From: Sasha Levin <sashal@kernel.org>
To: linux-kernel@vger.kernel.org, stable@vger.kernel.org
Cc: Stephane Eranian <eranian@google.com>,
Peter Zijlstra <peterz@infradead.org>,
Sasha Levin <sashal@kernel.org>,
mingo@redhat.com, acme@kernel.org, tglx@linutronix.de,
bp@alien8.de, dave.hansen@linux.intel.com, x86@kernel.org,
linux-perf-users@vger.kernel.org
Subject: [PATCH AUTOSEL 5.15 15/41] perf/x86/rapl: fix AMD event handling
Date: Thu, 3 Feb 2022 15:32:19 -0500 [thread overview]
Message-ID: <20220203203245.3007-15-sashal@kernel.org> (raw)
In-Reply-To: <20220203203245.3007-1-sashal@kernel.org>
From: Stephane Eranian <eranian@google.com>
[ Upstream commit 0036fb00a756a2f6e360d44e2e3d2200a8afbc9b ]
The RAPL events exposed under /sys/devices/power/events should only reflect
what the underlying hardware actually support. This is how it works on Intel
RAPL and Intel core/uncore PMUs in general.
But on AMD, this was not the case. All possible RAPL events were advertised.
This is what it showed on an AMD Fam17h:
$ ls /sys/devices/power/events/
energy-cores energy-gpu energy-pkg energy-psys
energy-ram energy-cores.scale energy-gpu.scale energy-pkg.scale
energy-psys.scale energy-ram.scale energy-cores.unit energy-gpu.unit
energy-pkg.unit energy-psys.unit energy-ram.unit
Yet, on AMD Fam17h, only energy-pkg is supported.
This patch fixes the problem. Given the way perf_msr_probe() works, the
amd_rapl_msrs[] table has to have all entries filled out and in particular
the group field, otherwise perf_msr_probe() defaults to making the event
visible.
With the patch applied, the kernel now only shows was is actually supported:
$ ls /sys/devices/power/events/
energy-pkg energy-pkg.scale energy-pkg.unit
The patch also uses the RAPL_MSR_MASK because only the 32-bits LSB of the
RAPL counters are relevant when reading power consumption.
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20220105185659.643355-1-eranian@google.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
arch/x86/events/rapl.c | 9 ++++++---
1 file changed, 6 insertions(+), 3 deletions(-)
diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c
index 85feafacc445d..77e3a47af5ad5 100644
--- a/arch/x86/events/rapl.c
+++ b/arch/x86/events/rapl.c
@@ -536,11 +536,14 @@ static struct perf_msr intel_rapl_spr_msrs[] = {
* - perf_msr_probe(PERF_RAPL_MAX)
* - want to use same event codes across both architectures
*/
-static struct perf_msr amd_rapl_msrs[PERF_RAPL_MAX] = {
- [PERF_RAPL_PKG] = { MSR_AMD_PKG_ENERGY_STATUS, &rapl_events_pkg_group, test_msr },
+static struct perf_msr amd_rapl_msrs[] = {
+ [PERF_RAPL_PP0] = { 0, &rapl_events_cores_group, 0, false, 0 },
+ [PERF_RAPL_PKG] = { MSR_AMD_PKG_ENERGY_STATUS, &rapl_events_pkg_group, test_msr, false, RAPL_MSR_MASK },
+ [PERF_RAPL_RAM] = { 0, &rapl_events_ram_group, 0, false, 0 },
+ [PERF_RAPL_PP1] = { 0, &rapl_events_gpu_group, 0, false, 0 },
+ [PERF_RAPL_PSYS] = { 0, &rapl_events_psys_group, 0, false, 0 },
};
-
static int rapl_cpu_offline(unsigned int cpu)
{
struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu);
--
2.34.1
next prev parent reply other threads:[~2022-02-03 20:34 UTC|newest]
Thread overview: 41+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-02-03 20:32 [PATCH AUTOSEL 5.15 01/41] NFS: change nfs_access_get_cached to only report the mask Sasha Levin
2022-02-03 20:32 ` [PATCH AUTOSEL 5.15 02/41] NFSv4 only print the label when its queried Sasha Levin
2022-02-03 20:32 ` [PATCH AUTOSEL 5.15 03/41] nfs: nfs4clinet: check the return value of kstrdup() Sasha Levin
2022-02-03 20:32 ` [PATCH AUTOSEL 5.15 04/41] NFSv4.1: Fix uninitialised variable in devicenotify Sasha Levin
2022-02-03 20:32 ` [PATCH AUTOSEL 5.15 05/41] netfilter: nf_conntrack_netbios_ns: fix helper module alias Sasha Levin
2022-02-03 20:32 ` [PATCH AUTOSEL 5.15 06/41] NFSv4 remove zero number of fs_locations entries error check Sasha Levin
2022-02-03 20:32 ` [PATCH AUTOSEL 5.15 07/41] NFSv4 store server support for fs_location attribute Sasha Levin
2022-02-03 20:32 ` [PATCH AUTOSEL 5.15 08/41] NFSv4.1 query for fs_location attr on a new file system Sasha Levin
