From 3294f202dc1acd82223e83ef59f272bd87bb06b2 Mon Sep 17 00:00:00 2001 From: Gerrit Renker Date: Wed, 11 Jun 2008 11:19:09 +0100 Subject: [PATCH 01/20] dccp ccid-3: Bug-Fix - Zero RTT is possible In commit $(825de27d9e40b3117b29a79d412b7a4b78c5d815) (from 27th May, commit message `dccp ccid-3: Fix "t_ipi explosion" bug'), the CCID-3 window counter computation was fixed to cope with RTTs < 4 microseconds. Such RTTs can be found e.g. when running CCID-3 over loopback. The fix removed a check against RTT < 4, but introduced a divide-by-zero bug. All steady-state RTTs in DCCP are filtered using dccp_sample_rtt(), which ensures non-zero samples. However, a zero RTT is possible on initialisation, when there is no RTT sample from the Request/Response exchange. The fix is to use the fallback-RTT from RFC 4340, 3.4. This is also better than just fixing update_win_count() since it allows other parts of the code to always assume that the RTT is non-zero during the time that the CCID is used. Signed-off-by: Gerrit Renker --- net/dccp/ccids/ccid3.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c index f813077234b7..0474f4c5707a 100644 --- a/net/dccp/ccids/ccid3.c +++ b/net/dccp/ccids/ccid3.c @@ -329,8 +329,14 @@ static int ccid3_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb) hctx->ccid3hctx_x = rfc3390_initial_rate(sk); hctx->ccid3hctx_t_ld = now; } else { - /* Sender does not have RTT sample: X_pps = 1 pkt/sec */ - hctx->ccid3hctx_x = hctx->ccid3hctx_s; + /* + * Sender does not have RTT sample: + * - set fallback RTT (RFC 4340, 3.4) since a RTT value + * is needed in several parts (e.g. window counter); + * - set sending rate X_pps = 1pps as per RFC 3448, 4.2. + */ + hctx->ccid3hctx_rtt = DCCP_FALLBACK_RTT; + hctx->ccid3hctx_x = hctx->ccid3hctx_s; hctx->ccid3hctx_x <<= 6; } ccid3_update_send_interval(hctx); From 1e2f0e5e8376f2a0ada8760fc9d3104e1a81382b Mon Sep 17 00:00:00 2001 From: Gerrit Renker Date: Wed, 11 Jun 2008 11:19:09 +0100 Subject: [PATCH 02/20] dccp: Fix sparse warnings This patch fixes the following sparse warnings: * nested min(max()) expression: net/dccp/ccids/ccid3.c:91:21: warning: symbol '__x' shadows an earlier one net/dccp/ccids/ccid3.c:91:21: warning: symbol '__y' shadows an earlier one * Declaration of function prototypes in .c instead of .h file, resulting in "should it be static?" warnings. * Declared "struct dccpw" static (local to dccp_probe). * Disabled dccp_delayed_ack() - not fully removed due to RFC 4340, 11.3 ("Receivers SHOULD implement delayed acknowledgement timers ..."). * Used a different local variable name to avoid net/dccp/ackvec.c:293:13: warning: symbol 'state' shadows an earlier one net/dccp/ackvec.c:238:33: originally declared here * Removed unused functions `dccp_ackvector_print' and `dccp_ackvec_print'. Signed-off-by: Gerrit Renker --- net/dccp/ackvec.c | 29 ++--------------------------- net/dccp/ccids/ccid3.c | 4 ++-- net/dccp/ccids/lib/tfrc.c | 8 -------- net/dccp/ccids/lib/tfrc.h | 11 +++++++++-- net/dccp/output.c | 2 ++ net/dccp/probe.c | 2 +- 6 files changed, 16 insertions(+), 40 deletions(-) diff --git a/net/dccp/ackvec.c b/net/dccp/ackvec.c index 6de4bd195d28..1e8be246ad15 100644 --- a/net/dccp/ackvec.c +++ b/net/dccp/ackvec.c @@ -290,12 +290,12 @@ int dccp_ackvec_add(struct dccp_ackvec *av, const struct sock *sk, while (1) { const u8 len = dccp_ackvec_len(av, index); - const u8 state = dccp_ackvec_state(av, index); + const u8 av_state = dccp_ackvec_state(av, index); /* * valid packets not yet in av_buf have a reserved * entry, with a len equal to 0. */ - if (state == DCCP_ACKVEC_STATE_NOT_RECEIVED && + if (av_state == DCCP_ACKVEC_STATE_NOT_RECEIVED && len == 0 && delta == 0) { /* Found our reserved seat! */ dccp_pr_debug("Found %llu reserved seat!\n", @@ -325,31 +325,6 @@ out_duplicate: return -EILSEQ; } -#ifdef CONFIG_IP_DCCP_DEBUG -void dccp_ackvector_print(const u64 ackno, const unsigned char *vector, int len) -{ - dccp_pr_debug_cat("ACK vector len=%d, ackno=%llu |", len, - (unsigned long long)ackno); - - while (len--) { - const u8 state = (*vector & DCCP_ACKVEC_STATE_MASK) >> 6; - const u8 rl = *vector & DCCP_ACKVEC_LEN_MASK; - - dccp_pr_debug_cat("%d,%d|", state, rl); - ++vector; - } - - dccp_pr_debug_cat("\n"); -} - -void dccp_ackvec_print(const struct dccp_ackvec *av) -{ - dccp_ackvector_print(av->av_buf_ackno, - av->av_buf + av->av_buf_head, - av->av_vec_len); -} -#endif - static void dccp_ackvec_throw_record(struct dccp_ackvec *av, struct dccp_ackvec_record *avr) { diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c index 0474f4c5707a..a1929f33d703 100644 --- a/net/dccp/ccids/ccid3.c +++ b/net/dccp/ccids/ccid3.c @@ -159,8 +159,8 @@ static void ccid3_hc_tx_update_x(struct sock *sk, ktime_t *stamp) } else if (ktime_us_delta(now, hctx->ccid3hctx_t_ld) - (s64)hctx->ccid3hctx_rtt >= 0) { - hctx->ccid3hctx_x = - max(min(2 * hctx->ccid3hctx_x, min_rate), + hctx->ccid3hctx_x = min(2 * hctx->ccid3hctx_x, min_rate); + hctx->ccid3hctx_x = max(hctx->ccid3hctx_x, scaled_div(((__u64)hctx->ccid3hctx_s) << 6, hctx->ccid3hctx_rtt)); hctx->ccid3hctx_t_ld = now; diff --git a/net/dccp/ccids/lib/tfrc.c b/net/dccp/ccids/lib/tfrc.c index d1dfbb8de64c..97ecec0a8e76 100644 --- a/net/dccp/ccids/lib/tfrc.c +++ b/net/dccp/ccids/lib/tfrc.c @@ -14,14 +14,6 @@ module_param(tfrc_debug, bool, 0444); MODULE_PARM_DESC(tfrc_debug, "Enable debug messages"); #endif -extern int tfrc_tx_packet_history_init(void); -extern void tfrc_tx_packet_history_exit(void); -extern int tfrc_rx_packet_history_init(void); -extern void tfrc_rx_packet_history_exit(void); - -extern int tfrc_li_init(void); -extern void tfrc_li_exit(void); - static int __init tfrc_module_init(void) { int rc = tfrc_li_init(); diff --git a/net/dccp/ccids/lib/tfrc.h b/net/dccp/ccids/lib/tfrc.h index 1fb1187bbf1c..ddd8107b927f 100644 --- a/net/dccp/ccids/lib/tfrc.h +++ b/net/dccp/ccids/lib/tfrc.h @@ -58,7 +58,14 @@ static inline u32 tfrc_ewma(const u32 avg, const u32 newval, const u8 weight) return avg ? (weight * avg + (10 - weight) * newval) / 10 : newval; } -extern u32 tfrc_calc_x(u16 s, u32 R, u32 p); -extern u32 tfrc_calc_x_reverse_lookup(u32 fvalue); +extern u32 tfrc_calc_x(u16 