* [PATCH 12/18] ipvs: wakeup master thread
From: Simon Horman @ 2012-05-02 6:22 UTC (permalink / raw)
To: Pablo Neira Ayuso
Cc: lvs-devel, netdev, netfilter-devel, Wensong Zhang,
Julian Anastasov, Hans Schillstrom, Jesper Dangaard Brouer,
Simon Horman
In-Reply-To: <1335939762-1912-1-git-send-email-horms@verge.net.au>
From: Julian Anastasov <ja@ssi.bg>
High rate of sync messages in master can lead to
overflowing the socket buffer and dropping the messages.
Fixed sleep of 1 second without wakeup events is not suitable
for loaded masters,
Use delayed_work to schedule sending for queued messages
and limit the delay to IPVS_SYNC_SEND_DELAY (20ms). This will
reduce the rate of wakeups but to avoid sending long bursts we
wakeup the master thread after IPVS_SYNC_WAKEUP_RATE (8) messages.
Add hard limit for the queued messages before sending
by using "sync_qlen_max" sysctl var. It defaults to 1/32 of
the memory pages but actually represents number of messages.
It will protect us from allocating large parts of memory
when the sending rate is lower than the queuing rate.
As suggested by Pablo, add new sysctl var
"sync_sock_size" to configure the SNDBUF (master) or
RCVBUF (slave) socket limit. Default value is 0 (preserve
system defaults).
Change the master thread to detect and block on
SNDBUF overflow, so that we do not drop messages when
the socket limit is low but the sync_qlen_max limit is
not reached. On ENOBUFS or other errors just drop the
messages.
Change master thread to enter TASK_INTERRUPTIBLE
state early, so that we do not miss wakeups due to messages or
kthread_should_stop event.
Thanks to Pablo Neira Ayuso for his valuable feedback!
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
include/net/ip_vs.h | 29 ++++++++
net/netfilter/ipvs/ip_vs_ctl.c | 16 +++++
net/netfilter/ipvs/ip_vs_sync.c | 149 ++++++++++++++++++++++++++++++---------
3 files changed, 162 insertions(+), 32 deletions(-)
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index a903a82..8721a78 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -870,6 +870,8 @@ struct netns_ipvs {
#endif
int sysctl_snat_reroute;
int sysctl_sync_ver;
+ int sysctl_sync_qlen_max;
+ int sysctl_sync_sock_size;
int sysctl_cache_bypass;
int sysctl_expire_nodest_conn;
int sysctl_expire_quiescent_template;
@@ -890,6 +892,9 @@ struct netns_ipvs {
struct timer_list est_timer; /* Estimation timer */
/* ip_vs_sync */
struct list_head sync_queue;
+ int sync_queue_len;
+ unsigned int sync_queue_delay;
+ struct delayed_work master_wakeup_work;
spinlock_t sync_lock;
struct ip_vs_sync_buff *sync_buff;
spinlock_t sync_buff_lock;
@@ -912,6 +917,10 @@ struct netns_ipvs {
#define DEFAULT_SYNC_THRESHOLD 3
#define DEFAULT_SYNC_PERIOD 50
#define DEFAULT_SYNC_VER 1
+#define IPVS_SYNC_WAKEUP_RATE 8
+#define IPVS_SYNC_QLEN_MAX (IPVS_SYNC_WAKEUP_RATE * 4)
+#define IPVS_SYNC_SEND_DELAY (HZ / 50)
+#define IPVS_SYNC_CHECK_PERIOD HZ
#ifdef CONFIG_SYSCTL
@@ -930,6 +939,16 @@ static inline int sysctl_sync_ver(struct netns_ipvs *ipvs)
return ipvs->sysctl_sync_ver;
}
+static inline int sysctl_sync_qlen_max(struct netns_ipvs *ipvs)
+{
+ return ipvs->sysctl_sync_qlen_max;
+}
+
+static inline int sysctl_sync_sock_size(struct netns_ipvs *ipvs)
+{
+ return ipvs->sysctl_sync_sock_size;
+}
+
#else
static inline int sysctl_sync_threshold(struct netns_ipvs *ipvs)
@@ -947,6 +966,16 @@ static inline int sysctl_sync_ver(struct netns_ipvs *ipvs)
return DEFAULT_SYNC_VER;
}
+static inline int sysctl_sync_qlen_max(struct netns_ipvs *ipvs)
+{
+ return IPVS_SYNC_QLEN_MAX;
+}
+
+static inline int sysctl_sync_sock_size(struct netns_ipvs *ipvs)
+{
+ return 0;
+}
+
#endif
/*
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index b8d0df7..854e9a6 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -1718,6 +1718,18 @@ static struct ctl_table vs_vars[] = {
.proc_handler = &proc_do_sync_mode,
},
{
+ .procname = "sync_qlen_max",
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
+ .procname = "sync_sock_size",
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
.procname = "cache_bypass",
.maxlen = sizeof(int),
.mode = 0644,
@@ -3662,6 +3674,10 @@ int __net_init ip_vs_control_net_init_sysctl(struct net *net)
tbl[idx++].data = &ipvs->sysctl_snat_reroute;
ipvs->sysctl_sync_ver = 1;
tbl[idx++].data = &ipvs->sysctl_sync_ver;
+ ipvs->sysctl_sync_qlen_max = nr_free_buffer_pages() / 32;
+ tbl[idx++].data = &ipvs->sysctl_sync_qlen_max;
+ ipvs->sysctl_sync_sock_size = 0;
+ tbl[idx++].data = &ipvs->sysctl_sync_sock_size;
tbl[idx++].data = &ipvs->sysctl_cache_bypass;
tbl[idx++].data = &ipvs->sysctl_expire_nodest_conn;
tbl[idx++].data = &ipvs->sysctl_expire_quiescent_template;
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index eeed767..eafc1d2 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -307,11 +307,15 @@ static inline struct ip_vs_sync_buff *sb_dequeue(struct netns_ipvs *ipvs)
spin_lock_bh(&ipvs->sync_lock);
if (list_empty(&ipvs->sync_queue)) {
sb = NULL;
+ __set_current_state(TASK_INTERRUPTIBLE);
} else {
sb = list_entry(ipvs->sync_queue.next,
struct ip_vs_sync_buff,
list);
list_del(&sb->list);
+ ipvs->sync_queue_len--;
+ if (!ipvs->sync_queue_len)
+ ipvs->sync_queue_delay = 0;
}
spin_unlock_bh(&ipvs->sync_lock);
@@ -358,9 +362,16 @@ static inline void sb_queue_tail(struct netns_ipvs *ipvs)
struct ip_vs_sync_buff *sb = ipvs->sync_buff;
spin_lock(&ipvs->sync_lock);
- if (ipvs->sync_state & IP_VS_STATE_MASTER)
+ if (ipvs->sync_state & IP_VS_STATE_MASTER &&
+ ipvs->sync_queue_len < sysctl_sync_qlen_max(ipvs)) {
+ if (!ipvs->sync_queue_len)
+ schedule_delayed_work(&ipvs->master_wakeup_work,
+ max(IPVS_SYNC_SEND_DELAY, 1));
+ ipvs->sync_queue_len++;
list_add_tail(&sb->list, &ipvs->sync_queue);
- else
+ if ((++ipvs->sync_queue_delay) == IPVS_SYNC_WAKEUP_RATE)
+ wake_up_process(ipvs->master_thread);
+ } else
ip_vs_sync_buff_release(sb);
spin_unlock(&ipvs->sync_lock);
}
@@ -379,6 +390,7 @@ get_curr_sync_buff(struct netns_ipvs *ipvs, unsigned long time)
time_after_eq(jiffies - ipvs->sync_buff->firstuse, time)) {
sb = ipvs->sync_buff;
ipvs->sync_buff = NULL;
+ __set_current_state(TASK_RUNNING);
} else
sb = NULL;
spin_unlock_bh(&ipvs->sync_buff_lock);
@@ -392,26 +404,23 @@ get_curr_sync_buff(struct netns_ipvs *ipvs, unsigned long time)
void ip_vs_sync_switch_mode(struct net *net, int mode)
{
struct netns_ipvs *ipvs = net_ipvs(net);
+ struct ip_vs_sync_buff *sb;
+ spin_lock_bh(&ipvs->sync_buff_lock);
if (!(ipvs->sync_state & IP_VS_STATE_MASTER))
- return;
- if (mode == sysctl_sync_ver(ipvs) || !ipvs->sync_buff)
- return;
+ goto unlock;
+ sb = ipvs->sync_buff;
+ if (mode == sysctl_sync_ver(ipvs) || !sb)
+ goto unlock;
- spin_lock_bh(&ipvs->sync_buff_lock);
/* Buffer empty ? then let buf_create do the job */
- if (ipvs->sync_buff->mesg->size <= sizeof(struct ip_vs_sync_mesg)) {
- kfree(ipvs->sync_buff);
+ if (sb->mesg->size <= sizeof(struct ip_vs_sync_mesg)) {
+ ip_vs_sync_buff_release(sb);
ipvs->sync_buff = NULL;
- } else {
- spin_lock_bh(&ipvs->sync_lock);
- if (ipvs->sync_state & IP_VS_STATE_MASTER)
- list_add_tail(&ipvs->sync_buff->list,
- &ipvs->sync_queue);
- else
- ip_vs_sync_buff_release(ipvs->sync_buff);
- spin_unlock_bh(&ipvs->sync_lock);
- }
+ } else
+ sb_queue_tail(ipvs);
+
+unlock:
spin_unlock_bh(&ipvs->sync_buff_lock);
}
@@ -1130,6 +1139,28 @@ static void ip_vs_process_message(struct net *net, __u8 *buffer,
/*
+ * Setup sndbuf (mode=1) or rcvbuf (mode=0)
+ */
+static void set_sock_size(struct sock *sk, int mode, int val)
+{
+ /* setsockopt(sock, SOL_SOCKET, SO_SNDBUF, &val, sizeof(val)); */
+ /* setsockopt(sock, SOL_SOCKET, SO_RCVBUF, &val, sizeof(val)); */
+ lock_sock(sk);
+ if (mode) {
+ val = clamp_t(int, val, (SOCK_MIN_SNDBUF + 1) / 2,
+ sysctl_wmem_max);
+ sk->sk_sndbuf = val * 2;
+ sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
+ } else {
+ val = clamp_t(int, val, (SOCK_MIN_RCVBUF + 1) / 2,
+ sysctl_rmem_max);
+ sk->sk_rcvbuf = val * 2;
+ sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
+ }
+ release_sock(sk);
+}
+
+/*
* Setup loopback of outgoing multicasts on a sending socket
*/
static void set_mcast_loop(struct sock *sk, u_char loop)
@@ -1305,6 +1336,9 @@ static struct socket *make_send_sock(struct net *net)
set_mcast_loop(sock->sk, 0);
set_mcast_ttl(sock->sk, 1);
+ result = sysctl_sync_sock_size(ipvs);
+ if (result > 0)
+ set_sock_size(sock->sk, 1, result);
result = bind_mcastif_addr(sock, ipvs->master_mcast_ifn);
if (result < 0) {
@@ -1350,6 +1384,9 @@ static struct socket *make_receive_sock(struct net *net)
sk_change_net(sock->sk, net);
/* it is equivalent to the REUSEADDR option in user-space */
sock->sk->sk_reuse = 1;
+ result = sysctl_sync_sock_size(ipvs);
+ if (result > 0)
+ set_sock_size(sock->sk, 0, result);
result = sock->ops->bind(sock, (struct sockaddr *) &mcast_addr,
sizeof(struct sockaddr));
@@ -1392,18 +1429,22 @@ ip_vs_send_async(struct socket *sock, const char *buffer, const size_t length)
return len;
}
-static void
+static int
ip_vs_send_sync_msg(struct socket *sock, struct ip_vs_sync_mesg *msg)
{
int msize;
+ int ret;
msize = msg->size;
/* Put size in network byte order */
msg->size = htons(msg->size);
- if (ip_vs_send_async(sock, (char *)msg, msize) != msize)
- pr_err("ip_vs_send_async error\n");
+ ret = ip_vs_send_async(sock, (char *)msg, msize);
+ if (ret >= 0 || ret == -EAGAIN)
+ return ret;
+ pr_err("ip_vs_send_async error %d\n", ret);
+ return 0;
}
static int
@@ -1428,36 +1469,75 @@ ip_vs_receive(struct socket *sock, char *buffer, const size_t buflen)
return len;
}
+/* Wakeup the master thread for sending */
+static void master_wakeup_work_handler(struct work_struct *work)
+{
+ struct netns_ipvs *ipvs = container_of(work, struct netns_ipvs,
+ master_wakeup_work.work);
+
+ spin_lock_bh(&ipvs->sync_lock);
+ if (ipvs->sync_queue_len &&
+ ipvs->sync_queue_delay < IPVS_SYNC_WAKEUP_RATE) {
+ ipvs->sync_queue_delay = IPVS_SYNC_WAKEUP_RATE;
+ wake_up_process(ipvs->master_thread);
+ }
+ spin_unlock_bh(&ipvs->sync_lock);
+}
+
+/* Get next buffer to send */
+static inline struct ip_vs_sync_buff *
+next_sync_buff(struct netns_ipvs *ipvs)
+{
+ struct ip_vs_sync_buff *sb;
+
+ sb = sb_dequeue(ipvs);
+ if (sb)
+ return sb;
+ /* Do not delay entries in buffer for more than 2 seconds */
+ return get_curr_sync_buff(ipvs, 2 * HZ);
+}
static int sync_thread_master(void *data)
{
struct ip_vs_sync_thread_data *tinfo = data;
struct netns_ipvs *ipvs = net_ipvs(tinfo->net);
+ struct sock *sk = tinfo->sock->sk;
struct ip_vs_sync_buff *sb;
pr_info("sync thread started: state = MASTER, mcast_ifn = %s, "
"syncid = %d\n",
ipvs->master_mcast_ifn, ipvs->master_syncid);
- while (!kthread_should_stop()) {
- while ((sb = sb_dequeue(ipvs))) {
- ip_vs_send_sync_msg(tinfo->sock, sb->mesg);
- ip_vs_sync_buff_release(sb);
+ for (;;) {
+ sb = next_sync_buff(ipvs);
+ if (unlikely(kthread_should_stop()))
+ break;
+ if (!sb) {
+ schedule_timeout(IPVS_SYNC_CHECK_PERIOD);
+ continue;
}
-
- /* check if entries stay in ipvs->sync_buff for 2 seconds */
- sb = get_curr_sync_buff(ipvs, 2 * HZ);
- if (sb) {
- ip_vs_send_sync_msg(tinfo->sock, sb->mesg);
- ip_vs_sync_buff_release(sb);
+ while (ip_vs_send_sync_msg(tinfo->sock, sb->mesg) < 0) {
+ int ret = 0;
+
+ __wait_event_interruptible(*sk_sleep(sk),
+ sock_writeable(sk) ||
+ kthread_should_stop(),
+ ret);
+ if (unlikely(kthread_should_stop()))
+ goto done;
}
-
- schedule_timeout_interruptible(HZ);
+ ip_vs_sync_buff_release(sb);
}
+done:
+ __set_current_state(TASK_RUNNING);
+ if (sb)
+ ip_vs_sync_buff_release(sb);
+
/* clean up the sync_buff queue */
while ((sb = sb_dequeue(ipvs)))
ip_vs_sync_buff_release(sb);
+ __set_current_state(TASK_RUNNING);
/* clean up the current sync_buff */
sb = get_curr_sync_buff(ipvs, 0);
@@ -1538,6 +1618,10 @@ int start_sync_thread(struct net *net, int state, char *mcast_ifn, __u8 syncid)
realtask = &ipvs->master_thread;
name = "ipvs_master:%d";
threadfn = sync_thread_master;
+ ipvs->sync_queue_len = 0;
+ ipvs->sync_queue_delay = 0;
+ INIT_DELAYED_WORK(&ipvs->master_wakeup_work,
+ master_wakeup_work_handler);
sock = make_send_sock(net);
} else if (state == IP_VS_STATE_BACKUP) {
if (ipvs->backup_thread)
@@ -1623,6 +1707,7 @@ int stop_sync_thread(struct net *net, int state)
spin_lock_bh(&ipvs->sync_lock);
ipvs->sync_state &= ~IP_VS_STATE_MASTER;
spin_unlock_bh(&ipvs->sync_lock);
+ cancel_delayed_work_sync(&ipvs->master_wakeup_work);
retc = kthread_stop(ipvs->master_thread);
ipvs->master_thread = NULL;
} else if (state == IP_VS_STATE_BACKUP) {
--
1.7.10
^ permalink raw reply related
* [PATCH 14/18] ipvs: add support for sync threads
From: Simon Horman @ 2012-05-02 6:22 UTC (permalink / raw)
To: Pablo Neira Ayuso
Cc: lvs-devel, netdev, netfilter-devel, Wensong Zhang,
Julian Anastasov, Hans Schillstrom, Jesper Dangaard Brouer,
Simon Horman
In-Reply-To: <1335939762-1912-1-git-send-email-horms@verge.net.au>
From: Julian Anastasov <ja@ssi.bg>
Allow master and backup servers to use many threads
for sync traffic. Add sysctl var "sync_ports" to define the
number of threads. Every thread will use single UDP port,
thread 0 will use the default port 8848 while last thread
will use port 8848+sync_ports-1.
