summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/core/dev.c26
-rw-r--r--net/core/devmem.c6
-rw-r--r--net/core/devmem.h7
-rw-r--r--net/core/netpoll.c7
-rw-r--r--net/ipv4/ip_output.c15
-rw-r--r--net/ipv6/ip6_offload.c4
-rw-r--r--net/kcm/kcmsock.c6
-rw-r--r--net/netlink/af_netlink.c2
-rw-r--r--net/packet/af_packet.c12
-rw-r--r--net/sched/sch_mqprio.c2
-rw-r--r--net/sched/sch_taprio.c21
-rw-r--r--net/sunrpc/auth_gss/gss_krb5_crypto.c4
-rw-r--r--net/sunrpc/xdr.c110
-rw-r--r--net/sunrpc/xprtsock.c40
14 files changed, 99 insertions, 163 deletions
diff --git a/net/core/dev.c b/net/core/dev.c
index b28ce68830b2..68dc47d7e700 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6978,6 +6978,12 @@ int napi_set_threaded(struct napi_struct *napi,
if (napi->config)
napi->config->threaded = threaded;
+ /* Setting/unsetting threaded mode on a napi might not immediately
+ * take effect, if the current napi instance is actively being
+ * polled. In this case, the switch between threaded mode and
+ * softirq mode will happen in the next round of napi_schedule().
+ * This should not cause hiccups/stalls to the live traffic.
+ */
if (!threaded && napi->thread) {
napi_stop_kthread(napi);
} else {
@@ -7011,23 +7017,9 @@ int netif_set_threaded(struct net_device *dev,
WRITE_ONCE(dev->threaded, threaded);
- /* Make sure kthread is created before THREADED bit
- * is set.
- */
- smp_mb__before_atomic();
-
- /* Setting/unsetting threaded mode on a napi might not immediately
- * take effect, if the current napi instance is actively being
- * polled. In this case, the switch between threaded mode and
- * softirq mode will happen in the next round of napi_schedule().
- * This should not cause hiccups/stalls to the live traffic.
- */
- list_for_each_entry(napi, &dev->napi_list, dev_list) {
- if (!threaded && napi->thread)
- napi_stop_kthread(napi);
- else
- assign_bit(NAPI_STATE_THREADED, &napi->state, threaded);
- }
+ /* The error should not occur as the kthreads are already created. */
+ list_for_each_entry(napi, &dev->napi_list, dev_list)
+ WARN_ON_ONCE(napi_set_threaded(napi, threaded));
return err;
}
diff --git a/net/core/devmem.c b/net/core/devmem.c
index b3a62ca0df65..24c591ab38ae 100644
--- a/net/core/devmem.c
+++ b/net/core/devmem.c
@@ -70,14 +70,13 @@ void __net_devmem_dmabuf_binding_free(struct work_struct *wq)
gen_pool_destroy(binding->chunk_pool);
dma_buf_unmap_attachment_unlocked(binding->attachment, binding->sgt,
- DMA_FROM_DEVICE);
+ binding->direction);
dma_buf_detach(binding->dmabuf, binding->attachment);
dma_buf_put(binding->dmabuf);
xa_destroy(&binding->bound_rxqs);
kvfree(binding->tx_vec);
kfree(binding);
}
-EXPORT_SYMBOL(__net_devmem_dmabuf_binding_free);
struct net_iov *
net_devmem_alloc_dmabuf(struct net_devmem_dmabuf_binding *binding)
@@ -208,6 +207,7 @@ net_devmem_bind_dmabuf(struct net_device *dev,
mutex_init(&binding->lock);
binding->dmabuf = dmabuf;
+ binding->direction = direction;
binding->attachment = dma_buf_attach(binding->dmabuf, dev->dev.parent);
if (IS_ERR(binding->attachment)) {
@@ -312,7 +312,7 @@ err_tx_vec:
kvfree(binding->tx_vec);
err_unmap:
dma_buf_unmap_attachment_unlocked(binding->attachment, binding->sgt,
- DMA_FROM_DEVICE);
+ direction);
err_detach:
dma_buf_detach(dmabuf, binding->attachment);
err_free_binding:
diff --git a/net/core/devmem.h b/net/core/devmem.h
index 0a3b28ba5c13..41cd6e1c9141 100644
--- a/net/core/devmem.h
+++ b/net/core/devmem.h
@@ -56,6 +56,9 @@ struct net_devmem_dmabuf_binding {
*/
u32 id;
+ /* DMA direction, FROM_DEVICE for Rx binding, TO_DEVICE for Tx. */
+ enum dma_data_direction direction;
+
/* Array of net_iov pointers for this binding, sorted by virtual
* address. This array is convenient to map the virtual addresses to
* net_iovs in the TX path.
