bpf: Convert bpf_selem_unlink_map to failable

To prepare for changing bpf_local_storage_map_bucket::lock to rqspinlock,
convert bpf_selem_unlink_map() to failable. It still always succeeds and
returns 0 for now.

Since some operations updating local storage cannot fail in the middle,
open-code bpf_selem_unlink_map() to take the b->lock before the
operation. There are two such locations:

- bpf_local_storage_alloc()

  The first selem will be unlinked from smap if cmpxchg owner_storage_ptr
  fails, which should not fail. Therefore, hold b->lock when linking
  until allocation complete. Helpers that assume b->lock is held by
  callers are introduced: bpf_selem_link_map_nolock() and
  bpf_selem_unlink_map_nolock().

- bpf_local_storage_update()

  The three step update process: link_map(new_selem),
  link_storage(new_selem), and unlink_map(old_selem) should not fail in
  the middle.

In bpf_selem_unlink(), bpf_selem_unlink_map() and
bpf_selem_unlink_storage() should either all succeed or fail as a whole
instead of failing in the middle. So, return if unlink_map() failed.
Remove the selem_linked_to_map_lockless() check as an selem in the
common paths (not bpf_local_storage_map_free() or
bpf_local_storage_destroy()), will be unlinked under b->lock and
local_storage->lock and therefore no other threads can unlink the selem
from map at the same time.

In bpf_local_storage_destroy(), ignore the return of
bpf_selem_unlink_map() for now. A later patch will allow
bpf_local_storage_destroy() to unlink selems even when failing to
acquire locks.

Note that while this patch removes all callers of selem_linked_to_map(),
a later patch that introduces bpf_selem_unlink_nofail() will use it
again.

Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Amery Hung <ameryhung@gmail.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://patch.msgid.link/20260205222916.1788211-3-ameryhung@gmail.com

diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c
index 91b28f4e31303f3cff4de8467de2e0eb300e3d15..6fa71502c7d716e272b508ea57411654c6c92466 100644 (file)
--- a/kernel/bpf/bpf_local_storage.c
+++ b/kernel/bpf/bpf_local_storage.c
@@ -61,11 +61,6 @@ static bool selem_linked_to_storage(const struct bpf_local_storage_elem *selem)
        return !hlist_unhashed(&selem->snode);
 }
 
-static bool selem_linked_to_map_lockless(const struct bpf_local_storage_elem *selem)
-{
-       return !hlist_unhashed_lockless(&selem->map_node);
-}
-
 static bool selem_linked_to_map(const struct bpf_local_storage_elem *selem)
 {
        return !hlist_unhashed(&selem->map_node);
@@ -347,25 +342,27 @@ void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage,
        hlist_add_head_rcu(&selem->snode, &local_storage->list);
 }
 
-static void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem)
+static int bpf_selem_unlink_map(struct bpf_local_storage_elem *selem)
 {
        struct bpf_local_storage *local_storage;
        struct bpf_local_storage_map *smap;
        struct bpf_local_storage_map_bucket *b;
        unsigned long flags;
 
-       if (unlikely(!selem_linked_to_map_lockless(selem)))
-               /* selem has already be unlinked from smap */
-               return;
-
        local_storage = rcu_dereference_check(selem->local_storage,
                                              bpf_rcu_lock_held());
        smap = rcu_dereference_check(SDATA(selem)->smap, bpf_rcu_lock_held());
        b = select_bucket(smap, local_storage);
        raw_spin_lock_irqsave(&b->lock, flags);
-       if (likely(selem_linked_to_map(selem)))
-               hlist_del_init_rcu(&selem->map_node);
+       hlist_del_init_rcu(&selem->map_node);
        raw_spin_unlock_irqrestore(&b->lock, flags);
+
+       return 0;
+}
+
+static void bpf_selem_unlink_map_nolock(struct bpf_local_storage_elem *selem)
+{
+       hlist_del_init_rcu(&selem->map_node);
 }
 
 void bpf_selem_link_map(struct bpf_local_storage_map *smap,
@@ -381,13 +378,24 @@ void bpf_selem_link_map(struct bpf_local_storage_map *smap,
        raw_spin_unlock_irqrestore(&b->lock, flags);
 }
 
