bpf: Avoid taking spinlock in bpf_task_storage_get if potential deadlock is detected

bpf_task_storage_get() does a lookup and optionally inserts
new data if BPF_LOCAL_STORAGE_GET_F_CREATE is present.

During lookup, it will cache the lookup result and caching requires to
acquire a spinlock.  When potential deadlock is detected (by the
bpf_task_storage_busy pcpu-counter added in
commit bc235cdb423a ("bpf: Prevent deadlock from recursive bpf_task_storage_[get|delete]")),
the current behavior is returning NULL immediately to avoid deadlock.  It is
too pessimistic.  This patch will go ahead to do a lookup (which is a
lockless operation) but it will avoid caching it in order to avoid
acquiring the spinlock.

When lookup fails to find the data and BPF_LOCAL_STORAGE_GET_F_CREATE
is set, an insertion is needed and this requires acquiring a spinlock.
This patch will still return NULL when a potential deadlock is detected.

Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://lore.kernel.org/r/20221025184524.3526117-5-martin.lau@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c
index 9dc6de1cf18530beeebf056dad3eb95f4b269dc8..781d14167140d960159f9dff9b55454d84cc76af 100644 (file)
--- a/kernel/bpf/bpf_local_storage.c
+++ b/kernel/bpf/bpf_local_storage.c
@@ -242,6 +242,7 @@ void bpf_selem_unlink(struct bpf_local_storage_elem *selem, bool use_trace_rcu)
        __bpf_selem_unlink_storage(selem, use_trace_rcu);
 }
 
+/* If cacheit_lockit is false, this lookup function is lockless */
 struct bpf_local_storage_data *
 bpf_local_storage_lookup(struct bpf_local_storage *local_storage,
                         struct bpf_local_storage_map *smap,

diff --git a/kernel/bpf/bpf_task_storage.c b/kernel/bpf/bpf_task_storage.c
index 2726435e3eda914407d998f938dad35b6e584c6e..bc52bc8b59f796ec97f21eb271090db4dfaa4746 100644 (file)
--- a/kernel/bpf/bpf_task_storage.c
+++ b/kernel/bpf/bpf_task_storage.c
@@ -230,17 +230,17 @@ out:
 /* Called by bpf_task_storage_get*() helpers */
 static void *__bpf_task_storage_get(struct bpf_map *map,
                                    struct task_struct *task, void *value,
-                                   u64 flags, gfp_t gfp_flags)
+                                   u64 flags, gfp_t gfp_flags, bool nobusy)
 {
        struct bpf_local_storage_data *sdata;
 
-       sdata = task_storage_lookup(task, map, true);
+       sdata = task_storage_lookup(task, map, nobusy);
        if (sdata)
                return sdata->data;
 
        /* only allocate new storage, when the task is refcounted */
        if (refcount_read(&task->usage) &&
-           (flags & BPF_LOCAL_STORAGE_GET_F_CREATE)) {
+           (flags & BPF_LOCAL_STORAGE_GET_F_CREATE) && nobusy) {
                sdata = bpf_local_storage_update(
                        task, (struct bpf_local_storage_map *)map, value,
                        BPF_NOEXIST, gfp_flags);
@@ -254,17 +254,18 @@ static void *__bpf_task_storage_get(struct bpf_map *map,
 BPF_CALL_5(bpf_task_storage_get_recur, struct bpf_map *, map, struct task_struct *,
           task, void *, value, u64, flags, gfp_t, gfp_flags)
 {
+       bool nobusy;
        void *data;
 
        WARN_ON_ONCE(!bpf_rcu_lock_held());
        if (flags & ~BPF_LOCAL_STORAGE_GET_F_CREATE || !task)
                return (unsigned long)NULL;
 
-       if (!bpf_task_storage_trylock())
-               return (unsigned long)NULL;
+       nobusy = bpf_task_storage_trylock();
        data = __bpf_task_storage_get(map, task, value, flags,
-                                     gfp_flags);
-       bpf_task_storage_unlock();
+                                     gfp_flags, nobusy);
+       if (nobusy)
+               bpf_task_storage_unlock();
        return (unsigned long)data;
 }