Commit 5ea3f6fb authored by Zhenzhong Duan's avatar Zhenzhong Duan Committed by Ingo Molnar

perf/x86: Apply more accurate check on hypervisor platform

check_msr is used to fix a bug report in guest where KVM doesn't support
LBR MSR and cause #GP.

The msr check is bypassed on real HW to workaround a false failure,
see commit d0e1a507 ("perf/x86/intel: Disable check_msr for real HW")

When running a guest with CONFIG_HYPERVISOR_GUEST not set or "nopv"
enabled, current check isn't enough and #GP could trigger.
Signed-off-by: default avatarZhenzhong Duan <zhenzhong.duan@oracle.com>
Signed-off-by: default avatarPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/1564022366-18293-1-git-send-email-zhenzhong.duan@oracle.comSigned-off-by: default avatarIngo Molnar <mingo@kernel.org>
parent 3b238a64
...@@ -20,7 +20,6 @@ ...@@ -20,7 +20,6 @@
#include <asm/intel-family.h> #include <asm/intel-family.h>
#include <asm/apic.h> #include <asm/apic.h>
#include <asm/cpu_device_id.h> #include <asm/cpu_device_id.h>
#include <asm/hypervisor.h>
#include "../perf_event.h" #include "../perf_event.h"
...@@ -4053,7 +4052,7 @@ static bool check_msr(unsigned long msr, u64 mask) ...@@ -4053,7 +4052,7 @@ static bool check_msr(unsigned long msr, u64 mask)
* Disable the check for real HW, so we don't * Disable the check for real HW, so we don't
* mess with potentionaly enabled registers: * mess with potentionaly enabled registers:
*/ */
if (hypervisor_is_type(X86_HYPER_NATIVE)) if (!boot_cpu_has(X86_FEATURE_HYPERVISOR))
return true; return true;
/* /*
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment