From: Dapeng Mi <dapeng1.mi@linux.intel.com>
To: Sean Christopherson <seanjc@google.com>,
Paolo Bonzini <pbonzini@redhat.com>,
Jim Mattson <jmattson@google.com>,
Mingwei Zhang <mizhang@google.com>
Cc: kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
Xiong Zhang <xiong.y.zhang@intel.com>,
Zhenyu Wang <zhenyuw@linux.intel.com>,
Like Xu <like.xu.linux@gmail.com>,
Jinrong Liang <cloudliang@tencent.com>,
Dapeng Mi <dapeng1.mi@intel.com>,
Dapeng Mi <dapeng1.mi@linux.intel.com>
Subject: [kvm-unit-tests Patch v4 04/17] x86: pmu: Fix the issue that pmu_counter_t.config crosses cache line
Date: Fri, 19 Apr 2024 11:52:20 +0800 [thread overview]
Message-ID: <20240419035233.3837621-5-dapeng1.mi@linux.intel.com> (raw)
In-Reply-To: <20240419035233.3837621-1-dapeng1.mi@linux.intel.com>
When running pmu test on SPR, the following #GP fault is reported.
Unhandled exception 13 #GP at ip 000000000040771f
error_code=0000 rflags=00010046 cs=00000008
rax=00000000004031ad rcx=0000000000000186 rdx=0000000000000000 rbx=00000000005142f0
rbp=0000000000514260 rsi=0000000000000020 rdi=0000000000000340
r8=0000000000513a65 r9=00000000000003f8 r10=000000000000000d r11=00000000ffffffff
r12=000000000043003c r13=0000000000514450 r14=000000000000000b r15=0000000000000001
cr0=0000000080010011 cr2=0000000000000000 cr3=0000000001007000 cr4=0000000000000020
cr8=0000000000000000
STACK: @40771f 40040e 400976 400aef 40148d 401da9 4001ad
FAIL pmu
It looks EVENTSEL0 MSR (0x186) is written a invalid value (0x4031ad) and
cause a #GP.
Further investigation shows the #GP is caused by below code in
__start_event().
rmsr(MSR_GP_EVENT_SELECTx(event_to_global_idx(evt)),
evt->config | EVNTSEL_EN);
The evt->config is correctly initialized but seems corrupted before
writing to MSR.
The original pmu_counter_t layout looks as below.
typedef struct {
uint32_t ctr;
uint64_t config;
uint64_t count;
int idx;
} pmu_counter_t;
Obviously the config filed crosses two cache lines. When the two cache
lines are not updated simultaneously, the config value is corrupted.
Adjust pmu_counter_t fields order and ensure config field is cache-line
aligned.
Signeduoff-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
---
x86/pmu.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/x86/pmu.c b/x86/pmu.c
index c971386db4e6..5fd7439a0eba 100644
--- a/x86/pmu.c
+++ b/x86/pmu.c
@@ -20,9 +20,9 @@
typedef struct {
uint32_t ctr;
+ uint32_t idx;
uint64_t config;
uint64_t count;
- int idx;
} pmu_counter_t;
struct pmu_event {
--
2.34.1
next prev parent reply other threads:[~2024-04-19 3:45 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-04-19 3:52 [kvm-unit-tests Patch v4 00/17] pmu test bugs fix and improvements Dapeng Mi
2024-04-19 3:52 ` [kvm-unit-tests Patch v4 01/17] x86: pmu: Remove duplicate code in pmu_init() Dapeng Mi
2024-04-19 3:52 ` [kvm-unit-tests Patch v4 02/17] x86: pmu: Remove blank line and redundant space Dapeng Mi
2024-04-19 3:52 ` [kvm-unit-tests Patch v4 03/17] x86: pmu: Refine fixed_events[] names Dapeng Mi
2024-04-19 3:52 ` Dapeng Mi [this message]
2024-04-19 3:52 ` [kvm-unit-tests Patch v4 05/17] x86: pmu: Enlarge cnt[] length to 48 in check_counters_many() Dapeng Mi
2024-04-19 3:52 ` [kvm-unit-tests Patch v4 06/17] x86: pmu: Add asserts to warn inconsistent fixed events and counters Dapeng Mi
2024-04-19 3:52 ` [kvm-unit-tests Patch v4 07/17] x86: pmu: Fix cycles event validation failure Dapeng Mi
2024-04-19 3:52 ` [kvm-unit-tests Patch v4 08/17] x86: pmu: Use macro to replace hard-coded branches event index Dapeng Mi
2024-04-19 3:52 ` [kvm-unit-tests Patch v4 09/17] x86: pmu: Use macro to replace hard-coded ref-cycles " Dapeng Mi
2024-04-19 3:52 ` [kvm-unit-tests Patch v4 10/17] x86: pmu: Use macro to replace hard-coded instructions " Dapeng Mi
2024-04-19 3:52 ` [kvm-unit-tests Patch v4 11/17] x86: pmu: Enable and disable PMCs in loop() asm blob Dapeng Mi
2024-04-19 3:52 ` [kvm-unit-tests Patch v4 12/17] x86: pmu: Improve instruction and branches events verification Dapeng Mi
2024-04-19 3:52 ` [kvm-unit-tests Patch v4 13/17] x86: pmu: Improve LLC misses event verification Dapeng Mi
2024-04-19 3:52 ` [kvm-unit-tests Patch v4 14/17] x86: pmu: Adjust lower boundary of llc-misses event to 0 for legacy CPUs Dapeng Mi
2024-04-19 3:52 ` [kvm-unit-tests Patch v4 15/17] x86: pmu: Add IBPB indirect jump asm blob Dapeng Mi
2024-04-19 3:52 ` [kvm-unit-tests Patch v4 16/17] x86: pmu: Adjust lower boundary of branch-misses event Dapeng Mi
2024-04-19 3:52 ` [kvm-unit-tests Patch v4 17/17] x86: pmu: Optimize emulated instruction validation Dapeng Mi
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=20240419035233.3837621-5-dapeng1.mi@linux.intel.com \
--to=dapeng1.mi@linux.intel.com \
--cc=cloudliang@tencent.com \
--cc=dapeng1.mi@intel.com \
--cc=jmattson@google.com \
--cc=kvm@vger.kernel.org \
--cc=like.xu.linux@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mizhang@google.com \
--cc=pbonzini@redhat.com \
--cc=seanjc@google.com \
--cc=xiong.y.zhang@intel.com \
--cc=zhenyuw@linux.intel.com \
/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