@@ -165,10 +168,6 @@ static inline void net_devmem_put_net_iov(struct net_iov *niov)
{
}
-static inline void __net_devmem_dmabuf_binding_free(struct work_struct *wq)
-{
-}
-
static inline struct net_devmem_dmabuf_binding *
net_devmem_bind_dmabuf(struct net_device *dev,
enum dma_data_direction direction,
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index a1da97b5b30b..5f65b62346d4 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -768,6 +768,13 @@ int netpoll_setup(struct netpoll *np)
if (err)
goto flush;
rtnl_unlock();
+
+ /* Make sure all NAPI polls which started before dev->npinfo
+ * was visible have exited before we start calling NAPI poll.
+ * NAPI skips locking if dev->npinfo is NULL.
+ */
+ synchronize_rcu();
+
return 0;
flush:
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 10a1d182fd84..84e7f8a2f50f 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -425,15 +425,20 @@ int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb)
int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
- struct net_device *dev = skb_dst_dev(skb), *indev = skb->dev;
+ struct net_device *dev, *indev = skb->dev;
+ int ret_val;
+ rcu_read_lock();
+ dev = skb_dst_dev_rcu(skb);
skb->dev = dev;
skb->protocol = htons(ETH_P_IP);
- return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING,
- net, sk, skb, indev, dev,
- ip_finish_output,
- !(IPCB(skb)->flags & IPSKB_REROUTED));
+ ret_val = NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING,
+ net, sk, skb, indev, dev,
+ ip_finish_output,
+ !(IPCB(skb)->flags & IPSKB_REROUTED));
+ rcu_read_unlock();
+ return ret_val;
}
EXPORT_SYMBOL(ip_output);
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 9822163428b0..fce91183797a 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -148,7 +148,9 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
ops = rcu_dereference(inet6_offloads[proto]);
if (likely(ops && ops->callbacks.gso_segment)) {
- skb_reset_transport_header(skb);
+ if (!skb_reset_transport_header_careful(skb))
+ goto out;
+
segs = ops->callbacks.gso_segment(skb, features);
if (!segs)
skb->network_header = skb_mac_header(skb) + nhoff - skb->head;
diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index a0be3896a934..a4971e6fa943 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -19,6 +19,7 @@
#include <linux/rculist.h>
#include <linux/skbuff.h>
#include <linux/socket.h>
+#include <linux/splice.h>
#include <linux/uaccess.h>
#include <linux/workqueue.h>
#include <linux/syscalls.h>
@@ -1029,6 +1030,11 @@ static ssize_t kcm_splice_read(struct socket *sock, loff_t *ppos,
ssize_t copied;
struct sk_buff *skb;
+ if (sock->file->f_flags & O_NONBLOCK || flags & SPLICE_F_NONBLOCK)
+ flags = MSG_DONTWAIT;
+ else
+ flags = 0;
+
/* Only support splice for SOCKSEQPACKET */
skb = skb_recv_datagram(sk, flags, &err);
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 5949855fa29e..e2f7080dd5d7 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1218,7 +1218,7 @@ int netlink_attachskb(struct sock *sk, struct sk_buff *skb,
nlk = nlk_sk(sk);
rmem = atomic_add_return(skb->truesize, &sk->sk_rmem_alloc);
- if ((rmem == skb->truesize || rmem < READ_ONCE(sk->sk_rcvbuf)) &&
+ if ((rmem == skb->truesize || rmem <= READ_ONCE(sk->sk_rcvbuf)) &&
!test_bit(NETLINK_S_CONGESTED, &nlk->state)) {
netlink_skb_set_owner_r(skb, sk);
return 0;
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index bc438d0d96a7..a7017d7f0927 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -4573,10 +4573,10 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
spin_lock(&po->bind_lock);
was_running = packet_sock_flag(po, PACKET_SOCK_RUNNING);
num = po->num;
- if (was_running) {
- WRITE_ONCE(po->num, 0);
+ WRITE_ONCE(po->num, 0);
+ if (was_running)
__unregister_prot_hook(sk, false);
- }
+
spin_unlock(&po->bind_lock);
synchronize_net();
@@ -4608,10 +4608,10 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
mutex_unlock(&po->pg_vec_lock);
spin_lock(&po->bind_lock);
- if (was_running) {
- WRITE_ONCE(po->num, num);
