summaryrefslogtreecommitdiff
path: root/include/linux/skmsg.h
diff options
context:
space:
mode:
Diffstat (limited to 'include/linux/skmsg.h')
-rw-r--r--include/linux/skmsg.h93
1 files changed, 79 insertions, 14 deletions
diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index 2cbe0c22a32f..a8553401b1c9 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -4,6 +4,7 @@
#ifndef _LINUX_SKMSG_H
#define _LINUX_SKMSG_H
+#include <linux/bitops.h>
#include <linux/bpf.h>
#include <linux/filter.h>
#include <linux/scatterlist.h>
@@ -91,10 +92,14 @@ struct sk_psock {
struct sk_psock_progs progs;
#if IS_ENABLED(CONFIG_BPF_STREAM_PARSER)
struct strparser strp;
+ u32 copied_seq;
+ u32 ingress_bytes;
#endif
struct sk_buff_head ingress_skb;
struct list_head ingress_msg;
spinlock_t ingress_lock;
+ /** @msg_tot_len: Total bytes queued in ingress_msg list. */
+ u32 msg_tot_len;
unsigned long state;
struct list_head link;
spinlock_t link_lock;
@@ -139,6 +144,8 @@ int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from,
struct sk_msg *msg, u32 bytes);
int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
int len, int flags);
+int __sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
+ int len, int flags, int *copied_from_self);
bool sk_msg_is_readable(struct sock *sk);
static inline void sk_msg_check_to_free(struct sk_msg *msg, u32 i, u32 bytes)
@@ -193,11 +200,14 @@ static inline void sk_msg_xfer(struct sk_msg *dst, struct sk_msg *src,
int which, u32 size)
{
dst->sg.data[which] = src->sg.data[which];
+ __assign_bit(which, dst->sg.copy, test_bit(which, src->sg.copy));
dst->sg.data[which].length = size;
dst->sg.size += size;
src->sg.size -= size;
src->sg.data[which].length -= size;
src->sg.data[which].offset += size;
+ if (!src->sg.data[which].length)
+ __clear_bit(which, src->sg.copy);
}
static inline void sk_msg_xfer_full(struct sk_msg *dst, struct sk_msg *src)
@@ -267,16 +277,19 @@ static inline void sk_msg_page_add(struct sk_msg *msg, struct page *page,
static inline void sk_msg_sg_copy(struct sk_msg *msg, u32 i, bool copy_state)
{
do {
- if (copy_state)
- __set_bit(i, msg->sg.copy);
- else
- __clear_bit(i, msg->sg.copy);
+ __assign_bit(i, msg->sg.copy, copy_state);
sk_msg_iter_var_next(i);
if (i == msg->sg.end)
break;
} while (1);
}
+static inline void sk_msg_sg_copy_assign(struct sk_msg *dst, u32 dst_i,
+ const struct sk_msg *src, u32 src_i)
+{
+ __assign_bit(dst_i, dst->sg.copy, test_bit(src_i, src->sg.copy));
+}
+
static inline void sk_msg_sg_copy_set(struct sk_msg *msg, u32 start)
{
sk_msg_sg_copy(msg, start, true);
@@ -313,10 +326,31 @@ static inline bool sk_psock_test_state(const struct sk_psock *psock,
static inline void sock_drop(struct sock *sk, struct sk_buff *skb)
{
- sk_drops_add(sk, skb);
+ sk_drops_skbadd(sk, skb);
kfree_skb(skb);
}
+static inline u32 sk_psock_get_msg_len_nolock(struct sk_psock *psock)
+{
+ /* Used by ioctl to read msg_tot_len only; lock-free for performance */
+ return READ_ONCE(psock->msg_tot_len);
+}
+
+static inline void sk_psock_msg_len_add_locked(struct sk_psock *psock, int diff)
+{
+ /* Use WRITE_ONCE to ensure correct read in sk_psock_get_msg_len_nolock().
