* [PATCH RFC] Allow to turn off TCP window scale opt per route
From: Gilad Ben-Yossef @ 2009-10-20 15:22 UTC (permalink / raw)
To: netdev; +Cc: ori, Gilad Ben-Yossef
In-Reply-To: <1256052161-14156-6-git-send-email-gilad@codefidence.com>
Add and use no window scale bit in the features field.
Signed-off-by: Gilad Ben-Yossef <gilad@codefidence.com>
Sigend-off-by: Ori Finkelman <ori@comsleep.com>
Sigend-off-by: Yony Amit <yony@comsleep.com>
---
include/linux/rtnetlink.h | 1 +
net/ipv4/tcp_input.c | 3 ++-
net/ipv4/tcp_output.c | 6 ++++--
3 files changed, 7 insertions(+), 3 deletions(-)
diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h
index 2ab8c75..6784b34 100644
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -380,6 +380,7 @@ enum
#define RTAX_FEATURE_NO_SACK 0x00000002
#define RTAX_FEATURE_NO_TSTAMP 0x00000004
#define RTAX_FEATURE_ALLFRAG 0x00000008
+#define RTAX_FEATURE_NO_WSCALE 0x00000010
struct rta_session
{
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index d2f9742..4f5e914 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3739,7 +3739,8 @@ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx,
break;
case TCPOPT_WINDOW:
if (opsize == TCPOLEN_WINDOW && th->syn &&
- !estab && sysctl_tcp_window_scaling) {
+ !estab && sysctl_tcp_window_scaling &&
+ !dst_feature(dst, RTAX_FEATURE_NO_WSCALE)) {
__u8 snd_wscale = *(__u8 *)ptr;
opt_rx->wscale_ok = 1;
if (snd_wscale > 14) {
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 8f30c18..ff60a21 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -496,7 +496,8 @@ static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb,
opts->tsecr = tp->rx_opt.ts_recent;
size += TCPOLEN_TSTAMP_ALIGNED;
}
- if (likely(sysctl_tcp_window_scaling)) {
+ if (likely(sysctl_tcp_window_scaling &&
+ !dst_feature(dst, RTAX_FEATURE_NO_WSCALE))) {
opts->ws = tp->rx_opt.rcv_wscale;
opts->options |= OPTION_WSCALE;
size += TCPOLEN_WSCALE_ALIGNED;
@@ -2347,7 +2348,8 @@ static void tcp_connect_init(struct sock *sk)
tp->advmss - (tp->rx_opt.ts_recent_stamp ? tp->tcp_header_len - sizeof(struct tcphdr) : 0),
&tp->rcv_wnd,
&tp->window_clamp,
- sysctl_tcp_window_scaling,
+ (sysctl_tcp_window_scaling &&
+ !dst_feature(dst, RTAX_FEATURE_NO_WSCALE)),
&rcv_wscale);
tp->rx_opt.rcv_wscale = rcv_wscale;
--
1.5.6.3
^ permalink raw reply related
* [PATCH RFC] Add dst_feature to query route entry features
From: Gilad Ben-Yossef @ 2009-10-20 15:22 UTC (permalink / raw)
To: netdev; +Cc: ori, Gilad Ben-Yossef
In-Reply-To: <1256052161-14156-3-git-send-email-gilad@codefidence.com>
Adding an accessor to existing dst_entry feautres field and
refactor the only supported feature (allfrag) to use it.
Signed-off-by: Gilad Ben-Yossef <gilad@codefidence.com>
Sigend-off-by: Ori Finkelman <ori@comsleep.com>
Sigend-off-by: Yony Amit <yony@comsleep.com>
---
include/net/dst.h | 8 +++++++-
1 files changed, 7 insertions(+), 1 deletions(-)
diff --git a/include/net/dst.h b/include/net/dst.h
index 5a900dd..b562be3 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -111,6 +111,12 @@ dst_metric(const struct dst_entry *dst, int metric)
return dst->metrics[metric-1];
}
+static inline u32
+dst_feature(const struct dst_entry *dst, u32 feature)
+{
+ return dst_metric(dst, RTAX_FEATURES) & feature;
+}
+
static inline u32 dst_mtu(const struct dst_entry *dst)
{
u32 mtu = dst_metric(dst, RTAX_MTU);
@@ -136,7 +142,7 @@ static inline void set_dst_metric_rtt(struct dst_entry *dst, int metric,
static inline u32
dst_allfrag(const struct dst_entry *dst)
{
- int ret = dst_metric(dst, RTAX_FEATURES) & RTAX_FEATURE_ALLFRAG;
+ int ret = dst_feature(dst, RTAX_FEATURE_ALLFRAG);
/* Yes, _exactly_. This is paranoia. */
barrier();
return ret;
--
1.5.6.3
^ permalink raw reply related
* [PATCH RFC] Allow disabling TCP timestamp options per route
From: Gilad Ben-Yossef @ 2009-10-20 15:22 UTC (permalink / raw)
To: netdev; +Cc: ori, Gilad Ben-Yossef
In-Reply-To: <1256052161-14156-5-git-send-email-gilad@codefidence.com>
Implement querying and acting upon the no timestamp bit in the feature
field.
Signed-off-by: Gilad Ben-Yossef <gilad@codefidence.com>
Sigend-off-by: Ori Finkelman <ori@comsleep.com>
Sigend-off-by: Yony Amit <yony@comsleep.com>
---
include/linux/rtnetlink.h | 2 +-
net/ipv4/tcp_input.c | 3 ++-
net/ipv4/tcp_output.c | 8 ++++++--
3 files changed, 9 insertions(+), 4 deletions(-)
diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h
index 9c802a6..2ab8c75 100644
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -378,7 +378,7 @@ enum
#define RTAX_FEATURE_ECN 0x00000001
#define RTAX_FEATURE_NO_SACK 0x00000002
-#define RTAX_FEATURE_TIMESTAMP 0x00000004
+#define RTAX_FEATURE_NO_TSTAMP 0x00000004
#define RTAX_FEATURE_ALLFRAG 0x00000008
struct rta_session
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index b14f780..d2f9742 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3755,7 +3755,8 @@ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx,
case TCPOPT_TIMESTAMP:
if ((opsize == TCPOLEN_TIMESTAMP) &&
((estab && opt_rx->tstamp_ok) ||
- (!estab && sysctl_tcp_timestamps))) {
+ (!estab && sysctl_tcp_timestamps &&
+ !dst_feature(dst, RTAX_FEATURE_NO_TSTAMP)))) {
opt_rx->saw_tstamp = 1;
opt_rx->rcv_tsval = get_unaligned_be32(ptr);
opt_rx->rcv_tsecr = get_unaligned_be32(ptr + 4);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 64db8dd..8f30c18 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -488,7 +488,9 @@ static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb,
opts->mss = tcp_advertise_mss(sk);
size += TCPOLEN_MSS_ALIGNED;
- if (likely(sysctl_tcp_timestamps && *md5 == NULL)) {
+ if (likely(sysctl_tcp_timestamps &&
+ !dst_feature(dst, RTAX_FEATURE_NO_TSTAMP) &&
+ *md5 == NULL)) {
opts->options |= OPTION_TS;
opts->tsval = TCP_SKB_CB(skb)->when;
opts->tsecr = tp->rx_opt.ts_recent;
@@ -2317,7 +2319,9 @@ static void tcp_connect_init(struct sock *sk)
* See tcp_input.c:tcp_rcv_state_process case TCP_SYN_SENT.
*/
tp->tcp_header_len = sizeof(struct tcphdr) +
- (sysctl_tcp_timestamps ? TCPOLEN_TSTAMP_ALIGNED : 0);
+ (sysctl_tcp_timestamps &&
+ (!dst_feature(dst, RTAX_FEATURE_NO_TSTAMP) ?
+ TCPOLEN_TSTAMP_ALIGNED : 0));
#ifdef CONFIG_TCP_MD5SIG
if (tp->af_specific->md5_lookup(sk, sk) != NULL)
--
1.5.6.3
^ permalink raw reply related
* [PATCH RFC] Add the no SACK route option feature
From: Gilad Ben-Yossef @ 2009-10-20 15:22 UTC (permalink / raw)
To: netdev; +Cc: ori, Gilad Ben-Yossef
In-Reply-To: <1256052161-14156-4-git-send-email-gilad@codefidence.com>
Implement querying and acting upon the no sack bit in the features
field.
