From 65291dcfcf8936e1b23cfd7718fdfde7cfaf7706 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 26 Mar 2024 15:32:08 +0100 Subject: mm/secretmem: fix GUP-fast succeeding on secretmem folios folio_is_secretmem() currently relies on secretmem folios being LRU folios, to save some cycles. However, folios might reside in a folio batch without the LRU flag set, or temporarily have their LRU flag cleared. Consequently, the LRU flag is unreliable for this purpose. In particular, this is the case when secretmem_fault() allocates a fresh page and calls filemap_add_folio()->folio_add_lru(). The folio might be added to the per-cpu folio batch and won't get the LRU flag set until the batch was drained using e.g., lru_add_drain(). Consequently, folio_is_secretmem() might not detect secretmem folios and GUP-fast can succeed in grabbing a secretmem folio, crashing the kernel when we would later try reading/writing to the folio, because the folio has been unmapped from the directmap. Fix it by removing that unreliable check. Link: https://lkml.kernel.org/r/20240326143210.291116-2-david@redhat.com Fixes: 1507f51255c9 ("mm: introduce memfd_secret system call to create "secret" memory areas") Signed-off-by: David Hildenbrand Reported-by: xingwei lee Reported-by: yue sun Closes: https://lore.kernel.org/lkml/CABOYnLyevJeravW=QrH0JUPYEcDN160aZFb7kwndm-J2rmz0HQ@mail.gmail.com/ Debugged-by: Miklos Szeredi Tested-by: Miklos Szeredi Reviewed-by: Mike Rapoport (IBM) Cc: Lorenzo Stoakes Cc: Signed-off-by: Andrew Morton --- include/linux/secretmem.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/secretmem.h b/include/linux/secretmem.h index 35f3a4a8ceb1..acf7e1a3f3de 100644 --- a/include/linux/secretmem.h +++ b/include/linux/secretmem.h @@ -13,10 +13,10 @@ static inline bool folio_is_secretmem(struct folio *folio) /* * Using folio_mapping() is quite slow because of the actual call * instruction. - * We know that secretmem pages are not compound and LRU so we can + * We know that secretmem pages are not compound, so we can * save a couple of cycles here. */ - if (folio_test_large(folio) || !folio_test_lru(folio)) + if (folio_test_large(folio)) return false; mapping = (struct address_space *) -- cgit v1.2.3 From a6c1d9cb9a68bfa4512248419c4f4d880d19fe90 Mon Sep 17 00:00:00 2001 From: Peter Collingbourne Date: Mon, 1 Apr 2024 17:14:58 -0700 Subject: stackdepot: rename pool_index to pool_index_plus_1 Commit 3ee34eabac2a ("lib/stackdepot: fix first entry having a 0-handle") changed the meaning of the pool_index field to mean "the pool index plus 1". This made the code accessing this field less self-documenting, as well as causing debuggers such as drgn to not be able to easily remain compatible with both old and new kernels, because they typically do that by testing for presence of the new field. Because stackdepot is a debugging tool, we should make sure that it is debugger friendly. Therefore, give the field a different name to improve readability as well as enabling debugger backwards compatibility. This is needed in 6.9, which would otherwise become an odd release with the new semantics and old name so debuggers wouldn't recognize the new semantics there. Fixes: 3ee34eabac2a ("lib/stackdepot: fix first entry having a 0-handle") Link: https://lkml.kernel.org/r/20240402001500.53533-1-pcc@google.com Link: https://linux-review.googlesource.com/id/Ib3e70c36c1d230dd0a118dc22649b33e768b9f88 Signed-off-by: Peter Collingbourne Acked-by: Vlastimil Babka Reviewed-by: Alexander Potapenko Acked-by: Marco Elver Acked-by: Oscar Salvador Cc: Andrey Konovalov Cc: Michal Hocko Cc: Omar Sandoval Signed-off-by: Andrew Morton --- include/linux/stackdepot.h | 7 +++---- lib/stackdepot.c | 4 ++-- 2 files changed, 5 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h index 3c6caa5abc7c..e9ec32fb97d4 100644 --- a/include/linux/stackdepot.h +++ b/include/linux/stackdepot.h @@ -44,10 +44,9 @@ typedef u32 depot_stack_handle_t; union handle_parts { depot_stack_handle_t handle; struct { - /* pool_index is offset by 1 */ - u32 pool_index : DEPOT_POOL_INDEX_BITS; - u32 offset : DEPOT_OFFSET_BITS; - u32 extra : STACK_DEPOT_EXTRA_BITS; + u32 pool_index_plus_1 : DEPOT_POOL_INDEX_BITS; + u32 offset : DEPOT_OFFSET_BITS; + u32 extra : STACK_DEPOT_EXTRA_BITS; }; }; diff --git a/lib/stackdepot.c b/lib/stackdepot.c index af6cc19a2003..68c97387aa54 100644 --- a/lib/stackdepot.c +++ b/lib/stackdepot.c @@ -330,7 +330,7 @@ static struct stack_record *depot_pop_free_pool(void **prealloc, size_t size) stack = current_pool + pool_offset; /* Pre-initialize handle once. */ - stack->handle.pool_index = pool_index + 1; + stack->handle.pool_index_plus_1 = pool_index + 1; stack->handle.offset = pool_offset >> DEPOT_STACK_ALIGN; stack->handle.extra = 0; INIT_LIST_HEAD(&stack->hash_list); @@ -441,7 +441,7 @@ static struct stack_record *depot_fetch_stack(depot_stack_handle_t handle) const int pools_num_cached = READ_ONCE(pools_num); union handle_parts parts = { .handle = handle }; void *pool; - u32 pool_index = parts.pool_index - 1; + u32 pool_index = parts.pool_index_plus_1 - 1; size_t offset = parts.offset << DEPOT_STACK_ALIGN; struct stack_record *stack; -- cgit v1.2.3