From fc350777c705a39a312728ac5e8a6f164a828f5d Mon Sep 17 00:00:00 2001 From: Joerg Marx Date: Thu, 20 May 2010 15:55:30 +0200 Subject: netfilter: nf_conntrack: fix a race in __nf_conntrack_confirm against nf_ct_get_next_corpse() This race was triggered by a 'conntrack -F' command running in parallel to the insertion of a hash for a new connection. Losing this race led to a dead conntrack entry effectively blocking traffic for a particular connection until timeout or flushing the conntrack hashes again. Now the check for an already dying connection is done inside the lock. Signed-off-by: Joerg Marx Signed-off-by: Patrick McHardy --- include/net/netfilter/nf_conntrack_core.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h index dffde8e6920e..3d7524fba194 100644 --- a/include/net/netfilter/nf_conntrack_core.h +++ b/include/net/netfilter/nf_conntrack_core.h @@ -61,7 +61,7 @@ static inline int nf_conntrack_confirm(struct sk_buff *skb) int ret = NF_ACCEPT; if (ct && ct != &nf_conntrack_untracked) { - if (!nf_ct_is_confirmed(ct) && !nf_ct_is_dying(ct)) + if (!nf_ct_is_confirmed(ct)) ret = __nf_conntrack_confirm(skb); if (likely(ret == NF_ACCEPT)) nf_ct_deliver_cached_events(ct); -- cgit v1.3-8-gc7d7 From 7aecf4944f2c05aafb73b4820e469c74b4ec8517 Mon Sep 17 00:00:00 2001 From: Sjur Braendeland Date: Fri, 21 May 2010 02:16:08 +0000 Subject: caif: Bugfix - use standard Linux lists Discovered bug when running high number of parallel connect requests. Replace buggy home brewed list with linux/list.h. Signed-off-by: Sjur Braendeland Signed-off-by: David S. Miller --- include/net/caif/cfctrl.h | 4 +-- net/caif/cfctrl.c | 92 ++++++++++++++--------------------------------- 2 files changed, 28 insertions(+), 68 deletions(-) (limited to 'include/net') diff --git a/include/net/caif/cfctrl.h b/include/net/caif/cfctrl.h index 997603f2bf4c..9402543fc20d 100644 --- a/include/net/caif/cfctrl.h +++ b/include/net/caif/cfctrl.h @@ -94,8 +94,8 @@ struct cfctrl_request_info { enum cfctrl_cmd cmd; u8 channel_id; struct cfctrl_link_param param; - struct cfctrl_request_info *next; struct cflayer *client_layer; + struct list_head list; }; struct cfctrl { @@ -103,7 +103,7 @@ struct cfctrl { struct cfctrl_rsp res; atomic_t req_seq_no; atomic_t rsp_seq_no; - struct cfctrl_request_info *first_req; + struct list_head list; /* Protects from simultaneous access to first_req list */ spinlock_t info_list_lock; #ifndef CAIF_NO_LOOP diff --git a/net/caif/cfctrl.c b/net/caif/cfctrl.c index 0ffe1e1ce901..fcfda98a5e6d 100644 --- a/net/caif/cfctrl.c +++ b/net/caif/cfctrl.c @@ -44,13 +44,14 @@ struct cflayer *cfctrl_create(void) dev_info.id = 0xff; memset(this, 0, sizeof(*this)); cfsrvl_init(&this->serv, 0, &dev_info); - spin_lock_init(&this->info_list_lock); atomic_set(&this->req_seq_no, 1); atomic_set(&this->rsp_seq_no, 1); this->serv.layer.receive = cfctrl_recv; sprintf(this->serv.layer.name, "ctrl"); this->serv.layer.ctrlcmd = cfctrl_ctrlcmd; spin_lock_init(&this->loop_linkid_lock); + spin_lock_init(&this->info_list_lock); + INIT_LIST_HEAD(&this->list); this->loop_linkid = 1; return &this->serv.layer; } @@ -112,20 +113,10 @@ bool cfctrl_req_eq(struct cfctrl_request_info *r1, void cfctrl_insert_req(struct cfctrl *ctrl, struct cfctrl_request_info *req) { - struct cfctrl_request_info *p; spin_lock(&ctrl->info_list_lock); - req->next = NULL; atomic_inc(&ctrl->req_seq_no); req->sequence_no = atomic_read(&ctrl->req_seq_no); - if (ctrl->first_req == NULL) { - ctrl->first_req = req; - spin_unlock(&ctrl->info_list_lock); - return; - } - p = ctrl->first_req; - while (p->next != NULL) - p = p->next; - p->next = req; + list_add_tail(&req->list, &ctrl->list); spin_unlock(&ctrl->info_list_lock); } @@ -133,46 +124,28 @@ void cfctrl_insert_req(struct cfctrl *ctrl, struct cfctrl_request_info *cfctrl_remove_req(struct cfctrl *ctrl, struct cfctrl_request_info *req) { - struct cfctrl_request_info *p; - struct cfctrl_request_info *ret; + struct cfctrl_request_info *p, *tmp, *first; spin_lock(&ctrl->info_list_lock); - if (ctrl->first_req == NULL) { - spin_unlock(&ctrl->info_list_lock); - return NULL; - } - - if (cfctrl_req_eq(req, ctrl->first_req)) { - ret = ctrl->first_req; - caif_assert(ctrl->first_req); - atomic_set(&ctrl->rsp_seq_no, - ctrl->first_req->sequence_no); - ctrl->first_req = ctrl->first_req->next; - spin_unlock(&ctrl->info_list_lock); - return ret; - } + first = list_first_entry(&ctrl->list, struct cfctrl_request_info, list); - p = ctrl->first_req; - - while (p->next != NULL) { - if (cfctrl_req_eq(req, p->next)) { - pr_warning("CAIF: %s(): Requests are not " + list_for_each_entry_safe(p, tmp, &ctrl->list, list) { + if (cfctrl_req_eq(req, p)) { + if (p != first) + pr_warning("CAIF: %s(): Requests are not " "received in order\n", __func__); - ret = p->next; + atomic_set(&ctrl->rsp_seq_no, - p->next->sequence_no); - p->next = p->next->next; - spin_unlock(&ctrl->info_list_lock); - return ret; + p->sequence_no); + list_del(&p->list); + goto out; } - p = p->next; } + p = NULL; +out: spin_unlock(&ctrl->info_list_lock); - - pr_warning("CAIF: %s(): Request does not match\n", - __func__); - return NULL; + return p; } struct cfctrl_rsp *cfctrl_get_respfuncs(struct cflayer *layer) @@ -388,31 +361,18 @@ void cfctrl_getstartreason_req(struct cflayer *layer) void cfctrl_cancel_req(struct cflayer *layr, struct cflayer *adap_layer) { - struct cfctrl_request_info *p, *req; + struct cfctrl_request_info *p, *tmp; struct cfctrl *ctrl = container_obj(layr); spin_lock(&ctrl->info_list_lock); - - if (ctrl->first_req == NULL) { - spin_unlock(&ctrl->info_list_lock); - return; - } - - if (ctrl->first_req->client_layer == adap_layer) { - - req = ctrl->first_req; - ctrl->first_req = ctrl->first_req->next; - kfree(req); - } - - p = ctrl->first_req; - while (p != NULL && p->next != NULL) { - if (p->next->client_layer == adap_layer) { - - req = p->next; - p->next = p->next->next; - kfree(p->next); + pr_warning("CAIF: %s(): enter\n", __func__); + + list_for_each_entry_safe(p, tmp, &ctrl->list, list) { + if (p->client_layer == adap_layer) { + pr_warning("CAIF: %s(): cancel req :%d\n", __func__, + p->sequence_no); + list_del(&p->list); + kfree(p); } - p = p->next; } spin_unlock(&ctrl->info_list_lock); @@ -634,7 +594,7 @@ static void cfctrl_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl, case _CAIF_CTRLCMD_PHYIF_FLOW_OFF_IND: case CAIF_CTRLCMD_FLOW_OFF_IND: spin_lock(&this->info_list_lock); - if (this->first_req != NULL) { + if (!list_empty(&this->list)) { pr_debug("CAIF: %s(): Received flow off in " "control layer", __func__); } -- cgit v1.3-8-gc7d7 From f845172531fb7410c7fb7780b1a6e51ee6df7d52 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Mon, 24 May 2010 00:12:34 -0700 Subject: cls_cgroup: Store classid in struct sock Up until now cls_cgroup has relied on fetching the classid out of the current executing thread. This runs into trouble when a packet processing is delayed in which case it may execute out of another thread's context. Furthermore, even when a packet is not delayed we may fail to classify it if soft IRQs have been disabled, because this scenario is indistinguishable from one where a packet unrelated to the current thread is processed by a real soft IRQ. In fact, the current semantics is inherently broken, as a single skb may be constructed out of the writes of two different tasks. A different manifestation of this problem is when the TCP stack transmits in response of an incoming ACK. This is currently unclassified. As we already have a concept of packet ownership for accounting purposes in the skb->sk pointer, this is a natural place to store the classid in a persistent manner. This patch adds the cls_cgroup classid in struct sock, filling up an existing hole on 64-bit :) The value is set at socket creation time. So all sockets created via socket(2) automatically gains the ID of the thread creating it. Whenever another process touches the socket by either reading or writing to it, we will change the socket classid to that of the process if it has a valid (non-zero) classid. For sockets created on inbound connections through accept(2), we inherit the classid of the original listening socket through sk_clone, possibly preceding the actual accept(2) call. In order to minimise risks, I have not made this the authoritative classid. For now it is only used as a backup when we execute with soft IRQs disabled. Once we're completely happy with its semantics we can use it as the sole classid. Footnote: I have rearranged the error path on cls_group module creation. If we didn't do this, then there is a window where someone could create a tc rule using cls_group before the cgroup subsystem has been registered. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/net/cls_cgroup.h | 63 ++++++++++++++++++++++++++++++++++++++++++++++++ include/net/sock.h | 10 +++++++- net/core/sock.c | 18 ++++++++++++++ net/sched/cls_cgroup.c | 50 ++++++++++++++++++++++++++------------ net/socket.c | 9 +++++++ 5 files changed, 133 insertions(+), 17 deletions(-) create mode 100644 include/net/cls_cgroup.h (limited to 'include/net') diff --git a/include/net/cls_cgroup.h b/include/net/cls_cgroup.h new file mode 100644 index 000000000000..ef2df1475b51 --- /dev/null +++ b/include/net/cls_cgroup.h @@ -0,0 +1,63 @@ +/* + * cls_cgroup.h Control Group Classifier + * + * Authors: Thomas Graf + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation; either version 2 of the License, or (at your option) + * any later version. + * + */ + +#ifndef _NET_CLS_CGROUP_H +#define _NET_CLS_CGROUP_H + +#include +#include +#include + +#ifdef