From: Willem de Bruijn <will...@google.com>
The kernel supports zerocopy sendmsg in virtio and tap. Expand the
infrastructure to support other socket types. Introduce a completion
notification channel over the socket error queue. Notifications are
returned with ee_origin SO_EE_ORIGIN_ZEROCOPY. ee_errno is 0 to avoid
blocking the send/recv path on receiving notifications.
Add reference counting, to support the skb split, merge, resize and
clone operations possible with SOCK_STREAM and other socket types.
The patch does not yet modify any datapaths.
Signed-off-by: Willem de Bruijn <will...@google.com>
---
include/linux/skbuff.h | 46 +++++++++++++++++
include/linux/socket.h | 1 +
include/net/sock.h | 2 +
include/uapi/linux/errqueue.h | 1 +
net/core/datagram.c | 37 ++++++++++----
net/core/skbuff.c | 114 ++++++++++++++++++++++++++++++++++++++++++
net/core/sock.c | 2 +
7 files changed, 192 insertions(+), 11 deletions(-)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 065e10b..a93e17c 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -306,6 +306,7 @@ enum {
SKBTX_ACK_TSTAMP = 1 << 7,
};
+#define SKBTX_ZEROCOPY_FRAG (SKBTX_DEV_ZEROCOPY | SKBTX_SHARED_FRAG)
#define SKBTX_ANY_SW_TSTAMP (SKBTX_SW_TSTAMP | \
SKBTX_SCHED_TSTAMP | \
SKBTX_ACK_TSTAMP)
@@ -323,8 +324,27 @@ struct ubuf_info {
void (*callback)(struct ubuf_info *, bool zerocopy_success);
void *ctx;
unsigned long desc;
+ atomic_t refcnt;
};
+#define skb_uarg(SKB) ((struct ubuf_info *)(skb_shinfo(SKB)->destructor_arg))
+
+struct ubuf_info *sock_zerocopy_alloc(struct sock *sk, size_t size);
+
+static inline void sock_zerocopy_get(struct ubuf_info *uarg)
+{
+ atomic_inc(&uarg->refcnt);
+}
+
+void sock_zerocopy_put(struct ubuf_info *uarg);
+
+void sock_zerocopy_callback(struct ubuf_info *uarg, bool success);
+
+bool skb_zerocopy_alloc(struct sk_buff *skb, size_t size);
+int skb_zerocopy_add_frags_iter(struct sock *sk, struct sk_buff *skb,
+ struct iov_iter *iter, int len,
+ struct ubuf_info *uarg);
+
/* This data is invariant across clones and lives at
* the end of the header data, ie. at skb->end.
*/
@@ -1037,6 +1057,32 @@ static inline struct skb_shared_hwtstamps
*skb_hwtstamps(struct sk_buff *skb)
return &skb_shinfo(skb)->hwtstamps;
}
+static inline struct ubuf_info *skb_zcopy(struct sk_buff *skb)
+{
+ bool is_zcopy = skb && skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY;
+
+ return is_zcopy ? skb_uarg(skb) : NULL;
+}
+
+static inline void skb_zcopy_set(struct sk_buff *skb, struct ubuf_info *uarg)
+{
+ if (uarg) {
+ sock_zerocopy_get(uarg);
+ skb_shinfo(skb)->destructor_arg = uarg;
+ skb_shinfo(skb)->tx_flags |= SKBTX_ZEROCOPY_FRAG;
+ }
+}
+
+static inline void skb_zcopy_clear(struct sk_buff *skb)
+{
+ struct ubuf_info *uarg = skb_zcopy(skb);
+
+ if (uarg) {
+ sock_zerocopy_put(uarg);
+ skb_shinfo(skb)->tx_flags &= ~SKBTX_DEV_ZEROCOPY;
+ }
+}
+
/**
* skb_queue_empty - check if a queue is empty
* @list: queue head
diff --git a/include/linux/socket.h b/include/linux/socket.h
index 5bf59c8..5e99866 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -276,6 +276,7 @@ struct ucred {
#define MSG_SENDPAGE_NOTLAST 0x20000 /* sendpage() internal : not the last
page */
#define MSG_EOF MSG_FIN
+#define MSG_ZEROCOPY 0x4000000 /* Use user data in kernel path */
#define MSG_FASTOPEN 0x20000000 /* Send data in TCP SYN */
#define MSG_CMSG_CLOEXEC 0x40000000 /* Set close_on_exec for file
descriptor received through
diff --git a/include/net/sock.h b/include/net/sock.h
index 43c6abc..56895af 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -281,6 +281,7 @@ struct cg_proto;
