From 4571928fc73589e9c5217cd069d2c0b4ff1818a8 Mon Sep 17 00:00:00 2001 From: David Sterba Date: Fri, 14 Jan 2011 14:59:44 +0100 Subject: Bluetooth: l2cap: fix misuse of logical operation in place of bitop MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit CC: Marcel Holtmann CC: "Gustavo F. Padovan" CC: João Paulo Rechi Vita Signed-off-by: David Sterba Signed-off-by: Gustavo F. Padovan --- net/bluetooth/l2cap.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/bluetooth/l2cap.c b/net/bluetooth/l2cap.c index c791fcda7b2d..4fd88eb0a464 100644 --- a/net/bluetooth/l2cap.c +++ b/net/bluetooth/l2cap.c @@ -1893,8 +1893,8 @@ static int l2cap_sock_sendmsg(struct kiocb *iocb, struct socket *sock, struct ms if (pi->mode == L2CAP_MODE_STREAMING) { l2cap_streaming_send(sk); } else { - if (pi->conn_state & L2CAP_CONN_REMOTE_BUSY && - pi->conn_state && L2CAP_CONN_WAIT_F) { + if ((pi->conn_state & L2CAP_CONN_REMOTE_BUSY) && + (pi->conn_state & L2CAP_CONN_WAIT_F)) { err = len; break; } -- cgit v1.2.3 From e2e0cacbd4b0c7c69c7591d37c243f2363aeaa71 Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Tue, 4 Jan 2011 12:08:50 +0200 Subject: Bluetooth: Fix leaking blacklist when unregistering a hci device The blacklist should be freed before the hci device gets unregistered. Signed-off-by: Johan Hedberg Signed-off-by: Gustavo F. Padovan --- net/bluetooth/hci_core.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'net') diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 8b602d881fd7..9c4541bc488a 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -1011,6 +1011,10 @@ int hci_unregister_dev(struct hci_dev *hdev) destroy_workqueue(hdev->workqueue); + hci_dev_lock_bh(hdev); + hci_blacklist_clear(hdev); + hci_dev_unlock_bh(hdev); + __hci_dev_put(hdev); return 0; -- cgit v1.2.3 From 683d949a7fbf33c244670e34d35c460e0d6558cb Mon Sep 17 00:00:00 2001 From: Lukáš Turek <8an@praha12.net> Date: Wed, 5 Jan 2011 02:43:59 +0100 Subject: Bluetooth: Never deallocate a session when some DLC points to it Fix a bug introduced in commit 9cf5b0ea3a7f1432c61029f7aaf4b8b338628884: function rfcomm_recv_ua calls rfcomm_session_put without checking that the session is not referenced by some DLC. If the session is freed, that DLC would refer to deallocated memory, causing an oops later, as shown in this bug report: https://bugzilla.kernel.org/show_bug.cgi?id=15994 Signed-off-by: Lukas Turek <8an@praha12.net> Signed-off-by: Gustavo F. Padovan --- net/bluetooth/rfcomm/core.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index ff8aaa736650..6b83776534fb 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -1164,7 +1164,8 @@ static int rfcomm_recv_ua(struct rfcomm_session *s, u8 dlci) * initiator rfcomm_process_rx already calls * rfcomm_session_put() */ if (s->sock->sk->sk_state != BT_CLOSED) - rfcomm_session_put(s); + if (list_empty(&s->dlcs)) + rfcomm_session_put(s); break; } } -- cgit v1.2.3 From 88644bb9fee591b2743a881923263bc28df4cded Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Wed, 19 Jan 2011 12:06:48 +0530 Subject: Revert "Bluetooth: Update sec_level/auth_type for already existing connections" This reverts commit 045309820afe047920a50de25634dab46a1e851d. That commit is wrong for two reasons: - The conn->sec_level shouldn't be updated without performing authentication first (as it's supposed to represent the level of security that the existing connection has) - A higher auth_type value doesn't mean "more secure" like the commit seems to assume. E.g. dedicated bonding with MITM protection is 0x03 whereas general bonding without MITM protection is 0x04. hci_conn_auth already takes care of updating conn->auth_type so hci_connect doesn't need to do it. Signed-off-by: Johan Hedberg Acked-by: Marcel Holtmann Signed-off-by: Gustavo F. Padovan --- net/bluetooth/hci_conn.c | 5 ----- 1 file changed, 5 deletions(-) (limited to 'net') diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 6b90a4191734..65a3fb5678eb 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -382,11 +382,6 @@ struct hci_conn *hci_connect(struct hci_dev *hdev, int type, bdaddr_t *dst, __u8 acl->sec_level = sec_level; acl->auth_type = auth_type; hci_acl_connect(acl); - } else { - if (acl->sec_level < sec_level) - acl->sec_level = sec_level; - if (acl->auth_type < auth_type) - acl->auth_type = auth_type; } if (type == ACL_LINK) -- cgit v1.2.3 From 65cf686ee102b7eb0477a4bab82ff227071a0258 Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Wed, 19 Jan 2011 12:06:49 +0530 Subject: Bluetooth: Fix MITM protection requirement preservation If an existing connection has a MITM protection requirement (the first bit of the auth_type) then that requirement should not be cleared by new sockets that reuse the ACL but don't have that requirement. Signed-off-by: Johan Hedberg Acked-by: Marcel Holtmann Signed-off-by: Gustavo F. Padovan --- net/bluetooth/hci_conn.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'net') diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 65a3fb5678eb..fe712a89a856 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -442,6 +442,9 @@ static int hci_conn_auth(struct hci_conn *conn, __u8 sec_level, __u8 auth_type) else if (conn->link_mode & HCI_LM_AUTH) return 1; + /* Make sure we preserve an existing MITM requirement*/ + auth_type |= (conn->auth_type & 0x01); + conn->auth_type = auth_type; if (!test_and_set_bit(HCI_CONN_AUTH_PEND, &conn->pend)) { -- cgit v1.2.3 From 8556edd32f01c50a3c99e44dc2c3b1252ea59605 Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Wed, 19 Jan 2011 12:06:50 +0530 Subject: Bluetooth: Create a unified auth_type evaluation function The logic for determining the needed auth_type for an L2CAP socket is rather complicated and has so far been duplicated in l2cap_check_security as well as l2cap_do_connect. Additionally the l2cap_check_security code was completely missing the handling of SOCK_RAW type sockets. This patch creates a unified function for the evaluation and makes l2cap_do_connect and l2cap_check_security use that function. Signed-off-by: Johan Hedberg Acked-by: Marcel Holtmann Signed-off-by: Gustavo F. Padovan --- net/bluetooth/l2cap.c | 77 +++++++++++++++++++-------------------------------- 1 file changed, 28 insertions(+), 49 deletions(-) (limited to 'net') diff --git a/net/bluetooth/l2cap.c b/net/bluetooth/l2cap.c index 4fd88eb0a464..ae227bf25563 100644 --- a/net/bluetooth/l2cap.c +++ b/net/bluetooth/l2cap.c @@ -305,33 +305,44 @@ static void l2cap_chan_del(struct sock *sk, int err) } } -/* Service level security */ -static inline int l2cap_check_security(struct sock *sk) +static inline u8 l2cap_get_auth_type(struct sock *sk) { - struct l2cap_conn *conn = l2cap_pi(sk)->conn; - __u8 auth_type; + if (sk->sk_type == SOCK_RAW) { + switch (l2cap_pi(sk)->sec_level) { + case BT_SECURITY_HIGH: + return HCI_AT_DEDICATED_BONDING_MITM; + case BT_SECURITY_MEDIUM: + return HCI_AT_DEDICATED_BONDING; + default: + return HCI_AT_NO_BONDING; + } + } else if (l2cap_pi(sk)->psm == cpu_to_le16(0x0001)) { + if (l2cap_pi(sk)->sec_level == BT_SECURITY_LOW) + l2cap_pi(sk)->sec_level = BT_SECURITY_SDP; - if (l2cap_pi(sk)->psm == cpu_to_le16(0x0001)) { if (l2cap_pi(sk)->sec_level == BT_SECURITY_HIGH) - auth_type = HCI_AT_NO_BONDING_MITM; + return HCI_AT_NO_BONDING_MITM; else - auth_type = HCI_AT_NO_BONDING; - - if (l2cap_pi(sk)->sec_level == BT_SECURITY_LOW) - l2cap_pi(sk)->sec_level = BT_SECURITY_SDP; + return HCI_AT_NO_BONDING; } else { switch (l2cap_pi(sk)->sec_level) { case BT_SECURITY_HIGH: - auth_type = HCI_AT_GENERAL_BONDING_MITM; - break; + return HCI_AT_GENERAL_BONDING_MITM; case BT_SECURITY_MEDIUM: - auth_type = HCI_AT_GENERAL_BONDING; - break; + return HCI_AT_GENERAL_BONDING; default: - auth_type = HCI_AT_NO_BONDING; - break; + return HCI_AT_NO_BONDING; } } +} + +/* Service level security */ +static inline int l2cap_check_security(struct sock *sk) +{ + struct l2cap_conn *conn = l2cap_pi(sk)->conn; + __u8 auth_type; + + auth_type = l2cap_get_auth_type(sk); return hci_conn_security(conn->hcon, l2cap_pi(sk)->sec_level, auth_type); @@ -1068,39 +1079,7 @@ static int l2cap_do_connect(struct sock *sk) err = -ENOMEM; - if (sk->sk_type == SOCK_RAW) { - switch (l2cap_pi(sk)->sec_level) { - case BT_SECURITY_HIGH: - auth_type = HCI_AT_DEDICATED_BONDING_MITM; - break; - case BT_SECURITY_MEDIUM: - auth_type = HCI_AT_DEDICATED_BONDING; - break; - default: - auth_type = HCI_AT_NO_BONDING; - break; - } - } else if (l2cap_pi(sk)->psm == cpu_to_le16(0x0001)) { - if (l2cap_pi(sk)->sec_level == BT_SECURITY_HIGH) - auth_type = HCI_AT_NO_BONDING_MITM; - else - auth_type = HCI_AT_NO_BONDING; - - if (l2cap_pi(sk)->sec_level == BT_SECURITY_LOW) - l2cap_pi(sk)->sec_level = BT_SECURITY_SDP; - } else { - switch (l2cap_pi(sk)->sec_level) { - case BT_SECURITY_HIGH: - auth_type = HCI_AT_GENERAL_BONDING_MITM; - break; - case BT_SECURITY_MEDIUM: - auth_type = HCI_AT_GENERAL_BONDING; - break; - default: - auth_type = HCI_AT_NO_BONDING; - break; - } - } + auth_type = l2cap_get_auth_type(sk); hcon = hci_connect(hdev, ACL_LINK, dst, l2cap_pi(sk)->sec_level, auth_type); -- cgit v1.2.3 From d00ef24fc2923b65fdd440dc6445903e965841ac Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Wed, 19 Jan 2011 12:06:51 +0530 Subject: Bluetooth: Fix authentication request for L2CAP raw sockets When there is an existing connection l2cap_check_security needs to be called to ensure that the security level of the new socket is fulfilled. Normally l2cap_do_start takes care of this, but that function doesn't get called for SOCK_RAW type sockets. This patch adds the necessary l2cap_check_security call to the appropriate branch in l2cap_do_connect. Signed-off-by: Johan Hedberg Acked-by: Marcel Holtmann Signed-off-by: Gustavo F. Padovan --- net/bluetooth/l2cap.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/bluetooth/l2cap.c b/net/bluetooth/l2cap.c index ae227bf25563..7550abb0c96a 100644 --- a/net/bluetooth/l2cap.c +++ b/net/bluetooth/l2cap.c @@ -1106,7 +1106,8 @@ static int l2cap_do_connect(struct sock *sk) if (sk->sk_type != SOCK_SEQPACKET && sk->sk_type != SOCK_STREAM) { l2cap_sock_clear_timer(sk); - sk->sk_state = BT_CONNECTED; + if (l2cap_check_security(sk)) + sk->sk_state = BT_CONNECTED; } else l2cap_do_start(sk); } -- cgit v1.2.3 From 765c2a964b49bd06b61a52991519281c85d82b67 Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Wed, 19 Jan 2011 12:06:52 +0530 Subject: Bluetooth: Fix race condition with conn->sec_level The conn->sec_level value is supposed to represent the current level of security that the connection has. However, by assigning to it before requesting authentication it will have the wrong value during the authentication procedure. To fix this a pending_sec_level variable is added which is used to track the desired security level while making sure that sec_level always represents the current level of security. Signed-off-by: Johan Hedberg Signed-off-by: Gustavo F. Padovan --- include/net/bluetooth/hci_core.h | 1 + net/bluetooth/hci_conn.c | 8 ++++++-- net/bluetooth/hci_event.c | 9 +++++---- 3 files changed, 12 insertions(+), 6 deletions(-) (limited to 'net') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index a29feb01854e..d2cf88407690 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -184,6 +184,7 @@ struct hci_conn { __u32 link_mode; __u8 auth_type; __u8 sec_level; + __u8 pending_sec_level; __u8 power_save; __u16 disc_timeout; unsigned long pend; diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index