You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
kernel_samsung_sm7125/mm/kasan/quarantine.c

330 lines
8.8 KiB

// SPDX-License-Identifier: GPL-2.0
mm: kasan: initial memory quarantine implementation Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. When the object is freed, its state changes from KASAN_STATE_ALLOC to KASAN_STATE_QUARANTINE. The object is poisoned and put into quarantine instead of being returned to the allocator, therefore every subsequent access to that object triggers a KASAN error, and the error handler is able to say where the object has been allocated and deallocated. When it's time for the object to leave quarantine, its state becomes KASAN_STATE_FREE and it's returned to the allocator. From now on the allocator may reuse it for another allocation. Before that happens, it's still possible to detect a use-after free on that object (it retains the allocation/deallocation stacks). When the allocator reuses this object, the shadow is unpoisoned and old allocation/deallocation stacks are wiped. Therefore a use of this object, even an incorrect one, won't trigger ASan warning. Without the quarantine, it's not guaranteed that the objects aren't reused immediately, that's why the probability of catching a use-after-free is lower than with quarantine in place. Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. Freed objects are first added to per-cpu quarantine queues. When a cache is destroyed or memory shrinking is requested, the objects are moved into the global quarantine queue. Whenever a kmalloc call allows memory reclaiming, the oldest objects are popped out of the global queue until the total size of objects in quarantine is less than 3/4 of the maximum quarantine size (which is a fraction of installed physical memory). As long as an object remains in the quarantine, KASAN is able to report accesses to it, so the chance of reporting a use-after-free is increased. Once the object leaves quarantine, the allocator may reuse it, in which case the object is unpoisoned and KASAN can't detect incorrect accesses to it. Right now quarantine support is only enabled in SLAB allocator. Unification of KASAN features in SLAB and SLUB will be done later. This patch is based on the "mm: kasan: quarantine" patch originally prepared by Dmitry Chernenkov. A number of improvements have been suggested by Andrey Ryabinin. [glider@google.com: v9] Link: http://lkml.kernel.org/r/1462987130-144092-1-git-send-email-glider@google.com Signed-off-by: Alexander Potapenko <glider@google.com> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Andrey Konovalov <adech.fo@gmail.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Konstantin Serebryany <kcc@google.com> Cc: Dmitry Chernenkov <dmitryc@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
9 years ago
/*
* KASAN quarantine.
*
* Author: Alexander Potapenko <glider@google.com>
* Copyright (C) 2016 Google, Inc.
*
* Based on code by Dmitry Chernenkov.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* version 2 as published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* General Public License for more details.
*
*/
#include <linux/gfp.h>
#include <linux/hash.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/percpu.h>
#include <linux/printk.h>
#include <linux/shrinker.h>
#include <linux/slab.h>
kasan: fix races in quarantine_remove_cache() quarantine_remove_cache() frees all pending objects that belong to the cache, before we destroy the cache itself. However there are currently two possibilities how it can fail to do so. First, another thread can hold some of the objects from the cache in temp list in quarantine_put(). quarantine_put() has a windows of enabled interrupts, and on_each_cpu() in quarantine_remove_cache() can finish right in that window. These objects will be later freed into the destroyed cache. Then, quarantine_reduce() has the same problem. It grabs a batch of objects from the global quarantine, then unlocks quarantine_lock and then frees the batch. quarantine_remove_cache() can finish while some objects from the cache are still in the local to_free list in quarantine_reduce(). Fix the race with quarantine_put() by disabling interrupts for the whole duration of quarantine_put(). In combination with on_each_cpu() in quarantine_remove_cache() it ensures that quarantine_remove_cache() either sees the objects in the per-cpu list or in the global list. Fix the race with quarantine_reduce() by protecting quarantine_reduce() with srcu critical section and then doing synchronize_srcu() at the end of quarantine_remove_cache(). I've done some assessment of how good synchronize_srcu() works in this case. And on a 4 CPU VM I see that it blocks waiting for pending read critical sections in about 2-3% of cases. Which looks good to me. I suspect that these races are the root cause of some GPFs that I episodically hit. Previously I did not have any explanation for them. BUG: unable to handle kernel NULL pointer dereference at 00000000000000c8 IP: qlist_free_all+0x2e/0xc0 mm/kasan/quarantine.c:155 PGD 6aeea067 PUD 60ed7067 PMD 0 Oops: 0000 [#1] SMP KASAN Dumping ftrace buffer: (ftrace buffer empty) Modules linked in: CPU: 0 PID: 13667 Comm: syz-executor2 Not tainted 4.10.0+ #60 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 task: ffff88005f948040 task.stack: ffff880069818000 RIP: 0010:qlist_free_all+0x2e/0xc0 mm/kasan/quarantine.c:155 RSP: 0018:ffff88006981f298 EFLAGS: 00010246 RAX: ffffea0000ffff00 RBX: 0000000000000000 RCX: ffffea0000ffff1f RDX: 0000000000000000 RSI: ffff88003fffc3e0 RDI: 0000000000000000 RBP: ffff88006981f2c0 R08: ffff88002fed7bd8 R09: 00000001001f000d R10: 00000000001f000d R11: ffff88006981f000 R12: ffff88003fffc3e0 R13: ffff88006981f2d0 R14: ffffffff81877fae R15: 0000000080000000 FS: 00007fb911a2d700(0000) GS:ffff88003ec00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000000000c8 CR3: 0000000060ed6000 CR4: 00000000000006f0 Call Trace: quarantine_reduce+0x10e/0x120 mm/kasan/quarantine.c:239 kasan_kmalloc+0xca/0xe0 mm/kasan/kasan.c:590 kasan_slab_alloc+0x12/0x20 mm/kasan/kasan.c:544 slab_post_alloc_hook mm/slab.h:456 [inline] slab_alloc_node mm/slub.c:2718 [inline] kmem_cache_alloc_node+0x1d3/0x280 mm/slub.c:2754 __alloc_skb+0x10f/0x770 net/core/skbuff.c:219 alloc_skb include/linux/skbuff.h:932 [inline] _sctp_make_chunk+0x3b/0x260 net/sctp/sm_make_chunk.c:1388 sctp_make_data net/sctp/sm_make_chunk.c:1420 [inline] sctp_make_datafrag_empty+0x208/0x360 net/sctp/sm_make_chunk.c:746 sctp_datamsg_from_user+0x7e8/0x11d0 net/sctp/chunk.c:266 sctp_sendmsg+0x2611/0x3970 net/sctp/socket.c:1962 inet_sendmsg+0x164/0x5b0 net/ipv4/af_inet.c:761 sock_sendmsg_nosec net/socket.c:633 [inline] sock_sendmsg+0xca/0x110 net/socket.c:643 SYSC_sendto+0x660/0x810 net/socket.c:1685 SyS_sendto+0x40/0x50 net/socket.c:1653 I am not sure about backporting. The bug is quite hard to trigger, I've seen it few times during our massive continuous testing (however, it could be cause of some other episodic stray crashes as it leads to memory corruption...). If it is triggered, the consequences are very bad -- almost definite bad memory corruption. The fix is non trivial and has chances of introducing new bugs. I am also not sure how actively people use KASAN on older releases. [dvyukov@google.com: - sorted includes[ Link: http://lkml.kernel.org/r/20170309094028.51088-1-dvyukov@google.com Link: http://lkml.kernel.org/r/20170308151532.5070-1-dvyukov@google.com Signed-off-by: Dmitry Vyukov <dvyukov@google.com> Acked-by: Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: Greg Thelen <gthelen@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
8 years ago
#include <linux/srcu.h>
mm: kasan: initial memory quarantine implementation Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. When the object is freed, its state changes from KASAN_STATE_ALLOC to KASAN_STATE_QUARANTINE. The object is poisoned and put into quarantine instead of being returned to the allocator, therefore every subsequent access to that object triggers a KASAN error, and the error handler is able to say where the object has been allocated and deallocated. When it's time for the object to leave quarantine, its state becomes KASAN_STATE_FREE and it's returned to the allocator. From now on the allocator may reuse it for another allocation. Before that happens, it's still possible to detect a use-after free on that object (it retains the allocation/deallocation stacks). When the allocator reuses this object, the shadow is unpoisoned and old allocation/deallocation stacks are wiped. Therefore a use of this object, even an incorrect one, won't trigger ASan warning. Without the quarantine, it's not guaranteed that the objects aren't reused immediately, that's why the probability of catching a use-after-free is lower than with quarantine in place. Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. Freed objects are first added to per-cpu quarantine queues. When a cache is destroyed or memory shrinking is requested, the objects are moved into the global quarantine queue. Whenever a kmalloc call allows memory reclaiming, the oldest objects are popped out of the global queue until the total size of objects in quarantine is less than 3/4 of the maximum quarantine size (which is a fraction of installed physical memory). As long as an object remains in the quarantine, KASAN is able to report accesses to it, so the chance of reporting a use-after-free is increased. Once the object leaves quarantine, the allocator may reuse it, in which case the object is unpoisoned and KASAN can't detect incorrect accesses to it. Right now quarantine support is only enabled in SLAB allocator. Unification of KASAN features in SLAB and SLUB will be done later. This patch is based on the "mm: kasan: quarantine" patch originally prepared by Dmitry Chernenkov. A number of improvements have been suggested by Andrey Ryabinin. [glider@google.com: v9] Link: http://lkml.kernel.org/r/1462987130-144092-1-git-send-email-glider@google.com Signed-off-by: Alexander Potapenko <glider@google.com> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Andrey Konovalov <adech.fo@gmail.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Konstantin Serebryany <kcc@google.com> Cc: Dmitry Chernenkov <dmitryc@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
9 years ago
#include <linux/string.h>
#include <linux/types.h>
#include "../slab.h"
#include "kasan.h"
/* Data structure and operations for quarantine queues. */
/*
* Each queue is a signle-linked list, which also stores the total size of
* objects inside of it.
*/
struct qlist_head {
struct qlist_node *head;
struct qlist_node *tail;
size_t bytes;
};
#define QLIST_INIT { NULL, NULL, 0 }
static bool qlist_empty(struct qlist_head *q)
{
return !q->head;
}
static void qlist_init(struct qlist_head *q)
{
q->head = q->tail = NULL;
q->bytes = 0;
}
static void qlist_put(struct qlist_head *q, struct qlist_node *qlink,
size_t size)
{
if (unlikely(qlist_empty(q)))
q->head = qlink;
else
q->tail->next = qlink;
q->tail = qlink;
qlink->next = NULL;
q->bytes += size;
}
static void qlist_move_all(struct qlist_head *from, struct qlist_head *to)
{
if (unlikely(qlist_empty(from)))
return;
if (qlist_empty(to)) {
*to = *from;
qlist_init(from);
return;
}
to->tail->next = from->head;
to->tail = from->tail;
to->bytes += from->bytes;
qlist_init(from);
}
kasan: eliminate long stalls during quarantine reduction Currently we dedicate 1/32 of RAM for quarantine and then reduce it by 1/4 of total quarantine size. This can be a significant amount of memory. For example, with 4GB of RAM total quarantine size is 128MB and it is reduced by 32MB at a time. With 128GB of RAM total quarantine size is 4GB and it is reduced by 1GB. This leads to several problems: - freeing 1GB can take tens of seconds, causes rcu stall warnings and just introduces unexpected long delays at random places - if kmalloc() is called under a mutex, other threads stall on that mutex while a thread reduces quarantine - threads wait on quarantine_lock while one thread grabs a large batch of objects to evict - we walk the uncached list of object to free twice which makes all of the above worse - when a thread frees objects, they are already not accounted against global_quarantine.bytes; as the result we can have quarantine_size bytes in quarantine + unbounded amount of memory in large batches in threads that are in process of freeing Reduce size of quarantine in smaller batches to reduce the delays. The only reason to reduce it in batches is amortization of overheads, the new batch size of 1MB should be well enough to amortize spinlock lock/unlock and few function calls. Plus organize quarantine as a FIFO array of batches. This allows to not walk the list in quarantine_reduce() under quarantine_lock, which in turn reduces contention and is just faster. This improves performance of heavy load (syzkaller fuzzing) by ~20% with 4 CPUs and 32GB of RAM. Also this eliminates frequent (every 5 sec) drops of CPU consumption from ~400% to ~100% (one thread reduces quarantine while others are waiting on a mutex). Some reference numbers: 1. Machine with 4 CPUs and 4GB of memory. Quarantine size 128MB. Currently we free 32MB at at time. With new code we free 1MB at a time (1024 batches, ~128 are used). 2. Machine with 32 CPUs and 128GB of memory. Quarantine size 4GB. Currently we free 1GB at at time. With new code we free 8MB at a time (1024 batches, ~512 are used). 3. Machine with 4096 CPUs and 1TB of memory. Quarantine size 32GB. Currently we free 8GB at at time. With new code we free 4MB at a time (16K batches, ~8K are used). Link: http://lkml.kernel.org/r/1478756952-18695-1-git-send-email-dvyukov@google.com Signed-off-by: Dmitry Vyukov <dvyukov@google.com> Cc: Eric Dumazet <edumazet@google.com> Cc: Greg Thelen <gthelen@google.com> Cc: Alexander Potapenko <glider@google.com> Cc: Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: Andrey Konovalov <andreyknvl@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
8 years ago
#define QUARANTINE_PERCPU_SIZE (1 << 20)
#define QUARANTINE_BATCHES \
(1024 > 4 * CONFIG_NR_CPUS ? 1024 : 4 * CONFIG_NR_CPUS)
mm: kasan: initial memory quarantine implementation Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. When the object is freed, its state changes from KASAN_STATE_ALLOC to KASAN_STATE_QUARANTINE. The object is poisoned and put into quarantine instead of being returned to the allocator, therefore every subsequent access to that object triggers a KASAN error, and the error handler is able to say where the object has been allocated and deallocated. When it's time for the object to leave quarantine, its state becomes KASAN_STATE_FREE and it's returned to the allocator. From now on the allocator may reuse it for another allocation. Before that happens, it's still possible to detect a use-after free on that object (it retains the allocation/deallocation stacks). When the allocator reuses this object, the shadow is unpoisoned and old allocation/deallocation stacks are wiped. Therefore a use of this object, even an incorrect one, won't trigger ASan warning. Without the quarantine, it's not guaranteed that the objects aren't reused immediately, that's why the probability of catching a use-after-free is lower than with quarantine in place. Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. Freed objects are first added to per-cpu quarantine queues. When a cache is destroyed or memory shrinking is requested, the objects are moved into the global quarantine queue. Whenever a kmalloc call allows memory reclaiming, the oldest objects are popped out of the global queue until the total size of objects in quarantine is less than 3/4 of the maximum quarantine size (which is a fraction of installed physical memory). As long as an object remains in the quarantine, KASAN is able to report accesses to it, so the chance of reporting a use-after-free is increased. Once the object leaves quarantine, the allocator may reuse it, in which case the object is unpoisoned and KASAN can't detect incorrect accesses to it. Right now quarantine support is only enabled in SLAB allocator. Unification of KASAN features in SLAB and SLUB will be done later. This patch is based on the "mm: kasan: quarantine" patch originally prepared by Dmitry Chernenkov. A number of improvements have been suggested by Andrey Ryabinin. [glider@google.com: v9] Link: http://lkml.kernel.org/r/1462987130-144092-1-git-send-email-glider@google.com Signed-off-by: Alexander Potapenko <glider@google.com> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Andrey Konovalov <adech.fo@gmail.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Konstantin Serebryany <kcc@google.com> Cc: Dmitry Chernenkov <dmitryc@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
9 years ago
/*
* The object quarantine consists of per-cpu queues and a global queue,
* guarded by quarantine_lock.
