Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

BPF alignment tests got a conflict because the registers
are output as Rn_w instead of just Rn in net-next, and
in net a fixup for a testcase prohibits logical operations
on pointers before using them.

Also, we should attempt to patch BPF call args if JIT always on is
enabled.  Instead, if we fail to JIT the subprogs we should pass
an error back up and fail immediately.

Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 114 insertions, 17 deletions

diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 7c25426d3cf5..aaa319848e7d 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -53,9 +53,10 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 {
 	bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY;
 	int numa_node = bpf_map_attr_numa_node(attr);
+	u32 elem_size, index_mask, max_entries;
+	bool unpriv = !capable(CAP_SYS_ADMIN);
 	struct bpf_array *array;
 	u64 array_size;
-	u32 elem_size;
 
 	/* check sanity of attributes */
 	if (attr->max_entries == 0 || attr->key_size != 4 ||
@@ -72,11 +73,20 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 
 	elem_size = round_up(attr->value_size, 8);
 
+	max_entries = attr->max_entries;
+	index_mask = roundup_pow_of_two(max_entries) - 1;
+
+	if (unpriv)
+		/* round up array size to nearest power of 2,
+		 * since cpu will speculate within index_mask limits
+		 */
+		max_entries = index_mask + 1;
+
 	array_size = sizeof(*array);
 	if (percpu)
-		array_size += (u64) attr->max_entries * sizeof(void *);
+		array_size += (u64) max_entries * sizeof(void *);
 	else
-		array_size += (u64) attr->max_entries * elem_size;
+		array_size += (u64) max_entries * elem_size;
 
 	/* make sure there is no u32 overflow later in round_up() */
 	if (array_size >= U32_MAX - PAGE_SIZE)
@@ -86,6 +96,8 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 	array = bpf_map_area_alloc(array_size, numa_node);
 	if (!array)
 		return ERR_PTR(-ENOMEM);
+	array->index_mask = index_mask;
+	array->map.unpriv_array = unpriv;
 
 	/* copy mandatory map attributes */
 	array->map.map_type = attr->map_type;
@@ -121,12 +133,13 @@ static void *array_map_lookup_elem(struct bpf_map *map, void *key)
 	if (unlikely(index >= array->map.max_entries))
 		return NULL;
 
-	return array->value + array->elem_size * index;
+	return array->value + array->elem_size * (index & array->index_mask);
 }
 
 /* emit BPF instructions equivalent to C code of array_map_lookup_elem() */
 static u32 array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
 {
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
 	struct bpf_insn *insn = insn_buf;
 	u32 elem_size = round_up(map->value_size, 8);
 	const int ret = BPF_REG_0;
@@ -135,7 +148,12 @@ static u32 array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
 
 	*insn++ = BPF_ALU64_IMM(BPF_ADD, map_ptr, offsetof(struct bpf_array, value));
 	*insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0);
-	*insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 3);
+	if (map->unpriv_array) {
+		*insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 4);
+		*insn++ = BPF_ALU32_IMM(BPF_AND, ret, array->index_mask);
+	} else {
+		*insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 3);
+	}
 
 	if (is_power_of_2(elem_size)) {
 		*insn++ = BPF_ALU64_IMM(BPF_LSH, ret, ilog2(elem_size));
@@ -157,7 +175,7 @@ static void *percpu_array_map_lookup_elem(struct bpf_map *map, void *key)
 	if (unlikely(index >= array->map.max_entries))
 		return NULL;
 
-	return this_cpu_ptr(array->pptrs[index]);
+	return this_cpu_ptr(array->pptrs[index & array->index_mask]);
 }
 
 int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value)
@@ -177,7 +195,7 @@ int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value)
 	 */
 	size = round_up(map->value_size, 8);
 	rcu_read_lock();
-	pptr = array->pptrs[index];
+	pptr = array->pptrs[index & array->index_mask];
 	for_each_possible_cpu(cpu) {
 		bpf_long_memcpy(value + off, per_cpu_ptr(pptr, cpu), size);
 		off += size;
@@ -225,10 +243,11 @@ static int array_map_update_elem(struct bpf_map *map, void *key, void *value,
 		return -EEXIST;
 
