This is a note to let you know that I've just added the patch titled
bpf: Fix prog_array_map_poke_run map poke update
to the 6.1-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
bpf-fix-prog_array_map_poke_run-map-poke-update.patch
and it can be found in the queue-6.1 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
>From 4b7de801606e504e69689df71475d27e35336fb3 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@xxxxxxxxxx>
Date: Wed, 6 Dec 2023 09:30:40 +0100
Subject: bpf: Fix prog_array_map_poke_run map poke update
From: Jiri Olsa <jolsa@xxxxxxxxxx>
commit 4b7de801606e504e69689df71475d27e35336fb3 upstream.
Lee pointed out issue found by syscaller [0] hitting BUG in prog array
map poke update in prog_array_map_poke_run function due to error value
returned from bpf_arch_text_poke function.
There's race window where bpf_arch_text_poke can fail due to missing
bpf program kallsym symbols, which is accounted for with check for
-EINVAL in that BUG_ON call.
The problem is that in such case we won't update the tail call jump
and cause imbalance for the next tail call update check which will
fail with -EBUSY in bpf_arch_text_poke.
I'm hitting following race during the program load:
CPU 0 CPU 1
bpf_prog_load
bpf_check
do_misc_fixups
prog_array_map_poke_track
map_update_elem
bpf_fd_array_map_update_elem
prog_array_map_poke_run
bpf_arch_text_poke returns -EINVAL
bpf_prog_kallsyms_add
After bpf_arch_text_poke (CPU 1) fails to update the tail call jump, the next
poke update fails on expected jump instruction check in bpf_arch_text_poke
with -EBUSY and triggers the BUG_ON in prog_array_map_poke_run.
Similar race exists on the program unload.
Fixing this by moving the update to bpf_arch_poke_desc_update function which
makes sure we call __bpf_arch_text_poke that skips the bpf address check.
Each architecture has slightly different approach wrt looking up bpf address
in bpf_arch_text_poke, so instead of splitting the function or adding new
'checkip' argument in previous version, it seems best to move the whole
map_poke_run update as arch specific code.
[0] https://syzkaller.appspot.com/bug?extid=97a4fe20470e9bc30810
Fixes: ebf7d1f508a7 ("bpf, x64: rework pro/epilogue and tailcall handling in JIT")
Reported-by: syzbot+97a4fe20470e9bc30810@xxxxxxxxxxxxxxxxxxxxxxxxx
Signed-off-by: Jiri Olsa <jolsa@xxxxxxxxxx>
Signed-off-by: Daniel Borkmann <daniel@xxxxxxxxxxxxx>
Acked-by: Yonghong Song <yonghong.song@xxxxxxxxx>
Cc: Lee Jones <lee@xxxxxxxxxx>
Cc: Maciej Fijalkowski <maciej.fijalkowski@xxxxxxxxx>
Link: https://lore.kernel.org/bpf/20231206083041.1306660-2-jolsa@xxxxxxxxxx
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
arch/x86/net/bpf_jit_comp.c | 46 ++++++++++++++++++++++++++++++++++
include/linux/bpf.h | 3 ++
kernel/bpf/arraymap.c | 58 +++++++-------------------------------------
3 files changed, 59 insertions(+), 48 deletions(-)
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -2553,3 +2553,49 @@ void bpf_jit_free(struct bpf_prog *prog)
bpf_prog_unlock_free(prog);
}
+
+void bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke,
+ struct bpf_prog *new, struct bpf_prog *old)
+{
+ u8 *old_addr, *new_addr, *old_bypass_addr;
+ int ret;
+
+ old_bypass_addr = old ? NULL : poke->bypass_addr;
+ old_addr = old ? (u8 *)old->bpf_func + poke->adj_off : NULL;
+ new_addr = new ? (u8 *)new->bpf_func + poke->adj_off : NULL;
+
+ /*
+ * On program loading or teardown, the program's kallsym entry
+ * might not be in place, so we use __bpf_arch_text_poke to skip
+ * the kallsyms check.