Signed-off-by: Gilad Ben-Yossef <gilad@codefidence.com>
Sigend-off-by: Ori Finkelman <ori@comsleep.com>
Sigend-off-by: Yony Amit <yony@comsleep.com>
---
include/linux/rtnetlink.h | 2 +-
net/ipv4/tcp_input.c | 3 ++-
net/ipv4/tcp_output.c | 4 +++-
3 files changed, 6 insertions(+), 3 deletions(-)
diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h
index adf2068..9c802a6 100644
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -377,7 +377,7 @@ enum
#define RTAX_MAX (__RTAX_MAX - 1)
#define RTAX_FEATURE_ECN 0x00000001
-#define RTAX_FEATURE_SACK 0x00000002
+#define RTAX_FEATURE_NO_SACK 0x00000002
#define RTAX_FEATURE_TIMESTAMP 0x00000004
#define RTAX_FEATURE_ALLFRAG 0x00000008
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index d502f49..b14f780 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3763,7 +3763,8 @@ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx,
break;
case TCPOPT_SACK_PERM:
if (opsize == TCPOLEN_SACK_PERM && th->syn &&
- !estab && sysctl_tcp_sack) {
+ !estab && sysctl_tcp_sack &&
+ !dst_feature(dst, RTAX_FEATURE_NO_SACK)) {
opt_rx->sack_ok = 1;
tcp_sack_reset(opt_rx);
}
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index fcd278a..64db8dd 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -464,6 +464,7 @@ static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb,
struct tcp_md5sig_key **md5) {
struct tcp_sock *tp = tcp_sk(sk);
unsigned size = 0;
+ struct dst_entry *dst = __sk_dst_get(sk);
#ifdef CONFIG_TCP_MD5SIG
*md5 = tp->af_specific->md5_lookup(sk, sk);
@@ -498,7 +499,8 @@ static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb,
opts->options |= OPTION_WSCALE;
size += TCPOLEN_WSCALE_ALIGNED;
}
- if (likely(sysctl_tcp_sack)) {
+ if (likely(sysctl_tcp_sack &&
+ !dst_feature(dst, RTAX_FEATURE_NO_SACK))) {
opts->options |= OPTION_SACK_ADVERTISE;
if (unlikely(!(OPTION_TS & opts->options)))
size += TCPOLEN_SACKPERM_ALIGNED;
--
1.5.6.3
^ permalink raw reply related
* [PATCH RFC] Only parse time stamp TCP option in time wait sock
From: Gilad Ben-Yossef @ 2009-10-20 15:22 UTC (permalink / raw)
To: netdev; +Cc: ori, Gilad Ben-Yossef, Yony Amit
In-Reply-To: <1256052161-14156-1-git-send-email-gilad@codefidence.com>
A time wait socket is established - we already know if time stamp
option is called for or not.
Signed-off-by: Gilad Ben-Yossef <gilad@codefidence.com>
Signed-off-by: Ori Finkelman <ori@comsleep.com>
Signed-off-by: Yony Amit <yony@comsleep.com>
---
net/ipv4/tcp_minisocks.c | 3 +--
1 files changed, 1 insertions(+), 2 deletions(-)
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 624c3c9..c49a550 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -100,9 +100,8 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
struct tcp_options_received tmp_opt;
int paws_reject = 0;
- tmp_opt.saw_tstamp = 0;
if (th->doff > (sizeof(*th) >> 2) && tcptw->tw_ts_recent_stamp) {
- tcp_parse_options(skb, &tmp_opt, 0);
+ tcp_parse_options(skb, &tmp_opt, 1);
if (tmp_opt.saw_tstamp) {
tmp_opt.ts_recent = tcptw->tw_ts_recent;
--
1.5.6.3
^ permalink raw reply related
* [PATCH RFC] Document future removal of sysctl_tcp_* options
From: Gilad Ben-Yossef @ 2009-10-20 15:22 UTC (permalink / raw)
To: netdev; +Cc: ori, Gilad Ben-Yossef
In-Reply-To: <1256052161-14156-8-git-send-email-gilad@codefidence.com>
No need for global kill switches if we have per route entry controls.
Wait a year before removing in case someone is using this.
Signed-off-by: Gilad Ben-Yossef <gilad@codefidence.com>
---
Documentation/feature-removal-schedule.txt | 12 ++++++++++++
1 files changed, 12 insertions(+), 0 deletions(-)
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index 89a47b5..60db855 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -6,6 +6,18 @@ be removed from this file.
---------------------------
+What: sysctl_tcp_sack, sysctl_tcp_timestamps, sysctl_tcp_window_scaling,
+ sysctl_tcp_dsack
+When: October 2010
+
+Why: These options can now be set on a per route basis via the
+ RTAX_FEATURE_NO_SACK, RTAX_FEATURE_NO_TSTAMP, RTAX_FEATURE_NO_WSCALE,
+ and RTAX_FEATURE_NO_DSACK route feature options.
+
+Who: Gilad Ben-Yossef <gilad@codefidence.com>
+
+---------------------------
+
What: PRISM54
When: 2.6.34
--
1.5.6.3
^ permalink raw reply related
* [PATCH RFC] Allow disabling of DSACK TCP option per route
From: Gilad Ben-Yossef @ 2009-10-20 15:22 UTC (permalink / raw)
To: netdev; +Cc: ori, Gilad Ben-Yossef
In-Reply-To: <1256052161-14156-7-git-send-email-gilad@codefidence.com>
Add and use no DSCAK bit in the features field.
Signed-off-by: Gilad Ben-Yossef <gilad@codefidence.com>
Sigend-off-by: Ori Finkelman <ori@comsleep.com>
Sigend-off-by: Yony Amit <yony@comsleep.com>
---
include/linux/rtnetlink.h | 1 +
net/ipv4/tcp_input.c | 8 ++++++--
2 files changed, 7 insertions(+), 2 deletions(-)
diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h
index 6784b34..e78b60c 100644
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -381,6 +381,7 @@ enum
#define RTAX_FEATURE_NO_TSTAMP 0x00000004
#define RTAX_FEATURE_ALLFRAG 0x00000008
#define RTAX_FEATURE_NO_WSCALE 0x00000010
+#define RTAX_FEATURE_NO_DSACK 0x00000020
struct rta_session
{
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 4f5e914..4262da5 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4080,8 +4080,10 @@ static inline int tcp_sack_extend(struct tcp_sack_block *sp, u32 seq,
static void tcp_dsack_set(struct sock *sk, u32 seq, u32 end_seq)
{
struct tcp_sock *tp = tcp_sk(sk);
+ struct dst_entry *dst = __sk_dst_get(sk);
- if (tcp_is_sack(tp) && sysctl_tcp_dsack) {
+ if (tcp_is_sack(tp) && sysctl_tcp_dsack &&
+ !dst_feature(dst, RTAX_FEATURE_NO_DSACK)) {
int mib_idx;
if (before(seq, tp->rcv_nxt))
@@ -4110,13 +4112,15 @@ static void tcp_dsack_extend(struct sock *sk, u32 seq, u32 end_seq)
static void tcp_send_dupack(struct sock *sk, struct sk_buff *skb)
{
struct tcp_sock *tp = tcp_sk(sk);
+ struct dst_entry *dst = __sk_dst_get(sk);
if (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq &&
before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) {
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_DELAYEDACKLOST);
tcp_enter_quickack_mode(sk);
- if (tcp_is_sack(tp) && sysctl_tcp_dsack) {
+ if (tcp_is_sack(tp) && sysctl_tcp_dsack &&
+ !dst_feature(dst, RTAX_FEATURE_NO_DSACK)) {
u32 end_seq = TCP_SKB_CB(skb)->end_seq;
if (after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt))
--
1.5.6.3
^ permalink raw reply related
* [PATCH RFC] Allow tcp_parse_options to consult dst entry
From: Gilad Ben-Yossef @ 2009-10-20 15:22 UTC (permalink / raw)
To: netdev; +Cc: ori, Gilad Ben-Yossef
In-Reply-To: <1256052161-14156-2-git-send-email-gilad@codefidence.com>
We need tcp_parse_options to be aware of dst_entry to
take into account per dst_entry TCP options settings
Signed-off-by: Gilad Ben-Yossef <gilad@codefidence.com>
Sigend-off-by: Ori Finkelman <ori@comsleep.com>
Sigend-off-by: Yony Amit <yony@comsleep.com>
---
include/net/tcp.h | 3 ++-
net/ipv4/syncookies.c | 27 ++++++++++++++-------------
net/ipv4/tcp_input.c | 9 ++++++---
net/ipv4/tcp_ipv4.c | 19 ++++++++++---------
net/ipv4/tcp_minisocks.c | 7 +++++--
net/ipv6/syncookies.c | 28 +++++++++++++++-------------
net/ipv6/tcp_ipv6.c | 3 ++-
7 files changed, 54 insertions(+), 42 deletions(-)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 03a49c7..740d09b 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -409,7 +409,8 @@ extern int tcp_recvmsg(struct kiocb *iocb, struct sock *sk,
extern void tcp_parse_options(struct sk_buff *skb,
struct tcp_options_received *opt_rx,
- int estab);
+ int estab,
+ struct dst_entry *dst);
extern u8 *tcp_parse_md5sig_option(struct tcphdr *th);
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index a6e0e07..4990dd4 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -276,13 +276,6 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SYNCOOKIESRECV);
- /* check for timestamp cookie support */
- memset(&tcp_opt, 0, sizeof(tcp_opt));
- tcp_parse_options(skb, &tcp_opt, 0);
-
- if (tcp_opt.saw_tstamp)
- cookie_check_timestamp(&tcp_opt);
-
ret = NULL;
req = inet_reqsk_alloc(&tcp_request_sock_ops); /* for safety */
if (!req)
@@ -298,12 +291,6 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
ireq->loc_addr = ip_hdr(skb)->daddr;
ireq->rmt_addr = ip_hdr(skb)->saddr;
ireq->ecn_ok = 0;
- ireq->snd_wscale = tcp_opt.snd_wscale;
- ireq->rcv_wscale = tcp_opt.rcv_wscale;
- ireq->sack_ok = tcp_opt.sack_ok;
- ireq->wscale_ok = tcp_opt.wscale_ok;
- ireq->tstamp_ok = tcp_opt.saw_tstamp;
- req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0;
/* We throwed the options of the initial SYN away, so we hope
* the ACK carries the same options again (see RFC1122 4.2.3.8)
@@ -351,6 +338,20 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
}
}
+ /* check for timestamp cookie support */
+ memset(&tcp_opt, 0, sizeof(tcp_opt));
+ tcp_parse_options(skb, &tcp_opt, 0, &rt->u.dst);
+
+ if (tcp_opt.saw_tstamp)
+ cookie_check_timestamp(&tcp_opt);
+
+ ireq->snd_wscale = tcp_opt.snd_wscale;
+ ireq->rcv_wscale = tcp_opt.rcv_wscale;
+ ireq->sack_ok = tcp_opt.sack_ok;
+ ireq->wscale_ok = tcp_opt.wscale_ok;
+ ireq->tstamp_ok = tcp_opt.saw_tstamp;
+ req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0;
+
/* Try to redo what tcp_v4_send_synack did. */
req->window_clamp = tp->window_clamp ? :dst_metric(&rt->u.dst, RTAX_WINDOW);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index d86784b..d502f49 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3698,12 +3698,14 @@ old_ack:
* the fast version below fails.
