From 64b0812b6d26bb30cac74c65f51f4ebfb4ec5429 Mon Sep 17 00:00:00 2001 From: Wei Yongjun Date: Mon, 15 Oct 2007 11:50:38 +0900 Subject: [PATCH 01/45] SCTP : Fix bad formatted comment in outqueue.c Just fix the bad format of the comment in outqueue.c. Signed-off-by: Wei Yongjun Signed-off-by: Vlad Yasevich --- net/sctp/outqueue.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 28f4fe77ceee..e315c6c756ca 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -641,7 +641,8 @@ static int sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt, /* If we are here due to a retransmit timeout or a fast * retransmit and if there are any chunks left in the retransmit - * queue that could not fit in the PMTU sized packet, they need * to be marked as ineligible for a subsequent fast retransmit. + * queue that could not fit in the PMTU sized packet, they need + * to be marked as ineligible for a subsequent fast retransmit. */ if (rtx_timeout && !lchunk) { list_for_each(lchunk1, lqueue) { From f3830ccc2ea503ab37d605f6c313d61423ddd94e Mon Sep 17 00:00:00 2001 From: Wei Yongjun Date: Mon, 15 Oct 2007 11:51:03 +0900 Subject: [PATCH 02/45] SCTP : Fix to process bundled ASCONF chunk correctly If ASCONF chunk is bundled with other chunks as the first chunk, when process the ASCONF parameters, full packet data will be process as the parameters of the ASCONF chunk, not only the real parameters. So if you send a ASCONF chunk bundled with other chunks, you will get an unexpect result. This problem also exists when ASCONF-ACK chunk is bundled with other chunks. This patch fix this problem. Signed-off-by: Wei Yongjun Signed-off-by: Vlad Yasevich --- net/sctp/sm_make_chunk.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index c377e4e8f653..5de4729fe993 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -2848,10 +2848,11 @@ struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc, __be16 err_code; int length = 0; - int chunk_len = asconf->skb->len; + int chunk_len; __u32 serial; int all_param_pass = 1; + chunk_len = ntohs(asconf->chunk_hdr->length) - sizeof(sctp_chunkhdr_t); hdr = (sctp_addiphdr_t *)asconf->skb->data; serial = ntohl(hdr->serial); @@ -2990,7 +2991,7 @@ static __be16 sctp_get_asconf_response(struct sctp_chunk *asconf_ack, sctp_addip_param_t *asconf_ack_param; sctp_errhdr_t *err_param; int length; - int asconf_ack_len = asconf_ack->skb->len; + int asconf_ack_len; __be16 err_code; if (no_err) @@ -2998,6 +2999,9 @@ static __be16 sctp_get_asconf_response(struct sctp_chunk *asconf_ack, else err_code = SCTP_ERROR_REQ_REFUSED; + asconf_ack_len = ntohs(asconf_ack->chunk_hdr->length) - + sizeof(sctp_chunkhdr_t); + /* Skip the addiphdr from the asconf_ack chunk and store a pointer to * the first asconf_ack parameter. */ From b6157d8e03e1e780660a328f7183bcbfa4a93a19 Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Wed, 24 Oct 2007 15:59:16 -0400 Subject: [PATCH 03/45] SCTP: Fix difference cases of retransmit. Commit d0ce92910bc04e107b2f3f2048f07e94f570035d broke several retransmit cases including fast retransmit. The reason is that we should only delay by rto while doing retranmists as a result of a timeout. Retransmit as a result of path mtu discover, fast retransmit, or other evernts that should trigger immidiate retransmissions got broken. Also, since rto is doubled prior to marking of packets elegable for retransmission, we never marked correct chunks anyway. The fix is provide a reason for a given retransmission so that we can mark chunks appropriately and to save the old rto value to do comparisons against. All regressions tests passed with this code. Spotted by Wei Yongjun Signed-off-by: Vlad Yasevich --- include/net/sctp/command.h | 1 + include/net/sctp/constants.h | 1 + include/net/sctp/sctp.h | 1 + include/net/sctp/structs.h | 5 +++-- net/sctp/outqueue.c | 33 +++++++++++++++++---------------- net/sctp/sm_sideeffect.c | 10 +++++++++- net/sctp/sm_statefuns.c | 2 +- net/sctp/transport.c | 5 +++-- 8 files changed, 36 insertions(+), 22 deletions(-) diff --git a/include/net/sctp/command.h b/include/net/sctp/command.h index b8733364557f..c1f797673571 100644 --- a/include/net/sctp/command.h +++ b/include/net/sctp/command.h @@ -103,6 +103,7 @@ typedef enum { SCTP_CMD_ASSOC_CHANGE, /* generate and send assoc_change event */ SCTP_CMD_ADAPTATION_IND, /* generate and send adaptation event */ SCTP_CMD_ASSOC_SHKEY, /* generate the association shared keys */ + SCTP_CMD_T1_RETRAN, /* Mark for retransmission after T1 timeout */ SCTP_CMD_LAST } sctp_verb_t; diff --git a/include/net/sctp/constants.h b/include/net/sctp/constants.h index da8354e8e33c..73fbdf6a24f8 100644 --- a/include/net/sctp/constants.h +++ b/include/net/sctp/constants.h @@ -407,6 +407,7 @@ typedef enum { SCTP_RTXR_T3_RTX, SCTP_RTXR_FAST_RTX, SCTP_RTXR_PMTUD, + SCTP_RTXR_T1_RTX, } sctp_retransmit_reason_t; /* Reasons to lower cwnd. */ diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index 93eb708609e7..70827305f501 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -267,6 +267,7 @@ enum SCTP_MIB_T5_SHUTDOWN_GUARD_EXPIREDS, SCTP_MIB_DELAY_SACK_EXPIREDS, SCTP_MIB_AUTOCLOSE_EXPIREDS, + SCTP_MIB_T1_RETRANSMITS, SCTP_MIB_T3_RETRANSMITS, SCTP_MIB_PMTUD_RETRANSMITS, SCTP_MIB_FAST_RETRANSMITS, diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index ef892e00c833..482c2aab3d67 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -873,10 +873,11 @@ struct sctp_transport { * address list derived from the INIT or INIT ACK chunk, a * number of data elements needs to be maintained including: */ - __u32 rtt; /* This is the most recent RTT. */ - /* RTO : The current retransmission timeout value. */ unsigned long rto; + unsigned long last_rto; + + __u32 rtt; /* This is the most recent RTT. */ /* RTTVAR : The current RTT variation. */ __u32 rttvar; diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index e315c6c756ca..99a3db5d5fae 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -382,7 +382,7 @@ static void sctp_insert_list(struct list_head *head, struct list_head *new) /* Mark all the eligible packets on a transport for retransmission. */ void sctp_retransmit_mark(struct sctp_outq *q, struct sctp_transport *transport, - __u8 fast_retransmit) + __u8 reason) { struct list_head *lchunk, *ltemp; struct sctp_chunk *chunk; @@ -412,20 +412,20 @@ void sctp_retransmit_mark(struct sctp_outq *q, continue; } - /* If we are doing retransmission due to a fast retransmit, - * only the chunk's that are marked for fast retransmit - * should be added to the retransmit queue. If we are doing - * retransmission due to a timeout or pmtu discovery, only the - * chunks that are not yet acked should be added to the - * retransmit queue. + /* If we are doing retransmission due to a timeout or pmtu + * discovery, only the chunks that are not yet acked should + * be added to the retransmit queue. */ - if ((fast_retransmit && (chunk->fast_retransmit > 0)) || - (!fast_retransmit && !chunk->tsn_gap_acked)) { + if ((reason == SCTP_RTXR_FAST_RTX && + (chunk->fast_retransmit > 0)) || + (reason != SCTP_RTXR_FAST_RTX && !chunk->tsn_gap_acked)) { /* If this chunk was sent less then 1 rto ago, do not * retransmit this chunk, but give the peer time - * to acknowlege it. + * to acknowlege it. Do this only when + * retransmitting due to T3 timeout. */ - if ((jiffies - chunk->sent_at) < transport->rto) + if (reason == SCTP_RTXR_T3_RTX && + (jiffies - chunk->sent_at) < transport->last_rto) continue; /* RFC 2960 6.2.1 Processing a Received SACK @@ -467,10 +467,10 @@ void sctp_retransmit_mark(struct sctp_outq *q, } } - SCTP_DEBUG_PRINTK("%s: transport: %p, fast_retransmit: %d, " + SCTP_DEBUG_PRINTK("%s: transport: %p, reason: %d, " "cwnd: %d, ssthresh: %d, flight_size: %d, " "pba: %d\n", __FUNCTION__, - transport, fast_retransmit, + transport, reason, transport->cwnd, transport->ssthresh, transport->flight_size, transport->partial_bytes_acked); @@ -484,7 +484,6 @@ void sctp_retransmit(struct sctp_outq *q, struct sctp_transport *transport, sctp_retransmit_reason_t reason) { int error = 0; - __u8 fast_retransmit = 0; switch(reason) { case SCTP_RTXR_T3_RTX: @@ -499,16 +498,18 @@ void sctp_retransmit(struct sctp_outq *q, struct sctp_transport *transport, case SCTP_RTXR_FAST_RTX: SCTP_INC_STATS(SCTP_MIB_FAST_RETRANSMITS); sctp_transport_lower_cwnd(transport, SCTP_LOWER_CWND_FAST_RTX); - fast_retransmit = 1; break; case SCTP_RTXR_PMTUD: SCTP_INC_STATS(SCTP_MIB_PMTUD_RETRANSMITS); break; + case SCTP_RTXR_T1_RTX: + SCTP_INC_STATS(SCTP_MIB_T1_RETRANSMITS); + break; default: BUG(); } - sctp_retransmit_mark(q, transport, fast_retransmit); + sctp_retransmit_mark(q, transport, reason); /* PR-SCTP A5) Any time the T3-rtx timer expires, on any destination, * the sender SHOULD try to advance the "Advanced.Peer.Ack.Point" by diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index bbdc938da86f..78d1a8a49bd0 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -453,6 +453,7 @@ static void sctp_do_8_2_transport_strike(struct sctp_association *asoc, * maximum value discussed in rule C7 above (RTO.max) may be * used to provide an upper bound to this doubling operation. */ + transport->last_rto = transport->rto; transport->rto = min((transport->rto * 2), transport->asoc->rto_max); } @@ -1267,6 +1268,12 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, sctp_ootb_pkt_free(packet); break; + case SCTP_CMD_T1_RETRAN: + /* Mark a transport for retransmission. */ + sctp_retransmit(&asoc->outqueue, cmd->obj.transport, + SCTP_RTXR_T1_RTX); + break; + case SCTP_CMD_RETRAN: /* Mark a transport for retransmission. */ sctp_retransmit(&asoc->outqueue, cmd->obj.transport, @@ -1393,7 +1400,8 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, list_for_each(pos, &asoc->peer.transport_addr_list) { t = list_entry(pos, struct sctp_transport, transports); - sctp_retransmit_mark(&asoc->outqueue, t, 0); + sctp_retransmit_mark(&asoc->outqueue, t, + SCTP_RTXR_T1_RTX); } sctp_add_cmd_sf(commands, diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index f01b408508ff..a66075a70f29 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -2305,7 +2305,7 @@ static sctp_disposition_t sctp_sf_do_5_2_6_stale(const struct sctp_endpoint *ep, /* If we've sent any data bundled with COOKIE-ECHO we will need to * resend */ - sctp_add_cmd_sf(commands, SCTP_CMD_RETRAN, + sctp_add_cmd_sf(commands, SCTP_CMD_T1_RETRAN, SCTP_TRANSPORT(asoc->peer.primary_path)); /* Cast away the const modifier, as we want to just diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 5f467c914f80..d55ce83a020b 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -74,8 +74,8 @@ static struct sctp_transport *sctp_transport_init(struct sctp_transport *peer, * given destination transport address, set RTO to the protocol * parameter 'RTO.Initial'. */ + peer->last_rto = peer->rto = msecs_to_jiffies(sctp_rto_initial); peer->rtt = 0; - peer->rto = msecs_to_jiffies(sctp_rto_initial); peer->rttvar = 0; peer->srtt = 0; peer->rto_pending = 0; @@ -385,6 +385,7 @@ void sctp_transport_update_rto(struct sctp_transport *tp, __u32 rtt) tp->rto = tp->asoc->rto_max; tp->rtt = rtt; + tp->last_rto = tp->rto; /* Reset rto_pending so that a new RTT measurement is started when a * new data chunk is sent. @@ -578,7 +579,7 @@ void sctp_transport_reset(struct sctp_transport *t) */ t->cwnd = min(4*asoc->pathmtu, max_t(__u32, 2*asoc->pathmtu, 4380)); t->ssthresh = asoc->peer.i.a_rwnd; - t->rto = asoc->rto_initial; + t->last_rto = t->rto = asoc->rto_initial; t->rtt = 0; t->srtt = 0; t->rttvar = 0; From 0ed90fb0f668fd07f14ae2007a809e8b26cd27a6 Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Wed, 24 Oct 2007 16:10:00 -0400 Subject: [PATCH 04/45] SCTP: Update RCU handling during the ADD-IP case After learning more about rcu, it looks like the ADD-IP hadling doesn't need to call call_rcu_bh. All the rcu critical sections use rcu_read_lock, so using call_rcu_bh is wrong here. Now, restore the local_bh_disable() code blocks and use normal call_rcu() calls. Also restore the missing return statement. Signed-off-by: Vlad Yasevich --- include/net/sctp/structs.h | 4 +--- net/sctp/bind_addr.c | 13 +++---------- net/sctp/sm_make_chunk.c | 6 +++++- net/sctp/socket.c | 2 +- 4 files changed, 10 insertions(+), 15 deletions(-) diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 482c2aab3d67..a17701740624 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -1185,9 +1185,7 @@ int sctp_bind_addr_copy(struct sctp_bind_addr *dest, int flags); int sctp_add_bind_addr(struct sctp_bind_addr *, union sctp_addr *, __u8 use_as_src, gfp_t gfp); -int sctp_del_bind_addr(struct sctp_bind_addr *, union sctp_addr *, - void fastcall (*rcu_call)(struct rcu_head *, - void (*func)(struct rcu_head *))); +int sctp_del_bind_addr(struct sctp_bind_addr *, union sctp_addr *); int sctp_bind_addr_match(struct sctp_bind_addr *, const union sctp_addr *, struct sctp_sock *); union sctp_addr *sctp_find_unmatch_addr(struct sctp_bind_addr *bp, diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c index dfffa94fb9f6..cae95af9a8cc 100644 --- a/net/sctp/bind_addr.c +++ b/net/sctp/bind_addr.c @@ -180,9 +180,7 @@ int sctp_add_bind_addr(struct sctp_bind_addr *bp, union sctp_addr *new, /* Delete an address from the bind address list in the SCTP_bind_addr * structure. */ -int sctp_del_bind_addr(struct sctp_bind_addr *bp, union sctp_addr *del_addr, - void fastcall (*rcu_call)(struct rcu_head *head, - void (*func)(struct rcu_head *head))) +int sctp_del_bind_addr(struct sctp_bind_addr *bp, union sctp_addr *del_addr) { struct sctp_sockaddr_entry *addr, *temp; @@ -198,15 +196,10 @@ int sctp_del_bind_addr(struct sctp_bind_addr *bp, union sctp_addr *del_addr, } } - /* Call the rcu callback provided in the args. This function is - * called by both BH packet processing and user side socket option - * processing, but it works on different lists in those 2 contexts. - * Each context provides it's own callback, whether call_rcu_bh() - * or call_rcu(), to make sure that we wait for an appropriate time. - */ if (addr && !addr->valid) { - rcu_call(&addr->rcu, sctp_local_addr_free); + call_rcu(&addr->rcu, sctp_local_addr_free); SCTP_DBG_OBJCNT_DEC(addr); + return 0; } return -EINVAL; diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 5de4729fe993..c60564dd169d 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -2953,13 +2953,17 @@ static int sctp_asconf_param_success(struct sctp_association *asoc, /* This is always done in BH context with a socket lock * held, so the list can not change. */ + local_bh_disable(); list_for_each_entry(saddr, &bp->address_list, list) { if (sctp_cmp_addr_exact(&saddr->a, &addr)) saddr->use_as_src = 1; } + local_bh_enable(); break; case SCTP_PARAM_DEL_IP: - retval = sctp_del_bind_addr(bp, &addr, call_rcu_bh); + local_bh_disable(); + retval = sctp_del_bind_addr(bp, &addr); + local_bh_enable(); list_for_each(pos, &asoc->peer.transport_addr_list) { transport = list_entry(pos, struct sctp_transport, transports); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index a7ecf3159e53..6ce9b490fad5 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -660,7 +660,7 @@ static int sctp_bindx_rem(struct sock *sk, struct sockaddr *addrs, int addrcnt) * socket routing and failover schemes. Refer to comments in * sctp_do_bind(). -daisy */ - retval = sctp_del_bind_addr(bp, sa_addr, call_rcu); + retval = sctp_del_bind_addr(bp, sa_addr); addr_buf += af->sockaddr_len; err_bindx_rem: From 88799fe5ec65fad1d5cb1d4dc5d8f78edb949f1c Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Wed, 24 Oct 2007 17:24:23 -0400 Subject: [PATCH 05/45] SCTP: Correctly disable ADD-IP when AUTH is not supported. Signed-off-by: Vlad Yasevich --- include/net/sctp/structs.h | 1 - net/sctp/associola.c | 2 +- net/sctp/sm_make_chunk.c | 5 +++-- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index a17701740624..41f1039186dd 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -1540,7 +1540,6 @@ struct sctp_association { __u8 asconf_capable; /* Does peer support ADDIP? */ __u8 prsctp_capable; /* Can peer do PR-SCTP? */ __u8 auth_capable; /* Is peer doing SCTP-AUTH? */ - __u8 addip_capable; /* Can peer do ADD-IP */ __u32 adaptation_ind; /* Adaptation Code point. */ diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 03158e3665da..eaad5c5535a8 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -265,7 +265,7 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a /* Assume that the peer recongizes ASCONF until reported otherwise * via an ERROR chunk. */ - asoc->peer.asconf_capable = 1; + asoc->peer.asconf_capable = 0; /* Create an input queue. */ sctp_inq_init(&asoc->base.inqueue); diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index c60564dd169d..2ff3a3df049d 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -1847,7 +1847,7 @@ static void sctp_process_ext_param(struct sctp_association *asoc, break; case SCTP_CID_ASCONF: case SCTP_CID_ASCONF_ACK: - asoc->peer.addip_capable = 1; + asoc->peer.asconf_capable = 1; break; default: break; @@ -2138,10 +2138,11 @@ int sctp_process_init(struct sctp_association *asoc, sctp_cid_t cid, /* If the peer claims support for ADD-IP without support * for AUTH, disable support for ADD-IP. */ - if (asoc->peer.addip_capable && !asoc->peer.auth_capable) { + if (asoc->peer.asconf_capable && !asoc->peer.auth_capable) { asoc->peer.addip_disabled_mask |= (SCTP_PARAM_ADD_IP | SCTP_PARAM_DEL_IP | SCTP_PARAM_SET_PRIMARY); + asoc->peer.asconf_capable = 0; } /* Walk list of transports, removing transports in the UNKNOWN state. */ From 73d9c4fd1a6ec4950b2eac8135d35506bf400d6c Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Wed, 24 Oct 2007 17:24:26 -0400 Subject: [PATCH 06/45] SCTP: Allow ADD_IP to work with AUTH for backward compatibility. This patch adds a tunable that will allow ADD_IP to work without AUTH for backward compatibility. The default value is off since the default value for ADD_IP is off as well. People who need to use ADD-IP with older implementations take risks of connection hijacking and should consider upgrading or turning this tunable on. Signed-off-by: Vlad Yasevich --- include/net/sctp/structs.h | 2 ++ net/sctp/associola.c | 8 ++++++-- net/sctp/protocol.c | 1 + net/sctp/sm_make_chunk.c | 4 +++- net/sctp/sysctl.c | 9 +++++++++ 5 files changed, 21 insertions(+), 3 deletions(-) diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 41f1039186dd..44f2672859e2 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -212,6 +212,7 @@ extern struct sctp_globals { /* Flag to indicate if addip is enabled. */ int addip_enable; + int addip_noauth_enable; /* Flag to indicate if PR-SCTP is enabled. */ int prsctp_enable; @@ -249,6 +250,7 @@ extern struct sctp_globals { #define sctp_local_addr_list (sctp_globals.local_addr_list) #define sctp_local_addr_lock (sctp_globals.addr_list_lock) #define sctp_addip_enable (sctp_globals.addip_enable) +#define