s, u32 R, u32 p); +extern u32 tfrc_calc_x_reverse_lookup(u32 fvalue); +extern int tfrc_tx_packet_history_init(void); +extern void tfrc_tx_packet_history_exit(void); +extern int tfrc_rx_packet_history_init(void); +extern void tfrc_rx_packet_history_exit(void); + +extern int tfrc_li_init(void); +extern void tfrc_li_exit(void); #endif /* _TFRC_H_ */ diff --git a/net/dccp/output.c b/net/dccp/output.c index 1f8a9b64c083..fe20068c5d8e 100644 --- a/net/dccp/output.c +++ b/net/dccp/output.c @@ -508,6 +508,7 @@ void dccp_send_ack(struct sock *sk) EXPORT_SYMBOL_GPL(dccp_send_ack); +#if 0 /* FIXME: Is this still necessary (11.3) - currently nowhere used by DCCP. */ void dccp_send_delayed_ack(struct sock *sk) { @@ -538,6 +539,7 @@ void dccp_send_delayed_ack(struct sock *sk) icsk->icsk_ack.timeout = timeout; sk_reset_timer(sk, &icsk->icsk_delack_timer, timeout); } +#endif void dccp_send_sync(struct sock *sk, const u64 ackno, const enum dccp_pkt_type pkt_type) diff --git a/net/dccp/probe.c b/net/dccp/probe.c index 0bcdc9250279..81368a7f5379 100644 --- a/net/dccp/probe.c +++ b/net/dccp/probe.c @@ -42,7 +42,7 @@ static int bufsize = 64 * 1024; static const char procname[] = "dccpprobe"; -struct { +static struct { struct kfifo *fifo; spinlock_t lock; wait_queue_head_t wait; From 65907a433ac0ca450c4408080f24c6e4743386b2 Mon Sep 17 00:00:00 2001 From: Gerrit Renker Date: Wed, 11 Jun 2008 11:19:09 +0100 Subject: [PATCH 03/20] dccp ccid-2: Bug-Fix - Ack Vectors need to be ignored on request sockets This fixes an oversight from an earlier patch, ensuring that Ack Vectors are not processed on request sockets. The issue is that Ack Vectors must not be parsed on request sockets, since the Ack Vector feature depends on the selection of the (TX) CCID. During the initial handshake the CCIDs are undefined, and so RFC 4340, 10.3 applies: "Using CCID-specific options and feature options during a negotiation for the corresponding CCID feature is NOT RECOMMENDED [...]" And it is not even possible: when the server receives the Request from the client, the CCID and Ack vector features are undefined; when the Ack finalising the 3-way hanshake arrives, the request socket has not been cloned yet into a full socket. (This order is necessary, since otherwise the newly created socket would have to be destroyed whenever an option error occurred - a malicious hacker could simply send garbage options and exploit this.) Signed-off-by: Gerrit Renker --- net/dccp/options.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/dccp/options.c b/net/dccp/options.c index d2a84a2fecee..43bc24e761d0 100644 --- a/net/dccp/options.c +++ b/net/dccp/options.c @@ -107,9 +107,11 @@ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq, * * CCID-specific options are ignored during connection setup, as * negotiation may still be in progress (see RFC 4340, 10.3). + * The same applies to Ack Vectors, as these depend on the CCID. * */ - if (dreq != NULL && opt >= 128) + if (dreq != NULL && (opt >= 128 || + opt == DCCPO_ACK_VECTOR_0 || opt == DCCPO_ACK_VECTOR_1)) goto ignore_option; switch (opt) { From 1e8a287c79f64226541f5c44aa52d4698bb84cf5 Mon Sep 17 00:00:00 2001 From: Gerrit Renker Date: Wed, 11 Jun 2008 11:19:10 +0100 Subject: [PATCH 04/20] dccp ccid-3: TFRC reverse-lookup Bug-Fix This fixes a bug in the reverse lookup of p: given a value f(p), instead of p, the function returned the smallest tabulated value f(p). The smallest tabulated value of 10^6 * f(p) = sqrt(2*p/3) + 12 * sqrt(3*p/8) * (32 * p^3 + p) for p=0.0001 is 8172. Since this value is scaled by 10^6, the outcome of this bug is that a loss of 8172/10^6 = 0.8172% was reported whenever the input was below the table resolution of 0.01%. This means that the value was over 80 times too high, resulting in large spikes of the initial loss interval, thus unnecessarily reducing the throughput. Also corrected the printk format (%u for u32). Signed-off-by: Gerrit Renker --- net/dccp/ccids/lib/tfrc_equation.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/net/dccp/ccids/lib/tfrc_equation.c b/net/dccp/ccids/lib/tfrc_equation.c index e4e64b76c10c..2f20a29cffe4 100644 --- a/net/dccp/ccids/lib/tfrc_equation.c +++ b/net/dccp/ccids/lib/tfrc_equation.c @@ -661,7 +661,7 @@ u32 tfrc_calc_x(u16 s, u32 R, u32 p) EXPORT_SYMBOL_GPL(tfrc_calc_x); -/* +/** * tfrc_calc_x_reverse_lookup - try to find p given f(p) * * @fvalue: function value to match, scaled by 1000000 @@ -676,11 +676,11 @@ u32 tfrc_calc_x_reverse_lookup(u32 fvalue) /* Error cases. */ if (fvalue < tfrc_calc_x_lookup[0][1]) { - DCCP_WARN("fvalue %d smaller than resolution\n", fvalue); - return tfrc_calc_x_lookup[0][1]; + DCCP_WARN("fvalue %u smaller than resolution\n", fvalue); + return TFRC_SMALLEST_P; } if (fvalue > tfrc_calc_x_lookup[TFRC_CALC_X_ARRSIZE - 1][0]) { - DCCP_WARN("fvalue %d exceeds bounds!\n", fvalue); + DCCP_WARN("fvalue %u exceeds bounds!\n", fvalue); return 1000000; } From 7deb0f851003287d7e259bf6b33548b144c0f2d5 Mon Sep 17 00:00:00 2001 From: Gerrit Renker Date: Wed, 11 Jun 2008 11:19:10 +0100 Subject: [PATCH 05/20] dccp ccid-3: X truncated due to type conversion This fixes a bug in computing the inter-packet-interval t_ipi = s/X: scaled_div32(a, b) uses u32 for b, but in "scaled_div32(s, X)" the type of the sending rate `X' is u64. Since X is scaled by 2^6, this truncates rates greater than 2^26 Bps (~537 Mbps). Using full 64-bit division now. Signed-off-by: Gerrit Renker --- net/dccp/ccids/lib/tfrc.h | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) diff --git a/net/dccp/ccids/lib/tfrc.h b/net/dccp/ccids/lib/tfrc.h index ddd8107b927f..ed9857527acf 100644 --- a/net/dccp/ccids/lib/tfrc.h +++ b/net/dccp/ccids/lib/tfrc.h @@ -15,7 +15,7 @@ * (at your option) any later version. */ #include -#include +#include #include "../../dccp.h" /* internal includes that this module exports: */ #include "loss_interval.h" @@ -29,21 +29,19 @@ extern int tfrc_debug; #endif /* integer-arithmetic divisions of type (a * 1000000)/b */ -static inline u64 scaled_div(u64 a, u32 b) +static inline u64 scaled_div(u64 a, u64 b) { BUG_ON(b==0); - a *= 1000000; - do_div(a, b); - return a; + return div64_u64(a * 1000000, b); } -static inline u32 scaled_div32(u64 a, u32 b) +static inline u32 scaled_div32(u64 a, u64 b) { u64 result = scaled_div(a, b); if (result > UINT_MAX) { - DCCP_CRIT("Overflow: a(%llu)/b(%u) > ~0U", - (unsigned long long)a, b); + DCCP_CRIT("Overflow: %llu/%llu > UINT_MAX", + (unsigned long long)a, (unsigned long long)b); return UINT_MAX; } return result; From be4c798a41bf626cdaacf96c382f116ed2f7dbe9 Mon Sep 17 00:00:00 2001 From: Gerrit Renker Date: Wed, 11 Jun 2008 11:19:10 +0100 Subject: [PATCH 06/20] dccp: Bug in initial acknowledgment number assignment Step 8.5 in RFC 4340 says for the newly cloned socket Initialize S.GAR := S.ISS, but what in fact the code (minisocks.c) does is Initialize S.GAR := S.ISR, which is wrong (typo?) -- fixed by the patch. Signed-off-by: Gerrit Renker --- net/dccp/minisocks.