| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20230609100221.2620633-7-dhowells@redhat.com>
Date: Fri, 9 Jun 2023 11:02:21 +0100
From: David Howells <dhowells@...hat.com>
To: netdev@...r.kernel.org
Cc: David Howells <dhowells@...hat.com>,
Jakub Kicinski <kuba@...nel.org>,
"David S. Miller" <davem@...emloft.net>,
Eric Dumazet <edumazet@...gle.com>,
Paolo Abeni <pabeni@...hat.com>,
Willem de Bruijn <willemdebruijn.kernel@...il.com>,
David Ahern <dsahern@...nel.org>,
Matthew Wilcox <willy@...radead.org>,
Jens Axboe <axboe@...nel.dk>,
linux-mm@...ck.org,
linux-kernel@...r.kernel.org,
Tom Herbert <tom@...bertland.com>,
Tom Herbert <tom@...ntonium.net>
Subject: [PATCH net-next 6/6] kcm: Send multiple frags in one sendmsg()
Rewrite the AF_KCM transmission loop to send all the fragments in a single
skb or frag_list-skb in one sendmsg() with MSG_SPLICE_PAGES set. The list
of fragments in each skb is conveniently a bio_vec[] that can just be
attached to a BVEC iter.
Note: I'm working out the size of each fragment-skb by adding up bv_len for
all the bio_vecs in skb->frags[] - but surely this information is recorded
somewhere? For the skbs in head->frag_list, this is equal to
skb->data_len, but not for the head. head->data_len includes all the tail
frags too.
Signed-off-by: David Howells <dhowells@...hat.com>
cc: Tom Herbert <tom@...bertland.com>
cc: Tom Herbert <tom@...ntonium.net>
cc: "David S. Miller" <davem@...emloft.net>
cc: Eric Dumazet <edumazet@...gle.com>
cc: Jakub Kicinski <kuba@...nel.org>
cc: Paolo Abeni <pabeni@...hat.com>
cc: Jens Axboe <axboe@...nel.dk>
cc: Matthew Wilcox <willy@...radead.org>
cc: netdev@...r.kernel.org
---
include/net/kcm.h | 2 +-
net/kcm/kcmsock.c | 126 ++++++++++++++++++----------------------------
2 files changed, 51 insertions(+), 77 deletions(-)
diff --git a/include/net/kcm.h b/include/net/kcm.h
index 2d704f8f4905..90279e5e09a5 100644
--- a/include/net/kcm.h
+++ b/include/net/kcm.h
@@ -47,9 +47,9 @@ struct kcm_stats {
struct kcm_tx_msg {
unsigned int sent;
- unsigned int fragidx;
unsigned int frag_offset;
unsigned int msg_flags;
+ bool started_tx;
struct sk_buff *frag_skb;
struct sk_buff *last_skb;
};
diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index 3bcac1453f10..d75d775e9462 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -581,12 +581,10 @@ static void kcm_report_tx_retry(struct kcm_sock *kcm)
*/
static int kcm_write_msgs(struct kcm_sock *kcm)
{
+ unsigned int total_sent = 0;
struct sock *sk = &kcm->sk;
struct kcm_psock *psock;
- struct sk_buff *skb, *head;
- struct kcm_tx_msg *txm;
- unsigned short fragidx, frag_offset;
- unsigned int sent, total_sent = 0;
+ struct sk_buff *head;
int ret = 0;
kcm->tx_wait_more = false;
@@ -600,78 +598,57 @@ static int kcm_write_msgs(struct kcm_sock *kcm)
if (skb_queue_empty(&sk->sk_write_queue))
return 0;
- kcm_tx_msg(skb_peek(&sk->sk_write_queue))->sent = 0;
-
- } else if (skb_queue_empty(&sk->sk_write_queue)) {
- return 0;
+ kcm_tx_msg(skb_peek(&sk->sk_write_queue))->started_tx = false;
}
- head = skb_peek(&sk->sk_write_queue);
- txm = kcm_tx_msg(head);
-
- if (txm->sent) {
- /* Send of first skbuff in queue already in progress */
