Welcome to mirror list, hosted at ThFree Co, Russian Federation.

github.com/torvalds/linux.git - Unnamed repository; edit this file 'description' to name the repository.
summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/ax25/af_ax25.c23
-rw-r--r--net/ax25/ax25_dev.c28
-rw-r--r--net/ax25/ax25_route.c13
-rw-r--r--net/bridge/netfilter/nft_reject_bridge.c8
-rw-r--r--net/ceph/ceph_common.c7
-rw-r--r--net/ceph/messenger.c4
-rw-r--r--net/ceph/messenger_v1.c54
-rw-r--r--net/ceph/messenger_v2.c250
-rw-r--r--net/core/neighbour.c18
-rw-r--r--net/core/rtnetlink.c6
-rw-r--r--net/ieee802154/nl802154.c8
-rw-r--r--net/ipv4/netfilter/Kconfig4
-rw-r--r--net/ipv4/tcp.c7
-rw-r--r--net/ipv4/tcp_input.c2
-rw-r--r--net/ipv6/netfilter/Kconfig4
-rw-r--r--net/ipv6/netfilter/Makefile3
-rw-r--r--net/ipv6/netfilter/nf_flow_table_ipv6.c0
-rw-r--r--net/netfilter/nf_tables_api.c1
-rw-r--r--net/netfilter/nft_byteorder.c12
-rw-r--r--net/netfilter/nft_ct.c5
-rw-r--r--net/packet/af_packet.c8
-rw-r--r--net/sched/cls_api.c11
-rw-r--r--net/smc/af_smc.c133
-rw-r--r--net/smc/smc.h20
-rw-r--r--net/smc/smc_diag.c2
25 files changed, 492 insertions, 139 deletions
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index 02f43f3e2c56..3e49d28824ed 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -77,6 +77,7 @@ static void ax25_kill_by_device(struct net_device *dev)
{
ax25_dev *ax25_dev;
ax25_cb *s;
+ struct sock *sk;
if ((ax25_dev = ax25_dev_ax25dev(dev)) == NULL)
return;
@@ -85,13 +86,16 @@ static void ax25_kill_by_device(struct net_device *dev)
again:
ax25_for_each(s, &ax25_list) {
if (s->ax25_dev == ax25_dev) {
+ sk = s->sk;
+ sock_hold(sk);
spin_unlock_bh(&ax25_list_lock);
- lock_sock(s->sk);
+ lock_sock(sk);
s->ax25_dev = NULL;
- release_sock(s->sk);
+ ax25_dev_put(ax25_dev);
+ release_sock(sk);
ax25_disconnect(s, ENETUNREACH);
spin_lock_bh(&ax25_list_lock);
-
+ sock_put(sk);
/* The entry could have been deleted from the
* list meanwhile and thus the next pointer is
* no longer valid. Play it safe and restart
@@ -355,21 +359,25 @@ static int ax25_ctl_ioctl(const unsigned int cmd, void __user *arg)
if (copy_from_user(&ax25_ctl, arg, sizeof(ax25_ctl)))
return -EFAULT;
- if ((ax25_dev = ax25_addr_ax25dev(&ax25_ctl.port_addr)) == NULL)
- return -ENODEV;
-
if (ax25_ctl.digi_count > AX25_MAX_DIGIS)
return -EINVAL;
if (ax25_ctl.arg > ULONG_MAX / HZ && ax25_ctl.cmd != AX25_KILL)
return -EINVAL;
+ ax25_dev = ax25_addr_ax25dev(&ax25_ctl.port_addr);
+ if (!ax25_dev)
+ return -ENODEV;
+
digi.ndigi = ax25_ctl.digi_count;
for (k = 0; k < digi.ndigi; k++)
digi.calls[k] = ax25_ctl.digi_addr[k];
- if ((ax25 = ax25_find_cb(&ax25_ctl.source_addr, &ax25_ctl.dest_addr, &digi, ax25_dev->dev)) == NULL)
+ ax25 = ax25_find_cb(&ax25_ctl.source_addr, &ax25_ctl.dest_addr, &digi, ax25_dev->dev);
+ if (!ax25) {
+ ax25_dev_put(ax25_dev);
return -ENOTCONN;
+ }
switch (ax25_ctl.cmd) {
case AX25_KILL:
@@ -436,6 +444,7 @@ static int ax25_ctl_ioctl(const unsigned int cmd, void __user *arg)
}
out_put:
+ ax25_dev_put(ax25_dev);
ax25_cb_put(ax25);
return ret;
diff --git a/net/ax25/ax25_dev.c b/net/ax25/ax25_dev.c
index 256fadb94df3..d2a244e1c260 100644
--- a/net/ax25/ax25_dev.c
+++ b/net/ax25/ax25_dev.c
@@ -37,6 +37,7 @@ ax25_dev *ax25_addr_ax25dev(ax25_address *addr)
for (ax25_dev = ax25_dev_list; ax25_dev != NULL; ax25_dev = ax25_dev->next)
if (ax25cmp(addr, (const ax25_address *)ax25_dev->dev->dev_addr) == 0) {
res = ax25_dev;
+ ax25_dev_hold(ax25_dev);
}
spin_unlock_bh(&ax25_dev_lock);
@@ -56,6 +57,7 @@ void ax25_dev_device_up(struct net_device *dev)
return;
}
+ refcount_set(&ax25_dev->refcount, 1);
dev->ax25_ptr = ax25_dev;
ax25_dev->dev = dev;
dev_hold_track(dev, &ax25_dev->dev_tracker, GFP_ATOMIC);
@@ -84,6 +86,7 @@ void ax25_dev_device_up(struct net_device *dev)
ax25_dev->next = ax25_dev_list;
ax25_dev_list = ax25_dev;
spin_unlock_bh(&ax25_dev_lock);
+ ax25_dev_hold(ax25_dev);
ax25_register_dev_sysctl(ax25_dev);
}
@@ -113,9 +116,10 @@ void ax25_dev_device_down(struct net_device *dev)
if ((s = ax25_dev_list) == ax25_dev) {
ax25_dev_list = s->next;
spin_unlock_bh(&ax25_dev_lock);
+ ax25_dev_put(ax25_dev);
dev->ax25_ptr = NULL;
dev_put_track(dev, &ax25_dev->dev_tracker);
- kfree(ax25_dev);
+ ax25_dev_put(ax25_dev);
return;
}
@@ -123,9 +127,10 @@ void ax25_dev_device_down(struct net_device *dev)
if (s->next == ax25_dev) {
s->next = ax25_dev->next;
spin_unlock_bh(&ax25_dev_lock);
+ ax25_dev_put(ax25_dev);
dev->ax25_ptr = NULL;
dev_put_track(dev, &ax25_dev->dev_tracker);
- kfree(ax25_dev);
+ ax25_dev_put(ax25_dev);
return;
}
