public inbox for stable@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, Like Xu <likexu@tencent.com>,
	"Peter Zijlstra (Intel)" <peterz@infradead.org>,
	Liam Merwick <liam.merwick@oracle.com>,
	Kim Phillips <kim.phillips@amd.com>
Subject: [PATCH 4.14 32/42] perf/x86/amd: Dont touch the AMD64_EVENTSEL_HOSTONLY bit inside the guest
Date: Fri, 13 Aug 2021 17:06:58 +0200	[thread overview]
Message-ID: <20210813150526.179743749@linuxfoundation.org> (raw)
In-Reply-To: <20210813150525.098817398@linuxfoundation.org>

From: Like Xu <likexu@tencent.com>

commit df51fe7ea1c1c2c3bfdb81279712fdd2e4ea6c27 upstream.

If we use "perf record" in an AMD Milan guest, dmesg reports a #GP
warning from an unchecked MSR access error on MSR_F15H_PERF_CTLx:

  [] unchecked MSR access error: WRMSR to 0xc0010200 (tried to write 0x0000020000110076) at rIP: 0xffffffff8106ddb4 (native_write_msr+0x4/0x20)
  [] Call Trace:
  []  amd_pmu_disable_event+0x22/0x90
  []  x86_pmu_stop+0x4c/0xa0
  []  x86_pmu_del+0x3a/0x140

The AMD64_EVENTSEL_HOSTONLY bit is defined and used on the host,
while the guest perf driver should avoid such use.

Fixes: 1018faa6cf23 ("perf/x86/kvm: Fix Host-Only/Guest-Only counting with SVM disabled")
Signed-off-by: Like Xu <likexu@tencent.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Liam Merwick <liam.merwick@oracle.com>
Tested-by: Kim Phillips <kim.phillips@amd.com>
Tested-by: Liam Merwick <liam.merwick@oracle.com>
Link: https://lkml.kernel.org/r/20210802070850.35295-1-likexu@tencent.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/x86/events/perf_event.h |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -792,9 +792,10 @@ void x86_pmu_stop(struct perf_event *eve
 
 static inline void x86_pmu_disable_event(struct perf_event *event)
 {
+	u64 disable_mask = __this_cpu_read(cpu_hw_events.perf_ctr_virt_mask);
 	struct hw_perf_event *hwc = &event->hw;
 
-	wrmsrl(hwc->config_base, hwc->config);
+	wrmsrl(hwc->config_base, hwc->config & ~disable_mask);
 }
 
 void x86_pmu_enable_event(struct perf_event *event);



  parent reply	other threads:[~2021-08-13 15:12 UTC|newest]

