Skip to content

L
linux
Commit 1f00d375 authored by KP Singh's avatar KP Singh Committed by Alexei Starovoitov
Browse files
Options

bpf: Renames in preparation for bpf_local_storage 

A purely mechanical change to split the renaming from the actual
generalization.

Flags/consts:

  SK_STORAGE_CREATE_FLAG_MASK	BPF_LOCAL_STORAGE_CREATE_FLAG_MASK
  BPF_SK_STORAGE_CACHE_SIZE	BPF_LOCAL_STORAGE_CACHE_SIZE
  MAX_VALUE_SIZE		BPF_LOCAL_STORAGE_MAX_VALUE_SIZE

Structs:

  bucket			bpf_local_storage_map_bucket
  bpf_sk_storage_map		bpf_local_storage_map
  bpf_sk_storage_data		bpf_local_storage_data
  bpf_sk_storage_elem		bpf_local_storage_elem
  bpf_sk_storage		bpf_local_storage

The "sk" member in bpf_local_storage is also updated to "owner"
in preparation for changing the type to void * in a subsequent patch.

Functions:

  selem_linked_to_sk			selem_linked_to_storage
  selem_alloc				bpf_selem_alloc
  __selem_unlink_sk			bpf_selem_unlink_storage_nolock
  __selem_link_sk			bpf_selem_link_storage_nolock
  selem_unlink_sk			__bpf_selem_unlink_storage
  sk_storage_update			bpf_local_storage_update
  __sk_storage_lookup			bpf_local_storage_lookup
  bpf_sk_storage_map_free		bpf_local_storage_map_free
  bpf_sk_storage_map_alloc		bpf_local_storage_map_alloc
  bpf_sk_storage_map_alloc_check	bpf_local_storage_map_alloc_check
  bpf_sk_storage_map_check_btf		bpf_local_storage_map_check_btf
Signed-off-by: default avatarKP Singh <kpsingh@google.com>
Signed-off-by: default avatarAlexei Starovoitov <ast@kernel.org>
Acked-by: default avatarMartin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20200825182919.1118197-2-kpsingh@chromium.org
parent 0fcdfffe
Show whitespace changes
Inline Side-by-side
Showing with 255 additions and 243 deletions
include/net/sock.h
View file @ 1f00d375
...@@ -246,7 +246,7 @@ struct sock_common { ...@@ -246,7 +246,7 @@ struct sock_common {
/* public: */ /* public: */
}; };
struct bpf_sk_storage; struct bpf_local_storage;
/** /**
* struct sock - network layer representation of sockets * struct sock - network layer representation of sockets
...@@ -517,7 +517,7 @@ struct sock { ...@@ -517,7 +517,7 @@ struct sock {
void (*sk_destruct)(struct sock *sk); void (*sk_destruct)(struct sock *sk);
struct sock_reuseport __rcu *sk_reuseport_cb; struct sock_reuseport __rcu *sk_reuseport_cb;
#ifdef CONFIG_BPF_SYSCALL #ifdef CONFIG_BPF_SYSCALL
struct bpf_sk_storage __rcu *sk_bpf_storage; struct bpf_local_storage __rcu *sk_bpf_storage;
#endif #endif
struct rcu_head sk_rcu; struct rcu_head sk_rcu;
}; };
......
net/core/bpf_sk_storage.c
View file @ 1f00d375
...@@ -12,33 +12,32 @@ ...@@ -12,33 +12,32 @@
#include <uapi/linux/sock_diag.h> #include <uapi/linux/sock_diag.h>
#include <uapi/linux/btf.h> #include <uapi/linux/btf.h>
#define SK_STORAGE_CREATE_FLAG_MASK \ #define BPF_LOCAL_STORAGE_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_CLONE)
(BPF_F_NO_PREALLOC | BPF_F_CLONE)
struct bucket { struct bpf_local_storage_map_bucket {
struct hlist_head list; struct hlist_head list;
raw_spinlock_t lock; raw_spinlock_t lock;
}; };
/* Thp map is not the primary owner of a bpf_sk_storage_elem. /* Thp map is not the primary owner of a bpf_local_storage_elem.
* Instead, the sk->sk_bpf_storage is. * Instead, the container object (eg. sk->sk_bpf_storage) is.
* *
* The map (bpf_sk_storage_map) is for two purposes * The map (bpf_local_storage_map) is for two purposes
* 1. Define the size of the "sk local storage". It is * 1. Define the size of the "local storage". It is
* the map's value_size. * the map's value_size.
* *
* 2. Maintain a list to keep track of all elems such * 2. Maintain a list to keep track of all elems such
* that they can be cleaned up during the map destruction. * that they can be cleaned up during the map destruction.
* *
* When a bpf local storage is being looked up for a * When a bpf local storage is being looked up for a
* particular sk, the "bpf_map" pointer is actually used * particular object, the "bpf_map" pointer is actually used
* as the "key" to search in the list of elem in * as the "key" to search in the list of elem in
* sk->sk_bpf_storage. * the respective bpf_local_storage owned by the object.
* *
* Hence, consider sk->sk_bpf_storage is the mini-map * e.g. sk->sk_bpf_storage is the mini-map with the "bpf_map" pointer
* with the "bpf_map" pointer as the searching key. * as the searching key.
*/ */
struct bpf_sk_storage_map { struct bpf_local_storage_map {
struct bpf_map map; struct bpf_map map;
/* Lookup elem does not require accessing the map. /* Lookup elem does not require accessing the map.
* *
...@@ -46,55 +45,57 @@ struct bpf_sk_storage_map { ...@@ -46,55 +45,57 @@ struct bpf_sk_storage_map {
* link/unlink the elem from the map. Having * link/unlink the elem from the map. Having
* multiple buckets to improve contention. * multiple buckets to improve contention.
*/ */
struct bucket *buckets; struct bpf_local_storage_map_bucket *buckets;
u32 bucket_log; u32 bucket_log;
u16 elem_size; u16 elem_size;
u16 cache_idx; u16 cache_idx;
}; };
struct bpf_sk_storage_data { struct bpf_local_storage_data {
/* smap is used as the searching key when looking up /* smap is used as the searching key when looking up
* from sk->sk_bpf_storage. * from the object's bpf_local_storage.
* *
* Put it in the same cacheline as the data to minimize * Put it in the same cacheline as the data to minimize
* the number of cachelines access during the cache hit case. * the number of cachelines access during the cache hit case.
*/ */
struct bpf_sk_storage_map __rcu *smap; struct bpf_local_storage_map __rcu *smap;
u8 data[] __aligned(8); u8 data[] __aligned(8);
}; };
/* Linked to bpf_sk_storage and bpf_sk_storage_map */ /* Linked to bpf_local_storage and bpf_local_storage_map */
struct bpf_sk_storage_elem { struct bpf_local_storage_elem {
struct hlist_node map_node; /* Linked to bpf_sk_storage_map */ struct hlist_node map_node; /* Linked to bpf_local_storage_map */
struct hlist_node snode; /* Linked to bpf_sk_storage */ struct hlist_node snode; /* Linked to bpf_local_storage */
struct bpf_sk_storage __rcu *sk_storage; struct bpf_local_storage __rcu *local_storage;
struct rcu_head rcu; struct rcu_head rcu;
/* 8 bytes hole */ /* 8 bytes hole */
/* The data is stored in aother cacheline to minimize /* The data is stored in aother cacheline to minimize
* the number of cachelines access during a cache hit. * the number of cachelines access during a cache hit.