The sync traffic for connections is scheduled to many
master threads based on the cp address but one connection is
always assigned to same thread to avoid reordering of the
sync messages.
Remove ip_vs_sync_switch_mode because this check
for sync mode change is still risky. Instead, check for mode
change under sync_buff_lock.
Make sure the backup socks do not block on reading.
Special thanks to Aleksey Chudov for helping in all tests.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Tested-by: Aleksey Chudov <aleksey.chudov@gmail.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
include/net/ip_vs.h | 34 +++-
net/netfilter/ipvs/ip_vs_conn.c | 7 +
net/netfilter/ipvs/ip_vs_ctl.c | 29 ++-
net/netfilter/ipvs/ip_vs_sync.c | 401 ++++++++++++++++++++++++---------------
4 files changed, 305 insertions(+), 166 deletions(-)
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 941df45..75824e2 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -785,6 +785,16 @@ struct ip_vs_app {
void (*timeout_change)(struct ip_vs_app *app, int flags);
};
+struct ipvs_master_sync_state {
+ struct list_head sync_queue;
+ struct ip_vs_sync_buff *sync_buff;
+ int sync_queue_len;
+ unsigned int sync_queue_delay;
+ struct task_struct *master_thread;
+ struct delayed_work master_wakeup_work;
+ struct netns_ipvs *ipvs;
+};
+
/* IPVS in network namespace */
struct netns_ipvs {
int gen; /* Generation */
@@ -871,6 +881,7 @@ struct netns_ipvs {
#endif
int sysctl_snat_reroute;
int sysctl_sync_ver;
+ int sysctl_sync_ports;
int sysctl_sync_qlen_max;
int sysctl_sync_sock_size;
int sysctl_cache_bypass;
@@ -894,16 +905,11 @@ struct netns_ipvs {
spinlock_t est_lock;
struct timer_list est_timer; /* Estimation timer */
/* ip_vs_sync */
- struct list_head sync_queue;
- int sync_queue_len;
- unsigned int sync_queue_delay;
- struct delayed_work master_wakeup_work;
spinlock_t sync_lock;
- struct ip_vs_sync_buff *sync_buff;
+ struct ipvs_master_sync_state *ms;
spinlock_t sync_buff_lock;
- struct sockaddr_in sync_mcast_addr;
- struct task_struct *master_thread;
- struct task_struct *backup_thread;
+ struct task_struct **backup_threads;
+ int threads_mask;
int send_mesg_maxlen;
int recv_mesg_maxlen;
volatile int sync_state;
@@ -927,6 +933,7 @@ struct netns_ipvs {
#define IPVS_SYNC_SEND_DELAY (HZ / 50)
#define IPVS_SYNC_CHECK_PERIOD HZ
#define IPVS_SYNC_FLUSH_TIME (HZ * 2)
+#define IPVS_SYNC_PORTS_MAX (1 << 6)
#ifdef CONFIG_SYSCTL
@@ -955,6 +962,11 @@ static inline int sysctl_sync_ver(struct netns_ipvs *ipvs)
return ipvs->sysctl_sync_ver;
}
+static inline int sysctl_sync_ports(struct netns_ipvs *ipvs)
+{
+ return ACCESS_ONCE(ipvs->sysctl_sync_ports);
+}
+
static inline int sysctl_sync_qlen_max(struct netns_ipvs *ipvs)
{
return ipvs->sysctl_sync_qlen_max;
@@ -992,6 +1004,11 @@ static inline int sysctl_sync_ver(struct netns_ipvs *ipvs)
return DEFAULT_SYNC_VER;
}
+static inline int sysctl_sync_ports(struct netns_ipvs *ipvs)
+{
+ return 1;
+}
+
static inline int sysctl_sync_qlen_max(struct netns_ipvs *ipvs)
{
return IPVS_SYNC_QLEN_MAX;
@@ -1242,7 +1259,6 @@ extern struct ip_vs_stats ip_vs_stats;
extern const struct ctl_path net_vs_ctl_path[];
extern int sysctl_ip_vs_sync_ver;
-extern void ip_vs_sync_switch_mode(struct net *net, int mode);
extern struct ip_vs_service *
ip_vs_service_get(struct net *net, int af, __u32 fwmark, __u16 protocol,
const union nf_inet_addr *vaddr, __be16 vport);
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 46260fb..6a43c93 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -618,12 +618,19 @@ struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp)
if (dest) {
struct ip_vs_proto_data *pd;
+ spin_lock(&cp->lock);
+ if (cp->dest) {
+ spin_unlock(&cp->lock);
+ return dest;
+ }
+
/* Applications work depending on the forwarding method
* but better to reassign them always when binding dest */
if (cp->app)
ip_vs_unbind_app(cp);
ip_vs_bind_dest(cp, dest);
+ spin_unlock(&cp->lock);
/* Update its packet transmitter */
cp->packet_xmit = NULL;
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 83bdbbc..0e599a4 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -1657,9 +1657,24 @@ proc_do_sync_mode(ctl_table *table, int write,
if ((*valp < 0) || (*valp > 1)) {
/* Restore the correct value */
*valp = val;
- } else {
- struct net *net = current->nsproxy->net_ns;
- ip_vs_sync_switch_mode(net, val);
+ }
+ }
+ return rc;
+}
+
+static int
+proc_do_sync_ports(ctl_table *table, int write,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ int *valp = table->data;
+ int val = *valp;
+ int rc;
+
+ rc = proc_dointvec(table, write, buffer, lenp, ppos);
+ if (write && (*valp != val)) {
+ if (*valp < 1 || !is_power_of_2(*valp)) {
+ /* Restore the correct value */
+ *valp = val;
}
}
return rc;
@@ -1723,6 +1738,12 @@ static struct ctl_table vs_vars[] = {
.proc_handler = &proc_do_sync_mode,
},
{
+ .procname = "sync_ports",
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = &proc_do_sync_ports,
+ },
+ {
.procname = "sync_qlen_max",
.maxlen = sizeof(int),
.mode = 0644,
@@ -3693,6 +3714,8 @@ int __net_init ip_vs_control_net_init_sysctl(struct net *net)
tbl[idx++].data = &ipvs->sysctl_snat_reroute;
ipvs->sysctl_sync_ver = 1;
tbl[idx++].data = &ipvs->sysctl_sync_ver;
+ ipvs->sysctl_sync_ports = 1;
+ tbl[idx++].data = &ipvs->sysctl_sync_ports;
ipvs->sysctl_sync_qlen_max = nr_free_buffer_pages() / 32;
tbl[idx++].data = &ipvs->sysctl_sync_qlen_max;
ipvs->sysctl_sync_sock_size = 0;
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index 4aa9290..8550f37 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -196,6 +196,7 @@ struct ip_vs_sync_thread_data {
struct net *net;
struct socket *sock;
char *buf;
+ int id;
};
/* Version 0 definition of packet sizes */
@@ -271,13 +272,6 @@ struct ip_vs_sync_buff {
unsigned char *end;
};
-/* multicast addr */
-static struct sockaddr_in mcast_addr = {
- .sin_family = AF_INET,
- .sin_port = cpu_to_be16(IP_VS_SYNC_PORT),
- .sin_addr.s_addr = cpu_to_be32(IP_VS_SYNC_GROUP),
-};
-
/*
* Copy of struct ip_vs_seq
* From unaligned network order to aligned host order
@@ -300,22 +294,22 @@ static void hton_seq(struct ip_vs_seq *ho, struct ip_vs_seq *no)
put_unaligned_be32(ho->previous_delta, &no->previous_delta);
}
-static inline struct ip_vs_sync_buff *sb_dequeue(struct netns_ipvs *ipvs)
+static inline struct ip_vs_sync_buff *
+sb_dequeue(struct netns_ipvs *ipvs, struct ipvs_master_sync_state *ms)
{
struct ip_vs_sync_buff *sb;
spin_lock_bh(&ipvs->sync_lock);
- if (list_empty(&ipvs->sync_queue)) {
+ if (list_empty(&ms->sync_queue)) {
sb = NULL;
__set_current_state(TASK_INTERRUPTIBLE);
} else {
- sb = list_entry(ipvs->sync_queue.next,
- struct ip_vs_sync_buff,
+ sb = list_entry(ms->sync_queue.next, struct ip_vs_sync_buff,
list);
list_del(&sb->list);
- ipvs->sync_queue_len--;
- if (!ipvs->sync_queue_len)
- ipvs->sync_queue_delay = 0;
+ ms->sync_queue_len--;
+ if (!ms->sync_queue_len)
+ ms->sync_queue_delay = 0;
}
spin_unlock_bh(&ipvs->sync_lock);
@@ -338,7 +332,7 @@ ip_vs_sync_buff_create(struct netns_ipvs *ipvs)
kfree(sb);
return NULL;
}
- sb->mesg->reserved = 0; /* old nr_conns i.e. must be zeo now */
+ sb->mesg->reserved = 0; /* old nr_conns i.e. must be zero now */
sb->mesg->version = SYNC_PROTO_VER;
sb->mesg->syncid = ipvs->master_syncid;
sb->mesg->size = sizeof(struct ip_vs_sync_mesg);
@@ -357,20 +351,21 @@ static inline void ip_vs_sync_buff_release(struct ip_vs_sync_buff *sb)
kfree(sb);
}
-static inline void sb_queue_tail(struct netns_ipvs *ipvs)
+static inline void sb_queue_tail(struct netns_ipvs *ipvs,
+ struct ipvs_master_sync_state *ms)
{
- struct ip_vs_sync_buff *sb = ipvs->sync_buff;
+ struct ip_vs_sync_buff *sb = ms->sync_buff;
spin_lock(&ipvs->sync_lock);
if (ipvs->sync_state & IP_VS_STATE_MASTER &&
- ipvs->sync_queue_len < sysctl_sync_qlen_max(ipvs)) {
- if (!ipvs->sync_queue_len)
- schedule_delayed_work(&ipvs->master_wakeup_work,
+ ms->sync_queue_len < sysctl_sync_qlen_max(ipvs)) {
+ if (!ms->sync_queue_len)
+ schedule_delayed_work(&ms->master_wakeup_work,
max(IPVS_SYNC_SEND_DELAY, 1));
- ipvs->sync_queue_len++;
- list_add_tail(&sb->list, &ipvs->sync_queue);
- if ((++ipvs->sync_queue_delay) == IPVS_SYNC_WAKEUP_RATE)
- wake_up_process(ipvs->master_thread);
+ ms->sync_queue_len++;
+ list_add_tail(&sb->list, &ms->sync_queue);
+ if ((++ms->sync_queue_delay) == IPVS_SYNC_WAKEUP_RATE)
+ wake_up_process(ms->master_thread);
} else
ip_vs_sync_buff_release(sb);
spin_unlock(&ipvs->sync_lock);
@@ -381,15 +376,15 @@ static inline void sb_queue_tail(struct netns_ipvs *ipvs)
* than the specified time or the specified time is zero.