*/
void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx,
- int estab)
+ int estab, struct dst_entry *dst)
{
unsigned char *ptr;
struct tcphdr *th = tcp_hdr(skb);
int length = (th->doff * 4) - sizeof(struct tcphdr);
+ BUG_ON(!estab && !dst);
+
ptr = (unsigned char *)(th + 1);
opt_rx->saw_tstamp = 0;
@@ -3820,7 +3822,7 @@ static int tcp_fast_parse_options(struct sk_buff *skb, struct tcphdr *th,
if (tcp_parse_aligned_timestamp(tp, th))
return 1;
}
- tcp_parse_options(skb, &tp->rx_opt, 1);
+ tcp_parse_options(skb, &tp->rx_opt, 1, NULL);
return 1;
}
@@ -5364,8 +5366,9 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
struct tcp_sock *tp = tcp_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
int saved_clamp = tp->rx_opt.mss_clamp;
+ struct dst_entry *dst = __sk_dst_get(sk);
- tcp_parse_options(skb, &tp->rx_opt, 0);
+ tcp_parse_options(skb, &tp->rx_opt, 0, dst);
if (th->ack) {
/* rfc793:
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 7cda24b..1cb0ec4 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1256,11 +1256,18 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
tcp_rsk(req)->af_specific = &tcp_request_sock_ipv4_ops;
#endif
+ ireq = inet_rsk(req);
+ ireq->loc_addr = daddr;
+ ireq->rmt_addr = saddr;
+ ireq->no_srccheck = inet_sk(sk)->transparent;
+ ireq->opt = tcp_v4_save_options(sk, skb);
+
+ dst = inet_csk_route_req(sk, req);
tcp_clear_options(&tmp_opt);
tmp_opt.mss_clamp = 536;
tmp_opt.user_mss = tcp_sk(sk)->rx_opt.user_mss;
- tcp_parse_options(skb, &tmp_opt, 0);
+ tcp_parse_options(skb, &tmp_opt, 0, dst);
if (want_cookie && !tmp_opt.saw_tstamp)
tcp_clear_options(&tmp_opt);
@@ -1269,14 +1276,8 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
tcp_openreq_init(req, &tmp_opt, skb);
- ireq = inet_rsk(req);
- ireq->loc_addr = daddr;
- ireq->rmt_addr = saddr;
- ireq->no_srccheck = inet_sk(sk)->transparent;
- ireq->opt = tcp_v4_save_options(sk, skb);
-
if (security_inet_conn_request(sk, skb, req))
- goto drop_and_free;
+ goto drop_and_release;
if (!want_cookie)
TCP_ECN_create_request(req, tcp_hdr(skb));
@@ -1301,7 +1302,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
*/
if (tmp_opt.saw_tstamp &&
tcp_death_row.sysctl_tw_recycle &&
- (dst = inet_csk_route_req(sk, req)) != NULL &&
+ dst != NULL &&
(peer = rt_get_peer((struct rtable *)dst)) != NULL &&
peer->v4daddr == saddr) {
if (get_seconds() < peer->tcp_ts_stamp + TCP_PAWS_MSL &&
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index c49a550..70ff955 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -101,7 +101,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
int paws_reject = 0;
if (th->doff > (sizeof(*th) >> 2) && tcptw->tw_ts_recent_stamp) {
- tcp_parse_options(skb, &tmp_opt, 1);
+ tcp_parse_options(skb, &tmp_opt, 1, NULL);
if (tmp_opt.saw_tstamp) {
tmp_opt.ts_recent = tcptw->tw_ts_recent;
@@ -499,10 +499,11 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
int paws_reject = 0;
struct tcp_options_received tmp_opt;
struct sock *child;
+ struct dst_entry *dst = inet_csk_route_req(sk, req);
tmp_opt.saw_tstamp = 0;
if (th->doff > (sizeof(struct tcphdr)>>2)) {
- tcp_parse_options(skb, &tmp_opt, 0);
+ tcp_parse_options(skb, &tmp_opt, 0, dst);
if (tmp_opt.saw_tstamp) {
tmp_opt.ts_recent = req->ts_recent;
@@ -515,6 +516,8 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
}
}
+ dst_release(dst);
+
/* Check for pure retransmitted SYN. */
if (TCP_SKB_CB(skb)->seq == tcp_rsk(req)->rcv_isn &&
flg == TCP_FLAG_SYN &&
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 6b6ae91..6ece408 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -184,13 +184,6 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SYNCOOKIESRECV);
- /* check for timestamp cookie support */
- memset(&tcp_opt, 0, sizeof(tcp_opt));
- tcp_parse_options(skb, &tcp_opt, 0);
-
- if (tcp_opt.saw_tstamp)
- cookie_check_timestamp(&tcp_opt);
-
ret = NULL;
req = inet6_reqsk_alloc(&tcp6_request_sock_ops);
if (!req)
@@ -224,12 +217,6 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
req->expires = 0UL;
req->retrans = 0;
ireq->ecn_ok = 0;
- ireq->snd_wscale = tcp_opt.snd_wscale;
- ireq->rcv_wscale = tcp_opt.rcv_wscale;
- ireq->sack_ok = tcp_opt.sack_ok;
- ireq->wscale_ok = tcp_opt.wscale_ok;
- ireq->tstamp_ok = tcp_opt.saw_tstamp;
- req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0;
treq->rcv_isn = ntohl(th->seq) - 1;
treq->snt_isn = cookie;
@@ -264,6 +251,21 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
goto out_free;
}
+ /* check for timestamp cookie support */
+ memset(&tcp_opt, 0, sizeof(tcp_opt));
+ tcp_parse_options(skb, &tcp_opt, 0, dst);
+
+ if (tcp_opt.saw_tstamp)
+ cookie_check_timestamp(&tcp_opt);
+
+ req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0;
+
+ ireq->snd_wscale = tcp_opt.snd_wscale;
+ ireq->rcv_wscale = tcp_opt.rcv_wscale;
+ ireq->sack_ok = tcp_opt.sack_ok;
+ ireq->wscale_ok = tcp_opt.wscale_ok;
+ ireq->tstamp_ok = tcp_opt.saw_tstamp;
+
req->window_clamp = tp->window_clamp ? :dst_metric(dst, RTAX_WINDOW);
tcp_select_initial_window(tcp_full_space(sk), req->mss,
&req->rcv_wnd, &req->window_clamp,
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 21d100b..2eebab5 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1165,6 +1165,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
struct tcp_sock *tp = tcp_sk(sk);
struct request_sock *req = NULL;
__u32 isn = TCP_SKB_CB(skb)->when;
+ struct dst_entry *dst = __sk_dst_get(sk);
#ifdef CONFIG_SYN_COOKIES
int want_cookie = 0;
#else
@@ -1203,7 +1204,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
tmp_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr);
tmp_opt.user_mss = tp->rx_opt.user_mss;
- tcp_parse_options(skb, &tmp_opt, 0);
+ tcp_parse_options(skb, &tmp_opt, 0, dst);
if (want_cookie && !tmp_opt.saw_tstamp)
tcp_clear_options(&tmp_opt);
--
1.5.6.3
^ permalink raw reply related
* [PATCH RFC] Per route TCP options
From: Gilad Ben-Yossef @ 2009-10-20 15:22 UTC (permalink / raw)
To: netdev; +Cc: ori, Gilad Ben-Yossef
Turn the global sysctls allowing disabling of TCP SACK, DSCAK,
time stamp and window scale into per route entry feature options,
laying the ground to future removal of the relevant global sysctls.
You really only want to disable SACK, DSACK, time stamp or window
scale if you've got a piece of broken networking equipment somewhere
as a stop gap until you can bring a big enough hammer to deal with
the broken network equipment. It doesn't make sense to "punish" the
entire connections going through the machine to destinations not
related to the broken equipment.
This is doubly true when you're dealing with network containers
used to isolate several virtual domains.
Per route options implemented in free bits in the features route
entry property, which in some cases were reserved by name for these
options, so this does not inflate any structure and I expect that
when the apropriate global sysctls will be removed the overall code
base will be smaller.
Tested on x86 using Qemu/KVM.
Will send the matching patch to iproute2 if/when this is ACKed or
if someone wants to test this.
Patchset based on original work by Ori Finkelman and Yoni Amit
from ComSleep Ltd.
