Merge remote-tracking branch 'wireless/main' into wireless-next

Pull in wireless/main content since some new code would
otherwise conflict with it.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>

6 files changed, 197 insertions, 41 deletions

diff --git a/net/core/devlink.c b/net/core/devlink.c
index 7776dc82f88d..89baa7c0938b 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -371,6 +371,13 @@ static struct devlink *devlink_get_from_attrs(struct net *net,
 	return ERR_PTR(-ENODEV);
 }
 
+#define ASSERT_DEVLINK_PORT_REGISTERED(devlink_port)				\
+	WARN_ON_ONCE(!(devlink_port)->registered)
+#define ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port)			\
+	WARN_ON_ONCE((devlink_port)->registered)
+#define ASSERT_DEVLINK_PORT_INITIALIZED(devlink_port)				\
+	WARN_ON_ONCE(!(devlink_port)->initialized)
+
 static struct devlink_port *devlink_port_get_by_index(struct devlink *devlink,
 						      unsigned int port_index)
 {
@@ -9848,6 +9855,44 @@ static void devlink_port_type_warn_cancel(struct devlink_port *devlink_port)
 }
 
 /**
+ * devlink_port_init() - Init devlink port
+ *
+ * @devlink: devlink
+ * @devlink_port: devlink port
+ *
+ * Initialize essencial stuff that is needed for functions
+ * that may be called before devlink port registration.
+ * Call to this function is optional and not needed
+ * in case the driver does not use such functions.
+ */
+void devlink_port_init(struct devlink *devlink,
+		       struct devlink_port *devlink_port)
+{
+	if (devlink_port->initialized)
+		return;
+	devlink_port->devlink = devlink;
+	INIT_LIST_HEAD(&devlink_port->region_list);
+	devlink_port->initialized = true;
+}
+EXPORT_SYMBOL_GPL(devlink_port_init);
+
+/**
+ * devlink_port_fini() - Deinitialize devlink port
+ *
+ * @devlink_port: devlink port
+ *
+ * Deinitialize essencial stuff that is in use for functions
+ * that may be called after devlink port unregistration.
+ * Call to this function is optional and not needed
+ * in case the driver does not use such functions.
+ */
+void devlink_port_fini(struct devlink_port *devlink_port)
+{
+	WARN_ON(!list_empty(&devlink_port->region_list));
+}
+EXPORT_SYMBOL_GPL(devlink_port_fini);
+
+/**
  * devl_port_register() - Register devlink port
  *
  * @devlink: devlink
@@ -9869,14 +9914,15 @@ int devl_port_register(struct devlink *devlink,
 	if (devlink_port_index_exists(devlink, port_index))
 		return -EEXIST;
 
-	WARN_ON(devlink_port->devlink);
-	devlink_port->devlink = devlink;
+	ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port);
+
+	devlink_port_init(devlink, devlink_port);
+	devlink_port->registered = true;
 	devlink_port->index = port_index;
 	spin_lock_init(&devlink_port->type_lock);
 	INIT_LIST_HEAD(&devlink_port->reporter_list);
 	mutex_init(&devlink_port->reporters_lock);
 	list_add_tail(&devlink_port->list, &devlink->port_list);
-	INIT_LIST_HEAD(&devlink_port->region_list);
 
 	INIT_DELAYED_WORK(&devlink_port->type_warn_dw, &devlink_port_type_warn);
 	devlink_port_type_warn_schedule(devlink_port);
@@ -9926,8 +9972,8 @@ void devl_port_unregister(struct devlink_port *devlink_port)
 	devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_DEL);
 	list_del(&devlink_port->list);
 	WARN_ON(!list_empty(&devlink_port->reporter_list));
-	WARN_ON(!list_empty(&devlink_port->region_list));
 	mutex_destroy(&devlink_port->reporters_lock);
+	devlink_port->registered = false;
 }
 EXPORT_SYMBOL_GPL(devl_port_unregister);
 
