From 6e4aff103774d6ee937a1dba9b1b4bf89100e7f6 Mon Sep 17 00:00:00 2001 From: Santosh Nayak Date: Thu, 1 Mar 2012 22:46:36 +0530 Subject: Bluetooth: Fix Endian Bug. Fix network to host endian conversion for L2CAP chan id. Signed-off-by: Santosh Nayak Acked-by: Andrei Emeltchenko Signed-off-by: Gustavo F. Padovan --- net/bluetooth/l2cap_sock.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index c4fe583b0af6..29122ed28ea9 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -82,7 +82,7 @@ static int l2cap_sock_bind(struct socket *sock, struct sockaddr *addr, int alen) } if (la.l2_cid) - err = l2cap_add_scid(chan, la.l2_cid); + err = l2cap_add_scid(chan, __le16_to_cpu(la.l2_cid)); else err = l2cap_add_psm(chan, &la.l2_bdaddr, la.l2_psm); @@ -123,7 +123,8 @@ static int l2cap_sock_connect(struct socket *sock, struct sockaddr *addr, int al if (la.l2_cid && la.l2_psm) return -EINVAL; - err = l2cap_chan_connect(chan, la.l2_psm, la.l2_cid, &la.l2_bdaddr); + err = l2cap_chan_connect(chan, la.l2_psm, __le16_to_cpu(la.l2_cid), + &la.l2_bdaddr); if (err) return err; -- cgit v1.2.3 From 94324962066231a938564bebad0f941cd2d06bb2 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Thu, 15 Mar 2012 14:48:41 +0100 Subject: Bluetooth: hci_core: fix NULL-pointer dereference at unregister Make sure hci_dev_open returns immediately if hci_dev_unregister has been called. This fixes a race between hci_dev_open and hci_dev_unregister which can lead to a NULL-pointer dereference. Bug is 100% reproducible using hciattach and a disconnected serial port: 0. # hciattach -n /dev/ttyO1 any noflow 1. hci_dev_open called from hci_power_on grabs req lock 2. hci_init_req executes but device fails to initialise (times out eventually) 3. hci_dev_open is called from hci_sock_ioctl and sleeps on req lock 4. hci_uart_tty_close calls hci_dev_unregister and sleeps on req lock in hci_dev_do_close 5. hci_dev_open (1) releases req lock 6. hci_dev_do_close grabs req lock and returns as device is not up 7. hci_dev_unregister sleeps in destroy_workqueue 8. hci_dev_open (3) grabs req lock, calls hci_init_req and eventually sleeps 9. hci_dev_unregister finishes, while hci_dev_open is still running... [ 79.627136] INFO: trying to register non-static key. [ 79.632354] the code is fine but needs lockdep annotation. [ 79.638122] turning off the locking correctness validator. [ 79.643920] [] (unwind_backtrace+0x0/0xf8) from [] (__lock_acquire+0x1590/0x1ab0) [ 79.653594] [] (__lock_acquire+0x1590/0x1ab0) from [] (lock_acquire+0x9c/0x128) [ 79.663085] [] (lock_acquire+0x9c/0x128) from [] (run_timer_softirq+0x150/0x3ac) [ 79.672668] [] (run_timer_softirq+0x150/0x3ac) from [] (__do_softirq+0xd4/0x22c) [ 79.682281] [] (__do_softirq+0xd4/0x22c) from [] (irq_exit+0x8c/0x94) [ 79.690856] [] (irq_exit+0x8c/0x94) from [] (handle_IRQ+0x34/0x84) [ 79.699157] [] (handle_IRQ+0x34/0x84) from [] (omap3_intc_handle_irq+0x48/0x4c) [ 79.708648] [] (omap3_intc_handle_irq+0x48/0x4c) from [] (__irq_usr+0x3c/0x60) [ 79.718048] Exception stack(0xcf281fb0 to 0xcf281ff8) [ 79.723358] 1fa0: 0001e6a0 be8dab00 0001e698 00036698 [ 79.731933] 1fc0: 0002df98 0002df38 0000001f 00000000 b6f234d0 00000000 00000004 00000000 [ 79.740509] 1fe0: 0001e6f8 be8d6aa0 be8dac50 0000aab8 80000010 ffffffff [ 79.747497] Unable to handle kernel NULL pointer dereference at virtual address 00000000 [ 79.756011] pgd = cf3b4000 [ 79.758850] [00000000] *pgd=8f0c7831, *pte=00000000, *ppte=00000000 [ 79.765502] Internal error: Oops: 80000007 [#1] [ 79.770294] Modules linked in: [ 79.773529] CPU: 0 Tainted: G W (3.3.0-rc6-00002-gb5d5c87 #421) [ 79.781066] PC is at 0x0 [ 79.783721] LR is at run_timer_softirq+0x16c/0x3ac [ 79.788787] pc : [<00000000>] lr : [] psr: 60000113 [ 79.788787] sp : cf281ee0 ip : 00000000 fp : cf280000 [ 79.800903] r10: 00000004 r9 : 00000100 r8 : b6f234d0 [ 79.806427] r7 : c0519c28 r6 : cf093488 r5 : c0561a00 r4 : 00000000 [ 79.813323] r3 : 00000000 r2 : c054eee0 r1 : 00000001 r0 : 00000000 [ 79.820190] Flags: nZCv IRQs on FIQs on Mode SVC_32 ISA ARM Segment user [ 79.827728] Control: 10c5387d Table: 8f3b4019 DAC: 00000015 [ 79.833801] Process gpsd (pid: 1265, stack limit = 0xcf2802e8) [ 79.839965] Stack: (0xcf281ee0 to 0xcf282000) [ 79.844573] 1ee0: 00000002 00000000 c0040a24 00000000 00000002 cf281f08 00200200 00000000 [ 79.853210] 1f00: 00000000 cf281f18 cf281f08 00000000 00000000 00000000 cf281f18 cf281f18 [ 79.861816] 1f20: 00000000 00000001 c056184c 00000000 00000001 b6f234d0 c0561848 00000004 [ 79.870452] 1f40: cf280000 c003a3b8 c051e79c 00000001 00000000 00000100 3fa9e7b8 0000000a [ 79.879089] 1f60: 00000025 cf280000 00000025 00000000 00000000 b6f234d0 00000000 00000004 [ 79.887756] 1f80: 00000000 c003a924 c053ad38 c0013a50 fa200000 cf281fb0 ffffffff c0008530 [ 79.896362] 1fa0: 0001e6a0 0000aab8 80000010 c037499c 0001e6a0 be8dab00 0001e698 00036698 [ 79.904998] 1fc0: 0002df98 0002df38 0000001f 00000000 b6f234d0 00000000 00000004 00000000 [ 79.913665] 1fe0: 0001e6f8 be8d6aa0 be8dac50 0000aab8 80000010 ffffffff 00fbf700 04ffff00 [ 79.922302] [] (run_timer_softirq+0x16c/0x3ac) from [] (__do_softirq+0xd4/0x22c) [ 79.931945] [] (__do_softirq+0xd4/0x22c) from [] (irq_exit+0x8c/0x94) [ 