[PATCH AUTOSEL 6.6 17/18] drivers/perf: riscv: Reset the counter to hpmevent mapping while starting cpus

Sasha Levin sashal at kernel.org
Tue Jul 16 07:26:52 PDT 2024


From: Samuel Holland <samuel.holland at sifive.com>

[ Upstream commit 7dd646cf745c34d31e7ed2a52265e9ca8308f58f ]

Currently, we stop all the counters while a new cpu is brought online.
However, the hpmevent to counter mappings are not reset. The firmware may
have some stale encoding in their mapping structure which may lead to
undesirable results. We have not encountered such scenario though.

Signed-off-by: Samuel Holland <samuel.holland at sifive.com>
Signed-off-by: Atish Patra <atishp at rivosinc.com>
Link: https://lore.kernel.org/r/20240628-misc_perf_fixes-v4-2-e01cfddcf035@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer at rivosinc.com>
Signed-off-by: Sasha Levin <sashal at kernel.org>
---
 drivers/perf/riscv_pmu_sbi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c
index d80b4b09152df..ae16ecb15f2d9 100644
--- a/drivers/perf/riscv_pmu_sbi.c
+++ b/drivers/perf/riscv_pmu_sbi.c
@@ -611,7 +611,7 @@ static inline void pmu_sbi_stop_all(struct riscv_pmu *pmu)
 	 * which may include counters that are not enabled yet.
 	 */
 	sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_STOP,
-		  0, pmu->cmask, 0, 0, 0, 0);
+		  0, pmu->cmask, SBI_PMU_STOP_FLAG_RESET, 0, 0, 0);
 }
 
 static inline void pmu_sbi_stop_hw_ctrs(struct riscv_pmu *pmu)
-- 
2.43.0




More information about the linux-riscv mailing list