Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Alexei Starovoitov says:

====================
pull-request: bpf-next 2021-12-30

The following pull-request contains BPF updates for your *net-next* tree.

We've added 72 non-merge commits during the last 20 day(s) which contain
a total of 223 files changed, 3510 insertions(+), 1591 deletions(-).

The main changes are:

1) Automatic setrlimit in libbpf when bpf is memcg's in the kernel, from Andrii.

2) Beautify and de-verbose verifier logs, from Christy.

3) Composable verifier types, from Hao.

4) bpf_strncmp helper, from Hou.

5) bpf.h header dependency cleanup, from Jakub.

6) get_func_[arg|ret|arg_cnt] helpers, from Jiri.

7) Sleepable local storage, from KP.

8) Extend kfunc with PTR_TO_CTX, PTR_TO_MEM argument support, from Kumar.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 37 insertions, 13 deletions

diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c
index b305270b7a4b..71de2a89869c 100644
--- a/kernel/bpf/bpf_local_storage.c
+++ b/kernel/bpf/bpf_local_storage.c
@@ -11,6 +11,9 @@
 #include <net/sock.h>
 #include <uapi/linux/sock_diag.h>
 #include <uapi/linux/btf.h>
+#include <linux/rcupdate.h>
+#include <linux/rcupdate_trace.h>
+#include <linux/rcupdate_wait.h>
 
 #define BPF_LOCAL_STORAGE_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_CLONE)
 
@@ -81,6 +84,22 @@ bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner,
 	return NULL;
 }
 
+void bpf_local_storage_free_rcu(struct rcu_head *rcu)
+{
+	struct bpf_local_storage *local_storage;
+
+	local_storage = container_of(rcu, struct bpf_local_storage, rcu);
+	kfree_rcu(local_storage, rcu);
+}
+
+static void bpf_selem_free_rcu(struct rcu_head *rcu)
+{
+	struct bpf_local_storage_elem *selem;
+
+	selem = container_of(rcu, struct bpf_local_storage_elem, rcu);
+	kfree_rcu(selem, rcu);
+}
+
 /* 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.
@@ -93,7 +112,7 @@ bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage,
 	bool free_local_storage;
 	void *owner;
 
-	smap = rcu_dereference(SDATA(selem)->smap);
+	smap = rcu_dereference_check(SDATA(selem)->smap, bpf_rcu_lock_held());
 	owner = local_storage->owner;
 
 	/* All uncharging on the owner must be done first.
@@ -118,12 +137,12 @@ bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage,
 		 *
 		 * Although the unlock will be done under
 		 * rcu_read_lock(),  it is more intutivie to
-		 * read if kfree_rcu(local_storage, rcu) is done
+		 * read if the freeing of the storage 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.
+		 * to the caller which then calls then frees the storage after
+		 * all the RCU grace periods have expired.
 		 */
 	}
 	hlist_del_init_rcu(&selem->snode);
@@ -131,8 +150,7 @@ bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage,
 	    SDATA(selem))
 		RCU_INIT_POINTER(local_storage->cache[smap->cache_idx], NULL);
 
-	kfree_rcu(selem, rcu);
-
+	call_rcu_tasks_trace(&selem->rcu, bpf_selem_free_rcu);
 	return free_local_storage;
 }
 
@@ -146,7 +164,8 @@ static void __bpf_selem_unlink_storage(struct bpf_local_storage_elem *selem)
 		/* selem has already been unlinked from sk */
 		return;
 
-	local_storage = rcu_dereference(selem->local_storage);
+	local_storage = rcu_dereference_check(selem->local_storage,
+					      bpf_rcu_lock_held());
 	raw_spin_lock_irqsave(&local_storage->lock, flags);
 	if (likely(selem_linked_to_storage(selem)))
 		free_local_storage = bpf_selem_unlink_storage_nolock(
@@ -154,7 +173,8 @@ static void __bpf_selem_unlink_storage(struct bpf_local_storage_elem *selem)
 	raw_spin_unlock_irqrestore(&local_storage->lock, flags);
 
 	if (free_local_storage)
-		kfree_rcu(local_storage, rcu);
+		call_rcu_tasks_trace(&local_storage->rcu,
+				     bpf_local_storage_free_rcu);
 }
 
 void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage,
@@ -174,7 +194,7 @@ void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem)
 		/* selem has already be unlinked from smap */
 		return;
 
-	smap = rcu_dereference(SDATA(selem)->smap);
+	smap = rcu_dereference_check(SDATA(selem)->smap, bpf_rcu_lock_held());
 	b = select_bucket(smap, selem);
 	raw_spin_lock_irqsave(&b->lock, flags);
 	if (likely(selem_linked_to_map(selem)))
@@ -213,12 +233,14 @@ bpf_local_storage_lookup(struct bpf_local_storage *local_storage,
 	struct bpf_local_storage_elem *selem;
 
 	/* Fast path (cache hit) */
-	sdata = rcu_dereference(local_storage->cache[smap->cache_idx]);
+	sdata = rcu_dereference_check(local_storage->cache[smap->cache_idx],
+				      bpf_rcu_lock_held());
 	if (sdata && rcu_access_pointer(sdata->smap) == smap)
 		return sdata;
 
 	/* Slow path (cache miss) */
-	hlist_for_each_entry_rcu(selem, &local_storage->list, snode)
+	hlist_for_each_entry_rcu(selem, &local_storage->list, snode,
+				  rcu_read_lock_trace_held())
 		if (rcu_access_pointer(SDATA(selem)->smap) == smap)
 			break;
 
@@ -306,7 +328,8 @@ int bpf_local_storage_alloc(void *owner,
 		 * 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.
+		 * synchronize_rcu_mult (waiting for both sleepable and
+		 * normal programs) before walking the bucket->list.
 		 * Hence, no one is accessing selem from the
 		 * bucket->list under rcu_read_lock().
 		 */
@@ -342,7 +365,8 @@ bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap,
 		     !map_value_has_spin_lock(&smap->map)))
 		return ERR_PTR(-EINVAL);
 
-	local_storage = rcu_dereference(*owner_storage(smap, owner));
+	local_storage = rcu_dereference_check(*owner_storage(smap, owner),
+					      bpf_rcu_lock_held());
 	if (!local_storage || hlist_empty(&local_storage->list)) {
 		/* Very first elem for the owner */
 		err = check_flags(NULL, map_flags);