diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2024-03-27 13:30:48 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2024-03-27 13:30:48 -0700 |
commit | dc189b8e6adbe113a6d4b3a7c5d0c9cd7febb3bb (patch) | |
tree | 7c196dea5150c5a0cbb4e589ccac538caf540dbd /mm/zswap.c | |
parent | 962490525cffee6270422206c9d5bdb12d472c2b (diff) | |
parent | 32fbe5246582af4f611ccccee33fd6e559087252 (diff) | |
download | linux-dc189b8e6adbe113a6d4b3a7c5d0c9cd7febb3bb.tar.gz |
Merge tag 'mm-hotfixes-stable-2024-03-27-11-25' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Pull misc fixes from Andrew Morton:
"Various hotfixes. About half are cc:stable and the remainder address
post-6.8 issues or aren't considered suitable for backporting.
zswap figures prominently in the post-6.8 issues - folloup against the
large amount of changes we have just made to that code.
Apart from that, all over the map"
* tag 'mm-hotfixes-stable-2024-03-27-11-25' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (21 commits)
crash: use macro to add crashk_res into iomem early for specific arch
mm: zswap: fix data loss on SWP_SYNCHRONOUS_IO devices
selftests/mm: fix ARM related issue with fork after pthread_create
hexagon: vmlinux.lds.S: handle attributes section
userfaultfd: fix deadlock warning when locking src and dst VMAs
tmpfs: fix race on handling dquot rbtree
selftests/mm: sigbus-wp test requires UFFD_FEATURE_WP_HUGETLBFS_SHMEM
mm: zswap: fix writeback shinker GFP_NOIO/GFP_NOFS recursion
ARM: prctl: reject PR_SET_MDWE on pre-ARMv6
prctl: generalize PR_SET_MDWE support check to be per-arch
MAINTAINERS: remove incorrect M: tag for dm-devel@lists.linux.dev
mm: zswap: fix kernel BUG in sg_init_one
selftests: mm: restore settings from only parent process
tools/Makefile: remove cgroup target
mm: cachestat: fix two shmem bugs
mm: increase folio batch size
mm,page_owner: fix recursion
mailmap: update entry for Leonard Crestez
init: open /initrd.image with O_LARGEFILE
selftests/mm: Fix build with _FORTIFY_SOURCE
...
Diffstat (limited to 'mm/zswap.c')
-rw-r--r-- | mm/zswap.c | 45 |
1 files changed, 39 insertions, 6 deletions
diff --git a/mm/zswap.c b/mm/zswap.c index 9dec853647c8e4..caed028945b046 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -1080,7 +1080,17 @@ static void zswap_decompress(struct zswap_entry *entry, struct page *page) mutex_lock(&acomp_ctx->mutex); src = zpool_map_handle(zpool, entry->handle, ZPOOL_MM_RO); - if (acomp_ctx->is_sleepable && !zpool_can_sleep_mapped(zpool)) { + /* + * If zpool_map_handle is atomic, we cannot reliably utilize its mapped buffer + * to do crypto_acomp_decompress() which might sleep. In such cases, we must + * resort to copying the buffer to a temporary one. + * Meanwhile, zpool_map_handle() might return a non-linearly mapped buffer, + * such as a kmap address of high memory or even ever a vmap address. + * However, sg_init_one is only equipped to handle linearly mapped low memory. + * In such cases, we also must copy the buffer to a temporary and lowmem one. + */ + if ((acomp_ctx->is_sleepable && !zpool_can_sleep_mapped(zpool)) || + !virt_addr_valid(src)) { memcpy(acomp_ctx->buffer, src, entry->length); src = acomp_ctx->buffer; zpool_unmap_handle(zpool, entry->handle); @@ -1094,7 +1104,7 @@ static void zswap_decompress(struct zswap_entry *entry, struct page *page) BUG_ON(acomp_ctx->req->dlen != PAGE_SIZE); mutex_unlock(&acomp_ctx->mutex); - if (!acomp_ctx->is_sleepable || zpool_can_sleep_mapped(zpool)) + if (src != acomp_ctx->buffer) zpool_unmap_handle(zpool, entry->handle); } @@ -1313,6 +1323,14 @@ static unsigned long zswap_shrinker_count(struct shrinker *shrinker, if (!zswap_shrinker_enabled || !mem_cgroup_zswap_writeback_enabled(memcg)) return 0; + /* + * The shrinker resumes swap writeback, which will enter block + * and may enter fs. XXX: Harmonize with vmscan.c __GFP_FS + * rules (may_enter_fs()), which apply on a per-folio basis. + */ + if (!gfp_has_io_fs(sc->gfp_mask)) + return 0; + #ifdef CONFIG_MEMCG_KMEM mem_cgroup_flush_stats(memcg); nr_backing = memcg_page_state(memcg, MEMCG_ZSWAP_B) >> PAGE_SHIFT; @@ -1618,6 +1636,7 @@ bool zswap_load(struct folio *folio) swp_entry_t swp = folio->swap; pgoff_t offset = swp_offset(swp); struct page *page = &folio->page; + bool swapcache = folio_test_swapcache(folio); struct zswap_tree *tree = swap_zswap_tree(swp); struct zswap_entry *entry; u8 *dst; @@ -1630,7 +1649,20 @@ bool zswap_load(struct folio *folio) spin_unlock(&tree->lock); return false; } - zswap_rb_erase(&tree->rbroot, entry); + /* + * When reading into the swapcache, invalidate our entry. The + * swapcache can be the authoritative owner of the page and + * its mappings, and the pressure that results from having two + * in-memory copies outweighs any benefits of caching the + * compression work. + * + * (Most swapins go through the swapcache. The notable + * exception is the singleton fault on SWP_SYNCHRONOUS_IO + * files, which reads into a private page and may free it if + * the fault fails. We remain the primary owner of the entry.) + */ + if (swapcache) + zswap_rb_erase(&tree->rbroot, entry); spin_unlock(&tree->lock); if (entry->length) @@ -1645,9 +1677,10 @@ bool zswap_load(struct folio *folio) if (entry->objcg) count_objcg_event(entry->objcg, ZSWPIN); - zswap_entry_free(entry); - - folio_mark_dirty(folio); + if (swapcache) { + zswap_entry_free(entry); + folio_mark_dirty(folio); + } return true; } |