2022-02-03 20:32 ` [PATCH AUTOSEL 5.15 09/41] NFSv4 expose nfs_parse_server_name function Sasha Levin
2022-02-03 20:32 ` [PATCH AUTOSEL 5.15 10/41] NFSv4 handle port presence in fs_location server string Sasha Levin
2022-02-03 20:32 ` [PATCH AUTOSEL 5.15 11/41] SUNRPC allow for unspecified transport time in rpc_clnt_add_xprt Sasha Levin
2022-02-03 20:32 ` [PATCH AUTOSEL 5.15 12/41] net/sunrpc: fix reference count leaks in rpc_sysfs_xprt_state_change Sasha Levin
2022-02-03 20:32 ` [PATCH AUTOSEL 5.15 13/41] sunrpc: Fix potential race conditions in rpc_sysfs_xprt_state_change() Sasha Levin
2022-02-03 20:32 ` [PATCH AUTOSEL 5.15 14/41] irqchip/realtek-rtl: Service all pending interrupts Sasha Levin
2022-02-03 20:32 ` Sasha Levin [this message]
2022-02-03 20:32 ` [PATCH AUTOSEL 5.15 16/41] x86/perf: Avoid warning for Arch LBR without XSAVE Sasha Levin
2022-02-03 20:32 ` [PATCH AUTOSEL 5.15 17/41] sched/pelt: Relax the sync of runnable_sum with runnable_avg Sasha Levin
2022-02-03 20:32 ` [PATCH AUTOSEL 5.15 18/41] sched: Avoid double preemption in __cond_resched_*lock*() Sasha Levin
2022-02-03 20:32 ` [PATCH AUTOSEL 5.15 19/41] drm/vc4: Fix deadlock on DSI device attach error Sasha Levin
2022-02-03 20:32 ` [PATCH AUTOSEL 5.15 20/41] drm: panel-orientation-quirks: Add quirk for the 1Netbook OneXPlayer Sasha Levin
2022-02-03 20:32 ` [PATCH AUTOSEL 5.15 21/41] net: sched: Clarify error message when qdisc kind is unknown Sasha Levin
2022-02-03 20:32 ` [PATCH AUTOSEL 5.15 22/41] powerpc/fixmap: Fix VM debug warning on unmap Sasha Levin
2022-02-03 20:32 ` [PATCH AUTOSEL 5.15 23/41] scsi: target: iscsi: Make sure the np under each tpg is unique Sasha Levin
2022-02-03 20:32 ` [PATCH AUTOSEL 5.15 24/41] scsi: ufs: ufshcd-pltfrm: Check the return value of devm_kstrdup() Sasha Levin
2022-02-03 20:32 ` [PATCH AUTOSEL 5.15 25/41] scsi: qedf: Add stag_work to all the vports Sasha Levin
2022-02-03 20:32 ` [PATCH AUTOSEL 5.15 26/41] scsi: qedf: Fix refcount issue when LOGO is received during TMF Sasha Levin
2022-02-03 20:32 ` [PATCH AUTOSEL 5.15 27/41] scsi: qedf: Change context reset messages to ratelimited Sasha Levin
2022-02-03 20:32 ` [PATCH AUTOSEL 5.15 28/41] scsi: pm8001: Fix bogus FW crash for maxcpus=1 Sasha Levin
2022-02-03 20:32 ` [PATCH AUTOSEL 5.15 29/41] scsi: ufs: Use generic error code in ufshcd_set_dev_pwr_mode() Sasha Levin
2022-02-03 20:32 ` [PATCH AUTOSEL 5.15 30/41] scsi: ufs: Treat link loss as fatal error Sasha Levin
2022-02-03 20:32 ` [PATCH AUTOSEL 5.15 31/41] scsi: myrs: Fix crash in error case Sasha Levin
2022-02-03 20:32 ` [PATCH AUTOSEL 5.15 32/41] net: stmmac: reduce unnecessary wakeups from eee sw timer Sasha Levin
2022-02-03 20:32 ` [PATCH AUTOSEL 5.15 33/41] PM: wakeup: simplify the output logic of pm_show_wakelocks() Sasha Levin
2022-02-03 20:32 ` [PATCH AUTOSEL 5.15 34/41] PM: hibernate: Remove register_nosave_region_late() Sasha Levin
2022-02-03 20:32 ` [PATCH AUTOSEL 5.15 35/41] drm/amd/display: Correct MPC split policy for DCN301 Sasha Levin
2022-02-03 20:32 ` [PATCH AUTOSEL 5.15 36/41] usb: dwc2: gadget: don't try to disable ep0 in dwc2_hsotg_suspend Sasha Levin
2022-02-03 20:32 ` [PATCH AUTOSEL 5.15 37/41] perf: Always wake the parent event Sasha Levin
2022-02-03 20:32 ` [PATCH AUTOSEL 5.15 38/41] nvme-pci: add the IGNORE_DEV_SUBNQN quirk for Intel P4500/P4600 SSDs Sasha Levin
2022-02-03 20:32 ` [PATCH AUTOSEL 5.15 39/41] MIPS: Fix build error due to PTR used in more places Sasha Levin
2022-02-03 20:32 ` [PATCH AUTOSEL 5.15 40/41] net: stmmac: dwmac-sun8i: use return val of readl_poll_timeout() Sasha Levin
2022-02-03 20:32 ` [PATCH AUTOSEL 5.15 41/41] block: add bio_start_io_acct_time() to control start_time Sasha Levin
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=20220203203245.3007-15-sashal@kernel.org \
--to=sashal@kernel.org \
--cc=acme@kernel.org \
--cc=bp@alien8.de \
--cc=dave.hansen@linux.intel.com \
--cc=eranian@google.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-perf-users@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=peterz@infradead.org \
--cc=stable@vger.kernel.org \
--cc=tglx@linutronix.de \
--cc=x86@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