[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <173928636768.10177.18009351351852464312.tip-bot2@tip-bot2>
Date: Tue, 11 Feb 2025 15:06:07 -0000
From: "tip-bot2 for Dhananjay Ugwekar" <tip-bot2@...utronix.de>
To: linux-tip-commits@...r.kernel.org
Cc: Koichiro Den <koichiro.den@...onical.com>,
Dhananjay Ugwekar <dhananjay.ugwekar@....com>,
"Peter Zijlstra (Intel)" <peterz@...radead.org>, x86@...nel.org,
linux-kernel@...r.kernel.org
Subject: [tip: perf/urgent] perf/x86/rapl: Fix the error checking order
The following commit has been merged into the perf/urgent branch of tip:
Commit-ID: 469c76a83bb9f6b2c7b2989c46617c4fe01fee79
Gitweb: https://git.kernel.org/tip/469c76a83bb9f6b2c7b2989c46617c4fe01fee79
Author: Dhananjay Ugwekar <dhananjay.ugwekar@....com>
AuthorDate: Wed, 29 Jan 2025 08:05:14
Committer: Peter Zijlstra <peterz@...radead.org>
CommitterDate: Sat, 08 Feb 2025 15:47:25 +01:00
perf/x86/rapl: Fix the error checking order
After the commit b4943b8bfc41 ("perf/x86/rapl: Add core energy counter
support for AMD CPUs"), the default "perf record"/"perf top" command is
broken in systems where there isn't a PMU registered for type
PERF_TYPE_RAW.
This is due to the change in order of error checks in rapl_pmu_event_init()
Due to which we return -EINVAL instead of -ENOENT, when we reach here from
the fallback loop in perf_init_event().
Move the "PMU and event type match" back to the beginning of the function
so that we return -ENOENT early on.
Closes: https://lore.kernel.org/all/uv7mz6vew2bzgre5jdpmwldxljp5djzmuiksqdcdwipfm4zm7w@ribobcretidk/
Fixes: b4943b8bfc41 ("perf/x86/rapl: Add core energy counter support for AMD CPUs")
Reported-by: Koichiro Den <koichiro.den@...onical.com>
Signed-off-by: Dhananjay Ugwekar <dhananjay.ugwekar@....com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@...radead.org>
Link: https://lkml.kernel.org/r/20250129080513.30353-1-dhananjay.ugwekar@amd.com
---
arch/x86/events/rapl.c | 12 ++++--------
1 file changed, 4 insertions(+), 8 deletions(-)
diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c
index d3bb386..4952faf 100644
--- a/arch/x86/events/rapl.c
+++ b/arch/x86/events/rapl.c
@@ -370,6 +370,10 @@ static int rapl_pmu_event_init(struct perf_event *event)
unsigned int rapl_pmu_idx;
struct rapl_pmus *rapl_pmus;
+ /* only look at RAPL events */
+ if (event->attr.type != event->pmu->type)
+ return -ENOENT;
+
/* unsupported modes and filters */
if (event->attr.sample_period) /* no sampling */
return -EINVAL;
@@ -387,10 +391,6 @@ static int rapl_pmu_event_init(struct perf_event *event)
rapl_pmus_scope = rapl_pmus->pmu.scope;
if (rapl_pmus_scope == PERF_PMU_SCOPE_PKG || rapl_pmus_scope == PERF_PMU_SCOPE_DIE) {
- /* only look at RAPL package events */
- if (event->attr.type != rapl_pmus_pkg->pmu.type)
- return -ENOENT;
-
cfg = array_index_nospec((long)cfg, NR_RAPL_PKG_DOMAINS + 1);
if (!cfg || cfg >= NR_RAPL_PKG_DOMAINS + 1)
return -EINVAL;
@@ -398,10 +398,6 @@ static int rapl_pmu_event_init(struct perf_event *event)
bit = cfg - 1;
event->hw.event_base = rapl_model->rapl_pkg_msrs[bit].msr;
} else if (rapl_pmus_scope == PERF_PMU_SCOPE_CORE) {
- /* only look at RAPL core events */
- if (event->attr.type != rapl_pmus_core->pmu.type)
- return -ENOENT;
-
cfg = array_index_nospec((long)cfg, NR_RAPL_CORE_DOMAINS + 1);
if (!cfg || cfg >= NR_RAPL_PKG_DOMAINS + 1)
return -EINVAL;
Powered by blists - more mailing lists