79.940582] [] (irq_exit+0x8c/0x94) from [] (handle_IRQ+0x34/0x84) [ 79.948913] [] (handle_IRQ+0x34/0x84) from [] (omap3_intc_handle_irq+0x48/0x4c) [ 79.958404] [] (omap3_intc_handle_irq+0x48/0x4c) from [] (__irq_usr+0x3c/0x60) [ 79.967773] Exception stack(0xcf281fb0 to 0xcf281ff8) [ 79.973083] 1fa0: 0001e6a0 be8dab00 0001e698 00036698 [ 79.981658] 1fc0: 0002df98 0002df38 0000001f 00000000 b6f234d0 00000000 00000004 00000000 [ 79.990234] 1fe0: 0001e6f8 be8d6aa0 be8dac50 0000aab8 80000010 ffffffff [ 79.997161] Code: bad PC value [ 80.000396] ---[ end trace 6f6739840475f9ee ]--- [ 80.005279] Kernel panic - not syncing: Fatal exception in interrupt Cc: stable Signed-off-by: Johan Hovold Acked-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/hci.h | 1 + net/bluetooth/hci_core.c | 7 +++++++ 2 files changed, 8 insertions(+) (limited to 'net') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 344b0f972828..8f928f75e85e 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -92,6 +92,7 @@ enum { HCI_SERVICE_CACHE, HCI_LINK_KEYS, HCI_DEBUG_KEYS, + HCI_UNREGISTER, HCI_LE_SCAN, HCI_SSP_ENABLED, diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 59ec99eb739b..2054c1321c87 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -666,6 +666,11 @@ int hci_dev_open(__u16 dev) hci_req_lock(hdev); + if (test_bit(HCI_UNREGISTER, &hdev->dev_flags)) { + ret = -ENODEV; + goto done; + } + if (hdev->rfkill && rfkill_blocked(hdev->rfkill)) { ret = -ERFKILL; goto done; @@ -1850,6 +1855,8 @@ void hci_unregister_dev(struct hci_dev *hdev) BT_DBG("%p name %s bus %d", hdev, hdev->name, hdev->bus); + set_bit(HCI_UNREGISTER, &hdev->dev_flags); + write_lock(&hci_dev_list_lock); list_del(&hdev->list); write_unlock(&hci_dev_list_lock); -- cgit v1.2.3 From 8d7e1c7f7e5f9fe8f6279752fc33fcb77afd5001 Mon Sep 17 00:00:00 2001 From: Andrei Emeltchenko Date: Fri, 23 Mar 2012 09:42:15 +0200 Subject: Bluetooth: Fix memory leaks due to chan refcnt When we queue delayed work we hold(chan) and delayed work shall put(chan) after execution. Signed-off-by: Andrei Emeltchenko Signed-off-by: Gustavo Padovan --- net/bluetooth/l2cap_core.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'net') diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 3e450f4a3125..38d934a1124a 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -1309,6 +1309,7 @@ static void l2cap_monitor_timeout(struct work_struct *work) if (chan->retry_count >= chan->remote_max_tx) { l2cap_send_disconn_req(chan->conn, chan, ECONNABORTED); l2cap_chan_unlock(chan); + l2cap_chan_put(chan); return; } @@ -1317,6 +1318,7 @@ static void l2cap_monitor_timeout(struct work_struct *work) l2cap_send_rr_or_rnr(chan, L2CAP_CTRL_POLL); l2cap_chan_unlock(chan); + l2cap_chan_put(chan); } static void l2cap_retrans_timeout(struct work_struct *work) @@ -1336,6 +1338,7 @@ static void l2cap_retrans_timeout(struct work_struct *work) l2cap_send_rr_or_rnr(chan, L2CAP_CTRL_POLL); l2cap_chan_unlock(chan); + l2cap_chan_put(chan); } static void l2cap_drop_acked_frames(struct l2cap_chan *chan) -- cgit v1.2.3 From 531563850b29726bf37a81e877277902881ab77e Mon Sep 17 00:00:00 2001 From: Brian Gix Date: Fri, 9 Mar 2012 14:07:03 -0800 Subject: Bluetooth: mgmt: Fix corruption of device_connected pkt Incorrect pointer passed to eir_append_data made mgmt_device_connected event unparsable by mgmt user space entity. Signed-off-by: Brian Gix Signed-off-by: Johan Hedberg --- net/bluetooth/mgmt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 7fcff8887131..0e169dacfd4f 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -2936,7 +2936,7 @@ int mgmt_device_connected(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, name, name_len); if (dev_class && memcmp(dev_class, "\0\0\0", 3) != 0) - eir_len = eir_append_data(&ev->eir[eir_len], eir_len, + eir_len = eir_append_data(ev->eir, eir_len, EIR_CLASS_OF_DEV, dev_class, 3); put_unaligned_le16(eir_len, &ev->eir_len); -- cgit v1.2.3 From 76ec9de843c3cff41b3b15b752e1d08d91f0ad18 Mon Sep 17 00:00:00 2001 From: Andrei Emeltchenko Date: Mon, 12 Mar 2012 12:13:11 +0200 Subject: Bluetooth: mgmt: Add missing endian conversion Add missing endian conversion for page scan interval and window. Signed-off-by: Andrei Emeltchenko Acked-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- net/bluetooth/mgmt.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'net') diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 0e169dacfd4f..4ef275c69675 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -2523,13 +2523,18 @@ static int set_fast_connectable(struct sock *sk, struct hci_dev *hdev, if (cp->val) { type = PAGE_SCAN_TYPE_INTERLACED; - acp.interval = 0x0024; /* 22.5 msec page scan interval */ + + /* 22.5 msec page scan interval */ + acp.interval = __constant_cpu_to_le16(0x0024); } else { type = PAGE_SCAN_TYPE_STANDARD; /* default */ - acp.interval = 0x0800; /* default 1.28 sec page scan */ + + /* default 1.28 sec page scan */ + acp.interval = __constant_cpu_to_le16(0x0800); } - acp.window = 0x0012; /* default 11.25 msec page scan window */ + /* default 11.25 msec page scan window */ + acp.window = __constant_cpu_to_le16(0x0012); err = hci_send_cmd(hdev, HCI_OP_WRITE_PAGE_SCAN_ACTIVITY, sizeof(acp), &acp); -- cgit v1.2.3 From a2bd1140a264b561e38d99e656cd843c2d840e86 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Wed, 4 Apr 2012 16:10:46 -0700 Subject: netdma: adding alignment check for NETDMA ops This is the fallout from adding memcpy alignment workaround for certain IOATDMA hardware. NetDMA will only use DMA engine that can handle byte align ops. Acked-by: David S. Miller Signed-off-by: Dave Jiang Signed-off-by: Dan Williams --- drivers/dma/dmaengine.c | 14 ++++++++++++++ include/linux/dmaengine.h | 1 + net/ipv4/tcp.c | 4 ++-- net/ipv4/tcp_input.c | 2 +- net/ipv4/tcp_ipv4.c | 2 +- net/ipv6/tcp_ipv6.c | 2 +- 6 files changed, 20 insertions(+), 5 deletions(-) (limited to 'net') diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c index a6c6051ec858..0f1ca74fe0bb 100644 --- a/drivers/dma/dmaengine.c +++ b/drivers/dma/dmaengine.c @@ -332,6 +332,20 @@ struct dma_chan *dma_find_channel(enum dma_transaction_type tx_type) } EXPORT_SYMBOL(dma_find_channel); +/* + * net_dma_find_channel - find a channel for net_dma + * net_dma has alignment requirements + */ +struct dma_chan *net_dma_find_channel(void) +{ + struct dma_chan *chan = dma_find_channel(DMA_MEMCPY); + if (chan && !is_dma_copy_aligned(chan->device, 1, 1, 1)) + return NULL; + + return chan; +} +EXPORT_SYMBOL(net_dma_find_channel); + /** * dma_issue_pending_all - flush all pending operations across all channels */ diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 679b349d9b66..a5bb3ad5c7a5 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -948,6 +948,7 @@ int dma_async_device_register(struct dma_device *device); void dma_async_device_unregister(struct dma_device *device); void dma_run_dependencies(struct dma_async_tx_descriptor *tx); struct dma_chan *dma_find_channel(enum dma_transaction_type tx_type); +struct dma_chan *net_dma_find_channel(void); #define dma_request_channel(mask, x, y) __dma_request_channel(&(mask), x, y) /* --- Helper iov-locking functions --- */ diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 22ef5f9fd2ff..8712c5d4f91d 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1450,7 +1450,7 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, if ((available < target) && (len > sysctl_tcp_dma_copybreak) && !(flags & MSG_PEEK) && !sysctl_tcp_low_latency && - dma_find_channel(DMA_MEMCPY)) { + net_dma_find_channel()) { preempt_enable_no_resched(); tp->ucopy.pinned_list = dma_pin_iovec_pages(msg->msg_iov, len); @@ -1665,7 +1665,7 @@ do_prequeue: if (!(flags & MSG_TRUNC)) { #ifdef CONFIG_NET_DMA if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list) - tp->ucopy.dma_chan = dma_find_channel(DMA_MEMCPY); + tp->ucopy.dma_chan = net_dma_find_channel(); if (tp->ucopy.dma_chan) { tp->ucopy.dma_cookie = dma_skb_copy_datagram_iovec( diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index b5e315f13641..27c676dfea33 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5190,7 +5190,7 @@ static int tcp_dma_try_early_copy(struct sock *sk, struct sk_buff *skb, return 0; if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list) - tp->ucopy.dma_chan = dma_find_channel(DMA_MEMCPY); + tp->ucopy.dma_chan = net_dma_find_channel(); if (tp->ucopy.dma_chan && skb_csum_unnecessary(skb)) { diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index fd54c5f8a255..3810b6fe0a1e 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1727,7 +1727,7 @@ process: #ifdef CONFIG_NET_DMA struct tcp_sock *tp = tcp_sk(sk); if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list) - tp->ucopy.dma_chan = dma_find_channel(DMA_MEMCPY); + tp->ucopy.dma_chan = net_dma_find_channel(); if (tp->ucopy.dma_chan) ret = tcp_v4_do_rcv(sk, skb); else diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 3edd05ae4388..fcb3e4f0010e 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1755,7 +1755,7 @@ process: #ifdef CONFIG_NET_DMA struct tcp_sock *tp = tcp_sk(sk); if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list) - tp->ucopy.dma_chan = dma_find_channel(DMA_MEMCPY); + tp->ucopy.dma_chan = net_dma_find_channel(); if (tp->ucopy.dma_chan) ret = tcp_v6_do_rcv(sk, skb); else -- cgit v1.2.3 From 6ee0b693bdb8ec56689e0d1cc533b16466fda048 Mon Sep 17 00:00:00 2001 From: Changli Gao Date: Sun, 1 Apr 2012 17:25:06 +0000 Subject: netfilter: nf_ct_tcp: don't scale the size of the window up twice For a picked up connection, the window win is scaled twice: one is by the initialization code, and the other is by the sender updating code. I use the temporary variable swin instead of modifying the variable win. Signed-off-by: Changli Gao Acked-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_proto_tcp.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 361eade62a09..0d07a1dcf605 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -584,8 +584,8 @@ static bool tcp_in_window(const struct nf_conn *ct, * Let's try to use the data from the packet. */ sender->td_end = end; - win <<= sender->td_scale; - sender->td_maxwin = (win == 0 ? 1 : win); + swin = win << sender->td_scale; + sender->td_maxwin = (swin == 0 ? 