From e66f3185fa04ccb807c6fbf0ea066574f4308831 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Sun, 27 Oct 2024 12:59:34 -0700 Subject: [PATCH 1/7] mm/thp: fix deferred split queue not partially_mapped Recent changes are putting more pressure on THP deferred split queues: under load revealing long-standing races, causing list_del corruptions, "Bad page state"s and worse (I keep BUGs in both of those, so usually don't get to see how badly they end up without). The relevant recent changes being 6.8's mTHP, 6.10's mTHP swapout, and 6.12's mTHP swapin, improved swap allocation, and underused THP splitting. The new unlocked list_del_init() in deferred_split_scan() is buggy. I gave bad advice, it looks plausible since that's a local on-stack list, but the fact is that it can race with a third party freeing or migrating the preceding folio (properly unqueueing it with refcount 0 while holding split_queue_lock), thereby corrupting the list linkage. The obvious answer would be to take split_queue_lock there: but it has a long history of contention, so I'm reluctant to add to that. Instead, make sure that there is always one safe (raised refcount) folio before, by delaying its folio_put(). (And of course I was wrong to suggest updating split_queue_len without the lock: leave that until the splice.) And remove two over-eager partially_mapped checks, restoring those tests to how they were before: if uncharge_folio() or free_tail_page_prepare() finds _deferred_list non-empty, it's in trouble whether or not that folio is partially_mapped (and the flag was already cleared in the latter case). Link: https://lkml.kernel.org/r/81e34a8b-113a-0701-740e-2135c97eb1d7@google.com Fixes: dafff3f4c850 ("mm: split underused THPs") Signed-off-by: Hugh Dickins Acked-by: Usama Arif Reviewed-by: David Hildenbrand Reviewed-by: Baolin Wang Acked-by: Zi Yan Cc: Barry Song Cc: Chris Li Cc: Johannes Weiner Cc: Kefeng Wang Cc: Kirill A. Shutemov Cc: Matthew Wilcox (Oracle) Cc: Nhat Pham Cc: Ryan Roberts Cc: Shakeel Butt Cc: Wei Yang Cc: Yang Shi Signed-off-by: Andrew Morton --- mm/huge_memory.c | 21 +++++++++++++++++---- mm/memcontrol.c | 3 +-- mm/page_alloc.c | 5 ++--- 3 files changed, 20 insertions(+), 9 deletions(-) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 2fb328880b509..a1d345f1680cb 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -3718,8 +3718,8 @@ static unsigned long deferred_split_scan(struct shrinker *shrink, struct deferred_split *ds_queue = &pgdata->deferred_split_queue; unsigned long flags; LIST_HEAD(list); - struct folio *folio, *next; - int split = 0; + struct folio *folio, *next, *prev = NULL; + int split = 0, removed = 0; #ifdef CONFIG_MEMCG if (sc->memcg) @@ -3775,15 +3775,28 @@ static unsigned long deferred_split_scan(struct shrinker *shrink, */ if (!did_split && !folio_test_partially_mapped(folio)) { list_del_init(&folio->_deferred_list); - ds_queue->split_queue_len--; + removed++; + } else { + /* + * That unlocked list_del_init() above would be unsafe, + * unless its folio is separated from any earlier folios + * left on the list (which may be concurrently unqueued) + * by one safe folio with refcount still raised. + */ + swap(folio, prev); } - folio_put(folio); + if (folio) + folio_put(folio); } spin_lock_irqsave(&ds_queue->split_queue_lock, flags); list_splice_tail(&list, &ds_queue->split_queue); + ds_queue->split_queue_len -= removed; spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags); + if (prev) + folio_put(prev); + /* * Stop shrinker if we didn't split any page, but the queue is empty. * This can happen if pages were freed under us. diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 7845c64a2c570..2703227cce88b 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4631,8 +4631,7 @@ static void uncharge_folio(struct folio *folio, struct uncharge_gather *ug) VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); VM_BUG_ON_FOLIO(folio_order(folio) > 1 && !folio_test_hugetlb(folio) && - !list_empty(&folio->_deferred_list) && - folio_test_partially_mapped(folio), folio); + !list_empty(&folio->_deferred_list), folio); /* * Nobody should be changing or seriously looking at diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 94a2ffe280089..5e108ae755cc9 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -961,9 +961,8 @@ static int free_tail_page_prepare(struct page *head_page, struct page *page) break; case 2: /* the second tail page: deferred_list overlaps ->mapping */ - if (unlikely(!list_empty(&folio->_deferred_list) && - folio_test_partially_mapped(folio))) { - bad_page(page, "partially mapped folio on deferred list"); + if (unlikely(!list_empty(&folio->_deferred_list))) { + bad_page(page, "on deferred list"); goto out; } break; From f8f931bba0f92052cf842b7e30917b1afcc77d5a Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Sun, 27 Oct 2024 13:02:13 -0700 Subject: [PATCH 2/7] mm/thp: fix deferred split unqueue naming and locking Recent changes are putting more pressure on THP deferred split queues: under load revealing long-standing races, causing list_del corruptions, "Bad page state"s and worse (I keep BUGs in both of those, so usually don't get to see how badly they end up without). The relevant recent changes being 6.8's mTHP, 6.10's mTHP swapout, and 6.12's mTHP swapin, improved swap allocation, and underused THP splitting. Before fixing locking: rename misleading folio_undo_large_rmappable(), which does not undo large_rmappable, to folio_unqueue_deferred_split(), which is what it does. But that and its out-of-line __callee are mm internals of very limited usability: add comment and WARN_ON_ONCEs to check usage; and return a bool to say if a deferred split was unqueued, which can then be used in WARN_ON_ONCEs around safety checks (sparing callers the arcane conditionals in __folio_unqueue_deferred_split()). Just omit the folio_unqueue_deferred_split() from free_unref_folios(), all of whose callers now call it beforehand (and if any forget then bad_page() will tell) - except for its caller put_pages_list(), which itself no longer has any callers (and will be deleted separately). Swapout: mem_cgroup_swapout() has been resetting folio->memcg_data 0 without checking and unqueueing a THP folio from deferred split list; which is unfortunate, since the split_queue_lock depends on the memcg (when memcg is enabled); so swapout has