*/
static inline struct ip_vs_sync_buff *
-get_curr_sync_buff(struct netns_ipvs *ipvs, unsigned long time)
+get_curr_sync_buff(struct netns_ipvs *ipvs, struct ipvs_master_sync_state *ms,
+ unsigned long time)
{
struct ip_vs_sync_buff *sb;
spin_lock_bh(&ipvs->sync_buff_lock);
- if (ipvs->sync_buff &&
- time_after_eq(jiffies - ipvs->sync_buff->firstuse, time)) {
- sb = ipvs->sync_buff;
- ipvs->sync_buff = NULL;
+ sb = ms->sync_buff;
+ if (sb && time_after_eq(jiffies - sb->firstuse, time)) {
+ ms->sync_buff = NULL;
__set_current_state(TASK_RUNNING);
} else
sb = NULL;
@@ -397,31 +392,10 @@ get_curr_sync_buff(struct netns_ipvs *ipvs, unsigned long time)
return sb;
}
-/*
- * Switch mode from sending version 0 or 1
- * - must handle sync_buf
- */
-void ip_vs_sync_switch_mode(struct net *net, int mode)
+static inline int
+select_master_thread_id(struct netns_ipvs *ipvs, struct ip_vs_conn *cp)
{
- struct netns_ipvs *ipvs = net_ipvs(net);
- struct ip_vs_sync_buff *sb;
-
- spin_lock_bh(&ipvs->sync_buff_lock);
- if (!(ipvs->sync_state & IP_VS_STATE_MASTER))
- goto unlock;
- sb = ipvs->sync_buff;
- if (mode == sysctl_sync_ver(ipvs) || !sb)
- goto unlock;
-
- /* Buffer empty ? then let buf_create do the job */
- if (sb->mesg->size <= sizeof(struct ip_vs_sync_mesg)) {
- ip_vs_sync_buff_release(sb);
- ipvs->sync_buff = NULL;
- } else
- sb_queue_tail(ipvs);
-
-unlock:
- spin_unlock_bh(&ipvs->sync_buff_lock);
+ return ((long) cp >> (1 + ilog2(sizeof(*cp)))) & ipvs->threads_mask;
}
/*
@@ -543,6 +517,9 @@ static void ip_vs_sync_conn_v0(struct net *net, struct ip_vs_conn *cp,
struct netns_ipvs *ipvs = net_ipvs(net);
struct ip_vs_sync_mesg_v0 *m;
struct ip_vs_sync_conn_v0 *s;
+ struct ip_vs_sync_buff *buff;
+ struct ipvs_master_sync_state *ms;
+ int id;
int len;
if (unlikely(cp->af != AF_INET))
@@ -555,20 +532,37 @@ static void ip_vs_sync_conn_v0(struct net *net, struct ip_vs_conn *cp,
return;
spin_lock(&ipvs->sync_buff_lock);
- if (!ipvs->sync_buff) {
- ipvs->sync_buff =
- ip_vs_sync_buff_create_v0(ipvs);
- if (!ipvs->sync_buff) {
+ if (!(ipvs->sync_state & IP_VS_STATE_MASTER)) {
+ spin_unlock(&ipvs->sync_buff_lock);
+ return;
+ }
+
+ id = select_master_thread_id(ipvs, cp);
+ ms = &ipvs->ms[id];
+ buff = ms->sync_buff;
+ if (buff) {
+ m = (struct ip_vs_sync_mesg_v0 *) buff->mesg;
+ /* Send buffer if it is for v1 */
+ if (!m->nr_conns) {
+ sb_queue_tail(ipvs, ms);
+ ms->sync_buff = NULL;
+ buff = NULL;
+ }
+ }
+ if (!buff) {
+ buff = ip_vs_sync_buff_create_v0(ipvs);
+ if (!buff) {
spin_unlock(&ipvs->sync_buff_lock);
pr_err("ip_vs_sync_buff_create failed.\n");
return;
}
+ ms->sync_buff = buff;
}
len = (cp->flags & IP_VS_CONN_F_SEQ_MASK) ? FULL_CONN_SIZE :
SIMPLE_CONN_SIZE;
- m = (struct ip_vs_sync_mesg_v0 *)ipvs->sync_buff->mesg;
- s = (struct ip_vs_sync_conn_v0 *)ipvs->sync_buff->head;
+ m = (struct ip_vs_sync_mesg_v0 *) buff->mesg;
+ s = (struct ip_vs_sync_conn_v0 *) buff->head;
/* copy members */
s->reserved = 0;
@@ -589,12 +583,12 @@ static void ip_vs_sync_conn_v0(struct net *net, struct ip_vs_conn *cp,
m->nr_conns++;
m->size += len;
- ipvs->sync_buff->head += len;
+ buff->head += len;
/* check if there is a space for next one */
- if (ipvs->sync_buff->head + FULL_CONN_SIZE > ipvs->sync_buff->end) {
- sb_queue_tail(ipvs);
- ipvs->sync_buff = NULL;
+ if (buff->head + FULL_CONN_SIZE > buff->end) {
+ sb_queue_tail(ipvs, ms);
+ ms->sync_buff = NULL;
}
spin_unlock(&ipvs->sync_buff_lock);
@@ -619,6 +613,9 @@ void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp, int pkts)
struct netns_ipvs *ipvs = net_ipvs(net);
struct ip_vs_sync_mesg *m;
union ip_vs_sync_conn *s;
+ struct ip_vs_sync_buff *buff;
+ struct ipvs_master_sync_state *ms;
+ int id;
__u8 *p;
unsigned int len, pe_name_len, pad;
@@ -645,6 +642,13 @@ sloop:
}
spin_lock(&ipvs->sync_buff_lock);
+ if (!(ipvs->sync_state & IP_VS_STATE_MASTER)) {
+ spin_unlock(&ipvs->sync_buff_lock);
+ return;
+ }
+
+ id = select_master_thread_id(ipvs, cp);
+ ms = &ipvs->ms[id];
#ifdef CONFIG_IP_VS_IPV6
if (cp->af == AF_INET6)
@@ -663,27 +667,32 @@ sloop:
/* check if there is a space for this one */
pad = 0;
- if (ipvs->sync_buff) {
- pad = (4 - (size_t)ipvs->sync_buff->head) & 3;
- if (ipvs->sync_buff->head + len + pad > ipvs->sync_buff->end) {
- sb_queue_tail(ipvs);
- ipvs->sync_buff = NULL;
+ buff = ms->sync_buff;
+ if (buff) {
+ m = buff->mesg;
+ pad = (4 - (size_t) buff->head) & 3;
+ /* Send buffer if it is for v0 */
+ if (buff->head + len + pad > buff->end || m->reserved) {
+ sb_queue_tail(ipvs, ms);
+ ms->sync_buff = NULL;
+ buff = NULL;
pad = 0;
}
}
- if (!ipvs->sync_buff) {
- ipvs->sync_buff = ip_vs_sync_buff_create(ipvs);
- if (!ipvs->sync_buff) {
+ if (!buff) {
+ buff = ip_vs_sync_buff_create(ipvs);
+ if (!buff) {
spin_unlock(&ipvs->sync_buff_lock);
pr_err("ip_vs_sync_buff_create failed.\n");
return;
}
+ ms->sync_buff = buff;
+ m = buff->mesg;
}
- m = ipvs->sync_buff->mesg;
- p = ipvs->sync_buff->head;
- ipvs->sync_buff->head += pad + len;
+ p = buff->head;
+ buff->head += pad + len;
m->size += pad + len;
/* Add ev. padding from prev. sync_conn */
while (pad--)
@@ -834,6 +843,7 @@ static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param,
kfree(param->pe_data);
dest = cp->dest;
+ spin_lock(&cp->lock);
if ((cp->flags ^ flags) & IP_VS_CONN_F_INACTIVE &&
!(flags & IP_VS_CONN_F_TEMPLATE) && dest) {
if (flags & IP_VS_CONN_F_INACTIVE) {
@@ -847,6 +857,7 @@ static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param,
flags &= IP_VS_CONN_F_BACKUP_UPD_MASK;
flags |= cp->flags & ~IP_VS_CONN_F_BACKUP_UPD_MASK;
cp->flags = flags;
+ spin_unlock(&cp->lock);
if (!dest) {
dest = ip_vs_try_bind_dest(cp);
if (dest)
@@ -1399,9 +1410,15 @@ static int bind_mcastif_addr(struct socket *sock, char *ifname)
/*
* Set up sending multicast socket over UDP
*/
-static struct socket *make_send_sock(struct net *net)
+static struct socket *make_send_sock(struct net *net, int id)
{
struct netns_ipvs *ipvs = net_ipvs(net);
+ /* multicast addr */
+ struct sockaddr_in mcast_addr = {
+ .sin_family = AF_INET,
+ .sin_port = cpu_to_be16(IP_VS_SYNC_PORT + id),
+ .sin_addr.s_addr = cpu_to_be32(IP_VS_SYNC_GROUP),
+ };
struct socket *sock;
int result;
@@ -1453,9 +1470,15 @@ error:
/*
* Set up receiving multicast socket over UDP
*/
-static struct socket *make_receive_sock(struct net *net)
+static struct socket *make_receive_sock(struct net *net, int id)
{
struct netns_ipvs *ipvs = net_ipvs(net);
+ /* multicast addr */
+ struct sockaddr_in mcast_addr = {
+ .sin_family = AF_INET,
+ .sin_port = cpu_to_be16(IP_VS_SYNC_PORT + id),
+ .sin_addr.s_addr = cpu_to_be32(IP_VS_SYNC_GROUP),
+ };
struct socket *sock;
int result;
@@ -1549,10 +1572,10 @@ ip_vs_receive(struct socket *sock, char *buffer, const size_t buflen)
iov.iov_base = buffer;
iov.iov_len = (size_t)buflen;
- len = kernel_recvmsg(sock, &msg, &iov, 1, buflen, 0);
+ len = kernel_recvmsg(sock, &msg, &iov, 1, buflen, MSG_DONTWAIT);
if (len < 0)
- return -1;
+ return len;
LeaveFunction(7);
return len;
@@ -1561,44 +1584,47 @@ ip_vs_receive(struct socket *sock, char *buffer, const size_t buflen)
/* Wakeup the master thread for sending */
static void master_wakeup_work_handler(struct work_struct *work)
{
- struct netns_ipvs *ipvs = container_of(work, struct netns_ipvs,
- master_wakeup_work.work);
+ struct ipvs_master_sync_state *ms =
+ container_of(work, struct ipvs_master_sync_state,
+ master_wakeup_work.work);
+ struct netns_ipvs *ipvs = ms->ipvs;
spin_lock_bh(&ipvs->sync_lock);
- if (ipvs->sync_queue_len &&
- ipvs->sync_queue_delay < IPVS_SYNC_WAKEUP_RATE) {
- ipvs->sync_queue_delay = IPVS_SYNC_WAKEUP_RATE;
- wake_up_process(ipvs->master_thread);
+ if (ms->sync_queue_len &&
+ ms->sync_queue_delay < IPVS_SYNC_WAKEUP_RATE) {
+ ms->sync_queue_delay = IPVS_SYNC_WAKEUP_RATE;
+ wake_up_process(ms->master_thread);
}
spin_unlock_bh(&ipvs->sync_lock);
}
/* Get next buffer to send */
static inline struct ip_vs_sync_buff *
-next_sync_buff(struct netns_ipvs *ipvs)
+next_sync_buff(struct netns_ipvs *ipvs, struct ipvs_master_sync_state *ms)
{
struct ip_vs_sync_buff *sb;
- sb = sb_dequeue(ipvs);
+ sb = sb_dequeue(ipvs, ms);
if (sb)
return sb;
/* Do not delay entries in buffer for more than 2 seconds */
- return get_curr_sync_buff(ipvs, IPVS_SYNC_FLUSH_TIME);
+ return get_curr_sync_buff(ipvs, ms, IPVS_SYNC_FLUSH_TIME);
}
static int sync_thread_master(void *data)
{
struct ip_vs_sync_thread_data *tinfo = data;
struct netns_ipvs *ipvs = net_ipvs(tinfo->net);
+ struct ipvs_master_sync_state *ms = &ipvs->ms[tinfo->id];
struct sock *sk = tinfo->sock->sk;
struct ip_vs_sync_buff *sb;
pr_info("sync thread started: state = MASTER, mcast_ifn = %s, "
- "syncid = %d\n",
- ipvs->master_mcast_ifn, ipvs->master_syncid);
+ "syncid = %d, id = %d\n",
+ ipvs->master_mcast_ifn, ipvs->master_syncid, tinfo->id);
for (;;) {
- sb = next_sync_buff(ipvs);
+ sb = next_sync_buff(ipvs, ms);
if (unlikely(kthread_should_stop()))
break;
if (!sb) {
@@ -1624,12 +1650,12 @@ done:
ip_vs_sync_buff_release(sb);
/* clean up the sync_buff queue */
- while ((sb = sb_dequeue(ipvs)))
+ while ((sb = sb_dequeue(ipvs, ms)))
ip_vs_sync_buff_release(sb);
__set_current_state(TASK_RUNNING);
/* clean up the current sync_buff */
- sb = get_curr_sync_buff(ipvs, 0);
+ sb = get_curr_sync_buff(ipvs, ms, 0);
if (sb)
ip_vs_sync_buff_release(sb);
@@ -1648,8 +1674,8 @@ static int sync_thread_backup(void *data)
int len;
pr_info("sync thread started: state = BACKUP, mcast_ifn = %s, "
- "syncid = %d\n",
- ipvs->backup_mcast_ifn, ipvs->backup_syncid);
+ "syncid = %d, id = %d\n",
+ ipvs->backup_mcast_ifn, ipvs->backup_syncid, tinfo->id);
while (!kthread_should_stop()) {
wait_event_interruptible(*sk_sleep(tinfo->sock->sk),
@@ -1661,7 +1687,8 @@ static int sync_thread_backup(void *data)
len = ip_vs_receive(tinfo->sock, tinfo->buf,
ipvs->recv_mesg_maxlen);
if (len <= 0) {
- pr_err("receiving message error\n");
+ if (len != -EAGAIN)
+ pr_err("receiving message error\n");
break;
}
@@ -1685,90 +1712,140 @@ static int sync_thread_backup(void *data)
int start_sync_thread(struct net *net, int state, char *mcast_ifn, __u8 syncid)
{
struct ip_vs_sync_thread_data *tinfo;
- struct task_struct **realtask, *task;
+ struct task_struct **array = NULL, *task;
struct socket *sock;
struct netns_ipvs *ipvs = net_ipvs(net);
- char *name, *buf = NULL;
+ char *name;
int (*threadfn)(void *data);
+ int id, count;
int result = -ENOMEM;
IP_VS_DBG(7, "%s(): pid %d\n", __func__, task_pid_nr(current));
IP_VS_DBG(7, "Each ip_vs_sync_conn entry needs %Zd bytes\n",
sizeof(struct ip_vs_sync_conn_v0));
+ if (!ipvs->sync_state) {
+ count = clamp(sysctl_sync_ports(ipvs), 1, IPVS_SYNC_PORTS_MAX);
+ ipvs->threads_mask = count - 1;
+ } else
+ count = ipvs->threads_mask + 1;
if (state == IP_VS_STATE_MASTER) {
- if (ipvs->master_thread)
+ if (ipvs->ms)
return -EEXIST;
strlcpy(ipvs->master_mcast_ifn, mcast_ifn,
sizeof(ipvs->master_mcast_ifn));
ipvs->master_syncid = syncid;
- realtask = &ipvs->master_thread;
- name = "ipvs_master:%d";
+ name = "ipvs-m:%d:%d";
threadfn = sync_thread_master;
- ipvs->sync_queue_len = 0;
- ipvs->sync_queue_delay = 0;
- INIT_DELAYED_WORK(&ipvs->master_wakeup_work,
- master_wakeup_work_handler);
- sock = make_send_sock(net);
} else if (state == IP_VS_STATE_BACKUP) {
- if (ipvs->backup_thread)
+ if (ipvs->backup_threads)
return -EEXIST;
strlcpy(ipvs->backup_mcast_ifn, mcast_ifn,
sizeof(ipvs->backup_mcast_ifn));
ipvs->backup_syncid = syncid;
- realtask = &ipvs->backup_thread;
- name = "ipvs_backup:%d";
+ name = "ipvs-b:%d:%d";
threadfn = sync_thread_backup;
- sock = make_receive_sock(net);
} else {
return -EINVAL;
}
- if (IS_ERR(sock)) {
- result = PTR_ERR(sock);
- goto out;
- }
+ if (state == IP_VS_STATE_MASTER) {
+ struct ipvs_master_sync_state *ms;
- set_sync_mesg_maxlen(net, state);
- if (state == IP_VS_STATE_BACKUP) {
- buf = kmalloc(ipvs->recv_mesg_maxlen, GFP_KERNEL);
- if (!buf)
- goto outsocket;
+ ipvs->ms = kzalloc(count * sizeof(ipvs->ms[0]), GFP_KERNEL);
+ if (!ipvs->ms)
+ goto out;
+ ms = ipvs->ms;
+ for (id = 0; id < count; id++, ms++) {
+ INIT_LIST_HEAD(&ms->sync_queue);
+ ms->sync_queue_len = 0;
+ ms->sync_queue_delay = 0;
+ INIT_DELAYED_WORK(&ms->master_wakeup_work,
+ master_wakeup_work_handler);
+ ms->ipvs = ipvs;
+ }
+ } else {
+ array = kzalloc(count * sizeof(struct task_struct *),
+ GFP_KERNEL);
+ if (!array)
+ goto out;
}
+ set_sync_mesg_maxlen(net, state);
- tinfo = kmalloc(sizeof(*tinfo), GFP_KERNEL);
- if (!tinfo)
- goto outbuf;
-
- tinfo->net = net;
- tinfo->sock = sock;
- tinfo->buf = buf;
+ tinfo = NULL;
+ for (id = 0; id < count; id++) {
+ if (state == IP_VS_STATE_MASTER)
+ sock = make_send_sock(net, id);
+ else
+ sock = make_receive_sock(net, id);
+ if (IS_ERR(sock)) {
+ result = PTR_ERR(sock);
+ goto outtinfo;
+ }
+ tinfo = kmalloc(sizeof(*tinfo), GFP_KERNEL);
+ if (!tinfo)
+ goto outsocket;
+ tinfo->net = net;
+ tinfo->sock = sock;
+ if (state == IP_VS_STATE_BACKUP) {
+ tinfo->buf = kmalloc(ipvs->recv_mesg_maxlen,
+ GFP_KERNEL);
+ if (!tinfo->buf)
+ goto outtinfo;
+ }
+ tinfo->id = id;
- task = kthread_run(threadfn, tinfo, name, ipvs->gen);
- if (IS_ERR(task)) {
- result = PTR_ERR(task);
- goto outtinfo;
+ task = kthread_run(threadfn, tinfo, name, ipvs->gen, id);
+ if (IS_ERR(task)) {
+ result = PTR_ERR(task);
+ goto outtinfo;
+ }
+ tinfo = NULL;
+ if (state == IP_VS_STATE_MASTER)
+ ipvs->ms[id].master_thread = task;
+ else
+ array[id] = task;
}
/* mark as active */
- *realtask = task;
+
+ if (state == IP_VS_STATE_BACKUP)
+ ipvs->backup_threads = array;
+ spin_lock_bh(&ipvs->sync_buff_lock);
ipvs->sync_state |= state;
+ spin_unlock_bh(&ipvs->sync_buff_lock);
/* increase the module use count */
ip_vs_use_count_inc();
return 0;
-outtinfo:
- kfree(tinfo);
-outbuf:
- kfree(buf);
outsocket:
sk_release_kernel(sock->sk);
+
+outtinfo:
+ if (tinfo) {
+ sk_release_kernel(tinfo->sock->sk);
+ kfree(tinfo->buf);
+ kfree(tinfo);
+ }
+ count = id;
+ while (count-- > 0) {
+ if (state == IP_VS_STATE_MASTER)
+ kthread_stop(ipvs->ms[count].master_thread);
+ else
+ kthread_stop(array[count]);
+ }
+ kfree(array);
+
out:
+ if (!(ipvs->sync_state & IP_VS_STATE_MASTER)) {
+ kfree(ipvs->ms);
+ ipvs->ms = NULL;
+ }
return result;
}
@@ -1776,39 +1853,60 @@ out:
int stop_sync_thread(struct net *net, int state)
{
struct netns_ipvs *ipvs = net_ipvs(net);
+ struct task_struct **array;
+ int id;
int retc = -EINVAL;
IP_VS_DBG(7, "%s(): pid %d\n", __func__, task_pid_nr(current));
if (state == IP_VS_STATE_MASTER) {
- if (!ipvs->master_thread)
+ if (!ipvs->ms)
return -ESRCH;
- pr_info("stopping master sync thread %d ...\n",
- task_pid_nr(ipvs->master_thread));
-
/*
* The lock synchronizes with sb_queue_tail(), so that we don't
* add sync buffers to the queue, when we are already in
* progress of stopping the master sync daemon.