sctp_addip_noauth (sctp_globals.addip_noauth_enable) #define sctp_prsctp_enable (sctp_globals.prsctp_enable) #define sctp_auth_enable (sctp_globals.auth_enable) diff --git a/net/sctp/associola.c b/net/sctp/associola.c index eaad5c5535a8..013e3d3ab0f1 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -262,10 +262,14 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a */ asoc->peer.sack_needed = 1; - /* Assume that the peer recongizes ASCONF until reported otherwise - * via an ERROR chunk. + /* Assume that the peer will tell us if he recognizes ASCONF + * as part of INIT exchange. + * The sctp_addip_noauth option is there for backward compatibilty + * and will revert old behavior. */ asoc->peer.asconf_capable = 0; + if (sctp_addip_noauth) + asoc->peer.asconf_capable = 1; /* Create an input queue. */ sctp_inq_init(&asoc->base.inqueue); diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 40c1a47d1b8d..ecfab0344e73 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -1179,6 +1179,7 @@ SCTP_STATIC __init int sctp_init(void) /* Disable ADDIP by default. */ sctp_addip_enable = 0; + sctp_addip_noauth = 0; /* Enable PR-SCTP by default. */ sctp_prsctp_enable = 1; diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 2ff3a3df049d..43e8de1228f9 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -2137,8 +2137,10 @@ int sctp_process_init(struct sctp_association *asoc, sctp_cid_t cid, /* If the peer claims support for ADD-IP without support * for AUTH, disable support for ADD-IP. + * Do this only if backward compatible mode is turned off. */ - if (asoc->peer.asconf_capable && !asoc->peer.auth_capable) { + if (!sctp_addip_noauth && + (asoc->peer.asconf_capable && !asoc->peer.auth_capable)) { asoc->peer.addip_disabled_mask |= (SCTP_PARAM_ADD_IP | SCTP_PARAM_DEL_IP | SCTP_PARAM_SET_PRIMARY); diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index 0669778e4335..da4f15734fb1 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -263,6 +263,15 @@ static ctl_table sctp_table[] = { .proc_handler = &proc_dointvec, .strategy = &sysctl_intvec }, + { + .ctl_name = CTL_UNNUMBERED, + .procname = "addip_noauth_enable", + .data = &sctp_addip_noauth, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + .strategy = &sysctl_intvec + }, { .ctl_name = 0 } }; From 027f6e1ad32de32f9fe1c61d0f744e329e8acfd9 Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Wed, 7 Nov 2007 11:39:27 -0500 Subject: [PATCH 07/45] SCTP: Fix a potential race between timers and receive path. There is a possible race condition where the timer code will free the association and the next packet in the queue will also attempt to free the same association. The example is, when we receive an ABORT at about the same time as the retransmission timer fires. If the timer wins the race, it will free the association. Once it releases the lock, the queue processing will recieve the ABORT and will try to free the association again. Signed-off-by: Vlad Yasevich --- net/sctp/inqueue.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c index f10fe7fbf24c..cf4b7eb023b3 100644 --- a/net/sctp/inqueue.c +++ b/net/sctp/inqueue.c @@ -90,6 +90,10 @@ void sctp_inq_free(struct sctp_inq *queue) void sctp_inq_push(struct sctp_inq *q, struct sctp_chunk *chunk) { /* Directly call the packet handling routine. */ + if (chunk->rcvr->dead) { + sctp_chunk_free(chunk); + return; + } /* We are now calling this either from the soft interrupt * or from the backlog processing. From 123ed979eaa8de0dd2422862d247469eda0bd645 Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Fri, 9 Nov 2007 11:41:36 -0500 Subject: [PATCH 08/45] SCTP: Use hashed lookup when looking for an association. A SCTP endpoint may have a lot of associations on them and walking the list is fairly inefficient. Instead, use a hashed lookup, and filter out the hash list based on the endopoing we already have. Signed-off-by: Vlad Yasevich --- net/sctp/endpointola.c | 40 +++++++++++++++++++++++++--------------- 1 file changed, 25 insertions(+), 15 deletions(-) diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c index 2d2d81ef4a69..68f0556efcc6 100644 --- a/net/sctp/endpointola.c +++ b/net/sctp/endpointola.c @@ -328,24 +328,34 @@ static struct sctp_association *__sctp_endpoint_lookup_assoc( const union sctp_addr *paddr, struct sctp_transport **transport) { + struct sctp_association *asoc = NULL; + struct sctp_transport *t = NULL; + struct sctp_hashbucket *head; + struct sctp_ep_common *epb; + int hash; int rport; - struct sctp_association *asoc; - struct list_head *pos; - - rport = ntohs(paddr->v4.sin_port); - - list_for_each(pos, &ep->asocs) { - asoc = list_entry(pos, struct sctp_association, asocs); - if (rport == asoc->peer.port) { - *transport = sctp_assoc_lookup_paddr(asoc, paddr); - - if (*transport) - return asoc; - } - } *transport = NULL; - return NULL; + rport = ntohs(paddr->v4.sin_port); + + hash = sctp_assoc_hashfn(ep->base.bind_addr.port, rport); + head = &sctp_assoc_hashtable[hash]; + read_lock(&head->lock); + for (epb = head->chain; epb; epb = epb->next) { + asoc = sctp_assoc(epb); + if (asoc->ep != ep || rport != asoc->peer.port) + goto next; + + t = sctp_assoc_lookup_paddr(asoc, paddr); + if (t) { + *transport = t; + break; + } +next: + asoc = NULL; + } + read_unlock(&head->lock); + return asoc; } /* Lookup association on an endpoint based on a peer address. BH-safe. */ From d970dbf8455eb1b8cebd3cde6e18f73dd1b3ce38 Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Fri, 9 Nov 2007 11:43:40 -0500 Subject: [PATCH 09/45] SCTP: Convert custom hash lists to use hlist. Convert the custom hash list traversals to use hlist functions. Signed-off-by: Vlad Yasevich --- include/net/sctp/sctp.h | 3 +++ include/net/sctp/structs.h | 10 ++++----- net/sctp/endpointola.c | 3 ++- net/sctp/input.c | 43 ++++++++++---------------------------- net/sctp/proc.c | 6 ++++-- net/sctp/protocol.c | 6 +++--- net/sctp/socket.c | 14 +++++-------- 7 files changed, 32 insertions(+), 53 deletions(-) diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index 70827305f501..67c997cecf58 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -665,6 +665,9 @@ static inline int sctp_vtag_hashfn(__u16 lport, __u16 rport, __u32 vtag) return (h & (sctp_assoc_hashsize-1)); } +#define sctp_for_each_hentry(epb, node, head) \ + hlist_for_each_entry(epb, node, head, node) + /* Is a socket of this style? */ #define sctp_style(sk, style) __sctp_style((sk), (SCTP_SOCKET_##style)) static inline int __sctp_style(const struct sock *sk, sctp_socket_type_t style) diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 44f2672859e2..eb3113c38a94 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -100,20 +100,19 @@ struct crypto_hash; struct sctp_bind_bucket { unsigned short port; unsigned short fastreuse; - struct sctp_bind_bucket *next; - struct sctp_bind_bucket **pprev; + struct hlist_node node; struct hlist_head owner; }; struct sctp_bind_hashbucket { spinlock_t lock; - struct sctp_bind_bucket *chain; + struct hlist_head chain; }; /* Used for hashing all associations. */ struct sctp_hashbucket { rwlock_t lock; - struct sctp_ep_common *chain; + struct hlist_head chain; } __attribute__((__aligned__(8))); @@ -1230,8 +1229,7 @@ typedef enum { struct sctp_ep_common { /* Fields to help us manage our entries in the hash tables. */ - struct sctp_ep_common *next; - struct sctp_ep_common **pprev; + struct hlist_node node; int hashent; /* Runtime type information. What kind of endpoint is this? */ diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c index 68f0556efcc6..de6f505d6ff8 100644 --- a/net/sctp/endpointola.c +++ b/net/sctp/endpointola.c @@ -332,6 +332,7 @@ static struct sctp_association *__sctp_endpoint_lookup_assoc( struct sctp_transport *t = NULL; struct sctp_hashbucket *head; struct sctp_ep_common *epb; + struct hlist_node *node; int hash; int rport; @@ -341,7 +342,7 @@ static struct sctp_association *__sctp_endpoint_lookup_assoc( hash = sctp_assoc_hashfn(ep->base.bind_addr.port, rport); head = &sctp_assoc_hashtable[hash]; read_lock(&head->lock); - for (epb = head->chain; epb; epb = epb->next) { + sctp_for_each_hentry(epb, node, &head->chain) { asoc = sctp_assoc(epb); if (asoc->ep != ep || rport != asoc->peer.port) goto next; diff --git a/net/sctp/input.c b/net/sctp/input.c index 86503e7fa21e..91ae463b079b 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -656,7 +656,6 @@ static int sctp_rcv_ootb(struct sk_buff *skb) /* Insert endpoint into the hash table. */ static void __sctp_hash_endpoint(struct sctp_endpoint *ep) { - struct sctp_ep_common **epp; struct sctp_ep_common *epb; struct sctp_hashbucket *head; @@ -666,12 +665,7 @@ static void __sctp_hash_endpoint(struct sctp_endpoint *ep) head = &sctp_ep_hashtable[epb->hashent]; sctp_write_lock(&head->lock); - epp = &head->chain; - epb->next = *epp; - if (epb->next) - (*epp)->pprev = &epb->next; - *epp = epb; - epb->pprev = epp; + hlist_add_head(&epb->node, &head->chain); sctp_write_unlock(&head->lock); } @@ -691,19 +685,15 @@ static void __sctp_unhash_endpoint(struct sctp_endpoint *ep) epb = &ep->base; + if (hlist_unhashed(&epb->node)) + return; + epb->hashent = sctp_ep_hashfn(epb->bind_addr.port); head = &sctp_ep_hashtable[epb->hashent]; sctp_write_lock(&head->lock); - - if (epb->pprev) { - if (epb->next) - epb->next->pprev = epb->pprev; - *epb->pprev = epb->next; - epb->pprev = NULL; - } - + __hlist_del(&epb->node); sctp_write_unlock(&head->lock); } @@ -721,12 +711,13 @@ static struct sctp_endpoint *__sctp_rcv_lookup_endpoint(const union sctp_addr *l struct sctp_hashbucket *head; struct sctp_ep_common *epb; struct sctp_endpoint *ep; + struct hlist_node *node; int hash; hash = sctp_ep_hashfn(ntohs(laddr->v4.sin_port)); head = &sctp_ep_hashtable[hash]; read_lock(&head->lock); - for (epb = head->chain; epb; epb = epb->next) { + sctp_for_each_hentry(epb, node, &head->chain) { ep = sctp_ep(epb); if (sctp_endpoint_is_match(ep, laddr)) goto hit; @@ -744,7 +735,6 @@ static struct sctp_endpoint *__sctp_rcv_lookup_endpoint(const union sctp_addr *l /* Insert association into the hash table. */ static void __sctp_hash_established(struct sctp_association *asoc) { - struct sctp_ep_common **epp; struct sctp_ep_common *epb; struct sctp_hashbucket *head; @@ -756,12 +746,7 @@ static void __sctp_hash_established(struct sctp_association *asoc) head = &sctp_assoc_hashtable[epb->hashent]; sctp_write_lock(&head->lock); - epp = &head->chain; - epb->next = *epp; - if (epb->next) - (*epp)->pprev = &epb->next; - *epp = epb; - epb->pprev = epp; + hlist_add_head(&epb->node, &head->chain); sctp_write_unlock(&head->lock); } @@ -790,14 +775,7 @@ static void __sctp_unhash_established(struct sctp_association *asoc) head = &sctp_assoc_hashtable[epb->hashent]; sctp_write_lock(&head->lock); - - if (epb->pprev) { - if (epb->next) - epb->next->pprev = epb->pprev; - *epb->pprev = epb->next; - epb->pprev = NULL; - } - + __hlist_del(&epb->node); sctp_write_unlock(&head->lock); } @@ -822,6 +800,7 @@ static struct sctp_association *__sctp_lookup_association( struct sctp_ep_common *epb; struct sctp_association *asoc; struct sctp_transport *transport; + struct hlist_node *node; int hash; /* Optimize here for direct hit, only listening connections can @@ -830,7 +809,7 @@ static struct sctp_association *__sctp_lookup_association( hash = sctp_assoc_hashfn(ntohs(local->v4.sin_port), ntohs(peer->v4.sin_port)); head = &sctp_assoc_hashtable[hash]; read_lock(&head->lock); - for (epb = head->chain; epb; epb = epb->next) { + sctp_for_each_hentry(epb, node, &head->chain) { asoc = sctp_assoc(epb); transport = sctp_assoc_is_match(asoc, local, peer); if (transport) diff --git a/net/sctp/proc.c b/net/sctp/proc.c index e4cd841a22e4..249973204070 100644 --- a/net/sctp/proc.c +++ b/net/sctp/proc.c @@ -225,6 +225,7 @@ static int sctp_eps_seq_show(struct seq_file *seq, void *v) struct sctp_ep_common *epb; struct sctp_endpoint *ep; struct sock *sk; + struct hlist_node *node; int hash = *(loff_t *)v; if (hash >= sctp_ep_hashsize) @@ -233,7 +234,7 @@ static int sctp_eps_seq_show(struct seq_file *seq, void *v) head = &sctp_ep_hashtable[hash]; sctp_local_bh_disable(); read_lock(&head->lock); - for (epb = head->chain; epb; epb = epb->next) { + sctp_for_each_hentry(epb, node, &head->chain) { ep = sctp_ep(epb); sk = epb->sk; seq_printf(seq, "%8p %8p %-3d %-3d %-4d %-5d %5d %5lu ", ep, sk, @@ -328,6 +329,7 @@ static int sctp_assocs_seq_show(struct seq_file *seq, void *v) struct sctp_ep_common *epb; struct sctp_association *assoc; struct sock *sk; + struct hlist_node *node; int hash = *(loff_t *)v; if (hash >= sctp_assoc_hashsize) @@ -336,7 +338,7 @@ static int sctp_assocs_seq_show(struct seq_file *seq, void *v) head = &sctp_assoc_hashtable[hash]; sctp_local_bh_disable(); read_lock(&head->lock); - for (epb = head->chain; epb; epb = epb->next) { + sctp_for_each_hentry(epb, node, &head->chain) { assoc = sctp_assoc(epb); sk = epb->sk; seq_printf(seq, diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index ecfab0344e73..d50f610d1b02 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -1137,7 +1137,7 @@ SCTP_STATIC __init int sctp_init(void) } for (i = 0; i < sctp_assoc_hashsize; i++) { rwlock_init(&sctp_assoc_hashtable[i].lock); - sctp_assoc_hashtable[i].chain = NULL; + INIT_HLIST_HEAD(&sctp_assoc_hashtable[i].chain); } /* Allocate and initialize the endpoint hash table. */ @@ -1151,7 +1151,7 @@ SCTP_STATIC __init int sctp_init(void) } for (i = 0; i < sctp_ep_hashsize; i++) { rwlock_init(&sctp_ep_hashtable[i].lock); - sctp_ep_hashtable[i].chain = NULL; + INIT_HLIST_HEAD(&sctp_ep_hashtable[i].chain); } /* Allocate and initialize the SCTP port hash table. */ @@ -1170,7 +1170,7 @@ SCTP_STATIC __init int sctp_init(void) } for (i = 0; i < sctp_port_hashsize; i++) { spin_lock_init(&sctp_port_hashtable[i].lock); - sctp_port_hashtable[i].chain = NULL; + INIT_HLIST_HEAD(&sctp_port_hashtable[i].chain); } printk(KERN_INFO "SCTP: Hash tables configured " diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 6ce9b490fad5..ff8bc95670ed 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -5307,6 +5307,7 @@ static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr) { struct sctp_bind_hashbucket *head; /* hash list */ struct sctp_bind_bucket *pp; /* hash list port iterator */ + struct hlist_node *node; unsigned short snum; int ret; @@ -5331,7 +5332,7 @@ static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr) index = sctp_phashfn(rover); head = &sctp_port_hashtable[index]; sctp_spin_lock(&head->lock); - for (pp = head->chain; pp; pp = pp->next) + sctp_for_each_hentry(pp, node, &head->chain) if (pp->port == rover) goto next; break; @@ -5358,7 +5359,7 @@ static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr) */ head = &sctp_port_hashtable[sctp_phashfn(snum)]; sctp_spin_lock(&head->lock); - for (pp = head->chain; pp; pp = pp->next) { + sctp_for_each_hentry(pp, node, &head->chain) { if (pp->port == snum) goto pp_found; } @@ -5702,10 +5703,7 @@ static struct sctp_bind_bucket *sctp_bucket_create( pp->port = snum; pp->fastreuse = 0; INIT_HLIST_HEAD(&pp->owner); - if ((pp->next = head->chain) != NULL) - pp->next->pprev = &pp->next; - head->chain = pp; - pp->pprev = &head->chain; + hlist_add_head(&pp->node, &head->chain); } return pp; } @@ -5714,9 +5712,7 @@ static struct sctp_bind_bucket *sctp_bucket_create( static void sctp_bucket_destroy(struct sctp_bind_bucket *pp) { if (pp && hlist_empty(&pp->owner)) { - if (pp->next) - pp->next->pprev = pp->pprev; - *(pp->pprev) = pp->next; + __hlist_del(&pp->node); kmem_cache_free(sctp_bucket_cachep, pp); SCTP_DBG_OBJCNT_DEC(bind_bucket); } From 7ab9080467040054e27ae54d67cc185f24d881ae Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Fri, 9 Nov 2007 11:43:41 -0500 Subject: [PATCH 10/45] SCTP: Make sctp_verify_param return multiple indications. SCTP-AUTH and future ADD-IP updates have a requirement to do additional verification of parameters and an ability to ABORT the association if verification fails. So, introduce additional return code so that we can clear signal a required action. Signed-off-by: Vlad Yasevich --- include/net/sctp/constants.h | 2 + net/sctp/sm_make_chunk.c | 149 ++++++++++++++++++----------------- 2 files changed, 77 insertions(+), 74 deletions(-) diff --git a/include/net/sctp/constants.h b/include/net/sctp/constants.h index 73fbdf6a24f8..f30b537d6952 100644 --- a/include/net/sctp/constants.h +++ b/include/net/sctp/constants.h @@ -186,6 +186,8 @@ typedef enum { SCTP_IERROR_AUTH_BAD_HMAC, SCTP_IERROR_AUTH_BAD_KEYID, SCTP_IERROR_PROTO_VIOLATION, + SCTP_IERROR_ERROR, + SCTP_IERROR_ABORT, } sctp_ierror_t; diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 43e8de1228f9..5a9783c38de1 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -1788,9 +1788,14 @@ static int sctp_process_inv_paramlength(const struct sctp_association *asoc, sizeof(sctp_paramhdr_t); + /* This is a fatal error. Any accumulated non-fatal errors are + * not reported. + */ + if (*errp) + sctp_chunk_free(*errp); + /* Create an error chunk and fill it in with our payload. */ - if (!*errp) - *errp = sctp_make_op_error_space(asoc, chunk, payload_len); + *errp = sctp_make_op_error_space(asoc, chunk, payload_len); if (*errp) { sctp_init_cause(*errp, SCTP_ERROR_PROTO_VIOLATION, @@ -1813,9 +1818,15 @@ static int sctp_process_hn_param(const struct sctp_association *asoc, { __u16 len = ntohs(param.p->length); - /* Make an ERROR chunk. */ - if (!