fe712a89a856..99cd8d9d891b 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -379,7 +379,8 @@ struct hci_conn *hci_connect(struct hci_dev *hdev, int type, bdaddr_t *dst, __u8 hci_conn_hold(acl); if (acl->state == BT_OPEN || acl->state == BT_CLOSED) { - acl->sec_level = sec_level; + acl->sec_level = BT_SECURITY_LOW; + acl->pending_sec_level = sec_level; acl->auth_type = auth_type; hci_acl_connect(acl); } @@ -437,8 +438,11 @@ static int hci_conn_auth(struct hci_conn *conn, __u8 sec_level, __u8 auth_type) { BT_DBG("conn %p", conn); + if (conn->pending_sec_level > sec_level) + sec_level = conn->pending_sec_level; + if (sec_level > conn->sec_level) - conn->sec_level = sec_level; + conn->pending_sec_level = sec_level; else if (conn->link_mode & HCI_LM_AUTH) return 1; diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 38100170d380..a290854fdaa6 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -692,13 +692,13 @@ static int hci_outgoing_auth_needed(struct hci_dev *hdev, if (conn->state != BT_CONFIG || !conn->out) return 0; - if (conn->sec_level == BT_SECURITY_SDP) + if (conn->pending_sec_level == BT_SECURITY_SDP) return 0; /* Only request authentication for SSP connections or non-SSP * devices with sec_level HIGH */ if (!(hdev->ssp_mode > 0 && conn->ssp_mode > 0) && - conn->sec_level != BT_SECURITY_HIGH) + conn->pending_sec_level != BT_SECURITY_HIGH) return 0; return 1; @@ -1095,9 +1095,10 @@ static inline void hci_auth_complete_evt(struct hci_dev *hdev, struct sk_buff *s conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(ev->handle)); if (conn) { - if (!ev->status) + if (!ev->status) { conn->link_mode |= HCI_LM_AUTH; - else + conn->sec_level = conn->pending_sec_level; + } else conn->sec_level = BT_SECURITY_LOW; clear_bit(HCI_CONN_AUTH_PEND, &conn->pend); -- cgit v1.2.3 From d1dc7abf2fafa34b0ffcd070fd59405aa9c0a4d8 Mon Sep 17 00:00:00 2001 From: Michal Schmidt Date: Mon, 24 Jan 2011 12:08:48 +0000 Subject: GRO: fix merging a paged skb after non-paged skbs Suppose that several linear skbs of the same flow were received by GRO. They were thus merged into one skb with a frag_list. Then a new skb of the same flow arrives, but it is a paged skb with data starting in its frags[]. Before adding the skb to the frag_list skb_gro_receive() will of course adjust the skb to throw away the headers. It correctly modifies the page_offset and size of the frag, but it leaves incorrect information in the skb: ->data_len is not decreased at all. ->len is decreased only by headlen, as if no change were done to the frag. Later in a receiving process this causes skb_copy_datagram_iovec() to return -EFAULT and this is seen in userspace as the result of the recv() syscall. In practice the bug can be reproduced with the sfc driver. By default the driver uses an adaptive scheme when it switches between using napi_gro_receive() (with skbs) and napi_gro_frags() (with pages). The bug is reproduced when under rx load with enough successful GRO merging the driver decides to switch from the former to the latter. Manual control is also possible, so reproducing this is easy with netcat: - on machine1 (with sfc): nc -l 12345 > /dev/null - on machine2: nc machine1 12345 < /dev/zero - on machine1: echo 1 > /sys/module/sfc/parameters/rx_alloc_method # use skbs echo 2 > /sys/module/sfc/parameters/rx_alloc_method # use pages - See that nc has quit suddenly. [v2: Modified by Eric Dumazet to avoid advancing skb->data past the end and to use a temporary variable.] Signed-off-by: Michal Schmidt Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/core/skbuff.