@@ -2200,16 +2200,6 @@ unsigned filemap_get_folios(struct address_space *mapping, pgoff_t *start,
}
EXPORT_SYMBOL(filemap_get_folios);
-static inline
-bool folio_more_pages(struct folio *folio, pgoff_t index, pgoff_t max)
-{
- if (!folio_test_large(folio) || folio_test_hugetlb(folio))
- return false;
- if (index >= max)
- return false;
- return index < folio->index + folio_nr_pages(folio) - 1;
-}
-
/**
* filemap_get_folios_contig - Get a batch of contiguous folios
* @mapping: The address_space to search
@@ -3351,6 +3341,53 @@ static inline struct folio *next_map_page(struct address_space *mapping,
mapping, xas, end_pgoff);
}
+/*
+ * Map page range [start_page, start_page + nr_pages) of folio.
+ * start_page is gotten from start by folio_page(folio, start)
+ */
+static vm_fault_t filemap_map_folio_range(struct vm_fault *vmf,
+ struct folio *folio, unsigned long start,
+ unsigned long addr, unsigned int nr_pages)
+{
+ vm_fault_t ret = 0;
+ struct vm_area_struct *vma = vmf->vma;
+ struct file *file = vma->vm_file;
+ struct page *page = folio_page(folio, start);
+ unsigned int mmap_miss = READ_ONCE(file->f_ra.mmap_miss);
+ unsigned int ref_count = 0, count = 0;
+
+ do {
+ if (PageHWPoison(page))
+ continue;
+
+ if (mmap_miss > 0)
+ mmap_miss--;
+
+ /*
+ * NOTE: If there're PTE markers, we'll leave them to be
+ * handled in the specific fault path, and it'll prohibit the
+ * fault-around logic.
+ */
+ if (!pte_none(*vmf->pte))
+ continue;
+
+ if (vmf->address == addr)
+ ret = VM_FAULT_NOPAGE;
+
+ ref_count++;
+ do_set_pte(vmf, page, addr);
+ update_mmu_cache(vma, addr, vmf->pte);
+ } while (vmf->pte++, page++, addr += PAGE_SIZE, ++count < nr_pages);
+
+ /* Restore the vmf->pte */
+ vmf->pte -= nr_pages;
+
+ folio_ref_add(folio, ref_count);
+ WRITE_ONCE(file->f_ra.mmap_miss, mmap_miss);
+
+ return ret;
+}
+
vm_fault_t filemap_map_pages(struct vm_fault *vmf,
pgoff_t start_pgoff, pgoff_t end_pgoff)
{
@@ -3361,9 +3398,9 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf,
unsigned long addr;
XA_STATE(xas, &mapping->i_pages, start_pgoff);
struct folio *folio;
- struct page *page;
unsigned int mmap_miss = READ_ONCE(file->f_ra.mmap_miss);
vm_fault_t ret = 0;
+ int nr_pages = 0;
rcu_read_lock();
folio = first_map_page(mapping, &xas, end_pgoff);
@@ -3378,45 +3415,18 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf,
addr = vma->vm_start + ((start_pgoff - vma->vm_pgoff) << PAGE_SHIFT);
vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, addr, &vmf->ptl);
do {
-again:
- page = folio_file_page(folio, xas.xa_index);
- if (PageHWPoison(page))
- goto unlock;
-
- if (mmap_miss > 0)
- mmap_miss--;
+ unsigned long end;
addr += (xas.xa_index - last_pgoff) << PAGE_SHIFT;
vmf->pte += xas.xa_index - last_pgoff;
last_pgoff = xas.xa_index;
+ end = folio->index + folio_nr_pages(folio) - 1;
+ nr_pages = min(end, end_pgoff) - xas.xa_index + 1;
- /*
- * NOTE: If there're PTE markers, we'll leave them to be
- * handled in the specific fault path, and it'll prohibit the
- * fault-around logic.
- */
- if (!pte_none(*vmf->pte))
- goto unlock;
-
- /* We're about to handle the fault */
- if (vmf->address == addr)
- ret = VM_FAULT_NOPAGE;
+ ret |= filemap_map_folio_range(vmf, folio,
+ xas.xa_index - folio->index, addr, nr_pages);
+ xas.xa_index += nr_pages;
- do_set_pte(vmf, page, addr);
- /* no need to invalidate: a not-present page won't be cached */
- update_mmu_cache(vma, addr, vmf->pte);
- if (folio_more_pages(folio, xas.xa_index, end_pgoff)) {
- xas.xa_index++;
- folio_ref_inc(folio);
- goto again;
- }
- folio_unlock(folio);
- continue;
-unlock:
- if (folio_more_pages(folio, xas.xa_index, end_pgoff)) {
- xas.xa_index++;
- goto again;
- }
folio_unlock(folio);
folio_put(folio);
} while ((folio = next_map_page(mapping, &xas, end_pgoff)) != NULL);
filemap_map_folio_range() maps partial/full folio. Comparing to original filemap_map_pages(), it batched updates refcount and get minor performance improvement for large folio. With a will-it-scale.page_fault3 like app (change file write fault testing to read fault testing. Trying to upstream it to will-it-scale at [1]), got 2% performance gain on a 48C/96T Cascade Lake test box with 96 processes running against xfs. [1]: https://github.com/antonblanchard/will-it-scale/pull/37 Signed-off-by: Yin Fengwei <fengwei.yin@intel.com> --- mm/filemap.c | 98 +++++++++++++++++++++++++++++----------------------- 1 file changed, 54 insertions(+), 44 deletions(-)