From: KP Singh <[email protected]>
# v3 -> v4
- Fixed a missing include to bpf_sk_storage.h in bpf_sk_storage.c
- Fixed some functions that were not marked as static which led to
W=1 compilation warnings.
# v2 -> v3
* Restructured the code as per Martin's suggestions:
- Common functionality in bpf_local_storage.c
- bpf_sk_storage functionality remains in net/bpf_sk_storage.
- bpf_inode_storage is kept separate as it is enabled only with
CONFIG_BPF_LSM.
* A separate cache for inode and sk storage with macros to define it.
* Use the ops style approach as suggested by Martin instead of the
enum + switch style.
* Added the inode map to bpftool bash completion and docs.
* Rebase and indentation fixes.
# v1 -> v2
* Use the security blob pointer instead of dedicated member in
struct inode.
* Better code re-use as suggested by Alexei.
* Dropped the inode count arithmetic as pointed out by Alexei.
* Minor bug fixes and rebase.
bpf_sk_storage can already be used by some BPF program types to annotate
socket objects. These annotations are managed with the life-cycle of the
object (i.e. freed when the object is freed) which makes BPF programs
much simpler and less prone to errors and leaks.
This patch series:
* Generalizes the bpf_sk_storage infrastructure to allow easy
implementation of local storage for other objects
* Implements local storage for inodes
* Makes both bpf_{sk, inode}_storage available to LSM programs.
Local storage is safe to use in LSM programs as the attachment sites are
limited and the owning object won't be freed, however, this is not the
case for tracing. Usage in tracing is expected to follow a white-list
based approach similar to the d_path helper
(https://lore.kernel.org/bpf/[email protected]).
Access to local storage would allow LSM programs to implement stateful
detections like detecting the unlink of a running executable from the
examples shared as a part of the KRSI series
https://lore.kernel.org/bpf/[email protected]/
and
https://github.com/sinkap/linux-krsi/blob/patch/v1/examples/samples/bpf/lsm_detect_exec_unlink.c
KP Singh (4):
bpf: Generalize bpf_sk_storage
bpf: Implement bpf_local_storage for inodes
bpf: Allow local storage to be used from LSM programs
bpf: Add selftests for local_storage
include/linux/bpf.h | 14 +
include/linux/bpf_local_storage.h | 190 ++++
include/linux/bpf_lsm.h | 21 +
include/linux/bpf_types.h | 3 +
include/net/bpf_sk_storage.h | 2 +
include/net/sock.h | 4 +-
include/uapi/linux/bpf.h | 54 +-
kernel/bpf/Makefile | 2 +
kernel/bpf/bpf_inode_storage.c | 333 +++++++
kernel/bpf/bpf_local_storage.c | 517 +++++++++++
kernel/bpf/bpf_lsm.c | 21 +-
kernel/bpf/syscall.c | 3 +-
kernel/bpf/verifier.c | 10 +
net/core/bpf_sk_storage.c | 825 ++++--------------
security/bpf/hooks.c | 7 +
.../bpf/bpftool/Documentation/bpftool-map.rst | 2 +-
tools/bpf/bpftool/bash-completion/bpftool | 3 +-
tools/bpf/bpftool/map.c | 3 +-
tools/include/uapi/linux/bpf.h | 54 +-
tools/lib/bpf/libbpf_probes.c | 5 +-
.../bpf/prog_tests/test_local_storage.c | 60 ++
.../selftests/bpf/progs/local_storage.c | 136 +++
22 files changed, 1599 insertions(+), 670 deletions(-)
create mode 100644 include/linux/bpf_local_storage.h
create mode 100644 kernel/bpf/bpf_inode_storage.c
create mode 100644 kernel/bpf/bpf_local_storage.c
create mode 100644 tools/testing/selftests/bpf/prog_tests/test_local_storage.c
create mode 100644 tools/testing/selftests/bpf/progs/local_storage.c
--
2.27.0.389.gc38d7665816-goog
From: KP Singh <[email protected]>
Refactor the functionality in bpf_sk_storage.c so that concept of
storage linked to kernel objects can be extended to other objects like
inode, task_struct etc.
bpf_sk_storage is updated to be bpf_local_storage with a union that
contains a pointer to the owner object. The type of the
bpf_local_storage can be determined using the newly added
bpf_local_storage_type enum.
Each new local storage will still be a separate map and provide its own
set of helpers. This allows for future object specific extensions and
still share a lot of the underlying implementation.
Signed-off-by: KP Singh <[email protected]>
---
include/linux/bpf.h | 14 +
include/linux/bpf_local_storage.h | 175 +++++++
include/net/sock.h | 4 +-
include/uapi/linux/bpf.h | 12 +-
kernel/bpf/Makefile | 1 +
kernel/bpf/bpf_local_storage.c | 517 +++++++++++++++++++
net/core/bpf_sk_storage.c | 803 ++++++------------------------
tools/include/uapi/linux/bpf.h | 12 +-
8 files changed, 879 insertions(+), 659 deletions(-)
create mode 100644 include/linux/bpf_local_storage.h
create mode 100644 kernel/bpf/bpf_local_storage.c
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 0cd7f6884c5c..95ab7031cd8e 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -33,6 +33,9 @@ struct btf;
struct btf_type;
struct exception_table_entry;
struct seq_operations;
+struct bpf_local_storage;
+struct bpf_local_storage_map;
+struct bpf_local_storage_elem;
extern struct idr btf_idr;
extern spinlock_t btf_idr_lock;
@@ -93,6 +96,17 @@ struct bpf_map_ops {
__poll_t (*map_poll)(struct bpf_map *map, struct file *filp,
struct poll_table_struct *pts);
+ /* Functions called by bpf_local_storage maps */
+ void (*map_local_storage_unlink)(struct bpf_local_storage *local_storage,
+ bool uncharge_omem);
+ struct bpf_local_storage_elem *(*map_selem_alloc)(
+ struct bpf_local_storage_map *smap, void *owner, void *value,
+ bool charge_omem);
+ struct bpf_local_storage_data *(*map_local_storage_update)(
+ void *owner, struct bpf_map *map, void *value, u64 flags);
+ int (*map_local_storage_alloc)(void *owner,
+ struct bpf_local_storage_map *smap,
+ struct bpf_local_storage_elem *elem);
/* BTF name and id of struct allocated by map_alloc */
const char * const map_btf_name;
int *map_btf_id;
diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h
new file mode 100644
index 000000000000..605b81f2f806
--- /dev/null
+++ b/include/linux/bpf_local_storage.h
@@ -0,0 +1,175 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2019 Facebook
+ * Copyright 2020 Google LLC.
+ */
+
+#ifndef _BPF_LOCAL_STORAGE_H
+#define _BPF_LOCAL_STORAGE_H
+
+#include <linux/bpf.h>
+#include <linux/rculist.h>
+#include <linux/list.h>
+#include <linux/hash.h>
+#include <linux/types.h>
+#include <uapi/linux/btf.h>
+
+#define LOCAL_STORAGE_CREATE_FLAG_MASK \
+ (BPF_F_NO_PREALLOC | BPF_F_CLONE)
+
+struct bucket {
+ struct hlist_head list;
+ raw_spinlock_t lock;
+};
+
+/* Thp map is not the primary owner of a bpf_local_storage_elem.
+ * Instead, the container object (eg. sk->sk_bpf_storage) is.
+ *
+ * The map (bpf_local_storage_map) is for two purposes
+ * 1. Define the size of the "local storage". It is
+ * the map's value_size.
+ *
+ * 2. Maintain a list to keep track of all elems such
+ * that they can be cleaned up during the map destruction.
+ *
+ * When a bpf local storage is being looked up for a
+ * particular object, the "bpf_map" pointer is actually used
+ * as the "key" to search in the list of elem in
+ * the respective bpf_local_storage owned by the object.
+ *
+ * e.g. sk->sk_bpf_storage is the mini-map with the "bpf_map" pointer
+ * as the searching key.
+ */
+struct bpf_local_storage_map {
+ struct bpf_map map;
+ /* Lookup elem does not require accessing the map.
+ *
+ * Updating/Deleting requires a bucket lock to
+ * link/unlink the elem from the map. Having
+ * multiple buckets to improve contention.
+ */
+ struct bucket *buckets;
+ u32 bucket_log;
+ u16 elem_size;
+ u16 cache_idx;
+};
+
+struct bpf_local_storage_data {
+ /* smap is used as the searching key when looking up
+ * from the obejct's bpf_local_storage.
+ *
+ * Put it in the same cacheline as the data to minimize
+ * the number of cachelines access during the cache hit case.
+ */
+ struct bpf_local_storage_map __rcu *smap;
+ u8 data[] __aligned(8);
+};
+
+/* Linked to bpf_local_storage and bpf_local_storage_map */
+struct bpf_local_storage_elem {
+ struct hlist_node map_node; /* Linked to bpf_local_storage_map */
+ struct hlist_node snode; /* Linked to bpf_local_storage */
+ struct bpf_local_storage __rcu *local_storage;
+ struct rcu_head rcu;
+ /* 8 bytes hole */
+ /* The data is stored in aother cacheline to minimize
+ * the number of cachelines access during a cache hit.
+ */
+ struct bpf_local_storage_data sdata ____cacheline_aligned;
+};
+
+#define SELEM(_SDATA) \
+ container_of((_SDATA), struct bpf_local_storage_elem, sdata)
+#define SDATA(_SELEM) (&(_SELEM)->sdata)
+#define BPF_STORAGE_CACHE_SIZE 16
+
+u16 bpf_ls_cache_idx_get(spinlock_t *cache_idx_lock,
+ u64 *cache_idx_usage_count);
+
+void bpf_ls_cache_idx_free(spinlock_t *cache_idx_lock,
+ u64 *cache_idx_usage_counts, u16 idx);
+
+#define DEFINE_BPF_STORAGE_CACHE(type) \
+static DEFINE_SPINLOCK(cache_idx_lock_##type); \
+static u64 cache_idx_usage_counts_##type[BPF_STORAGE_CACHE_SIZE]; \
+static u16 cache_idx_get_##type(void) \
+{ \
+ return bpf_ls_cache_idx_get(&cache_idx_lock_##type, \
+ cache_idx_usage_counts_##type); \
+} \
+static void cache_idx_free_##type(u16 idx) \
+{ \
+ return bpf_ls_cache_idx_free(&cache_idx_lock_##type, \
+ cache_idx_usage_counts_##type, \
+ idx); \
+}
+
+/* U16_MAX is much more than enough for sk local storage
+ * considering a tcp_sock is ~2k.
+ */
+#define BPF_LOCAL_STORAGE_MAX_VALUE_SIZE \
+ min_t(u32, \
+ (KMALLOC_MAX_SIZE - MAX_BPF_STACK - \
+ sizeof(struct bpf_local_storage_elem)), \
+ (U16_MAX - sizeof(struct bpf_local_storage_elem)))
+
+struct bpf_local_storage {
+ struct bpf_local_storage_data __rcu *cache[BPF_STORAGE_CACHE_SIZE];
+ struct hlist_head list; /* List of bpf_local_storage_elem */
+ /* The object that owns the the above "list" of
+ * bpf_local_storage_elem
+ */
+ union {
+ struct sock *sk;
+ };
+ struct rcu_head rcu;
+ raw_spinlock_t lock; /* Protect adding/removing from the "list" */
+};
+
+/* Helper functions for bpf_local_storage */
+int bpf_local_storage_map_alloc_check(union bpf_attr *attr);
+
+struct bpf_local_storage_map *bpf_local_storage_map_alloc(union bpf_attr *attr);
+
+struct bpf_local_storage_data *
+bpf_local_storage_lookup(struct bpf_local_storage *local_storage,
+ struct bpf_local_storage_map *smap,
+ bool cacheit_lockit);
+
+void bpf_local_storage_map_free(struct bpf_local_storage_map *smap);
+
+int bpf_local_storage_map_check_btf(const struct bpf_map *map,
+ const struct btf *btf,
+ const struct btf_type *key_type,
+ const struct btf_type *value_type);
+
+void bpf_selem_link(struct bpf_local_storage *local_storage,
+ struct bpf_local_storage_elem *selem);
+
+bool bpf_selem_unlink(struct bpf_local_storage *local_storage,
+ struct bpf_local_storage_elem *selem, bool uncharge_omem);
+
+void bpf_selem_unlink_map_elem(struct bpf_local_storage_elem *selem);
+
+void bpf_selem_link_map(struct bpf_local_storage_map *smap,
+ struct bpf_local_storage_elem *selem);
+
+void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem);
+
+struct bpf_local_storage_elem *
+bpf_selem_alloc(struct bpf_local_storage_map *smap, void *value);
+
+struct bpf_local_storage *
+bpf_local_storage_alloc(struct bpf_local_storage_map *smap);
+
+int bpf_local_storage_publish(struct bpf_local_storage_elem *first_selem,
+ struct bpf_local_storage **addr,
+ struct bpf_local_storage *curr);
+
+int bpf_local_storage_check_update_flags(struct bpf_map *map, u64 map_flags);
+
+struct bpf_local_storage_data *
+bpf_local_storage_update(void *owner, struct bpf_map *map,
+ struct bpf_local_storage *local_storage, void *value,
+ u64 map_flags);
+#endif /* _BPF_LOCAL_STORAGE_H */
diff --git a/include/net/sock.h b/include/net/sock.h
index 84c813dd0152..5eada8a5eb21 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -245,7 +245,7 @@ struct sock_common {
/* public: */
};
-struct bpf_sk_storage;
+struct bpf_local_storage;
/**
* struct sock - network layer representation of sockets
@@ -516,7 +516,7 @@ struct sock {
void (*sk_destruct)(struct sock *sk);
struct sock_reuseport __rcu *sk_reuseport_cb;
#ifdef CONFIG_BPF_SYSCALL
- struct bpf_sk_storage __rcu *sk_bpf_storage;
+ struct bpf_local_storage __rcu *sk_bpf_storage;
#endif
struct rcu_head sk_rcu;
};
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 548a749aebb3..1f3e831c4813 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2802,10 +2802,10 @@ union bpf_attr {
* "type". The bpf-local-storage "type" (i.e. the *map*) is
* searched against all bpf-local-storages residing at *sk*.
*
- * An optional *flags* (**BPF_SK_STORAGE_GET_F_CREATE**) can be
+ * 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_SK_STORAGE_GET_F_CREATE** to specify
+ * 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
@@ -3572,9 +3572,13 @@ enum {
BPF_F_SYSCTL_BASE_NAME = (1ULL << 0),
};
-/* BPF_FUNC_sk_storage_get flags */
+/* BPF_FUNC_<local>_storage_get flags */
enum {
- BPF_SK_STORAGE_GET_F_CREATE = (1ULL << 0),
+ BPF_LOCAL_STORAGE_GET_F_CREATE = (1ULL << 0),
+ /* BPF_SK_STORAGE_GET_F_CREATE is only kept for backward compatibility
+ * and BPF_LOCAL_STORAGE_GET_F_CREATE must be used instead.
+ */
+ BPF_SK_STORAGE_GET_F_CREATE = BPF_LOCAL_STORAGE_GET_F_CREATE,
};
/* BPF_FUNC_read_branch_records flags. */
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 1131a921e1a6..0acb8f8a6042 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -12,6 +12,7 @@ obj-$(CONFIG_BPF_JIT) += dispatcher.o
ifeq ($(CONFIG_NET),y)
obj-$(CONFIG_BPF_SYSCALL) += devmap.o
obj-$(CONFIG_BPF_SYSCALL) += cpumap.o
+obj-$(CONFIG_BPF_SYSCALL) += bpf_local_storage.o
obj-$(CONFIG_BPF_SYSCALL) += offload.o
obj-$(CONFIG_BPF_SYSCALL) += net_namespace.o
endif
diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c
new file mode 100644
index 000000000000..c818eb6f8261
--- /dev/null
+++ b/kernel/bpf/bpf_local_storage.c
@@ -0,0 +1,517 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2019 Facebook
+ * Copyright 2020 Google LLC.
+ */
+
+#include <linux/rculist.h>
+#include <linux/list.h>
+#include <linux/hash.h>
+#include <linux/types.h>
+#include <linux/spinlock.h>
+#include <linux/bpf.h>
+#include <linux/bpf_local_storage.h>
+#include <net/sock.h>
+#include <uapi/linux/sock_diag.h>
+#include <uapi/linux/btf.h>
+
+#define SELEM(_SDATA) \
+ container_of((_SDATA), struct bpf_local_storage_elem, sdata)
+#define SDATA(_SELEM) (&(_SELEM)->sdata)
+
+static struct bucket *select_bucket(struct bpf_local_storage_map *smap,
+ struct bpf_local_storage_elem *selem)
+{
+ return &smap->buckets[hash_ptr(selem, smap->bucket_log)];
+}
+
+static bool selem_linked_to_node(const struct bpf_local_storage_elem *selem)
+{
+ return !hlist_unhashed(&selem->snode);
+}
+
+static bool selem_linked_to_map(const struct bpf_local_storage_elem *selem)
+{
+ return !hlist_unhashed(&selem->map_node);
+}
+
+struct bpf_local_storage_elem *
+bpf_selem_alloc(struct bpf_local_storage_map *smap, void *value)
+{
+ struct bpf_local_storage_elem *selem;
+
+ selem = kzalloc(smap->elem_size, GFP_ATOMIC | __GFP_NOWARN);
+ if (selem) {
+ if (value)
+ memcpy(SDATA(selem)->data, value, smap->map.value_size);
+ return selem;
+ }
+
+ return NULL;
+}
+
+/* local_storage->lock must be held and selem->local_storage == local_storage.
+ * The caller must ensure selem->smap is still valid to be
+ * dereferenced for its smap->elem_size and smap->cache_idx.
+ *
+ * uncharge_omem is only relevant for BPF_MAP_TYPE_SK_STORAGE.