*/ */
struct bpf_sk_storage_data sdata ____cacheline_aligned; struct bpf_local_storage_data sdata ____cacheline_aligned;
}; };
#define SELEM(_SDATA) container_of((_SDATA), struct bpf_sk_storage_elem, sdata) #define SELEM(_SDATA) \
container_of((_SDATA), struct bpf_local_storage_elem, sdata)
#define SDATA(_SELEM) (&(_SELEM)->sdata) #define SDATA(_SELEM) (&(_SELEM)->sdata)
#define BPF_SK_STORAGE_CACHE_SIZE 16 #define BPF_LOCAL_STORAGE_CACHE_SIZE 16
static DEFINE_SPINLOCK(cache_idx_lock); static DEFINE_SPINLOCK(cache_idx_lock);
static u64 cache_idx_usage_counts[BPF_SK_STORAGE_CACHE_SIZE]; static u64 cache_idx_usage_counts[BPF_LOCAL_STORAGE_CACHE_SIZE];
struct bpf_sk_storage { struct bpf_local_storage {
struct bpf_sk_storage_data __rcu *cache[BPF_SK_STORAGE_CACHE_SIZE]; struct bpf_local_storage_data __rcu *cache[BPF_LOCAL_STORAGE_CACHE_SIZE];
struct hlist_head list; /* List of bpf_sk_storage_elem */ struct hlist_head list; /* List of bpf_local_storage_elem */
struct sock *sk; /* The sk that owns the the above "list" of struct sock *owner; /* The object that owns the above "list" of
* bpf_sk_storage_elem. * bpf_local_storage_elem.
*/ */
struct rcu_head rcu; struct rcu_head rcu;
raw_spinlock_t lock; /* Protect adding/removing from the "list" */ raw_spinlock_t lock; /* Protect adding/removing from the "list" */
}; };
static struct bucket *select_bucket(struct bpf_sk_storage_map *smap, static struct bpf_local_storage_map_bucket *
struct bpf_sk_storage_elem *selem) select_bucket(struct bpf_local_storage_map *smap,
struct bpf_local_storage_elem *selem)
{ {
return &smap->buckets[hash_ptr(selem, smap->bucket_log)]; return &smap->buckets[hash_ptr(selem, smap->bucket_log)];
} }
...@@ -111,21 +112,21 @@ static int omem_charge(struct sock *sk, unsigned int size) ...@@ -111,21 +112,21 @@ static int omem_charge(struct sock *sk, unsigned int size)
return -ENOMEM; return -ENOMEM;
} }
static bool selem_linked_to_sk(const struct bpf_sk_storage_elem *selem) static bool selem_linked_to_storage(const struct bpf_local_storage_elem *selem)
{ {
return !hlist_unhashed(&selem->snode); return !hlist_unhashed(&selem->snode);
} }
static bool selem_linked_to_map(const struct bpf_sk_storage_elem *selem) static bool selem_linked_to_map(const struct bpf_local_storage_elem *selem)
{ {
return !hlist_unhashed(&selem->map_node); return !hlist_unhashed(&selem->map_node);
} }
static struct bpf_sk_storage_elem *selem_alloc(struct bpf_sk_storage_map *smap, static struct bpf_local_storage_elem *
struct sock *sk, void *value, bpf_selem_alloc(struct bpf_local_storage_map *smap, struct sock *sk,
bool charge_omem) void *value, bool charge_omem)
{ {
struct bpf_sk_storage_elem *selem; struct bpf_local_storage_elem *selem;
if (charge_omem && omem_charge(sk, smap->elem_size)) if (charge_omem && omem_charge(sk, smap->elem_size))
return NULL; return NULL;
...@@ -143,89 +144,93 @@ static struct bpf_sk_storage_elem *selem_alloc(struct bpf_sk_storage_map *smap, ...@@ -143,89 +144,93 @@ static struct bpf_sk_storage_elem *selem_alloc(struct bpf_sk_storage_map *smap,
return NULL; return NULL;
} }
/* sk_storage->lock must be held and selem->sk_storage == sk_storage. /* local_storage->lock must be held and selem->local_storage == local_storage.
* The caller must ensure selem->smap is still valid to be * The caller must ensure selem->smap is still valid to be
* dereferenced for its smap->elem_size and smap->cache_idx. * dereferenced for its smap->elem_size and smap->cache_idx.
*/ */
static bool __selem_unlink_sk(struct bpf_sk_storage *sk_storage, static bool
struct bpf_sk_storage_elem *selem, bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage,
struct bpf_local_storage_elem *selem,
bool uncharge_omem) bool uncharge_omem)
{ {
struct bpf_sk_storage_map *smap; struct bpf_local_storage_map *smap;
bool free_sk_storage; bool free_local_storage;
struct sock *sk; struct sock *sk;
smap = rcu_dereference(SDATA(selem)->smap); smap = rcu_dereference(SDATA(selem)->smap);
sk = sk_storage->sk; sk = local_storage->owner;
/* All uncharging on sk->sk_omem_alloc must be done first. /* All uncharging on the owner must be done first.
* sk may be freed once the last selem is unlinked from sk_storage. * The owner may be freed once the last selem is unlinked
* from local_storage.
*/ */
if (uncharge_omem) if (uncharge_omem)
atomic_sub(smap->elem_size, &sk->sk_omem_alloc); atomic_sub(smap->elem_size, &sk->sk_omem_alloc);
free_sk_storage = hlist_is_singular_node(&selem->snode, free_local_storage = hlist_is_singular_node(&selem->snode,
&sk_storage->list); &local_storage->list);
if (free_sk_storage) { if (free_local_storage) {
atomic_sub(sizeof(struct bpf_sk_storage), &sk->sk_omem_alloc); atomic_sub(sizeof(struct bpf_local_storage), &sk->sk_omem_alloc);
sk_storage->sk = NULL; local_storage->owner = NULL;
/* After this RCU_INIT, sk may be freed and cannot be used */ /* After this RCU_INIT, sk may be freed and cannot be used */
RCU_INIT_POINTER(sk->sk_bpf_storage, NULL); RCU_INIT_POINTER(sk->sk_bpf_storage, NULL);
/* sk_storage is not freed now. sk_storage->lock is /* local_storage is not freed now. local_storage->lock is
* still held and raw_spin_unlock_bh(&sk_storage->lock) * still held and raw_spin_unlock_bh(&local_storage->lock)
* will be done by the caller. * will be done by the caller.
* *
* Although the unlock will be done under * Although the unlock will be done under
* rcu_read_lock(), it is more intutivie to * rcu_read_lock(), it is more intutivie to
* read if kfree_rcu(sk_storage, rcu) is done * read if kfree_rcu(local_storage, rcu) is done
* after the raw_spin_unlock_bh(&sk_storage->lock). * after the raw_spin_unlock_bh(&local_storage->lock).
* *
* Hence, a "bool free_sk_storage" is returned * Hence, a "bool free_local_storage" is returned
* to the caller which then calls the kfree_rcu() * to the caller which then calls the kfree_rcu()
* after unlock. * after unlock.