@@ -133,6 +138,7 @@ void ax25_dev_device_down(struct net_device *dev)
}
spin_unlock_bh(&ax25_dev_lock);
dev->ax25_ptr = NULL;
+ ax25_dev_put(ax25_dev);
}
int ax25_fwd_ioctl(unsigned int cmd, struct ax25_fwd_struct *fwd)
@@ -144,20 +150,32 @@ int ax25_fwd_ioctl(unsigned int cmd, struct ax25_fwd_struct *fwd)
switch (cmd) {
case SIOCAX25ADDFWD:
- if ((fwd_dev = ax25_addr_ax25dev(&fwd->port_to)) == NULL)
+ fwd_dev = ax25_addr_ax25dev(&fwd->port_to);
+ if (!fwd_dev) {
+ ax25_dev_put(ax25_dev);
return -EINVAL;
- if (ax25_dev->forward != NULL)
+ }
+ if (ax25_dev->forward) {
+ ax25_dev_put(fwd_dev);
+ ax25_dev_put(ax25_dev);
return -EINVAL;
+ }
ax25_dev->forward = fwd_dev->dev;
+ ax25_dev_put(fwd_dev);
+ ax25_dev_put(ax25_dev);
break;
case SIOCAX25DELFWD:
- if (ax25_dev->forward == NULL)
+ if (!ax25_dev->forward) {
+ ax25_dev_put(ax25_dev);
return -EINVAL;
+ }
ax25_dev->forward = NULL;
+ ax25_dev_put(ax25_dev);
break;
default:
+ ax25_dev_put(ax25_dev);
return -EINVAL;
}
diff --git a/net/ax25/ax25_route.c b/net/ax25/ax25_route.c
index d0b2e094bd55..9751207f7757 100644
--- a/net/ax25/ax25_route.c
+++ b/net/ax25/ax25_route.c
@@ -75,11 +75,13 @@ static int __must_check ax25_rt_add(struct ax25_routes_struct *route)
ax25_dev *ax25_dev;
int i;
- if ((ax25_dev = ax25_addr_ax25dev(&route->port_addr)) == NULL)
- return -EINVAL;
if (route->digi_count > AX25_MAX_DIGIS)
return -EINVAL;
+ ax25_dev = ax25_addr_ax25dev(&route->port_addr);
+ if (!ax25_dev)
+ return -EINVAL;
+
write_lock_bh(&ax25_route_lock);
ax25_rt = ax25_route_list;
@@ -91,6 +93,7 @@ static int __must_check ax25_rt_add(struct ax25_routes_struct *route)
if (route->digi_count != 0) {
if ((ax25_rt->digipeat = kmalloc(sizeof(ax25_digi), GFP_ATOMIC)) == NULL) {
write_unlock_bh(&ax25_route_lock);
+ ax25_dev_put(ax25_dev);
return -ENOMEM;
}
ax25_rt->digipeat->lastrepeat = -1;
@@ -101,6 +104,7 @@ static int __must_check ax25_rt_add(struct ax25_routes_struct *route)
}
}
write_unlock_bh(&ax25_route_lock);
+ ax25_dev_put(ax25_dev);
return 0;
}
ax25_rt = ax25_rt->next;
@@ -108,6 +112,7 @@ static int __must_check ax25_rt_add(struct ax25_routes_struct *route)
if ((ax25_rt = kmalloc(sizeof(ax25_route), GFP_ATOMIC)) == NULL) {
write_unlock_bh(&ax25_route_lock);
+ ax25_dev_put(ax25_dev);
return -ENOMEM;
}
@@ -120,6 +125,7 @@ static int __must_check ax25_rt_add(struct ax25_routes_struct *route)
if ((ax25_rt->digipeat = kmalloc(sizeof(ax25_digi), GFP_ATOMIC)) == NULL) {
write_unlock_bh(&ax25_route_lock);
kfree(ax25_rt);
+ ax25_dev_put(ax25_dev);
return -ENOMEM;
}
ax25_rt->digipeat->lastrepeat = -1;
@@ -132,6 +138,7 @@ static int __must_check ax25_rt_add(struct ax25_routes_struct *route)
ax25_rt->next = ax25_route_list;
ax25_route_list = ax25_rt;
write_unlock_bh(&ax25_route_lock);
+ ax25_dev_put(ax25_dev);
return 0;
}
@@ -173,6 +180,7 @@ static int ax25_rt_del(struct ax25_routes_struct *route)
}
}
write_unlock_bh(&ax25_route_lock);
+ ax25_dev_put(ax25_dev);
return 0;
}
@@ -215,6 +223,7 @@ static int ax25_rt_opt(struct ax25_route_opt_struct *rt_option)
out:
write_unlock_bh(&ax25_route_lock);
+ ax25_dev_put(ax25_dev);
return err;
}
diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c
index eba0efe64d05..fbf858ddec35 100644
--- a/net/bridge/netfilter/nft_reject_bridge.c
+++ b/net/bridge/netfilter/nft_reject_bridge.c
@@ -49,7 +49,7 @@ static void nft_reject_br_send_v4_tcp_reset(struct net *net,
{
struct sk_buff *nskb;
- nskb = nf_reject_skb_v4_tcp_reset(net, oldskb, dev, hook);
+ nskb = nf_reject_skb_v4_tcp_reset(net, oldskb, NULL, hook);
if (!nskb)
return;
@@ -65,7 +65,7 @@ static void nft_reject_br_send_v4_unreach(struct net *net,
{
struct sk_buff *nskb;
- nskb = nf_reject_skb_v4_unreach(net, oldskb, dev, hook, code);
+ nskb = nf_reject_skb_v4_unreach(net, oldskb, NULL, hook, code);
if (!nskb)
return;
@@ -81,7 +81,7 @@ static void nft_reject_br_send_v6_tcp_reset(struct net *net,
{
struct sk_buff *nskb;
- nskb = nf_reject_skb_v6_tcp_reset(net, oldskb, dev, hook);
+ nskb = nf_reject_skb_v6_tcp_reset(net, oldskb, NULL, hook);
if (!nskb)
return;
@@ -98,7 +98,7 @@ static void nft_reject_br_send_v6_unreach(struct net *net,
{
struct sk_buff *nskb;
- nskb = nf_reject_skb_v6_unreach(net, oldskb, dev, hook, code);
+ nskb = nf_reject_skb_v6_unreach(net, oldskb, NULL, hook, code);
if (!nskb)
return;
diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c
index ecc400a0b7bb..4c6441536d55 100644
--- a/net/ceph/ceph_common.c
+++ b/net/ceph/ceph_common.c
@@ -246,6 +246,7 @@ enum {
Opt_cephx_sign_messages,
Opt_tcp_nodelay,
Opt_abort_on_full,
+ Opt_rxbounce,
};
enum {