been unqueueing such THPs later, when freeing the folio, using the pgdat's lock instead: potentially corrupting the memcg's list. __remove_mapping() has frozen refcount to 0 here, so no problem with calling folio_unqueue_deferred_split() before resetting memcg_data. That goes back to 5.4 commit 87eaceb3faa5 ("mm: thp: make deferred split shrinker memcg aware"): which included a check on swapcache before adding to deferred queue, but no check on deferred queue before adding THP to swapcache. That worked fine with the usual sequence of events in reclaim (though there were a couple of rare ways in which a THP on deferred queue could have been swapped out), but 6.12 commit dafff3f4c850 ("mm: split underused THPs") avoids splitting underused THPs in reclaim, which makes swapcache THPs on deferred queue commonplace. Keep the check on swapcache before adding to deferred queue? Yes: it is no longer essential, but preserves the existing behaviour, and is likely to be a worthwhile optimization (vmstat showed much more traffic on the queue under swapping load if the check was removed); update its comment. Memcg-v1 move (deprecated): mem_cgroup_move_account() has been changing folio->memcg_data without checking and unqueueing a THP folio from the deferred list, sometimes corrupting "from" memcg's list, like swapout. Refcount is non-zero here, so folio_unqueue_deferred_split() can only be used in a WARN_ON_ONCE to validate the fix, which must be done earlier: mem_cgroup_move_charge_pte_range() first try to split the THP (splitting of course unqueues), or skip it if that fails. Not ideal, but moving charge has been requested, and khugepaged should repair the THP later: nobody wants new custom unqueueing code just for this deprecated case. The 87eaceb3faa5 commit did have the code to move from one deferred list to another (but was not conscious of its unsafety while refcount non-0); but that was removed by 5.6 commit fac0516b5534 ("mm: thp: don't need care deferred split queue in memcg charge move path"), which argued that the existence of a PMD mapping guarantees that the THP cannot be on a deferred list. As above, false in rare cases, and now commonly false. Backport to 6.11 should be straightforward. Earlier backports must take care that other _deferred_list fixes and dependencies are included. There is not a strong case for backports, but they can fix cornercases. Link: https://lkml.kernel.org/r/8dc111ae-f6db-2da7-b25c-7a20b1effe3b@google.com Fixes: 87eaceb3faa5 ("mm: thp: make deferred split shrinker memcg aware") Fixes: dafff3f4c850 ("mm: split underused THPs") Signed-off-by: Hugh Dickins Acked-by: David Hildenbrand Reviewed-by: Yang Shi Cc: Baolin Wang Cc: Barry Song Cc: Chris Li Cc: Johannes Weiner Cc: Kefeng Wang Cc: Kirill A. Shutemov Cc: Matthew Wilcox (Oracle) Cc: Nhat Pham Cc: Ryan Roberts Cc: Shakeel Butt Cc: Usama Arif Cc: Wei Yang Cc: Zi Yan Cc: Signed-off-by: Andrew Morton --- mm/huge_memory.c | 35 ++++++++++++++++++++++++++--------- mm/internal.h | 10 +++++----- mm/memcontrol-v1.c | 25 +++++++++++++++++++++++++ mm/memcontrol.c | 8 +++++--- mm/migrate.c | 4 ++-- mm/page_alloc.c | 1 - mm/swap.c | 4 ++-- mm/vmscan.c | 4 ++-- 8 files changed, 67 insertions(+), 24 deletions(-) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index a1d345f1680cb..03fd4bc39ea15 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -3588,10 +3588,27 @@ int split_folio_to_list(struct folio *folio, struct list_head *list) return split_huge_page_to_list_to_order(&folio->page, list, ret); } -void __folio_undo_large_rmappable(struct folio *folio) +/* + * __folio_unqueue_deferred_split() is not to be called directly: + * the folio_unqueue_deferred_split() inline wrapper in mm/internal.h + * limits its calls to those folios which may have a _deferred_list for + * queueing THP splits, and that list is (racily observed to be) non-empty. + * + * It is unsafe to call folio_unqueue_deferred_split() until folio refcount is + * zero: because even when split_queue_lock is held, a non-empty _deferred_list + * might be in use on deferred_split_scan()'s unlocked on-stack list. + * + * If memory cgroups are enabled, split_queue_lock is in the mem_cgroup: it is + * therefore important to unqueue deferred split before changing folio memcg. + */ +bool __folio_unqueue_deferred_split(struct folio *folio) { struct deferred_split *ds_queue; unsigned long flags; + bool unqueued = false; + + WARN_ON_ONCE(folio_ref_count(folio)); + WARN_ON_ONCE(!mem_cgroup_disabled() && !folio_memcg(folio)); ds_queue = get_deferred_split_queue(folio); spin_lock_irqsave(&ds_queue->split_queue_lock, flags); @@ -3603,8 +3620,11 @@ void __folio_undo_large_rmappable(struct folio *folio) MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1); } list_del_init(&folio->_deferred_list); + unqueued = true; } spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags); + + return unqueued; /* useful for debug warnings */ } /* partially_mapped=false won't clear PG_partially_mapped folio flag */ @@ -3627,14 +3647,11 @@ void deferred_split_folio(struct folio *folio, bool partially_mapped) return; /* - * The try_to_unmap() in page reclaim path might reach here too, - * this may cause a race condition to corrupt deferred split queue. - * And, if page reclaim is already handling the same folio, it is - * unnecessary to handle it again in shrinker. - * - * Check the swapcache flag to determine if the folio is being - * handled by page reclaim since THP swap would add the folio into - * swap cache before calling try_to_unmap(). + * Exclude swapcache: originally to avoid a corrupt deferred split + * queue. Nowadays that is fully prevented by mem_cgroup_swapout(); + * but if page reclaim is already handling the same folio, it is + * unnecessary to handle it again in the shrinker, so excluding + * swapcache here may still be a useful optimization. */ if (folio_test_swapcache(folio)) return; diff --git a/mm/internal.h b/mm/internal.h index 93083bbeeefae..16c1f3cd599e5 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -639,11 +639,11 @@ static inline void folio_set_order(struct folio *folio, unsigned int order) #endif } -void __folio_undo_large_rmappable(struct folio *folio); -static inline void folio_undo_large_rmappable(struct folio *folio) +bool __folio_unqueue_deferred_split(struct folio *folio); +static inline bool