From: "Uladzislau Rezki (Sony)" urezki@gmail.com
[ Upstream commit 79357cd06d41d0f5a11b17d7c86176e395d10ef2 ]
kasan_populate_vmalloc() and its helpers ignore the caller's gfp_mask and always allocate memory using the hardcoded GFP_KERNEL flag. This makes them inconsistent with vmalloc(), which was recently extended to support GFP_NOFS and GFP_NOIO allocations.
Page table allocations performed during shadow population also ignore the external gfp_mask. To preserve the intended semantics of GFP_NOFS and GFP_NOIO, wrap the apply_to_page_range() calls into the appropriate memalloc scope.
xfs calls vmalloc with GFP_NOFS, so this bug could lead to deadlock.
There was a report here https://lkml.kernel.org/r/686ea951.050a0220.385921.0016.GAE@google.com
This patch: - Extends kasan_populate_vmalloc() and helpers to take gfp_mask; - Passes gfp_mask down to alloc_pages_bulk() and __get_free_page(); - Enforces GFP_NOFS/NOIO semantics with memalloc_*_save()/restore() around apply_to_page_range(); - Updates vmalloc.c and percpu allocator call sites accordingly.
Link: https://lkml.kernel.org/r/20250831121058.92971-1-urezki@gmail.com Fixes: 451769ebb7e7 ("mm/vmalloc: alloc GFP_NO{FS,IO} for vmalloc") Signed-off-by: Uladzislau Rezki (Sony) urezki@gmail.com Reported-by: syzbot+3470c9ffee63e4abafeb@syzkaller.appspotmail.com Reviewed-by: Andrey Ryabinin ryabinin.a.a@gmail.com Cc: Baoquan He bhe@redhat.com Cc: Michal Hocko mhocko@kernel.org Cc: Alexander Potapenko glider@google.com Cc: Andrey Konovalov andreyknvl@gmail.com Cc: Dmitry Vyukov dvyukov@google.com Cc: Vincenzo Frascino vincenzo.frascino@arm.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/kasan.h | 6 +++--- mm/kasan/shadow.c | 31 ++++++++++++++++++++++++------- mm/vmalloc.c | 8 ++++---- 3 files changed, 31 insertions(+), 14 deletions(-)
diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 6bbfc8aa42e8f..ef81c543ea2a0 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -564,7 +564,7 @@ static inline void kasan_init_hw_tags(void) { } #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
void kasan_populate_early_vm_area_shadow(void *start, unsigned long size); -int kasan_populate_vmalloc(unsigned long addr, unsigned long size); +int kasan_populate_vmalloc(unsigned long addr, unsigned long size, gfp_t gfp_mask); void kasan_release_vmalloc(unsigned long start, unsigned long end, unsigned long free_region_start, unsigned long free_region_end, @@ -576,7 +576,7 @@ static inline void kasan_populate_early_vm_area_shadow(void *start, unsigned long size) { } static inline int kasan_populate_vmalloc(unsigned long start, - unsigned long size) + unsigned long size, gfp_t gfp_mask) { return 0; } @@ -612,7 +612,7 @@ static __always_inline void kasan_poison_vmalloc(const void *start, static inline void kasan_populate_early_vm_area_shadow(void *start, unsigned long size) { } static inline int kasan_populate_vmalloc(unsigned long start, - unsigned long size) + unsigned long size, gfp_t gfp_mask) { return 0; } diff --git a/mm/kasan/shadow.c b/mm/kasan/shadow.c index d2c70cd2afb1d..c7c0be1191737 100644 --- a/mm/kasan/shadow.c +++ b/mm/kasan/shadow.c @@ -335,13 +335,13 @@ static void ___free_pages_bulk(struct page **pages, int nr_pages) } }
-static int ___alloc_pages_bulk(struct page **pages, int nr_pages) +static int ___alloc_pages_bulk(struct page **pages, int nr_pages, gfp_t gfp_mask) { unsigned long nr_populated, nr_total = nr_pages; struct page **page_array = pages;
