From bb422a738f6566f7439cd347d54e321e4fe92a9f Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Mon, 18 Dec 2017 20:31:41 +0900 Subject: mm,vmscan: Make unregister_shrinker() no-op if register_shrinker() failed. Syzbot caught an oops at unregister_shrinker() because combination of commit 1d3d4437eae1bb29 ("vmscan: per-node deferred work") and fault injection made register_shrinker() fail and the caller of register_shrinker() did not check for failure. ---------- [ 554.881422] FAULT_INJECTION: forcing a failure. [ 554.881422] name failslab, interval 1, probability 0, space 0, times 0 [ 554.881438] CPU: 1 PID: 13231 Comm: syz-executor1 Not tainted 4.14.0-rc8+ #82 [ 554.881443] Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 [ 554.881445] Call Trace: [ 554.881459] dump_stack+0x194/0x257 [ 554.881474] ? arch_local_irq_restore+0x53/0x53 [ 554.881486] ? find_held_lock+0x35/0x1d0 [ 554.881507] should_fail+0x8c0/0xa40 [ 554.881522] ? fault_create_debugfs_attr+0x1f0/0x1f0 [ 554.881537] ? check_noncircular+0x20/0x20 [ 554.881546] ? find_next_zero_bit+0x2c/0x40 [ 554.881560] ? ida_get_new_above+0x421/0x9d0 [ 554.881577] ? find_held_lock+0x35/0x1d0 [ 554.881594] ? __lock_is_held+0xb6/0x140 [ 554.881628] ? check_same_owner+0x320/0x320 [ 554.881634] ? lock_downgrade+0x990/0x990 [ 554.881649] ? find_held_lock+0x35/0x1d0 [ 554.881672] should_failslab+0xec/0x120 [ 554.881684] __kmalloc+0x63/0x760 [ 554.881692] ? lock_downgrade+0x990/0x990 [ 554.881712] ? register_shrinker+0x10e/0x2d0 [ 554.881721] ? trace_event_raw_event_module_request+0x320/0x320 [ 554.881737] register_shrinker+0x10e/0x2d0 [ 554.881747] ? prepare_kswapd_sleep+0x1f0/0x1f0 [ 554.881755] ? _down_write_nest_lock+0x120/0x120 [ 554.881765] ? memcpy+0x45/0x50 [ 554.881785] sget_userns+0xbcd/0xe20 (...snipped...) [ 554.898693] kasan: CONFIG_KASAN_INLINE enabled [ 554.898724] kasan: GPF could be caused by NULL-ptr deref or user memory access [ 554.898732] general protection fault: 0000 [#1] SMP KASAN [ 554.898737] Dumping ftrace buffer: [ 554.898741] (ftrace buffer empty) [ 554.898743] Modules linked in: [ 554.898752] CPU: 1 PID: 13231 Comm: syz-executor1 Not tainted 4.14.0-rc8+ #82 [ 554.898755] Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 [ 554.898760] task: ffff8801d1dbe5c0 task.stack: ffff8801c9e38000 [ 554.898772] RIP: 0010:__list_del_entry_valid+0x7e/0x150 [ 554.898775] RSP: 0018:ffff8801c9e3f108 EFLAGS: 00010246 [ 554.898780] RAX: dffffc0000000000 RBX: 0000000000000000 RCX: 0000000000000000 [ 554.898784] RDX: 0000000000000000 RSI: ffff8801c53c6f98 RDI: ffff8801c53c6fa0 [ 554.898788] RBP: ffff8801c9e3f120 R08: 1ffff100393c7d55 R09: 0000000000000004 [ 554.898791] R10: ffff8801c9e3ef70 R11: 0000000000000000 R12: 0000000000000000 [ 554.898795] R13: dffffc0000000000 R14: 1ffff100393c7e45 R15: ffff8801c53c6f98 [ 554.898800] FS: 0000000000000000(0000) GS:ffff8801db300000(0000) knlGS:0000000000000000 [ 554.898804] CS: 0010 DS: 002b ES: 002b CR0: 0000000080050033 [ 554.898807] CR2: 00000000dbc23000 CR3: 00000001c7269000 CR4: 00000000001406e0 [ 554.898813] DR0: 0000000020000000 DR1: 0000000020000000 DR2: 0000000000000000 [ 