summaryrefslogtreecommitdiffstats
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/ceph/ceph_common.c2
-rw-r--r--net/ceph/debugfs.c8
-rw-r--r--net/ceph/mon_client.c150
-rw-r--r--net/core/datagram.c36
-rw-r--r--net/core/skbuff.c3
-rw-r--r--net/ipv4/udp.c4
-rw-r--r--net/sctp/sysctl.c32
7 files changed, 214 insertions, 21 deletions
diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c
index 67d7721d237e..1675021d8c12 100644
--- a/net/ceph/ceph_common.c
+++ b/net/ceph/ceph_common.c
@@ -72,6 +72,8 @@ const char *ceph_msg_type_name(int type)
case CEPH_MSG_MON_SUBSCRIBE_ACK: return "mon_subscribe_ack";
case CEPH_MSG_STATFS: return "statfs";
case CEPH_MSG_STATFS_REPLY: return "statfs_reply";
+ case CEPH_MSG_MON_GET_VERSION: return "mon_get_version";
+ case CEPH_MSG_MON_GET_VERSION_REPLY: return "mon_get_version_reply";
case CEPH_MSG_MDS_MAP: return "mds_map";
case CEPH_MSG_CLIENT_SESSION: return "client_session";
case CEPH_MSG_CLIENT_RECONNECT: return "client_reconnect";
diff --git a/net/ceph/debugfs.c b/net/ceph/debugfs.c
index 10421a4b76f8..d1a62c69a9f4 100644
--- a/net/ceph/debugfs.c
+++ b/net/ceph/debugfs.c
@@ -126,9 +126,13 @@ static int monc_show(struct seq_file *s, void *p)
req = rb_entry(rp, struct ceph_mon_generic_request, node);
op = le16_to_cpu(req->request->hdr.type);
if (op == CEPH_MSG_STATFS)
- seq_printf(s, "%lld statfs\n", req->tid);
+ seq_printf(s, "%llu statfs\n", req->tid);
+ else if (op == CEPH_MSG_POOLOP)
+ seq_printf(s, "%llu poolop\n", req->tid);
+ else if (op == CEPH_MSG_MON_GET_VERSION)
+ seq_printf(s, "%llu mon_get_version", req->tid);
else
- seq_printf(s, "%lld unknown\n", req->tid);
+ seq_printf(s, "%llu unknown\n", req->tid);
}
mutex_unlock(&monc->mutex);
diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c
index 2ac9ef35110b..067d3af2eaf6 100644
--- a/net/ceph/mon_client.c
+++ b/net/ceph/mon_client.c
@@ -296,6 +296,33 @@ void ceph_monc_request_next_osdmap(struct ceph_mon_client *monc)
__send_subscribe(monc);
mutex_unlock(&monc->mutex);
}
+EXPORT_SYMBOL(ceph_monc_request_next_osdmap);
+
+int ceph_monc_wait_osdmap(struct ceph_mon_client *monc, u32 epoch,
+ unsigned long timeout)
+{
+ unsigned long started = jiffies;
+ int ret;
+
+ mutex_lock(&monc->mutex);
+ while (monc->have_osdmap < epoch) {
+ mutex_unlock(&monc->mutex);
+
+ if (timeout != 0 && time_after_eq(jiffies, started + timeout))
+ return -ETIMEDOUT;
+
+ ret = wait_event_interruptible_timeout(monc->client->auth_wq,
+ monc->have_osdmap >= epoch, timeout);
+ if (ret < 0)
+ return ret;
+
+ mutex_lock(&monc->mutex);
+ }
+
+ mutex_unlock(&monc->mutex);
+ return 0;
+}
+EXPORT_SYMBOL(ceph_monc_wait_osdmap);
/*
*
@@ -477,14 +504,13 @@ static struct ceph_msg *get_generic_reply(struct ceph_connection *con,
return m;
}
-static int do_generic_request(struct ceph_mon_client *monc,
- struct ceph_mon_generic_request *req)
+static int __do_generic_request(struct ceph_mon_client *monc, u64 tid,
+ struct ceph_mon_generic_request *req)
{
int err;
/* register request */
- mutex_lock(&monc->mutex);
- req->tid = ++monc->last_tid;
+ req->tid = tid != 0 ? tid : ++monc->last_tid;
req->request->hdr.tid = cpu_to_le64(req->tid);
__insert_generic_request(monc, req);
monc->num_generic_requests++;
@@ -496,13 +522,24 @@ static int do_generic_request(struct ceph_mon_client *monc,