*/ */
} }
hlist_del_init_rcu(&selem->snode); hlist_del_init_rcu(&selem->snode);
if (rcu_access_pointer(sk_storage->cache[smap->cache_idx]) == if (rcu_access_pointer(local_storage->cache[smap->cache_idx]) ==
SDATA(selem)) SDATA(selem))
RCU_INIT_POINTER(sk_storage->cache[smap->cache_idx], NULL); RCU_INIT_POINTER(local_storage->cache[smap->cache_idx], NULL);
kfree_rcu(selem, rcu); kfree_rcu(selem, rcu);
return free_sk_storage; return free_local_storage;
} }
static void selem_unlink_sk(struct bpf_sk_storage_elem *selem) static void __bpf_selem_unlink_storage(struct bpf_local_storage_elem *selem)
{ {
struct bpf_sk_storage *sk_storage; struct bpf_local_storage *local_storage;
bool free_sk_storage = false; bool free_local_storage = false;
if (unlikely(!selem_linked_to_sk(selem))) if (unlikely(!selem_linked_to_storage(selem)))
/* selem has already been unlinked from sk */ /* selem has already been unlinked from sk */
return; return;
sk_storage = rcu_dereference(selem->sk_storage); local_storage = rcu_dereference(selem->local_storage);
raw_spin_lock_bh(&sk_storage->lock); raw_spin_lock_bh(&local_storage->lock);
if (likely(selem_linked_to_sk(selem))) if (likely(selem_linked_to_storage(selem)))
free_sk_storage = __selem_unlink_sk(sk_storage, selem, true); free_local_storage =
raw_spin_unlock_bh(&sk_storage->lock); bpf_selem_unlink_storage_nolock(local_storage, selem, true);
raw_spin_unlock_bh(&local_storage->lock);
if (free_sk_storage) if (free_local_storage)
kfree_rcu(sk_storage, rcu); kfree_rcu(local_storage, rcu);
} }
static void __selem_link_sk(struct bpf_sk_storage *sk_storage, static void
struct bpf_sk_storage_elem *selem) bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage,
struct bpf_local_storage_elem *selem)
{ {
RCU_INIT_POINTER(selem->sk_storage, sk_storage); RCU_INIT_POINTER(selem->local_storage, local_storage);
hlist_add_head(&selem->snode, &sk_storage->list); hlist_add_head(&selem->snode, &local_storage->list);
} }
static void selem_unlink_map(struct bpf_sk_storage_elem *selem) static void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem)
{ {
struct bpf_sk_storage_map *smap; struct bpf_local_storage_map *smap;
struct bucket *b; struct bpf_local_storage_map_bucket *b;
if (unlikely(!selem_linked_to_map(selem))) if (unlikely(!selem_linked_to_map(selem)))
/* selem has already be unlinked from smap */ /* selem has already be unlinked from smap */
...@@ -239,10 +244,10 @@ static void selem_unlink_map(struct bpf_sk_storage_elem *selem) ...@@ -239,10 +244,10 @@ static void selem_unlink_map(struct bpf_sk_storage_elem *selem)
raw_spin_unlock_bh(&b->lock); raw_spin_unlock_bh(&b->lock);
} }
static void selem_link_map(struct bpf_sk_storage_map *smap, static void bpf_selem_link_map(struct bpf_local_storage_map *smap,
struct bpf_sk_storage_elem *selem) struct bpf_local_storage_elem *selem)
{ {
struct bucket *b = select_bucket(smap, selem); struct bpf_local_storage_map_bucket *b = select_bucket(smap, selem);
raw_spin_lock_bh(&b->lock); raw_spin_lock_bh(&b->lock);
RCU_INIT_POINTER(SDATA(selem)->smap, smap); RCU_INIT_POINTER(SDATA(selem)->smap, smap);
...@@ -250,31 +255,31 @@ static void selem_link_map(struct bpf_sk_storage_map *smap, ...@@ -250,31 +255,31 @@ static void selem_link_map(struct bpf_sk_storage_map *smap,
raw_spin_unlock_bh(&b->lock); raw_spin_unlock_bh(&b->lock);
} }
static void selem_unlink(struct bpf_sk_storage_elem *selem) static void bpf_selem_unlink(struct bpf_local_storage_elem *selem)
{ {
/* Always unlink from map before unlinking from sk_storage /* Always unlink from map before unlinking from local_storage
* because selem will be freed after successfully unlinked from * because selem will be freed after successfully unlinked from
* the sk_storage. * the local_storage.
*/ */
selem_unlink_map(selem); bpf_selem_unlink_map(selem);
selem_unlink_sk(selem); __bpf_selem_unlink_storage(selem);
} }
static struct bpf_sk_storage_data * static struct bpf_local_storage_data *
__sk_storage_lookup(struct bpf_sk_storage *sk_storage, bpf_local_storage_lookup(struct bpf_local_storage *local_storage,
struct bpf_sk_storage_map *smap, struct bpf_local_storage_map *smap,
bool cacheit_lockit) bool cacheit_lockit)
{ {
struct bpf_sk_storage_data *sdata; struct bpf_local_storage_data *sdata;
struct bpf_sk_storage_elem *selem; struct bpf_local_storage_elem *selem;
/* Fast path (cache hit) */ /* Fast path (cache hit) */
sdata = rcu_dereference(sk_storage->cache[smap->cache_idx]); sdata = rcu_dereference(local_storage->cache[smap->cache_idx]);
if (sdata && rcu_access_pointer(sdata->smap) == smap) if (sdata && rcu_access_pointer(sdata->smap) == smap)
return sdata; return sdata;
/* Slow path (cache miss) */ /* Slow path (cache miss) */
hlist_for_each_entry_rcu(selem, &sk_storage->list, snode) hlist_for_each_entry_rcu(selem, &local_storage->list, snode)
if (rcu_access_pointer(SDATA(selem)->smap) == smap) if (rcu_access_pointer(SDATA(selem)->smap) == smap)
break; break;
...@@ -286,33 +291,33 @@ __sk_storage_lookup(struct bpf_sk_storage *sk_storage, ...@@ -286,33 +291,33 @@ __sk_storage_lookup(struct bpf_sk_storage *sk_storage,
/* spinlock is needed to avoid racing with the /* spinlock is needed to avoid racing with the
* parallel delete. Otherwise, publishing an already * parallel delete. Otherwise, publishing an already
* deleted sdata to the cache will become a use-after-free * deleted sdata to the cache will become a use-after-free
* problem in the next __sk_storage_lookup(). * problem in the next bpf_local_storage_lookup().
*/ */
raw_spin_lock_bh(&sk_storage->lock); raw_spin_lock_bh(&local_storage->lock);
if (selem_linked_to_sk(selem)) if (selem_linked_to_storage(selem))
rcu_assign_pointer(sk_storage->cache[smap->cache_idx], rcu_assign_pointer(local_storage->cache[smap->cache_idx],
sdata); sdata);
raw_spin_unlock_bh(&sk_storage->lock); raw_spin_unlock_bh(&local_storage->lock);
} }
return sdata; return sdata;
} }
static struct bpf_sk_storage_data * static struct bpf_local_storage_data *
sk_storage_lookup(struct sock *sk, struct bpf_map *map, bool cacheit_lockit) sk_storage_lookup(struct sock *sk, struct bpf_map *map, bool cacheit_lockit)
{ {
struct bpf_sk_storage *sk_storage; struct bpf_local_storage *sk_storage;
struct bpf_sk_storage_map *smap; struct bpf_local_storage_map *smap;
sk_storage = rcu_dereference(sk->sk_bpf_storage); sk_storage = rcu_dereference(sk->sk_bpf_storage);
if (!sk_storage) if (!sk_storage)
return NULL; return NULL;
smap = (struct bpf_sk_storage_map *)map; smap = (struct bpf_local_storage_map *)map;
return __sk_storage_lookup(sk_storage, smap, cacheit_lockit); return bpf_local_storage_lookup(sk_storage, smap, cacheit_lockit);
} }
static int check_flags(const struct bpf_sk_storage_data *old_sdata, static int check_flags(const struct bpf_local_storage_data *old_sdata,
u64 map_flags) u64 map_flags)
{ {
if (old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_NOEXIST) if (old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_NOEXIST)
...@@ -327,10 +332,10 @@ static int check_flags(const struct bpf_sk_storage_data *old_sdata, ...@@ -327,10 +332,10 @@ static int check_flags(const struct bpf_sk_storage_data *old_sdata,
} }
static int sk_storage_alloc(struct sock *sk, static int sk_storage_alloc(struct sock *sk,
struct bpf_sk_storage_map *smap, struct bpf_local_storage_map *smap,
struct bpf_sk_storage_elem *first_selem) struct bpf_local_storage_elem *first_selem)
{ {
struct bpf_sk_storage *prev_sk_storage, *sk_storage; struct bpf_local_storage *prev_sk_storage, *sk_storage;
int err; int err;
err = omem_charge(sk, sizeof(*sk_storage)); err = omem_charge(sk, sizeof(*sk_storage));
...@@ -344,10 +349,10 @@ static int sk_storage_alloc(struct sock *sk, ...@@ -344,10 +349,10 @@ static int sk_storage_alloc(struct sock *sk,
} }
INIT_HLIST_HEAD(&sk_storage->list); INIT_HLIST_HEAD(&sk_storage->list);
raw_spin_lock_init(&sk_storage->lock); raw_spin_lock_init(&sk_storage->lock);
sk_storage->sk = sk; sk_storage->owner = sk;
__selem_link_sk(sk_storage, first_selem); bpf_selem_link_storage_nolock(sk_storage, first_selem);
selem_link_map(smap, first_selem); bpf_selem_link_map(smap, first_selem);
/* Publish sk_storage to sk. sk->sk_lock cannot be acquired. /* Publish sk_storage to sk. sk->sk_lock cannot be acquired.
