[SRU][F][PATCH 1/2] net-zerocopy: Refactor frag-is-remappable test.
Koichiro Den
koichiro.den at canonical.com
Tue Sep 10 01:42:03 UTC 2024
From: Arjun Roy <arjunroy at google.com>
Refactor frag-is-remappable test for tcp receive zerocopy. This is
part of a patch set that introduces short-circuited hybrid copies
for small receive operations, which results in roughly 33% fewer
syscalls for small RPC scenarios.
Signed-off-by: Arjun Roy <arjunroy at google.com>
Signed-off-by: Eric Dumazet <edumazet at google.com>
Signed-off-by: Soheil Hassas Yeganeh <soheil at google.com>
Signed-off-by: Jakub Kicinski <kuba at kernel.org>
(backported from commit 98917cf0d6eda01e8c3c34d35398d46b247b6fd3)
[koichiroden: Adjusted context due to missing commit 18fb76ed5386
("net-zerocopy: Copy straggler unaligned data for TCP Rx. zerocopy.")]
CVE-2024-26640
Signed-off-by: Koichiro Den <koichiro.den at canonical.com>
---
net/ipv4/tcp.c | 34 ++++++++++++++++++++++++++--------
1 file changed, 26 insertions(+), 8 deletions(-)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 54399256a438..7510e1937734 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1753,6 +1753,26 @@ int tcp_mmap(struct file *file, struct socket *sock,
}
EXPORT_SYMBOL(tcp_mmap);
+static bool can_map_frag(const skb_frag_t *frag)
+{
+ return skb_frag_size(frag) == PAGE_SIZE && !skb_frag_off(frag);
+}
+
+static int find_next_mappable_frag(const skb_frag_t *frag,
+ int remaining_in_skb)
+{
+ int offset = 0;
+
+ if (likely(can_map_frag(frag)))
+ return 0;
+
+ while (offset < remaining_in_skb && !can_map_frag(frag)) {
+ offset += skb_frag_size(frag);
+ ++frag;
+ }
+ return offset;
+}
+
static int tcp_zerocopy_receive(struct sock *sk,
struct tcp_zerocopy_receive *zc)
{
@@ -1795,6 +1815,8 @@ static int tcp_zerocopy_receive(struct sock *sk,
}
ret = 0;
while (length + PAGE_SIZE <= zc->length) {
+ int mappable_offset;
+
if (zc->recv_skip_hint < PAGE_SIZE) {
if (skb) {
skb = skb->next;
@@ -1815,15 +1837,11 @@ static int tcp_zerocopy_receive(struct sock *sk,
frags++;
}
}
- if (skb_frag_size(frags) != PAGE_SIZE || skb_frag_off(frags)) {
- int remaining = zc->recv_skip_hint;
- while (remaining && (skb_frag_size(frags) != PAGE_SIZE ||
- skb_frag_off(frags))) {
- remaining -= skb_frag_size(frags);
- frags++;
- }
- zc->recv_skip_hint -= remaining;
+ mappable_offset = find_next_mappable_frag(frags,
+ zc->recv_skip_hint);
+ if (mappable_offset) {
+ zc->recv_skip_hint = mappable_offset;
break;
}
ret = vm_insert_page(vma, address + length,
--
2.43.0
More information about the kernel-team
mailing list