Linux-mm Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: James Houghton <jthoughton@google.com>
To: Will Deacon <will@kernel.org>,
	Catalin Marinas <catalin.marinas@arm.com>,
	 Muchun Song <muchun.song@linux.dev>,
	Oscar Salvador <osalvador@suse.de>
Cc: Nikos Nikoleris <nikos.nikoleris@arm.com>,
	Linu Cherian <linu.cherian@arm.com>,
	 Mark Rutland <mark.rutland@arm.com>,
	David Hildenbrand <david@kernel.org>,
	 Andrew Morton <akpm@linux-foundation.org>,
	Ryan Roberts <ryan.roberts@arm.com>,
	 Nanyong Sun <sunnanyong@huawei.com>, Yu Zhao <yuzhao@google.com>,
	 Frank van der Linden <fvdl@google.com>,
	David Rientjes <rientjes@google.com>,
	 James Houghton <jthoughton@google.com>,
	linux-kernel@vger.kernel.org,
	 linux-arm-kernel@lists.infradead.org, linux-mm@kvack.org
Subject: [PATCH 11/18] hugetlb_vmemmap: Use try_populate_vmemmap_pmd for replacing in-use PMDs
Date: Wed,  8 Jul 2026 03:11:21 +0000	[thread overview]
Message-ID: <20260708031129.3503195-12-jthoughton@google.com> (raw)
In-Reply-To: <20260708031129.3503195-1-jthoughton@google.com>

This routine is to be used for updating in-use, leaf-level PMDs in the
vmemmap without introducing a window where vmemmap accesses might fault.

Because try_populate_vmemmap_pmd() can fail, the split_page() call needs
to be moved to after the PMD update. Because both split_page() and the
PMD update are done under the page table lock, this rearrangement is
safe.

Only leaf-level PMD to non-leaf PMD (mapping the same physical pages) is
the only transition that needs to be supported.

Collapsing a non-leaf PMD to a leaf-level PMD is not used by HVO, so
try_populate_vmemmap_pmd() need not support it.

This patch allows arm64's implementation to replaced with one that does
not require BBML2_NOABORT.

Signed-off-by: James Houghton <jthoughton@google.com>
---
 arch/arm64/include/asm/pgalloc.h     |  9 +++++++++
 arch/loongarch/include/asm/pgalloc.h |  8 ++++++++
 arch/riscv/include/asm/pgalloc.h     |  8 ++++++++
 arch/x86/include/asm/pgalloc.h       |  8 ++++++++
 include/linux/pgalloc.h              | 20 ++++++++++++++++++++
 mm/hugetlb_vmemmap.c                 | 28 ++++++++++++++++------------
 6 files changed, 69 insertions(+), 12 deletions(-)

diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h
index 1b4509d3382c..c8946250d431 100644
--- a/arch/arm64/include/asm/pgalloc.h
+++ b/arch/arm64/include/asm/pgalloc.h
@@ -121,4 +121,13 @@ pmd_populate(struct mm_struct *mm, pmd_t *pmdp, pgtable_t ptep)
 		       PMD_TYPE_TABLE | PMD_TABLE_AF | PMD_TABLE_PXN);
 }
 
+#define __HAVE_ARCH_TRY_POPULATE_VMEMMAP_PMD
+static inline int try_populate_vmemmap_pmd(pmd_t *pmdp, pte_t *pgtable,
+					   unsigned long addr)
+{
+	/* BBML2_NOABORT is required. Its presence has been checked. */
+	pmd_populate_kernel(&init_mm, pmdp, pgtable);
+	return 0;
+}
+
 #endif
diff --git a/arch/loongarch/include/asm/pgalloc.h b/arch/loongarch/include/asm/pgalloc.h
index 248f62d0b590..9322d962c9cc 100644
--- a/arch/loongarch/include/asm/pgalloc.h
+++ b/arch/loongarch/include/asm/pgalloc.h
@@ -24,6 +24,14 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, pgtable_t pte)
 	set_pmd(pmd, __pmd((unsigned long)page_address(pte)));
 }
 