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/core/skbuff.c b/net/core/skbuff.c index d31bb36ae0dc..7cd1bc86d591 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2744,8 +2744,12 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb) merge: if (offset > headlen) { - skbinfo->frags[0].page_offset += offset - headlen; - skbinfo->frags[0].size -= offset - headlen; + unsigned int eat = offset - headlen; + + skbinfo->frags[0].page_offset += eat; + skbinfo->frags[0].size -= eat; + skb->data_len -= eat; + skb->len -= eat; offset = headlen; } -- cgit v1.2.3 From 3408404a4c2a4eead9d73b0bbbfe3f225b65f492 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Mon, 24 Jan 2011 14:37:46 -0800 Subject: inetpeer: Use correct AVL tree base pointer in inet_getpeer(). Family was hard-coded to AF_INET but should be daddr->family. This fixes crashes when unlinking ipv6 peer entries, since the unlink code was looking up the base pointer properly. Reported-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/inetpeer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index d9bc85751c74..a96e65674ac3 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -475,7 +475,7 @@ static int cleanup_once(unsigned long ttl) struct inet_peer *inet_getpeer(struct inetpeer_addr *daddr, int create) { struct inet_peer __rcu **stack[PEER_MAXDEPTH], ***stackptr; - struct inet_peer_base *base = family_to_base(AF_INET); + struct inet_peer_base *base = family_to_base(daddr->family); struct inet_peer *p; /* Look up for the address quickly, lockless. -- cgit v1.2.3 From fd0273c5033630b8673554cd39660435d1ab2ac4 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 24 Jan 2011 14:41:20 -0800 Subject: tcp: fix bug in listening_get_next() commit a8b690f98baf9fb19 (tcp: Fix slowness in read /proc/net/tcp) introduced a bug in handling of SYN_RECV sockets. st->offset represents number of sockets found since beginning of listening_hash[st->bucket]. We should not reset st->offset when iterating through syn_table[st->sbucket], or else if more than ~25 sockets (if PAGE_SIZE=4096) are in SYN_RECV state, we exit from listening_get_next() with a too small st->offset Next time we enter tcp_seek_last_pos(), we are not able to seek past already found sockets. Reported-by: PK CC: Tom Herbert Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 1 - 1 file changed, 1 deletion(-) (limited to 'net') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 856f68466d49..02f583b3744a 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1994,7 +1994,6 @@ static void *listening_get_next(struct seq_file *seq, void *cur) } req = req->dl_next; } - st->offset = 0; if (++st->sbucket >= icsk->icsk_accept_queue.listen_opt->nr_table_entries) break; get_req: -- cgit v1.2.3 From 3dce38a02d6370dca690cd923619d4b00024b723 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Fri, 21 Jan 2011 16:35:18 +0000 Subject: dcbnl: make get_app handling symmetric for IEEE and CEE DCBx The IEEE get/set app handlers use generic routines and do not require the net_device to implement the dcbnl_ops routines. This patch makes it symmetric so user space and drivers do not have to handle the CEE version and IEEE DCBx versions differently. Signed-off-by: John Fastabend Signed-off-by: David S. Miller --- net/dcb/dcbnl.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index d900ab99814a..6b03f561caec 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -583,7 +583,7 @@ static int dcbnl_getapp(struct net_device *netdev, struct nlattr **tb, u8 up, idtype; int ret = -EINVAL; - if (!tb[DCB_ATTR_APP] || !netdev->dcbnl_ops->getapp) + if (!tb[DCB_ATTR_APP]) goto out; ret = nla_parse_nested(app_tb, DCB_APP_ATTR_MAX, tb[DCB_ATTR_APP], @@ -604,7 +604,16 @@ static int dcbnl_getapp(struct net_device *netdev, struct nlattr **tb, goto out; id = nla_get_u16(app_tb[DCB_APP_ATTR_ID]); - up = netdev->dcbnl_ops->getapp(netdev, idtype, id); + + if (netdev->dcbnl_ops->getapp) { + up = netdev->dcbnl_ops->getapp(netdev, idtype, id); + } else { + struct dcb_app app = { + .selector = idtype, + .protocol = id, + }; + up = dcb_getapp(netdev, &app); + } /* send this back */ dcbnl_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); -- cgit v1.2.3 From d80bc0fd262ef840ed4e82593ad6416fa1ba3fc4 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Mon, 24 Jan 2011 16:01:58 -0800 Subject: ipv6: Always clone offlink routes. Do not handle PMTU vs. route lookup creation any differently wrt. offlink routes, always clone them. Reported-by: PK Signed-off-by: David S. Miller --- net/ipv6/route.c | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) (limited to 'net') diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 373bd0416f69..1534508f6c68 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -72,8 +72,6 @@ #define RT6_TRACE(x...) do { ; } while (0) #endif -#define CLONE_OFFLINK_ROUTE 0 - static struct rt6_info * ip6_rt_copy(struct rt6_info *ort); static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie); static unsigned int ip6_default_advmss(const struct dst_entry *dst); @@ -738,13 +736,8 @@ restart: if (!rt->rt6i_nexthop && !(rt->rt6i_flags & RTF_NONEXTHOP)) nrt = rt6_alloc_cow(rt, &fl->fl6_dst, &fl->fl6_src); - else { -#if CLONE_OFFLINK_ROUTE + else nrt = rt6_alloc_clone(rt, &fl->fl6_dst); -#else - goto out2; -#endif - } dst_release(&rt->dst); rt = nrt ? : net->ipv6.ip6_null_entry; -- cgit v1.2.3 From b7c7d01aaed1f71d9afe815a569f0a81465a1744 Mon Sep 17 00:00:00 2001 From: Eugene Teo Date: Mon, 24 Jan 2011 21:05:17 -0800 Subject: net: clear heap allocation for ethtool_get_regs() There is a conflict between commit b00916b1 and a77f5db3. This patch resolves the conflict by clearing the heap allocation in ethtool_get_regs(). Cc: stable@kernel.org Signed-off-by: Eugene Teo Signed-off-by: David S. Miller --- net/core/ethtool.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 17741782a345..ff2302910b5e 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -817,7 +817,7 @@ static int ethtool_get_regs(struct net_device *dev, char __user *useraddr) if (regs.len > reglen) regs.len = reglen; - regbuf = vmalloc(reglen); + regbuf = vzalloc(reglen); if (!regbuf) return -ENOMEM; -- cgit v1.2.3 From 73a8bd74e2618990dbb218c3d82f53e60acd9af0 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Sun, 23 Jan 2011 23:27:15 -0800 Subject: ipv6: Revert 'administrative down' address handling changes. This reverts the following set of commits: d1ed113f1669390da9898da3beddcc058d938587 ("ipv6: remove duplicate neigh_ifdown") 29ba5fed1bbd09c2cba890798c8f9eaab251401d ("ipv6: don't flush routes when setting loopback down") 9d82ca98f71fd686ef2f3017c5e3e6a4871b6e46 ("ipv6: fix missing in6_ifa_put in addrconf") 2de795707294972f6c34bae9de713e502c431296 ("ipv6: addrconf: don't remove address state on ifdown if the address is being kept") 8595805aafc8b077e01804c9a3668e9aa3510e89 ("IPv6: only notify protocols if address is compeletely gone") 27bdb2abcc5edb3526e25407b74bf17d1872c329 ("IPv6: keep tentative addresses in hash table") 93fa159abe50d3c55c7f83622d3f5c09b6e06f4b ("IPv6: keep route for tentative address") 8f37ada5b5f6bfb4d251a7f510f249cb855b77b3 ("IPv6: fix race between cleanup and add/delete address") 84e8b803f1e16f3a2b8b80f80a63fa2f2f8a9be6 ("IPv6: addrconf notify when address is unavailable") dc2b99f71ef477a31020511876ab4403fb7c4420 ("IPv6: keep permanent addresses on admin down") because the core semantic change to ipv6 address handling on ifdown has broken some things, in particular "disable_ipv6" sysctl handling. Stephen has made several attempts to get things back in working order, but nothing has restored disable_ipv6 fully yet. Reported-by: Eric W. Biederman Tested-by: Eric W. Biederman Signed-off-by: David S. Miller --- net/ipv6/addrconf.c | 81 ++++++++++++++++++++++------------------------------- 1 file changed, 33 insertions(+), 48 deletions(-) (limited to 'net') diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 24a1cf110d80..fd6782e3a038 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2661,14 +2661,12 @@ static int addrconf_ifdown(struct net_device *dev, int how) struct net *net = dev_net(dev); struct inet6_dev *idev; struct inet6_ifaddr *ifa; - LIST_HEAD(keep_list); - int state; + int state, i; ASSERT_RTNL(); - /* Flush routes if device is being removed or it is not loopback */ - if (how || !