554.898816] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000600 [ 554.898818] Call Trace: [ 554.898828] unregister_shrinker+0x79/0x300 [ 554.898837] ? perf_trace_mm_vmscan_writepage+0x750/0x750 [ 554.898844] ? down_write+0x87/0x120 [ 554.898851] ? deactivate_super+0x139/0x1b0 [ 554.898857] ? down_read+0x150/0x150 [ 554.898864] ? check_same_owner+0x320/0x320 [ 554.898875] deactivate_locked_super+0x64/0xd0 [ 554.898883] deactivate_super+0x141/0x1b0 ---------- Since allowing register_shrinker() callers to call unregister_shrinker() when register_shrinker() failed can simplify error recovery path, this patch makes unregister_shrinker() no-op when register_shrinker() failed. Also, reset shrinker->nr_deferred in case unregister_shrinker() was by error called twice. Signed-off-by: Tetsuo Handa Signed-off-by: Aliaksei Karaliou Reported-by: syzbot Cc: Glauber Costa Cc: Al Viro Signed-off-by: Al Viro --- mm/vmscan.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/mm/vmscan.c b/mm/vmscan.c index c02c850ea349..47d5ced51f2d 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -297,10 +297,13 @@ EXPORT_SYMBOL(register_shrinker); */ void unregister_shrinker(struct shrinker *shrinker) { + if (!shrinker->nr_deferred) + return; down_write(&shrinker_rwsem); list_del(&shrinker->list); up_write(&shrinker_rwsem); kfree(shrinker->nr_deferred); + shrinker->nr_deferred = NULL; } EXPORT_SYMBOL(unregister_shrinker); -- cgit v1.2.3-59-g8ed1b From 9ee332d99e4d5a97548943b81c54668450ce641b Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 18 Dec 2017 15:05:07 -0500 Subject: sget(): handle failures of register_shrinker() Signed-off-by: Al Viro --- fs/super.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/fs/super.c b/fs/super.c index 7ff1349609e4..06bd25d90ba5 100644 --- a/fs/super.c +++ b/fs/super.c @@ -517,7 +517,11 @@ retry: hlist_add_head(&s->s_instances, &type->fs_supers); spin_unlock(&sb_lock); get_filesystem(type); - register_shrinker(&s->s_shrink); + err = register_shrinker(&s->s_shrink); + if (err) { + deactivate_locked_super(s); + s = ERR_PTR(err); + } return s; } -- cgit v1.2.3-59-g8ed1b From 040ee69226f8a96b7943645d68f41d5d44b5ff7d Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 2 Dec 2017 20:20:38 -0500 Subject: fix "netfilter: xt_bpf: Fix XT_BPF_MODE_FD_PINNED mode of 'xt_bpf_info_v1'" Descriptor table is a shared object; it's not a place where you can stick temporary references to files, especially when we don't need an opened file at all. Cc: stable@vger.kernel.org # v4.14 Fixes: 98589a0998b8 ("netfilter: xt_bpf: Fix XT_BPF_MODE_FD_PINNED mode of 'xt_bpf_info_v1'") Signed-off-by: Al Viro --- include/linux/bpf.h | 10 ++++++++++ kernel/bpf/inode.c | 40 +++++++++++++++++++++++++++++++++++++++- kernel/bpf/syscall.c | 2 +- net/netfilter/xt_bpf.c | 14 ++------------ 4 files changed, 52 insertions(+), 14 deletions(-) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e55e4255a210..b63a592ad29d 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -419,6 +419,8 @@ static inline int bpf_map_attr_numa_node(const union bpf_attr *attr) attr->numa_node : NUMA_NO_NODE; } +struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type); + #else /* !CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get(u32 ufd) { @@ -506,6 +508,12 @@ static inline int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, { return 0; } + +static inline struct bpf_prog *bpf_prog_get_type_path(const char *name, + enum bpf_prog_type type) +{ + return ERR_PTR(-EOPNOTSUPP); +} #endif /* CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get_type(u32 ufd, @@ -514,6 +522,8 @@ static inline struct bpf_prog *bpf_prog_get_type(u32 ufd, return bpf_prog_get_type_dev(ufd, type, false); } +bool bpf_prog_get_ok(struct bpf_prog *, enum bpf_prog_type *, bool); + int bpf_prog_offload_compile(struct bpf_prog *prog); void bpf_prog_offload_destroy(struct bpf_prog *prog); diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 01aaef1a77c5..5bb5e49ef4c3 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -368,7 +368,45 @@ out: putname(pname); return ret; } -EXPORT_SYMBOL_GPL(bpf_obj_get_user); + +static struct bpf_prog *__get_prog_inode(struct inode *inode, enum bpf_prog_type type) +{ + struct bpf_prog *prog; + int ret = inode_permission(inode, MAY_READ | MAY_WRITE); + if (ret) + return ERR_PTR(ret); + + if (inode->i_op == &bpf_map_iops) + return ERR_PTR(-EINVAL); + if (inode->i_op != &bpf_prog_iops) + return ERR_PTR(-EACCES); + + prog = inode->i_private; + + ret = security_bpf_prog(prog); + if (ret < 0) + return ERR_PTR(ret); + + if (!bpf_prog_get_ok(prog, &type, false)) + return ERR_PTR(-EINVAL); + + return bpf_prog_inc(prog); +} + +struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type) +{ + struct bpf_prog *prog; + struct path path; + int ret = kern_path(name, LOOKUP_FOLLOW, &path); + if (ret) + return ERR_PTR(ret); + prog = __get_prog_inode(d_backing_inode(path.dentry), type); + if (!IS_ERR(prog)) + touch_atime(&path); + path_put(&path); + return prog; +} +EXPORT_SYMBOL(bpf_prog_get_type_path); static void bpf_evict_inode(struct inode *inode) { diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 2c4cfeaa8d5e..5cb783fc8224 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1057,7 +1057,7 @@ struct bpf_prog *bpf_prog_inc_not_zero(struct bpf_prog *prog) } EXPORT_SYMBOL_GPL(bpf_prog_inc_not_zero); -static bool bpf_prog_get_ok(struct bpf_prog *prog, +bool bpf_prog_get_ok(struct bpf_prog *prog, enum bpf_prog_type *attach_type, bool attach_drv) { /* not an attachment, just a refcount inc, always allow */ diff --git a/net/netfilter/xt_bpf.c b/net/netfilter/xt_bpf.c index 041da0d9c06f..fa2ca0a13619 100644 --- a/net/netfilter/xt_bpf.c +++ b/net/netfilter/xt_bpf.c @@ -52,18 +52,8 @@ static int __bpf_mt_check_fd(int fd, struct bpf_prog **ret) static int __bpf_mt_check_path(const char *path, struct bpf_prog **ret) { - mm_segment_t oldfs = get_fs(); - int retval, fd; - - set_fs(KERNEL_DS); - fd = bpf_obj_get_user(path, 0); - set_fs(oldfs); - if (fd < 0) - return fd; - - retval = __bpf_mt_check_fd(fd, ret); - sys_close(fd); - return retval; + *ret = bpf_prog_get_type_path(path, BPF_PROG_TYPE_SOCKET_FILTER); + return PTR_ERR_OR_ZERO(*ret); } static int bpf_mt_check(const struct xt_mtchk_param *par) -- cgit v1.2.3-59-g8ed1b