*/
- spin_lock_bh(&ipvs->sync_lock);
+ spin_lock_bh(&ipvs->sync_buff_lock);
+ spin_lock(&ipvs->sync_lock);
ipvs->sync_state &= ~IP_VS_STATE_MASTER;
- spin_unlock_bh(&ipvs->sync_lock);
- cancel_delayed_work_sync(&ipvs->master_wakeup_work);
- retc = kthread_stop(ipvs->master_thread);
- ipvs->master_thread = NULL;
+ spin_unlock(&ipvs->sync_lock);
+ spin_unlock_bh(&ipvs->sync_buff_lock);
+
+ retc = 0;
+ for (id = ipvs->threads_mask; id >= 0; id--) {
+ struct ipvs_master_sync_state *ms = &ipvs->ms[id];
+ int ret;
+
+ pr_info("stopping master sync thread %d ...\n",
+ task_pid_nr(ms->master_thread));
+ cancel_delayed_work_sync(&ms->master_wakeup_work);
+ ret = kthread_stop(ms->master_thread);
+ if (retc >= 0)
+ retc = ret;
+ }
+ kfree(ipvs->ms);
+ ipvs->ms = NULL;
} else if (state == IP_VS_STATE_BACKUP) {
- if (!ipvs->backup_thread)
+ if (!ipvs->backup_threads)
return -ESRCH;
- pr_info("stopping backup sync thread %d ...\n",
- task_pid_nr(ipvs->backup_thread));
-
ipvs->sync_state &= ~IP_VS_STATE_BACKUP;
- retc = kthread_stop(ipvs->backup_thread);
- ipvs->backup_thread = NULL;
+ array = ipvs->backup_threads;
+ retc = 0;
+ for (id = ipvs->threads_mask; id >= 0; id--) {
+ int ret;
+
+ pr_info("stopping backup sync thread %d ...\n",
+ task_pid_nr(array[id]));
+ ret = kthread_stop(array[id]);
+ if (retc >= 0)
+ retc = ret;
+ }
+ kfree(array);
+ ipvs->backup_threads = NULL;
}
/* decrease the module use count */
@@ -1825,13 +1923,8 @@ int __net_init ip_vs_sync_net_init(struct net *net)
struct netns_ipvs *ipvs = net_ipvs(net);
__mutex_init(&ipvs->sync_mutex, "ipvs->sync_mutex", &__ipvs_sync_key);
- INIT_LIST_HEAD(&ipvs->sync_queue);
spin_lock_init(&ipvs->sync_lock);
spin_lock_init(&ipvs->sync_buff_lock);
-
- ipvs->sync_mcast_addr.sin_family = AF_INET;
- ipvs->sync_mcast_addr.sin_port = cpu_to_be16(IP_VS_SYNC_PORT);
- ipvs->sync_mcast_addr.sin_addr.s_addr = cpu_to_be32(IP_VS_SYNC_GROUP);
return 0;
}
--
1.7.10
^ permalink raw reply related
* [PATCH 15/18] ipvs: optimize the use of flags in ip_vs_bind_dest
From: Simon Horman @ 2012-05-02 6:22 UTC (permalink / raw)
To: Pablo Neira Ayuso
Cc: lvs-devel, netdev, netfilter-devel, Wensong Zhang,
Julian Anastasov, Hans Schillstrom, Jesper Dangaard Brouer,
Simon Horman
In-Reply-To: <1335939762-1912-1-git-send-email-horms@verge.net.au>
From: Julian Anastasov <ja@ssi.bg>
cp->flags is marked volatile but ip_vs_bind_dest
can safely modify the flags, so save some CPU cycles by
using temp variable.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
net/netfilter/ipvs/ip_vs_conn.c | 15 +++++++++------
1 file changed, 9 insertions(+), 6 deletions(-)
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 6a43c93..7f21b91 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -548,6 +548,7 @@ static inline void
ip_vs_bind_dest(struct ip_vs_conn *cp, struct ip_vs_dest *dest)
{
unsigned int conn_flags;
+ __u32 flags;
/* if dest is NULL, then return directly */
if (!dest)
@@ -559,17 +560,19 @@ ip_vs_bind_dest(struct ip_vs_conn *cp, struct ip_vs_dest *dest)
conn_flags = atomic_read(&dest->conn_flags);
if (cp->protocol != IPPROTO_UDP)
conn_flags &= ~IP_VS_CONN_F_ONE_PACKET;
+ flags = cp->flags;
/* Bind with the destination and its corresponding transmitter */
- if (cp->flags & IP_VS_CONN_F_SYNC) {
+ if (flags & IP_VS_CONN_F_SYNC) {
/* if the connection is not template and is created
* by sync, preserve the activity flag.
*/
- if (!(cp->flags & IP_VS_CONN_F_TEMPLATE))
+ if (!(flags & IP_VS_CONN_F_TEMPLATE))
conn_flags &= ~IP_VS_CONN_F_INACTIVE;
/* connections inherit forwarding method from dest */
- cp->flags &= ~(IP_VS_CONN_F_FWD_MASK | IP_VS_CONN_F_NOOUTPUT);
+ flags &= ~(IP_VS_CONN_F_FWD_MASK | IP_VS_CONN_F_NOOUTPUT);
}
- cp->flags |= conn_flags;
+ flags |= conn_flags;
+ cp->flags = flags;
cp->dest = dest;
IP_VS_DBG_BUF(7, "Bind-dest %s c:%s:%d v:%s:%d "
@@ -584,11 +587,11 @@ ip_vs_bind_dest(struct ip_vs_conn *cp, struct ip_vs_dest *dest)
atomic_read(&dest->refcnt));
/* Update the connection counters */
- if (!(cp->flags & IP_VS_CONN_F_TEMPLATE)) {
+ if (!(flags & IP_VS_CONN_F_TEMPLATE)) {
/* It is a normal connection, so modify the counters
* according to the flags, later the protocol can
* update them on state change */
- if (!(cp->flags & IP_VS_CONN_F_INACTIVE))
+ if (!(flags & IP_VS_CONN_F_INACTIVE))
atomic_inc(&dest->activeconns);
else
atomic_inc(&dest->inactconns);
--
1.7.10
^ permalink raw reply related
* [PATCH 16/18] IPVS: ip_vs_ftp.c: local functions should not be exposed globally
From: Simon Horman @ 2012-05-02 6:22 UTC (permalink / raw)
To: Pablo Neira Ayuso
Cc: lvs-devel, netdev, netfilter-devel, Wensong Zhang,
Julian Anastasov, Hans Schillstrom, Jesper Dangaard Brouer,
H Hartley Sweeten, H Hartley Sweeten, David S. Miller,
Simon Horman
In-Reply-To: <1335939762-1912-1-git-send-email-horms@verge.net.au>
From: H Hartley Sweeten <hartleys@visionengravers.com>
Functions not referenced outside of a source file should be marked
static to prevent it from being exposed globally.
This quiets the sparse warnings:
warning: symbol 'ip_vs_ftp_init' was not declared. Should it be static?
Signed-off-by: H Hartley Sweeten <hsweeten@visionengravers.com>
Cc: "David S. Miller" <davem@davemloft.net>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
net/netfilter/ipvs/ip_vs_ftp.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c
index debb8c7..091bec9 100644
--- a/net/netfilter/ipvs/ip_vs_ftp.c
+++ b/net/netfilter/ipvs/ip_vs_ftp.c
@@ -483,7 +483,7 @@ static struct pernet_operations ip_vs_ftp_ops = {
.exit = __ip_vs_ftp_exit,
};
-int __init ip_vs_ftp_init(void)
+static int __init ip_vs_ftp_init(void)
{
int rv;
--
1.7.10
^ permalink raw reply related
* [PATCH 17/18] IPVS: ip_vs_proto.c: local functions should not be exposed globally
From: Simon Horman @ 2012-05-02 6:22 UTC (permalink / raw)
To: Pablo Neira Ayuso
Cc: lvs-devel, netdev, netfilter-devel, Wensong Zhang,
Julian Anastasov, Hans Schillstrom, Jesper Dangaard Brouer,
H Hartley Sweeten, H Hartley Sweeten, David S. Miller,
Simon Horman
In-Reply-To: <1335939762-1912-1-git-send-email-horms@verge.net.au>
From: H Hartley Sweeten <hartleys@visionengravers.com>
Functions not referenced outside of a source file should be marked
static to prevent it from being exposed globally.
This quiets the sparse warnings:
warning: symbol '__ipvs_proto_data_get' was not declared. Should it be static?
Signed-off-by: H Hartley Sweeten <hsweeten@visionengravers.com>
Cc: "David S. Miller" <davem@davemloft.net>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
net/netfilter/ipvs/ip_vs_proto.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/netfilter/ipvs/ip_vs_proto.c b/net/netfilter/ipvs/ip_vs_proto.c
index 8726488..e3f4bb0 100644
--- a/net/netfilter/ipvs/ip_vs_proto.c
+++ b/net/netfilter/ipvs/ip_vs_proto.c
@@ -153,7 +153,7 @@ EXPORT_SYMBOL(ip_vs_proto_get);
/*
* get ip_vs_protocol object data by netns and proto
*/
-struct ip_vs_proto_data *
+static struct ip_vs_proto_data *
__ipvs_proto_data_get(struct netns_ipvs *ipvs, unsigned short proto)
{
struct ip_vs_proto_data *pd;
--
1.7.10
^ permalink raw reply related
* Re: [V2 PATCH 0/9] vhost/macvtap zeropcopy fixes
From: David Miller @ 2012-05-02 6:44 UTC (permalink / raw)
To: mst; +Cc: jasowang, eric.dumazet, netdev, linux-kernel, ebiederm
In-Reply-To: <20120502055008.GA29319@redhat.com>
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Wed, 2 May 2012 08:50:09 +0300
> On Wed, May 02, 2012 at 11:41:21AM +0800, Jason Wang wrote:
>> This is an updated since the last series of vhost/macvtap zerocopy fixes which
>> fixes the the possible transmission stall, host kernel stack overflow and other
>> misc fixes.
>>
>> Changes from V1:
>> - Addressing comments from Eric and Michael.
>> - Adding more fixes into the seires.
>
> Thanks for fixing this.
> Acked-by: Michael S. Tsirkin <mst@redhat.com>
>
> Dave, can you merge this for 3.4 please?
It's rather late in the -RC for such a large patch set.
^ permalink raw reply
* Re: [PATCH] netfilter: Fix error in ipq_enqueue_packet
From: David Miller @ 2012-05-02 6:45 UTC (permalink / raw)
To: krkumar2; +Cc: netdev, kaber
In-Reply-To: <20120502061029.30442.48870.sendpatchset@localhost.localdomain>
Please post netfilter patches to netfilter-devel, I do not apply
them directly.
^ permalink raw reply
* Re: [PATCH] net: skb_set_dev do not unconditionally drop ref to dst
From: Eric Dumazet @ 2012-05-02 6:59 UTC (permalink / raw)
To: Frank Blaschka; +Cc: davem, netdev, arnd, linux-s390
In-Reply-To: <20120502055018.GA50959@tuxmaker.boeblingen.de.ibm.com>
On Wed, 2012-05-02 at 07:50 +0200, Frank Blaschka wrote:
> On Mon, Apr 30, 2012 at 07:51:33AM +0200, Eric Dumazet wrote:
> > On Mon, 2012-04-30 at 07:38 +0200, Frank Blaschka wrote:
> > > From: Frank Blaschka <frank.blaschka@de.ibm.com>
> > >
> > > commit 8a83a00b0735190384a348156837918271034144 unconditionally
> > > drops dst reference when skb->dev is set. This causes a regression
> > > with VLAN and the qeth_l3 network driver. qeth_l3 can not get gw
> > > information from the skb coming from the vlan driver. It is only
> > > valid to drop the dst in case of different name spaces.
> > >
> > > Signed-off-by: Frank Blaschka <frank.blaschka@de.ibm.com>
> > > ---
> > > net/core/dev.c | 2 +-
> > > 1 file changed, 1 insertion(+), 1 deletion(-)
> > >
> > > --- a/net/core/dev.c
> > > +++ b/net/core/dev.c
> > > @@ -1881,8 +1881,8 @@ EXPORT_SYMBOL(netif_device_attach);
> > > #ifdef CONFIG_NET_NS
> > > void skb_set_dev(struct sk_buff *skb, struct net_device *dev)
> > > {
> > > - skb_dst_drop(skb);
> > > if (skb->dev && !net_eq(dev_net(skb->dev), dev_net(dev))) {
> > > + skb_dst_drop(skb);
> > > secpath_reset(skb);
> > > nf_reset(skb);
> > > skb_init_secmark(skb);
> > >
> >
> > You forgot CC Arnd Bergmann <arnd@arndb.de> ?
> >
> > But we do want to do the skb_dst_drop() in dev_forward_skb()
> >
> > Your patch breaks dev_forward_skb() then.
> If NET_NS is not defined is this broken too?
> >
> > But apparently this forward path was alredy broken in Arnd patch...
> >
> Ok, until nobody comes up with an other idea I will post a patch to
> change back the vlan driver (use skb->dev = dev instead of skb_set_dev)
> next week.
> >
If Arnd doesnt care to even reply, we can just revert his buggy patch,
instead of trying to understand and fix all issues.
^ permalink raw reply
* Re: [RFC] [PATCH] ipv6: Fix potential hang in mif6_add
From: Eric Dumazet @ 2012-05-02 7:02 UTC (permalink / raw)
To: Krishna Kumar; +Cc: davem, netdev
In-Reply-To: <20120502060957.30368.34595.sendpatchset@localhost.localdomain>
On Wed, 2012-05-02 at 11:39 +0530, Krishna Kumar wrote:
> Fix a potential "waiting for %s to become free" hang.
> mif6_add() called ip6mr_reg_vif to allocate/register a
> netdevice, which also took an extra reference on the
> device. On error, mif6_add should drop this reference
> before unregistering the device.
>
> (untested, noticed from code walkthrough)
>
> Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com>
> ---
> net/ipv6/ip6mr.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff -ruNp org/net/ipv6/ip6mr.c new/net/ipv6/ip6mr.c
> --- org/net/ipv6/ip6mr.c 2012-04-19 09:03:34.000000000 +0530
> +++ new/net/ipv6/ip6mr.c 2012-05-02 10:51:01.953110994 +0530
> @@ -937,8 +937,8 @@ static int mif6_add(struct net *net, str
> return -ENOBUFS;
> err = dev_set_allmulti(dev, 1);
> if (err) {
> - unregister_netdevice(dev);
> dev_put(dev);
> + unregister_netdevice(dev);
> return err;
> }
> break;
>
This makes no difference to dev_put() before or after
unregister_netdevice() because we hold RTNL in mif6_add()
^ permalink raw reply
* [PATCH net-next] netfilter: remove two dropwatch false positives
From: Eric Dumazet @ 2012-05-02 7:13 UTC (permalink / raw)
To: Pablo Neira Ayuso; +Cc: netdev, netfilter-devel, David Miller
From: Eric Dumazet <edumazet@google.com>
After skb_copy_expand() call, we want to switch skbs without dropping
original one. Call consume_skb() to avoid drop_monitor sending a drop
event.