@@ -295,6 +296,7 @@ static const struct fs_parameter_spec ceph_parameters[] = {
fsparam_u32 ("osdkeepalive", Opt_osdkeepalivetimeout),
fsparam_enum ("read_from_replica", Opt_read_from_replica,
ceph_param_read_from_replica),
+ fsparam_flag ("rxbounce", Opt_rxbounce),
fsparam_enum ("ms_mode", Opt_ms_mode,
ceph_param_ms_mode),
fsparam_string ("secret", Opt_secret),
@@ -584,6 +586,9 @@ int ceph_parse_param(struct fs_parameter *param, struct ceph_options *opt,
case Opt_abort_on_full:
opt->flags |= CEPH_OPT_ABORT_ON_FULL;
break;
+ case Opt_rxbounce:
+ opt->flags |= CEPH_OPT_RXBOUNCE;
+ break;
default:
BUG();
@@ -660,6 +665,8 @@ int ceph_print_client_options(struct seq_file *m, struct ceph_client *client,
seq_puts(m, "notcp_nodelay,");
if (show_all && (opt->flags & CEPH_OPT_ABORT_ON_FULL))
seq_puts(m, "abort_on_full,");
+ if (opt->flags & CEPH_OPT_RXBOUNCE)
+ seq_puts(m, "rxbounce,");
if (opt->mount_timeout != CEPH_MOUNT_TIMEOUT_DEFAULT)
seq_printf(m, "mount_timeout=%d,",
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 45eba2dcb67a..d3bb656308b4 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -515,6 +515,10 @@ static void ceph_con_reset_protocol(struct ceph_connection *con)
ceph_msg_put(con->out_msg);
con->out_msg = NULL;
}
+ if (con->bounce_page) {
+ __free_page(con->bounce_page);
+ con->bounce_page = NULL;
+ }
if (ceph_msgr2(from_msgr(con->msgr)))
ceph_con_v2_reset_protocol(con);
diff --git a/net/ceph/messenger_v1.c b/net/ceph/messenger_v1.c
index 2cb5ffdf071a..6b014eca3a13 100644
--- a/net/ceph/messenger_v1.c
+++ b/net/ceph/messenger_v1.c
@@ -992,8 +992,7 @@ static int read_partial_message_section(struct ceph_connection *con,
static int read_partial_msg_data(struct ceph_connection *con)
{
- struct ceph_msg *msg = con->in_msg;
- struct ceph_msg_data_cursor *cursor = &msg->cursor;
+ struct ceph_msg_data_cursor *cursor = &con->in_msg->cursor;
bool do_datacrc = !ceph_test_opt(from_msgr(con->msgr), NOCRC);
struct page *page;
size_t page_offset;
@@ -1001,9 +1000,6 @@ static int read_partial_msg_data(struct ceph_connection *con)
u32 crc = 0;
int ret;
- if (!msg->num_data_items)
- return -EIO;
-
if (do_datacrc)
crc = con->in_data_crc;
while (cursor->total_resid) {
@@ -1031,6 +1027,46 @@ static int read_partial_msg_data(struct ceph_connection *con)
return 1; /* must return > 0 to indicate success */
}
+static int read_partial_msg_data_bounce(struct ceph_connection *con)
+{
+ struct ceph_msg_data_cursor *cursor = &con->in_msg->cursor;
+ struct page *page;
+ size_t off, len;
+ u32 crc;
+ int ret;
+
+ if (unlikely(!con->bounce_page)) {
+ con->bounce_page = alloc_page(GFP_NOIO);
+ if (!con->bounce_page) {
+ pr_err("failed to allocate bounce page\n");
+ return -ENOMEM;
+ }
+ }
+
+ crc = con->in_data_crc;
+ while (cursor->total_resid) {
+ if (!cursor->resid) {
+ ceph_msg_data_advance(cursor, 0);
+ continue;
+ }
+
+ page = ceph_msg_data_next(cursor, &off, &len, NULL);
+ ret = ceph_tcp_recvpage(con->sock, con->bounce_page, 0, len);
+ if (ret <= 0) {
+ con->in_data_crc = crc;
+ return ret;
+ }
+
+ crc = crc32c(crc, page_address(con->bounce_page), ret);
+ memcpy_to_page(page, off, page_address(con->bounce_page), ret);
+
+ ceph_msg_data_advance(cursor, ret);
+ }
+ con->in_data_crc = crc;
+
+ return 1; /* must return > 0 to indicate success */
+}
+
/*
* read (part of) a message.
*/
@@ -1141,7 +1177,13 @@ static int read_partial_message(struct ceph_connection *con)
/* (page) data */
if (data_len) {
- ret = read_partial_msg_data(con);
+ if (!m->num_data_items)
+ return -EIO;
+
+ if (ceph_test_opt(from_msgr(con->msgr), RXBOUNCE))
+ ret = read_partial_msg_data_bounce(con);
+ else
+ ret = read_partial_msg_data(con);
if (ret <= 0)
return ret;
}
diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c
index c4099b641b38..c81379f93ad5 100644
--- a/net/ceph/messenger_v2.c
+++ b/net/ceph/messenger_v2.c
@@ -57,8 +57,9 @@
#define IN_S_HANDLE_CONTROL_REMAINDER 3
#define IN_S_PREPARE_READ_DATA 4
#define IN_S_PREPARE_READ_DATA_CONT 5
-#define IN_S_HANDLE_EPILOGUE 6
-#define IN_S_FINISH_SKIP 7
+#define IN_S_PREPARE_READ_ENC_PAGE 6
+#define IN_S_HANDLE_EPILOGUE 7
+#define IN_S_FINISH_SKIP 8
#define OUT_S_QUEUE_DATA 1
#define OUT_S_QUEUE_DATA_CONT 2
@@ -1032,22 +1033,41 @@ static int decrypt_control_remainder(struct ceph_connection *con)
padded_len(rem_len) + CEPH_GCM_TAG_LEN);
}
-static int decrypt_message(struct ceph_connection *con)
+static int decrypt_tail(struct ceph_connection *con)
{
+ struct sg_table enc_sgt = {};
struct sg_table sgt = {};
+ int tail_len;
int ret;
+ tail_len = tail_onwire_len(con->in_msg, true);