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index 33ad48321b08..66dca5bba858 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -165,12 +165,12 @@ out_free: /* See dccp_v4_conn_request */ newdmsk->dccpms_sequence_window = req->rcv_wnd; - newdp->dccps_gar = newdp->dccps_isr = dreq->dreq_isr; - dccp_update_gsr(newsk, dreq->dreq_isr); - - newdp->dccps_iss = dreq->dreq_iss; + newdp->dccps_gar = newdp->dccps_iss = dreq->dreq_iss; dccp_update_gss(newsk, dreq->dreq_iss); + newdp->dccps_isr = dreq->dreq_isr; + dccp_update_gsr(newsk, dreq->dreq_isr); + /* * SWL and AWL are initially adjusted so that they are not less than * the initial Sequence Numbers received and sent, respectively: From 20c61fbd8deb2ada0ac3acecf6156a986dbfff2d Mon Sep 17 00:00:00 2001 From: YOSHIFUJI Hideaki Date: Mon, 28 Apr 2008 14:40:55 +0900 Subject: [PATCH 07/20] ipv6 mcast: Check address family of gf_group in getsockopt(MS_FILTER). Signed-off-by: YOSHIFUJI Hideaki --- net/ipv6/ipv6_sockglue.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 26b83e512a09..ce794d6acb70 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -874,6 +874,8 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, return -EINVAL; if (copy_from_user(&gsf, optval, GROUP_FILTER_SIZE(0))) return -EFAULT; + if (gsf.gf_group.ss_family != AF_INET6) + return -EADDRNOTAVAIL; lock_sock(sk); err = ip6_mc_msfget(sk, &gsf, (struct group_filter __user *)optval, optlen); From 36e3deae8ba84865fd9eb3f2f21bbc00d49b7544 Mon Sep 17 00:00:00 2001 From: YOSHIFUJI Hideaki Date: Tue, 13 May 2008 02:52:55 +0900 Subject: [PATCH 08/20] ipv6 route: Fix route lifetime in netlink message. 1) We may have route lifetime larger than INT_MAX. In that case we had wired value in lifetime. Use INT_MAX if lifetime does not fit in s32. 2) Lifetime is valid iif RTF_EXPIRES is set. Signed-off-by: YOSHIFUJI Hideaki --- net/ipv6/route.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 220cffe9e63b..d1f3e19b06c7 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2196,8 +2196,12 @@ static int rt6_fill_node(struct sk_buff *skb, struct rt6_info *rt, NLA_PUT_U32(skb, RTA_PRIORITY, rt->rt6i_metric); - expires = (rt->rt6i_flags & RTF_EXPIRES) ? - rt->rt6i_expires - jiffies : 0; + if (!(rt->rt6i_flags & RTF_EXPIRES)) + expires = 0; + else if (rt->rt6i_expires - jiffies < INT_MAX) + expires = rt->rt6i_expires - jiffies; + else + expires = INT_MAX; if (rtnl_put_cacheinfo(skb, &rt->u.dst, 0, 0, 0, expires, rt->u.dst.error) < 0) From e8766fc86b34d44a8c55a2f9d71da69e091b1ca4 Mon Sep 17 00:00:00 2001 From: Shan Wei Date: Tue, 10 Jun 2008 15:50:55 +0800 Subject: [PATCH 09/20] ipv6: Check the hop limit setting in ancillary data. When specifing the outgoing hop limit as ancillary data for sendmsg(), the kernel doesn't check the integer hop limit value as specified in [RFC-3542] section 6.3. Signed-off-by: Shan Wei Signed-off-by: YOSHIFUJI Hideaki --- net/ipv6/datagram.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index b9c2de84a8a2..0f0f94a40335 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -705,6 +705,11 @@ int datagram_send_ctl(struct net *net, } *hlimit = *(int *)CMSG_DATA(cmsg); + if (*hlimit < -1 || *hlimit > 0xff) { + err = -EINVAL; + goto exit_f; + } + break; case IPV6_TCLASS: From 28d4488216645cd71402925cffde9528b0cfdb7e Mon Sep 17 00:00:00 2001 From: YOSHIFUJI Hideaki Date: Thu, 12 Jun 2008 03:14:51 +0900 Subject: [PATCH 10/20] ipv6: Check IPV6_MULTICAST_LOOP option value. Only 0 and 1 are valid for IPV6_MULTICAST_LOOP socket option, and we should return an error of EINVAL otherwise, per RFC3493. Based on patch from Shan Wei . Signed-off-by: YOSHIFUJI Hideaki --- net/ipv6/ipv6_sockglue.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index ce794d6acb70..9a3697172d5e 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -458,6 +458,8 @@ done: case IPV6_MULTICAST_LOOP: if (optlen < sizeof(int)) goto e_inval; + if (val != valbool) + goto e_inval; np->mc_loop = valbool; retv = 0; break; From 1717699cd5130009b7cd6756e883d8582c1fe706 Mon Sep 17 00:00:00 2001 From: YOSHIFUJI Hideaki Date: Thu, 12 Jun 2008 03:27:26 +0900 Subject: [PATCH 11/20] ipv6: Fail with appropriate error code when setting not-applicable sockopt. IPV6_MULTICAST_HOPS, for example, is not valid for stream sockets. Since they are virtually unavailable for stream sockets, we should return ENOPROTOOPT instead of EINVAL. Signed-off-by: YOSHIFUJI Hideaki --- net/ipv6/ipv6_sockglue.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 9a3697172d5e..c042ce19bd14 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -67,7 +67,7 @@ int ip6_ra_control(struct sock *sk, int sel, void (*destructor)(struct sock *)) /* RA packet may be delivered ONLY to IPPROTO_RAW socket */ if (sk->sk_type != SOCK_RAW || inet_sk(sk)->num != IPPROTO_RAW) - return -EINVAL; + return -ENOPROTOOPT; new_ra = (sel>=0) ? kmalloc(sizeof(*new_ra), GFP_KERNEL) : NULL; @@ -446,7 +446,7 @@ done: case IPV6_MULTICAST_HOPS: if (sk->sk_type == SOCK_STREAM) - goto e_inval; + break; if (optlen < sizeof(int)) goto e_inval; if (val > 255 || val < -1) @@ -466,7 +466,7 @@ done: case IPV6_MULTICAST_IF: if (sk->sk_type == SOCK_STREAM) - goto e_inval; + break; if (optlen < sizeof(int)) goto e_inval; @@ -862,7 +862,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, if (sk->sk_protocol != IPPROTO_UDP && sk->sk_protocol != IPPROTO_UDPLITE && sk->sk_protocol != IPPROTO_TCP) - return -EINVAL; + return -ENOPROTOOPT; if (sk->sk_state != TCP_ESTABLISHED) return -ENOTCONN; val = sk->sk_family; From b66985b11b8b00e1ec65b89a3112510ac9a9ec6e Mon Sep 17 00:00:00 2001 From: Eric Leblond Date: Wed, 11 Jun 2008 17:50:27 -0700 Subject: [PATCH 12/20] netfilter: Make nflog quiet when no one listen in userspace. The message "nf_log_packet: can't log since no backend logging module loaded in! Please either load one, or disable logging explicitly" was displayed for each logged packet when no userspace application is listening to nflog events. The message seems to warn for a problem with a kernel module missing but as said before this is not the case. I thus propose to suppress the message (I don't see any reason to flood the log because a user application has crashed.) Signed-off-by: Eric Leblond Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- net/netfilter/nf_log.