* @sk_stamp: time stamp of last packet received
* @sk_tsflags: SO_TIMESTAMPING socket options
* @sk_tskey: counter to disambiguate concurrent tstamp requests
+ * @sk_zckey: counter to order MSG_ZEROCOPY notifications
* @sk_socket: Identd and reporting IO signals
* @sk_user_data: RPC layer private data
* @sk_frag: cached page frag
@@ -419,6 +420,7 @@ struct sock {
ktime_t sk_stamp;
u16 sk_tsflags;
u32 sk_tskey;
+ atomic_t sk_zckey;
struct socket *sk_socket;
void *sk_user_data;
struct page_frag sk_frag;
diff --git a/include/uapi/linux/errqueue.h b/include/uapi/linux/errqueue.h
index 07bdce1..0f15a77 100644
--- a/include/uapi/linux/errqueue.h
+++ b/include/uapi/linux/errqueue.h
@@ -18,6 +18,7 @@ struct sock_extended_err {
#define SO_EE_ORIGIN_ICMP 2
#define SO_EE_ORIGIN_ICMP6 3
#define SO_EE_ORIGIN_TXSTATUS 4
+#define SO_EE_ORIGIN_ZEROCOPY 5
#define SO_EE_ORIGIN_TIMESTAMPING SO_EE_ORIGIN_TXSTATUS
#define SO_EE_OFFENDER(ee) ((struct sockaddr*)((ee)+1))
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 617088a..4d5bbab 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -520,19 +520,16 @@ EXPORT_SYMBOL(skb_copy_datagram_from_iter);
* The function will first copy up to headlen, and then pin the userspace
* pages and build frags through them.
*
+ * XXX: move to net/core/skbuff.c (skipping in this RFC patchset)
+ *
* Returns 0, -EFAULT or -EMSGSIZE.
*/
-int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *from)
+int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb,
+ struct iov_iter *from, size_t length)
{
- int len = iov_iter_count(from);
- int copy = min_t(int, skb_headlen(skb), len);
- int frag = 0;
-
- /* copy up to skb headlen */
- if (skb_copy_datagram_from_iter(skb, 0, from, copy))
- return -EFAULT;
+ int frag = skb_shinfo(skb)->nr_frags;
- while (iov_iter_count(from)) {
+ while (length && iov_iter_count(from)) {
struct page *pages[MAX_SKB_FRAGS];
size_t start;
ssize_t copied;
@@ -542,18 +539,24 @@ int zerocopy_sg_from_iter(struct sk_buff *skb, struct
iov_iter *from)
if (frag == MAX_SKB_FRAGS)
return -EMSGSIZE;
- copied = iov_iter_get_pages(from, pages, ~0U,
+ copied = iov_iter_get_pages(from, pages, length,
MAX_SKB_FRAGS - frag, &start);
if (copied < 0)
return -EFAULT;
iov_iter_advance(from, copied);
+ length -= copied;
truesize = PAGE_ALIGN(copied + start);
skb->data_len += copied;
skb->len += copied;
skb->truesize += truesize;
- atomic_add(truesize, &skb->sk->sk_wmem_alloc);
+ if (sk && sk->sk_type == SOCK_STREAM) {
+ sk->sk_wmem_queued += truesize;
+ sk_mem_charge(sk, truesize);
+ } else {
+ atomic_add(truesize, &skb->sk->sk_wmem_alloc);
+ }
while (copied) {
int size = min_t(int, copied, PAGE_SIZE - start);
skb_fill_page_desc(skb, frag++, pages[n], start, size);
@@ -564,6 +567,18 @@ int zerocopy_sg_from_iter(struct sk_buff *skb, struct
iov_iter *from)
}
return 0;
}
+EXPORT_SYMBOL(__zerocopy_sg_from_iter);
+
+int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *from)
+{
+ int copy = min_t(int, skb_headlen(skb), iov_iter_count(from));
+
+ /* copy up to skb headlen */
+ if (skb_copy_datagram_from_iter(skb, 0, from, copy))
+ return -EFAULT;
+
+ return __zerocopy_sg_from_iter(NULL, skb, from, ~0U);
+}
EXPORT_SYMBOL(zerocopy_sg_from_iter);
static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset,
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index f1aa781..85dc612 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -858,6 +858,120 @@ struct sk_buff *skb_morph(struct sk_buff *dst, struct
sk_buff *src)
}
EXPORT_SYMBOL_GPL(skb_morph);
+/* must only be called from process context */
+struct ubuf_info *sock_zerocopy_alloc(struct sock *sk, size_t size)