*errp) - *errp = sctp_make_op_error_space(asoc, chunk, len); + /* Processing of the HOST_NAME parameter will generate an + * ABORT. If we've accumulated any non-fatal errors, they + * would be unrecognized parameters and we should not include + * them in the ABORT. + */ + if (*errp) + sctp_chunk_free(*errp); + + *errp = sctp_make_op_error_space(asoc, chunk, len); if (*errp) { sctp_init_cause(*errp, SCTP_ERROR_DNS_FAILED, len); @@ -1862,56 +1873,40 @@ static void sctp_process_ext_param(struct sctp_association *asoc, * taken if the processing endpoint does not recognize the * Parameter Type. * - * 00 - Stop processing this SCTP chunk and discard it, - * do not process any further chunks within it. + * 00 - Stop processing this parameter; do not process any further + * parameters within this chunk * - * 01 - Stop processing this SCTP chunk and discard it, - * do not process any further chunks within it, and report - * the unrecognized parameter in an 'Unrecognized - * Parameter Type' (in either an ERROR or in the INIT ACK). + * 01 - Stop processing this parameter, do not process any further + * parameters within this chunk, and report the unrecognized + * parameter in an 'Unrecognized Parameter' ERROR chunk. * * 10 - Skip this parameter and continue processing. * * 11 - Skip this parameter and continue processing but * report the unrecognized parameter in an - * 'Unrecognized Parameter Type' (in either an ERROR or in - * the INIT ACK). + * 'Unrecognized Parameter' ERROR chunk. * * Return value: - * 0 - discard the chunk - * 1 - continue with the chunk + * SCTP_IERROR_NO_ERROR - continue with the chunk + * SCTP_IERROR_ERROR - stop and report an error. + * SCTP_IERROR_NOMEME - out of memory. */ -static int sctp_process_unk_param(const struct sctp_association *asoc, - union sctp_params param, - struct sctp_chunk *chunk, - struct sctp_chunk **errp) +static sctp_ierror_t sctp_process_unk_param(const struct sctp_association *asoc, + union sctp_params param, + struct sctp_chunk *chunk, + struct sctp_chunk **errp) { - int retval = 1; + int retval = SCTP_IERROR_NO_ERROR; switch (param.p->type & SCTP_PARAM_ACTION_MASK) { case SCTP_PARAM_ACTION_DISCARD: - retval = 0; - break; - case SCTP_PARAM_ACTION_DISCARD_ERR: - retval = 0; - /* Make an ERROR chunk, preparing enough room for - * returning multiple unknown parameters. - */ - if (NULL == *errp) - *errp = sctp_make_op_error_space(asoc, chunk, - ntohs(chunk->chunk_hdr->length)); - - if (*errp) { - sctp_init_cause(*errp, SCTP_ERROR_UNKNOWN_PARAM, - WORD_ROUND(ntohs(param.p->length))); - sctp_addto_chunk(*errp, - WORD_ROUND(ntohs(param.p->length)), - param.v); - } - + retval = SCTP_IERROR_ERROR; break; case SCTP_PARAM_ACTION_SKIP: break; + case SCTP_PARAM_ACTION_DISCARD_ERR: + retval = SCTP_IERROR_ERROR; + /* Fall through */ case SCTP_PARAM_ACTION_SKIP_ERR: /* Make an ERROR chunk, preparing enough room for * returning multiple unknown parameters. @@ -1932,9 +1927,8 @@ static int sctp_process_unk_param(const struct sctp_association *asoc, * to the peer and the association won't be * established. */ - retval = 0; + retval = SCTP_IERROR_NOMEM; } - break; default: break; @@ -1943,18 +1937,20 @@ static int sctp_process_unk_param(const struct sctp_association *asoc, return retval; } -/* Find unrecognized parameters in the chunk. +/* Verify variable length parameters * Return values: - * 0 - discard the chunk - * 1 - continue with the chunk + * SCTP_IERROR_ABORT - trigger an ABORT + * SCTP_IERROR_NOMEM - out of memory (abort) + * SCTP_IERROR_ERROR - stop processing, trigger an ERROR + * SCTP_IERROR_NO_ERROR - continue with the chunk */ -static int sctp_verify_param(const struct sctp_association *asoc, - union sctp_params param, - sctp_cid_t cid, - struct sctp_chunk *chunk, - struct sctp_chunk **err_chunk) +static sctp_ierror_t sctp_verify_param(const struct sctp_association *asoc, + union sctp_params param, + sctp_cid_t cid, + struct sctp_chunk *chunk, + struct sctp_chunk **err_chunk) { - int retval = 1; + int retval = SCTP_IERROR_NO_ERROR; /* FIXME - This routine is not looking at each parameter per the * chunk type, i.e., unrecognized parameters should be further @@ -1976,7 +1972,9 @@ static int sctp_verify_param(const struct sctp_association *asoc, case SCTP_PARAM_HOST_NAME_ADDRESS: /* Tell the peer, we won't support this param. */ - return sctp_process_hn_param(asoc, param, chunk, err_chunk); + sctp_process_hn_param(asoc, param, chunk, err_chunk); + retval = SCTP_IERROR_ABORT; + break; case SCTP_PARAM_FWD_TSN_SUPPORT: if (sctp_prsctp_enable) @@ -1993,9 +1991,11 @@ static int sctp_verify_param(const struct sctp_association *asoc, * cause 'Protocol Violation'. */ if (SCTP_AUTH_RANDOM_LENGTH != - ntohs(param.p->length) - sizeof(sctp_paramhdr_t)) - return sctp_process_inv_paramlength(asoc, param.p, + ntohs(param.p->length) - sizeof(sctp_paramhdr_t)) { + sctp_process_inv_paramlength(asoc, param.p, chunk, err_chunk); + retval = SCTP_IERROR_ABORT; + } break; case SCTP_PARAM_CHUNKS: @@ -2007,9 +2007,11 @@ static int sctp_verify_param(const struct sctp_association *asoc, * INIT-ACK chunk if the sender wants to receive authenticated * chunks. Its maximum length is 260 bytes. */ - if (260 < ntohs(param.p->length)) - return sctp_process_inv_paramlength(asoc, param.p, - chunk, err_chunk); + if (260 < ntohs(param.p->length)) { + sctp_process_inv_paramlength(asoc, param.p, + chunk, err_chunk); + retval = SCTP_IERROR_ABORT; + } break; case SCTP_PARAM_HMAC_ALGO: @@ -2020,8 +2022,7 @@ static int sctp_verify_param(const struct sctp_association *asoc, default: SCTP_DEBUG_PRINTK("Unrecognized param: %d for chunk %d.\n", ntohs(param.p->type), cid); - return sctp_process_unk_param(asoc, param, chunk, err_chunk); - + retval = sctp_process_unk_param(asoc, param, chunk, err_chunk); break; } return retval; @@ -2036,6 +2037,7 @@ int sctp_verify_init(const struct sctp_association *asoc, { union sctp_params param; int has_cookie = 0; + int result; /* Verify stream values are non-zero. */ if ((0 == peer_init->init_hdr.num_outbound_streams) || @@ -2043,8 +2045,7 @@ int sctp_verify_init(const struct sctp_association *asoc, (0 == peer_init->init_hdr.init_tag) || (SCTP_DEFAULT_MINWINDOW > ntohl(peer_init->init_hdr.a_rwnd))) { - sctp_process_inv_mandatory(asoc, chunk, errp); - return 0; + return sctp_process_inv_mandatory(asoc, chunk, errp); } /* Check for missing mandatory parameters. */ @@ -2062,29 +2063,29 @@ int sctp_verify_init(const struct sctp_association *asoc, * VIOLATION error. We build the ERROR chunk here and let the normal * error handling code build and send the packet. */ - if (param.v != (void*)chunk->chunk_end) { - sctp_process_inv_paramlength(asoc, param.p, chunk, errp); - return 0; - } + if (param.v != (void*)chunk->chunk_end) + return sctp_process_inv_paramlength(asoc, param.p, chunk, errp); /* The only missing mandatory param possible today is * the state cookie for an INIT-ACK chunk. */ - if ((SCTP_CID_INIT_ACK == cid) && !has_cookie) { - sctp_process_missing_param(asoc, SCTP_PARAM_STATE_COOKIE, - chunk, errp); - return 0; - } - - /* Find unrecognized parameters. */ + if ((SCTP_CID_INIT_ACK == cid) && !has_cookie) + return sctp_process_missing_param(asoc, SCTP_PARAM_STATE_COOKIE, + chunk, errp); + /* Verify all the variable length parameters */ sctp_walk_params(param, peer_init, init_hdr.params) { - if (!sctp_verify_param(asoc, param, cid, chunk, errp)) { - if (SCTP_PARAM_HOST_NAME_ADDRESS == param.p->type) + result = sctp_verify_param(asoc, param, cid, chunk, errp); + switch (result) { + case SCTP_IERROR_ABORT: + case SCTP_IERROR_NOMEM: return 0; - else + case SCTP_IERROR_ERROR: return 1; + case SCTP_IERROR_NO_ERROR: + default: + break; } } /* for (loop through all parameters) */ From cd3ae8e61570b55e32864c5f9e50085aa67126e9 Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Fri, 9 Nov 2007 11:43:41 -0500 Subject: [PATCH 11/45] SCTP: Fix PR-SCTP to deliver all the accumulated ordered chunks There is a small bug when we process a FWD-TSN. We'll deliver anything upto the current next expected SSN. However, if the next expected is already in the queue, it will take another chunk to trigger its delivery. The fix is to simply check the current queued SSN is the next expected one. Signed-off-by: Vlad Yasevich --- net/sctp/ulpqueue.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c index 4be92d0a2cab..4908041ffb31 100644 --- a/net/sctp/ulpqueue.c +++ b/net/sctp/ulpqueue.c @@ -862,7 +862,7 @@ static inline void sctp_ulpq_reap_ordered(struct sctp_ulpq *ulpq, __u16 sid) continue; /* see if this ssn has been marked by skipping */ - if (!SSN_lt(cssn, sctp_ssn_peek(in, csid))) + if (!SSN_lte(cssn, sctp_ssn_peek(in, csid))) break; __skb_unlink(pos, &ulpq->lobby); From fa7ff654e14ccacd4e758c9878ff4884f816c877 Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Fri, 9 Nov 2007 11:43:41 -0500 Subject: [PATCH 12/45] SCTP: Clean-up some defines for regressions tests. Signed-off-by: Vlad Yasevich --- include/net/sctp/sctp.h | 1 - 1 file changed, 1 deletion(-) diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index 67c997cecf58..34318a33a94c 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -65,7 +65,6 @@ #ifdef TEST_FRAME -#undef CONFIG_PROC_FS #undef CONFIG_SCTP_DBG_OBJCNT #undef CONFIG_SYSCTL #endif /* TEST_FRAME */ From 7d54dc6876b83d6bb75b8f7e865b7b9051056d22 Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Fri, 9 Nov 2007 11:43:41 -0500 Subject: [PATCH 13/45] SCTP: Always flush the queue when uncorcking. When the code calls uncork, trigger a queue flush, even if the queue was not corked. Most callers that explicitely cork the queue will have additinal checks to see if they corked it. Callers who do not cork the queue expect packets to flow when they call uncork. The scneario that showcased this bug happend when we were not able to bundle DATA with outgoing COOKIE-ECHO. As a result the data just sat in the outqueue and did not get transmitted. The application expected a response, but nothing happened. Signed-off-by: Vlad Yasevich --- net/sctp/outqueue.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 99a3db5d5fae..fa76f235169b 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -662,10 +662,9 @@ static int sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt, int sctp_outq_uncork(struct sctp_outq *q) { int error = 0; - if (q->cork) { + if (q->cork) q->cork = 0; - error = sctp_outq_flush(q, 0); - } + error = sctp_outq_flush(q, 0); return error; } From 9abed245a6dc94c32b2f45a1ecc51a0829d11470 Mon Sep 17 00:00:00 2001 From: Jesper Juhl Date: Sun, 11 Nov 2007 23:57:49 +0100 Subject: [PATCH 14/45] Fix memory leak in discard case of sctp_sf_abort_violation() In net/sctp/sm_statefuns.c::sctp_sf_abort_violation() we may leak the storage allocated for 'abort' by returning from the function without using or freeing it. This happens in case "sctp_auth_recv_cid(SCTP_CID_ABORT, asoc)" is true and we jump to the 'discard' label. Spotted by the Coverity checker. The simple fix is to simply move the creation of the "abort chunk" to after the possible jump to the 'discard' label. This way we don't even have to allocate the memory at all in the problem case. Signed-off-by: Jesper Juhl Signed-off-by: Vlad Yasevich --- net/sctp/sm_statefuns.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index a66075a70f29..5ebbe808d801 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -4064,11 +4064,6 @@ static sctp_disposition_t sctp_sf_abort_violation( struct sctp_chunk *chunk = arg; struct sctp_chunk *abort = NULL; - /* Make the abort chunk. */ - abort = sctp_make_abort_violation(asoc, chunk, payload, paylen); - if (!abort) - goto nomem; - /* SCTP-AUTH, Section 6.3: * It should be noted that if the receiver wants to tear * down an association in an authenticated way only, the @@ -4083,6 +4078,11 @@ static sctp_disposition_t sctp_sf_abort_violation( if (sctp_auth_recv_cid(SCTP_CID_ABORT, asoc)) goto discard; + /* Make the abort chunk. */ + abort = sctp_make_abort_violation(asoc, chunk, payload, paylen); + if (!abort) + goto nomem; + if (asoc) { sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(abort)); SCTP_INC_STATS(SCTP_MIB_OUTCTRLCHUNKS); From dbb2ed24851a290616d66212dc75373fd863d636 Mon Sep 17 00:00:00 2001 From: Pierre Ynard Date: Mon, 12 Nov 2007 17:58:35 -0800 Subject: [PATCH 15/45] [IPV6]: Add ifindex field to ND user option messages. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Userland neighbor discovery options are typically heavily involved with the interface on which thay are received: add a missing ifindex field to the original struct. Thanks to Rémi Denis-Courmont. Signed-off-by: Pierre Ynard Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 2 ++ net/ipv6/ndisc.c | 1 + 2 files changed, 3 insertions(+) diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 5bf618241ab9..4e81836191df 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -491,9 +491,11 @@ struct nduseroptmsg unsigned char nduseropt_family; unsigned char nduseropt_pad1; unsigned short nduseropt_opts_len; /* Total length of options */ + int nduseropt_ifindex; __u8 nduseropt_icmp_type; __u8 nduseropt_icmp_code; unsigned short nduseropt_pad2; + unsigned int nduseropt_pad3; /* Followed by one or more ND options */ }; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 36f7dbfb6dbb..67997a74ddce 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1037,6 +1037,7 @@ static void ndisc_ra_useropt(struct sk_buff *ra, struct nd_opt_hdr *opt) ndmsg = nlmsg_data(nlh); ndmsg->nduseropt_family = AF_INET6; + ndmsg->nduseropt_ifindex = ra->dev->ifindex; ndmsg->nduseropt_icmp_type = icmp6h->icmp6_type; ndmsg->nduseropt_icmp_code = icmp6h->icmp6_code; ndmsg->nduseropt_opts_len = opt->nd_opt_len << 3; From cd228d5458186f66bc36c4884f4f26ed955c5945 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Mon, 12 Nov 2007 18:07:31 -0800 Subject: [PATCH 16/45] [PPP]: Remove ptr comparisons to 0 fix sparse warnings "Using plain integer as NULL pointer" Signed-off-by: Joe Perches Signed-off-by: David S. Miller --- drivers/net/ppp_async.c | 34 +++++----- drivers/net/ppp_generic.c | 126 +++++++++++++++++++------------------- drivers/net/ppp_synctty.c | 27 ++++---- 3 files changed, 94 insertions(+), 93 deletions(-) diff --git a/drivers/net/ppp_async.c b/drivers/net/ppp_async.c index 8d278c87ba48..f023d5b67e6e 100644 --- a/drivers/net/ppp_async.c +++ b/drivers/net/ppp_async.c @@ -160,7 +160,7 @@ ppp_asynctty_open(struct tty_struct *tty) err = -ENOMEM; ap = kzalloc(sizeof(*ap), GFP_KERNEL); - if (ap == 0) + if (!ap) goto out; /* initialize the asyncppp structure */ @@ -215,7 +215,7 @@ ppp_asynctty_close(struct tty_struct *tty) ap = tty->disc_data; tty->disc_data = NULL; write_unlock_irq(&disc_data_lock); - if (ap == 0) + if (!ap) return; /* @@ -230,10 +230,10 @@ ppp_asynctty_close(struct tty_struct *tty) tasklet_kill(&ap->tsk); ppp_unregister_channel(&ap->chan); - if (ap->rpkt != 0) + if (ap->rpkt) kfree_skb(ap->rpkt); skb_queue_purge(&ap->rqueue); - if (ap->tpkt != 0) + if (ap->tpkt) kfree_skb(ap->tpkt); kfree(ap); } @@ -285,13 +285,13 @@ ppp_asynctty_ioctl(struct tty_struct *tty, struct file *file, int err, val; int __user *p = (int __user *)arg; - if (ap == 0) + if (!ap) return -ENXIO; err = -EFAULT; switch (cmd) { case PPPIOCGCHAN: err = -ENXIO; - if (ap == 0) + if (!ap) break; err = -EFAULT; if (put_user(ppp_channel_index(&ap->chan), p)) @@ -301,7 +301,7 @@ ppp_asynctty_ioctl(struct tty_struct *tty, struct file *file, case PPPIOCGUNIT: err = -ENXIO; - if (ap == 0) + if (!ap) break; err = -EFAULT; if (put_user(ppp_unit_number(&ap->chan), p)) @@ -350,7 +350,7 @@ ppp_asynctty_receive(struct tty_struct *tty, const unsigned char *buf, struct asyncppp *ap = ap_get(tty); unsigned long flags; - if (ap == 0) + if (!ap) return; spin_lock_irqsave(&ap->recv_lock, flags); ppp_async_input(ap, buf, cflags, count); @@ -369,7 +369,7 @@ ppp_asynctty_wakeup(struct tty_struct *tty) struct asyncppp *ap = ap_get(tty); clear_bit(TTY_DO_WRITE_WAKEUP, &tty->flags); - if (ap == 0) + if (!ap) return; set_bit(XMIT_WAKEUP, &ap->xmit_flags); tasklet_schedule(&ap->tsk); @@ -684,7 +684,7 @@ ppp_async_push(struct asyncppp *ap) tty_stuffed = 1; continue; } - if (ap->optr >= ap->olim && ap->tpkt != 0) { + if (ap->optr >= ap->olim && ap->tpkt) { if (ppp_async_encode(ap)) { /* finished processing ap->tpkt */ clear_bit(XMIT_FULL, &ap->xmit_flags); @@ -704,7 +704,7 @@ ppp_async_push(struct asyncppp *ap) clear_bit(XMIT_BUSY, &ap->xmit_flags); /* any more work to do? if not, exit the loop */ if (!(test_bit(XMIT_WAKEUP, &ap->xmit_flags) - || (!tty_stuffed && ap->tpkt != 0))) + || (!tty_stuffed && ap->tpkt))) break; /* more work to do, see if we can do it now */ if (test_and_set_bit(XMIT_BUSY, &ap->xmit_flags)) @@ -715,7 +715,7 @@ ppp_async_push(struct asyncppp *ap) flush: clear_bit(XMIT_BUSY, &ap->xmit_flags); - if (ap->tpkt != 0) { + if (ap->tpkt) { kfree_skb(ap->tpkt); ap->tpkt = NULL; clear_bit(XMIT_FULL, &ap->xmit_flags); @@ -848,7 +848,7 @@ ppp_async_input(struct asyncppp *ap, const unsigned char *buf, s = 0; for (i = 0; i < count; ++i) { c = buf[i]; - if (flags != 0 && flags[i] != 0) + if (flags && flags[i] != 0) continue; s |= (c & 0x80)? SC_RCV_B7_1: SC_RCV_B7_0; c = ((c >> 4) ^ c) & 0xf; @@ -865,7 +865,7 @@ ppp_async_input(struct asyncppp *ap, const unsigned char *buf, n = scan_ordinary(ap, buf, count); f = 0; - if (flags != 0 && (ap->state & SC_TOSS) == 0) { + if (flags && (ap->state & SC_TOSS) == 0) { /* check the flags to see if any char had an error */ for (j = 0; j < n; ++j) if ((f = flags[j]) != 0) @@ -878,9 +878,9 @@ ppp_async_input(struct asyncppp *ap, const unsigned char *buf, } else if (n > 0 && (ap->state & SC_TOSS) == 0) { /* stuff the chars in the skb */ skb = ap->rpkt; - if (skb == 0) { + if (!skb) { skb = dev_alloc_skb(ap->mru + PPP_HDRLEN + 2); - if (skb == 0) + if (!skb) goto nomem; ap->rpkt = skb; } @@ -927,7 +927,7 @@ ppp_async_input(struct asyncppp *ap, const unsigned char *buf, ++n; buf += n; - if (flags != 0) + if (flags) flags += n; count -= n; } diff --git a/drivers/net/ppp_generic.c b/drivers/net/ppp_generic.c index 4b49d0e8c7eb..4f690378bb77 100644 --- a/drivers/net/ppp_generic.c +++ b/drivers/net/ppp_generic.c @@ -367,7 +367,7 @@ static int ppp_release(struct inode *inode, struct file *file) struct ppp_file *pf = file->private_data; struct ppp *ppp; - if (pf != 0) { + if (pf) { file->private_data = NULL; if (pf->kind == INTERFACE) { ppp = PF_TO_PPP(pf); @@ -398,7 +398,7 @@ static ssize_t ppp_read(struct file *file, char __user *buf, ret = count; - if (pf == 0) + if (!pf) return -ENXIO; add_wait_queue(&pf->rwait, &wait); for (;;) { @@ -431,7 +431,7 @@ static ssize_t ppp_read(struct file *file, char __user *buf, set_current_state(TASK_RUNNING); remove_wait_queue(&pf->rwait, &wait); - if (skb == 0) + if (!skb) goto out; ret = -EOVERFLOW; @@ -455,11 +455,11 @@ static ssize_t ppp_write(struct file *file, const char __user *buf, struct sk_buff *skb; ssize_t ret; - if (pf == 0) + if (!pf) return -ENXIO; ret = -ENOMEM; skb = alloc_skb(count + pf->hdrlen, GFP_KERNEL); - if (skb == 0) + if (!skb) goto out; skb_reserve(skb, pf->hdrlen); ret = -EFAULT; @@ -491,11 +491,11 @@ static unsigned int ppp_poll(struct file *file, poll_table *wait) struct ppp_file *pf = file->private_data; unsigned int mask; - if (pf == 0) + if (!pf) return 0; poll_wait(file, &pf->rwait, wait); mask = POLLOUT | POLLWRNORM; - if (skb_peek(&pf->rq) != 0) + if (skb_peek(&pf->rq)) mask |= POLLIN | POLLRDNORM; if (pf->dead) mask |= POLLHUP; @@ -559,7 +559,7 @@ static int ppp_ioctl(struct inode *inode, struct file *file, void __user *argp = (void __user *)arg; int __user *p = argp; - if (pf == 0) + if (!pf) return ppp_unattached_ioctl(pf, file, cmd, arg); if (cmd == PPPIOCDETACH) { @@ -689,13 +689,13 @@ static int ppp_ioctl(struct inode *inode, struct file *file, val &= 0xffff; } vj = slhc_init(val2+1, val+1); - if (vj == 0) { + if (!vj) { printk(KERN_ERR "PPP: no memory (VJ compressor)\n"); err = -ENOMEM; break; } ppp_lock(ppp); - if (ppp->vj != 0) + if (ppp->vj) slhc_free(ppp->vj); ppp->vj = vj; ppp_unlock(ppp); @@ -786,7 +786,7 @@ static int ppp_unattached_ioctl(struct ppp_file *pf, struct file *file, if (get_user(unit, p)) break; ppp = ppp_create_interface(unit, &err); - if (ppp == 0) + if (!ppp) break; file->private_data = &ppp->file; ppp->owner = file; @@ -803,7 +803,7 @@ static int ppp_unattached_ioctl(struct ppp_file *pf, struct file *file, mutex_lock(&all_ppp_mutex); err = -ENXIO; ppp = ppp_find_unit(unit); - if (ppp != 0) { + if (ppp) { atomic_inc(&ppp->file.refcnt); file->private_data = &ppp->file; err = 0; @@ -817,7 +817,7 @@ static int ppp_unattached_ioctl(struct ppp_file *pf, struct file *file, spin_lock_bh(&all_channels_lock); err = -ENXIO; chan = ppp_find_channel(unit); - if (chan != 0) { + if (chan) { atomic_inc(&chan->file.refcnt); file->private_data = &chan->file; err = 0; @@ -946,9 +946,9 @@ ppp_net_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) case SIOCGPPPCSTATS: memset(&cstats, 0, sizeof(cstats)); - if (ppp->xc_state != 0) + if (ppp->xc_state) ppp->xcomp->comp_stat(ppp->xc_state, &cstats.c); - if (ppp->rc_state != 0) + if (ppp->rc_state) ppp->rcomp->decomp_stat(ppp->rc_state, &cstats.d); if (copy_to_user(addr, &cstats, sizeof(cstats))) break; @@ -993,14 +993,14 @@ ppp_xmit_process(struct ppp *ppp) struct sk_buff *skb; ppp_xmit_lock(ppp); - if (ppp->dev != 0) { + if (ppp->dev) { ppp_push(ppp); - while (ppp->xmit_pending == 0 - && (skb = skb_dequeue(&ppp->file.xq)) != 0) + while (!ppp->xmit_pending + && (skb = skb_dequeue(&ppp->file.xq))) ppp_send_frame(ppp, skb); /* If there's no work left to do, tell the core net code that we can accept some more. */ - if (ppp->xmit_pending == 0 && skb_peek(&ppp->file.xq) == 0) + if (!ppp->xmit_pending && !skb_peek(&ppp->file.xq)) netif_wake_queue(ppp->dev); } ppp_xmit_unlock(ppp); @@ -1100,12 +1100,12 @@ ppp_send_frame(struct ppp *ppp, struct sk_buff *skb) switch (proto) { case PPP_IP: - if (ppp->vj == 0 || (ppp->flags & SC_COMP_TCP) == 0) + if (!ppp->vj || (ppp->flags & SC_COMP_TCP) == 0) break; /* try to do VJ TCP header compression */ new_skb = alloc_skb(skb->len + ppp->dev->hard_header_len - 2, GFP_ATOMIC); - if (new_skb == 0) { + if (!new_skb) { printk(KERN_ERR "PPP: no memory (VJ comp pkt)\n"); goto drop; } @@ -1140,7 +1140,7 @@ ppp_send_frame(struct ppp *ppp, struct sk_buff *skb) } /* try to do packet compression */ - if ((ppp->xstate & SC_COMP_RUN) && ppp->xc_state != 0 + if ((ppp->xstate & SC_COMP_RUN) && ppp->xc_state && proto != PPP_LCP && proto != PPP_CCP) { if (!