+ ret = sg_alloc_table_from_pages(&enc_sgt, con->v2.in_enc_pages,
+ con->v2.in_enc_page_cnt, 0, tail_len,
+ GFP_NOIO);
+ if (ret)
+ goto out;
+
ret = setup_message_sgs(&sgt, con->in_msg, FRONT_PAD(con->v2.in_buf),
MIDDLE_PAD(con->v2.in_buf), DATA_PAD(con->v2.in_buf),
con->v2.in_buf, true);
if (ret)
goto out;
- ret = gcm_crypt(con, false, sgt.sgl, sgt.sgl,
- tail_onwire_len(con->in_msg, true));
+ dout("%s con %p msg %p enc_page_cnt %d sg_cnt %d\n", __func__, con,
+ con->in_msg, con->v2.in_enc_page_cnt, sgt.orig_nents);
+ ret = gcm_crypt(con, false, enc_sgt.sgl, sgt.sgl, tail_len);
+ if (ret)
+ goto out;
+
+ WARN_ON(!con->v2.in_enc_page_cnt);
+ ceph_release_page_vector(con->v2.in_enc_pages,
+ con->v2.in_enc_page_cnt);
+ con->v2.in_enc_pages = NULL;
+ con->v2.in_enc_page_cnt = 0;
out:
sg_free_table(&sgt);
+ sg_free_table(&enc_sgt);
return ret;
}
@@ -1733,54 +1753,157 @@ static int prepare_read_control_remainder(struct ceph_connection *con)
return 0;
}
-static void prepare_read_data(struct ceph_connection *con)
+static int prepare_read_data(struct ceph_connection *con)
{
struct bio_vec bv;
- if (!con_secure(con))
- con->in_data_crc = -1;
+ con->in_data_crc = -1;
ceph_msg_data_cursor_init(&con->v2.in_cursor, con->in_msg,
data_len(con->in_msg));
get_bvec_at(&con->v2.in_cursor, &bv);
- set_in_bvec(con, &bv);
+ if (ceph_test_opt(from_msgr(con->msgr), RXBOUNCE)) {
+ if (unlikely(!con->bounce_page)) {
+ con->bounce_page = alloc_page(GFP_NOIO);
+ if (!con->bounce_page) {
+ pr_err("failed to allocate bounce page\n");
+ return -ENOMEM;
+ }
+ }
+
+ bv.bv_page = con->bounce_page;
+ bv.bv_offset = 0;
+ set_in_bvec(con, &bv);
+ } else {
+ set_in_bvec(con, &bv);
+ }
con->v2.in_state = IN_S_PREPARE_READ_DATA_CONT;
+ return 0;
}
static void prepare_read_data_cont(struct ceph_connection *con)
{
struct bio_vec bv;
- if (!con_secure(con))
+ if (ceph_test_opt(from_msgr(con->msgr), RXBOUNCE)) {
+ con->in_data_crc = crc32c(con->in_data_crc,
+ page_address(con->bounce_page),
+ con->v2.in_bvec.bv_len);
+
+ get_bvec_at(&con->v2.in_cursor, &bv);
+ memcpy_to_page(bv.bv_page, bv.bv_offset,
+ page_address(con->bounce_page),
+ con->v2.in_bvec.bv_len);
+ } else {
con->in_data_crc = ceph_crc32c_page(con->in_data_crc,
con->v2.in_bvec.bv_page,
con->v2.in_bvec.bv_offset,
con->v2.in_bvec.bv_len);
+ }
ceph_msg_data_advance(&con->v2.in_cursor, con->v2.in_bvec.bv_len);
if (con->v2.in_cursor.total_resid) {
get_bvec_at(&con->v2.in_cursor, &bv);
- set_in_bvec(con, &bv);
+ if (ceph_test_opt(from_msgr(con->msgr), RXBOUNCE)) {
+ bv.bv_page = con->bounce_page;
+ bv.bv_offset = 0;
+ set_in_bvec(con, &bv);
+ } else {
+ set_in_bvec(con, &bv);
+ }
WARN_ON(con->v2.in_state != IN_S_PREPARE_READ_DATA_CONT);
return;
}
/*
- * We've read all data. Prepare to read data padding (if any)
- * and epilogue.
+ * We've read all data. Prepare to read epilogue.
*/
reset_in_kvecs(con);
- if (con_secure(con)) {
- if (need_padding(data_len(con->in_msg)))
- add_in_kvec(con, DATA_PAD(con->v2.in_buf),
- padding_len(data_len(con->in_msg)));
- add_in_kvec(con, con->v2.in_buf, CEPH_EPILOGUE_SECURE_LEN);
+ add_in_kvec(con, con->v2.in_buf, CEPH_EPILOGUE_PLAIN_LEN);
+ con->v2.in_state = IN_S_HANDLE_EPILOGUE;
+}
+
+static int prepare_read_tail_plain(struct ceph_connection *con)
+{
+ struct ceph_msg *msg = con->in_msg;
+
+ if (!front_len(msg) && !middle_len(msg)) {
+ WARN_ON(!data_len(msg));
+ return prepare_read_data(con);
+ }
+
+ reset_in_kvecs(con);
+ if (front_len(msg)) {
+ add_in_kvec(con, msg->front.iov_base, front_len(msg));
+ WARN_ON(msg->front.iov_len != front_len(msg));
+ }
+ if (middle_len(msg)) {
+ add_in_kvec(con, msg->middle->vec.iov_base, middle_len(msg));
+ WARN_ON(msg->middle->vec.iov_len != middle_len(msg));
+ }
+
+ if (data_len(msg)) {
+ con->v2.in_state = IN_S_PREPARE_READ_DATA;
} else {
add_in_kvec(con, con->v2.in_buf, CEPH_EPILOGUE_PLAIN_LEN);
+ con->v2.in_state = IN_S_HANDLE_EPILOGUE;
}
+ return 0;
+}
+
+static void prepare_read_enc_page(struct ceph_connection *con)
+{
+ struct bio_vec bv;
+
+ dout("%s con %p i %d resid %d\n", __func__, con, con->v2.in_enc_i,
+ con->v2.in_enc_resid);
+ WARN_ON(!con->v2.in_enc_resid);
+
+ bv.bv_page = con->v2.in_enc_pages[con->v2.in_enc_i];
+ bv.bv_offset = 0;
+ bv.bv_len = min(con->v2.in_enc_resid, (int)PAGE_SIZE);
+
+ set_in_bvec(con, &bv);
+ con->v2.in_enc_i++;
+ con->v2.in_enc_resid -= bv.bv_len;
+
+ if (con->v2.in_enc_resid) {
+ con->v2.in_state = IN_S_PREPARE_READ_ENC_PAGE;
+ return;
+ }
+
+ /*
+ * We are set to read the last piece of ciphertext (ending
+ * with epilogue) + auth tag.