folio_unqueue_deferred_split(struct folio *folio) { if (folio_order(folio) <= 1 || !folio_test_large_rmappable(folio)) - return; + return false; /* * At this point, there is no one trying to add the folio to @@ -651,9 +651,9 @@ static inline void folio_undo_large_rmappable(struct folio *folio) * to check without acquiring the split_queue_lock. */ if (data_race(list_empty(&folio->_deferred_list))) - return; + return false; - __folio_undo_large_rmappable(folio); + return __folio_unqueue_deferred_split(folio); } static inline struct folio *page_rmappable_folio(struct page *page) diff --git a/mm/memcontrol-v1.c b/mm/memcontrol-v1.c index 81d8819f13cdb..f8744f5630bb9 100644 --- a/mm/memcontrol-v1.c +++ b/mm/memcontrol-v1.c @@ -848,6 +848,8 @@ static int mem_cgroup_move_account(struct folio *folio, css_get(&to->css); css_put(&from->css); + /* Warning should never happen, so don't worry about refcount non-0 */ + WARN_ON_ONCE(folio_unqueue_deferred_split(folio)); folio->memcg_data = (unsigned long)to; __folio_memcg_unlock(from); @@ -1217,7 +1219,9 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd, enum mc_target_type target_type; union mc_target target; struct folio *folio; + bool tried_split_before = false; +retry_pmd: ptl = pmd_trans_huge_lock(pmd, vma); if (ptl) { if (mc.precharge < HPAGE_PMD_NR) { @@ -1227,6 +1231,27 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd, target_type = get_mctgt_type_thp(vma, addr, *pmd, &target); if (target_type == MC_TARGET_PAGE) { folio = target.folio; + /* + * Deferred split queue locking depends on memcg, + * and unqueue is unsafe unless folio refcount is 0: + * split or skip if on the queue? first try to split. + */ + if (!list_empty(&folio->_deferred_list)) { + spin_unlock(ptl); + if (!tried_split_before) + split_folio(folio); + folio_unlock(folio); + folio_put(folio); + if (tried_split_before) + return 0; + tried_split_before = true; + goto retry_pmd; + } + /* + * So long as that pmd lock is held, the folio cannot + * be racily added to the _deferred_list, because + * __folio_remove_rmap() will find !partially_mapped. + */ if (folio_isolate_lru(folio)) { if (!mem_cgroup_move_account(folio, true, mc.from, mc.to)) { diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 2703227cce88b..06df2af974159 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4629,9 +4629,6 @@ static void uncharge_folio(struct folio *folio, struct uncharge_gather *ug) struct obj_cgroup *objcg; VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); - VM_BUG_ON_FOLIO(folio_order(folio) > 1 && - !folio_test_hugetlb(folio) && - !list_empty(&folio->_deferred_list), folio); /* * Nobody should be changing or seriously looking at @@ -4678,6 +4675,7 @@ static void uncharge_folio(struct folio *folio, struct uncharge_gather *ug) ug->nr_memory += nr_pages; ug->pgpgout++; + WARN_ON_ONCE(folio_unqueue_deferred_split(folio)); folio->memcg_data = 0; } @@ -4789,6 +4787,9 @@ void mem_cgroup_migrate(struct folio *old, struct folio *new) /* Transfer the charge and the css ref */ commit_charge(new, memcg); + + /* Warning should never happen, so don't worry about refcount non-0 */ + WARN_ON_ONCE(folio_unqueue_deferred_split(old)); old->memcg_data = 0; } @@ -4975,6 +4976,7 @@ void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry) VM_BUG_ON_FOLIO(oldid, folio); mod_memcg_state(swap_memcg, MEMCG_SWAP, nr_entries); + folio_unqueue_deferred_split(folio); folio->memcg_data = 0; if (!mem_cgroup_is_root(memcg)) diff --git a/mm/migrate.c b/mm/migrate.c index fab84a7760889..dfa24e41e8f95 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -490,7 +490,7 @@ static int __folio_migrate_mapping(struct address_space *mapping, folio_test_large_rmappable(folio)) { if (!folio_ref_freeze(folio, expected_count)) return -EAGAIN; - folio_undo_large_rmappable(folio); + folio_unqueue_deferred_split(folio); folio_ref_unfreeze(folio, expected_count); } @@ -515,7 +515,7 @@ static int __folio_migrate_mapping(struct address_space *mapping, } /* Take off deferred split queue while frozen and memcg set */ - folio_undo_large_rmappable(folio); + folio_unqueue_deferred_split(folio); /* * Now we know that no one else is looking at the folio: diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 5e108ae755cc9..8ad38cd5e574b 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2681,7 +2681,6 @@ void free_unref_folios(struct folio_batch *folios) unsigned long pfn = folio_pfn(folio); unsigned int order = folio_order(folio); - folio_undo_large_rmappable(folio); if (!free_pages_prepare(&folio->page, order)) continue; /* diff --git a/mm/swap.c b/mm/swap.c index 835bdf324b76e..b8e3259ea2c47 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -121,7 +121,7 @@ void __folio_put(struct folio *folio) } page_cache_release(folio); - folio_undo_large_rmappable(folio); + folio_unqueue_deferred_split(folio); mem_cgroup_uncharge(folio); free_unref_page(&folio->page, folio_order(folio)); } @@ -988,7 +988,7 @@ void folios_put_refs(struct folio_batch *folios, unsigned int *refs) free_huge_folio(folio); continue; } - folio_undo_large_rmappable(folio); + folio_unqueue_deferred_split(folio); __page_cache_release(folio, &lruvec, &flags); if (j != i) diff --git a/mm/vmscan.c b/mm/vmscan.c index ddaaff67642e1..28ba2b06fc7dc 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1476,7 +1476,7 @@ static unsigned int shrink_folio_list(struct list_head *folio_list, */ nr_reclaimed += nr_pages; - folio_undo_large_rmappable(folio); + folio_unqueue_deferred_split(folio); if (folio_batch_add(&free_folios, folio) == 0) { mem_cgroup_uncharge_folios(&free_folios); try_to_unmap_flush(); @@ -1864,7 +1864,7 @@ static unsigned int move_folios_to_lru(struct lruvec *lruvec, if (unlikely(folio_put_testzero(folio))) { __folio_clear_lru_flags(folio); - folio_undo_large_rmappable(folio); + folio_unqueue_deferred_split(folio); if (folio_batch_add(&free_folios, folio) == 0) { spin_unlock_irq(&lruvec->lru_lock); mem_cgroup_uncharge_folios(&free_folios); From 3dd6ed34ce1f2356a77fb88edafb5ec96784e3cf Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Tue, 29 Oct 2024 18:11:44 +0000 Subject: [PATCH 3/7] mm: avoid unsafe VMA hook invocation when error arises on mmap hook Patch series "fix error handling in mmap_region() and refactor (hotfixes)", v4. mmap_region() is somewhat terrifying, with spaghetti-like control flow and numerous means by which issues can