[PATCH v6 36/38] mm: Convert do_set_pte() to set_pte_range()

From: Matthew Wilcox (Oracle)
Date: Wed Aug 02 2023 - 11:17:00 EST


From: Yin Fengwei <fengwei.yin@xxxxxxxxx>

set_pte_range() allows to setup page table entries for a specific
range. It takes advantage of batched rmap update for large folio.
It now takes care of calling update_mmu_cache_range().

Signed-off-by: Yin Fengwei <fengwei.yin@xxxxxxxxx>
Signed-off-by: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx>
---
Documentation/filesystems/locking.rst | 2 +-
include/linux/mm.h | 3 ++-
mm/filemap.c | 3 +--
mm/memory.c | 37 +++++++++++++++++----------
4 files changed, 28 insertions(+), 17 deletions(-)

diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst
index 89c5ec9e3392..cd032f2324e8 100644
--- a/Documentation/filesystems/locking.rst
+++ b/Documentation/filesystems/locking.rst
@@ -670,7 +670,7 @@ locked. The VM will unlock the page.
Filesystem should find and map pages associated with offsets from "start_pgoff"
till "end_pgoff". ->map_pages() is called with the RCU lock held and must
not block. If it's not possible to reach a page without blocking,
-filesystem should skip it. Filesystem should use do_set_pte() to setup
+filesystem should skip it. Filesystem should use set_pte_range() to setup
page table entry. Pointer to entry associated with the page is passed in
"pte" field in vm_fault structure. Pointers to entries for other offsets
should be calculated relative to "pte".
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 2fbc6c631764..19493d6a2bb8 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1346,7 +1346,8 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
}

vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page);
-void do_set_pte(struct vm_fault *vmf, struct page *page, unsigned long addr);
+void set_pte_range(struct vm_fault *vmf, struct folio *folio,
+ struct page *page, unsigned int nr, unsigned long addr);

vm_fault_t finish_fault(struct vm_fault *vmf);
vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf);
diff --git a/mm/filemap.c b/mm/filemap.c
index 9dc15af7ab5b..2e7050461a87 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -3506,8 +3506,7 @@ static vm_fault_t filemap_map_folio_range(struct vm_fault *vmf,
ret = VM_FAULT_NOPAGE;

ref_count++;
- do_set_pte(vmf, page, addr);
- update_mmu_cache(vma, addr, vmf->pte);
+ set_pte_range(vmf, folio, page, 1, addr);
} while (vmf->pte++, page++, addr += PAGE_SIZE, ++count < nr_pages);

/* Restore the vmf->pte */
diff --git a/mm/memory.c b/mm/memory.c
index e25edd4c24b8..621716109627 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4465,15 +4465,24 @@ vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page)
}
#endif

-void do_set_pte(struct vm_fault *vmf, struct page *page, unsigned long addr)
+/**
+ * set_pte_range - Set a range of PTEs to point to pages in a folio.
+ * @vmf: Fault decription.
+ * @folio: The folio that contains @page.
+ * @page: The first page to create a PTE for.
+ * @nr: The number of PTEs to create.
+ * @addr: The first address to create a PTE for.
+ */
+void set_pte_range(struct vm_fault *vmf, struct folio *folio,
+ struct page *page, unsigned int nr, unsigned long addr)
{
struct vm_area_struct *vma = vmf->vma;
bool uffd_wp = vmf_orig_pte_uffd_wp(vmf);
bool write = vmf->flags & FAULT_FLAG_WRITE;
- bool prefault = vmf->address != addr;
+ bool prefault = in_range(vmf->address, addr, nr * PAGE_SIZE);
pte_t entry;

- flush_icache_page(vma, page);
+ flush_icache_pages(vma, page, nr);
entry = mk_pte(page, vma->vm_page_prot);

if (prefault && arch_wants_old_prefaulted_pte())
@@ -4487,14 +4496,18 @@ void do_set_pte(struct vm_fault *vmf, struct page *page, unsigned long addr)
entry = pte_mkuffd_wp(entry);
/* copy-on-write page */
if (write && !(vma->vm_flags & VM_SHARED)) {
- inc_mm_counter(vma->vm_mm, MM_ANONPAGES);
- page_add_new_anon_rmap(page, vma, addr);
- lru_cache_add_inactive_or_unevictable(page, vma);
+ add_mm_counter(vma->vm_mm, MM_ANONPAGES, nr);
+ VM_BUG_ON_FOLIO(nr != 1, folio);
+ folio_add_new_anon_rmap(folio, vma, addr);
+ folio_add_lru_vma(folio, vma);
} else {
- inc_mm_counter(vma->vm_mm, mm_counter_file(page));
- page_add_file_rmap(page, vma, false);
+ add_mm_counter(vma->vm_mm, mm_counter_file(page), nr);
+ folio_add_file_rmap_range(folio, page, nr, vma, false);
}
- set_pte_at(vma->vm_mm, addr, vmf->pte, entry);
+ set_ptes(vma->vm_mm, addr, vmf->pte, entry, nr);
+
+ /* no need to invalidate: a not-present page won't be cached */
+ update_mmu_cache_range(vmf, vma, addr, vmf->pte, nr);
}

static bool vmf_pte_changed(struct vm_fault *vmf)
@@ -4562,11 +4575,9 @@ vm_fault_t finish_fault(struct vm_fault *vmf)

/* Re-check under ptl */
if (likely(!vmf_pte_changed(vmf))) {
- do_set_pte(vmf, page, vmf->address);
-
- /* no need to invalidate: a not-present page won't be cached */
- update_mmu_cache(vma, vmf->address, vmf->pte);
+ struct folio *folio = page_folio(page);

+ set_pte_range(vmf, folio, page, 1, vmf->address);
ret = 0;
} else {
update_mmu_tlb(vma, vmf->address, vmf->pte);
--
2.40.1