Gilad Ben-Yossef (8):
Only parse time stamp TCP option in time wait sock
Allow tcp_parse_options to consult dst entry
Infrastructure for querying route entry features
Add the no SACK route option feature
Allow disabling TCP timestamp options per route
Allow to turn off TCP window scale opt per route
Allow disabling of DSACK TCP option per route
Document future removal of sysctl_tcp_* options
Documentation/feature-removal-schedule.txt | 12 ++++++++++++
include/linux/rtnetlink.h | 6 ++++--
include/net/dst.h | 8 +++++++-
include/net/tcp.h | 3 ++-
net/ipv4/syncookies.c | 27 ++++++++++++++-------------
net/ipv4/tcp_input.c | 26 ++++++++++++++++++--------
net/ipv4/tcp_ipv4.c | 19 ++++++++++---------
net/ipv4/tcp_minisocks.c | 8 +++++---
net/ipv4/tcp_output.c | 18 +++++++++++++-----
net/ipv6/syncookies.c | 28 +++++++++++++++-------------
net/ipv6/tcp_ipv6.c | 3 ++-
11 files changed, 102 insertions(+), 56 deletions(-)
^ permalink raw reply
* Re: kernel panic in latest vanilla stable, while using nameif with "alive" pppoe interfaces
From: Cyrill Gorcunov @ 2009-10-20 14:23 UTC (permalink / raw)
To: Denys Fedoryschenko
Cc: Michal Ostrowski, Eric Dumazet, netdev, linux-ppp, paulus,
mostrows
In-Reply-To: <200910201720.00473.denys@visp.net.lb>
[Denys Fedoryschenko - Tue, Oct 20, 2009 at 05:20:00PM +0300]
|
| It panics almost immediately on boot(even on old operations that was stable,
| seems on first pppoe customer login attempt), i will rebuild kernel and if
| interesting will try to get panic message.
|
...
ok, thanks. I continue digging.
^ permalink raw reply
* Re: kernel panic in latest vanilla stable, while using nameif with "alive" pppoe interfaces
From: Denys Fedoryschenko @ 2009-10-20 14:20 UTC (permalink / raw)
To: Cyrill Gorcunov
Cc: Michal Ostrowski, Eric Dumazet, netdev, linux-ppp, paulus,
mostrows
In-Reply-To: <20091020135920.GB5181@lenovo>
It panics almost immediately on boot(even on old operations that was stable,
seems on first pppoe customer login attempt), i will rebuild kernel and if
interesting will try to get panic message.
On Tuesday 20 October 2009 16:59:20 Cyrill Gorcunov wrote:
> [Denys Fedoryschenko - Tue, Oct 20, 2009 at 04:50:09PM +0300]
>
> ...
>
> | > Thanks Denys, I'm preparing new patch (just back from office
> | > and had no inet connection that is why reply is delayed, sorry).
> |
> | There is no problem at all.
> | This rename operation is just future operation and host is redundant, so
> | i can do tests on it anytime.
>
> ok, here is it, please try (it's still a draft version though)
>
> -- Cyrill
> ---
> drivers/net/pppoe.c | 106
> +++++++++++++++++++++++++++++++++++++++------------- 1 file changed, 81
> insertions(+), 25 deletions(-)
>
> Index: linux-2.6.git/drivers/net/pppoe.c
> =====================================================================
> --- linux-2.6.git.orig/drivers/net/pppoe.c
> +++ linux-2.6.git/drivers/net/pppoe.c
> @@ -313,8 +313,8 @@ static void pppoe_flush_dev(struct net_d
> sk = sk_pppox(po);
> spin_lock(&flush_lock);
> po->pppoe_dev = NULL;
> - spin_unlock(&flush_lock);
> dev_put(dev);
> + spin_unlock(&flush_lock);
>
> /* We always grab the socket lock, followed by the
> * hash_lock, in that order. Since we should
> @@ -386,13 +386,21 @@ static struct notifier_block pppoe_notif
> static int pppoe_rcv_core(struct sock *sk, struct sk_buff *skb)
> {
> struct pppox_sock *po = pppox_sk(sk);
> - struct pppox_sock *relay_po;
> + struct pppox_sock *relay_po = NULL;
> + struct net_device *dev = NULL;
>
> if (sk->sk_state & PPPOX_BOUND) {
> ppp_input(&po->chan, skb);
> } else if (sk->sk_state & PPPOX_RELAY) {
> - relay_po = get_item_by_addr(dev_net(po->pppoe_dev),
> - &po->pppoe_relay);
> + struct pppoe_net *pn = pppoe_pernet(sock_net(sk));
> + read_lock_bh(&pn->hash_lock);
> + dev = po->pppoe_dev;
> + if (dev) {
> + dev_hold(dev);
> + relay_po = get_item_by_addr(dev_net(dev),
> + &po->pppoe_relay);
> + }
> + read_unlock_bh(&pn->hash_lock);
> if (relay_po == NULL)
> goto abort_kfree;
>
> @@ -401,6 +409,7 @@ static int pppoe_rcv_core(struct sock *s
>
> if (!__pppoe_xmit(sk_pppox(relay_po), skb))
> goto abort_put;
> + dev_put(dev);
> } else {
> if (sock_queue_rcv_skb(sk, skb))
> goto abort_kfree;
> @@ -412,6 +421,8 @@ abort_put:
> sock_put(sk_pppox(relay_po));
>
> abort_kfree:
> + if (dev)
> + dev_put(dev);
> kfree_skb(skb);
> return NET_RX_DROP;
> }
> @@ -625,8 +636,8 @@ static int pppoe_connect(struct socket *
> struct sock *sk = sock->sk;
> struct sockaddr_pppox *sp = (struct sockaddr_pppox *)uservaddr;
> struct pppox_sock *po = pppox_sk(sk);
> - struct net_device *dev;
> - struct pppoe_net *pn;
> + struct net_device *dev = NULL;
> + struct pppoe_net *pn = NULL;
> int error;
>
> lock_sock(sk);
> @@ -652,12 +663,15 @@ static int pppoe_connect(struct socket *
> /* Delete the old binding */
> if (stage_session(po->pppoe_pa.sid)) {
> pppox_unbind_sock(sk);
> + spin_lock(&flush_lock);
> if (po->pppoe_dev) {
> pn = pppoe_pernet(dev_net(po->pppoe_dev));
> delete_item(pn, po->pppoe_pa.sid,
> po->pppoe_pa.remote, po->pppoe_ifindex);
> dev_put(po->pppoe_dev);
> + po->pppoe_dev = NULL;
> }
> + spin_unlock(&flush_lock);
> memset(sk_pppox(po) + 1, 0,
> sizeof(struct pppox_sock) - sizeof(struct sock));
> sk->sk_state = PPPOX_NONE;
> @@ -670,10 +684,11 @@ static int pppoe_connect(struct socket *
> if (!dev)
> goto end;
>
> + write_lock_bh(&pn->hash_lock);
> + dev_hold(dev);
> po->pppoe_dev = dev;
> po->pppoe_ifindex = dev->ifindex;
> pn = pppoe_pernet(dev_net(dev));
> - write_lock_bh(&pn->hash_lock);
> if (!(dev->flags & IFF_UP)) {
> write_unlock_bh(&pn->hash_lock);
> goto err_put;
> @@ -700,6 +715,7 @@ static int pppoe_connect(struct socket *
> goto err_put;
>
> sk->sk_state = PPPOX_CONNECTED;
> + dev_put(dev);
> }
>
> po->num = sp->sa_addr.pppoe.sid;
> @@ -708,10 +724,13 @@ end:
> release_sock(sk);
> return error;
> err_put:
> + dev_put(dev);
> + write_lock_bh(&pn->hash_lock);
> if (po->pppoe_dev) {
> dev_put(po->pppoe_dev);
> po->pppoe_dev = NULL;
> }
> + write_unlock_bh(&pn->hash_lock);
> goto end;
> }
>
> @@ -738,6 +757,8 @@ static int pppoe_ioctl(struct socket *so
> {
> struct sock *sk = sock->sk;
> struct pppox_sock *po = pppox_sk(sk);
> + struct pppoe_net *pn = pppoe_pernet(sock_net(sk));
> + unsigned int mtu = 0;
> int val;
> int err;
>
> @@ -746,11 +767,17 @@ static int pppoe_ioctl(struct socket *so
> err = -ENXIO;
> if (!(sk->sk_state & PPPOX_CONNECTED))
> break;
> -
> + read_lock_bh(&pn->hash_lock);
> + err = -ENODEV;
> + if (po->pppoe_dev) {
> + mtu = po->pppoe_dev->mtu;
> + err = 0;
> + }
> + read_unlock_bh(&pn->hash_lock);
> + if (err)
> + break;
> err = -EFAULT;
> - if (put_user(po->pppoe_dev->mtu -
> - sizeof(struct pppoe_hdr) -
> - PPP_HDRLEN,
> + if (put_user(mtu - sizeof(struct pppoe_hdr) - PPP_HDRLEN,
> (int __user *)arg))
> break;
> err = 0;
> @@ -761,13 +788,21 @@ static int pppoe_ioctl(struct socket *so
> if (!(sk->sk_state & PPPOX_CONNECTED))
> break;
>
> + read_lock_bh(&pn->hash_lock);
> + err = -ENODEV;
> + if (po->pppoe_dev) {
> + mtu = po->pppoe_dev->mtu;
> + err = 0;
> + }
> + read_unlock_bh(&pn->hash_lock);
> + if (err)
> + break;
> +