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index bc11d7092032..9fda6ee95a31 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -92,10 +92,6 @@ void nf_log_packet(int pf, vsnprintf(prefix, sizeof(prefix), fmt, args); va_end(args); logger->logfn(pf, hooknum, skb, in, out, loginfo, prefix); - } else if (net_ratelimit()) { - printk(KERN_WARNING "nf_log_packet: can\'t log since " - "no backend logging module loaded in! Please either " - "load one, or disable logging explicitly\n"); } rcu_read_unlock(); } From ceeff7541e5a4ba8e8d97ffbae32b3f283cb7a3f Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 11 Jun 2008 17:51:10 -0700 Subject: [PATCH 13/20] netfilter: nf_conntrack: fix ctnetlink related crash in nf_nat_setup_info() When creation of a new conntrack entry in ctnetlink fails after having set up the NAT mappings, the conntrack has an extension area allocated that is not getting properly destroyed when freeing the conntrack again. This means the NAT extension is still in the bysource hash, causing a crash when walking over the hash chain the next time: BUG: unable to handle kernel paging request at 00120fbd IP: [] nf_nat_setup_info+0x221/0x58a *pde = 00000000 Oops: 0000 [#1] PREEMPT SMP Pid: 2795, comm: conntrackd Not tainted (2.6.26-rc5 #1) EIP: 0060:[] EFLAGS: 00010206 CPU: 1 EIP is at nf_nat_setup_info+0x221/0x58a EAX: 00120fbd EBX: 00120fbd ECX: 00000001 EDX: 00000000 ESI: 0000019e EDI: e853bbb4 EBP: e853bbc8 ESP: e853bb78 DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068 Process conntrackd (pid: 2795, ti=e853a000 task=f7de10f0 task.ti=e853a000) Stack: 00000000 e853bc2c e85672ec 00000008 c0561084 63c1db4a 00000000 00000000 00000000 0002e109 61d2b1c3 00000000 00000000 00000000 01114e22 61d2b1c3 00000000 00000000 f7444674 e853bc04 00000008 c038e728 0000000a f7444674 Call Trace: [] nla_parse+0x5c/0xb0 [] ctnetlink_change_status+0x190/0x1c6 [] ctnetlink_new_conntrack+0x189/0x61f [] update_curr+0x3d/0x52 [] nfnetlink_rcv_msg+0xc1/0xd8 [] nfnetlink_rcv_msg+0x18/0xd8 [] nfnetlink_rcv_msg+0x0/0xd8 [] netlink_rcv_skb+0x2d/0x71 [] nfnetlink_rcv+0x19/0x24 [] netlink_unicast+0x1b3/0x216 ... Move invocation of the extension destructors to nf_conntrack_free() to fix this problem. Fixes http://bugzilla.kernel.org/show_bug.cgi?id=10875 Reported-and-Tested-by: Krzysztof Piotr Oledzki Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- net/netfilter/nf_conntrack_core.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index c4b1799da5d7..662c1ccfee26 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -196,8 +196,6 @@ destroy_conntrack(struct nf_conntrack *nfct) if (l4proto && l4proto->destroy) l4proto->destroy(ct); - nf_ct_ext_destroy(ct); - rcu_read_unlock(); spin_lock_bh(&nf_conntrack_lock); @@ -520,6 +518,7 @@ static void nf_conntrack_free_rcu(struct rcu_head *head) void nf_conntrack_free(struct nf_conn *ct) { + nf_ct_ext_destroy(ct); call_rcu(&ct->rcu, nf_conntrack_free_rcu); } EXPORT_SYMBOL_GPL(nf_conntrack_free); From 0761248f08ccd94ddceb5454eb1ad96626b10611 Mon Sep 17 00:00:00 2001 From: Roel Kluin Date: Mon, 9 Jun 2008 16:33:50 -0700 Subject: [PATCH 14/20] ipg: fix receivemode IPG_RM_RECEIVEMULTICAST{,HASH} in ipg_nic_set_multicast_list() The branches are dead code. even when dev->flag IFF_MULTICAST (defined 0x1000) is set, dev->flags & IFF_MULTICAST & [boolean] always evaluates to 0. Signed-off-by: Roel Kluin Cc: Francois Romieu Cc: Jeff Garzik Signed-off-by: Andrew Morton Signed-off-by: Jeff Garzik --- drivers/net/ipg.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ipg.c b/drivers/net/ipg.c index 9b358f61ed7f..679a0826780e 100644 --- a/drivers/net/ipg.c +++ b/drivers/net/ipg.c @@ -577,12 +577,12 @@ static void ipg_nic_set_multicast_list(struct net_device *dev) /* NIC to be configured in promiscuous mode. */ receivemode = IPG_RM_RECEIVEALLFRAMES; } else if ((dev->flags & IFF_ALLMULTI) || - (dev->flags & IFF_MULTICAST & + ((dev->flags & IFF_MULTICAST) && (dev->mc_count > IPG_MULTICAST_HASHTABLE_SIZE))) { /* NIC to be configured to receive all multicast * frames. */ receivemode |= IPG_RM_RECEIVEMULTICAST; - } else if (dev->flags & IFF_MULTICAST & (dev->mc_count > 0)) { + } else if ((dev->flags & IFF_MULTICAST) && (dev->mc_count > 0)) { /* NIC to be configured to receive selected * multicast addresses. */ receivemode |= IPG_RM_RECEIVEMULTICASTHASH; From 8b9835108f68938a5f7e74fd2c0fc65da2abad92 Mon Sep 17 00:00:00 2001 From: Roel Kluin Date: Mon, 9 Jun 2008 16:33:51 -0700 Subject: [PATCH 15/20] fec_mpc52xx: MPC52xx_MESSAGES_DEFAULT: 2nd NETIF_MSG_IFDOWN => IFUP Duplicate NETIF_MSG_IFDOWN, 2nd should be NETIF_MSG_IFUP Signed-off-by: Roel Kluin Acked-by: Sylvain Munaut Cc: Grant Likely Signed-off-by: Andrew Morton Signed-off-by: Jeff Garzik --- drivers/net/fec_mpc52xx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/fec_mpc52xx.c b/drivers/net/fec_mpc52xx.c index 5f9c42e7a7f1..329edd9c08fc 100644 --- a/drivers/net/fec_mpc52xx.c +++ b/drivers/net/fec_mpc52xx.c @@ -78,7 +78,7 @@ module_param_array_named(mac, mpc52xx_fec_mac_addr, byte, NULL, 0); MODULE_PARM_DESC(mac, "six hex digits, ie. 0x1,0x2,0xc0,0x01,0xba,0xbe"); #define MPC52xx_MESSAGES_DEFAULT ( NETIF_MSG_DRV | NETIF_MSG_PROBE | \ - NETIF_MSG_LINK | NETIF_MSG_IFDOWN | NETIF_MSG_IFDOWN ) + NETIF_MSG_LINK | NETIF_MSG_IFDOWN | NETIF_MSG_IFUP) static int debug = -1; /* the above default */ module_param(debug, int, 0); MODULE_PARM_DESC(debug, "debugging messages level"); From 208aefa2451cc1f4d87622cb9b2ca4333afa8337 Mon Sep 17 00:00:00 2001 From: Christophe Jaillet Date: Thu, 15 May 2008 23:26:22 +0200 Subject: [PATCH 16/20] drivers/net/r6040.c: correct bad use of round_jiffies() Compared to other places in the kernel, I think that this driver misuses the function round_jiffies. Signed-off-by: Christophe Jaillet Signed-off-by: Jeff Garzik --- drivers/net/r6040.