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: [e-mail]
Signed-off-by: Jiri Olsa <[e-mail]>
Signed-off-by: Daniel Borkmann <[e-mail]>
Acked-by: Yonghong Song <[e-mail]>
Cc: Lee Jones <[e-mail]>
Cc: Maciej Fijalkowski <[e-mail]>
Link: https://lore.kernel.org/bpf/[e-mail]

arch/x86/net/bpf_jit_comp.c

···
 #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);
+	}
+}

include/linux/bpf.h

···
 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);
 

kernel/bpf/arraymap.c

···
 	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;
 
···
 
 	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];
···
 			 *    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;
···
 			    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);
 		}
 	}
 }