@@ -9952,8 +9998,8 @@ static void __devlink_port_type_set(struct devlink_port *devlink_port,
 				    enum devlink_port_type type,
 				    void *type_dev)
 {
-	if (WARN_ON(!devlink_port->devlink))
-		return;
+	ASSERT_DEVLINK_PORT_REGISTERED(devlink_port);
+
 	devlink_port_type_warn_cancel(devlink_port);
 	spin_lock_bh(&devlink_port->type_lock);
 	devlink_port->type = type;
@@ -10072,8 +10118,8 @@ void devlink_port_attrs_set(struct devlink_port *devlink_port,
 {
 	int ret;
 
-	if (WARN_ON(devlink_port->devlink))
-		return;
+	ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port);
+
 	devlink_port->attrs = *attrs;
 	ret = __devlink_port_attrs_set(devlink_port, attrs->flavour);
 	if (ret)
@@ -10096,8 +10142,8 @@ void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u32 contro
 	struct devlink_port_attrs *attrs = &devlink_port->attrs;
 	int ret;
 
-	if (WARN_ON(devlink_port->devlink))
-		return;
+	ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port);
+
 	ret = __devlink_port_attrs_set(devlink_port,
 				       DEVLINK_PORT_FLAVOUR_PCI_PF);
 	if (ret)
@@ -10123,8 +10169,8 @@ void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, u32 contro
 	struct devlink_port_attrs *attrs = &devlink_port->attrs;
 	int ret;
 
-	if (WARN_ON(devlink_port->devlink))
-		return;
+	ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port);
+
 	ret = __devlink_port_attrs_set(devlink_port,
 				       DEVLINK_PORT_FLAVOUR_PCI_VF);
 	if (ret)
@@ -10151,8 +10197,8 @@ void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port, u32 contro
 	struct devlink_port_attrs *attrs = &devlink_port->attrs;
 	int ret;
 
-	if (WARN_ON(devlink_port->devlink))
-		return;
+	ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port);
+
 	ret = __devlink_port_attrs_set(devlink_port,
 				       DEVLINK_PORT_FLAVOUR_PCI_SF);
 	if (ret)
@@ -10267,8 +10313,8 @@ EXPORT_SYMBOL_GPL(devl_rate_nodes_destroy);
 void devlink_port_linecard_set(struct devlink_port *devlink_port,
 			       struct devlink_linecard *linecard)
 {
-	if (WARN_ON(devlink_port->devlink))
-		return;
+	ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port);
+
 	devlink_port->linecard = linecard;
 }
 EXPORT_SYMBOL_GPL(devlink_port_linecard_set);
@@ -11339,6 +11385,8 @@ devlink_port_region_create(struct devlink_port *port,
 	struct devlink_region *region;
 	int err = 0;
 
+	ASSERT_DEVLINK_PORT_INITIALIZED(port);
+
 	if (WARN_ON(!ops) || WARN_ON(!ops->destructor))
 		return ERR_PTR(-EINVAL);
 
diff --git a/net/core/filter.c b/net/core/filter.c
index 31608801078e..bb0136e7a8e4 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -18,6 +18,7 @@
  */
 
 #include <linux/atomic.h>
+#include <linux/bpf_verifier.h>
 #include <linux/module.h>
 #include <linux/types.h>
 #include <linux/mm.h>
@@ -5101,6 +5102,59 @@ static int bpf_sol_tcp_setsockopt(struct sock *sk, int optname,
 	return 0;
 }
 