* Hence, atomic ops is used to set sk->sk_bpf_storage * Hence, atomic ops is used to set sk->sk_bpf_storage
* from NULL to the newly allocated sk_storage ptr. * from NULL to the newly allocated sk_storage ptr.
...@@ -357,17 +362,17 @@ static int sk_storage_alloc(struct sock *sk, ...@@ -357,17 +362,17 @@ static int sk_storage_alloc(struct sock *sk,
* the sk->sk_bpf_storage, the sk_storage->lock must * the sk->sk_bpf_storage, the sk_storage->lock must
* be held before setting sk->sk_bpf_storage to NULL. * be held before setting sk->sk_bpf_storage to NULL.
*/ */
prev_sk_storage = cmpxchg((struct bpf_sk_storage **)&sk->sk_bpf_storage, prev_sk_storage = cmpxchg((struct bpf_local_storage **)&sk->sk_bpf_storage,
NULL, sk_storage); NULL, sk_storage);
if (unlikely(prev_sk_storage)) { if (unlikely(prev_sk_storage)) {
selem_unlink_map(first_selem); bpf_selem_unlink_map(first_selem);
err = -EAGAIN; err = -EAGAIN;
goto uncharge; goto uncharge;
/* Note that even first_selem was linked to smap's /* Note that even first_selem was linked to smap's
* bucket->list, first_selem can be freed immediately * bucket->list, first_selem can be freed immediately
* (instead of kfree_rcu) because * (instead of kfree_rcu) because
* bpf_sk_storage_map_free() does a * bpf_local_storage_map_free() does a
* synchronize_rcu() before walking the bucket->list. * synchronize_rcu() before walking the bucket->list.
* Hence, no one is accessing selem from the * Hence, no one is accessing selem from the
* bucket->list under rcu_read_lock(). * bucket->list under rcu_read_lock().
...@@ -387,15 +392,14 @@ static int sk_storage_alloc(struct sock *sk, ...@@ -387,15 +392,14 @@ static int sk_storage_alloc(struct sock *sk,
* Otherwise, it will become a leak (and other memory issues * Otherwise, it will become a leak (and other memory issues
* during map destruction). * during map destruction).
*/ */
static struct bpf_sk_storage_data *sk_storage_update(struct sock *sk, static struct bpf_local_storage_data *
struct bpf_map *map, bpf_local_storage_update(struct sock *sk, struct bpf_map *map, void *value,
void *value,
u64 map_flags) u64 map_flags)
{ {
struct bpf_sk_storage_data *old_sdata = NULL; struct bpf_local_storage_data *old_sdata = NULL;
struct bpf_sk_storage_elem *selem; struct bpf_local_storage_elem *selem;
struct bpf_sk_storage *sk_storage; struct bpf_local_storage *local_storage;
struct bpf_sk_storage_map *smap; struct bpf_local_storage_map *smap;
int err; int err;
/* BPF_EXIST and BPF_NOEXIST cannot be both set */ /* BPF_EXIST and BPF_NOEXIST cannot be both set */
...@@ -404,15 +408,15 @@ static struct bpf_sk_storage_data *sk_storage_update(struct sock *sk, ...@@ -404,15 +408,15 @@ static struct bpf_sk_storage_data *sk_storage_update(struct sock *sk,
unlikely((map_flags & BPF_F_LOCK) && !map_value_has_spin_lock(map))) unlikely((map_flags & BPF_F_LOCK) && !map_value_has_spin_lock(map)))
return ERR_PTR(-EINVAL); return ERR_PTR(-EINVAL);
smap = (struct bpf_sk_storage_map *)map; smap = (struct bpf_local_storage_map *)map;
sk_storage = rcu_dereference(sk->sk_bpf_storage); local_storage = rcu_dereference(sk->sk_bpf_storage);
if (!sk_storage || hlist_empty(&sk_storage->list)) { if (!local_storage || hlist_empty(&local_storage->list)) {
/* Very first elem for this sk */ /* Very first elem for the owner */
err = check_flags(NULL, map_flags); err = check_flags(NULL, map_flags);
if (err) if (err)
return ERR_PTR(err); return ERR_PTR(err);
selem = selem_alloc(smap, sk, value, true); selem = bpf_selem_alloc(smap, sk, value, true);
if (!selem) if (!selem)
return ERR_PTR(-ENOMEM); return ERR_PTR(-ENOMEM);
...@@ -428,25 +432,26 @@ static struct bpf_sk_storage_data *sk_storage_update(struct sock *sk, ...@@ -428,25 +432,26 @@ static struct bpf_sk_storage_data *sk_storage_update(struct sock *sk,
if ((map_flags & BPF_F_LOCK) && !(map_flags & BPF_NOEXIST)) { if ((map_flags & BPF_F_LOCK) && !(map_flags & BPF_NOEXIST)) {
/* Hoping to find an old_sdata to do inline update /* Hoping to find an old_sdata to do inline update
* such that it can avoid taking the sk_storage->lock * such that it can avoid taking the local_storage->lock
* and changing the lists. * and changing the lists.
*/ */
old_sdata = __sk_storage_lookup(sk_storage, smap, false); old_sdata =
bpf_local_storage_lookup(local_storage, smap, false);
err = check_flags(old_sdata, map_flags); err = check_flags(old_sdata, map_flags);
if (err) if (err)
return ERR_PTR(err); return ERR_PTR(err);
if (old_sdata && selem_linked_to_sk(SELEM(old_sdata))) { if (old_sdata && selem_linked_to_storage(SELEM(old_sdata))) {
copy_map_value_locked(map, old_sdata->data, copy_map_value_locked(map, old_sdata->data,
value, false); value, false);
return old_sdata; return old_sdata;
} }
} }
raw_spin_lock_bh(&sk_storage->lock); raw_spin_lock_bh(&local_storage->lock);
/* Recheck sk_storage->list under sk_storage->lock */ /* Recheck local_storage->list under local_storage->lock */
if (unlikely(hlist_empty(&sk_storage->list))) { if (unlikely(hlist_empty(&local_storage->list))) {
/* A parallel del is happening and sk_storage is going /* A parallel del is happening and local_storage is going
* away. It has just been checked before, so very * away. It has just been checked before, so very
* unlikely. Return instead of retry to keep things * unlikely. Return instead of retry to keep things
* simple. * simple.
...@@ -455,7 +460,7 @@ static struct bpf_sk_storage_data *sk_storage_update(struct sock *sk, ...@@ -455,7 +460,7 @@ static struct bpf_sk_storage_data *sk_storage_update(struct sock *sk,
goto unlock_err; goto unlock_err;
} }
old_sdata = __sk_storage_lookup(sk_storage, smap, false); old_sdata = bpf_local_storage_lookup(local_storage, smap, false);
err = check_flags(old_sdata, map_flags); err = check_flags(old_sdata, map_flags);
if (err) if (err)
goto unlock_err; goto unlock_err;
...@@ -466,50 +471,52 @@ static struct bpf_sk_storage_data *sk_storage_update(struct sock *sk, ...@@ -466,50 +471,52 @@ static struct bpf_sk_storage_data *sk_storage_update(struct sock *sk,
goto unlock; goto unlock;
} }
/* sk_storage->lock is held. Hence, we are sure /* local_storage->lock is held. Hence, we are sure
* we can unlink and uncharge the old_sdata successfully * we can unlink and uncharge the old_sdata successfully
* later. Hence, instead of charging the new selem now * later. Hence, instead of charging the new selem now
* and then uncharge the old selem later (which may cause * and then uncharge the old selem later (which may cause
* a potential but unnecessary charge failure), avoid taking * a potential but unnecessary charge failure), avoid taking
* a charge at all here (the "!old_sdata" check) and the * a charge at all here (the "!old_sdata" check) and the
* old_sdata will not be uncharged later during __selem_unlink_sk(). * old_sdata will not be uncharged later during
* bpf_selem_unlink_storage_nolock().
