linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Rik van Riel <riel@surriel.com>
To: x86@kernel.org
Cc: linux-kernel@vger.kernel.org, kernel-team@meta.com,
	dave.hansen@linux.intel.com, luto@kernel.org,
	peterz@infradead.org, tglx@linutronix.de, mingo@redhat.com,
	bp@alien8.de, hpa@zytor.com, akpm@linux-foundation.org,
	nadav.amit@gmail.com, zhengqi.arch@bytedance.com,
	linux-mm@kvack.org, Rik van Riel <riel@surriel.com>
Subject: [PATCH 08/12] x86/mm: use broadcast TLB flushing for page reclaim TLB flushing
Date: Mon, 30 Dec 2024 12:53:09 -0500	[thread overview]
Message-ID: <20241230175550.4046587-9-riel@surriel.com> (raw)
In-Reply-To: <20241230175550.4046587-1-riel@surriel.com>

In the page reclaim code, we only track the CPU(s) where the TLB needs
to be flushed, rather than all the individual mappings that may be getting
invalidated.

Use broadcast TLB flushing when that is available.

Signed-off-by: Rik van Riel <riel@surriel.com>
---
 arch/x86/mm/tlb.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 266d5174fc7b..64f1679c37e1 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -1310,8 +1310,16 @@ EXPORT_SYMBOL_GPL(__flush_tlb_all);
 void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
 {
 	struct flush_tlb_info *info;
+	int cpu;
+
+	if (cpu_feature_enabled(X86_FEATURE_INVLPGB)) {
+		guard(preempt)();
+		invlpgb_flush_all_nonglobals();
+		tlbsync();
+		return;
+	}
 
-	int cpu = get_cpu();
+	cpu = get_cpu();
 
 	info = get_flush_tlb_info(NULL, 0, TLB_FLUSH_ALL, 0, false,
 				  TLB_GENERATION_INVALID);
-- 
2.47.1



  parent reply	other threads:[~2024-12-30 17:57 UTC|newest]