+static int sol_tcp_sockopt_congestion(struct sock *sk, char *optval,
+				      int *optlen, bool getopt)
+{
+	struct tcp_sock *tp;
+	int ret;
+
+	if (*optlen < 2)
+		return -EINVAL;
+
+	if (getopt) {
+		if (!inet_csk(sk)->icsk_ca_ops)
+			return -EINVAL;
+		/* BPF expects NULL-terminated tcp-cc string */
+		optval[--(*optlen)] = '\0';
+		return do_tcp_getsockopt(sk, SOL_TCP, TCP_CONGESTION,
+					 KERNEL_SOCKPTR(optval),
+					 KERNEL_SOCKPTR(optlen));
+	}
+
+	/* "cdg" is the only cc that alloc a ptr
+	 * in inet_csk_ca area.  The bpf-tcp-cc may
+	 * overwrite this ptr after switching to cdg.
+	 */
+	if (*optlen >= sizeof("cdg") - 1 && !strncmp("cdg", optval, *optlen))
+		return -ENOTSUPP;
+
+	/* It stops this looping
+	 *
+	 * .init => bpf_setsockopt(tcp_cc) => .init =>
+	 * bpf_setsockopt(tcp_cc)" => .init => ....
+	 *
+	 * The second bpf_setsockopt(tcp_cc) is not allowed
+	 * in order to break the loop when both .init
+	 * are the same bpf prog.
+	 *
+	 * This applies even the second bpf_setsockopt(tcp_cc)
+	 * does not cause a loop.  This limits only the first
+	 * '.init' can call bpf_setsockopt(TCP_CONGESTION) to
+	 * pick a fallback cc (eg. peer does not support ECN)
+	 * and the second '.init' cannot fallback to
+	 * another.
+	 */
+	tp = tcp_sk(sk);
+	if (tp->bpf_chg_cc_inprogress)
+		return -EBUSY;
+
+	tp->bpf_chg_cc_inprogress = 1;
+	ret = do_tcp_setsockopt(sk, SOL_TCP, TCP_CONGESTION,
+				KERNEL_SOCKPTR(optval), *optlen);
+	tp->bpf_chg_cc_inprogress = 0;
+	return ret;
+}
+
 static int sol_tcp_sockopt(struct sock *sk, int optname,
 			   char *optval, int *optlen,
 			   bool getopt)
@@ -5124,9 +5178,7 @@ static int sol_tcp_sockopt(struct sock *sk, int optname,
 			return -EINVAL;
 		break;
 	case TCP_CONGESTION:
-		if (*optlen < 2)
-			return -EINVAL;
-		break;
+		return sol_tcp_sockopt_congestion(sk, optval, optlen, getopt);
 	case TCP_SAVED_SYN:
 		if (*optlen < 1)
 			return -EINVAL;
@@ -5151,13 +5203,6 @@ static int sol_tcp_sockopt(struct sock *sk, int optname,
 			return 0;
 		}
 
-		if (optname == TCP_CONGESTION) {
-			if (!inet_csk(sk)->icsk_ca_ops)
-				return -EINVAL;
-			/* BPF expects NULL-terminated tcp-cc string */
-			optval[--(*optlen)] = '\0';
-		}
-
 		return do_tcp_getsockopt(sk, SOL_TCP, optname,
 					 KERNEL_SOCKPTR(optval),
 					 KERNEL_SOCKPTR(optlen));
@@ -5284,12 +5329,6 @@ static int _bpf_getsockopt(struct sock *sk, int level, int optname,
 BPF_CALL_5(bpf_sk_setsockopt, struct sock *, sk, int, level,
 	   int, optname, char *, optval, int, optlen)
 {
-	if (level == SOL_TCP && optname == TCP_CONGESTION) {
-		if (optlen >= sizeof("cdg") - 1 &&
-		    !strncmp("cdg", optval, optlen))
-			return -ENOTSUPP;
-	}
-
 	return _bpf_setsockopt(sk, level, optname, optval, optlen);
 }
 
@@ -8605,6 +8644,36 @@ static bool tc_cls_act_is_valid_access(int off, int size,
 	return bpf_skb_is_valid_access(off, size, type, prog, info);
 }
 
