[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20241109003727.3958374-3-riel@surriel.com>
Date: Fri, 8 Nov 2024 19:27:49 -0500
From: Rik van Riel <riel@...riel.com>
To: linux-kernel@...r.kernel.org
Cc: dave.hansen@...ux.intel.com,
luto@...nel.org,
peterz@...radead.org,
tglx@...utronix.de,
mingo@...hat.com,
bp@...en8.de,
x86@...nel.org,
kernel-team@...a.com,
hpa@...or.com,
Rik van Riel <riel@...riel.com>,
Dave Hansen <dave.hansen@...el.com>
Subject: [PATCH 2/3] x86,tlb: add tracepoint for TLB flush IPI to stale CPU
Add a tracepoint when we send a TLB flush IPI to a CPU that used
to be in the mm_cpumask, but isn't any more.
This can be used to evaluate whether there any workloads where
we end up in this path problematically often. Hopefully they
don't exist.
Suggested-by: Dave Hansen <dave.hansen@...el.com>
Signed-off-by: Rik van Riel <riel@...riel.com>
---
arch/x86/mm/tlb.c | 1 +
include/linux/mm_types.h | 1 +
2 files changed, 2 insertions(+)
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index f19f6378cabf..9d0d34576928 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -760,6 +760,7 @@ static void flush_tlb_func(void *info)
/* Can only happen on remote CPUs */
if (f->mm && f->mm != loaded_mm) {
cpumask_clear_cpu(raw_smp_processor_id(), mm_cpumask(f->mm));
+ trace_tlb_flush(TLB_REMOTE_WRONG_CPU, 0);
return;
}
}
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 6e3bdf8e38bc..6b6f05404304 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -1335,6 +1335,7 @@ enum tlb_flush_reason {
TLB_LOCAL_SHOOTDOWN,
TLB_LOCAL_MM_SHOOTDOWN,
TLB_REMOTE_SEND_IPI,
+ TLB_REMOTE_WRONG_CPU,
NR_TLB_FLUSH_REASONS,
};
--
2.45.2
Powered by blists - more mailing lists