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/r6040.c b/drivers/net/r6040.c index 169edc154928..858b191517b3 100644 --- a/drivers/net/r6040.c +++ b/drivers/net/r6040.c @@ -733,7 +733,7 @@ static void r6040_timer(unsigned long data) } /* Timer active again */ - mod_timer(&lp->timer, jiffies + round_jiffies(HZ)); + mod_timer(&lp->timer, round_jiffies(jiffies + HZ)); } /* Read/set MAC address routines */ From 4bb073c0e32a0862bdb5215d11af19f6c0180c98 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Thu, 12 Jun 2008 02:22:02 -0700 Subject: [PATCH 17/20] net: Eliminate flush_scheduled_work() calls while RTNL is held. If the RTNL is held when we invoke flush_scheduled_work() we could deadlock. One such case is linkwatch, it is a work struct which tries to grab the RTNL semaphore. The most common case are net driver ->stop() methods. The simplest conversion is to instead use cancel_{delayed_}work_sync() explicitly on the various work struct the driver uses. This is an OK transformation because these work structs are doing things like resetting the chip, restarting link negotiation, and so forth. And if we're bringing down the device, we're about to turn the chip off and reset it anways. So if we cancel a pending work event, that's fine here. Some drivers were working around this deadlock by using a msleep() polling loop of some sort, and those cases are converted to instead use cancel_{delayed_}work_sync() as well. Signed-off-by: David S. Miller --- drivers/net/bnx2.c | 9 +-------- drivers/net/bnx2.h | 1 - drivers/net/ehea/ehea_main.c | 3 ++- drivers/net/hamradio/baycom_epp.c | 2 +- drivers/net/smc911x.c | 24 +++++------------------ drivers/net/smc91x.c | 17 +++------------- drivers/net/tulip/tulip_core.c | 2 +- drivers/net/usb/kaweth.c | 2 +- drivers/net/wireless/hostap/hostap_main.c | 8 +++++++- 9 files changed, 21 insertions(+), 47 deletions(-) diff --git a/drivers/net/bnx2.c b/drivers/net/bnx2.c index 4b46e68183e0..367b6d462708 100644 --- a/drivers/net/bnx2.c +++ b/drivers/net/bnx2.c @@ -5724,14 +5724,12 @@ bnx2_reset_task(struct work_struct *work) if (!netif_running(bp->dev)) return; - bp->in_reset_task = 1; bnx2_netif_stop(bp); bnx2_init_nic(bp); atomic_set(&bp->intr_sem, 1); bnx2_netif_start(bp); - bp->in_reset_task = 0; } static void @@ -5907,12 +5905,7 @@ bnx2_close(struct net_device *dev) struct bnx2 *bp = netdev_priv(dev); u32 reset_code; - /* Calling flush_scheduled_work() may deadlock because - * linkwatch_event() may be on the workqueue and it will try to get - * the rtnl_lock which we are holding. - */ - while (bp->in_reset_task) - msleep(1); + cancel_work_sync(&bp->reset_task); bnx2_disable_int_sync(bp); bnx2_napi_disable(bp); diff --git a/drivers/net/bnx2.h b/drivers/net/bnx2.h index 1eaf5bb3d9c2..2377cc13bf61 100644 --- a/drivers/net/bnx2.h +++ b/drivers/net/bnx2.h @@ -6656,7 +6656,6 @@ struct bnx2 { int current_interval; struct timer_list timer; struct work_struct reset_task; - int in_reset_task; /* Used to synchronize phy accesses. */ spinlock_t phy_lock; diff --git a/drivers/net/ehea/ehea_main.c b/drivers/net/ehea/ehea_main.c index faae01dc1c4b..075fd547421e 100644 --- a/drivers/net/ehea/ehea_main.c +++ b/drivers/net/ehea/ehea_main.c @@ -2605,7 +2605,8 @@ static int ehea_stop(struct net_device *dev) if (netif_msg_ifdown(port)) ehea_info("disabling port %s", dev->name); - flush_scheduled_work(); + cancel_work_sync(&port->reset_task); + mutex_lock(&port->port_lock); netif_stop_queue(dev); port_napi_disable(port); diff --git a/drivers/net/hamradio/baycom_epp.c b/drivers/net/hamradio/baycom_epp.c index dde9c7e6408a..00bc7fbb6b37 100644 --- a/drivers/net/hamradio/baycom_epp.c +++ b/drivers/net/hamradio/baycom_epp.c @@ -959,7 +959,7 @@ static int epp_close(struct net_device *dev) unsigned char tmp[1]; bc->work_running = 0; - flush_scheduled_work(); + cancel_delayed_work_sync(&bc->run_work); bc->stat = EPP_DCDBIT; tmp[0] = 0; pp->ops->epp_write_addr(pp, tmp, 1, 0); diff --git a/drivers/net/smc911x.c b/drivers/net/smc911x.c index 4e2800205189..e2ee91a6ae7e 100644 --- a/drivers/net/smc911x.c +++ b/drivers/net/smc911x.c @@ -136,7 +136,6 @@ struct smc911x_local { /* work queue */ struct work_struct phy_configure; - int work_pending; int tx_throttle; spinlock_t lock; @@ -960,11 +959,11 @@ static void smc911x_phy_configure(struct work_struct *work) * We should not be called if phy_type is zero. */ if (lp->phy_type == 0) - goto smc911x_phy_configure_exit_nolock; + return; if (smc911x_phy_reset(dev, phyaddr)) { printk("%s: PHY reset timed out\n", dev->name); - goto smc911x_phy_configure_exit_nolock; + return; } spin_lock_irqsave(&lp->lock, flags); @@ -1033,8 +1032,6 @@ static void smc911x_phy_configure(struct work_struct *work) smc911x_phy_configure_exit: spin_unlock_irqrestore(&lp->lock, flags); -smc911x_phy_configure_exit_nolock: - lp->work_pending = 0; } /* @@ -1356,11 +1353,8 @@ static void smc911x_timeout(struct net_device *dev) * smc911x_phy_configure() calls msleep() which calls schedule_timeout() * which calls schedule(). Hence we use a work queue. */ - if (lp->phy_type != 0) { - if (schedule_work(&lp->phy_configure)) { - lp->work_pending = 1; - } - } + if (lp->phy_type != 0) + schedule_work(&lp->phy_configure); /* We can accept TX packets again */ dev->trans_start = jiffies; @@ -1531,16 +1525,8 @@ static int smc911x_close(struct net_device *dev) if (lp->phy_type != 0) { /* We need to ensure that no calls to * smc911x_phy_configure are pending. - - * flush_scheduled_work() cannot be called because we - * are running with the netlink semaphore held (from - * devinet_ioctl()) and the pending work