[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20250519074824.42909-3-dev.jain@arm.com>
Date: Mon, 19 May 2025 13:18:21 +0530
From: Dev Jain <dev.jain@....com>
To: akpm@...ux-foundation.org
Cc: ryan.roberts@....com,
david@...hat.com,
willy@...radead.org,
linux-mm@...ck.org,
linux-kernel@...r.kernel.org,
catalin.marinas@....com,
will@...nel.org,
Liam.Howlett@...cle.com,
lorenzo.stoakes@...cle.com,
vbabka@...e.cz,
jannh@...gle.com,
anshuman.khandual@....com,
peterx@...hat.com,
joey.gouly@....com,
ioworker0@...il.com,
baohua@...nel.org,
kevin.brodsky@....com,
quic_zhenhuah@...cinc.com,
christophe.leroy@...roup.eu,
yangyicong@...ilicon.com,
linux-arm-kernel@...ts.infradead.org,
hughd@...gle.com,
yang@...amperecomputing.com,
ziy@...dia.com,
Dev Jain <dev.jain@....com>
Subject: [PATCH v3 2/5] mm: Add batched versions of ptep_modify_prot_start/commit
Batch ptep_modify_prot_start/commit in preparation for optimizing mprotect.
Architecture can override these helpers; in case not, they are implemented
as a simple loop over the corresponding single pte helpers.
Signed-off-by: Dev Jain <dev.jain@....com>
---
include/linux/pgtable.h | 75 +++++++++++++++++++++++++++++++++++++++++
mm/mprotect.c | 4 +--
2 files changed, 77 insertions(+), 2 deletions(-)
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index b50447ef1c92..e40ed57e034d 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -1333,6 +1333,81 @@ static inline void ptep_modify_prot_commit(struct vm_area_struct *vma,
__ptep_modify_prot_commit(vma, addr, ptep, pte);
}
#endif /* __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION */
+
+/**
+ * modify_prot_start_ptes - Start a pte protection read-modify-write transaction
+ * over a batch of ptes, which protects against asynchronous hardware modifications
+ * to the ptes. The intention is not to prevent the hardware from making pte
+ * updates, but to prevent any updates it may make from being lost.
+ * Please see the comment above ptep_modify_prot_start() for full description.
+ *
+ * @vma: The virtual memory area the pages are mapped into.
+ * @addr: Address the first page is mapped at.
+ * @ptep: Page table pointer for the first entry.
+ * @nr: Number of entries.
+ *
+ * May be overridden by the architecture; otherwise, implemented as a simple
+ * loop over ptep_modify_prot_start(), collecting the a/d bits of the mapped
+ * folio.
+ *
+ * Note that PTE bits in the PTE range besides the PFN can differ.
+ *
+ * Context: The caller holds the page table lock. The PTEs map consecutive
+ * pages that belong to the same folio. The PTEs are all in the same PMD.
+ */
+#ifndef modify_prot_start_ptes
+static inline pte_t modify_prot_start_ptes(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *ptep, unsigned int nr)
+{
+ pte_t pte, tmp_pte;
+
+ pte = ptep_modify_prot_start(vma, addr, ptep);
+ while (--nr) {
+ ptep++;
+ addr += PAGE_SIZE;
+ tmp_pte = ptep_modify_prot_start(vma, addr, ptep);
+ if (pte_dirty(tmp_pte))
+ pte = pte_mkdirty(pte);
+ if (pte_young(tmp_pte))
+ pte = pte_mkyoung(pte);
+ }
+ return pte;
+}
+#endif
+
+/**
+ * modify_prot_commit_ptes - Commit an update to a batch of ptes, leaving any
+ * hardware-controlled bits in the PTE unmodified.
+ *
+ * @vma: The virtual memory area the pages are mapped into.
+ * @addr: Address the first page is mapped at.
+ * @ptep: Page table pointer for the first entry.
+ * @nr: Number of entries.
+ *
+ * May be overridden by the architecture; otherwise, implemented as a simple
+ * loop over ptep_modify_prot_commit().
+ *
+ * Note that PTE bits in the PTE range besides the PFN can differ.
+ *
+ * Context: The caller holds the page table lock. The PTEs map consecutive
+ * pages that belong to the same folio. The PTEs are all in the same PMD.
+ */
+#ifndef modify_prot_commit_ptes
+static inline void modify_prot_commit_ptes(struct vm_area_struct *vma, unsigned long addr,
+ pte_t *ptep, pte_t old_pte, pte_t pte, unsigned int nr)
+{
+ int i;
+
+ for (i = 0; i < nr; ++i) {
+ ptep_modify_prot_commit(vma, addr, ptep, old_pte, pte);
+ ptep++;
+ addr += PAGE_SIZE;
+ old_pte = pte_next_pfn(old_pte);
+ pte = pte_next_pfn(pte);
+ }
+}
+#endif
+
#endif /* CONFIG_MMU */
/*
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 1ee160ed0b14..124612ce3d24 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -188,7 +188,7 @@ static long change_pte_range(struct mmu_gather *tlb,
jiffies_to_msecs(jiffies));
}
- oldpte = ptep_modify_prot_start(vma, addr, pte);
+ oldpte = modify_prot_start_ptes(vma, addr, pte, nr_ptes);
ptent = pte_modify(oldpte, newprot);
if (uffd_wp)
@@ -214,7 +214,7 @@ static long change_pte_range(struct mmu_gather *tlb,
can_change_pte_writable(vma, addr, ptent))
ptent = pte_mkwrite(ptent, vma);
- ptep_modify_prot_commit(vma, addr, pte, oldpte, ptent);
+ modify_prot_commit_ptes(vma, addr, pte, oldpte, ptent, nr_ptes);
if (pte_needs_flush(oldpte, ptent))
tlb_flush_pte_range(tlb, addr, PAGE_SIZE);
pages++;
--
2.30.2
Powered by blists - more mailing lists