+ * ingress_lock should be held to prevent concurrent updates to msg_tot_len
+ */
+ WRITE_ONCE(psock->msg_tot_len, psock->msg_tot_len + diff);
+}
+
+static inline void sk_psock_msg_len_add(struct sk_psock *psock, int diff)
+{
+ spin_lock_bh(&psock->ingress_lock);
+ sk_psock_msg_len_add_locked(psock, diff);
+ spin_unlock_bh(&psock->ingress_lock);
+}
+
static inline bool sk_psock_queue_msg(struct sk_psock *psock,
struct sk_msg *msg)
{
@@ -325,6 +359,7 @@ static inline bool sk_psock_queue_msg(struct sk_psock *psock,
spin_lock_bh(&psock->ingress_lock);
if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) {
list_add_tail(&msg->list, &psock->ingress_msg);
+ sk_psock_msg_len_add_locked(psock, msg->sg.size);
ret = true;
} else {
sk_msg_free(psock->sk, msg);
@@ -341,18 +376,25 @@ static inline struct sk_msg *sk_psock_dequeue_msg(struct sk_psock *psock)
spin_lock_bh(&psock->ingress_lock);
msg = list_first_entry_or_null(&psock->ingress_msg, struct sk_msg, list);
- if (msg)
+ if (msg) {
list_del(&msg->list);
+ sk_psock_msg_len_add_locked(psock, -msg->sg.size);
+ }
spin_unlock_bh(&psock->ingress_lock);
return msg;
}
+static inline struct sk_msg *sk_psock_peek_msg_locked(struct sk_psock *psock)
+{
+ return list_first_entry_or_null(&psock->ingress_msg, struct sk_msg, list);
+}
+
static inline struct sk_msg *sk_psock_peek_msg(struct sk_psock *psock)
{
struct sk_msg *msg;
spin_lock_bh(&psock->ingress_lock);
- msg = list_first_entry_or_null(&psock->ingress_msg, struct sk_msg, list);
+ msg = sk_psock_peek_msg_locked(psock);
spin_unlock_bh(&psock->ingress_lock);
return msg;
}
@@ -425,8 +467,7 @@ int sk_psock_msg_verdict(struct sock *sk, struct sk_psock *psock,
* intentional to enforce typesafety.
*/
#define sk_psock_init_link() \
- ((struct sk_psock_link *)kzalloc(sizeof(struct sk_psock_link), \
- GFP_ATOMIC | __GFP_NOWARN))
+ kzalloc_obj(struct sk_psock_link, GFP_ATOMIC | __GFP_NOWARN)
static inline void sk_psock_free_link(struct sk_psock_link *link)
{
@@ -510,13 +551,37 @@ static inline void psock_progs_drop(struct sk_psock_progs *progs)
psock_set_prog(&progs->skb_verdict, NULL);
}
-int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb);
+/* for tcp only, sk is locked */
+static inline ssize_t sk_psock_msg_inq(struct sock *sk)
+{
+ struct sk_psock *psock;
+ ssize_t inq = 0;
+
+ psock = sk_psock_get(sk);
+ if (likely(psock)) {
+ inq = sk_psock_get_msg_len_nolock(psock);
+ sk_psock_put(sk, psock);
+ }
+ return inq;
+}
-static inline bool sk_psock_strp_enabled(struct sk_psock *psock)
+/* for udp only, sk is not locked */
+static inline ssize_t sk_msg_first_len(struct sock *sk)
{
- if (!psock)
- return false;
- return !!psock->saved_data_ready;
+ struct sk_psock *psock;
+ struct sk_msg *msg;
+ ssize_t inq = 0;
+
+ psock = sk_psock_get(sk);
+ if (likely(psock)) {
+ spin_lock_bh(&psock->ingress_lock);
+ msg = sk_psock_peek_msg_locked(psock);
+ if (msg)
+ inq = msg->sg.size;
+ spin_unlock_bh(&psock->ingress_lock);
+ sk_psock_put(sk, psock);
+ }
+ return inq;
}
#if IS_ENABLED(CONFIG_NET_SOCK_MSG)