summaryrefslogtreecommitdiff
path: root/net/ipv4/tcp.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4/tcp.c')
-rw-r--r--net/ipv4/tcp.c95
1 files changed, 77 insertions, 18 deletions
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 15d47d5e7951..6f0caf9a866d 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1734,7 +1734,7 @@ int tcp_mmap(struct file *file, struct socket *sock,
return -EPERM;
vma->vm_flags &= ~(VM_MAYWRITE | VM_MAYEXEC);
- /* Instruct vm_insert_page() to not down_read(mmap_sem) */
+ /* Instruct vm_insert_page() to not mmap_read_lock(mm) */
vma->vm_flags |= VM_MIXEDMAP;
vma->vm_ops = &tcp_vm_ops;
@@ -1742,14 +1742,48 @@ int tcp_mmap(struct file *file, struct socket *sock,
}
EXPORT_SYMBOL(tcp_mmap);
+static int tcp_zerocopy_vm_insert_batch(struct vm_area_struct *vma,
+ struct page **pages,
+ unsigned long pages_to_map,
+ unsigned long *insert_addr,
+ u32 *length_with_pending,
+ u32 *seq,
+ struct tcp_zerocopy_receive *zc)
+{
+ unsigned long pages_remaining = pages_to_map;
+ int bytes_mapped;
+ int ret;
+
+ ret = vm_insert_pages(vma, *insert_addr, pages, &pages_remaining);
+ bytes_mapped = PAGE_SIZE * (pages_to_map - pages_remaining);
+ /* Even if vm_insert_pages fails, it may have partially succeeded in
+ * mapping (some but not all of the pages).
+ */
+ *seq += bytes_mapped;
+ *insert_addr += bytes_mapped;
+ if (ret) {
+ /* But if vm_insert_pages did fail, we have to unroll some state
+ * we speculatively touched before.
+ */
+ const int bytes_not_mapped = PAGE_SIZE * pages_remaining;
+ *length_with_pending -= bytes_not_mapped;
+ zc->recv_skip_hint += bytes_not_mapped;
+ }
+ return ret;
+}
+
static int tcp_zerocopy_receive(struct sock *sk,
struct tcp_zerocopy_receive *zc)
{
unsigned long address = (unsigned long)zc->address;
u32 length = 0, seq, offset, zap_len;
+ #define PAGE_BATCH_SIZE 8
+ struct page *pages[PAGE_BATCH_SIZE];
const skb_frag_t *frags = NULL;
struct vm_area_struct *vma;
struct sk_buff *skb = NULL;
+ unsigned long pg_idx = 0;
+ unsigned long curr_addr;
struct tcp_sock *tp;
int inq;
int ret;
@@ -1762,16 +1796,17 @@ static int tcp_zerocopy_receive(struct sock *sk,
sock_rps_record_flow(sk);
- down_read(&current->mm->mmap_sem);
+ tp = tcp_sk(sk);
+
+ mmap_read_lock(current->mm);
vma = find_vma(current->mm, address);
if (!vma || vma->vm_start > address || vma->vm_ops != &tcp_vm_ops) {
- up_read(&current->mm->mmap_sem);
+ mmap_read_unlock(current->mm);
return -EINVAL;
}
zc->length = min_t(unsigned long, zc->length, vma->vm_end - address);
- tp = tcp_sk(sk);
seq = tp->copied_seq;
inq = tcp_inq(sk);
zc->length = min_t(u32, zc->length, inq);
@@ -1783,8 +1818,20 @@ static int tcp_zerocopy_receive(struct sock *sk,
zc->recv_skip_hint = zc->length;
}
ret = 0;
+ curr_addr = address;
while (length + PAGE_SIZE <= zc->length) {
if (zc->recv_skip_hint < PAGE_SIZE) {
+ /* If we're here, finish the current batch. */
+ if (pg_idx) {
+ ret = tcp_zerocopy_vm_insert_batch(vma, pages,
+ pg_idx,
+ &curr_addr,
+ &length,
+ &seq, zc);
+ if (ret)
+ goto out;
+ pg_idx = 0;
+ }
if (skb) {
if (zc->recv_skip_hint > 0)
break;
@@ -1793,7 +1840,6 @@ static int tcp_zerocopy_receive(struct sock *sk,
} else {
skb = tcp_recv_skb(sk, seq, &offset);
}
-
zc->recv_skip_hint = skb->len - offset;
offset -= skb_headlen(skb);
if ((int)offset < 0 || skb_has_frag_list(skb))
@@ -1817,17 +1863,27 @@ static int tcp_zerocopy_receive(struct sock *sk,
zc->recv_skip_hint -= remaining;
break;
}
- ret = vm_insert_page(vma, address + length,
- skb_frag_page(frags));
- if (ret)
- break;
+ pages[pg_idx] = skb_frag_page(frags);
+ pg_idx++;
length += PAGE_SIZE;
- seq += PAGE_SIZE;
zc->recv_skip_hint -= PAGE_SIZE;
frags++;
+ if (pg_idx == PAGE_BATCH_SIZE) {
+ ret = tcp_zerocopy_vm_insert_batch(vma, pages, pg_idx,
+ &curr_addr, &length,
+ &seq, zc);
+ if (ret)
+ goto out;
+ pg_idx = 0;
+ }
+ }
+ if (pg_idx) {
+ ret = tcp_zerocopy_vm_insert_batch(vma, pages, pg_idx,
+ &curr_addr, &length, &seq,
+ zc);
}
out:
- up_read(&current->mm->mmap_sem);
+ mmap_read_unlock(current->mm);
if (length) {
WRITE_ONCE(tp->copied_seq, seq);
tcp_rcv_space_adjust(sk);
@@ -2635,6 +2691,9 @@ int tcp_disconnect(struct sock *sk, int flags)
tp->window_clamp = 0;
tp->delivered = 0;
tp->delivered_ce = 0;
+ if (icsk->icsk_ca_ops->release)
+ icsk->icsk_ca_ops->release(sk);
+ memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
tcp_set_ca_state(sk, TCP_CA_Open);
tp->is_sack_reneg = 0;
tcp_clear_retrans(tp);
@@ -3190,10 +3249,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
#ifdef CONFIG_TCP_MD5SIG
case TCP_MD5SIG:
case TCP_MD5SIG_EXT:
- if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))
- err = tp->af_specific->md5_parse(sk, optname, optval, optlen);
- else
- err = -EINVAL;
+ err = tp->af_specific->md5_parse(sk, optname, optval, optlen);
break;
#endif
case TCP_USER_TIMEOUT:
@@ -3977,11 +4033,14 @@ EXPORT_SYMBOL(tcp_md5_hash_skb_data);
int tcp_md5_hash_key(struct tcp_md5sig_pool *hp, const struct tcp_md5sig_key *key)
{
+ u8 keylen = READ_ONCE(key->keylen); /* paired with WRITE_ONCE() in tcp_md5_do_add */
struct scatterlist sg;
- sg_init_one(&sg, key->key, key->keylen);
- ahash_request_set_crypt(hp->md5_req, &sg, NULL, key->keylen);
- return crypto_ahash_update(hp->md5_req);
+ sg_init_one(&sg, key->key, keylen);
+ ahash_request_set_crypt(hp->md5_req, &sg, NULL, keylen);
+
+ /* We use data_race() because tcp_md5_do_add() might change key->key under us */
+ return data_race(crypto_ahash_update(hp->md5_req));
}
EXPORT_SYMBOL(tcp_md5_hash_key);
generated by cgit v1.2.3 (git 2.51.0) at 2025-09-26 15:22:39 +0000