CONFIG_CGROUPS +struct cgroup_cls_state +{ + struct cgroup_subsys_state css; + u32 classid; +}; + +#ifdef CONFIG_NET_CLS_CGROUP +static inline u32 task_cls_classid(struct task_struct *p) +{ + if (in_interrupt()) + return 0; + + return container_of(task_subsys_state(p, net_cls_subsys_id), + struct cgroup_cls_state, css).classid; +} +#else +extern int net_cls_subsys_id; + +static inline u32 task_cls_classid(struct task_struct *p) +{ + int id; + u32 classid; + + if (in_interrupt()) + return 0; + + rcu_read_lock(); + id = rcu_dereference(net_cls_subsys_id); + if (id >= 0) + classid = container_of(task_subsys_state(p, id), + struct cgroup_cls_state, css)->classid; + rcu_read_unlock(); + + return classid; +} +#endif +#else +static inline u32 task_cls_classid(struct task_struct *p) +{ + return 0; +} +#endif +#endif /* _NET_CLS_CGROUP_H */ diff --git a/include/net/sock.h b/include/net/sock.h index 5697caf8cc76..d24f382cb712 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -312,7 +312,7 @@ struct sock { void *sk_security; #endif __u32 sk_mark; - /* XXX 4 bytes hole on 64 bit */ + u32 sk_classid; void (*sk_state_change)(struct sock *sk); void (*sk_data_ready)(struct sock *sk, int bytes); void (*sk_write_space)(struct sock *sk); @@ -1074,6 +1074,14 @@ extern void *sock_kmalloc(struct sock *sk, int size, extern void sock_kfree_s(struct sock *sk, void *mem, int size); extern void sk_send_sigurg(struct sock *sk); +#ifdef CONFIG_CGROUPS +extern void sock_update_classid(struct sock *sk); +#else +static inline void sock_update_classid(struct sock *sk) +{ +} +#endif + /* * Functions to fill in entries in struct proto_ops when a protocol * does not implement a particular function. diff --git a/net/core/sock.c b/net/core/sock.c index bf88a167c8f2..a05ae7f9771e 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -123,6 +123,7 @@ #include #include #include +#include #include @@ -217,6 +218,11 @@ __u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX; int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512); EXPORT_SYMBOL(sysctl_optmem_max); +#if defined(CONFIG_CGROUPS) && !defined(CONFIG_NET_CLS_CGROUP) +int net_cls_subsys_id = -1; +EXPORT_SYMBOL_GPL(net_cls_subsys_id); +#endif + static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen) { struct timeval tv; @@ -1050,6 +1056,16 @@ static void sk_prot_free(struct proto *prot, struct sock *sk) module_put(owner); } +#ifdef CONFIG_CGROUPS +void sock_update_classid(struct sock *sk) +{ + u32 classid = task_cls_classid(current); + + if (classid && classid != sk->sk_classid) + sk->sk_classid = classid; +} +#endif + /** * sk_alloc - All socket objects are allocated here * @net: the applicable net namespace @@ -1073,6 +1089,8 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority, sock_lock_init(sk); sock_net_set(sk, get_net(net)); atomic_set(&sk->sk_wmem_alloc, 1); + + sock_update_classid(sk); } return sk; diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c index 221180384fd7..78ef2c5e130b 100644 --- a/net/sched/cls_cgroup.c +++ b/net/sched/cls_cgroup.c @@ -16,14 +16,11 @@ #include #include #include +#include #include #include - -struct cgroup_cls_state -{ - struct cgroup_subsys_state css; - u32 classid; -}; +#include +#include static struct cgroup_subsys_state *cgrp_create(struct cgroup_subsys *ss, struct cgroup *cgrp); @@ -112,6 +109,10 @@ static int cls_cgroup_classify(struct sk_buff *skb, struct tcf_proto *tp, struct cls_cgroup_head *head = tp->root; u32 classid; + rcu_read_lock(); + classid = task_cls_state(current)->classid; + rcu_read_unlock(); + /* * Due to the nature of the classifier it is required to ignore all * packets originating from softirq context as accessing `current' @@ -122,12 +123,12 @@ static int cls_cgroup_classify(struct sk_buff *skb, struct tcf_proto *tp, * calls by looking at the number of nested bh disable calls because * softirqs always disables bh. */ - if (softirq_count() != SOFTIRQ_OFFSET) - return -1; - - rcu_read_lock(); - classid = task_cls_state(current)->classid; - rcu_read_unlock(); + if (softirq_count() != SOFTIRQ_OFFSET) { + /* If there is an sk_classid we'll use that. */ + if (!skb->sk) + return -1; + classid = skb->sk->sk_classid; + } if (!classid) return -1; @@ -289,18 +290,35 @@ static struct tcf_proto_ops cls_cgroup_ops __read_mostly = { static int __init init_cgroup_cls(void) { - int ret = register_tcf_proto_ops(&cls_cgroup_ops); - if (ret) - return ret; + int ret; + ret = cgroup_load_subsys(&net_cls_subsys); if (ret) - unregister_tcf_proto_ops(&cls_cgroup_ops); + goto out; + +#ifndef CONFIG_NET_CLS_CGROUP + /* We can't use rcu_assign_pointer because this is an int. */ + smp_wmb(); + net_cls_subsys_id = net_cls_subsys.subsys_id; +#endif + + ret = register_tcf_proto_ops(&cls_cgroup_ops); + if (ret) + cgroup_unload_subsys(&net_cls_subsys); + +out: return ret; } static void __exit exit_cgroup_cls(void) { unregister_tcf_proto_ops(&cls_cgroup_ops); + +#ifndef CONFIG_NET_CLS_CGROUP + net_cls_subsys_id = -1; + synchronize_rcu(); +#endif + cgroup_unload_subsys(&net_cls_subsys); } diff --git a/net/socket.c b/net/socket.c index f9f7d0872cac..367d5477d00f 100644 --- a/net/socket.c +++ b/net/socket.c @@ -94,6 +94,7 @@ #include #include +#include #include #include @@ -558,6 +559,8 @@ static inline int __sock_sendmsg(struct kiocb *iocb, struct socket *sock, struct sock_iocb *si = kiocb_to_siocb(iocb); int err; + sock_update_classid(sock->sk); + si->sock = sock; si->scm = NULL; si->msg = msg; @@ -684,6 +687,8 @@ static inline int __sock_recvmsg_nosec(struct kiocb *iocb, struct socket *sock, { struct sock_iocb *si = kiocb_to_siocb(iocb); + sock_update_classid(sock->sk); + si->sock = sock; si->scm = NULL; si->msg = msg; @@ -777,6 +782,8 @@ static ssize_t sock_splice_read(struct file *file, loff_t *ppos, if (unlikely(!sock->ops->splice_read)) return -EINVAL; + sock_update_classid(sock->sk); + return sock->ops->splice_read(sock, ppos, pipe, len, flags); } @@ -3069,6 +3076,8 @@ int kernel_setsockopt(struct socket *sock, int level, int optname, int kernel_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags) { + sock_update_classid(sock->sk); + if (sock->ops->sendpage) return sock->ops->sendpage(sock, page, offset, size, flags); -- cgit v1.3-8-gc7d7 From 3dc3fc52ea1537f5f37ab301d2b1468a0e79988f Mon Sep 17 00:00:00 2001 From: "John W. Linville" Date: Mon, 24 May 2010 13:36:37 -0400 Subject: Revert "ath9k: Group Key fix for VAPs" This reverts commit 03ceedea972a82d343fa5c2528b3952fa9e615d5. This patch was reported to cause a regression in which connectivity is lost and cannot be reestablished after a suspend/resume cycle. Signed-off-by: John W. Linville --- drivers/net/wireless/ath/ath9k/main.c | 28 +++------------------------- include/net/mac80211.h | 1 - net/mac80211/key.c | 1 - 3 files changed, 3 insertions(+), 27 deletions(-) (limited to 'include/net') diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c index 893b552981a0..abfa0493236f 100644 --- a/drivers/net/wireless/ath/ath9k/main.c +++ b/drivers/net/wireless/ath/ath9k/main.c @@ -752,7 +752,6 @@ static int ath_key_config(struct ath_common *common, struct ath_hw *ah = common->ah; struct ath9k_keyval hk; const u8 *mac = NULL; - u8 gmac[ETH_ALEN]; int ret = 0; int idx; @@ -776,30 +775,9 @@ static int ath_key_config(struct ath_common *common, memcpy(hk.kv_val, key->key, key->keylen); if (!(key->flags & IEEE80211_KEY_FLAG_PAIRWISE)) { - - if (key->ap_addr) { - /* - * Group keys on hardware that supports multicast frame - * key search use a mac that is the sender's address with - * the high bit set instead of the app-specified address. - */ - memcpy(gmac, key->ap_addr, ETH_ALEN); - gmac[0] |= 0x80; - mac = gmac; - - if (key->alg == ALG_TKIP) - idx = ath_reserve_key_cache_slot_tkip(common); - else - idx = ath_reserve_key_cache_slot(common); - if (idx < 0) - mac = NULL; /* no free key cache entries */ - } - - if (!mac) { - /* For now, use the default keys for broadcast keys. This may - * need to change with virtual interfaces. */ - idx = key->keyidx; - } + /* For now, use the default keys for broadcast keys. This may + * need to change with virtual interfaces. */ + idx = key->keyidx; } else if (key->keyidx) { if (WARN_ON(!sta)) return -EOPNOTSUPP; diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 5be900d19660..e24b0363e6cb 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -831,7 +831,6 @@ struct ieee80211_key_conf { u8 iv_len; u8 hw_key_idx; u8 flags; - u8 *ap_addr; s8 keyidx; u8 keylen; u8 key[0]; diff --git a/net/mac80211/key.c b/net/mac80211/key.c index 8d4b41787dcf..e8f6e3b252d8 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -140,7 +140,6 @@ static void ieee80211_key_enable_hw_accel(struct ieee80211_key *key) struct ieee80211_sub_if_data, u.ap); - key->conf.ap_addr = sdata->dev->dev_addr; ret = drv_set_key(key->local, SET_KEY, sdata, sta, &key->conf); if (!ret) { -- cgit v1.3-8-gc7d7 From 4e8998f09bd777f99ea3dae6f87f2c367979e6c0 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 21 May 2010 11:28:33 -0700 Subject: wireless: fix mac80211.h kernel-doc warnings Fix kernel-doc warnings in mac80211.h: Warning(include/net/mac80211.h:838): No description found for parameter 'ap_addr' Warning(include/net/mac80211.h:1726): No description found for parameter 'get_survey' Signed-off-by: Randy Dunlap Signed-off-by: John W. Linville --- include/net/mac80211.