*/
static DEFINE_PER_CPU(struct qlist_head, cpu_quarantine);
kasan: eliminate long stalls during quarantine reduction Currently we dedicate 1/32 of RAM for quarantine and then reduce it by 1/4 of total quarantine size. This can be a significant amount of memory. For example, with 4GB of RAM total quarantine size is 128MB and it is reduced by 32MB at a time. With 128GB of RAM total quarantine size is 4GB and it is reduced by 1GB. This leads to several problems: - freeing 1GB can take tens of seconds, causes rcu stall warnings and just introduces unexpected long delays at random places - if kmalloc() is called under a mutex, other threads stall on that mutex while a thread reduces quarantine - threads wait on quarantine_lock while one thread grabs a large batch of objects to evict - we walk the uncached list of object to free twice which makes all of the above worse - when a thread frees objects, they are already not accounted against global_quarantine.bytes; as the result we can have quarantine_size bytes in quarantine + unbounded amount of memory in large batches in threads that are in process of freeing Reduce size of quarantine in smaller batches to reduce the delays. The only reason to reduce it in batches is amortization of overheads, the new batch size of 1MB should be well enough to amortize spinlock lock/unlock and few function calls. Plus organize quarantine as a FIFO array of batches. This allows to not walk the list in quarantine_reduce() under quarantine_lock, which in turn reduces contention and is just faster. This improves performance of heavy load (syzkaller fuzzing) by ~20% with 4 CPUs and 32GB of RAM. Also this eliminates frequent (every 5 sec) drops of CPU consumption from ~400% to ~100% (one thread reduces quarantine while others are waiting on a mutex). Some reference numbers: 1. Machine with 4 CPUs and 4GB of memory. Quarantine size 128MB. Currently we free 32MB at at time. With new code we free 1MB at a time (1024 batches, ~128 are used). 2. Machine with 32 CPUs and 128GB of memory. Quarantine size 4GB. Currently we free 1GB at at time. With new code we free 8MB at a time (1024 batches, ~512 are used). 3. Machine with 4096 CPUs and 1TB of memory. Quarantine size 32GB. Currently we free 8GB at at time. With new code we free 4MB at a time (16K batches, ~8K are used). Link: http://lkml.kernel.org/r/1478756952-18695-1-git-send-email-dvyukov@google.com Signed-off-by: Dmitry Vyukov <dvyukov@google.com> Cc: Eric Dumazet <edumazet@google.com> Cc: Greg Thelen <gthelen@google.com> Cc: Alexander Potapenko <glider@google.com> Cc: Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: Andrey Konovalov <andreyknvl@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
8 years ago
/* Round-robin FIFO array of batches. */
static struct qlist_head global_quarantine[QUARANTINE_BATCHES];
static int quarantine_head;
static int quarantine_tail;
/* Total size of all objects in global_quarantine across all batches. */
static unsigned long quarantine_size;
static DEFINE_RAW_SPINLOCK(quarantine_lock);
kasan: fix races in quarantine_remove_cache() quarantine_remove_cache() frees all pending objects that belong to the cache, before we destroy the cache itself. However there are currently two possibilities how it can fail to do so. First, another thread can hold some of the objects from the cache in temp list in quarantine_put(). quarantine_put() has a windows of enabled interrupts, and on_each_cpu() in quarantine_remove_cache() can finish right in that window. These objects will be later freed into the destroyed cache. Then, quarantine_reduce() has the same problem. It grabs a batch of objects from the global quarantine, then unlocks quarantine_lock and then frees the batch. quarantine_remove_cache() can finish while some objects from the cache are still in the local to_free list in quarantine_reduce(). Fix the race with quarantine_put() by disabling interrupts for the whole duration of quarantine_put(). In combination with on_each_cpu() in quarantine_remove_cache() it ensures that quarantine_remove_cache() either sees the objects in the per-cpu list or in the global list. Fix the race with quarantine_reduce() by protecting quarantine_reduce() with srcu critical section and then doing synchronize_srcu() at the end of quarantine_remove_cache(). I've done some assessment of how good synchronize_srcu() works in this case. And on a 4 CPU VM I see that it blocks waiting for pending read critical sections in about 2-3% of cases. Which looks good to me. I suspect that these races are the root cause of some GPFs that I episodically hit. Previously I did not have any explanation for them. BUG: unable to handle kernel NULL pointer dereference at 00000000000000c8 IP: qlist_free_all+0x2e/0xc0 mm/kasan/quarantine.c:155 PGD 6aeea067 PUD 60ed7067 PMD 0 Oops: 0000 [#1] SMP KASAN Dumping ftrace buffer: (ftrace buffer empty) Modules linked in: CPU: 0 PID: 13667 Comm: syz-executor2 Not tainted 4.10.0+ #60 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 task: ffff88005f948040 task.stack: ffff880069818000 RIP: 0010:qlist_free_all+0x2e/0xc0 mm/kasan/quarantine.c:155 RSP: 0018:ffff88006981f298 EFLAGS: 00010246 RAX: ffffea0000ffff00 RBX: 0000000000000000 RCX: ffffea0000ffff1f RDX: 0000000000000000 RSI: ffff88003fffc3e0 RDI: 0000000000000000 RBP: ffff88006981f2c0 R08: ffff88002fed7bd8 R09: 00000001001f000d R10: 00000000001f000d R11: ffff88006981f000 R12: ffff88003fffc3e0 R13: ffff88006981f2d0 R14: ffffffff81877fae R15: 0000000080000000 FS: 00007fb911a2d700(0000) GS:ffff88003ec00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000000000c8 CR3: 0000000060ed6000 CR4: 00000000000006f0 Call Trace: quarantine_reduce+0x10e/0x120 mm/kasan/quarantine.c:239 kasan_kmalloc+0xca/0xe0 mm/kasan/kasan.c:590 kasan_slab_alloc+0x12/0x20 mm/kasan/kasan.c:544 slab_post_alloc_hook mm/slab.h:456 [inline] slab_alloc_node mm/slub.c:2718 [inline] kmem_cache_alloc_node+0x1d3/0x280 mm/slub.c:2754 __alloc_skb+0x10f/0x770 net/core/skbuff.c:219 alloc_skb include/linux/skbuff.h:932 [inline] _sctp_make_chunk+0x3b/0x260 net/sctp/sm_make_chunk.c:1388 sctp_make_data net/sctp/sm_make_chunk.c:1420 [inline] sctp_make_datafrag_empty+0x208/0x360 net/sctp/sm_make_chunk.c:746 sctp_datamsg_from_user+0x7e8/0x11d0 net/sctp/chunk.c:266 sctp_sendmsg+0x2611/0x3970 net/sctp/socket.c:1962 inet_sendmsg+0x164/0x5b0 net/ipv4/af_inet.c:761 sock_sendmsg_nosec net/socket.c:633 [inline] sock_sendmsg+0xca/0x110 net/socket.c:643 SYSC_sendto+0x660/0x810 net/socket.c:1685 SyS_sendto+0x40/0x50 net/socket.c:1653 I am not sure about backporting. The bug is quite hard to trigger, I've seen it few times during our massive continuous testing (however, it could be cause of some other episodic stray crashes as it leads to memory corruption...). If it is triggered, the consequences are very bad -- almost definite bad memory corruption. The fix is non trivial and has chances of introducing new bugs. I am also not sure how actively people use KASAN on older releases. [dvyukov@google.com: - sorted includes[ Link: http://lkml.kernel.org/r/20170309094028.51088-1-dvyukov@google.com Link: http://lkml.kernel.org/r/20170308151532.5070-1-dvyukov@google.com Signed-off-by: Dmitry Vyukov <dvyukov@google.com> Acked-by: Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: Greg Thelen <gthelen@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
8 years ago
DEFINE_STATIC_SRCU(remove_cache_srcu);
mm: kasan: initial memory quarantine implementation Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. When the object is freed, its state changes from KASAN_STATE_ALLOC to KASAN_STATE_QUARANTINE. The object is poisoned and put into quarantine instead of being returned to the allocator, therefore every subsequent access to that object triggers a KASAN error, and the error handler is able to say where the object has been allocated and deallocated. When it's time for the object to leave quarantine, its state becomes KASAN_STATE_FREE and it's returned to the allocator. From now on the allocator may reuse it for another allocation. Before that happens, it's still possible to detect a use-after free on that object (it retains the allocation/deallocation stacks). When the allocator reuses this object, the shadow is unpoisoned and old allocation/deallocation stacks are wiped. Therefore a use of this object, even an incorrect one, won't trigger ASan warning. Without the quarantine, it's not guaranteed that the objects aren't reused immediately, that's why the probability of catching a use-after-free is lower than with quarantine in place. Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. Freed objects are first added to per-cpu quarantine queues. When a cache is destroyed or memory shrinking is requested, the objects are moved into the global quarantine queue. Whenever a kmalloc call allows memory reclaiming, the oldest objects are popped out of the global queue until the total size of objects in quarantine is less than 3/4 of the maximum quarantine size (which is a fraction of installed physical memory). As long as an object remains in the quarantine, KASAN is able to report accesses to it, so the chance of reporting a use-after-free is increased. Once the object leaves quarantine, the allocator may reuse it, in which case the object is unpoisoned and KASAN can't detect incorrect accesses to it. Right now quarantine support is only enabled in SLAB allocator. Unification of KASAN features in SLAB and SLUB will be done later. This patch is based on the "mm: kasan: quarantine" patch originally prepared by Dmitry Chernenkov. A number of improvements have been suggested by Andrey Ryabinin. [glider@google.com: v9] Link: http://lkml.kernel.org/r/1462987130-144092-1-git-send-email-glider@google.com Signed-off-by: Alexander Potapenko <glider@google.com> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Andrey Konovalov <adech.fo@gmail.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Konstantin Serebryany <kcc@google.com> Cc: Dmitry Chernenkov <dmitryc@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
9 years ago
/* Maximum size of the global queue. */
kasan: eliminate long stalls during quarantine reduction Currently we dedicate 1/32 of RAM for quarantine and then reduce it by 1/4 of total quarantine size. This can be a significant amount of memory. For example, with 4GB of RAM total quarantine size is 128MB and it is reduced by 32MB at a time. With 128GB of RAM total quarantine size is 4GB and it is reduced by 1GB. This leads to several problems: - freeing 1GB can take tens of seconds, causes rcu stall warnings and just introduces unexpected long delays at random places - if kmalloc() is called under a mutex, other threads stall on that mutex while a thread reduces quarantine - threads wait on quarantine_lock while one thread grabs a large batch of objects to evict - we walk the uncached list of object to free twice which makes all of the above worse - when a thread frees objects, they are already not accounted against global_quarantine.bytes; as the result we can have quarantine_size bytes in quarantine + unbounded amount of memory in large batches in threads that are in process of freeing Reduce size of quarantine in smaller batches to reduce the delays. The only reason to reduce it in batches is amortization of overheads, the new batch size of 1MB should be well enough to amortize spinlock lock/unlock and few function calls. Plus organize quarantine as a FIFO array of batches. This allows to not walk the list in quarantine_reduce() under quarantine_lock, which in turn reduces contention and is just faster. This improves performance of heavy load (syzkaller fuzzing) by ~20% with 4 CPUs and 32GB of RAM. Also this eliminates frequent (every 5 sec) drops of CPU consumption from ~400% to ~100% (one thread reduces quarantine while others are waiting on a mutex). Some reference numbers: 1. Machine with 4 CPUs and 4GB of memory. Quarantine size 128MB. Currently we free 32MB at at time. With new code we free 1MB at a time (1024 batches, ~128 are used). 2. Machine with 32 CPUs and 128GB of memory. Quarantine size 4GB. Currently we free 1GB at at time. With new code we free 8MB at a time (1024 batches, ~512 are used). 3. Machine with 4096 CPUs and 1TB of memory. Quarantine size 32GB. Currently we free 8GB at at time. With new code we free 4MB at a time (16K batches, ~8K are used). Link: http://lkml.kernel.org/r/1478756952-18695-1-git-send-email-dvyukov@google.com Signed-off-by: Dmitry Vyukov <dvyukov@google.com> Cc: Eric Dumazet <edumazet@google.com> Cc: Greg Thelen <gthelen@google.com> Cc: Alexander Potapenko <glider@google.com> Cc: Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: Andrey Konovalov <andreyknvl@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
8 years ago
static unsigned long quarantine_max_size;
/*
* Target size of a batch in global_quarantine.
* Usually equal to QUARANTINE_PERCPU_SIZE unless we have too much RAM.
*/
static unsigned long quarantine_batch_size;
mm: kasan: initial memory quarantine implementation Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. When the object is freed, its state changes from KASAN_STATE_ALLOC to KASAN_STATE_QUARANTINE. The object is poisoned and put into quarantine instead of being returned to the allocator, therefore every subsequent access to that object triggers a KASAN error, and the error handler is able to say where the object has been allocated and deallocated. When it's time for the object to leave quarantine, its state becomes KASAN_STATE_FREE and it's returned to the allocator. From now on the allocator may reuse it for another allocation. Before that happens, it's still possible to detect a use-after free on that object (it retains the allocation/deallocation stacks). When the allocator reuses this object, the shadow is unpoisoned and old allocation/deallocation stacks are wiped. Therefore a use of this object, even an incorrect one, won't trigger ASan warning. Without the quarantine, it's not guaranteed that the objects aren't reused immediately, that's why the probability of catching a use-after-free is lower than with quarantine in place. Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. Freed objects are first added to per-cpu quarantine queues. When a cache is destroyed or memory shrinking is requested, the objects are moved into the global quarantine queue. Whenever a kmalloc call allows memory reclaiming, the oldest objects are popped out of the global queue until the total size of objects in quarantine is less than 3/4 of the maximum quarantine size (which is a fraction of installed physical memory). As long as an object remains in the quarantine, KASAN is able to report accesses to it, so the chance of reporting a use-after-free is increased. Once the object leaves quarantine, the allocator may reuse it, in which case the object is unpoisoned and KASAN can't detect incorrect accesses to it. Right now quarantine support is only enabled in SLAB allocator. Unification of KASAN features in SLAB and SLUB will be done later. This patch is based on the "mm: kasan: quarantine" patch originally prepared by Dmitry Chernenkov. A number of improvements have been suggested by Andrey Ryabinin. [glider@google.com: v9] Link: http://lkml.kernel.org/r/1462987130-144092-1-git-send-email-glider@google.com Signed-off-by: Alexander Potapenko <glider@google.com> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Andrey Konovalov <adech.fo@gmail.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Konstantin Serebryany <kcc@google.com> Cc: Dmitry Chernenkov <dmitryc@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
9 years ago
/*
* The fraction of physical memory the quarantine is allowed to occupy.
* Quarantine doesn't support memory shrinker with SLAB allocator, so we keep
* the ratio low to avoid OOM.