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
net/ipv4/netfilter/ip_queue.c | 2 +-
net/ipv6/netfilter/ip6_queue.c | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/net/ipv4/netfilter/ip_queue.c b/net/ipv4/netfilter/ip_queue.c
index 09775a1..dd88537 100644
--- a/net/ipv4/netfilter/ip_queue.c
+++ b/net/ipv4/netfilter/ip_queue.c
@@ -296,7 +296,7 @@ ipq_mangle_ipv4(ipq_verdict_msg_t *v, struct nf_queue_entry *e)
"in mangle, dropping packet\n");
return -ENOMEM;
}
- kfree_skb(e->skb);
+ consume_skb(e->skb);
e->skb = nskb;
}
skb_put(e->skb, diff);
diff --git a/net/ipv6/netfilter/ip6_queue.c b/net/ipv6/netfilter/ip6_queue.c
index 3ca9303..e1d5465 100644
--- a/net/ipv6/netfilter/ip6_queue.c
+++ b/net/ipv6/netfilter/ip6_queue.c
@@ -296,7 +296,7 @@ ipq_mangle_ipv6(ipq_verdict_msg_t *v, struct nf_queue_entry *e)
"in mangle, dropping packet\n");
return -ENOMEM;
}
- kfree_skb(e->skb);
+ consume_skb(e->skb);
e->skb = nskb;
}
skb_put(e->skb, diff);
^ permalink raw reply related
* Re: [v12 PATCH 2/3] NETFILTER module xt_hmark, new target for HASH based fwmark
From: Hans Schillstrom @ 2012-05-02 7:55 UTC (permalink / raw)
To: Pablo Neira Ayuso
Cc: kaber@trash.net, jengelh@medozas.de,
netfilter-devel@vger.kernel.org, netdev@vger.kernel.org,
hans@schillstrom.com
In-Reply-To: <20120502003414.GA14940@1984>
Hello Pablo
(Sorry for spamming some of you, kmail started to send HTML mail)
On Wednesday 02 May 2012 02:34:14 Pablo Neira Ayuso wrote:
> Hi Hans,
>
> I have decided to take your patch and give it one spin today.
>
> Please, find it attached. The main things I've done are:
>
> * splitting the code into smaller functions, thus, it becomes more
> maintainable.
>
> * try to put common code into functions, eg. the layer 4 protocol
> parsing to obtain the ports is the same for both IPv4 and IPv6.
>
> * adding the hmark_tuple abstraction, cleaner than using several
> variables to set the address, ports, and so on. Thus, we only pass
> one single pointer to it.
>
> * I have removed most of the comments, they bloat the file and most
> information can be extracted by reading the code. I only left the
> comments that clarify "strange" things.
>
> Regarding ICMP traffic, I think we can use the ID field for the
> hashing as well. Thus, we handle ICMP like other protocols.
Yes why not, I can give it a try.
>
> Please, I'd appreciate if you can test and spot issues after my
> rework. I have slightly tested here.
OK I found some minor things, I'll send an updated version back later today.
I will run all my tests it will take a couple of hours.
This is what I have founf so far (before testing)
+ t->dst = (__force u32)
+ (otuple->src.u3.in6.s6_addr32[0] &
+ info->dst_mask.in6.s6_addr32[0]) ^
+ (otuple->src.u3.in6.s6_addr32[1] &
+ info->dst_mask.in6.s6_addr32[1]) ^
+ (otuple->src.u3.in6.s6_addr32[2] &
+ info->dst_mask.in6.s6_addr32[2]) ^
+ (otuple->src.u3.in6.s6_addr32[3] &
+ info->dst_mask.in6.s6_addr32[3]);
Should be rtuple
+ if (t->proto != IPPROTO_ICMP) {
+ t->uports.p16.src = (otuple->src.u.all & info->port_mask.v32) |
+ info->port_set.v32;
+ t->uports.p16.dst = (rtuple->src.u.all & info->port_mask.v32) |
+ info->port_set.v32;
+ }
in hmark_ct_set_htuple_ipv4() and hmark_ct_set_htuple_ipv6()
Wrong port_mask and port_set, this will work better..
if (t->proto != IPPROTO_ICMP) {
t->uports.p16.src = otuple->src.u.all;
t->uports.p16.dst = rtuple->src.u.all;
t->uports.v32 = (t->uports.v32 & info->port_mask.v32) |
info->port_set.v32;
>
> I may make some minor cleanup on it before submission but, in that
> case, in that case, I'll post the patch. I would not expect more major
> changes in it.
>
> Let me know.
Thanks Pablo
I realized that I sent wrong version as v12 (v11 with updated comments only), sorry for the confusion.
Basically the changes are the same but you have split it up a little bit more.
--
Regards
Hans Schillstrom <hans.schillstrom@ericsson.com>
^ permalink raw reply
* Re: [PATCH] mwl8k: Add 0x2a02 PCI device-id (Marvell 88W8361)
From: Arend van Spriel @ 2012-05-02 7:59 UTC (permalink / raw)
To: sedat.dilek
Cc: Sedat Dilek, Lennert Buytenhek, John W. Linville, linux-wireless,
netdev, linux-kernel, lautriv, Jim Cromie, Ben Hutchings,
Hauke Mehrtens, Xose Vazquez Perez
In-Reply-To: <CA+icZUV=qtXwVxb+uvQJcsza0y+6k2LHJFFPnECY0M=QWBexaQ@mail.gmail.com>
On 05/01/2012 03:54 PM, Sedat Dilek wrote:
> On Tue, May 1, 2012 at 2:51 PM, Lennert Buytenhek
> <buytenh@wantstofly.org> wrote:
>> On Sun, Apr 29, 2012 at 12:25:21AM +0200, Sedat Dilek wrote:
>>
>>>> On 1st sight, logs look fine:
>>>>
>>>> [21:52:52]<lautriv> [ 6.050967] ieee80211 phy0: 88w8361p v4,
>>>> 00173f3bdde3, STA firmware 2.1.4.25
>>>>
>>>> But WLAN connection is not that fast and stable as lautriv reports
>>>> (several abnormalities were observed).
>>>>
>>>> I requested a tarball which includes:
>>>> * dmesg (Linux-3.3.3)
>>>> * e_n_a (/etc/network/interfaces)
>>>> * ifconfig output
>>>> * iwconfig output
>>>> * iw_phy output
>>>> * ps_axu (WPA) output
>>>>
>>>> lautriv will be so kind to be around on #linux-wireless/Freenode the
>>>> next days (UTC+2: German/Swiss local-time).
>>>> Just ping him.
>>>>
>>>> Hope you have fun, together!
>>>>
>>>> - Sedat -
>>>
>>> A new tarball from lautriv with same outputs as before, but now tested
>>> with Linux-3.4-rc4.
>
> [ CC hauke (OpenWrt) and Ben Hutchings (linux-firmware maintainer) ]
>
>> The output looks good enough for me to ACK adding the PCI ID.
>>
>> Can the firmware being used here be submitted to the linux-firmware
>> git tree?
>
> I can't say much about the firmware [1] inclusion or the procedure of
> it into linux-firmware [2].
> Maybe, Ben can explain the procedure and what has to be considered
> before inclusion in linux-firmware.
> The original firmware and helper images were extracted from a Netgear
> Windows driver [1].
>
> From what I read in the OpenWrt forum posting [3]: You wanted to care
> for inclusion:
>
> "Firmware isn't included in the kernel tree anymore, there's the
> linux-firmware git tree for that these days. I will contact some
> people at Marvell to ask whether 8361P firmware can be included
> there."
Basically, all firmware in linux-firmware repository should be
accompanied with license information. Also you are signing off the patch
to add the firmware to the repository so you are bound to the
Developer's Certificate of Origin 1.1 in [1]. Having the firmware
extracted from a windows driver does not fall under that statement,
unless Marvell is ok with its redistribution. Recently a patch was
submitted for a README in the linux-firmware repository about the
process. It must be a binary patch. Easiest way is to use 'git
format-patch -B'.
Gr. AvS
[1] http://lxr.linux.no/linux+v3.3.4/Documentation/SubmittingPatches
[2] https://lkml.org/lkml/2012/4/21/177
^ permalink raw reply
* Re: [v12 PATCH 2/3] NETFILTER module xt_hmark, new target for HASH based fwmark
From: Pablo Neira Ayuso @ 2012-05-02 8:09 UTC (permalink / raw)
To: Hans Schillstrom
Cc: kaber@trash.net, jengelh@medozas.de,
netfilter-devel@vger.kernel.org, netdev@vger.kernel.org,
hans@schillstrom.com
In-Reply-To: <201205020955.01498.hans.schillstrom@ericsson.com>
On Wed, May 02, 2012 at 09:55:00AM +0200, Hans Schillstrom wrote:
> Hello Pablo
> (Sorry for spamming some of you, kmail started to send HTML mail)
>
> On Wednesday 02 May 2012 02:34:14 Pablo Neira Ayuso wrote:
> > Hi Hans,
> >
> > I have decided to take your patch and give it one spin today.
> >
> > Please, find it attached. The main things I've done are:
> >
> > * splitting the code into smaller functions, thus, it becomes more
> > maintainable.
> >
> > * try to put common code into functions, eg. the layer 4 protocol
> > parsing to obtain the ports is the same for both IPv4 and IPv6.
> >
> > * adding the hmark_tuple abstraction, cleaner than using several
> > variables to set the address, ports, and so on. Thus, we only pass
> > one single pointer to it.
> >
> > * I have removed most of the comments, they bloat the file and most
> > information can be extracted by reading the code. I only left the
> > comments that clarify "strange" things.
> >
> > Regarding ICMP traffic, I think we can use the ID field for the
> > hashing as well. Thus, we handle ICMP like other protocols.
>
> Yes why not, I can give it a try.
>
> >
> > Please, I'd appreciate if you can test and spot issues after my
> > rework. I have slightly tested here.
>
> OK I found some minor things, I'll send an updated version back later today.
> I will run all my tests it will take a couple of hours.
Please, go ahead.
> This is what I have founf so far (before testing)
>
> + t->dst = (__force u32)
> + (otuple->src.u3.in6.s6_addr32[0] &
> + info->dst_mask.in6.s6_addr32[0]) ^
> + (otuple->src.u3.in6.s6_addr32[1] &
> + info->dst_mask.in6.s6_addr32[1]) ^
> + (otuple->src.u3.in6.s6_addr32[2] &
> + info->dst_mask.in6.s6_addr32[2]) ^
> + (otuple->src.u3.in6.s6_addr32[3] &
> + info->dst_mask.in6.s6_addr32[3]);
>
> Should be rtuple
>
> + if (t->proto != IPPROTO_ICMP) {
> + t->uports.p16.src = (otuple->src.u.all & info->port_mask.v32) |
> + info->port_set.v32;
> + t->uports.p16.dst = (rtuple->src.u.all & info->port_mask.v32) |
> + info->port_set.v32;
> + }
>
> in hmark_ct_set_htuple_ipv4() and hmark_ct_set_htuple_ipv6()
> Wrong port_mask and port_set, this will work better..
>
> if (t->proto != IPPROTO_ICMP) {
> t->uports.p16.src = otuple->src.u.all;
> t->uports.p16.dst = rtuple->src.u.all;
> t->uports.v32 = (t->uports.v32 & info->port_mask.v32) |
> info->port_set.v32;
Fine, thanks.
> >
> > I may make some minor cleanup on it before submission but, in that
> > case, in that case, I'll post the patch. I would not expect more major
> > changes in it.
> >
> > Let me know.
> Thanks Pablo
> I realized that I sent wrong version as v12 (v11 with updated comments only), sorry for the confusion.
Yes, I noticed that.
> Basically the changes are the same but you have split it up a little bit more.
Exactly, my idea was to split it up to make it more maintainable and
to try to re-use code as much as possible.
^ permalink raw reply
* Re: [V2 PATCH 0/9] vhost/macvtap zeropcopy fixes
From: Michael S. Tsirkin @ 2012-05-02 8:11 UTC (permalink / raw)
To: David Miller; +Cc: jasowang, eric.dumazet, netdev, linux-kernel, ebiederm
In-Reply-To: <20120502.024427.22049954455309204.davem@davemloft.net>
On Wed, May 02, 2012 at 02:44:27AM -0400, David Miller wrote:
> From: "Michael S. Tsirkin" <mst@redhat.com>
> Date: Wed, 2 May 2012 08:50:09 +0300
>
> > On Wed, May 02, 2012 at 11:41:21AM +0800, Jason Wang wrote:
> >> This is an updated since the last series of vhost/macvtap zerocopy fixes which
> >> fixes the the possible transmission stall, host kernel stack overflow and other
> >> misc fixes.
> >>
> >> Changes from V1:
> >> - Addressing comments from Eric and Michael.
> >> - Adding more fixes into the seires.
> >
> > Thanks for fixing this.
> > Acked-by: Michael S. Tsirkin <mst@redhat.com>
> >
> > Dave, can you merge this for 3.4 please?
>
> It's rather late in the -RC for such a large patch set.
I was in doubt that's why I asked instead of just merging through my tree.
OK, I'll apply to my tree and send pull request for net-next a bit later.
--
MST
^ permalink raw reply
* [PATCH net-next] net: take care of cloned skbs in tcp_try_coalesce()
From: Eric Dumazet @ 2012-05-02 8:13 UTC (permalink / raw)
To: Alexander Duyck
Cc: Alexander Duyck, David Miller, netdev, Neal Cardwell, Tom Herbert,
Jeff Kirsher, Michael Chan, Matt Carlson, Herbert Xu,
Ben Hutchings, Ilpo Järvinen, Maciej Żenczykowski
In-Reply-To: <1335926862.22133.42.camel@edumazet-glaptop>
From: Eric Dumazet <edumazet@google.com>
Before stealing fragments or skb head, we must make sure skb is not
cloned.
If skb is cloned, we must take references on pages instead.
Bug happened using tcpdump (if not using mmap())
Reported-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
net/ipv4/tcp_input.c | 17 ++++++++++++++---
1 file changed, 14 insertions(+), 3 deletions(-)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 96a631d..7686d7f 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4467,7 +4467,7 @@ static bool tcp_try_coalesce(struct sock *sk,
struct sk_buff *from,
bool *fragstolen)
{
- int delta, len = from->len;
+ int i, delta, len = from->len;
*fragstolen = false;
if (tcp_hdr(from)->fin)
@@ -4497,7 +4497,13 @@ copyfrags:
skb_shinfo(from)->frags,
skb_shinfo(from)->nr_frags * sizeof(skb_frag_t));
skb_shinfo(to)->nr_frags += skb_shinfo(from)->nr_frags;
- skb_shinfo(from)->nr_frags = 0;
+
+ if (skb_cloned(from))
+ for (i = 0; i < skb_shinfo(from)->nr_frags; i++)
+ skb_frag_ref(from, i);
+ else
+ skb_shinfo(from)->nr_frags = 0;
+
to->truesize += delta;
atomic_add(delta, &sk->sk_rmem_alloc);
sk_mem_charge(sk, delta);
@@ -4515,7 +4521,12 @@ copyfrags:
offset = from->data - (unsigned char *)page_address(page);
skb_fill_page_desc(to, skb_shinfo(to)->nr_frags,
page, offset, skb_headlen(from));
- *fragstolen = true;
+
+ if (skb_cloned(from))
+ get_page(page);
+ else
+ *fragstolen = true;
+
delta = len; /* we dont know real truesize... */
goto copyfrags;
}
^ permalink raw reply related
* Re: [PATCH 3/4 v2 net-next] net: make GRO aware of skb->head_frag
From: Eric Dumazet @ 2012-05-02 8:24 UTC (permalink / raw)
To: Alexander Duyck
Cc: Alexander Duyck, David Miller, netdev, Neal Cardwell, Tom Herbert,
Jeff Kirsher, Michael Chan, Matt Carlson, Herbert Xu,
Ben Hutchings, Ilpo Järvinen, Maciej Żenczykowski
In-Reply-To: <4FA03D69.6060907@intel.com>
On Tue, 2012-05-01 at 12:45 -0700, Alexander Duyck wrote:
> I have a hacked together ixgbe up and running now with the new build_skb
> logic and RSC/LRO disabled. It looks like it is giving me a 5%
> performance boost for small packet routing, but I am using more CPU for
> netperf TCP receive tests and I was wondering if you had seen anything
> similar on the tg3 driver?