+static void bpf_selem_link_map_nolock(struct bpf_local_storage_map_bucket *b,
+                                     struct bpf_local_storage_elem *selem)
+{
+       hlist_add_head_rcu(&selem->map_node, &b->list);
+}
+
 void bpf_selem_unlink(struct bpf_local_storage_elem *selem, bool reuse_now)
 {
+       int err;
+
        /* 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);
+       err = bpf_selem_unlink_map(selem);
+       if (err)
+               return;
+
        bpf_selem_unlink_storage(selem, reuse_now);
 }
 
@@ -429,6 +437,8 @@ int bpf_local_storage_alloc(void *owner,
 {
        struct bpf_local_storage *prev_storage, *storage;
        struct bpf_local_storage **owner_storage_ptr;
+       struct bpf_local_storage_map_bucket *b;
+       unsigned long flags;
        int err;
 
        err = mem_charge(smap, owner, sizeof(*storage));
@@ -453,7 +463,10 @@ int bpf_local_storage_alloc(void *owner,
        storage->use_kmalloc_nolock = smap->use_kmalloc_nolock;
 
        bpf_selem_link_storage_nolock(storage, first_selem);
-       bpf_selem_link_map(smap, storage, first_selem);
+
+       b = select_bucket(smap, storage);
+       raw_spin_lock_irqsave(&b->lock, flags);
+       bpf_selem_link_map_nolock(b, first_selem);
 
        owner_storage_ptr =
                (struct bpf_local_storage **)owner_storage(smap, owner);
@@ -469,10 +482,12 @@ int bpf_local_storage_alloc(void *owner,
         */
        prev_storage = cmpxchg(owner_storage_ptr, NULL, storage);
        if (unlikely(prev_storage)) {
-               bpf_selem_unlink_map(first_selem);
+               bpf_selem_unlink_map_nolock(first_selem);
+               raw_spin_unlock_irqrestore(&b->lock, flags);
                err = -EAGAIN;
                goto uncharge;
        }
+       raw_spin_unlock_irqrestore(&b->lock, flags);
 
        return 0;
 
@@ -494,8 +509,9 @@ bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap,
        struct bpf_local_storage_data *old_sdata = NULL;
        struct bpf_local_storage_elem *alloc_selem, *selem = NULL;
        struct bpf_local_storage *local_storage;
+       struct bpf_local_storage_map_bucket *b;
        HLIST_HEAD(old_selem_free_list);
-       unsigned long flags;
+       unsigned long flags, b_flags;
        int err;
 
        /* BPF_EXIST and BPF_NOEXIST cannot be both set */
@@ -579,20 +595,25 @@ bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap,
                goto unlock;
        }
 
+       b = select_bucket(smap, local_storage);
+
+       raw_spin_lock_irqsave(&b->lock, b_flags);
+
        alloc_selem = NULL;
        /* First, link the new selem to the map */
-       bpf_selem_link_map(smap, local_storage, selem);
+       bpf_selem_link_map_nolock(b, selem);
 
        /* Second, link (and publish) the new selem to local_storage */
        bpf_selem_link_storage_nolock(local_storage, selem);
 
        /* Third, remove old selem, SELEM(old_sdata) */
        if (old_sdata) {
-               bpf_selem_unlink_map(SELEM(old_sdata));
+               bpf_selem_unlink_map_nolock(SELEM(old_sdata));
                bpf_selem_unlink_storage_nolock(local_storage, SELEM(old_sdata),
                                                &old_selem_free_list);
        }
 
+       raw_spin_unlock_irqrestore(&b->lock, b_flags);
 unlock:
        raw_spin_unlock_irqrestore(&local_storage->lock, flags);
        bpf_selem_free_list(&old_selem_free_list, false);