Merge tag 'for-netdev' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
pull-request: bpf-next 2022-10-18

We've added 33 non-merge commits during the last 14 day(s) which contain
a total of 31 files changed, 874 insertions(+), 538 deletions(-).

The main changes are:

1) Add RCU grace period chaining to BPF to wait for the completion
   of access from both sleepable and non-sleepable BPF programs,
   from Hou Tao & Paul E. McKenney.

2) Improve helper UAPI by explicitly defining BPF_FUNC_xxx integer
   values. In the wild we have seen OS vendors doing buggy backports
   where helper call numbers mismatched. This is an attempt to make
   backports more foolproof, from Andrii Nakryiko.

3) Add libbpf *_opts API-variants for bpf_*_get_fd_by_id() functions,
   from Roberto Sassu.

4) Fix libbpf's BTF dumper for structs with padding-only fields,
   from Eduard Zingerman.

5) Fix various libbpf bugs which have been found from fuzzing with
   malformed BPF object files, from Shung-Hsi Yu.

6) Clean up an unneeded check on existence of SSE2 in BPF x86-64 JIT,
   from Jie Meng.

7) Fix various ASAN bugs in both libbpf and selftests when running
   the BPF selftest suite on arm64, from Xu Kuohai.

8) Fix missing bpf_iter_vma_offset__destroy() call in BPF iter selftest
   and use in-skeleton link pointer to remove an explicit bpf_link__destroy(),
   from Jiri Olsa.

9) Fix BPF CI breakage by pointing to iptables-legacy instead of relying
   on symlinked iptables which got upgraded to iptables-nft,
   from Martin KaFai Lau.

10) Minor BPF selftest improvements all over the place, from various others.

* tag 'for-netdev' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (33 commits)
  bpf/docs: Update README for most recent vmtest.sh
  bpf: Use rcu_trace_implies_rcu_gp() for program array freeing
  bpf: Use rcu_trace_implies_rcu_gp() in local storage map
  bpf: Use rcu_trace_implies_rcu_gp() in bpf memory allocator
  rcu-tasks: Provide rcu_trace_implies_rcu_gp()
  selftests/bpf: Use sys_pidfd_open() helper when possible
  libbpf: Fix null-pointer dereference in find_prog_by_sec_insn()
  libbpf: Deal with section with no data gracefully
  libbpf: Use elf_getshdrnum() instead of e_shnum
  selftest/bpf: Fix error usage of ASSERT_OK in xdp_adjust_tail.c
  selftests/bpf: Fix error failure of case test_xdp_adjust_tail_grow
  selftest/bpf: Fix memory leak in kprobe_multi_test
  selftests/bpf: Fix memory leak caused by not destroying skeleton
  libbpf: Fix memory leak in parse_usdt_arg()
  libbpf: Fix use-after-free in btf_dump_name_dups
  selftests/bpf: S/iptables/iptables-legacy/ in the bpf_nf and xdp_synproxy test
  selftests/bpf: Alphabetize DENYLISTs
  selftests/bpf: Add tests for _opts variants of bpf_*_get_fd_by_id()
  libbpf: Introduce bpf_link_get_fd_by_id_opts()
  libbpf: Introduce bpf_btf_get_fd_by_id_opts()
  ...
====================

Link: https://lore.kernel.org/r/20221018210631.11211-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

4 files changed, 30 insertions, 8 deletions

diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c
index 802fc15b0d73..9dc6de1cf185 100644
--- a/kernel/bpf/bpf_local_storage.c
+++ b/kernel/bpf/bpf_local_storage.c
@@ -88,8 +88,14 @@ void bpf_local_storage_free_rcu(struct rcu_head *rcu)
 {
 	struct bpf_local_storage *local_storage;
 
+	/* If RCU Tasks Trace grace period implies RCU grace period, do
+	 * kfree(), else do kfree_rcu().
+	 */
 	local_storage = container_of(rcu, struct bpf_local_storage, rcu);
-	kfree_rcu(local_storage, rcu);
+	if (rcu_trace_implies_rcu_gp())
+		kfree(local_storage);
+	else
+		kfree_rcu(local_storage, rcu);
 }
 
 static void bpf_selem_free_rcu(struct rcu_head *rcu)
@@ -97,7 +103,10 @@ 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);
+	if (rcu_trace_implies_rcu_gp())
+		kfree(selem);
+	else
+		kfree_rcu(selem, rcu);
 }
 
 /* local_storage->lock must be held and selem->local_storage == local_storage.
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 59cf4dc728a5..a0e762a2bf97 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -2251,8 +2251,14 @@ static void __bpf_prog_array_free_sleepable_cb(struct rcu_head *rcu)
 {
 	struct bpf_prog_array *progs;
 
+	/* If RCU Tasks Trace grace period implies RCU grace period, there is
+	 * no need to call kfree_rcu(), just call kfree() directly.
+	 */
 	progs = container_of(rcu, struct bpf_prog_array, rcu);
-	kfree_rcu(progs, rcu);
+	if (rcu_trace_implies_rcu_gp())
+		kfree(progs);
+	else
+		kfree_rcu(progs, rcu);
 }
 
 void bpf_prog_array_free_sleepable(struct bpf_prog_array *progs)
diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index 5f83be1d2018..2433be58bb85 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -222,9 +222,13 @@ static void __free_rcu(struct rcu_head *head)
 
 static void __free_rcu_tasks_trace(struct rcu_head *head)
 {
-	struct bpf_mem_cache *c = container_of(head, struct bpf_mem_cache, rcu);
-
-	call_rcu(&c->rcu, __free_rcu);
+	/* If RCU Tasks Trace grace period implies RCU grace period,
+	 * there is no need to invoke call_rcu().
+	 */
+	if (rcu_trace_implies_rcu_gp())
+		__free_rcu(head);
+	else
+		call_rcu(head, __free_rcu);
 }
 
 static void enque_to_free(struct bpf_mem_cache *c, void *obj)
@@ -253,8 +257,9 @@ static void do_call_rcu(struct bpf_mem_cache *c)
 		 */
 		__llist_add(llnode, &c->waiting_for_gp);
 	/* Use call_rcu_tasks_trace() to wait for sleepable progs to finish.
-	 * Then use call_rcu() to wait for normal progs to finish
-	 * and finally do free_one() on each element.
+	 * If RCU Tasks Trace grace period implies RCU grace period, free
+	 * these elements directly, else use call_rcu() to wait for normal
+	 * progs to finish and finally do free_one() on each element.
 	 */
 	call_rcu_tasks_trace(&c->rcu, __free_rcu_tasks_trace);
 }
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index f5bf6fb430da..9435e5a7b53e 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -1535,6 +1535,8 @@ static void rcu_tasks_trace_postscan(struct list_head *hop)
 {
 	// Wait for late-stage exiting tasks to finish exiting.
 	// These might have passed the call to exit_tasks_rcu_finish().
+
+	// If you remove the following line, update rcu_trace_implies_rcu_gp()!!!
 	synchronize_rcu();
 	// Any tasks that exit after this point will set
 	// TRC_NEED_QS_CHECKED in ->trc_reader_special.b.need_qs.