(ppp->flags & SC_CCP_UP) && (ppp->flags & SC_MUST_COMP)) { if (net_ratelimit()) @@ -1185,7 +1185,7 @@ ppp_push(struct ppp *ppp) struct channel *pch; struct sk_buff *skb = ppp->xmit_pending; - if (skb == 0) + if (!skb) return; list = &ppp->channels; @@ -1355,7 +1355,7 @@ static int ppp_mp_explode(struct ppp *ppp, struct sk_buff *skb) if (flen == len && nfree == 0) bits |= E; frag = alloc_skb(flen + hdrlen + (flen == 0), GFP_ATOMIC); - if (frag == 0) + if (!frag) goto noskb; q = skb_put(frag, flen + hdrlen); @@ -1425,7 +1425,7 @@ ppp_channel_push(struct channel *pch) struct ppp *ppp; spin_lock_bh(&pch->downl); - if (pch->chan != 0) { + if (pch->chan) { while (!skb_queue_empty(&pch->file.xq)) { skb = skb_dequeue(&pch->file.xq); if (!pch->chan->ops->start_xmit(pch->chan, skb)) { @@ -1443,7 +1443,7 @@ ppp_channel_push(struct channel *pch) if (skb_queue_empty(&pch->file.xq)) { read_lock_bh(&pch->upl); ppp = pch->ppp; - if (ppp != 0) + if (ppp) ppp_xmit_process(ppp); read_unlock_bh(&pch->upl); } @@ -1462,7 +1462,7 @@ ppp_do_recv(struct ppp *ppp, struct sk_buff *skb, struct channel *pch) { ppp_recv_lock(ppp); /* ppp->dev == 0 means interface is closing down */ - if (ppp->dev != 0) + if (ppp->dev) ppp_receive_frame(ppp, skb, pch); else kfree_skb(skb); @@ -1475,19 +1475,19 @@ ppp_input(struct ppp_channel *chan, struct sk_buff *skb) struct channel *pch = chan->ppp; int proto; - if (pch == 0 || skb->len == 0) { + if (!pch || skb->len == 0) { kfree_skb(skb); return; } proto = PPP_PROTO(skb); read_lock_bh(&pch->upl); - if (pch->ppp == 0 || proto >= 0xc000 || proto == PPP_CCPFRAG) { + if (!pch->ppp || proto >= 0xc000 || proto == PPP_CCPFRAG) { /* put it on the channel queue */ skb_queue_tail(&pch->file.rq, skb); /* drop old frames if queue too long */ while (pch->file.rq.qlen > PPP_MAX_RQLEN - && (skb = skb_dequeue(&pch->file.rq)) != 0) + && (skb = skb_dequeue(&pch->file.rq))) kfree_skb(skb); wake_up_interruptible(&pch->file.rwait); } else { @@ -1503,13 +1503,13 @@ ppp_input_error(struct ppp_channel *chan, int code) struct channel *pch = chan->ppp; struct sk_buff *skb; - if (pch == 0) + if (!pch) return; read_lock_bh(&pch->upl); - if (pch->ppp != 0) { + if (pch->ppp) { skb = alloc_skb(0, GFP_ATOMIC); - if (skb != 0) { + if (skb) { skb->len = 0; /* probably unnecessary */ skb->cb[0] = code; ppp_do_recv(pch->ppp, skb, pch); @@ -1548,7 +1548,7 @@ static void ppp_receive_error(struct ppp *ppp) { ++ppp->stats.rx_errors; - if (ppp->vj != 0) + if (ppp->vj) slhc_toss(ppp->vj); } @@ -1563,7 +1563,7 @@ ppp_receive_nonmp_frame(struct ppp *ppp, struct sk_buff *skb) * Note that some decompressors need to see uncompressed frames * that come in as well as compressed frames. */ - if (ppp->rc_state != 0 && (ppp->rstate & SC_DECOMP_RUN) + if (ppp->rc_state && (ppp->rstate & SC_DECOMP_RUN) && (ppp->rstate & (SC_DC_FERROR | SC_DC_ERROR)) == 0) skb = ppp_decompress_frame(ppp, skb); @@ -1574,13 +1574,13 @@ ppp_receive_nonmp_frame(struct ppp *ppp, struct sk_buff *skb) switch (proto) { case PPP_VJC_COMP: /* decompress VJ compressed packets */ - if (ppp->vj == 0 || (ppp->flags & SC_REJ_COMP_TCP)) + if (!ppp->vj || (ppp->flags & SC_REJ_COMP_TCP)) goto err; if (skb_tailroom(skb) < 124 || skb_cloned(skb)) { /* copy to a new sk_buff with more tailroom */ ns = dev_alloc_skb(skb->len + 128); - if (ns == 0) { + if (!ns) { printk(KERN_ERR"PPP: no memory (VJ decomp)\n"); goto err; } @@ -1606,7 +1606,7 @@ ppp_receive_nonmp_frame(struct ppp *ppp, struct sk_buff *skb) break; case PPP_VJC_UNCOMP: - if (ppp->vj == 0 || (ppp->flags & SC_REJ_COMP_TCP)) + if (!ppp->vj || (ppp->flags & SC_REJ_COMP_TCP)) goto err; /* Until we fix the decompressor need to make sure @@ -1636,7 +1636,7 @@ ppp_receive_nonmp_frame(struct ppp *ppp, struct sk_buff *skb) skb_queue_tail(&ppp->file.rq, skb); /* limit queue length by dropping old frames */ while (ppp->file.rq.qlen > PPP_MAX_RQLEN - && (skb = skb_dequeue(&ppp->file.rq)) != 0) + && (skb = skb_dequeue(&ppp->file.rq))) kfree_skb(skb); /* wake up any process polling or blocking on read */ wake_up_interruptible(&ppp->file.rwait); @@ -1718,7 +1718,7 @@ ppp_decompress_frame(struct ppp *ppp, struct sk_buff *skb) } ns = dev_alloc_skb(obuff_size); - if (ns == 0) { + if (!ns) { printk(KERN_ERR "ppp_decompress_frame: no memory\n"); goto err; } @@ -1836,7 +1836,7 @@ ppp_receive_mp_frame(struct ppp *ppp, struct sk_buff *skb, struct channel *pch) ppp->minseq = ppp->mrq.next->sequence; /* Pull completed packets off the queue and receive them. */ - while ((skb = ppp_mp_reconstruct(ppp)) != 0) + while ((skb = ppp_mp_reconstruct(ppp))) ppp_receive_nonmp_frame(ppp, skb); return; @@ -2002,7 +2002,7 @@ ppp_register_channel(struct ppp_channel *chan) struct channel *pch; pch = kzalloc(sizeof(struct channel), GFP_KERNEL); - if (pch == 0) + if (!pch) return -ENOMEM; pch->ppp = NULL; pch->chan = chan; @@ -2030,7 +2030,7 @@ int ppp_channel_index(struct ppp_channel *chan) { struct channel *pch = chan->ppp; - if (pch != 0) + if (pch) return pch->file.index; return -1; } @@ -2043,9 +2043,9 @@ int ppp_unit_number(struct ppp_channel *chan) struct channel *pch = chan->ppp; int unit = -1; - if (pch != 0) { + if (pch) { read_lock_bh(&pch->upl); - if (pch->ppp != 0) + if (pch->ppp) unit = pch->ppp->file.index; read_unlock_bh(&pch->upl); } @@ -2061,7 +2061,7 @@ ppp_unregister_channel(struct ppp_channel *chan) { struct channel *pch = chan->ppp; - if (pch == 0) + if (!pch) return; /* should never happen */ chan->ppp = NULL; @@ -2093,7 +2093,7 @@ ppp_output_wakeup(struct ppp_channel *chan) { struct channel *pch = chan->ppp; - if (pch == 0) + if (!pch) return; ppp_channel_push(pch); } @@ -2124,18 +2124,18 @@ ppp_set_compress(struct ppp *ppp, unsigned long arg) cp = find_compressor(ccp_option[0]); #ifdef CONFIG_KMOD - if (cp == 0) { + if (!cp) { request_module("ppp-compress-%d", ccp_option[0]); cp = find_compressor(ccp_option[0]); } #endif /* CONFIG_KMOD */ - if (cp == 0) + if (!cp) goto out; err = -ENOBUFS; if (data.transmit) { state = cp->comp_alloc(ccp_option, data.length); - if (state != 0) { + if (state) { ppp_xmit_lock(ppp); ppp->xstate &= ~SC_COMP_RUN; ocomp = ppp->xcomp; @@ -2143,7 +2143,7 @@ ppp_set_compress(struct ppp *ppp, unsigned long arg) ppp->xcomp = cp; ppp->xc_state = state; ppp_xmit_unlock(ppp); - if (ostate != 0) { + if (ostate) { ocomp->comp_free(ostate); module_put(ocomp->owner); } @@ -2153,7 +2153,7 @@ ppp_set_compress(struct ppp *ppp, unsigned long arg) } else { state = cp->decomp_alloc(ccp_option, data.length); - if (state != 0) { + if (state) { ppp_recv_lock(ppp); ppp->rstate &= ~SC_DECOMP_RUN; ocomp = ppp->rcomp; @@ -2161,7 +2161,7 @@ ppp_set_compress(struct ppp *ppp, unsigned long arg) ppp->rcomp = cp; ppp->rc_state = state; ppp_recv_unlock(ppp); - if (ostate != 0) { + if (ostate) { ocomp->decomp_free(ostate); module_put(ocomp->owner); } @@ -2228,7 +2228,7 @@ ppp_ccp_peek(struct ppp *ppp, struct sk_buff *skb, int inbound) break; if (inbound) { /* we will start receiving compressed packets */ - if (ppp->rc_state == 0) + if (!ppp->rc_state) break; if (ppp->rcomp->decomp_init(ppp->rc_state, dp, len, ppp->file.index, 0, ppp->mru, ppp->debug)) { @@ -2237,7 +2237,7 @@ ppp_ccp_peek(struct ppp *ppp, struct sk_buff *skb, int inbound) } } else { /* we will soon start sending compressed packets */ - if (ppp->xc_state == 0) + if (!ppp->xc_state) break; if (ppp->xcomp->comp_init(ppp->xc_state, dp, len, ppp->file.index, 0, ppp->debug)) @@ -2320,11 +2320,11 @@ ppp_register_compressor(struct compressor *cp) int ret; spin_lock(&compressor_list_lock); ret = -EEXIST; - if (find_comp_entry(cp->compress_proto) != 0) + if (find_comp_entry(cp->compress_proto)) goto out; ret = -ENOMEM; ce = kmalloc(sizeof(struct compressor_entry), GFP_ATOMIC); - if (ce == 0) + if (!ce) goto out; ret = 0; ce->comp = cp; @@ -2342,7 +2342,7 @@ ppp_unregister_compressor(struct compressor *cp) spin_lock(&compressor_list_lock); ce = find_comp_entry(cp->compress_proto); - if (ce != 0 && ce->comp == cp) { + if (ce && ce->comp == cp) { list_del(&ce->list); kfree(ce); } @@ -2358,7 +2358,7 @@ find_compressor(int type) spin_lock(&compressor_list_lock); ce = find_comp_entry(type); - if (ce != 0) { + if (ce) { cp = ce->comp; if (!try_module_get(cp->owner)) cp = NULL; @@ -2383,7 +2383,7 @@ ppp_get_stats(struct ppp *ppp, struct ppp_stats *st) st->p.ppp_opackets = ppp->stats.tx_packets; st->p.ppp_oerrors = ppp->stats.tx_errors; st->p.ppp_obytes = ppp->stats.tx_bytes; - if (vj == 0) + if (!vj) return; st->vj.vjs_packets = vj->sls_o_compressed + vj->sls_o_uncompressed; st->vj.vjs_compressed = vj->sls_o_compressed; @@ -2604,11 +2604,11 @@ ppp_connect_channel(struct channel *pch, int unit) mutex_lock(&all_ppp_mutex); ppp = ppp_find_unit(unit); - if (ppp == 0) + if (!ppp) goto out; write_lock_bh(&pch->upl); ret = -EINVAL; - if (pch->ppp != 0) + if (pch->ppp) goto outl; ppp_lock(ppp); @@ -2644,7 +2644,7 @@ ppp_disconnect_channel(struct channel *pch) ppp = pch->ppp; pch->ppp = NULL; write_unlock_bh(&pch->upl); - if (ppp != 0) { + if (ppp) { /* remove it from the ppp unit's list */ ppp_lock(ppp); list_del(&pch->clist); diff --git a/drivers/net/ppp_synctty.c b/drivers/net/ppp_synctty.c index 00e2fb48b4ae..f0c6a1926a02 100644 --- a/drivers/net/ppp_synctty.c +++ b/drivers/net/ppp_synctty.c @@ -209,7 +209,7 @@ ppp_sync_open(struct tty_struct *tty) ap = kzalloc(sizeof(*ap), GFP_KERNEL); err = -ENOMEM; - if (ap == 0) + if (!ap) goto out; /* initialize the syncppp structure */ @@ -262,7 +262,7 @@ ppp_sync_close(struct tty_struct *tty) ap = tty->disc_data; tty->disc_data = NULL; write_unlock_irq(&disc_data_lock); - if (ap == 0) + if (!ap) return; /* @@ -278,7 +278,7 @@ ppp_sync_close(struct tty_struct *tty) ppp_unregister_channel(&ap->chan); skb_queue_purge(&ap->rqueue); - if (ap->tpkt != 0) + if (ap->tpkt) kfree_skb(ap->tpkt); kfree(ap); } @@ -325,13 +325,13 @@ ppp_synctty_ioctl(struct tty_struct *tty, struct file *file, int __user *p = (int __user *)arg; int err, val; - if (ap == 0) + if (!ap) return -ENXIO; err = -EFAULT; switch (cmd) { case PPPIOCGCHAN: err = -ENXIO; - if (ap == 0) + if (!ap) break; err = -EFAULT; if (put_user(ppp_channel_index(&ap->chan), p)) @@ -341,7 +341,7 @@ ppp_synctty_ioctl(struct tty_struct *tty, struct file *file, case PPPIOCGUNIT: err = -ENXIO; - if (ap == 0) + if (!ap) break; err = -EFAULT; if (put_user(ppp_unit_number(&ap->chan), p)) @@ -390,7 +390,7 @@ ppp_sync_receive(struct tty_struct *tty, const unsigned char *buf, struct syncppp *ap = sp_get(tty); unsigned long flags; - if (ap == 0) + if (!ap) return; spin_lock_irqsave(&ap->recv_lock, flags); ppp_sync_input(ap, buf, cflags, count); @@ -409,7 +409,7 @@ ppp_sync_wakeup(struct tty_struct *tty) struct syncppp *ap = sp_get(tty); clear_bit(TTY_DO_WRITE_WAKEUP, &tty->flags); - if (ap == 0) + if (!ap) return; set_bit(XMIT_WAKEUP, &ap->xmit_flags); tasklet_schedule(&ap->tsk); @@ -651,7 +651,7 @@ ppp_sync_push(struct syncppp *ap) for (;;) { if (test_and_clear_bit(XMIT_WAKEUP, &ap->xmit_flags)) tty_stuffed = 0; - if (!tty_stuffed && ap->tpkt != 0) { + if (!tty_stuffed && ap->tpkt) { set_bit(TTY_DO_WRITE_WAKEUP, &tty->flags); sent = tty->driver->write(tty, ap->tpkt->data, ap->tpkt->len); if (sent < 0) @@ -669,7 +669,7 @@ ppp_sync_push(struct syncppp *ap) /* haven't made any progress */ spin_unlock_bh(&ap->xmit_lock); if (!(test_bit(XMIT_WAKEUP, &ap->xmit_flags) - || (!tty_stuffed && ap->tpkt != 0))) + || (!tty_stuffed && ap->tpkt))) break; if (!spin_trylock_bh(&ap->xmit_lock)) break; @@ -677,7 +677,7 @@ ppp_sync_push(struct syncppp *ap) return done; flush: - if (ap->tpkt != 0) { + if (ap->tpkt) { kfree_skb(ap->tpkt); ap->tpkt = NULL; clear_bit(XMIT_FULL, &ap->xmit_flags); @@ -732,7 +732,8 @@ ppp_sync_input(struct syncppp *ap, const unsigned char *buf, ppp_print_buffer ("receive buffer", buf, count); /* stuff the chars in the skb */ - if ((skb = dev_alloc_skb(ap->mru + PPP_HDRLEN + 2)) == 0) { + skb = dev_alloc_skb(ap->mru + PPP_HDRLEN + 2); + if (!skb) { printk(KERN_ERR "PPPsync: no memory (input pkt)\n"); goto err; } @@ -740,7 +741,7 @@ ppp_sync_input(struct syncppp *ap, const unsigned char *buf, if (buf[0] != PPP_ALLSTATIONS) skb_reserve(skb, 2 + (buf[0] & 1)); - if (flags != 0 && *flags) { + if (flags && *flags) { /* error flag set, ignore frame */ goto err; } else if (count > skb_tailroom(skb)) { From 62768e28d606c10ba54217f908123de34dad9374 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 12 Nov 2007 18:09:25 -0800 Subject: [PATCH 17/45] [SUNGEM]: Fix suspend regression due to NAPI changes. Commit bea3348e (the NAPI changes) made sungem unconditionally enable NAPI when resuming and unconditionally disable when suspending, this, however, makes napi_disable() hang when suspending when the interface was taken down before suspend because taking the interface down also disables NAPI. This patch makes touching the napi struct in suspend/resume code paths depend on having the interface up, thereby fixing the hang on suspend. The patch also moves the napi_disable() in gem_close() under the lock so that the NAPI state is always modified atomically together with the "opened" variable. Signed-off-by: Johannes Berg Acked-by: Benjamin Herrenschmidt Signed-off-by: David S. Miller --- drivers/net/sungem.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/drivers/net/sungem.c b/drivers/net/sungem.c index 53b8344a68ef..f6fedcc32de1 100644 --- a/drivers/net/sungem.c +++ b/drivers/net/sungem.c @@ -2333,10 +2333,10 @@ static int gem_close(struct net_device *dev) { struct gem *gp = dev->priv; - napi_disable(&gp->napi); - mutex_lock(&gp->pm_mutex); + napi_disable(&gp->napi); + gp->opened = 0; if (!gp->asleep) gem_do_stop(dev, 0); @@ -2355,8 +2355,6 @@ static int gem_suspend(struct pci_dev *pdev, pm_message_t state) mutex_lock(&gp->pm_mutex); - napi_disable(&gp->napi); - printk(KERN_INFO "%s: suspending, WakeOnLan %s\n", dev->name, (gp->wake_on_lan && gp->opened) ? "enabled" : "disabled"); @@ -2370,6 +2368,8 @@ static int gem_suspend(struct pci_dev *pdev, pm_message_t state) /* If the driver is opened, we stop the MAC */ if (gp->opened) { + napi_disable(&gp->napi); + /* Stop traffic, mark us closed */ netif_device_detach(dev); @@ -2460,6 +2460,7 @@ static int gem_resume(struct pci_dev *pdev) /* Re-attach net device */ netif_device_attach(dev); + napi_enable(&gp->napi); } spin_lock_irqsave(&gp->lock, flags); @@ -2479,8 +2480,6 @@ static int gem_resume(struct pci_dev *pdev) spin_unlock(&gp->tx_lock); spin_unlock_irqrestore(&gp->lock, flags); - napi_enable(&gp->napi); - mutex_unlock(&gp->pm_mutex); return 0; From 91cf45f02af5c871251165d000c3f42a2a0b0552 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 12 Nov 2007 18:10:39 -0800 Subject: [PATCH 18/45] [NET]: Add the helper kernel_sock_shutdown() ...and fix a couple of bugs in the NBD, CIFS and OCFS2 socket handlers. Looking at the sock->op->shutdown() handlers, it looks as if all of them take a SHUT_RD/SHUT_WR/SHUT_RDWR argument instead of the RCV_SHUTDOWN/SEND_SHUTDOWN arguments. Add a helper, and then define the SHUT_* enum to ensure that kernel users of shutdown() don't get confused. Signed-off-by: Trond Myklebust Acked-by: Mark Fasheh Acked-by: David Howells Signed-off-by: David S. Miller --- drivers/block/nbd.c | 3 ++- fs/cifs/connect.c | 2 +- fs/ocfs2/cluster/tcp.c | 4 ++-- include/linux/net.h | 8 ++++++++ net/rxrpc/ar-local.c | 4 ++-- net/socket.c | 6 ++++++ 6 files changed, 21 insertions(+), 6 deletions(-) diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 6332acad078c..b4c0888aedc3 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -28,6 +28,7 @@ #include #include #include +#include #include #include @@ -126,7 +127,7 @@ static void sock_shutdown(struct nbd_device *lo, int lock) if (lo->sock) { printk(KERN_WARNING "%s: shutting down socket\n", lo->disk->disk_name); - lo->sock->ops->shutdown(lo->sock, SEND_SHUTDOWN|RCV_SHUTDOWN); + kernel_sock_shutdown(lo->sock, SHUT_RDWR); lo->sock = NULL; } if (lock) diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 1102160f6661..c52a76ff4bb9 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -160,7 +160,7 @@ cifs_reconnect(struct TCP_Server_Info *server) if (server->ssocket) { cFYI(1, ("State: 0x%x Flags: 0x%lx", server->ssocket->state, server->ssocket->flags)); - server->ssocket->ops->shutdown(server->ssocket, SEND_SHUTDOWN); + kernel_sock_shutdown(server->ssocket, SHUT_WR); cFYI(1, ("Post shutdown state: 0x%x Flags: 0x%lx", server->ssocket->state, server->ssocket->flags)); diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c index 685c18065c82..d84bd155997b 100644 --- a/fs/ocfs2/cluster/tcp.c +++ b/fs/ocfs2/cluster/tcp.c @@ -58,6 +58,7 @@ #include #include #include +#include #include #include @@ -616,8 +617,7 @@ static void o2net_shutdown_sc(struct work_struct *work) del_timer_sync(&sc->sc_idle_timeout); o2net_sc_cancel_delayed_work(sc, &sc->sc_keepalive_work); sc_put(sc); - sc->sc_sock->ops->shutdown(sc->sc_sock, - RCV_SHUTDOWN|SEND_SHUTDOWN); + kernel_sock_shutdown(sc->sc_sock, SHUT_RDWR); } /* not fatal so failed connects before the other guy has our diff --git a/include/linux/net.h b/include/linux/net.h index dd79cdb8c4cf..596131ea46f4 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -95,6 +95,12 @@ enum sock_type { #endif /* ARCH_HAS_SOCKET_TYPES */ +enum sock_shutdown_cmd { + SHUT_RD = 0, + SHUT_WR = 1, + SHUT_RDWR = 2, +}; + /** * struct socket - general BSD socket * @state: socket state (%SS_CONNECTED, etc) @@ -223,6 +229,8 @@ extern int kernel_setsockopt(struct socket *sock, int level, int optname, extern int kernel_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags); extern int kernel_sock_ioctl(struct socket *sock, int cmd, unsigned long arg); +extern int kernel_sock_shutdown(struct socket *sock, + enum sock_shutdown_cmd how); #ifndef CONFIG_SMP #define SOCKOPS_WRAPPED(name) name diff --git a/net/rxrpc/ar-local.c b/net/rxrpc/ar-local.c index fe03f71f17da..f3a2bd747a8f 100644 --- a/net/rxrpc/ar-local.c +++ b/net/rxrpc/ar-local.c @@ -114,7 +114,7 @@ static int rxrpc_create_local(struct rxrpc_local *local) return 0; error: - local->socket->ops->shutdown(local->socket, 2); + kernel_sock_shutdown(local->socket, SHUT_RDWR); local->socket->sk->sk_user_data = NULL; sock_release(local->socket); local->socket = NULL; @@ -267,7 +267,7 @@ static void rxrpc_destroy_local(struct work_struct *work) /* finish cleaning up the local descriptor */ rxrpc_purge_queue(&local->accept_queue); rxrpc_purge_queue(&local->reject_queue); - local->socket->ops->shutdown(local->socket, 2); + kernel_sock_shutdown(local->socket, SHUT_RDWR); sock_release(local->socket); up_read(&rxrpc_local_sem); diff --git a/net/socket.c b/net/socket.c index 5d879fd3d01d..74784dfe8e5b 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2319,6 +2319,11 @@ int kernel_sock_ioctl(struct socket *sock, int cmd, unsigned long arg) return err; } +int kernel_sock_shutdown(struct socket *sock, enum sock_shutdown_cmd how) +{ + return sock->ops->shutdown(sock, how); +} + /* ABI emulation layers need these two */ EXPORT_SYMBOL(move_addr_to_kernel); EXPORT_SYMBOL(move_addr_to_user); @@ -2345,3 +2350,4 @@ EXPORT_SYMBOL(kernel_getsockopt); EXPORT_SYMBOL(kernel_setsockopt); EXPORT_SYMBOL(kernel_sendpage); EXPORT_SYMBOL(kernel_sock_ioctl); +EXPORT_SYMBOL(kernel_sock_shutdown); From c0d8248710d7d914c44dd79768b3ad85a62e194a Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 12 Nov 2007 21:02:51 -0800 Subject: [PATCH 19/45] [INET]: Remove leftover prototypes from include/net/inet_common.h Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/net/inet_common.h | 4 ---- 1 file changed, 4 deletions(-) diff --git a/include/net/inet_common.h b/include/net/inet_common.h index 227adcbdfec8..38d5a1e9980d 100644 --- a/include/net/inet_common.h +++ b/include/net/inet_common.h @@ -13,9 +13,6 @@ struct sock; struct sockaddr; struct socket; -extern void inet_remove_sock(struct sock *sk1); -extern void inet_put_sock(unsigned short num, - struct sock *sk); extern int inet_release(struct socket *sock); extern int inet_stream_connect(struct socket *sock, struct sockaddr * uaddr, @@ -30,7 +27,6 @@ extern int inet_sendmsg(struct kiocb *iocb, struct msghdr *msg, size_t size); extern int inet_shutdown(struct socket *sock, int how); -extern unsigned int inet_poll(struct file * file, struct socket *sock, struct poll_table_struct *wait); extern int inet_listen(struct socket *sock, int backlog); extern void inet_sock_destruct(struct sock *sk); From 57ce45dd16cd427ac2bdef202daf513bd25d650b Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Mon, 12 Nov 2007 21:03:58 -0800 Subject: [PATCH 20/45] [NET]: Remove references to net-modules.txt. When I removed net-modules.txt because it only contained ancient information I missed that many Kconfig entries pointed to this ancient information. Signed-off-by: Adrian Bunk Signed-off-by: David S. Miller --- Documentation/networking/3c505.txt | 3 +- drivers/net/Kconfig | 199 ++++++++++------------------- drivers/net/arcnet/Kconfig | 15 +-- drivers/net/tulip/Kconfig | 21 +-- 4 files changed, 82 insertions(+), 156 deletions(-) diff --git a/Documentation/networking/3c505.txt b/Documentation/networking/3c505.txt index b9d5b7230118..72f38b13101d 100644 --- a/Documentation/networking/3c505.txt +++ b/Documentation/networking/3c505.txt @@ -14,8 +14,7 @@ If no base address is given at boot time, the driver will autoprobe ports 0x300, 0x280 and 0x310 (in that order). If no IRQ is given, the driver will try to probe for it. -The driver can be used as a loadable module. See net-modules.txt for details -of the parameters it can take. +The driver can be used as a loadable module. Theoretically, one instance of the driver can now run multiple cards, in the standard way (when loading a module, say "modprobe 3c505 diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index bf8890ebbc4c..e8d69b0adf90 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -366,8 +366,7 @@ config MAC89x0 read the Ethernet-HOWTO, available from . - To compile this driver as a module, choose M here and read - . This module will + To compile this driver as a module, choose M here. This module will be called mac89x0. config MACSONIC @@ -380,8 +379,7 @@ config MACSONIC one of these say Y and read the Ethernet-HOWTO, available from . - To compile this driver as a module, choose M here and read - . This module will + To compile this driver as a module, choose M here. This module will be called macsonic. config MACMACE @@ -619,8 +617,7 @@ config EL1 have problems. Some people suggest to ping ("man ping") a nearby machine every minute ("man cron") when using this card. - To compile this driver as a module, choose M here and read - . The module + To compile this driver as a module, choose M here. The module will be called 3c501. config EL2 @@ -632,8 +629,7 @@ config EL2 the Ethernet-HOWTO, available from . - To compile this driver as a module, choose M here and read - . The module + To compile this driver as a module, choose M here. The module will be called 3c503. config ELPLUS @@ -645,8 +641,7 @@ config ELPLUS this type, say Y and read the Ethernet-HOWTO, available from . - To compile this driver as a module, choose M here and read - . The module + To compile this driver as a module, choose M here. The module will be called 3c505. config EL16 @@ -657,8 +652,7 @@ config EL16 the Ethernet-HOWTO, available from . - To compile this driver as a module, choose M here and read - . The module + To compile this driver as a module, choose M here. The module will be called 3c507. config EL3 @@ -673,8 +667,7 @@ config EL3 setup disk to disable Plug & Play mode, and to select the default media type. - To compile this driver as a module, choose M here and read - . The module + To compile this driver as a module, choose M here. The module will be called 3c509. config 3C515 @@ -685,8 +678,7 @@ config 3C515 network card, say Y and read the Ethernet-HOWTO, available from . - To compile this driver as a module, choose M here and read - . The module + To compile this driver as a module, choose M here. The module will be called 3c515. config ELMC @@ -697,8 +689,7 @@ config ELMC the Ethernet-HOWTO, available from . - To compile this driver as a module, choose M here and read - . The module + To compile this driver as a module, choose M here. The module will be called 3c523. config ELMC_II @@ -709,8 +700,7 @@ config ELMC_II the Ethernet-HOWTO, available from . - To compile this driver as a module, choose M here and read - . The module + To compile this driver as a module, choose M here. The module will be called 3c527. config VORTEX @@ -733,8 +723,7 @@ config VORTEX and in the comments at the beginning of . - To compile this support as a module, choose M here and read - . + To compile this support as a module, choose M here. config TYPHOON tristate "3cr990 series \"Typhoon\" support" @@ -751,8 +740,7 @@ config TYPHOON the Ethernet-HOWTO, available from . - To compile this driver as a module, choose M here and read - . The module + To compile this driver as a module, choose M here. The module will be called typhoon. config LANCE @@ -789,8 +777,7 @@ config WD80x3 the Ethernet-HOWTO, available from . - To compile this driver as a module, choose M here and read - . The module + To compile this driver as a module, choose M here. The module will be called wd. config ULTRAMCA @@ -802,8 +789,7 @@ config ULTRAMCA an MCA based system (PS/2), say Y and read the Ethernet-HOWTO, available from . - To compile this driver as a module, choose M here and read - . The module + To compile this driver as a module, choose M here. The module will be called smc-mca. config ULTRA @@ -822,8 +808,7 @@ config ULTRA this but keep it in mind if you have such a SCSI card and have problems. - To compile this driver as a module, choose M here and read - . The module + To compile this driver as a module, choose M here. The module will be called smc-ultra. config ULTRA32 @@ -835,8 +820,7 @@ config ULTRA32 the Ethernet-HOWTO, available from . - To compile this driver as a module, choose M here and read - . The module + To compile this driver as a module, choose M here. The module will be called smc-ultra32. config BFIN_MAC @@ -897,8 +881,7 @@ config SMC9194 and the Ethernet-HOWTO, available from . - To compile this driver as a module, choose M here and read - . The module + To compile this driver as a module, choose M here. The module will be called smc9194. config SMC91X @@ -916,8 +899,7 @@ config SMC91X This driver is also available as a module ( = code which can be inserted in and removed from the running kernel whenever you want). The module will be called smc91x. If you want to compile it as a - module, say M here and read - as well as . + module, say M here and read . config NET_NETX tristate "NetX Ethernet support" @@ -926,8 +908,7 @@ config NET_NETX help This is support for the Hilscher netX builtin Ethernet ports - To compile this driver as a module, choose M here and read - . The module + To compile this driver as a module, choose M here. The module will be called netx-eth. config DM9000 @@ -938,9 +919,8 @@ config DM9000 ---help--- Support for DM9000 chipset. - To compile this driver as a module, choose M here and read - . The module will be - called dm9000. + To compile this driver as a module, choose M here. The module + will be called dm9000. config SMC911X tristate "SMSC LAN911[5678] support" @@ -980,8 +960,7 @@ config NI5010 . Note that this is still experimental code. - To compile this driver as a module, choose M here and read - . The module + To compile this driver as a module, choose M here. The module will be called ni5010. config NI52 @@ -992,8 +971,7 @@ config NI52 the Ethernet-HOWTO, available from . - To compile this driver as a module, choose M here and read - . The module + To compile this driver as a module, choose M here. The module will be called ni52. config NI65 @@ -1004,8 +982,7 @@ config NI65 the Ethernet-HOWTO, available from . - To compile this driver as a module, choose M here and read - . The module + To compile this driver as a module, choose M here. The module will be called ni65. source "drivers/net/tulip/Kconfig" @@ -1019,8 +996,7 @@ config AT1700 the Ethernet-HOWTO, available from . - To compile this driver as a module, choose M here and read - . The module + To compile this driver as a module, choose M here. The module will be called at1700. config DEPCA @@ -1033,8 +1009,7 @@ config DEPCA as well as . - To compile this driver as a module, choose M here and read - . The module + To compile this driver as a module, choose M here. The module will be called depca. config HP100 @@ -1045,8 +1020,7 @@ config HP100 the Ethernet-HOWTO, available from . - To compile this driver as a module, choose M here and read - . The module + To compile this driver as a module, choose M here. The module will be called hp100. config NET_ISA @@ -1075,8 +1049,7 @@ config E2100 the Ethernet-HOWTO, available from . - To compile this driver as a module, choose M here and read - . The module + To compile this driver as a module, choose M here. The module will be called e2100. config EWRK3 @@ -1090,8 +1063,7 @@ config EWRK3 well as the Ethernet-HOWTO, available from . - To compile this driver as a module, choose M here and read - . The module + To compile this driver as a module, choose M here. The module will be called ewrk3. config EEXPRESS @@ -1105,8 +1077,7 @@ config EEXPRESS because the driver was very unreliable. We now have a new driver that should do better. - To compile this driver as a module, choose M here and read - . The module + To compile this driver as a module, choose M here. The module will be called eexpress. config EEXPRESS_PRO @@ -1119,8 +1090,7 @@ config EEXPRESS_PRO driver. Please read the Ethernet-HOWTO, available from . - To compile this driver as a module, choose M here and read - . The module + To compile this driver as a module, choose M here. The module will be called eepro. config HPLAN_PLUS @@ -1132,8 +1102,7 @@ config HPLAN_PLUS the Ethernet-HOWTO, available from . - To compile this driver as a module, choose M here and read - . The module + To compile this driver as a module, choose M here. The module will be called hp-plus. config HPLAN @@ -1145,8 +1114,7 @@ config HPLAN the Ethernet-HOWTO, available from . - To compile this driver as a module, choose M here and read - . The module + To compile this driver as a module, choose M here. The module will be called hp. config LP486E @@ -1165,8 +1133,7 @@ config ETH16I the Ethernet-HOWTO, available from . - To compile this driver as a module, choose M here and read - . The module + To compile this driver as a module, choose M here. The module will be called eth16i. config NE2000 @@ -1186,8 +1153,7 @@ config NE2000 laptops), say N here and Y to "NE/2 (ne2000 MCA version) support", below. - To compile this driver as a module, choose M here and read - . The module + To compile this driver as a module, choose M here. The module will be called ne. config ZNET @@ -1208,8 +1174,7 @@ config SEEQ8005 is for you, read the Ethernet-HOWTO, available from . - To compile this driver as a module, choose M here and read - . The module + To compile this driver as a module, choose M here. The module will be called seeq8005. config NE2_MCA @@ -1221,8 +1186,7 @@ config NE2_MCA the Ethernet-HOWTO, available from . - To compile this driver as a module, choose M here and read - . The module + To compile this driver as a module, choose M here. The module will be called ne2. config IBMLANA @@ -1233,8 +1197,7 @@ config IBMLANA CONFIG_MCA to use this driver. It is both available as an in-kernel driver and as a module. - To compile this driver as a module, choose M here and read - . The only + To compile this driver as a module, choose M here. The only currently supported card is the IBM LAN Adapter/A for Ethernet. It will both support 16K and 32K memory windows, however a 32K window gives a better security against packet losses. Usage of multiple @@ -1248,8 +1211,7 @@ config IBMVETH This driver supports virtual ethernet adapters on newer IBM iSeries and pSeries systems. - To compile this driver as a module, choose M here and read - . The module will + To compile this driver as a module, choose M here. The module will be called ibmveth. source "drivers/net/ibm_emac/Kconfig" @@ -1279,8 +1241,7 @@ config PCNET32 answer Y here and read the Ethernet-HOWTO, available from . - To compile this driver as a module, choose M here and read - . The module + To compile this driver as a module, choose M here. The module will be called pcnet32. config PCNET32_NAPI @@ -1307,8 +1268,7 @@ config AMD8111_ETH answer Y here and read the Ethernet-HOWTO, available from . - To compile this driver as a module, choose M here and read - . The module + To compile this driver as a module, choose M here. The module will be called amd8111e. config AMD8111E_NAPI @@ -1362,8 +1322,7 @@ config AC3200 the Ethernet-HOWTO, available from . - To compile this driver as a module, choose M here and read - . The module + To compile this driver as a module, choose M here. The module will be called ac3200. config APRICOT @@ -1374,9 +1333,8 @@ config APRICOT read the Ethernet-HOWTO, available from . - To compile this driver as a module, choose M here and read - . The module will be - called apricot. + To compile this driver as a module, choose M here. The module + will be called apricot. config B44 tristate "Broadcom 440x/47xx ethernet support" @@ -1388,9 +1346,8 @@ config B44 or M and read the Ethernet-HOWTO, available from . - To compile this driver as a module, choose M here and read - . The module will be - called b44. + To compile this driver as a module, choose M here. The module + will be called b44. # Auto-select SSB PCI-HOST support, if possible config B44_PCI_AUTOSELECT @@ -1419,9 +1376,8 @@ config FORCEDETH read the Ethernet-HOWTO, available from . - To compile this driver as a module, choose M here and read - . The module will be - called forcedeth. + To compile this driver as a module, choose M here. The module + will be called forcedeth. config FORCEDETH_NAPI bool "Use Rx Polling (NAPI) (EXPERIMENTAL)" @@ -1447,9 +1403,8 @@ config CS89x0 as well as . - To compile this driver as a module, choose M here and read - . The module will be - called cs89x0. + To compile this driver as a module, choose M here. The module + will be called cs89x0. config TC35815 tristate "TOSHIBA TC35815 Ethernet support" @@ -1465,8 +1420,7 @@ config EEPRO100 card, say Y and read the Ethernet-HOWTO, available from . - To compile this driver as a module, choose M here and read - . The module + To compile this driver as a module, choose M here. The module will be called eepro100. @@ -1493,8 +1447,7 @@ config E100 More specific information on configuring the driver is in . - To compile this driver as a module, choose M here and read - . The module + To compile this driver as a module, choose M here. The module will be called e100. config LNE390 @@ -1506,8 +1459,7 @@ config LNE390 the Ethernet-HOWTO, available from . - To compile this driver as a module, choose M here and read - . The module + To compile this driver as a module, choose M here. The module will be called lne390. config FEALNX @@ -1547,8 +1499,7 @@ config NE2K_PCI NetVin NV5000SC Via 86C926 SureCom NE34 Winbond Holtek HT80232 Holtek HT80229 - To compile this driver as a module, choose M here and read - . The module + To compile this driver as a module, choose M here. The module will be called ne2k-pci. config NE3210 @@ -1561,8 +1512,7 @@ config NE3210 . Note that this driver will NOT WORK for NE3200 cards as they are completely different. - To compile this driver as a module, choose M here and read - . The module + To compile this driver as a module, choose M here. The module will be called ne3210. config ES3210 @@ -1574,8 +1524,7 @@ config ES3210 the Ethernet-HOWTO, available from . - To compile this driver as a module, choose M here and read - . The module + To compile this driver as a module, choose M here. The module will be called es3210. config 8139CP @@ -1705,8 +1654,7 @@ config TLAN Compaq NetFlex and Olicom cards. Please read the file for more details. - To compile this driver as a module, choose M here and read - . The module + To compile this driver as a module, choose M here. The module will be called tlan. Please email feedback to . @@ -1996,8 +1944,7 @@ config E1000 More specific information on configuring the driver is in . - To compile this driver as a module, choose M here and read - . The module + To compile this driver as a module, choose M here. The module will be called e1000. config E1000_NAPI @@ -2042,8 +1989,7 @@ config E1000E More specific information on configuring the driver is in . - To compile this driver as a module, choose M here and read - . The module + To compile this driver as a module, choose M here. The module will be called e1000e. source "drivers/net/ixp2000/Kconfig" @@ -2076,8 +2022,7 @@ config HAMACHI the Ethernet-HOWTO, available from . - To compile this driver as a module, choose M here and read - . The module will be + To compile this driver as a module, choose M here. The module will be called hamachi. config YELLOWFIN @@ -2526,8 +2471,7 @@ config IXGBE More specific information on configuring the driver is in . - To compile this driver as a module, choose M here and read - . The module + To compile this driver as a module, choose M here. The module will be called ixgbe. config IXGB @@ -2549,8 +2493,7 @@ config IXGB More specific information on configuring the driver is in . - To compile this driver as a module, choose M here and read - . The module + To compile this driver as a module, choose M here. The module will be called ixgb. config IXGB_NAPI @@ -2603,8 +2546,7 @@ config MYRI10GE - To compile this driver as a module, choose M here and read - . The module + To compile this driver as a module, choose M here. The module will be called myri10ge. config NETXEN_NIC @@ -2828,10 +2770,9 @@ config PLIP with the PLIP support in Linux versions 1.0.x. This option enlarges your kernel by about 8 KB. - To compile this driver as a module, choose M here and read - . The module will be - called plip. If unsure, say Y or M, in case you buy a laptop - later. + To compile this driver as a module, choose M here. The module + will be called plip. If unsure, say Y or M, in case you buy + a laptop later. config PPP tristate "PPP (point-to-point protocol) support" @@ -2861,8 +2802,7 @@ config PPP If you said Y to "Version information on all symbols" above, then you cannot compile the PPP driver into the kernel; you can then only compile it as a module. To compile this driver as a module, choose M - here and read . - The module will be called ppp_generic. + here. The module will be called ppp_generic. config PPP_MULTILINK bool "PPP multilink support (EXPERIMENTAL)" @@ -3023,9 +2963,8 @@ config SLIP ). SLIP support will enlarge your kernel by about 4 KB. If unsure, say N. - To compile this driver as a module, choose M here and read - . The module will be - called slip. + To compile this driver as a module, choose M here. The module + will be called slip. config SLIP_COMPRESSED bool "CSLIP compressed headers" diff --git a/drivers/net/arcnet/Kconfig b/drivers/net/arcnet/Kconfig index 4030274fe788..3b2f7f115464 100644 --- a/drivers/net/arcnet/Kconfig +++ b/drivers/net/arcnet/Kconfig @@ -19,8 +19,7 @@ menuconfig ARCNET from (even though ARCnet is not really Ethernet). - To compile this driver as a module, choose M here and read - . The module will + To compile this driver as a module, choose M here. The module will be called arcnet. if ARCNET @@ -81,8 +80,7 @@ config ARCNET_COM90xx have always used the old ARCnet driver without knowing what type of card you had, this is probably the one for you. - To compile this driver as a module, choose M here and read - . The module will + To compile this driver as a module, choose M here. The module will be called com90xx. config ARCNET_COM90xxIO @@ -93,8 +91,7 @@ config ARCNET_COM90xxIO the normal driver. Only use it if your card doesn't support shared memory. - To compile this driver as a module, choose M here and read - . The module will + To compile this driver as a module, choose M here. The module will be called com90io. config ARCNET_RIM_I @@ -105,8 +102,7 @@ config ARCNET_RIM_I driver is completely untested, so if you have one of these cards, please mail , especially if it works! - To compile this driver as a module, choose M here and read - . The module will + To compile this driver as a module, choose M here. The module will be called arc-rimi. config ARCNET_COM20020 @@ -116,8 +112,7 @@ config ARCNET_COM20020 things as promiscuous mode, so packet sniffing is possible, and extra diagnostic information. - To compile this driver as a module, choose M here and read - . The module will + To compile this driver as a module, choose M here. The module will be called com20020. config ARCNET_COM20020_ISA diff --git a/drivers/net/tulip/Kconfig b/drivers/net/tulip/Kconfig index 49d7a290dbbc..20ac1503021e 100644 --- a/drivers/net/tulip/Kconfig +++ b/drivers/net/tulip/Kconfig @@ -24,8 +24,7 @@ config DE2104X will say Y here.) Do read the Ethernet-HOWTO, available from . - To compile this driver as a module, choose M here and read - . The module will + To compile this driver as a module, choose M here. The module will be called de2104x. config TULIP @@ -42,8 +41,7 @@ config TULIP will say Y here.) Do read the Ethernet-HOWTO, available from . - To compile this driver as a module, choose M here and read - . The module will + To compile this driver as a module, choose M here. The module will be called tulip. config TULIP_MWI @@ -104,8 +102,7 @@ config DE4X5 information is contained in . - To compile this driver as a module, choose M here and read - . The module will + To compile this driver as a module, choose M here. The module will be called de4x5. config WINBOND_840 @@ -129,8 +126,7 @@ config DM9102 (Ethernet) card, say Y. Some information is contained in the file . - To compile this driver as a module, choose M here and read - . The module will + To compile this driver as a module, choose M here. The module will be called dmfe. config ULI526X @@ -141,8 +137,7 @@ config ULI526X This driver is for ULi M5261/M5263 10/100M Ethernet Controller (). - To compile this driver as a module, choose M here and read - . The module will + To compile this driver as a module, choose M here. The module will be called uli526x. config PCMCIA_XIRCOM @@ -154,8 +149,7 @@ config PCMCIA_XIRCOM as with work-alike chips from Lite-On (PNIC) and Macronix (MXIC) and ASIX. - To compile this driver as a module, choose M here and read - . The module will + To compile this driver as a module, choose M here. The module will be called xircom_cb. If unsure, say N. config PCMCIA_XIRTULIP @@ -168,8 +162,7 @@ config PCMCIA_XIRTULIP as with work-alike chips from Lite-On (PNIC) and Macronix (MXIC) and ASIX. - To compile this driver as a module, choose M here and read - . The module will + To compile this driver as a module, choose M here. The module will be called xircom_tulip_cb. If unsure, say N. endif # NET_TULIP From be85d4ad8ab69520e5ca4717c491a311c9eeae59 Mon Sep 17 00:00:00 2001 From: Urs Thuermann Date: Mon, 12 Nov 2007 21:05:20 -0800 Subject: [PATCH 21/45] [AF_PACKET]: Fix minor code duplication Simplify some code by eliminating duplicate if-else clauses in packet_do_bind(). Signed-off-by: Urs Thuermann Signed-off-by: David S. Miller --- net/packet/af_packet.c | 16 +++++----------- 1 file changed, 5 insertions(+), 11 deletions(-) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index eb6be5030c70..8a7807dbba01 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -881,20 +881,14 @@ static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 protoc if (protocol == 0) goto out_unlock; - if (dev) { - if (dev->flags&IFF_UP) { - dev_add_pack(&po->prot_hook); - sock_hold(sk); - po->running = 1; - } else { - sk->sk_err = ENETDOWN; - if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); - } - } else { + if (!dev || (dev->flags & IFF_UP)) { dev_add_pack(&po->prot_hook); sock_hold(sk); po->running = 1; + } else { + sk->sk_err = ENETDOWN; + if (!sock_flag(sk, SOCK_DEAD)) + sk->sk_error_report(sk); } out_unlock: From c88864df27590b80fca4a991e0c257d1757cec41 Mon Sep 17 00:00:00 2001 From: Matt Carlson Date: Mon, 12 Nov 2007 21:07:01 -0800 Subject: [PATCH 22/45] [TG3]: Fix 5761 PXEboot crash When 5761 devices boot the machine using PXEboot, PXE leaves the device active when it terminates. The tg3 driver has code to detect this condition and resets the device during initialization. On 5761 devices, device resets involve sending a driver state update message to the APE on the 5761. However, during this initialization stage, communications to the APE registers have not yet been set up. The driver then dereferences a NULL pointer and crashes the machine. The fix is to move the APE register access setup earlier in the initialization code to cover this condition. Signed-off-by: Matt Carlson Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/tg3.c | 74 +++++++++++++++++++++++------------------------ 1 file changed, 37 insertions(+), 37 deletions(-) diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c index cad519910767..ddeaa0c78305 100644 --- a/drivers/net/tg3.c +++ b/drivers/net/tg3.c @@ -12464,43 +12464,6 @@ static int __devinit tg3_init_one(struct pci_dev *pdev, goto err_out_iounmap; } - /* - * Reset chip in case UNDI or EFI driver did not shutdown - * DMA self test will enable WDMAC and we'll see (spurious) - * pending DMA on the PCI bus at that point. - */ - if ((tr32(HOSTCC_MODE) & HOSTCC_MODE_ENABLE) || - (tr32(WDMAC_MODE) & WDMAC_MODE_ENABLE)) { - tw32(MEMARB_MODE, MEMARB_MODE_ENABLE); - tg3_halt(tp, RESET_KIND_SHUTDOWN, 1); - } - - err = tg3_test_dma(tp); - if (err) { - printk(KERN_ERR PFX "DMA engine test failed, aborting.\n"); - goto err_out_iounmap; - } - - /* Tigon3 can do ipv4 only... and some chips have buggy - * checksumming. - */ - if ((tp->tg3_flags & TG3_FLAG_BROKEN_CHECKSUMS) == 0) { - dev->features |= NETIF_F_IP_CSUM | NETIF_F_SG; - if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5755 || - GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5787 || - GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5784 || - GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5761) - dev->features |= NETIF_F_IPV6_CSUM; - - tp->tg3_flags |= TG3_FLAG_RX_CHECKSUMS; - } else - tp->tg3_flags &= ~TG3_FLAG_RX_CHECKSUMS; - - /* flow control autonegotiation is default behavior */ - tp->tg3_flags |= TG3_FLAG_PAUSE_AUTONEG; - - tg3_init_coal(tp); - if (tp->tg3_flags3 & TG3_FLG3_ENABLE_APE) { if (!(pci_resource_flags(pdev, 2) & IORESOURCE_MEM)) { printk(KERN_ERR PFX "Cannot find proper PCI device " @@ -12523,6 +12486,43 @@ static int __devinit tg3_init_one(struct pci_dev *pdev, tg3_ape_lock_init(tp); } + /* + * Reset chip in case UNDI or EFI driver did not shutdown + * DMA self test will enable WDMAC and we'll see (spurious) + * pending DMA on the PCI bus at that point. + */ + if ((tr32(HOSTCC_MODE) & HOSTCC_MODE_ENABLE) || + (tr32(WDMAC_MODE) & WDMAC_MODE_ENABLE)) { + tw32(MEMARB_MODE, MEMARB_MODE_ENABLE); + tg3_halt(tp, RESET_KIND_SHUTDOWN, 1); + } + + err = tg3_test_dma(tp); + if (err) { + printk(KERN_ERR PFX "DMA engine test failed, aborting.\n"); + goto err_out_apeunmap; + } + + /* Tigon3 can do ipv4 only... and some chips have buggy + * checksumming. + */ + if ((tp->tg3_flags & TG3_FLAG_BROKEN_CHECKSUMS) == 0) { + dev->features |= NETIF_F_IP_CSUM | NETIF_F_SG; + if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5755 || + GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5787 || + GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5784 || + GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5761) + dev->features |= NETIF_F_IPV6_CSUM; + + tp->tg3_flags |= TG3_FLAG_RX_CHECKSUMS; + } else + tp->tg3_flags &= ~TG3_FLAG_RX_CHECKSUMS; + + /* flow control autonegotiation is default behavior */ + tp->tg3_flags |= TG3_FLAG_PAUSE_AUTONEG; + + tg3_init_coal(tp); + pci_set_drvdata(pdev, dev); err = register_netdev(dev); From ce057f01956bfcb3cb8588091000ae546be78e00 Mon Sep 17 00:00:00 2001 From: Matt Carlson Date: Mon, 12 Nov 2007 21:08:03 -0800 Subject: [PATCH 23/45] [TG3]: 5784 / 5764 GPHY power down fix 5784 and 5764 devices fail to link / pass traffic after one load / unload cycle. This happens because of a hardware bug in the new CPMU. During normal operation, the MAC depends on the PHY clock being available. When the PHY is powered down, the clock the MAC depends on is disabled. The fix is to switch the MAC clock to an alternate source before powering down the PHY, and to restore the MAC clock to the PHY source upon device resume. Signed-off-by: Matt Carlson Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/tg3.c | 26 ++++++++++++++++++++++++-- drivers/net/tg3.h | 9 ++++++++- 2 files changed, 32 insertions(+), 3 deletions(-) diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c index ddeaa0c78305..82b1cf0e2d18 100644 --- a/drivers/net/tg3.c +++ b/drivers/net/tg3.c @@ -1106,6 +1106,19 @@ static int tg3_phy_reset(struct tg3 *tp) if (err) return err; + if (tp->pci_chip_rev_id == CHIPREV_ID_5784_A0 || + tp->pci_chip_rev_id == CHIPREV_ID_5761_A0) { + u32 val; + + val = tr32(TG3_CPMU_LSPD_1000MB_CLK); + if ((val & CPMU_LSPD_1000MB_MACCLK_MASK) == + CPMU_LSPD_1000MB_MACCLK_12_5) { + val &= ~CPMU_LSPD_1000MB_MACCLK_MASK; + udelay(40); + tw32_f(TG3_CPMU_LSPD_1000MB_CLK, val); + } + } + out: if (tp->tg3_flags2 & TG3_FLG2_PHY_ADC_BUG) { tg3_writephy(tp, MII_TG3_AUX_CTRL, 0x0c00); @@ -1297,6 +1310,8 @@ static void tg3_nvram_unlock(struct tg3 *); static void tg3_power_down_phy(struct tg3 *tp) { + u32 val; + if (tp->tg3_flags2 & TG3_FLG2_PHY_SERDES) { if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5704) { u32 sg_dig_ctrl = tr32(SG_DIG_CTRL); @@ -1311,8 +1326,6 @@ static void tg3_power_down_phy(struct tg3 *tp) } if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5906) { - u32 val; - tg3_bmcr_reset(tp); val = tr32(GRC_MISC_CFG); tw32_f(GRC_MISC_CFG, val | GRC_MISC_CFG_EPHY_IDDQ); @@ -1332,6 +1345,15 @@ static void tg3_power_down_phy(struct tg3 *tp) (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5780 && (tp->tg3_flags2 & TG3_FLG2_MII_SERDES))) return; + + if (tp->pci_chip_rev_id == CHIPREV_ID_5784_A0 || + tp->pci_chip_rev_id == CHIPREV_ID_5761_A0) { + val = tr32(TG3_CPMU_LSPD_1000MB_CLK); + val &= ~CPMU_LSPD_1000MB_MACCLK_MASK; + val |= CPMU_LSPD_1000MB_MACCLK_12_5; + tw32_f(TG3_CPMU_LSPD_1000MB_CLK, val); + } + tg3_writephy(tp, MII_BMCR, BMCR_PDOWN); } diff --git a/drivers/net/tg3.h b/drivers/net/tg3.h index 1d5b2a3dd29d..4659697beb4b 100644 --- a/drivers/net/tg3.h +++ b/drivers/net/tg3.h @@ -109,6 +109,7 @@ #define CHIPREV_ID_5714_A2 0x9002 #define CHIPREV_ID_5906_A1 0xc001 #define CHIPREV_ID_5784_A0 0x5784000 +#define CHIPREV_ID_5761_A0 0x5761000 #define GET_ASIC_REV(CHIP_REV_ID) ((CHIP_REV_ID) >> 12) #define ASIC_REV_5700 0x07 #define ASIC_REV_5701 0x00 @@ -856,7 +857,13 @@ #define CPMU_CTRL_LINK_IDLE_MODE 0x00000200 #define CPMU_CTRL_LINK_AWARE_MODE 0x00000400 #define CPMU_CTRL_LINK_SPEED_MODE 0x00004000 -/* 0x3604 --> 0x365c unused */ +/* 0x3604 --> 0x360c unused */ + +#define TG3_CPMU_LSPD_1000MB_CLK 0x0000360c +#define CPMU_LSPD_1000MB_MACCLK_62_5 0x00000000 +#define CPMU_LSPD_1000MB_MACCLK_12_5 0x00110000 +#define CPMU_LSPD_1000MB_MACCLK_MASK 0x001f0000 +/* 0x3610 --> 0x365c unused */ #define TG3_CPMU_MUTEX_REQ 0x0000365c #define CPMU_MUTEX_REQ_DRIVER 0x00001000 From 84af67fdf07c4fce664dbca87a8d5e2802901bff Mon Sep 17 00:00:00 2001 From: Matt Carlson Date: Mon, 12 Nov 2007 21:08:59 -0800 Subject: [PATCH 24/45] [TG3]: APE flag fix This patch corrects a bug where the ENABLE_APE flag was tested against the wrong flag variable. Signed-off-by: Matt Carlson Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/tg3.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c index 82b1cf0e2d18..833cb9b7f343 100644 --- a/drivers/net/tg3.c +++ b/drivers/net/tg3.c @@ -10881,7 +10881,7 @@ static void __devinit tg3_read_fw_ver(struct tg3 *tp) } if (!