queue - * contains linkwatch_event() (scheduled by - * netif_carrier_off() above). linkwatch_event() also - * wants the netlink semaphore. */ - while (lp->work_pending) - schedule(); + cancel_work_sync(&lp->phy_configure); smc911x_phy_powerdown(dev, lp->mii.phy_id); } diff --git a/drivers/net/smc91x.c b/drivers/net/smc91x.c index a188e33484e6..f2051b209da2 100644 --- a/drivers/net/smc91x.c +++ b/drivers/net/smc91x.c @@ -1016,15 +1016,8 @@ static void smc_phy_powerdown(struct net_device *dev) /* We need to ensure that no calls to smc_phy_configure are pending. - - flush_scheduled_work() cannot be called because we are - running with the netlink semaphore held (from - devinet_ioctl()) and the pending work queue contains - linkwatch_event() (scheduled by netif_carrier_off() - above). linkwatch_event() also wants the netlink semaphore. */ - while(lp->work_pending) - yield(); + cancel_work_sync(&lp->phy_configure); bmcr = smc_phy_read(dev, phy, MII_BMCR); smc_phy_write(dev, phy, MII_BMCR, bmcr | BMCR_PDOWN); @@ -1161,7 +1154,6 @@ static void smc_phy_configure(struct work_struct *work) smc_phy_configure_exit: SMC_SELECT_BANK(lp, 2); spin_unlock_irq(&lp->lock); - lp->work_pending = 0; } /* @@ -1389,11 +1381,8 @@ static void smc_timeout(struct net_device *dev) * smc_phy_configure() calls msleep() which calls schedule_timeout() * which calls schedule(). Hence we use a work queue. */ - if (lp->phy_type != 0) { - if (schedule_work(&lp->phy_configure)) { - lp->work_pending = 1; - } - } + if (lp->phy_type != 0) + schedule_work(&lp->phy_configure); /* We can accept TX packets again */ dev->trans_start = jiffies; diff --git a/drivers/net/tulip/tulip_core.c b/drivers/net/tulip/tulip_core.c index 55670b5eb611..af8d2c436efd 100644 --- a/drivers/net/tulip/tulip_core.c +++ b/drivers/net/tulip/tulip_core.c @@ -731,7 +731,7 @@ static void tulip_down (struct net_device *dev) void __iomem *ioaddr = tp->base_addr; unsigned long flags; - flush_scheduled_work(); + cancel_work_sync(&tp->media_work); #ifdef CONFIG_TULIP_NAPI napi_disable(&tp->napi); diff --git a/drivers/net/usb/kaweth.c b/drivers/net/usb/kaweth.c index 0dcfc0310264..7c66b052f55a 100644 --- a/drivers/net/usb/kaweth.c +++ b/drivers/net/usb/kaweth.c @@ -706,7 +706,7 @@ static void kaweth_kill_urbs(struct kaweth_device *kaweth) usb_kill_urb(kaweth->rx_urb); usb_kill_urb(kaweth->tx_urb); - flush_scheduled_work(); + cancel_delayed_work_sync(&kaweth->lowmem_work); /* a scheduled work may have resubmitted, we hit them again */ diff --git a/drivers/net/wireless/hostap/hostap_main.c b/drivers/net/wireless/hostap/hostap_main.c index 20d387f6658c..f7aec9309d04 100644 --- a/drivers/net/wireless/hostap/hostap_main.c +++ b/drivers/net/wireless/hostap/hostap_main.c @@ -682,7 +682,13 @@ static int prism2_close(struct net_device *dev) netif_device_detach(dev); } - flush_scheduled_work(); + cancel_work_sync(&local->reset_queue); + cancel_work_sync(&local->set_multicast_list_queue); + cancel_work_sync(&local->set_tim_queue); +#ifndef PRISM2_NO_STATION_MODES + cancel_work_sync(&local->info_queue); +#endif + cancel_work_sync(&local->comms_qual_update); module_put(local->hw_module); From 24e3fcefb9cc61acce59ed54c00c4e4c32537de7 Mon Sep 17 00:00:00 2001 From: Eilon Greenstein Date: Thu, 12 Jun 2008 14:30:28 -0700 Subject: [PATCH 18/20] bnx2x: Updating the Maintainer I would like to thank Eliezer Tamir for writing and maintaining the driver for the past two years. I will take over maintaining the bnx2x driver from now on. Signed-off-by: Eilon Greenstein Signed-off-by: Eliezer Tamir Signed-off-by: David S. Miller --- MAINTAINERS | 4 ++-- drivers/net/bnx2x.c | 5 +++-- drivers/net/bnx2x.h | 3 ++- drivers/net/bnx2x_init.h | 3 ++- 4 files changed, 9 insertions(+), 6 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index 46fa1797707a..7c8e561dbe19 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -995,8 +995,8 @@ L: netdev@vger.kernel.org S: Supported BROADCOM BNX2X 10 GIGABIT ETHERNET DRIVER -P: Eliezer Tamir -M: eliezert@broadcom.com +P: Eilon Greenstein +M: eilong@broadcom.com L: netdev@vger.kernel.org S: Supported diff --git a/drivers/net/bnx2x.c b/drivers/net/bnx2x.c index 7bdb5af35951..70cba64732ca 100644 --- a/drivers/net/bnx2x.c +++ b/drivers/net/bnx2x.c @@ -6,7 +6,8 @@ * it under the terms of the GNU General Public License as published by * the Free Software Foundation. * - * Written by: Eliezer Tamir + * Maintained by: Eilon Greenstein + * Written by: Eliezer Tamir * Based on code from Michael Chan's bnx2 driver * UDP CSUM errata workaround by Arik Gendelman * Slowpath rework by Vladislav Zolotarov @@ -74,7 +75,7 @@ static char version[] __devinitdata = "Broadcom NetXtreme II 5771X 10Gigabit Ethernet Driver " DRV_MODULE_NAME " " DRV_MODULE_VERSION " (" DRV_MODULE_RELDATE ")\n"; -MODULE_AUTHOR("Eliezer Tamir "); +MODULE_AUTHOR("Eliezer Tamir"); MODULE_DESCRIPTION("Broadcom NetXtreme II BCM57710 Driver"); MODULE_LICENSE("GPL"); MODULE_VERSION(DRV_MODULE_VERSION); diff --git a/drivers/net/bnx2x.h b/drivers/net/bnx2x.h index 4f0c0d31e7c1..8e68d06510a6 100644 --- a/drivers/net/bnx2x.h +++ b/drivers/net/bnx2x.h @@ -6,7 +6,8 @@ * it under the terms of the GNU General Public License as published by * the Free Software Foundation. * - * Written by: Eliezer Tamir + * Maintained by: Eilon Greenstein + * Written by: Eliezer Tamir * Based on code from Michael Chan's bnx2 driver */ diff --git a/drivers/net/bnx2x_init.h b/drivers/net/bnx2x_init.h index dcaecc53bdb1..370686eef97c 100644 --- a/drivers/net/bnx2x_init.h +++ b/drivers/net/bnx2x_init.h @@ -6,7 +6,8 @@ * it under the terms of the GNU General Public License as published by * the Free Software Foundation. * - * Written by: Eliezer Tamir + * Maintained by: Eilon Greenstein + * Written by: Eliezer Tamir */ #ifndef BNX2X_INIT_H From f23d60de719e639690b2dc5c2d0e4243ff614b7a Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Thu, 12 Jun 2008 14:47:58 -0700 Subject: [PATCH 19/20] ipv6: Fix duplicate initialization of rawv6_prot.destroy In changeset 22dd485022f3d0b162ceb5e67d85de7c3806aa20 ("raw: Raw socket leak.") code was added so that we flush pending frames on raw sockets to avoid leaks. The ipv4 part was fine, but the ipv6 part was not done correctly. Unlike the ipv4 side, the ipv6 code already has a .destroy method for rawv6_prot. So now there were two assignments to this member, and what the compiler does is use the last one, effectively making the ipv6 parts of that changeset a NOP. Fix this by removing the: .destroy = inet6_destroy_sock, line, and adding an inet6_destroy_sock() call to the end of raw6_destroy(). Noticed by Al Viro. Signed-off-by: David S. Miller Acked-by: YOSHIFUJI Hideaki --- net/ipv6/raw.