(dev->flags & IFF_LOOPBACK)) - rt6_ifdown(net, dev); + rt6_ifdown(net, dev); + neigh_ifdown(&nd_tbl, dev); idev = __in6_dev_get(dev); if (idev == NULL) @@ -2689,6 +2687,23 @@ static int addrconf_ifdown(struct net_device *dev, int how) } + /* Step 2: clear hash table */ + for (i = 0; i < IN6_ADDR_HSIZE; i++) { + struct hlist_head *h = &inet6_addr_lst[i]; + struct hlist_node *n; + + spin_lock_bh(&addrconf_hash_lock); + restart: + hlist_for_each_entry_rcu(ifa, n, h, addr_lst) { + if (ifa->idev == idev) { + hlist_del_init_rcu(&ifa->addr_lst); + addrconf_del_timer(ifa); + goto restart; + } + } + spin_unlock_bh(&addrconf_hash_lock); + } + write_lock_bh(&idev->lock); /* Step 2: clear flags for stateless addrconf */ @@ -2722,52 +2737,23 @@ static int addrconf_ifdown(struct net_device *dev, int how) struct inet6_ifaddr, if_list); addrconf_del_timer(ifa); - /* If just doing link down, and address is permanent - and not link-local, then retain it. */ - if (!how && - (ifa->flags&IFA_F_PERMANENT) && - !(ipv6_addr_type(&ifa->addr) & IPV6_ADDR_LINKLOCAL)) { - list_move_tail(&ifa->if_list, &keep_list); - - /* If not doing DAD on this address, just keep it. */ - if ((dev->flags&(IFF_NOARP|IFF_LOOPBACK)) || - idev->cnf.accept_dad <= 0 || - (ifa->flags & IFA_F_NODAD)) - continue; + list_del(&ifa->if_list); - /* If it was tentative already, no need to notify */ - if (ifa->flags & IFA_F_TENTATIVE) - continue; + write_unlock_bh(&idev->lock); - /* Flag it for later restoration when link comes up */ - ifa->flags |= IFA_F_TENTATIVE; - ifa->state = INET6_IFADDR_STATE_DAD; - } else { - list_del(&ifa->if_list); - - /* clear hash table */ - spin_lock_bh(&addrconf_hash_lock); - hlist_del_init_rcu(&ifa->addr_lst); - spin_unlock_bh(&addrconf_hash_lock); - - write_unlock_bh(&idev->lock); - spin_lock_bh(&ifa->state_lock); - state = ifa->state; - ifa->state = INET6_IFADDR_STATE_DEAD; - spin_unlock_bh(&ifa->state_lock); - - if (state != INET6_IFADDR_STATE_DEAD) { - __ipv6_ifa_notify(RTM_DELADDR, ifa); - atomic_notifier_call_chain(&inet6addr_chain, - NETDEV_DOWN, ifa); - } + spin_lock_bh(&ifa->state_lock); + state = ifa->state; + ifa->state = INET6_IFADDR_STATE_DEAD; + spin_unlock_bh(&ifa->state_lock); - in6_ifa_put(ifa); - write_lock_bh(&idev->lock); + if (state != INET6_IFADDR_STATE_DEAD) { + __ipv6_ifa_notify(RTM_DELADDR, ifa); + atomic_notifier_call_chain(&inet6addr_chain, NETDEV_DOWN, ifa); } - } + in6_ifa_put(ifa); - list_splice(&keep_list, &idev->addr_list); + write_lock_bh(&idev->lock); + } write_unlock_bh(&idev->lock); @@ -4156,8 +4142,7 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) addrconf_leave_solict(ifp->idev, &ifp->addr); dst_hold(&ifp->rt->dst); - if (ifp->state == INET6_IFADDR_STATE_DEAD && - ip6_del_rt(ifp->rt)) + if (ip6_del_rt(ifp->rt)) dst_free(&ifp->rt->dst); break; } -- cgit v1.2.3 From eb3e554b4b3a56386ef5214dbe0e3935a350178b Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Mon, 24 Jan 2011 19:28:49 +0100 Subject: mac80211: fix a crash in ieee80211_beacon_get_tim on change_interface Some drivers (e.g. ath9k) do not always disable beacons when they're supposed to. When an interface is changed using the change_interface op, the mode specific sdata part is in an undefined state and trying to get a beacon at this point can produce weird crashes. To fix this, add a check for ieee80211_sdata_running before using anything from the sdata. Signed-off-by: Felix Fietkau Cc: stable@kernel.org Signed-off-by: John W. Linville --- net/mac80211/tx.