Really hard to say, numbers are so small on Gb link :
what do you use to make your numbers ?
netperf -H 172.30.42.23 -t OMNI -C -c
OMNI Send TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 172.30.42.23 (172.30.42.23) port 0 AF_INET
Local Local Local Elapsed Throughput Throughput Local Local Remote Remote Local Remote Service
Send Socket Send Socket Send Time Units CPU CPU CPU CPU Service Service Demand
Size Size Size (sec) Util Util Util Util Demand Demand Units
Final Final % Method % Method
1700840 1700840 16384 10.01 931.60 10^6bits/s 4.50 S 1.32 S 1.582 2.783 usec/KB
About ixgbe, feel free to send your patch ;)
Thanks !
^ permalink raw reply
* Re: [net-next v2 6/8] ixgbe: add syfs interface for to export read only driver information
From: Jeff Kirsher @ 2012-05-02 8:41 UTC (permalink / raw)
To: David Miller; +Cc: donald.c.skidmore, netdev, gospo, sassmann, bhutchings
In-Reply-To: <20120501.100241.1409452912879198250.davem@davemloft.net>
[-- Attachment #1: Type: text/plain, Size: 1680 bytes --]
On Tue, 2012-05-01 at 10:02 -0400, David Miller wrote:
> From: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
> Date: Tue, 1 May 2012 01:51:07 -0700
>
> > From: Don Skidmore <donald.c.skidmore@intel.com>
> >
> > This patch exports non-thermal (which was done via hwmon in an earlier
> > patch) data to sysfs which isn't readily available elsewhere. All of the
> > fields are read only as this interface is to only export driver data.
> >
> > Signed-off-by: Don Skidmore <donald.c.skidmore@intel.com>
> > Tested-by: Stephen Ko <stephen.s.ko@intel.com>
> > Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
>
> I don't like it.
>
> Some of this stuff is generic and belongs somewhere like ethtool, for
> example the descriptor sizes and queue sizes.
>
> The others are reading registers, and we have an ethtool API for that
> already.
>
> But putting anything like this in sysfs is pointless, because the
> stuff that other cards have too will then go into differently named
> sysfs files which, as is oft repeated here, is a terrible user
> experience.
>
> If you want to do this right, add a new ethtool interface that allows
> the publication of card specific unchanging values, in a style like
> what we already do for statistics. Have one query that gets the
> string list, and then another which fetches the actual values.
>
> I hate sysfs, don't send me any more patches that add sysfs files for
> networking devices. :-)
Ok.
So the other two patches (patch 4 & 5 in the series) should be fine
since they integrate hwmon interface like how Ben Hutchings has done
with other drivers and do not add any sysfs, correct?
[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 836 bytes --]
^ permalink raw reply
* RE: [PATCH 01/14 v3] usb/net: rndis: inline the cpu_to_le32() macro
From: David Laight @ 2012-05-02 8:44 UTC (permalink / raw)
To: Linus Walleij, netdev-u79uwXL29TY76Z2rM5mHXA,
linux-usb-u79uwXL29TY76Z2rM5mHXA, Greg Kroah-Hartman,
David S. Miller, Felipe Balbi
Cc: Jussi Kivilinna, Haiyang Zhang, Wei Yongjun, Ben Hutchings
In-Reply-To: <1335896100-12469-1-git-send-email-linus.walleij-QSEj5FYQhm4dnm+yROfE0A@public.gmane.org>
> -----Original Message-----
> From: netdev-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
> [mailto:netdev-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org] On Behalf Of Linus Walleij
> Sent: 01 May 2012 19:15
> To: netdev-u79uwXL29TY76Z2rM5mHXA@public.gmane.org; linux-usb-u79uwXL29TY76Z2rM5mHXA@public.gmane.org; Greg
> Kroah-Hartman; David S. Miller; Felipe Balbi
> Cc: Jussi Kivilinna; Haiyang Zhang; Wei Yongjun; Ben
> Hutchings; Linus Walleij
> Subject: [PATCH 01/14 v3] usb/net: rndis: inline the
> cpu_to_le32() macro
>
> The header file <linux/usb/rndis_host.h> used a number of #defines
> that included the cpu_to_le32() macro to assure the result will be
> in LE endianness. Inlining this into the code instead of using it
> in the code definitions yields consolidation opportunities later
> on as you will see in the following patches. The individual
> drivers also used local defines - all are switched over to the
> pattern of doing the conversion at the call sites instead.
>
> Signed-off-by: Linus Walleij <linus.walleij-QSEj5FYQhm4dnm+yROfE0A@public.gmane.org>
> ---
> drivers/net/usb/rndis_host.c | 52 +++++++-------
> drivers/net/wireless/rndis_wlan.c | 138
> +++++++++++++++++++------------------
> include/linux/usb/rndis_host.h | 84 +++++++++++-----------
> 3 files changed, 139 insertions(+), 135 deletions(-)
>
> diff --git a/drivers/net/usb/rndis_host.c
> b/drivers/net/usb/rndis_host.c
> index c8f1b5b..05cad0b 100644
> --- a/drivers/net/usb/rndis_host.c
> +++ b/drivers/net/usb/rndis_host.c
> @@ -78,10 +78,10 @@ static void rndis_msg_indicate(struct
> usbnet *dev, struct rndis_indicate *msg,
> dev->driver_info->indication(dev, msg, buflen);
> } else {
> switch (msg->status) {
> - case RNDIS_STATUS_MEDIA_CONNECT:
> + case cpu_to_le32(RNDIS_STATUS_MEDIA_CONNECT):
> dev_info(udev, "rndis media connect\n");
> break;
I don't actually see how this helps!
It seems to make the code more unreadable and more likely to
be wrong (due to typos/coding slipups etc).
I didn't see anything in the earlier versions of the patches
where leaving the constants 'host endian' helped.
I also actually suspect that the generated code for some of the
switch statements would be better if the 'status' were byteswapped.
In particular it might allow the compiler to use a jump table
(when all the case labels are in one set of values).
David
--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [net-next v2 6/8] ixgbe: add syfs interface for to export read only driver information
From: David Miller @ 2012-05-02 8:51 UTC (permalink / raw)
To: jeffrey.t.kirsher; +Cc: donald.c.skidmore, netdev, gospo, sassmann, bhutchings
In-Reply-To: <1335948107.2656.33.camel@jtkirshe-mobl>
From: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Date: Wed, 02 May 2012 01:41:47 -0700
> So the other two patches (patch 4 & 5 in the series) should be fine
> since they integrate hwmon interface like how Ben Hutchings has done
> with other drivers and do not add any sysfs, correct?
Correct.
^ permalink raw reply
* Re: [PATCH] mwl8k: Add 0x2a02 PCI device-id (Marvell 88W8361)
From: Sedat Dilek @ 2012-05-02 8:58 UTC (permalink / raw)
To: Lennert Buytenhek
Cc: Pat Erley, John W. Linville, linux-wireless, netdev, linux-kernel,
lautriv, Jim Cromie, Ben Hutchings, Hauke Mehrtens
In-Reply-To: <20120502023836.GW3157@wantstofly.org>
On Wed, May 2, 2012 at 4:38 AM, Lennert Buytenhek
<buytenh@wantstofly.org> wrote:
> On Tue, May 01, 2012 at 09:12:25PM -0400, Pat Erley wrote:
>
>> >--- a/drivers/net/wireless/mwl8k.c
>> >+++ b/drivers/net/wireless/mwl8k.c
>> >@@ -5225,6 +5225,7 @@ static void mwl8k_finalize_join_worker(struct work_struct *work)
>> > }
>> >
>> > enum {
>> >+ MWL8361P = 0,
>> > MWL8363 = 0,
>> > MWL8687,
>> > MWL8366,
>>
>> I'm not an expert, but isn't this giving both 8361P and 8363 the
>> same values in the enum?
>
> Yeah, this is broken.
Before this email, Helmut pointed me to the enum thingie in a private query.
As I was busy with OverlayFS the last days, I couldn't give that
information back.
So, this should be:
...
enum {
MWL8361P = 0,
MWL8363,
MWL8687,
MWL8366,
...
Shall I cook up a new patch with a proper history and documented
origin (original patch is from OpenWrt, I refreshed it against
upstream)?
...add some Tested-by (Helmut, Jim)...
...send that to linux-wireless ML for a review?
- Sedat -
^ permalink raw reply
* [net-next v2 0/7][pull request] Intel Wired LAN Driver Updates
From: Jeff Kirsher @ 2012-05-02 9:13 UTC (permalink / raw)
To: davem; +Cc: Jeff Kirsher, netdev, gospo, sassmann, bhutchings
This series of patches contains updates for e1000e and ixgbe.
Patch 4 & 5 integrate the hwmon interface for ixgbe as Ben Hutchings
has done for other drivers.
v2: dropped the ixgbe patch which added the sysfs interface
The following are changes since commit e4ae004b84b315dd4b762e474f97403eac70f76a:
netem: add ECN capability
and are available in the git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/net-next master
Bruce Allan (3):
e1000e: workaround EEPROM configuration change on 82579
e1000e: PHY initialization flow changes for 82577/8/9
e1000e: fix .ndo_set_rx_mode for 82579
Don Skidmore (2):
ixgbe: add support functions to access thermal data
ixgbe: add hwmon interface to export thermal data
Greg Rose (2):
ixgbe: Deny MACVLAN requests from VFs with admin set MAC
ixgbe: Reset max_vfs to zero when user request is out of range
drivers/net/ethernet/intel/Kconfig | 8 +
drivers/net/ethernet/intel/e1000e/80003es2lan.c | 1 +
drivers/net/ethernet/intel/e1000e/82571.c | 4 +-
drivers/net/ethernet/intel/e1000e/e1000.h | 2 +-
drivers/net/ethernet/intel/e1000e/hw.h | 6 +
drivers/net/ethernet/intel/e1000e/ich8lan.c | 339 ++++++++++++++++-------
drivers/net/ethernet/intel/e1000e/mac.c | 10 +-
drivers/net/ethernet/intel/e1000e/netdev.c | 12 +-
drivers/net/ethernet/intel/ixgbe/Makefile | 2 +-
drivers/net/ethernet/intel/ixgbe/ixgbe.h | 26 ++
drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c | 2 +
drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c | 2 +
drivers/net/ethernet/intel/ixgbe/ixgbe_common.c | 169 +++++++++++
drivers/net/ethernet/intel/ixgbe/ixgbe_common.h | 13 +
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 13 +-
drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c | 6 +
drivers/net/ethernet/intel/ixgbe/ixgbe_sysfs.c | 271 ++++++++++++++++++
drivers/net/ethernet/intel/ixgbe/ixgbe_type.h | 40 +++
drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c | 2 +
19 files changed, 808 insertions(+), 120 deletions(-)
create mode 100644 drivers/net/ethernet/intel/ixgbe/ixgbe_sysfs.c
--
1.7.7.6
^ permalink raw reply
* [net-next 1/7] e1000e: workaround EEPROM configuration change on 82579
From: Jeff Kirsher @ 2012-05-02 9:13 UTC (permalink / raw)
To: davem; +Cc: Bruce Allan, netdev, gospo, sassmann, Jeff Kirsher
In-Reply-To: <1335950025-13294-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Bruce Allan <bruce.w.allan@intel.com>
An update to the EEPROM on 82579 will extend a delay in hardware to fix an
issue with WoL not working after a G3->S5 transition which is unrelated to
the driver. However, this extended delay conflicts with nominal operation
of the device when it is initialized by the driver and after every reset
of the hardware (i.e. the driver starts configuring the device before the
hardware is done with it's own configuration work). The workaround for
when the driver is in control of the device is to tell the hardware after
every reset the configuration delay should be the original shorter one.
Some pre-existing variables are renamed generically to be re-used with
new register accesses.
Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Tested-by: Jeff Pieper <jeffrey.e.pieper@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/e1000e/hw.h | 1 +
drivers/net/ethernet/intel/e1000e/ich8lan.c | 48 ++++++++++++++++++--------
2 files changed, 34 insertions(+), 15 deletions(-)
diff --git a/drivers/net/ethernet/intel/e1000e/hw.h b/drivers/net/ethernet/intel/e1000e/hw.h
index 7ca1b68..3a5acb5 100644
--- a/drivers/net/ethernet/intel/e1000e/hw.h
+++ b/drivers/net/ethernet/intel/e1000e/hw.h
@@ -51,6 +51,7 @@ enum e1e_registers {
E1000_FEXTNVM = 0x00028, /* Future Extended NVM - RW */
E1000_FCT = 0x00030, /* Flow Control Type - RW */
E1000_VET = 0x00038, /* VLAN Ether Type - RW */
+ E1000_FEXTNVM3 = 0x0003C, /* Future Extended NVM 3 - RW */
E1000_ICR = 0x000C0, /* Interrupt Cause Read - R/clr */
E1000_ITR = 0x000C4, /* Interrupt Throttling Rate - RW */
E1000_ICS = 0x000C8, /* Interrupt Cause Set - WO */
diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c
index d7fd1e8..2506ee2 100644
--- a/drivers/net/ethernet/intel/e1000e/ich8lan.c
+++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c
@@ -105,6 +105,9 @@
#define E1000_FEXTNVM_SW_CONFIG 1
#define E1000_FEXTNVM_SW_CONFIG_ICH8M (1 << 27) /* Bit redefined for ICH8M :/ */
+#define E1000_FEXTNVM3_PHY_CFG_COUNTER_MASK 0x0C000000
+#define E1000_FEXTNVM3_PHY_CFG_COUNTER_50MSEC 0x08000000
+
#define E1000_FEXTNVM4_BEACON_DURATION_MASK 0x7
#define E1000_FEXTNVM4_BEACON_DURATION_8USEC 0x7
#define E1000_FEXTNVM4_BEACON_DURATION_16USEC 0x3
@@ -286,16 +289,23 @@ static inline void __ew32flash(struct e1000_hw *hw, unsigned long reg, u32 val)
static void e1000_toggle_lanphypc_value_ich8lan(struct e1000_hw *hw)
{
- u32 ctrl;
+ u32 reg;
- ctrl = er32(CTRL);
- ctrl |= E1000_CTRL_LANPHYPC_OVERRIDE;
- ctrl &= ~E1000_CTRL_LANPHYPC_VALUE;
- ew32(CTRL, ctrl);
+ /* Set Phy Config Counter to 50msec */
+ reg = er32(FEXTNVM3);
+ reg &= ~E1000_FEXTNVM3_PHY_CFG_COUNTER_MASK;
+ reg |= E1000_FEXTNVM3_PHY_CFG_COUNTER_50MSEC;
+ ew32(FEXTNVM3, reg);
+
+ /* Toggle LANPHYPC Value bit */
+ reg = er32(CTRL);
+ reg |= E1000_CTRL_LANPHYPC_OVERRIDE;
+ reg &= ~E1000_CTRL_LANPHYPC_VALUE;
+ ew32(CTRL, reg);
e1e_flush();
udelay(10);
- ctrl &= ~E1000_CTRL_LANPHYPC_OVERRIDE;
- ew32(CTRL, ctrl);
+ reg &= ~E1000_CTRL_LANPHYPC_OVERRIDE;
+ ew32(CTRL, reg);
}
/**
@@ -3071,8 +3081,8 @@ static s32 e1000_get_bus_info_ich8lan(struct e1000_hw *hw)
static s32 e1000_reset_hw_ich8lan(struct e1000_hw *hw)
{
struct e1000_dev_spec_ich8lan *dev_spec = &hw->dev_spec.ich8lan;
- u16 reg;
- u32 ctrl, kab;
+ u16 kum_cfg;
+ u32 ctrl, reg;
s32 ret_val;
/*
@@ -3106,12 +3116,12 @@ static s32 e1000_reset_hw_ich8lan(struct e1000_hw *hw)
}
if (hw->mac.type == e1000_pchlan) {
- /* Save the NVM K1 bit setting*/
- ret_val = e1000_read_nvm(hw, E1000_NVM_K1_CONFIG, 1, ®);
+ /* Save the NVM K1 bit setting */
+ ret_val = e1000_read_nvm(hw, E1000_NVM_K1_CONFIG, 1, &kum_cfg);
if (ret_val)
return ret_val;
- if (reg & E1000_NVM_K1_ENABLE)
+ if (kum_cfg & E1000_NVM_K1_ENABLE)
dev_spec->nvm_k1_enabled = true;
else
dev_spec->nvm_k1_enabled = false;
@@ -3141,6 +3151,14 @@ static s32 e1000_reset_hw_ich8lan(struct e1000_hw *hw)
/* cannot issue a flush here because it hangs the hardware */
msleep(20);
+ /* Set Phy Config Counter to 50msec */
+ if (hw->mac.type == e1000_pch2lan) {
+ reg = er32(FEXTNVM3);
+ reg &= ~E1000_FEXTNVM3_PHY_CFG_COUNTER_MASK;
+ reg |= E1000_FEXTNVM3_PHY_CFG_COUNTER_50MSEC;
+ ew32(FEXTNVM3, reg);
+ }
+
if (!ret_val)
clear_bit(__E1000_ACCESS_SHARED_RESOURCE, &hw->adapter->state);
@@ -3165,9 +3183,9 @@ static s32 e1000_reset_hw_ich8lan(struct e1000_hw *hw)
ew32(IMC, 0xffffffff);
er32(ICR);
- kab = er32(KABGTXD);
- kab |= E1000_KABGTXD_BGSQLBIAS;
- ew32(KABGTXD, kab);
+ reg = er32(KABGTXD);
+ reg |= E1000_KABGTXD_BGSQLBIAS;
+ ew32(KABGTXD, reg);
return 0;
}
--
1.7.7.6
^ permalink raw reply related
* [net-next 6/7] ixgbe: Deny MACVLAN requests from VFs with admin set MAC
From: Jeff Kirsher @ 2012-05-02 9:13 UTC (permalink / raw)
To: davem; +Cc: Greg Rose, netdev, gospo, sassmann, Jeff Kirsher
In-Reply-To: <1335950025-13294-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Greg Rose <gregory.v.rose@intel.com>
If the host VMM administrator has set the virtual function device's
MAC address then also deny VF requests for MACVLAN filters.