 	if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
-		memcpy(this_cpu_ptr(array->pptrs[index]),
+		memcpy(this_cpu_ptr(array->pptrs[index & array->index_mask]),
 		       value, map->value_size);
 	else
-		memcpy(array->value + array->elem_size * index,
+		memcpy(array->value +
+		       array->elem_size * (index & array->index_mask),
 		       value, map->value_size);
 	return 0;
 }
@@ -262,7 +281,7 @@ int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value,
 	 */
 	size = round_up(map->value_size, 8);
 	rcu_read_lock();
-	pptr = array->pptrs[index];
+	pptr = array->pptrs[index & array->index_mask];
 	for_each_possible_cpu(cpu) {
 		bpf_long_memcpy(per_cpu_ptr(pptr, cpu), value + off, size);
 		off += size;
@@ -613,6 +632,7 @@ static void *array_of_map_lookup_elem(struct bpf_map *map, void *key)
 static u32 array_of_map_gen_lookup(struct bpf_map *map,
 				   struct bpf_insn *insn_buf)
 {
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
 	u32 elem_size = round_up(map->value_size, 8);
 	struct bpf_insn *insn = insn_buf;
 	const int ret = BPF_REG_0;
@@ -621,7 +641,12 @@ static u32 array_of_map_gen_lookup(struct bpf_map *map,
 
 	*insn++ = BPF_ALU64_IMM(BPF_ADD, map_ptr, offsetof(struct bpf_array, value));
 	*insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0);
-	*insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 5);
+	if (map->unpriv_array) {
+		*insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 6);
+		*insn++ = BPF_ALU32_IMM(BPF_AND, ret, array->index_mask);
+	} else {
+		*insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 5);
+	}
 	if (is_power_of_2(elem_size))
 		*insn++ = BPF_ALU64_IMM(BPF_LSH, ret, ilog2(elem_size));
 	else
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 70a534549cd3..25e723b0dfd4 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -781,6 +781,7 @@ noinline u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
 }
 EXPORT_SYMBOL_GPL(__bpf_call_base);
 
+#ifndef CONFIG_BPF_JIT_ALWAYS_ON
 /**
  *	__bpf_prog_run - run eBPF program on a given context
  *	@ctx: is the data we are operating on
@@ -1377,6 +1378,14 @@ void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth)
 	insn->code = BPF_JMP | BPF_CALL_ARGS;
 }
 
+#else
+static unsigned int __bpf_prog_ret0(const void *ctx,
+				    const struct bpf_insn *insn)
+{
+	return 0;
+}
+#endif
+
 bool bpf_prog_array_compatible(struct bpf_array *array,
 			       const struct bpf_prog *fp)
 {
@@ -1427,9 +1436,13 @@ static int bpf_check_tail_call(const struct bpf_prog *fp)
  */
 struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
 {
+#ifndef CONFIG_BPF_JIT_ALWAYS_ON
 	u32 stack_depth = max_t(u32, fp->aux->stack_depth, 1);
 
 	fp->bpf_func = interpreters[(round_up(stack_depth, 32) / 32) - 1];
+#else
+	fp->bpf_func = __bpf_prog_ret0;
+#endif
 
 	/* eBPF JITs can rewrite the program in case constant
 	 * blinding is active. However, in case of error during
@@ -1439,6 +1452,12 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
 	 */
 	if (!bpf_prog_is_dev_bound(fp->aux)) {
 		fp = bpf_int_jit_compile(fp);
+#ifdef CONFIG_BPF_JIT_ALWAYS_ON
+		if (!fp->jited) {
+			*err = -ENOTSUPP;
+			return fp;
+		}
+#endif
 	} else {
 		*err = bpf_prog_offload_compile(fp);
 		if (*err)
diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c
index 3f662ee23a34..079968680bc3 100644
--- a/kernel/bpf/sockmap.c
+++ b/kernel/bpf/sockmap.c
@@ -583,8 +583,15 @@ static void sock_map_free(struct bpf_map *map)
 
