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

Alexei Starovoitov says:

====================
pull-request: bpf 2022-10-23

We've added 7 non-merge commits during the last 18 day(s) which contain
a total of 8 files changed, 69 insertions(+), 5 deletions(-).

The main changes are:

1) Wait for busy refill_work when destroying bpf memory allocator, from Hou.

2) Allow bpf_user_ringbuf_drain() callbacks to return 1, from David.

3) Fix dispatcher patchable function entry to 5 bytes nop, from Jiri.

4) Prevent decl_tag from being referenced in func_proto, from Stanislav.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf:
  bpf: Use __llist_del_all() whenever possbile during memory draining
  bpf: Wait for busy refill_work when destroying bpf memory allocator
  bpf: Fix dispatcher patchable function entry to 5 bytes nop
  bpf: prevent decl_tag from being referenced in func_proto
  selftests/bpf: Add reproducer for decl_tag in func_proto return type
  selftests/bpf: Make bpf_user_ringbuf_drain() selftest callback return 1
  bpf: Allow bpf_user_ringbuf_drain() callbacks to return 1
====================

Link: https://lore.kernel.org/r/20221023192244.81137-1-alexei.starovoitov@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

4 files changed, 28 insertions, 2 deletions

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index eba603cec2c5..35c07afac924 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -4436,6 +4436,11 @@ static int btf_func_proto_check(struct btf_verifier_env *env,
 			return -EINVAL;
 		}
 
+		if (btf_type_is_resolve_source_only(ret_type)) {
+			btf_verifier_log_type(env, t, "Invalid return type");
+			return -EINVAL;
+		}
+
 		if (btf_type_needs_resolve(ret_type) &&
 		    !env_type_is_resolved(env, ret_type_id)) {
 			err = btf_resolve(env, ret_type, ret_type_id);
diff --git a/kernel/bpf/dispatcher.c b/kernel/bpf/dispatcher.c
index fa64b80b8bca..04f0a045dcaa 100644
--- a/kernel/bpf/dispatcher.c
+++ b/kernel/bpf/dispatcher.c
@@ -4,6 +4,7 @@
 #include <linux/hash.h>
 #include <linux/bpf.h>
 #include <linux/filter.h>
+#include <linux/init.h>
 
 /* The BPF dispatcher is a multiway branch code generator. The
  * dispatcher is a mechanism to avoid the performance penalty of an
@@ -90,6 +91,11 @@ int __weak arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int n
 	return -ENOTSUPP;
 }
 
+int __weak __init bpf_arch_init_dispatcher_early(void *ip)
+{
+	return -ENOTSUPP;
+}
+
 static int bpf_dispatcher_prepare(struct bpf_dispatcher *d, void *image, void *buf)
 {
 	s64 ips[BPF_DISPATCHER_MAX] = {}, *ipsp = &ips[0];
diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index 5f83be1d2018..4901fa1048cd 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -418,14 +418,17 @@ static void drain_mem_cache(struct bpf_mem_cache *c)
 	/* No progs are using this bpf_mem_cache, but htab_map_free() called
 	 * bpf_mem_cache_free() for all remaining elements and they can be in
 	 * free_by_rcu or in waiting_for_gp lists, so drain those lists now.
+	 *
+	 * Except for waiting_for_gp list, there are no concurrent operations
+	 * on these lists, so it is safe to use __llist_del_all().
 	 */
 	llist_for_each_safe(llnode, t, __llist_del_all(&c->free_by_rcu))
 		free_one(c, llnode);
 	llist_for_each_safe(llnode, t, llist_del_all(&c->waiting_for_gp))
 		free_one(c, llnode);
-	llist_for_each_safe(llnode, t, llist_del_all(&c->free_llist))
+	llist_for_each_safe(llnode, t, __llist_del_all(&c->free_llist))
 		free_one(c, llnode);
-	llist_for_each_safe(llnode, t, llist_del_all(&c->free_llist_extra))
+	llist_for_each_safe(llnode, t, __llist_del_all(&c->free_llist_extra))
 		free_one(c, llnode);
 }
 
@@ -493,6 +496,16 @@ void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma)
 		rcu_in_progress = 0;
 		for_each_possible_cpu(cpu) {
 			c = per_cpu_ptr(ma->cache, cpu);
+			/*
+			 * refill_work may be unfinished for PREEMPT_RT kernel
+			 * in which irq work is invoked in a per-CPU RT thread.
+			 * It is also possible for kernel with
+			 * arch_irq_work_has_interrupt() being false and irq
+			 * work is invoked in timer interrupt. So waiting for
+			 * the completion of irq work to ease the handling of
+			 * concurrency.
+			 */
+			irq_work_sync(&c->refill_work);
 			drain_mem_cache(c);
 			rcu_in_progress += atomic_read(&c->call_rcu_in_progress);
 		}
@@ -507,6 +520,7 @@ void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma)
 			cc = per_cpu_ptr(ma->caches, cpu);
 			for (i = 0; i < NUM_CACHES; i++) {
 				c = &cc->cache[i];
+				irq_work_sync(&c->refill_work);
 				drain_mem_cache(c);
 				rcu_in_progress += atomic_read(&c->call_rcu_in_progress);
 			}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 014ee0953dbd..7f0a9f6cb889 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -6946,6 +6946,7 @@ static int set_user_ringbuf_callback_state(struct bpf_verifier_env *env,
 	__mark_reg_not_init(env, &callee->regs[BPF_REG_5]);
 
 	callee->in_callback_fn = true;
+	callee->callback_ret_range = tnum_range(0, 1);
 	return 0;
 }