Hi Baolin,
On Thu, Jun 06, 2024 at 07:58:55PM +0800, Baolin Wang wrote:
> In the following patches, shmem will support the swap out of large folios,
> which means the shmem mappings may contain large order swap entries, so an
> 'orders' array is added for find_get_entries() and find_lock_entries() to
> obtain the order size of shmem swap entries, which will help in the release
> of shmem large folio swap entries.
>
> Signed-off-by: Baolin Wang <baolin.wang@xxxxxxxxxxxxxxxxx>
> ---
> mm/filemap.c | 27 +++++++++++++++++++++++++--
> mm/internal.h | 4 ++--
> mm/shmem.c | 17 +++++++++--------
> mm/truncate.c | 8 ++++----
> 4 files changed, 40 insertions(+), 16 deletions(-)
>
> diff --git a/mm/filemap.c b/mm/filemap.c
> index 37061aafd191..47fcd9ee6012 100644
> --- a/mm/filemap.c
> +++ b/mm/filemap.c
> @@ -2036,14 +2036,24 @@ static inline struct folio *find_get_entry(struct xa_state *xas, pgoff_t max,
> * Return: The number of entries which were found.
> */
> unsigned find_get_entries(struct address_space *mapping, pgoff_t *start,
> - pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices)
> + pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices,
> + int *orders)
> {
> XA_STATE(xas, &mapping->i_pages, *start);
> struct folio *folio;
> + int order;
>
> rcu_read_lock();
> while ((folio = find_get_entry(&xas, end, XA_PRESENT)) != NULL) {
> indices[fbatch->nr] = xas.xa_index;
> + if (orders) {
> + if (!xa_is_value(folio))
> + order = folio_order(folio);
> + else
> + order = xa_get_order(xas.xa, xas.xa_index);
> +
> + orders[fbatch->nr] = order;
> + }
> if (!folio_batch_add(fbatch, folio))
> break;
> }
> @@ -2056,6 +2066,8 @@ unsigned find_get_entries(struct address_space *mapping, pgoff_t *start,
> folio = fbatch->folios[idx];
> if (!xa_is_value(folio))
> nr = folio_nr_pages(folio);
> + else if (orders)
> + nr = 1 << orders[idx];
> *start = indices[idx] + nr;
> }
> return folio_batch_count(fbatch);
> @@ -2082,10 +2094,12 @@ unsigned find_get_entries(struct address_space *mapping, pgoff_t *start,
> * Return: The number of entries which were found.
> */
> unsigned find_lock_entries(struct address_space *mapping, pgoff_t *start,
> - pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices)
> + pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices,
> + int *orders)
> {
> XA_STATE(xas, &mapping->i_pages, *start);
> struct folio *folio;
> + int order;
>
> rcu_read_lock();
> while ((folio = find_get_entry(&xas, end, XA_PRESENT))) {
> @@ -2099,9 +2113,16 @@ unsigned find_lock_entries(struct address_space *mapping, pgoff_t *start,
> if (folio->mapping != mapping ||
> folio_test_writeback(folio))
> goto unlock;
> + if (orders)
> + order = folio_order(folio);
> VM_BUG_ON_FOLIO(!folio_contains(folio, xas.xa_index),
> folio);
> + } else if (orders) {
> + order = xa_get_order(xas.xa, xas.xa_index);
> }
> +
> + if (orders)
> + orders[fbatch->nr] = order;
> indices[fbatch->nr] = xas.xa_index;
> if (!folio_batch_add(fbatch, folio))
> break;
> @@ -2120,6 +2141,8 @@ unsigned find_lock_entries(struct address_space *mapping, pgoff_t *start,
> folio = fbatch->folios[idx];
> if (!xa_is_value(folio))
> nr = folio_nr_pages(folio);
> + else if (orders)
> + nr = 1 << orders[idx];
> *start = indices[idx] + nr;
> }
> return folio_batch_count(fbatch);
> diff --git a/mm/internal.h b/mm/internal.h
> index 3419c329b3bc..0b5adb6c33cc 100644
> --- a/mm/internal.h
> +++ b/mm/internal.h
> @@ -339,9 +339,9 @@ static inline void force_page_cache_readahead(struct address_space *mapping,
> }
>
> unsigned find_lock_entries(struct address_space *mapping, pgoff_t *start,
> - pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices);
> + pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices, int *orders);
> unsigned find_get_entries(struct address_space *mapping, pgoff_t *start,
> - pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices);
> + pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices, int *orders);
> void filemap_free_folio(struct address_space *mapping, struct folio *folio);
> int truncate_inode_folio(struct address_space *mapping, struct folio *folio);
> bool truncate_inode_partial_folio(struct folio *folio, loff_t start,
> diff --git a/mm/shmem.c b/mm/shmem.c
> index 0ac71580decb..28ba603d87b8 100644
> --- a/mm/shmem.c
> +++ b/mm/shmem.c
> @@ -840,14 +840,14 @@ static void shmem_delete_from_page_cache(struct folio *folio, void *radswap)
> * Remove swap entry from page cache, free the swap and its page cache.
