summaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
authorJiri Olsa <jolsa@kernel.org>2023-12-06 09:30:40 +0100
committerDaniel Borkmann <daniel@iogearbox.net>2023-12-06 22:40:16 +0100
commit4b7de801606e504e69689df71475d27e35336fb3 (patch)
tree1ab3b1d4f0d0bad6e845121d2cee745cb32d064e /arch/x86
parente4d008d49a7135214e0ee70537405b6a069e3a3f (diff)
bpf: Fix prog_array_map_poke_run map poke update
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@syzkaller.appspotmail.com Signed-off-by: Jiri Olsa <jolsa@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Yonghong Song <yonghong.song@linux.dev> Cc: Lee Jones <lee@kernel.org> Cc: Maciej Fijalkowski <maciej.fijalkowski@intel.com> Link: https://lore.kernel.org/bpf/20231206083041.1306660-2-jolsa@kernel.org
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/net/bpf_jit_comp.c46
1 files changed, 46 insertions, 0 deletions
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 8c10d9abc239..e89e415aa743 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -3025,3 +3025,49 @@ void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp
#endif
WARN(1, "verification of programs using bpf_throw should have failed\n");
}
+
+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);
+ }
+}