+#define __HAVE_ARCH_TRY_POPULATE_VMEMMAP_PMD
+static inline int try_populate_vmemmap_pmd(pmd_t *pmdp, pte_t *pgtable,
+					   unsigned long addr)
+{
+	pmd_populate_kernel(&init_mm, pmdp, pgtable);
+	return 0;
+}
+
 #ifndef __PAGETABLE_PMD_FOLDED
 
 static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
diff --git a/arch/riscv/include/asm/pgalloc.h b/arch/riscv/include/asm/pgalloc.h
index 770ce18a7328..8dbbe62b2574 100644
--- a/arch/riscv/include/asm/pgalloc.h
+++ b/arch/riscv/include/asm/pgalloc.h
@@ -31,6 +31,14 @@ static inline void pmd_populate(struct mm_struct *mm,
 	set_pmd(pmd, __pmd((pfn << _PAGE_PFN_SHIFT) | _PAGE_TABLE));
 }
 
+#define __HAVE_ARCH_TRY_POPULATE_VMEMMAP_PMD
+static inline int try_populate_vmemmap_pmd(pmd_t *pmdp, pte_t *pgtable,
+					   unsigned long addr)
+{
+	pmd_populate_kernel(&init_mm, pmdp, pgtable);
+	return 0;
+}
+
 #ifndef __PAGETABLE_PMD_FOLDED
 static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
 {
diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h
index c88691b15f3c..47b56bbd6236 100644
--- a/arch/x86/include/asm/pgalloc.h
+++ b/arch/x86/include/asm/pgalloc.h
@@ -82,6 +82,14 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
 	set_pmd(pmd, __pmd(((pteval_t)pfn << PAGE_SHIFT) | _PAGE_TABLE));
 }
 
+#define __HAVE_ARCH_TRY_POPULATE_VMEMMAP_PMD
+static inline int try_populate_vmemmap_pmd(pmd_t *pmdp, pte_t *pgtable,
+					   unsigned long addr)
+{
+	pmd_populate_kernel(&init_mm, pmdp, pgtable);
+	return 0;
+}
+
 #if CONFIG_PGTABLE_LEVELS > 2
 extern void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd);
 
diff --git a/include/linux/pgalloc.h b/include/linux/pgalloc.h
index 9174fa59bbc5..ed446d95ca37 100644
--- a/include/linux/pgalloc.h
+++ b/include/linux/pgalloc.h
@@ -26,4 +26,24 @@
 			arch_sync_kernel_mappings(addr, addr);		\
 	} while (0)
 
+#ifndef __HAVE_ARCH_TRY_POPULATE_VMEMMAP_PMD
+/*
+ * try_populate_vmemmap_pmd - Populate a PMD that is in use by the vmemmap.
+ * @addr: Base address of the remapped PMD.
+ * @pmdp: Page table pointer to be overwritten.
+ * @pgtable: Pointer to the page table that the new PMD will point to.
+ *
+ * This function is only to be used to update PMDs that map the vmemmap to
+ * point to a page of already-populated PTEs that map the same pages.
+ *
+ * Implementations of this function must ensure that, while the update is taking
+ * place, CPUs will not fault on the remapped virtual address range.
+ */
+static inline int try_populate_vmemmap_pmd(pmd_t *pmdp, pte_t *pgtable,
+					   unsigned long addr)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+
 #endif /* _LINUX_PGALLOC_H */
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index 977249e22ed0..b445febac0d2 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -55,6 +55,7 @@ static int vmemmap_split_pmd(pmd_t *pmd, struct page *head, unsigned long start,
 			     struct vmemmap_remap_walk *walk)
 {
 	pmd_t __pmd;
+	int ret;
 	int i;
 	unsigned long addr = start;
 	pte_t *pgtable;
@@ -74,8 +75,15 @@ static int vmemmap_split_pmd(pmd_t *pmd, struct page *head, unsigned long start,
 		set_pte_at(&init_mm, addr, pte, entry);
 	}
 
+	ret = 0;
 	spin_lock(&init_mm.page_table_lock);
 	if (likely(pmd_leaf(*pmd))) {
+		/* Make pte visible before pmd. See comment in pmd_install(). */
+		smp_wmb();
+		ret = try_populate_vmemmap_pmd(pmd, pgtable, start);
+		if (ret)
+			goto free;
+
 		/*
 		 * Higher order allocations from buddy allocator must be able to
 		 * be treated as independent small pages (as they can be freed
@@ -84,21 +92,17 @@ static int vmemmap_split_pmd(pmd_t *pmd, struct page *head, unsigned long start,
 		if (!PageReserved(head))
 			split_page(head, get_order(PMD_SIZE));
 
