Linux-libre 4.3.2-gnu

4 files changed, 162 insertions, 56 deletions

diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index cb31229a6..29ace107f 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -150,15 +150,15 @@ static int __init register_array_map(void)
 }
 late_initcall(register_array_map);
 
-static struct bpf_map *prog_array_map_alloc(union bpf_attr *attr)
+static struct bpf_map *fd_array_map_alloc(union bpf_attr *attr)
 {
-	/* only bpf_prog file descriptors can be stored in prog_array map */
+	/* only file descriptors can be stored in this type of map */
 	if (attr->value_size != sizeof(u32))
 		return ERR_PTR(-EINVAL);
 	return array_map_alloc(attr);
 }
 
-static void prog_array_map_free(struct bpf_map *map)
+static void fd_array_map_free(struct bpf_map *map)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
 	int i;
@@ -167,21 +167,21 @@ static void prog_array_map_free(struct bpf_map *map)
 
 	/* make sure it's empty */
 	for (i = 0; i < array->map.max_entries; i++)
-		BUG_ON(array->prog[i] != NULL);
+		BUG_ON(array->ptrs[i] != NULL);
 	kvfree(array);
 }
 
-static void *prog_array_map_lookup_elem(struct bpf_map *map, void *key)
+static void *fd_array_map_lookup_elem(struct bpf_map *map, void *key)
 {
 	return NULL;
 }
 
 /* only called from syscall */
-static int prog_array_map_update_elem(struct bpf_map *map, void *key,
-				      void *value, u64 map_flags)
+static int fd_array_map_update_elem(struct bpf_map *map, void *key,
+				    void *value, u64 map_flags)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
-	struct bpf_prog *prog, *old_prog;
+	void *new_ptr, *old_ptr;
 	u32 index = *(u32 *)key, ufd;
 
 	if (map_flags != BPF_ANY)
@@ -191,57 +191,75 @@ static int prog_array_map_update_elem(struct bpf_map *map, void *key,
 		return -E2BIG;
 
 	ufd = *(u32 *)value;
-	prog = bpf_prog_get(ufd);
-	if (IS_ERR(prog))
-		return PTR_ERR(prog);
-
-	if (!bpf_prog_array_compatible(array, prog)) {
-		bpf_prog_put(prog);
-		return -EINVAL;
-	}
+	new_ptr = map->ops->map_fd_get_ptr(map, ufd);
+	if (IS_ERR(new_ptr))
+		return PTR_ERR(new_ptr);
 
-	old_prog = xchg(array->prog + index, prog);
-	if (old_prog)
-		bpf_prog_put_rcu(old_prog);
+	old_ptr = xchg(array->ptrs + index, new_ptr);
+	if (old_ptr)
+		map->ops->map_fd_put_ptr(old_ptr);
 
 	return 0;
 }
 
-static int prog_array_map_delete_elem(struct bpf_map *map, void *key)
+static int fd_array_map_delete_elem(struct bpf_map *map, void *key)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
-	struct bpf_prog *old_prog;
+	void *old_ptr;
 	u32 index = *(u32 *)key;
 
 	if (index >= array->map.max_entries)
 		return -E2BIG;
 
-	old_prog = xchg(array->prog + index, NULL);
-	if (old_prog) {
-		bpf_prog_put_rcu(old_prog);
+	old_ptr = xchg(array->ptrs + index, NULL);
+	if (old_ptr) {
+		map->ops->map_fd_put_ptr(old_ptr);
 		return 0;
 	} else {
 		return -ENOENT;
 	}
 }
 
+static void *prog_fd_array_get_ptr(struct bpf_map *map, int fd)
+{
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	struct bpf_prog *prog = bpf_prog_get(fd);
+	if (IS_ERR(prog))
+		return prog;
+
+	if (!bpf_prog_array_compatible(array, prog)) {
+		bpf_prog_put(prog);
+		return ERR_PTR(-EINVAL);
+	}
+	return prog;
+}
+
+static void prog_fd_array_put_ptr(void *ptr)
+{
+	struct bpf_prog *prog = ptr;
+
+	bpf_prog_put_rcu(prog);
+}
+
 /* decrement refcnt of all bpf_progs that are stored in this map */
-void bpf_prog_array_map_clear(struct bpf_map *map)
+void bpf_fd_array_map_clear(struct bpf_map *map)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
 	int i;
 
 	for (i = 0; i < array->map.max_entries; i++)
-		prog_array_map_delete_elem(map, &i);
+		fd_array_map_delete_elem(map, &i);
 }
 
 static const struct bpf_map_ops prog_array_ops = {
-	.map_alloc = prog_array_map_alloc,
-	.map_free = prog_array_map_free,
+	.map_alloc = fd_array_map_alloc,
+	.map_free = fd_array_map_free,
 	.map_get_next_key = array_map_get_next_key,
-	.map_lookup_elem = prog_array_map_lookup_elem,
-	.map_update_elem = prog_array_map_update_elem,
-	.map_delete_elem = prog_array_map_delete_elem,
+	.map_lookup_elem = fd_array_map_lookup_elem,
+	.map_update_elem = fd_array_map_update_elem,
+	.map_delete_elem = fd_array_map_delete_elem,
+	.map_fd_get_ptr = prog_fd_array_get_ptr,
+	.map_fd_put_ptr = prog_fd_array_put_ptr,
 };
 
 static struct bpf_map_type_list prog_array_type __read_mostly = {
@@ -255,3 +273,60 @@ static int __init register_prog_array_map(void)
 	return 0;
 }
 late_initcall(register_prog_array_map);
+
+static void perf_event_array_map_free(struct bpf_map *map)
+{
+	bpf_fd_array_map_clear(map);
+	fd_array_map_free(map);
+}
+
+static void *perf_event_fd_array_get_ptr(struct bpf_map *map, int fd)
+{
+	struct perf_event *event;
+	const struct perf_event_attr *attr;
+
+	event = perf_event_get(fd);
+	if (IS_ERR(event))
+		return event;
+
+	attr = perf_event_attrs(event);
+	if (IS_ERR(attr))
+		return (void *)attr;
+
+	if (attr->type != PERF_TYPE_RAW &&
+	    attr->type != PERF_TYPE_HARDWARE) {
+		perf_event_release_kernel(event);
+		return ERR_PTR(-EINVAL);
+	}
+	return event;
+}
+
+static void perf_event_fd_array_put_ptr(void *ptr)
+{
+	struct perf_event *event = ptr;
+
+	perf_event_release_kernel(event);
+}
+
+static const struct bpf_map_ops perf_event_array_ops = {
+	.map_alloc = fd_array_map_alloc,
+	.map_free = perf_event_array_map_free,
+	.map_get_next_key = array_map_get_next_key,
+	.map_lookup_elem = fd_array_map_lookup_elem,
+	.map_update_elem = fd_array_map_update_elem,
+	.map_delete_elem = fd_array_map_delete_elem,
+	.map_fd_get_ptr = perf_event_fd_array_get_ptr,
+	.map_fd_put_ptr = perf_event_fd_array_put_ptr,
+};
+
+static struct bpf_map_type_list perf_event_array_type __read_mostly = {
+	.ops = &perf_event_array_ops,
+	.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
+};
+
+static int __init register_perf_event_array_map(void)
+{
+	bpf_register_map_type(&perf_event_array_type);
+	return 0;
+}
+late_initcall(register_perf_event_array_map);
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index c5bedc82b..67c380cfa 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -177,6 +177,7 @@ noinline u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
 {
 	return 0;
 }
+EXPORT_SYMBOL_GPL(__bpf_call_base);
 
 /**
  *	__bpf_prog_run - run eBPF program on a given context
@@ -449,11 +450,15 @@ select_insn:
 
 		tail_call_cnt++;
 