Signed-off-by: Greg Rose <gregory.v.rose@intel.com>
Tested-by: Garrett, Robert <robertx.e.garrett@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c | 6 ++++++
1 files changed, 6 insertions(+), 0 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
index 88a58cb..3985637 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
@@ -635,6 +635,12 @@ static int ixgbe_rcv_msg_from_vf(struct ixgbe_adapter *adapter, u32 vf)
}
break;
case IXGBE_VF_SET_MACVLAN:
+ if (adapter->vfinfo[vf].pf_set_mac) {
+ e_warn(drv, "VF %d requested MACVLAN filter but is "
+ "administratively denied\n", vf);
+ retval = -1;
+ break;
+ }
index = (msgbuf[0] & IXGBE_VT_MSGINFO_MASK) >>
IXGBE_VT_MSGINFO_SHIFT;
/*
--
1.7.7.6
^ permalink raw reply related
* [net-next 3/7] e1000e: fix .ndo_set_rx_mode for 82579
From: Jeff Kirsher @ 2012-05-02 9:13 UTC (permalink / raw)
To: davem; +Cc: Bruce Allan, netdev, gospo, sassmann, Jeff Kirsher
In-Reply-To: <1335950025-13294-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Bruce Allan <bruce.w.allan@intel.com>
Secondary unicast and multicast addresses are added to the Receive
Address registers (RAR) for most parts supported by the driver. For
82579, there is only one actual RAR and a number of Shared Receive Address
registers (SHRAR) that are shared among the driver and f/w which can be
reserved and write-protected by the f/w. On this device, use the SHRARs
that are not taken by f/w for the additional addresses.
Add a MAC ops function pointer infrastructure (similar to other MAC
operations in the driver) for setting RARs, introduce a new rar_set
function for 82579 and convert the existing code that sets RARs on other
devices to a generic rar_set function.
Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Tested-by: Jeff Pieper <jeffrey.e.pieper@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/e1000e/80003es2lan.c | 1 +
drivers/net/ethernet/intel/e1000e/82571.c | 4 +-
drivers/net/ethernet/intel/e1000e/e1000.h | 2 +-
drivers/net/ethernet/intel/e1000e/hw.h | 5 ++
drivers/net/ethernet/intel/e1000e/ich8lan.c | 72 ++++++++++++++++++++++-
drivers/net/ethernet/intel/e1000e/mac.c | 10 ++--
drivers/net/ethernet/intel/e1000e/netdev.c | 12 ++--
7 files changed, 92 insertions(+), 14 deletions(-)
diff --git a/drivers/net/ethernet/intel/e1000e/80003es2lan.c b/drivers/net/ethernet/intel/e1000e/80003es2lan.c
index a212846..66f9877 100644
--- a/drivers/net/ethernet/intel/e1000e/80003es2lan.c
+++ b/drivers/net/ethernet/intel/e1000e/80003es2lan.c
@@ -1439,6 +1439,7 @@ static const struct e1000_mac_operations es2_mac_ops = {
/* setup_physical_interface dependent on media type */
.setup_led = e1000e_setup_led_generic,
.config_collision_dist = e1000e_config_collision_dist_generic,
+ .rar_set = e1000e_rar_set_generic,
};
static const struct e1000_phy_operations es2_phy_ops = {
diff --git a/drivers/net/ethernet/intel/e1000e/82571.c b/drivers/net/ethernet/intel/e1000e/82571.c
index d0ea316..7b02e87 100644
--- a/drivers/net/ethernet/intel/e1000e/82571.c
+++ b/drivers/net/ethernet/intel/e1000e/82571.c
@@ -1762,7 +1762,8 @@ void e1000e_set_laa_state_82571(struct e1000_hw *hw, bool state)
* incoming packets directed to this port are dropped.
* Eventually the LAA will be in RAR[0] and RAR[14].
*/
- e1000e_rar_set(hw, hw->mac.addr, hw->mac.rar_entry_count - 1);
+ hw->mac.ops.rar_set(hw, hw->mac.addr,
+ hw->mac.rar_entry_count - 1);
}
/**
@@ -1926,6 +1927,7 @@ static const struct e1000_mac_operations e82571_mac_ops = {
.setup_led = e1000e_setup_led_generic,
.config_collision_dist = e1000e_config_collision_dist_generic,
.read_mac_addr = e1000_read_mac_addr_82571,
+ .rar_set = e1000e_rar_set_generic,
};
static const struct e1000_phy_operations e82_phy_ops_igp = {
diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h
index 1dc2067..1da9bfa 100644
--- a/drivers/net/ethernet/intel/e1000e/e1000.h
+++ b/drivers/net/ethernet/intel/e1000e/e1000.h
@@ -576,7 +576,7 @@ extern void e1000e_init_rx_addrs(struct e1000_hw *hw, u16 rar_count);
extern void e1000e_update_mc_addr_list_generic(struct e1000_hw *hw,
u8 *mc_addr_list,
u32 mc_addr_count);
-extern void e1000e_rar_set(struct e1000_hw *hw, u8 *addr, u32 index);
+extern void e1000e_rar_set_generic(struct e1000_hw *hw, u8 *addr, u32 index);
extern s32 e1000e_set_fc_watermarks(struct e1000_hw *hw);
extern void e1000e_set_pcie_no_snoop(struct e1000_hw *hw, u32 no_snoop);
extern s32 e1000e_get_hw_semaphore(struct e1000_hw *hw);
diff --git a/drivers/net/ethernet/intel/e1000e/hw.h b/drivers/net/ethernet/intel/e1000e/hw.h
index 3a5acb5..00a0ebb 100644
--- a/drivers/net/ethernet/intel/e1000e/hw.h
+++ b/drivers/net/ethernet/intel/e1000e/hw.h
@@ -200,6 +200,10 @@ enum e1e_registers {
#define E1000_RA (E1000_RAL(0))
E1000_RAH_BASE = 0x05404, /* Receive Address High - RW */
#define E1000_RAH(_n) (E1000_RAH_BASE + ((_n) * 8))
+ E1000_SHRAL_BASE = 0x05438, /* Shared Receive Address Low - RW */
+#define E1000_SHRAL(_n) (E1000_SHRAL_BASE + ((_n) * 8))
+ E1000_SHRAH_BASE = 0x0543C, /* Shared Receive Address High - RW */
+#define E1000_SHRAH(_n) (E1000_SHRAH_BASE + ((_n) * 8))
E1000_VFTA = 0x05600, /* VLAN Filter Table Array - RW Array */
E1000_WUC = 0x05800, /* Wakeup Control - RW */
E1000_WUFC = 0x05808, /* Wakeup Filter Control - RW */
@@ -782,6 +786,7 @@ struct e1000_mac_operations {
s32 (*setup_led)(struct e1000_hw *);
void (*write_vfta)(struct e1000_hw *, u32, u32);
void (*config_collision_dist)(struct e1000_hw *);
+ void (*rar_set)(struct e1000_hw *, u8 *, u32);
s32 (*read_mac_addr)(struct e1000_hw *);
};
diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c
index 4c8b0fb..ca34ebf 100644
--- a/drivers/net/ethernet/intel/e1000e/ich8lan.c
+++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c
@@ -115,6 +115,7 @@
#define PCIE_ICH8_SNOOP_ALL PCIE_NO_SNOOP_ALL
#define E1000_ICH_RAR_ENTRIES 7
+#define E1000_PCH2_RAR_ENTRIES 5 /* RAR[0], SHRA[0-3] */
#define PHY_PAGE_SHIFT 5
#define PHY_REG(page, reg) (((page) << PHY_PAGE_SHIFT) | \
@@ -259,6 +260,7 @@ static s32 e1000_k1_gig_workaround_hv(struct e1000_hw *hw, bool link);
static s32 e1000_set_mdio_slow_mode_hv(struct e1000_hw *hw);
static bool e1000_check_mng_mode_ich8lan(struct e1000_hw *hw);
static bool e1000_check_mng_mode_pchlan(struct e1000_hw *hw);
+static void e1000_rar_set_pch2lan(struct e1000_hw *hw, u8 *addr, u32 index);
static s32 e1000_k1_workaround_lv(struct e1000_hw *hw);
static void e1000_gate_hw_phy_config_ich8lan(struct e1000_hw *hw, bool gate);
@@ -672,8 +674,11 @@ static s32 e1000_init_mac_params_ich8lan(struct e1000_hw *hw)
mac->ops.led_on = e1000_led_on_ich8lan;
mac->ops.led_off = e1000_led_off_ich8lan;
break;
- case e1000_pchlan:
case e1000_pch2lan:
+ mac->rar_entry_count = E1000_PCH2_RAR_ENTRIES;
+ mac->ops.rar_set = e1000_rar_set_pch2lan;
+ /* fall-through */
+ case e1000_pchlan:
/* check management mode */
mac->ops.check_mng_mode = e1000_check_mng_mode_pchlan;
/* ID LED init */
@@ -1048,6 +1053,70 @@ static bool e1000_check_mng_mode_pchlan(struct e1000_hw *hw)
}
/**
+ * e1000_rar_set_pch2lan - Set receive address register
+ * @hw: pointer to the HW structure
+ * @addr: pointer to the receive address
+ * @index: receive address array register
+ *
+ * Sets the receive address array register at index to the address passed
+ * in by addr. For 82579, RAR[0] is the base address register that is to
+ * contain the MAC address but RAR[1-6] are reserved for manageability (ME).
+ * Use SHRA[0-3] in place of those reserved for ME.
+ **/
+static void e1000_rar_set_pch2lan(struct e1000_hw *hw, u8 *addr, u32 index)
+{
+ u32 rar_low, rar_high;
+
+ /*
+ * HW expects these in little endian so we reverse the byte order
+ * from network order (big endian) to little endian
+ */
+ rar_low = ((u32)addr[0] |
+ ((u32)addr[1] << 8) |
+ ((u32)addr[2] << 16) | ((u32)addr[3] << 24));
+
+ rar_high = ((u32)addr[4] | ((u32)addr[5] << 8));
+
+ /* If MAC address zero, no need to set the AV bit */
+ if (rar_low || rar_high)
+ rar_high |= E1000_RAH_AV;
+
+ if (index == 0) {
+ ew32(RAL(index), rar_low);
+ e1e_flush();
+ ew32(RAH(index), rar_high);
+ e1e_flush();
+ return;
+ }
+
+ if (index < hw->mac.rar_entry_count) {
+ s32 ret_val;
+
+ ret_val = e1000_acquire_swflag_ich8lan(hw);
+ if (ret_val)
+ goto out;
+
+ ew32(SHRAL(index - 1), rar_low);
+ e1e_flush();
+ ew32(SHRAH(index - 1), rar_high);
+ e1e_flush();
+
+ e1000_release_swflag_ich8lan(hw);
+
+ /* verify the register updates */
+ if ((er32(SHRAL(index - 1)) == rar_low) &&
+ (er32(SHRAH(index - 1)) == rar_high))
+ return;
+
+ e_dbg("SHRA[%d] might be locked by ME - FWSM=0x%8.8x\n",
+ (index - 1), er32(FWSM));
+ }
+
+out:
+ e_dbg("Failed to write receive address at index %d\n", index);
+}
+
+/**
* e1000_check_reset_block_ich8lan - Check if PHY reset is blocked
* @hw: pointer to the HW structure
*
@@ -4100,6 +4169,7 @@ static const struct e1000_mac_operations ich8_mac_ops = {
.setup_physical_interface= e1000_setup_copper_link_ich8lan,
/* id_led_init dependent on mac type */
.config_collision_dist = e1000e_config_collision_dist_generic,
+ .rar_set = e1000e_rar_set_generic,
};
static const struct e1000_phy_operations ich8_phy_ops = {
diff --git a/drivers/net/ethernet/intel/e1000e/mac.c b/drivers/net/ethernet/intel/e1000e/mac.c
index d832749..026e8b3 100644
--- a/drivers/net/ethernet/intel/e1000e/mac.c
+++ b/drivers/net/ethernet/intel/e1000e/mac.c
@@ -143,12 +143,12 @@ void e1000e_init_rx_addrs(struct e1000_hw *hw, u16 rar_count)
/* Setup the receive address */
e_dbg("Programming MAC Address into RAR[0]\n");
- e1000e_rar_set(hw, hw->mac.addr, 0);
+ hw->mac.ops.rar_set(hw, hw->mac.addr, 0);
/* Zero out the other (rar_entry_count - 1) receive addresses */
e_dbg("Clearing RAR[1-%u]\n", rar_count - 1);
for (i = 1; i < rar_count; i++)
- e1000e_rar_set(hw, mac_addr, i);
+ hw->mac.ops.rar_set(hw, mac_addr, i);
}
/**
@@ -215,13 +215,13 @@ s32 e1000_check_alt_mac_addr_generic(struct e1000_hw *hw)
* same as the normal permanent MAC address stored by the HW into the
* RAR. Do this by mapping this address into RAR0.
