From 46a9ea6681907a3be6b6b0d43776dccc62cad6cf Mon Sep 17 00:00:00 2001 From: Rafael Aquini Date: Fri, 8 Sep 2023 19:06:49 -0400 Subject: [PATCH 1/2] mm/slab_common: fix slab_caches list corruption after kmem_cache_destroy() After the commit in Fixes:, if a module that created a slab cache does not release all of its allocated objects before destroying the cache (at rmmod time), we might end up releasing the kmem_cache object without removing it from the slab_caches list thus corrupting the list as kmem_cache_destroy() ignores the return value from shutdown_cache(), which in turn never removes the kmem_cache object from slabs_list in case __kmem_cache_shutdown() fails to release all of the cache's slabs. This is easily observable on a kernel built with CONFIG_DEBUG_LIST=y as after that ill release the system will immediately trip on list_add, or list_del, assertions similar to the one shown below as soon as another kmem_cache gets created, or destroyed: [ 1041.213632] list_del corruption. next->prev should be ffff89f596fb5768, but was 52f1e5016aeee75d. (next=ffff89f595a1b268) [ 1041.219165] ------------[ cut here ]------------ [ 1041.221517] kernel BUG at lib/list_debug.c:62! [ 1041.223452] invalid opcode: 0000 [#1] PREEMPT SMP PTI [ 1041.225408] CPU: 2 PID: 1852 Comm: rmmod Kdump: loaded Tainted: G B W OE 6.5.0 #15 [ 1041.228244] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS edk2-20230524-3.fc37 05/24/2023 [ 1041.231212] RIP: 0010:__list_del_entry_valid+0xae/0xb0 Another quick way to trigger this issue, in a kernel with CONFIG_SLUB=y, is to set slub_debug to poison the released objects and then just run cat /proc/slabinfo after removing the module that leaks slab objects, in which case the kernel will panic: [ 50.954843] general protection fault, probably for non-canonical address 0xa56b6b6b6b6b6b8b: 0000 [#1] PREEMPT SMP PTI [ 50.961545] CPU: 2 PID: 1495 Comm: cat Kdump: loaded Tainted: G B W OE 6.5.0 #15 [ 50.966808] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS edk2-20230524-3.fc37 05/24/2023 [ 50.972663] RIP: 0010:get_slabinfo+0x42/0xf0 This patch fixes this issue by properly checking shutdown_cache()'s return value before taking the kmem_cache_release() branch. Fixes: 0495e337b703 ("mm/slab_common: Deleting kobject in kmem_cache_destroy() without holding slab_mutex/cpu_hotplug_lock") Signed-off-by: Rafael Aquini Cc: stable@vger.kernel.org Reviewed-by: Waiman Long Signed-off-by: Vlastimil Babka --- mm/slab_common.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/mm/slab_common.c b/mm/slab_common.c index 01cdbf122463..e99e821065c3 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -479,7 +479,7 @@ void slab_kmem_cache_release(struct kmem_cache *s) void kmem_cache_destroy(struct kmem_cache *s) { - int refcnt; + int err = -EBUSY; bool rcu_set; if (unlikely(!s) || !kasan_check_byte(s)) @@ -490,17 +490,17 @@ void kmem_cache_destroy(struct kmem_cache *s) rcu_set = s->flags & SLAB_TYPESAFE_BY_RCU; - refcnt = --s->refcount; - if (refcnt) + s->refcount--; + if (s->refcount) goto out_unlock; - WARN(shutdown_cache(s), - "%s %s: Slab cache still has objects when called from %pS", + err = shutdown_cache(s); + WARN(err, "%s %s: Slab cache still has objects when called from %pS", __func__, s->name, (void *)_RET_IP_); out_unlock: mutex_unlock(&slab_mutex); cpus_read_unlock(); - if (!refcnt && !rcu_set) + if (!err && !rcu_set) kmem_cache_release(s); } EXPORT_SYMBOL(kmem_cache_destroy); From 8446a4deb6b6bc998f1d8d2a85d1a0c64b9e3a71 Mon Sep 17 00:00:00 2001 From: David Laight Date: Thu, 7 Sep 2023 12:42:20 +0000 Subject: [PATCH 2/2] slab: kmalloc_size_roundup() must not return 0 for non-zero size The typical use of kmalloc_size_roundup() is: ptr = kmalloc(sz = kmalloc_size_roundup(size), ...); if (!ptr) return -ENOMEM. This means it is vitally important that the returned value isn't less than the argument even if the argument is insane. In particular if kmalloc_slab() fails or the value is above (MAX_ULONG - PAGE_SIZE) zero is returned and kmalloc() will return its single zero-length buffer ZERO_SIZE_PTR. Fix this by returning the input size if the size exceeds KMALLOC_MAX_SIZE. kmalloc() will then return NULL as the size really is too big. kmalloc_slab() should not normally return NULL, unless called too early. Again, returning zero is not the correct action as it can be in some usage scenarios stored to a variable and only later cause kmalloc() return ZERO_SIZE_PTR and subsequent crashes on access. Instead we can simply stop checking the kmalloc_slab() result completely, as calling kmalloc_size_roundup() too early would then result in an immediate crash during boot and the developer noticing an issue in their code. [vbabka@suse.cz: remove kmalloc_slab() result check, tweak comments and commit log] Fixes: 05a940656e1e ("slab: Introduce kmalloc_size_roundup()") Signed-off-by: David Laight Signed-off-by: Vlastimil Babka --- mm/slab_common.c | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/mm/slab_common.c b/mm/slab_common.c index e99e821065c3..306e6f0074ff 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -745,24 +745,24 @@ struct kmem_cache *kmalloc_slab(size_t size, gfp_t flags, unsigned long caller) size_t kmalloc_size_roundup(size_t size) { - struct kmem_cache *c; + if (size && size <= KMALLOC_MAX_CACHE_SIZE) { + /* + * The flags don't matter since size_index is common to all. + * Neither does the caller for just getting ->object_size. + */ + return kmalloc_slab(size, GFP_KERNEL, 0)->object_size; + } - /* Short-circuit the 0 size case. */ - if (unlikely(size == 0)) - return 0; - /* Short-circuit saturated "too-large" case. */ - if (unlikely(size == SIZE_MAX)) - return SIZE_MAX; /* Above the smaller buckets, size is a multiple of page size. */ - if (size > KMALLOC_MAX_CACHE_SIZE) + if (size && size <= KMALLOC_MAX_SIZE) return PAGE_SIZE << get_order(size); /* - * The flags don't matter since size_index is common to all. - * Neither does the caller for just getting ->object_size. + * Return 'size' for 0 - kmalloc() returns ZERO_SIZE_PTR + * and very large size - kmalloc() may fail. */ - c = kmalloc_slab(size, GFP_KERNEL, 0); - return c ? c->object_size : 0; + return size; + } EXPORT_SYMBOL(kmalloc_size_roundup);