> err = -EFAULT;
> if (get_user(val, (int __user *)arg))
> break;
>
> - if (val < (po->pppoe_dev->mtu
> - - sizeof(struct pppoe_hdr)
> - - PPP_HDRLEN))
> + if (val < (mtu - sizeof(struct pppoe_hdr) - PPP_HDRLEN))
> err = 0;
> else
> err = -EINVAL;
> @@ -839,10 +874,11 @@ static int pppoe_sendmsg(struct kiocb *i
> struct sk_buff *skb;
> struct sock *sk = sock->sk;
> struct pppox_sock *po = pppox_sk(sk);
> + struct pppoe_net *pn = pppoe_pernet(sock_net(sk));
> int error;
> struct pppoe_hdr hdr;
> struct pppoe_hdr *ph;
> - struct net_device *dev;
> + struct net_device *dev = NULL;
> char *start;
>
> lock_sock(sk);
> @@ -856,18 +892,27 @@ static int pppoe_sendmsg(struct kiocb *i
> hdr.code = 0;
> hdr.sid = po->num;
>
> - dev = po->pppoe_dev;
> + read_lock_bh(&pn->hash_lock);
> + error = -ENODEV;
> + if (po->pppoe_dev) {
> + dev = po->pppoe_dev;
> + dev_hold(dev);
> + error = 0;
> + }
> + read_unlock_bh(&pn->hash_lock);
> + if (error)
> + goto end;
>
> error = -EMSGSIZE;
> if (total_len > (dev->mtu + dev->hard_header_len))
> - goto end;
> + goto end_put;
>
>
> skb = sock_wmalloc(sk, total_len + dev->hard_header_len + 32,
> 0, GFP_KERNEL);
> if (!skb) {
> error = -ENOMEM;
> - goto end;
> + goto end_put;
> }
>
> /* Reserve space for headers. */
> @@ -885,7 +930,7 @@ static int pppoe_sendmsg(struct kiocb *i
> error = memcpy_fromiovec(start, m->msg_iov, total_len);
> if (error < 0) {
> kfree_skb(skb);
> - goto end;
> + goto end_put;
> }
>
> error = total_len;
> @@ -898,6 +943,8 @@ static int pppoe_sendmsg(struct kiocb *i
>
> dev_queue_xmit(skb);
>
> +end_put:
> + dev_put(dev);
> end:
> release_sock(sk);
> return error;
> @@ -911,21 +958,28 @@ end:
> static int __pppoe_xmit(struct sock *sk, struct sk_buff *skb)
> {
> struct pppox_sock *po = pppox_sk(sk);
> - struct net_device *dev = po->pppoe_dev;
> + struct pppoe_net *pn = pppoe_pernet(sock_net(sk));
> + struct net_device *dev;
> struct pppoe_hdr *ph;
> int data_len = skb->len;
>
> - if (sock_flag(sk, SOCK_DEAD) || !(sk->sk_state & PPPOX_CONNECTED))
> + read_lock_bh(&pn->hash_lock);
> + if (!po->pppoe_dev) {
> + read_unlock_bh(&pn->hash_lock);
> goto abort;
> + }
> + dev = po->pppoe_dev;
> + dev_hold(dev);
> + read_unlock_bh(&pn->hash_lock);
>
> - if (!dev)
> - goto abort;
> + if (sock_flag(sk, SOCK_DEAD) || !(sk->sk_state & PPPOX_CONNECTED))
> + goto abort_put;
>
> /* Copy the data if there is no space for the header or if it's
> * read-only.
> */
> if (skb_cow_head(skb, sizeof(*ph) + dev->hard_header_len))
> - goto abort;
> + goto abort_put;
>
> __skb_push(skb, sizeof(*ph));
> skb_reset_network_header(skb);
> @@ -944,9 +998,11 @@ static int __pppoe_xmit(struct sock *sk,
> po->pppoe_pa.remote, NULL, data_len);
>
> dev_queue_xmit(skb);
> -
> + dev_put(dev);
> return 1;
>
> +abort_put:
> + dev_put(dev);
> abort:
> kfree_skb(skb);
> return 1;
^ permalink raw reply
* Re: kernel panic in latest vanilla stable, while using nameif with "alive" pppoe interfaces
From: Cyrill Gorcunov @ 2009-10-20 13:59 UTC (permalink / raw)
To: Denys Fedoryschenko
Cc: Michal Ostrowski, Eric Dumazet, netdev, linux-ppp, paulus,
mostrows
In-Reply-To: <200910201650.10066.denys@visp.net.lb>
[Denys Fedoryschenko - Tue, Oct 20, 2009 at 04:50:09PM +0300]
|
...
| >
| > Thanks Denys, I'm preparing new patch (just back from office
| > and had no inet connection that is why reply is delayed, sorry).
| There is no problem at all.
| This rename operation is just future operation and host is redundant, so i can
| do tests on it anytime.
|
ok, here is it, please try (it's still a draft version though)
-- Cyrill
---
drivers/net/pppoe.c | 106 +++++++++++++++++++++++++++++++++++++++-------------
1 file changed, 81 insertions(+), 25 deletions(-)
Index: linux-2.6.git/drivers/net/pppoe.c
=====================================================================
--- linux-2.6.git.orig/drivers/net/pppoe.c
+++ linux-2.6.git/drivers/net/pppoe.c
@@ -313,8 +313,8 @@ static void pppoe_flush_dev(struct net_d
sk = sk_pppox(po);
spin_lock(&flush_lock);
po->pppoe_dev = NULL;
- spin_unlock(&flush_lock);
dev_put(dev);
+ spin_unlock(&flush_lock);
/* We always grab the socket lock, followed by the
* hash_lock, in that order. Since we should
@@ -386,13 +386,21 @@ static struct notifier_block pppoe_notif
static int pppoe_rcv_core(struct sock *sk, struct sk_buff *skb)
{
struct pppox_sock *po = pppox_sk(sk);
- struct pppox_sock *relay_po;
+ struct pppox_sock *relay_po = NULL;
+ struct net_device *dev = NULL;
if (sk->sk_state & PPPOX_BOUND) {
ppp_input(&po->chan, skb);
} else if (sk->sk_state & PPPOX_RELAY) {
- relay_po = get_item_by_addr(dev_net(po->pppoe_dev),
- &po->pppoe_relay);
+ struct pppoe_net *pn = pppoe_pernet(sock_net(sk));
+ read_lock_bh(&pn->hash_lock);
+ dev = po->pppoe_dev;
+ if (dev) {
+ dev_hold(dev);
+ relay_po = get_item_by_addr(dev_net(dev),
+ &po->pppoe_relay);
+ }
+ read_unlock_bh(&pn->hash_lock);
if (relay_po == NULL)
goto abort_kfree;
@@ -401,6 +409,7 @@ static int pppoe_rcv_core(struct sock *s
if (!__pppoe_xmit(sk_pppox(relay_po), skb))
goto abort_put;
+ dev_put(dev);
} else {
if (sock_queue_rcv_skb(sk, skb))
goto abort_kfree;
@@ -412,6 +421,8 @@ abort_put:
sock_put(sk_pppox(relay_po));
abort_kfree:
+ if (dev)
+ dev_put(dev);
kfree_skb(skb);
return NET_RX_DROP;
}
@@ -625,8 +636,8 @@ static int pppoe_connect(struct socket *
struct sock *sk = sock->sk;
struct sockaddr_pppox *sp = (struct sockaddr_pppox *)uservaddr;
struct pppox_sock *po = pppox_sk(sk);
- struct net_device *dev;
- struct pppoe_net *pn;
+ struct net_device *dev = NULL;
+ struct pppoe_net *pn = NULL;
int error;
lock_sock(sk);
@@ -652,12 +663,15 @@ static int pppoe_connect(struct socket *
/* Delete the old binding */
if (stage_session(po->pppoe_pa.sid)) {
pppox_unbind_sock(sk);
+ spin_lock(&flush_lock);
if (po->pppoe_dev) {
pn = pppoe_pernet(dev_net(po->pppoe_dev));
delete_item(pn, po->pppoe_pa.sid,
po->pppoe_pa.remote, po->pppoe_ifindex);
dev_put(po->pppoe_dev);
+ po->pppoe_dev = NULL;
}
+ spin_unlock(&flush_lock);
memset(sk_pppox(po) + 1, 0,
sizeof(struct pppox_sock) - sizeof(struct sock));
sk->sk_state = PPPOX_NONE;
@@ -670,10 +684,11 @@ static int pppoe_connect(struct socket *
if (!dev)
goto end;
+ write_lock_bh(&pn->hash_lock);
+ dev_hold(dev);
po->pppoe_dev = dev;
po->pppoe_ifindex = dev->ifindex;
pn = pppoe_pernet(dev_net(dev));
- write_lock_bh(&pn->hash_lock);
if (!(dev->flags & IFF_UP)) {
write_unlock_bh(&pn->hash_lock);
goto err_put;
@@ -700,6 +715,7 @@ static int pppoe_connect(struct socket *
goto err_put;
sk->sk_state = PPPOX_CONNECTED;
+ dev_put(dev);
}
po->num = sp->sa_addr.pppoe.sid;
@@ -708,10 +724,13 @@ end:
release_sock(sk);
return error;
err_put:
+ dev_put(dev);
+ write_lock_bh(&pn->hash_lock);
if (po->pppoe_dev) {
dev_put(po->pppoe_dev);
po->pppoe_dev = NULL;
}
+ write_unlock_bh(&pn->hash_lock);
goto end;
}
@@ -738,6 +757,8 @@ static int pppoe_ioctl(struct socket *so
{
struct sock *sk = sock->sk;
struct pppox_sock *po = pppox_sk(sk);
+ struct pppoe_net *pn = pppoe_pernet(sock_net(sk));
+ unsigned int mtu = 0;
int val;
int err;
@@ -746,11 +767,17 @@ static int pppoe_ioctl(struct socket *so
err = -ENXIO;
if (!(sk->sk_state & PPPOX_CONNECTED))