+ */
+ WARN_ON(con->v2.in_enc_i != con->v2.in_enc_page_cnt);
con->v2.in_state = IN_S_HANDLE_EPILOGUE;
}
+static int prepare_read_tail_secure(struct ceph_connection *con)
+{
+ struct page **enc_pages;
+ int enc_page_cnt;
+ int tail_len;
+
+ tail_len = tail_onwire_len(con->in_msg, true);
+ WARN_ON(!tail_len);
+
+ enc_page_cnt = calc_pages_for(0, tail_len);
+ enc_pages = ceph_alloc_page_vector(enc_page_cnt, GFP_NOIO);
+ if (IS_ERR(enc_pages))
+ return PTR_ERR(enc_pages);
+
+ WARN_ON(con->v2.in_enc_pages || con->v2.in_enc_page_cnt);
+ con->v2.in_enc_pages = enc_pages;
+ con->v2.in_enc_page_cnt = enc_page_cnt;
+ con->v2.in_enc_resid = tail_len;
+ con->v2.in_enc_i = 0;
+
+ prepare_read_enc_page(con);
+ return 0;
+}
+
static void __finish_skip(struct ceph_connection *con)
{
con->in_seq++;
@@ -2589,47 +2712,26 @@ static int __handle_control(struct ceph_connection *con, void *p)
}
msg = con->in_msg; /* set in process_message_header() */
- if (!front_len(msg) && !middle_len(msg)) {
- if (!data_len(msg))
- return process_message(con);
-
- prepare_read_data(con);
- return 0;
- }
-
- reset_in_kvecs(con);
if (front_len(msg)) {
WARN_ON(front_len(msg) > msg->front_alloc_len);
- add_in_kvec(con, msg->front.iov_base, front_len(msg));
msg->front.iov_len = front_len(msg);
-
- if (con_secure(con) && need_padding(front_len(msg)))
- add_in_kvec(con, FRONT_PAD(con->v2.in_buf),
- padding_len(front_len(msg)));
} else {
msg->front.iov_len = 0;
}
if (middle_len(msg)) {
WARN_ON(middle_len(msg) > msg->middle->alloc_len);
- add_in_kvec(con, msg->middle->vec.iov_base, middle_len(msg));
msg->middle->vec.iov_len = middle_len(msg);
-
- if (con_secure(con) && need_padding(middle_len(msg)))
- add_in_kvec(con, MIDDLE_PAD(con->v2.in_buf),
- padding_len(middle_len(msg)));
} else if (msg->middle) {
msg->middle->vec.iov_len = 0;
}
- if (data_len(msg)) {
- con->v2.in_state = IN_S_PREPARE_READ_DATA;
- } else {
- add_in_kvec(con, con->v2.in_buf,
- con_secure(con) ? CEPH_EPILOGUE_SECURE_LEN :
- CEPH_EPILOGUE_PLAIN_LEN);
- con->v2.in_state = IN_S_HANDLE_EPILOGUE;
- }
- return 0;
+ if (!front_len(msg) && !middle_len(msg) && !data_len(msg))
+ return process_message(con);
+
+ if (con_secure(con))
+ return prepare_read_tail_secure(con);
+
+ return prepare_read_tail_plain(con);
}
static int handle_preamble(struct ceph_connection *con)
@@ -2717,7 +2819,7 @@ static int handle_epilogue(struct ceph_connection *con)
int ret;
if (con_secure(con)) {
- ret = decrypt_message(con);
+ ret = decrypt_tail(con);
if (ret) {
if (ret == -EBADMSG)
con->error_msg = "integrity error, bad epilogue auth tag";
@@ -2785,13 +2887,16 @@ static int populate_in_iter(struct ceph_connection *con)
ret = handle_control_remainder(con);
break;
case IN_S_PREPARE_READ_DATA:
- prepare_read_data(con);
- ret = 0;
+ ret = prepare_read_data(con);
break;
case IN_S_PREPARE_READ_DATA_CONT:
prepare_read_data_cont(con);
ret = 0;
break;
+ case IN_S_PREPARE_READ_ENC_PAGE:
+ prepare_read_enc_page(con);
+ ret = 0;
+ break;
case IN_S_HANDLE_EPILOGUE:
ret = handle_epilogue(con);
break;
@@ -3326,20 +3431,16 @@ void ceph_con_v2_revoke(struct ceph_connection *con)
static void revoke_at_prepare_read_data(struct ceph_connection *con)
{
- int remaining; /* data + [data padding] + epilogue */
+ int remaining;
int resid;
+ WARN_ON(con_secure(con));
WARN_ON(!data_len(con->in_msg));
WARN_ON(!iov_iter_is_kvec(&con->v2.in_iter));
resid = iov_iter_count(&con->v2.in_iter);
WARN_ON(!resid);
- if (con_secure(con))
- remaining = padded_len(data_len(con->in_msg)) +
- CEPH_EPILOGUE_SECURE_LEN;
- else
- remaining = data_len(con->in_msg) + CEPH_EPILOGUE_PLAIN_LEN;
-
+ remaining = data_len(con->in_msg) + CEPH_EPILOGUE_PLAIN_LEN;
dout("%s con %p resid %d remaining %d\n", __func__, con, resid,
remaining);
con->v2.in_iter.count -= resid;
@@ -3350,8 +3451,9 @@ static void revoke_at_prepare_read_data(struct ceph_connection *con)
static void revoke_at_prepare_read_data_cont(struct ceph_connection *con)
{
int recved, resid; /* current piece of data */
- int remaining; /* [data padding] + epilogue */
+ int remaining;
+ WARN_ON(con_secure(con));
WARN_ON(!data_len(con->in_msg));
WARN_ON(!iov_iter_is_bvec(&con->v2.in_iter));
resid = iov_iter_count(&con->v2.in_iter);
@@ -3363,12 +3465,7 @@ static void revoke_at_prepare_read_data_cont(struct ceph_connection *con)
ceph_msg_data_advance(&con->v2.in_cursor, recved);
WARN_ON(resid > con->v2.in_cursor.total_resid);
- if (con_secure(con))
- remaining = padding_len(data_len(con->in_msg)) +
- CEPH_EPILOGUE_SECURE_LEN;
- else
- remaining = CEPH_EPILOGUE_PLAIN_LEN;
-
+ remaining = CEPH_EPILOGUE_PLAIN_LEN;
dout("%s con %p total_resid %zu remaining %d\n", __func__, con,
con->v2.in_cursor.total_resid, remaining);
con->v2.in_iter.count -= resid;
@@ -3376,11 +3473,26 @@ static void revoke_at_prepare_read_data_cont(struct ceph_connection *con)
con->v2.in_state = IN_S_FINISH_SKIP;
}
+static void revoke_at_prepare_read_enc_page(struct ceph_connection *con)
+{
+ int resid; /* current enc page (not necessarily data) */
+
+ WARN_ON(!con_secure(con));
+ WARN_ON(!iov_iter_is_bvec(&con->v2.in_iter));
+ resid = iov_iter_count(&con->v2.in_iter);
+ WARN_ON(!resid || resid > con->v2.in_bvec.bv_len);
+
+ dout("%s con %p resid %d enc_resid %d\n", __func__, con, resid,
+ con->v2.in_enc_resid);
+ con->v2.in_iter.count -= resid;
+ set_in_skip(con, resid + con->v2.in_enc_resid);
+ con->v2.in_state = IN_S_FINISH_SKIP;
+}
+
static void revoke_at_handle_epilogue(struct ceph_connection *con)
{
int resid;
- WARN_ON(!iov_iter_is_kvec(&con->v2.in_iter));
resid = iov_iter_count(&con->v2.in_iter);
WARN_ON(!resid);
@@ -3399,6 +3511,9 @@ void ceph_con_v2_revoke_incoming(struct ceph_connection *con)
case IN_S_PREPARE_READ_DATA_CONT:
revoke_at_prepare_read_data_cont(con);
break;
+ case IN_S_PREPARE_READ_ENC_PAGE:
+ revoke_at_prepare_read_enc_page(con);
+ break;
case IN_S_HANDLE_EPILOGUE:
revoke_at_handle_epilogue(con);
break;
@@ -3432,6 +3547,13 @@ void ceph_con_v2_reset_protocol(struct ceph_connection *con)
clear_out_sign_kvecs(con);
free_conn_bufs(con);
+ if (con->v2.in_enc_pages) {
+ WARN_ON(!con->v2.in_enc_page_cnt);
+ ceph_release_page_vector(con->v2.in_enc_pages,
+ con->v2.in_enc_page_cnt);
+ con->v2.in_enc_pages = NULL;
+ con->v2.in_enc_page_cnt = 0;
+ }
if (con->v2.out_enc_pages) {
WARN_ON(!con->v2.out_enc_page_cnt);
ceph_release_page_vector(con->v2.out_enc_pages,
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 6c2016f7f3d1..ec0bf737b076 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1133,7 +1133,8 @@ out:
neigh_release(neigh);
}
-int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
+int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb,
+ const bool immediate_ok)
{
int rc;
bool immediate_probe = false;
@@ -1154,12 +1155,17 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
atomic_set(&neigh->probes,
NEIGH_VAR(neigh->parms, UCAST_PROBES));
neigh_del_timer(neigh);
- neigh->nud_state = NUD_INCOMPLETE;
+ neigh->nud_state = NUD_INCOMPLETE;
neigh->updated = now;
- next = now + max(NEIGH_VAR(neigh->parms, RETRANS_TIME),
- HZ/100);
+ if (!immediate_ok) {
+ next = now + 1;
+ } else {
+ immediate_probe = true;
+ next = now + max(NEIGH_VAR(neigh->parms,
+ RETRANS_TIME),
+ HZ / 100);
+ }
neigh_add_timer(neigh, next);
- immediate_probe = true;
} else {
neigh->nud_state = NUD_FAILED;
neigh->updated = jiffies;
@@ -1571,7 +1577,7 @@ static void neigh_managed_work(struct work_struct *work)
write_lock_bh(&tbl->lock);
list_for_each_entry(neigh, &tbl->managed_list, managed_list)
- neigh_event_send(neigh, NULL);
+ neigh_event_send_probe(neigh, NULL, false);
queue_delayed_work(system_power_efficient_wq, &tbl->managed_work,
NEIGH_VAR(&tbl->parms, DELAY_PROBE_TIME));
write_unlock_bh(&tbl->lock);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index e476403231f0..710da8a36729 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3275,8 +3275,8 @@ static int __rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh,
struct nlattr *slave_attr[RTNL_SLAVE_MAX_TYPE + 1];
unsigned char name_assign_type = NET_NAME_USER;
struct nlattr *linkinfo[IFLA_INFO_MAX + 1];
- const struct rtnl_link_ops *m_ops = NULL;
- struct net_device *master_dev = NULL;
+ const struct rtnl_link_ops *m_ops;
+ struct net_device *master_dev;
struct net *net = sock_net(skb->sk);
const struct rtnl_link_ops *ops;
struct nlattr *tb[IFLA_MAX + 1];
@@ -3314,6 +3314,8 @@ replay:
else
dev = NULL;
+ master_dev = NULL;
+ m_ops = NULL;
if (dev) {
master_dev = netdev_master_upper_dev_get(dev);
if (master_dev)
diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index 277124f206e0..e0b072aecf0f 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -1441,7 +1441,7 @@ static int nl802154_send_key(struct sk_buff *msg, u32 cmd, u32 portid,
hdr = nl802154hdr_put(msg, portid, seq, flags, cmd);
if (!hdr)
- return -1;
+ return -ENOBUFS;
if (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex))
goto nla_put_failure;
@@ -1634,7 +1634,7 @@ static int nl802154_send_device(struct sk_buff *msg, u32 cmd, u32 portid,
hdr = nl802154hdr_put(msg, portid, seq, flags, cmd);
if (!hdr)
- return -1;
+ return -ENOBUFS;
if (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex))
goto nla_put_failure;
@@ -1812,7 +1812,7 @@ static int nl802154_send_devkey(struct sk_buff *msg, u32 cmd, u32 portid,
hdr = nl802154hdr_put(msg, portid, seq, flags, cmd);
if (!hdr)
- return -1;
+ return -ENOBUFS;
if (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex))
goto nla_put_failure;
@@ -1988,7 +1988,7 @@ static int nl802154_send_seclevel(struct sk_buff *msg, u32 cmd, u32 portid,
hdr = nl802154hdr_put(msg, portid, seq, flags, cmd);
if (!hdr)
- return -1;
+ return -ENOBUFS;
if (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex))
goto nla_put_failure;
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index 67087f95579f..aab384126f61 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -58,10 +58,6 @@ config NF_TABLES_ARP
endif # NF_TABLES
-config NF_FLOW_TABLE_IPV4
- tristate
- select NF_FLOW_TABLE_INET
-
config NF_DUP_IPV4
tristate "Netfilter IPv4 packet duplication to alternate destination"
depends on !NF_CONNTRACK || NF_CONNTRACK
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 78e81465f5f3..bdf108f544a4 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1322,10 +1322,13 @@ new_segment:
/* skb changing from pure zc to mixed, must charge zc */
if (unlikely(skb_zcopy_pure(skb))) {
- if (!sk_wmem_schedule(sk, skb->data_len))
+ u32 extra = skb->truesize -
+ SKB_TRUESIZE(skb_end_offset(skb));
+
+ if (!sk_wmem_schedule(sk, extra))
goto wait_for_space;
- sk_mem_charge(sk, skb->data_len);
+ sk_mem_charge(sk, extra);
skb_shinfo(skb)->flags &= ~SKBFL_PURE_ZEROCOPY;
}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index dc49a3d551eb..bfe4112e000c 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1660,6 +1660,8 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb,
(mss != tcp_skb_seglen(skb)))
goto out;
+ if (!tcp_skb_can_collapse(prev, skb))
+ goto out;
len = skb->len;
pcount = tcp_skb_pcount(skb);
if (tcp_skb_shift(prev, skb, pcount, len))
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index 97d3d1b36dbc..0ba62f4868f9 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -47,10 +47,6 @@ config NFT_FIB_IPV6
endif # NF_TABLES_IPV6
endif # NF_TABLES
-config NF_FLOW_TABLE_IPV6
- tristate
- select NF_FLOW_TABLE_INET
-
config NF_DUP_IPV6