*/
#define QUARANTINE_FRACTION 32
static struct kmem_cache *qlink_to_cache(struct qlist_node *qlink)
{
return virt_to_head_page(qlink)->slab_cache;
}
static void *qlink_to_object(struct qlist_node *qlink, struct kmem_cache *cache)
{
struct kasan_free_meta *free_info =
container_of(qlink, struct kasan_free_meta,
quarantine_link);
return ((void *)free_info) - cache->kasan_info.free_meta_offset;
}
static void qlink_free(struct qlist_node *qlink, struct kmem_cache *cache)
{
void *object = qlink_to_object(qlink, cache);
unsigned long flags;
if (IS_ENABLED(CONFIG_SLAB))
local_irq_save(flags);
mm: kasan: initial memory quarantine implementation Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. When the object is freed, its state changes from KASAN_STATE_ALLOC to KASAN_STATE_QUARANTINE. The object is poisoned and put into quarantine instead of being returned to the allocator, therefore every subsequent access to that object triggers a KASAN error, and the error handler is able to say where the object has been allocated and deallocated. When it's time for the object to leave quarantine, its state becomes KASAN_STATE_FREE and it's returned to the allocator. From now on the allocator may reuse it for another allocation. Before that happens, it's still possible to detect a use-after free on that object (it retains the allocation/deallocation stacks). When the allocator reuses this object, the shadow is unpoisoned and old allocation/deallocation stacks are wiped. Therefore a use of this object, even an incorrect one, won't trigger ASan warning. Without the quarantine, it's not guaranteed that the objects aren't reused immediately, that's why the probability of catching a use-after-free is lower than with quarantine in place. Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. Freed objects are first added to per-cpu quarantine queues. When a cache is destroyed or memory shrinking is requested, the objects are moved into the global quarantine queue. Whenever a kmalloc call allows memory reclaiming, the oldest objects are popped out of the global queue until the total size of objects in quarantine is less than 3/4 of the maximum quarantine size (which is a fraction of installed physical memory). As long as an object remains in the quarantine, KASAN is able to report accesses to it, so the chance of reporting a use-after-free is increased. Once the object leaves quarantine, the allocator may reuse it, in which case the object is unpoisoned and KASAN can't detect incorrect accesses to it. Right now quarantine support is only enabled in SLAB allocator. Unification of KASAN features in SLAB and SLUB will be done later. This patch is based on the "mm: kasan: quarantine" patch originally prepared by Dmitry Chernenkov. A number of improvements have been suggested by Andrey Ryabinin. [glider@google.com: v9] Link: http://lkml.kernel.org/r/1462987130-144092-1-git-send-email-glider@google.com Signed-off-by: Alexander Potapenko <glider@google.com> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Andrey Konovalov <adech.fo@gmail.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Konstantin Serebryany <kcc@google.com> Cc: Dmitry Chernenkov <dmitryc@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
9 years ago
___cache_free(cache, object, _THIS_IP_);
if (IS_ENABLED(CONFIG_SLAB))
local_irq_restore(flags);
mm: kasan: initial memory quarantine implementation Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. When the object is freed, its state changes from KASAN_STATE_ALLOC to KASAN_STATE_QUARANTINE. The object is poisoned and put into quarantine instead of being returned to the allocator, therefore every subsequent access to that object triggers a KASAN error, and the error handler is able to say where the object has been allocated and deallocated. When it's time for the object to leave quarantine, its state becomes KASAN_STATE_FREE and it's returned to the allocator. From now on the allocator may reuse it for another allocation. Before that happens, it's still possible to detect a use-after free on that object (it retains the allocation/deallocation stacks). When the allocator reuses this object, the shadow is unpoisoned and old allocation/deallocation stacks are wiped. Therefore a use of this object, even an incorrect one, won't trigger ASan warning. Without the quarantine, it's not guaranteed that the objects aren't reused immediately, that's why the probability of catching a use-after-free is lower than with quarantine in place. Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. Freed objects are first added to per-cpu quarantine queues. When a cache is destroyed or memory shrinking is requested, the objects are moved into the global quarantine queue. Whenever a kmalloc call allows memory reclaiming, the oldest objects are popped out of the global queue until the total size of objects in quarantine is less than 3/4 of the maximum quarantine size (which is a fraction of installed physical memory). As long as an object remains in the quarantine, KASAN is able to report accesses to it, so the chance of reporting a use-after-free is increased. Once the object leaves quarantine, the allocator may reuse it, in which case the object is unpoisoned and KASAN can't detect incorrect accesses to it. Right now quarantine support is only enabled in SLAB allocator. Unification of KASAN features in SLAB and SLUB will be done later. This patch is based on the "mm: kasan: quarantine" patch originally prepared by Dmitry Chernenkov. A number of improvements have been suggested by Andrey Ryabinin. [glider@google.com: v9] Link: http://lkml.kernel.org/r/1462987130-144092-1-git-send-email-glider@google.com Signed-off-by: Alexander Potapenko <glider@google.com> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Andrey Konovalov <adech.fo@gmail.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Konstantin Serebryany <kcc@google.com> Cc: Dmitry Chernenkov <dmitryc@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
9 years ago
}
static void qlist_free_all(struct qlist_head *q, struct kmem_cache *cache)
{
struct qlist_node *qlink;
if (unlikely(qlist_empty(q)))
return;
qlink = q->head;
while (qlink) {
struct kmem_cache *obj_cache =
cache ? cache : qlink_to_cache(qlink);
struct qlist_node *next = qlink->next;
qlink_free(qlink, obj_cache);
qlink = next;
}
qlist_init(q);
}
void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache)
{
unsigned long flags;
struct qlist_head *q;
struct qlist_head temp = QLIST_INIT;
kasan: fix races in quarantine_remove_cache() quarantine_remove_cache() frees all pending objects that belong to the cache, before we destroy the cache itself. However there are currently two possibilities how it can fail to do so. First, another thread can hold some of the objects from the cache in temp list in quarantine_put(). quarantine_put() has a windows of enabled interrupts, and on_each_cpu() in quarantine_remove_cache() can finish right in that window. These objects will be later freed into the destroyed cache. Then, quarantine_reduce() has the same problem. It grabs a batch of objects from the global quarantine, then unlocks quarantine_lock and then frees the batch. quarantine_remove_cache() can finish while some objects from the cache are still in the local to_free list in quarantine_reduce(). Fix the race with quarantine_put() by disabling interrupts for the whole duration of quarantine_put(). In combination with on_each_cpu() in quarantine_remove_cache() it ensures that quarantine_remove_cache() either sees the objects in the per-cpu list or in the global list. Fix the race with quarantine_reduce() by protecting quarantine_reduce() with srcu critical section and then doing synchronize_srcu() at the end of quarantine_remove_cache(). I've done some assessment of how good synchronize_srcu() works in this case. And on a 4 CPU VM I see that it blocks waiting for pending read critical sections in about 2-3% of cases. Which looks good to me. I suspect that these races are the root cause of some GPFs that I episodically hit. Previously I did not have any explanation for them. BUG: unable to handle kernel NULL pointer dereference at 00000000000000c8 IP: qlist_free_all+0x2e/0xc0 mm/kasan/quarantine.c:155 PGD 6aeea067 PUD 60ed7067 PMD 0 Oops: 0000 [#1] SMP KASAN Dumping ftrace buffer: (ftrace buffer empty) Modules linked in: CPU: 0 PID: 13667 Comm: syz-executor2 Not tainted 4.10.0+ #60 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 task: ffff88005f948040 task.stack: ffff880069818000 RIP: 0010:qlist_free_all+0x2e/0xc0 mm/kasan/quarantine.c:155 RSP: 0018:ffff88006981f298 EFLAGS: 00010246 RAX: ffffea0000ffff00 RBX: 0000000000000000 RCX: ffffea0000ffff1f RDX: 0000000000000000 RSI: ffff88003fffc3e0 RDI: 0000000000000000 RBP: ffff88006981f2c0 R08: ffff88002fed7bd8 R09: 00000001001f000d R10: 00000000001f000d R11: ffff88006981f000 R12: ffff88003fffc3e0 R13: ffff88006981f2d0 R14: ffffffff81877fae R15: 0000000080000000 FS: 00007fb911a2d700(0000) GS:ffff88003ec00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000000000c8 CR3: 0000000060ed6000 CR4: 00000000000006f0 Call Trace: quarantine_reduce+0x10e/0x120 mm/kasan/quarantine.c:239 kasan_kmalloc+0xca/0xe0 mm/kasan/kasan.c:590 kasan_slab_alloc+0x12/0x20 mm/kasan/kasan.c:544 slab_post_alloc_hook mm/slab.h:456 [inline] slab_alloc_node mm/slub.c:2718 [inline] kmem_cache_alloc_node+0x1d3/0x280 mm/slub.c:2754 __alloc_skb+0x10f/0x770 net/core/skbuff.c:219 alloc_skb include/linux/skbuff.h:932 [inline] _sctp_make_chunk+0x3b/0x260 net/sctp/sm_make_chunk.c:1388 sctp_make_data net/sctp/sm_make_chunk.c:1420 [inline] sctp_make_datafrag_empty+0x208/0x360 net/sctp/sm_make_chunk.c:746 sctp_datamsg_from_user+0x7e8/0x11d0 net/sctp/chunk.c:266 sctp_sendmsg+0x2611/0x3970 net/sctp/socket.c:1962 inet_sendmsg+0x164/0x5b0 net/ipv4/af_inet.c:761 sock_sendmsg_nosec net/socket.c:633 [inline] sock_sendmsg+0xca/0x110 net/socket.c:643 SYSC_sendto+0x660/0x810 net/socket.c:1685 SyS_sendto+0x40/0x50 net/socket.c:1653 I am not sure about backporting. The bug is quite hard to trigger, I've seen it few times during our massive continuous testing (however, it could be cause of some other episodic stray crashes as it leads to memory corruption...). If it is triggered, the consequences are very bad -- almost definite bad memory corruption. The fix is non trivial and has chances of introducing new bugs. I am also not sure how actively people use KASAN on older releases. [dvyukov@google.com: - sorted includes[ Link: http://lkml.kernel.org/r/20170309094028.51088-1-dvyukov@google.com Link: http://lkml.kernel.org/r/20170308151532.5070-1-dvyukov@google.com Signed-off-by: Dmitry Vyukov <dvyukov@google.com> Acked-by: Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: Greg Thelen <gthelen@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
8 years ago
/*
* Note: irq must be disabled until after we move the batch to the
* global quarantine. Otherwise quarantine_remove_cache() can miss
* some objects belonging to the cache if they are in our local temp
* list. quarantine_remove_cache() executes on_each_cpu() at the
* beginning which ensures that it either sees the objects in per-cpu
* lists or in the global quarantine.
*/
mm: kasan: initial memory quarantine implementation Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. When the object is freed, its state changes from KASAN_STATE_ALLOC to KASAN_STATE_QUARANTINE. The object is poisoned and put into quarantine instead of being returned to the allocator, therefore every subsequent access to that object triggers a KASAN error, and the error handler is able to say where the object has been allocated and deallocated. When it's time for the object to leave quarantine, its state becomes KASAN_STATE_FREE and it's returned to the allocator. From now on the allocator may reuse it for another allocation. Before that happens, it's still possible to detect a use-after free on that object (it retains the allocation/deallocation stacks). When the allocator reuses this object, the shadow is unpoisoned and old allocation/deallocation stacks are wiped. Therefore a use of this object, even an incorrect one, won't trigger ASan warning. Without the quarantine, it's not guaranteed that the objects aren't reused immediately, that's why the probability of catching a use-after-free is lower than with quarantine in place. Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. Freed objects are first added to per-cpu quarantine queues. When a cache is destroyed or memory shrinking is requested, the objects are moved into the global quarantine queue. Whenever a kmalloc call allows memory reclaiming, the oldest objects are popped out of the global queue until the total size of objects in quarantine is less than 3/4 of the maximum quarantine size (which is a fraction of installed physical memory). As long as an object remains in the quarantine, KASAN is able to report accesses to it, so the chance of reporting a use-after-free is increased. Once the object leaves quarantine, the allocator may reuse it, in which case the object is unpoisoned and KASAN can't detect incorrect accesses to it. Right now quarantine support is only enabled in SLAB allocator. Unification of KASAN features in SLAB and SLUB will be done later. This patch is based on the "mm: kasan: quarantine" patch originally prepared by Dmitry Chernenkov. A number of improvements have been suggested by Andrey Ryabinin. [glider@google.com: v9] Link: http://lkml.kernel.org/r/1462987130-144092-1-git-send-email-glider@google.com Signed-off-by: Alexander Potapenko <glider@google.com> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Andrey Konovalov <adech.fo@gmail.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Konstantin Serebryany <kcc@google.com> Cc: Dmitry Chernenkov <dmitryc@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
9 years ago
local_irq_save(flags);
q = this_cpu_ptr(&cpu_quarantine);
qlist_put(q, &info->quarantine_link, cache->size);
kasan: fix races in quarantine_remove_cache() quarantine_remove_cache() frees all pending objects that belong to the cache, before we destroy the cache itself. However there are currently two possibilities how it can fail to do so. First, another thread can hold some of the objects from the cache in temp list in quarantine_put(). quarantine_put() has a windows of enabled interrupts, and on_each_cpu() in quarantine_remove_cache() can finish right in that window. These objects will be later freed into the destroyed cache. Then, quarantine_reduce() has the same problem. It grabs a batch of objects from the global quarantine, then unlocks quarantine_lock and then frees the batch. quarantine_remove_cache() can finish while some objects from the cache are still in the local to_free list in quarantine_reduce(). Fix the race with quarantine_put() by disabling interrupts for the whole duration of quarantine_put(). In combination with on_each_cpu() in quarantine_remove_cache() it ensures that quarantine_remove_cache() either sees the objects in the per-cpu list or in the global list. Fix the race with quarantine_reduce() by protecting quarantine_reduce() with srcu critical section and then doing synchronize_srcu() at the end of quarantine_remove_cache(). I've done some assessment of how good synchronize_srcu() works in this case. And on a 4 CPU VM I see that it blocks waiting for pending read critical sections in about 2-3% of cases. Which looks good to me. I suspect that these races are the root cause of some GPFs that I episodically hit. Previously I did not have any explanation for them. BUG: unable to handle kernel NULL pointer dereference at 00000000000000c8 IP: qlist_free_all+0x2e/0xc0 mm/kasan/quarantine.c:155 PGD 6aeea067 PUD 60ed7067 PMD 0 Oops: 0000 [#1] SMP KASAN Dumping ftrace buffer: (ftrace buffer empty) Modules linked in: CPU: 0 PID: 13667 Comm: syz-executor2 Not tainted 4.10.0+ #60 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 task: ffff88005f948040 task.stack: ffff880069818000 RIP: 0010:qlist_free_all+0x2e/0xc0 mm/kasan/quarantine.c:155 RSP: 0018:ffff88006981f298 EFLAGS: 00010246 RAX: ffffea0000ffff00 RBX: 0000000000000000 RCX: ffffea0000ffff1f RDX: 0000000000000000 RSI: ffff88003fffc3e0 RDI: 0000000000000000 RBP: ffff88006981f2c0 R08: ffff88002fed7bd8 R09: 00000001001f000d R10: 00000000001f000d R11: ffff88006981f000 R12: ffff88003fffc3e0 R13: ffff88006981f2d0 R14: ffffffff81877fae R15: 0000000080000000 FS: 00007fb911a2d700(0000) GS:ffff88003ec00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000000000c8 CR3: 0000000060ed6000 CR4: 00000000000006f0 Call Trace: quarantine_reduce+0x10e/0x120 mm/kasan/quarantine.c:239 kasan_kmalloc+0xca/0xe0 mm/kasan/kasan.c:590 kasan_slab_alloc+0x12/0x20 mm/kasan/kasan.c:544 slab_post_alloc_hook mm/slab.h:456 [inline] slab_alloc_node mm/slub.c:2718 [inline] kmem_cache_alloc_node+0x1d3/0x280 mm/slub.c:2754 __alloc_skb+0x10f/0x770 net/core/skbuff.c:219 alloc_skb include/linux/skbuff.h:932 [inline] _sctp_make_chunk+0x3b/0x260 net/sctp/sm_make_chunk.c:1388 sctp_make_data net/sctp/sm_make_chunk.c:1420 [inline] sctp_make_datafrag_empty+0x208/0x360 net/sctp/sm_make_chunk.c:746 sctp_datamsg_from_user+0x7e8/0x11d0 net/sctp/chunk.c:266 sctp_sendmsg+0x2611/0x3970 net/sctp/socket.c:1962 inet_sendmsg+0x164/0x5b0 net/ipv4/af_inet.c:761 sock_sendmsg_nosec net/socket.c:633 [inline] sock_sendmsg+0xca/0x110 net/socket.c:643 SYSC_sendto+0x660/0x810 net/socket.c:1685 SyS_sendto+0x40/0x50 net/socket.c:1653 I am not sure about backporting. The bug is quite hard to trigger, I've seen it few times during our massive continuous testing (however, it could be cause of some other episodic stray crashes as it leads to memory corruption...). If it is triggered, the consequences are very bad -- almost definite bad memory corruption. The fix is non trivial and has chances of introducing new bugs. I am also not sure how actively people use KASAN on older releases. [dvyukov@google.com: - sorted includes[ Link: http://lkml.kernel.org/r/20170309094028.51088-1-dvyukov@google.com Link: http://lkml.kernel.org/r/20170308151532.5070-1-dvyukov@google.com Signed-off-by: Dmitry Vyukov <dvyukov@google.com> Acked-by: Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: Greg Thelen <gthelen@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
8 years ago
if (unlikely(q->bytes > QUARANTINE_PERCPU_SIZE)) {
mm: kasan: initial memory quarantine implementation Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. When the object is freed, its state changes from KASAN_STATE_ALLOC to KASAN_STATE_QUARANTINE. The object is poisoned and put into quarantine instead of being returned to the allocator, therefore every subsequent access to that object triggers a KASAN error, and the error handler is able to say where the object has been allocated and deallocated. When it's time for the object to leave quarantine, its state becomes KASAN_STATE_FREE and it's returned to the allocator. From now on the allocator may reuse it for another allocation. Before that happens, it's still possible to detect a use-after free on that object (it retains the allocation/deallocation stacks). When the allocator reuses this object, the shadow is unpoisoned and old allocation/deallocation stacks are wiped. Therefore a use of this object, even an incorrect one, won't trigger ASan warning. Without the quarantine, it's not guaranteed that the objects aren't reused immediately, that's why the probability of catching a use-after-free is lower than with quarantine in place. Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. Freed objects are first added to per-cpu quarantine queues. When a cache is destroyed or memory shrinking is requested, the objects are moved into the global quarantine queue. Whenever a kmalloc call allows memory reclaiming, the oldest objects are popped out of the global queue until the total size of objects in quarantine is less than 3/4 of the maximum quarantine size (which is a fraction of installed physical memory). As long as an object remains in the quarantine, KASAN is able to report accesses to it, so the chance of reporting a use-after-free is increased. Once the object leaves quarantine, the allocator may reuse it, in which case the object is unpoisoned and KASAN can't detect incorrect accesses to it. Right now quarantine support is only enabled in SLAB allocator. Unification of KASAN features in SLAB and SLUB will be done later. This patch is based on the "mm: kasan: quarantine" patch originally prepared by Dmitry Chernenkov. A number of improvements have been suggested by Andrey Ryabinin. [glider@google.com: v9] Link: http://lkml.kernel.org/r/1462987130-144092-1-git-send-email-glider@google.com Signed-off-by: Alexander Potapenko <glider@google.com> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Andrey Konovalov <adech.fo@gmail.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Konstantin Serebryany <kcc@google.com> Cc: Dmitry Chernenkov <dmitryc@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