break;
-
+ read_lock_bh(&pn->hash_lock);
+ err = -ENODEV;
+ if (po->pppoe_dev) {
+ mtu = po->pppoe_dev->mtu;
+ err = 0;
+ }
+ read_unlock_bh(&pn->hash_lock);
+ if (err)
+ break;
err = -EFAULT;
- if (put_user(po->pppoe_dev->mtu -
- sizeof(struct pppoe_hdr) -
- PPP_HDRLEN,
+ if (put_user(mtu - sizeof(struct pppoe_hdr) - PPP_HDRLEN,
(int __user *)arg))
break;
err = 0;
@@ -761,13 +788,21 @@ static int pppoe_ioctl(struct socket *so
if (!(sk->sk_state & PPPOX_CONNECTED))
break;
+ read_lock_bh(&pn->hash_lock);
+ err = -ENODEV;
+ if (po->pppoe_dev) {
+ mtu = po->pppoe_dev->mtu;
+ err = 0;
+ }
+ read_unlock_bh(&pn->hash_lock);
+ if (err)
+ break;
+
err = -EFAULT;
if (get_user(val, (int __user *)arg))
break;
- if (val < (po->pppoe_dev->mtu
- - sizeof(struct pppoe_hdr)
- - PPP_HDRLEN))
+ if (val < (mtu - sizeof(struct pppoe_hdr) - PPP_HDRLEN))
err = 0;
else
err = -EINVAL;
@@ -839,10 +874,11 @@ static int pppoe_sendmsg(struct kiocb *i
struct sk_buff *skb;
struct sock *sk = sock->sk;
struct pppox_sock *po = pppox_sk(sk);
+ struct pppoe_net *pn = pppoe_pernet(sock_net(sk));
int error;
struct pppoe_hdr hdr;
struct pppoe_hdr *ph;
- struct net_device *dev;
+ struct net_device *dev = NULL;
char *start;
lock_sock(sk);
@@ -856,18 +892,27 @@ static int pppoe_sendmsg(struct kiocb *i
hdr.code = 0;
hdr.sid = po->num;
- dev = po->pppoe_dev;
+ read_lock_bh(&pn->hash_lock);
+ error = -ENODEV;
+ if (po->pppoe_dev) {
+ dev = po->pppoe_dev;
+ dev_hold(dev);
+ error = 0;
+ }
+ read_unlock_bh(&pn->hash_lock);
+ if (error)
+ goto end;
error = -EMSGSIZE;
if (total_len > (dev->mtu + dev->hard_header_len))
- goto end;
+ goto end_put;
skb = sock_wmalloc(sk, total_len + dev->hard_header_len + 32,
0, GFP_KERNEL);
if (!skb) {
error = -ENOMEM;
- goto end;
+ goto end_put;
}
/* Reserve space for headers. */
@@ -885,7 +930,7 @@ static int pppoe_sendmsg(struct kiocb *i
error = memcpy_fromiovec(start, m->msg_iov, total_len);
if (error < 0) {
kfree_skb(skb);
- goto end;
+ goto end_put;
}
error = total_len;
@@ -898,6 +943,8 @@ static int pppoe_sendmsg(struct kiocb *i
dev_queue_xmit(skb);
+end_put:
+ dev_put(dev);
end:
release_sock(sk);
return error;
@@ -911,21 +958,28 @@ end:
static int __pppoe_xmit(struct sock *sk, struct sk_buff *skb)
{
struct pppox_sock *po = pppox_sk(sk);
- struct net_device *dev = po->pppoe_dev;
+ struct pppoe_net *pn = pppoe_pernet(sock_net(sk));
+ struct net_device *dev;
struct pppoe_hdr *ph;
int data_len = skb->len;
- if (sock_flag(sk, SOCK_DEAD) || !(sk->sk_state & PPPOX_CONNECTED))
+ read_lock_bh(&pn->hash_lock);
+ if (!po->pppoe_dev) {
+ read_unlock_bh(&pn->hash_lock);
goto abort;
+ }
+ dev = po->pppoe_dev;
+ dev_hold(dev);
+ read_unlock_bh(&pn->hash_lock);
- if (!dev)
- goto abort;
+ if (sock_flag(sk, SOCK_DEAD) || !(sk->sk_state & PPPOX_CONNECTED))
+ goto abort_put;
/* Copy the data if there is no space for the header or if it's
* read-only.
*/
if (skb_cow_head(skb, sizeof(*ph) + dev->hard_header_len))
- goto abort;
+ goto abort_put;
__skb_push(skb, sizeof(*ph));
skb_reset_network_header(skb);
@@ -944,9 +998,11 @@ static int __pppoe_xmit(struct sock *sk,
po->pppoe_pa.remote, NULL, data_len);
dev_queue_xmit(skb);
-
+ dev_put(dev);
return 1;
+abort_put:
+ dev_put(dev);
abort:
kfree_skb(skb);
return 1;
^ permalink raw reply
* Re: [PATCHv2 1/4] First Patch on TFRC-SP. Copy base files from TFRC
From: Ivo Calado @ 2009-10-20 13:51 UTC (permalink / raw)
To: Gerrit Renker, Ivo Calado, dccp, netdev
In-Reply-To: <20091019052153.GB3366@gerrit.erg.abdn.ac.uk>
On Mon, Oct 19, 2009 at 02:21, Gerrit Renker <gerrit@erg.abdn.ac.uk> wrote:
> | First Patch on TFRC-SP.
> Please find attached one edit that I made.
>
> I added unwinding the initialisation of tfrc_lib in the case where the
> initialisation of tfrc_sp_lib fails. Unwinding is now done in the reverse
> order of the steps done during initialisation.
>
Agree.
--
Ivo Augusto Andrade Rocha Calado
MSc. Candidate
Embedded Systems and Pervasive Computing Lab - http://embedded.ufcg.edu.br
Systems and Computing Department - http://www.dsc.ufcg.edu.br
Electrical Engineering and Informatics Center - http://www.ceei.ufcg.edu.br
Federal University of Campina Grande - http://www.ufcg.edu.br
PGP: 0x03422935
Quidquid latine dictum sit, altum viditur.
^ permalink raw reply
* Re: kernel panic in latest vanilla stable, while using nameif with "alive" pppoe interfaces
From: Denys Fedoryschenko @ 2009-10-20 13:50 UTC (permalink / raw)
To: Cyrill Gorcunov
Cc: Michal Ostrowski, Eric Dumazet, netdev, linux-ppp, paulus,
mostrows
In-Reply-To: <20091020134217.GA5181@lenovo>
On Tuesday 20 October 2009 16:42:17 Cyrill Gorcunov wrote:
> [Denys Fedoryschenko - Tue, Oct 20, 2009 at 02:52:58PM +0300]
> ...
>
> | > Thanks a lot! I'll back with new one in a couple of hours. Meanwhile i
> | > suppose you may try Michal's patch as well.
> |
> | I did, it didn't help.
> | Maybe i can run some debugging options in kernel?
> | Also i can add debug(printk) lines in kernel if you want, to see where is
> | bug appearing.
> | Note, i told to Michal, so will tell here, this pc is hyperthreading P4,
> | as i know it is very good to trigger various SMP race conditions.
> | I can try also it with nosmp if u want.
>
> Thanks Denys, I'm preparing new patch (just back from office
> and had no inet connection that is why reply is delayed, sorry).
There is no problem at all.
This rename operation is just future operation and host is redundant, so i can
do tests on it anytime.
^ permalink raw reply
* Re: kernel panic in latest vanilla stable, while using nameif with "alive" pppoe interfaces
From: Cyrill Gorcunov @ 2009-10-20 13:42 UTC (permalink / raw)
To: Denys Fedoryschenko
Cc: Michal Ostrowski, Eric Dumazet, netdev, linux-ppp, paulus,
mostrows
In-Reply-To: <200910201452.58789.denys@visp.net.lb>
[Denys Fedoryschenko - Tue, Oct 20, 2009 at 02:52:58PM +0300]
...
| > Thanks a lot! I'll back with new one in a couple of hours. Meanwhile i
| > suppose you may try Michal's patch as well.
| I did, it didn't help.
| Maybe i can run some debugging options in kernel?
| Also i can add debug(printk) lines in kernel if you want, to see where is bug
| appearing.
| Note, i told to Michal, so will tell here, this pc is hyperthreading P4, as i
| know it is very good to trigger various SMP race conditions.
| I can try also it with nosmp if u want.
|
Thanks Denys, I'm preparing new patch (just back from office
and had no inet connection that is why reply is delayed, sorry).
-- Cyrill
^ permalink raw reply
* Policy routing + route "via" gives a strange behavior
From: Guido Trotter @ 2009-10-20 13:28 UTC (permalink / raw)
To: netdev
Hi,
I'm seeing what I think might be a strange kernel behavior when setting up a
route "via" a gateway, with policy routing. When adding a route with a gateway,
the kernel accepts it only if the gateway is reachable via that device. For
example:
ip route add default dev eth1 via 192.168.5.254
is only accepted if there is a route like:
192.168.5.0/24 dev eth1 scope link
in the main routing table. which, of course, is ok, otherwise the kernel
wouldn't be able to reach 192.168.5.254 in the first place.