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index e24b0363e6cb..de22cbfef232 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -815,6 +815,7 @@ enum ieee80211_key_flags { * encrypted in hardware. * @alg: The key algorithm. * @flags: key flags, see &enum ieee80211_key_flags. + * @ap_addr: AP's MAC address * @keyidx: the key index (0-3) * @keylen: key material length * @key: key material. For ALG_TKIP the key is encoded as a 256-bit (32 byte) @@ -1637,6 +1638,8 @@ enum ieee80211_ampdu_mlme_action { * Returns a negative error code on failure. * The callback must be atomic. * + * @get_survey: Return per-channel survey information + * * @rfkill_poll: Poll rfkill hardware state. If you need this, you also * need to set wiphy->rfkill_poll to %true before registration, * and need to call wiphy_rfkill_set_hw_state() in the callback. -- cgit v1.3-8-gc7d7 From 937eada45fa7bd233dfa59bbd8c0b436b02b6491 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Mon, 24 May 2010 23:53:37 -0700 Subject: cls_cgroup: Fix build error when built-in There is a typo in cgroup_cls_state when cls_cgroup is built-in. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/net/cls_cgroup.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/cls_cgroup.h b/include/net/cls_cgroup.h index ef2df1475b51..6cf44866cecd 100644 --- a/include/net/cls_cgroup.h +++ b/include/net/cls_cgroup.h @@ -31,7 +31,7 @@ static inline u32 task_cls_classid(struct task_struct *p) return 0; return container_of(task_subsys_state(p, net_cls_subsys_id), - struct cgroup_cls_state, css).classid; + struct cgroup_cls_state, css)->classid; } #else extern int net_cls_subsys_id; -- cgit v1.3-8-gc7d7 From acfbe96a3035639619a6533e04d88ed4ef9ccb61 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 24 May 2010 23:54:18 -0700 Subject: sock.h: fix kernel-doc warning Fix sock.h kernel-doc warning: Warning(include/net/sock.h:1438): No description found for parameter 'wq' Signed-off-by: Randy Dunlap Signed-off-by: David S. Miller --- include/net/sock.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/sock.h b/include/net/sock.h index d24f382cb712..d2a71b04a5ae 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1412,7 +1412,7 @@ static inline int sk_has_allocations(const struct sock *sk) /** * wq_has_sleeper - check if there are any waiting processes - * @sk: struct socket_wq + * @wq: struct socket_wq * * Returns true if socket_wq has waiting processes * -- cgit v1.3-8-gc7d7 From 4be929be34f9bdeffa40d815d32d7d60d2c7f03b Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Mon, 24 May 2010 14:33:03 -0700 Subject: kernel-wide: replace USHORT_MAX, SHORT_MAX and SHORT_MIN with USHRT_MAX, SHRT_MAX and SHRT_MIN - C99 knows about USHRT_MAX/SHRT_MAX/SHRT_MIN, not USHORT_MAX/SHORT_MAX/SHORT_MIN. - Make SHRT_MIN of type s16, not int, for consistency. [akpm@linux-foundation.org: fix drivers/dma/timb_dma.c] [akpm@linux-foundation.org: fix security/keys/keyring.c] Signed-off-by: Alexey Dobriyan Acked-by: WANG Cong Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/dma/timb_dma.c | 2 +- drivers/scsi/fcoe/fcoe.c | 2 +- drivers/scsi/mpt2sas/mpt2sas_base.c | 2 +- drivers/scsi/mpt2sas/mpt2sas_config.c | 2 +- drivers/vhost/vhost.c | 2 +- fs/nfs/super.c | 4 ++-- fs/nfsd/nfsctl.c | 4 ++-- fs/ocfs2/blockcheck.c | 4 ++-- include/linux/kernel.h | 6 +++--- include/linux/sched.h | 2 +- include/net/ip.h | 6 +++--- include/net/ipv6.h | 6 +++--- ipc/msg.c | 12 ++++++------ ipc/util.c | 4 ++-- lib/vsprintf.c | 2 +- net/9p/protocol.c | 2 +- net/dccp/options.c | 2 +- net/ipv4/udp.c | 8 ++++---- net/mac80211/sta_info.c | 2 +- net/sunrpc/rpcb_clnt.c | 2 +- security/keys/keyring.c | 6 +++--- 21 files changed, 41 insertions(+), 41 deletions(-) (limited to 'include/net') diff --git a/drivers/dma/timb_dma.c b/drivers/dma/timb_dma.c index 0172fa3c7a2b..a1bf77c1993f 100644 --- a/drivers/dma/timb_dma.c +++ b/drivers/dma/timb_dma.c @@ -188,7 +188,7 @@ static void __td_unmap_descs(struct timb_dma_desc *td_desc, bool single) static int td_fill_desc(struct timb_dma_chan *td_chan, u8 *dma_desc, struct scatterlist *sg, bool last) { - if (sg_dma_len(sg) > USHORT_MAX) { + if (sg_dma_len(sg) > USHRT_MAX) { dev_err(chan2dev(&td_chan->chan), "Too big sg element\n"); return -EINVAL; } diff --git a/drivers/scsi/fcoe/fcoe.c b/drivers/scsi/fcoe/fcoe.c index 9276121db1ef..44a07593de56 100644 --- a/drivers/scsi/fcoe/fcoe.c +++ b/drivers/scsi/fcoe/fcoe.c @@ -688,7 +688,7 @@ static int fcoe_shost_config(struct fc_lport *lport, struct device *dev) } if (!lport->vport) - fc_host_max_npiv_vports(lport->host) = USHORT_MAX; + fc_host_max_npiv_vports(lport->host) = USHRT_MAX; snprintf(fc_host_symbolic_name(lport->host), FC_SYMBOLIC_NAME_SIZE, "%s v%s over %s", FCOE_NAME, FCOE_VERSION, diff --git a/drivers/scsi/mpt2sas/mpt2sas_base.c b/drivers/scsi/mpt2sas/mpt2sas_base.c index b830d61684dd..0ec1ed389c20 100644 --- a/drivers/scsi/mpt2sas/mpt2sas_base.c +++ b/drivers/scsi/mpt2sas/mpt2sas_base.c @@ -3757,7 +3757,7 @@ _base_reset_handler(struct MPT2SAS_ADAPTER *ioc, int reset_phase) if (ioc->config_cmds.status & MPT2_CMD_PENDING) { ioc->config_cmds.status |= MPT2_CMD_RESET; mpt2sas_base_free_smid(ioc, ioc->config_cmds.smid); - ioc->config_cmds.smid = USHORT_MAX; + ioc->config_cmds.smid = USHRT_MAX; complete(&ioc->config_cmds.done); } break; diff --git a/drivers/scsi/mpt2sas/mpt2sas_config.c b/drivers/scsi/mpt2sas/mpt2sas_config.c index e762dd3e2fcb..c65442982d7b 100644 --- a/drivers/scsi/mpt2sas/mpt2sas_config.c +++ b/drivers/scsi/mpt2sas/mpt2sas_config.c @@ -258,7 +258,7 @@ mpt2sas_config_done(struct MPT2SAS_ADAPTER *ioc, u16 smid, u8 msix_index, #ifdef CONFIG_SCSI_MPT2SAS_LOGGING _config_display_some_debug(ioc, smid, "config_done", mpi_reply); #endif - ioc->config_cmds.smid = USHORT_MAX; + ioc->config_cmds.smid = USHRT_MAX; complete(&ioc->config_cmds.done); return 1; } diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 750effe0f98b..c6fb8e968f21 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -806,7 +806,7 @@ static unsigned get_indirect(struct vhost_dev *dev, struct vhost_virtqueue *vq, count = indirect->len / sizeof desc; /* Buffers are chained via a 16 bit next field, so * we can have at most 2^16 of these. */ - if (count > USHORT_MAX + 1) { + if (count > USHRT_MAX + 1) { vq_err(vq, "Indirect buffer length too big: %d\n", indirect->len); return -E2BIG; diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 2f8b1157daa2..04214fc5c304 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -1060,7 +1060,7 @@ static int nfs_parse_mount_options(char *raw, goto out_nomem; rc = strict_strtoul(string, 10, &option); kfree(string); - if (rc != 0 || option > USHORT_MAX) + if (rc != 0 || option > USHRT_MAX) goto out_invalid_value; mnt->nfs_server.port = option; break; @@ -1181,7 +1181,7 @@ static int nfs_parse_mount_options(char *raw, goto out_nomem; rc = strict_strtoul(string, 10, &option); kfree(string); - if (rc != 0 || option > USHORT_MAX) + if (rc != 0 || option > USHRT_MAX) goto out_invalid_value; mnt->mount_server.port = option; break; diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index bc3194ea01f5..508941c23af7 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -998,7 +998,7 @@ static ssize_t __write_ports_addxprt(char *buf) if (sscanf(buf, "%15s %4u", transport, &port) != 2) return -EINVAL; - if (port < 1 || port > USHORT_MAX) + if (port < 1 || port > USHRT_MAX) return -EINVAL; err = nfsd_create_serv(); @@ -1040,7 +1040,7 @@ static ssize_t __write_ports_delxprt(char *buf) if (sscanf(&buf[1], "%15s %4u", transport, &port) != 2) return -EINVAL; - if (port < 1 || port > USHORT_MAX || nfsd_serv == NULL) + if (port < 1 || port > USHRT_MAX || nfsd_serv == NULL) return -EINVAL; xprt = svc_find_xprt(nfsd_serv, transport, AF_UNSPEC, port); diff --git a/fs/ocfs2/blockcheck.c b/fs/ocfs2/blockcheck.c index b7428c5d0d3b..ec6d12339593 100644 --- a/fs/ocfs2/blockcheck.c +++ b/fs/ocfs2/blockcheck.c @@ -403,7 +403,7 @@ void ocfs2_block_check_compute(void *data, size_t blocksize, * No ecc'd ocfs2 structure is larger than 4K, so ecc will be no * larger than 16 bits. */ - BUG_ON(ecc > USHORT_MAX); + BUG_ON(ecc > USHRT_MAX); bc->bc_crc32e = cpu_to_le32(crc); bc->bc_ecc = cpu_to_le16((u16)ecc); @@ -508,7 +508,7 @@ void ocfs2_block_check_compute_bhs(struct buffer_head **bhs, int nr, * No ecc'd ocfs2 structure is larger than 4K, so ecc will be no * larger than 16 bits. */ - BUG_ON(ecc > USHORT_MAX); + BUG_ON(ecc > USHRT_MAX); bc->bc_crc32e = cpu_to_le32(crc); bc->bc_ecc = cpu_to_le16((u16)ecc); diff --git a/include/linux/kernel.h b/include/linux/kernel.h index cc5e3ffe9fce..a2e7c32e17e7 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -24,9 +24,9 @@ extern const char linux_banner[]; extern const char linux_proc_banner[]; -#define USHORT_MAX ((u16)(~0U)) -#define SHORT_MAX ((s16)(USHORT_MAX>>1)) -#define SHORT_MIN (-SHORT_MAX - 1) +#define USHRT_MAX ((u16)(~0U)) +#define SHRT_MAX ((s16)(USHRT_MAX>>1)) +#define SHRT_MIN ((s16)(-SHRT_MAX - 1)) #define INT_MAX ((int)(~0U>>1)) #define INT_MIN (-INT_MAX - 1) #define UINT_MAX (~0U) diff --git a/include/linux/sched.h b/include/linux/sched.h index 415b8f8a3f45..c0151ffd3541 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -384,7 +384,7 @@ struct user_namespace; * 1-3 now and depends on arch. We use "5" as safe margin, here. */ #define MAPCOUNT_ELF_CORE_MARGIN (5) -#define DEFAULT_MAX_MAP_COUNT (USHORT_MAX - MAPCOUNT_ELF_CORE_MARGIN) +#define DEFAULT_MAX_MAP_COUNT (USHRT_MAX - MAPCOUNT_ELF_CORE_MARGIN) extern int sysctl_max_map_count; diff --git a/include/net/ip.h b/include/net/ip.h index 63548f0a44b1..452f229c380a 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -358,11 +358,11 @@ enum ip_defrag_users { IP_DEFRAG_LOCAL_DELIVER, IP_DEFRAG_CALL_RA_CHAIN, IP_DEFRAG_CONNTRACK_IN, - __IP_DEFRAG_CONNTRACK_IN_END = IP_DEFRAG_CONNTRACK_IN + USHORT_MAX, + __IP_DEFRAG_CONNTRACK_IN_END = IP_DEFRAG_CONNTRACK_IN + USHRT_MAX, IP_DEFRAG_CONNTRACK_OUT, - __IP_DEFRAG_CONNTRACK_OUT_END = IP_DEFRAG_CONNTRACK_OUT + USHORT_MAX, + __IP_DEFRAG_CONNTRACK_OUT_END = IP_DEFRAG_CONNTRACK_OUT + USHRT_MAX, IP_DEFRAG_CONNTRACK_BRIDGE_IN, - __IP_DEFRAG_CONNTRACK_BRIDGE_IN = IP_DEFRAG_CONNTRACK_BRIDGE_IN + USHORT_MAX, + __IP_DEFRAG_CONNTRACK_BRIDGE_IN = IP_DEFRAG_CONNTRACK_BRIDGE_IN + USHRT_MAX, IP_DEFRAG_VS_IN, IP_DEFRAG_VS_OUT, IP_DEFRAG_VS_FWD diff --git a/include/net/ipv6.h b/include/net/ipv6.h index eba5cc00325a..2600b69757b8 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -354,11 +354,11 @@ struct inet_frag_queue; enum ip6_defrag_users { IP6_DEFRAG_LOCAL_DELIVER, IP6_DEFRAG_CONNTRACK_IN, - __IP6_DEFRAG_CONNTRACK_IN = IP6_DEFRAG_CONNTRACK_IN + USHORT_MAX, + __IP6_DEFRAG_CONNTRACK_IN = IP6_DEFRAG_CONNTRACK_IN + USHRT_MAX, IP6_DEFRAG_CONNTRACK_OUT, - __IP6_DEFRAG_CONNTRACK_OUT = IP6_DEFRAG_CONNTRACK_OUT + USHORT_MAX, + __IP6_DEFRAG_CONNTRACK_OUT = IP6_DEFRAG_CONNTRACK_OUT + USHRT_MAX, IP6_DEFRAG_CONNTRACK_BRIDGE_IN, - __IP6_DEFRAG_CONNTRACK_BRIDGE_IN = IP6_DEFRAG_CONNTRACK_BRIDGE_IN + USHORT_MAX, + __IP6_DEFRAG_CONNTRACK_BRIDGE_IN = IP6_DEFRAG_CONNTRACK_BRIDGE_IN + USHRT_MAX, }; struct ip6_create_arg { diff --git a/ipc/msg.c b/ipc/msg.c index 9547cb7ac313..747b65507a91 100644 --- a/ipc/msg.c +++ b/ipc/msg.c @@ -345,19 +345,19 @@ copy_msqid_to_user(void __user *buf, struct msqid64_ds *in, int version) out.msg_rtime = in->msg_rtime; out.msg_ctime = in->msg_ctime; - if (in->msg_cbytes > USHORT_MAX) - out.msg_cbytes = USHORT_MAX; + if (in->msg_cbytes > USHRT_MAX) + out.msg_cbytes = USHRT_MAX; else out.msg_cbytes = in->msg_cbytes; out.msg_lcbytes = in->msg_cbytes; - if (in->msg_qnum > USHORT_MAX) - out.msg_qnum = USHORT_MAX; + if (in->msg_qnum > USHRT_MAX) + out.msg_qnum = USHRT_MAX; else out.msg_qnum = in->msg_qnum; - if (in->msg_qbytes > USHORT_MAX) - out.msg_qbytes = USHORT_MAX; + if (in->msg_qbytes > USHRT_MAX) + out.msg_qbytes = USHRT_MAX; else out.msg_qbytes = in->msg_qbytes; out.msg_lqbytes = in->msg_qbytes; diff --git a/ipc/util.c b/ipc/util.c index 79ce84e890f7..69a0cc13d966 100644 --- a/ipc/util.c +++ b/ipc/util.c @@ -124,8 +124,8 @@ void ipc_init_ids(struct ipc_ids *ids) ids->seq = 0; { int seq_limit = INT_MAX/SEQ_MULTIPLIER; - if (seq_limit > USHORT_MAX) - ids->seq_max = USHORT_MAX; + if (seq_limit > USHRT_MAX) + ids->seq_max = USHRT_MAX; else ids->seq_max = seq_limit; } diff --git a/lib/vsprintf.c b/lib/vsprintf.c index 46d34b0b74a8..20c95121d8a1 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -1980,7 +1980,7 @@ int vsscanf(const char *buf, const char *fmt, va_list args) { char *s = (char *)va_arg(args, char *); if (field_width == -1) - field_width = SHORT_MAX; + field_width = SHRT_MAX; /* first, skip leading white space in buffer */ str = skip_spaces(str); diff --git a/net/9p/protocol.c b/net/9p/protocol.c index 77d3aab4036b..149f82160130 100644 --- a/net/9p/protocol.c +++ b/net/9p/protocol.c @@ -394,7 +394,7 @@ p9pdu_vwritef(struct p9_fcall *pdu, int proto_version, const char *fmt, const char *sptr = va_arg(ap, const char *); int16_t len = 0; if (sptr) - len = MIN(strlen(sptr), USHORT_MAX); + len = MIN(strlen(sptr), USHRT_MAX); errcode = p9pdu_writef(pdu, proto_version, "w", len); diff --git a/net/dccp/options.c b/net/dccp/options.c index 1b08cae9c65b..07395f861d35 100644 --- a/net/dccp/options.c +++ b/net/dccp/options.c @@ -296,7 +296,7 @@ static inline u8 dccp_ndp_len(const u64 ndp) { if (likely(ndp <= 0xFF)) return 1; - return likely(ndp <= USHORT_MAX) ? 2 : (ndp <= UINT_MAX ? 4 : 6); + return likely(ndp <= USHRT_MAX) ? 2 : (ndp <= UINT_MAX ? 4 : 6); } int dccp_insert_option(struct sock *sk, struct sk_buff *skb, diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 9de6a698f91d..baeec29fe0f1 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1686,8 +1686,8 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, return -ENOPROTOOPT; if (val != 0 && val < 8) /* Illegal coverage: use default (8) */ val = 8; - else if (val > USHORT_MAX) - val = USHORT_MAX; + else if (val > USHRT_MAX) + val = USHRT_MAX; up->pcslen = val; up->pcflag |= UDPLITE_SEND_CC; break; @@ -1700,8 +1700,8 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, return -ENOPROTOOPT; if (val != 0 && val < 8) /* Avoid silly minimal values. */ val = 8; - else if (val > USHORT_MAX) - val = USHORT_MAX; + else if (val > USHRT_MAX) + val = USHRT_MAX; up->pcrlen = val; up->pcflag |= UDPLITE_RECV_CC; break; diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 730197591ab5..ba9360a475b0 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -259,7 +259,7 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, skb_queue_head_init(&sta->tx_filtered); for (i = 0; i < NUM_RX_DATA_QUEUES; i++) - sta->last_seq_ctrl[i] = cpu_to_le16(USHORT_MAX); + sta->last_seq_ctrl[i] = cpu_to_le16(USHRT_MAX); #ifdef