+ */
+bool bpf_selem_unlink(struct bpf_local_storage *local_storage,
+ struct bpf_local_storage_elem *selem, bool uncharge_omem)
+{
+ struct bpf_local_storage_map *smap;
+ bool free_local_storage;
+
+ smap = rcu_dereference(SDATA(selem)->smap);
+ free_local_storage = hlist_is_singular_node(&selem->snode,
+ &local_storage->list);
+
+ /* local_storage is not freed now. local_storage->lock is
+ * still held and raw_spin_unlock_bh(&local_storage->lock)
+ * will be done by the caller.
+ * Although the unlock will be done under
+ * rcu_read_lock(), it is more intutivie to
+ * read if kfree_rcu(local_storage, rcu) is done
+ * after the raw_spin_unlock_bh(&local_storage->lock).
+ *
+ * Hence, a "bool free_local_storage" is returned
+ * to the caller which then calls the kfree_rcu()
+ * after unlock.
+ */
+ if (free_local_storage)
+ smap->map.ops->map_local_storage_unlink(local_storage,
+ uncharge_omem);
+
+ hlist_del_init_rcu(&selem->snode);
+ if (rcu_access_pointer(local_storage->cache[smap->cache_idx]) ==
+ SDATA(selem))
+ RCU_INIT_POINTER(local_storage->cache[smap->cache_idx], NULL);
+
+ kfree_rcu(selem, rcu);
+
+ return free_local_storage;
+}
+
+void bpf_selem_link(struct bpf_local_storage *local_storage,
+ struct bpf_local_storage_elem *selem)
+{
+ RCU_INIT_POINTER(selem->local_storage, local_storage);
+ hlist_add_head(&selem->snode, &local_storage->list);
+}
+
+void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem)
+{
+ struct bpf_local_storage_map *smap;
+ struct bucket *b;
+
+ if (unlikely(!selem_linked_to_map(selem)))
+ /* selem has already be unlinked from smap */
+ return;
+
+ smap = rcu_dereference(SDATA(selem)->smap);
+ b = select_bucket(smap, selem);
+ raw_spin_lock_bh(&b->lock);
+ if (likely(selem_linked_to_map(selem)))
+ hlist_del_init_rcu(&selem->map_node);
+ raw_spin_unlock_bh(&b->lock);
+}
+
+void bpf_selem_link_map(struct bpf_local_storage_map *smap,
+ struct bpf_local_storage_elem *selem)
+{
+ struct bucket *b = select_bucket(smap, selem);
+
+ raw_spin_lock_bh(&b->lock);
+ RCU_INIT_POINTER(SDATA(selem)->smap, smap);
+ hlist_add_head_rcu(&selem->map_node, &b->list);
+ raw_spin_unlock_bh(&b->lock);
+}
+
+void bpf_selem_unlink_map_elem(struct bpf_local_storage_elem *selem)
+{
+ struct bpf_local_storage *local_storage;
+ bool free_local_storage = false;
+
+ /* Always unlink from map before unlinking from local_storage
+ * because selem will be freed after successfully unlinked from
+ * the local_storage.
+ */
+ bpf_selem_unlink_map(selem);
+
+ if (unlikely(!selem_linked_to_node(selem)))
+ /* selem has already been unlinked from its owner */
+ return;
+
+ local_storage = rcu_dereference(selem->local_storage);
+ raw_spin_lock_bh(&local_storage->lock);
+ if (likely(selem_linked_to_node(selem)))
+ free_local_storage =
+ bpf_selem_unlink(local_storage, selem, true);
+ raw_spin_unlock_bh(&local_storage->lock);
+
+ if (free_local_storage)
+ kfree_rcu(local_storage, rcu);
+}
+
+struct bpf_local_storage_data *
+bpf_local_storage_lookup(struct bpf_local_storage *local_storage,
+ struct bpf_local_storage_map *smap,
+ bool cacheit_lockit)
+{
+ struct bpf_local_storage_data *sdata;
+ struct bpf_local_storage_elem *selem;
+
+ /* Fast path (cache hit) */
+ sdata = rcu_dereference(local_storage->cache[smap->cache_idx]);
+ if (sdata && rcu_access_pointer(sdata->smap) == smap)
+ return sdata;
+
+ /* Slow path (cache miss) */
+ hlist_for_each_entry_rcu(selem, &local_storage->list, snode)
+ if (rcu_access_pointer(SDATA(selem)->smap) == smap)
+ break;
+
+ if (!selem)
+ return NULL;
+
+ sdata = SDATA(selem);
+ if (cacheit_lockit) {
+ /* spinlock is needed to avoid racing with the
+ * parallel delete. Otherwise, publishing an already
+ * deleted sdata to the cache will become a use-after-free
+ * problem in the next bpf_local_storage_lookup().
+ */
+ raw_spin_lock_bh(&local_storage->lock);
+ if (selem_linked_to_node(selem))
+ rcu_assign_pointer(
+ local_storage->cache[smap->cache_idx], sdata);
+ raw_spin_unlock_bh(&local_storage->lock);
+ }
+
+ return sdata;
+}
+
+static int check_flags(const struct bpf_local_storage_data *old_sdata,
+ u64 map_flags)
+{
+ if (old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_NOEXIST)
+ /* elem already exists */
+ return -EEXIST;
+
+ if (!old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_EXIST)
+ /* elem doesn't exist, cannot update it */
+ return -ENOENT;
+
+ return 0;
+}
+
+struct bpf_local_storage *
+bpf_local_storage_alloc(struct bpf_local_storage_map *smap)
+{
+ struct bpf_local_storage *storage;
+
+ storage = kzalloc(sizeof(*storage), GFP_ATOMIC | __GFP_NOWARN);
+ if (!storage)
+ return NULL;
+
+ INIT_HLIST_HEAD(&storage->list);
+ raw_spin_lock_init(&storage->lock);
+ return storage;
+}
+
+/* Publish local_storage to the address. This is used because we are already
+ * in a region where we cannot grab a lock on the object owning the storage (
+ * (e.g sk->sk_lock). Hence, atomic ops is used.
+ *
+ * From now on, the addr pointer is protected
+ * by the local_storage->lock. Hence, upon freeing,
+ * the local_storage->lock must be held before unlinking the storage from the
+ * owner.
+ */
+int bpf_local_storage_publish(struct bpf_local_storage_elem *first_selem,
+ struct bpf_local_storage **addr,
+ struct bpf_local_storage *curr)
+{
+ struct bpf_local_storage *prev;
+
+ prev = cmpxchg(addr, NULL, curr);
+ if (unlikely(prev)) {
+ /* Note that even first_selem was linked to smap's
+ * bucket->list, first_selem can be freed immediately
+ * (instead of kfree_rcu) because
+ * bpf_local_storage_map_free() does a
+ * synchronize_rcu() before walking the bucket->list.
+ * Hence, no one is accessing selem from the
+ * bucket->list under rcu_read_lock().
+ */
+ bpf_selem_unlink_map(first_selem);
+ return -EAGAIN;
+ }
+
+ return 0;
+}
+
+int bpf_local_storage_check_update_flags(struct bpf_map *map, u64 map_flags)
+{
+ /* BPF_EXIST and BPF_NOEXIST cannot be both set */
+ if (unlikely((map_flags & ~BPF_F_LOCK) > BPF_EXIST) ||
+ /* BPF_F_LOCK can only be used in a value with spin_lock */
+ unlikely((map_flags & BPF_F_LOCK) && !map_value_has_spin_lock(map)))
+ return -EINVAL;
+
+ return 0;
+}
+
+struct bpf_local_storage_data *
+bpf_local_storage_update(void *owner, struct bpf_map *map,
+ struct bpf_local_storage *local_storage, void *value,
+ u64 map_flags)
+{
+ struct bpf_local_storage_data *old_sdata = NULL;
+ struct bpf_local_storage_elem *selem;
+ struct bpf_local_storage_map *smap;
+ int err;
+
+ smap = (struct bpf_local_storage_map *)map;
+
+ if ((map_flags & BPF_F_LOCK) && !(map_flags & BPF_NOEXIST)) {
+ /* Hoping to find an old_sdata to do inline update
+ * such that it can avoid taking the local_storage->lock
+ * and changing the lists.
+ */
+ old_sdata = bpf_local_storage_lookup(local_storage, smap, false);
+ err = check_flags(old_sdata, map_flags);
+ if (err)
+ return ERR_PTR(err);
+
+ if (old_sdata && selem_linked_to_node(SELEM(old_sdata))) {
+ copy_map_value_locked(map, old_sdata->data,
+ value, false);
+ return old_sdata;
+ }
+ }
+
+ raw_spin_lock_bh(&local_storage->lock);
+
+ /* Recheck local_storage->list under local_storage->lock */
+ if (unlikely(hlist_empty(&local_storage->list))) {
+ /* A parallel del is happening and local_storage is going
+ * away. It has just been checked before, so very
+ * unlikely. Return instead of retry to keep things
+ * simple.
+ */
+ err = -EAGAIN;
+ goto unlock_err;
+ }
+
+ old_sdata = bpf_local_storage_lookup(local_storage, smap, false);
+ err = check_flags(old_sdata, map_flags);
+ if (err)
+ goto unlock_err;
+
+ if (old_sdata && (map_flags & BPF_F_LOCK)) {
+ copy_map_value_locked(map, old_sdata->data, value, false);
+ selem = SELEM(old_sdata);
+ goto unlock;
+ }
+
+ /* local_storage->lock is held. Hence, we are sure
+ * we can unlink and uncharge the old_sdata successfully
+ * later. Hence, instead of charging the new selem now
+ * and then uncharge the old selem later (which may cause
+ * a potential but unnecessary charge failure), avoid taking
+ * a charge at all here (the "!old_sdata" check) and the
+ * old_sdata will not be uncharged later during bpf_selem_unlink().
+ */
+ selem = map->ops->map_selem_alloc(smap, owner, value, !old_sdata);
+ if (!selem) {
+ err = -ENOMEM;
+ goto unlock_err;
+ }
+
+ /* First, link the new selem to the map */
+ bpf_selem_link_map(smap, selem);
+
+ /* Second, link (and publish) the new selem to local_storage */
+ bpf_selem_link(local_storage, selem);
+
+ /* Third, remove old selem, SELEM(old_sdata) */
+ if (old_sdata) {
+ bpf_selem_unlink_map(SELEM(old_sdata));
+ bpf_selem_unlink(local_storage, SELEM(old_sdata), false);
+ }
+
+unlock:
+ raw_spin_unlock_bh(&local_storage->lock);
+ return SDATA(selem);
+
+unlock_err:
+ raw_spin_unlock_bh(&local_storage->lock);
+ return ERR_PTR(err);
+}
+
+u16 bpf_ls_cache_idx_get(spinlock_t *cache_idx_lock,
+ u64 *cache_idx_usage_counts)
+{
+ u64 min_usage = U64_MAX;
+ u16 i, res = 0;
+
+ spin_lock(cache_idx_lock);
+
+ for (i = 0; i < BPF_STORAGE_CACHE_SIZE; i++) {
+ if (cache_idx_usage_counts[i] < min_usage) {
+ min_usage = cache_idx_usage_counts[i];
+ res = i;
+
+ /* Found a free cache_idx */
+ if (!min_usage)
+ break;
+ }
+ }
+ cache_idx_usage_counts[res]++;
+
+ spin_unlock(cache_idx_lock);
+
+ return res;
+}
+
+void bpf_ls_cache_idx_free(spinlock_t *cache_idx_lock,
+ u64 *cache_idx_usage_counts, u16 idx)
+{
+ spin_lock(cache_idx_lock);
+ cache_idx_usage_counts[idx]--;
+ spin_unlock(cache_idx_lock);
+}
+
+void bpf_local_storage_map_free(struct bpf_local_storage_map *smap)
+{
+ struct bpf_local_storage_elem *selem;
+ struct bucket *b;
+ unsigned int i;
+
+ /* Note that this map might be concurrently cloned from
+ * bpf_sk_storage_clone. Wait for any existing bpf_sk_storage_clone
+ * RCU read section to finish before proceeding. New RCU
+ * read sections should be prevented via bpf_map_inc_not_zero.
+ */
+ synchronize_rcu();
+
+ /* bpf prog and the userspace can no longer access this map
+ * now. No new selem (of this map) can be added
+ * to the bpf_local_storage or to the map bucket's list.
+ *
+ * The elem of this map can be cleaned up here
+ * or by bpf_local_storage_free() during the destruction of the
+ * owner object. eg. __sk_destruct.
+ */
+ for (i = 0; i < (1U << smap->bucket_log); i++) {
+ b = &smap->buckets[i];
+
+ rcu_read_lock();
+ /* No one is adding to b->list now */
+ while ((selem = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(&b->list)),
+ struct bpf_local_storage_elem,
+ map_node))) {
+ bpf_selem_unlink_map_elem(selem);
+ cond_resched_rcu();
+ }
+ rcu_read_unlock();
+ }
+
+ /* bpf_local_storage_free() may still need to access the map.
+ * e.g. bpf_local_storage_free() has unlinked selem from the map
+ * which then made the above while((selem = ...)) loop
+ * exited immediately.
+ *
+ * However, the bpf_local_storage_free() still needs to access
+ * the smap->elem_size to do the uncharging in
+ * bpf_selem_unlink().
+ *
+ * Hence, wait another rcu grace period for the
+ * bpf_local_storage_free() to finish.
+ */
+ synchronize_rcu();
+
+ kvfree(smap->buckets);
+ kfree(smap);
+}
+
+int bpf_local_storage_map_alloc_check(union bpf_attr *attr)
+{
+ if (attr->map_flags & ~LOCAL_STORAGE_CREATE_FLAG_MASK ||
+ !(attr->map_flags & BPF_F_NO_PREALLOC) ||
+ attr->max_entries ||
+ attr->key_size != sizeof(int) || !attr->value_size ||
+ /* Enforce BTF for userspace sk dumping */
+ !attr->btf_key_type_id || !attr->btf_value_type_id)
+ return -EINVAL;
+
+ if (!bpf_capable())
+ return -EPERM;
+
+ if (attr->value_size > BPF_LOCAL_STORAGE_MAX_VALUE_SIZE)
+ return -E2BIG;
+
+ return 0;
+}
+
+struct bpf_local_storage_map *bpf_local_storage_map_alloc(union bpf_attr *attr)
+{
+ struct bpf_local_storage_map *smap;
+ unsigned int i;
+ u32 nbuckets;
+ u64 cost;
+ int ret;
+
+ smap = kzalloc(sizeof(*smap), GFP_USER | __GFP_NOWARN);
+ if (!smap)
+ return ERR_PTR(-ENOMEM);
+ bpf_map_init_from_attr(&smap->map, attr);
+
+ nbuckets = roundup_pow_of_two(num_possible_cpus());
+ /* Use at least 2 buckets, select_bucket() is undefined behavior with 1 bucket */
+ nbuckets = max_t(u32, 2, nbuckets);
+ smap->bucket_log = ilog2(nbuckets);
+ cost = sizeof(*smap->buckets) * nbuckets + sizeof(*smap);
+
+ ret = bpf_map_charge_init(&smap->map.memory, cost);
+ if (ret < 0) {
+ kfree(smap);
+ return ERR_PTR(ret);
+ }
+
+ smap->buckets = kvcalloc(sizeof(*smap->buckets), nbuckets,
+ GFP_USER | __GFP_NOWARN);
+ if (!smap->buckets) {
+ bpf_map_charge_finish(&smap->map.memory);
+ kfree(smap);
+ return ERR_PTR(-ENOMEM);
+ }
+
+ for (i = 0; i < nbuckets; i++) {
+ INIT_HLIST_HEAD(&smap->buckets[i].list);
+ raw_spin_lock_init(&smap->buckets[i].lock);
+ }
+
+ smap->elem_size =
+ sizeof(struct bpf_local_storage_elem) + attr->value_size;
+
+ return smap;
+}
+
+int bpf_local_storage_map_check_btf(const struct bpf_map *map,
+ const struct btf *btf,
+ const struct btf_type *key_type,
+ const struct btf_type *value_type)
+{
+ u32 int_data;
+
+ if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT)
+ return -EINVAL;
+
+ int_data = *(u32 *)(key_type + 1);
+ if (BTF_INT_BITS(int_data) != 32 || BTF_INT_OFFSET(int_data))
+ return -EINVAL;
+
+ return 0;
+}
diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
index 6f921c4ddc2c..a2b00a09d843 100644
--- a/net/core/bpf_sk_storage.c
+++ b/net/core/bpf_sk_storage.c
@@ -1,103 +1,20 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2019 Facebook */
+#include "linux/bpf.h"
+#include "asm-generic/bug.h"
+#include "linux/err.h"
#include <linux/rculist.h>
#include <linux/list.h>
#include <linux/hash.h>
#include <linux/types.h>
#include <linux/spinlock.h>
#include <linux/bpf.h>
+#include <linux/bpf_local_storage.h>
#include <net/bpf_sk_storage.h>
#include <net/sock.h>
#include <uapi/linux/sock_diag.h>
#include <uapi/linux/btf.h>
-#define SK_STORAGE_CREATE_FLAG_MASK \
- (BPF_F_NO_PREALLOC | BPF_F_CLONE)
-
-struct bucket {
- struct hlist_head list;
- raw_spinlock_t lock;
-};
-
-/* Thp map is not the primary owner of a bpf_sk_storage_elem.
- * Instead, the sk->sk_bpf_storage is.
- *
- * The map (bpf_sk_storage_map) is for two purposes
- * 1. Define the size of the "sk local storage". It is
- * the map's value_size.
- *
- * 2. Maintain a list to keep track of all elems such
- * that they can be cleaned up during the map destruction.
- *
- * When a bpf local storage is being looked up for a
- * particular sk, the "bpf_map" pointer is actually used
- * as the "key" to search in the list of elem in
- * sk->sk_bpf_storage.
- *
- * Hence, consider sk->sk_bpf_storage is the mini-map
- * with the "bpf_map" pointer as the searching key.