Thread overview: 89+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-12-30 17:53 [PATCH v3 00/12] AMD broadcast TLB invalidation Rik van Riel
2024-12-30 17:53 ` [PATCH 01/12] x86/mm: make MMU_GATHER_RCU_TABLE_FREE unconditional Rik van Riel
2024-12-30 18:41   ` Borislav Petkov
2024-12-31 16:11     ` Rik van Riel
2024-12-31 16:19       ` Borislav Petkov
2024-12-31 16:30         ` Rik van Riel
2025-01-02 11:52           ` Borislav Petkov
2025-01-02 19:56       ` Peter Zijlstra
2025-01-03 12:18         ` Borislav Petkov
2025-01-04 16:27           ` Peter Zijlstra
2025-01-06 15:54             ` Dave Hansen
2025-01-06 15:47           ` Rik van Riel
2024-12-30 17:53 ` [PATCH 02/12] x86/mm: remove pv_ops.mmu.tlb_remove_table call Rik van Riel
2024-12-31  3:18   ` Qi Zheng
2024-12-30 17:53 ` [PATCH 03/12] x86/mm: add X86_FEATURE_INVLPGB definition Rik van Riel
2025-01-02 12:04   ` Borislav Petkov
2025-01-03 18:27     ` Rik van Riel
2025-01-03 21:07       ` Borislav Petkov
2024-12-30 17:53 ` [PATCH 04/12] x86/mm: get INVLPGB count max from CPUID Rik van Riel
2025-01-02 12:15   ` Borislav Petkov
2025-01-10 18:44   ` Tom Lendacky
2025-01-10 20:27     ` Rik van Riel
2025-01-10 20:31       ` Tom Lendacky
2025-01-10 20:34       ` Borislav Petkov
2024-12-30 17:53 ` [PATCH 05/12] x86/mm: add INVLPGB support code Rik van Riel
2025-01-02 12:42   ` Borislav Petkov
2025-01-06 16:50     ` Dave Hansen
2025-01-06 17:32       ` Rik van Riel
2025-01-06 18:14       ` Borislav Petkov
2025-01-14 19:50     ` Rik van Riel
2025-01-03 12:44   ` Borislav Petkov
2024-12-30 17:53 ` [PATCH 06/12] x86/mm: use INVLPGB for kernel TLB flushes Rik van Riel
2025-01-03 12:39   ` Borislav Petkov
2025-01-06 17:21   ` Dave Hansen
2025-01-09 20:16     ` Rik van Riel
2025-01-09 21:18       ` Dave Hansen
2025-01-10  5:31         ` Rik van Riel
2025-01-10  6:07         ` Nadav Amit
2025-01-10 15:14           ` Dave Hansen
2025-01-10 16:08             ` Rik van Riel
2025-01-10 16:29               ` Dave Hansen
2025-01-10 16:36                 ` Rik van Riel
2025-01-10 18:53   ` Tom Lendacky
2025-01-10 20:29     ` Rik van Riel
2024-12-30 17:53 ` [PATCH 07/12] x86/tlb: use INVLPGB in flush_tlb_all Rik van Riel
2025-01-06 17:29   ` Dave Hansen
2025-01-06 17:35     ` Rik van Riel
2025-01-06 17:54       ` Dave Hansen
2024-12-30 17:53 ` Rik van Riel [this message]
2024-12-30 17:53 ` [PATCH 09/12] x86/mm: enable broadcast TLB invalidation for multi-threaded processes Rik van Riel
2024-12-30 19:24   ` Nadav Amit
2025-01-01  4:42     ` Rik van Riel
2025-01-01 15:20       ` Nadav Amit
2025-01-01 16:15         ` Karim Manaouil
2025-01-01 16:23           ` Rik van Riel
2025-01-02  0:06             ` Nadav Amit
2025-01-03 17:36   ` Jann Horn
2025-01-04  2:55     ` Rik van Riel
2025-01-06 13:04       ` Jann Horn
2025-01-06 14:26         ` Rik van Riel
2025-01-06 14:52   ` Nadav Amit
2025-01-06 16:03     ` Rik van Riel
2025-01-06 18:40   ` Dave Hansen
2025-01-12  2:36     ` Rik van Riel
2024-12-30 17:53 ` [PATCH 10/12] x86,tlb: do targeted broadcast flushing from tlbbatch code Rik van Riel
2024-12-30 17:53 ` [PATCH 11/12] x86/mm: enable AMD translation cache extensions Rik van Riel
2024-12-30 18:25   ` Nadav Amit
2024-12-30 18:27     ` Rik van Riel
2025-01-03 17:49   ` Jann Horn
2025-01-04  3:08     ` Rik van Riel
2025-01-06 13:10       ` Jann Horn
2025-01-06 18:29         ` Sean Christopherson
2025-01-10 19:34   ` Tom Lendacky
2025-01-10 19:45     ` Rik van Riel
2025-01-10 19:58       ` Borislav Petkov
2025-01-10 20:43         ` Rik van Riel
2024-12-30 17:53 ` [PATCH 12/12] x86/mm: only invalidate final translations with INVLPGB Rik van Riel
2025-01-03 18:40   ` Jann Horn
2025-01-12  2:39     ` Rik van Riel
2025-01-06 19:03 ` [PATCH v3 00/12] AMD broadcast TLB invalidation Dave Hansen
2025-01-12  2:46   ` Rik van Riel
2025-01-06 22:49 ` Yosry Ahmed
2025-01-07  3:25   ` Rik van Riel
2025-01-08  1:36     ` Yosry Ahmed
2025-01-09  2:25       ` Andrew Cooper
2025-01-09  2:47       ` Andrew Cooper
2025-01-09 21:32         ` Yosry Ahmed
2025-01-09 23:00           ` Andrew Cooper
2025-01-09 23:26             ` Yosry Ahmed

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=20241230175550.4046587-9-riel@surriel.com \
    --to=riel@surriel.com \
    --cc=akpm@linux-foundation.org \
    --cc=bp@alien8.de \
    --cc=dave.hansen@linux.intel.com \
    --cc=hpa@zytor.com \
    --cc=kernel-team@meta.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=luto@kernel.org \
    --cc=mingo@redhat.com \
    --cc=nadav.amit@gmail.com \
    --cc=peterz@infradead.org \
    --cc=tglx@linutronix.de \
    --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;
as well as URLs for NNTP newsgroup(s).