From: Linus Torvalds Date: Thu, 22 Dec 2011 02:29:26 +0000 (-0800) Subject: Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net X-Git-Tag: v3.2-rc7~12 X-Git-Url: https://git.openpandora.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=ecefc36b41ac0fe92d76273a23faf27b2da13411;hp=d5ed5e48f4a6333cde05c5235b88a8a94e72afe8;p=pandora-kernel.git Merge git://git./linux/kernel/git/davem/net * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: net: Add a flow_cache_flush_deferred function ipv4: reintroduce route cache garbage collector net: have ipconfig not wait if no dev is available sctp: Do not account for sizeof(struct sk_buff) in estimated rwnd asix: new device id davinci-cpdma: fix locking issue in cpdma_chan_stop sctp: fix incorrect overflow check on autoclose r8169: fix Config2 MSIEnable bit setting. llc: llc_cmsg_rcv was getting called after sk_eat_skb. net: bpf_jit: fix an off-one bug in x86_64 cond jump target iwlwifi: update SCD BC table for all SCD queues Revert "Bluetooth: Revert: Fix L2CAP connection establishment" Bluetooth: Clear RFCOMM session timer when disconnecting last channel Bluetooth: Prevent uninitialized data access in L2CAP configuration iwlwifi: allow to switch to HT40 if not associated iwlwifi: tx_sync only on PAN context mwifiex: avoid double list_del in command cancel path ath9k: fix max phy rate at rate control init nfc: signedness bug in __nci_request() iwlwifi: do not set the sequence control bit is not needed --- diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index bfab3fa10edc..7b65f752c5f8 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -568,8 +568,8 @@ cond_branch: f_offset = addrs[i + filter[i].jf] - addrs[i]; break; } if (filter[i].jt != 0) { - if (filter[i].jf) - t_offset += is_near(f_offset) ? 2 : 6; + if (filter[i].jf && f_offset) + t_offset += is_near(f_offset) ? 2 : 5; EMIT_COND_JMP(t_op, t_offset); if (filter[i].jf) EMIT_JMP(f_offset); diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index 67bf07819992..c8f47f17186f 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -477,7 +477,6 @@ enum rtl_register_content { /* Config1 register p.24 */ LEDS1 = (1 << 7), LEDS0 = (1 << 6), - MSIEnable = (1 << 5), /* Enable Message Signaled Interrupt */ Speed_down = (1 << 4), MEMMAP = (1 << 3), IOMAP = (1 << 2), @@ -485,6 +484,7 @@ enum rtl_register_content { PMEnable = (1 << 0), /* Power Management Enable */ /* Config2 register p. 25 */ + MSIEnable = (1 << 5), /* 8169 only. Reserved in the 8168. */ PCI_Clock_66MHz = 0x01, PCI_Clock_33MHz = 0x00, @@ -3426,22 +3426,24 @@ static const struct rtl_cfg_info { }; /* Cfg9346_Unlock assumed. */ -static unsigned rtl_try_msi(struct pci_dev *pdev, void __iomem *ioaddr, +static unsigned rtl_try_msi(struct rtl8169_private *tp, const struct rtl_cfg_info *cfg) { + void __iomem *ioaddr = tp->mmio_addr; unsigned msi = 0; u8 cfg2; cfg2 = RTL_R8(Config2) & ~MSIEnable; if (cfg->features & RTL_FEATURE_MSI) { - if (pci_enable_msi(pdev)) { - dev_info(&pdev->dev, "no MSI. Back to INTx.\n"); + if (pci_enable_msi(tp->pci_dev)) { + netif_info(tp, hw, tp->dev, "no MSI. Back to INTx.