+ */
+ if (new) {
+ ret = __bpf_arch_text_poke(poke->tailcall_target,
+ BPF_MOD_JUMP,
+ old_addr, new_addr);
+ BUG_ON(ret < 0);
+ if (!old) {
+ ret = __bpf_arch_text_poke(poke->tailcall_bypass,
+ BPF_MOD_JUMP,
+ poke->bypass_addr,
+ NULL);
+ BUG_ON(ret < 0);
+ }
+ } else {
+ ret = __bpf_arch_text_poke(poke->tailcall_bypass,
+ BPF_MOD_JUMP,
+ old_bypass_addr,
+ poke->bypass_addr);
+ BUG_ON(ret < 0);
+ /* let other CPUs finish the execution of program
+ * so that it will not possible to expose them
+ * to invalid nop, stack unwind, nop state
+ */
+ if (!ret)
+ synchronize_rcu();
+ ret = __bpf_arch_text_poke(poke->tailcall_target,
+ BPF_MOD_JUMP,
+ old_addr, NULL);
+ BUG_ON(ret < 0);
+ }
+}
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2681,6 +2681,9 @@ enum bpf_text_poke_type {
int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
void *addr1, void *addr2);
+void bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke,
+ struct bpf_prog *new, struct bpf_prog *old);
+
void *bpf_arch_text_copy(void *dst, void *src, size_t len);
int bpf_arch_text_invalidate(void *dst, size_t len);
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -997,11 +997,16 @@ static void prog_array_map_poke_untrack(
mutex_unlock(&aux->poke_mutex);
}
+void __weak bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke,
+ struct bpf_prog *new, struct bpf_prog *old)
+{
+ WARN_ON_ONCE(1);
+}
+
static void prog_array_map_poke_run(struct bpf_map *map, u32 key,
struct bpf_prog *old,
struct bpf_prog *new)
{
- u8 *old_addr, *new_addr, *old_bypass_addr;
struct prog_poke_elem *elem;
struct bpf_array_aux *aux;
@@ -1010,7 +1015,7 @@ static void prog_array_map_poke_run(stru
list_for_each_entry(elem, &aux->poke_progs, list) {
struct bpf_jit_poke_descriptor *poke;
- int i, ret;
+ int i;
for (i = 0; i < elem->aux->size_poke_tab; i++) {
poke = &elem->aux->poke_tab[i];
@@ -1029,21 +1034,10 @@ static void prog_array_map_poke_run(stru
* activated, so tail call updates can arrive from here
* while JIT is still finishing its final fixup for
* non-activated poke entries.
- * 3) On program teardown, the program's kallsym entry gets
- * removed out of RCU callback, but we can only untrack
- * from sleepable context, therefore bpf_arch_text_poke()
- * might not see that this is in BPF text section and
- * bails out with -EINVAL. As these are unreachable since
- * RCU grace period already passed, we simply skip them.
- * 4) Also programs reaching refcount of zero while patching
+ * 3) Also programs reaching refcount of zero while patching
* is in progress is okay since we're protected under
* poke_mutex and untrack the programs before the JIT
- * buffer is freed. When we're still in the middle of
- * patching and suddenly kallsyms entry of the program
- * gets evicted, we just skip the rest which is fine due
- * to point 3).
- * 5) Any other error happening below from bpf_arch_text_poke()
- * is a unexpected bug.
+ * buffer is freed.
*/
if (!READ_ONCE(poke->tailcall_target_stable))
continue;
@@ -1053,39 +1047,7 @@ static void prog_array_map_poke_run(stru
poke->tail_call.key != key)
continue;
- old_bypass_addr = old ? NULL : poke->bypass_addr;
- old_addr = old ? (u8 *)old->bpf_func + poke->adj_off : NULL;
- new_addr = new ? (u8 *)new->bpf_func + poke->adj_off : NULL;
-
- if (new) {
- ret = bpf_arch_text_poke(poke->tailcall_target,
- BPF_MOD_JUMP,
- old_addr, new_addr);
- BUG_ON(ret < 0 && ret != -EINVAL);
- if (!old) {
- ret = bpf_arch_text_poke(poke->tailcall_bypass,
- BPF_MOD_JUMP,
- poke->bypass_addr,
- NULL);
- BUG_ON(ret < 0 && ret != -EINVAL);
- }
- } else {
- ret = bpf_arch_text_poke(poke->tailcall_bypass,
- BPF_MOD_JUMP,
- old_bypass_addr,
- poke->bypass_addr);
- BUG_ON(ret < 0 && ret != -EINVAL);
- /* let other CPUs finish the execution of program
- * so that it will not possible to expose them
- * to invalid nop, stack unwind, nop state
- */
- if (!ret)
- synchronize_rcu();
- ret = bpf_arch_text_poke(poke->tailcall_target,
- BPF_MOD_JUMP,
- old_addr, NULL);
- BUG_ON(ret < 0 && ret != -EINVAL);
- }
+ bpf_arch_poke_desc_update(poke, new, old);
}
}
}
Patches currently in stable-queue which might be from jolsa@xxxxxxxxxx are
queue-6.1/bpf-fix-prog_array_map_poke_run-map-poke-update.patch
