From: Sasha Levin <sashal@kernel.org>
To: linux-kernel@vger.kernel.org, stable@vger.kernel.org
Cc: Jiri Olsa <jolsa@kernel.org>,
Alexander Shishkin <alexander.shishkin@linux.intel.com>,
Arnaldo Carvalho de Melo <acme@redhat.com>,
David Arcari <darcari@redhat.com>, Jiri Olsa <jolsa@redhat.com>,
Lendacky Thomas <Thomas.Lendacky@amd.com>,
Linus Torvalds <torvalds@linux-foundation.org>,
Peter Zijlstra <peterz@infradead.org>,
Stephane Eranian <eranian@google.com>,
Thomas Gleixner <tglx@linutronix.de>,
Vince Weaver <vincent.weaver@maine.edu>,
Ingo Molnar <mingo@kernel.org>, Sasha Levin <sashal@kernel.org>
Subject: [PATCH AUTOSEL 5.0 34/34] perf/x86/intel: Fix race in intel_pmu_disable_event()
Date: Thu, 16 May 2019 07:39:31 -0400 [thread overview]
Message-ID: <20190516113932.8348-34-sashal@kernel.org> (raw)
In-Reply-To: <20190516113932.8348-1-sashal@kernel.org>
From: Jiri Olsa <jolsa@kernel.org>
[ Upstream commit 6f55967ad9d9752813e36de6d5fdbd19741adfc7 ]
New race in x86_pmu_stop() was introduced by replacing the
atomic __test_and_clear_bit() of cpuc->active_mask by separate
test_bit() and __clear_bit() calls in the following commit:
3966c3feca3f ("x86/perf/amd: Remove need to check "running" bit in NMI handler")
The race causes panic for PEBS events with enabled callchains:
BUG: unable to handle kernel NULL pointer dereference at 0000000000000000
...
RIP: 0010:perf_prepare_sample+0x8c/0x530
Call Trace:
<NMI>
perf_event_output_forward+0x2a/0x80
__perf_event_overflow+0x51/0xe0
handle_pmi_common+0x19e/0x240
intel_pmu_handle_irq+0xad/0x170
perf_event_nmi_handler+0x2e/0x50
nmi_handle+0x69/0x110
default_do_nmi+0x3e/0x100
do_nmi+0x11a/0x180
end_repeat_nmi+0x16/0x1a
RIP: 0010:native_write_msr+0x6/0x20
...
</NMI>
intel_pmu_disable_event+0x98/0xf0
x86_pmu_stop+0x6e/0xb0
x86_pmu_del+0x46/0x140
event_sched_out.isra.97+0x7e/0x160
...
The event is configured to make samples from PEBS drain code,
but when it's disabled, we'll go through NMI path instead,
where data->callchain will not get allocated and we'll crash:
x86_pmu_stop
test_bit(hwc->idx, cpuc->active_mask)
intel_pmu_disable_event(event)
{
...
intel_pmu_pebs_disable(event);
...
EVENT OVERFLOW -> <NMI>
intel_pmu_handle_irq
handle_pmi_common
TEST PASSES -> test_bit(bit, cpuc->active_mask))
perf_event_overflow
perf_prepare_sample
{
...
if (!(sample_type & __PERF_SAMPLE_CALLCHAIN_EARLY))
data->callchain = perf_callchain(event, regs);
CRASH -> size += data->callchain->nr;
}
</NMI>
...
x86_pmu_disable_event(event)
}
__clear_bit(hwc->idx, cpuc->active_mask);
Fixing this by disabling the event itself before setting
off the PEBS bit.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: David Arcari <darcari@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Lendacky Thomas <Thomas.Lendacky@amd.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Fixes: 3966c3feca3f ("x86/perf/amd: Remove need to check "running" bit in NMI handler")
Link: http://lkml.kernel.org/r/20190504151556.31031-1-jolsa@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
arch/x86/events/intel/core.c | 10 +++++++---
1 file changed, 7 insertions(+), 3 deletions(-)
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 71fb8b7b29545..c87b06ad9f860 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2090,15 +2090,19 @@ static void intel_pmu_disable_event(struct perf_event *event)
cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx);
cpuc->intel_cp_status &= ~(1ull << hwc->idx);
- if (unlikely(event->attr.precise_ip))
- intel_pmu_pebs_disable(event);
-
if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
intel_pmu_disable_fixed(hwc);
return;
}
x86_pmu_disable_event(event);
+
+ /*
+ * Needs to be called after x86_pmu_disable_event,
+ * so we don't trigger the event without PEBS bit set.