- */
-struct bpf_sk_storage_map {
- struct bpf_map map;
- /* Lookup elem does not require accessing the map.
- *
- * Updating/Deleting requires a bucket lock to
- * link/unlink the elem from the map. Having
- * multiple buckets to improve contention.
- */
- struct bucket *buckets;
- u32 bucket_log;
- u16 elem_size;
- u16 cache_idx;
-};
-
-struct bpf_sk_storage_data {
- /* smap is used as the searching key when looking up
- * from sk->sk_bpf_storage.
- *
- * Put it in the same cacheline as the data to minimize
- * the number of cachelines access during the cache hit case.
- */
- struct bpf_sk_storage_map __rcu *smap;
- u8 data[] __aligned(8);
-};
-
-/* Linked to bpf_sk_storage and bpf_sk_storage_map */
-struct bpf_sk_storage_elem {
- struct hlist_node map_node; /* Linked to bpf_sk_storage_map */
- struct hlist_node snode; /* Linked to bpf_sk_storage */
- struct bpf_sk_storage __rcu *sk_storage;
- struct rcu_head rcu;
- /* 8 bytes hole */
- /* The data is stored in aother cacheline to minimize
- * the number of cachelines access during a cache hit.
- */
- struct bpf_sk_storage_data sdata ____cacheline_aligned;
-};
-
-#define SELEM(_SDATA) container_of((_SDATA), struct bpf_sk_storage_elem, sdata)
-#define SDATA(_SELEM) (&(_SELEM)->sdata)
-#define BPF_SK_STORAGE_CACHE_SIZE 16
-
-static DEFINE_SPINLOCK(cache_idx_lock);
-static u64 cache_idx_usage_counts[BPF_SK_STORAGE_CACHE_SIZE];
-
-struct bpf_sk_storage {
- struct bpf_sk_storage_data __rcu *cache[BPF_SK_STORAGE_CACHE_SIZE];
- struct hlist_head list; /* List of bpf_sk_storage_elem */
- struct sock *sk; /* The sk that owns the the above "list" of
- * bpf_sk_storage_elem.
- */
- struct rcu_head rcu;
- raw_spinlock_t lock; /* Protect adding/removing from the "list" */
-};
-
-static struct bucket *select_bucket(struct bpf_sk_storage_map *smap,
- struct bpf_sk_storage_elem *selem)
-{
- return &smap->buckets[hash_ptr(selem, smap->bucket_log)];
-}
-
static int omem_charge(struct sock *sk, unsigned int size)
{
/* same check as in sock_kmalloc() */
@@ -110,31 +27,19 @@ static int omem_charge(struct sock *sk, unsigned int size)
return -ENOMEM;
}
-static bool selem_linked_to_sk(const struct bpf_sk_storage_elem *selem)
-{
- return !hlist_unhashed(&selem->snode);
-}
-
-static bool selem_linked_to_map(const struct bpf_sk_storage_elem *selem)
+static struct bpf_local_storage_elem *
+sk_selem_alloc(struct bpf_local_storage_map *smap, void *owner, void *value,
+ bool charge_omem)
{
- return !hlist_unhashed(&selem->map_node);
-}
-
-static struct bpf_sk_storage_elem *selem_alloc(struct bpf_sk_storage_map *smap,
- struct sock *sk, void *value,
- bool charge_omem)
-{
- struct bpf_sk_storage_elem *selem;
+ struct bpf_local_storage_elem *selem;
+ struct sock *sk = owner;
if (charge_omem && omem_charge(sk, smap->elem_size))
return NULL;
- selem = kzalloc(smap->elem_size, GFP_ATOMIC | __GFP_NOWARN);
- if (selem) {
- if (value)
- memcpy(SDATA(selem)->data, value, smap->map.value_size);
+ selem = bpf_selem_alloc(smap, value);
+ if (selem)
return selem;
- }
if (charge_omem)
atomic_sub(smap->elem_size, &sk->sk_omem_alloc);
@@ -142,242 +47,53 @@ static struct bpf_sk_storage_elem *selem_alloc(struct bpf_sk_storage_map *smap,
return NULL;
}
-/* sk_storage->lock must be held and selem->sk_storage == sk_storage.
- * The caller must ensure selem->smap is still valid to be
- * dereferenced for its smap->elem_size and smap->cache_idx.
- */
-static bool __selem_unlink_sk(struct bpf_sk_storage *sk_storage,
- struct bpf_sk_storage_elem *selem,
+static void unlink_sk_storage(struct bpf_local_storage *local_storage,
bool uncharge_omem)
{
- struct bpf_sk_storage_map *smap;
- bool free_sk_storage;
- struct sock *sk;
-
- smap = rcu_dereference(SDATA(selem)->smap);
- sk = sk_storage->sk;
+ struct sock *sk = local_storage->sk;
- /* All uncharging on sk->sk_omem_alloc must be done first.
- * sk may be freed once the last selem is unlinked from sk_storage.
- */
if (uncharge_omem)
- atomic_sub(smap->elem_size, &sk->sk_omem_alloc);
-
- free_sk_storage = hlist_is_singular_node(&selem->snode,
- &sk_storage->list);
- if (free_sk_storage) {
- atomic_sub(sizeof(struct bpf_sk_storage), &sk->sk_omem_alloc);
- sk_storage->sk = NULL;
- /* After this RCU_INIT, sk may be freed and cannot be used */
- RCU_INIT_POINTER(sk->sk_bpf_storage, NULL);
-
- /* sk_storage is not freed now. sk_storage->lock is
- * still held and raw_spin_unlock_bh(&sk_storage->lock)
- * will be done by the caller.
- *
- * Although the unlock will be done under
- * rcu_read_lock(), it is more intutivie to
- * read if kfree_rcu(sk_storage, rcu) is done
- * after the raw_spin_unlock_bh(&sk_storage->lock).
- *
- * Hence, a "bool free_sk_storage" is returned
- * to the caller which then calls the kfree_rcu()
- * after unlock.
- */
- }
- hlist_del_init_rcu(&selem->snode);
- if (rcu_access_pointer(sk_storage->cache[smap->cache_idx]) ==
- SDATA(selem))
- RCU_INIT_POINTER(sk_storage->cache[smap->cache_idx], NULL);
-
- kfree_rcu(selem, rcu);
-
- return free_sk_storage;
-}
-
-static void selem_unlink_sk(struct bpf_sk_storage_elem *selem)
-{
- struct bpf_sk_storage *sk_storage;
- bool free_sk_storage = false;
-
- if (unlikely(!selem_linked_to_sk(selem)))
- /* selem has already been unlinked from sk */
- return;
-
- sk_storage = rcu_dereference(selem->sk_storage);
- raw_spin_lock_bh(&sk_storage->lock);
- if (likely(selem_linked_to_sk(selem)))
- free_sk_storage = __selem_unlink_sk(sk_storage, selem, true);
- raw_spin_unlock_bh(&sk_storage->lock);
-
- if (free_sk_storage)
- kfree_rcu(sk_storage, rcu);
-}
+ atomic_sub(sizeof(struct bpf_local_storage),
+ &sk->sk_omem_alloc);
-static void __selem_link_sk(struct bpf_sk_storage *sk_storage,
- struct bpf_sk_storage_elem *selem)
-{
- RCU_INIT_POINTER(selem->sk_storage, sk_storage);
- hlist_add_head(&selem->snode, &sk_storage->list);
+ /* After this RCU_INIT, sk may be freed and cannot be used */
+ RCU_INIT_POINTER(sk->sk_bpf_storage, NULL);
+ local_storage->sk = NULL;
}
-static void selem_unlink_map(struct bpf_sk_storage_elem *selem)
+static int sk_storage_alloc(void *owner,
+ struct bpf_local_storage_map *smap,
+ struct bpf_local_storage_elem *first_selem)
{
- struct bpf_sk_storage_map *smap;
- struct bucket *b;
-
- if (unlikely(!selem_linked_to_map(selem)))
- /* selem has already be unlinked from smap */
- return;
-
- smap = rcu_dereference(SDATA(selem)->smap);
- b = select_bucket(smap, selem);
- raw_spin_lock_bh(&b->lock);
- if (likely(selem_linked_to_map(selem)))
- hlist_del_init_rcu(&selem->map_node);
- raw_spin_unlock_bh(&b->lock);
-}
-
-static void selem_link_map(struct bpf_sk_storage_map *smap,
- struct bpf_sk_storage_elem *selem)
-{
- struct bucket *b = select_bucket(smap, selem);
-
- raw_spin_lock_bh(&b->lock);
- RCU_INIT_POINTER(SDATA(selem)->smap, smap);
- hlist_add_head_rcu(&selem->map_node, &b->list);
- raw_spin_unlock_bh(&b->lock);
-}
-
-static void selem_unlink(struct bpf_sk_storage_elem *selem)
-{
- /* Always unlink from map before unlinking from sk_storage
- * because selem will be freed after successfully unlinked from
- * the sk_storage.
- */
- selem_unlink_map(selem);
- selem_unlink_sk(selem);
-}
-
-static struct bpf_sk_storage_data *
-__sk_storage_lookup(struct bpf_sk_storage *sk_storage,
- struct bpf_sk_storage_map *smap,
- bool cacheit_lockit)
-{
- struct bpf_sk_storage_data *sdata;
- struct bpf_sk_storage_elem *selem;
-
- /* Fast path (cache hit) */
- sdata = rcu_dereference(sk_storage->cache[smap->cache_idx]);
- if (sdata && rcu_access_pointer(sdata->smap) == smap)
- return sdata;
-
- /* Slow path (cache miss) */
- hlist_for_each_entry_rcu(selem, &sk_storage->list, snode)
- if (rcu_access_pointer(SDATA(selem)->smap) == smap)
- break;
-
- if (!selem)
- return NULL;
-
- sdata = SDATA(selem);
- if (cacheit_lockit) {
- /* spinlock is needed to avoid racing with the
- * parallel delete. Otherwise, publishing an already
- * deleted sdata to the cache will become a use-after-free
- * problem in the next __sk_storage_lookup().
- */
- raw_spin_lock_bh(&sk_storage->lock);
- if (selem_linked_to_sk(selem))
- rcu_assign_pointer(sk_storage->cache[smap->cache_idx],
- sdata);
- raw_spin_unlock_bh(&sk_storage->lock);
- }
-
- return sdata;
-}
-
-static struct bpf_sk_storage_data *
-sk_storage_lookup(struct sock *sk, struct bpf_map *map, bool cacheit_lockit)
-{
- struct bpf_sk_storage *sk_storage;
- struct bpf_sk_storage_map *smap;
-
- sk_storage = rcu_dereference(sk->sk_bpf_storage);
- if (!sk_storage)
- return NULL;
-
- smap = (struct bpf_sk_storage_map *)map;
- return __sk_storage_lookup(sk_storage, smap, cacheit_lockit);
-}
-
-static int check_flags(const struct bpf_sk_storage_data *old_sdata,
- u64 map_flags)
-{
- if (old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_NOEXIST)
- /* elem already exists */
- return -EEXIST;
-
- if (!old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_EXIST)
- /* elem doesn't exist, cannot update it */
- return -ENOENT;
-
- return 0;
-}
-
-static int sk_storage_alloc(struct sock *sk,
- struct bpf_sk_storage_map *smap,
- struct bpf_sk_storage_elem *first_selem)
-{
- struct bpf_sk_storage *prev_sk_storage, *sk_storage;
+ struct bpf_local_storage *curr;
+ struct sock *sk = owner;
int err;
- err = omem_charge(sk, sizeof(*sk_storage));
+ err = omem_charge(sk, sizeof(*curr));
if (err)
return err;
- sk_storage = kzalloc(sizeof(*sk_storage), GFP_ATOMIC | __GFP_NOWARN);
- if (!sk_storage) {
+ curr = bpf_local_storage_alloc(smap);
+ if (!curr) {
err = -ENOMEM;
goto uncharge;
}
- INIT_HLIST_HEAD(&sk_storage->list);
- raw_spin_lock_init(&sk_storage->lock);
- sk_storage->sk = sk;
-
- __selem_link_sk(sk_storage, first_selem);
- selem_link_map(smap, first_selem);
- /* Publish sk_storage to sk. sk->sk_lock cannot be acquired.
- * Hence, atomic ops is used to set sk->sk_bpf_storage
- * from NULL to the newly allocated sk_storage ptr.
- *
- * From now on, the sk->sk_bpf_storage pointer is protected
- * by the sk_storage->lock. Hence, when freeing
- * the sk->sk_bpf_storage, the sk_storage->lock must
- * be held before setting sk->sk_bpf_storage to NULL.
- */
- prev_sk_storage = cmpxchg((struct bpf_sk_storage **)&sk->sk_bpf_storage,
- NULL, sk_storage);
- if (unlikely(prev_sk_storage)) {
- selem_unlink_map(first_selem);
- err = -EAGAIN;
- goto uncharge;
- /* Note that even first_selem was linked to smap's
- * bucket->list, first_selem can be freed immediately
- * (instead of kfree_rcu) because
- * bpf_sk_storage_map_free() does a
- * synchronize_rcu() before walking the bucket->list.
- * Hence, no one is accessing selem from the
- * bucket->list under rcu_read_lock().
- */
- }
+ curr->sk = sk;
+
+ bpf_selem_link(curr, first_selem);
+ bpf_selem_link_map(smap, first_selem);
+
+ err = bpf_local_storage_publish(first_selem,
+ (struct bpf_local_storage **)&sk->sk_bpf_storage, curr);
+ if (err)
+ goto uncharge;
return 0;
uncharge:
- kfree(sk_storage);
- atomic_sub(sizeof(*sk_storage), &sk->sk_omem_alloc);
+ kfree(curr);
+ atomic_sub(sizeof(*curr), &sk->sk_omem_alloc);
return err;
}
@@ -386,36 +102,31 @@ static int sk_storage_alloc(struct sock *sk,
* Otherwise, it will become a leak (and other memory issues
* during map destruction).
*/
-static struct bpf_sk_storage_data *sk_storage_update(struct sock *sk,
- struct bpf_map *map,
- void *value,
- u64 map_flags)
+static struct bpf_local_storage_data *
+sk_storage_update(void *owner, struct bpf_map *map, void *value, u64 map_flags)
{
- struct bpf_sk_storage_data *old_sdata = NULL;
- struct bpf_sk_storage_elem *selem;
- struct bpf_sk_storage *sk_storage;
- struct bpf_sk_storage_map *smap;
+ struct bpf_local_storage_data *old_sdata = NULL;
+ struct bpf_local_storage_elem *selem;
+ struct bpf_local_storage *local_storage;
+ struct bpf_local_storage_map *smap;
+ struct sock *sk;
int err;
- /* BPF_EXIST and BPF_NOEXIST cannot be both set */
- if (unlikely((map_flags & ~BPF_F_LOCK) > BPF_EXIST) ||
- /* BPF_F_LOCK can only be used in a value with spin_lock */
- unlikely((map_flags & BPF_F_LOCK) && !map_value_has_spin_lock(map)))
- return ERR_PTR(-EINVAL);
+ err = bpf_local_storage_check_update_flags(map, map_flags);
+ if (err)
+ return ERR_PTR(err);
- smap = (struct bpf_sk_storage_map *)map;
- sk_storage = rcu_dereference(sk->sk_bpf_storage);
- if (!sk_storage || hlist_empty(&sk_storage->list)) {
- /* Very first elem for this sk */
- err = check_flags(NULL, map_flags);
- if (err)
- return ERR_PTR(err);
+ sk = owner;
+ local_storage = rcu_dereference(sk->sk_bpf_storage);
+ smap = (struct bpf_local_storage_map *)map;
- selem = selem_alloc(smap, sk, value, true);
+ if (!local_storage || hlist_empty(&local_storage->list)) {
+ /* Very first elem */
+ selem = map->ops->map_selem_alloc(smap, owner, value, !old_sdata);
if (!selem)
return ERR_PTR(-ENOMEM);
- err = sk_storage_alloc(sk, smap, selem);
+ err = map->ops->map_local_storage_alloc(owner, smap, selem);
if (err) {
kfree(selem);
atomic_sub(smap->elem_size, &sk->sk_omem_alloc);
@@ -425,130 +136,42 @@ static struct bpf_sk_storage_data *sk_storage_update(struct sock *sk,
return SDATA(selem);
}
- if ((map_flags & BPF_F_LOCK) && !(map_flags & BPF_NOEXIST)) {
- /* Hoping to find an old_sdata to do inline update
- * such that it can avoid taking the sk_storage->lock
- * and changing the lists.
- */
- old_sdata = __sk_storage_lookup(sk_storage, smap, false);
- err = check_flags(old_sdata, map_flags);
- if (err)
- return ERR_PTR(err);
- if (old_sdata && selem_linked_to_sk(SELEM(old_sdata))) {
- copy_map_value_locked(map, old_sdata->data,
- value, false);
- return old_sdata;
- }
- }
-
- raw_spin_lock_bh(&sk_storage->lock);
-
- /* Recheck sk_storage->list under sk_storage->lock */
- if (unlikely(hlist_empty(&sk_storage->list))) {
- /* A parallel del is happening and sk_storage is going
- * away. It has just been checked before, so very
- * unlikely. Return instead of retry to keep things
- * simple.
- */
- err = -EAGAIN;
- goto unlock_err;
- }
-
- old_sdata = __sk_storage_lookup(sk_storage, smap, false);
- err = check_flags(old_sdata, map_flags);
- if (err)
- goto unlock_err;
-
- if (old_sdata && (map_flags & BPF_F_LOCK)) {
- copy_map_value_locked(map, old_sdata->data, value, false);
- selem = SELEM(old_sdata);
- goto unlock;
- }
-
- /* sk_storage->lock is held. Hence, we are sure
- * we can unlink and uncharge the old_sdata successfully
- * later. Hence, instead of charging the new selem now
- * and then uncharge the old selem later (which may cause
- * a potential but unnecessary charge failure), avoid taking
- * a charge at all here (the "!old_sdata" check) and the
- * old_sdata will not be uncharged later during __selem_unlink_sk().