*/ */
selem = selem_alloc(smap, sk, value, !old_sdata); selem = bpf_selem_alloc(smap, sk, value, !old_sdata);
if (!selem) { if (!selem) {
err = -ENOMEM; err = -ENOMEM;
goto unlock_err; goto unlock_err;
} }
/* First, link the new selem to the map */ /* First, link the new selem to the map */
selem_link_map(smap, selem); bpf_selem_link_map(smap, selem);
/* Second, link (and publish) the new selem to sk_storage */ /* Second, link (and publish) the new selem to local_storage */
__selem_link_sk(sk_storage, selem); bpf_selem_link_storage_nolock(local_storage, selem);
/* Third, remove old selem, SELEM(old_sdata) */ /* Third, remove old selem, SELEM(old_sdata) */
if (old_sdata) { if (old_sdata) {
selem_unlink_map(SELEM(old_sdata)); bpf_selem_unlink_map(SELEM(old_sdata));
__selem_unlink_sk(sk_storage, SELEM(old_sdata), false); bpf_selem_unlink_storage_nolock(local_storage, SELEM(old_sdata),
false);
} }
unlock: unlock:
raw_spin_unlock_bh(&sk_storage->lock); raw_spin_unlock_bh(&local_storage->lock);
return SDATA(selem); return SDATA(selem);
unlock_err: unlock_err:
raw_spin_unlock_bh(&sk_storage->lock); raw_spin_unlock_bh(&local_storage->lock);
return ERR_PTR(err); return ERR_PTR(err);
} }
static int sk_storage_delete(struct sock *sk, struct bpf_map *map) 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); sdata = sk_storage_lookup(sk, map, false);
if (!sdata) if (!sdata)
return -ENOENT; return -ENOENT;
selem_unlink(SELEM(sdata)); bpf_selem_unlink(SELEM(sdata));
return 0; return 0;
} }
...@@ -521,7 +528,7 @@ static u16 cache_idx_get(void) ...@@ -521,7 +528,7 @@ static u16 cache_idx_get(void)
spin_lock(&cache_idx_lock); spin_lock(&cache_idx_lock);
for (i = 0; i < BPF_SK_STORAGE_CACHE_SIZE; i++) { for (i = 0; i < BPF_LOCAL_STORAGE_CACHE_SIZE; i++) {
if (cache_idx_usage_counts[i] < min_usage) { if (cache_idx_usage_counts[i] < min_usage) {
min_usage = cache_idx_usage_counts[i]; min_usage = cache_idx_usage_counts[i];
res = i; res = i;
...@@ -548,8 +555,8 @@ static void cache_idx_free(u16 idx) ...@@ -548,8 +555,8 @@ static void cache_idx_free(u16 idx)
/* Called by __sk_destruct() & bpf_sk_storage_clone() */ /* Called by __sk_destruct() & bpf_sk_storage_clone() */
void bpf_sk_storage_free(struct sock *sk) void bpf_sk_storage_free(struct sock *sk)
{ {
struct bpf_sk_storage_elem *selem; struct bpf_local_storage_elem *selem;
struct bpf_sk_storage *sk_storage; struct bpf_local_storage *sk_storage;
bool free_sk_storage = false; bool free_sk_storage = false;
struct hlist_node *n; struct hlist_node *n;
...@@ -565,7 +572,7 @@ void bpf_sk_storage_free(struct sock *sk) ...@@ -565,7 +572,7 @@ void bpf_sk_storage_free(struct sock *sk)
* Thus, no elem can be added-to or deleted-from the * 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. * sk_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 * when unlinking elem from the sk_storage->list and
* the map's bucket->list. * the map's bucket->list.
*/ */
...@@ -574,8 +581,9 @@ void bpf_sk_storage_free(struct sock *sk) ...@@ -574,8 +581,9 @@ void bpf_sk_storage_free(struct sock *sk)
/* Always unlink from map before unlinking from /* Always unlink from map before unlinking from
* sk_storage. * sk_storage.
*/ */
selem_unlink_map(selem); bpf_selem_unlink_map(selem);
free_sk_storage = __selem_unlink_sk(sk_storage, selem, true); free_sk_storage = bpf_selem_unlink_storage_nolock(sk_storage,
selem, true);
} }
raw_spin_unlock_bh(&sk_storage->lock); raw_spin_unlock_bh(&sk_storage->lock);
rcu_read_unlock(); rcu_read_unlock();
...@@ -584,14 +592,14 @@ void bpf_sk_storage_free(struct sock *sk) ...@@ -584,14 +592,14 @@ void bpf_sk_storage_free(struct sock *sk)
kfree_rcu(sk_storage, rcu); kfree_rcu(sk_storage, rcu);
} }
static void bpf_sk_storage_map_free(struct bpf_map *map) static void bpf_local_storage_map_free(struct bpf_map *map)
{ {
struct bpf_sk_storage_elem *selem; struct bpf_local_storage_elem *selem;
struct bpf_sk_storage_map *smap; struct bpf_local_storage_map *smap;
struct bucket *b; struct bpf_local_storage_map_bucket *b;
unsigned int i; unsigned int i;
smap = (struct bpf_sk_storage_map *)map; smap = (struct bpf_local_storage_map *)map;
cache_idx_free(smap->cache_idx); cache_idx_free(smap->cache_idx);
...@@ -604,10 +612,10 @@ static void bpf_sk_storage_map_free(struct bpf_map *map) ...@@ -604,10 +612,10 @@ static void bpf_sk_storage_map_free(struct bpf_map *map)
/* bpf prog and the userspace can no longer access this map /* bpf prog and the userspace can no longer access this map
* now. No new selem (of this map) can be added * now. No new selem (of this map) can be added
* to the sk->sk_bpf_storage or to the map bucket's list. * to the owner->storage or to the map bucket's list.
* *
* The elem of this map can be cleaned up here * The elem of this map can be cleaned up here
* or * or when the storage is freed e.g.
* by bpf_sk_storage_free() during __sk_destruct(). * by bpf_sk_storage_free() during __sk_destruct().
*/ */
for (i = 0; i < (1U << smap->bucket_log); i++) { for (i = 0; i < (1U << smap->bucket_log); i++) {
...@@ -615,26 +623,26 @@ static void bpf_sk_storage_map_free(struct bpf_map *map) ...@@ -615,26 +623,26 @@ static void bpf_sk_storage_map_free(struct bpf_map *map)
rcu_read_lock(); rcu_read_lock();
/* No one is adding to b->list now */ /* No one is adding to b->list now */
while ((selem = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(&b->list)), while ((selem = hlist_entry_safe(
struct bpf_sk_storage_elem, rcu_dereference_raw(hlist_first_rcu(&b->list)),
map_node))) { struct bpf_local_storage_elem, map_node))) {
selem_unlink(selem); bpf_selem_unlink(selem);
cond_resched_rcu(); cond_resched_rcu();
} }
rcu_read_unlock(); rcu_read_unlock();
} }
/* bpf_sk_storage_free() may still need to access the map. /* While freeing the storage we may still need to access the map.
* e.g. bpf_sk_storage_free() has unlinked selem from the map *
* e.g. when bpf_sk_storage_free() has unlinked selem from the map
* which then made the above while((selem = ...)) loop * which then made the above while((selem = ...)) loop
* exited immediately. * exit immediately.
