Ryan noticed 1% performance regression for kernel build with the ranged file map with ext4 file system. It was later identified wrong xas.xa_index update in filemap_map_pages() when folio is not large folio. Matthew suggested to use XArray API instead of touch xas.xa_index directly at [1]. [1] https://lore.kernel.org/linux-mm/ZBho6Q6Xq%2FYqRmBT@xxxxxxxxxxxxxxxxxxxx/ Signed-off-by: Yin Fengwei <fengwei.yin@xxxxxxxxx> Suggested-by: Matthew Wilcox <willy@xxxxxxxxxxxxx> --- mm/filemap.c | 30 ++++++------------------------ 1 file changed, 6 insertions(+), 24 deletions(-) diff --git a/mm/filemap.c b/mm/filemap.c index 40be33b5ee46..fdb3e0a339b3 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -3416,10 +3416,10 @@ static bool filemap_map_pmd(struct vm_fault *vmf, struct folio *folio, return false; } -static struct folio *next_uptodate_page(struct folio *folio, - struct address_space *mapping, - struct xa_state *xas, pgoff_t end_pgoff) +static struct folio *next_uptodate_folio(struct xa_state *xas, + struct address_space *mapping, pgoff_t end_pgoff) { + struct folio *folio = xas_next_entry(xas, end_pgoff); unsigned long max_idx; do { @@ -3457,22 +3457,6 @@ static struct folio *next_uptodate_page(struct folio *folio, return NULL; } -static inline struct folio *first_map_page(struct address_space *mapping, - struct xa_state *xas, - pgoff_t end_pgoff) -{ - return next_uptodate_page(xas_find(xas, end_pgoff), - mapping, xas, end_pgoff); -} - -static inline struct folio *next_map_page(struct address_space *mapping, - struct xa_state *xas, - pgoff_t end_pgoff) -{ - return next_uptodate_page(xas_next_entry(xas, end_pgoff), - 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) @@ -3543,12 +3527,11 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf, unsigned long addr; XA_STATE(xas, &mapping->i_pages, start_pgoff); struct folio *folio; - 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); + folio = next_uptodate_folio(&xas, mapping, end_pgoff); if (!folio) goto out; @@ -3570,15 +3553,14 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf, ret |= filemap_map_folio_range(vmf, folio, xas.xa_index - folio->index, addr, nr_pages); - xas.xa_index += nr_pages; folio_unlock(folio); folio_put(folio); - } while ((folio = next_map_page(mapping, &xas, end_pgoff)) != NULL); + folio = next_uptodate_folio(&xas, mapping, end_pgoff); + } while (folio); pte_unmap_unlock(vmf->pte, vmf->ptl); out: rcu_read_unlock(); - WRITE_ONCE(file->f_ra.mmap_miss, mmap_miss); return ret; } EXPORT_SYMBOL(filemap_map_pages); -- 2.30.2