- */
- selem = selem_alloc(smap, sk, value, !old_sdata);
- if (!selem) {
- err = -ENOMEM;
- goto unlock_err;
- }
-
- /* First, link the new selem to the map */
- selem_link_map(smap, selem);
-
- /* Second, link (and publish) the new selem to sk_storage */
- __selem_link_sk(sk_storage, selem);
+ return bpf_local_storage_update(owner, map, local_storage, value,
+ map_flags);
+}
- /* Third, remove old selem, SELEM(old_sdata) */
- if (old_sdata) {
- selem_unlink_map(SELEM(old_sdata));
- __selem_unlink_sk(sk_storage, SELEM(old_sdata), false);
- }
+static struct bpf_local_storage_data *
+sk_storage_lookup(struct sock *sk, struct bpf_map *map, bool cacheit_lockit)
+{
+ struct bpf_local_storage *sk_storage;
+ struct bpf_local_storage_map *smap;
-unlock:
- raw_spin_unlock_bh(&sk_storage->lock);
- return SDATA(selem);
+ sk_storage = rcu_dereference(sk->sk_bpf_storage);
+ if (!sk_storage)
+ return NULL;
-unlock_err:
- raw_spin_unlock_bh(&sk_storage->lock);
- return ERR_PTR(err);
+ smap = (struct bpf_local_storage_map *)map;
+ return bpf_local_storage_lookup(sk_storage, smap, cacheit_lockit);
}
static int sk_storage_delete(struct sock *sk, struct bpf_map *map)
{
- struct bpf_sk_storage_data *sdata;
+ struct bpf_local_storage_data *sdata;
sdata = sk_storage_lookup(sk, map, false);
if (!sdata)
return -ENOENT;
- selem_unlink(SELEM(sdata));
+ bpf_selem_unlink_map_elem(SELEM(sdata));
return 0;
}
-static u16 cache_idx_get(void)
-{
- u64 min_usage = U64_MAX;
- u16 i, res = 0;
-
- spin_lock(&cache_idx_lock);
-
- for (i = 0; i < BPF_SK_STORAGE_CACHE_SIZE; i++) {
- if (cache_idx_usage_counts[i] < min_usage) {
- min_usage = cache_idx_usage_counts[i];
- res = i;
-
- /* Found a free cache_idx */
- if (!min_usage)
- break;
- }
- }
- cache_idx_usage_counts[res]++;
-
- spin_unlock(&cache_idx_lock);
-
- return res;
-}
-
-static void cache_idx_free(u16 idx)
-{
- spin_lock(&cache_idx_lock);
- cache_idx_usage_counts[idx]--;
- spin_unlock(&cache_idx_lock);
-}
-
/* Called by __sk_destruct() & bpf_sk_storage_clone() */
void bpf_sk_storage_free(struct sock *sk)
{
- struct bpf_sk_storage_elem *selem;
- struct bpf_sk_storage *sk_storage;
+ struct bpf_local_storage_elem *selem;
+ struct bpf_local_storage *sk_storage;
bool free_sk_storage = false;
struct hlist_node *n;
@@ -562,9 +185,9 @@ void bpf_sk_storage_free(struct sock *sk)
/* Netiher the bpf_prog nor the bpf-map's syscall
* could be modifying the sk_storage->list now.
* Thus, no elem can be added-to or deleted-from the
- * sk_storage->list by the bpf_prog or by the bpf-map's syscall.
+ * local_storage->list by the bpf_prog or by the bpf-map's syscall.
*
- * It is racing with bpf_sk_storage_map_free() alone
+ * It is racing with bpf_local_storage_map_free() alone
* when unlinking elem from the sk_storage->list and
* the map's bucket->list.
*/
@@ -573,8 +196,8 @@ void bpf_sk_storage_free(struct sock *sk)
/* Always unlink from map before unlinking from
* sk_storage.
*/
- selem_unlink_map(selem);
- free_sk_storage = __selem_unlink_sk(sk_storage, selem, true);
+ bpf_selem_unlink_map(selem);
+ free_sk_storage = bpf_selem_unlink(sk_storage, selem, true);
}
raw_spin_unlock_bh(&sk_storage->lock);
rcu_read_unlock();
@@ -583,163 +206,11 @@ void bpf_sk_storage_free(struct sock *sk)
kfree_rcu(sk_storage, rcu);
}
-static void bpf_sk_storage_map_free(struct bpf_map *map)
+static void *bpf_sk_storage_lookup_elem(struct bpf_map *map, void *key)
{
- struct bpf_sk_storage_elem *selem;
- struct bpf_sk_storage_map *smap;
- struct bucket *b;
- unsigned int i;
-
- smap = (struct bpf_sk_storage_map *)map;
-
- cache_idx_free(smap->cache_idx);
-
- /* Note that this map might be concurrently cloned from
- * bpf_sk_storage_clone. Wait for any existing bpf_sk_storage_clone
- * RCU read section to finish before proceeding. New RCU
- * read sections should be prevented via bpf_map_inc_not_zero.
- */
- synchronize_rcu();
-
- /* bpf prog and the userspace can no longer access this map
- * now. No new selem (of this map) can be added
- * to the sk->sk_bpf_storage or to the map bucket's list.
- *
- * The elem of this map can be cleaned up here
- * or
- * by bpf_sk_storage_free() during __sk_destruct().
- */
- for (i = 0; i < (1U << smap->bucket_log); i++) {
- b = &smap->buckets[i];
-
- rcu_read_lock();
- /* No one is adding to b->list now */
- while ((selem = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(&b->list)),
- struct bpf_sk_storage_elem,
- map_node))) {
- selem_unlink(selem);
- cond_resched_rcu();
- }
- rcu_read_unlock();
- }
-
- /* bpf_sk_storage_free() may still need to access the map.
- * e.g. bpf_sk_storage_free() has unlinked selem from the map
- * which then made the above while((selem = ...)) loop
- * exited immediately.
- *
- * However, the bpf_sk_storage_free() still needs to access
- * the smap->elem_size to do the uncharging in
- * __selem_unlink_sk().
- *
- * Hence, wait another rcu grace period for the
- * bpf_sk_storage_free() to finish.
- */
- synchronize_rcu();
-
- kvfree(smap->buckets);
- kfree(map);
-}
-
-/* U16_MAX is much more than enough for sk local storage
- * considering a tcp_sock is ~2k.
- */
-#define MAX_VALUE_SIZE \
- min_t(u32, \
- (KMALLOC_MAX_SIZE - MAX_BPF_STACK - sizeof(struct bpf_sk_storage_elem)), \
- (U16_MAX - sizeof(struct bpf_sk_storage_elem)))
-
-static int bpf_sk_storage_map_alloc_check(union bpf_attr *attr)
-{
- if (attr->map_flags & ~SK_STORAGE_CREATE_FLAG_MASK ||
- !(attr->map_flags & BPF_F_NO_PREALLOC) ||
- attr->max_entries ||
- attr->key_size != sizeof(int) || !attr->value_size ||
- /* Enforce BTF for userspace sk dumping */
- !attr->btf_key_type_id || !attr->btf_value_type_id)
- return -EINVAL;
-
- if (!bpf_capable())
- return -EPERM;
-
- if (attr->value_size > MAX_VALUE_SIZE)
- return -E2BIG;
-
- return 0;
-}
-
-static struct bpf_map *bpf_sk_storage_map_alloc(union bpf_attr *attr)
-{
- struct bpf_sk_storage_map *smap;
- unsigned int i;
- u32 nbuckets;
- u64 cost;
- int ret;
-
- smap = kzalloc(sizeof(*smap), GFP_USER | __GFP_NOWARN);
- if (!smap)
- return ERR_PTR(-ENOMEM);
- bpf_map_init_from_attr(&smap->map, attr);
-
- nbuckets = roundup_pow_of_two(num_possible_cpus());
- /* Use at least 2 buckets, select_bucket() is undefined behavior with 1 bucket */
- nbuckets = max_t(u32, 2, nbuckets);
- smap->bucket_log = ilog2(nbuckets);
- cost = sizeof(*smap->buckets) * nbuckets + sizeof(*smap);
-
- ret = bpf_map_charge_init(&smap->map.memory, cost);
- if (ret < 0) {
- kfree(smap);
- return ERR_PTR(ret);
- }
-
- smap->buckets = kvcalloc(sizeof(*smap->buckets), nbuckets,
- GFP_USER | __GFP_NOWARN);
- if (!smap->buckets) {
- bpf_map_charge_finish(&smap->map.memory);
- kfree(smap);
- return ERR_PTR(-ENOMEM);
- }
-
- for (i = 0; i < nbuckets; i++) {
- INIT_HLIST_HEAD(&smap->buckets[i].list);
- raw_spin_lock_init(&smap->buckets[i].lock);
- }
-
- smap->elem_size = sizeof(struct bpf_sk_storage_elem) + attr->value_size;
- smap->cache_idx = cache_idx_get();
-
- return &smap->map;
-}
-
-static int notsupp_get_next_key(struct bpf_map *map, void *key,
- void *next_key)
-{
- return -ENOTSUPP;
-}
-
-static int bpf_sk_storage_map_check_btf(const struct bpf_map *map,
- const struct btf *btf,
- const struct btf_type *key_type,
- const struct btf_type *value_type)
-{
- u32 int_data;
-
- if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT)
- return -EINVAL;
-
- int_data = *(u32 *)(key_type + 1);
- if (BTF_INT_BITS(int_data) != 32 || BTF_INT_OFFSET(int_data))
- return -EINVAL;
-
- return 0;
-}
-
-static void *bpf_fd_sk_storage_lookup_elem(struct bpf_map *map, void *key)
-{
- struct bpf_sk_storage_data *sdata;
+ struct bpf_local_storage_data *sdata;
struct socket *sock;
- int fd, err;
+ int fd, err = -EINVAL;
fd = *(int *)key;
sock = sockfd_lookup(fd, &err);
@@ -752,17 +223,18 @@ static void *bpf_fd_sk_storage_lookup_elem(struct bpf_map *map, void *key)
return ERR_PTR(err);
}
-static int bpf_fd_sk_storage_update_elem(struct bpf_map *map, void *key,
- void *value, u64 map_flags)
+static int bpf_sk_storage_update_elem(struct bpf_map *map, void *key,
+ void *value, u64 map_flags)
{
- struct bpf_sk_storage_data *sdata;
+ struct bpf_local_storage_data *sdata;
struct socket *sock;
int fd, err;
fd = *(int *)key;
sock = sockfd_lookup(fd, &err);
if (sock) {
- sdata = sk_storage_update(sock->sk, map, value, map_flags);
+ sdata = map->ops->map_local_storage_update(sock->sk, map, value,
+ map_flags);
sockfd_put(sock);
return PTR_ERR_OR_ZERO(sdata);
}
@@ -770,7 +242,7 @@ static int bpf_fd_sk_storage_update_elem(struct bpf_map *map, void *key,
return err;
}
-static int bpf_fd_sk_storage_delete_elem(struct bpf_map *map, void *key)
+static int bpf_sk_storage_delete_elem(struct bpf_map *map, void *key)
{
struct socket *sock;
int fd, err;
@@ -780,20 +252,19 @@ static int bpf_fd_sk_storage_delete_elem(struct bpf_map *map, void *key)
if (sock) {
err = sk_storage_delete(sock->sk, map);
sockfd_put(sock);
- return err;
}
return err;
}
-static struct bpf_sk_storage_elem *
+static struct bpf_local_storage_elem *
bpf_sk_storage_clone_elem(struct sock *newsk,
- struct bpf_sk_storage_map *smap,
- struct bpf_sk_storage_elem *selem)
+ struct bpf_local_storage_map *smap,
+ struct bpf_local_storage_elem *selem)
{
- struct bpf_sk_storage_elem *copy_selem;
+ struct bpf_local_storage_elem *copy_selem;
- copy_selem = selem_alloc(smap, newsk, NULL, true);
+ copy_selem = sk_selem_alloc(smap, newsk, NULL, true);
if (!copy_selem)
return NULL;
@@ -809,9 +280,9 @@ bpf_sk_storage_clone_elem(struct sock *newsk,
int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk)
{
- struct bpf_sk_storage *new_sk_storage = NULL;
- struct bpf_sk_storage *sk_storage;
- struct bpf_sk_storage_elem *selem;
+ struct bpf_local_storage *new_sk_storage = NULL;
+ struct bpf_local_storage *sk_storage;
+ struct bpf_local_storage_elem *selem;
int ret = 0;
RCU_INIT_POINTER(newsk->sk_bpf_storage, NULL);
@@ -823,8 +294,8 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk)
goto out;
hlist_for_each_entry_rcu(selem, &sk_storage->list, snode) {
- struct bpf_sk_storage_elem *copy_selem;
- struct bpf_sk_storage_map *smap;
+ struct bpf_local_storage_elem *copy_selem;
+ struct bpf_local_storage_map *smap;
struct bpf_map *map;
smap = rcu_dereference(SDATA(selem)->smap);
@@ -832,7 +303,7 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk)
continue;
/* Note that for lockless listeners adding new element
- * here can race with cleanup in bpf_sk_storage_map_free.
+ * here can race with cleanup in bpf_local_storage_map_free.
* Try to grab map refcnt to make sure that it's still
* alive and prevent concurrent removal.
*/
@@ -848,8 +319,8 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk)
}
if (new_sk_storage) {
- selem_link_map(smap, copy_selem);
- __selem_link_sk(new_sk_storage, copy_selem);
+ bpf_selem_link_map(smap, copy_selem);
+ bpf_selem_link(new_sk_storage, copy_selem);
} else {
ret = sk_storage_alloc(newsk, smap, copy_selem);
if (ret) {
@@ -860,7 +331,8 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk)
goto out;
}
- new_sk_storage = rcu_dereference(copy_selem->sk_storage);
+ new_sk_storage =
+ rcu_dereference(copy_selem->local_storage);
}
bpf_map_put(map);
}
@@ -869,7 +341,7 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk)
rcu_read_unlock();
/* In case of an error, don't free anything explicitly here, the
- * caller is responsible to call bpf_sk_storage_free.
+ * caller is responsible to call bpf_local_storage_free.
*/
return ret;
@@ -878,7 +350,7 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk)
BPF_CALL_4(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk,
void *, value, u64, flags)
{
- struct bpf_sk_storage_data *sdata;
+ struct bpf_local_storage_data *sdata;
if (flags > BPF_SK_STORAGE_GET_F_CREATE)
return (unsigned long)NULL;
@@ -887,7 +359,7 @@ BPF_CALL_4(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk,
if (sdata)
return (unsigned long)sdata->data;
- if (flags == BPF_SK_STORAGE_GET_F_CREATE &&
+ if (flags == BPF_LOCAL_STORAGE_GET_F_CREATE &&
/* Cannot add new elem to a going away sk.
* Otherwise, the new elem may become a leak
* (and also other memory issues during map
@@ -919,18 +391,51 @@ BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk)
return -ENOENT;
}
+static int notsupp_get_next_key(struct bpf_map *map, void *key,
+ void *next_key)
+{
+ return -ENOTSUPP;
+}
+
+DEFINE_BPF_STORAGE_CACHE(sk);
+
+static struct bpf_map *sk_storage_map_alloc(union bpf_attr *attr)
+{
+ struct bpf_local_storage_map *smap;
+
+ smap = bpf_local_storage_map_alloc(attr);
+ if (IS_ERR(smap))
+ return ERR_CAST(smap);
+
+ smap->cache_idx = cache_idx_get_sk();
+ return &smap->map;
+}
+
+static void sk_storage_map_free(struct bpf_map *map)
+{
+ struct bpf_local_storage_map *smap;
+
+ smap = (struct bpf_local_storage_map *)map;
+ cache_idx_free_sk(smap->cache_idx);
+ bpf_local_storage_map_free(smap);
+}
+
static int sk_storage_map_btf_id;
const struct bpf_map_ops sk_storage_map_ops = {
- .map_alloc_check = bpf_sk_storage_map_alloc_check,
- .map_alloc = bpf_sk_storage_map_alloc,
- .map_free = bpf_sk_storage_map_free,
+ .map_alloc_check = bpf_local_storage_map_alloc_check,
+ .map_alloc = sk_storage_map_alloc,
+ .map_free = sk_storage_map_free,
.map_get_next_key = notsupp_get_next_key,
- .map_lookup_elem = bpf_fd_sk_storage_lookup_elem,
- .map_update_elem = bpf_fd_sk_storage_update_elem,
- .map_delete_elem = bpf_fd_sk_storage_delete_elem,
- .map_check_btf = bpf_sk_storage_map_check_btf,
- .map_btf_name = "bpf_sk_storage_map",
+ .map_lookup_elem = bpf_sk_storage_lookup_elem,
+ .map_update_elem = bpf_sk_storage_update_elem,
+ .map_delete_elem = bpf_sk_storage_delete_elem,
+ .map_check_btf = bpf_local_storage_map_check_btf,
+ .map_btf_name = "bpf_local_storage_map",
.map_btf_id = &sk_storage_map_btf_id,
+ .map_local_storage_alloc = sk_storage_alloc,
+ .map_selem_alloc = sk_selem_alloc,
+ .map_local_storage_update = sk_storage_update,
+ .map_local_storage_unlink = unlink_sk_storage,
};
const struct bpf_func_proto bpf_sk_storage_get_proto = {
@@ -1011,7 +516,7 @@ bpf_sk_storage_diag_alloc(const struct nlattr *nla_stgs)
u32 nr_maps = 0;
int rem, err;
- /* bpf_sk_storage_map is currently limited to CAP_SYS_ADMIN as
+ /* bpf_local_storage_map is currently limited to CAP_SYS_ADMIN as
* the map_alloc_check() side also does.