* *
* However, the bpf_sk_storage_free() still needs to access * However, while freeing the storage one still needs to access the
* the smap->elem_size to do the uncharging in * smap->elem_size to do the uncharging in
* __selem_unlink_sk(). * bpf_selem_unlink_storage_nolock().
* *
* Hence, wait another rcu grace period for the * Hence, wait another rcu grace period for the storage to be freed.
* bpf_sk_storage_free() to finish.
*/ */
synchronize_rcu(); synchronize_rcu();
...@@ -645,14 +653,15 @@ static void bpf_sk_storage_map_free(struct bpf_map *map) ...@@ -645,14 +653,15 @@ static void bpf_sk_storage_map_free(struct bpf_map *map)
/* U16_MAX is much more than enough for sk local storage /* U16_MAX is much more than enough for sk local storage
* considering a tcp_sock is ~2k. * considering a tcp_sock is ~2k.
*/ */
#define MAX_VALUE_SIZE \ #define BPF_LOCAL_STORAGE_MAX_VALUE_SIZE \
min_t(u32, \ min_t(u32, \
(KMALLOC_MAX_SIZE - MAX_BPF_STACK - sizeof(struct bpf_sk_storage_elem)), \ (KMALLOC_MAX_SIZE - MAX_BPF_STACK - \
(U16_MAX - sizeof(struct bpf_sk_storage_elem))) sizeof(struct bpf_local_storage_elem)), \
(U16_MAX - sizeof(struct bpf_local_storage_elem)))
static int bpf_sk_storage_map_alloc_check(union bpf_attr *attr) static int bpf_local_storage_map_alloc_check(union bpf_attr *attr)
{ {
if (attr->map_flags & ~SK_STORAGE_CREATE_FLAG_MASK || if (attr->map_flags & ~BPF_LOCAL_STORAGE_CREATE_FLAG_MASK ||
!(attr->map_flags & BPF_F_NO_PREALLOC) || !(attr->map_flags & BPF_F_NO_PREALLOC) ||
attr->max_entries || attr->max_entries ||
attr->key_size != sizeof(int) || !attr->value_size || attr->key_size != sizeof(int) || !attr->value_size ||
...@@ -663,15 +672,15 @@ static int bpf_sk_storage_map_alloc_check(union bpf_attr *attr) ...@@ -663,15 +672,15 @@ static int bpf_sk_storage_map_alloc_check(union bpf_attr *attr)
if (!bpf_capable()) if (!bpf_capable())
return -EPERM; return -EPERM;
if (attr->value_size > MAX_VALUE_SIZE) if (attr->value_size > BPF_LOCAL_STORAGE_MAX_VALUE_SIZE)
return -E2BIG; return -E2BIG;
return 0; return 0;
} }
static struct bpf_map *bpf_sk_storage_map_alloc(union bpf_attr *attr) static struct bpf_map *bpf_local_storage_map_alloc(union bpf_attr *attr)
{ {
struct bpf_sk_storage_map *smap; struct bpf_local_storage_map *smap;
unsigned int i; unsigned int i;
u32 nbuckets; u32 nbuckets;
u64 cost; u64 cost;
...@@ -707,7 +716,8 @@ static struct bpf_map *bpf_sk_storage_map_alloc(union bpf_attr *attr) ...@@ -707,7 +716,8 @@ static struct bpf_map *bpf_sk_storage_map_alloc(union bpf_attr *attr)
raw_spin_lock_init(&smap->buckets[i].lock); raw_spin_lock_init(&smap->buckets[i].lock);
} }
smap->elem_size = sizeof(struct bpf_sk_storage_elem) + attr->value_size; smap->elem_size =
sizeof(struct bpf_local_storage_elem) + attr->value_size;
smap->cache_idx = cache_idx_get(); smap->cache_idx = cache_idx_get();
return &smap->map; return &smap->map;
...@@ -719,7 +729,7 @@ static int notsupp_get_next_key(struct bpf_map *map, void *key, ...@@ -719,7 +729,7 @@ static int notsupp_get_next_key(struct bpf_map *map, void *key,
return -ENOTSUPP; return -ENOTSUPP;
} }
static int bpf_sk_storage_map_check_btf(const struct bpf_map *map, static int bpf_local_storage_map_check_btf(const struct bpf_map *map,
const struct btf *btf, const struct btf *btf,
const struct btf_type *key_type, const struct btf_type *key_type,
const struct btf_type *value_type) const struct btf_type *value_type)
...@@ -738,7 +748,7 @@ static int bpf_sk_storage_map_check_btf(const struct bpf_map *map, ...@@ -738,7 +748,7 @@ static int bpf_sk_storage_map_check_btf(const struct bpf_map *map,
static void *bpf_fd_sk_storage_lookup_elem(struct bpf_map *map, void *key) 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; struct socket *sock;
int fd, err; int fd, err;
...@@ -756,14 +766,15 @@ static void *bpf_fd_sk_storage_lookup_elem(struct bpf_map *map, void *key) ...@@ -756,14 +766,15 @@ static void *bpf_fd_sk_storage_lookup_elem(struct bpf_map *map, void *key)
static int bpf_fd_sk_storage_update_elem(struct bpf_map *map, void *key, static int bpf_fd_sk_storage_update_elem(struct bpf_map *map, void *key,
void *value, u64 map_flags) void *value, u64 map_flags)
{ {
struct bpf_sk_storage_data *sdata; struct bpf_local_storage_data *sdata;
struct socket *sock; struct socket *sock;
int fd, err; int fd, err;
fd = *(int *)key; fd = *(int *)key;
sock = sockfd_lookup(fd, &err); sock = sockfd_lookup(fd, &err);
if (sock) { if (sock) {
sdata = sk_storage_update(sock->sk, map, value, map_flags); sdata = bpf_local_storage_update(sock->sk, map, value,
map_flags);
sockfd_put(sock); sockfd_put(sock);
return PTR_ERR_OR_ZERO(sdata); return PTR_ERR_OR_ZERO(sdata);
} }
...@@ -787,14 +798,14 @@ static int bpf_fd_sk_storage_delete_elem(struct bpf_map *map, void *key) ...@@ -787,14 +798,14 @@ static int bpf_fd_sk_storage_delete_elem(struct bpf_map *map, void *key)
return err; return err;
} }
static struct bpf_sk_storage_elem * static struct bpf_local_storage_elem *
bpf_sk_storage_clone_elem(struct sock *newsk, bpf_sk_storage_clone_elem(struct sock *newsk,
struct bpf_sk_storage_map *smap, struct bpf_local_storage_map *smap,
struct bpf_sk_storage_elem *selem) 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 = bpf_selem_alloc(smap, newsk, NULL, true);
if (!copy_selem) if (!copy_selem)
return NULL; return NULL;
...@@ -810,9 +821,9 @@ bpf_sk_storage_clone_elem(struct sock *newsk, ...@@ -810,9 +821,9 @@ bpf_sk_storage_clone_elem(struct sock *newsk,
int bpf_sk_storage_clone(const struct sock *sk, 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_local_storage *new_sk_storage = NULL;
struct bpf_sk_storage *sk_storage; struct bpf_local_storage *sk_storage;
struct bpf_sk_storage_elem *selem; struct bpf_local_storage_elem *selem;
int ret = 0; int ret = 0;
RCU_INIT_POINTER(newsk->sk_bpf_storage, NULL); RCU_INIT_POINTER(newsk->sk_bpf_storage, NULL);
...@@ -824,8 +835,8 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk) ...@@ -824,8 +835,8 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk)
goto out; goto out;
hlist_for_each_entry_rcu(selem, &sk_storage->list, snode) { hlist_for_each_entry_rcu(selem, &sk_storage->list, snode) {
struct bpf_sk_storage_elem *copy_selem; struct bpf_local_storage_elem *copy_selem;
struct bpf_sk_storage_map *smap; struct bpf_local_storage_map *smap;
struct bpf_map *map; struct bpf_map *map;
smap = rcu_dereference(SDATA(selem)->smap); smap = rcu_dereference(SDATA(selem)->smap);
...@@ -833,7 +844,7 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk) ...@@ -833,7 +844,7 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk)
continue; continue;
/* Note that for lockless listeners adding new element /* 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 * Try to grab map refcnt to make sure that it's still
* alive and prevent concurrent removal. * alive and prevent concurrent removal.