9 years ago
qlist_move_all(q, &temp);
raw_spin_lock(&quarantine_lock);
kasan: eliminate long stalls during quarantine reduction Currently we dedicate 1/32 of RAM for quarantine and then reduce it by 1/4 of total quarantine size. This can be a significant amount of memory. For example, with 4GB of RAM total quarantine size is 128MB and it is reduced by 32MB at a time. With 128GB of RAM total quarantine size is 4GB and it is reduced by 1GB. This leads to several problems: - freeing 1GB can take tens of seconds, causes rcu stall warnings and just introduces unexpected long delays at random places - if kmalloc() is called under a mutex, other threads stall on that mutex while a thread reduces quarantine - threads wait on quarantine_lock while one thread grabs a large batch of objects to evict - we walk the uncached list of object to free twice which makes all of the above worse - when a thread frees objects, they are already not accounted against global_quarantine.bytes; as the result we can have quarantine_size bytes in quarantine + unbounded amount of memory in large batches in threads that are in process of freeing Reduce size of quarantine in smaller batches to reduce the delays. The only reason to reduce it in batches is amortization of overheads, the new batch size of 1MB should be well enough to amortize spinlock lock/unlock and few function calls. Plus organize quarantine as a FIFO array of batches. This allows to not walk the list in quarantine_reduce() under quarantine_lock, which in turn reduces contention and is just faster. This improves performance of heavy load (syzkaller fuzzing) by ~20% with 4 CPUs and 32GB of RAM. Also this eliminates frequent (every 5 sec) drops of CPU consumption from ~400% to ~100% (one thread reduces quarantine while others are waiting on a mutex). Some reference numbers: 1. Machine with 4 CPUs and 4GB of memory. Quarantine size 128MB. Currently we free 32MB at at time. With new code we free 1MB at a time (1024 batches, ~128 are used). 2. Machine with 32 CPUs and 128GB of memory. Quarantine size 4GB. Currently we free 1GB at at time. With new code we free 8MB at a time (1024 batches, ~512 are used). 3. Machine with 4096 CPUs and 1TB of memory. Quarantine size 32GB. Currently we free 8GB at at time. With new code we free 4MB at a time (16K batches, ~8K are used). Link: http://lkml.kernel.org/r/1478756952-18695-1-git-send-email-dvyukov@google.com Signed-off-by: Dmitry Vyukov <dvyukov@google.com> Cc: Eric Dumazet <edumazet@google.com> Cc: Greg Thelen <gthelen@google.com> Cc: Alexander Potapenko <glider@google.com> Cc: Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: Andrey Konovalov <andreyknvl@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
8 years ago
WRITE_ONCE(quarantine_size, quarantine_size + temp.bytes);
qlist_move_all(&temp, &global_quarantine[quarantine_tail]);
if (global_quarantine[quarantine_tail].bytes >=
READ_ONCE(quarantine_batch_size)) {
int new_tail;
new_tail = quarantine_tail + 1;
if (new_tail == QUARANTINE_BATCHES)
new_tail = 0;
if (new_tail != quarantine_head)
quarantine_tail = new_tail;
}
raw_spin_unlock(&quarantine_lock);
mm: kasan: initial memory quarantine implementation Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. When the object is freed, its state changes from KASAN_STATE_ALLOC to KASAN_STATE_QUARANTINE. The object is poisoned and put into quarantine instead of being returned to the allocator, therefore every subsequent access to that object triggers a KASAN error, and the error handler is able to say where the object has been allocated and deallocated. When it's time for the object to leave quarantine, its state becomes KASAN_STATE_FREE and it's returned to the allocator. From now on the allocator may reuse it for another allocation. Before that happens, it's still possible to detect a use-after free on that object (it retains the allocation/deallocation stacks). When the allocator reuses this object, the shadow is unpoisoned and old allocation/deallocation stacks are wiped. Therefore a use of this object, even an incorrect one, won't trigger ASan warning. Without the quarantine, it's not guaranteed that the objects aren't reused immediately, that's why the probability of catching a use-after-free is lower than with quarantine in place. Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. Freed objects are first added to per-cpu quarantine queues. When a cache is destroyed or memory shrinking is requested, the objects are moved into the global quarantine queue. Whenever a kmalloc call allows memory reclaiming, the oldest objects are popped out of the global queue until the total size of objects in quarantine is less than 3/4 of the maximum quarantine size (which is a fraction of installed physical memory). As long as an object remains in the quarantine, KASAN is able to report accesses to it, so the chance of reporting a use-after-free is increased. Once the object leaves quarantine, the allocator may reuse it, in which case the object is unpoisoned and KASAN can't detect incorrect accesses to it. Right now quarantine support is only enabled in SLAB allocator. Unification of KASAN features in SLAB and SLUB will be done later. This patch is based on the "mm: kasan: quarantine" patch originally prepared by Dmitry Chernenkov. A number of improvements have been suggested by Andrey Ryabinin. [glider@google.com: v9] Link: http://lkml.kernel.org/r/1462987130-144092-1-git-send-email-glider@google.com Signed-off-by: Alexander Potapenko <glider@google.com> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Andrey Konovalov <adech.fo@gmail.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Konstantin Serebryany <kcc@google.com> Cc: Dmitry Chernenkov <dmitryc@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
9 years ago
}
kasan: fix races in quarantine_remove_cache() quarantine_remove_cache() frees all pending objects that belong to the cache, before we destroy the cache itself. However there are currently two possibilities how it can fail to do so. First, another thread can hold some of the objects from the cache in temp list in quarantine_put(). quarantine_put() has a windows of enabled interrupts, and on_each_cpu() in quarantine_remove_cache() can finish right in that window. These objects will be later freed into the destroyed cache. Then, quarantine_reduce() has the same problem. It grabs a batch of objects from the global quarantine, then unlocks quarantine_lock and then frees the batch. quarantine_remove_cache() can finish while some objects from the cache are still in the local to_free list in quarantine_reduce(). Fix the race with quarantine_put() by disabling interrupts for the whole duration of quarantine_put(). In combination with on_each_cpu() in quarantine_remove_cache() it ensures that quarantine_remove_cache() either sees the objects in the per-cpu list or in the global list. Fix the race with quarantine_reduce() by protecting quarantine_reduce() with srcu critical section and then doing synchronize_srcu() at the end of quarantine_remove_cache(). I've done some assessment of how good synchronize_srcu() works in this case. And on a 4 CPU VM I see that it blocks waiting for pending read critical sections in about 2-3% of cases. Which looks good to me. I suspect that these races are the root cause of some GPFs that I episodically hit. Previously I did not have any explanation for them. BUG: unable to handle kernel NULL pointer dereference at 00000000000000c8 IP: qlist_free_all+0x2e/0xc0 mm/kasan/quarantine.c:155 PGD 6aeea067 PUD 60ed7067 PMD 0 Oops: 0000 [#1] SMP KASAN Dumping ftrace buffer: (ftrace buffer empty) Modules linked in: CPU: 0 PID: 13667 Comm: syz-executor2 Not tainted 4.10.0+ #60 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 task: ffff88005f948040 task.stack: ffff880069818000 RIP: 0010:qlist_free_all+0x2e/0xc0 mm/kasan/quarantine.c:155 RSP: 0018:ffff88006981f298 EFLAGS: 00010246 RAX: ffffea0000ffff00 RBX: 0000000000000000 RCX: ffffea0000ffff1f RDX: 0000000000000000 RSI: ffff88003fffc3e0 RDI: 0000000000000000 RBP: ffff88006981f2c0 R08: ffff88002fed7bd8 R09: 00000001001f000d R10: 00000000001f000d R11: ffff88006981f000 R12: ffff88003fffc3e0 R13: ffff88006981f2d0 R14: ffffffff81877fae R15: 0000000080000000 FS: 00007fb911a2d700(0000) GS:ffff88003ec00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000000000c8 CR3: 0000000060ed6000 CR4: 00000000000006f0 Call Trace: quarantine_reduce+0x10e/0x120 mm/kasan/quarantine.c:239 kasan_kmalloc+0xca/0xe0 mm/kasan/kasan.c:590 kasan_slab_alloc+0x12/0x20 mm/kasan/kasan.c:544 slab_post_alloc_hook mm/slab.h:456 [inline] slab_alloc_node mm/slub.c:2718 [inline] kmem_cache_alloc_node+0x1d3/0x280 mm/slub.c:2754 __alloc_skb+0x10f/0x770 net/core/skbuff.c:219 alloc_skb include/linux/skbuff.h:932 [inline] _sctp_make_chunk+0x3b/0x260 net/sctp/sm_make_chunk.c:1388 sctp_make_data net/sctp/sm_make_chunk.c:1420 [inline] sctp_make_datafrag_empty+0x208/0x360 net/sctp/sm_make_chunk.c:746 sctp_datamsg_from_user+0x7e8/0x11d0 net/sctp/chunk.c:266 sctp_sendmsg+0x2611/0x3970 net/sctp/socket.c:1962 inet_sendmsg+0x164/0x5b0 net/ipv4/af_inet.c:761 sock_sendmsg_nosec net/socket.c:633 [inline] sock_sendmsg+0xca/0x110 net/socket.c:643 SYSC_sendto+0x660/0x810 net/socket.c:1685 SyS_sendto+0x40/0x50 net/socket.c:1653 I am not sure about backporting. The bug is quite hard to trigger, I've seen it few times during our massive continuous testing (however, it could be cause of some other episodic stray crashes as it leads to memory corruption...). If it is triggered, the consequences are very bad -- almost definite bad memory corruption. The fix is non trivial and has chances of introducing new bugs. I am also not sure how actively people use KASAN on older releases. [dvyukov@google.com: - sorted includes[ Link: http://lkml.kernel.org/r/20170309094028.51088-1-dvyukov@google.com Link: http://lkml.kernel.org/r/20170308151532.5070-1-dvyukov@google.com Signed-off-by: Dmitry Vyukov <dvyukov@google.com> Acked-by: Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: Greg Thelen <gthelen@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
8 years ago
local_irq_restore(flags);
mm: kasan: initial memory quarantine implementation Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. When the object is freed, its state changes from KASAN_STATE_ALLOC to KASAN_STATE_QUARANTINE. The object is poisoned and put into quarantine instead of being returned to the allocator, therefore every subsequent access to that object triggers a KASAN error, and the error handler is able to say where the object has been allocated and deallocated. When it's time for the object to leave quarantine, its state becomes KASAN_STATE_FREE and it's returned to the allocator. From now on the allocator may reuse it for another allocation. Before that happens, it's still possible to detect a use-after free on that object (it retains the allocation/deallocation stacks). When the allocator reuses this object, the shadow is unpoisoned and old allocation/deallocation stacks are wiped. Therefore a use of this object, even an incorrect one, won't trigger ASan warning. Without the quarantine, it's not guaranteed that the objects aren't reused immediately, that's why the probability of catching a use-after-free is lower than with quarantine in place. Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. Freed objects are first added to per-cpu quarantine queues. When a cache is destroyed or memory shrinking is requested, the objects are moved into the global quarantine queue. Whenever a kmalloc call allows memory reclaiming, the oldest objects are popped out of the global queue until the total size of objects in quarantine is less than 3/4 of the maximum quarantine size (which is a fraction of installed physical memory). As long as an object remains in the quarantine, KASAN is able to report accesses to it, so the chance of reporting a use-after-free is increased. Once the object leaves quarantine, the allocator may reuse it, in which case the object is unpoisoned and KASAN can't detect incorrect accesses to it. Right now quarantine support is only enabled in SLAB allocator. Unification of KASAN features in SLAB and SLUB will be done later. This patch is based on the "mm: kasan: quarantine" patch originally prepared by Dmitry Chernenkov. A number of improvements have been suggested by Andrey Ryabinin. [glider@google.com: v9] Link: http://lkml.kernel.org/r/1462987130-144092-1-git-send-email-glider@google.com Signed-off-by: Alexander Potapenko <glider@google.com> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Andrey Konovalov <adech.fo@gmail.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Konstantin Serebryany <kcc@google.com> Cc: Dmitry Chernenkov <dmitryc@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
9 years ago
}
void quarantine_reduce(void)
{
kasan: eliminate long stalls during quarantine reduction Currently we dedicate 1/32 of RAM for quarantine and then reduce it by 1/4 of total quarantine size. This can be a significant amount of memory. For example, with 4GB of RAM total quarantine size is 128MB and it is reduced by 32MB at a time. With 128GB of RAM total quarantine size is 4GB and it is reduced by 1GB. This leads to several problems: - freeing 1GB can take tens of seconds, causes rcu stall warnings and just introduces unexpected long delays at random places - if kmalloc() is called under a mutex, other threads stall on that mutex while a thread reduces quarantine - threads wait on quarantine_lock while one thread grabs a large batch of objects to evict - we walk the uncached list of object to free twice which makes all of the above worse - when a thread frees objects, they are already not accounted against global_quarantine.bytes; as the result we can have quarantine_size bytes in quarantine + unbounded amount of memory in large batches in threads that are in process of freeing Reduce size of quarantine in smaller batches to reduce the delays. The only reason to reduce it in batches is amortization of overheads, the new batch size of 1MB should be well enough to amortize spinlock lock/unlock and few function calls. Plus organize quarantine as a FIFO array of batches. This allows to not walk the list in quarantine_reduce() under quarantine_lock, which in turn reduces contention and is just faster. This improves performance of heavy load (syzkaller fuzzing) by ~20% with 4 CPUs and 32GB of RAM. Also this eliminates frequent (every 5 sec) drops of CPU consumption from ~400% to ~100% (one thread reduces quarantine while others are waiting on a mutex). Some reference numbers: 1. Machine with 4 CPUs and 4GB of memory. Quarantine size 128MB. Currently we free 32MB at at time. With new code we free 1MB at a time (1024 batches, ~128 are used). 2. Machine with 32 CPUs and 128GB of memory. Quarantine size 4GB. Currently we free 1GB at at time. With new code we free 8MB at a time (1024 batches, ~512 are used). 3. Machine with 4096 CPUs and 1TB of memory. Quarantine size 32GB. Currently we free 8GB at at time. With new code we free 4MB at a time (16K batches, ~8K are used). Link: http://lkml.kernel.org/r/1478756952-18695-1-git-send-email-dvyukov@google.com Signed-off-by: Dmitry Vyukov <dvyukov@google.com> Cc: Eric Dumazet <edumazet@google.com> Cc: Greg Thelen <gthelen@google.com> Cc: Alexander Potapenko <glider@google.com> Cc: Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: Andrey Konovalov <andreyknvl@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
8 years ago
size_t total_size, new_quarantine_size, percpu_quarantines;
mm: kasan: initial memory quarantine implementation Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. When the object is freed, its state changes from KASAN_STATE_ALLOC to KASAN_STATE_QUARANTINE. The object is poisoned and put into quarantine instead of being returned to the allocator, therefore every subsequent access to that object triggers a KASAN error, and the error handler is able to say where the object has been allocated and deallocated. When it's time for the object to leave quarantine, its state becomes KASAN_STATE_FREE and it's returned to the allocator. From now on the allocator may reuse it for another allocation. Before that happens, it's still possible to detect a use-after free on that object (it retains the allocation/deallocation stacks). When the allocator reuses this object, the shadow is unpoisoned and old allocation/deallocation stacks are wiped. Therefore a use of this object, even an incorrect one, won't trigger ASan warning. Without the quarantine, it's not guaranteed that the objects aren't reused immediately, that's why the probability of catching a use-after-free is lower than with quarantine in place. Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. Freed objects are first added to per-cpu quarantine queues. When a cache is destroyed or memory shrinking is requested, the objects are moved into the global quarantine queue. Whenever a kmalloc call allows memory reclaiming, the oldest objects are popped out of the global queue until the total size of objects in quarantine is less than 3/4 of the maximum quarantine size (which is a fraction of installed physical memory). As long as an object remains in the quarantine, KASAN is able to report accesses to it, so the chance of reporting a use-after-free is increased. Once the object leaves quarantine, the allocator may reuse it, in which case the object is unpoisoned and KASAN can't detect incorrect accesses to it. Right now quarantine support is only enabled in SLAB allocator. Unification of KASAN features in SLAB and SLUB will be done later. This patch is based on the "mm: kasan: quarantine" patch originally prepared by Dmitry Chernenkov. A number of improvements have been suggested by Andrey Ryabinin. [glider@google.com: v9] Link: http://lkml.kernel.org/r/1462987130-144092-1-git-send-email-glider@google.com Signed-off-by: Alexander Potapenko <glider@google.com> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Andrey Konovalov <adech.fo@gmail.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Konstantin Serebryany <kcc@google.com> Cc: Dmitry Chernenkov <dmitryc@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
9 years ago
unsigned long flags;
kasan: fix races in quarantine_remove_cache() quarantine_remove_cache() frees all pending objects that belong to the cache, before we destroy the cache itself. However there are currently two possibilities how it can fail to do so. First, another thread can hold some of the objects from the cache in temp list in quarantine_put(). quarantine_put() has a windows of enabled interrupts, and on_each_cpu() in quarantine_remove_cache() can finish right in that window. These objects will be later freed into the destroyed cache. Then, quarantine_reduce() has the same problem. It grabs a batch of objects from the global quarantine, then unlocks quarantine_lock and then frees the batch. quarantine_remove_cache() can finish while some objects from the cache are still in the local to_free list in quarantine_reduce(). Fix the race with quarantine_put() by disabling interrupts for the whole duration of quarantine_put(). In combination with on_each_cpu() in quarantine_remove_cache() it ensures that quarantine_remove_cache() either sees the objects in the per-cpu list or in the global list. Fix the race with quarantine_reduce() by protecting quarantine_reduce() with srcu critical section and then doing synchronize_srcu() at the end of quarantine_remove_cache(). I've done some assessment of how good synchronize_srcu() works in this case. And on a 4 CPU VM I see that it blocks waiting for pending read critical sections in about 2-3% of cases. Which looks good to me. I suspect that these races are the root cause of some GPFs that I episodically hit. Previously I did not have any explanation for them. BUG: unable to handle kernel NULL pointer dereference at 00000000000000c8 IP: qlist_free_all+0x2e/0xc0 mm/kasan/quarantine.c:155 PGD 6aeea067 PUD 60ed7067 PMD 0 Oops: 0000 [#1] SMP KASAN Dumping ftrace buffer: (ftrace buffer empty) Modules linked in: CPU: 0 PID: 13667 Comm: syz-executor2 Not tainted 4.10.0+ #60 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 task: ffff88005f948040 task.stack: ffff880069818000 RIP: 0010:qlist_free_all+0x2e/0xc0 mm/kasan/quarantine.c:155 RSP: 0018:ffff88006981f298 EFLAGS: 00010246 RAX: ffffea0000ffff00 RBX: 0000000000000000 RCX: ffffea0000ffff1f RDX: 0000000000000000 RSI: ffff88003fffc3e0 RDI: 0000000000000000 RBP: ffff88006981f2c0 R08: ffff88002fed7bd8 R09: 00000001001f000d R10: 00000000001f000d R11: ffff88006981f000 R12: ffff88003fffc3e0 R13: ffff88006981f2d0 R14: ffffffff81877fae R15: 0000000080000000 FS: 00007fb911a2d700(0000) GS:ffff88003ec00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000000000c8 CR3: 0000000060ed6000 CR4: 00000000000006f0 Call Trace: quarantine_reduce+0x10e/0x120 mm/kasan/quarantine.c:239 kasan_kmalloc+0xca/0xe0 mm/kasan/kasan.c:590 kasan_slab_alloc+0x12/0x20 mm/kasan/kasan.c:544 slab_post_alloc_hook mm/slab.h:456 [inline] slab_alloc_node mm/slub.c:2718 [inline] kmem_cache_alloc_node+0x1d3/0x280 mm/slub.c:2754 __alloc_skb+0x10f/0x770 net/core/skbuff.c:219 alloc_skb include/linux/skbuff.h:932 [inline] _sctp_make_chunk+0x3b/0x260 net/sctp/sm_make_chunk.c:1388 sctp_make_data net/sctp/sm_make_chunk.c:1420 [inline] sctp_make_datafrag_empty+0x208/0x360 net/sctp/sm_make_chunk.c:746 sctp_datamsg_from_user+0x7e8/0x11d0 net/sctp/chunk.c:266 sctp_sendmsg+0x2611/0x3970 net/sctp/socket.c:1962 inet_sendmsg+0x164/0x5b0 net/ipv4/af_inet.c:761 sock_sendmsg_nosec net/socket.c:633 [inline] sock_sendmsg+0xca/0x110 net/socket.c:643 SYSC_sendto+0x660/0x810 net/socket.c:1685 SyS_sendto+0x40/0x50 net/socket.c:1653 I am not sure about backporting. The bug is quite hard to trigger, I've seen it few times during our massive continuous testing (however, it could be cause of some other episodic stray crashes as it leads to memory corruption...). If it is triggered, the consequences are very bad -- almost definite bad memory corruption. The fix is non trivial and has chances of introducing new bugs. I am also not sure how actively people use KASAN on older releases. [dvyukov@google.com: - sorted includes[ Link: http://lkml.kernel.org/r/20170309094028.51088-1-dvyukov@google.com Link: http://lkml.kernel.org/r/20170308151532.5070-1-dvyukov@google.com Signed-off-by: Dmitry Vyukov <dvyukov@google.com> Acked-by: Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: Greg Thelen <gthelen@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
8 years ago
int srcu_idx;
mm: kasan: initial memory quarantine implementation Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. When the object is freed, its state changes from KASAN_STATE_ALLOC to KASAN_STATE_QUARANTINE. The object is poisoned and put into quarantine instead of being returned to the allocator, therefore every subsequent access to that object triggers a KASAN error, and the error handler is able to say where the object has been allocated and deallocated. When it's time for the object to leave quarantine, its state becomes KASAN_STATE_FREE and it's returned to the allocator. From now on the allocator may reuse it for another allocation. Before that happens, it's still possible to detect a use-after free on that object (it retains the allocation/deallocation stacks). When the allocator reuses this object, the shadow is unpoisoned and old allocation/deallocation stacks are wiped. Therefore a use of this object, even an incorrect one, won't trigger ASan warning. Without the quarantine, it's not guaranteed that the objects aren't reused immediately, that's why the probability of catching a use-after-free is lower than with quarantine in place. Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. Freed objects are first added to per-cpu quarantine queues. When a cache is destroyed or memory shrinking is requested, the objects are moved into the global quarantine queue. Whenever a kmalloc call allows memory reclaiming, the oldest objects are popped out of the global queue until the total size of objects in quarantine is less than 3/4 of the maximum quarantine size (which is a fraction of installed physical memory). As long as an object remains in the quarantine, KASAN is able to report accesses to it, so the chance of reporting a use-after-free is increased. Once the object leaves quarantine, the allocator may reuse it, in which case the object is unpoisoned and KASAN can't detect incorrect accesses to it. Right now quarantine support is only enabled in SLAB allocator. Unification of KASAN features in SLAB and SLUB will be done later. This patch is based on the "mm: kasan: quarantine" patch originally prepared by Dmitry Chernenkov. A number of improvements have been suggested by Andrey Ryabinin. [glider@google.com: v9] Link: http://lkml.kernel.org/r/1462987130-144092-1-git-send-email-glider@google.com Signed-off-by: Alexander Potapenko <glider@google.com> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Andrey Konovalov <adech.fo@gmail.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Konstantin Serebryany <kcc@google.com> Cc: Dmitry Chernenkov <dmitryc@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
9 years ago
struct qlist_head to_free = QLIST_INIT;
kasan: eliminate long stalls during quarantine reduction Currently we dedicate 1/32 of RAM for quarantine and then reduce it by 1/4 of total quarantine size. This can be a significant amount of memory. For example, with 4GB of RAM total quarantine size is 128MB and it is reduced by 32MB at a time. With 128GB of RAM total quarantine size is 4GB and it is reduced by 1GB. This leads to several problems: - freeing 1GB can take tens of seconds, causes rcu stall warnings and just introduces unexpected long delays at random places - if kmalloc() is called under a mutex, other threads stall on that mutex while a thread reduces quarantine - threads wait on quarantine_lock while one thread grabs a large batch of objects to evict - we walk the uncached list of object to free twice which makes all of the above worse - when a thread frees objects, they are already not accounted against global_quarantine.bytes; as the result we can have quarantine_size bytes in quarantine + unbounded amount of memory in large batches in threads that are in process of freeing Reduce size of quarantine in smaller batches to reduce the delays. The only reason to reduce it in batches is amortization of overheads, the new batch size of 1MB should be well enough to amortize spinlock lock/unlock and few function calls. Plus organize quarantine as a FIFO array of batches. This allows to not walk the list in quarantine_reduce() under quarantine_lock, which in turn reduces contention and is just faster. This improves performance of heavy load (syzkaller fuzzing) by ~20% with 4 CPUs and 32GB of RAM. Also this eliminates frequent (every 5 sec) drops of CPU consumption from ~400% to ~100% (one thread reduces quarantine while others are waiting on a mutex). Some reference numbers: 1. Machine with 4 CPUs and 4GB of memory. Quarantine size 128MB. Currently we free 32MB at at time. With new code we free 1MB at a time (1024 batches, ~128 are used). 2. Machine with 32 CPUs and 128GB of memory. Quarantine size 4GB. Currently we free 1GB at at time. With new code we free 8MB at a time (1024 batches, ~512 are used). 3. Machine with 4096 CPUs and 1TB of memory. Quarantine size 32GB. Currently we free 8GB at at time. With new code we free 4MB at a time (16K batches, ~8K are used). Link: http://lkml.kernel.org/r/1478756952-18695-1-git-send-email-dvyukov@google.com Signed-off-by: Dmitry Vyukov <dvyukov@google.com> Cc: Eric Dumazet <edumazet@google.com> Cc: Greg Thelen <gthelen@google.com> Cc: Alexander Potapenko <glider@google.com> Cc: Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: Andrey Konovalov <andreyknvl@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
8 years ago
if (likely(READ_ONCE(quarantine_size) <=
READ_ONCE(quarantine_max_size)))
mm: kasan: initial memory quarantine implementation Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. When the object is freed, its state changes from KASAN_STATE_ALLOC to KASAN_STATE_QUARANTINE. The object is poisoned and put into quarantine instead of being returned to the allocator, therefore every subsequent access to that object triggers a KASAN error, and the error handler is able to say where the object has been allocated and deallocated. When it's time for the object to leave quarantine, its state becomes KASAN_STATE_FREE and it's returned to the allocator. From now on the allocator may reuse it for another allocation. Before that happens, it's still possible to detect a use-after free on that object (it retains the allocation/deallocation stacks). When the allocator reuses this object, the shadow is unpoisoned and old allocation/deallocation stacks are wiped. Therefore a use of this object, even an incorrect one, won't trigger ASan warning. Without the quarantine, it's not guaranteed that the objects aren't reused immediately, that's why the probability of catching a use-after-free is lower than with quarantine in place. Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. Freed objects are first added to per-cpu quarantine queues. When a cache is destroyed or memory shrinking is requested, the objects are moved into the global quarantine queue. Whenever a kmalloc call allows memory reclaiming, the oldest objects are popped out of the global queue until the total size of objects in quarantine is less than 3/4 of the maximum quarantine size (which is a fraction of installed physical memory). As long as an object remains in the quarantine, KASAN is able to report accesses to it, so the chance of reporting a use-after-free is increased. Once the object leaves quarantine, the allocator may reuse it, in which case the object is unpoisoned and KASAN can't detect incorrect accesses to it. Right now quarantine support is only enabled in SLAB allocator. Unification of KASAN features in SLAB and SLUB will be done later. This patch is based on the "mm: kasan: quarantine" patch originally prepared by Dmitry Chernenkov. A number of improvements have been suggested by Andrey Ryabinin. [glider@google.com: v9] Link: http://lkml.kernel.org/r/1462987130-144092-1-git-send-email-glider@google.com Signed-off-by: Alexander Potapenko <glider@google.com> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Andrey Konovalov <adech.fo@gmail.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Konstantin Serebryany <kcc@google.com> Cc: Dmitry Chernenkov <dmitryc@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
9 years ago
return;
kasan: fix races in quarantine_remove_cache() quarantine_remove_cache() frees all pending objects that belong to the cache, before we destroy the cache itself. However there are currently two possibilities how it can fail to do so. First, another thread can hold some of the objects from the cache in temp list in quarantine_put(). quarantine_put() has a windows of enabled interrupts, and on_each_cpu() in quarantine_remove_cache() can finish right in that window. These objects will be later freed into the destroyed cache. Then, quarantine_reduce() has the same problem. It grabs a batch of objects from the global quarantine, then unlocks quarantine_lock and then frees the batch. quarantine_remove_cache() can finish while some objects from the cache are still in the local to_free list in quarantine_reduce(). Fix the race with quarantine_put() by disabling interrupts for the whole duration of quarantine_put(). In combination with on_each_cpu() in quarantine_remove_cache() it ensures that quarantine_remove_cache() either sees the objects in the per-cpu list or in the global list. Fix the race with quarantine_reduce() by protecting quarantine_reduce() with srcu critical section and then doing synchronize_srcu() at the end of quarantine_remove_cache(). I've done some assessment of how good synchronize_srcu() works in this case. And on a 4 CPU VM I see that it blocks waiting for pending read critical sections in about 2-3% of cases. Which looks good to me. I suspect that these races are the root cause of some GPFs that I episodically hit. Previously I did not have any explanation for them. BUG: unable to handle kernel NULL pointer dereference at 00000000000000c8 IP: qlist_free_all+0x2e/0xc0 mm/kasan/quarantine.c:155 PGD 6aeea067 PUD 60ed7067 PMD 0 Oops: 0000 [#1] SMP KASAN Dumping ftrace buffer: (ftrace buffer empty) Modules linked in: CPU: 0 PID: 13667 Comm: syz-executor2 Not tainted 4.10.0+ #60 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 task: ffff88005f948040 task.stack: ffff880069818000 RIP: 0010:qlist_free_all+0x2e/0xc0 mm/kasan/quarantine.c:155 RSP: 0018:ffff88006981f298 EFLAGS: 00010246 RAX: ffffea0000ffff00 RBX: 0000000000000000 RCX: ffffea0000ffff1f RDX: 0000000000000000 RSI: ffff88003fffc3e0 RDI: 0000000000000000 RBP: ffff88006981f2c0 R08: ffff88002fed7bd8 R09: 00000001001f000d R10: 00000000001f000d R11: ffff88006981f000 R12: ffff88003fffc3e0 R13: ffff88006981f2d0 R14: ffffffff81877fae R15: 0000000080000000 FS: 00007fb911a2d700(0000) GS:ffff88003ec00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000000000c8 CR3: 0000000060ed6000 CR4: 00000000000006f0 Call Trace: quarantine_reduce+0x10e/0x120 mm/kasan/quarantine.c:239 kasan_kmalloc+0xca/0xe0 mm/kasan/kasan.c:590 kasan_slab_alloc+0x12/0x20 mm/kasan/kasan.c:544 slab_post_alloc_hook mm/slab.h:456 [inline] slab_alloc_node mm/slub.c:2718 [inline] kmem_cache_alloc_node+0x1d3/0x280 mm/slub.c:2754 __alloc_skb+0x10f/0x770 net/core/skbuff.c:219 alloc_skb include/linux/skbuff.h:932 [inline] _sctp_make_chunk+0x3b/0x260 net/sctp/sm_make_chunk.c:1388 sctp_make_data net/sctp/sm_make_chunk.c:1420 [inline] sctp_make_datafrag_empty+0x208/0x360 net/sctp/sm_make_chunk.c:746 sctp_datamsg_from_user+0x7e8/0x11d0 net/sctp/chunk.c:266 sctp_sendmsg+0x2611/0x3970 net/sctp/socket.c:1962 inet_sendmsg+0x164/0x5b0 net/ipv4/af_inet.c:761 sock_sendmsg_nosec net/socket.c:633 [inline] sock_sendmsg+0xca/0x110 net/socket.c:643 SYSC_sendto+0x660/0x810 net/socket.c:1685 SyS_sendto+0x40/0x50 net/socket.c:1653 I am not sure about backporting. The bug is quite hard to trigger, I've seen it few times during our massive continuous testing (however, it could be cause of some other episodic stray crashes as it leads to memory corruption...). If it is triggered, the consequences are very bad -- almost definite bad memory corruption. The fix is non trivial and has chances of introducing new bugs. I am also not sure how actively people use KASAN on older releases. [dvyukov@google.com: - sorted includes[ Link: http://lkml.kernel.org/r/20170309094028.51088-1-dvyukov@google.com Link: http://lkml.kernel.org/r/20170308151532.5070-1-dvyukov@google.com Signed-off-by: Dmitry Vyukov <dvyukov@google.com> Acked-by: Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: Greg Thelen <gthelen@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
8 years ago
/*
* srcu critical section ensures that quarantine_remove_cache()
* will not miss objects belonging to the cache while they are in our
* local to_free list. srcu is chosen because (1) it gives us private
* grace period domain that does not interfere with anything else,
* and (2) it allows synchronize_srcu() to return without waiting
* if there are no pending read critical sections (which is the
* expected case).
*/
srcu_idx = srcu_read_lock(&remove_cache_srcu);
raw_spin_lock_irqsave(&quarantine_lock, flags);
mm: kasan: initial memory quarantine implementation Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. When the object is freed, its state changes from KASAN_STATE_ALLOC to KASAN_STATE_QUARANTINE. The object is poisoned and put into quarantine instead of being returned to the allocator, therefore every subsequent access to that object triggers a KASAN error, and the error handler is able to say where the object has been allocated and deallocated. When it's time for the object to leave quarantine, its state becomes KASAN_STATE_FREE and it's returned to the allocator. From now on the allocator may reuse it for another allocation. Before that happens, it's still possible to detect a use-after free on that object (it retains the allocation/deallocation stacks). When the allocator reuses this object, the shadow is unpoisoned and old allocation/deallocation stacks are wiped. Therefore a use of this object, even an incorrect one, won't trigger ASan warning. Without the quarantine, it's not guaranteed that the objects aren't reused immediately, that's why the probability of catching a use-after-free is lower than with quarantine in place. Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. Freed objects are first added to per-cpu quarantine queues. When a cache is destroyed or memory shrinking is requested, the objects are moved into the global quarantine queue. Whenever a kmalloc call allows memory reclaiming, the oldest objects are popped out of the global queue until the total size of objects in quarantine is less than 3/4 of the maximum quarantine size (which is a fraction of installed physical memory). As long as an object remains in the quarantine, KASAN is able to report accesses to it, so the chance of reporting a use-after-free is increased. Once the object leaves quarantine, the allocator may reuse it, in which case the object is unpoisoned and KASAN can't detect incorrect accesses to it. Right now quarantine support is only enabled in SLAB allocator. Unification of KASAN features in SLAB and SLUB will be done later. This patch is based on the "mm: kasan: quarantine" patch originally prepared by Dmitry Chernenkov. A number of improvements have been suggested by Andrey Ryabinin. [glider@google.com: v9] Link: http://lkml.kernel.org/r/1462987130-144092-1-git-send-email-glider@google.com Signed-off-by: Alexander Potapenko <glider@google.com> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Andrey Konovalov <adech.fo@gmail.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Konstantin Serebryany <kcc@google.com> Cc: Dmitry Chernenkov <dmitryc@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
9 years ago
/*
* Update quarantine size in case of hotplug. Allocate a fraction of
* the installed memory to quarantine minus per-cpu queue limits.