*/
if (!bpf_capable())
@@ -1061,13 +566,13 @@ bpf_sk_storage_diag_alloc(const struct nlattr *nla_stgs)
}
EXPORT_SYMBOL_GPL(bpf_sk_storage_diag_alloc);
-static int diag_get(struct bpf_sk_storage_data *sdata, struct sk_buff *skb)
+static int diag_get(struct bpf_local_storage_data *sdata, struct sk_buff *skb)
{
struct nlattr *nla_stg, *nla_value;
- struct bpf_sk_storage_map *smap;
+ struct bpf_local_storage_map *smap;
/* It cannot exceed max nlattr's payload */
- BUILD_BUG_ON(U16_MAX - NLA_HDRLEN < MAX_VALUE_SIZE);
+ BUILD_BUG_ON(U16_MAX - NLA_HDRLEN < BPF_LOCAL_STORAGE_MAX_VALUE_SIZE);
nla_stg = nla_nest_start(skb, SK_DIAG_BPF_STORAGE);
if (!nla_stg)
@@ -1103,9 +608,9 @@ static int bpf_sk_storage_diag_put_all(struct sock *sk, struct sk_buff *skb,
{
/* stg_array_type (e.g. INET_DIAG_BPF_SK_STORAGES) */
unsigned int diag_size = nla_total_size(0);
- struct bpf_sk_storage *sk_storage;
- struct bpf_sk_storage_elem *selem;
- struct bpf_sk_storage_map *smap;
+ struct bpf_local_storage *sk_storage;
+ struct bpf_local_storage_elem *selem;
+ struct bpf_local_storage_map *smap;
struct nlattr *nla_stgs;
unsigned int saved_len;
int err = 0;
@@ -1158,8 +663,8 @@ int bpf_sk_storage_diag_put(struct bpf_sk_storage_diag *diag,
{
/* stg_array_type (e.g. INET_DIAG_BPF_SK_STORAGES) */
unsigned int diag_size = nla_total_size(0);
- struct bpf_sk_storage *sk_storage;
- struct bpf_sk_storage_data *sdata;
+ struct bpf_local_storage *sk_storage;
+ struct bpf_local_storage_data *sdata;
struct nlattr *nla_stgs;
unsigned int saved_len;
int err = 0;
@@ -1186,8 +691,8 @@ int bpf_sk_storage_diag_put(struct bpf_sk_storage_diag *diag,
saved_len = skb->len;
for (i = 0; i < diag->nr_maps; i++) {
- sdata = __sk_storage_lookup(sk_storage,
- (struct bpf_sk_storage_map *)diag->maps[i],
+ sdata = bpf_local_storage_lookup(sk_storage,
+ (struct bpf_local_storage_map *)diag->maps[i],
false);
if (!sdata)
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 548a749aebb3..1f3e831c4813 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -2802,10 +2802,10 @@ union bpf_attr {
* "type". The bpf-local-storage "type" (i.e. the *map*) is
* searched against all bpf-local-storages residing at *sk*.
*
- * An optional *flags* (**BPF_SK_STORAGE_GET_F_CREATE**) can be
+ * 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_SK_STORAGE_GET_F_CREATE** to specify
+ * 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
@@ -3572,9 +3572,13 @@ enum {
BPF_F_SYSCTL_BASE_NAME = (1ULL << 0),
};
-/* BPF_FUNC_sk_storage_get flags */
+/* BPF_FUNC_<local>_storage_get flags */
enum {
- BPF_SK_STORAGE_GET_F_CREATE = (1ULL << 0),
+ BPF_LOCAL_STORAGE_GET_F_CREATE = (1ULL << 0),
+ /* BPF_SK_STORAGE_GET_F_CREATE is only kept for backward compatibility
+ * and BPF_LOCAL_STORAGE_GET_F_CREATE must be used instead.
+ */
+ BPF_SK_STORAGE_GET_F_CREATE = BPF_LOCAL_STORAGE_GET_F_CREATE,
};
/* BPF_FUNC_read_branch_records flags. */
--
2.27.0.389.gc38d7665816-goog
From: KP Singh <[email protected]>
inode_local_storage:
* Hook to the file_open and inode_unlink LSM hooks.
* Create and unlink a temporary file.
* Store some information in the inode's bpf_local_storage during
file_open.
* Verify that this information exists when the file is unlinked.
sk_local_storage:
* Hook to the socket_post_create and socket_bind LSM hooks.
* Open and bind a socket and set the sk_storage in the
socket_post_create hook using the start_server helper.
* Verify if the information is set in the socket_bind hook.
Acked-by: Andrii Nakryiko <[email protected]>
Signed-off-by: KP Singh <[email protected]>
---
.../bpf/prog_tests/test_local_storage.c | 60 ++++++++
.../selftests/bpf/progs/local_storage.c | 136 ++++++++++++++++++
2 files changed, 196 insertions(+)
create mode 100644 tools/testing/selftests/bpf/prog_tests/test_local_storage.c
create mode 100644 tools/testing/selftests/bpf/progs/local_storage.c
diff --git a/tools/testing/selftests/bpf/prog_tests/test_local_storage.c b/tools/testing/selftests/bpf/prog_tests/test_local_storage.c
new file mode 100644
index 000000000000..d4ba89195c43
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_local_storage.c
@@ -0,0 +1,60 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright (C) 2020 Google LLC.
+ */
+
+#include <test_progs.h>
+#include <linux/limits.h>
+
+#include "local_storage.skel.h"
+#include "network_helpers.h"
+
+int create_and_unlink_file(void)
+{
+ char fname[PATH_MAX] = "/tmp/fileXXXXXX";
+ int fd;
+
+ fd = mkstemp(fname);
+ if (fd < 0)
+ return fd;
+
+ close(fd);
+ unlink(fname);
+ return 0;
+}
+
+void test_test_local_storage(void)
+{
+ struct local_storage *skel = NULL;
+ int err, duration = 0, serv_sk = -1;
+
+ skel = local_storage__open_and_load();
+ if (CHECK(!skel, "skel_load", "lsm skeleton failed\n"))
+ goto close_prog;
+
+ err = local_storage__attach(skel);
+ if (CHECK(err, "attach", "lsm attach failed: %d\n", err))
+ goto close_prog;
+
+ skel->bss->monitored_pid = getpid();
+
+ err = create_and_unlink_file();
+ if (CHECK(err < 0, "exec_cmd", "err %d errno %d\n", err, errno))
+ goto close_prog;
+
+ CHECK(!skel->bss->inode_storage_result, "inode_storage_result",
+ "inode_local_storage not set");
+
+ serv_sk = start_server(AF_INET6, SOCK_STREAM, NULL, 0, 0);
+ if (CHECK(serv_sk < 0, "start_server", "failed to start server\n"))
+ goto close_prog;
+
+ CHECK(!skel->bss->sk_storage_result, "sk_storage_result",
+ "sk_local_storage not set");
+
+ close(serv_sk);
+
+close_prog:
+ local_storage__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/progs/local_storage.c b/tools/testing/selftests/bpf/progs/local_storage.c
new file mode 100644
index 000000000000..cb608b7b90f0
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/local_storage.c
@@ -0,0 +1,136 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright 2020 Google LLC.
+ */
+
+#include <errno.h>
+#include <linux/bpf.h>
+#include <stdbool.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+#define DUMMY_STORAGE_VALUE 0xdeadbeef
+
+int monitored_pid = 0;
+bool inode_storage_result = false;
+bool sk_storage_result = false;
+
+struct dummy_storage {
+ __u32 value;
+};
+
+struct {
+ __uint(type, BPF_MAP_TYPE_INODE_STORAGE);
+ __uint(map_flags, BPF_F_NO_PREALLOC);
+ __type(key, int);
+ __type(value, struct dummy_storage);
+} inode_storage_map SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_SK_STORAGE);
+ __uint(map_flags, BPF_F_NO_PREALLOC | BPF_F_CLONE);
+ __type(key, int);
+ __type(value, struct dummy_storage);
+} sk_storage_map SEC(".maps");
+
+/* TODO Use vmlinux.h once BTF pruning for embedded types is fixed.
+ */
+struct sock {} __attribute__((preserve_access_index));
+struct sockaddr {} __attribute__((preserve_access_index));
+struct socket {
+ struct sock *sk;
+} __attribute__((preserve_access_index));
+
+struct inode {} __attribute__((preserve_access_index));
+struct dentry {
+ struct inode *d_inode;
+} __attribute__((preserve_access_index));
+struct file {
+ struct inode *f_inode;
+} __attribute__((preserve_access_index));
+
+
+SEC("lsm/inode_unlink")
+int BPF_PROG(unlink_hook, struct inode *dir, struct dentry *victim)
+{
+ __u32 pid = bpf_get_current_pid_tgid() >> 32;
+ struct dummy_storage *storage;
+
+ if (pid != monitored_pid)
+ return 0;
+
+ storage = bpf_inode_storage_get(&inode_storage_map, victim->d_inode, 0,
+ BPF_SK_STORAGE_GET_F_CREATE);
+ if (!storage)
+ return 0;
+
+ if (storage->value == DUMMY_STORAGE_VALUE)
+ inode_storage_result = true;
+
+ return 0;
+}
+
+SEC("lsm/socket_bind")
+int BPF_PROG(socket_bind, struct socket *sock, struct sockaddr *address,
+ int addrlen)
+{
+ __u32 pid = bpf_get_current_pid_tgid() >> 32;
+ struct dummy_storage *storage;
+
+ if (pid != monitored_pid)
+ return 0;
+
+ storage = bpf_sk_storage_get(&sk_storage_map, sock->sk, 0,
+ BPF_SK_STORAGE_GET_F_CREATE);
+ if (!storage)
+ return 0;
+
+ if (storage->value == DUMMY_STORAGE_VALUE)
+ sk_storage_result = true;
+
+ return 0;
+}
+
+SEC("lsm/socket_post_create")
+int BPF_PROG(socket_post_create, struct socket *sock, int family, int type,
+ int protocol, int kern)
+{
+ __u32 pid = bpf_get_current_pid_tgid() >> 32;
+ struct dummy_storage *storage;
+
+ if (pid != monitored_pid)
+ return 0;
+
+ storage = bpf_sk_storage_get(&sk_storage_map, sock->sk, 0,
+ BPF_SK_STORAGE_GET_F_CREATE);
+ if (!storage)
+ return 0;
+
+ storage->value = DUMMY_STORAGE_VALUE;
+
+ return 0;
+}
+
+SEC("lsm/file_open")
+int BPF_PROG(test_int_hook, struct file *file)
+{
+ __u32 pid = bpf_get_current_pid_tgid() >> 32;
+ struct dummy_storage *storage;
+
+ if (pid != monitored_pid)
+ return 0;
+
+ if (!file->f_inode)
+ return 0;
+
+ storage = bpf_inode_storage_get(&inode_storage_map, file->f_inode, 0,
+ BPF_LOCAL_STORAGE_GET_F_CREATE);
+ if (!storage)
+ return 0;
+
+ storage->value = DUMMY_STORAGE_VALUE;
+ return 0;
+}
--
2.27.0.389.gc38d7665816-goog
From: KP Singh <[email protected]>
Adds support for both bpf_{sk, inode}_storage_{get, delete} to be used
in LSM programs. These helpers are not used for tracing programs
(currently) as their usage is tied to the life-cycle of the object and
should only be used where the owning object won't be freed (when the
owning object is passed as an argument to the LSM hook). Thus, they
are safer to use in LSM hooks than tracing. Usage of local storage in
tracing programs will probably follow a per function based whitelist
approach.
Since the UAPI helper signature for bpf_sk_storage expect a bpf_sock,
it, leads to a compilation warning for LSM programs, it's also updated
to accept a void * pointer instead.
Signed-off-by: KP Singh <[email protected]>
---
include/net/bpf_sk_storage.h | 2 ++
include/uapi/linux/bpf.h | 4 ++--
kernel/bpf/bpf_lsm.c | 21 ++++++++++++++++++++-
net/core/bpf_sk_storage.c | 22 ++++++++++++++++++++++
tools/include/uapi/linux/bpf.h | 4 ++--
5 files changed, 48 insertions(+), 5 deletions(-)
diff --git a/include/net/bpf_sk_storage.h b/include/net/bpf_sk_storage.h
index 5036c94c0503..d231da1b57ca 100644
--- a/include/net/bpf_sk_storage.h
+++ b/include/net/bpf_sk_storage.h
@@ -9,6 +9,8 @@ void bpf_sk_storage_free(struct sock *sk);
extern const struct bpf_func_proto bpf_sk_storage_get_proto;
extern const struct bpf_func_proto bpf_sk_storage_delete_proto;
+extern const struct bpf_func_proto sk_storage_get_btf_proto;
+extern const struct bpf_func_proto sk_storage_delete_btf_proto;
struct bpf_sk_storage_diag;
struct sk_buff;
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 42fc442f4586..3d2859ccc7ae 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2787,7 +2787,7 @@ union bpf_attr {
*
* **-ERANGE** if resulting value was out of range.
*
- * void *bpf_sk_storage_get(struct bpf_map *map, struct bpf_sock *sk, void *value, u64 flags)
+ * void *bpf_sk_storage_get(struct bpf_map *map, void *sk, void *value, u64 flags)
* Description
* Get a bpf-local-storage from a *sk*.
*
@@ -2815,7 +2815,7 @@ union bpf_attr {
* **NULL** if not found or there was an error in adding
* a new bpf-local-storage.
*
- * long bpf_sk_storage_delete(struct bpf_map *map, struct bpf_sock *sk)
+ * long bpf_sk_storage_delete(struct bpf_map *map, void *sk)
* Description
* Delete a bpf-local-storage from a *sk*.
* Return
diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c
index fb278144e9fd..9cd1428c7199 100644
--- a/kernel/bpf/bpf_lsm.c
+++ b/kernel/bpf/bpf_lsm.c
@@ -11,6 +11,8 @@
#include <linux/bpf_lsm.h>
#include <linux/kallsyms.h>
#include <linux/bpf_verifier.h>
+#include <net/bpf_sk_storage.h>
+#include <linux/bpf_local_storage.h>
/* For every LSM hook that allows attachment of BPF programs, declare a nop
* function where a BPF program can be attached.
@@ -45,10 +47,27 @@ int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog,
return 0;
}
+static const struct bpf_func_proto *
+bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
+{
+ switch (func_id) {
+ case BPF_FUNC_inode_storage_get:
+ return &bpf_inode_storage_get_proto;
+ case BPF_FUNC_inode_storage_delete:
+ return &bpf_inode_storage_delete_proto;
+ case BPF_FUNC_sk_storage_get:
+ return &sk_storage_get_btf_proto;
+ case BPF_FUNC_sk_storage_delete:
+ return &sk_storage_delete_btf_proto;
+ default:
+ return tracing_prog_func_proto(func_id, prog);
+ }
+}
+
const struct bpf_prog_ops lsm_prog_ops = {
};
const struct bpf_verifier_ops lsm_verifier_ops = {
- .get_func_proto = tracing_prog_func_proto,
+ .get_func_proto = bpf_lsm_func_proto,
.is_valid_access = btf_ctx_access,
};
diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
index a2b00a09d843..ed0a07e0bb67 100644
--- a/net/core/bpf_sk_storage.c
+++ b/net/core/bpf_sk_storage.c
@@ -456,6 +456,28 @@ const struct bpf_func_proto bpf_sk_storage_delete_proto = {
.arg2_type = ARG_PTR_TO_SOCKET,
};
+static int sk_storage_get_btf_ids[4];
+const struct bpf_func_proto sk_storage_get_btf_proto = {
+ .func = bpf_sk_storage_get,
+ .gpl_only = false,
+ .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL,
+ .arg1_type = ARG_CONST_MAP_PTR,
+ .arg2_type = ARG_PTR_TO_BTF_ID,
+ .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL,
+ .arg4_type = ARG_ANYTHING,
+ .btf_id = sk_storage_get_btf_ids,
+};
+
+static int sk_storage_delete_btf_ids[2];
+const struct bpf_func_proto sk_storage_delete_btf_proto = {
+ .func = bpf_sk_storage_delete,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_CONST_MAP_PTR,
+ .arg2_type = ARG_PTR_TO_BTF_ID,
+ .btf_id = sk_storage_delete_btf_ids,
+};
+
struct bpf_sk_storage_diag {
u32 nr_maps;
struct bpf_map *maps[];
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 42fc442f4586..3d2859ccc7ae 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -2787,7 +2787,7 @@ union bpf_attr {
*
* **-ERANGE** if resulting value was out of range.
*
- * void *bpf_sk_storage_get(struct bpf_map *map, struct bpf_sock *sk, void *value, u64 flags)
+ * void *bpf_sk_storage_get(struct bpf_map *map, void *sk, void *value, u64 flags)
* Description
* Get a bpf-local-storage from a *sk*.
*
@@ -2815,7 +2815,7 @@ union bpf_attr {
* **NULL** if not found or there was an error in adding
* a new bpf-local-storage.
*
- * long bpf_sk_storage_delete(struct bpf_map *map, struct bpf_sock *sk)
+ * long bpf_sk_storage_delete(struct bpf_map *map, void *sk)
* Description
* Delete a bpf-local-storage from a *sk*.
