From: Nadav Amit <nadav.amit@gmail.com>
To: Rik van Riel <riel@surriel.com>, x86@kernel.org
Cc: linux-kernel@vger.kernel.org, bp@alien8.de, peterz@infradead.org,
dave.hansen@linux.intel.com, zhengqi.arch@bytedance.com,
thomas.lendacky@amd.com, kernel-team@meta.com,
linux-mm@kvack.org, akpm@linux-foundation.org, jannh@google.com,
mhklinux@outlook.com, andrew.cooper3@citrix.com
Subject: Re: [PATCH v5 10/12] x86,tlb: do targeted broadcast flushing from tlbbatch code
Date: Mon, 20 Jan 2025 16:14:49 +0200 [thread overview]
Message-ID: <2975f6a4-58ef-4499-b177-4b73ead4c670@gmail.com> (raw)
In-Reply-To: <4dcf2b4ecaede883e2c7f6af3db58a4f6afaf4ad.camel@surriel.com>
On 20/01/2025 16:02, Rik van Riel wrote:
> On Mon, 2025-01-20 at 11:56 +0200, Nadav Amit wrote:
>>
>>> @@ -1670,12 +1668,62 @@ void arch_tlbbatch_flush(struct
>>> arch_tlbflush_unmap_batch *batch)
>>> local_irq_enable();
>>> }
>>>
>>> + /*
>>> + * If we issued (asynchronous) INVLPGB flushes, wait for
>>> them here.
>>> + * The cpumask above contains only CPUs that were running
>>> tasks
>>> + * not using broadcast TLB flushing.
>>> + */
>>> + if (cpu_feature_enabled(X86_FEATURE_INVLPGB) && batch-
>>>> used_invlpgb) {
>>> + tlbsync();
>>> + migrate_enable();
>>
>> Maybe someone mentioned it before, but I would emphasize that I do
>> not
>> think that preventing migration for potentially long time is that
>> great.
>>
>> One alternative solution would be to set a bit on cpu_tlbstate, that
>> when set, you'd issue a tlbsync on context switch.
>>
>> (I can think about other solutions, but I think the one I just
>> mentioned
>> is the cleanest one).
>
> It is clean, but I'm not convinced it is good enough.
>
> We need to guarantee that the INVLPGBs have finished
> before we free the pages.
>
> Running a TLBSYNC at the next context switch could
> mean that TLBSYNC won't run until after the pages
> have been freed.
>
> In practice it is probably good enough, since it
> would be simpler for TLBSYNC to return once all
> pending (older) INVLPGBs have finished, but it's
> not architecturally guaranteed.
>
> We could send an IPI to remote CPUs in order for
> them to call TLBSYNC, but is that really better?
>
I am not sure we are on the same page. What I suggested is:
1. arch_tlbbatch_flush() would still do tlbsync()
2. No migrate_enable() in arch_tlbbatch_flush()
3. No migrate_disable() in arch_tlbbatch_add_pending()
4. arch_tlbbatch_add_pending() sets cpu_tlbstate.pending_tlb_broadcast
5. switch_mm_irqs_off() checks cpu_tlbstate.pending_tlb_broadcast and if
it is set performs tlbsync and clears it.
next prev parent reply other threads:[~2025-01-20 14:14 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-01-16 2:30 [PATCH v5 00/12] AMD broadcast TLB invalidation Rik van Riel
2025-01-16 2:30 ` [PATCH v5 01/12] x86/mm: make MMU_GATHER_RCU_TABLE_FREE unconditional Rik van Riel
2025-01-16 2:30 ` [PATCH v5 02/12] x86/mm: remove pv_ops.mmu.tlb_remove_table call Rik van Riel
2025-01-16 2:30 ` [PATCH v5 03/12] x86/mm: consolidate full flush threshold decision Rik van Riel
2025-01-17 19:23 ` Michael Kelley
2025-01-17 19:32 ` Rik van Riel
2025-01-16 2:30 ` [PATCH v5 04/12] x86/mm: get INVLPGB count max from CPUID Rik van Riel
2025-01-16 2:30 ` [PATCH v5 05/12] x86/mm: add INVLPGB support code Rik van Riel
2025-01-16 2:30 ` [PATCH v5 06/12] x86/mm: use INVLPGB for kernel TLB flushes Rik van Riel
2025-01-16 2:30 ` [PATCH v5 07/12] x86/tlb: use INVLPGB in flush_tlb_all Rik van Riel
2025-01-16 2:30 ` [PATCH v5 08/12] x86/mm: use broadcast TLB flushing for page reclaim TLB flushing Rik van Riel
2025-01-16 2:30 ` [PATCH v5 09/12] x86/mm: enable broadcast TLB invalidation for multi-threaded processes Rik van Riel
2025-01-16 2:30 ` [PATCH v5 10/12] x86,tlb: do targeted broadcast flushing from tlbbatch code Rik van Riel
2025-01-20 9:56 ` Nadav Amit
2025-01-20 14:02 ` Rik van Riel
2025-01-20 14:14 ` Nadav Amit [this message]
2025-01-20 16:11 ` Rik van Riel
2025-01-20 17:09 ` Nadav Amit
2025-01-20 17:11 ` Rik van Riel
2025-01-20 17:50 ` Nadav Amit
2025-01-20 17:56 ` Rik van Riel
2025-01-20 18:56 ` Nadav Amit
2025-01-21 2:33 ` Rik van Riel
2025-01-16 2:30 ` [PATCH v5 11/12] x86/mm: enable AMD translation cache extensions Rik van Riel
2025-01-16 2:30 ` [PATCH v5 12/12] x86/mm: only invalidate final translations with INVLPGB Rik van Riel
2025-01-16 18:14 ` [PATCH v5 00/12] AMD broadcast TLB invalidation Michael Kelley
2025-01-16 22:37 ` Peter Zijlstra
2025-01-17 0:00 ` Andrew Cooper
2025-01-21 10:45 ` Peter Zijlstra
2025-01-21 17:14 ` Dave Hansen
2025-01-21 21:24 ` Michael Kelley
2025-01-21 17:22 ` Jann Horn
2025-01-21 21:39 ` Michael Kelley
2025-01-21 21:56 ` Jann Horn
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=2975f6a4-58ef-4499-b177-4b73ead4c670@gmail.com \
--to=nadav.amit@gmail.com \
--cc=akpm@linux-foundation.org \
--cc=andrew.cooper3@citrix.com \
--cc=bp@alien8.de \
--cc=dave.hansen@linux.intel.com \
--cc=jannh@google.com \
--cc=kernel-team@meta.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mhklinux@outlook.com \
--cc=peterz@infradead.org \
--cc=riel@surriel.com \
--cc=thomas.lendacky@amd.com \
--cc=x86@kernel.org \
--cc=zhengqi.arch@bytedance.com \
/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