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 8fee9a15b2d3..3aee12310d94 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -1169,7 +1169,8 @@ static int raw6_destroy(struct sock *sk) lock_sock(sk); ip6_flush_pending_frames(sk); release_sock(sk); - return 0; + + return inet6_destroy_sock(sk); } static int rawv6_init_sk(struct sock *sk) @@ -1200,7 +1201,6 @@ struct proto rawv6_prot = { .disconnect = udp_disconnect, .ioctl = rawv6_ioctl, .init = rawv6_init_sk, - .destroy = inet6_destroy_sock, .setsockopt = rawv6_setsockopt, .getsockopt = rawv6_getsockopt, .sendmsg = rawv6_sendmsg, From ec0a196626bd12e0ba108d7daa6d95a4fb25c2c5 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Thu, 12 Jun 2008 16:31:35 -0700 Subject: [PATCH 20/20] tcp: Revert 'process defer accept as established' changes. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This reverts two changesets, ec3c0982a2dd1e671bad8e9d26c28dcba0039d87 ("[TCP]: TCP_DEFER_ACCEPT updates - process as established") and the follow-on bug fix 9ae27e0adbf471c7a6b80102e38e1d5a346b3b38 ("tcp: Fix slab corruption with ipv6 and tcp6fuzz"). This change causes several problems, first reported by Ingo Molnar as a distcc-over-loopback regression where connections were getting stuck. Ilpo Järvinen first spotted the locking problems. The new function added by this code, tcp_defer_accept_check(), only has the child socket locked, yet it is modifying state of the parent listening socket. Fixing that is non-trivial at best, because we can't simply just grab the parent listening socket lock at this point, because it would create an ABBA deadlock. The normal ordering is parent listening socket --> child socket, but this code path would require the reverse lock ordering. Next is a problem noticed by Vitaliy Gusev, he noted: ---------------------------------------- >--- a/net/ipv4/tcp_timer.c >+++ b/net/ipv4/tcp_timer.c >@@ -481,6 +481,11 @@ static void tcp_keepalive_timer (unsigned long data) > goto death; > } > >+ if (tp->defer_tcp_accept.request && sk->sk_state == TCP_ESTABLISHED) { >+ tcp_send_active_reset(sk, GFP_ATOMIC); >+ goto death; Here socket sk is not attached to listening socket's request queue. tcp_done() will not call inet_csk_destroy_sock() (and tcp_v4_destroy_sock() which should release this sk) as socket is not DEAD. Therefore socket sk will be lost for freeing. ---------------------------------------- Finally, Alexey Kuznetsov argues that there might not even be any real value or advantage to these new semantics even if we fix all of the bugs: ---------------------------------------- Hiding from accept() sockets with only out-of-order data only is the only thing which is impossible with old approach. Is this really so valuable? My opinion: no, this is nothing but a new loophole to consume memory without control. ---------------------------------------- So revert this thing for now. Signed-off-by: David S. Miller --- include/linux/tcp.h | 7 ----- include/net/request_sock.h | 4 +-- include/net/tcp.h | 1 - net/ipv4/inet_connection_sock.c | 11 +++++--- net/ipv4/tcp.c | 18 ++++++++----- net/ipv4/tcp_input.c | 45 --------------------------------- net/ipv4/tcp_ipv4.c | 8 ------ net/ipv4/tcp_minisocks.c | 32 +++++++++-------------- net/ipv4/tcp_timer.c | 5 ---- 9 files changed, 33 insertions(+), 98 deletions(-) diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 18e62e3d406f..b31b6b74aa28 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -239,11 +239,6 @@ static inline struct tcp_request_sock *tcp_rsk(const struct request_sock *req) return (struct tcp_request_sock *)req; } -struct tcp_deferred_accept_info { - struct sock *listen_sk; - struct request_sock *request; -}; - struct tcp_sock { /* inet_connection_sock has to be the first member of tcp_sock */ struct inet_connection_sock inet_conn; @@ -379,8 +374,6 @@ struct tcp_sock { unsigned int keepalive_intvl; /* time interval between keep alive probes */ int linger2; - struct tcp_deferred_accept_info defer_tcp_accept; - unsigned long last_synq_overflow; u32 tso_deferred; diff --git a/include/net/request_sock.h b/include/net/request_sock.h index b220b5f624de..0c96e7bed5db 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -115,8 +115,8 @@ struct request_sock_queue { struct request_sock *rskq_accept_head; struct request_sock *rskq_accept_tail; rwlock_t syn_wait_lock; - u16 rskq_defer_accept; - /* 2 bytes hole, try to pack */ + u8 rskq_defer_accept; + /* 3 bytes hole, try to pack */ struct listen_sock *listen_opt; }; diff --git a/include/net/tcp.h b/include/net/tcp.h index d448310c82c1..cf54034019d9 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -139,7 +139,6 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo); #define MAX_TCP_KEEPINTVL 32767 #define MAX_TCP_KEEPCNT 127 #define MAX_TCP_SYNCNT 127 -#define MAX_TCP_ACCEPT_DEFERRED 65535 #define TCP_SYNQ_INTERVAL (HZ/5) /* Period of SYNACK timer */ diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 828ea211ff21..045e799d3e1d 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -419,7 +419,8 @@ void inet_csk_reqsk_queue_prune(struct sock *parent, struct inet_connection_sock *icsk = inet_csk(parent); struct request_sock_queue *queue = &icsk->icsk_accept_queue; struct listen_sock *lopt = queue->listen_opt; - int thresh = icsk->icsk_syn_retries ? : sysctl_tcp_synack_retries; + int max_retries = icsk->icsk_syn_retries ? : sysctl_tcp_synack_retries; + int thresh = max_retries; unsigned long now = jiffies; struct request_sock **reqp, *req; int i, budget; @@ -455,6 +456,9 @@ void inet_csk_reqsk_queue_prune(struct sock *parent, } } + if (queue->rskq_defer_accept) + max_retries = queue->rskq_defer_accept; + budget = 2 * (lopt->nr_table_entries / (timeout / interval)); i = lopt->clock_hand; @@ -462,8 +466,9 @@ void inet_csk_reqsk_queue_prune(struct sock *parent, reqp=&lopt->syn_table[i]; while ((req = *reqp) != NULL) { if (time_after_eq(now, req->expires)) { - if (req->retrans < thresh && - !req->rsk_ops->rtx_syn_ack(parent, req)) { + if ((req->retrans < (inet_rsk(req)->acked ? max_retries : thresh)) && + (inet_rsk(req)->acked || + !req->rsk_ops->rtx_syn_ack(parent, req))) { unsigned long timeo; if (req->retrans++ == 0) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index ab66683b8043..fc54a48fde1e 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2112,12 +2112,15 @@ static int do_tcp_setsockopt(struct sock *sk, int level, break; case TCP_DEFER_ACCEPT: - if (val < 0) { - err = -EINVAL; - } else { - if (val > MAX_TCP_ACCEPT_DEFERRED) - val = MAX_TCP_ACCEPT_DEFERRED; - icsk->icsk_accept_queue.rskq_defer_accept = val; + icsk->icsk_accept_queue.rskq_defer_accept = 0; + if (val > 0) { + /* Translate value in seconds to number of + * retransmits */ + while (icsk->icsk_accept_queue.rskq_defer_accept < 32 && + val > ((TCP_TIMEOUT_INIT / HZ) << + icsk->icsk_accept_queue.rskq_defer_accept)) + icsk->icsk_accept_queue.rskq_defer_accept++; + icsk->icsk_accept_queue.rskq_defer_accept++; } break; @@ -2299,7 +2302,8 @@ static int do_tcp_getsockopt(struct sock *sk, int level, val = (val ? : sysctl_tcp_fin_timeout) / HZ; break; case TCP_DEFER_ACCEPT: - val = icsk->icsk_accept_queue.rskq_defer_accept; + val = !icsk->icsk_accept_queue.rskq_defer_accept ? 0 : + ((TCP_TIMEOUT_INIT / HZ) << (icsk->icsk_accept_queue.rskq_defer_accept - 1)); break; case TCP_WINDOW_CLAMP: val = tp->window_clamp; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index eba873e9b560..cad73b7dfef0 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4541,49 +4541,6 @@ static void tcp_urg(struct sock *sk, struct sk_buff *skb, struct tcphdr *th) } } -static int tcp_defer_accept_check(struct sock *sk) -{ - struct tcp_sock *tp = tcp_sk(sk); - - if (tp->defer_tcp_accept.request) { - int queued_data = tp->rcv_nxt - tp->copied_seq; - int hasfin = !skb_queue_empty(&sk->sk_receive_queue) ? - tcp_hdr((struct sk_buff *) - sk->sk_receive_queue.prev)->fin : 0; - - if (queued_data && hasfin) - queued_data--; - - if (queued_data && - tp->defer_tcp_accept.listen_sk->sk_state == TCP_LISTEN) { - if (sock_flag(sk, SOCK_KEEPOPEN)) { - inet_csk_reset_keepalive_timer(sk, - keepalive_time_when(tp)); - } else { - inet_csk_delete_keepalive_timer(sk); - } - - inet_csk_reqsk_queue_add( - tp->defer_tcp_accept.listen_sk, - tp->defer_tcp_accept.request, - sk); - - tp->defer_tcp_accept.listen_sk->sk_data_ready( - tp->defer_tcp_accept.listen_sk, 0); - - sock_put(tp->defer_tcp_accept.listen_sk); - sock_put(sk); - tp->defer_tcp_accept.listen_sk = NULL; - tp->defer_tcp_accept.request = NULL; - } else if (hasfin || - tp->defer_tcp_accept.listen_sk->sk_state != TCP_LISTEN) { - tcp_reset(sk); - return -1; - } - } - return 0; -} - static int tcp_copy_to_iovec(struct sock *sk, struct sk_buff *skb, int hlen) { struct tcp_sock *tp = tcp_sk(sk); @@ -4944,8 +4901,6 @@ step5: tcp_data_snd_check(sk); tcp_ack_snd_check(sk); - - tcp_defer_accept_check(sk); return 0; csum_error: diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 4f8485c67d1a..97a230026e13 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1918,14 +1918,6 @@ int tcp_v4_destroy_sock(struct sock *sk) sk->sk_sndmsg_page = NULL; } - if (tp->defer_tcp_accept.request) { - reqsk_free(tp->defer_tcp_accept.request); - sock_put(tp->defer_tcp_accept.listen_sk); - sock_put(sk); - tp->defer_tcp_accept.listen_sk = NULL; - tp->defer_tcp_accept.request = NULL; - } - atomic_dec(&tcp_sockets_allocated); return 0; diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 019c8c16e5cc..8245247a6ceb 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -571,8 +571,10 @@ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb, does sequence test, SYN is truncated, and thus we consider it a bare ACK. - Both ends (listening sockets) accept the new incoming - connection and try to talk to each other. 8-) + If icsk->icsk_accept_queue.rskq_defer_accept, we silently drop this + bare ACK. Otherwise, we create an established connection. Both + ends (listening sockets) accept the new incoming connection and try + to talk to each other. 8-) Note: This case is both harmless, and rare. Possibility is about the same as us discovering intelligent life on another plant tomorrow. @@ -640,6 +642,13 @@ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb, if (!(flg & TCP_FLAG_ACK)) return NULL; + /* If TCP_DEFER_ACCEPT is set, drop bare ACK. */ + if (inet_csk(sk)->icsk_accept_queue.rskq_defer_accept && + TCP_SKB_CB(skb)->end_seq == tcp_rsk(req)->rcv_isn + 1) { + inet_rsk(req)->acked = 1; + return NULL; + } + /* OK, ACK is valid, create big socket and * feed this segment to it. It will repeat all * the tests. THIS SEGMENT MUST MOVE SOCKET TO @@ -678,24 +687,7 @@ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb, inet_csk_reqsk_queue_unlink(sk, req, prev); inet_csk_reqsk_queue_removed(sk, req); - if (inet_csk(sk)->icsk_accept_queue.rskq_defer_accept && - TCP_SKB_CB(skb)->end_seq == tcp_rsk(req)->rcv_isn + 1) { - - /* the accept queue handling is done is est recv slow - * path so lets make sure to start there - */ - tcp_sk(child)->pred_flags = 0; - sock_hold(sk); - sock_hold(child); - tcp_sk(child)->defer_tcp_accept.listen_sk = sk; - tcp_sk(child)->defer_tcp_accept.request = req; - - inet_csk_reset_keepalive_timer(child, - inet_csk(sk)->icsk_accept_queue.rskq_defer_accept * HZ); - } else { - inet_csk_reqsk_queue_add(sk, req, child); - } - + inet_csk_reqsk_queue_add(sk, req, child); return child; listen_overflow: diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 4de68cf5f2aa..63ed9d6830e7 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -489,11 +489,6 @@ static void tcp_keepalive_timer (unsigned long data) goto death; } - if (tp->defer_tcp_accept.request && sk->sk_state == TCP_ESTABLISHED) { - tcp_send_active_reset(sk, GFP_ATOMIC); - goto death; - } - if (!sock_flag(sk, SOCK_KEEPOPEN) || sk->sk_state == TCP_CLOSE) goto out;