while (nr_pages) { - nr_populated = alloc_pages_bulk(GFP_KERNEL, nr_pages, pages); + nr_populated = alloc_pages_bulk(gfp_mask, nr_pages, pages); if (!nr_populated) { ___free_pages_bulk(page_array, nr_total - nr_pages); return -ENOMEM; @@ -353,25 +353,42 @@ static int ___alloc_pages_bulk(struct page **pages, int nr_pages) return 0; }
-static int __kasan_populate_vmalloc(unsigned long start, unsigned long end) +static int __kasan_populate_vmalloc(unsigned long start, unsigned long end, gfp_t gfp_mask) { unsigned long nr_pages, nr_total = PFN_UP(end - start); struct vmalloc_populate_data data; + unsigned int flags; int ret = 0;
- data.pages = (struct page **)__get_free_page(GFP_KERNEL | __GFP_ZERO); + data.pages = (struct page **)__get_free_page(gfp_mask | __GFP_ZERO); if (!data.pages) return -ENOMEM;
while (nr_total) { nr_pages = min(nr_total, PAGE_SIZE / sizeof(data.pages[0])); - ret = ___alloc_pages_bulk(data.pages, nr_pages); + ret = ___alloc_pages_bulk(data.pages, nr_pages, gfp_mask); if (ret) break;
data.start = start; + + /* + * page tables allocations ignore external gfp mask, enforce it + * by the scope API + */ + if ((gfp_mask & (__GFP_FS | __GFP_IO)) == __GFP_IO) + flags = memalloc_nofs_save(); + else if ((gfp_mask & (__GFP_FS | __GFP_IO)) == 0) + flags = memalloc_noio_save(); + ret = apply_to_page_range(&init_mm, start, nr_pages * PAGE_SIZE, kasan_populate_vmalloc_pte, &data); + + if ((gfp_mask & (__GFP_FS | __GFP_IO)) == __GFP_IO) + memalloc_nofs_restore(flags); + else if ((gfp_mask & (__GFP_FS | __GFP_IO)) == 0) + memalloc_noio_restore(flags); + ___free_pages_bulk(data.pages, nr_pages); if (ret) break; @@ -385,7 +402,7 @@ static int __kasan_populate_vmalloc(unsigned long start, unsigned long end) return ret; }
-int kasan_populate_vmalloc(unsigned long addr, unsigned long size) +int kasan_populate_vmalloc(unsigned long addr, unsigned long size, gfp_t gfp_mask) { unsigned long shadow_start, shadow_end; int ret; @@ -414,7 +431,7 @@ int kasan_populate_vmalloc(unsigned long addr, unsigned long size) shadow_start = PAGE_ALIGN_DOWN(shadow_start); shadow_end = PAGE_ALIGN(shadow_end);
- ret = __kasan_populate_vmalloc(shadow_start, shadow_end); + ret = __kasan_populate_vmalloc(shadow_start, shadow_end, gfp_mask); if (ret) return ret;
diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 3519c4e4f841d..79e6c0e599f5f 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1977,6 +1977,8 @@ static struct vmap_area *alloc_vmap_area(unsigned long size, if (unlikely(!vmap_initialized)) return ERR_PTR(-EBUSY);
+ /* Only reclaim behaviour flags are relevant. */ + gfp_mask = gfp_mask & GFP_RECLAIM_MASK; might_sleep();
/* @@ -1989,8 +1991,6 @@ static struct vmap_area *alloc_vmap_area(unsigned long size, */ va = node_alloc(size, align, vstart, vend, &addr, &vn_id); if (!va) { - gfp_mask = gfp_mask & GFP_RECLAIM_MASK; - va = kmem_cache_alloc_node(vmap_area_cachep, gfp_mask, node); if (unlikely(!va)) return ERR_PTR(-ENOMEM); @@ -2040,7 +2040,7 @@ static struct vmap_area *alloc_vmap_area(unsigned long size, BUG_ON(va->va_start < vstart); BUG_ON(va->va_end > vend);
- ret = kasan_populate_vmalloc(addr, size); + ret = kasan_populate_vmalloc(addr, size, gfp_mask); if (ret) { free_vmap_area(va); return ERR_PTR(ret); @@ -4789,7 +4789,7 @@ struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets,
/* populate the kasan shadow space */ for (area = 0; area < nr_vms; area++) { - if (kasan_populate_vmalloc(vas[area]->va_start, sizes[area])) + if (kasan_populate_vmalloc(vas[area]->va_start, sizes[area], GFP_KERNEL)) goto err_free_shadow; }