1 : swin); sender->td_maxend = end + sender->td_maxwin; /* * We haven't seen traffic in the other direction yet -- cgit v1.2.3 From 95ad2f873d5d404dc9ebc2377de0b762346346c0 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 6 Apr 2012 18:12:54 +0200 Subject: netfilter: ip6_tables: ip6t_ext_hdr is now static inline We may hit this in xt_LOG: net/built-in.o:xt_LOG.c:function dump_ipv6_packet: error: undefined reference to 'ip6t_ext_hdr' happens with these config options: CONFIG_NETFILTER_XT_TARGET_LOG=y CONFIG_IP6_NF_IPTABLES=m ip6t_ext_hdr is fairly small and it is called in the packet path. Make it static inline. Reported-by: Simon Kirby Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_ipv6/ip6_tables.h | 12 +++++++++++- net/ipv6/netfilter/ip6_tables.c | 14 -------------- 2 files changed, 11 insertions(+), 15 deletions(-) (limited to 'net') diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h index f549adccc94c..1bc898b14a80 100644 --- a/include/linux/netfilter_ipv6/ip6_tables.h +++ b/include/linux/netfilter_ipv6/ip6_tables.h @@ -287,7 +287,17 @@ extern unsigned int ip6t_do_table(struct sk_buff *skb, struct xt_table *table); /* Check for an extension */ -extern int ip6t_ext_hdr(u8 nexthdr); +static inline int +ip6t_ext_hdr(u8 nexthdr) +{ return (nexthdr == IPPROTO_HOPOPTS) || + (nexthdr == IPPROTO_ROUTING) || + (nexthdr == IPPROTO_FRAGMENT) || + (nexthdr == IPPROTO_ESP) || + (nexthdr == IPPROTO_AH) || + (nexthdr == IPPROTO_NONE) || + (nexthdr == IPPROTO_DSTOPTS); +} + /* find specified header and get offset to it */ extern int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, int target, unsigned short *fragoff); diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 94874b0bdcdc..9d4e15559319 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -78,19 +78,6 @@ EXPORT_SYMBOL_GPL(ip6t_alloc_initial_table); Hence the start of any table is given by get_table() below. */ -/* Check for an extension */ -int -ip6t_ext_hdr(u8 nexthdr) -{ - return (nexthdr == IPPROTO_HOPOPTS) || - (nexthdr == IPPROTO_ROUTING) || - (nexthdr == IPPROTO_FRAGMENT) || - (nexthdr == IPPROTO_ESP) || - (nexthdr == IPPROTO_AH) || - (nexthdr == IPPROTO_NONE) || - (nexthdr == IPPROTO_DSTOPTS); -} - /* Returns whether matches rule or not. */ /* Performance critical - called for every packet */ static inline bool @@ -2366,7 +2353,6 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, EXPORT_SYMBOL(ip6t_register_table); EXPORT_SYMBOL(ip6t_unregister_table); EXPORT_SYMBOL(ip6t_do_table); -EXPORT_SYMBOL(ip6t_ext_hdr); EXPORT_SYMBOL(ipv6_find_hdr); module_init(ip6_tables_init); -- cgit v1.2.3 From 3f9768a5d262d01d317b2a03933db3d5082fcb68 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 28 Mar 2012 21:02:46 +0200 Subject: mac80211: fix association beacon wait timeout The TU_TO_EXP_TIME() macro already includes the "jiffies +" piece of the calculation, so don't add jiffies again. Reported-by: Oliver Hartkopp Signed-off-by: Johannes Berg Tested-by: Oliver Hartkopp Signed-off-by: John W. Linville --- net/mac80211/mlme.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'net') diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 576fb25456dd..f76da5b3f5c5 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -3387,8 +3387,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, */ printk(KERN_DEBUG "%s: waiting for beacon from %pM\n", sdata->name, ifmgd->bssid); - assoc_data->timeout = jiffies + - TU_TO_EXP_TIME(req->bss->beacon_interval); + assoc_data->timeout = TU_TO_EXP_TIME(req->bss->beacon_interval); } else { assoc_data->have_beacon = true; assoc_data->sent_assoc = false; -- cgit v1.2.3 From 2b5f8b0b44e17e625cfba1e7b88db44f4dcc0441 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 2 Apr 2012 10:51:55 +0200 Subject: nl80211: ensure interface is up in various APIs The nl80211 handling code should ensure as much as it can that the interface is in a valid state, it can certainly ensure the interface is running. Not doing so can cause calls through mac80211 into the driver that result in warnings and unspecified behaviour in the driver. Cc: stable@vger.kernel.org Reported-by: Ben Greear Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- net/wireless/nl80211.c | 31 ++++++++++++++++++------------- 1 file changed, 18 insertions(+), 13 deletions(-) (limited to 'net') diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index e49da2797022..f432c57af05d 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -1294,6 +1294,11 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) goto bad_res; } + if (!netif_running(netdev)) { + result = -ENETDOWN; + goto bad_res; + } + nla_for_each_nested(nl_txq_params, info->attrs[NL80211_ATTR_WIPHY_TXQ_PARAMS], rem_txq_params) { @@ -6384,7 +6389,7 @@ static struct genl_ops nl80211_ops[] = { .doit = nl80211_get_key, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV | + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, }, { @@ -6416,7 +6421,7 @@ static struct genl_ops nl80211_ops[] = { .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, .doit = nl80211_set_beacon, - .internal_flags = NL80211_FLAG_NEED_NETDEV | + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, }, { @@ -6424,7 +6429,7 @@ static struct genl_ops nl80211_ops[] = { .