bpf: Enable task local storage for tracing programs

To access per-task data, BPF programs usually creates a hash table with
pid as the key. This is not ideal because:
 1. The user need to estimate the proper size of the hash table, which may
    be inaccurate;
 2. Big hash tables are slow;
 3. To clean up the data properly during task terminations, the user need
    to write extra logic.

Task local storage overcomes these issues and offers a better option for
these per-task data. Task local storage is only available to BPF_LSM. Now
enable it for tracing programs.

Unlike LSM programs, tracing programs can be called in IRQ contexts.
Helpers that access task local storage are updated to use
raw_spin_lock_irqsave() instead of raw_spin_lock_bh().

Tracing programs can attach to functions on the task free path, e.g.
exit_creds(). To avoid allocating task local storage after
bpf_task_storage_free(). bpf_task_storage_get() is updated to not allocate
new storage when the task is not refcounted (task->usage == 0).

Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: KP Singh <kpsingh@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20210225234319.336131-2-songliubraving@fb.com

1 files changed, 17 insertions, 11 deletions

diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c
index dd5aedee99e7..9bd47ad2b26f 100644
--- a/kernel/bpf/bpf_local_storage.c
+++ b/kernel/bpf/bpf_local_storage.c
@@ -140,17 +140,18 @@ static void __bpf_selem_unlink_storage(struct bpf_local_storage_elem *selem)
 {
 	struct bpf_local_storage *local_storage;
 	bool free_local_storage = false;
+	unsigned long flags;
 
 	if (unlikely(!selem_linked_to_storage(selem)))
 		/* selem has already been unlinked from sk */
 		return;
 
 	local_storage = rcu_dereference(selem->local_storage);
-	raw_spin_lock_bh(&local_storage->lock);
+	raw_spin_lock_irqsave(&local_storage->lock, flags);
 	if (likely(selem_linked_to_storage(selem)))
 		free_local_storage = bpf_selem_unlink_storage_nolock(
 			local_storage, selem, true);
-	raw_spin_unlock_bh(&local_storage->lock);
+	raw_spin_unlock_irqrestore(&local_storage->lock, flags);
 
 	if (free_local_storage)
 		kfree_rcu(local_storage, rcu);
@@ -167,6 +168,7 @@ void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem)
 {
 	struct bpf_local_storage_map *smap;
 	struct bpf_local_storage_map_bucket *b;
+	unsigned long flags;
 
 	if (unlikely(!selem_linked_to_map(selem)))
 		/* selem has already be unlinked from smap */
@@ -174,21 +176,22 @@ void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem)
 
 	smap = rcu_dereference(SDATA(selem)->smap);
 	b = select_bucket(smap, selem);
-	raw_spin_lock_bh(&b->lock);
+	raw_spin_lock_irqsave(&b->lock, flags);
 	if (likely(selem_linked_to_map(selem)))
 		hlist_del_init_rcu(&selem->map_node);
-	raw_spin_unlock_bh(&b->lock);
+	raw_spin_unlock_irqrestore(&b->lock, flags);
 }
 
 void bpf_selem_link_map(struct bpf_local_storage_map *smap,
 			struct bpf_local_storage_elem *selem)
 {
 	struct bpf_local_storage_map_bucket *b = select_bucket(smap, selem);
+	unsigned long flags;
 
-	raw_spin_lock_bh(&b->lock);
+	raw_spin_lock_irqsave(&b->lock, flags);
 	RCU_INIT_POINTER(SDATA(selem)->smap, smap);
 	hlist_add_head_rcu(&selem->map_node, &b->list);
-	raw_spin_unlock_bh(&b->lock);
+	raw_spin_unlock_irqrestore(&b->lock, flags);
 }
 
 void bpf_selem_unlink(struct bpf_local_storage_elem *selem)
@@ -224,16 +227,18 @@ bpf_local_storage_lookup(struct bpf_local_storage *local_storage,
 
 	sdata = SDATA(selem);
 	if (cacheit_lockit) {
+		unsigned long flags;
+
 		/* 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);
+		raw_spin_lock_irqsave(&local_storage->lock, flags);
 		if (selem_linked_to_storage(selem))
 			rcu_assign_pointer(local_storage->cache[smap->cache_idx],
 					   sdata);
-		raw_spin_unlock_bh(&local_storage->lock);
+		raw_spin_unlock_irqrestore(&local_storage->lock, flags);
 	}
 
 	return sdata;
@@ -327,6 +332,7 @@ 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 *selem;
 	struct bpf_local_storage *local_storage;
+	unsigned long flags;
 	int err;
 
 	/* BPF_EXIST and BPF_NOEXIST cannot be both set */
@@ -374,7 +380,7 @@ bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap,
 		}
 	}
 
-	raw_spin_lock_bh(&local_storage->lock);
+	raw_spin_lock_irqsave(&local_storage->lock, flags);
 
 	/* Recheck local_storage->list under local_storage->lock */
 	if (unlikely(hlist_empty(&local_storage->list))) {
@@ -428,11 +434,11 @@ bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap,
 	}
 
 unlock:
-	raw_spin_unlock_bh(&local_storage->lock);
+	raw_spin_unlock_irqrestore(&local_storage->lock, flags);
 	return SDATA(selem);
 
 unlock_err:
-	raw_spin_unlock_bh(&local_storage->lock);
+	raw_spin_unlock_irqrestore(&local_storage->lock, flags);
 	return ERR_PTR(err);
 }