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'net') diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 5950e3abead9..b64b42bc774b 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -2230,6 +2230,9 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw, sdata = vif_to_sdata(vif); + if (!ieee80211_sdata_running(sdata)) + goto out; + if (tim_offset) *tim_offset = 0; if (tim_length) -- cgit v1.2.3 From 44f5324b5d13ef2187729d949eca442689627f39 Mon Sep 17 00:00:00 2001 From: Jerry Chu Date: Tue, 25 Jan 2011 13:46:30 -0800 Subject: TCP: fix a bug that triggers large number of TCP RST by mistake This patch fixes a bug that causes TCP RST packets to be generated on otherwise correctly behaved applications, e.g., no unread data on close,..., etc. To trigger the bug, at least two conditions must be met: 1. The FIN flag is set on the last data packet, i.e., it's not on a separate, FIN only packet. 2. The size of the last data chunk on the receive side matches exactly with the size of buffer posted by the receiver, and the receiver closes the socket without any further read attempt. This bug was first noticed on our netperf based testbed for our IW10 proposal to IETF where a large number of RST packets were observed. netperf's read side code meets the condition 2 above 100%. Before the fix, tcp_data_queue() will queue the last skb that meets condition 1 to sk_receive_queue even though it has fully copied out (skb_copy_datagram_iovec()) the data. Then if condition 2 is also met, tcp_recvmsg() often returns all the copied out data successfully without actually consuming the skb, due to a check "if ((chunk = len - tp->ucopy.len) != 0) {" and "len -= chunk;" after tcp_prequeue_process() that causes "len" to become 0 and an early exit from the big while loop. I don't see any reason not to free the skb whose data have been fully consumed in tcp_data_queue(), regardless of the FIN flag. We won't get there if MSG_PEEK is on. Am I missing some arcane cases related to urgent data? Signed-off-by: H.K. Jerry Chu Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 2549b29b062d..eb7f82ebf4a3 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4399,7 +4399,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) if (!skb_copy_datagram_iovec(skb, 0, tp->ucopy.iov, chunk)) { tp->ucopy.len -= chunk; tp->copied_seq += chunk; - eaten = (chunk == skb->len && !th->fin); + eaten = (chunk == skb->len); tcp_rcv_space_adjust(sk); } local_bh_disable(); -- cgit v1.2.3 From 7cc2edb83447775a34ed3bf9d29d8295a434b523 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Wed, 26 Jan 2011 13:41:03 -0800 Subject: xfrm6: Don't forget to propagate peer into ipsec route. Like ipv4, we have to propagate the ipv6 route peer into the ipsec top-level route during instantiation. Signed-off-by: David S. Miller --- net/ipv6/xfrm6_policy.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'net') diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 7e74023ea6e4..da87428681cc 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -98,6 +98,10 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, if (!xdst->u.rt6.rt6i_idev) return -ENODEV; + xdst->u.rt6.rt6i_peer = rt->rt6i_peer; + if (rt->rt6i_peer) + atomic_inc(&rt->rt6i_peer->refcnt); + /* Sheit... I remember I did this right. Apparently, * it was magically lost, so this code needs audit */ xdst->u.rt6.rt6i_flags = rt->rt6i_flags & (RTF_ANYCAST | @@ -216,6 +220,8 @@ static void xfrm6_dst_destroy(struct dst_entry *dst) if (likely(xdst->u.rt6.rt6i_idev)) in6_dev_put(xdst->u.rt6.rt6i_idev); + if (likely(xdst->u.rt6.rt6i_peer)) + inet_putpeer(xdst->u.rt6.rt6i_peer); xfrm_dst_destroy(xdst); } -- cgit v1.2.3