(tp->tg3_flags & TG3_FLAG_ENABLE_ASF) || - (tp->tg3_flags & TG3_FLG3_ENABLE_APE)) + (tp->tg3_flags3 & TG3_FLG3_ENABLE_APE)) return; for (offset = TG3_NVM_DIR_START; From 9acb961e7d780291659bf950b3b718ff9e085620 Mon Sep 17 00:00:00 2001 From: Matt Carlson Date: Mon, 12 Nov 2007 21:10:06 -0800 Subject: [PATCH 25/45] [TG3]: 5784 / 5764 DMA engine lockup fix 5784 and 5764 devices lock up when the link speed is 10Mbps, the CPMU link speed mode is enabled, and the MAC clock is running at 1.5Mhz. The fix is to run the MAC clock at faster speeds. Signed-off-by: Matt Carlson Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/tg3.c | 15 +++++++++++++++ drivers/net/tg3.h | 15 +++++++++++++-- 2 files changed, 28 insertions(+), 2 deletions(-) diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c index 833cb9b7f343..b865c5d44837 100644 --- a/drivers/net/tg3.c +++ b/drivers/net/tg3.c @@ -6369,6 +6369,21 @@ static int tg3_reset_hw(struct tg3 *tp, int reset_phy) val = tr32(TG3_CPMU_CTRL); val &= ~(CPMU_CTRL_LINK_AWARE_MODE | CPMU_CTRL_LINK_IDLE_MODE); tw32(TG3_CPMU_CTRL, val); + + val = tr32(TG3_CPMU_LSPD_10MB_CLK); + val &= ~CPMU_LSPD_10MB_MACCLK_MASK; + val |= CPMU_LSPD_10MB_MACCLK_6_25; + tw32(TG3_CPMU_LSPD_10MB_CLK, val); + + val = tr32(TG3_CPMU_LNK_AWARE_PWRMD); + val &= ~CPMU_LNK_AWARE_MACCLK_MASK; + val |= CPMU_LNK_AWARE_MACCLK_6_25; + tw32(TG3_CPMU_LNK_AWARE_PWRMD, val); + + val = tr32(TG3_CPMU_HST_ACC); + val &= ~CPMU_HST_ACC_MACCLK_MASK; + val |= CPMU_HST_ACC_MACCLK_6_25; + tw32(TG3_CPMU_HST_ACC, val); } /* This works around an issue with Athlon chipsets on diff --git a/drivers/net/tg3.h b/drivers/net/tg3.h index 4659697beb4b..c6aad49a375d 100644 --- a/drivers/net/tg3.h +++ b/drivers/net/tg3.h @@ -857,13 +857,24 @@ #define CPMU_CTRL_LINK_IDLE_MODE 0x00000200 #define CPMU_CTRL_LINK_AWARE_MODE 0x00000400 #define CPMU_CTRL_LINK_SPEED_MODE 0x00004000 -/* 0x3604 --> 0x360c unused */ +#define TG3_CPMU_LSPD_10MB_CLK 0x00003604 +#define CPMU_LSPD_10MB_MACCLK_MASK 0x001f0000 +#define CPMU_LSPD_10MB_MACCLK_6_25 0x00130000 +/* 0x3608 --> 0x360c unused */ #define TG3_CPMU_LSPD_1000MB_CLK 0x0000360c #define CPMU_LSPD_1000MB_MACCLK_62_5 0x00000000 #define CPMU_LSPD_1000MB_MACCLK_12_5 0x00110000 #define CPMU_LSPD_1000MB_MACCLK_MASK 0x001f0000 -/* 0x3610 --> 0x365c unused */ +#define TG3_CPMU_LNK_AWARE_PWRMD 0x00003610 +#define CPMU_LNK_AWARE_MACCLK_MASK 0x001f0000 +#define CPMU_LNK_AWARE_MACCLK_6_25 0x00130000 +/* 0x3614 --> 0x361c unused */ + +#define TG3_CPMU_HST_ACC 0x0000361c +#define CPMU_HST_ACC_MACCLK_MASK 0x001f0000 +#define CPMU_HST_ACC_MACCLK_6_25 0x00130000 +/* 0x3620 --> 0x365c unused */ #define TG3_CPMU_MUTEX_REQ 0x0000365c #define CPMU_MUTEX_REQ_DRIVER 0x00001000 From a5767dec1980463aef5614b7ad8a800bb4f4c353 Mon Sep 17 00:00:00 2001 From: Matt Carlson Date: Mon, 12 Nov 2007 21:10:58 -0800 Subject: [PATCH 26/45] [TG3]: Fix nvram selftest failures Newer devices contain bootcode in the chip's private ROM area. This bootcode is called selfboot. Selfboot can be patched in the device's NVRAM and the patches can have several formats. In one particular format, the checksum calculation needs to be slightly modified. This patch adjusts the NVRAM test code for that case, and add support for the missing formats. Signed-off-by: Matt Carlson Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/tg3.c | 36 ++++++++++++++++++++++++++++++------ drivers/net/tg3.h | 8 ++++++++ 2 files changed, 38 insertions(+), 6 deletions(-) diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c index b865c5d44837..ef849b1eb110 100644 --- a/drivers/net/tg3.c +++ b/drivers/net/tg3.c @@ -8701,7 +8701,9 @@ static void tg3_get_ethtool_stats (struct net_device *dev, } #define NVRAM_TEST_SIZE 0x100 -#define NVRAM_SELFBOOT_FORMAT1_SIZE 0x14 +#define NVRAM_SELFBOOT_FORMAT1_0_SIZE 0x14 +#define NVRAM_SELFBOOT_FORMAT1_2_SIZE 0x18 +#define NVRAM_SELFBOOT_FORMAT1_3_SIZE 0x1c #define NVRAM_SELFBOOT_HW_SIZE 0x20 #define NVRAM_SELFBOOT_DATA_SIZE 0x1c @@ -8716,9 +8718,22 @@ static int tg3_test_nvram(struct tg3 *tp) if (magic == TG3_EEPROM_MAGIC) size = NVRAM_TEST_SIZE; else if ((magic & TG3_EEPROM_MAGIC_FW_MSK) == TG3_EEPROM_MAGIC_FW) { - if ((magic & 0xe00000) == 0x200000) - size = NVRAM_SELFBOOT_FORMAT1_SIZE; - else + if ((magic & TG3_EEPROM_SB_FORMAT_MASK) == + TG3_EEPROM_SB_FORMAT_1) { + switch (magic & TG3_EEPROM_SB_REVISION_MASK) { + case TG3_EEPROM_SB_REVISION_0: + size = NVRAM_SELFBOOT_FORMAT1_0_SIZE; + break; + case TG3_EEPROM_SB_REVISION_2: + size = NVRAM_SELFBOOT_FORMAT1_2_SIZE; + break; + case TG3_EEPROM_SB_REVISION_3: + size = NVRAM_SELFBOOT_FORMAT1_3_SIZE; + break; + default: + return 0; + } + } else return 0; } else if ((magic & TG3_EEPROM_MAGIC_HW_MSK) == TG3_EEPROM_MAGIC_HW) size = NVRAM_SELFBOOT_HW_SIZE; @@ -8745,8 +8760,17 @@ static int tg3_test_nvram(struct tg3 *tp) TG3_EEPROM_MAGIC_FW) { u8 *buf8 = (u8 *) buf, csum8 = 0; - for (i = 0; i < size; i++) - csum8 += buf8[i]; + if ((cpu_to_be32(buf[0]) & TG3_EEPROM_SB_REVISION_MASK) == + TG3_EEPROM_SB_REVISION_2) { + /* For rev 2, the csum doesn't include the MBA. */ + for (i = 0; i < TG3_EEPROM_SB_F1R2_MBA_OFF; i++) + csum8 += buf8[i]; + for (i = TG3_EEPROM_SB_F1R2_MBA_OFF + 4; i < size; i++) + csum8 += buf8[i]; + } else { + for (i = 0; i < size; i++) + csum8 += buf8[i]; + } if (csum8 == 0) { err = 0; diff --git a/drivers/net/tg3.h b/drivers/net/tg3.h index c6aad49a375d..f715b35dfd54 100644 --- a/drivers/net/tg3.h +++ b/drivers/net/tg3.h @@ -1555,6 +1555,12 @@ #define TG3_EEPROM_MAGIC 0x669955aa #define TG3_EEPROM_MAGIC_FW 0xa5000000 #define TG3_EEPROM_MAGIC_FW_MSK 0xff000000 +#define TG3_EEPROM_SB_FORMAT_MASK 0x00e00000 +#define TG3_EEPROM_SB_FORMAT_1 0x00200000 +#define TG3_EEPROM_SB_REVISION_MASK 0x001f0000 +#define TG3_EEPROM_SB_REVISION_0 0x00000000 +#define TG3_EEPROM_SB_REVISION_2 0x00020000 +#define TG3_EEPROM_SB_REVISION_3 0x00030000 #define TG3_EEPROM_MAGIC_HW 0xabcd #define TG3_EEPROM_MAGIC_HW_MSK 0xffff @@ -1765,6 +1771,8 @@ /* APE convenience enumerations. */ #define TG3_APE_LOCK_MEM 4 +#define TG3_EEPROM_SB_F1R2_MBA_OFF 0x10 + /* There are two ways to manage the TX descriptors on the tigon3. * Either the descriptors are in host DMA'able memory, or they From e875093c9659d2a9f3923aa9ee1b89ef40cf95b9 Mon Sep 17 00:00:00 2001 From: Matt Carlson Date: Mon, 12 Nov 2007 21:11:51 -0800 Subject: [PATCH 27/45] [TG3]: CPMU adjustments for loopback tests This patch adds the LINK_SPEED mode to the list of CPMU modes that can cause the loopback tests to fail. These bugs are planned to be fixed in future revisions of the chip, so the patch qualifies the fixes as such. Signed-off-by: Matt Carlson Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/tg3.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c index ef849b1eb110..25e57d8ddb51 100644 --- a/drivers/net/tg3.c +++ b/drivers/net/tg3.c @@ -9354,7 +9354,8 @@ static int tg3_test_loopback(struct tg3 *tp) if (err) return TG3_LOOPBACK_FAILED; - if (tp->tg3_flags & TG3_FLAG_CPMU_PRESENT) { + if (tp->pci_chip_rev_id == CHIPREV_ID_5784_A0 || + tp->pci_chip_rev_id == CHIPREV_ID_5761_A0) { int i; u32 status; @@ -9371,17 +9372,18 @@ static int tg3_test_loopback(struct tg3 *tp) if (status != CPMU_MUTEX_GNT_DRIVER) return TG3_LOOPBACK_FAILED; - cpmuctrl = tr32(TG3_CPMU_CTRL); - /* Turn off power management based on link speed. */ + cpmuctrl = tr32(TG3_CPMU_CTRL); tw32(TG3_CPMU_CTRL, - cpmuctrl & ~CPMU_CTRL_LINK_SPEED_MODE); + cpmuctrl & ~(CPMU_CTRL_LINK_SPEED_MODE | + CPMU_CTRL_LINK_AWARE_MODE)); } if (tg3_run_loopback(tp, TG3_MAC_LOOPBACK)) err |= TG3_MAC_LOOPBACK_FAILED; - if (tp->tg3_flags & TG3_FLAG_CPMU_PRESENT) { + if (tp->pci_chip_rev_id == CHIPREV_ID_5784_A0 || + tp->pci_chip_rev_id == CHIPREV_ID_5761_A0) { tw32(TG3_CPMU_CTRL, cpmuctrl); /* Release the mutex */ From 662f38d242488cfdcda7b3684ac610d3e4d568a7 Mon Sep 17 00:00:00 2001 From: Matt Carlson Date: Mon, 12 Nov 2007 21:16:17 -0800 Subject: [PATCH 28/45] [TG3]: Disable GPHY autopowerdown New CPMU devices contend with the GPHY for power management. The GPHY autopowerdown feature is enabled by default in the PHY and thus needs to be disabled after every PHY reset. Signed-off-by: Matt Carlson Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/tg3.c | 6 ++++++ drivers/net/tg3.h | 6 ++++++ 2 files changed, 12 insertions(+) diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c index 25e57d8ddb51..b5c4799003e0 100644 --- a/drivers/net/tg3.c +++ b/drivers/net/tg3.c @@ -1117,6 +1117,12 @@ static int tg3_phy_reset(struct tg3 *tp) udelay(40); tw32_f(TG3_CPMU_LSPD_1000MB_CLK, val); } + + /* Disable GPHY autopowerdown. */ + tg3_writephy(tp, MII_TG3_MISC_SHDW, + MII_TG3_MISC_SHDW_WREN | + MII_TG3_MISC_SHDW_APD_SEL | + MII_TG3_MISC_SHDW_APD_WKTM_84MS); } out: diff --git a/drivers/net/tg3.h b/drivers/net/tg3.h index f715b35dfd54..5b799ff2c4d6 100644 --- a/drivers/net/tg3.h +++ b/drivers/net/tg3.h @@ -1715,6 +1715,12 @@ #define MII_TG3_ISTAT 0x1a /* IRQ status register */ #define MII_TG3_IMASK 0x1b /* IRQ mask register */ +#define MII_TG3_MISC_SHDW 0x1c +#define MII_TG3_MISC_SHDW_WREN 0x8000 +#define MII_TG3_MISC_SHDW_APD_SEL 0x2800 + +#define MII_TG3_MISC_SHDW_APD_WKTM_84MS 0x0001 + /* ISTAT/IMASK event bits */ #define MII_TG3_INT_LINKCHG 0x0002 #define MII_TG3_INT_SPEEDCHG 0x0004 From 5f60891b80f1a0f0a0015b084f4838ae8b9637c7 Mon Sep 17 00:00:00 2001 From: Matt Carlson Date: Mon, 12 Nov 2007 21:17:07 -0800 Subject: [PATCH 29/45] [TG3]: Limit 5784 / 5764 to MAC LED mode Most 5784 / 5764 LED modes do not work as expected because of a hardware bug. This patch forces the LED mode to be in MAC LED mode. Signed-off-by: Matt Carlson Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/tg3.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c index b5c4799003e0..bb3b73435170 100644 --- a/drivers/net/tg3.c +++ b/drivers/net/tg3.c @@ -10610,6 +10610,9 @@ static void __devinit tg3_get_eeprom_hw_cfg(struct tg3 *tp) tp->pdev->subsystem_vendor == PCI_VENDOR_ID_DELL) tp->led_ctrl = LED_CTRL_MODE_PHY_2; + if (tp->pci_chip_rev_id == CHIPREV_ID_5784_A0) + tp->led_ctrl = LED_CTRL_MODE_MAC; + if (nic_cfg & NIC_SRAM_DATA_CFG_EEPROM_WP) { tp->tg3_flags |= TG3_FLAG_EEPROM_WRITE_PROT; if ((tp->pdev->subsystem_vendor == From aa6c91fe5913faa2cd2a62de993a3130799412b1 Mon Sep 17 00:00:00 2001 From: Matt Carlson Date: Mon, 12 Nov 2007 21:18:04 -0800 Subject: [PATCH 30/45] [TG3]: Prescaler fix Internal hardware timers become inaccurate after link events. Clock frequency switches performed by the CPMU fail to adjust timer prescalers. The fix is to detect core clock frequency changes during link events and adjust the timer prescalers accordingly. Signed-off-by: Matt Carlson Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/tg3.c | 16 ++++++++++++++++ drivers/net/tg3.h | 9 ++++++++- 2 files changed, 24 insertions(+), 1 deletion(-) diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c index bb3b73435170..ecd64a224e95 100644 --- a/drivers/net/tg3.c +++ b/drivers/net/tg3.c @@ -3154,6 +3154,22 @@ static int tg3_setup_phy(struct tg3 *tp, int force_reset) err = tg3_setup_copper_phy(tp, force_reset); } + if (tp->pci_chip_rev_id == CHIPREV_ID_5784_A0) { + u32 val, scale; + + val = tr32(TG3_CPMU_CLCK_STAT) & CPMU_CLCK_STAT_MAC_CLCK_MASK; + if (val == CPMU_CLCK_STAT_MAC_CLCK_62_5) + scale = 65; + else if (val == CPMU_CLCK_STAT_MAC_CLCK_6_25) + scale = 6; + else + scale = 12; + + val = tr32(GRC_MISC_CFG) & ~GRC_MISC_CFG_PRESCALAR_MASK; + val |= (scale << GRC_MISC_CFG_PRESCALAR_SHIFT); + tw32(GRC_MISC_CFG, val); + } + if (tp->link_config.active_speed == SPEED_1000 && tp->link_config.active_duplex == DUPLEX_HALF) tw32(MAC_TX_LENGTHS, diff --git a/drivers/net/tg3.h b/drivers/net/tg3.h index 5b799ff2c4d6..d325ab59b391 100644 --- a/drivers/net/tg3.h +++ b/drivers/net/tg3.h @@ -874,7 +874,14 @@ #define TG3_CPMU_HST_ACC 0x0000361c #define CPMU_HST_ACC_MACCLK_MASK 0x001f0000 #define CPMU_HST_ACC_MACCLK_6_25 0x00130000 -/* 0x3620 --> 0x365c unused */ +/* 0x3620 --> 0x3630 unused */ + +#define TG3_CPMU_CLCK_STAT 0x00003630 +#define CPMU_CLCK_STAT_MAC_CLCK_MASK 0x001f0000 +#define CPMU_CLCK_STAT_MAC_CLCK_62_5 0x00000000 +#define CPMU_CLCK_STAT_MAC_CLCK_12_5 0x00110000 +#define CPMU_CLCK_STAT_MAC_CLCK_6_25 0x00130000 +/* 0x3634 --> 0x365c unused */ #define TG3_CPMU_MUTEX_REQ 0x0000365c #define CPMU_MUTEX_REQ_DRIVER 0x00001000 From 5f5c51e3d473d8ddc0c32156c2b27e2fe92b9b57 Mon Sep 17 00:00:00 2001 From: Matt Carlson Date: Mon, 12 Nov 2007 21:19:37 -0800 Subject: [PATCH 31/45] [TG3]: Increase the PCI MRRS Previous devices hardcoded the PCI Maximum Read Request Size to 4K. To better comply with the PCI spec, the hardware now defaults the MRRS to 512 bytes. This will yield poor driver performance if left untouched. This patch increases the MRRS to 4K on driver initialization. Signed-off-by: Matt Carlson Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/tg3.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c index ecd64a224e95..72db78b1ec3b 100644 --- a/drivers/net/tg3.c +++ b/drivers/net/tg3.c @@ -5098,12 +5098,15 @@ static void tg3_restore_pci_state(struct tg3 *tp) pci_write_config_word(tp->pdev, PCI_COMMAND, tp->pci_cmd); - if (!(tp->tg3_flags2 & TG3_FLG2_PCI_EXPRESS)) { + if (tp->tg3_flags2 & TG3_FLG2_PCI_EXPRESS) + pcie_set_readrq(tp->pdev, 4096); + else { pci_write_config_byte(tp->pdev, PCI_CACHE_LINE_SIZE, tp->pci_cacheline_sz); pci_write_config_byte(tp->pdev, PCI_LATENCY_TIMER, tp->pci_lat_timer); } + /* Make sure PCI-X relaxed ordering bit is clear. */ if (tp->pcix_cap) { u16 pcix_cmd; @@ -11215,6 +11218,9 @@ static int __devinit tg3_get_invariants(struct tg3 *tp) pcie_cap = pci_find_capability(tp->pdev, PCI_CAP_ID_EXP); if (pcie_cap != 0) { tp->tg3_flags2 |= TG3_FLG2_PCI_EXPRESS; + + pcie_set_readrq(tp->pdev, 4096); + if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5906) { u16 lnkctl; From b5af7126ea7586eb8f030280c027611c42a6a9c7 Mon Sep 17 00:00:00 2001 From: Matt Carlson Date: Mon, 12 Nov 2007 21:22:02 -0800 Subject: [PATCH 32/45] [TG3]: Add A1 revs This patch adds the A1 revision of 5784, 5764, and 5761, and applies all previous bugfixes. In places where the list of devices gets too long, the patch uses a new TG3_FLG3_5761_5784_AX_FIXES flag instead. Signed-off-by: Matt Carlson Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/tg3.c | 30 ++++++++++++++++++------------ drivers/net/tg3.h | 3 +++ 2 files changed, 21 insertions(+), 12 deletions(-) diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c index 72db78b1ec3b..8e76092a171e 100644 --- a/drivers/net/tg3.c +++ b/drivers/net/tg3.c @@ -1106,8 +1106,7 @@ static int tg3_phy_reset(struct tg3 *tp) if (err) return err; - if (tp->pci_chip_rev_id == CHIPREV_ID_5784_A0 || - tp->pci_chip_rev_id == CHIPREV_ID_5761_A0) { + if (tp->tg3_flags3 & TG3_FLG3_5761_5784_AX_FIXES) { u32 val; val = tr32(TG3_CPMU_LSPD_1000MB_CLK); @@ -1352,8 +1351,7 @@ static void tg3_power_down_phy(struct tg3 *tp) (tp->tg3_flags2 & TG3_FLG2_MII_SERDES))) return; - if (tp->pci_chip_rev_id == CHIPREV_ID_5784_A0 || - tp->pci_chip_rev_id == CHIPREV_ID_5761_A0) { + if (tp->tg3_flags3 & TG3_FLG3_5761_5784_AX_FIXES) { val = tr32(TG3_CPMU_LSPD_1000MB_CLK); val &= ~CPMU_LSPD_1000MB_MACCLK_MASK; val |= CPMU_LSPD_1000MB_MACCLK_12_5; @@ -3154,7 +3152,8 @@ static int tg3_setup_phy(struct tg3 *tp, int force_reset) err = tg3_setup_copper_phy(tp, force_reset); } - if (tp->pci_chip_rev_id == CHIPREV_ID_5784_A0) { + if (tp->pci_chip_rev_id == CHIPREV_ID_5784_A0 || + tp->pci_chip_rev_id == CHIPREV_ID_5784_A1) { u32 val, scale; val = tr32(TG3_CPMU_CLCK_STAT) & CPMU_CLCK_STAT_MAC_CLCK_MASK; @@ -6390,7 +6389,8 @@ static int tg3_reset_hw(struct tg3 *tp, int reset_phy) tg3_write_sig_legacy(tp, RESET_KIND_INIT); - if (tp->pci_chip_rev_id == CHIPREV_ID_5784_A0) { + if (tp->pci_chip_rev_id == CHIPREV_ID_5784_A0 || + tp->pci_chip_rev_id == CHIPREV_ID_5784_A1) { val = tr32(TG3_CPMU_CTRL); val &= ~(CPMU_CTRL_LINK_AWARE_MODE | CPMU_CTRL_LINK_IDLE_MODE); tw32(TG3_CPMU_CTRL, val); @@ -9379,8 +9379,7 @@ static int tg3_test_loopback(struct tg3 *tp) if (err) return TG3_LOOPBACK_FAILED; - if (tp->pci_chip_rev_id == CHIPREV_ID_5784_A0 || - tp->pci_chip_rev_id == CHIPREV_ID_5761_A0) { + if (tp->tg3_flags3 & TG3_FLG3_5761_5784_AX_FIXES) { int i; u32 status; @@ -9407,8 +9406,7 @@ static int tg3_test_loopback(struct tg3 *tp) if (tg3_run_loopback(tp, TG3_MAC_LOOPBACK)) err |= TG3_MAC_LOOPBACK_FAILED; - if (tp->pci_chip_rev_id == CHIPREV_ID_5784_A0 || - tp->pci_chip_rev_id == CHIPREV_ID_5761_A0) { + if (tp->tg3_flags3 & TG3_FLG3_5761_5784_AX_FIXES) { tw32(TG3_CPMU_CTRL, cpmuctrl); /* Release the mutex */ @@ -10629,7 +10627,8 @@ static void __devinit tg3_get_eeprom_hw_cfg(struct tg3 *tp) tp->pdev->subsystem_vendor == PCI_VENDOR_ID_DELL) tp->led_ctrl = LED_CTRL_MODE_PHY_2; - if (tp->pci_chip_rev_id == CHIPREV_ID_5784_A0) + if (tp->pci_chip_rev_id == CHIPREV_ID_5784_A0 || + tp->pci_chip_rev_id == CHIPREV_ID_5784_A1) tp->led_ctrl = LED_CTRL_MODE_MAC; if (nic_cfg & NIC_SRAM_DATA_CFG_EEPROM_WP) { @@ -11401,9 +11400,16 @@ static int __devinit tg3_get_invariants(struct tg3 *tp) } if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5784 || - GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5761) + GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5761) { tp->tg3_flags |= TG3_FLAG_CPMU_PRESENT; + if (tp->pci_chip_rev_id == CHIPREV_ID_5784_A0 || + tp->pci_chip_rev_id == CHIPREV_ID_5784_A1 || + tp->pci_chip_rev_id == CHIPREV_ID_5761_A0 || + tp->pci_chip_rev_id == CHIPREV_ID_5761_A1) + tp->tg3_flags3 |= TG3_FLG3_5761_5784_AX_FIXES; + } + /* Set up tp->grc_local_ctrl before calling tg3_set_power_state(). * GPIO1 driven high will bring 5700's external PHY out of reset. * It is also used as eeprom write protect on LOMs. diff --git a/drivers/net/tg3.h b/drivers/net/tg3.h index d325ab59b391..da18fb220712 100644 --- a/drivers/net/tg3.h +++ b/drivers/net/tg3.h @@ -109,7 +109,9 @@ #define CHIPREV_ID_5714_A2 0x9002 #define CHIPREV_ID_5906_A1 0xc001 #define CHIPREV_ID_5784_A0 0x5784000 +#define CHIPREV_ID_5784_A1 0x5784001 #define CHIPREV_ID_5761_A0 0x5761000 +#define CHIPREV_ID_5761_A1 0x5761001 #define GET_ASIC_REV(CHIP_REV_ID) ((CHIP_REV_ID) >> 12) #define ASIC_REV_5700 0x07 #define ASIC_REV_5701 0x00 @@ -2391,6 +2393,7 @@ struct tg3 { u32 tg3_flags3; #define TG3_FLG3_NO_NVRAM_ADDR_TRANS 0x00000001 #define TG3_FLG3_ENABLE_APE 0x00000002 +#define TG3_FLG3_5761_5784_AX_FIXES 0x00000004 struct timer_list timer; u16 timer_counter; From 3bebab591413929c405925a8fdd98f5b0d660e39 Mon Sep 17 00:00:00 2001 From: Matt Carlson Date: Mon, 12 Nov 2007 21:22:40 -0800 Subject: [PATCH 33/45] [TG3]: MII => TP This patch changes the PHY type reported through ethtool for copper devices from MII to TP. The latter is more accurate. Signed-off-by: Matt Carlson Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/tg3.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c index 8e76092a171e..8d518cc85ad8 100644 --- a/drivers/net/tg3.c +++ b/drivers/net/tg3.c @@ -8329,7 +8329,7 @@ static int tg3_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) SUPPORTED_100baseT_Full | SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full | - SUPPORTED_MII); + SUPPORTED_TP); cmd->port = PORT_TP; } else { cmd->supported |= SUPPORTED_FIBRE; From 458c096ed787b2572303a7087d23bfab06b450be Mon Sep 17 00:00:00 2001 From: Matt Carlson Date: Mon, 12 Nov 2007 21:23:21 -0800 Subject: [PATCH 34/45] [TG3]: Update version to 3.86 This patch updates the version number to 3.86 Signed-off-by: Matt Carlson Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/tg3.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c index 8d518cc85ad8..4942f7d18937 100644 --- a/drivers/net/tg3.c +++ b/drivers/net/tg3.c @@ -64,8 +64,8 @@ #define DRV_MODULE_NAME "tg3" #define PFX DRV_MODULE_NAME ": " -#define DRV_MODULE_VERSION "3.85" -#define DRV_MODULE_RELDATE "October 18, 2007" +#define DRV_MODULE_VERSION "3.86" +#define DRV_MODULE_RELDATE "November 9, 2007" #define TG3_DEF_MAC_MODE 0 #define TG3_DEF_RX_MODE 0 From 6aed42159db1f99e83ccf17b1aa1a83bc75ac3e8 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Mon, 12 Nov 2007 21:24:14 -0800 Subject: [PATCH 35/45] [NET]: Unexport sysctl_{r,w}mem_max. sysctl_{r,w}mem_max can now be unexported. Signed-off-by: Adrian Bunk Signed-off-by: David S. Miller --- net/core/sock.