* Return
--
2.27.0.389.gc38d7665816-goog
From: KP Singh <[email protected]>
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 <[email protected]>
---
include/linux/bpf_local_storage.h | 15 +
include/linux/bpf_lsm.h | 21 ++
include/linux/bpf_types.h | 3 +
include/uapi/linux/bpf.h | 38 ++
kernel/bpf/Makefile | 1 +
kernel/bpf/bpf_inode_storage.c | 333 ++++++++++++++++++
kernel/bpf/syscall.c | 3 +-
kernel/bpf/verifier.c | 10 +
security/bpf/hooks.c | 7 +
.../bpf/bpftool/Documentation/bpftool-map.rst | 2 +-
tools/bpf/bpftool/bash-completion/bpftool | 3 +-
tools/bpf/bpftool/map.c | 3 +-
tools/include/uapi/linux/bpf.h | 38 ++
tools/lib/bpf/libbpf_probes.c | 5 +-
14 files changed, 476 insertions(+), 6 deletions(-)
create mode 100644 kernel/bpf/bpf_inode_storage.c
diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h
index 605b81f2f806..63cc7b93ae80 100644
--- a/include/linux/bpf_local_storage.h
+++ b/include/linux/bpf_local_storage.h
@@ -113,6 +113,8 @@ static void cache_idx_free_##type(u16 idx) \
sizeof(struct bpf_local_storage_elem)), \
(U16_MAX - sizeof(struct bpf_local_storage_elem)))
+struct inode;
+
struct bpf_local_storage {
struct bpf_local_storage_data __rcu *cache[BPF_STORAGE_CACHE_SIZE];
struct hlist_head list; /* List of bpf_local_storage_elem */
@@ -121,6 +123,9 @@ struct bpf_local_storage {
*/
union {
struct sock *sk;
+#ifdef CONFIG_BPF_LSM
+ struct inode *inode;
+#endif
};
struct rcu_head rcu;
raw_spinlock_t lock; /* Protect adding/removing from the "list" */
@@ -172,4 +177,14 @@ struct bpf_local_storage_data *
bpf_local_storage_update(void *owner, struct bpf_map *map,
struct bpf_local_storage *local_storage, void *value,
u64 map_flags);
+
+#ifdef CONFIG_BPF_LSM
+extern const struct bpf_func_proto bpf_inode_storage_get_proto;
+extern const struct bpf_func_proto bpf_inode_storage_delete_proto;
+void bpf_inode_storage_free(struct inode *inode);
+#else
+static inline void bpf_inode_storage_free(struct inode *inode)
+{
+}
+#endif
#endif /* _BPF_LOCAL_STORAGE_H */
diff --git a/include/linux/bpf_lsm.h b/include/linux/bpf_lsm.h
index af74712af585..d0683ada1e49 100644
--- a/include/linux/bpf_lsm.h
+++ b/include/linux/bpf_lsm.h
@@ -17,9 +17,24 @@
#include <linux/lsm_hook_defs.h>
#undef LSM_HOOK
+struct bpf_storage_blob {
+ struct bpf_local_storage __rcu *storage;
+};
+
+extern struct lsm_blob_sizes bpf_lsm_blob_sizes;
+
int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog,
const struct bpf_prog *prog);
+static inline struct bpf_storage_blob *bpf_inode(
+ const struct inode *inode)
+{
+ if (unlikely(!inode->i_security))
+ return NULL;
+
+ return inode->i_security + bpf_lsm_blob_sizes.lbs_inode;
+}
+
#else /* !CONFIG_BPF_LSM */
static inline int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog,
@@ -28,6 +43,12 @@ static inline int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog,
return -EOPNOTSUPP;
}
+static inline struct bpf_storage_blob *bpf_inode(
+ const struct inode *inode)
+{
+ return NULL;
+}
+
#endif /* CONFIG_BPF_LSM */
#endif /* _LINUX_BPF_LSM_H */
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index a18ae82a298a..2950576de4ae 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -105,6 +105,9 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_SK_STORAGE, sk_storage_map_ops)
BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops)
BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKHASH, sock_hash_ops)
#endif
+#ifdef CONFIG_BPF_LSM
+BPF_MAP_TYPE(BPF_MAP_TYPE_INODE_STORAGE, inode_storage_map_ops)
+#endif
BPF_MAP_TYPE(BPF_MAP_TYPE_CPUMAP, cpu_map_ops)
#if defined(CONFIG_XDP_SOCKETS)
BPF_MAP_TYPE(BPF_MAP_TYPE_XSKMAP, xsk_map_ops)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 1f3e831c4813..42fc442f4586 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -148,6 +148,7 @@ 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
@@ -3319,6 +3320,41 @@ union bpf_attr {
* A non-negative value equal to or less than *size* on success,
* or a negative error in case of failure.
*
+ * 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), \
@@ -3463,6 +3499,8 @@ union bpf_attr {
FN(skc_to_tcp_request_sock), \
FN(skc_to_udp6_sock), \
FN(get_task_stack), \
+ FN(inode_storage_get), \
+ FN(inode_storage_delete), \
/* */
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 0acb8f8a6042..0ea9fd15977c 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -5,6 +5,7 @@ CFLAGS_core.o += $(call cc-disable-warning, override-init)
obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o bpf_iter.o map_iter.o task_iter.o
obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o
obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o ringbuf.o
+obj-${CONFIG_BPF_LSM} += bpf_inode_storage.o
obj-$(CONFIG_BPF_SYSCALL) += disasm.o
obj-$(CONFIG_BPF_JIT) += trampoline.o
obj-$(CONFIG_BPF_SYSCALL) += btf.o
diff --git a/kernel/bpf/bpf_inode_storage.c b/kernel/bpf/bpf_inode_storage.c
new file mode 100644
index 000000000000..d63db7a24168
--- /dev/null
+++ b/kernel/bpf/bpf_inode_storage.c
@@ -0,0 +1,333 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2019 Facebook
+ * Copyright 2020 Google LLC.
+ */
+
+#include <linux/rculist.h>
+#include <linux/list.h>
+#include <linux/hash.h>
+#include <linux/types.h>
+#include <linux/spinlock.h>
+#include <linux/bpf.h>
+#include <linux/bpf_local_storage.h>
+#include <net/sock.h>
+#include <uapi/linux/sock_diag.h>
+#include <uapi/linux/btf.h>
+#include <linux/bpf_lsm.h>
+
+static struct bpf_local_storage_elem *
+inode_selem_alloc(struct bpf_local_storage_map *smap, void *owner,
+ void *value, bool charge_omem)
+{
+ return bpf_selem_alloc(smap, value);
+}
+
+static void unlink_inode_storage(struct bpf_local_storage *local_storage,
+ bool uncharge_omem)
+{
+ struct bpf_storage_blob *bsb;
+ struct inode *inode;
+
+ inode = local_storage->inode;
+ bsb = bpf_inode(inode);
+ if (!bsb)
+ return;
+ RCU_INIT_POINTER(bsb->storage, NULL);
+ local_storage->inode = NULL;
+}
+
+static struct bpf_local_storage_data *inode_storage_lookup(struct inode *inode,
+ struct bpf_map *map,
+ bool cacheit_lockit)
+{
+ struct bpf_local_storage *inode_storage;
+ struct bpf_local_storage_map *smap;
+ struct bpf_storage_blob *bsb;
+
+ bsb = bpf_inode(inode);
+ if (!bsb)
+ return ERR_PTR(-ENOENT);
+
+ inode_storage = rcu_dereference(bsb->storage);
+ if (!inode_storage)
+ return NULL;
+
+ smap = (struct bpf_local_storage_map *)map;
+ return bpf_local_storage_lookup(inode_storage, smap, cacheit_lockit);
+}
+
+static int inode_storage_alloc(void *owner, struct bpf_local_storage_map *smap,
+ struct bpf_local_storage_elem *first_selem)
+{
+ struct bpf_local_storage *curr;
+ struct bpf_storage_blob *bsb;
+ struct inode *inode = owner;
+ int err;
+
+ bsb = bpf_inode(inode);
+ if (!bsb)
+ return -EINVAL;
+
+ curr = bpf_local_storage_alloc(smap);
+ if (!curr)
+ return -ENOMEM;
+
+ curr->inode = inode;
+
+ bpf_selem_link(curr, first_selem);
+ bpf_selem_link_map(smap, first_selem);
+
+ err = bpf_local_storage_publish(first_selem,
+ (struct bpf_local_storage **)&bsb->storage, curr);
+ if (err) {
+ kfree(curr);
+ return err;
+ }
+
+ return 0;
+}
+
+static struct bpf_local_storage_data *inode_storage_update(void *owner,
+ struct bpf_map *map,
+ void *value,
+ u64 map_flags)
+{
+ struct bpf_local_storage_data *old_sdata = NULL;
+ struct bpf_local_storage_elem *selem;
+ struct bpf_local_storage *local_storage;
+ struct bpf_local_storage_map *smap;
+ struct bpf_storage_blob *bsb;
+ struct inode *inode;
+ int err;
+
+ err = bpf_local_storage_check_update_flags(map, map_flags);
+ if (err)
+ return ERR_PTR(err);
+
+ inode = owner;
+ bsb = bpf_inode(inode);
+ local_storage = rcu_dereference(bsb->storage);
+ smap = (struct bpf_local_storage_map *)map;
+
+ if (!local_storage || hlist_empty(&local_storage->list)) {
+ /* Very first elem */
+ selem = map->ops->map_selem_alloc(smap, owner, value, !old_sdata);
+ if (!selem)
+ return ERR_PTR(-ENOMEM);
+
+ err = map->ops->map_local_storage_alloc(owner, smap, selem);
+ if (err) {
+ kfree(selem);
+ return ERR_PTR(err);
+ }
+
+ return SDATA(selem);
+ }
+
+ return bpf_local_storage_update(owner, map, local_storage, value,
+ map_flags);
+}
+
+
+void bpf_inode_storage_free(struct inode *inode)
+{
+ struct bpf_local_storage_elem *selem;
+ struct bpf_local_storage *local_storage;
+ bool free_inode_storage = false;
+ struct bpf_storage_blob *bsb;
+ struct hlist_node *n;
+
+ bsb = bpf_inode(inode);
+ if (!bsb)
+ return;
+
+ rcu_read_lock();
+
+ local_storage = rcu_dereference(bsb->storage);
+ if (!local_storage) {
+ rcu_read_unlock();
+ return;
+ }
+
+ /* Netiher the bpf_prog nor the bpf-map's syscall
+ * could be modifying the local_storage->list now.
+ * Thus, no elem can be added-to or deleted-from the
+ * local_storage->list by the bpf_prog or by the bpf-map's syscall.
+ *
+ * It is racing with bpf_local_storage_map_free() alone
+ * when unlinking elem from the local_storage->list and
+ * the map's bucket->list.
+ */
+ raw_spin_lock_bh(&local_storage->lock);
+ hlist_for_each_entry_safe(selem, n, &local_storage->list, snode) {
+ /* Always unlink from map before unlinking from
+ * local_storage.
+ */
+ bpf_selem_unlink_map(selem);
+ free_inode_storage =
+ bpf_selem_unlink(local_storage, selem, false);
+ }
+ raw_spin_unlock_bh(&local_storage->lock);
+ rcu_read_unlock();
+
+ /* free_inoode_storage should always be true as long as
+ * local_storage->list was non-empty.
+ */
+ if (free_inode_storage)
+ kfree_rcu(local_storage, rcu);
+}
+
+
+static void *bpf_inode_storage_lookup_elem(struct bpf_map *map, void *key)
+{
+ struct bpf_local_storage_data *sdata;
+ struct inode *inode;
+ int err = -EINVAL;
+
+ if (key) {
+ inode = *(struct inode **)(key);
+ sdata = inode_storage_lookup(inode, map, true);
+ return sdata ? sdata->data : NULL;
+ }
+
+ return ERR_PTR(err);
+}
+
+static int bpf_inode_storage_update_elem(struct bpf_map *map, void *key,
+ void *value, u64 map_flags)
+{
+ struct bpf_local_storage_data *sdata;
+ struct inode *inode;
+ int err = -EINVAL;
+
+ if (key) {
+ inode = *(struct inode **)(key);
+ sdata = map->ops->map_local_storage_update(inode, map, value,
+ map_flags);
+ return PTR_ERR_OR_ZERO(sdata);
+ }
+ return err;
+}
+
+static int inode_storage_delete(struct inode *inode, struct bpf_map *map)
+{
+ struct bpf_local_storage_data *sdata;
+
+ sdata = inode_storage_lookup(inode, map, false);
+ if (!sdata)
+ return -ENOENT;
+
+ bpf_selem_unlink_map_elem(SELEM(sdata));
+
+ return 0;
+}
+
+static int bpf_inode_storage_delete_elem(struct bpf_map *map, void *key)
+{
+ struct inode *inode;
+ int err = -EINVAL;
+
+ if (key) {
+ inode = *(struct inode **)(key);
+ err = inode_storage_delete(inode, map);
+ }
+
+ return err;
+}
+
+BPF_CALL_4(bpf_inode_storage_get, struct bpf_map *, map, struct inode *, inode,
+ void *, value, u64, flags)
+{
+ struct bpf_local_storage_data *sdata;
+
+ if (flags & ~(BPF_LOCAL_STORAGE_GET_F_CREATE))
+ return (unsigned long)NULL;
+
+ sdata = inode_storage_lookup(inode, map, true);
+ if (sdata)
+ return (unsigned long)sdata->data;
+
+ if (flags & BPF_LOCAL_STORAGE_GET_F_CREATE) {
+ sdata = inode_storage_update(inode, map, value, BPF_NOEXIST);
+ return IS_ERR(sdata) ?
+ (unsigned long)NULL : (unsigned long)sdata->data;
+ }
+
+ return (unsigned long)NULL;
+}
+
+BPF_CALL_2(bpf_inode_storage_delete,
+ struct bpf_map *, map, struct inode *, inode)
+{
+ return inode_storage_delete(inode, map);
+}
+
+static int notsupp_get_next_key(struct bpf_map *map, void *key,
+ void *next_key)
+{
+ return -ENOTSUPP;
+}
+
+DEFINE_BPF_STORAGE_CACHE(inode);
+
+static struct bpf_map *inode_storage_map_alloc(union bpf_attr *attr)
+{
+ struct bpf_local_storage_map *smap;
+
+ smap = bpf_local_storage_map_alloc(attr);
+ if (IS_ERR(smap))
+ return ERR_CAST(smap);
+
+ smap->cache_idx = cache_idx_get_inode();
+ return &smap->map;
+}
+
+static void inode_storage_map_free(struct bpf_map *map)
+{
+ struct bpf_local_storage_map *smap;
+
+ smap = (struct bpf_local_storage_map *)map;
+ cache_idx_free_inode(smap->cache_idx);
+ bpf_local_storage_map_free(smap);
+}
+
+static int inode_storage_map_btf_id;
+const struct bpf_map_ops inode_storage_map_ops = {
+ .map_alloc_check = bpf_local_storage_map_alloc_check,
+ .map_alloc = inode_storage_map_alloc,
+ .map_free = inode_storage_map_free,
+ .map_get_next_key = notsupp_get_next_key,
+ .map_lookup_elem = bpf_inode_storage_lookup_elem,
+ .map_update_elem = bpf_inode_storage_update_elem,
+ .map_delete_elem = bpf_inode_storage_delete_elem,
+ .map_check_btf = bpf_local_storage_map_check_btf,
+ .map_btf_name = "bpf_local_storage_map",
+ .map_btf_id = &inode_storage_map_btf_id,
+ .map_local_storage_alloc = inode_storage_alloc,
+ .map_selem_alloc = inode_selem_alloc,
+ .map_local_storage_update = inode_storage_update,
+ .map_local_storage_unlink = unlink_inode_storage,
+};
+
+static int bpf_inode_storage_get_btf_ids[4];
+const struct bpf_func_proto bpf_inode_storage_get_proto = {
+ .func = bpf_inode_storage_get,
+ .gpl_only = false,
+ .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL,
+ .arg1_type = ARG_CONST_MAP_PTR,
+ .arg2_type = ARG_PTR_TO_BTF_ID,
+ .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL,
+ .arg4_type = ARG_ANYTHING,
+ .btf_id = bpf_inode_storage_get_btf_ids,
+};
+
+static int bpf_inode_storage_delete_btf_ids[2];
+const struct bpf_func_proto bpf_inode_storage_delete_proto = {
+ .func = bpf_inode_storage_delete,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_CONST_MAP_PTR,
+ .arg2_type = ARG_PTR_TO_BTF_ID,
+ .btf_id = bpf_inode_storage_delete_btf_ids,
+};
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 156f51ffada2..3fc7586408f7 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -768,7 +768,8 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf,
if (map->map_type != BPF_MAP_TYPE_HASH &&
map->map_type != BPF_MAP_TYPE_ARRAY &&
map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE &&
- map->map_type != BPF_MAP_TYPE_SK_STORAGE)
+ map->map_type != BPF_MAP_TYPE_SK_STORAGE &&
+ map->map_type != BPF_MAP_TYPE_INODE_STORAGE)
return -ENOTSUPP;
if (map->spin_lock_off + sizeof(struct bpf_spin_lock) >
map->value_size) {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index b608185e1ffd..9080a62b583a 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -4164,6 +4164,11 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
func_id != BPF_FUNC_sk_storage_delete)
goto error;
break;
+ case BPF_MAP_TYPE_INODE_STORAGE:
+ if (func_id != BPF_FUNC_inode_storage_get &&
+ func_id != BPF_FUNC_inode_storage_delete)
+ goto error;
+ break;
default:
break;
}
@@ -4237,6 +4242,11 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
if (map->map_type != BPF_MAP_TYPE_SK_STORAGE)
goto error;
break;
+ case BPF_FUNC_inode_storage_get:
+ case BPF_FUNC_inode_storage_delete:
+ if (map->map_type != BPF_MAP_TYPE_INODE_STORAGE)
+ goto error;
+ break;
default:
break;
}
diff --git a/security/bpf/hooks.c b/security/bpf/hooks.c
index 32d32d485451..35f9b19259e5 100644
--- a/security/bpf/hooks.c
+++ b/security/bpf/hooks.c
@@ -3,6 +3,7 @@
/*
* Copyright (C) 2020 Google LLC.
