linux-arch.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Lance Yang <lance.yang@linux.dev>
To: akpm@linux-foundation.org
Cc: will@kernel.org, aneesh.kumar@kernel.org, npiggin@gmail.com,
	peterz@infradead.org, tglx@linutronix.de, mingo@redhat.com,
	bp@alien8.de, dave.hansen@linux.intel.com, x86@kernel.org,
	hpa@zytor.com, arnd@arndb.de, david@kernel.org,
	lorenzo.stoakes@oracle.com, ziy@nvidia.com,
	baolin.wang@linux.alibaba.com, Liam.Howlett@oracle.com,
	npache@redhat.com, ryan.roberts@arm.com, dev.jain@arm.com,
	baohua@kernel.org, ioworker0@gmail.com, shy828301@gmail.com,
	riel@surriel.com, jannh@google.com, linux-arch@vger.kernel.org,
	linux-mm@kvack.org, linux-kernel@vger.kernel.org,
	Lance Yang <lance.yang@linux.dev>
Subject: [PATCH RESEND v1 2/3] x86/mm: implement redundant IPI elimination for page table operations
Date: Mon, 29 Dec 2025 22:36:56 +0800	[thread overview]
Message-ID: <20251229143657.76968-3-lance.yang@linux.dev> (raw)
In-Reply-To: <20251229143657.76968-1-lance.yang@linux.dev>

From: Lance Yang <lance.yang@linux.dev>

Add a callback function flush_tlb_multi_implies_ipi_broadcast to pv_mmu_ops
to explicitly track whether flush_tlb_multi IPIs provide sufficient
synchronization for GUP-fast when freeing or unsharing page tables.

Pass both freed_tables and unshared_tables to flush_tlb_mm_range() to
ensure lazy-TLB CPUs receive IPIs and flush their paging-structure caches:
	flush_tlb_mm_range(..., freed_tables || unshared_tables);

Suggested-by: David Hildenbrand (Red Hat) <david@kernel.org>
Signed-off-by: Lance Yang <lance.yang@linux.dev>
---
 arch/x86/include/asm/paravirt_types.h |  6 ++++++
 arch/x86/include/asm/tlb.h            | 19 ++++++++++++++++++-
 arch/x86/kernel/paravirt.c            | 10 ++++++++++
 3 files changed, 34 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 3502939415ad..a5bd0983da1f 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -133,6 +133,12 @@ struct pv_mmu_ops {
 	void (*flush_tlb_multi)(const struct cpumask *cpus,
 				const struct flush_tlb_info *info);
 
+	/*
+	 * Indicates whether flush_tlb_multi IPIs provide sufficient
+	 * synchronization for GUP-fast when freeing or unsharing page tables.
+	 */
+	bool (*flush_tlb_multi_implies_ipi_broadcast)(void);
+
 	/* Hook for intercepting the destruction of an mm_struct. */
 	void (*exit_mmap)(struct mm_struct *mm);
 	void (*notify_page_enc_status_changed)(unsigned long pfn, int npages, bool enc);
diff --git a/arch/x86/include/asm/tlb.h b/arch/x86/include/asm/tlb.h
index 866ea78ba156..3a7cdfdcea8e 100644
--- a/arch/x86/include/asm/tlb.h
+++ b/arch/x86/include/asm/tlb.h
@@ -5,10 +5,26 @@
 #define tlb_flush tlb_flush
 static inline void tlb_flush(struct mmu_gather *tlb);
 
+#define tlb_table_flush_implies_ipi_broadcast tlb_table_flush_implies_ipi_broadcast
+static inline bool tlb_table_flush_implies_ipi_broadcast(void);
+
 #include <asm-generic/tlb.h>
 #include <linux/kernel.h>
 #include <vdso/bits.h>
 #include <vdso/page.h>
+#include <asm/paravirt.h>
+
+static inline bool tlb_table_flush_implies_ipi_broadcast(void)
+{
+#ifdef CONFIG_PARAVIRT
+	if (pv_ops.mmu.flush_tlb_multi_implies_ipi_broadcast)
+		return pv_ops.mmu.flush_tlb_multi_implies_ipi_broadcast();
+
+	return false;
+#else
+	return !cpu_feature_enabled(X86_FEATURE_INVLPGB);
+#endif
+}
 
 static inline void tlb_flush(struct mmu_gather *tlb)
 {
@@ -20,7 +36,8 @@ static inline void tlb_flush(struct mmu_gather *tlb)
 		end = tlb->end;
 	}
 