arise and incomplete state, memory leaks and other unpleasantness can occur. A large amount of the complexity arises from trying to handle errors late in the process of mapping a VMA, which forms the basis of recently observed issues with resource leaks and observable inconsistent state. This series goes to great lengths to simplify how mmap_region() works and to avoid unwinding errors late on in the process of setting up the VMA for the new mapping, and equally avoids such operations occurring while the VMA is in an inconsistent state. The patches in this series comprise the minimal changes required to resolve existing issues in mmap_region() error handling, in order that they can be hotfixed and backported. There is additionally a follow up series which goes further, separated out from the v1 series and sent and updated separately. This patch (of 5): After an attempted mmap() fails, we are no longer in a situation where we can safely interact with VMA hooks. This is currently not enforced, meaning that we need complicated handling to ensure we do not incorrectly call these hooks. We can avoid the whole issue by treating the VMA as suspect the moment that the file->f_ops->mmap() function reports an error by replacing whatever VMA operations were installed with a dummy empty set of VMA operations. We do so through a new helper function internal to mm - mmap_file() - which is both more logically named than the existing call_mmap() function and correctly isolates handling of the vm_op reassignment to mm. All the existing invocations of call_mmap() outside of mm are ultimately nested within the call_mmap() from mm, which we now replace. It is therefore safe to leave call_mmap() in place as a convenience function (and to avoid churn). The invokers are: ovl_file_operations -> mmap -> ovl_mmap() -> backing_file_mmap() coda_file_operations -> mmap -> coda_file_mmap() shm_file_operations -> shm_mmap() shm_file_operations_huge -> shm_mmap() dma_buf_fops -> dma_buf_mmap_internal -> i915_dmabuf_ops -> i915_gem_dmabuf_mmap() None of these callers interact with vm_ops or mappings in a problematic way on error, quickly exiting out. Link: https://lkml.kernel.org/r/cover.1730224667.git.lorenzo.stoakes@oracle.com Link: https://lkml.kernel.org/r/d41fd763496fd0048a962f3fd9407dc72dd4fd86.1730224667.git.lorenzo.stoakes@oracle.com Fixes: deb0f6562884 ("mm/mmap: undo ->mmap() when arch_validate_flags() fails") Signed-off-by: Lorenzo Stoakes Reported-by: Jann Horn Reviewed-by: Liam R. Howlett Reviewed-by: Vlastimil Babka Reviewed-by: Jann Horn Cc: Andreas Larsson Cc: Catalin Marinas Cc: David S. Miller Cc: Helge Deller Cc: James E.J. Bottomley Cc: Linus Torvalds Cc: Mark Brown Cc: Peter Xu Cc: Will Deacon Cc: Signed-off-by: Andrew Morton --- mm/internal.h | 27 +++++++++++++++++++++++++++ mm/mmap.c | 6 +++--- mm/nommu.c | 4 ++-- 3 files changed, 32 insertions(+), 5 deletions(-) diff --git a/mm/internal.h b/mm/internal.h index 16c1f3cd599e5..4eab2961e69ce 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -108,6 +108,33 @@ static inline void *folio_raw_mapping(const struct folio *folio) return (void *)(mapping & ~PAGE_MAPPING_FLAGS); } +/* + * This is a file-backed mapping, and is about to be memory mapped - invoke its + * mmap hook and safely handle error conditions. On error, VMA hooks will be + * mutated. + * + * @file: File which backs the mapping. + * @vma: VMA which we are mapping. + * + * Returns: 0 if success, error otherwise. + */ +static inline int mmap_file(struct file *file, struct vm_area_struct *vma) +{ + int err = call_mmap(file, vma); + + if (likely(!err)) + return 0; + + /* + * OK, we tried to call the file hook for mmap(), but an error + * arose. The mapping is in an inconsistent state and we most not invoke + * any further hooks on it. + */ + vma->vm_ops = &vma_dummy_vm_ops; + + return err; +} + #ifdef CONFIG_MMU /* Flags for folio_pte_batch(). */ diff --git a/mm/mmap.c b/mm/mmap.c index 9841b41e3c762..6e3b25f7728f9 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1422,7 +1422,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr, /* * clear PTEs while the vma is still in the tree so that rmap * cannot race with the freeing later in the truncate scenario. - * This is also needed for call_mmap(), which is why vm_ops + * This is also needed for mmap_file(), which is why vm_ops * close function is called. */ vms_clean_up_area(&vms, &mas_detach); @@ -1447,7 +1447,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr, if (file) { vma->vm_file = get_file(file); - error = call_mmap(file, vma); + error = mmap_file(file, vma); if (error) goto unmap_and_free_vma; @@ -1470,7 +1470,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr, vma_iter_config(&vmi, addr, end); /* - * If vm_flags changed after call_mmap(), we should try merge + * If vm_flags changed after mmap_file(), we should try merge * vma again as we may succeed this time. */ if (unlikely(vm_flags != vma->vm_flags && vmg.prev)) { diff --git a/mm/nommu.c b/mm/nommu.c index 385b0c15add89..f9ccc02458ec6 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -885,7 +885,7 @@ static int do_mmap_shared_file(struct vm_area_struct *vma) { int ret; - ret = call_mmap(vma->vm_file, vma); + ret = mmap_file(vma->vm_file, vma); if (ret == 0) { vma->vm_region->vm_top = vma->vm_region->vm_end; return 0; @@ -918,7 +918,7 @@ static int do_mmap_private(struct vm_area_struct *vma, * happy. */ if (capabilities & NOMMU_MAP_DIRECT) { - ret = call_mmap(vma->vm_file, vma); + ret = mmap_file(vma->vm_file, vma); /* shouldn't return success if we're not sharing */ if (WARN_ON_ONCE(!is_nommu_shared_mapping(vma->vm_flags))) ret = -ENOSYS; From 4080ef1579b2413435413988d14ac8c68e4d42c8 Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Tue, 29 Oct 2024 18:11:45 +0000 Subject: [PATCH 4/7] mm: unconditionally close VMAs on error Incorrect invocation of VMA callbacks when the VMA is no longer in a consistent state is bug prone and risky to perform. With regards to the important vm_ops->close() callback We have gone to great lengths to try to track whether or not we ought to close VMAs. Rather than doing so and risking making a mistake somewhere, instead unconditionally close and reset vma->vm_ops to an empty dummy operations set with a NULL .close operator. We introduce a new function to do so - vma_close() - and simplify existing vms logic which tracked whether we needed to close or not. This simplifies the logic, avoids incorrect double-calling of the .close() callback and allows us to update error paths to simply call vma_close() unconditionally - making VMA closure idempotent. Link: https://lkml.kernel.org/r/28e89dda96f68c505cb6f8e9fc9b57c3e9f74b42.1730224667.git.lorenzo.stoakes@oracle.com Fixes: deb0f6562884 ("mm/mmap: undo ->mmap() when arch_validate_flags() fails") Signed-off-by: Lorenzo Stoakes Reported-by: Jann Horn Reviewed-by: Vlastimil Babka Reviewed-by: Liam R. Howlett Reviewed-by: Jann Horn Cc: Andreas Larsson Cc: Catalin Marinas Cc: David S. Miller Cc: Helge Deller Cc: James E.J. Bottomley Cc: Linus Torvalds Cc: Mark Brown Cc: Peter Xu Cc: Will Deacon Cc: Signed-off-by: Andrew Morton --- mm/internal.h | 18 ++++++++++++++++++ mm/mmap.c | 5 ++--- mm/nommu.c | 3 +-- mm/vma.c | 14 +++++--------- mm/vma.h | 4 +--- 5 files changed, 27 insertions(+), 17 deletions(-) diff --git a/mm/internal.h b/mm/internal.h index 4eab2961e69ce..64c2eb0b160e1 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -135,6 +135,24 @@ static inline int mmap_file(struct file *file, struct vm_area_struct *vma) return err; } +/* + * If the VMA has a close hook then close it, and since closing it might leave + * it in an inconsistent state which makes the use of any hooks suspect, clear + * them down by installing dummy empty hooks. + */ +static inline void vma_close(struct vm_area_struct *vma) +{ + if (vma->vm_ops && vma->vm_ops->close) { + vma->vm_ops->close(vma); + + /* + * The mapping is in an inconsistent state, and no further hooks + * may be invoked upon it. + */ + vma->vm_ops = &vma_dummy_vm_ops; + } +} + #ifdef CONFIG_MMU /* Flags for folio_pte_batch(). */ diff --git a/mm/mmap.c b/mm/mmap.c index 6e3b25f7728f9..ac0604f146f6e 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1573,8 +1573,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr, return addr; close_and_free_vma: - if (file && !vms.closed_vm_ops && vma->vm_ops && vma->vm_ops->close) - vma->vm_ops->close(vma); + vma_close(vma); if (file || vma->vm_file) { unmap_and_free_vma: @@ -1934,7 +1933,7 @@ void exit_mmap(struct mm_struct *mm) do { if (vma->vm_flags & VM_ACCOUNT) nr_accounted += vma_pages(vma); - remove_vma(vma, /* unreachable = */ true, /* closed = */ false); + remove_vma(vma, /* unreachable = */ true); count++; cond_resched(); vma = vma_next(&vmi); diff --git a/mm/nommu.c b/mm/nommu.c index f9ccc02458ec6..635d028d647b3 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -589,8 +589,7 @@ static int delete_vma_from_mm(struct vm_area_struct *vma) */ static void delete_vma(struct mm_struct *mm, struct vm_area_struct *vma) { - if (vma->vm_ops && vma->vm_ops->close) - vma->vm_ops->close(vma); + vma_close(vma); if (vma->vm_file) fput(vma->vm_file); put_nommu_region(vma->vm_region); diff --git a/mm/vma.c b/mm/vma.c index b21ffec33f8e0..7621384d64cf5 100644 --- a/mm/vma.c +++ b/mm/vma.c @@ -323,11 +323,10 @@ static bool can_vma_merge_right(struct vma_merge_struct *vmg, /* * Close a vm structure and free it. */ -void remove_vma(struct vm_area_struct *vma, bool unreachable, bool closed) +void remove_vma(struct vm_area_struct *vma, bool unreachable) { might_sleep(); - if (!closed && vma->vm_ops && vma->vm_ops->close) - vma->vm_ops->close(vma); + vma_close(vma); if (vma->vm_file) fput(vma->vm_file); mpol_put(vma_policy(vma)); @@ -1115,9 +1114,7 @@ void vms_clean_up_area(struct vma_munmap_struct *vms, vms_clear_ptes(vms, mas_detach, true); mas_set(mas_detach, 0); mas_for_each(mas_detach, vma, ULONG_MAX) - if (vma->vm_ops && vma->vm_ops->close) - vma->vm_ops->close(vma); - vms->closed_vm_ops = true; + vma_close(vma); } /* @@ -1160,7 +1157,7 @@ void vms_complete_munmap_vmas(struct vma_munmap_struct *vms, /* Remove and clean up vmas */ mas_set(mas_detach, 0); mas_for_each(mas_detach, vma, ULONG_MAX) - remove_vma(vma, /* = */ false, vms->closed_vm_ops); + remove_vma(vma, /* unreachable = */ false); vm_unacct_memory(vms->nr_accounted); validate_mm(mm); @@ -1684,8 +1681,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, return new_vma; out_vma_link: - if (new_vma->vm_ops && new_vma->vm_ops->close) - new_vma->vm_ops->close(new_vma); + vma_close(new_vma); if (new_vma->vm_file) fput(new_vma->vm_file); diff --git a/mm/vma.h b/mm/vma.h index 55457cb682008..75558b5e9c8cd 100644 --- a/mm/vma.h +++ b/mm/vma.h @@ -42,7 +42,6 @@ struct vma_munmap_struct { int vma_count; /* Number of vmas that will be removed */ bool unlock; /* Unlock after the munmap */ bool clear_ptes; /* If there are outstanding PTE to be cleared */ - bool closed_vm_ops; /* call_mmap() was encountered, so vmas may be closed */ /* 1 byte hole */ unsigned long nr_pages; /* Number of pages being removed */ unsigned long locked_vm; /* Number of locked pages */ @@ -198,7 +197,6 @@ static inline void init_vma_munmap(struct vma_munmap_struct *vms, vms->unmap_start = FIRST_USER_ADDRESS; vms->unmap_end = USER_PGTABLES_CEILING; vms->clear_ptes = false; - vms->closed_vm_ops = false; } #endif @@ -269,7 +267,7 @@ int do_vmi_munmap(struct vma_iterator *vmi, struct mm_struct *mm, unsigned long start, size_t len, struct list_head *uf, bool unlock); -void remove_vma(struct vm_area_struct *vma, bool unreachable, bool closed); +void remove_vma(struct vm_area_struct *vma, bool unreachable); void unmap_region(struct ma_state *mas, struct vm_area_struct *vma, struct vm_area_struct *prev, struct vm_area_struct *next); From 0fb4a7ad270b3b209e510eb9dc5b07bf02b7edaf Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Tue, 29 Oct 2024 18:11:46 +0000 Subject: [PATCH 5/7] mm: refactor map_deny_write_exec() Refactor the map_deny_write_exec() to not unnecessarily require a VMA parameter but rather to accept VMA flags parameters, which allows us to use this function early in mmap_region() in a subsequent commit. While we're here, we refactor the function to be more readable and add some additional documentation. Link: https://lkml.kernel.org/r/6be8bb59cd7c68006ebb006eb9d8dc27104b1f70.1730224667.git.lorenzo.stoakes@oracle.com Fixes: deb0f6562884 ("mm/mmap: undo ->mmap() when arch_validate_flags() fails") Signed-off-by: Lorenzo Stoakes Reported-by: Jann Horn Reviewed-by: Liam R. Howlett Reviewed-by: Vlastimil Babka Reviewed-by: Jann Horn Cc: Andreas Larsson Cc: Catalin Marinas Cc: David S. Miller Cc: Helge Deller