*/
+#include <linux/bpf_local_storage.h>
#include <linux/lsm_hooks.h>
#include <linux/bpf_lsm.h>
@@ -11,6 +12,7 @@ static struct security_hook_list bpf_lsm_hooks[] __lsm_ro_after_init = {
LSM_HOOK_INIT(NAME, bpf_lsm_##NAME),
#include <linux/lsm_hook_defs.h>
#undef LSM_HOOK
+ LSM_HOOK_INIT(inode_free_security, bpf_inode_storage_free),
};
static int __init bpf_lsm_init(void)
@@ -20,7 +22,12 @@ static int __init bpf_lsm_init(void)
return 0;
}
+struct lsm_blob_sizes bpf_lsm_blob_sizes __lsm_ro_after_init = {
+ .lbs_inode = sizeof(struct bpf_storage_blob),
+};
+
DEFINE_LSM(bpf) = {
.name = "bpf",
.init = bpf_lsm_init,
+ .blobs = &bpf_lsm_blob_sizes
};
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 25b25aca1112..34cadc081a78 100644
--- a/tools/bpf/bpftool/bash-completion/bpftool
+++ b/tools/bpf/bpftool/bash-completion/bpftool
@@ -688,7 +688,8 @@ _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 1f3e831c4813..42fc442f4586 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -148,6 +148,7 @@ 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
@@ -3319,6 +3320,41 @@ union bpf_attr {
* A non-negative value equal to or less than *size* on success,
* or a negative error in case of failure.
*
+ * 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), \
@@ -3463,6 +3499,8 @@ union bpf_attr {
FN(skc_to_tcp_request_sock), \
FN(skc_to_udp6_sock), \
FN(get_task_stack), \
+ 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 10cd8d1891f5..b859558ce290 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;
--
2.27.0.389.gc38d7665816-goog
On Thu, Jul 09, 2020 at 12:12:36PM +0200, KP Singh wrote:
> From: KP Singh <[email protected]>
>
> Refactor the functionality in bpf_sk_storage.c so that concept of
> storage linked to kernel objects can be extended to other objects like
> inode, task_struct etc.
>
> bpf_sk_storage is updated to be bpf_local_storage with a union that
> contains a pointer to the owner object.
> The type of the
> bpf_local_storage can be determined using the newly added
> bpf_local_storage_type enum.
This is out dated.
>
> Each new local storage will still be a separate map and provide its own
> set of helpers. This allows for future object specific extensions and
> still share a lot of the underlying implementation.
Thanks for v4.
I do find it quite hard to follow by directly moving to
bpf_local_storage.c without doing all the renaming locally
at bpf_sk_storage.c first. I will try my best to follow.
There are some unnecessary name/convention change and function
folding that do not help on this side either. Please keep them
unchanged for now and they can use another patch in the future if needed.
It will be easier to have a mostly one to one naming change
and please mention them in the commit message.
[ ... ]
> diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h
> new file mode 100644
> index 000000000000..605b81f2f806
> --- /dev/null
> +++ b/include/linux/bpf_local_storage.h
> @@ -0,0 +1,175 @@
> +/* SPDX-License-Identifier: GPL-2.0 */
> +/*
> + * Copyright (c) 2019 Facebook
> + * Copyright 2020 Google LLC.
> + */
> +
> +#ifndef _BPF_LOCAL_STORAGE_H
> +#define _BPF_LOCAL_STORAGE_H
> +
> +#include <linux/bpf.h>
> +#include <linux/rculist.h>
> +#include <linux/list.h>
> +#include <linux/hash.h>
> +#include <linux/types.h>
> +#include <uapi/linux/btf.h>
> +
> +#define LOCAL_STORAGE_CREATE_FLAG_MASK \
> + (BPF_F_NO_PREALLOC | BPF_F_CLONE)
> +
> +struct bucket {
Since it is in a .h, it can use a more specific name.
May be bpf_local_storage_map_bucket.
> + struct hlist_head list;
> + raw_spinlock_t lock;
> +};
> +
[ ... ]
> +struct bpf_local_storage {
> + struct bpf_local_storage_data __rcu *cache[BPF_STORAGE_CACHE_SIZE];
> + struct hlist_head list; /* List of bpf_local_storage_elem */
> + /* The object that owns the the above "list" of
> + * bpf_local_storage_elem
> + */
> + union {
> + struct sock *sk;
Instead of having a specific pointer type and then union them here,
would one "void *owner;" work as good?
> + };
> + struct rcu_head rcu;
> + raw_spinlock_t lock; /* Protect adding/removing from the "list" */
> +};
> +
> +/* Helper functions for bpf_local_storage */
[ ... ]
> diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c
> new file mode 100644
> index 000000000000..c818eb6f8261
> --- /dev/null
> +++ b/kernel/bpf/bpf_local_storage.c
> @@ -0,0 +1,517 @@
> +// SPDX-License-Identifier: GPL-2.0
> +/*
> + * Copyright (c) 2019 Facebook
> + * Copyright 2020 Google LLC.
> + */
> +
> +#include <linux/rculist.h>
> +#include <linux/list.h>
> +#include <linux/hash.h>
> +#include <linux/types.h>
> +#include <linux/spinlock.h>
> +#include <linux/bpf.h>
> +#include <linux/bpf_local_storage.h>
> +#include <net/sock.h>
> +#include <uapi/linux/sock_diag.h>
> +#include <uapi/linux/btf.h>
> +
> +#define SELEM(_SDATA) \
> + container_of((_SDATA), struct bpf_local_storage_elem, sdata)
> +#define SDATA(_SELEM) (&(_SELEM)->sdata)
> +
> +static struct bucket *select_bucket(struct bpf_local_storage_map *smap,
> + struct bpf_local_storage_elem *selem)
> +{
> + return &smap->buckets[hash_ptr(selem, smap->bucket_log)];
> +}
> +
> +static bool selem_linked_to_node(const struct bpf_local_storage_elem *selem)
The suffix was selem_linked_to"_sk" and it is changed to "_node" here.
However, the latter bpf_selem_unlink has removed the _sk suffix instead.
Instead of _to_node, it is linked to storage. How about
selem_linked_to_storage()?
> +{
> + return !hlist_unhashed(&selem->snode);
> +}
> +
> +static bool selem_linked_to_map(const struct bpf_local_storage_elem *selem)
> +{
> + return !hlist_unhashed(&selem->map_node);
> +}
> +
> +struct bpf_local_storage_elem *
> +bpf_selem_alloc(struct bpf_local_storage_map *smap, void *value)
> +{
> + struct bpf_local_storage_elem *selem;
> +
> + selem = kzalloc(smap->elem_size, GFP_ATOMIC | __GFP_NOWARN);
> + if (selem) {
> + if (value)
> + memcpy(SDATA(selem)->data, value, smap->map.value_size);
> + return selem;
> + }
> +
> + return NULL;
> +}
> +
> +/* local_storage->lock must be held and selem->local_storage == local_storage.
> + * The caller must ensure selem->smap is still valid to be
> + * dereferenced for its smap->elem_size and smap->cache_idx.
> + *
> + * uncharge_omem is only relevant for BPF_MAP_TYPE_SK_STORAGE.
> + */
> +bool bpf_selem_unlink(struct bpf_local_storage *local_storage,
> + struct bpf_local_storage_elem *selem, bool uncharge_omem)
It is originated from __selem_unlink_sk() which does not take the
local_storage->lock.
How about keeping the _sk suffix here somehow to distinguish it from
unlink_map?
was __selem_unlink_sk => bpf_selem_unlink_storage()?
> +{
> + struct bpf_local_storage_map *smap;
> + bool free_local_storage;
> +
> + smap = rcu_dereference(SDATA(selem)->smap);
> + free_local_storage = hlist_is_singular_node(&selem->snode,
> + &local_storage->list);
> +
> + /* local_storage is not freed now. local_storage->lock is
> + * still held and raw_spin_unlock_bh(&local_storage->lock)
> + * will be done by the caller.
> + * Although the unlock will be done under
> + * rcu_read_lock(), it is more intutivie to
> + * read if kfree_rcu(local_storage, rcu) is done
> + * after the raw_spin_unlock_bh(&local_storage->lock).
> + *
> + * Hence, a "bool free_local_storage" is returned
> + * to the caller which then calls the kfree_rcu()
> + * after unlock.
> + */
> + if (free_local_storage)
> + smap->map.ops->map_local_storage_unlink(local_storage,
> + uncharge_omem);
> +
> + hlist_del_init_rcu(&selem->snode);
> + if (rcu_access_pointer(local_storage->cache[smap->cache_idx]) ==
> + SDATA(selem))
> + RCU_INIT_POINTER(local_storage->cache[smap->cache_idx], NULL);
> +
> + kfree_rcu(selem, rcu);
> +
> + return free_local_storage;
> +}
> +
> +void bpf_selem_link(struct bpf_local_storage *local_storage,
> + struct bpf_local_storage_elem *selem)
was __selem_link_sk() => bpf_selem_link_storage()
> +{
> + RCU_INIT_POINTER(selem->local_storage, local_storage);
> + hlist_add_head(&selem->snode, &local_storage->list);
> +}
> +
> +void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem)
> +{
> + struct bpf_local_storage_map *smap;
> + struct bucket *b;
> +
> + if (unlikely(!selem_linked_to_map(selem)))
> + /* selem has already be unlinked from smap */
> + return;
> +
> + smap = rcu_dereference(SDATA(selem)->smap);
> + b = select_bucket(smap, selem);
> + raw_spin_lock_bh(&b->lock);
> + if (likely(selem_linked_to_map(selem)))
> + hlist_del_init_rcu(&selem->map_node);
> + raw_spin_unlock_bh(&b->lock);
> +}
> +
> +void bpf_selem_link_map(struct bpf_local_storage_map *smap,
> + struct bpf_local_storage_elem *selem)
> +{
> + struct bucket *b = select_bucket(smap, selem);
> +
> + raw_spin_lock_bh(&b->lock);
> + RCU_INIT_POINTER(SDATA(selem)->smap, smap);
> + hlist_add_head_rcu(&selem->map_node, &b->list);
> + raw_spin_unlock_bh(&b->lock);
> +}
> +
> +void bpf_selem_unlink_map_elem(struct bpf_local_storage_elem *selem)
How about keep the original no-suffix to mean unlink from both map and storage.
was selem_unlink() => bpf_selem_unlink()
> +{
> + struct bpf_local_storage *local_storage;
> + bool free_local_storage = false;
> +
> + /* Always unlink from map before unlinking from local_storage
> + * because selem will be freed after successfully unlinked from
> + * the local_storage.
> + */
> + bpf_selem_unlink_map(selem);
> +
> + if (unlikely(!selem_linked_to_node(selem)))
> + /* selem has already been unlinked from its owner */
> + return;
> +
> + local_storage = rcu_dereference(selem->local_storage);
> + raw_spin_lock_bh(&local_storage->lock);
> + if (likely(selem_linked_to_node(selem)))
> + free_local_storage =
> + bpf_selem_unlink(local_storage, selem, true);
> + raw_spin_unlock_bh(&local_storage->lock);
> +
> + if (free_local_storage)
> + kfree_rcu(local_storage, rcu);
Part of these is folding the selem_unlink_sk() into here.
Please don't do it for now.
Keep them in __bpf_selem_unlink_storage(). Hence, we only
need to remember the original "__" meaning is flipped
from unlock to lock.
> +}
> +
[ ... ]
> diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
> index 6f921c4ddc2c..a2b00a09d843 100644
> --- a/net/core/bpf_sk_storage.c
> +++ b/net/core/bpf_sk_storage.c
[ ... ]
> +static void unlink_sk_storage(struct bpf_local_storage *local_storage,
> bool uncharge_omem)
> {
> - struct bpf_sk_storage_map *smap;
> - bool free_sk_storage;
> - struct sock *sk;
> -
> - smap = rcu_dereference(SDATA(selem)->smap);
> - sk = sk_storage->sk;
> + struct sock *sk = local_storage->sk;
>
> - /* All uncharging on sk->sk_omem_alloc must be done first.
> - * sk may be freed once the last selem is unlinked from sk_storage.
> - */
> if (uncharge_omem)
> - atomic_sub(smap->elem_size, &sk->sk_omem_alloc);
Where is smap->elem_size uncharged?
> -
> - free_sk_storage = hlist_is_singular_node(&selem->snode,
> - &sk_storage->list);
> - if (free_sk_storage) {
> - atomic_sub(sizeof(struct bpf_sk_storage), &sk->sk_omem_alloc);
> - sk_storage->sk = NULL;
> - /* After this RCU_INIT, sk may be freed and cannot be used */
> - RCU_INIT_POINTER(sk->sk_bpf_storage, NULL);
> -
> - /* sk_storage is not freed now. sk_storage->lock is
> - * still held and raw_spin_unlock_bh(&sk_storage->lock)
> - * will be done by the caller.
> - *
> - * Although the unlock will be done under
> - * rcu_read_lock(), it is more intutivie to
> - * read if kfree_rcu(sk_storage, rcu) is done
> - * after the raw_spin_unlock_bh(&sk_storage->lock).
> - *
> - * Hence, a "bool free_sk_storage" is returned
> - * to the caller which then calls the kfree_rcu()
> - * after unlock.
> - */
> - }
> - hlist_del_init_rcu(&selem->snode);
> - if (rcu_access_pointer(sk_storage->cache[smap->cache_idx]) ==
> - SDATA(selem))
> - RCU_INIT_POINTER(sk_storage->cache[smap->cache_idx], NULL);
> -
> - kfree_rcu(selem, rcu);
> -
> - return free_sk_storage;
> -}
[ ... ]
> +static struct bpf_local_storage_data *
> +sk_storage_update(void *owner, struct bpf_map *map, void *value, u64 map_flags)
> {
> - struct bpf_sk_storage_data *old_sdata = NULL;
> - struct bpf_sk_storage_elem *selem;
> - struct bpf_sk_storage *sk_storage;
> - struct bpf_sk_storage_map *smap;
> + struct bpf_local_storage_data *old_sdata = NULL;
> + struct bpf_local_storage_elem *selem;
> + struct bpf_local_storage *local_storage;
> + struct bpf_local_storage_map *smap;
> + struct sock *sk;
> int err;
>
> - /* BPF_EXIST and BPF_NOEXIST cannot be both set */
> - if (unlikely((map_flags & ~BPF_F_LOCK) > BPF_EXIST) ||
> - /* BPF_F_LOCK can only be used in a value with spin_lock */
> - unlikely((map_flags & BPF_F_LOCK) && !map_value_has_spin_lock(map)))
> - return ERR_PTR(-EINVAL);
> + err = bpf_local_storage_check_update_flags(map, map_flags);
> + if (err)
> + return ERR_PTR(err);
>
> - smap = (struct bpf_sk_storage_map *)map;
> - sk_storage = rcu_dereference(sk->sk_bpf_storage);
> - if (!sk_storage || hlist_empty(&sk_storage->list)) {
> - /* Very first elem for this sk */
> - err = check_flags(NULL, map_flags);
> - if (err)
> - return ERR_PTR(err);
> + sk = owner;
> + local_storage = rcu_dereference(sk->sk_bpf_storage);
> + smap = (struct bpf_local_storage_map *)map;
>
> - selem = selem_alloc(smap, sk, value, true);
> + if (!local_storage || hlist_empty(&local_storage->list)) {
> + /* Very first elem */
> + selem = map->ops->map_selem_alloc(smap, owner, value, !old_sdata);
hmmm... If this map_selem_alloc is directly called here in sk_storage instead
of the common local_storage, does it have to be in map_ops?
> if (!selem)
> return ERR_PTR(-ENOMEM);
>
> - err = sk_storage_alloc(sk, smap, selem);
> + err = map->ops->map_local_storage_alloc(owner, smap, selem);
> if (err) {
> kfree(selem);
> atomic_sub(smap->elem_size, &sk->sk_omem_alloc);
[ ... ]
> -static void bpf_sk_storage_map_free(struct bpf_map *map)
> +static void *bpf_sk_storage_lookup_elem(struct bpf_map *map, void *key)
Hmmm... this change here... keep scrolling down and down .... :)
> {
> - struct bpf_sk_storage_elem *selem;
> - struct bpf_sk_storage_map *smap;
> - struct bucket *b;
> - unsigned int i;
> -
> - smap = (struct bpf_sk_storage_map *)map;
> -
> - cache_idx_free(smap->cache_idx);
> -
> - /* Note that this map might be concurrently cloned from
> - * bpf_sk_storage_clone. Wait for any existing bpf_sk_storage_clone
> - * RCU read section to finish before proceeding. New RCU
> - * read sections should be prevented via bpf_map_inc_not_zero.
> - */
> - synchronize_rcu();
> -
> - /* bpf prog and the userspace can no longer access this map
> - * now. No new selem (of this map) can be added
> - * to the sk->sk_bpf_storage or to the map bucket's list.
> - *
> - * The elem of this map can be cleaned up here
> - * or
> - * by bpf_sk_storage_free() during __sk_destruct().
> - */
> - for (i = 0; i < (1U << smap->bucket_log); i++) {
> - b = &smap->buckets[i];
> -
> - rcu_read_lock();
> - /* No one is adding to b->list now */
> - while ((selem = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(&b->list)),
> - struct bpf_sk_storage_elem,
> - map_node))) {
> - selem_unlink(selem);
> - cond_resched_rcu();
> - }
> - rcu_read_unlock();
> - }
> -
> - /* bpf_sk_storage_free() may still need to access the map.
> - * e.g. bpf_sk_storage_free() has unlinked selem from the map
> - * which then made the above while((selem = ...)) loop
> - * exited immediately.
> - *
> - * However, the bpf_sk_storage_free() still needs to access
> - * the smap->elem_size to do the uncharging in
> - * __selem_unlink_sk().
> - *
> - * Hence, wait another rcu grace period for the
> - * bpf_sk_storage_free() to finish.
> - */
> - synchronize_rcu();
> -
> - kvfree(smap->buckets);
> - kfree(map);
> -}
> -
> -/* U16_MAX is much more than enough for sk local storage
> - * considering a tcp_sock is ~2k.