+ WRITE_ONCE(po->num, num);
+ if (was_running)
register_prot_hook(sk);
- }
+
spin_unlock(&po->bind_lock);
if (pg_vec && (po->tp_version > TPACKET_V2)) {
/* Because we don't support block-based V3 on tx-ring */
diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c
index 51d4013b6121..f3e5ef9a9592 100644
--- a/net/sched/sch_mqprio.c
+++ b/net/sched/sch_mqprio.c
@@ -152,7 +152,7 @@ static int mqprio_parse_opt(struct net_device *dev, struct tc_mqprio_qopt *qopt,
static const struct
nla_policy mqprio_tc_entry_policy[TCA_MQPRIO_TC_ENTRY_MAX + 1] = {
[TCA_MQPRIO_TC_ENTRY_INDEX] = NLA_POLICY_MAX(NLA_U32,
- TC_QOPT_MAX_QUEUE),
+ TC_QOPT_MAX_QUEUE - 1),
[TCA_MQPRIO_TC_ENTRY_FP] = NLA_POLICY_RANGE(NLA_U32,
TC_FP_EXPRESS,
TC_FP_PREEMPTIBLE),
diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index e759e43ad27e..39b735386996 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -43,6 +43,11 @@ static struct static_key_false taprio_have_working_mqprio;
#define TAPRIO_SUPPORTED_FLAGS \
(TCA_TAPRIO_ATTR_FLAG_TXTIME_ASSIST | TCA_TAPRIO_ATTR_FLAG_FULL_OFFLOAD)
#define TAPRIO_FLAGS_INVALID U32_MAX
+/* Minimum value for picos_per_byte to ensure non-zero duration
+ * for minimum-sized Ethernet frames (ETH_ZLEN = 60).
+ * 60 * 17 > PSEC_PER_NSEC (1000)
+ */
+#define TAPRIO_PICOS_PER_BYTE_MIN 17
struct sched_entry {
/* Durations between this GCL entry and the GCL entry where the
@@ -1284,7 +1289,8 @@ static void taprio_start_sched(struct Qdisc *sch,
}
static void taprio_set_picos_per_byte(struct net_device *dev,
- struct taprio_sched *q)
+ struct taprio_sched *q,
+ struct netlink_ext_ack *extack)
{
struct ethtool_link_ksettings ecmd;
int speed = SPEED_10;
@@ -1300,6 +1306,15 @@ static void taprio_set_picos_per_byte(struct net_device *dev,
skip:
picos_per_byte = (USEC_PER_SEC * 8) / speed;
+ if (picos_per_byte < TAPRIO_PICOS_PER_BYTE_MIN) {
+ if (!extack)
+ pr_warn("Link speed %d is too high. Schedule may be inaccurate.\n",
+ speed);
+ NL_SET_ERR_MSG_FMT_MOD(extack,
+ "Link speed %d is too high. Schedule may be inaccurate.",
+ speed);
+ picos_per_byte = TAPRIO_PICOS_PER_BYTE_MIN;
+ }
atomic64_set(&q->picos_per_byte, picos_per_byte);
netdev_dbg(dev, "taprio: set %s's picos_per_byte to: %lld, linkspeed: %d\n",
@@ -1324,7 +1339,7 @@ static int taprio_dev_notifier(struct notifier_block *nb, unsigned long event,
if (dev != qdisc_dev(q->root))
continue;
- taprio_set_picos_per_byte(dev, q);
+ taprio_set_picos_per_byte(dev, q, NULL);
stab = rtnl_dereference(q->root->stab);
@@ -1844,7 +1859,7 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
q->flags = taprio_flags;
/* Needed for length_to_duration() during netlink attribute parsing */
- taprio_set_picos_per_byte(dev, q);
+ taprio_set_picos_per_byte(dev, q, extack);
err = taprio_parse_mqprio_opt(dev, mqprio, extack, q->flags);
if (err < 0)
diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c
index 8f2d65c1e831..16dcf115de1e 100644
--- a/net/sunrpc/auth_gss/gss_krb5_crypto.c
+++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c
@@ -875,8 +875,8 @@ out_err:
* krb5_etm_decrypt - Decrypt using the RFC 8009 rules
* @kctx: Kerberos context
* @offset: starting offset of the ciphertext, in bytes
- * @len:
- * @buf:
+ * @len: size of ciphertext to unwrap
+ * @buf: ciphertext to unwrap
* @headskip: OUT: the enctype's confounder length, in octets
* @tailskip: OUT: the enctype's HMAC length, in octets
*
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index 1346fdf33835..70efc727a9cd 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -37,19 +37,6 @@ xdr_encode_netobj(__be32 *p, const struct xdr_netobj *obj)
}
EXPORT_SYMBOL_GPL(xdr_encode_netobj);
-__be32 *
-xdr_decode_netobj(__be32 *p, struct xdr_netobj *obj)
-{
- unsigned int len;
-
- if ((len = be32_to_cpu(*p++)) > XDR_MAX_NETOBJ)
- return NULL;
- obj->len = len;
- obj->data = (u8 *) p;
- return p + XDR_QUADLEN(len);
-}
-EXPORT_SYMBOL_GPL(xdr_decode_netobj);
-
/**
* xdr_encode_opaque_fixed - Encode fixed length opaque data
* @p: pointer to current position in XDR buffer.
@@ -102,21 +89,6 @@ xdr_encode_string(__be32 *p, const char *string)
}
EXPORT_SYMBOL_GPL(xdr_encode_string);
-__be32 *
-xdr_decode_string_inplace(__be32 *p, char **sp,
- unsigned int *lenp, unsigned int maxlen)
-{
- u32 len;
-
- len = be32_to_cpu(*p++);
- if (len > maxlen)
- return NULL;
- *lenp = len;
- *sp = (char *) p;
- return p + XDR_QUADLEN(len);
-}
-EXPORT_SYMBOL_GPL(xdr_decode_string_inplace);
-
/**
* xdr_terminate_string - '\0'-terminate a string residing in an xdr_buf
* @buf: XDR buffer where string resides
@@ -2245,88 +2217,6 @@ out:
EXPORT_SYMBOL_GPL(xdr_process_buf);
/**
- * xdr_stream_decode_opaque - Decode variable length opaque
- * @xdr: pointer to xdr_stream
- * @ptr: location to store opaque data
- * @size: size of storage buffer @ptr
- *
- * Return values:
- * On success, returns size of object stored in *@ptr
- * %-EBADMSG on XDR buffer overflow
- * %-EMSGSIZE on overflow of storage buffer @ptr
- */
-ssize_t xdr_stream_decode_opaque(struct xdr_stream *xdr, void *ptr, size_t size)
-{
- ssize_t ret;
- void *p;
-
- ret = xdr_stream_decode_opaque_inline(xdr, &p, size);
- if (ret <= 0)
- return ret;
- memcpy(ptr, p, ret);
- return ret;
-}
-EXPORT_SYMBOL_GPL(xdr_stream_decode_opaque);
-
-/**
- * xdr_stream_decode_opaque_dup - Decode and duplicate variable length opaque
- * @xdr: pointer to xdr_stream
- * @ptr: location to store pointer to opaque data
- * @maxlen: maximum acceptable object size
- * @gfp_flags: GFP mask to use
- *
- * Return values:
- * On success, returns size of object stored in *@ptr
- * %-EBADMSG on XDR buffer overflow
- * %-EMSGSIZE if the size of the object would exceed @maxlen
- * %-ENOMEM on memory allocation failure
- */
-ssize_t xdr_stream_decode_opaque_dup(struct xdr_stream *xdr, void **ptr,
- size_t maxlen, gfp_t gfp_flags)
-{
- ssize_t ret;
- void *p;
-
- ret = xdr_stream_decode_opaque_inline(xdr, &p, maxlen);
- if (ret > 0) {
- *ptr = kmemdup(p, ret, gfp_flags);
- if (*ptr != NULL)
- return ret;
- ret = -ENOMEM;
- }
- *ptr = NULL;
- return ret;
-}
-EXPORT_SYMBOL_GPL(xdr_stream_decode_opaque_dup);
-
-/**
- * xdr_stream_decode_string - Decode variable length string
- * @xdr: pointer to xdr_stream
- * @str: location to store string
- * @size: size of storage buffer @str
- *
- * Return values:
- * On success, returns length of NUL-terminated string stored in *@str
- * %-EBADMSG on XDR buffer overflow
- * %-EMSGSIZE on overflow of storage buffer @str
- */
-ssize_t xdr_stream_decode_string(struct xdr_stream *xdr, char *str, size_t size)
-{
- ssize_t ret;
- void *p;
-
- ret = xdr_stream_decode_opaque_inline(xdr, &p, size);
- if (ret > 0) {
- memcpy(str, p, ret);
- str[ret] = '\0';
- return strlen(str);
- }
- *str = '\0';
- return ret;
-}
-EXPORT_SYMBOL_GPL(xdr_stream_decode_string);
-
-/**
* xdr_stream_decode_string_dup - Decode and duplicate variable length string
* @xdr: pointer to xdr_stream
* @str: location to store pointer to string
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 04ff66758fc3..c5f7bbf5775f 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -358,7 +358,7 @@ xs_alloc_sparse_pages(struct xdr_buf *buf, size_t want, gfp_t gfp)
static int
xs_sock_process_cmsg(struct socket *sock, struct msghdr *msg,
- struct cmsghdr *cmsg, int ret)
+ unsigned int *msg_flags, struct cmsghdr *cmsg, int ret)
{
u8 content_type = tls_get_record_type(sock->sk, cmsg);
u8 level, description;
@@ -371,7 +371,7 @@ xs_sock_process_cmsg(struct socket *sock, struct msghdr *msg,
* record, even though there might be more frames
* waiting to be decrypted.