 		write_lock_bh(&sock->sk_callback_lock);
 		psock = smap_psock_sk(sock);
-		smap_list_remove(psock, &stab->sock_map[i]);
-		smap_release_sock(psock, sock);
+		/* This check handles a racing sock event that can get the
+		 * sk_callback_lock before this case but after xchg happens
+		 * causing the refcnt to hit zero and sock user data (psock)
+		 * to be null and queued for garbage collection.
+		 */
+		if (likely(psock)) {
+			smap_list_remove(psock, &stab->sock_map[i]);
+			smap_release_sock(psock, sock);
+		}
 		write_unlock_bh(&sock->sk_callback_lock);
 	}
 	rcu_read_unlock();
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 3b2b47666180..48b61caa94cb 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1523,6 +1523,7 @@ continue_func:
 	goto continue_func;
 }
 
+#ifndef CONFIG_BPF_JIT_ALWAYS_ON
 static int get_callee_stack_depth(struct bpf_verifier_env *env,
 				  const struct bpf_insn *insn, int idx)
 {
@@ -1537,6 +1538,7 @@ static int get_callee_stack_depth(struct bpf_verifier_env *env,
 	subprog++;
 	return env->subprog_stack_depth[subprog];
 }
+#endif
 
 /* truncate register to smaller size (in bytes)
  * must be called with size < BPF_REG_SIZE
@@ -2321,6 +2323,13 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 	err = check_func_arg(env, BPF_REG_2, fn->arg2_type, &meta);
 	if (err)
 		return err;
+	if (func_id == BPF_FUNC_tail_call) {
+		if (meta.map_ptr == NULL) {
+			verbose(env, "verifier bug\n");
+			return -EINVAL;
+		}
+		env->insn_aux_data[insn_idx].map_ptr = meta.map_ptr;
+	}
 	err = check_func_arg(env, BPF_REG_3, fn->arg3_type, &meta);
 	if (err)
 		return err;
@@ -5264,14 +5273,20 @@ out_free:
 
 static int fixup_call_args(struct bpf_verifier_env *env)
 {
+#ifndef CONFIG_BPF_JIT_ALWAYS_ON
 	struct bpf_prog *prog = env->prog;
 	struct bpf_insn *insn = prog->insnsi;
 	int i, depth;
+#endif
+	int err;
 
-	if (env->prog->jit_requested)
-		if (jit_subprogs(env) == 0)
+	err = 0;
+	if (env->prog->jit_requested) {
+		err = jit_subprogs(env);
+		if (err == 0)
 			return 0;
-
+	}
+#ifndef CONFIG_BPF_JIT_ALWAYS_ON
 	for (i = 0; i < prog->len; i++, insn++) {
 		if (insn->code != (BPF_JMP | BPF_CALL) ||
 		    insn->src_reg != BPF_PSEUDO_CALL)
@@ -5281,7 +5296,9 @@ static int fixup_call_args(struct bpf_verifier_env *env)
 			return depth;
 		bpf_patch_call_args(insn, depth);
 	}
-	return 0;
+	err = 0;
+#endif
+	return err;
 }
 
 /* fixup insn->imm field of bpf_call instructions
@@ -5328,6 +5345,35 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
 			 */
 			insn->imm = 0;
 			insn->code = BPF_JMP | BPF_TAIL_CALL;
+
+			/* instead of changing every JIT dealing with tail_call
+			 * emit two extra insns:
+			 * if (index >= max_entries) goto out;
+			 * index &= array->index_mask;
+			 * to avoid out-of-bounds cpu speculation
+			 */
+			map_ptr = env->insn_aux_data[i + delta].map_ptr;
+			if (map_ptr == BPF_MAP_PTR_POISON) {
+				verbose(env, "tail_call obusing map_ptr\n");
+				return -EINVAL;
+			}
+			if (!map_ptr->unpriv_array)
+				continue;
+			insn_buf[0] = BPF_JMP_IMM(BPF_JGE, BPF_REG_3,
+						  map_ptr->max_entries, 2);
+			insn_buf[1] = BPF_ALU32_IMM(BPF_AND, BPF_REG_3,
+						    container_of(map_ptr,
+								 struct bpf_array,
+								 map)->index_mask);
+			insn_buf[2] = *insn;
+			cnt = 3;
+			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;
 		}