\n"); } else { cfg2 |= MSIEnable; msi = RTL_FEATURE_MSI; } } - RTL_W8(Config2, cfg2); + if (tp->mac_version <= RTL_GIGA_MAC_VER_06) + RTL_W8(Config2, cfg2); return msi; } @@ -4077,7 +4079,7 @@ rtl8169_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) tp->features |= RTL_FEATURE_WOL; if ((RTL_R8(Config5) & (UWF | BWF | MWF)) != 0) tp->features |= RTL_FEATURE_WOL; - tp->features |= rtl_try_msi(pdev, ioaddr, cfg); + tp->features |= rtl_try_msi(tp, cfg); RTL_W8(Cfg9346, Cfg9346_Lock); if (rtl_tbi_enabled(tp)) { diff --git a/drivers/net/ethernet/ti/davinci_cpdma.c b/drivers/net/ethernet/ti/davinci_cpdma.c index dca9d3369cdd..c97d2f590855 100644 --- a/drivers/net/ethernet/ti/davinci_cpdma.c +++ b/drivers/net/ethernet/ti/davinci_cpdma.c @@ -836,11 +836,13 @@ int cpdma_chan_stop(struct cpdma_chan *chan) chan_write(chan, cp, CPDMA_TEARDOWN_VALUE); /* handle completed packets */ + spin_unlock_irqrestore(&chan->lock, flags); do { ret = __cpdma_chan_process(chan); if (ret < 0) break; } while ((ret & CPDMA_DESC_TD_COMPLETE) == 0); + spin_lock_irqsave(&chan->lock, flags); /* remaining packets haven't been tx/rx'ed, clean them up */ while (chan->head) { diff --git a/drivers/net/usb/asix.c b/drivers/net/usb/asix.c index e6fed4d4cb77..e95f0e60a9bc 100644 --- a/drivers/net/usb/asix.c +++ b/drivers/net/usb/asix.c @@ -1655,6 +1655,10 @@ static const struct usb_device_id products [] = { // ASIX 88772a USB_DEVICE(0x0db0, 0xa877), .driver_info = (unsigned long) &ax88772_info, +}, { + // Asus USB Ethernet Adapter + USB_DEVICE (0x0b95, 0x7e2b), + .driver_info = (unsigned long) &ax88772_info, }, { }, // END }; diff --git a/drivers/net/wireless/ath/ath9k/rc.c b/drivers/net/wireless/ath/ath9k/rc.c index 888abc2be3a5..528d5f3e868c 100644 --- a/drivers/net/wireless/ath/ath9k/rc.c +++ b/drivers/net/wireless/ath/ath9k/rc.c @@ -1271,7 +1271,9 @@ static void ath_rc_init(struct ath_softc *sc, ath_rc_priv->max_valid_rate = k; ath_rc_sort_validrates(rate_table, ath_rc_priv); - ath_rc_priv->rate_max_phy = ath_rc_priv->valid_rate_index[k-4]; + ath_rc_priv->rate_max_phy = (k > 4) ? + ath_rc_priv->valid_rate_index[k-4] : + ath_rc_priv->valid_rate_index[k-1]; ath_rc_priv->rate_table = rate_table; ath_dbg(common, ATH_DBG_CONFIG, diff --git a/drivers/net/wireless/iwlwifi/iwl-agn-rxon.c b/drivers/net/wireless/iwlwifi/iwl-agn-rxon.c index a7a6def40d05..5c7c17c7166a 100644 --- a/drivers/net/wireless/iwlwifi/iwl-agn-rxon.c +++ b/drivers/net/wireless/iwlwifi/iwl-agn-rxon.c @@ -606,8 +606,8 @@ int iwlagn_mac_config(struct ieee80211_hw *hw, u32 changed) if (ctx->ht.enabled) { /* if HT40 is used, it should not change * after associated except channel switch */ - if (iwl_is_associated_ctx(ctx) && - !ctx->ht.is_40mhz) + if (!ctx->ht.is_40mhz || + !iwl_is_associated_ctx(ctx)) iwlagn_config_ht40(conf, ctx); } else ctx->ht.is_40mhz = false; diff --git a/drivers/net/wireless/iwlwifi/iwl-agn-tx.c b/drivers/net/wireless/iwlwifi/iwl-agn-tx.c index 35a6b71f358c..df1540ca6102 100644 --- a/drivers/net/wireless/iwlwifi/iwl-agn-tx.c +++ b/drivers/net/wireless/iwlwifi/iwl-agn-tx.c @@ -91,7 +91,10 @@ static void iwlagn_tx_cmd_build_basic(struct iwl_priv *priv, tx_cmd->tid_tspec = qc[0] & 0xf; tx_flags &= ~TX_CMD_FLG_SEQ_CTL_MSK; } else { - tx_flags |= TX_CMD_FLG_SEQ_CTL_MSK; + if (info->flags & IEEE80211_TX_CTL_ASSIGN_SEQ) + tx_flags |= TX_CMD_FLG_SEQ_CTL_MSK; + else + tx_flags &= ~TX_CMD_FLG_SEQ_CTL_MSK; } iwlagn_tx_cmd_protection(priv, info, fc, &tx_flags); diff --git a/drivers/net/wireless/iwlwifi/iwl-agn.c b/drivers/net/wireless/iwlwifi/iwl-agn.c index bacc06c95e7a..e0e9a3dfbc00 100644 --- a/drivers/net/wireless/iwlwifi/iwl-agn.c +++ b/drivers/net/wireless/iwlwifi/iwl-agn.c @@ -2850,6 +2850,9 @@ static int iwlagn_mac_tx_sync(struct ieee80211_hw *hw, int ret; u8 sta_id; + if (ctx->ctxid != IWL_RXON_CTX_PAN) + return 0; + IWL_DEBUG_MAC80211(priv, "enter\n"); mutex_lock(&priv->shrd->mutex); @@ -2898,6 +2901,9 @@ static void iwlagn_mac_finish_tx_sync(struct ieee80211_hw *hw, struct iwl_vif_priv *vif_priv = (void *)vif->drv_priv; struct iwl_rxon_context *ctx = vif_priv->ctx; + if (ctx->ctxid != IWL_RXON_CTX_PAN) + return; + IWL_DEBUG_MAC80211(priv, "enter\n"); mutex_lock(&priv->shrd->mutex); diff --git a/drivers/net/wireless/iwlwifi/iwl-trans-pcie.c b/drivers/net/wireless/iwlwifi/iwl-trans-pcie.c index ce918980e977..5f17ab8e76ba 100644 --- a/drivers/net/wireless/iwlwifi/iwl-trans-pcie.c +++ b/drivers/net/wireless/iwlwifi/iwl-trans-pcie.c @@ -1197,9 +1197,7 @@ static int iwl_trans_pcie_tx(struct iwl_trans *trans, struct sk_buff *skb, iwl_print_hex_dump(trans, IWL_DL_TX, (u8 *)tx_cmd->hdr, hdr_len); /* Set up entry for this TFD in Tx byte-count array */ - if (is_agg) - iwl_trans_txq_update_byte_cnt_tbl(trans, txq, - le16_to_cpu(tx_cmd->len)); + iwl_trans_txq_update_byte_cnt_tbl(trans, txq, le16_to_cpu(tx_cmd->len)); dma_sync_single_for_device(bus(trans)->dev, txcmd_phys, firstlen, DMA_BIDIRECTIONAL); diff --git a/drivers/net/wireless/mwifiex/cmdevt.c b/drivers/net/wireless/mwifiex/cmdevt.c index ac278156d390..6e0a3eaecf70 100644 --- a/drivers/net/wireless/mwifiex/cmdevt.c +++ b/drivers/net/wireless/mwifiex/cmdevt.c @@ -939,7 +939,6 @@ mwifiex_cancel_pending_ioctl(struct mwifiex_adapter *adapter) { struct cmd_ctrl_node *cmd_node = NULL, *tmp_node = NULL; unsigned long cmd_flags; - unsigned long cmd_pending_q_flags; unsigned long scan_pending_q_flags; uint16_t cancel_scan_cmd = false; @@ -949,12 +948,9 @@ mwifiex_cancel_pending_ioctl(struct mwifiex_adapter *adapter) cmd_node = adapter->curr_cmd; cmd_node->wait_q_enabled = false; cmd_node->cmd_flag |= CMD_F_CANCELED; - spin_lock_irqsave(&adapter->cmd_pending_q_lock, - cmd_pending_q_flags); - list_del(&cmd_node->list); - spin_unlock_irqrestore(&adapter->cmd_pending_q_lock, - cmd_pending_q_flags); mwifiex_insert_cmd_to_free_q(adapter, cmd_node); + mwifiex_complete_cmd(adapter, adapter->curr_cmd); + adapter->curr_cmd = NULL; spin_unlock_irqrestore(&adapter->mwifiex_cmd_lock, cmd_flags); } @@ -981,7 +977,6 @@ mwifiex_cancel_pending_ioctl(struct mwifiex_adapter *adapter) spin_unlock_irqrestore(&adapter->mwifiex_cmd_lock, cmd_flags); } adapter->cmd_wait_q.status = -1; - mwifiex_complete_cmd(adapter, adapter->curr_cmd); } /* diff --git a/include/net/flow.h b/include/net/flow.h index a09447749e2d..57f15a7f1cdd 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -207,6 +207,7 @@ extern struct flow_cache_object *flow_cache_lookup( u8 dir, flow_resolve_t resolver, void *ctx); extern void flow_cache_flush(void); +extern void flow_cache_flush_deferred(void); extern atomic_t flow_cache_genid; #endif diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index e90e7a9935dd..a15432da27c3 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -241,6 +241,9 @@ extern struct sctp_globals { * bits is an indicator of when to send and window update SACK. */ int rwnd_update_shift; + + /* Threshold for autoclose timeout, in seconds. */ + unsigned long max_autoclose; } sctp_globals; #define sctp_rto_initial (sctp_globals.rto_initial) @@ -281,6 +284,7 @@ extern struct sctp_globals { #define sctp_auth_enable (sctp_globals.auth_enable) #define sctp_checksum_disable (sctp_globals.checksum_disable) #define sctp_rwnd_upd_shift (sctp_globals.rwnd_update_shift) +#define sctp_max_autoclose (sctp_globals.max_autoclose) /* SCTP Socket type: UDP or TCP style. */ typedef enum { diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index e0af7237cd92..c1c597e3e198 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -673,7 +673,7 @@ int hci_conn_security(struct hci_conn *conn, __u8 sec_level, __u8 auth_type) goto encrypt; auth: - if (test_and_set_bit(HCI_CONN_ENCRYPT_PEND, &conn->pend)) + if (test_bit(HCI_CONN_ENCRYPT_PEND, &conn->pend)) return 0; if (!hci_conn_auth(conn, sec_level, auth_type)) diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 5ea94a1eecf2..17b5b1cd9657 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -2152,7 +2152,7 @@ static int l2cap_parse_conf_rsp(struct l2cap_chan *chan, void *rsp, int len, voi void *ptr = req->data; int type, olen; unsigned long val; - struct l2cap_conf_rfc rfc; + struct l2cap_conf_rfc rfc = { .mode = L2CAP_MODE_BASIC }; BT_DBG("chan %p, rsp %p, len %d, req %p", chan, rsp, len, data); @@ -2271,6 +2271,16 @@ static void l2cap_conf_rfc_get(struct l2cap_chan *chan, void *rsp, int len) } } + /* Use sane default values in case a misbehaving remote device + * did not send an RFC option. + */ + rfc.mode = chan->mode; + rfc.retrans_timeout = cpu_to_le16(L2CAP_DEFAULT_RETRANS_TO); + rfc.monitor_timeout = cpu_to_le16(L2CAP_DEFAULT_MONITOR_TO); + rfc.max_pdu_size = cpu_to_le16(chan->imtu); + + BT_ERR("Expected RFC option was not found, using defaults"); + done: switch (rfc.mode) { case L2CAP_MODE_ERTM: diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index 4e32e18211f9..2d28dfe98389 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -1146,6 +1146,7 @@ static int rfcomm_recv_ua(struct rfcomm_session *s, u8 dlci) if (list_empty(&s->dlcs)) { s->state = BT_DISCONN; rfcomm_send_disc(s, 0); + rfcomm_session_clear_timer(s); } break; diff --git a/net/core/flow.c b/net/core/flow.c index 8ae42de9c79e..e318c7e98042 100644 --- a/net/core/flow.c +++ b/net/core/flow.c @@ -358,6 +358,18 @@ void flow_cache_flush(void) put_online_cpus(); } +static void flow_cache_flush_task(struct work_struct *work) +{ + flow_cache_flush(); +} + +static DECLARE_WORK(flow_cache_flush_work, flow_cache_flush_task); + +void flow_cache_flush_deferred(void) +{ + schedule_work(&flow_cache_flush_work); +} + static int __cpuinit flow_cache_cpu_prepare(struct flow_cache *fc, int cpu) { struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, cpu); diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 0da2afc97f32..99ec116bef14 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -253,6 +253,10 @@ static int __init ic_open_devs(void) } } + /* no point in waiting if we could not bring up at least one device */ + if (!ic_first_dev) + goto have_carrier; + /* wait for a carrier on at least one device */ start = jiffies; while (jiffies - start < msecs_to_jiffies(CONF_CARRIER_TIMEOUT)) { diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 46af62363b8c..252c512e8a81 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -120,6 +120,7 @@ static int ip_rt_max_size; static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT; +static int