> - */
> -#define MAX_VALUE_SIZE \
> - min_t(u32, \
> - (KMALLOC_MAX_SIZE - MAX_BPF_STACK - sizeof(struct bpf_sk_storage_elem)), \
> - (U16_MAX - sizeof(struct bpf_sk_storage_elem)))
> -
> -static int bpf_sk_storage_map_alloc_check(union bpf_attr *attr)
> -{
> - if (attr->map_flags & ~SK_STORAGE_CREATE_FLAG_MASK ||
> - !(attr->map_flags & BPF_F_NO_PREALLOC) ||
> - attr->max_entries ||
> - attr->key_size != sizeof(int) || !attr->value_size ||
> - /* Enforce BTF for userspace sk dumping */
> - !attr->btf_key_type_id || !attr->btf_value_type_id)
> - return -EINVAL;
> -
> - if (!bpf_capable())
> - return -EPERM;
> -
> - if (attr->value_size > MAX_VALUE_SIZE)
> - return -E2BIG;
> -
> - return 0;
> -}
> -
> -static struct bpf_map *bpf_sk_storage_map_alloc(union bpf_attr *attr)
> -{
> - struct bpf_sk_storage_map *smap;
> - unsigned int i;
> - u32 nbuckets;
> - u64 cost;
> - int ret;
> -
> - smap = kzalloc(sizeof(*smap), GFP_USER | __GFP_NOWARN);
> - if (!smap)
> - return ERR_PTR(-ENOMEM);
> - bpf_map_init_from_attr(&smap->map, attr);
> -
> - nbuckets = roundup_pow_of_two(num_possible_cpus());
> - /* Use at least 2 buckets, select_bucket() is undefined behavior with 1 bucket */
> - nbuckets = max_t(u32, 2, nbuckets);
> - smap->bucket_log = ilog2(nbuckets);
> - cost = sizeof(*smap->buckets) * nbuckets + sizeof(*smap);
> -
> - ret = bpf_map_charge_init(&smap->map.memory, cost);
> - if (ret < 0) {
> - kfree(smap);
> - return ERR_PTR(ret);
> - }
> -
> - smap->buckets = kvcalloc(sizeof(*smap->buckets), nbuckets,
> - GFP_USER | __GFP_NOWARN);
> - if (!smap->buckets) {
> - bpf_map_charge_finish(&smap->map.memory);
> - kfree(smap);
> - return ERR_PTR(-ENOMEM);
> - }
> -
> - for (i = 0; i < nbuckets; i++) {
> - INIT_HLIST_HEAD(&smap->buckets[i].list);
> - raw_spin_lock_init(&smap->buckets[i].lock);
> - }
> -
> - smap->elem_size = sizeof(struct bpf_sk_storage_elem) + attr->value_size;
> - smap->cache_idx = cache_idx_get();
> -
> - return &smap->map;
> -}
> -
> -static int notsupp_get_next_key(struct bpf_map *map, void *key,
> - void *next_key)
> -{
> - return -ENOTSUPP;
> -}
> -
> -static int bpf_sk_storage_map_check_btf(const struct bpf_map *map,
> - const struct btf *btf,
> - const struct btf_type *key_type,
> - const struct btf_type *value_type)
> -{
> - u32 int_data;
> -
> - if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT)
> - return -EINVAL;
> -
> - int_data = *(u32 *)(key_type + 1);
> - if (BTF_INT_BITS(int_data) != 32 || BTF_INT_OFFSET(int_data))
> - return -EINVAL;
> -
> - return 0;
> -}
> -
> -static void *bpf_fd_sk_storage_lookup_elem(struct bpf_map *map, void *key)
.... finally got it :p
> -{
> - struct bpf_sk_storage_data *sdata;
> + struct bpf_local_storage_data *sdata;
> struct socket *sock;
> - int fd, err;
> + int fd, err = -EINVAL;
This is a bug fix or to suppress compiler warning?
>
> fd = *(int *)key;
> sock = sockfd_lookup(fd, &err);
> @@ -752,17 +223,18 @@ static void *bpf_fd_sk_storage_lookup_elem(struct bpf_map *map, void *key)
> return ERR_PTR(err);
> }
>
[ ... ]
> static int sk_storage_map_btf_id;
> const struct bpf_map_ops sk_storage_map_ops = {
> - .map_alloc_check = bpf_sk_storage_map_alloc_check,
> - .map_alloc = bpf_sk_storage_map_alloc,
> - .map_free = bpf_sk_storage_map_free,
> + .map_alloc_check = bpf_local_storage_map_alloc_check,
> + .map_alloc = sk_storage_map_alloc,
> + .map_free = sk_storage_map_free,
> .map_get_next_key = notsupp_get_next_key,
> - .map_lookup_elem = bpf_fd_sk_storage_lookup_elem,
> - .map_update_elem = bpf_fd_sk_storage_update_elem,
> - .map_delete_elem = bpf_fd_sk_storage_delete_elem,
Why this "_fd_" name change?
> - .map_check_btf = bpf_sk_storage_map_check_btf,
> - .map_btf_name = "bpf_sk_storage_map",
> + .map_lookup_elem = bpf_sk_storage_lookup_elem,
> + .map_update_elem = bpf_sk_storage_update_elem,
> + .map_delete_elem = bpf_sk_storage_delete_elem,
> + .map_check_btf = bpf_local_storage_map_check_btf,
> + .map_btf_name = "bpf_local_storage_map",
> .map_btf_id = &sk_storage_map_btf_id,
> + .map_local_storage_alloc = sk_storage_alloc,
> + .map_selem_alloc = sk_selem_alloc,
> + .map_local_storage_update = sk_storage_update,
> + .map_local_storage_unlink = unlink_sk_storage,
> };
On Thu, Jul 09, 2020 at 12:12:37PM +0200, KP Singh wrote:
> From: KP Singh <[email protected]>
>
> 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 <[email protected]>
[ ... ]
> +static void *bpf_inode_storage_lookup_elem(struct bpf_map *map, void *key)
> +{
> + struct bpf_local_storage_data *sdata;
> + struct inode *inode;
> + int err = -EINVAL;
> +
> + if (key) {
> + inode = *(struct inode **)(key);
The bpf_inode_storage_lookup_elem() here and the (update|delete)_elem() below
are called from the userspace syscall. How the userspace may provide this key?
> + sdata = inode_storage_lookup(inode, map, true);
> + return sdata ? sdata->data : NULL;
> + }
> +
> + return ERR_PTR(err);
> +}
> +
> +static int bpf_inode_storage_update_elem(struct bpf_map *map, void *key,
> + void *value, u64 map_flags)
> +{
> + struct bpf_local_storage_data *sdata;
> + struct inode *inode;
> + int err = -EINVAL;
> +
> + if (key) {
> + inode = *(struct inode **)(key);
> + sdata = map->ops->map_local_storage_update(inode, map, value,
> + map_flags);
> + return PTR_ERR_OR_ZERO(sdata);
> + }
> + return err;
> +}
> +
> +static int inode_storage_delete(struct inode *inode, struct bpf_map *map)
> +{
> + struct bpf_local_storage_data *sdata;
> +
> + sdata = inode_storage_lookup(inode, map, false);
> + if (!sdata)
> + return -ENOENT;
> +
> + bpf_selem_unlink_map_elem(SELEM(sdata));
> +
> + return 0;
> +}
> +
> +static int bpf_inode_storage_delete_elem(struct bpf_map *map, void *key)
> +{
> + struct inode *inode;
> + int err = -EINVAL;
> +
> + if (key) {
> + inode = *(struct inode **)(key);
> + err = inode_storage_delete(inode, map);
> + }
> +
> + return err;
> +}
> +
[ ... ]
> +static int inode_storage_map_btf_id;
> +const struct bpf_map_ops inode_storage_map_ops = {
> + .map_alloc_check = bpf_local_storage_map_alloc_check,
> + .map_alloc = inode_storage_map_alloc,
> + .map_free = inode_storage_map_free,
> + .map_get_next_key = notsupp_get_next_key,
> + .map_lookup_elem = bpf_inode_storage_lookup_elem,
> + .map_update_elem = bpf_inode_storage_update_elem,
> + .map_delete_elem = bpf_inode_storage_delete_elem,
> + .map_check_btf = bpf_local_storage_map_check_btf,
> + .map_btf_name = "bpf_local_storage_map",
> + .map_btf_id = &inode_storage_map_btf_id,
> + .map_local_storage_alloc = inode_storage_alloc,
> + .map_selem_alloc = inode_selem_alloc,
> + .map_local_storage_update = inode_storage_update,
> + .map_local_storage_unlink = unlink_inode_storage,
> +};
> +
On 15-Jul 14:57, Martin KaFai Lau wrote:
> On Thu, Jul 09, 2020 at 12:12:37PM +0200, KP Singh wrote:
> > From: KP Singh <[email protected]>
> >
> > 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 <[email protected]>
>
> [ ... ]
>
>
> > +static void *bpf_inode_storage_lookup_elem(struct bpf_map *map, void *key)
> > +{
> > + struct bpf_local_storage_data *sdata;
> > + struct inode *inode;
> > + int err = -EINVAL;
> > +
> > + if (key) {
> > + inode = *(struct inode **)(key);
> The bpf_inode_storage_lookup_elem() here and the (update|delete)_elem() below
> are called from the userspace syscall. How the userspace may provide this key?
I realized this when I replied about the _fd_ name in the sk helpers.
I am going to mark them as unsupported for now for inodes.
We could, probably and separately, use a combination of the device
and inode number as a key from userspace.
- KP
>
> > + sdata = inode_storage_lookup(inode, map, true);
> > + return sdata ? sdata->data : NULL;
> > + }
> > +
> > + return ERR_PTR(err);
> > +}
> > +
> > +static int bpf_inode_storage_update_elem(struct bpf_map *map, void *key,
> > + void *value, u64 map_flags)
> > +{
> > + struct bpf_local_storage_data *sdata;
> > + struct inode *inode;
> > + int err = -EINVAL;
> > +
> > + if (key) {
> > + inode = *(struct inode **)(key);
> > + sdata = map->ops->map_local_storage_update(inode, map, value,
> > + map_flags);
> > + return PTR_ERR_OR_ZERO(sdata);
> > + }
> > + return err;
> > +}
> > +
> > +static int inode_storage_delete(struct inode *inode, struct bpf_map *map)
> > +{
> > + struct bpf_local_storage_data *sdata;
> > +
> > + sdata = inode_storage_lookup(inode, map, false);
> > + if (!sdata)
> > + return -ENOENT;
> > +
> > + bpf_selem_unlink_map_elem(SELEM(sdata));
> > +
> > + return 0;
> > +}
> > +
> > +static int bpf_inode_storage_delete_elem(struct bpf_map *map, void *key)
> > +{
> > + struct inode *inode;
> > + int err = -EINVAL;
> > +
> > + if (key) {
> > + inode = *(struct inode **)(key);
> > + err = inode_storage_delete(inode, map);
> > + }
> > +
> > + return err;
> > +}
> > +
>
> [ ... ]
>
> > +static int inode_storage_map_btf_id;
> > +const struct bpf_map_ops inode_storage_map_ops = {
> > + .map_alloc_check = bpf_local_storage_map_alloc_check,
> > + .map_alloc = inode_storage_map_alloc,
> > + .map_free = inode_storage_map_free,
> > + .map_get_next_key = notsupp_get_next_key,
> > + .map_lookup_elem = bpf_inode_storage_lookup_elem,
> > + .map_update_elem = bpf_inode_storage_update_elem,
> > + .map_delete_elem = bpf_inode_storage_delete_elem,
> > + .map_check_btf = bpf_local_storage_map_check_btf,
> > + .map_btf_name = "bpf_local_storage_map",
> > + .map_btf_id = &inode_storage_map_btf_id,
> > + .map_local_storage_alloc = inode_storage_alloc,
> > + .map_selem_alloc = inode_selem_alloc,
> > + .map_local_storage_update = inode_storage_update,
> > + .map_local_storage_unlink = unlink_inode_storage,
> > +};
> > +
Hi KP,
I love your patch! Perhaps something to improve:
[auto build test WARNING on bpf-next/master]
url: https://github.com/0day-ci/linux/commits/KP-Singh/Generalizing-bpf_local_storage/20200709-181906
base: https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git master
config: s390-randconfig-s032-20200719 (attached as .config)
compiler: s390-linux-gcc (GCC) 9.3.0
reproduce:
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
chmod +x ~/bin/make.cross
# apt-get install sparse
# sparse version: v0.6.2-49-g707c5017-dirty
# save the attached .config to linux build tree
COMPILER_INSTALL_PATH=$HOME/0day COMPILER=gcc-9.3.0 make.cross C=1 CF='-fdiagnostic-prefix -D__CHECK_ENDIAN__' ARCH=s390
If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot <[email protected]>
sparse warnings: (new ones prefixed by >>)
>> kernel/bpf/bpf_local_storage.c:237:16: sparse: sparse: non size-preserving integer to pointer cast
vim +237 kernel/bpf/bpf_local_storage.c
221
222 /* Publish local_storage to the address. This is used because we are already
223 * in a region where we cannot grab a lock on the object owning the storage (
224 * (e.g sk->sk_lock). Hence, atomic ops is used.
225 *
226 * From now on, the addr pointer is protected
227 * by the local_storage->lock. Hence, upon freeing,
228 * the local_storage->lock must be held before unlinking the storage from the
229 * owner.
230 */
231 int bpf_local_storage_publish(struct bpf_local_storage_elem *first_selem,
232 struct bpf_local_storage **addr,
233 struct bpf_local_storage *curr)
234 {
235 struct bpf_local_storage *prev;
236
> 237 prev = cmpxchg(addr, NULL, curr);
238 if (unlikely(prev)) {
239 /* Note that even first_selem was linked to smap's
240 * bucket->list, first_selem can be freed immediately
241 * (instead of kfree_rcu) because
242 * bpf_local_storage_map_free() does a
243 * synchronize_rcu() before walking the bucket->list.
244 * Hence, no one is accessing selem from the
245 * bucket->list under rcu_read_lock().
246 */
247 bpf_selem_unlink_map(first_selem);
248 return -EAGAIN;
249 }
250
251 return 0;
252 }
253
---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/[email protected]
On 16-Jul 00:59, KP Singh wrote:
> On 15-Jul 14:57, Martin KaFai Lau wrote:
> > On Thu, Jul 09, 2020 at 12:12:37PM +0200, KP Singh wrote:
> > > From: KP Singh <[email protected]>
> > >
> > > 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 <[email protected]>
> >
> > [ ... ]
> >
> >
> > > +static void *bpf_inode_storage_lookup_elem(struct bpf_map *map, void *key)
> > > +{
> > > + struct bpf_local_storage_data *sdata;
> > > + struct inode *inode;
> > > + int err = -EINVAL;
> > > +
> > > + if (key) {
> > > + inode = *(struct inode **)(key);
> > The bpf_inode_storage_lookup_elem() here and the (update|delete)_elem() below
> > are called from the userspace syscall. How the userspace may provide this key?
>
> I realized this when I replied about the _fd_ name in the sk helpers.
> I am going to mark them as unsupported for now for inodes.
>
> We could, probably and separately, use a combination of the device
> and inode number as a key from userspace.
I actually implemented these as:
static int bpf_fd_inode_storage_delete_elem(struct bpf_map *map, void *key)
{
struct file *f;
int fd;
fd = *(int *)key;
f = fcheck(fd);
if (!f)
return -EINVAL;
return inode_storage_delete(f->f_inode, map);
}
This keeps it similar to sk_storage and the userspace can just pass an
fd.
- KP
>
> - KP
>
> >
> > > + sdata = inode_storage_lookup(inode, map, true);
> > > + return sdata ? sdata->data : NULL;
> > > + }
> > > +
> > > + return ERR_PTR(err);
> > > +}
> > > +
> > > +static int bpf_inode_storage_update_elem(struct bpf_map *map, void *key,
> > > + void *value, u64 map_flags)
> > > +{
> > > + struct bpf_local_storage_data *sdata;
> > > + struct inode *inode;
> > > + int err = -EINVAL;
> > > +
> > > + if (key) {
> > > + inode = *(struct inode **)(key);
> > > + sdata = map->ops->map_local_storage_update(inode, map, value,
> > > + map_flags);
> > > + return PTR_ERR_OR_ZERO(sdata);
> > > + }
> > > + return err;
> > > +}
> > > +
> > > +static int inode_storage_delete(struct inode *inode, struct bpf_map *map)
> > > +{
> > > + struct bpf_local_storage_data *sdata;
> > > +
> > > + sdata = inode_storage_lookup(inode, map, false);
> > > + if (!sdata)
> > > + return -ENOENT;
> > > +
> > > + bpf_selem_unlink_map_elem(SELEM(sdata));
> > > +
> > > + return 0;
> > > +}
> > > +
> > > +static int bpf_inode_storage_delete_elem(struct bpf_map *map, void *key)
> > > +{
> > > + struct inode *inode;
> > > + int err = -EINVAL;
> > > +
> > > + if (key) {
> > > + inode = *(struct inode **)(key);
> > > + err = inode_storage_delete(inode, map);
> > > + }
> > > +
> > > + return err;
> > > +}
> > > +
> >
> > [ ... ]
> >
> > > +static int inode_storage_map_btf_id;
> > > +const struct bpf_map_ops inode_storage_map_ops = {
> > > + .map_alloc_check = bpf_local_storage_map_alloc_check,
> > > + .map_alloc = inode_storage_map_alloc,
> > > + .map_free = inode_storage_map_free,
> > > + .map_get_next_key = notsupp_get_next_key,
> > > + .map_lookup_elem = bpf_inode_storage_lookup_elem,
> > > + .map_update_elem = bpf_inode_storage_update_elem,
> > > + .map_delete_elem = bpf_inode_storage_delete_elem,
> > > + .map_check_btf = bpf_local_storage_map_check_btf,
> > > + .map_btf_name = "bpf_local_storage_map",
> > > + .map_btf_id = &inode_storage_map_btf_id,
> > > + .map_local_storage_alloc = inode_storage_alloc,
> > > + .map_selem_alloc = inode_selem_alloc,
> > > + .map_local_storage_update = inode_storage_update,
> > > + .map_local_storage_unlink = unlink_inode_storage,
> > > +};
> > > +