*/
kasan: eliminate long stalls during quarantine reduction Currently we dedicate 1/32 of RAM for quarantine and then reduce it by 1/4 of total quarantine size. This can be a significant amount of memory. For example, with 4GB of RAM total quarantine size is 128MB and it is reduced by 32MB at a time. With 128GB of RAM total quarantine size is 4GB and it is reduced by 1GB. This leads to several problems: - freeing 1GB can take tens of seconds, causes rcu stall warnings and just introduces unexpected long delays at random places - if kmalloc() is called under a mutex, other threads stall on that mutex while a thread reduces quarantine - threads wait on quarantine_lock while one thread grabs a large batch of objects to evict - we walk the uncached list of object to free twice which makes all of the above worse - when a thread frees objects, they are already not accounted against global_quarantine.bytes; as the result we can have quarantine_size bytes in quarantine + unbounded amount of memory in large batches in threads that are in process of freeing Reduce size of quarantine in smaller batches to reduce the delays. The only reason to reduce it in batches is amortization of overheads, the new batch size of 1MB should be well enough to amortize spinlock lock/unlock and few function calls. Plus organize quarantine as a FIFO array of batches. This allows to not walk the list in quarantine_reduce() under quarantine_lock, which in turn reduces contention and is just faster. This improves performance of heavy load (syzkaller fuzzing) by ~20% with 4 CPUs and 32GB of RAM. Also this eliminates frequent (every 5 sec) drops of CPU consumption from ~400% to ~100% (one thread reduces quarantine while others are waiting on a mutex). Some reference numbers: 1. Machine with 4 CPUs and 4GB of memory. Quarantine size 128MB. Currently we free 32MB at at time. With new code we free 1MB at a time (1024 batches, ~128 are used). 2. Machine with 32 CPUs and 128GB of memory. Quarantine size 4GB. Currently we free 1GB at at time. With new code we free 8MB at a time (1024 batches, ~512 are used). 3. Machine with 4096 CPUs and 1TB of memory. Quarantine size 32GB. Currently we free 8GB at at time. With new code we free 4MB at a time (16K batches, ~8K are used). Link: http://lkml.kernel.org/r/1478756952-18695-1-git-send-email-dvyukov@google.com Signed-off-by: Dmitry Vyukov <dvyukov@google.com> Cc: Eric Dumazet <edumazet@google.com> Cc: Greg Thelen <gthelen@google.com> Cc: Alexander Potapenko <glider@google.com> Cc: Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: Andrey Konovalov <andreyknvl@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
8 years ago
total_size = (READ_ONCE(totalram_pages) << PAGE_SHIFT) /
mm: kasan: initial memory quarantine implementation Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. When the object is freed, its state changes from KASAN_STATE_ALLOC to KASAN_STATE_QUARANTINE. The object is poisoned and put into quarantine instead of being returned to the allocator, therefore every subsequent access to that object triggers a KASAN error, and the error handler is able to say where the object has been allocated and deallocated. When it's time for the object to leave quarantine, its state becomes KASAN_STATE_FREE and it's returned to the allocator. From now on the allocator may reuse it for another allocation. Before that happens, it's still possible to detect a use-after free on that object (it retains the allocation/deallocation stacks). When the allocator reuses this object, the shadow is unpoisoned and old allocation/deallocation stacks are wiped. Therefore a use of this object, even an incorrect one, won't trigger ASan warning. Without the quarantine, it's not guaranteed that the objects aren't reused immediately, that's why the probability of catching a use-after-free is lower than with quarantine in place. Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. Freed objects are first added to per-cpu quarantine queues. When a cache is destroyed or memory shrinking is requested, the objects are moved into the global quarantine queue. Whenever a kmalloc call allows memory reclaiming, the oldest objects are popped out of the global queue until the total size of objects in quarantine is less than 3/4 of the maximum quarantine size (which is a fraction of installed physical memory). As long as an object remains in the quarantine, KASAN is able to report accesses to it, so the chance of reporting a use-after-free is increased. Once the object leaves quarantine, the allocator may reuse it, in which case the object is unpoisoned and KASAN can't detect incorrect accesses to it. Right now quarantine support is only enabled in SLAB allocator. Unification of KASAN features in SLAB and SLUB will be done later. This patch is based on the "mm: kasan: quarantine" patch originally prepared by Dmitry Chernenkov. A number of improvements have been suggested by Andrey Ryabinin. [glider@google.com: v9] Link: http://lkml.kernel.org/r/1462987130-144092-1-git-send-email-glider@google.com Signed-off-by: Alexander Potapenko <glider@google.com> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Andrey Konovalov <adech.fo@gmail.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Konstantin Serebryany <kcc@google.com> Cc: Dmitry Chernenkov <dmitryc@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
9 years ago
QUARANTINE_FRACTION;
percpu_quarantines = QUARANTINE_PERCPU_SIZE * num_online_cpus();
kasan: eliminate long stalls during quarantine reduction Currently we dedicate 1/32 of RAM for quarantine and then reduce it by 1/4 of total quarantine size. This can be a significant amount of memory. For example, with 4GB of RAM total quarantine size is 128MB and it is reduced by 32MB at a time. With 128GB of RAM total quarantine size is 4GB and it is reduced by 1GB. This leads to several problems: - freeing 1GB can take tens of seconds, causes rcu stall warnings and just introduces unexpected long delays at random places - if kmalloc() is called under a mutex, other threads stall on that mutex while a thread reduces quarantine - threads wait on quarantine_lock while one thread grabs a large batch of objects to evict - we walk the uncached list of object to free twice which makes all of the above worse - when a thread frees objects, they are already not accounted against global_quarantine.bytes; as the result we can have quarantine_size bytes in quarantine + unbounded amount of memory in large batches in threads that are in process of freeing Reduce size of quarantine in smaller batches to reduce the delays. The only reason to reduce it in batches is amortization of overheads, the new batch size of 1MB should be well enough to amortize spinlock lock/unlock and few function calls. Plus organize quarantine as a FIFO array of batches. This allows to not walk the list in quarantine_reduce() under quarantine_lock, which in turn reduces contention and is just faster. This improves performance of heavy load (syzkaller fuzzing) by ~20% with 4 CPUs and 32GB of RAM. Also this eliminates frequent (every 5 sec) drops of CPU consumption from ~400% to ~100% (one thread reduces quarantine while others are waiting on a mutex). Some reference numbers: 1. Machine with 4 CPUs and 4GB of memory. Quarantine size 128MB. Currently we free 32MB at at time. With new code we free 1MB at a time (1024 batches, ~128 are used). 2. Machine with 32 CPUs and 128GB of memory. Quarantine size 4GB. Currently we free 1GB at at time. With new code we free 8MB at a time (1024 batches, ~512 are used). 3. Machine with 4096 CPUs and 1TB of memory. Quarantine size 32GB. Currently we free 8GB at at time. With new code we free 4MB at a time (16K batches, ~8K are used). Link: http://lkml.kernel.org/r/1478756952-18695-1-git-send-email-dvyukov@google.com Signed-off-by: Dmitry Vyukov <dvyukov@google.com> Cc: Eric Dumazet <edumazet@google.com> Cc: Greg Thelen <gthelen@google.com> Cc: Alexander Potapenko <glider@google.com> Cc: Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: Andrey Konovalov <andreyknvl@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
8 years ago
new_quarantine_size = (total_size < percpu_quarantines) ?
0 : total_size - percpu_quarantines;
WRITE_ONCE(quarantine_max_size, new_quarantine_size);
/* Aim at consuming at most 1/2 of slots in quarantine. */
WRITE_ONCE(quarantine_batch_size, max((size_t)QUARANTINE_PERCPU_SIZE,
2 * total_size / QUARANTINE_BATCHES));
if (likely(quarantine_size > quarantine_max_size)) {
qlist_move_all(&global_quarantine[quarantine_head], &to_free);
WRITE_ONCE(quarantine_size, quarantine_size - to_free.bytes);
quarantine_head++;
if (quarantine_head == QUARANTINE_BATCHES)
quarantine_head = 0;
mm: kasan: initial memory quarantine implementation Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. When the object is freed, its state changes from KASAN_STATE_ALLOC to KASAN_STATE_QUARANTINE. The object is poisoned and put into quarantine instead of being returned to the allocator, therefore every subsequent access to that object triggers a KASAN error, and the error handler is able to say where the object has been allocated and deallocated. When it's time for the object to leave quarantine, its state becomes KASAN_STATE_FREE and it's returned to the allocator. From now on the allocator may reuse it for another allocation. Before that happens, it's still possible to detect a use-after free on that object (it retains the allocation/deallocation stacks). When the allocator reuses this object, the shadow is unpoisoned and old allocation/deallocation stacks are wiped. Therefore a use of this object, even an incorrect one, won't trigger ASan warning. Without the quarantine, it's not guaranteed that the objects aren't reused immediately, that's why the probability of catching a use-after-free is lower than with quarantine in place. Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. Freed objects are first added to per-cpu quarantine queues. When a cache is destroyed or memory shrinking is requested, the objects are moved into the global quarantine queue. Whenever a kmalloc call allows memory reclaiming, the oldest objects are popped out of the global queue until the total size of objects in quarantine is less than 3/4 of the maximum quarantine size (which is a fraction of installed physical memory). As long as an object remains in the quarantine, KASAN is able to report accesses to it, so the chance of reporting a use-after-free is increased. Once the object leaves quarantine, the allocator may reuse it, in which case the object is unpoisoned and KASAN can't detect incorrect accesses to it. Right now quarantine support is only enabled in SLAB allocator. Unification of KASAN features in SLAB and SLUB will be done later. This patch is based on the "mm: kasan: quarantine" patch originally prepared by Dmitry Chernenkov. A number of improvements have been suggested by Andrey Ryabinin. [glider@google.com: v9] Link: http://lkml.kernel.org/r/1462987130-144092-1-git-send-email-glider@google.com Signed-off-by: Alexander Potapenko <glider@google.com> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Andrey Konovalov <adech.fo@gmail.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Konstantin Serebryany <kcc@google.com> Cc: Dmitry Chernenkov <dmitryc@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
9 years ago
}
raw_spin_unlock_irqrestore(&quarantine_lock, flags);
mm: kasan: initial memory quarantine implementation Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. When the object is freed, its state changes from KASAN_STATE_ALLOC to KASAN_STATE_QUARANTINE. The object is poisoned and put into quarantine instead of being returned to the allocator, therefore every subsequent access to that object triggers a KASAN error, and the error handler is able to say where the object has been allocated and deallocated. When it's time for the object to leave quarantine, its state becomes KASAN_STATE_FREE and it's returned to the allocator. From now on the allocator may reuse it for another allocation. Before that happens, it's still possible to detect a use-after free on that object (it retains the allocation/deallocation stacks). When the allocator reuses this object, the shadow is unpoisoned and old allocation/deallocation stacks are wiped. Therefore a use of this object, even an incorrect one, won't trigger ASan warning. Without the quarantine, it's not guaranteed that the objects aren't reused immediately, that's why the probability of catching a use-after-free is lower than with quarantine in place. Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. Freed objects are first added to per-cpu quarantine queues. When a cache is destroyed or memory shrinking is requested, the objects are moved into the global quarantine queue. Whenever a kmalloc call allows memory reclaiming, the oldest objects are popped out of the global queue until the total size of objects in quarantine is less than 3/4 of the maximum quarantine size (which is a fraction of installed physical memory). As long as an object remains in the quarantine, KASAN is able to report accesses to it, so the chance of reporting a use-after-free is increased. Once the object leaves quarantine, the allocator may reuse it, in which case the object is unpoisoned and KASAN can't detect incorrect accesses to it. Right now quarantine support is only enabled in SLAB allocator. Unification of KASAN features in SLAB and SLUB will be done later. This patch is based on the "mm: kasan: quarantine" patch originally prepared by Dmitry Chernenkov. A number of improvements have been suggested by Andrey Ryabinin. [glider@google.com: v9] Link: http://lkml.kernel.org/r/1462987130-144092-1-git-send-email-glider@google.com Signed-off-by: Alexander Potapenko <glider@google.com> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Andrey Konovalov <adech.fo@gmail.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Konstantin Serebryany <kcc@google.com> Cc: Dmitry Chernenkov <dmitryc@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
9 years ago
qlist_free_all(&to_free, NULL);
kasan: fix races in quarantine_remove_cache() quarantine_remove_cache() frees all pending objects that belong to the cache, before we destroy the cache itself. However there are currently two possibilities how it can fail to do so. First, another thread can hold some of the objects from the cache in temp list in quarantine_put(). quarantine_put() has a windows of enabled interrupts, and on_each_cpu() in quarantine_remove_cache() can finish right in that window. These objects will be later freed into the destroyed cache. Then, quarantine_reduce() has the same problem. It grabs a batch of objects from the global quarantine, then unlocks quarantine_lock and then frees the batch. quarantine_remove_cache() can finish while some objects from the cache are still in the local to_free list in quarantine_reduce(). Fix the race with quarantine_put() by disabling interrupts for the whole duration of quarantine_put(). In combination with on_each_cpu() in quarantine_remove_cache() it ensures that quarantine_remove_cache() either sees the objects in the per-cpu list or in the global list. Fix the race with quarantine_reduce() by protecting quarantine_reduce() with srcu critical section and then doing synchronize_srcu() at the end of quarantine_remove_cache(). I've done some assessment of how good synchronize_srcu() works in this case. And on a 4 CPU VM I see that it blocks waiting for pending read critical sections in about 2-3% of cases. Which looks good to me. I suspect that these races are the root cause of some GPFs that I episodically hit. Previously I did not have any explanation for them. BUG: unable to handle kernel NULL pointer dereference at 00000000000000c8 IP: qlist_free_all+0x2e/0xc0 mm/kasan/quarantine.c:155 PGD 6aeea067 PUD 60ed7067 PMD 0 Oops: 0000 [#1] SMP KASAN Dumping ftrace buffer: (ftrace buffer empty) Modules linked in: CPU: 0 PID: 13667 Comm: syz-executor2 Not tainted 4.10.0+ #60 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 task: ffff88005f948040 task.stack: ffff880069818000 RIP: 0010:qlist_free_all+0x2e/0xc0 mm/kasan/quarantine.c:155 RSP: 0018:ffff88006981f298 EFLAGS: 00010246 RAX: ffffea0000ffff00 RBX: 0000000000000000 RCX: ffffea0000ffff1f RDX: 0000000000000000 RSI: ffff88003fffc3e0 RDI: 0000000000000000 RBP: ffff88006981f2c0 R08: ffff88002fed7bd8 R09: 00000001001f000d R10: 00000000001f000d R11: ffff88006981f000 R12: ffff88003fffc3e0 R13: ffff88006981f2d0 R14: ffffffff81877fae R15: 0000000080000000 FS: 00007fb911a2d700(0000) GS:ffff88003ec00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000000000c8 CR3: 0000000060ed6000 CR4: 00000000000006f0 Call Trace: quarantine_reduce+0x10e/0x120 mm/kasan/quarantine.c:239 kasan_kmalloc+0xca/0xe0 mm/kasan/kasan.c:590 kasan_slab_alloc+0x12/0x20 mm/kasan/kasan.c:544 slab_post_alloc_hook mm/slab.h:456 [inline] slab_alloc_node mm/slub.c:2718 [inline] kmem_cache_alloc_node+0x1d3/0x280 mm/slub.c:2754 __alloc_skb+0x10f/0x770 net/core/skbuff.c:219 alloc_skb include/linux/skbuff.h:932 [inline] _sctp_make_chunk+0x3b/0x260 net/sctp/sm_make_chunk.c:1388 sctp_make_data net/sctp/sm_make_chunk.c:1420 [inline] sctp_make_datafrag_empty+0x208/0x360 net/sctp/sm_make_chunk.c:746 sctp_datamsg_from_user+0x7e8/0x11d0 net/sctp/chunk.c:266 sctp_sendmsg+0x2611/0x3970 net/sctp/socket.c:1962 inet_sendmsg+0x164/0x5b0 net/ipv4/af_inet.c:761 sock_sendmsg_nosec net/socket.c:633 [inline] sock_sendmsg+0xca/0x110 net/socket.c:643 SYSC_sendto+0x660/0x810 net/socket.c:1685 SyS_sendto+0x40/0x50 net/socket.c:1653 I am not sure about backporting. The bug is quite hard to trigger, I've seen it few times during our massive continuous testing (however, it could be cause of some other episodic stray crashes as it leads to memory corruption...). If it is triggered, the consequences are very bad -- almost definite bad memory corruption. The fix is non trivial and has chances of introducing new bugs. I am also not sure how actively people use KASAN on older releases. [dvyukov@google.com: - sorted includes[ Link: http://lkml.kernel.org/r/20170309094028.51088-1-dvyukov@google.com Link: http://lkml.kernel.org/r/20170308151532.5070-1-dvyukov@google.com Signed-off-by: Dmitry Vyukov <dvyukov@google.com> Acked-by: Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: Greg Thelen <gthelen@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
8 years ago
srcu_read_unlock(&remove_cache_srcu, srcu_idx);
mm: kasan: initial memory quarantine implementation Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. When the object is freed, its state changes from KASAN_STATE_ALLOC to KASAN_STATE_QUARANTINE. The object is poisoned and put into quarantine instead of being returned to the allocator, therefore every subsequent access to that object triggers a KASAN error, and the error handler is able to say where the object has been allocated and deallocated. When it's time for the object to leave quarantine, its state becomes KASAN_STATE_FREE and it's returned to the allocator. From now on the allocator may reuse it for another allocation. Before that happens, it's still possible to detect a use-after free on that object (it retains the allocation/deallocation stacks). When the allocator reuses this object, the shadow is unpoisoned and old allocation/deallocation stacks are wiped. Therefore a use of this object, even an incorrect one, won't trigger ASan warning. Without the quarantine, it's not guaranteed that the objects aren't reused immediately, that's why the probability of catching a use-after-free is lower than with quarantine in place. Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. Freed objects are first added to per-cpu quarantine queues. When a cache is destroyed or memory shrinking is requested, the objects are moved into the global quarantine queue. Whenever a kmalloc call allows memory reclaiming, the oldest objects are popped out of the global queue until the total size of objects in quarantine is less than 3/4 of the maximum quarantine size (which is a fraction of installed physical memory). As long as an object remains in the quarantine, KASAN is able to report accesses to it, so the chance of reporting a use-after-free is increased. Once the object leaves quarantine, the allocator may reuse it, in which case the object is unpoisoned and KASAN can't detect incorrect accesses to it. Right now quarantine support is only enabled in SLAB allocator. Unification of KASAN features in SLAB and SLUB will be done later. This patch is based on the "mm: kasan: quarantine" patch originally prepared by Dmitry Chernenkov. A number of improvements have been suggested by Andrey Ryabinin. [glider@google.com: v9] Link: http://lkml.kernel.org/r/1462987130-144092-1-git-send-email-glider@google.com Signed-off-by: Alexander Potapenko <glider@google.com> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Andrey Konovalov <adech.fo@gmail.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Konstantin Serebryany <kcc@google.com> Cc: Dmitry Chernenkov <dmitryc@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
9 years ago
}
static void qlist_move_cache(struct qlist_head *from,
struct qlist_head *to,
struct kmem_cache *cache)
{
struct qlist_node *curr;