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, .doit = nl80211_start_ap, - .internal_flags = NL80211_FLAG_NEED_NETDEV | + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, }, { @@ -6432,7 +6437,7 @@ static struct genl_ops nl80211_ops[] = { .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, .doit = nl80211_stop_ap, - .internal_flags = NL80211_FLAG_NEED_NETDEV | + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, }, { @@ -6448,7 +6453,7 @@ static struct genl_ops nl80211_ops[] = { .doit = nl80211_set_station, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV | + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, }, { @@ -6464,7 +6469,7 @@ static struct genl_ops nl80211_ops[] = { .doit = nl80211_del_station, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV | + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, }, { @@ -6497,7 +6502,7 @@ static struct genl_ops nl80211_ops[] = { .doit = nl80211_del_mpath, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV | + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, }, { @@ -6505,7 +6510,7 @@ static struct genl_ops nl80211_ops[] = { .doit = nl80211_set_bss, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV | + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, }, { @@ -6531,7 +6536,7 @@ static struct genl_ops nl80211_ops[] = { .doit = nl80211_get_mesh_config, .policy = nl80211_policy, /* can be retrieved by unprivileged users */ - .internal_flags = NL80211_FLAG_NEED_NETDEV | + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, }, { @@ -6664,7 +6669,7 @@ static struct genl_ops nl80211_ops[] = { .doit = nl80211_setdel_pmksa, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV | + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, }, { @@ -6672,7 +6677,7 @@ static struct genl_ops nl80211_ops[] = { .doit = nl80211_setdel_pmksa, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV | + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, }, { @@ -6680,7 +6685,7 @@ static struct genl_ops nl80211_ops[] = { .doit = nl80211_flush_pmksa, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV | + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, }, { @@ -6840,7 +6845,7 @@ static struct genl_ops nl80211_ops[] = { .doit = nl80211_probe_client, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV | + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, }, { -- cgit v1.2.3 From 7ab2485b69571a3beb0313c591486626c3374c85 Mon Sep 17 00:00:00 2001 From: Julia Lawall Date: Mon, 9 Apr 2012 11:01:09 +0200 Subject: net/wireless/wext-core.c: add missing kfree Free extra as done in the error-handling code just above. Signed-off-by: Julia Lawall Signed-off-by: John W. Linville --- net/wireless/wext-core.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/wireless/wext-core.c b/net/wireless/wext-core.c index 0af7f54e4f61..af648e08e61b 100644 --- a/net/wireless/wext-core.c +++ b/net/wireless/wext-core.c @@ -780,8 +780,10 @@ static int ioctl_standard_iw_point(struct iw_point *iwp, unsigned int cmd, if (cmd == SIOCSIWENCODEEXT) { struct iw_encode_ext *ee = (void *) extra; - if (iwp->length < sizeof(*ee) + ee->key_len) - return -EFAULT; + if (iwp->length < sizeof(*ee) + ee->key_len) { + err = -EFAULT; + goto out; + } } } -- cgit v1.2.3 From 8430eac2f6a3c2adce22d490e2ab8bb50d59077a Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Mon, 9 Apr 2012 16:32:16 +0200 Subject: netfilter: nf_ct_ipv4: handle invalid IPv4 and IPv6 packets consistently IPv6 conntrack marked invalid packets as INVALID and let the user drop those by an explicit rule, while IPv4 conntrack dropped such packets itself. IPv4 conntrack is changed so that it marks INVALID packets and let the user to drop them. Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index de9da21113a1..750b06afd20e 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -74,12 +74,12 @@ static int ipv4_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph); if (iph == NULL) - return -NF_DROP; + return -NF_ACCEPT; /* Conntrack defragments packets, we might still see fragments * inside ICMP packets though. */ if (iph->frag_off & htons(IP_OFFSET)) - return -NF_DROP; + return -NF_ACCEPT; *dataoff = nhoff + (iph->ihl << 2); *protonum = iph->protocol; -- cgit v1.2.3 From 07153c6ec074257ade76a461429b567cff2b3a1e Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Tue, 3 Apr 2012 22:02:01 +0200 Subject: netfilter: nf_ct_ipv4: packets with wrong ihl are invalid It was reported that the Linux kernel sometimes logs: klogd: [2629147.402413] kernel BUG at net / netfilter / nf_conntrack_proto_tcp.c: 447! klogd: [1072212.887368] kernel BUG at net / netfilter / nf_conntrack_proto_tcp.c: 392 ipv4_get_l4proto() in nf_conntrack_l3proto_ipv4.c and tcp_error() in nf_conntrack_proto_tcp.c should catch malformed packets, so the errors at the indicated lines - TCP options parsing - should not happen. However, tcp_error() relies on the "dataoff" offset to the TCP header, calculated by ipv4_get_l4proto(). But ipv4_get_l4proto() does not check bogus ihl values in IPv4 packets, which then can slip through tcp_error() and get caught at the TCP options parsing routines. The patch fixes ipv4_get_l4proto() by invalidating packets with bogus ihl value. The patch closes netfilter bugzilla id 771. Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'net') diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index 750b06afd20e..cf73cc70ed2d 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -84,6 +84,14 @@ static int ipv4_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, *dataoff = nhoff + (iph->ihl << 2); *protonum = iph->protocol; + /* Check bogus IP headers */ + if (*dataoff > skb->len) { + pr_debug("nf_conntrack_ipv4: bogus IPv4 packet: " + "nhoff %u, ihl %u, skblen %u\n", + nhoff, iph->ihl << 2, skb->len); + return -NF_ACCEPT; + } + return NF_ACCEPT; } -- cgit v1.2.3 From 6ba900676bec8baaf61aa2f85b7345c0e65774d9 Mon Sep 17 00:00:00 2001 From: Gao feng Date: Sat, 7 Apr 2012 16:08:28 +0000 Subject: netfilter: nf_conntrack: fix incorrect logic in nf_conntrack_init_net in function nf_conntrack_init_net,when nf_conntrack_timeout_init falied, we should call nf_conntrack_ecache_fini to do rollback. but the current code calls nf_conntrack_timeout_fini. Signed-off-by: Gao feng Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 3cc4487ac349..729f157a0efa 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1592,7 +1592,7 @@ static int nf_conntrack_init_net(struct net *net) return 0; err_timeout: - nf_conntrack_timeout_fini(net); + nf_conntrack_ecache_fini(net); err_ecache: nf_conntrack_tstamp_fini(net); err_tstamp: -- cgit v1.2.3 From 5fb84b1428b271f8767e0eb3fcd7231896edfaa4 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 10 Apr 2012 00:56:42 +0000 Subject: tcp: restore correct limit Commit c43b874d5d714f (tcp: properly initialize tcp memory limits) tried to fix a regression added in commits 4acb4190 & 3dc43e3, but still get it wrong. Result is machines with low amount of memory have too small tcp_rmem[2] value and slow tcp receives : Per socket limit being 1/1024 of memory instead of 1/128 in old kernels, so rcv window is capped to small values. Fix this to match comment and previous behavior. Signed-off-by: Eric Dumazet Cc: Jason Wang Cc: Glauber Costa Signed-off-by: David S. Miller --- net/ipv4/tcp.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'net') diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 5d54ed30e821..7758a83f98ff 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3302,8 +3302,7 @@ void __init tcp_init(void) tcp_init_mem(&init_net); /* Set per-socket limits to no more than 1/128 the pressure threshold */ - limit = nr_free_buffer_pages() << (PAGE_SHIFT - 10); - limit = max(limit, 128UL); + limit = nr_free_buffer_pages() << (PAGE_SHIFT - 7); max_share = min(4UL*1024*1024, limit); sysctl_tcp_wmem[0] = SK_MEM_QUANTUM; -- cgit v1.2.3 From 18a223e0b9ec8979320ba364b47c9772391d6d05 Mon Sep 17 00:00:00 2001 From: Neal Cardwell Date: Tue, 10 Apr 2012 07:59:20 +0000 Subject: tcp: fix tcp_rcv_rtt_update() use of an unscaled RTT sample Fix a code path in tcp_rcv_rtt_update() that was comparing scaled and unscaled RTT samples. The intent in the code was to only use the 'm' measurement if it was a new minimum. However, since 'm' had not yet been shifted left 3 bits but 'new_sample' had, this comparison would nearly always succeed, leading us to erroneously set our receive-side RTT estimate to the 'm' sample when that sample could be nearly 8x too high to use. The overall effect is to often cause the receive-side RTT estimate to be significantly too large (up to 40% too large for brief periods in my tests). Signed-off-by: Neal Cardwell Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index e886e2f7fa8d..e7b54d29690e 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -474,8 +474,11 @@ static void tcp_rcv_rtt_update(struct tcp_sock *tp, u32 sample, int win_dep) if (!win_dep) { m -= (new_sample >> 3); new_sample += m; - } else if (m < new_sample) - new_sample = m << 3; + } else { + m <<= 3; + if (m < new_sample) + new_sample = m; + } } else { /* No previous measure. */ new_sample = m << 3; -- cgit v1.2.3 From 996304bbea3d2a094b7ba54c3bd65d3fffeac57b Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Wed, 4 Apr 2012 01:01:20 +0000 Subject: bridge: Do not send queries on multicast group leaves As it stands the bridge IGMP snooping system will respond to group leave messages with queries for remaining membership. This is both unnecessary and undesirable. First of all any multicast routers present should be doing this rather than us. What's more the queries that we send may end up upsetting other multicast snooping swithces in the system that are buggy. In fact, we can simply remove the code that send these queries because the existing membership expiry mechanism doesn't rely on them anyway. So this patch simply removes all code associated with group queries in response to group leave messages. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- net/bridge/br_multicast.c | 81 ----------------------------------------------- net/bridge/br_private.h | 4 --- 2 files changed, 85 deletions(-) (limited to 'net') diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 702a1ae9220b..27ca25ed7021 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -241,7 +241,6 @@ static void br_multicast_group_expired(unsigned long data) hlist_del_rcu(&mp->hlist[mdb->ver]); mdb->size--; - del_timer(&mp->query_timer); call_rcu_bh(&mp->rcu, br_multicast_free_group); out: @@ -271,7 +270,6 @@ static void br_multicast_del_pg(struct net_bridge *br, rcu_assign_pointer(*pp, p->next); hlist_del_init(&p->mglist); del_timer(&p->timer); - del_timer(&p->query_timer); call_rcu_bh(&p->rcu, br_multicast_free_pg); if (!mp->ports && !mp->mglist && @@ -507,74 +505,6 @@ static struct sk_buff *br_multicast_alloc_query(struct net_bridge *br, return NULL; } -static void br_multicast_send_group_query(struct net_bridge_mdb_entry *mp) -{ - struct net_bridge *br = mp->br; - struct sk_buff *skb; - - skb = br_multicast_alloc_query(br, &mp->addr); - if (!skb) - goto timer; - - netif_rx(skb); - -timer: - if (++mp->queries_sent < br->multicast_last_member_count) - mod_timer(&mp->query_timer, - jiffies + br->multicast_last_member_interval); -} - -static void br_multicast_group_query_expired(unsigned long data) -{ - struct net_bridge_mdb_entry *mp = (void *)data; - struct net_bridge *br = mp->br; - - spin_lock(&br->multicast_lock); - if (!netif_running(br->dev) || !mp->mglist || - mp->queries_sent >= br->multicast_last_member_count) - goto out; - - br_multicast_send_group_query(mp); - -out: - spin_unlock(&br->multicast_lock); -} - -static void br_multicast_send_port_group_query(struct net_bridge_port_group *pg) -{ - struct net_bridge_port *port = pg->port; - struct net_bridge *br = port->br; - struct sk_buff *skb; - - skb = br_multicast_alloc_query(br, &pg->addr); - if (!skb) - goto timer; - - br_deliver(port, skb); - -timer: - if (++pg->queries_sent < br->multicast_last_member_count) - mod_timer(&pg->query_timer, - jiffies + br->multicast_last_member_interval); -} - -static void br_multicast_port_group_query_expired(unsigned long data) -{ - struct net_bridge_port_group *pg = (void *)data; - struct net_bridge_port *port = pg->port; - struct net_bridge *br = port->br; - - spin_lock(&br->multicast_lock); - if (!netif_running(br->dev) || hlist_unhashed(&pg->mglist) || - pg->queries_sent >= br->multicast_last_member_count) - goto out; - - br_multicast_send_port_group_query(pg); - -out: - spin_unlock(&br->multicast_lock); -} - static struct net_bridge_mdb_entry *br_multicast_get_group( struct net_bridge *br, struct net_bridge_port *port, struct br_ip *group, int hash) @@ -690,8 +620,6 @@ rehash: mp->addr = *group; setup_timer(&mp->timer, br_multicast_group_expired, (unsigned long)mp); - setup_timer(&mp->query_timer, br_multicast_group_query_expired, - (unsigned long)mp); hlist_add_head_rcu(&mp->hlist[mdb->ver], &mdb->mhash[hash]); mdb->size++; @@ -746,8 +674,6 @@ static int br_multicast_add_group(struct net_bridge *br, hlist_add_head(&p->mglist, &port->mglist); setup_timer(&p->timer, br_multicast_port_group_expired, (unsigned long)p); - setup_timer(&p->query_timer, br_multicast_port_group_query_expired, - (unsigned long)p); rcu_assign_pointer(*pp, p); @@ -1291,9 +1217,6 @@ static void br_multicast_leave_group(struct net_bridge *br, time_after(mp->timer.expires, time) : try_to_del_timer_sync(&mp->timer) >= 0)) { mod_timer(&mp->timer, time); - - mp->queries_sent = 0; - mod_timer(&mp->query_timer, now); } goto out; @@ -1310,9 +1233,6 @@ static void br_multicast_leave_group(struct net_bridge *br, time_after(p->timer.expires, time) : try_to_del_timer_sync(&p->timer) >= 0)) { mod_timer(&p->timer, time); - - p->queries_sent = 0; - mod_timer(&p->query_timer, now); } break; @@ -1681,7 +1601,6 @@ void br_multicast_stop(struct net_bridge *br) hlist_for_each_entry_safe(mp, p, n, &mdb->mhash[i], hlist[ver]) { del_timer(&mp->timer); - del_timer(&mp->query_timer); call_rcu_bh(&mp->rcu, br_multicast_free_group); } } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 0b67a63ad7a8..e1d882257877 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -82,9 +82,7 @@ struct net_bridge_port_group { struct hlist_node mglist; struct rcu_head rcu; struct timer_list timer; - struct timer_list query_timer; struct br_ip addr; - u32 queries_sent; }; struct net_bridge_mdb_entry @@ -94,10 +92,8 @@ struct net_bridge_mdb_entry struct net_bridge_port_group __rcu *ports; struct rcu_head rcu; struct timer_list timer; - struct timer_list query_timer; struct br_ip addr; bool mglist; - u32 queries_sent; }; struct net_bridge_mdb_htable -- cgit v1.2.3 From 87151b8689d890dfb495081f7be9b9e257f7a2df Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 10 Apr 2012 20:08:39 +0000 Subject: net: allow pskb_expand_head() to get maximum tailroom Marc Merlin reported many order-1 allocations failures in TX path on its wireless setup, that dont make any sense with MTU=1500 network, and non SG capable hardware. Turns out part of the problem comes from pskb_expand_head() not using ksize() to get exact head size given by kmalloc(). Doing the same thing than __alloc_skb() allows more tailroom in skb and can prevent future reallocations. As a bonus, struct skb_shared_info becomes cache line aligned. Reported-by: Marc MERLIN Tested-by: Marc MERLIN Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/core/skbuff.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/core/skbuff.c b/net/core/skbuff.c index baf8d281152c..e59840010d45 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -952,9 +952,11 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, goto adjust_others; } - data = kmalloc(size + sizeof(struct skb_shared_info), gfp_mask); + data = kmalloc(size + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)), + gfp_mask); if (!data) goto nodata; + size = SKB_WITH_OVERHEAD(ksize(data)); /* Copy only real data... and, alas, header. This should be * optimized for the cases when header is void. -- cgit v1.2.3 From a21d45726acacc963d8baddf74607d9b74e2b723 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 10 Apr 2012 20:30:48 +0000 Subject: tcp: avoid order-1 allocations on wifi and tx path Marc Merlin reported many order-1 allocations failures in TX path on its wireless setup, that dont make any sense with MTU=1500 network, and non SG capable hardware. After investigation, it turns out TCP uses sk_stream_alloc_skb() and used as a convention skb_tailroom(skb) to know how many bytes of data payload could be put in this skb (for non SG capable devices) Note : these skb used kmalloc-4096 (MTU=1500 + MAX_HEADER + sizeof(struct skb_shared_info) being above 2048) Later, mac80211 layer need to add some bytes at the tail of skb (IEEE80211_ENCRYPT_TAILROOM = 18 bytes) and since no more tailroom is available has to call pskb_expand_head() and request order-1 allocations. This patch changes sk_stream_alloc_skb() so that only sk->sk_prot->max_header bytes of headroom are reserved, and use a new skb field, avail_size to hold the data payload limit. This way, order-0 allocations done by TCP stack can leave more than 2 KB of tailroom and no more allocation is performed in mac80211 layer (or any layer needing some tailroom) avail_size is unioned with mark/dropcount, since mark will be set later in IP stack for output packets. Therefore, skb size is unchanged. Reported-by: Marc MERLIN Tested-by: Marc MERLIN Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 13 +++++++++++++ net/ipv4/tcp.c | 8 ++++---- net/ipv4/tcp_output.c | 2 +- 3 files changed, 18 insertions(+), 5 deletions(-) (limited to 'net') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 33370271b8b2..70a3f8d49118 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -481,6 +481,7 @@ struct sk_buff { union { __u32 mark; __u32 dropcount; + __u32 avail_size; }; sk_buff_data_t transport_header; @@ -1365,6 +1366,18 @@ static inline int skb_tailroom(const struct sk_buff *skb) return skb_is_nonlinear(skb) ? 0 : skb->end - skb->tail; } +/** + * skb_availroom - bytes at buffer end + * @skb: buffer to check + * + * Return the number of bytes of free space at the tail of an sk_buff + * allocated by sk_stream_alloc() + */ +static inline int skb_availroom(const struct sk_buff *skb) +{ + return skb_is_nonlinear(skb) ? 0 : skb->avail_size - skb->len; +} + /** * skb_reserve - adjust headroom * @skb: buffer to alter diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 7758a83f98ff..a5daa211a8e1 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -701,11 +701,12 @@ struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp) skb = alloc_skb_fclone(size + sk->sk_prot->max_header, gfp); if (skb) { if (sk_wmem_schedule(sk, skb->truesize)) { + skb_reserve(skb, sk->sk_prot->max_header); /* * Make sure that we have exactly size bytes * available to the caller, no more, no less. */ - skb_reserve(skb, skb_tailroom(skb) - size); + skb->avail_size = size; return skb; } __kfree_skb(skb); @@ -995,10 +996,9 @@ new_segment: copy = seglen; /* Where to copy to? */ - if (skb_tailroom(skb) > 0) { + if (skb_availroom(skb) > 0) { /* We have some space in skb head. Superb! */ - if (copy > skb_tailroom(skb)) - copy = skb_tailroom(skb); + copy = min_t(int, copy, skb_availroom(skb)); err = skb_add_data_nocache(sk, skb, from, copy); if (err) goto do_fault; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 364784a91939..376b2cfbb685 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2060,7 +2060,7 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to, /* Punt if not enough space exists in the first SKB for * the data in the second */ - if (skb->len > skb_tailroom(to)) + if (skb->len > skb_availroom(to)) break; if (after(TCP_SKB_CB(skb)->end_seq, tcp_wnd_end(tp))) -- cgit v1.2.3 From b4838d12e1f3cb48c2489a0b08733b5dbf848297 Mon Sep 17 00:00:00 2001 From: Samuel Ortiz Date: Tue, 10 Apr 2012 19:43:03 +0200 Subject: NFC: Fix the LLCP Tx fragmentation loop Reported-by: Dan Carpenter Signed-off-by: Samuel Ortiz Signed-off-by: John W. Linville --- net/nfc/llcp/commands.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/nfc/llcp/commands.c b/net/nfc/llcp/commands.c index 7b76eb7192f3..ef10ffcb4b6f 100644 --- a/net/nfc/llcp/commands.c +++ b/net/nfc/llcp/commands.c @@ -474,7 +474,7 @@ int nfc_llcp_send_i_frame(struct nfc_llcp_sock *sock, while (remaining_len > 0) { - frag_len = min_t(u16, local->remote_miu, remaining_len); + frag_len = min_t(size_t, local->remote_miu, remaining_len); pr_debug("Fragment %zd bytes remaining %zd", frag_len, remaining_len); @@ -497,7 +497,7 @@ int nfc_llcp_send_i_frame(struct nfc_llcp_sock *sock, release_sock(sk); remaining_len -= frag_len; - msg_ptr += len; + msg_ptr += frag_len; } kfree(msg_data); -- cgit v1.2.3