-		/* Make pte visible before pmd. See comment in pmd_install(). */
-		smp_wmb();
-		/*
-		 * On arm64, this requires BBML2_NOABORT. Its support has
-		 * already been checked.
-		 */
-		pmd_populate_kernel(&init_mm, pmd, pgtable);
 		if (!(walk->flags & VMEMMAP_SPLIT_NO_TLB_FLUSH))
 			flush_tlb_kernel_range(start, start + PMD_SIZE);
-	} else {
-		pte_free_kernel(&init_mm, pgtable);
-	}
-	spin_unlock(&init_mm.page_table_lock);
+	} else
+		goto free;
 
-	return 0;
+out:
+	spin_unlock(&init_mm.page_table_lock);
+	return ret;
+free:
+	pte_free_kernel(&init_mm, pgtable);
+	goto out;
 }
 
 static int vmemmap_pmd_entry(pmd_t *pmd, unsigned long addr,
-- 
2.55.0.795.g602f6c329a-goog



  parent reply	other threads:[~2026-07-08  3:12 UTC|newest]

Thread overview: 27+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-07-08  3:11 [PATCH 00/18] Another attempt at HVO support on arm64 James Houghton
2026-07-08  3:11 ` [PATCH 01/18] hugetlb_vmemmap: Always flush TLB if needed upon PTE remapping James Houghton
2026-07-08  3:11 ` [PATCH 02/18] hugetlb_vmemmap: Move vmemmap_get_tail up James Houghton
2026-07-08  3:11 ` [PATCH 03/18] hugetlb_vmemmap: Leave pages partially HVOed upon restore failure James Houghton
2026-07-08  3:11 ` [PATCH 04/18] hugetlb_vmemmap: Use try_update_vmemmap_pte to update in-use PTEs James Houghton
2026-07-08  3:11 ` [PATCH 05/18] hugetlb_vmemmap: Allow architectures not to allow HVO at runtime James Houghton
2026-07-08  3:11 ` [PATCH 06/18] arm64: Rename cpu_has_hw_af to system_has_hw_af James Houghton
2026-07-08  3:11 ` [PATCH 07/18] arm64: Add system_supports_hvo James Houghton
2026-07-08  3:11 ` [PATCH 08/18] arm64: Implement try_update_vmemmap_pte using the AF trick James Houghton
2026-07-08  3:11 ` [PATCH 09/18] arm64: Prevent HVO if the HVO system feature is not enabled James Houghton
2026-07-08  3:11 ` [PATCH 10/18] arm64: Support hugetlb vmemmap optimization James Houghton
2026-07-08  3:11 ` James Houghton [this message]
2026-07-08  3:11 ` [PATCH 12/18] arm64: Implement try_populate_vmemmap_pmd using AF trick James Houghton
2026-07-08  3:11 ` [PATCH 13/18] arm64: Drop BBML2_NOABORT requirement for HVO James Houghton
2026-07-08  3:11 ` [PATCH 14/18] hugetlb_vmemmap: Rename mm/hugetlb_vmemmap.h to mm/hugetlb_vmemmap_internal.h James Houghton
2026-07-08  3:11 ` [PATCH 15/18] hugetlb_vmemmap: Add a way to permanently disable HVO when needed James Houghton
2026-07-08  3:11 ` [PATCH 16/18] arm64: Allow "optional" CPU features to be required sometimes James Houghton
2026-07-08  3:11 ` [PATCH 17/18] arm64: Permit onlining of HVO-incompatible late CPUs if HVO is not in use James Houghton
2026-07-08  3:11 ` [PATCH 18/18] arm64: Remove user-selectable HVO Kconfig James Houghton
2026-07-08  8:40 ` [PATCH 00/18] Another attempt at HVO support on arm64 Muchun Song
2026-07-08 16:49   ` James Houghton
2026-07-09  9:54     ` Muchun Song
2026-07-09 19:04       ` James Houghton
2026-07-10  3:40         ` Muchun Song
2026-07-11  2:22         ` Muchun Song
2026-07-09  9:58 ` David Hildenbrand (Arm)
2026-07-10  4:58 ` Muchun Song

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=20260708031129.3503195-12-jthoughton@google.com \
    --to=jthoughton@google.com \
    --cc=akpm@linux-foundation.org \
    --cc=catalin.marinas@arm.com \
    --cc=david@kernel.org \
    --cc=fvdl@google.com \
    --cc=linu.cherian@arm.com \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mark.rutland@arm.com \
    --cc=muchun.song@linux.dev \
    --cc=nikos.nikoleris@arm.com \
    --cc=osalvador@suse.de \
    --cc=rientjes@google.com \
    --cc=ryan.roberts@arm.com \
    --cc=sunnanyong@huawei.com \
    --cc=will@kernel.org \
    --cc=yuzhao@google.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