- if (WARN_ON(!psock)) {
- ret = -EINVAL;
- goto out;
+retry:
+ while ((head = skb_peek(&sk->sk_write_queue))) {
+ struct msghdr msg = {
+ .msg_flags = MSG_DONTWAIT | MSG_SPLICE_PAGES,
+ };
+ struct kcm_tx_msg *txm = kcm_tx_msg(head);
+ struct sk_buff *skb;
+ unsigned int msize;
+ int i;
+
+ if (!txm->started_tx) {
+ psock = reserve_psock(kcm);
+ if (!psock)
+ goto out;
+ skb = head;
+ txm->frag_offset = 0;
+ txm->sent = 0;
+ txm->started_tx = true;
+ } else {
+ if (WARN_ON(!psock)) {
+ ret = -EINVAL;
+ goto out;
+ }
+ skb = txm->frag_skb;
}
- sent = txm->sent;
- frag_offset = txm->frag_offset;
- fragidx = txm->fragidx;
- skb = txm->frag_skb;
-
- goto do_frag;
- }
-
-try_again:
- psock = reserve_psock(kcm);
- if (!psock)
- goto out;
-
- do {
- skb = head;
- txm = kcm_tx_msg(head);
- sent = 0;
-do_frag_list:
if (WARN_ON(!skb_shinfo(skb)->nr_frags)) {
ret = -EINVAL;
goto out;
}
- for (fragidx = 0; fragidx < skb_shinfo(skb)->nr_frags;
- fragidx++) {
- struct bio_vec bvec;
- struct msghdr msg = {
- .msg_flags = MSG_DONTWAIT | MSG_SPLICE_PAGES,
- };
- skb_frag_t *frag;
-
- frag_offset = 0;
-do_frag:
- frag = &skb_shinfo(skb)->frags[fragidx];
- if (WARN_ON(!skb_frag_size(frag))) {
- ret = -EINVAL;
- goto out;
- }
+ msize = 0;
+ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++)
+ msize += skb_shinfo(skb)->frags[i].bv_len;
+
+ iov_iter_bvec(&msg.msg_iter, ITER_SOURCE,
+ skb_shinfo(skb)->frags, skb_shinfo(skb)->nr_frags,
+ msize);
+ iov_iter_advance(&msg.msg_iter, txm->frag_offset);
- bvec_set_page(&bvec,
- skb_frag_page(frag),
- skb_frag_size(frag) - frag_offset,
- skb_frag_off(frag) + frag_offset);
- iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1,
- bvec.bv_len);
+ do {
ret = sock_sendmsg(psock->sk->sk_socket, &msg);
if (ret <= 0) {
if (ret == -EAGAIN) {
/* Save state to try again when there's
* write space on the socket
*/
- txm->sent = sent;
- txm->frag_offset = frag_offset;
- txm->fragidx = fragidx;
txm->frag_skb = skb;
-
ret = 0;
goto out;
}
@@ -685,39 +662,36 @@ static int kcm_write_msgs(struct kcm_sock *kcm)
true);
unreserve_psock(kcm);
- txm->sent = 0;
+ txm->started_tx = false;
kcm_report_tx_retry(kcm);
ret = 0;
-
- goto try_again;
+ goto retry;
}
- sent += ret;
- frag_offset += ret;
+ txm->sent += ret;
+ txm->frag_offset += ret;
KCM_STATS_ADD(psock->stats.tx_bytes, ret);
- if (frag_offset < skb_frag_size(frag)) {
- /* Not finished with this frag */
- goto do_frag;
- }
- }
+ } while (msg.msg_iter.count > 0);
if (skb == head) {
if (skb_has_frag_list(skb)) {
- skb = skb_shinfo(skb)->frag_list;
- goto do_frag_list;
+ txm->frag_skb = skb_shinfo(skb)->frag_list;
+ txm->frag_offset = 0;
+ continue;
}
} else if (skb->next) {
- skb = skb->next;
- goto do_frag_list;
+ txm->frag_skb = skb->next;
+ txm->frag_offset = 0;
+ continue;
}
/* Successfully sent the whole packet, account for it. */
+ sk->sk_wmem_queued -= txm->sent;
+ total_sent += txm->sent;
skb_dequeue(&sk->sk_write_queue);
kfree_skb(head);
- sk->sk_wmem_queued -= sent;
- total_sent += sent;
KCM_STATS_INCR(psock->stats.tx_msgs);
- } while ((head = skb_peek(&sk->sk_write_queue)));
+ }
out:
if (!head) {
/* Done with all queued messages. */
Powered by blists - more mailing lists