mm: kasan: initial memory quarantine implementation Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. When the object is freed, its state changes from KASAN_STATE_ALLOC to KASAN_STATE_QUARANTINE. The object is poisoned and put into quarantine instead of being returned to the allocator, therefore every subsequent access to that object triggers a KASAN error, and the error handler is able to say where the object has been allocated and deallocated. When it's time for the object to leave quarantine, its state becomes KASAN_STATE_FREE and it's returned to the allocator. From now on the allocator may reuse it for another allocation. Before that happens, it's still possible to detect a use-after free on that object (it retains the allocation/deallocation stacks). When the allocator reuses this object, the shadow is unpoisoned and old allocation/deallocation stacks are wiped. Therefore a use of this object, even an incorrect one, won't trigger ASan warning. Without the quarantine, it's not guaranteed that the objects aren't reused immediately, that's why the probability of catching a use-after-free is lower than with quarantine in place. Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. Freed objects are first added to per-cpu quarantine queues. When a cache is destroyed or memory shrinking is requested, the objects are moved into the global quarantine queue. Whenever a kmalloc call allows memory reclaiming, the oldest objects are popped out of the global queue until the total size of objects in quarantine is less than 3/4 of the maximum quarantine size (which is a fraction of installed physical memory). As long as an object remains in the quarantine, KASAN is able to report accesses to it, so the chance of reporting a use-after-free is increased. Once the object leaves quarantine, the allocator may reuse it, in which case the object is unpoisoned and KASAN can't detect incorrect accesses to it. Right now quarantine support is only enabled in SLAB allocator. Unification of KASAN features in SLAB and SLUB will be done later. This patch is based on the "mm: kasan: quarantine" patch originally prepared by Dmitry Chernenkov. A number of improvements have been suggested by Andrey Ryabinin. [glider@google.com: v9] Link: http://lkml.kernel.org/r/1462987130-144092-1-git-send-email-glider@google.com Signed-off-by: Alexander Potapenko <glider@google.com> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Andrey Konovalov <adech.fo@gmail.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Konstantin Serebryany <kcc@google.com> Cc: Dmitry Chernenkov <dmitryc@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
9 years ago
if (unlikely(qlist_empty(from)))
return;
curr = from->head;
qlist_init(from);
mm: kasan: initial memory quarantine implementation Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. When the object is freed, its state changes from KASAN_STATE_ALLOC to KASAN_STATE_QUARANTINE. The object is poisoned and put into quarantine instead of being returned to the allocator, therefore every subsequent access to that object triggers a KASAN error, and the error handler is able to say where the object has been allocated and deallocated. When it's time for the object to leave quarantine, its state becomes KASAN_STATE_FREE and it's returned to the allocator. From now on the allocator may reuse it for another allocation. Before that happens, it's still possible to detect a use-after free on that object (it retains the allocation/deallocation stacks). When the allocator reuses this object, the shadow is unpoisoned and old allocation/deallocation stacks are wiped. Therefore a use of this object, even an incorrect one, won't trigger ASan warning. Without the quarantine, it's not guaranteed that the objects aren't reused immediately, that's why the probability of catching a use-after-free is lower than with quarantine in place. Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. Freed objects are first added to per-cpu quarantine queues. When a cache is destroyed or memory shrinking is requested, the objects are moved into the global quarantine queue. Whenever a kmalloc call allows memory reclaiming, the oldest objects are popped out of the global queue until the total size of objects in quarantine is less than 3/4 of the maximum quarantine size (which is a fraction of installed physical memory). As long as an object remains in the quarantine, KASAN is able to report accesses to it, so the chance of reporting a use-after-free is increased. Once the object leaves quarantine, the allocator may reuse it, in which case the object is unpoisoned and KASAN can't detect incorrect accesses to it. Right now quarantine support is only enabled in SLAB allocator. Unification of KASAN features in SLAB and SLUB will be done later. This patch is based on the "mm: kasan: quarantine" patch originally prepared by Dmitry Chernenkov. A number of improvements have been suggested by Andrey Ryabinin. [glider@google.com: v9] Link: http://lkml.kernel.org/r/1462987130-144092-1-git-send-email-glider@google.com Signed-off-by: Alexander Potapenko <glider@google.com> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Andrey Konovalov <adech.fo@gmail.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Konstantin Serebryany <kcc@google.com> Cc: Dmitry Chernenkov <dmitryc@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
9 years ago
while (curr) {
struct qlist_node *next = curr->next;
struct kmem_cache *obj_cache = qlink_to_cache(curr);
if (obj_cache == cache)
qlist_put(to, curr, obj_cache->size);
else
qlist_put(from, curr, obj_cache->size);
curr = next;
mm: kasan: initial memory quarantine implementation Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. When the object is freed, its state changes from KASAN_STATE_ALLOC to KASAN_STATE_QUARANTINE. The object is poisoned and put into quarantine instead of being returned to the allocator, therefore every subsequent access to that object triggers a KASAN error, and the error handler is able to say where the object has been allocated and deallocated. When it's time for the object to leave quarantine, its state becomes KASAN_STATE_FREE and it's returned to the allocator. From now on the allocator may reuse it for another allocation. Before that happens, it's still possible to detect a use-after free on that object (it retains the allocation/deallocation stacks). When the allocator reuses this object, the shadow is unpoisoned and old allocation/deallocation stacks are wiped. Therefore a use of this object, even an incorrect one, won't trigger ASan warning. Without the quarantine, it's not guaranteed that the objects aren't reused immediately, that's why the probability of catching a use-after-free is lower than with quarantine in place. Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. Freed objects are first added to per-cpu quarantine queues. When a cache is destroyed or memory shrinking is requested, the objects are moved into the global quarantine queue. Whenever a kmalloc call allows memory reclaiming, the oldest objects are popped out of the global queue until the total size of objects in quarantine is less than 3/4 of the maximum quarantine size (which is a fraction of installed physical memory). As long as an object remains in the quarantine, KASAN is able to report accesses to it, so the chance of reporting a use-after-free is increased. Once the object leaves quarantine, the allocator may reuse it, in which case the object is unpoisoned and KASAN can't detect incorrect accesses to it. Right now quarantine support is only enabled in SLAB allocator. Unification of KASAN features in SLAB and SLUB will be done later. This patch is based on the "mm: kasan: quarantine" patch originally prepared by Dmitry Chernenkov. A number of improvements have been suggested by Andrey Ryabinin. [glider@google.com: v9] Link: http://lkml.kernel.org/r/1462987130-144092-1-git-send-email-glider@google.com Signed-off-by: Alexander Potapenko <glider@google.com> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Andrey Konovalov <adech.fo@gmail.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Konstantin Serebryany <kcc@google.com> Cc: Dmitry Chernenkov <dmitryc@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
9 years ago
}
}
static void per_cpu_remove_cache(void *arg)
{
struct kmem_cache *cache = arg;
struct qlist_head to_free = QLIST_INIT;
struct qlist_head *q;
q = this_cpu_ptr(&cpu_quarantine);
qlist_move_cache(q, &to_free, cache);
qlist_free_all(&to_free, cache);
}
kasan: drain quarantine of memcg slab objects Per memcg slab accounting and kasan have a problem with kmem_cache destruction. - kmem_cache_create() allocates a kmem_cache, which is used for allocations from processes running in root (top) memcg. - Processes running in non root memcg and allocating with either __GFP_ACCOUNT or from a SLAB_ACCOUNT cache use a per memcg kmem_cache. - Kasan catches use-after-free by having kfree() and kmem_cache_free() defer freeing of objects. Objects are placed in a quarantine. - kmem_cache_destroy() destroys root and non root kmem_caches. It takes care to drain the quarantine of objects from the root memcg's kmem_cache, but ignores objects associated with non root memcg. This causes leaks because quarantined per memcg objects refer to per memcg kmem cache being destroyed. To see the problem: 1) create a slab cache with kmem_cache_create(,,,SLAB_ACCOUNT,) 2) from non root memcg, allocate and free a few objects from cache 3) dispose of the cache with kmem_cache_destroy() kmem_cache_destroy() will trigger a "Slab cache still has objects" warning indicating that the per memcg kmem_cache structure was leaked. Fix the leak by draining kasan quarantined objects allocated from non root memcg. Racing memcg deletion is tricky, but handled. kmem_cache_destroy() => shutdown_memcg_caches() => __shutdown_memcg_cache() => shutdown_cache() flushes per memcg quarantined objects, even if that memcg has been rmdir'd and gone through memcg_deactivate_kmem_caches(). This leak only affects destroyed SLAB_ACCOUNT kmem caches when kasan is enabled. So I don't think it's worth patching stable kernels. Link: http://lkml.kernel.org/r/1482257462-36948-1-git-send-email-gthelen@google.com Signed-off-by: Greg Thelen <gthelen@google.com> Reviewed-by: Vladimir Davydov <vdavydov.dev@gmail.com> Acked-by: Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: Alexander Potapenko <glider@google.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
8 years ago
/* Free all quarantined objects belonging to cache. */
mm: kasan: initial memory quarantine implementation Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. When the object is freed, its state changes from KASAN_STATE_ALLOC to KASAN_STATE_QUARANTINE. The object is poisoned and put into quarantine instead of being returned to the allocator, therefore every subsequent access to that object triggers a KASAN error, and the error handler is able to say where the object has been allocated and deallocated. When it's time for the object to leave quarantine, its state becomes KASAN_STATE_FREE and it's returned to the allocator. From now on the allocator may reuse it for another allocation. Before that happens, it's still possible to detect a use-after free on that object (it retains the allocation/deallocation stacks). When the allocator reuses this object, the shadow is unpoisoned and old allocation/deallocation stacks are wiped. Therefore a use of this object, even an incorrect one, won't trigger ASan warning. Without the quarantine, it's not guaranteed that the objects aren't reused immediately, that's why the probability of catching a use-after-free is lower than with quarantine in place. Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. Freed objects are first added to per-cpu quarantine queues. When a cache is destroyed or memory shrinking is requested, the objects are moved into the global quarantine queue. Whenever a kmalloc call allows memory reclaiming, the oldest objects are popped out of the global queue until the total size of objects in quarantine is less than 3/4 of the maximum quarantine size (which is a fraction of installed physical memory). As long as an object remains in the quarantine, KASAN is able to report accesses to it, so the chance of reporting a use-after-free is increased. Once the object leaves quarantine, the allocator may reuse it, in which case the object is unpoisoned and KASAN can't detect incorrect accesses to it. Right now quarantine support is only enabled in SLAB allocator. Unification of KASAN features in SLAB and SLUB will be done later. This patch is based on the "mm: kasan: quarantine" patch originally prepared by Dmitry Chernenkov. A number of improvements have been suggested by Andrey Ryabinin. [glider@google.com: v9] Link: http://lkml.kernel.org/r/1462987130-144092-1-git-send-email-glider@google.com Signed-off-by: Alexander Potapenko <glider@google.com> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Andrey Konovalov <adech.fo@gmail.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Konstantin Serebryany <kcc@google.com> Cc: Dmitry Chernenkov <dmitryc@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
9 years ago
void quarantine_remove_cache(struct kmem_cache *cache)
{
kasan: eliminate long stalls during quarantine reduction Currently we dedicate 1/32 of RAM for quarantine and then reduce it by 1/4 of total quarantine size. This can be a significant amount of memory. For example, with 4GB of RAM total quarantine size is 128MB and it is reduced by 32MB at a time. With 128GB of RAM total quarantine size is 4GB and it is reduced by 1GB. This leads to several problems: - freeing 1GB can take tens of seconds, causes rcu stall warnings and just introduces unexpected long delays at random places - if kmalloc() is called under a mutex, other threads stall on that mutex while a thread reduces quarantine - threads wait on quarantine_lock while one thread grabs a large batch of objects to evict - we walk the uncached list of object to free twice which makes all of the above worse - when a thread frees objects, they are already not accounted against global_quarantine.bytes; as the result we can have quarantine_size bytes in quarantine + unbounded amount of memory in large batches in threads that are in process of freeing Reduce size of quarantine in smaller batches to reduce the delays. The only reason to reduce it in batches is amortization of overheads, the new batch size of 1MB should be well enough to amortize spinlock lock/unlock and few function calls. Plus organize quarantine as a FIFO array of batches. This allows to not walk the list in quarantine_reduce() under quarantine_lock, which in turn reduces contention and is just faster. This improves performance of heavy load (syzkaller fuzzing) by ~20% with 4 CPUs and 32GB of RAM. Also this eliminates frequent (every 5 sec) drops of CPU consumption from ~400% to ~100% (one thread reduces quarantine while others are waiting on a mutex). Some reference numbers: 1. Machine with 4 CPUs and 4GB of memory. Quarantine size 128MB. Currently we free 32MB at at time. With new code we free 1MB at a time (1024 batches, ~128 are used). 2. Machine with 32 CPUs and 128GB of memory. Quarantine size 4GB. Currently we free 1GB at at time. With new code we free 8MB at a time (1024 batches, ~512 are used). 3. Machine with 4096 CPUs and 1TB of memory. Quarantine size 32GB. Currently we free 8GB at at time. With new code we free 4MB at a time (16K batches, ~8K are used). Link: http://lkml.kernel.org/r/1478756952-18695-1-git-send-email-dvyukov@google.com Signed-off-by: Dmitry Vyukov <dvyukov@google.com> Cc: Eric Dumazet <edumazet@google.com> Cc: Greg Thelen <gthelen@google.com> Cc: Alexander Potapenko <glider@google.com> Cc: Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: Andrey Konovalov <andreyknvl@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
8 years ago
unsigned long flags, i;
mm: kasan: initial memory quarantine implementation Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. When the object is freed, its state changes from KASAN_STATE_ALLOC to KASAN_STATE_QUARANTINE. The object is poisoned and put into quarantine instead of being returned to the allocator, therefore every subsequent access to that object triggers a KASAN error, and the error handler is able to say where the object has been allocated and deallocated. When it's time for the object to leave quarantine, its state becomes KASAN_STATE_FREE and it's returned to the allocator. From now on the allocator may reuse it for another allocation. Before that happens, it's still possible to detect a use-after free on that object (it retains the allocation/deallocation stacks). When the allocator reuses this object, the shadow is unpoisoned and old allocation/deallocation stacks are wiped. Therefore a use of this object, even an incorrect one, won't trigger ASan warning. Without the quarantine, it's not guaranteed that the objects aren't reused immediately, that's why the probability of catching a use-after-free is lower than with quarantine in place. Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. Freed objects are first added to per-cpu quarantine queues. When a cache is destroyed or memory shrinking is requested, the objects are moved into the global quarantine queue. Whenever a kmalloc call allows memory reclaiming, the oldest objects are popped out of the global queue until the total size of objects in quarantine is less than 3/4 of the maximum quarantine size (which is a fraction of installed physical memory). As long as an object remains in the quarantine, KASAN is able to report accesses to it, so the chance of reporting a use-after-free is increased. Once the object leaves quarantine, the allocator may reuse it, in which case the object is unpoisoned and KASAN can't detect incorrect accesses to it. Right now quarantine support is only enabled in SLAB allocator. Unification of KASAN features in SLAB and SLUB will be done later. This patch is based on the "mm: kasan: quarantine" patch originally prepared by Dmitry Chernenkov. A number of improvements have been suggested by Andrey Ryabinin. [glider@google.com: v9] Link: http://lkml.kernel.org/r/1462987130-144092-1-git-send-email-glider@google.com Signed-off-by: Alexander Potapenko <glider@google.com> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Andrey Konovalov <adech.fo@gmail.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Konstantin Serebryany <kcc@google.com> Cc: Dmitry Chernenkov <dmitryc@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
9 years ago
struct qlist_head to_free = QLIST_INIT;
kasan: fix races in quarantine_remove_cache() quarantine_remove_cache() frees all pending objects that belong to the cache, before we destroy the cache itself. However there are currently two possibilities how it can fail to do so. First, another thread can hold some of the objects from the cache in temp list in quarantine_put(). quarantine_put() has a windows of enabled interrupts, and on_each_cpu() in quarantine_remove_cache() can finish right in that window. These objects will be later freed into the destroyed cache. Then, quarantine_reduce() has the same problem. It grabs a batch of objects from the global quarantine, then unlocks quarantine_lock and then frees the batch. quarantine_remove_cache() can finish while some objects from the cache are still in the local to_free list in quarantine_reduce(). Fix the race with quarantine_put() by disabling interrupts for the whole duration of quarantine_put(). In combination with on_each_cpu() in quarantine_remove_cache() it ensures that quarantine_remove_cache() either sees the objects in the per-cpu list or in the global list. Fix the race with quarantine_reduce() by protecting quarantine_reduce() with srcu critical section and then doing synchronize_srcu() at the end of quarantine_remove_cache(). I've done some assessment of how good synchronize_srcu() works in this case. And on a 4 CPU VM I see that it blocks waiting for pending read critical sections in about 2-3% of cases. Which looks good to me. I suspect that these races are the root cause of some GPFs that I episodically hit. Previously I did not have any explanation for them. BUG: unable to handle kernel NULL pointer dereference at 00000000000000c8 IP: qlist_free_all+0x2e/0xc0 mm/kasan/quarantine.c:155 PGD 6aeea067 PUD 60ed7067 PMD 0 Oops: 0000 [#1] SMP KASAN Dumping ftrace buffer: (ftrace buffer empty) Modules linked in: CPU: 0 PID: 13667 Comm: syz-executor2 Not tainted 4.10.0+ #60 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 task: ffff88005f948040 task.stack: ffff880069818000 RIP: 0010:qlist_free_all+0x2e/0xc0 mm/kasan/quarantine.c:155 RSP: 0018:ffff88006981f298 EFLAGS: 00010246 RAX: ffffea0000ffff00 RBX: 0000000000000000 RCX: ffffea0000ffff1f RDX: 0000000000000000 RSI: ffff88003fffc3e0 RDI: 0000000000000000 RBP: ffff88006981f2c0 R08: ffff88002fed7bd8 R09: 00000001001f000d R10: 00000000001f000d R11: ffff88006981f000 R12: ffff88003fffc3e0 R13: ffff88006981f2d0 R14: ffffffff81877fae R15: 0000000080000000 FS: 00007fb911a2d700(0000) GS:ffff88003ec00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000000000c8 CR3: 0000000060ed6000 CR4: 00000000000006f0 Call Trace: quarantine_reduce+0x10e/0x120 mm/kasan/quarantine.c:239 kasan_kmalloc+0xca/0xe0 mm/kasan/kasan.c:590 kasan_slab_alloc+0x12/0x20 mm/kasan/kasan.c:544 slab_post_alloc_hook mm/slab.h:456 [inline] slab_alloc_node mm/slub.c:2718 [inline] kmem_cache_alloc_node+0x1d3/0x280 mm/slub.c:2754 __alloc_skb+0x10f/0x770 net/core/skbuff.c:219 alloc_skb include/linux/skbuff.h:932 [inline] _sctp_make_chunk+0x3b/0x260 net/sctp/sm_make_chunk.c:1388 sctp_make_data net/sctp/sm_make_chunk.c:1420 [inline] sctp_make_datafrag_empty+0x208/0x360 net/sctp/sm_make_chunk.c:746 sctp_datamsg_from_user+0x7e8/0x11d0 net/sctp/chunk.c:266 sctp_sendmsg+0x2611/0x3970 net/sctp/socket.c:1962 inet_sendmsg+0x164/0x5b0 net/ipv4/af_inet.c:761 sock_sendmsg_nosec net/socket.c:633 [inline] sock_sendmsg+0xca/0x110 net/socket.c:643 SYSC_sendto+0x660/0x810 net/socket.c:1685 SyS_sendto+0x40/0x50 net/socket.c:1653 I am not sure about backporting. The bug is quite hard to trigger, I've seen it few times during our massive continuous testing (however, it could be cause of some other episodic stray crashes as it leads to memory corruption...). If it is triggered, the consequences are very bad -- almost definite bad memory corruption. The fix is non trivial and has chances of introducing new bugs. I am also not sure how actively people use KASAN on older releases. [dvyukov@google.com: - sorted includes[ Link: http://lkml.kernel.org/r/20170309094028.51088-1-dvyukov@google.com Link: http://lkml.kernel.org/r/20170308151532.5070-1-dvyukov@google.com Signed-off-by: Dmitry Vyukov <dvyukov@google.com> Acked-by: Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: Greg Thelen <gthelen@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
8 years ago
/*
* Must be careful to not miss any objects that are being moved from
* per-cpu list to the global quarantine in quarantine_put(),
* nor objects being freed in quarantine_reduce(). on_each_cpu()
* achieves the first goal, while synchronize_srcu() achieves the
* second.