+DEFINE_MUTEX(nf_conn_btf_access_lock);
+EXPORT_SYMBOL_GPL(nf_conn_btf_access_lock);
+
+int (*nfct_btf_struct_access)(struct bpf_verifier_log *log, const struct btf *btf,
+			      const struct btf_type *t, int off, int size,
+			      enum bpf_access_type atype, u32 *next_btf_id,
+			      enum bpf_type_flag *flag);
+EXPORT_SYMBOL_GPL(nfct_btf_struct_access);
+
+static int tc_cls_act_btf_struct_access(struct bpf_verifier_log *log,
+					const struct btf *btf,
+					const struct btf_type *t, int off,
+					int size, enum bpf_access_type atype,
+					u32 *next_btf_id,
+					enum bpf_type_flag *flag)
+{
+	int ret = -EACCES;
+
+	if (atype == BPF_READ)
+		return btf_struct_access(log, btf, t, off, size, atype, next_btf_id,
+					 flag);
+
+	mutex_lock(&nf_conn_btf_access_lock);
+	if (nfct_btf_struct_access)
+		ret = nfct_btf_struct_access(log, btf, t, off, size, atype, next_btf_id, flag);
+	mutex_unlock(&nf_conn_btf_access_lock);
+
+	return ret;
+}
+
 static bool __is_valid_xdp_access(int off, int size)
 {
 	if (off < 0 || off >= sizeof(struct xdp_md))
@@ -8664,6 +8733,27 @@ void bpf_warn_invalid_xdp_action(struct net_device *dev, struct bpf_prog *prog,
 }
 EXPORT_SYMBOL_GPL(bpf_warn_invalid_xdp_action);
 
+static int xdp_btf_struct_access(struct bpf_verifier_log *log,
+				 const struct btf *btf,
+				 const struct btf_type *t, int off,
+				 int size, enum bpf_access_type atype,
+				 u32 *next_btf_id,
+				 enum bpf_type_flag *flag)
+{
+	int ret = -EACCES;
+
+	if (atype == BPF_READ)
+		return btf_struct_access(log, btf, t, off, size, atype, next_btf_id,
+					 flag);
+
+	mutex_lock(&nf_conn_btf_access_lock);
+	if (nfct_btf_struct_access)
+		ret = nfct_btf_struct_access(log, btf, t, off, size, atype, next_btf_id, flag);
+	mutex_unlock(&nf_conn_btf_access_lock);
+
+	return ret;
+}
+
 static bool sock_addr_is_valid_access(int off, int size,
 				      enum bpf_access_type type,
 				      const struct bpf_prog *prog,
@@ -10558,6 +10648,7 @@ const struct bpf_verifier_ops tc_cls_act_verifier_ops = {
 	.convert_ctx_access	= tc_cls_act_convert_ctx_access,
 	.gen_prologue		= tc_cls_act_prologue,
 	.gen_ld_abs		= bpf_gen_ld_abs,
+	.btf_struct_access	= tc_cls_act_btf_struct_access,
 };
 
 const struct bpf_prog_ops tc_cls_act_prog_ops = {
@@ -10569,6 +10660,7 @@ const struct bpf_verifier_ops xdp_verifier_ops = {
 	.is_valid_access	= xdp_is_valid_access,
 	.convert_ctx_access	= xdp_convert_ctx_access,
 	.gen_prologue		= bpf_noop_prologue,
+	.btf_struct_access	= xdp_btf_struct_access,
 };
 
 const struct bpf_prog_ops xdp_prog_ops = {
diff --git a/net/core/gro.c b/net/core/gro.c
index b4190eb08467..bc9451743307 100644
--- a/net/core/gro.c
+++ b/net/core/gro.c
@@ -160,6 +160,7 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb)
 	unsigned int gro_max_size;
 	unsigned int new_truesize;
 	struct sk_buff *lp;
+	int segs;
 
 	/* pairs with WRITE_ONCE() in netif_set_gro_max_size() */
 	gro_max_size = READ_ONCE(p->dev->gro_max_size);
@@ -175,6 +176,7 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb)
 			return -E2BIG;
 	}
 
+	segs = NAPI_GRO_CB(skb)->count;
 	lp = NAPI_GRO_CB(p)->last;
 	pinfo = skb_shinfo(lp);
 
@@ -265,7 +267,7 @@ merge:
 	lp = p;
 
 done:
-	NAPI_GRO_CB(p)->count++;
+	NAPI_GRO_CB(p)->count += segs;
 	p->data_len += len;
 	p->truesize += delta_truesize;
 	p->len += len;
@@ -496,8 +498,15 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 		BUILD_BUG_ON(!IS_ALIGNED(offsetof(struct napi_gro_cb, zeroed),
 					 sizeof(u32))); /* Avoid slow unaligned acc */
 		*(u32 *)&NAPI_GRO_CB(skb)->zeroed = 0;
-		NAPI_GRO_CB(skb)->flush = skb_is_gso(skb) || skb_has_frag_list(skb);
+		NAPI_GRO_CB(skb)->flush = skb_has_frag_list(skb);
 		NAPI_GRO_CB(skb)->is_atomic = 1;
+		NAPI_GRO_CB(skb)->count = 1;
+		if (unlikely(skb_is_gso(skb))) {
+			NAPI_GRO_CB(skb)->count = skb_shinfo(skb)->gso_segs;
+			/* Only support TCP at the moment. */
+			if (!skb_is_gso_tcp(skb))
+				NAPI_GRO_CB(skb)->flush = 1;
+		}
 
 		/* Setup for GRO checksum validation */
 		switch (skb->ip_summed) {
@@ -545,10 +554,10 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 	else
 		gro_list->count++;
 
-	NAPI_GRO_CB(skb)->count = 1;
 	NAPI_GRO_CB(skb)->age = jiffies;
 	NAPI_GRO_CB(skb)->last = skb;
-	skb_shinfo(skb)->gso_size = skb_gro_len(skb);
+	if (!skb_is_gso(skb))
+		skb_shinfo(skb)->gso_size = skb_gro_len(skb);
 	list_add(&skb->list, &gro_list->list);
 	ret = GRO_HELD;
 
@@ -660,6 +669,7 @@ static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb)
 
 	skb->encapsulation = 0;
 	skb_shinfo(skb)->gso_type = 0;
+	skb_shinfo(skb)->gso_size = 0;
 	if (unlikely(skb->slow_gro)) {
 		skb_orphan(skb);
 		skb_ext_reset(skb);
diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c
index 9ccd64e8a666..6fac2f0ef074 100644
--- a/net/core/lwtunnel.c
+++ b/net/core/lwtunnel.c
@@ -50,6 +50,7 @@ static const char *lwtunnel_encap_str(enum lwtunnel_encap_types encap_type)
 		return "IOAM6";
 	case LWTUNNEL_ENCAP_IP6:
 	case LWTUNNEL_ENCAP_IP:
+	case LWTUNNEL_ENCAP_XFRM:
 	case LWTUNNEL_ENCAP_NONE:
 	case __LWTUNNEL_ENCAP_MAX:
 		/* should not have got here */
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 188f8558d27d..ca70525621c7 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -434,8 +434,10 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
 			if (copied + copy > len)
 				copy = len - copied;
 			copy = copy_page_to_iter(page, sge->offset, copy, iter);
-			if (!copy)
-				return copied ? copied : -EFAULT;
+			if (!copy) {
+				copied = copied ? copied : -EFAULT;
+				goto out;
+			}
 
 			copied += copy;
 			if (likely(!peek)) {
@@ -455,7 +457,7 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
 				 * didn't copy the entire length lets just break.
 				 */
 				if (copy != sge->length)
-					return copied;
+					goto out;
 				sk_msg_iter_var_next(i);
 			}
 
@@ -477,7 +479,9 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
 		}
 		msg_rx = sk_psock_peek_msg(psock);
 	}
-
+out:
+	if (psock->work_state.skb && copied > 0)
+		schedule_work(&psock->work);
 	return copied;
 }
 EXPORT_SYMBOL_GPL(sk_msg_recvmsg);
diff --git a/net/core/stream.c b/net/core/stream.c
index ccc083cdef23..1105057ce00a 100644
--- a/net/core/stream.c
+++ b/net/core/stream.c
@@ -159,7 +159,8 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p)
 		*timeo_p = current_timeo;
 	}
 out:
-	remove_wait_queue(sk_sleep(sk), &wait);
+	if (!sock_flag(sk, SOCK_DEAD))
+		remove_wait_queue(sk_sleep(sk), &wait);
 	return err;
 
 do_error: