diff options
| -rw-r--r-- | .mailmap | 1 | ||||
| -rw-r--r-- | MAINTAINERS | 4 | ||||
| -rw-r--r-- | include/linux/leafops.h | 32 | ||||
| -rw-r--r-- | lib/bug.c | 7 | ||||
| -rw-r--r-- | mm/damon/sysfs.c | 10 | ||||
| -rw-r--r-- | mm/memory.c | 18 | ||||
| -rw-r--r-- | mm/mseal.c | 3 | ||||
| -rw-r--r-- | mm/pagewalk.c | 25 | ||||
| -rw-r--r-- | mm/swap_state.c | 9 |
9 files changed, 77 insertions, 32 deletions
@@ -316,6 +316,7 @@ Hans Verkuil <hverkuil@kernel.org> <hverkuil-cisco@xs4all.nl> Hans Verkuil <hverkuil@kernel.org> <hansverk@cisco.com> Hao Ge <hao.ge@linux.dev> <gehao@kylinos.cn> Harry Yoo <harry.yoo@oracle.com> <42.hyeyoo@gmail.com> +Harry Yoo <harry@kernel.org> <harry.yoo@oracle.com> Heiko Carstens <hca@linux.ibm.com> <h.carstens@de.ibm.com> Heiko Carstens <hca@linux.ibm.com> <heiko.carstens@de.ibm.com> Heiko Stuebner <heiko@sntech.de> <heiko.stuebner@bqreaders.com> diff --git a/MAINTAINERS b/MAINTAINERS index 23d88c825175..5969f7b00761 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -16883,7 +16883,7 @@ M: Lorenzo Stoakes <ljs@kernel.org> R: Rik van Riel <riel@surriel.com> R: Liam R. Howlett <Liam.Howlett@oracle.com> R: Vlastimil Babka <vbabka@kernel.org> -R: Harry Yoo <harry.yoo@oracle.com> +R: Harry Yoo <harry@kernel.org> R: Jann Horn <jannh@google.com> L: linux-mm@kvack.org S: Maintained @@ -24349,7 +24349,7 @@ F: drivers/nvmem/layouts/sl28vpd.c SLAB ALLOCATOR M: Vlastimil Babka <vbabka@kernel.org> -M: Harry Yoo <harry.yoo@oracle.com> +M: Harry Yoo <harry@kernel.org> M: Andrew Morton <akpm@linux-foundation.org> R: Hao Li <hao.li@linux.dev> R: Christoph Lameter <cl@gentwo.org> diff --git a/include/linux/leafops.h b/include/linux/leafops.h index a9ff94b744f2..05673d3529e7 100644 --- a/include/linux/leafops.h +++ b/include/linux/leafops.h @@ -363,6 +363,23 @@ static inline unsigned long softleaf_to_pfn(softleaf_t entry) return swp_offset(entry) & SWP_PFN_MASK; } +static inline void softleaf_migration_sync(softleaf_t entry, + struct folio *folio) +{ + /* + * Ensure we do not race with split, which might alter tail pages into new + * folios and thus result in observing an unlocked folio. + * This matches the write barrier in __split_folio_to_order(). + */ + smp_rmb(); + + /* + * Any use of migration entries may only occur while the + * corresponding page is locked + */ + VM_WARN_ON_ONCE(!folio_test_locked(folio)); +} + /** * softleaf_to_page() - Obtains struct page for PFN encoded within leaf entry. * @entry: Leaf entry, softleaf_has_pfn(@entry) must return true. @@ -374,11 +391,8 @@ static inline struct page *softleaf_to_page(softleaf_t entry) struct page *page = pfn_to_page(softleaf_to_pfn(entry)); VM_WARN_ON_ONCE(!softleaf_has_pfn(entry)); - /* - * Any use of migration entries may only occur while the - * corresponding page is locked - */ - VM_WARN_ON_ONCE(softleaf_is_migration(entry) && !PageLocked(page)); + if (softleaf_is_migration(entry)) + softleaf_migration_sync(entry, page_folio(page)); return page; } @@ -394,12 +408,8 @@ static inline struct folio *softleaf_to_folio(softleaf_t entry) struct folio *folio = pfn_folio(softleaf_to_pfn(entry)); VM_WARN_ON_ONCE(!softleaf_has_pfn(entry)); - /* - * Any use of migration entries may only occur while the - * corresponding folio is locked. - */ - VM_WARN_ON_ONCE(softleaf_is_migration(entry) && - !folio_test_locked(folio)); + if (softleaf_is_migration(entry)) + softleaf_migration_sync(entry, folio); return folio; } diff --git a/lib/bug.c b/lib/bug.c index 623c467a8b76..aab9e6a40c5f 100644 --- a/lib/bug.c +++ b/lib/bug.c @@ -173,10 +173,8 @@ struct bug_entry *find_bug(unsigned long bugaddr) return module_find_bug(bugaddr); } -__diag_push(); -__diag_ignore(GCC, all, "-Wsuggest-attribute=format", - "Not a valid __printf() conversion candidate."); -static void __warn_printf(const char *fmt, struct pt_regs *regs) +static __printf(1, 0) +void __warn_printf(const char *fmt, struct pt_regs *regs) { if (!fmt) return; @@ -195,7 +193,6 @@ static void __warn_printf(const char *fmt, struct pt_regs *regs) printk("%s", fmt); } -__diag_pop(); static enum bug_trap_type __report_bug(struct bug_entry *bug, unsigned long bugaddr, struct pt_regs *regs) { diff --git a/mm/damon/sysfs.c b/mm/damon/sysfs.c index 576d1ddd736b..6a44a2f3d8fc 100644 --- a/mm/damon/sysfs.c +++ b/mm/damon/sysfs.c @@ -1524,8 +1524,10 @@ static int damon_sysfs_commit_input(void *data) if (IS_ERR(param_ctx)) return PTR_ERR(param_ctx); test_ctx = damon_sysfs_new_test_ctx(kdamond->damon_ctx); - if (!test_ctx) + if (!test_ctx) { + damon_destroy_ctx(param_ctx); return -ENOMEM; + } err = damon_commit_ctx(test_ctx, param_ctx); if (err) goto out; @@ -1618,9 +1620,12 @@ static int damon_sysfs_repeat_call_fn(void *data) if (!mutex_trylock(&damon_sysfs_lock)) return 0; + if (sysfs_kdamond->contexts->nr != 1) + goto out; damon_sysfs_upd_tuned_intervals(sysfs_kdamond); damon_sysfs_upd_schemes_stats(sysfs_kdamond); damon_sysfs_upd_schemes_effective_quotas(sysfs_kdamond); +out: mutex_unlock(&damon_sysfs_lock); return 0; } @@ -1747,6 +1752,9 @@ static int damon_sysfs_update_schemes_tried_regions( static int damon_sysfs_handle_cmd(enum damon_sysfs_cmd cmd, struct damon_sysfs_kdamond *kdamond) { + if (cmd != DAMON_SYSFS_CMD_OFF && kdamond->contexts->nr != 1) + return -EINVAL; + switch (cmd) { case DAMON_SYSFS_CMD_ON: return damon_sysfs_turn_damon_on(kdamond); diff --git a/mm/memory.c b/mm/memory.c index 2f815a34d924..c65e82c86fed 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -6815,11 +6815,16 @@ retry: pudp = pud_offset(p4dp, address); pud = pudp_get(pudp); - if (pud_none(pud)) + if (!pud_present(pud)) goto out; if (pud_leaf(pud)) { lock = pud_lock(mm, pudp); - if (!unlikely(pud_leaf(pud))) { + pud = pudp_get(pudp); + + if (unlikely(!pud_present(pud))) { + spin_unlock(lock); + goto out; + } else if (unlikely(!pud_leaf(pud))) { spin_unlock(lock); goto retry; } @@ -6831,9 +6836,16 @@ retry: pmdp = pmd_offset(pudp, address); pmd = pmdp_get_lockless(pmdp); + if (!pmd_present(pmd)) + goto out; if (pmd_leaf(pmd)) { lock = pmd_lock(mm, pmdp); - if (!unlikely(pmd_leaf(pmd))) { + pmd = pmdp_get(pmdp); + + if (unlikely(!pmd_present(pmd))) { + spin_unlock(lock); + goto out; + } else if (unlikely(!pmd_leaf(pmd))) { spin_unlock(lock); goto retry; } diff --git a/mm/mseal.c b/mm/mseal.c index 316b5e1dec78..ac58643181f7 100644 --- a/mm/mseal.c +++ b/mm/mseal.c @@ -56,7 +56,6 @@ static int mseal_apply(struct mm_struct *mm, unsigned long start, unsigned long end) { struct vm_area_struct *vma, *prev; - unsigned long curr_start = start; VMA_ITERATOR(vmi, mm, start); /* We know there are no gaps so this will be non-NULL. */ @@ -66,6 +65,7 @@ static int mseal_apply(struct mm_struct *mm, prev = vma; for_each_vma_range(vmi, vma, end) { + const unsigned long curr_start = MAX(vma->vm_start, start); const unsigned long curr_end = MIN(vma->vm_end, end); if (!(vma->vm_flags & VM_SEALED)) { @@ -79,7 +79,6 @@ static int mseal_apply(struct mm_struct *mm, } prev = vma; - curr_start = curr_end; } return 0; diff --git a/mm/pagewalk.c b/mm/pagewalk.c index a94c401ab2cf..4e7bcd975c54 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -97,6 +97,7 @@ static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, struct mm_walk *walk) { + pud_t pudval = pudp_get(pud); pmd_t *pmd; unsigned long next; const struct mm_walk_ops *ops = walk->ops; @@ -105,6 +106,24 @@ static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, int err = 0; int depth = real_depth(3); + /* + * For PTE handling, pte_offset_map_lock() takes care of checking + * whether there actually is a page table. But it also has to be + * very careful about concurrent page table reclaim. + * + * Similarly, we have to be careful here - a PUD entry that points + * to a PMD table cannot go away, so we can just walk it. But if + * it's something else, we need to ensure we didn't race something, + * so need to retry. + * + * A pertinent example of this is a PUD refault after PUD split - + * we will need to split again or risk accessing invalid memory. + */ + if (!pud_present(pudval) || pud_leaf(pudval)) { + walk->action = ACTION_AGAIN; + return 0; + } + pmd = pmd_offset(pud, addr); do { again: @@ -218,12 +237,12 @@ static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, else if (pud_leaf(*pud) || !pud_present(*pud)) continue; /* Nothing to do. */ - if (pud_none(*pud)) - goto again; - err = walk_pmd_range(pud, addr, next, walk); if (err) break; + + if (walk->action == ACTION_AGAIN) + goto again; } while (pud++, addr = next, addr != end); return err; diff --git a/mm/swap_state.c b/mm/swap_state.c index 6d0eef7470be..48aff2c917c0 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -494,6 +494,10 @@ static struct folio *__swap_cache_prepare_and_add(swp_entry_t entry, __folio_set_locked(folio); __folio_set_swapbacked(folio); + + if (!charged && mem_cgroup_swapin_charge_folio(folio, NULL, gfp, entry)) + goto failed; + for (;;) { ret = swap_cache_add_folio(folio, entry, &shadow); if (!ret) @@ -514,11 +518,6 @@ static struct folio *__swap_cache_prepare_and_add(swp_entry_t entry, goto failed; } - if (!charged && mem_cgroup_swapin_charge_folio(folio, NULL, gfp, entry)) { - swap_cache_del_folio(folio); - goto failed; - } - memcg1_swapin(entry, folio_nr_pages(folio)); if (shadow) workingset_refault(folio, shadow); |