ip_rt_gc_interval __read_mostly = 60 * HZ; static int ip_rt_gc_min_interval __read_mostly = HZ / 2; static int ip_rt_redirect_number __read_mostly = 9; static int ip_rt_redirect_load __read_mostly = HZ / 50; @@ -133,6 +134,9 @@ static int ip_rt_min_advmss __read_mostly = 256; static int rt_chain_length_max __read_mostly = 20; static int redirect_genid; +static struct delayed_work expires_work; +static unsigned long expires_ljiffies; + /* * Interface to generic destination cache. */ @@ -830,6 +834,97 @@ static int has_noalias(const struct rtable *head, const struct rtable *rth) return ONE; } +static void rt_check_expire(void) +{ + static unsigned int rover; + unsigned int i = rover, goal; + struct rtable *rth; + struct rtable __rcu **rthp; + unsigned long samples = 0; + unsigned long sum = 0, sum2 = 0; + unsigned long delta; + u64 mult; + + delta = jiffies - expires_ljiffies; + expires_ljiffies = jiffies; + mult = ((u64)delta) << rt_hash_log; + if (ip_rt_gc_timeout > 1) + do_div(mult, ip_rt_gc_timeout); + goal = (unsigned int)mult; + if (goal > rt_hash_mask) + goal = rt_hash_mask + 1; + for (; goal > 0; goal--) { + unsigned long tmo = ip_rt_gc_timeout; + unsigned long length; + + i = (i + 1) & rt_hash_mask; + rthp = &rt_hash_table[i].chain; + + if (need_resched()) + cond_resched(); + + samples++; + + if (rcu_dereference_raw(*rthp) == NULL) + continue; + length = 0; + spin_lock_bh(rt_hash_lock_addr(i)); + while ((rth = rcu_dereference_protected(*rthp, + lockdep_is_held(rt_hash_lock_addr(i)))) != NULL) { + prefetch(rth->dst.rt_next); + if (rt_is_expired(rth)) { + *rthp = rth->dst.rt_next; + rt_free(rth); + continue; + } + if (rth->dst.expires) { + /* Entry is expired even if it is in use */ + if (time_before_eq(jiffies, rth->dst.expires)) { +nofree: + tmo >>= 1; + rthp = &rth->dst.rt_next; + /* + * We only count entries on + * a chain with equal hash inputs once + * so that entries for different QOS + * levels, and other non-hash input + * attributes don't unfairly skew + * the length computation + */ + length += has_noalias(rt_hash_table[i].chain, rth); + continue; + } + } else if (!rt_may_expire(rth, tmo, ip_rt_gc_timeout)) + goto nofree; + + /* Cleanup aged off entries. */ + *rthp = rth->dst.rt_next; + rt_free(rth); + } + spin_unlock_bh(rt_hash_lock_addr(i)); + sum += length; + sum2 += length*length; + } + if (samples) { + unsigned long avg = sum / samples; + unsigned long sd = int_sqrt(sum2 / samples - avg*avg); + rt_chain_length_max = max_t(unsigned long, + ip_rt_gc_elasticity, + (avg + 4*sd) >> FRACT_BITS); + } + rover = i; +} + +/* + * rt_worker_func() is run in process context. + * we call rt_check_expire() to scan part of the hash table + */ +static void rt_worker_func(struct work_struct *work) +{ + rt_check_expire(); + schedule_delayed_work(&expires_work, ip_rt_gc_interval); +} + /* * Perturbation of rt_genid by a small quantity [1..256] * Using 8 bits of shuffling ensure we can call rt_cache_invalidate() @@ -3178,6 +3273,13 @@ static ctl_table ipv4_route_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, + { + .procname = "gc_interval", + .data = &ip_rt_gc_interval, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, { .procname = "redirect_load", .data = &ip_rt_redirect_load, @@ -3388,6 +3490,11 @@ int __init ip_rt_init(void) devinet_init(); ip_fib_init(); + INIT_DELAYED_WORK_DEFERRABLE(&expires_work, rt_worker_func); + expires_ljiffies = jiffies; + schedule_delayed_work(&expires_work, + net_random() % ip_rt_gc_interval + ip_rt_gc_interval); + if (ip_rt_proc_init()) printk(KERN_ERR "Unable to create route proc files\n"); #ifdef CONFIG_XFRM diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index dfd3a648a551..a18e6c3d36e3 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -833,15 +833,15 @@ static int llc_ui_recvmsg(struct kiocb *iocb, struct socket *sock, copied += used; len -= used; + /* For non stream protcols we get one packet per recvmsg call */ + if (sk->sk_type != SOCK_STREAM) + goto copy_uaddr; + if (!(flags & MSG_PEEK)) { sk_eat_skb(sk, skb, 0); *seq = 0; } - /* For non stream protcols we get one packet per recvmsg call */ - if (sk->sk_type != SOCK_STREAM) - goto copy_uaddr; - /* Partial read */ if (used + offset < skb->len) continue; @@ -857,6 +857,12 @@ copy_uaddr: } if (llc_sk(sk)->cmsg_flags) llc_cmsg_rcv(msg, skb); + + if (!(flags & MSG_PEEK)) { + sk_eat_skb(sk, skb, 0); + *seq = 0; + } + goto out; } diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index 3925c6578767..ea66034499ce 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -69,7 +69,7 @@ static int __nci_request(struct nci_dev *ndev, __u32 timeout) { int rc = 0; - unsigned long completion_rc; + long completion_rc; ndev->req_status = NCI_REQ_PEND; diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 152b5b3c3fff..acd2edbc073e 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -173,7 +173,7 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a asoc->timeouts[SCTP_EVENT_TIMEOUT_HEARTBEAT] = 0; asoc->timeouts[SCTP_EVENT_TIMEOUT_SACK] = asoc->sackdelay; asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE] = - (unsigned long)sp->autoclose * HZ; + min_t(unsigned long, sp->autoclose, sctp_max_autoclose) * HZ; /* Initializes the timers */ for (i = SCTP_EVENT_TIMEOUT_NONE; i < SCTP_NUM_TIMEOUT_TYPES; ++i) diff --git a/net/sctp/output.c b/net/sctp/output.c index 08b3cead6503..817174eb5f41 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -697,13 +697,7 @@ static void sctp_packet_append_data(struct sctp_packet *packet, /* Keep track of how many bytes are in flight to the receiver. */ asoc->outqueue.outstanding_bytes += datasize; - /* Update our view of the receiver's rwnd. Include sk_buff overhead - * while updating peer.rwnd so that it reduces the chances of a - * receiver running out of receive buffer space even when receive - * window is still open. This can happen when a sender is sending - * sending small messages. - */ - datasize += sizeof(struct sk_buff); + /* Update our view of the receiver's rwnd. */ if (datasize < rwnd) rwnd -= datasize; else diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 14c2b06028ff..cfeb1d4a1ee6 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -411,8 +411,7 @@ void sctp_retransmit_mark(struct sctp_outq *q, chunk->transport->flight_size -= sctp_data_size(chunk); q->outstanding_bytes -= sctp_data_size(chunk); - q->asoc->peer.rwnd += (sctp_data_size(chunk) + - sizeof(struct sk_buff)); + q->asoc->peer.rwnd += sctp_data_size(chunk); } continue; } @@ -432,8 +431,7 @@ void sctp_retransmit_mark(struct sctp_outq *q, * (Section 7.2.4)), add the data size of those * chunks to the rwnd. */ - q->asoc->peer.rwnd += (sctp_data_size(chunk) + - sizeof(struct sk_buff)); + q->asoc->peer.rwnd += sctp_data_size(chunk); q->outstanding_bytes -= sctp_data_size(chunk); if (chunk->transport) transport->flight_size -= sctp_data_size(chunk); diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 61b9fca5a173..6f6ad8686833 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -1285,6 +1285,9 @@ SCTP_STATIC __init int sctp_init(void) sctp_max_instreams = SCTP_DEFAULT_INSTREAMS; sctp_max_outstreams = SCTP_DEFAULT_OUTSTREAMS; + /* Initialize maximum autoclose timeout. */ + sctp_max_autoclose = INT_MAX / HZ; + /* Initialize handle used for association ids. */ idr_init(&sctp_assocs_id); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 13bf5fcdbff1..54a7cd2fdd7a 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -2200,8 +2200,6 @@ static int sctp_setsockopt_autoclose(struct sock *sk, char __user *optval, return -EINVAL; if (copy_from_user(&sp->autoclose, optval, optlen)) return -EFAULT; - /* make sure it won't exceed MAX_SCHEDULE_TIMEOUT */ - sp->autoclose = min_t(long, sp->autoclose, MAX_SCHEDULE_TIMEOUT / HZ); return 0; } diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index 6b3952961b85..60ffbd067ff7 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -53,6 +53,10 @@ static int sack_timer_min = 1; static int sack_timer_max = 500; static int addr_scope_max = 3; /* check sctp_scope_policy_t in include/net/sctp/constants.h for max entries */ static int rwnd_scale_max = 16; +static unsigned long max_autoclose_min = 0; +static unsigned long max_autoclose_max = + (MAX_SCHEDULE_TIMEOUT / HZ > UINT_MAX) + ? UINT_MAX : MAX_SCHEDULE_TIMEOUT / HZ; extern long sysctl_sctp_mem[3]; extern int sysctl_sctp_rmem[3]; @@ -258,6 +262,15 @@ static ctl_table sctp_table[] = { .extra1 = &one, .extra2 = &rwnd_scale_max, }, + { + .procname = "max_autoclose", + .data = &sctp_max_autoclose, + .maxlen = sizeof(unsigned long), + .mode = 0644, + .proc_handler = &proc_doulongvec_minmax, + .extra1 = &max_autoclose_min, + .extra2 = &max_autoclose_max, + }, { /* sentinel */ } }; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 2118d6446630..9049a5caeb25 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2276,8 +2276,6 @@ static void __xfrm_garbage_collect(struct net *net) { struct dst_entry *head, *next; - flow_cache_flush(); - spin_lock_bh(&xfrm_policy_sk_bundle_lock); head = xfrm_policy_sk_bundles; xfrm_policy_sk_bundles = NULL; @@ -2290,6 +2288,18 @@ static void __xfrm_garbage_collect(struct net *net) } } +static void xfrm_garbage_collect(struct net *net) +{ + flow_cache_flush(); + __xfrm_garbage_collect(net); +} + +static void xfrm_garbage_collect_deferred(struct net *net) +{ + flow_cache_flush_deferred(); + __xfrm_garbage_collect(net); +} + static void xfrm_init_pmtu(struct dst_entry *dst) { do { @@ -2422,7 +2432,7 @@ int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo) if (likely(dst_ops->neigh_lookup == NULL)) dst_ops->neigh_lookup = xfrm_neigh_lookup; if (likely(afinfo->garbage_collect == NULL)) - afinfo->garbage_collect = __xfrm_garbage_collect; + afinfo->garbage_collect = xfrm_garbage_collect_deferred; xfrm_policy_afinfo[afinfo->family] = afinfo; } write_unlock_bh(&xfrm_policy_afinfo_lock); @@ -2516,7 +2526,7 @@ static int xfrm_dev_event(struct notifier_block *this, unsigned long event, void switch (event) { case NETDEV_DOWN: - __xfrm_garbage_collect(dev_net(dev)); + xfrm_garbage_collect(dev_net(dev)); } return NOTIFY_DONE; }