tristate "Netfilter IPv6 packet duplication to alternate destination"
depends on !NF_CONNTRACK || NF_CONNTRACK
diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile
index b85383606df7..b8d6dc9aeeb6 100644
--- a/net/ipv6/netfilter/Makefile
+++ b/net/ipv6/netfilter/Makefile
@@ -28,9 +28,6 @@ obj-$(CONFIG_NFT_REJECT_IPV6) += nft_reject_ipv6.o
obj-$(CONFIG_NFT_DUP_IPV6) += nft_dup_ipv6.o
obj-$(CONFIG_NFT_FIB_IPV6) += nft_fib_ipv6.o
-# flow table support
-obj-$(CONFIG_NF_FLOW_TABLE_IPV6) += nf_flow_table_ipv6.o
-
# matches
obj-$(CONFIG_IP6_NF_MATCH_AH) += ip6t_ah.o
obj-$(CONFIG_IP6_NF_MATCH_EUI64) += ip6t_eui64.o
diff --git a/net/ipv6/netfilter/nf_flow_table_ipv6.c b/net/ipv6/netfilter/nf_flow_table_ipv6.c
deleted file mode 100644
index e69de29bb2d1..000000000000
--- a/net/ipv6/netfilter/nf_flow_table_ipv6.c
+++ /dev/null
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index cf454f8ca2b0..5fa16990da95 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -2011,7 +2011,6 @@ static void nft_last_rule(struct nft_rule_blob *blob, const void *ptr)
prule = (struct nft_rule_dp *)ptr;
prule->is_last = 1;
- ptr += offsetof(struct nft_rule_dp, data);
/* blob size does not include the trailer rule */
}
diff --git a/net/netfilter/nft_byteorder.c b/net/netfilter/nft_byteorder.c
index 9d5947ab8d4e..e646e9ee4a98 100644
--- a/net/netfilter/nft_byteorder.c
+++ b/net/netfilter/nft_byteorder.c
@@ -167,12 +167,24 @@ nla_put_failure:
return -1;
}
+static bool nft_byteorder_reduce(struct nft_regs_track *track,
+ const struct nft_expr *expr)
+{
+ struct nft_byteorder *priv = nft_expr_priv(expr);
+
+ track->regs[priv->dreg].selector = NULL;
+ track->regs[priv->dreg].bitwise = NULL;
+
+ return false;
+}
+
static const struct nft_expr_ops nft_byteorder_ops = {
.type = &nft_byteorder_type,
.size = NFT_EXPR_SIZE(sizeof(struct nft_byteorder)),
.eval = nft_byteorder_eval,
.init = nft_byteorder_init,
.dump = nft_byteorder_dump,
+ .reduce = nft_byteorder_reduce,
};
struct nft_expr_type nft_byteorder_type __read_mostly = {
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index 518d96c8c247..5adf8bb628a8 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -260,9 +260,12 @@ static void nft_ct_set_zone_eval(const struct nft_expr *expr,
ct = this_cpu_read(nft_ct_pcpu_template);
if (likely(refcount_read(&ct->ct_general.use) == 1)) {
+ refcount_inc(&ct->ct_general.use);
nf_ct_zone_add(ct, &zone);
} else {
- /* previous skb got queued to userspace */
+ /* previous skb got queued to userspace, allocate temporary
+ * one until percpu template can be reused.
+ */
ct = nf_ct_tmpl_alloc(nft_net(pkt), &zone, GFP_ATOMIC);
if (!ct) {
regs->verdict.code = NF_DROP;
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 85ea7ddb48db..ab87f22cc7ec 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1789,7 +1789,10 @@ static int fanout_add(struct sock *sk, struct fanout_args *args)
err = -ENOSPC;
if (refcount_read(&match->sk_ref) < match->max_num_members) {
__dev_remove_pack(&po->prot_hook);
- po->fanout = match;
+
+ /* Paired with packet_setsockopt(PACKET_FANOUT_DATA) */
+ WRITE_ONCE(po->fanout, match);
+
po->rollover = rollover;
rollover = NULL;
refcount_set(&match->sk_ref, refcount_read(&match->sk_ref) + 1);
@@ -3934,7 +3937,8 @@ packet_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval,
}
case PACKET_FANOUT_DATA:
{
- if (!po->fanout)
+ /* Paired with the WRITE_ONCE() in fanout_add() */
+ if (!READ_ONCE(po->fanout))
return -EINVAL;
return fanout_set_data(po, optval, optlen);
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index d4e27c679123..5f0f346b576f 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1945,9 +1945,9 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
bool prio_allocate;
u32 parent;
u32 chain_index;
- struct Qdisc *q = NULL;
+ struct Qdisc *q;
struct tcf_chain_info chain_info;
- struct tcf_chain *chain = NULL;
+ struct tcf_chain *chain;
struct tcf_block *block;
struct tcf_proto *tp;
unsigned long cl;
@@ -1976,6 +1976,8 @@ replay:
tp = NULL;
cl = 0;
block = NULL;
+ q = NULL;
+ chain = NULL;
flags = 0;
if (prio == 0) {
@@ -2798,8 +2800,8 @@ static int tc_ctl_chain(struct sk_buff *skb, struct nlmsghdr *n,
struct tcmsg *t;
u32 parent;
u32 chain_index;
- struct Qdisc *q = NULL;
- struct tcf_chain *chain = NULL;
+ struct Qdisc *q;
+ struct tcf_chain *chain;
struct tcf_block *block;
unsigned long cl;
int err;
@@ -2809,6 +2811,7 @@ static int tc_ctl_chain(struct sk_buff *skb, struct nlmsghdr *n,
return -EPERM;
replay:
+ q = NULL;
err = nlmsg_parse_deprecated(n, sizeof(*t), tca, TCA_MAX,
rtm_tca_policy, extack);
if (err < 0)
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index d5ea62b82bb8..8c89d0b0ca18 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -566,17 +566,115 @@ static void smc_stat_fallback(struct smc_sock *smc)
mutex_unlock(&net->smc.mutex_fback_rsn);
}
+/* must be called under rcu read lock */
+static void smc_fback_wakeup_waitqueue(struct smc_sock *smc, void *key)
+{
+ struct socket_wq *wq;
+ __poll_t flags;
+
+ wq = rcu_dereference(smc->sk.sk_wq);
+ if (!skwq_has_sleeper(wq))
+ return;
+
+ /* wake up smc sk->sk_wq */
+ if (!key) {
+ /* sk_state_change */
+ wake_up_interruptible_all(&wq->wait);
+ } else {
+ flags = key_to_poll(key);
+ if (flags & (EPOLLIN | EPOLLOUT))
+ /* sk_data_ready or sk_write_space */
+ wake_up_interruptible_sync_poll(&wq->wait, flags);
+ else if (flags & EPOLLERR)
+ /* sk_error_report */
+ wake_up_interruptible_poll(&wq->wait, flags);
+ }
+}
+
+static int smc_fback_mark_woken(wait_queue_entry_t *wait,
+ unsigned int mode, int sync, void *key)
+{
+ struct smc_mark_woken *mark =
+ container_of(wait, struct smc_mark_woken, wait_entry);
+
+ mark->woken = true;
