public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
To: linux-kernel@vger.kernel.org
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
	stable@vger.kernel.org, Anand K Mistry <amistry@google.com>,
	"Peter Zijlstra (Intel)" <peterz@infradead.org>,
	Sasha Levin <sashal@kernel.org>
Subject: [PATCH 4.4 18/18] perf/x86: Reset destroy callback on event init failure
Date: Thu, 14 Oct 2021 16:53:50 +0200	[thread overview]
Message-ID: <20211014145206.908742524@linuxfoundation.org> (raw)
In-Reply-To: <20211014145206.330102860@linuxfoundation.org>

From: Anand K Mistry <amistry@google.com>

[ Upstream commit 02d029a41dc986e2d5a77ecca45803857b346829 ]

perf_init_event tries multiple init callbacks and does not reset the
event state between tries. When x86_pmu_event_init runs, it
unconditionally sets the destroy callback to hw_perf_event_destroy. On
the next init attempt after x86_pmu_event_init, in perf_try_init_event,
if the pmu's capabilities includes PERF_PMU_CAP_NO_EXCLUDE, the destroy
callback will be run. However, if the next init didn't set the destroy
callback, hw_perf_event_destroy will be run (since the callback wasn't
reset).

Looking at other pmu init functions, the common pattern is to only set
the destroy callback on a successful init. Resetting the callback on
failure tries to replicate that pattern.

This was discovered after commit f11dd0d80555 ("perf/x86/amd/ibs: Extend
PERF_PMU_CAP_NO_EXCLUDE to IBS Op") when the second (and only second)
run of the perf tool after a reboot results in 0 samples being
generated. The extra run of hw_perf_event_destroy results in
active_events having an extra decrement on each perf run. The second run
has active_events == 0 and every subsequent run has active_events < 0.
When active_events == 0, the NMI handler will early-out and not record
any samples.

Signed-off-by: Anand K Mistry <amistry@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20210929170405.1.I078b98ee7727f9ae9d6df8262bad7e325e40faf0@changeid
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/x86/kernel/cpu/perf_event.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index b983d3dc4e6c..851fbdb99767 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -2001,6 +2001,7 @@ static int x86_pmu_event_init(struct perf_event *event)
 	if (err) {
 		if (event->destroy)
 			event->destroy(event);
+		event->destroy = NULL;
 	}
 
 	if (ACCESS_ONCE(x86_pmu.attr_rdpmc))
-- 
2.33.0




  parent reply	other threads:[~2021-10-14 14:55 UTC|newest]

Thread overview: 23+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-10-14 14:53 [PATCH 4.4 00/18] 4.4.289-rc1 review Greg Kroah-Hartman
2021-10-14 14:53 ` [PATCH 4.4 01/18] USB: cdc-acm: fix racy tty buffer accesses Greg Kroah-Hartman
2021-10-14 14:53 ` [PATCH 4.4 02/18] USB: cdc-acm: fix break reporting Greg Kroah-Hartman
2021-10-14 14:53 ` [PATCH 4.4 03/18] nfsd4: Handle the NFSv4 READDIR dircount hint being zero Greg Kroah-Hartman
2021-10-14 14:53 ` [PATCH 4.4 04/18] xtensa: call irqchip_init only when CONFIG_USE_OF is selected Greg Kroah-Hartman
2021-10-14 14:53 ` [PATCH 4.4 05/18] phy: mdio: fix memory leak Greg Kroah-Hartman
2021-10-14 14:53 ` [PATCH 4.4 06/18] net_sched: fix NULL deref in fifo_set_limit() Greg Kroah-Hartman
2021-10-14 14:53 ` [PATCH 4.4 07/18] ptp_pch: Load module automatically if ID matches Greg Kroah-Hartman
2021-10-14 14:53 ` [PATCH 4.4 08/18] ARM: imx6: disable the GIC CPU interface before calling stby-poweroff sequence Greg Kroah-Hartman
2021-10-14 14:53 ` [PATCH 4.4 09/18] netlink: annotate data races around nlk->bound Greg Kroah-Hartman
2021-10-14 14:53 ` [PATCH 4.4 10/18] i40e: fix endless loop under rtnl Greg Kroah-Hartman
2021-10-14 14:53 ` [PATCH 4.4 11/18] gup: document and work around "COW can break either way" issue Greg Kroah-Hartman
2021-10-14 14:53 ` [PATCH 4.4 12/18] mm: check VMA flags to avoid invalid PROT_NONE NUMA balancing Greg Kroah-Hartman
2021-10-14 14:53 ` [PATCH 4.4 13/18] HID: apple: Fix logical maximum and usage maximum of Magic Keyboard JIS Greg Kroah-Hartman
2021-10-14 14:53 ` [PATCH 4.4 14/18] netfilter: ip6_tables: zero-initialize fragment offset Greg Kroah-Hartman
2021-10-14 14:53 ` [PATCH 4.4 15/18] mac80211: Drop frames from invalid MAC address in ad-hoc mode Greg Kroah-Hartman
2021-10-14 14:53 ` [PATCH 4.4 16/18] scsi: ses: Fix unsigned comparison with less than zero Greg Kroah-Hartman
2021-10-14 14:53 ` [PATCH 4.4 17/18] scsi: virtio_scsi: Fix spelling mistake "Unsupport" -> "Unsupported" Greg Kroah-Hartman
2021-10-14 14:53 ` Greg Kroah-Hartman [this message]
2021-10-14 21:06 ` [PATCH 4.4 00/18] 4.4.289-rc1 review Pavel Machek
2021-10-14 22:40 ` Shuah Khan
2021-10-15 22:05 ` Guenter Roeck
2021-10-15 23:11 ` Daniel Díaz

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=20211014145206.908742524@linuxfoundation.org \
    --to=gregkh@linuxfoundation.org \
    --cc=amistry@google.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=peterz@infradead.org \
    --cc=sashal@kernel.org \
    --cc=stable@vger.kernel.org \
    /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