mutex_lock(&monc->mutex);
rb_erase(&req->node, &monc->generic_request_tree);
monc->num_generic_requests--;
- mutex_unlock(&monc->mutex);
if (!err)
err = req->result;
return err;
}
+static int do_generic_request(struct ceph_mon_client *monc,
+ struct ceph_mon_generic_request *req)
+{
+ int err;
+
+ mutex_lock(&monc->mutex);
+ err = __do_generic_request(monc, 0, req);
+ mutex_unlock(&monc->mutex);
+
+ return err;
+}
+
/*
* statfs
*/
@@ -579,6 +616,96 @@ out:
}
EXPORT_SYMBOL(ceph_monc_do_statfs);
+static void handle_get_version_reply(struct ceph_mon_client *monc,
+ struct ceph_msg *msg)
+{
+ struct ceph_mon_generic_request *req;
+ u64 tid = le64_to_cpu(msg->hdr.tid);
+ void *p = msg->front.iov_base;
+ void *end = p + msg->front_alloc_len;
+ u64 handle;
+
+ dout("%s %p tid %llu\n", __func__, msg, tid);
+
+ ceph_decode_need(&p, end, 2*sizeof(u64), bad);
+ handle = ceph_decode_64(&p);
+ if (tid != 0 && tid != handle)
+ goto bad;
+
+ mutex_lock(&monc->mutex);
+ req = __lookup_generic_req(monc, handle);
+ if (req) {
+ *(u64 *)req->buf = ceph_decode_64(&p);
+ req->result = 0;
+ get_generic_request(req);
+ }
+ mutex_unlock(&monc->mutex);
+ if (req) {
+ complete_all(&req->completion);
+ put_generic_request(req);
+ }
+
+ return;
+bad:
+ pr_err("corrupt mon_get_version reply\n");
+ ceph_msg_dump(msg);
+}
+
+/*
+ * Send MMonGetVersion and wait for the reply.
+ *
+ * @what: one of "mdsmap", "osdmap" or "monmap"
+ */
+int ceph_monc_do_get_version(struct ceph_mon_client *monc, const char *what,
+ u64 *newest)
+{
+ struct ceph_mon_generic_request *req;
+ void *p, *end;
+ u64 tid;
+ int err;
+
+ req = kzalloc(sizeof(*req), GFP_NOFS);
+ if (!req)
+ return -ENOMEM;
+
+ kref_init(&req->kref);
+ req->buf = newest;
+ req->buf_len = sizeof(*newest);
+ init_completion(&req->completion);
+
+ req->request = ceph_msg_new(CEPH_MSG_MON_GET_VERSION,
+ sizeof(u64) + sizeof(u32) + strlen(what),
+ GFP_NOFS, true);
+ if (!req->request) {
+ err = -ENOMEM;
+ goto out;
+ }
+
+ req->reply = ceph_msg_new(CEPH_MSG_MON_GET_VERSION_REPLY, 1024,
+ GFP_NOFS, true);
+ if (!req->reply) {
+ err = -ENOMEM;
+ goto out;
+ }
+
+ p = req->request->front.iov_base;
+ end = p + req->request->front_alloc_len;
+
+ /* fill out request */
+ mutex_lock(&monc->mutex);
+ tid = ++monc->last_tid;
+ ceph_encode_64(&p, tid); /* handle */
+ ceph_encode_string(&p, end, what, strlen(what));
+
+ err = __do_generic_request(monc, tid, req);
+
+ mutex_unlock(&monc->mutex);
+out:
+ kref_put(&req->kref, release_generic_request);
+ return err;
+}
+EXPORT_SYMBOL(ceph_monc_do_get_version);
+
/*
* pool ops
*/
@@ -981,6 +1108,10 @@ static void dispatch(struct ceph_connection *con, struct ceph_msg *msg)
handle_statfs_reply(monc, msg);
break;
+ case CEPH_MSG_MON_GET_VERSION_REPLY:
+ handle_get_version_reply(monc, msg);
+ break;
+
case CEPH_MSG_POOLOP_REPLY:
handle_poolop_reply(monc, msg);
break;
@@ -1029,6 +1160,15 @@ static struct ceph_msg *mon_alloc_msg(struct ceph_connection *con,
case CEPH_MSG_AUTH_REPLY:
m = ceph_msg_get(monc->m_auth_reply);
break;
+ case CEPH_MSG_MON_GET_VERSION_REPLY:
+ if (le64_to_cpu(hdr->tid) != 0)
+ return get_generic_reply(con, hdr, skip);
+
+ /*
+ * Older OSDs don't set reply tid even if the orignal
+ * request had a non-zero tid. Workaround this weirdness
+ * by falling through to the allocate case.