+ mark->key = key;
+ return 0;
+}
+
+static void smc_fback_forward_wakeup(struct smc_sock *smc, struct sock *clcsk,
+ void (*clcsock_callback)(struct sock *sk))
+{
+ struct smc_mark_woken mark = { .woken = false };
+ struct socket_wq *wq;
+
+ init_waitqueue_func_entry(&mark.wait_entry,
+ smc_fback_mark_woken);
+ rcu_read_lock();
+ wq = rcu_dereference(clcsk->sk_wq);
+ if (!wq)
+ goto out;
+ add_wait_queue(sk_sleep(clcsk), &mark.wait_entry);
+ clcsock_callback(clcsk);
+ remove_wait_queue(sk_sleep(clcsk), &mark.wait_entry);
+
+ if (mark.woken)
+ smc_fback_wakeup_waitqueue(smc, mark.key);
+out:
+ rcu_read_unlock();
+}
+
+static void smc_fback_state_change(struct sock *clcsk)
+{
+ struct smc_sock *smc =
+ smc_clcsock_user_data(clcsk);
+
+ if (!smc)
+ return;
+ smc_fback_forward_wakeup(smc, clcsk, smc->clcsk_state_change);
+}
+
+static void smc_fback_data_ready(struct sock *clcsk)
+{
+ struct smc_sock *smc =
+ smc_clcsock_user_data(clcsk);
+
+ if (!smc)
+ return;
+ smc_fback_forward_wakeup(smc, clcsk, smc->clcsk_data_ready);
+}
+
+static void smc_fback_write_space(struct sock *clcsk)
+{
+ struct smc_sock *smc =
+ smc_clcsock_user_data(clcsk);
+
+ if (!smc)
+ return;
+ smc_fback_forward_wakeup(smc, clcsk, smc->clcsk_write_space);
+}
+
+static void smc_fback_error_report(struct sock *clcsk)
+{
+ struct smc_sock *smc =
+ smc_clcsock_user_data(clcsk);
+
+ if (!smc)
+ return;
+ smc_fback_forward_wakeup(smc, clcsk, smc->clcsk_error_report);
+}
+
static int smc_switch_to_fallback(struct smc_sock *smc, int reason_code)
{
- wait_queue_head_t *smc_wait = sk_sleep(&smc->sk);
- wait_queue_head_t *clc_wait;
- unsigned long flags;
+ struct sock *clcsk;
mutex_lock(&smc->clcsock_release_lock);
if (!smc->clcsock) {
mutex_unlock(&smc->clcsock_release_lock);
return -EBADF;
}
+ clcsk = smc->clcsock->sk;
+
smc->use_fallback = true;
smc->fallback_rsn = reason_code;
smc_stat_fallback(smc);
@@ -587,16 +685,22 @@ static int smc_switch_to_fallback(struct smc_sock *smc, int reason_code)
smc->clcsock->wq.fasync_list =
smc->sk.sk_socket->wq.fasync_list;
- /* There may be some entries remaining in
- * smc socket->wq, which should be removed
- * to clcsocket->wq during the fallback.
+ /* There might be some wait entries remaining
+ * in smc sk->sk_wq and they should be woken up
+ * as clcsock's wait queue is woken up.
*/
- clc_wait = sk_sleep(smc->clcsock->sk);
- spin_lock_irqsave(&smc_wait->lock, flags);
- spin_lock_nested(&clc_wait->lock, SINGLE_DEPTH_NESTING);
- list_splice_init(&smc_wait->head, &clc_wait->head);
- spin_unlock(&clc_wait->lock);
- spin_unlock_irqrestore(&smc_wait->lock, flags);
+ smc->clcsk_state_change = clcsk->sk_state_change;
+ smc->clcsk_data_ready = clcsk->sk_data_ready;
+ smc->clcsk_write_space = clcsk->sk_write_space;
+ smc->clcsk_error_report = clcsk->sk_error_report;
+
+ clcsk->sk_state_change = smc_fback_state_change;
+ clcsk->sk_data_ready = smc_fback_data_ready;
+ clcsk->sk_write_space = smc_fback_write_space;
+ clcsk->sk_error_report = smc_fback_error_report;
+
+ smc->clcsock->sk->sk_user_data =
+ (void *)((uintptr_t)smc | SK_USER_DATA_NOCOPY);
}
mutex_unlock(&smc->clcsock_release_lock);
return 0;
@@ -2115,10 +2219,9 @@ out:
static void smc_clcsock_data_ready(struct sock *listen_clcsock)
{
- struct smc_sock *lsmc;
+ struct smc_sock *lsmc =
+ smc_clcsock_user_data(listen_clcsock);
- lsmc = (struct smc_sock *)
- ((uintptr_t)listen_clcsock->sk_user_data & ~SK_USER_DATA_NOCOPY);
if (!lsmc)
return;
lsmc->clcsk_data_ready(listen_clcsock);
diff --git a/net/smc/smc.h b/net/smc/smc.h
index 3d0b8e300deb..37b2001a0255 100644
--- a/net/smc/smc.h
+++ b/net/smc/smc.h
@@ -139,6 +139,12 @@ enum smc_urg_state {
SMC_URG_READ = 3, /* data was already read */
};
+struct smc_mark_woken {
+ bool woken;
+ void *key;
+ wait_queue_entry_t wait_entry;
+};
+
struct smc_connection {
struct rb_node alert_node;
struct smc_link_group *lgr; /* link group of connection */
@@ -228,8 +234,14 @@ struct smc_connection {
struct smc_sock { /* smc sock container */
struct sock sk;
struct socket *clcsock; /* internal tcp socket */
+ void (*clcsk_state_change)(struct sock *sk);
+ /* original stat_change fct. */
void (*clcsk_data_ready)(struct sock *sk);
- /* original data_ready fct. **/
+ /* original data_ready fct. */
+ void (*clcsk_write_space)(struct sock *sk);
+ /* original write_space fct. */
+ void (*clcsk_error_report)(struct sock *sk);
+ /* original error_report fct. */
struct smc_connection conn; /* smc connection */
struct smc_sock *listen_smc; /* listen parent */
struct work_struct connect_work; /* handle non-blocking connect*/
@@ -264,6 +276,12 @@ static inline struct smc_sock *smc_sk(const struct sock *sk)
return (struct smc_sock *)sk;
}
+static inline struct smc_sock *smc_clcsock_user_data(struct sock *clcsk)
+{
+ return (struct smc_sock *)
+ ((uintptr_t)clcsk->sk_user_data & ~SK_USER_DATA_NOCOPY);
+}
+
extern struct workqueue_struct *smc_hs_wq; /* wq for handshake work */
extern struct workqueue_struct *smc_close_wq; /* wq for close work */
diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c
index b8898c787d23..1fca2f90a9c7 100644
--- a/net/smc/smc_diag.c
+++ b/net/smc/smc_diag.c
@@ -146,13 +146,11 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb,
(req->diag_ext & (1 << (SMC_DIAG_LGRINFO - 1))) &&
!list_empty(&smc->conn.lgr->list)) {
struct smc_link *link = smc->conn.lnk;
- struct net *net = read_pnet(&link->smcibdev->ibdev->coredev.rdma_net);
struct smc_diag_lgrinfo linfo = {
.role = smc->conn.lgr->role,
.lnk[0].ibport = link->ibport,
.lnk[0].link_id = link->link_id,
- .lnk[0].net_cookie = net->net_cookie,
};
memcpy(linfo.lnk[0].ibname,
generated by cgit v1.2.3 (git 2.25.1) at 2024-07-25 15:54:40 +0300