*/
- e1000e_rar_set(hw, alt_mac_addr, 0);
+ hw->mac.ops.rar_set(hw, alt_mac_addr, 0);
return 0;
}
/**
- * e1000e_rar_set - Set receive address register
+ * e1000e_rar_set_generic - Set receive address register
* @hw: pointer to the HW structure
* @addr: pointer to the receive address
* @index: receive address array register
@@ -229,7 +229,7 @@ s32 e1000_check_alt_mac_addr_generic(struct e1000_hw *hw)
* Sets the receive address array register at index to the address passed
* in by addr.
**/
-void e1000e_rar_set(struct e1000_hw *hw, u8 *addr, u32 index)
+void e1000e_rar_set_generic(struct e1000_hw *hw, u8 *addr, u32 index)
{
u32 rar_low, rar_high;
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 140fee1..c0e211b 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -3209,7 +3209,7 @@ static int e1000e_write_uc_addr_list(struct net_device *netdev)
netdev_for_each_uc_addr(ha, netdev) {
if (!rar_entries)
break;
- e1000e_rar_set(hw, ha->addr, rar_entries--);
+ hw->mac.ops.rar_set(hw, ha->addr, rar_entries--);
count++;
}
}
@@ -4018,6 +4018,7 @@ static int e1000_close(struct net_device *netdev)
static int e1000_set_mac(struct net_device *netdev, void *p)
{
struct e1000_adapter *adapter = netdev_priv(netdev);
+ struct e1000_hw *hw = &adapter->hw;
struct sockaddr *addr = p;
if (!is_valid_ether_addr(addr->sa_data))
@@ -4026,7 +4027,7 @@ static int e1000_set_mac(struct net_device *netdev, void *p)
memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len);
memcpy(adapter->hw.mac.addr, addr->sa_data, netdev->addr_len);
- e1000e_rar_set(&adapter->hw, adapter->hw.mac.addr, 0);
+ hw->mac.ops.rar_set(&adapter->hw, adapter->hw.mac.addr, 0);
if (adapter->flags & FLAG_RESET_OVERWRITES_LAA) {
/* activate the work around */
@@ -4040,9 +4041,8 @@ static int e1000_set_mac(struct net_device *netdev, void *p)
* are dropped. Eventually the LAA will be in RAR[0] and
* RAR[14]
*/
- e1000e_rar_set(&adapter->hw,
- adapter->hw.mac.addr,
- adapter->hw.mac.rar_entry_count - 1);
+ hw->mac.ops.rar_set(&adapter->hw, adapter->hw.mac.addr,
+ adapter->hw.mac.rar_entry_count - 1);
}
return 0;
@@ -4621,7 +4621,7 @@ link_up:
* reset from the other port. Set the appropriate LAA in RAR[0]
*/
if (e1000e_get_laa_state_82571(hw))
- e1000e_rar_set(hw, adapter->hw.mac.addr, 0);
+ hw->mac.ops.rar_set(hw, adapter->hw.mac.addr, 0);
if (adapter->flags2 & FLAG2_CHECK_PHY_HANG)
e1000e_check_82574_phy_workaround(adapter);
--
1.7.7.6
^ permalink raw reply related
* [net-next 4/7] ixgbe: add support functions to access thermal data
From: Jeff Kirsher @ 2012-05-02 9:13 UTC (permalink / raw)
To: davem; +Cc: Don Skidmore, netdev, gospo, sassmann, bhutchings, Jeff Kirsher
In-Reply-To: <1335950025-13294-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Don Skidmore <donald.c.skidmore@intel.com>
Some 82599 adapters contain thermal data that we can get to via
an i2c interface. These functions provide support to get at that
data. A following patch will export this data.
Signed-off-by: Don Skidmore <donald.c.skidmore@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe_common.c | 171 +++++++++++++++++++++++
drivers/net/ethernet/intel/ixgbe/ixgbe_common.h | 13 ++
drivers/net/ethernet/intel/ixgbe/ixgbe_type.h | 40 ++++++
3 files changed, 224 insertions(+), 0 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
index e598881..6c6c66e 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
@@ -3604,3 +3604,174 @@ void ixgbe_clear_tx_pending(struct ixgbe_hw *hw)
IXGBE_WRITE_REG(hw, IXGBE_GCR_EXT, gcr_ext);
IXGBE_WRITE_REG(hw, IXGBE_HLREG0, hlreg0);
}
+
+static const u8 ixgbe_emc_temp_data[4] = {
+ IXGBE_EMC_INTERNAL_DATA,
+ IXGBE_EMC_DIODE1_DATA,
+ IXGBE_EMC_DIODE2_DATA,
+ IXGBE_EMC_DIODE3_DATA
+};
+static const u8 ixgbe_emc_therm_limit[4] = {
+ IXGBE_EMC_INTERNAL_THERM_LIMIT,
+ IXGBE_EMC_DIODE1_THERM_LIMIT,
+ IXGBE_EMC_DIODE2_THERM_LIMIT,
+ IXGBE_EMC_DIODE3_THERM_LIMIT
+};
+
+/**
+ * ixgbe_get_ets_data - Extracts the ETS bit data
+ * @hw: pointer to hardware structure
+ * @ets_cfg: extected ETS data
+ * @ets_offset: offset of ETS data
+ *
+ * Returns error code.
+ **/
+static s32 ixgbe_get_ets_data(struct ixgbe_hw *hw, u16 *ets_cfg,
+ u16 *ets_offset)
+{
+ s32 status = 0;
+
+ status = hw->eeprom.ops.read(hw, IXGBE_ETS_CFG, ets_offset);
+ if (status)
+ goto out;
+
+ if ((*ets_offset == 0x0000) || (*ets_offset == 0xFFFF)) {
+ status = IXGBE_NOT_IMPLEMENTED;
+ goto out;
+ }
+
+ status = hw->eeprom.ops.read(hw, *ets_offset, ets_cfg);
+ if (status)
+ goto out;
+
+ if ((*ets_cfg & IXGBE_ETS_TYPE_MASK) != IXGBE_ETS_TYPE_EMC_SHIFTED) {
+ status = IXGBE_NOT_IMPLEMENTED;
+ goto out;
+ }
+
+out:
+ return status;
+}
+
+/**
+ * ixgbe_get_thermal_sensor_data - Gathers thermal sensor data
+ * @hw: pointer to hardware structure
+ *
+ * Returns the thermal sensor data structure
+ **/
+s32 ixgbe_get_thermal_sensor_data_generic(struct ixgbe_hw *hw)
+{
+ s32 status = 0;
+ u16 ets_offset;
+ u16 ets_cfg;
+ u16 ets_sensor;
+ u8 num_sensors;
+ u8 i;
+ struct ixgbe_thermal_sensor_data *data = &hw->mac.thermal_sensor_data;
+
+ /* Only support thermal sensors attached to 82599 physical port 0 */
+ if ((hw->mac.type != ixgbe_mac_82599EB) ||
+ (IXGBE_READ_REG(hw, IXGBE_STATUS) & IXGBE_STATUS_LAN_ID_1)) {
+ status = IXGBE_NOT_IMPLEMENTED;
+ goto out;
+ }
+
+ status = ixgbe_get_ets_data(hw, &ets_cfg, &ets_offset);
+ if (status)
+ goto out;
+
+ num_sensors = (ets_cfg & IXGBE_ETS_NUM_SENSORS_MASK);
+ if (num_sensors > IXGBE_MAX_SENSORS)
+ num_sensors = IXGBE_MAX_SENSORS;
+
+ for (i = 0; i < num_sensors; i++) {
+ u8 sensor_index;
+ u8 sensor_location;
+
+ status = hw->eeprom.ops.read(hw, (ets_offset + 1 + i),
+ &ets_sensor);
+ if (status)
+ goto out;
+
+ sensor_index = ((ets_sensor & IXGBE_ETS_DATA_INDEX_MASK) >>
+ IXGBE_ETS_DATA_INDEX_SHIFT);
+ sensor_location = ((ets_sensor & IXGBE_ETS_DATA_LOC_MASK) >>
+ IXGBE_ETS_DATA_LOC_SHIFT);
+
+ if (sensor_location != 0) {
+ status = hw->phy.ops.read_i2c_byte(hw,
+ ixgbe_emc_temp_data[sensor_index],
+ IXGBE_I2C_THERMAL_SENSOR_ADDR,
+ &data->sensor[i].temp);
+ if (status)
+ goto out;
+ }
+ }
+out:
+ return status;
+}
+
+/**
+ * ixgbe_init_thermal_sensor_thresh_generic - Inits thermal sensor thresholds
+ * @hw: pointer to hardware structure
+ *
+ * Inits the thermal sensor thresholds according to the NVM map
+ * and save off the threshold and location values into mac.thermal_sensor_data
+ **/
+s32 ixgbe_init_thermal_sensor_thresh_generic(struct ixgbe_hw *hw)
+{
+ s32 status = 0;
+ u16 ets_offset;
+ u16 ets_cfg;
+ u16 ets_sensor;
+ u8 low_thresh_delta;
+ u8 num_sensors;
+ u8 therm_limit;
+ u8 i;
+ struct ixgbe_thermal_sensor_data *data = &hw->mac.thermal_sensor_data;
+
+ memset(data, 0, sizeof(struct ixgbe_thermal_sensor_data));
+
+ /* Only support thermal sensors attached to 82599 physical port 0 */
+ if ((hw->mac.type != ixgbe_mac_82599EB) ||
+ (IXGBE_READ_REG(hw, IXGBE_STATUS) & IXGBE_STATUS_LAN_ID_1)) {
+ status = IXGBE_NOT_IMPLEMENTED;
+ goto out;
+ }
+
+ status = ixgbe_get_ets_data(hw, &ets_cfg, &ets_offset);
+ if (status)
+ goto out;
+
+ low_thresh_delta = ((ets_cfg & IXGBE_ETS_LTHRES_DELTA_MASK) >>
+ IXGBE_ETS_LTHRES_DELTA_SHIFT);
+ num_sensors = (ets_cfg & IXGBE_ETS_NUM_SENSORS_MASK);
+ if (num_sensors > IXGBE_MAX_SENSORS)
+ num_sensors = IXGBE_MAX_SENSORS;
+
+ for (i = 0; i < num_sensors; i++) {
+ u8 sensor_index;
+ u8 sensor_location;
+
+ hw->eeprom.ops.read(hw, (ets_offset + 1 + i), &ets_sensor);
+ sensor_index = ((ets_sensor & IXGBE_ETS_DATA_INDEX_MASK) >>
+ IXGBE_ETS_DATA_INDEX_SHIFT);
+ sensor_location = ((ets_sensor & IXGBE_ETS_DATA_LOC_MASK) >>
+ IXGBE_ETS_DATA_LOC_SHIFT);
+ therm_limit = ets_sensor & IXGBE_ETS_DATA_HTHRESH_MASK;
+
+ hw->phy.ops.write_i2c_byte(hw,
+ ixgbe_emc_therm_limit[sensor_index],
+ IXGBE_I2C_THERMAL_SENSOR_ADDR, therm_limit);
+
+ if (sensor_location == 0)
+ continue;
+
+ data->sensor[i].location = sensor_location;
+ data->sensor[i].caution_thresh = therm_limit;
+ data->sensor[i].max_op_thresh = therm_limit - low_thresh_delta;
+ }
+out:
+ return status;
+}
+
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h
index d6d3432..f992777 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h
@@ -107,6 +107,19 @@ void ixgbe_clear_tx_pending(struct ixgbe_hw *hw);
void ixgbe_set_rxpba_generic(struct ixgbe_hw *hw, int num_pb,
u32 headroom, int strategy);
+#define IXGBE_I2C_THERMAL_SENSOR_ADDR 0xF8
+#define IXGBE_EMC_INTERNAL_DATA 0x00
+#define IXGBE_EMC_INTERNAL_THERM_LIMIT 0x20
+#define IXGBE_EMC_DIODE1_DATA 0x01
+#define IXGBE_EMC_DIODE1_THERM_LIMIT 0x19
+#define IXGBE_EMC_DIODE2_DATA 0x23
+#define IXGBE_EMC_DIODE2_THERM_LIMIT 0x1A
+#define IXGBE_EMC_DIODE3_DATA 0x2A
+#define IXGBE_EMC_DIODE3_THERM_LIMIT 0x30
+
+s32 ixgbe_get_thermal_sensor_data_generic(struct ixgbe_hw *hw);
+s32 ixgbe_init_thermal_sensor_thresh_generic(struct ixgbe_hw *hw);
+
#define IXGBE_WRITE_REG(a, reg, value) writel((value), ((a)->hw_addr + (reg)))
#ifndef writeq
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
index 4acd9e6..d82e25c 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
@@ -112,6 +112,27 @@
#define IXGBE_I2C_DATA_OUT 0x00000008
#define IXGBE_I2C_CLOCK_STRETCHING_TIMEOUT 500
+#define IXGBE_I2C_THERMAL_SENSOR_ADDR 0xF8
+#define IXGBE_EMC_INTERNAL_DATA 0x00
+#define IXGBE_EMC_INTERNAL_THERM_LIMIT 0x20
+#define IXGBE_EMC_DIODE1_DATA 0x01
+#define IXGBE_EMC_DIODE1_THERM_LIMIT 0x19
+#define IXGBE_EMC_DIODE2_DATA 0x23
+#define IXGBE_EMC_DIODE2_THERM_LIMIT 0x1A
+
+#define IXGBE_MAX_SENSORS 3
+
+struct ixgbe_thermal_diode_data {
+ u8 location;
+ u8 temp;
+ u8 caution_thresh;
+ u8 max_op_thresh;
+};
+
+struct ixgbe_thermal_sensor_data {
+ struct ixgbe_thermal_diode_data sensor[IXGBE_MAX_SENSORS];
+};
+
/* Interrupt Registers */
#define IXGBE_EICR 0x00800
#define IXGBE_EICS 0x00808
@@ -1678,6 +1699,22 @@ enum {
#define IXGBE_PBANUM0_PTR 0x15
#define IXGBE_PBANUM1_PTR 0x16
#define IXGBE_FREE_SPACE_PTR 0X3E
+
+/* External Thermal Sensor Config */
+#define IXGBE_ETS_CFG 0x26
+#define IXGBE_ETS_LTHRES_DELTA_MASK 0x07C0
+#define IXGBE_ETS_LTHRES_DELTA_SHIFT 6
+#define IXGBE_ETS_TYPE_MASK 0x0038
+#define IXGBE_ETS_TYPE_SHIFT 3
+#define IXGBE_ETS_TYPE_EMC 0x000
+#define IXGBE_ETS_TYPE_EMC_SHIFTED 0x000
+#define IXGBE_ETS_NUM_SENSORS_MASK 0x0007
+#define IXGBE_ETS_DATA_LOC_MASK 0x3C00
+#define IXGBE_ETS_DATA_LOC_SHIFT 10
+#define IXGBE_ETS_DATA_INDEX_MASK 0x0300
+#define IXGBE_ETS_DATA_INDEX_SHIFT 8
+#define IXGBE_ETS_DATA_HTHRESH_MASK 0x00FF
+
#define IXGBE_SAN_MAC_ADDR_PTR 0x28
#define IXGBE_DEVICE_CAPS 0x2C
#define IXGBE_SERIAL_NUMBER_MAC_ADDR 0x11
@@ -2775,6 +2812,8 @@ struct ixgbe_mac_operations {
/* Manageability interface */
s32 (*set_fw_drv_ver)(struct ixgbe_hw *, u8, u8, u8, u8);
+ s32 (*get_thermal_sensor_data)(struct ixgbe_hw *);
+ s32 (*init_thermal_sensor_thresh)(struct ixgbe_hw *hw);
};
struct ixgbe_phy_operations {
@@ -2832,6 +2871,7 @@ struct ixgbe_mac_info {
bool orig_link_settings_stored;
bool autotry_restart;
u8 flags;
+ struct ixgbe_thermal_sensor_data thermal_sensor_data;
};
struct ixgbe_phy_info {
--
1.7.7.6
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox