mm: add get_and_clear_ptes() and clear_ptes()

Patch series "Optimizations for khugepaged", v4.

If the underlying folio mapped by the ptes is large, we can process those
ptes in a batch using folio_pte_batch().

For arm64 specifically, this results in a 16x reduction in the number of
ptep_get() calls, since on a contig block, ptep_get() on arm64 will
iterate through all 16 entries to collect a/d bits.  Next, ptep_clear()
will cause a TLBI for every contig block in the range via
contpte_try_unfold().  Instead, use clear_ptes() to only do the TLBI at
the first and last contig block of the range.

For split folios, there will be no pte batching; the batch size returned
by folio_pte_batch() will be 1.  For pagetable split folios, the ptes will
still point to the same large folio; for arm64, this results in the
optimization described above, and for other arches, a minor improvement is
expected due to a reduction in the number of function calls and batching
atomic operations.

This patch (of 3):

Let's add variants to be used where "full" does not apply -- which will
be the majority of cases in the future. "full" really only applies if
we are about to tear down a full MM.

Use get_and_clear_ptes() in existing code, clear_ptes() users will
be added next.

Link: https://lkml.kernel.org/r/20250724052301.23844-2-dev.jain@arm.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Dev Jain <dev.jain@arm.com>
Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Reviewed-by: Barry Song <baohua@kernel.org>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Mariano Pache <npache@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index abd9725796e9ed9e1975ba69cde6701ed656b978..20a89ab97dc50082ba066bfc6e4453ca8c73a090 100644 (file)
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -1528,7 +1528,7 @@ early_initcall(prevent_bootmem_remove_init);
 pte_t modify_prot_start_ptes(struct vm_area_struct *vma, unsigned long addr,
                             pte_t *ptep, unsigned int nr)
 {
-       pte_t pte = get_and_clear_full_ptes(vma->vm_mm, addr, ptep, nr, /* full = */ 0);
+       pte_t pte = get_and_clear_ptes(vma->vm_mm, addr, ptep, nr);
 
        if (alternative_has_cap_unlikely(ARM64_WORKAROUND_2645198)) {
                /*

diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index e3b99920be05cd2da765c04c1475bb573f3373a0..4c035637eeb77f46101a4f75b09723a031fe1845 100644 (file)
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -736,6 +736,29 @@ static inline pte_t get_and_clear_full_ptes(struct mm_struct *mm,
 }
 #endif
 
+/**
+ * get_and_clear_ptes - Clear present PTEs that map consecutive pages of
+ *                     the same folio, collecting dirty/accessed bits.
+ * @mm: Address space 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 to clear.
+ *
+ * Use this instead of get_and_clear_full_ptes() if it is known that we don't
+ * need to clear the full mm, which is mostly the case.
+ *
+ * Note that PTE bits in the PTE range besides the PFN can differ. For example,
+ * some PTEs might be write-protected.
+ *
+ * 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.
+ */
+static inline pte_t get_and_clear_ptes(struct mm_struct *mm, unsigned long addr,
+               pte_t *ptep, unsigned int nr)
+{
+       return get_and_clear_full_ptes(mm, addr, ptep, nr, 0);
+}
+
 #ifndef clear_full_ptes
 /**
  * clear_full_ptes - Clear present PTEs that map consecutive pages of the same
@@ -768,6 +791,28 @@ static inline void clear_full_ptes(struct mm_struct *mm, unsigned long addr,
 }
 #endif
 
+/**
+ * clear_ptes - Clear present PTEs that map consecutive pages of the same folio.
+ * @mm: Address space 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 to clear.
+ *
+ * Use this instead of clear_full_ptes() if it is known that we don't need to
+ * clear the full mm, which is mostly the case.
+ *
+ * Note that PTE bits in the PTE range besides the PFN can differ. For example,
+ * some PTEs might be write-protected.
+ *
+ * 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.
+ */
+static inline void clear_ptes(struct mm_struct *mm, unsigned long addr,
+               pte_t *ptep, unsigned int nr)
+{
+       clear_full_ptes(mm, addr, ptep, nr, 0);
+}
+
 /*
  * If two threads concurrently fault at the same page, the thread that
  * won the race updates the PTE and its local TLB/Cache. The other thread

diff --git a/mm/mremap.c b/mm/mremap.c
index ac39845e971804a858804a269f49732c3c82538b..677a4d744df9cf5b9b4bff75b361330f13add20e 100644 (file)
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -280,7 +280,7 @@ static int move_ptes(struct pagetable_move_control *pmc,
                                                         old_pte, max_nr_ptes);
                        force_flush = true;
                }
-               pte = get_and_clear_full_ptes(mm, old_addr, old_ptep, nr_ptes, 0);
+               pte = get_and_clear_ptes(mm, old_addr, old_ptep, nr_ptes);
                pte = move_pte(pte, old_addr, new_addr);
                pte = move_soft_dirty_pte(pte);
 

diff --git a/mm/rmap.c b/mm/rmap.c
index f93ce27132abcc10ae6f3ad58df9793d5a8d92a6..568198e9efc2927f540518f88e9ada9025248154 100644 (file)
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -2036,7 +2036,7 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
                        flush_cache_range(vma, address, end_addr);
 
                        /* Nuke the page table entry. */
-                       pteval = get_and_clear_full_ptes(mm, address, pvmw.pte, nr_pages, 0);
+                       pteval = get_and_clear_ptes(mm, address, pvmw.pte, nr_pages);
                        /*
                         * We clear the PTE but do not flush so potentially
                         * a remote CPU could still be writing to the folio.