Cc: James E.J. Bottomley Cc: Linus Torvalds Cc: Mark Brown Cc: Peter Xu Cc: Will Deacon Cc: Signed-off-by: Andrew Morton --- include/linux/mman.h | 21 ++++++++++++++++++--- mm/mmap.c | 2 +- mm/mprotect.c | 2 +- mm/vma.h | 2 +- 4 files changed, 21 insertions(+), 6 deletions(-) diff --git a/include/linux/mman.h b/include/linux/mman.h index bcb201ab7a412..8ddca62d6460b 100644 --- a/include/linux/mman.h +++ b/include/linux/mman.h @@ -188,16 +188,31 @@ static inline bool arch_memory_deny_write_exec_supported(void) * * d) mmap(PROT_READ | PROT_EXEC) * mmap(PROT_READ | PROT_EXEC | PROT_BTI) + * + * This is only applicable if the user has set the Memory-Deny-Write-Execute + * (MDWE) protection mask for the current process. + * + * @old specifies the VMA flags the VMA originally possessed, and @new the ones + * we propose to set. + * + * Return: false if proposed change is OK, true if not ok and should be denied. */ -static inline bool map_deny_write_exec(struct vm_area_struct *vma, unsigned long vm_flags) +static inline bool map_deny_write_exec(unsigned long old, unsigned long new) { + /* If MDWE is disabled, we have nothing to deny. */ if (!test_bit(MMF_HAS_MDWE, ¤t->mm->flags)) return false; - if ((vm_flags & VM_EXEC) && (vm_flags & VM_WRITE)) + /* If the new VMA is not executable, we have nothing to deny. */ + if (!(new & VM_EXEC)) + return false; + + /* Under MDWE we do not accept newly writably executable VMAs... */ + if (new & VM_WRITE) return true; - if (!(vma->vm_flags & VM_EXEC) && (vm_flags & VM_EXEC)) + /* ...nor previously non-executable VMAs becoming executable. */ + if (!(old & VM_EXEC)) return true; return false; diff --git a/mm/mmap.c b/mm/mmap.c index ac0604f146f6e..ab71d4c3464cd 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1505,7 +1505,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr, vma_set_anonymous(vma); } - if (map_deny_write_exec(vma, vma->vm_flags)) { + if (map_deny_write_exec(vma->vm_flags, vma->vm_flags)) { error = -EACCES; goto close_and_free_vma; } diff --git a/mm/mprotect.c b/mm/mprotect.c index 0c5d6d06107de..6f450af3252eb 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -810,7 +810,7 @@ static int do_mprotect_pkey(unsigned long start, size_t len, break; } - if (map_deny_write_exec(vma, newflags)) { + if (map_deny_write_exec(vma->vm_flags, newflags)) { error = -EACCES; break; } diff --git a/mm/vma.h b/mm/vma.h index 75558b5e9c8cd..d58068c0ff2ea 100644 --- a/mm/vma.h +++ b/mm/vma.h @@ -42,7 +42,7 @@ struct vma_munmap_struct { int vma_count; /* Number of vmas that will be removed */ bool unlock; /* Unlock after the munmap */ bool clear_ptes; /* If there are outstanding PTE to be cleared */ - /* 1 byte hole */ + /* 2 byte hole */ unsigned long nr_pages; /* Number of pages being removed */ unsigned long locked_vm; /* Number of locked pages */ unsigned long nr_accounted; /* Number of VM_ACCOUNT pages */ From 5baf8b037debf4ec60108ccfeccb8636d1dbad81 Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Tue, 29 Oct 2024 18:11:47 +0000 Subject: [PATCH 6/7] mm: refactor arch_calc_vm_flag_bits() and arm64 MTE handling Currently MTE is permitted in two circumstances (desiring to use MTE having been specified by the VM_MTE flag) - where MAP_ANONYMOUS is specified, as checked by arch_calc_vm_flag_bits() and actualised by setting the VM_MTE_ALLOWED flag, or if the file backing the mapping is shmem, in which case we set VM_MTE_ALLOWED in shmem_mmap() when the mmap hook is activated in mmap_region(). The function that checks that, if VM_MTE is set, VM_MTE_ALLOWED is also set is the arm64 implementation of arch_validate_flags(). Unfortunately, we intend to refactor mmap_region() to perform this check earlier, meaning that in the case of a shmem backing we will not have invoked shmem_mmap() yet, causing the mapping to fail spuriously. It is inappropriate to set this architecture-specific flag in general mm code anyway, so a sensible resolution of this issue is to instead move the check somewhere else. We resolve this by setting VM_MTE_ALLOWED much earlier in do_mmap(), via the arch_calc_vm_flag_bits() call. This is an appropriate place to do this as we already check for the MAP_ANONYMOUS case here, and the shmem file case is simply a variant of the same idea - we permit RAM-backed memory. This requires a modification to the arch_calc_vm_flag_bits() signature to pass in a pointer to the struct file associated with the mapping, however this is not too egregious as this is only used by two architectures anyway - arm64 and parisc. So this patch performs this adjustment and removes the unnecessary assignment of VM_MTE_ALLOWED in shmem_mmap(). [akpm@linux-foundation.org: fix whitespace, per Catalin] Link: https://lkml.kernel.org/r/ec251b20ba1964fb64cf1607d2ad80c47f3873df.1730224667.git.lorenzo.stoakes@oracle.com Fixes: deb0f6562884 ("mm/mmap: undo ->mmap() when arch_validate_flags() fails") Signed-off-by: Lorenzo Stoakes Suggested-by: Catalin Marinas Reported-by: Jann Horn Reviewed-by: Catalin Marinas Reviewed-by: Vlastimil Babka Cc: Andreas Larsson Cc: David S. Miller Cc: Helge Deller Cc: James E.J. Bottomley Cc: Liam R. Howlett Cc: Linus Torvalds Cc: Mark Brown Cc: Peter Xu Cc: Will Deacon Cc: Signed-off-by: Andrew Morton --- arch/arm64/include/asm/mman.h | 10 +++++++--- arch/parisc/include/asm/mman.h | 5 +++-- include/linux/mman.h | 7 ++++--- mm/mmap.c | 2 +- mm/nommu.c | 2 +- mm/shmem.c | 3 --- 6 files changed, 16 insertions(+), 13 deletions(-) diff --git a/arch/arm64/include/asm/mman.h b/arch/arm64/include/asm/mman.h index 9e39217b4afbb..798d965760d43 100644 --- a/arch/arm64/include/asm/mman.h +++ b/arch/arm64/include/asm/mman.h @@ -6,6 +6,8 @@ #ifndef BUILD_VDSO #include +#include +#include #include static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot, @@ -31,19 +33,21 @@ static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot, } #define arch_calc_vm_prot_bits(prot, pkey) arch_calc_vm_prot_bits(prot, pkey) -static inline unsigned long arch_calc_vm_flag_bits(unsigned long flags) +static inline unsigned long arch_calc_vm_flag_bits(struct file *file, + unsigned long flags) { /* * Only allow MTE on anonymous mappings as these are guaranteed to be * backed by tags-capable memory. The vm_flags may be overridden by a * filesystem supporting MTE (RAM-based). */ - if (system_supports_mte() && (flags & MAP_ANONYMOUS)) + if (system_supports_mte() && + ((flags & MAP_ANONYMOUS) || shmem_file(file))) return VM_MTE_ALLOWED; return 0; } -#define arch_calc_vm_flag_bits(flags) arch_calc_vm_flag_bits(flags) +#define arch_calc_vm_flag_bits(file, flags) arch_calc_vm_flag_bits(file, flags) static inline bool arch_validate_prot(unsigned long prot, unsigned long addr __always_unused) diff --git a/arch/parisc/include/asm/mman.h b/arch/parisc/include/asm/mman.h index 89b6beeda0b86..663f587dc7896 100644 --- a/arch/parisc/include/asm/mman.h +++ b/arch/parisc/include/asm/mman.h @@ -2,6 +2,7 @@ #ifndef __ASM_MMAN_H__ #define __ASM_MMAN_H__ +#include #include /* PARISC cannot allow mdwe as it needs writable stacks */ @@ -11,7 +12,7 @@ static inline bool arch_memory_deny_write_exec_supported(void) } #define arch_memory_deny_write_exec_supported arch_memory_deny_write_exec_supported -static inline unsigned long arch_calc_vm_flag_bits(unsigned long flags) +static inline unsigned long arch_calc_vm_flag_bits(struct file *file, unsigned long flags) { /* * The stack on parisc grows upwards, so if userspace requests memory @@ -23,6 +24,6 @@ static inline unsigned long arch_calc_vm_flag_bits(unsigned long flags) return 0; } -#define arch_calc_vm_flag_bits(flags) arch_calc_vm_flag_bits(flags) +#define arch_calc_vm_flag_bits(file, flags) arch_calc_vm_flag_bits(file, flags) #endif /* __ASM_MMAN_H__ */ diff --git a/include/linux/mman.h b/include/linux/mman.h index 8ddca62d6460b..a842783ffa62b 100644 --- a/include/linux/mman.h +++ b/include/linux/mman.h @@ -2,6 +2,7 @@ #ifndef _LINUX_MMAN_H #define _LINUX_MMAN_H +#include #include #include @@ -94,7 +95,7 @@ static inline void vm_unacct_memory(long pages) #endif #ifndef arch_calc_vm_flag_bits -#define arch_calc_vm_flag_bits(flags) 0 +#define arch_calc_vm_flag_bits(file, flags) 0 #endif #ifndef arch_validate_prot @@ -151,13 +152,13 @@ calc_vm_prot_bits(unsigned long prot, unsigned long pkey) * Combine the mmap "flags" argument into "vm_flags" used internally. */ static inline unsigned long -calc_vm_flag_bits(unsigned long flags) +calc_vm_flag_bits(struct file *file, unsigned long flags) { return _calc_vm_trans(flags, MAP_GROWSDOWN, VM_GROWSDOWN ) | _calc_vm_trans(flags, MAP_LOCKED, VM_LOCKED ) | _calc_vm_trans(flags, MAP_SYNC, VM_SYNC ) | _calc_vm_trans(flags, MAP_STACK, VM_NOHUGEPAGE) | - arch_calc_vm_flag_bits(flags); + arch_calc_vm_flag_bits(file, flags); } unsigned long vm_commit_limit(void); diff --git a/mm/mmap.c b/mm/mmap.c index ab71d4c3464cd..aee5fa08ae5d1 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -344,7 +344,7 @@ unsigned long do_mmap(struct file *file, unsigned long addr, * to. we assume access permissions have been handled by the open * of the memory object, so we don't do any here. */ - vm_flags |= calc_vm_prot_bits(prot, pkey) | calc_vm_flag_bits(flags) | + vm_flags |= calc_vm_prot_bits(prot, pkey) | calc_vm_flag_bits(file, flags) | mm->def_flags | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC; /* Obtain the address to map to. we verify (or select) it and ensure diff --git a/mm/nommu.c b/mm/nommu.c index 635d028d647b3..e9b5f527ab5b4 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -842,7 +842,7 @@ static unsigned long determine_vm_flags(struct file *file, { unsigned long vm_flags; - vm_flags = calc_vm_prot_bits(prot, 0) | calc_vm_flag_bits(flags); + vm_flags = calc_vm_prot_bits(prot, 0) | calc_vm_flag_bits(file, flags); if (!file) { /* diff --git a/mm/shmem.c b/mm/shmem.c index 4ba1d00fabdaa..e87f5d6799a7b 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2733,9 +2733,6 @@ static int shmem_mmap(struct file *file, struct vm_area_struct *vma) if (ret) return ret; - /* arm64 - allow memory tagging on RAM-based files */ - vm_flags_set(vma, VM_MTE_ALLOWED); - file_accessed(file); /* This is anonymous shared memory if it is unlinked at the time of mmap */ if (inode->i_nlink) From 5de195060b2e251a835f622759550e6202167641 Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Tue, 29 Oct 2024 18:11:48 +0000 Subject: [PATCH 7/7] mm: resolve faulty mmap_region() error path behaviour The mmap_region() function is somewhat terrifying, with spaghetti-like control flow and numerous means by which issues can arise and incomplete state, memory leaks and other unpleasantness can occur. A large amount of the complexity arises from trying to handle errors late in the process of mapping a VMA, which forms the basis of recently observed issues with resource leaks and observable inconsistent state. Taking advantage of previous patches in this series we move a number of checks earlier in the code, simplifying things by moving the core of the logic into a static internal function __mmap_region(). Doing this allows us to perform a number of checks up front before we do any real work, and allows us to unwind the writable unmap check unconditionally as required and to perform a CONFIG_DEBUG_VM_MAPLE_TREE validation unconditionally also. We move a number of things here: 1. We preallocate memory for the iterator before we call the file-backed memory hook, allowing us to exit early and avoid having to perform complicated and error-prone close/free logic. We carefully free iterator state on both success and error paths. 2. The enclosing mmap_region() function handles the mapping_map_writable() logic early. Previously the logic had the mapping_map_writable() at the point of mapping a newly allocated file-backed VMA, and a matching mapping_unmap_writable() on success and error paths. We now do this unconditionally if this is a file-backed, shared writable mapping. If a driver changes the flags to eliminate VM_MAYWRITE, however doing so does not invalidate the seal check we just performed, and we in any case always decrement the counter in the wrapper. We perform a debug assert to ensure a driver does not attempt to do the opposite. 