Thread overview: 46+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-08-13 15:06 [PATCH 4.14 00/42] 4.14.244-rc1 review Greg Kroah-Hartman
2021-08-13 15:06 ` [PATCH 4.14 01/42] Revert "ACPICA: Fix memory leak caused by _CID repair function" Greg Kroah-Hartman
2021-08-13 15:06 ` [PATCH 4.14 02/42] ALSA: seq: Fix racy deletion of subscriber Greg Kroah-Hartman
2021-08-13 15:06 ` [PATCH 4.14 03/42] clk: stm32f4: fix post divisor setup for I2S/SAI PLLs Greg Kroah-Hartman
2021-08-13 15:06 ` [PATCH 4.14 04/42] omap5-board-common: remove not physically existing vdds_1v8_main fixed-regulator Greg Kroah-Hartman
2021-08-13 15:06 ` [PATCH 4.14 05/42] scsi: sr: Return correct event when media event code is 3 Greg Kroah-Hartman
2021-08-13 15:06 ` [PATCH 4.14 06/42] media: videobuf2-core: dequeue if start_streaming fails Greg Kroah-Hartman
2021-08-13 15:06 ` [PATCH 4.14 07/42] net: natsemi: Fix missing pci_disable_device() in probe and remove Greg Kroah-Hartman
2021-08-13 15:06 ` [PATCH 4.14 08/42] nfp: update ethtool reporting of pauseframe control Greg Kroah-Hartman
2021-08-13 15:06 ` [PATCH 4.14 09/42] mips: Fix non-POSIX regexp Greg Kroah-Hartman
2021-08-13 15:06 ` [PATCH 4.14 10/42] bnx2x: fix an error code in bnx2x_nic_load() Greg Kroah-Hartman
2021-08-13 15:06 ` [PATCH 4.14 11/42] net: pegasus: fix uninit-value in get_interrupt_interval Greg Kroah-Hartman
2021-08-13 15:06 ` [PATCH 4.14 12/42] net: fec: fix use-after-free in fec_drv_remove Greg Kroah-Hartman
2021-08-13 15:06 ` [PATCH 4.14 13/42] net: vxge: fix use-after-free in vxge_device_unregister Greg Kroah-Hartman
2021-08-13 15:06 ` [PATCH 4.14 14/42] Bluetooth: defer cleanup of resources in hci_unregister_dev() Greg Kroah-Hartman
2021-08-13 15:06 ` [PATCH 4.14 15/42] USB: usbtmc: Fix RCU stall warning Greg Kroah-Hartman
2021-08-13 15:06 ` [PATCH 4.14 16/42] USB: serial: option: add Telit FD980 composition 0x1056 Greg Kroah-Hartman
2021-08-13 15:06 ` [PATCH 4.14 17/42] USB: serial: ch341: fix character loss at high transfer rates Greg Kroah-Hartman
2021-08-13 15:06 ` [PATCH 4.14 18/42] USB: serial: ftdi_sio: add device ID for Auto-M3 OP-COM v2 Greg Kroah-Hartman
2021-08-13 15:06 ` [PATCH 4.14 19/42] usb: gadget: f_hid: added GET_IDLE and SET_IDLE handlers Greg Kroah-Hartman
2021-08-13 15:06 ` [PATCH 4.14 20/42] usb: gadget: f_hid: fixed NULL pointer dereference Greg Kroah-Hartman
2021-08-13 15:06 ` [PATCH 4.14 21/42] usb: gadget: f_hid: idle uses the highest byte for duration Greg Kroah-Hartman
2021-08-13 15:06 ` [PATCH 4.14 22/42] usb: otg-fsm: Fix hrtimer list corruption Greg Kroah-Hartman
2021-08-13 15:06 ` [PATCH 4.14 23/42] scripts/tracing: fix the bug that cant parse raw_trace_func Greg Kroah-Hartman
2021-08-13 15:06 ` [PATCH 4.14 24/42] staging: rtl8723bs: Fix a resource leak in sd_int_dpc Greg Kroah-Hartman
2021-08-13 15:06 ` [PATCH 4.14 25/42] media: rtl28xxu: fix zero-length control request Greg Kroah-Hartman
2021-08-13 15:06 ` [PATCH 4.14 26/42] pipe: increase minimum default pipe size to 2 pages Greg Kroah-Hartman
2021-08-13 15:06 ` [PATCH 4.14 27/42] ext4: fix potential htree corruption when growing large_dir directories Greg Kroah-Hartman
2021-08-13 15:06 ` [PATCH 4.14 28/42] serial: 8250: Mask out floating 16/32-bit bus bits Greg Kroah-Hartman
2021-08-13 15:06 ` [PATCH 4.14 29/42] MIPS: Malta: Do not byte-swap accesses to the CBUS UART Greg Kroah-Hartman
2021-08-13 15:06 ` [PATCH 4.14 30/42] pcmcia: i82092: fix a null pointer dereference bug Greg Kroah-Hartman
2021-08-13 15:06 ` [PATCH 4.14 31/42] spi: meson-spicc: fix memory leak in meson_spicc_remove Greg Kroah-Hartman
2021-08-13 15:06 ` Greg Kroah-Hartman [this message]
2021-08-13 15:06 ` [PATCH 4.14 33/42] qmi_wwan: add network device usage statistics for qmimux devices Greg Kroah-Hartman
2021-08-13 15:07 ` [PATCH 4.14 34/42] libata: fix ata_pio_sector for CONFIG_HIGHMEM Greg Kroah-Hartman
2021-08-13 15:07 ` [PATCH 4.14 35/42] reiserfs: add check for root_inode in reiserfs_fill_super Greg Kroah-Hartman
2021-08-13 15:07 ` [PATCH 4.14 36/42] reiserfs: check directory items on read from disk Greg Kroah-Hartman
2021-08-13 15:07 ` [PATCH 4.14 37/42] alpha: Send stop IPI to send to online CPUs Greg Kroah-Hartman
2021-08-13 15:07 ` [PATCH 4.14 38/42] net/qla3xxx: fix schedule while atomic in ql_wait_for_drvr_lock and ql_adapter_reset Greg Kroah-Hartman
2021-08-13 15:07 ` [PATCH 4.14 39/42] USB:ehci:fix Kunpeng920 ehci hardware problem Greg Kroah-Hartman
2021-08-13 15:07 ` [PATCH 4.14 40/42] ppp: Fix generating ppp unit id when ifname is not specified Greg Kroah-Hartman
2021-08-13 15:07 ` [PATCH 4.14 41/42] ovl: prevent private clone if bind mount is not allowed Greg Kroah-Hartman
2021-08-13 15:07 ` [PATCH 4.14 42/42] net: xilinx_emaclite: Do not print real IOMEM pointer Greg Kroah-Hartman
2021-08-14 14:04 ` [PATCH 4.14 00/42] 4.14.244-rc1 review Naresh Kamboju
2021-08-14 18:14 ` Guenter Roeck
2021-08-16  3:01 ` Samuel Zou

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=20210813150526.179743749@linuxfoundation.org \
    --to=gregkh@linuxfoundation.org \
    --cc=kim.phillips@amd.com \
    --cc=liam.merwick@oracle.com \
    --cc=likexu@tencent.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=peterz@infradead.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