From: Alexandre Ghiti A large folio reaches zswap_load() only when the caller expects the whole range to be on disk. Zswap still stores large folios as independent order-0 entries, so reconstructing a large folio from zswap entries would risk returning partially initialized data. Teach zswap_load() to scan the covered range. If no slot is in zswap, return -ENOENT so swap_read_folio() reads the backing device. If any slot is still in zswap, fail the large-folio read so the caller can fall back to per-page swapin. Return -EIO rather than -EINVAL for that conflict. Large-folio loads are now valid requests; the error means zswap cannot safely satisfy the request from partial per-page compressed state, not that the request is unsupported. Existing callers only distinguish -ENOENT, so this is a semantic clarification rather than a behavioral change. Add zswap_is_present() so PMD swap-entry consumers can make the same range decision before attempting PMD-order swapin. Also use it from __swap_cache_add_check() for multi-page insertions while holding the swap cluster lock. That check runs before folio allocation and again immediately before swap-cache insertion, closing the race with zswap writeback and rejecting mixed zswap/disk backing with -EBUSY. Signed-off-by: Alexandre Ghiti Signed-off-by: Usama Arif --- include/linux/zswap.h | 6 ++++++ mm/swap_state.c | 10 ++++++++++ mm/zswap.c | 46 +++++++++++++++++++++++++++++++------------ 3 files changed, 49 insertions(+), 13 deletions(-) diff --git a/include/linux/zswap.h b/include/linux/zswap.h index 30c193a1207e1..cd9efcf9dec94 100644 --- a/include/linux/zswap.h +++ b/include/linux/zswap.h @@ -35,6 +35,7 @@ void zswap_lruvec_state_init(struct lruvec *lruvec); void zswap_folio_swapin(struct folio *folio); bool zswap_is_enabled(void); bool zswap_never_enabled(void); +bool zswap_is_present(swp_entry_t entry, unsigned int nr); #else struct zswap_lruvec_state {}; @@ -69,6 +70,11 @@ static inline bool zswap_never_enabled(void) return true; } +static inline bool zswap_is_present(swp_entry_t entry, unsigned int nr) +{ + return false; +} + #endif #endif /* _LINUX_ZSWAP_H */ diff --git a/mm/swap_state.c b/mm/swap_state.c index b76eb3d876fd7..15e200d6966b9 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include @@ -191,6 +192,15 @@ static int __swap_cache_add_check(struct swap_cluster_info *ci, if (nr == 1) return 0; + /* + * The cluster lock serializes swap-cache insertion with zswap + * writeback. Reject mixed zswap/disk backing before allocating a + * large folio and recheck it before adding the folio to swap cache. + */ + if (zswap_is_present(swp_entry(swp_type(targ_entry), + round_down(swp_offset(targ_entry), nr)), nr)) + return -EBUSY; + is_zero = __swap_table_test_zero(ci, ci_off); ci_off = round_down(ci_off, nr); ci_end = ci_off + nr; diff --git a/mm/zswap.c b/mm/zswap.c index 37f34e406c8e3..32671dc2bf84d 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -1571,6 +1571,23 @@ bool zswap_store(struct folio *folio) return ret; } +/** + * zswap_is_present() - is any slot in [entry, entry + nr) in zswap? + * @entry: base swap entry of the range + * @nr: number of contiguous slots to check (pass 1 for a single-slot query) + */ +bool zswap_is_present(swp_entry_t entry, unsigned int nr) +{ + pgoff_t offset = swp_offset(entry); + struct xarray *tree = swap_zswap_tree(entry); + unsigned long index = offset; + + if (!nr || zswap_never_enabled()) + return false; + + return xa_find(tree, &index, offset + nr - 1, XA_PRESENT); +} + /** * zswap_load() - load a folio from zswap * @folio: folio to load @@ -1578,13 +1595,9 @@ bool zswap_store(struct folio *folio) * Return: 0 on success, with the folio unlocked and marked up-to-date, or one * of the following error codes: * - * -EIO: if the swapped out content was in zswap, but could not be loaded - * into the page due to a decompression failure. The folio is unlocked, but - * NOT marked up-to-date, so that an IO error is emitted (e.g. do_swap_page() - * will SIGBUS). - * - * -EINVAL: if the swapped out content was in zswap, but the page belongs - * to a large folio, which is not supported by zswap. The folio is unlocked, + * -EIO: if the swapped out content was in zswap but could not be handed + * back, either because decompression failed or because a slot in a + * large-folio range is unexpectedly still in zswap. The folio is unlocked, * but NOT marked up-to-date, so that an IO error is emitted (e.g. * do_swap_page() will SIGBUS). * @@ -1605,13 +1618,20 @@ int zswap_load(struct folio *folio) return -ENOENT; /* - * Large folios should not be swapped in while zswap is being used, as - * they are not properly handled. Zswap does not properly load large - * folios, and a large folio may only be partially in zswap. + * A large folio reaches zswap_load() only when its whole range is + * expected to be on disk: PMD swap-entry consumers split before + * calling into PMD-order swapin whenever any slot is still in zswap. + * Confirm the range is entirely absent from zswap and return -ENOENT + * so the caller reads it from disk; if a slot is unexpectedly still in + * zswap, fail the read rather than return partially-initialized data. */ - if (WARN_ON_ONCE(folio_test_large(folio))) { - folio_unlock(folio); - return -EINVAL; + if (folio_test_large(folio)) { + if (WARN_ON_ONCE(zswap_is_present(swp, + folio_nr_pages(folio)))) { + folio_unlock(folio); + return -EIO; + } + return -ENOENT; } entry = xa_load(tree, offset); -- 2.53.0-Meta