3. We also move arch_validate_flags() up into the mmap_region() function. This is only relevant on arm64 and sparc64, and the check is only meaningful for SPARC with ADI enabled. We explicitly add a warning for this arch if a driver invalidates this check, though the code ought eventually to be fixed to eliminate the need for this. With all of these measures in place, we no longer need to explicitly close the VMA on error paths, as we place all checks which might fail prior to a call to any driver mmap hook. This eliminates an entire class of errors, makes the code easier to reason about and more robust. Link: https://lkml.kernel.org/r/6e0becb36d2f5472053ac5d544c0edfe9b899e25.1730224667.git.lorenzo.stoakes@oracle.com Fixes: deb0f6562884 ("mm/mmap: undo ->mmap() when arch_validate_flags() fails") Signed-off-by: Lorenzo Stoakes Reported-by: Jann Horn Reviewed-by: Liam R. Howlett Reviewed-by: Vlastimil Babka Tested-by: Mark Brown Cc: Andreas Larsson Cc: Catalin Marinas Cc: David S. Miller Cc: Helge Deller Cc: James E.J. Bottomley Cc: Linus Torvalds Cc: Peter Xu Cc: Will Deacon Cc: Signed-off-by: Andrew Morton --- mm/mmap.c | 119 +++++++++++++++++++++++++++++------------------------- 1 file changed, 65 insertions(+), 54 deletions(-) diff --git a/mm/mmap.c b/mm/mmap.c index aee5fa08ae5d1..79d541f1502b2 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1358,20 +1358,18 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len, return do_vmi_munmap(&vmi, mm, start, len, uf, false); } -unsigned long mmap_region(struct file *file, unsigned long addr, +static unsigned long __mmap_region(struct file *file, unsigned long addr, unsigned long len, vm_flags_t vm_flags, unsigned long pgoff, struct list_head *uf) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma = NULL; pgoff_t pglen = PHYS_PFN(len); - struct vm_area_struct *merge; unsigned long charged = 0; struct vma_munmap_struct vms; struct ma_state mas_detach; struct maple_tree mt_detach; unsigned long end = addr + len; - bool writable_file_mapping = false; int error; VMA_ITERATOR(vmi, mm, addr); VMG_STATE(vmg, mm, &vmi, addr, end, vm_flags, pgoff); @@ -1445,28 +1443,26 @@ unsigned long mmap_region(struct file *file, unsigned long addr, vm_flags_init(vma, vm_flags); vma->vm_page_prot = vm_get_page_prot(vm_flags); + if (vma_iter_prealloc(&vmi, vma)) { + error = -ENOMEM; + goto free_vma; + } + if (file) { vma->vm_file = get_file(file); error = mmap_file(file, vma); if (error) - goto unmap_and_free_vma; - - if (vma_is_shared_maywrite(vma)) { - error = mapping_map_writable(file->f_mapping); - if (error) - goto close_and_free_vma; - - writable_file_mapping = true; - } + goto unmap_and_free_file_vma; + /* Drivers cannot alter the address of the VMA. */ + WARN_ON_ONCE(addr != vma->vm_start); /* - * Expansion is handled above, merging is handled below. - * Drivers should not alter the address of the VMA. + * Drivers should not permit writability when previously it was + * disallowed. */ - if (WARN_ON((addr != vma->vm_start))) { - error = -EINVAL; - goto close_and_free_vma; - } + VM_WARN_ON_ONCE(vm_flags != vma->vm_flags && + !(vm_flags & VM_MAYWRITE) && + (vma->vm_flags & VM_MAYWRITE)); vma_iter_config(&vmi, addr, end); /* @@ -1474,6 +1470,8 @@ unsigned long mmap_region(struct file *file, unsigned long addr, * vma again as we may succeed this time. */ if (unlikely(vm_flags != vma->vm_flags && vmg.prev)) { + struct vm_area_struct *merge; + vmg.flags = vma->vm_flags; /* If this fails, state is reset ready for a reattempt. */ merge = vma_merge_new_range(&vmg); @@ -1491,7 +1489,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr, vma = merge; /* Update vm_flags to pick up the change. */ vm_flags = vma->vm_flags; - goto unmap_writable; + goto file_expanded; } vma_iter_config(&vmi, addr, end); } @@ -1500,26 +1498,15 @@ unsigned long mmap_region(struct file *file, unsigned long addr, } else if (vm_flags & VM_SHARED) { error = shmem_zero_setup(vma); if (error) - goto free_vma; + goto free_iter_vma; } else { vma_set_anonymous(vma); } - if (map_deny_write_exec(vma->vm_flags, vma->vm_flags)) { - error = -EACCES; - goto close_and_free_vma; - } - - /* Allow architectures to sanity-check the vm_flags */ - if (!arch_validate_flags(vma->vm_flags)) { - error = -EINVAL; - goto close_and_free_vma; - } - - if (vma_iter_prealloc(&vmi, vma)) { - error = -ENOMEM; - goto close_and_free_vma; - } +#ifdef CONFIG_SPARC64 + /* TODO: Fix SPARC ADI! */ + WARN_ON_ONCE(!arch_validate_flags(vm_flags)); +#endif /* Lock the VMA since it is modified after insertion into VMA tree */ vma_start_write(vma); @@ -1533,10 +1520,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr, */ khugepaged_enter_vma(vma, vma->vm_flags); - /* Once vma denies write, undo our temporary denial count */ -unmap_writable: - if (writable_file_mapping) - mapping_unmap_writable(file->f_mapping); +file_expanded: file = vma->vm_file; ksm_add_vma(vma); expanded: @@ -1569,23 +1553,17 @@ unsigned long mmap_region(struct file *file, unsigned long addr, vma_set_page_prot(vma); - validate_mm(mm); return addr; -close_and_free_vma: - vma_close(vma); - - if (file || vma->vm_file) { -unmap_and_free_vma: - fput(vma->vm_file); - vma->vm_file = NULL; +unmap_and_free_file_vma: + fput(vma->vm_file); + vma->vm_file = NULL; - vma_iter_set(&vmi, vma->vm_end); - /* Undo any partial mapping done by a device driver. */ - unmap_region(&vmi.mas, vma, vmg.prev, vmg.next); - } - if (writable_file_mapping) - mapping_unmap_writable(file->f_mapping); + vma_iter_set(&vmi, vma->vm_end); + /* Undo any partial mapping done by a device driver. */ + unmap_region(&vmi.mas, vma, vmg.prev, vmg.next); +free_iter_vma: + vma_iter_free(&vmi); free_vma: vm_area_free(vma); unacct_error: @@ -1595,10 +1573,43 @@ unsigned long mmap_region(struct file *file, unsigned long addr, abort_munmap: vms_abort_munmap_vmas(&vms, &mas_detach); gather_failed: - validate_mm(mm); return error; } +unsigned long mmap_region(struct file *file, unsigned long addr, + unsigned long len, vm_flags_t vm_flags, unsigned long pgoff, + struct list_head *uf) +{ + unsigned long ret; + bool writable_file_mapping = false; + + /* Check to see if MDWE is applicable. */ + if (map_deny_write_exec(vm_flags, vm_flags)) + return -EACCES; + + /* Allow architectures to sanity-check the vm_flags. */ + if (!arch_validate_flags(vm_flags)) + return -EINVAL; + + /* Map writable and ensure this isn't a sealed memfd. */ + if (file && is_shared_maywrite(vm_flags)) { + int error = mapping_map_writable(file->f_mapping); + + if (error) + return error; + writable_file_mapping = true; + } + + ret = __mmap_region(file, addr, len, vm_flags, pgoff, uf); + + /* Clear our write mapping regardless of error. */ + if (writable_file_mapping) + mapping_unmap_writable(file->f_mapping); + + validate_mm(current->mm); + return ret; +} + static int __vm_munmap(unsigned long start, size_t len, bool unlock) { int ret;