+ */
case CEPH_MSG_MON_MAP:
case CEPH_MSG_MDS_MAP:
case CEPH_MSG_OSD_MAP:
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 6b1c04ca1d50..488dd1a825c0 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -739,22 +739,38 @@ __sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len)
__sum16 sum;
sum = csum_fold(skb_checksum(skb, 0, len, skb->csum));
- if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) && !sum &&
- !skb->csum_complete_sw)
- netdev_rx_csum_fault(skb->dev);
-
- /* Save checksum complete for later use */
- skb->csum = sum;
- skb->ip_summed = CHECKSUM_COMPLETE;
- skb->csum_complete_sw = 1;
-
+ if (likely(!sum)) {
+ if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
+ !skb->csum_complete_sw)
+ netdev_rx_csum_fault(skb->dev);
+ }
+ skb->csum_valid = !sum;
return sum;
}
EXPORT_SYMBOL(__skb_checksum_complete_head);
__sum16 __skb_checksum_complete(struct sk_buff *skb)
{
- return __skb_checksum_complete_head(skb, skb->len);
+ __wsum csum;
+ __sum16 sum;
+
+ csum = skb_checksum(skb, 0, skb->len, 0);
+
+ /* skb->csum holds pseudo checksum */
+ sum = csum_fold(csum_add(skb->csum, csum));
+ if (likely(!sum)) {
+ if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
+ !skb->csum_complete_sw)
+ netdev_rx_csum_fault(skb->dev);
+ }
+
+ /* Save full packet checksum */
+ skb->csum = csum;
+ skb->ip_summed = CHECKSUM_COMPLETE;
+ skb->csum_complete_sw = 1;
+ skb->csum_valid = !sum;
+
+ return sum;
}
EXPORT_SYMBOL(__skb_checksum_complete);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index bf92824af3f7..9cd5344fad73 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -689,6 +689,9 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
new->ooo_okay = old->ooo_okay;
new->no_fcs = old->no_fcs;
new->encapsulation = old->encapsulation;
+ new->encap_hdr_csum = old->encap_hdr_csum;
+ new->csum_valid = old->csum_valid;
+ new->csum_complete_sw = old->csum_complete_sw;
#ifdef CONFIG_XFRM
new->sp = secpath_get(old->sp);
#endif
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 185ed3e59802..d92f94b7e402 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1861,6 +1861,10 @@ static struct sock *__udp4_lib_mcast_demux_lookup(struct net *net,
unsigned int count, slot = udp_hashfn(net, hnum, udp_table.mask);
struct udp_hslot *hslot = &udp_table.hash[slot];
+ /* Do not bother scanning a too big list */
+ if (hslot->count > 10)
+ return NULL;
+
rcu_read_lock();
begin:
count = 0;
diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c
index 7e5eb7554990..dcb19592761e 100644
--- a/net/sctp/sysctl.c
+++ b/net/sctp/sysctl.c
@@ -34,6 +34,8 @@
* Sridhar Samudrala <sri@us.ibm.com>
*/
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <net/sctp/structs.h>
#include <net/sctp/sctp.h>
#include <linux/sysctl.h>
@@ -46,6 +48,11 @@ static int sack_timer_min = 1;
static int sack_timer_max = 500;
static int addr_scope_max = 3; /* check sctp_scope_policy_t in include/net/sctp/constants.h for max entries */
static int rwnd_scale_max = 16;
+static int rto_alpha_min = 0;
+static int rto_beta_min = 0;
+static int rto_alpha_max = 1000;
+static int rto_beta_max = 1000;
+
static unsigned long max_autoclose_min = 0;
static unsigned long max_autoclose_max =
(MAX_SCHEDULE_TIMEOUT / HZ > UINT_MAX)
@@ -64,6 +71,9 @@ static int proc_sctp_do_rto_min(struct ctl_table *ctl, int write,
static int proc_sctp_do_rto_max(struct ctl_table *ctl, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos);
+static int proc_sctp_do_alpha_beta(struct ctl_table *ctl, int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos);
static int proc_sctp_do_auth(struct ctl_table *ctl, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos);
@@ -126,15 +136,19 @@ static struct ctl_table sctp_net_table[] = {
.procname = "rto_alpha_exp_divisor",
.data = &init_net.sctp.rto_alpha,
.maxlen = sizeof(int),
- .mode = 0444,
- .proc_handler = proc_dointvec,
+ .mode = 0644,
+ .proc_handler = proc_sctp_do_alpha_beta,
+ .extra1 = &rto_alpha_min,
+ .extra2 = &rto_alpha_max,
},
{
.procname = "rto_beta_exp_divisor",
.data = &init_net.sctp.rto_beta,
.maxlen = sizeof(int),
- .mode = 0444,
- .proc_handler = proc_dointvec,
+ .mode = 0644,
+ .proc_handler = proc_sctp_do_alpha_beta,
+ .extra1 = &rto_beta_min,
+ .extra2 = &rto_beta_max,
},
{
.procname = "max_burst",
@@ -403,6 +417,16 @@ static int proc_sctp_do_rto_max(struct ctl_table *ctl, int write,
return ret;
}
+static int proc_sctp_do_alpha_beta(struct ctl_table *ctl, int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos)
+{
+ pr_warn_once("Changing rto_alpha or rto_beta may lead to "
+ "suboptimal rtt/srtt estimations!\n");
+
+ return proc_dointvec_minmax(ctl, write, buffer, lenp, ppos);
+}
+
static int proc_sctp_do_auth(struct ctl_table *ctl, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos)