bpf: avoid retpoline for lookup/update/delete calls on maps

While some of the BPF map lookup helpers provide a ->map_gen_lookup()
callback for inlining the map lookup altogether it is not available
for every map, so the remaining ones have to call bpf_map_lookup_elem()
helper which does a dispatch to map->ops->map_lookup_elem(). In
times of retpolines, this will control and trap speculative execution
rather than letting it do its work for the indirect call and will
therefore cause a slowdown. Likewise, bpf_map_update_elem() and
bpf_map_delete_elem() do not have an inlined version and need to call
into their map->ops->map_update_elem() resp. map->ops->map_delete_elem()
handlers.

Before:

  # bpftool prog dump xlated id 1
    0: (bf) r2 = r10
    1: (07) r2 += -8
    2: (7a) *(u64 *)(r2 +0) = 0
    3: (18) r1 = map[id:1]
    5: (85) call __htab_map_lookup_elem#232656
    6: (15) if r0 == 0x0 goto pc+4
    7: (71) r1 = *(u8 *)(r0 +35)
    8: (55) if r1 != 0x0 goto pc+1
    9: (72) *(u8 *)(r0 +35) = 1
   10: (07) r0 += 56
   11: (15) if r0 == 0x0 goto pc+4
   12: (bf) r2 = r0
   13: (18) r1 = map[id:1]
   15: (85) call bpf_map_delete_elem#215008  <-- indirect call via
   16: (95) exit                                 helper

After:

  # bpftool prog dump xlated id 1
    0: (bf) r2 = r10
    1: (07) r2 += -8
    2: (7a) *(u64 *)(r2 +0) = 0
    3: (18) r1 = map[id:1]
    5: (85) call __htab_map_lookup_elem#233328
    6: (15) if r0 == 0x0 goto pc+4
    7: (71) r1 = *(u8 *)(r0 +35)
    8: (55) if r1 != 0x0 goto pc+1
    9: (72) *(u8 *)(r0 +35) = 1
   10: (07) r0 += 56
   11: (15) if r0 == 0x0 goto pc+4
   12: (bf) r2 = r0
   13: (18) r1 = map[id:1]
   15: (85) call htab_lru_map_delete_elem#238240  <-- direct call
   16: (95) exit

In all three lookup/update/delete cases however we can use the actual
address of the map callback directly if we find that there's only a
single path with a map pointer leading to the helper call, meaning
when the map pointer has not been poisoned from verifier side.
Example code can be seen above for the delete case.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

include/linux/filter.h

@@ -301,6 +301,9 @@ struct xdp_buff;
 
 /* Function call */
 
+#define BPF_CAST_CALL(x)					\
+		((u64 (*)(u64, u64, u64, u64, u64))(x))
+
 #define BPF_EMIT_CALL(FUNC)					\
 	((struct bpf_insn) {					\
 		.code  = BPF_JMP | BPF_CALL,			\

kernel/bpf/hashtab.c

@@ -503,7 +503,9 @@ static u32 htab_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
 	struct bpf_insn *insn = insn_buf;
 	const int ret = BPF_REG_0;
 
-	*insn++ = BPF_EMIT_CALL((u64 (*)(u64, u64, u64, u64, u64))__htab_map_lookup_elem);
+	BUILD_BUG_ON(!__same_type(&__htab_map_lookup_elem,
+		     (void *(*)(struct bpf_map *map, void *key))NULL));
+	*insn++ = BPF_EMIT_CALL(BPF_CAST_CALL(__htab_map_lookup_elem));
 	*insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 1);
 	*insn++ = BPF_ALU64_IMM(BPF_ADD, ret,
 				offsetof(struct htab_elem, key) +
@@ -530,7 +532,9 @@ static u32 htab_lru_map_gen_lookup(struct bpf_map *map,
 	const int ret = BPF_REG_0;
 	const int ref_reg = BPF_REG_1;
 
-	*insn++ = BPF_EMIT_CALL((u64 (*)(u64, u64, u64, u64, u64))__htab_map_lookup_elem);
+	BUILD_BUG_ON(!__same_type(&__htab_map_lookup_elem,
+		     (void *(*)(struct bpf_map *map, void *key))NULL));
+	*insn++ = BPF_EMIT_CALL(BPF_CAST_CALL(__htab_map_lookup_elem));
 	*insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 4);
 	*insn++ = BPF_LDX_MEM(BPF_B, ref_reg, ret,
 			      offsetof(struct htab_elem, lru_node) +
@@ -1369,7 +1373,9 @@ static u32 htab_of_map_gen_lookup(struct bpf_map *map,
 	struct bpf_insn *insn = insn_buf;
 	const int ret = BPF_REG_0;
 
-	*insn++ = BPF_EMIT_CALL((u64 (*)(u64, u64, u64, u64, u64))__htab_map_lookup_elem);
+	BUILD_BUG_ON(!__same_type(&__htab_map_lookup_elem,
+		     (void *(*)(struct bpf_map *map, void *key))NULL));
+	*insn++ = BPF_EMIT_CALL(BPF_CAST_CALL(__htab_map_lookup_elem));
 	*insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 2);
 	*insn++ = BPF_ALU64_IMM(BPF_ADD, ret,
 				offsetof(struct htab_elem, key) +

kernel/bpf/verifier.c

@@ -2421,8 +2421,11 @@ record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
 	struct bpf_insn_aux_data *aux = &env->insn_aux_data[insn_idx];
 
 	if (func_id != BPF_FUNC_tail_call &&
-	    func_id != BPF_FUNC_map_lookup_elem)
+	    func_id != BPF_FUNC_map_lookup_elem &&
+	    func_id != BPF_FUNC_map_update_elem &&
+	    func_id != BPF_FUNC_map_delete_elem)
 		return 0;
+
 	if (meta->map_ptr == NULL) {
 		verbose(env, "kernel subsystem misconfigured verifier\n");
 		return -EINVAL;
@@ -5586,6 +5589,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
 	struct bpf_insn *insn = prog->insnsi;
 	const struct bpf_func_proto *fn;
 	const int insn_cnt = prog->len;
+	const struct bpf_map_ops *ops;
 	struct bpf_insn_aux_data *aux;
 	struct bpf_insn insn_buf[16];
 	struct bpf_prog *new_prog;
@@ -5715,35 +5719,61 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
 		}
 
 		/* BPF_EMIT_CALL() assumptions in some of the map_gen_lookup
-		 * handlers are currently limited to 64 bit only.
+		 * and other inlining handlers are currently limited to 64 bit
+		 * only.
 		 */
 		if (prog->jit_requested && BITS_PER_LONG == 64 &&
-		    insn->imm == BPF_FUNC_map_lookup_elem) {
+		    (insn->imm == BPF_FUNC_map_lookup_elem ||
+		     insn->imm == BPF_FUNC_map_update_elem ||
+		     insn->imm == BPF_FUNC_map_delete_elem)) {
 			aux = &env->insn_aux_data[i + delta];
 			if (bpf_map_ptr_poisoned(aux))
 				goto patch_call_imm;
 
 			map_ptr = BPF_MAP_PTR(aux->map_state);
-			if (!map_ptr->ops->map_gen_lookup)
-				goto patch_call_imm;
+			ops = map_ptr->ops;
+			if (insn->imm == BPF_FUNC_map_lookup_elem &&
+			    ops->map_gen_lookup) {
+				cnt = ops->map_gen_lookup(map_ptr, insn_buf);
+				if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) {
+					verbose(env, "bpf verifier is misconfigured\n");
+					return -EINVAL;
+				}
 
-			cnt = map_ptr->ops->map_gen_lookup(map_ptr, insn_buf);
-			if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) {
-				verbose(env, "bpf verifier is misconfigured\n");
-				return -EINVAL;
-			}
+				new_prog = bpf_patch_insn_data(env, i + delta,
+							       insn_buf, cnt);
+				if (!new_prog)
+					return -ENOMEM;
 
-			new_prog = bpf_patch_insn_data(env, i + delta, insn_buf,
-						       cnt);
-			if (!new_prog)
-				return -ENOMEM;
+				delta    += cnt - 1;
+				env->prog = prog = new_prog;
+				insn      = new_prog->insnsi + i + delta;
+				continue;
+			}
 
-			delta += cnt - 1;
+			BUILD_BUG_ON(!__same_type(ops->map_lookup_elem,
+				     (void *(*)(struct bpf_map *map, void *key))NULL));
+			BUILD_BUG_ON(!__same_type(ops->map_delete_elem,
+				     (int (*)(struct bpf_map *map, void *key))NULL));
+			BUILD_BUG_ON(!__same_type(ops->map_update_elem,
+				     (int (*)(struct bpf_map *map, void *key, void *value,
+					      u64 flags))NULL));
+			switch (insn->imm) {
+			case BPF_FUNC_map_lookup_elem:
+				insn->imm = BPF_CAST_CALL(ops->map_lookup_elem) -
+					    __bpf_call_base;
+				continue;
+			case BPF_FUNC_map_update_elem:
+				insn->imm = BPF_CAST_CALL(ops->map_update_elem) -
+					    __bpf_call_base;
+				continue;
+			case BPF_FUNC_map_delete_elem:
+				insn->imm = BPF_CAST_CALL(ops->map_delete_elem) -
+					    __bpf_call_base;
+				continue;
+			}
 
-			/* keep walking new program and skip insns we just inserted */
-			env->prog = prog = new_prog;
-			insn      = new_prog->insnsi + i + delta;
-			continue;
+			goto patch_call_imm;
 		}
 
 		if (insn->imm == BPF_FUNC_redirect_map) {