Now, when adding policy routing to the mix, if I do:
ip route add table 100 default dev eth1 via 192.168.5.254
This is also refused unless a route like the one before appears in the default
table, even though it does appear in table 100. Is this the right behavior, and
if yes, why? It seems to me that it should be acceptable to have the network
route as well just in the separate routing table, since the "via" will only be
used by traffic hitting that table anyway.
Thanks a lot,
Guido
^ permalink raw reply
* [PATCH] ifb: should not use __dev_get_by_index() without locks
From: Eric Dumazet @ 2009-10-20 12:35 UTC (permalink / raw)
To: David Miller; +Cc: netdev
In-Reply-To: <20091019.212855.179405364.davem@davemloft.net>
David Miller a écrit :
> From: Eric Dumazet <eric.dumazet@gmail.com>
> Date: Tue, 20 Oct 2009 06:23:54 +0200
>
>> I wonder if the whole thing could use RCU somehow, since some
>> workloads hit this dev_base_lock rwlock pretty hard...
>
> True, but for now we'll put your fix in :-)
Here is another vulnerable point, needing following patch.
Thanks
[PATCH] ifb: should not use __dev_get_by_index() without locks
At this point (ri_tasklet()), RTNL or dev_base_lock are not held,
we must use dev_get_by_index() instead of __dev_get_by_index()
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
---
diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c
index 801f088..030913f 100644
--- a/drivers/net/ifb.c
+++ b/drivers/net/ifb.c
@@ -98,12 +98,13 @@ static void ri_tasklet(unsigned long dev)
stats->tx_packets++;
stats->tx_bytes +=skb->len;
- skb->dev = __dev_get_by_index(&init_net, skb->iif);
+ skb->dev = dev_get_by_index(&init_net, skb->iif);
if (!skb->dev) {
dev_kfree_skb(skb);
stats->tx_dropped++;
break;
}
+ dev_put(skb->dev);
skb->iif = _dev->ifindex;
if (from & AT_EGRESS) {
^ permalink raw reply related
* Re: [PATCH net-next V2 1/3] iwmc3200top: Add Intel Wireless MultiCom 3200 top driver.
From: Tomas Winkler @ 2009-10-20 11:53 UTC (permalink / raw)
To: David Miller, Marcel Holtmann
Cc: linville, netdev, linux-wireless, linux-mmc, yi.zhu,
inaky.perez-gonzalez, cindy.h.kao, guy.cohen, ron.rindjunsky
In-Reply-To: <20091019.215457.43252934.davem@davemloft.net>
On Tue, Oct 20, 2009 at 6:54 AM, David Miller <davem@davemloft.net> wrote:
> From: Tomas Winkler <tomas.winkler@intel.com>
> Date: Sat, 17 Oct 2009 21:09:34 +0200
>
>> This patch adds Intel Wireless MultiCom 3200 top driver.
>> IWMC3200 is 4Wireless Com CHIP (GPS/BT/WiFi/WiMAX).
>> Top driver is responsible for device initialization and firmware download.
>> Firmware handled by top is responsible for top itself and
>> as well as bluetooth and GPS coms. (Wifi and WiMax provide their own firmware)
>> In addition top driver is used to retrieve firmware logs
>> and supports other debugging features
>>
>> Signed-off-by: Tomas Winkler <tomas.winkler@intel.com>
>
> Applied to net-next-2.6
Thanks Dave
Marcel
I want to send out now the BT driver, would like the patch against
bluetooth-next-2.6.git, then I wait till you sync or can you also pick
it from net-next if Dave is OK with that?
Thanks
Tomas
^ permalink raw reply
* Re: kernel panic in latest vanilla stable, while using nameif with "alive" pppoe interfaces
From: Denys Fedoryschenko @ 2009-10-20 11:52 UTC (permalink / raw)
To: Cyrill Gorcunov
Cc: Michal Ostrowski, Eric Dumazet, netdev, linux-ppp, paulus,
mostrows
In-Reply-To: <aa79d98a0910200450n1a283f87hf946bb3b756d0bd@mail.gmail.com>
On Tuesday 20 October 2009 14:50:09 Cyrill Gorcunov wrote:
> On 10/20/09, Denys Fedoryschenko <denys@visp.net.lb> wrote:
> > On Tuesday 20 October 2009 06:04:35 Cyrill Gorcunov wrote:
> >> On 10/20/09, Denys Fedoryschenko <denys@visp.net.lb> wrote:
> >> > On Tuesday 20 October 2009 00:22:39 Michal Ostrowski wrote:
> >> >> I'm assuming that there was a race in us sending patches at nearly
> >> >> the same
> >> >> time I'm convinced now that the flush_lock can die, and the patch I
> >> >> sent
> >> >> out kills it.
> >> >
> >> > o_O
> >> >
> >> > I am drowning in patches. Just let me know which one to test :-)
> >>
> >> Oh ;) Try out latest Michal's patch (and then mine). I'll continue
> >> digg this issue at next spare time slot. Thanks!
> >
> > Tried your patch, panic almost immediately
> > Here is a text of panic message over netconsole
> > http://www.nuclearcat.com/files/panic_pppoe3.txt
> > It is different now, before it was pppoe_device_event, now in pppoe_rcv
>
> Thanks a lot! I'll back with new one in a couple of hours. Meanwhile i
> suppose you may try Michal's patch as well.
I did, it didn't help.
Maybe i can run some debugging options in kernel?
Also i can add debug(printk) lines in kernel if you want, to see where is bug
appearing.
Note, i told to Michal, so will tell here, this pc is hyperthreading P4, as i
know it is very good to trigger various SMP race conditions.
I can try also it with nosmp if u want.
^ permalink raw reply
* Re: kernel panic in latest vanilla stable, while using nameif with "alive" pppoe interfaces
From: Cyrill Gorcunov @ 2009-10-20 11:50 UTC (permalink / raw)
To: Denys Fedoryschenko
Cc: Michal Ostrowski, Eric Dumazet, netdev, linux-ppp, paulus,
mostrows
In-Reply-To: <200910201436.50249.denys@visp.net.lb>
On 10/20/09, Denys Fedoryschenko <denys@visp.net.lb> wrote:
> On Tuesday 20 October 2009 06:04:35 Cyrill Gorcunov wrote:
>> On 10/20/09, Denys Fedoryschenko <denys@visp.net.lb> wrote:
>> > On Tuesday 20 October 2009 00:22:39 Michal Ostrowski wrote:
>> >> I'm assuming that there was a race in us sending patches at nearly the
>> >> same
>> >> time I'm convinced now that the flush_lock can die, and the patch I
>> >> sent
>> >> out kills it.
>> >
>> > o_O
>> >
>> > I am drowning in patches. Just let me know which one to test :-)
>>
>> Oh ;) Try out latest Michal's patch (and then mine). I'll continue
>> digg this issue at next spare time slot. Thanks!
> Tried your patch, panic almost immediately
> Here is a text of panic message over netconsole
> http://www.nuclearcat.com/files/panic_pppoe3.txt
> It is different now, before it was pppoe_device_event, now in pppoe_rcv
>
>
Thanks a lot! I'll back with new one in a couple of hours. Meanwhile i
suppose you may try Michal's patch as well.
^ permalink raw reply
* Re: kernel panic in latest vanilla stable, while using nameif with "alive" pppoe interfaces
From: Denys Fedoryschenko @ 2009-10-20 11:36 UTC (permalink / raw)
To: Cyrill Gorcunov
Cc: Michal Ostrowski, Eric Dumazet, netdev, linux-ppp, paulus,
mostrows
In-Reply-To: <aa79d98a0910192004g43de90d5p823293b888cf0c1d@mail.gmail.com>
On Tuesday 20 October 2009 06:04:35 Cyrill Gorcunov wrote:
> On 10/20/09, Denys Fedoryschenko <denys@visp.net.lb> wrote:
> > On Tuesday 20 October 2009 00:22:39 Michal Ostrowski wrote:
> >> I'm assuming that there was a race in us sending patches at nearly the
> >> same
> >> time I'm convinced now that the flush_lock can die, and the patch I sent
> >> out kills it.
> >
> > o_O
> >
> > I am drowning in patches. Just let me know which one to test :-)
>
> Oh ;) Try out latest Michal's patch (and then mine). I'll continue
> digg this issue at next spare time slot. Thanks!
Tried your patch, panic almost immediately
Here is a text of panic message over netconsole
http://www.nuclearcat.com/files/panic_pppoe3.txt
It is different now, before it was pppoe_device_event, now in pppoe_rcv
^ permalink raw reply
* Re: [Patch] (updated) netfilter: remove deprecated CONFIG_NF_CT_ACCT
From: Cong Wang @ 2009-10-20 9:58 UTC (permalink / raw)
To: Krzysztof Olędzki; +Cc: linux-kernel, netdev, akpm, netfilter-devel
In-Reply-To: <4AD70FC2.5050302@ans.pl>
Sorry that I lost this thread. :(
Krzysztof Olędzki wrote:
> [resend, previously I incorrectly copied netfilter-devel-owner]
>
> Adding CC to netfilter-devel@vger.kernel.org, where netfilter
> related issues are discussed.
>
> On Thu, 15 Oct 2009, Amerigo Wang wrote:
>
>>
>> CONFIG_NF_CT_ACCT is scheduled to be removed in 2.6.29.