> */
> static int shmem_free_swap(struct address_space *mapping,
> - pgoff_t index, void *radswap)
> + pgoff_t index, void *radswap, int order)
> {
> void *old;
Matthew Wilcox suggested [1] returning the number of pages freed in shmem_free_swap().
[1] https://lore.kernel.org/all/ZQRf2pGWurrE0uO+@xxxxxxxxxxxxxxxxxxxx/
Which I submitted here:
https://lore.kernel.org/all/20231028211518.3424020-5-da.gomez@xxxxxxxxxxx/
Do you agree with the suggestion? If so, could we update my patch to use
free_swap_and_cache_nr() or include that here?
>
> old = xa_cmpxchg_irq(&mapping->i_pages, index, radswap, NULL, 0);
> if (old != radswap)
> return -ENOENT;
> - free_swap_and_cache(radix_to_swp_entry(radswap));
> + free_swap_and_cache_nr(radix_to_swp_entry(radswap), 1 << order);
> return 0;
> }
>
> @@ -981,6 +981,7 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
> pgoff_t end = (lend + 1) >> PAGE_SHIFT;
> struct folio_batch fbatch;
> pgoff_t indices[PAGEVEC_SIZE];
> + int orders[PAGEVEC_SIZE];
> struct folio *folio;
> bool same_folio;
> long nr_swaps_freed = 0;
> @@ -996,15 +997,15 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
> folio_batch_init(&fbatch);
> index = start;
> while (index < end && find_lock_entries(mapping, &index, end - 1,
> - &fbatch, indices)) {
> + &fbatch, indices, orders)) {
> for (i = 0; i < folio_batch_count(&fbatch); i++) {
> folio = fbatch.folios[i];
>
> if (xa_is_value(folio)) {
> if (unfalloc)
> continue;
> - nr_swaps_freed += !shmem_free_swap(mapping,
> - indices[i], folio);
> + if (!shmem_free_swap(mapping, indices[i], folio, orders[i]))
> + nr_swaps_freed += 1 << orders[i];
> continue;
> }
>
> @@ -1058,7 +1059,7 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
> cond_resched();
>
> if (!find_get_entries(mapping, &index, end - 1, &fbatch,
> - indices)) {
> + indices, orders)) {
> /* If all gone or hole-punch or unfalloc, we're done */
> if (index == start || end != -1)
> break;
> @@ -1072,12 +1073,12 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
> if (xa_is_value(folio)) {
> if (unfalloc)
> continue;
> - if (shmem_free_swap(mapping, indices[i], folio)) {
> + if (shmem_free_swap(mapping, indices[i], folio, orders[i])) {
> /* Swap was replaced by page: retry */
> index = indices[i];
> break;
> }
> - nr_swaps_freed++;
> + nr_swaps_freed += 1 << orders[i];
> continue;
> }
>
> diff --git a/mm/truncate.c b/mm/truncate.c
> index 5ce62a939e55..3a4bc9dba451 100644
> --- a/mm/truncate.c
> +++ b/mm/truncate.c
> @@ -352,7 +352,7 @@ void truncate_inode_pages_range(struct address_space *mapping,
> folio_batch_init(&fbatch);
> index = start;
> while (index < end && find_lock_entries(mapping, &index, end - 1,
> - &fbatch, indices)) {
> + &fbatch, indices, NULL)) {
> truncate_folio_batch_exceptionals(mapping, &fbatch, indices);
> for (i = 0; i < folio_batch_count(&fbatch); i++)
> truncate_cleanup_folio(fbatch.folios[i]);
> @@ -392,7 +392,7 @@ void truncate_inode_pages_range(struct address_space *mapping,
> while (index < end) {
> cond_resched();
> if (!find_get_entries(mapping, &index, end - 1, &fbatch,
> - indices)) {
> + indices, NULL)) {
> /* If all gone from start onwards, we're done */
> if (index == start)
> break;
> @@ -496,7 +496,7 @@ unsigned long mapping_try_invalidate(struct address_space *mapping,
> int i;
>
> folio_batch_init(&fbatch);
> - while (find_lock_entries(mapping, &index, end, &fbatch, indices)) {
> + while (find_lock_entries(mapping, &index, end, &fbatch, indices, NULL)) {
> for (i = 0; i < folio_batch_count(&fbatch); i++) {
> struct folio *folio = fbatch.folios[i];
>
> @@ -622,7 +622,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
>
> folio_batch_init(&fbatch);
> index = start;
> - while (find_get_entries(mapping, &index, end, &fbatch, indices)) {
> + while (find_get_entries(mapping, &index, end, &fbatch, indices, NULL)) {
> for (i = 0; i < folio_batch_count(&fbatch); i++) {
> struct folio *folio = fbatch.folios[i];
>
> --
> 2.39.3
>
Daniel
