab88359d4a0fce468e upstream.
When lockdep is enabled, the for_each_sibling_event(sibling, event) macro checks that event->ctx->mutex is held. When creating a new group leader event, we call perf_event_validate_size() on a partially initialized event where event->ctx is NULL, and so when for_each_sibling_event() attempts to check event->ctx->mutex, we get a splat, as reported by Lucas De Marchi:
WARNING: CPU: 8 PID: 1471 at kernel/events/core.c:1950 __do_sys_perf_event_open+0xf37/0x1080
This only happens for a new event which is its own group_leader, and in this case there cannot be any sibling events. Thus it's safe to skip the check for siblings, which avoids having to make invasive and ugly changes to for_each_sibling_event().
Avoid the splat by bailing out early when the new event is its own group_leader.
Fixes: 382c27f4ed28f803 ("perf: Fix perf_event_validate_size()") Closes: https://lore.kernel.org/lkml/20231214000620.3081018-1-lucas.demarchi@intel.c... Closes: https://lore.kernel.org/lkml/ZXpm6gQ%2Fd59jGsuW@xpf.sh.intel.com/ Reported-by: Lucas De Marchi lucas.demarchi@intel.com Reported-by: Pengfei Xu pengfei.xu@intel.com Signed-off-by: Mark Rutland mark.rutland@arm.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Link: https://lkml.kernel.org/r/20231215112450.3972309-1-mark.rutland@arm.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Yang Jihong yangjihong1@huawei.com --- kernel/events/core.c | 10 ++++++++++ 1 file changed, 10 insertions(+)
diff --git a/kernel/events/core.c b/kernel/events/core.c index 17b59843ae9b..be528436a03b 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1826,6 +1826,16 @@ static bool perf_event_validate_size(struct perf_event *event) group_leader->nr_siblings + 1) > 16*1024) return false;
+ /* + * When creating a new group leader, group_leader->ctx is initialized + * after the size has been validated, but we cannot safely use + * for_each_sibling_event() until group_leader->ctx is set. A new group + * leader cannot have any siblings yet, so we can safely skip checking + * the non-existent siblings. + */ + if (event == group_leader) + return true; + for_each_sibling_event(sibling, group_leader) { if (__perf_event_read_size(sibling->attr.read_format, group_leader->nr_siblings + 1) > 16*1024)
反馈: 您发送到kernel@openeuler.org的补丁/补丁集,已成功转换为PR! PR链接地址: https://gitee.com/openeuler/kernel/pulls/3606 邮件列表地址:https://mailweb.openeuler.org/hyperkitty/list/kernel@openeuler.org/message/N...
FeedBack: The patch(es) which you have sent to kernel@openeuler.org mailing list has been converted to a pull request successfully! Pull request link: https://gitee.com/openeuler/kernel/pulls/3606 Mailing list address: https://mailweb.openeuler.org/hyperkitty/list/kernel@openeuler.org/message/N...