Merge tag 'bpf-next-6.16' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-nextHEADmaster

Pull bpf updates from Alexei Starovoitov:

 - Fix and improve BTF deduplication of identical BTF types (Alan
   Maguire and Andrii Nakryiko)

 - Support up to 12 arguments in BPF trampoline on arm64 (Xu Kuohai and
   Alexis Lothoré)

 - Support load-acquire and store-release instructions in BPF JIT on
   riscv64 (Andrea Parri)

 - Fix uninitialized values in BPF_{CORE,PROBE}_READ macros (Anton
   Protopopov)

 - Streamline allowed helpers across program types (Feng Yang)

 - Support atomic update for hashtab of BPF maps (Hou Tao)

 - Implement json output for BPF helpers (Ihor Solodrai)

 - Several s390 JIT fixes (Ilya Leoshkevich)

 - Various sockmap fixes (Jiayuan Chen)

 - Support mmap of vmlinux BTF data (Lorenz Bauer)

 - Support BPF rbtree traversal and list peeking (Martin KaFai Lau)

 - Tests for sockmap/sockhash redirection (Michal Luczaj)

 - Introduce kfuncs for memory reads into dynptrs (Mykyta Yatsenko)

 - Add support for dma-buf iterators in BPF (T.J. Mercier)

 - The verifier support for __bpf_trap() (Yonghong Song)

* tag 'bpf-next-6.16' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (135 commits)
  bpf, arm64: Remove unused-but-set function and variable.
  selftests/bpf: Add tests with stack ptr register in conditional jmp
  bpf: Do not include stack ptr register in precision backtracking bookkeeping
  selftests/bpf: enable many-args tests for arm64
  bpf, arm64: Support up to 12 function arguments
  bpf: Check rcu_read_lock_trace_held() in bpf_map_lookup_percpu_elem()
  bpf: Avoid __bpf_prog_ret0_warn when jit fails
  bpftool: Add support for custom BTF path in prog load/loadall
  selftests/bpf: Add unit tests with __bpf_trap() kfunc
  bpf: Warn with __bpf_trap() kfunc maybe due to uninitialized variable
  bpf: Remove special_kfunc_set from verifier
  selftests/bpf: Add test for open coded dmabuf_iter
  selftests/bpf: Add test for dmabuf_iter
  bpf: Add open coded dmabuf iterator
  bpf: Add dmabuf iterator
  dma-buf: Rename debugfs symbols
  bpf: Fix error return value in bpf_copy_from_user_dynptr
  libbpf: Use mmap to parse vmlinux BTF from sysfs
  selftests: bpf: Add a test for mmapable vmlinux BTF
  btf: Allow mmap of vmlinux btf
  ...

2 files changed, 35 insertions, 35 deletions

diff --git a/net/core/filter.c b/net/core/filter.c
index 577a4504e26f..ab456bf1056e 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -8023,10 +8023,6 @@ sock_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	if (func_proto)
 		return func_proto;
 
-	func_proto = cgroup_current_func_proto(func_id, prog);
-	if (func_proto)
-		return func_proto;
-
 	switch (func_id) {
 	case BPF_FUNC_get_socket_cookie:
 		return &bpf_get_socket_cookie_sock_proto;
@@ -8052,10 +8048,6 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	if (func_proto)
 		return func_proto;
 
-	func_proto = cgroup_current_func_proto(func_id, prog);
-	if (func_proto)
-		return func_proto;
-
 	switch (func_id) {
 	case BPF_FUNC_bind:
 		switch (prog->expected_attach_type) {
@@ -8489,18 +8481,12 @@ sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_msg_pop_data_proto;
 	case BPF_FUNC_perf_event_output:
 		return &bpf_event_output_data_proto;
-	case BPF_FUNC_get_current_uid_gid:
-		return &bpf_get_current_uid_gid_proto;
 	case BPF_FUNC_sk_storage_get:
 		return &bpf_sk_storage_get_proto;
 	case BPF_FUNC_sk_storage_delete:
 		return &bpf_sk_storage_delete_proto;
 	case BPF_FUNC_get_netns_cookie:
 		return &bpf_get_netns_cookie_sk_msg_proto;
-#ifdef CONFIG_CGROUP_NET_CLASSID
-	case BPF_FUNC_get_cgroup_classid:
-		return &bpf_get_cgroup_classid_curr_proto;
-#endif
 	default:
 		return bpf_sk_base_func_proto(func_id, prog);
 	}
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 0ddc4c718833..34c51eb1a14f 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -530,16 +530,22 @@ static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb,
 					u32 off, u32 len,
 					struct sk_psock *psock,
 					struct sock *sk,
-					struct sk_msg *msg)
+					struct sk_msg *msg,
+					bool take_ref)
 {
 	int num_sge, copied;
 
+	/* skb_to_sgvec will fail when the total number of fragments in
+	 * frag_list and frags exceeds MAX_MSG_FRAGS. For example, the
+	 * caller may aggregate multiple skbs.
+	 */
 	num_sge = skb_to_sgvec(skb, msg->sg.data, off, len);
 	if (num_sge < 0) {
 		/* skb linearize may fail with ENOMEM, but lets simply try again
 		 * later if this happens. Under memory pressure we don't want to
 		 * drop the skb. We need to linearize the skb so that the mapping
 		 * in skb_to_sgvec can not error.
+		 * Note that skb_linearize requires the skb not to be shared.
 		 */
 		if (skb_linearize(skb))
 			return -EAGAIN;
@@ -556,7 +562,7 @@ static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb,
 	msg->sg.start = 0;
 	msg->sg.size = copied;
 	msg->sg.end = num_sge;
-	msg->skb = skb;
+	msg->skb = take_ref ? skb_get(skb) : skb;
 
 	sk_psock_queue_msg(psock, msg);
 	sk_psock_data_ready(sk, psock);
@@ -564,7 +570,7 @@ static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb,
 }
 
 static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb,
-				     u32 off, u32 len);
+				     u32 off, u32 len, bool take_ref);
 
 static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb,
 				u32 off, u32 len)
@@ -578,7 +584,7 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb,
 	 * correctly.
 	 */
 	if (unlikely(skb->sk == sk))
-		return sk_psock_skb_ingress_self(psock, skb, off, len);
+		return sk_psock_skb_ingress_self(psock, skb, off, len, true);
 	msg = sk_psock_create_ingress_msg(sk, skb);
 	if (!msg)
 		return -EAGAIN;
@@ -590,7 +596,7 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb,
 	 * into user buffers.
 	 */
 	skb_set_owner_r(skb, sk);
-	err = sk_psock_skb_ingress_enqueue(skb, off, len, psock, sk, msg);
+	err = sk_psock_skb_ingress_enqueue(skb, off, len, psock, sk, msg, true);
 	if (err < 0)
 		kfree(msg);
 	return err;
@@ -601,7 +607,7 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb,
  * because the skb is already accounted for here.
  */
 static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb,
-				     u32 off, u32 len)
+				     u32 off, u32 len, bool take_ref)
 {
 	struct sk_msg *msg = alloc_sk_msg(GFP_ATOMIC);
 	struct sock *sk = psock->sk;
@@ -610,7 +616,7 @@ static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb
 	if (unlikely(!msg))
 		return -EAGAIN;
 	skb_set_owner_r(skb, sk);
-	err = sk_psock_skb_ingress_enqueue(skb, off, len, psock, sk, msg);
+	err = sk_psock_skb_ingress_enqueue(skb, off, len, psock, sk, msg, take_ref);
 	if (err < 0)
 		kfree(msg);
 	return err;
@@ -619,18 +625,13 @@ static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb
 static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb,
 			       u32 off, u32 len, bool ingress)
 {
-	int err = 0;
-
 	if (!ingress) {
 		if (!sock_writeable(psock->sk))
 			return -EAGAIN;
 		return skb_send_sock(psock->sk, skb, off, len);
 	}
-	skb_get(skb);
-	err = sk_psock_skb_ingress(psock, skb, off, len);
-	if (err < 0)
-		kfree_skb(skb);
-	return err;
+
+	return sk_psock_skb_ingress(psock, skb, off, len);
 }
 
 static void sk_psock_skb_state(struct sk_psock *psock,
@@ -655,12 +656,14 @@ static void sk_psock_backlog(struct work_struct *work)
 	bool ingress;
 	int ret;
 
+	/* Increment the psock refcnt to synchronize with close(fd) path in
+	 * sock_map_close(), ensuring we wait for backlog thread completion
+	 * before sk_socket freed. If refcnt increment fails, it indicates
+	 * sock_map_close() completed with sk_socket potentially already freed.
+	 */
+	if (!sk_psock_get(psock->sk))
+		return;
 	mutex_lock(&psock->work_mutex);
-	if (unlikely(state->len)) {
-		len = state->len;
-		off = state->off;
-	}
-
 	while ((skb = skb_peek(&psock->ingress_skb))) {
 		len = skb->len;
 		off = 0;
@@ -670,6 +673,13 @@ static void sk_psock_backlog(struct work_struct *work)
 			off = stm->offset;
 			len = stm->full_len;
 		}
+
+		/* Resume processing from previous partial state */
+		if (unlikely(state->len)) {
+			len = state->len;
+			off = state->off;
+		}
+
 		ingress = skb_bpf_ingress(skb);
 		skb_bpf_redirect_clear(skb);
 		do {
@@ -680,7 +690,8 @@ static void sk_psock_backlog(struct work_struct *work)
 			if (ret <= 0) {
 				if (ret == -EAGAIN) {
 					sk_psock_skb_state(psock, state, len, off);
-
+					/* Restore redir info we cleared before */
+					skb_bpf_set_redir(skb, psock->sk, ingress);
 					/* Delay slightly to prioritize any
 					 * other work that might be here.
 					 */
@@ -697,11 +708,14 @@ static void sk_psock_backlog(struct work_struct *work)
 			len -= ret;
 		} while (len);
 
+		/* The entire skb sent, clear state */
+		sk_psock_skb_state(psock, state, 0, 0);
 		skb = skb_dequeue(&psock->ingress_skb);
 		kfree_skb(skb);
 	}
 end:
 	mutex_unlock(&psock->work_mutex);
+	sk_psock_put(psock->sk, psock);
 }
 
 struct sk_psock *sk_psock_init(struct sock *sk, int node)
@@ -1014,7 +1028,7 @@ static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb,
 				off = stm->offset;
 				len = stm->full_len;
 			}
-			err = sk_psock_skb_ingress_self(psock, skb, off, len);
+			err = sk_psock_skb_ingress_self(psock, skb, off, len, false);
 		}
 		if (err < 0) {
 			spin_lock_bh(&psock->ingress_lock);