-	flush_tlb_mm_range(tlb->mm, start, end, stride_shift, tlb->freed_tables);
+	flush_tlb_mm_range(tlb->mm, start, end, stride_shift,
+			   tlb->freed_tables || tlb->unshared_tables);
 }
 
 static inline void invlpg(unsigned long addr)
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index ab3e172dcc69..4eaa44800b39 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -60,6 +60,15 @@ void __init native_pv_lock_init(void)
 		static_branch_enable(&virt_spin_lock_key);
 }
 
+static bool native_flush_tlb_multi_implies_ipi_broadcast(void)
+{
+	/* Paravirt may use hypercalls that don't send real IPIs. */
+	if (pv_ops.mmu.flush_tlb_multi != native_flush_tlb_multi)
+		return false;
+
+	return !cpu_feature_enabled(X86_FEATURE_INVLPGB);
+}
+
 struct static_key paravirt_steal_enabled;
 struct static_key paravirt_steal_rq_enabled;
 
@@ -173,6 +182,7 @@ struct paravirt_patch_template pv_ops = {
 	.mmu.flush_tlb_kernel	= native_flush_tlb_global,
 	.mmu.flush_tlb_one_user	= native_flush_tlb_one_user,
 	.mmu.flush_tlb_multi	= native_flush_tlb_multi,
+	.mmu.flush_tlb_multi_implies_ipi_broadcast = native_flush_tlb_multi_implies_ipi_broadcast,
 
 	.mmu.exit_mmap		= paravirt_nop,
 	.mmu.notify_page_enc_status_changed	= paravirt_nop,
-- 
2.49.0


  parent reply	other threads:[~2025-12-29 14:38 UTC|newest]

Thread overview: 5+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-12-29 14:36 [PATCH RESEND v1 0/3] skip redundant TLB sync IPIs Lance Yang
2025-12-29 14:36 ` [PATCH RESEND v1 1/3] mm/tlb: allow architectures to " Lance Yang
2025-12-29 14:36 ` Lance Yang [this message]
2025-12-29 14:36 ` [PATCH RESEND v1 3/3] mm: embed TLB flush IPI check in tlb_remove_table_sync_one() Lance Yang
  -- strict thread matches above, loose matches on Subject: below --
2025-12-29 14:30 [PATCH RESEND v1 0/3] skip redundant TLB sync IPIs Lance Yang
2025-12-29 14:30 ` [PATCH RESEND v1 2/3] x86/mm: implement redundant IPI elimination for page table operations Lance Yang

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=20251229143657.76968-3-lance.yang@linux.dev \
    --to=lance.yang@linux.dev \
    --cc=Liam.Howlett@oracle.com \
    --cc=akpm@linux-foundation.org \
    --cc=aneesh.kumar@kernel.org \
    --cc=arnd@arndb.de \
    --cc=baohua@kernel.org \
    --cc=baolin.wang@linux.alibaba.com \
    --cc=bp@alien8.de \
    --cc=dave.hansen@linux.intel.com \
    --cc=david@kernel.org \
    --cc=dev.jain@arm.com \
    --cc=hpa@zytor.com \
    --cc=ioworker0@gmail.com \
    --cc=jannh@google.com \
    --cc=linux-arch@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=lorenzo.stoakes@oracle.com \
    --cc=mingo@redhat.com \
    --cc=npache@redhat.com \
    --cc=npiggin@gmail.com \
    --cc=peterz@infradead.org \
    --cc=riel@surriel.com \
    --cc=ryan.roberts@arm.com \
    --cc=shy828301@gmail.com \
    --cc=tglx@linutronix.de \
    --cc=will@kernel.org \
    --cc=x86@kernel.org \
    --cc=ziy@nvidia.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).