-		prog = READ_ONCE(array->prog[index]);
+		prog = READ_ONCE(array->ptrs[index]);
 		if (unlikely(!prog))
 			goto out;
 
-		ARG1 = BPF_R1;
+		/* ARG1 at this point is guaranteed to point to CTX from
+		 * the verifier side due to the fact that the tail call is
+		 * handeled like a helper, that is, bpf_tail_call_proto,
+		 * where arg1_type is ARG_PTR_TO_CTX.
+		 */
 		insn = prog->insnsi;
 		goto select_insn;
 out:
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index a1b14d197..35bac8e8b 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -72,7 +72,7 @@ static int bpf_map_release(struct inode *inode, struct file *filp)
 		/* prog_array stores refcnt-ed bpf_prog pointers
 		 * release them all when user space closes prog_array_fd
 		 */
-		bpf_prog_array_map_clear(map);
+		bpf_fd_array_map_clear(map);
 
 	bpf_map_put(map);
 	return 0;
@@ -155,14 +155,15 @@ static int map_lookup_elem(union bpf_attr *attr)
 	void __user *ukey = u64_to_ptr(attr->key);
 	void __user *uvalue = u64_to_ptr(attr->value);
 	int ufd = attr->map_fd;
-	struct fd f = fdget(ufd);
 	struct bpf_map *map;
 	void *key, *value, *ptr;
+	struct fd f;
 	int err;
 
 	if (CHECK_ATTR(BPF_MAP_LOOKUP_ELEM))
 		return -EINVAL;
 
+	f = fdget(ufd);
 	map = bpf_map_get(f);
 	if (IS_ERR(map))
 		return PTR_ERR(map);
@@ -213,14 +214,15 @@ static int map_update_elem(union bpf_attr *attr)
 	void __user *ukey = u64_to_ptr(attr->key);
 	void __user *uvalue = u64_to_ptr(attr->value);
 	int ufd = attr->map_fd;
-	struct fd f = fdget(ufd);
 	struct bpf_map *map;
 	void *key, *value;
+	struct fd f;
 	int err;
 
 	if (CHECK_ATTR(BPF_MAP_UPDATE_ELEM))
 		return -EINVAL;
 
+	f = fdget(ufd);
 	map = bpf_map_get(f);
 	if (IS_ERR(map))
 		return PTR_ERR(map);
@@ -265,14 +267,15 @@ static int map_delete_elem(union bpf_attr *attr)
 {
 	void __user *ukey = u64_to_ptr(attr->key);
 	int ufd = attr->map_fd;
-	struct fd f = fdget(ufd);
 	struct bpf_map *map;
+	struct fd f;
 	void *key;
 	int err;
 
 	if (CHECK_ATTR(BPF_MAP_DELETE_ELEM))
 		return -EINVAL;
 
+	f = fdget(ufd);
 	map = bpf_map_get(f);
 	if (IS_ERR(map))
 		return PTR_ERR(map);
@@ -305,14 +308,15 @@ static int map_get_next_key(union bpf_attr *attr)
 	void __user *ukey = u64_to_ptr(attr->key);
 	void __user *unext_key = u64_to_ptr(attr->next_key);
 	int ufd = attr->map_fd;
-	struct fd f = fdget(ufd);
 	struct bpf_map *map;
 	void *key, *next_key;
+	struct fd f;
 	int err;
 
 	if (CHECK_ATTR(BPF_MAP_GET_NEXT_KEY))
 		return -EINVAL;
 
+	f = fdget(ufd);
 	map = bpf_map_get(f);
 	if (IS_ERR(map))
 		return PTR_ERR(map);
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 039d866fd..b074b2300 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -238,6 +238,14 @@ static const char * const reg_type_str[] = {
 	[CONST_IMM]		= "imm",
 };
 