*/
mm: kasan: initial memory quarantine implementation Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. When the object is freed, its state changes from KASAN_STATE_ALLOC to KASAN_STATE_QUARANTINE. The object is poisoned and put into quarantine instead of being returned to the allocator, therefore every subsequent access to that object triggers a KASAN error, and the error handler is able to say where the object has been allocated and deallocated. When it's time for the object to leave quarantine, its state becomes KASAN_STATE_FREE and it's returned to the allocator. From now on the allocator may reuse it for another allocation. Before that happens, it's still possible to detect a use-after free on that object (it retains the allocation/deallocation stacks). When the allocator reuses this object, the shadow is unpoisoned and old allocation/deallocation stacks are wiped. Therefore a use of this object, even an incorrect one, won't trigger ASan warning. Without the quarantine, it's not guaranteed that the objects aren't reused immediately, that's why the probability of catching a use-after-free is lower than with quarantine in place. Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. Freed objects are first added to per-cpu quarantine queues. When a cache is destroyed or memory shrinking is requested, the objects are moved into the global quarantine queue. Whenever a kmalloc call allows memory reclaiming, the oldest objects are popped out of the global queue until the total size of objects in quarantine is less than 3/4 of the maximum quarantine size (which is a fraction of installed physical memory). As long as an object remains in the quarantine, KASAN is able to report accesses to it, so the chance of reporting a use-after-free is increased. Once the object leaves quarantine, the allocator may reuse it, in which case the object is unpoisoned and KASAN can't detect incorrect accesses to it. Right now quarantine support is only enabled in SLAB allocator. Unification of KASAN features in SLAB and SLUB will be done later. This patch is based on the "mm: kasan: quarantine" patch originally prepared by Dmitry Chernenkov. A number of improvements have been suggested by Andrey Ryabinin. [glider@google.com: v9] Link: http://lkml.kernel.org/r/1462987130-144092-1-git-send-email-glider@google.com Signed-off-by: Alexander Potapenko <glider@google.com> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Andrey Konovalov <adech.fo@gmail.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Konstantin Serebryany <kcc@google.com> Cc: Dmitry Chernenkov <dmitryc@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
9 years ago
on_each_cpu(per_cpu_remove_cache, cache, 1);
raw_spin_lock_irqsave(&quarantine_lock, flags);
for (i = 0; i < QUARANTINE_BATCHES; i++) {
if (qlist_empty(&global_quarantine[i]))
continue;
kasan: eliminate long stalls during quarantine reduction Currently we dedicate 1/32 of RAM for quarantine and then reduce it by 1/4 of total quarantine size. This can be a significant amount of memory. For example, with 4GB of RAM total quarantine size is 128MB and it is reduced by 32MB at a time. With 128GB of RAM total quarantine size is 4GB and it is reduced by 1GB. This leads to several problems: - freeing 1GB can take tens of seconds, causes rcu stall warnings and just introduces unexpected long delays at random places - if kmalloc() is called under a mutex, other threads stall on that mutex while a thread reduces quarantine - threads wait on quarantine_lock while one thread grabs a large batch of objects to evict - we walk the uncached list of object to free twice which makes all of the above worse - when a thread frees objects, they are already not accounted against global_quarantine.bytes; as the result we can have quarantine_size bytes in quarantine + unbounded amount of memory in large batches in threads that are in process of freeing Reduce size of quarantine in smaller batches to reduce the delays. The only reason to reduce it in batches is amortization of overheads, the new batch size of 1MB should be well enough to amortize spinlock lock/unlock and few function calls. Plus organize quarantine as a FIFO array of batches. This allows to not walk the list in quarantine_reduce() under quarantine_lock, which in turn reduces contention and is just faster. This improves performance of heavy load (syzkaller fuzzing) by ~20% with 4 CPUs and 32GB of RAM. Also this eliminates frequent (every 5 sec) drops of CPU consumption from ~400% to ~100% (one thread reduces quarantine while others are waiting on a mutex). Some reference numbers: 1. Machine with 4 CPUs and 4GB of memory. Quarantine size 128MB. Currently we free 32MB at at time. With new code we free 1MB at a time (1024 batches, ~128 are used). 2. Machine with 32 CPUs and 128GB of memory. Quarantine size 4GB. Currently we free 1GB at at time. With new code we free 8MB at a time (1024 batches, ~512 are used). 3. Machine with 4096 CPUs and 1TB of memory. Quarantine size 32GB. Currently we free 8GB at at time. With new code we free 4MB at a time (16K batches, ~8K are used). Link: http://lkml.kernel.org/r/1478756952-18695-1-git-send-email-dvyukov@google.com Signed-off-by: Dmitry Vyukov <dvyukov@google.com> Cc: Eric Dumazet <edumazet@google.com> Cc: Greg Thelen <gthelen@google.com> Cc: Alexander Potapenko <glider@google.com> Cc: Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: Andrey Konovalov <andreyknvl@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
8 years ago
qlist_move_cache(&global_quarantine[i], &to_free, cache);
/* Scanning whole quarantine can take a while. */
raw_spin_unlock_irqrestore(&quarantine_lock, flags);
cond_resched();
raw_spin_lock_irqsave(&quarantine_lock, flags);
}
raw_spin_unlock_irqrestore(&quarantine_lock, flags);
mm: kasan: initial memory quarantine implementation Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. When the object is freed, its state changes from KASAN_STATE_ALLOC to KASAN_STATE_QUARANTINE. The object is poisoned and put into quarantine instead of being returned to the allocator, therefore every subsequent access to that object triggers a KASAN error, and the error handler is able to say where the object has been allocated and deallocated. When it's time for the object to leave quarantine, its state becomes KASAN_STATE_FREE and it's returned to the allocator. From now on the allocator may reuse it for another allocation. Before that happens, it's still possible to detect a use-after free on that object (it retains the allocation/deallocation stacks). When the allocator reuses this object, the shadow is unpoisoned and old allocation/deallocation stacks are wiped. Therefore a use of this object, even an incorrect one, won't trigger ASan warning. Without the quarantine, it's not guaranteed that the objects aren't reused immediately, that's why the probability of catching a use-after-free is lower than with quarantine in place. Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. Freed objects are first added to per-cpu quarantine queues. When a cache is destroyed or memory shrinking is requested, the objects are moved into the global quarantine queue. Whenever a kmalloc call allows memory reclaiming, the oldest objects are popped out of the global queue until the total size of objects in quarantine is less than 3/4 of the maximum quarantine size (which is a fraction of installed physical memory). As long as an object remains in the quarantine, KASAN is able to report accesses to it, so the chance of reporting a use-after-free is increased. Once the object leaves quarantine, the allocator may reuse it, in which case the object is unpoisoned and KASAN can't detect incorrect accesses to it. Right now quarantine support is only enabled in SLAB allocator. Unification of KASAN features in SLAB and SLUB will be done later. This patch is based on the "mm: kasan: quarantine" patch originally prepared by Dmitry Chernenkov. A number of improvements have been suggested by Andrey Ryabinin. [glider@google.com: v9] Link: http://lkml.kernel.org/r/1462987130-144092-1-git-send-email-glider@google.com Signed-off-by: Alexander Potapenko <glider@google.com> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Andrey Konovalov <adech.fo@gmail.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Konstantin Serebryany <kcc@google.com> Cc: Dmitry Chernenkov <dmitryc@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
9 years ago
qlist_free_all(&to_free, cache);
kasan: fix races in quarantine_remove_cache() quarantine_remove_cache() frees all pending objects that belong to the cache, before we destroy the cache itself. However there are currently two possibilities how it can fail to do so. First, another thread can hold some of the objects from the cache in temp list in quarantine_put(). quarantine_put() has a windows of enabled interrupts, and on_each_cpu() in quarantine_remove_cache() can finish right in that window. These objects will be later freed into the destroyed cache. Then, quarantine_reduce() has the same problem. It grabs a batch of objects from the global quarantine, then unlocks quarantine_lock and then frees the batch. quarantine_remove_cache() can finish while some objects from the cache are still in the local to_free list in quarantine_reduce(). Fix the race with quarantine_put() by disabling interrupts for the whole duration of quarantine_put(). In combination with on_each_cpu() in quarantine_remove_cache() it ensures that quarantine_remove_cache() either sees the objects in the per-cpu list or in the global list. Fix the race with quarantine_reduce() by protecting quarantine_reduce() with srcu critical section and then doing synchronize_srcu() at the end of quarantine_remove_cache(). I've done some assessment of how good synchronize_srcu() works in this case. And on a 4 CPU VM I see that it blocks waiting for pending read critical sections in about 2-3% of cases. Which looks good to me. I suspect that these races are the root cause of some GPFs that I episodically hit. Previously I did not have any explanation for them. BUG: unable to handle kernel NULL pointer dereference at 00000000000000c8 IP: qlist_free_all+0x2e/0xc0 mm/kasan/quarantine.c:155 PGD 6aeea067 PUD 60ed7067 PMD 0 Oops: 0000 [#1] SMP KASAN Dumping ftrace buffer: (ftrace buffer empty) Modules linked in: CPU: 0 PID: 13667 Comm: syz-executor2 Not tainted 4.10.0+ #60 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 task: ffff88005f948040 task.stack: ffff880069818000 RIP: 0010:qlist_free_all+0x2e/0xc0 mm/kasan/quarantine.c:155 RSP: 0018:ffff88006981f298 EFLAGS: 00010246 RAX: ffffea0000ffff00 RBX: 0000000000000000 RCX: ffffea0000ffff1f RDX: 0000000000000000 RSI: ffff88003fffc3e0 RDI: 0000000000000000 RBP: ffff88006981f2c0 R08: ffff88002fed7bd8 R09: 00000001001f000d R10: 00000000001f000d R11: ffff88006981f000 R12: ffff88003fffc3e0 R13: ffff88006981f2d0 R14: ffffffff81877fae R15: 0000000080000000 FS: 00007fb911a2d700(0000) GS:ffff88003ec00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000000000c8 CR3: 0000000060ed6000 CR4: 00000000000006f0 Call Trace: quarantine_reduce+0x10e/0x120 mm/kasan/quarantine.c:239 kasan_kmalloc+0xca/0xe0 mm/kasan/kasan.c:590 kasan_slab_alloc+0x12/0x20 mm/kasan/kasan.c:544 slab_post_alloc_hook mm/slab.h:456 [inline] slab_alloc_node mm/slub.c:2718 [inline] kmem_cache_alloc_node+0x1d3/0x280 mm/slub.c:2754 __alloc_skb+0x10f/0x770 net/core/skbuff.c:219 alloc_skb include/linux/skbuff.h:932 [inline] _sctp_make_chunk+0x3b/0x260 net/sctp/sm_make_chunk.c:1388 sctp_make_data net/sctp/sm_make_chunk.c:1420 [inline] sctp_make_datafrag_empty+0x208/0x360 net/sctp/sm_make_chunk.c:746 sctp_datamsg_from_user+0x7e8/0x11d0 net/sctp/chunk.c:266 sctp_sendmsg+0x2611/0x3970 net/sctp/socket.c:1962 inet_sendmsg+0x164/0x5b0 net/ipv4/af_inet.c:761 sock_sendmsg_nosec net/socket.c:633 [inline] sock_sendmsg+0xca/0x110 net/socket.c:643 SYSC_sendto+0x660/0x810 net/socket.c:1685 SyS_sendto+0x40/0x50 net/socket.c:1653 I am not sure about backporting. The bug is quite hard to trigger, I've seen it few times during our massive continuous testing (however, it could be cause of some other episodic stray crashes as it leads to memory corruption...). If it is triggered, the consequences are very bad -- almost definite bad memory corruption. The fix is non trivial and has chances of introducing new bugs. I am also not sure how actively people use KASAN on older releases. [dvyukov@google.com: - sorted includes[ Link: http://lkml.kernel.org/r/20170309094028.51088-1-dvyukov@google.com Link: http://lkml.kernel.org/r/20170308151532.5070-1-dvyukov@google.com Signed-off-by: Dmitry Vyukov <dvyukov@google.com> Acked-by: Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: Greg Thelen <gthelen@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
8 years ago
synchronize_srcu(&remove_cache_srcu);
mm: kasan: initial memory quarantine implementation Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. When the object is freed, its state changes from KASAN_STATE_ALLOC to KASAN_STATE_QUARANTINE. The object is poisoned and put into quarantine instead of being returned to the allocator, therefore every subsequent access to that object triggers a KASAN error, and the error handler is able to say where the object has been allocated and deallocated. When it's time for the object to leave quarantine, its state becomes KASAN_STATE_FREE and it's returned to the allocator. From now on the allocator may reuse it for another allocation. Before that happens, it's still possible to detect a use-after free on that object (it retains the allocation/deallocation stacks). When the allocator reuses this object, the shadow is unpoisoned and old allocation/deallocation stacks are wiped. Therefore a use of this object, even an incorrect one, won't trigger ASan warning. Without the quarantine, it's not guaranteed that the objects aren't reused immediately, that's why the probability of catching a use-after-free is lower than with quarantine in place. Quarantine isolates freed objects in a separate queue. The objects are returned to the allocator later, which helps to detect use-after-free errors. Freed objects are first added to per-cpu quarantine queues. When a cache is destroyed or memory shrinking is requested, the objects are moved into the global quarantine queue. Whenever a kmalloc call allows memory reclaiming, the oldest objects are popped out of the global queue until the total size of objects in quarantine is less than 3/4 of the maximum quarantine size (which is a fraction of installed physical memory). As long as an object remains in the quarantine, KASAN is able to report accesses to it, so the chance of reporting a use-after-free is increased. Once the object leaves quarantine, the allocator may reuse it, in which case the object is unpoisoned and KASAN can't detect incorrect accesses to it. Right now quarantine support is only enabled in SLAB allocator. Unification of KASAN features in SLAB and SLUB will be done later. This patch is based on the "mm: kasan: quarantine" patch originally prepared by Dmitry Chernenkov. A number of improvements have been suggested by Andrey Ryabinin. [glider@google.com: v9] Link: http://lkml.kernel.org/r/1462987130-144092-1-git-send-email-glider@google.com Signed-off-by: Alexander Potapenko <glider@google.com> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Andrey Konovalov <adech.fo@gmail.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Konstantin Serebryany <kcc@google.com> Cc: Dmitry Chernenkov <dmitryc@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
9 years ago
}