+{
+ struct sk_buff *skb;
+ struct ubuf_info *uarg;
+
+ skb = sock_wmalloc(sk, 0, 0, GFP_KERNEL);
+ if (!skb)
+ return NULL;
+
+ BUILD_BUG_ON(sizeof(*uarg) > sizeof(skb->cb));
+ uarg = (void *)skb->cb;
+
+ uarg->callback = sock_zerocopy_callback;
+ uarg->desc = atomic_inc_return(&sk->sk_zckey) - 1;
+ atomic_set(&uarg->refcnt, 0);
+
+ return uarg;
+}
+EXPORT_SYMBOL_GPL(sock_zerocopy_alloc);
+
+#define skb_from_uarg(skb) container_of((void *)uarg, struct sk_buff, cb)
+
+void sock_zerocopy_callback(struct ubuf_info *uarg, bool success)
+{
+ struct sock_exterr_skb *serr;
+ struct sk_buff *skb = skb_from_uarg(skb);
+ struct sock *sk = skb->sk;
+ u16 id = uarg->desc;
+
+ serr = SKB_EXT_ERR(skb);
+ memset(serr, 0, sizeof(*serr));
+ serr->ee.ee_errno = 0;
+ serr->ee.ee_origin = SO_EE_ORIGIN_ZEROCOPY;
+ serr->ee.ee_data = id;
+
+ skb_queue_tail(&sk->sk_error_queue, skb);
+
+ if (!sock_flag(sk, SOCK_DEAD))
+ sk->sk_error_report(sk);
+}
+EXPORT_SYMBOL_GPL(sock_zerocopy_callback);
+
+void sock_zerocopy_put(struct ubuf_info *uarg)
+{
+ if (uarg && atomic_dec_and_test(&uarg->refcnt)) {
+ if (uarg->callback)
+ uarg->callback(uarg, true);
+ else
+ consume_skb(skb_from_uarg(uarg));
+ }
+}
+EXPORT_SYMBOL_GPL(sock_zerocopy_put);
+
+bool skb_zerocopy_alloc(struct sk_buff *skb, size_t size)
+{
+ struct ubuf_info *uarg;
+
+ uarg = sock_zerocopy_alloc(skb->sk, size);
+ if (!uarg)
+ return false;
+
+ skb_zcopy_set(skb, uarg);
+ return true;
+}
+EXPORT_SYMBOL_GPL(skb_zerocopy_alloc);
+
+extern int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb,
+ struct iov_iter *from, size_t length);
+
+int skb_zerocopy_add_frags_iter(struct sock *sk, struct sk_buff *skb,
+ struct iov_iter *iter, int len,
+ struct ubuf_info *uarg)
+{
+ struct ubuf_info *orig_uarg = skb_zcopy(skb);
+ struct iov_iter orig_iter = *iter;
+ int ret, orig_len = skb->len;
+
+ if (orig_uarg && orig_uarg != uarg)
+ return -EEXIST;
+
+ ret = __zerocopy_sg_from_iter(sk, skb, iter, len);
+ if (ret && (ret != -EMSGSIZE || skb->len == orig_len)) {
+ *iter = orig_iter;
+ ___pskb_trim(skb, orig_len);
+ return ret;
+ }
+
+ if (!orig_uarg)
+ skb_zcopy_set(skb, uarg);
+
+ return skb->len - orig_len;
+}
+EXPORT_SYMBOL_GPL(skb_zerocopy_add_frags_iter);
+
+/* unused only until next patch in the series; will remove attribute */
+static int __attribute__((unused))
+ skb_zerocopy_clone(struct sk_buff *nskb, struct sk_buff *orig,
+ gfp_t gfp_mask)
+{
+ if (skb_zcopy(orig)) {
+ if (skb_zcopy(nskb)) {
+ /* !gfp_mask callers are verified to !skb_zcopy(nskb) */
+ BUG_ON(!gfp_mask);
+ if (skb_uarg(nskb) == skb_uarg(orig))
+ return 0;
+ if (skb_copy_ubufs(nskb, GFP_ATOMIC))
+ return -EIO;
+ }
+ skb_zcopy_set(nskb, skb_uarg(orig));
+ }
+ return 0;
+}
+
/**
* skb_copy_ubufs - copy userspace skb frags buffers to kernel
* @skb: the skb to modify
diff --git a/net/core/sock.c b/net/core/sock.c
index 193901d..0ab9a3b 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1525,6 +1525,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const
gfp_t priority)
newsk->sk_forward_alloc = 0;
newsk->sk_send_head = NULL;
newsk->sk_userlocks = sk->sk_userlocks &
~SOCK_BINDPORT_LOCK;
+ atomic_set(&newsk->sk_zckey, 0);
sock_reset_flag(newsk, SOCK_DONE);
skb_queue_head_init(&newsk->sk_error_queue);
@@ -2345,6 +2346,7 @@ void sock_init_data(struct socket *sock, struct sock *sk)
sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT;
sk->sk_stamp = ktime_set(-1L, 0);
+ atomic_set(&sk->sk_zckey, 0);
#ifdef CONFIG_NET_RX_BUSY_POLL
sk->sk_napi_id = 0;
--
2.5.0.276.gf5e568e
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
