From: Magnus Lindholm <linmag7@gmail.com>
To: richard.henderson@linaro.org, mattst88@gmail.com,
linux-kernel@vger.kernel.org, linux-alpha@vger.kernel.org
Cc: glaubitz@physik.fu-berlin.de, mcree@orcon.net.nz,
ink@unseen.parts, macro@orcam.me.uk,
Magnus Lindholm <linmag7@gmail.com>
Subject: [PATCH 5/6] alpha: invalidate the local context in flush_tlb_mm()
Date: Sun, 9 Aug 2026 10:49:37 +0200 [thread overview]
Message-ID: <20260809085208.3262799-6-linmag7@gmail.com> (raw)
In-Reply-To: <20260809085208.3262799-1-linmag7@gmail.com>
The SMP flush_tlb_mm() only touches the calling CPU when the mm is its
active_mm:
if (mm == current->active_mm) {
flush_tlb_current(mm);
...
}
smp_call_function(ipi_flush_tlb_mm, mm, 1);
If it is not, nothing happens locally at all: smp_call_function() does not
call back into the caller. mm->context[cpu] is left valid, so this CPU
may later reuse the old ASN, and any translations it still holds for MM
stay usable.
Callers reach this regularly - counting the branch gave 2934 such calls
over a fork-heavy workload and 632 while otherwise idle.
Add the missing else. The UP implementation in asm/tlbflush.h already has
exactly this shape:
if (mm == current->active_mm)
flush_tlb_current(mm);
else
flush_tlb_other(mm);
Unlike flush_tlb_page(), the active_mm test itself is valid here:
flush_tlb_current() calls __load_new_mm_context(), which allocates and
loads a fresh context rather than relying on a targeted tbi() to operate
on whatever ASN happened to be loaded beforehand.
Signed-off-by: Magnus Lindholm <linmag7@gmail.com>
---
arch/alpha/kernel/smp.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/arch/alpha/kernel/smp.c b/arch/alpha/kernel/smp.c
index d167b3ba1303..f501a91001cc 100644
--- a/arch/alpha/kernel/smp.c
+++ b/arch/alpha/kernel/smp.c
@@ -649,6 +649,13 @@ flush_tlb_mm(struct mm_struct *mm)
preempt_enable();
return;
}
+ } else {
+ /*
+ * smp_call_function() below does not call back into this
+ * CPU, so this is the only chance to retire what it holds
+ * for MM. The UP implementation already does this.
+ */
+ flush_tlb_other(mm);
}
smp_call_function(ipi_flush_tlb_mm, mm, 1);
--
2.53.0
next prev parent reply other threads:[~2026-08-09 8:55 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-08-09 8:49 [PATCH 0/6] alpha: fix stale TLB translations breaking copy-on-write and writeback Magnus Lindholm
2026-08-09 8:49 ` [PATCH 1/6] alpha: run check_mmu_context() from finish_arch_post_lock_switch() Magnus Lindholm
2026-08-10 2:37 ` Matt Turner
2026-08-10 2:40 ` Matt Turner
2026-08-10 6:15 ` Magnus Lindholm
2026-08-09 8:49 ` [PATCH 2/6] alpha: only use a targeted tbi() when the target mm is really current Magnus Lindholm
2026-08-09 8:49 ` [PATCH 3/6] alpha: fix the local TLB invalidate in flush_tlb_page() Magnus Lindholm
2026-08-10 2:43 ` Matt Turner
2026-08-10 6:26 ` Magnus Lindholm
2026-08-09 8:49 ` [PATCH 4/6] alpha: only use a targeted tbi() when the target mm is really current (UP) Magnus Lindholm
2026-08-10 2:45 ` Matt Turner
2026-08-10 6:42 ` Magnus Lindholm
2026-08-09 8:49 ` Magnus Lindholm [this message]
2026-08-09 8:49 ` [PATCH 6/6] alpha: invalidate the local context in flush_icache_user_page() Magnus Lindholm
2026-08-10 3:03 ` Matt Turner
2026-08-10 6:11 ` Magnus Lindholm
2026-08-10 2:35 ` [PATCH 0/6] alpha: fix stale TLB translations breaking copy-on-write and writeback Matt Turner
2026-08-10 7:24 ` Magnus Lindholm
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=20260809085208.3262799-6-linmag7@gmail.com \
--to=linmag7@gmail.com \
--cc=glaubitz@physik.fu-berlin.de \
--cc=ink@unseen.parts \
--cc=linux-alpha@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=macro@orcam.me.uk \
--cc=mattst88@gmail.com \
--cc=mcree@orcon.net.nz \
--cc=richard.henderson@linaro.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