bpf: Implement bpf_local_storage for inodes

Similar to bpf_local_storage for sockets, add local storage for inodes.
The life-cycle of storage is managed with the life-cycle of the inode.
i.e. the storage is destroyed along with the owning inode.

The BPF LSM allocates an __rcu pointer to the bpf_local_storage in the
security blob which are now stackable and can co-exist with other LSMs.

Signed-off-by: KP Singh <kpsingh@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200825182919.1118197-6-kpsingh@chromium.org

5 files changed, 47 insertions, 6 deletions

diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst
index 41e2a74252d0..083db6c2fc67 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-map.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst
@@ -49,7 +49,7 @@ MAP COMMANDS
 |		| **lru_percpu_hash** | **lpm_trie** | **array_of_maps** | **hash_of_maps**
 |		| **devmap** | **devmap_hash** | **sockmap** | **cpumap** | **xskmap** | **sockhash**
 |		| **cgroup_storage** | **reuseport_sockarray** | **percpu_cgroup_storage**
-|		| **queue** | **stack** | **sk_storage** | **struct_ops** | **ringbuf** }
+|		| **queue** | **stack** | **sk_storage** | **struct_ops** | **ringbuf** | **inode_storage** }
 
 DESCRIPTION
 ===========
diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool
index f53ed2f1a4aa..7b68e3c0a5fb 100644
--- a/tools/bpf/bpftool/bash-completion/bpftool
+++ b/tools/bpf/bpftool/bash-completion/bpftool
@@ -704,7 +704,8 @@ _bpftool()
                                 lru_percpu_hash lpm_trie array_of_maps \
                                 hash_of_maps devmap devmap_hash sockmap cpumap \
                                 xskmap sockhash cgroup_storage reuseport_sockarray \
-                                percpu_cgroup_storage queue stack' -- \
+                                percpu_cgroup_storage queue stack sk_storage \
+                                struct_ops inode_storage' -- \
                                                    "$cur" ) )
                             return 0
                             ;;
diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index 3a27d31a1856..bc0071228f88 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -50,6 +50,7 @@ const char * const map_type_name[] = {
 	[BPF_MAP_TYPE_SK_STORAGE]		= "sk_storage",
 	[BPF_MAP_TYPE_STRUCT_OPS]		= "struct_ops",
 	[BPF_MAP_TYPE_RINGBUF]			= "ringbuf",
+	[BPF_MAP_TYPE_INODE_STORAGE]		= "inode_storage",
 };
 
 const size_t map_type_name_size = ARRAY_SIZE(map_type_name);
@@ -1442,7 +1443,7 @@ static int do_help(int argc, char **argv)
 		"                 lru_percpu_hash | lpm_trie | array_of_maps | hash_of_maps |\n"
 		"                 devmap | devmap_hash | sockmap | cpumap | xskmap | sockhash |\n"
 		"                 cgroup_storage | reuseport_sockarray | percpu_cgroup_storage |\n"
-		"                 queue | stack | sk_storage | struct_ops | ringbuf }\n"
+		"                 queue | stack | sk_storage | struct_ops | ringbuf | inode_storage }\n"
 		"       " HELP_SPEC_OPTIONS "\n"
 		"",
 		bin_name, argv[-2]);
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 2cbd137eed86..b6bfcd085a76 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -155,6 +155,7 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_DEVMAP_HASH,
 	BPF_MAP_TYPE_STRUCT_OPS,
 	BPF_MAP_TYPE_RINGBUF,
+	BPF_MAP_TYPE_INODE_STORAGE,
 };
 
 /* Note that tracing related programs such as
@@ -3509,6 +3510,41 @@ union bpf_attr {
  *
  *		**-EPERM** This helper cannot be used under the
  *			   current sock_ops->op.
+ * void *bpf_inode_storage_get(struct bpf_map *map, void *inode, void *value, u64 flags)
+ *	Description
+ *		Get a bpf_local_storage from an *inode*.
+ *
+ *		Logically, it could be thought of as getting the value from
+ *		a *map* with *inode* as the **key**.  From this
+ *		perspective,  the usage is not much different from
+ *		**bpf_map_lookup_elem**\ (*map*, **&**\ *inode*) except this
+ *		helper enforces the key must be an inode and the map must also
+ *		be a **BPF_MAP_TYPE_INODE_STORAGE**.
+ *
+ *		Underneath, the value is stored locally at *inode* instead of
+ *		the *map*.  The *map* is used as the bpf-local-storage
+ *		"type". The bpf-local-storage "type" (i.e. the *map*) is
+ *		searched against all bpf_local_storage residing at *inode*.
+ *
+ *		An optional *flags* (**BPF_LOCAL_STORAGE_GET_F_CREATE**) can be
+ *		used such that a new bpf_local_storage will be
+ *		created if one does not exist.  *value* can be used
+ *		together with **BPF_LOCAL_STORAGE_GET_F_CREATE** to specify
+ *		the initial value of a bpf_local_storage.  If *value* is
+ *		**NULL**, the new bpf_local_storage will be zero initialized.
+ *	Return
+ *		A bpf_local_storage pointer is returned on success.
+ *
+ *		**NULL** if not found or there was an error in adding
+ *		a new bpf_local_storage.
+ *
+ * int bpf_inode_storage_delete(struct bpf_map *map, void *inode)
+ *	Description
+ *		Delete a bpf_local_storage from an *inode*.
+ *	Return
+ *		0 on success.
+ *
+ *		**-ENOENT** if the bpf_local_storage cannot be found.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3655,7 +3691,9 @@ union bpf_attr {
 	FN(get_task_stack),		\
 	FN(load_hdr_opt),		\
 	FN(store_hdr_opt),		\
-	FN(reserve_hdr_opt),
+	FN(reserve_hdr_opt),		\
+	FN(inode_storage_get),		\
+	FN(inode_storage_delete),	\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c
index 010c9a76fd2b..5482a9b7ae2d 100644
--- a/tools/lib/bpf/libbpf_probes.c
+++ b/tools/lib/bpf/libbpf_probes.c
@@ -170,7 +170,7 @@ int libbpf__load_raw_btf(const char *raw_types, size_t types_len,
 	return btf_fd;
 }
 
-static int load_sk_storage_btf(void)
+static int load_local_storage_btf(void)
 {
 	const char strs[] = "\0bpf_spin_lock\0val\0cnt\0l";
 	/* struct bpf_spin_lock {
@@ -229,12 +229,13 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
 		key_size	= 0;
 		break;
 	case BPF_MAP_TYPE_SK_STORAGE:
+	case BPF_MAP_TYPE_INODE_STORAGE:
 		btf_key_type_id = 1;
 		btf_value_type_id = 3;
 		value_size = 8;
 		max_entries = 0;
 		map_flags = BPF_F_NO_PREALLOC;
-		btf_fd = load_sk_storage_btf();
+		btf_fd = load_local_storage_btf();
 		if (btf_fd < 0)
 			return false;
 		break;