>>
>> Cc: Krzysztof Piotr Oledzki <ole@ans.pl>
>> Signed-off-by: WANG Cong <amwang@redhat.com>
>
> This is not so easy - it was decided that we don't want to remove it
> just that because of connbytes. The final conclusion was to keep it
> disabled by default (if not enabled by kernel/modules/sysctl option) but
> enabling it automatically for the current NS if nefilter rules contains
> "-m connbytes".
>
> Sorry, I should have gotten into this and finished it earlier, my bad. :(
No problem.
So we just want CONFIG_NF_CT_ACCT=n in default configs?
Thanks!
--
To unsubscribe from this list: send the line "unsubscribe netfilter-devel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [PATCH] Add new cs89x0 driver
From: Ben Dooks @ 2009-10-20 9:55 UTC (permalink / raw)
To: Sascha Hauer
Cc: netdev, Lennert Buytenhek, Ivo Clarysse, Gilles Chanteperdrix
In-Reply-To: <1240387172-21818-1-git-send-email-s.hauer@pengutronix.de>
On Wed, Apr 22, 2009 at 09:59:30AM +0200, Sascha Hauer wrote:
> While this is a very old chip it is still in use on some embedded boards.
> I see myself unable to fix the in Kernel driver to bring it to driver
> model support, so this patch adds a new driver designed to replace
> the old one, at least for non-ISA hardware.
I think it is worthwile, there's a number of SMDK boards and similar
which have used this board, including boards released in the last year
or so.
I will try and see if I can do some reviewing and testing of this in
the next few days.
--
Ben (ben@fluff.org, http://www.fluff.org/)
'a smiley only costs 4 bytes'
^ permalink raw reply
* [PATCH 4/4 v4] net: Use sk_tx_queue_mapping for connected sockets
From: Krishna Kumar @ 2009-10-20 9:50 UTC (permalink / raw)
To: davem; +Cc: netdev, herbert, Krishna Kumar, dada1
In-Reply-To: <20091020094607.10404.81794.sendpatchset@localhost.localdomain>
From: Krishna Kumar <krkumar2@in.ibm.com>
For connected sockets, the first run of dev_pick_tx saves the
calculated txq in sk_tx_queue_mapping. This is not saved if
either the device has a queue select or the socket is not
connected. Next iterations of dev_pick_tx uses the cached value
of sk_tx_queue_mapping.
Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com>
---
net/core/dev.c | 24 ++++++++++++++++++------
1 file changed, 18 insertions(+), 6 deletions(-)
diff -ruNp org/net/core/dev.c new/net/core/dev.c
--- org/net/core/dev.c 2009-10-19 15:43:30.000000000 +0530
+++ new/net/core/dev.c 2009-10-20 12:24:40.000000000 +0530
@@ -1791,13 +1791,25 @@ EXPORT_SYMBOL(skb_tx_hash);
static struct netdev_queue *dev_pick_tx(struct net_device *dev,
struct sk_buff *skb)
{
- const struct net_device_ops *ops = dev->netdev_ops;
- u16 queue_index = 0;
+ u16 queue_index;
+ struct sock *sk = skb->sk;
+
+ if (sk_tx_queue_recorded(sk)) {
+ queue_index = sk_tx_queue_get(sk);
+ } else {
+ const struct net_device_ops *ops = dev->netdev_ops;
- if (ops->ndo_select_queue)
- queue_index = ops->ndo_select_queue(dev, skb);
- else if (dev->real_num_tx_queues > 1)
- queue_index = skb_tx_hash(dev, skb);
+ if (ops->ndo_select_queue) {
+ queue_index = ops->ndo_select_queue(dev, skb);
+ } else {
+ queue_index = 0;
+ if (dev->real_num_tx_queues > 1)
+ queue_index = skb_tx_hash(dev, skb);
+
+ if (sk && sk->sk_dst_cache)
+ sk_tx_queue_set(sk, queue_index);
+ }
+ }
skb_set_queue_mapping(skb, queue_index);
return netdev_get_tx_queue(dev, queue_index);
^ permalink raw reply
* [PATCH 3/4 v4] net: Fix for dst_negative_advice
From: Krishna Kumar @ 2009-10-20 9:46 UTC (permalink / raw)
To: davem; +Cc: netdev, herbert, Krishna Kumar, dada1
In-Reply-To: <20091020094607.10404.81794.sendpatchset@localhost.localdomain>
From: Krishna Kumar <krkumar2@in.ibm.com>
dst_negative_advice() should check for changed dst and reset
sk_tx_queue_mapping accordingly. Pass sock to the callers of
dst_negative_advice.
(sk_reset_txq is defined just for use by dst_negative_advice. The
only way I could find to get around this is to move dst_negative_()
from dst.h to dst.c, include sock.h in dst.c, etc)
Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com>
---
include/net/dst.h | 12 ++++++++++--
net/core/sock.c | 6 ++++++
net/dccp/timer.c | 4 ++--
net/decnet/af_decnet.c | 2 +-
net/ipv4/tcp_timer.c | 4 ++--
5 files changed, 21 insertions(+), 7 deletions(-)
diff -ruNp org/include/net/dst.h new/include/net/dst.h
--- org/include/net/dst.h 2009-10-16 21:30:56.000000000 +0530
+++ new/include/net/dst.h 2009-10-16 21:31:30.000000000 +0530
@@ -222,11 +222,19 @@ static inline void dst_confirm(struct ds
neigh_confirm(dst->neighbour);
}
-static inline void dst_negative_advice(struct dst_entry **dst_p)
+static inline void dst_negative_advice(struct dst_entry **dst_p,
+ struct sock *sk)
{
struct dst_entry * dst = *dst_p;
- if (dst && dst->ops->negative_advice)
+ if (dst && dst->ops->negative_advice) {
*dst_p = dst->ops->negative_advice(dst);
+
+ if (dst != *dst_p) {
+ extern void sk_reset_txq(struct sock *sk);
+
+ sk_reset_txq(sk);
+ }
+ }
}
static inline void dst_link_failure(struct sk_buff *skb)
diff -ruNp org/net/core/sock.c new/net/core/sock.c
--- org/net/core/sock.c 2009-10-16 21:30:56.000000000 +0530
+++ new/net/core/sock.c 2009-10-16 21:32:33.000000000 +0530
@@ -352,6 +352,12 @@ discard_and_relse:
}
EXPORT_SYMBOL(sk_receive_skb);
+void sk_reset_txq(struct sock *sk)
+{
+ sk_tx_queue_clear(sk);
+}
+EXPORT_SYMBOL(sk_reset_txq);
+
struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie)
{
struct dst_entry *dst = sk->sk_dst_cache;
diff -ruNp org/net/dccp/timer.c new/net/dccp/timer.c
--- org/net/dccp/timer.c 2009-10-16 21:30:56.000000000 +0530
+++ new/net/dccp/timer.c 2009-10-16 21:31:30.000000000 +0530
@@ -38,7 +38,7 @@ static int dccp_write_timeout(struct soc
if (sk->sk_state == DCCP_REQUESTING || sk->sk_state == DCCP_PARTOPEN) {
if (icsk->icsk_retransmits != 0)
- dst_negative_advice(&sk->sk_dst_cache);
+ dst_negative_advice(&sk->sk_dst_cache, sk);
retry_until = icsk->icsk_syn_retries ?
: sysctl_dccp_request_retries;
} else {
@@ -63,7 +63,7 @@ static int dccp_write_timeout(struct soc
Golden words :-).
*/
- dst_negative_advice(&sk->sk_dst_cache);
+ dst_negative_advice(&sk->sk_dst_cache, sk);
}
retry_until = sysctl_dccp_retries2;
diff -ruNp org/net/decnet/af_decnet.c new/net/decnet/af_decnet.c
--- org/net/decnet/af_decnet.c 2009-10-16 21:30:56.000000000 +0530
+++ new/net/decnet/af_decnet.c 2009-10-16 21:31:30.000000000 +0530
@@ -1955,7 +1955,7 @@ static int dn_sendmsg(struct kiocb *iocb
}
if ((flags & MSG_TRYHARD) && sk->sk_dst_cache)
- dst_negative_advice(&sk->sk_dst_cache);
+ dst_negative_advice(&sk->sk_dst_cache, sk);
mss = scp->segsize_rem;
fctype = scp->services_rem & NSP_FC_MASK;
diff -ruNp org/net/ipv4/tcp_timer.c new/net/ipv4/tcp_timer.c
--- org/net/ipv4/tcp_timer.c 2009-10-16 21:30:56.000000000 +0530
+++ new/net/ipv4/tcp_timer.c 2009-10-16 21:31:30.000000000 +0530
@@ -141,14 +141,14 @@ static int tcp_write_timeout(struct sock
if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
if (icsk->icsk_retransmits)
- dst_negative_advice(&sk->sk_dst_cache);
+ dst_negative_advice(&sk->sk_dst_cache, sk);
retry_until = icsk->icsk_syn_retries ? : sysctl_tcp_syn_retries;
} else {
if (retransmits_timed_out(sk, sysctl_tcp_retries1)) {
/* Black hole detection */
tcp_mtu_probing(icsk, sk);
- dst_negative_advice(&sk->sk_dst_cache);
+ dst_negative_advice(&sk->sk_dst_cache, sk);
}
retry_until = sysctl_tcp_retries2;
^ permalink raw reply
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