*/
- msg->msg_flags &= ~MSG_EOR;
+ *msg_flags &= ~MSG_EOR;
break;
case TLS_RECORD_TYPE_ALERT:
tls_alert_recv(sock->sk, msg, &level, &description);
@@ -386,19 +386,33 @@ xs_sock_process_cmsg(struct socket *sock, struct msghdr *msg,
}
static int
-xs_sock_recv_cmsg(struct socket *sock, struct msghdr *msg, int flags)
+xs_sock_recv_cmsg(struct socket *sock, unsigned int *msg_flags, int flags)
{
union {
struct cmsghdr cmsg;
u8 buf[CMSG_SPACE(sizeof(u8))];
} u;
+ u8 alert[2];
+ struct kvec alert_kvec = {
+ .iov_base = alert,
+ .iov_len = sizeof(alert),
+ };
+ struct msghdr msg = {
+ .msg_flags = *msg_flags,
+ .msg_control = &u,
+ .msg_controllen = sizeof(u),
+ };
int ret;
- msg->msg_control = &u;
- msg->msg_controllen = sizeof(u);
- ret = sock_recvmsg(sock, msg, flags);
- if (msg->msg_controllen != sizeof(u))
- ret = xs_sock_process_cmsg(sock, msg, &u.cmsg, ret);
+ iov_iter_kvec(&msg.msg_iter, ITER_DEST, &alert_kvec, 1,
+ alert_kvec.iov_len);
+ ret = sock_recvmsg(sock, &msg, flags);
+ if (ret > 0 &&
+ tls_get_record_type(sock->sk, &u.cmsg) == TLS_RECORD_TYPE_ALERT) {
+ iov_iter_revert(&msg.msg_iter, ret);
+ ret = xs_sock_process_cmsg(sock, &msg, msg_flags, &u.cmsg,
+ -EAGAIN);
+ }
return ret;
}
@@ -408,7 +422,13 @@ xs_sock_recvmsg(struct socket *sock, struct msghdr *msg, int flags, size_t seek)
ssize_t ret;
if (seek != 0)
iov_iter_advance(&msg->msg_iter, seek);
- ret = xs_sock_recv_cmsg(sock, msg, flags);
+ ret = sock_recvmsg(sock, msg, flags);
+ /* Handle TLS inband control message lazily */
+ if (msg->msg_flags & MSG_CTRUNC) {
+ msg->msg_flags &= ~(MSG_CTRUNC | MSG_EOR);
+ if (ret == 0 || ret == -EIO)
+ ret = xs_sock_recv_cmsg(sock, &msg->msg_flags, flags);
+ }
return ret > 0 ? ret + seek : ret;
}
@@ -434,7 +454,7 @@ xs_read_discard(struct socket *sock, struct msghdr *msg, int flags,
size_t count)
{
iov_iter_discard(&msg->msg_iter, ITER_DEST, count);
- return xs_sock_recv_cmsg(sock, msg, flags);
+ return xs_sock_recvmsg(sock, msg, flags, 0);
}
#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
generated by cgit v1.2.3 (git 2.46.0) at 2025-08-09 16:27:23 +0000