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/net/core/sock.c b/net/core/sock.c index 8fc2f84209e4..c519b439b8b1 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2097,7 +2097,3 @@ EXPORT_SYMBOL(sock_wmalloc); EXPORT_SYMBOL(sock_i_uid); EXPORT_SYMBOL(sock_i_ino); EXPORT_SYMBOL(sysctl_optmem_max); -#ifdef CONFIG_SYSCTL -EXPORT_SYMBOL(sysctl_rmem_max); -EXPORT_SYMBOL(sysctl_wmem_max); -#endif From 22649d1afbe6988688a07fd70abb06f1e2213567 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Mon, 12 Nov 2007 21:25:24 -0800 Subject: [PATCH 36/45] [IPVS]: Remove unused exports. This patch removes the following unused EXPORT_SYMBOL's: - ip_vs_try_bind_dest - ip_vs_find_dest Signed-off-by: Adrian Bunk Signed-off-by: David S. Miller --- net/ipv4/ipvs/ip_vs_conn.c | 1 - net/ipv4/ipvs/ip_vs_ctl.c | 1 - 2 files changed, 2 deletions(-) diff --git a/net/ipv4/ipvs/ip_vs_conn.c b/net/ipv4/ipvs/ip_vs_conn.c index b7eeae622d9b..0a9f3c37e18d 100644 --- a/net/ipv4/ipvs/ip_vs_conn.c +++ b/net/ipv4/ipvs/ip_vs_conn.c @@ -441,7 +441,6 @@ struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp) } else return NULL; } -EXPORT_SYMBOL(ip_vs_try_bind_dest); /* diff --git a/net/ipv4/ipvs/ip_vs_ctl.c b/net/ipv4/ipvs/ip_vs_ctl.c index 3c4d22a468ec..b64cf45a9ead 100644 --- a/net/ipv4/ipvs/ip_vs_ctl.c +++ b/net/ipv4/ipvs/ip_vs_ctl.c @@ -604,7 +604,6 @@ struct ip_vs_dest *ip_vs_find_dest(__be32 daddr, __be16 dport, ip_vs_service_put(svc); return dest; } -EXPORT_SYMBOL(ip_vs_find_dest); /* * Lookup dest by {svc,addr,port} in the destination trash. From d71209ded2ba6010070d02005384897c59859d00 Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Mon, 12 Nov 2007 21:27:28 -0800 Subject: [PATCH 37/45] [INET]: Use list_head-s in inetpeer.c The inetpeer.c tracks the LRU list of inet_perr-s, but makes it by hands. Use the list_head-s for this. Signed-off-by: Pavel Emelyanov Signed-off-by: David S. Miller --- include/net/inetpeer.h | 2 +- net/ipv4/inetpeer.c | 42 +++++++++++++++--------------------------- 2 files changed, 16 insertions(+), 28 deletions(-) diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h index aa10a8178e70..ad8404b56113 100644 --- a/include/net/inetpeer.h +++ b/include/net/inetpeer.h @@ -22,7 +22,7 @@ struct inet_peer __be32 v4daddr; /* peer's address */ __u16 avl_height; __u16 ip_id_count; /* IP ID for the next packet */ - struct inet_peer *unused_next, **unused_prevp; + struct list_head unused; __u32 dtime; /* the time of last use of not * referenced entries */ atomic_t refcnt; diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index 771031dfbd0f..af995198f643 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -61,7 +61,7 @@ * 4. Global variable peer_total is modified under the pool lock. * 5. struct inet_peer fields modification: * avl_left, avl_right, avl_parent, avl_height: pool lock - * unused_next, unused_prevp: unused node list lock + * unused: unused node list lock * refcnt: atomically against modifications on other CPU; * usually under some other lock to prevent node disappearing * dtime: unused node list lock @@ -94,8 +94,7 @@ int inet_peer_maxttl __read_mostly = 10 * 60 * HZ; /* usual time to live: 10 min int inet_peer_gc_mintime __read_mostly = 10 * HZ; int inet_peer_gc_maxtime __read_mostly = 120 * HZ; -static struct inet_peer *inet_peer_unused_head; -static struct inet_peer **inet_peer_unused_tailp = &inet_peer_unused_head; +static LIST_HEAD(unused_peers); static DEFINE_SPINLOCK(inet_peer_unused_lock); static void peer_check_expire(unsigned long dummy); @@ -138,15 +137,7 @@ void __init inet_initpeers(void) static void unlink_from_unused(struct inet_peer *p) { spin_lock_bh(&inet_peer_unused_lock); - if (p->unused_prevp != NULL) { - /* On unused list. */ - *p->unused_prevp = p->unused_next; - if (p->unused_next != NULL) - p->unused_next->unused_prevp = p->unused_prevp; - else - inet_peer_unused_tailp = p->unused_prevp; - p->unused_prevp = NULL; /* mark it as removed */ - } + list_del_init(&p->unused); spin_unlock_bh(&inet_peer_unused_lock); } @@ -337,24 +328,24 @@ static void unlink_from_pool(struct inet_peer *p) /* May be called with local BH enabled. */ static int cleanup_once(unsigned long ttl) { - struct inet_peer *p; + struct inet_peer *p = NULL; /* Remove the first entry from the list of unused nodes. */ spin_lock_bh(&inet_peer_unused_lock); - p = inet_peer_unused_head; - if (p != NULL) { - __u32 delta = (__u32)jiffies - p->dtime; + if (!list_empty(&unused_peers)) { + __u32 delta; + + p = list_first_entry(&unused_peers, struct inet_peer, unused); + delta = (__u32)jiffies - p->dtime; + if (delta < ttl) { /* Do not prune fresh entries. */ spin_unlock_bh(&inet_peer_unused_lock); return -1; } - inet_peer_unused_head = p->unused_next; - if (p->unused_next != NULL) - p->unused_next->unused_prevp = p->unused_prevp; - else - inet_peer_unused_tailp = p->unused_prevp; - p->unused_prevp = NULL; /* mark as not on the list */ + + list_del_init(&p->unused); + /* Grab an extra reference to prevent node disappearing * before unlink_from_pool() call. */ atomic_inc(&p->refcnt); @@ -412,7 +403,7 @@ struct inet_peer *inet_getpeer(__be32 daddr, int create) /* Link the node. */ link_to_pool(n); - n->unused_prevp = NULL; /* not on the list */ + INIT_LIST_HEAD(&n->unused); peer_total++; write_unlock_bh(&peer_pool_lock); @@ -467,10 +458,7 @@ void inet_putpeer(struct inet_peer *p) { spin_lock_bh(&inet_peer_unused_lock); if (atomic_dec_and_test(&p->refcnt)) { - p->unused_prevp = inet_peer_unused_tailp; - p->unused_next = NULL; - *inet_peer_unused_tailp = p; - inet_peer_unused_tailp = &p->unused_next; + list_add_tail(&p->unused, &unused_peers); p->dtime = (__u32)jiffies; } spin_unlock_bh(&inet_peer_unused_lock); From e0bf9cf15fc30d300b7fbd821c6bc975531fab44 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Tue, 13 Nov 2007 02:57:16 -0800 Subject: [PATCH 38/45] [NETFILTER]: nf_nat: fix memset error The size passing to memset is the size of a pointer. Signed-off-by: Li Zefan Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- net/ipv4/netfilter/nf_nat_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c index 56e93f692e82..70e7997ea284 100644 --- a/net/ipv4/netfilter/nf_nat_core.c +++ b/net/ipv4/netfilter/nf_nat_core.c @@ -681,7 +681,7 @@ static int clean_nat(struct nf_conn *i, void *data) if (!nat) return 0; - memset(nat, 0, sizeof(nat)); + memset(nat, 0, sizeof(*nat)); i->status &= ~(IPS_NAT_MASK | IPS_NAT_DONE_MASK | IPS_SEQ_ADJUST); return 0; } From 4ce5ba6aecb218981fc76585b6d9a7d0019e61b5 Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Tue, 13 Nov 2007 02:58:09 -0800 Subject: [PATCH 39/45] [NETFILTER]: Consolidate nf_sockopt and compat_nf_sockopt Both lookup the nf_sockopt_ops object to call the get/set callbacks from, but they perform it in a completely similar way. Introduce the helper for finding the ops. Signed-off-by: Pavel Emelyanov Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- net/netfilter/nf_sockopt.c | 128 ++++++++++++++++--------------------- 1 file changed, 55 insertions(+), 73 deletions(-) diff --git a/net/netfilter/nf_sockopt.c b/net/netfilter/nf_sockopt.c index 2dfac3253569..87bc1443c520 100644 --- a/net/netfilter/nf_sockopt.c +++ b/net/netfilter/nf_sockopt.c @@ -60,6 +60,41 @@ void nf_unregister_sockopt(struct nf_sockopt_ops *reg) } EXPORT_SYMBOL(nf_unregister_sockopt); +static struct nf_sockopt_ops *nf_sockopt_find(struct sock *sk, int pf, + int val, int get) +{ + struct nf_sockopt_ops *ops; + + if (sk->sk_net != &init_net) + return ERR_PTR(-ENOPROTOOPT); + + if (mutex_lock_interruptible(&nf_sockopt_mutex) != 0) + return ERR_PTR(-EINTR); + + list_for_each_entry(ops, &nf_sockopts, list) { + if (ops->pf == pf) { + if (!try_module_get(ops->owner)) + goto out_nosup; + + if (get) { + if (val >= ops->get_optmin && + val < ops->get_optmax) + goto out; + } else { + if (val >= ops->set_optmin && + val < ops->set_optmax) + goto out; + } + module_put(ops->owner); + } + } +out_nosup: + ops = ERR_PTR(-ENOPROTOOPT); +out: + mutex_unlock(&nf_sockopt_mutex); + return ops; +} + /* Call get/setsockopt() */ static int nf_sockopt(struct sock *sk, int pf, int val, char __user *opt, int *len, int get) @@ -67,39 +102,15 @@ static int nf_sockopt(struct sock *sk, int pf, int val, struct nf_sockopt_ops *ops; int ret; - if (sk->sk_net != &init_net) - return -ENOPROTOOPT; + ops = nf_sockopt_find(sk, pf, val, get); + if (IS_ERR(ops)) + return PTR_ERR(ops); - if (mutex_lock_interruptible(&nf_sockopt_mutex) != 0) - return -EINTR; + if (get) + ret = ops->get(sk, val, opt, len); + else + ret = ops->set(sk, val, opt, *len); - list_for_each_entry(ops, &nf_sockopts, list) { - if (ops->pf == pf) { - if (!try_module_get(ops->owner)) - goto out_nosup; - if (get) { - if (val >= ops->get_optmin - && val < ops->get_optmax) { - mutex_unlock(&nf_sockopt_mutex); - ret = ops->get(sk, val, opt, len); - goto out; - } - } else { - if (val >= ops->set_optmin - && val < ops->set_optmax) { - mutex_unlock(&nf_sockopt_mutex); - ret = ops->set(sk, val, opt, *len); - goto out; - } - } - module_put(ops->owner); - } - } - out_nosup: - mutex_unlock(&nf_sockopt_mutex); - return -ENOPROTOOPT; - - out: module_put(ops->owner); return ret; } @@ -124,51 +135,22 @@ static int compat_nf_sockopt(struct sock *sk, int pf, int val, struct nf_sockopt_ops *ops; int ret; - if (sk->sk_net != &init_net) - return -ENOPROTOOPT; + ops = nf_sockopt_find(sk, pf, val, get); + if (IS_ERR(ops)) + return PTR_ERR(ops); - - if (mutex_lock_interruptible(&nf_sockopt_mutex) != 0) - return -EINTR; - - list_for_each_entry(ops, &nf_sockopts, list) { - if (ops->pf == pf) { - if (!try_module_get(ops->owner)) - goto out_nosup; - - if (get) { - if (val >= ops->get_optmin - && val < ops->get_optmax) { - mutex_unlock(&nf_sockopt_mutex); - if (ops->compat_get) - ret = ops->compat_get(sk, - val, opt, len); - else - ret = ops->get(sk, - val, opt, len); - goto out; - } - } else { - if (val >= ops->set_optmin - && val < ops->set_optmax) { - mutex_unlock(&nf_sockopt_mutex); - if (ops->compat_set) - ret = ops->compat_set(sk, - val, opt, *len); - else - ret = ops->set(sk, - val, opt, *len); - goto out; - } - } - module_put(ops->owner); - } + if (get) { + if (ops->compat_get) + ret = ops->compat_get(sk, val, opt, len); + else + ret = ops->get(sk, val, ops, len); + } else { + if (ops->compat_set) + ret = ops->compat_set(sk, val, ops, *len); + else + ret = ops->set(sk, val, ops, *len); } - out_nosup: - mutex_unlock(&nf_sockopt_mutex); - return -ENOPROTOOPT; - out: module_put(ops->owner); return ret; } From 81d9ddae856678c45297550e9353c8a5a7fd6438 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Tue, 13 Nov 2007 02:58:44 -0800 Subject: [PATCH 40/45] [NETFILTER]: bridge: fix double POSTROUTING hook invocation Packets routed between bridges have the POST_ROUTING hook invoked twice since bridging mistakes them for bridged packets because they have skb->nf_bridge set. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- net/bridge/br_netfilter.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index da22f900e89d..c1757c79dfbb 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -766,6 +766,9 @@ static unsigned int br_nf_post_routing(unsigned int hook, struct sk_buff *skb, if (!nf_bridge) return NF_ACCEPT; + if (!(nf_bridge->mask & (BRNF_BRIDGED | BRNF_BRIDGED_DNAT))) + return NF_ACCEPT; + if (!realoutdev) return NF_DROP; From 9db7720cca8f55a1e0c8d0dc1587e35dca50afbf Mon Sep 17 00:00:00 2001 From: Roel Kluin <12o3l@tiscali.nl> Date: Tue, 13 Nov 2007 03:16:17 -0800 Subject: [PATCH 41/45] [MYRI_SBUS]: Prevent that myri_do_handshake lies about ticks. With '<=' tick can be incremented up to 26, The last loop is redundant since even when 'softstate' becomes 'STATE_READY', 'if (tick > 25)' will still cause the function to return -1, Signed-off-by: Roel Kluin <12o3l@tiscali.nl> Signed-off-by: David S. Miller --- drivers/net/myri_sbus.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/myri_sbus.c b/drivers/net/myri_sbus.c index 8d29319cc5cb..656a260fc956 100644 --- a/drivers/net/myri_sbus.c +++ b/drivers/net/myri_sbus.c @@ -134,7 +134,7 @@ static int myri_do_handshake(struct myri_eth *mp) myri_disable_irq(mp->lregs, cregs); - while (tick++ <= 25) { + while (tick++ < 25) { u32 softstate; /* Wake it up. */ From 072ee3f9bd26a2f89a79d1eae9052d30b8d745a5 Mon Sep 17 00:00:00 2001 From: Roel Kluin <12o3l@tiscali.nl> Date: Tue, 13 Nov 2007 03:17:16 -0800 Subject: [PATCH 42/45] [TEHUTI]: Fix incorrect usage of strncat in bdx_get_drvinfo() Fix incorrect length for strncat by replacing it with strlcat Signed-off-by: Roel Kluin <12o3l@tiscali.nl> Signed-off-by: David S. Miller --- drivers/net/tehuti.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/tehuti.c b/drivers/net/tehuti.c index 4e1b84e6d66a..21230c97b2a0 100644 --- a/drivers/net/tehuti.c +++ b/drivers/net/tehuti.c @@ -2168,10 +2168,10 @@ bdx_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo) { struct bdx_priv *priv = netdev->priv; - strncat(drvinfo->driver, BDX_DRV_NAME, sizeof(drvinfo->driver)); - strncat(drvinfo->version, BDX_DRV_VERSION, sizeof(drvinfo->version)); - strncat(drvinfo->fw_version, "N/A", sizeof(drvinfo->fw_version)); - strncat(drvinfo->bus_info, pci_name(priv->pdev), + strlcat(drvinfo->driver, BDX_DRV_NAME, sizeof(drvinfo->driver)); + strlcat(drvinfo->version, BDX_DRV_VERSION, sizeof(drvinfo->version)); + strlcat(drvinfo->fw_version, "N/A", sizeof(drvinfo->fw_version)); + strlcat(drvinfo->bus_info, pci_name(priv->pdev), sizeof(drvinfo->bus_info)); drvinfo->n_stats = ((priv->stats_flag) ? From ed160e839d2e1118529e58b04d52dba703ca629c Mon Sep 17 00:00:00 2001 From: "Denis V. Lunev" Date: Tue, 13 Nov 2007 03:23:21 -0800 Subject: [PATCH 43/45] [NET]: Cleanup pernet operation without CONFIG_NET_NS If CONFIG_NET_NS is not set, the only namespace is possible. This patch removes list of pernet_operations and cleanups code a bit. This list is not needed if there are no namespaces. We should just call ->init method. Additionally, the ->exit will be called on module unloading only. This case is safe - the code is not discarded. For the in/kernel code, ->exit should never be called. Signed-off-by: Denis V. Lunev Signed-off-by: David S. Miller --- net/core/net_namespace.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 3f6d37deac45..383252b50411 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -188,6 +188,7 @@ static int __init net_ns_init(void) pure_initcall(net_ns_init); +#ifdef CONFIG_NET_NS static int register_pernet_operations(struct list_head *list, struct pernet_operations *ops) { @@ -228,6 +229,23 @@ static void unregister_pernet_operations(struct pernet_operations *ops) ops->exit(net); } +#else + +static int register_pernet_operations(struct list_head *list, + struct pernet_operations *ops) +{ + if (ops->init == NULL) + return 0; + return ops->init(&init_net); +} + +static void unregister_pernet_operations(struct pernet_operations *ops) +{ + if (ops->exit) + ops->exit(&init_net); +} +#endif + /** * register_pernet_subsys - register a network namespace subsystem * @ops: pernet operations structure for the subsystem From 022cbae611a37eda80d498f8f379794c8ac3be47 Mon Sep 17 00:00:00 2001 From: "Denis V. Lunev" Date: Tue, 13 Nov 2007 03:23:50 -0800 Subject: [PATCH 44/45] [NET]: Move unneeded data to initdata section. This patch reverts Eric's commit 2b008b0a8e96b726c603c5e1a5a7a509b5f61e35 It diets .text & .data section of the kernel if CONFIG_NET_NS is not set. This is safe after list operations cleanup. Signed-of-by: Denis V. Lunev Signed-off-by: David S. Miller --- drivers/net/loopback.c | 2 +- fs/proc/proc_net.c | 2 +- include/net/net_namespace.h | 2 ++ net/core/dev.c | 6 +++--- net/core/dev_mcast.c | 2 +- net/netlink/af_netlink.c | 2 +- 6 files changed, 9 insertions(+), 7 deletions(-) diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c index 45f30a2974b8..662b8d16803c 100644 --- a/drivers/net/loopback.c +++ b/drivers/net/loopback.c @@ -284,7 +284,7 @@ static __net_exit void loopback_net_exit(struct net *net) unregister_netdev(dev); } -static struct pernet_operations loopback_net_ops = { +static struct pernet_operations __net_initdata loopback_net_ops = { .init = loopback_net_init, .exit = loopback_net_exit, }; diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c index 153554cf5575..131f9c68be5f 100644 --- a/fs/proc/proc_net.c +++ b/fs/proc/proc_net.c @@ -178,7 +178,7 @@ static __net_exit void proc_net_ns_exit(struct net *net) kfree(net->proc_net_root); } -static struct pernet_operations proc_net_ns_ops = { +static struct pernet_operations __net_initdata proc_net_ns_ops = { .init = proc_net_ns_init, .exit = proc_net_ns_exit, }; diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 1fd449a6530b..5dd6d90b37eb 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -119,9 +119,11 @@ static inline struct net *maybe_get_net(struct net *net) #ifdef CONFIG_NET_NS #define __net_init #define __net_exit +#define __net_initdata #else #define __net_init __init #define __net_exit __exit_refok +#define __net_initdata __initdata #endif struct pernet_operations { diff --git a/net/core/dev.c b/net/core/dev.c index dd7e30754cbc..dd40b35bb006 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2688,7 +2688,7 @@ static void __net_exit dev_proc_net_exit(struct net *net) proc_net_remove(net, "dev"); } -static struct pernet_operations dev_proc_ops = { +static struct pernet_operations __net_initdata dev_proc_ops = { .init = dev_proc_net_init, .exit = dev_proc_net_exit, }; @@ -4353,7 +4353,7 @@ static void __net_exit netdev_exit(struct net *net) kfree(net->dev_index_head); } -static struct pernet_operations netdev_net_ops = { +static struct pernet_operations __net_initdata netdev_net_ops = { .init = netdev_init, .exit = netdev_exit, }; @@ -4384,7 +4384,7 @@ static void __net_exit default_device_exit(struct net *net) rtnl_unlock(); } -static struct pernet_operations default_device_ops = { +static struct pernet_operations __net_initdata default_device_ops = { .exit = default_device_exit, }; diff --git a/net/core/dev_mcast.c b/net/core/dev_mcast.c index 647973daca2b..69fff16ece10 100644 --- a/net/core/dev_mcast.c +++ b/net/core/dev_mcast.c @@ -285,7 +285,7 @@ static void __net_exit dev_mc_net_exit(struct net *net) proc_net_remove(net, "dev_mcast"); } -static struct pernet_operations dev_mc_net_ops = { +static struct pernet_operations __net_initdata dev_mc_net_ops = { .init = dev_mc_net_init, .exit = dev_mc_net_exit, }; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 415c97236f63..de3988ba1f46 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1888,7 +1888,7 @@ static void __net_exit netlink_net_exit(struct net *net) #endif } -static struct pernet_operations netlink_net_ops = { +static struct pernet_operations __net_initdata netlink_net_ops = { .init = netlink_net_init, .exit = netlink_net_exit, }; From 53756524e42a71011f5ae6410d6ac386bf3a9e7b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 13 Nov 2007 03:49:53 -0800 Subject: [PATCH 45/45] [NETFILTER]: xt_time should not assume CONFIG_KTIME_SCALAR It is not correct to assume one can get nsec from a ktime directly by using .tv64 field. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/netfilter/xt_time.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netfilter/xt_time.c b/net/netfilter/xt_time.c index ff44f86c24ce..f9c55dcd894b 100644 --- a/net/netfilter/xt_time.c +++ b/net/netfilter/xt_time.c @@ -170,7 +170,7 @@ static bool xt_time_match(const struct sk_buff *skb, if (skb->tstamp.tv64 == 0) __net_timestamp((struct sk_buff *)skb); - stamp = skb->tstamp.tv64; + stamp = ktime_to_ns(skb->tstamp); do_div(stamp, NSEC_PER_SEC); if (info->flags & XT_TIME_LOCAL_TZ)