+ */
+ if (unlikely(event->attr.precise_ip))
+ intel_pmu_pebs_disable(event);
}
static void intel_pmu_del_event(struct perf_event *event)
--
2.20.1
prev parent reply other threads:[~2019-05-16 11:40 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-05-16 11:38 [PATCH AUTOSEL 5.0 01/34] xfrm: policy: Fix out-of-bound array accesses in __xfrm_policy_unlink Sasha Levin
2019-05-16 11:38 ` [PATCH AUTOSEL 5.0 02/34] xfrm: Reset secpath in xfrm failure Sasha Levin
2019-05-16 11:39 ` [PATCH AUTOSEL 5.0 03/34] xfrm6_tunnel: Fix potential panic when unloading xfrm6_tunnel module Sasha Levin
2019-05-16 11:39 ` [PATCH AUTOSEL 5.0 04/34] vti4: ipip tunnel deregistration fixes Sasha Levin
2019-05-16 11:39 ` [PATCH AUTOSEL 5.0 05/34] xfrm: clean up xfrm protocol checks Sasha Levin
2019-05-16 11:39 ` [PATCH AUTOSEL 5.0 06/34] esp4: add length check for UDP encapsulation Sasha Levin
2019-05-16 11:39 ` [PATCH AUTOSEL 5.0 07/34] xfrm: Honor original L3 slave device in xfrmi policy lookup Sasha Levin
2019-05-16 11:39 ` [PATCH AUTOSEL 5.0 08/34] xfrm4: Fix uninitialized memory read in _decode_session4 Sasha Levin
2019-05-16 11:39 ` [PATCH AUTOSEL 5.0 09/34] ARC: PAE40: don't panic and instead turn off hw ioc Sasha Levin
2019-05-16 11:39 ` [PATCH AUTOSEL 5.0 10/34] clk: sunxi-ng: nkmp: Avoid GENMASK(-1, 0) Sasha Levin
2019-05-16 11:39 ` [PATCH AUTOSEL 5.0 11/34] KVM: PPC: Book3S HV: Perserve PSSCR FAKE_SUSPEND bit on guest exit Sasha Levin
2019-05-16 11:39 ` [PATCH AUTOSEL 5.0 12/34] KVM: PPC: Book3S: Protect memslots while validating user address Sasha Levin
2019-05-16 11:39 ` [PATCH AUTOSEL 5.0 13/34] power: supply: cpcap-battery: Fix division by zero Sasha Levin
2019-05-16 11:39 ` [PATCH AUTOSEL 5.0 14/34] securityfs: fix use-after-free on symlink traversal Sasha Levin
2019-05-16 11:39 ` [PATCH AUTOSEL 5.0 15/34] apparmorfs: " Sasha Levin
2019-05-16 11:39 ` [PATCH AUTOSEL 5.0 16/34] PCI: Fix issue with "pci=disable_acs_redir" parameter being ignored Sasha Levin
2019-05-16 11:39 ` [PATCH AUTOSEL 5.0 17/34] x86: kvm: hyper-v: deal with buggy TLB flush requests from WS2012 Sasha Levin
2019-05-16 11:39 ` [PATCH AUTOSEL 5.0 18/34] mac80211: Fix kernel panic due to use of txq after free Sasha Levin
2019-05-16 11:39 ` [PATCH AUTOSEL 5.0 19/34] net: ieee802154: fix missing checks for regmap_update_bits Sasha Levin
2019-05-16 11:39 ` [PATCH AUTOSEL 5.0 20/34] KVM: arm/arm64: Ensure vcpu target is unset on reset failure Sasha Levin
2019-05-16 11:39 ` [PATCH AUTOSEL 5.0 21/34] power: supply: sysfs: prevent endless uevent loop with CONFIG_POWER_SUPPLY_DEBUG Sasha Levin
2019-05-16 11:39 ` [PATCH AUTOSEL 5.0 22/34] tools: bpftool: fix infinite loop in map create Sasha Levin
2019-05-16 11:39 ` [PATCH AUTOSEL 5.0 23/34] bpf: Fix preempt_enable_no_resched() abuse Sasha Levin
2019-05-16 11:39 ` [PATCH AUTOSEL 5.0 24/34] qmi_wwan: new Wistron, ZTE and D-Link devices Sasha Levin
2019-05-16 11:39 ` [PATCH AUTOSEL 5.0 25/34] iwlwifi: mvm: check for length correctness in iwl_mvm_create_skb() Sasha Levin
2019-05-16 11:39 ` [PATCH AUTOSEL 5.0 26/34] sched/cpufreq: Fix kobject memleak Sasha Levin
2019-05-16 11:39 ` [PATCH AUTOSEL 5.0 27/34] x86/mm/mem_encrypt: Disable all instrumentation for early SME setup Sasha Levin
2019-05-16 11:39 ` [PATCH AUTOSEL 5.0 28/34] KVM: fix KVM_CLEAR_DIRTY_LOG for memory slots of unaligned size Sasha Levin
2019-05-16 11:39 ` [PATCH AUTOSEL 5.0 29/34] KVM: selftests: make hyperv_cpuid test pass on AMD Sasha Levin
2019-05-16 11:39 ` [PATCH AUTOSEL 5.0 30/34] ufs: fix braino in ufs_get_inode_gid() for solaris UFS flavour Sasha Levin
2019-05-16 11:39 ` [PATCH AUTOSEL 5.0 31/34] i2c: designware: ratelimit 'transfer when suspended' errors Sasha Levin
2019-05-16 11:39 ` [PATCH AUTOSEL 5.0 32/34] perf bench numa: Add define for RUSAGE_THREAD if not present Sasha Levin
2019-05-16 11:39 ` [PATCH AUTOSEL 5.0 33/34] perf cs-etm: Always allocate memory for cs_etm_queue::prev_packet Sasha Levin
2019-05-16 11:39 ` Sasha Levin [this message]
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=20190516113932.8348-34-sashal@kernel.org \
--to=sashal@kernel.org \
--cc=Thomas.Lendacky@amd.com \
--cc=acme@redhat.com \
--cc=alexander.shishkin@linux.intel.com \
--cc=darcari@redhat.com \
--cc=eranian@google.com \
--cc=jolsa@kernel.org \
--cc=jolsa@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=peterz@infradead.org \
--cc=stable@vger.kernel.org \
--cc=tglx@linutronix.de \
--cc=torvalds@linux-foundation.org \
--cc=vincent.weaver@maine.edu \
/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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).