*/ */
...@@ -849,8 +860,8 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk) ...@@ -849,8 +860,8 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk)
} }
if (new_sk_storage) { if (new_sk_storage) {
selem_link_map(smap, copy_selem); bpf_selem_link_map(smap, copy_selem);
__selem_link_sk(new_sk_storage, copy_selem); bpf_selem_link_storage_nolock(new_sk_storage, copy_selem);
} else { } else {
ret = sk_storage_alloc(newsk, smap, copy_selem); ret = sk_storage_alloc(newsk, smap, copy_selem);
if (ret) { if (ret) {
...@@ -861,7 +872,8 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk) ...@@ -861,7 +872,8 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk)
goto out; goto out;
} }
new_sk_storage = rcu_dereference(copy_selem->sk_storage); new_sk_storage =
rcu_dereference(copy_selem->local_storage);
} }
bpf_map_put(map); bpf_map_put(map);
} }
...@@ -879,7 +891,7 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk) ...@@ -879,7 +891,7 @@ 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, BPF_CALL_4(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk,
void *, value, u64, flags) void *, value, u64, flags)
{ {
struct bpf_sk_storage_data *sdata; struct bpf_local_storage_data *sdata;
if (flags > BPF_SK_STORAGE_GET_F_CREATE) if (flags > BPF_SK_STORAGE_GET_F_CREATE)
return (unsigned long)NULL; return (unsigned long)NULL;
...@@ -895,7 +907,7 @@ BPF_CALL_4(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk, ...@@ -895,7 +907,7 @@ BPF_CALL_4(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk,
* destruction). * destruction).
*/ */
refcount_inc_not_zero(&sk->sk_refcnt)) { refcount_inc_not_zero(&sk->sk_refcnt)) {
sdata = sk_storage_update(sk, map, value, BPF_NOEXIST); sdata = bpf_local_storage_update(sk, map, value, BPF_NOEXIST);
/* sk must be a fullsock (guaranteed by verifier), /* sk must be a fullsock (guaranteed by verifier),
* so sock_gen_put() is unnecessary. * so sock_gen_put() is unnecessary.
*/ */
...@@ -922,15 +934,15 @@ BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk) ...@@ -922,15 +934,15 @@ BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk)
static int sk_storage_map_btf_id; static int sk_storage_map_btf_id;
const struct bpf_map_ops sk_storage_map_ops = { const struct bpf_map_ops sk_storage_map_ops = {
.map_alloc_check = bpf_sk_storage_map_alloc_check, .map_alloc_check = bpf_local_storage_map_alloc_check,
.map_alloc = bpf_sk_storage_map_alloc, .map_alloc = bpf_local_storage_map_alloc,
.map_free = bpf_sk_storage_map_free, .map_free = bpf_local_storage_map_free,
.map_get_next_key = notsupp_get_next_key, .map_get_next_key = notsupp_get_next_key,
.map_lookup_elem = bpf_fd_sk_storage_lookup_elem, .map_lookup_elem = bpf_fd_sk_storage_lookup_elem,
.map_update_elem = bpf_fd_sk_storage_update_elem, .map_update_elem = bpf_fd_sk_storage_update_elem,
.map_delete_elem = bpf_fd_sk_storage_delete_elem, .map_delete_elem = bpf_fd_sk_storage_delete_elem,
.map_check_btf = bpf_sk_storage_map_check_btf, .map_check_btf = bpf_local_storage_map_check_btf,
.map_btf_name = "bpf_sk_storage_map", .map_btf_name = "bpf_local_storage_map",
.map_btf_id = &sk_storage_map_btf_id, .map_btf_id = &sk_storage_map_btf_id,
}; };
...@@ -1022,7 +1034,7 @@ bpf_sk_storage_diag_alloc(const struct nlattr *nla_stgs) ...@@ -1022,7 +1034,7 @@ bpf_sk_storage_diag_alloc(const struct nlattr *nla_stgs)
u32 nr_maps = 0; u32 nr_maps = 0;
int rem, err; 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. * the map_alloc_check() side also does.
*/ */
if (!bpf_capable()) if (!bpf_capable())
...@@ -1072,13 +1084,13 @@ bpf_sk_storage_diag_alloc(const struct nlattr *nla_stgs) ...@@ -1072,13 +1084,13 @@ bpf_sk_storage_diag_alloc(const struct nlattr *nla_stgs)
} }
EXPORT_SYMBOL_GPL(bpf_sk_storage_diag_alloc); 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 nlattr *nla_stg, *nla_value;
struct bpf_sk_storage_map *smap; struct bpf_local_storage_map *smap;
/* It cannot exceed max nlattr's payload */ /* 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); nla_stg = nla_nest_start(skb, SK_DIAG_BPF_STORAGE);
if (!nla_stg) if (!nla_stg)
...@@ -1114,9 +1126,9 @@ static int bpf_sk_storage_diag_put_all(struct sock *sk, struct sk_buff *skb, ...@@ -1114,9 +1126,9 @@ 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) */ /* stg_array_type (e.g. INET_DIAG_BPF_SK_STORAGES) */
unsigned int diag_size = nla_total_size(0); unsigned int diag_size = nla_total_size(0);
struct bpf_sk_storage *sk_storage; struct bpf_local_storage *sk_storage;
struct bpf_sk_storage_elem *selem; struct bpf_local_storage_elem *selem;
struct bpf_sk_storage_map *smap; struct bpf_local_storage_map *smap;
struct nlattr *nla_stgs; struct nlattr *nla_stgs;
unsigned int saved_len; unsigned int saved_len;
int err = 0; int err = 0;
...@@ -1169,8 +1181,8 @@ int bpf_sk_storage_diag_put(struct bpf_sk_storage_diag *diag, ...@@ -1169,8 +1181,8 @@ int bpf_sk_storage_diag_put(struct bpf_sk_storage_diag *diag,
{ {
/* stg_array_type (e.g. INET_DIAG_BPF_SK_STORAGES) */ /* stg_array_type (e.g. INET_DIAG_BPF_SK_STORAGES) */
unsigned int diag_size = nla_total_size(0); unsigned int diag_size = nla_total_size(0);
struct bpf_sk_storage *sk_storage; struct bpf_local_storage *sk_storage;
struct bpf_sk_storage_data *sdata; struct bpf_local_storage_data *sdata;
struct nlattr *nla_stgs; struct nlattr *nla_stgs;
unsigned int saved_len; unsigned int saved_len;
int err = 0; int err = 0;
...@@ -1197,8 +1209,8 @@ int bpf_sk_storage_diag_put(struct bpf_sk_storage_diag *diag, ...@@ -1197,8 +1209,8 @@ int bpf_sk_storage_diag_put(struct bpf_sk_storage_diag *diag,
saved_len = skb->len; saved_len = skb->len;
for (i = 0; i < diag->nr_maps; i++) { for (i = 0; i < diag->nr_maps; i++) {
sdata = __sk_storage_lookup(sk_storage, sdata = bpf_local_storage_lookup(sk_storage,
(struct bpf_sk_storage_map *)diag->maps[i], (struct bpf_local_storage_map *)diag->maps[i],
false); false);
if (!sdata) if (!sdata)
...@@ -1235,19 +1247,19 @@ struct bpf_iter_seq_sk_storage_map_info { ...@@ -1235,19 +1247,19 @@ struct bpf_iter_seq_sk_storage_map_info {
unsigned skip_elems; unsigned skip_elems;
}; };
static struct bpf_sk_storage_elem * static struct bpf_local_storage_elem *
bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info, bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info,
struct bpf_sk_storage_elem *prev_selem) struct bpf_local_storage_elem *prev_selem)
{ {
struct bpf_sk_storage *sk_storage; struct bpf_local_storage *sk_storage;
