summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
authorHou Tao <houtao1@huawei.com>2023-02-15 11:21:31 +0300
committerAlexei Starovoitov <ast@kernel.org>2023-02-16 02:40:06 +0300
commit997849c4b969034e225153f41026657def66d286 (patch)
tree33940f953e6fcae84d0aa3a2b509fd2aec52d658 /kernel
parentb2d9002ee9a65aa0eaf01ae494876fe16389d535 (diff)
downloadlinux-997849c4b969034e225153f41026657def66d286.tar.xz
bpf: Zeroing allocated object from slab in bpf memory allocator
Currently the freed element in bpf memory allocator may be immediately reused, for htab map the reuse will reinitialize special fields in map value (e.g., bpf_spin_lock), but lookup procedure may still access these special fields, and it may lead to hard-lockup as shown below: NMI backtrace for cpu 16 CPU: 16 PID: 2574 Comm: htab.bin Tainted: G L 6.1.0+ #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), RIP: 0010:queued_spin_lock_slowpath+0x283/0x2c0 ...... Call Trace: <TASK> copy_map_value_locked+0xb7/0x170 bpf_map_copy_value+0x113/0x3c0 __sys_bpf+0x1c67/0x2780 __x64_sys_bpf+0x1c/0x20 do_syscall_64+0x30/0x60 entry_SYSCALL_64_after_hwframe+0x46/0xb0 ...... </TASK> For htab map, just like the preallocated case, these is no need to initialize these special fields in map value again once these fields have been initialized. For preallocated htab map, these fields are initialized through __GFP_ZERO in bpf_map_area_alloc(), so do the similar thing for non-preallocated htab in bpf memory allocator. And there is no need to use __GFP_ZERO for per-cpu bpf memory allocator, because __alloc_percpu_gfp() does it implicitly. Fixes: 0fd7c5d43339 ("bpf: Optimize call_rcu in non-preallocated hash map.") Signed-off-by: Hou Tao <houtao1@huawei.com> Link: https://lore.kernel.org/r/20230215082132.3856544-2-houtao@huaweicloud.com Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/hashtab.c4
-rw-r--r--kernel/bpf/memalloc.c2
2 files changed, 3 insertions, 3 deletions
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 66bded144377..5dfcb5ad0d06 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -1004,8 +1004,6 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
l_new = ERR_PTR(-ENOMEM);
goto dec_count;
}
- check_and_init_map_value(&htab->map,
- l_new->key + round_up(key_size, 8));
}
memcpy(l_new->key, key, key_size);
@@ -1592,6 +1590,7 @@ static int __htab_map_lookup_and_delete_elem(struct bpf_map *map, void *key,
else
copy_map_value(map, value, l->key +
roundup_key_size);
+ /* Zeroing special fields in the temp buffer */
check_and_init_map_value(map, value);
}
@@ -1792,6 +1791,7 @@ again_nocopy:
true);
else
copy_map_value(map, dst_val, value);
+ /* Zeroing special fields in the temp buffer */
check_and_init_map_value(map, dst_val);
}
if (do_delete) {
diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index 490d03a4581a..5fcdacbb8439 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -143,7 +143,7 @@ static void *__alloc(struct bpf_mem_cache *c, int node)
return obj;
}
- return kmalloc_node(c->unit_size, flags, node);
+ return kmalloc_node(c->unit_size, flags | __GFP_ZERO, node);
}
static struct mem_cgroup *get_memcg(const struct bpf_mem_cache *c)