From c4cf6785599b8126ea29160800fec5f1db0a6a30 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Tue, 7 Jun 2022 17:20:10 +0200 Subject: mm/slub: Move the stackdepot related allocation out of IRQ-off section. The set_track() invocation in free_debug_processing() is invoked with acquired slab_lock(). The lock disables interrupts on PREEMPT_RT and this forbids to allocate memory which is done in stack_depot_save(). Split set_track() into two parts: set_track_prepare() which allocate memory and set_track_update() which only performs the assignment of the trace data structure. Use set_track_prepare() before disabling interrupts. [ vbabka@suse.cz: make set_track() call set_track_update() instead of open-coded assignments ] Fixes: 5cf909c553e9e ("mm/slub: use stackdepot to save stack trace in objects") Signed-off-by: Sebastian Andrzej Siewior Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Signed-off-by: Vlastimil Babka Link: https://lore.kernel.org/r/Yp9sqoUi4fVa5ExF@linutronix.de --- mm/slub.c | 41 ++++++++++++++++++++++++++++++++++------- 1 file changed, 34 insertions(+), 7 deletions(-) (limited to 'mm') diff --git a/mm/slub.c b/mm/slub.c index e5535020e0fd..a5b14c1dfd86 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -726,25 +726,48 @@ static struct track *get_track(struct kmem_cache *s, void *object, return kasan_reset_tag(p + alloc); } -static void noinline set_track(struct kmem_cache *s, void *object, - enum track_item alloc, unsigned long addr) -{ - struct track *p = get_track(s, object, alloc); - #ifdef CONFIG_STACKDEPOT +static noinline depot_stack_handle_t set_track_prepare(void) +{ + depot_stack_handle_t handle; unsigned long entries[TRACK_ADDRS_COUNT]; unsigned int nr_entries; nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 3); - p->handle = stack_depot_save(entries, nr_entries, GFP_NOWAIT); + handle = stack_depot_save(entries, nr_entries, GFP_NOWAIT); + + return handle; +} +#else +static inline depot_stack_handle_t set_track_prepare(void) +{ + return 0; +} #endif +static void set_track_update(struct kmem_cache *s, void *object, + enum track_item alloc, unsigned long addr, + depot_stack_handle_t handle) +{ + struct track *p = get_track(s, object, alloc); + +#ifdef CONFIG_STACKDEPOT + p->handle = handle; +#endif p->addr = addr; p->cpu = smp_processor_id(); p->pid = current->pid; p->when = jiffies; } +static __always_inline void set_track(struct kmem_cache *s, void *object, + enum track_item alloc, unsigned long addr) +{ + depot_stack_handle_t handle = set_track_prepare(); + + set_track_update(s, object, alloc, addr, handle); +} + static void init_tracking(struct kmem_cache *s, void *object) { struct track *p; @@ -1373,6 +1396,10 @@ static noinline int free_debug_processing( int cnt = 0; unsigned long flags, flags2; int ret = 0; + depot_stack_handle_t handle = 0; + + if (s->flags & SLAB_STORE_USER) + handle = set_track_prepare(); spin_lock_irqsave(&n->list_lock, flags); slab_lock(slab, &flags2); @@ -1391,7 +1418,7 @@ next_object: } if (s->flags & SLAB_STORE_USER) - set_track(s, object, TRACK_FREE, addr); + set_track_update(s, object, TRACK_FREE, addr, handle); trace(s, slab, object, 0); /* Freepointer not overwritten by init_object(), SLAB_POISON moved it */ init_object(s, object, SLUB_RED_INACTIVE); -- cgit v1.2.3-70-g09d2 From eeaa345e128515135ccb864c04482180c08e3259 Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Wed, 8 Jun 2022 20:22:05 +0200 Subject: mm/slub: add missing TID updates on slab deactivation The fastpath in slab_alloc_node() assumes that c->slab is stable as long as the TID stays the same. However, two places in __slab_alloc() currently don't update the TID when deactivating the CPU slab. If multiple operations race the right way, this could lead to an object getting lost; or, in an even more unlikely situation, it could even lead to an object being freed onto the wrong slab's freelist, messing up the `inuse` counter and eventually causing a page to be freed to the page allocator while it still contains slab objects. (I haven't actually tested these cases though, this is just based on looking at the code. Writing testcases for this stuff seems like it'd be a pain...) The race leading to state inconsistency is (all operations on the same CPU and kmem_cache): - task A: begin do_slab_free(): - read TID - read pcpu freelist (==NULL) - check `slab == c->slab` (true) - [PREEMPT A->B] - task B: begin slab_alloc_node(): - fastpath fails (`c->freelist` is NULL) - enter __slab_alloc() - slub_get_cpu_ptr() (disables preemption) - enter ___slab_alloc() - take local_lock_irqsave() - read c->freelist as NULL - get_freelist() returns NULL - write `c->slab = NULL` - drop local_unlock_irqrestore() - goto new_slab - slub_percpu_partial() is NULL - get_partial() returns NULL - slub_put_cpu_ptr() (enables preemption) - [PREEMPT B->A] - task A: finish do_slab_free(): - this_cpu_cmpxchg_double() succeeds() - [CORRUPT STATE: c->slab==NULL, c->freelist!=NULL] From there, the object on c->freelist will get lost if task B is allowed to continue from here: It will proceed to the retry_load_slab label, set c->slab, then jump to load_freelist, which clobbers c->freelist. But if we instead continue as follows, we get worse corruption: - task A: run __slab_free() on object from other struct slab: - CPU_PARTIAL_FREE case (slab was on no list, is now on pcpu partial) - task A: run slab_alloc_node() with NUMA node constraint: - fastpath fails (c->slab is NULL) - call __slab_alloc() - slub_get_cpu_ptr() (disables preemption) - enter ___slab_alloc() - c->slab is NULL: goto new_slab - slub_percpu_partial() is non-NULL - set c->slab to slub_percpu_partial(c) - [CORRUPT STATE: c->slab points to slab-1, c->freelist has objects from slab-2] - goto redo - node_match() fails - goto deactivate_slab - existing c->freelist is passed into deactivate_slab() - inuse count of slab-1 is decremented to account for object from slab-2 At this point, the inuse count of slab-1 is 1 lower than it should be. This means that if we free all allocated objects in slab-1 except for one, SLUB will think that slab-1 is completely unused, and may free its page, leading to use-after-free. Fixes: c17dda40a6a4e ("slub: Separate out kmem_cache_cpu processing from deactivate_slab") Fixes: 03e404af26dc2 ("slub: fast release on full slab") Cc: stable@vger.kernel.org Signed-off-by: Jann Horn Acked-by: Christoph Lameter Acked-by: David Rientjes Reviewed-by: Muchun Song Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Signed-off-by: Vlastimil Babka Link: https://lore.kernel.org/r/20220608182205.2945720-1-jannh@google.com --- mm/slub.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'mm') diff --git a/mm/slub.c b/mm/slub.c index a5b14c1dfd86..b1281b8654bd 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2963,6 +2963,7 @@ redo: if (!freelist) { c->slab = NULL; + c->tid = next_tid(c->tid); local_unlock_irqrestore(&s->cpu_slab->lock, flags); stat(s, DEACTIVATE_BYPASS); goto new_slab; @@ -2995,6 +2996,7 @@ deactivate_slab: freelist = c->freelist; c->slab = NULL; c->freelist = NULL; + c->tid = next_tid(c->tid); local_unlock_irqrestore(&s->cpu_slab->lock, flags); deactivate_slab(s, slab, freelist); -- cgit v1.2.3-70-g09d2