struct bpf_sk_storage_elem *selem; struct bpf_local_storage_elem *selem;
u32 skip_elems = info->skip_elems; u32 skip_elems = info->skip_elems;
struct bpf_sk_storage_map *smap; struct bpf_local_storage_map *smap;
u32 bucket_id = info->bucket_id; u32 bucket_id = info->bucket_id;
u32 i, count, n_buckets; u32 i, count, n_buckets;
struct bucket *b; struct bpf_local_storage_map_bucket *b;
smap = (struct bpf_sk_storage_map *)info->map; smap = (struct bpf_local_storage_map *)info->map;
n_buckets = 1U << smap->bucket_log; n_buckets = 1U << smap->bucket_log;
if (bucket_id >= n_buckets) if (bucket_id >= n_buckets)
return NULL; return NULL;
...@@ -1257,7 +1269,7 @@ bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info, ...@@ -1257,7 +1269,7 @@ bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info,
count = 0; count = 0;
while (selem) { while (selem) {
selem = hlist_entry_safe(selem->map_node.next, selem = hlist_entry_safe(selem->map_node.next,
struct bpf_sk_storage_elem, map_node); struct bpf_local_storage_elem, map_node);
if (!selem) { if (!selem) {
/* not found, unlock and go to the next bucket */ /* not found, unlock and go to the next bucket */
b = &smap->buckets[bucket_id++]; b = &smap->buckets[bucket_id++];
...@@ -1265,7 +1277,7 @@ bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info, ...@@ -1265,7 +1277,7 @@ bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info,
skip_elems = 0; skip_elems = 0;
break; break;
} }
sk_storage = rcu_dereference_raw(selem->sk_storage); sk_storage = rcu_dereference_raw(selem->local_storage);
if (sk_storage) { if (sk_storage) {
info->skip_elems = skip_elems + count; info->skip_elems = skip_elems + count;
return selem; return selem;
...@@ -1278,7 +1290,7 @@ bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info, ...@@ -1278,7 +1290,7 @@ bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info,
raw_spin_lock_bh(&b->lock); raw_spin_lock_bh(&b->lock);
count = 0; count = 0;
hlist_for_each_entry(selem, &b->list, map_node) { hlist_for_each_entry(selem, &b->list, map_node) {
sk_storage = rcu_dereference_raw(selem->sk_storage); sk_storage = rcu_dereference_raw(selem->local_storage);
if (sk_storage && count >= skip_elems) { if (sk_storage && count >= skip_elems) {
info->bucket_id = i; info->bucket_id = i;
info->skip_elems = count; info->skip_elems = count;
...@@ -1297,7 +1309,7 @@ bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info, ...@@ -1297,7 +1309,7 @@ bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info,
static void *bpf_sk_storage_map_seq_start(struct seq_file *seq, loff_t *pos) static void *bpf_sk_storage_map_seq_start(struct seq_file *seq, loff_t *pos)
{ {
struct bpf_sk_storage_elem *selem; struct bpf_local_storage_elem *selem;
selem = bpf_sk_storage_map_seq_find_next(seq->private, NULL); selem = bpf_sk_storage_map_seq_find_next(seq->private, NULL);
if (!selem) if (!selem)
...@@ -1330,11 +1342,11 @@ DEFINE_BPF_ITER_FUNC(bpf_sk_storage_map, struct bpf_iter_meta *meta, ...@@ -1330,11 +1342,11 @@ DEFINE_BPF_ITER_FUNC(bpf_sk_storage_map, struct bpf_iter_meta *meta,
void *value) void *value)
static int __bpf_sk_storage_map_seq_show(struct seq_file *seq, static int __bpf_sk_storage_map_seq_show(struct seq_file *seq,
struct bpf_sk_storage_elem *selem) struct bpf_local_storage_elem *selem)
{ {
struct bpf_iter_seq_sk_storage_map_info *info = seq->private; struct bpf_iter_seq_sk_storage_map_info *info = seq->private;
struct bpf_iter__bpf_sk_storage_map ctx = {}; struct bpf_iter__bpf_sk_storage_map ctx = {};
struct bpf_sk_storage *sk_storage; struct bpf_local_storage *sk_storage;
struct bpf_iter_meta meta; struct bpf_iter_meta meta;
struct bpf_prog *prog; struct bpf_prog *prog;
int ret = 0; int ret = 0;
...@@ -1345,8 +1357,8 @@ static int __bpf_sk_storage_map_seq_show(struct seq_file *seq, ...@@ -1345,8 +1357,8 @@ static int __bpf_sk_storage_map_seq_show(struct seq_file *seq,
ctx.meta = &meta; ctx.meta = &meta;
ctx.map = info->map; ctx.map = info->map;
if (selem) { if (selem) {
sk_storage = rcu_dereference_raw(selem->sk_storage); sk_storage = rcu_dereference_raw(selem->local_storage);
ctx.sk = sk_storage->sk; ctx.sk = sk_storage->owner;
ctx.value = SDATA(selem)->data; ctx.value = SDATA(selem)->data;
} }
ret = bpf_iter_run_prog(prog, &ctx); ret = bpf_iter_run_prog(prog, &ctx);
...@@ -1363,13 +1375,13 @@ static int bpf_sk_storage_map_seq_show(struct seq_file *seq, void *v) ...@@ -1363,13 +1375,13 @@ static int bpf_sk_storage_map_seq_show(struct seq_file *seq, void *v)
static void bpf_sk_storage_map_seq_stop(struct seq_file *seq, void *v) static void bpf_sk_storage_map_seq_stop(struct seq_file *seq, void *v)
{ {
struct bpf_iter_seq_sk_storage_map_info *info = seq->private; struct bpf_iter_seq_sk_storage_map_info *info = seq->private;
struct bpf_sk_storage_map *smap; struct bpf_local_storage_map *smap;
struct bucket *b; struct bpf_local_storage_map_bucket *b;
if (!v) { if (!v) {
(void)__bpf_sk_storage_map_seq_show(seq, v); (void)__bpf_sk_storage_map_seq_show(seq, v);
} else { } else {
smap = (struct bpf_sk_storage_map *)info->map; smap = (struct bpf_local_storage_map *)info->map;
b = &smap->buckets[info->bucket_id]; b = &smap->buckets[info->bucket_id];
raw_spin_unlock_bh(&b->lock); raw_spin_unlock_bh(&b->lock);
} }
......
tools/testing/selftests/bpf/progs/map_ptr_kern.c
View file @ 1f00d375
...@@ -589,7 +589,7 @@ static inline int check_stack(void) ...@@ -589,7 +589,7 @@ static inline int check_stack(void)
return 1; return 1;
} }
struct bpf_sk_storage_map { struct bpf_local_storage_map {
struct bpf_map map; struct bpf_map map;
} __attribute__((preserve_access_index)); } __attribute__((preserve_access_index));
...@@ -602,8 +602,8 @@ struct { ...@@ -602,8 +602,8 @@ struct {
static inline int check_sk_storage(void) static inline int check_sk_storage(void)
{ {
struct bpf_sk_storage_map *sk_storage = struct bpf_local_storage_map *sk_storage =
(struct bpf_sk_storage_map *)&m_sk_storage; (struct bpf_local_storage_map *)&m_sk_storage;
struct bpf_map *map = (struct bpf_map *)&m_sk_storage; struct bpf_map *map = (struct bpf_map *)&m_sk_storage;
VERIFY(check(&sk_storage->map, map, sizeof(__u32), sizeof(__u32), 0)); VERIFY(check(&sk_storage->map, map, sizeof(__u32), sizeof(__u32), 0));
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment
GitLab Nexedi Edition | About GitLab | About Nexedi | 沪ICP备2021021310号-2 | 沪ICP备2021021310号-7