+static const struct {
+	int map_type;
+	int func_id;
+} func_limit[] = {
+	{BPF_MAP_TYPE_PROG_ARRAY, BPF_FUNC_tail_call},
+	{BPF_MAP_TYPE_PERF_EVENT_ARRAY, BPF_FUNC_perf_event_read},
+};
+
 static void print_verifier_state(struct verifier_env *env)
 {
 	enum bpf_reg_type t;
@@ -275,7 +283,7 @@ static const char *const bpf_class_string[] = {
 	[BPF_ALU64] = "alu64",
 };
 
-static const char *const bpf_alu_string[] = {
+static const char *const bpf_alu_string[16] = {
 	[BPF_ADD >> 4]  = "+=",
 	[BPF_SUB >> 4]  = "-=",
 	[BPF_MUL >> 4]  = "*=",
@@ -299,7 +307,7 @@ static const char *const bpf_ldst_string[] = {
 	[BPF_DW >> 3] = "u64",
 };
 
-static const char *const bpf_jmp_string[] = {
+static const char *const bpf_jmp_string[16] = {
 	[BPF_JA >> 4]   = "jmp",
 	[BPF_JEQ >> 4]  = "==",
 	[BPF_JGT >> 4]  = ">",
@@ -648,6 +656,9 @@ static int check_mem_access(struct verifier_env *env, u32 regno, int off,
 	struct verifier_state *state = &env->cur_state;
 	int size, err = 0;
 
+	if (state->regs[regno].type == PTR_TO_STACK)
+		off += state->regs[regno].imm;
+
 	size = bpf_size_to_bytes(bpf_size);
 	if (size < 0)
 		return size;
@@ -667,7 +678,8 @@ static int check_mem_access(struct verifier_env *env, u32 regno, int off,
 		if (!err && t == BPF_READ && value_regno >= 0)
 			mark_reg_unknown_value(state->regs, value_regno);
 
-	} else if (state->regs[regno].type == FRAME_PTR) {
+	} else if (state->regs[regno].type == FRAME_PTR ||
+		   state->regs[regno].type == PTR_TO_STACK) {
 		if (off >= 0 || off < -MAX_BPF_STACK) {
 			verbose("invalid stack off=%d size=%d\n", off, size);
 			return -EACCES;
@@ -833,6 +845,28 @@ static int check_func_arg(struct verifier_env *env, u32 regno,
 	return err;
 }
 
+static int check_map_func_compatibility(struct bpf_map *map, int func_id)
+{
+	bool bool_map, bool_func;
+	int i;
+
+	if (!map)
+		return 0;
+
+	for (i = 0; i < ARRAY_SIZE(func_limit); i++) {
+		bool_map = (map->map_type == func_limit[i].map_type);
+		bool_func = (func_id == func_limit[i].func_id);
+		/* only when map & func pair match it can continue.
+		 * don't allow any other map type to be passed into
+		 * the special func;
+		 */
+		if (bool_map != bool_func)
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int check_call(struct verifier_env *env, int func_id)
 {
 	struct verifier_state *state = &env->cur_state;
@@ -908,21 +942,9 @@ static int check_call(struct verifier_env *env, int func_id)
 		return -EINVAL;
 	}
 
-	if (map && map->map_type == BPF_MAP_TYPE_PROG_ARRAY &&
-	    func_id != BPF_FUNC_tail_call)
-		/* prog_array map type needs extra care:
-		 * only allow to pass it into bpf_tail_call() for now.
-		 * bpf_map_delete_elem() can be allowed in the future,
-		 * while bpf_map_update_elem() must only be done via syscall
-		 */
-		return -EINVAL;
-
-	if (func_id == BPF_FUNC_tail_call &&
-	    map->map_type != BPF_MAP_TYPE_PROG_ARRAY)
-		/* don't allow any other map type to be passed into
-		 * bpf_tail_call()
-		 */
-		return -EINVAL;
+	err = check_map_func_compatibility(map, func_id);
+	if (err)
+		return err;
 
 	return 0;
 }