CONFIG_MAC80211_VERBOSE_DEBUG printk(KERN_DEBUG "%s: Allocated STA %pM\n", diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index 121105355f60..dac219a56ae1 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -783,7 +783,7 @@ static int rpcb_dec_getport(struct rpc_rqst *req, __be32 *p, port = ntohl(*p); dprintk("RPC: %5u PMAP_%s result: %lu\n", task->tk_pid, task->tk_msg.rpc_proc->p_name, port); - if (unlikely(port > USHORT_MAX)) + if (unlikely(port > USHRT_MAX)) return -EIO; rpcb->r_port = port; diff --git a/security/keys/keyring.c b/security/keys/keyring.c index ef03a82a0135..d37f713e73ce 100644 --- a/security/keys/keyring.c +++ b/security/keys/keyring.c @@ -669,7 +669,7 @@ static void keyring_unlink_rcu_disposal(struct rcu_head *rcu) struct keyring_list *klist = container_of(rcu, struct keyring_list, rcu); - if (klist->delkey != USHORT_MAX) + if (klist->delkey != USHRT_MAX) key_put(klist->keys[klist->delkey]); kfree(klist); } @@ -746,7 +746,7 @@ int __key_link_begin(struct key *keyring, const struct key_type *type, max += klist->maxkeys; ret = -ENFILE; - if (max > USHORT_MAX - 1) + if (max > USHRT_MAX - 1) goto error_quota; size = sizeof(*klist) + sizeof(struct key *) * max; if (size > PAGE_SIZE) @@ -763,7 +763,7 @@ int __key_link_begin(struct key *keyring, const struct key_type *type, sizeof(struct key *) * klist->nkeys); nklist->delkey = klist->nkeys; nklist->nkeys = klist->nkeys + 1; - klist->delkey = USHORT_MAX; + klist->delkey = USHRT_MAX; } else { nklist->nkeys = 1; nklist->delkey = 0; -- cgit v1.3-8-gc7d7 From ea16f912a6ad9fe43131a2e2a108f089c432d510 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Tue, 25 May 2010 18:53:57 -0700 Subject: cls_cgroup: Initialise classid when module is absent When the cls_cgroup module is not loaded, task_cls_classid will return an uninitialised classid instead of zero. Reported-by: Stephen Rothwell Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/net/cls_cgroup.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/cls_cgroup.h b/include/net/cls_cgroup.h index 6cf44866cecd..726cc3536409 100644 --- a/include/net/cls_cgroup.h +++ b/include/net/cls_cgroup.h @@ -39,7 +39,7 @@ extern int net_cls_subsys_id; static inline u32 task_cls_classid(struct task_struct *p) { int id; - u32 classid; + u32 classid = 0; if (in_interrupt()) return 0; -- cgit v1.3-8-gc7d7 From ff937938e7781b2c1bffce0a5400af308e3946d5 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 26 May 2010 00:40:11 -0700 Subject: sctp: dubious bitfields in sctp_transport Sparse complains because these one-bit bitfields are signed. include/net/sctp/structs.h:879:24: error: dubious one-bit signed bitfield include/net/sctp/structs.h:889:31: error: dubious one-bit signed bitfield include/net/sctp/structs.h:895:26: error: dubious one-bit signed bitfield include/net/sctp/structs.h:898:31: error: dubious one-bit signed bitfield include/net/sctp/structs.h:901:27: error: dubious one-bit signed bitfield It doesn't cause a problem in the current code, but it would be better to clean it up. This was introduced by c0058a35aacc7: "sctp: Save some room in the sctp_transport by using bitfields". Signed-off-by: Dan Carpenter Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 6173c619913a..4b860116e096 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -876,7 +876,7 @@ struct sctp_transport { /* Reference counting. */ atomic_t refcnt; - int dead:1, + __u32 dead:1, /* RTO-Pending : A flag used to track if one of the DATA * chunks sent to this address is currently being * used to compute a RTT. If this flag is 0, -- cgit v1.3-8-gc7d7 From 8a74ad60a546b13bd1096b2a61a7a5c6fd9ae17c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 26 May 2010 19:20:18 +0000 Subject: net: fix lock_sock_bh/unlock_sock_bh This new sock lock primitive was introduced to speedup some user context socket manipulation. But it is unsafe to protect two threads, one using regular lock_sock/release_sock, one using lock_sock_bh/unlock_sock_bh This patch changes lock_sock_bh to be careful against 'owned' state. If owned is found to be set, we must take the slow path. lock_sock_bh() now returns a boolean to say if the slow path was taken, and this boolean is used at unlock_sock_bh time to call the appropriate unlock function. After this change, BH are either disabled or enabled during the lock_sock_bh/unlock_sock_bh protected section. This might be misleading, so we rename these functions to lock_sock_fast()/unlock_sock_fast(). Reported-by: Anton Blanchard Signed-off-by: Eric Dumazet Tested-by: Anton Blanchard Signed-off-by: David S. Miller --- include/net/sock.h | 20 ++++++++++++++------ net/core/datagram.c | 6 ++++-- net/core/sock.c | 33 +++++++++++++++++++++++++++++++++ net/ipv4/udp.c | 14 ++++++++------ net/ipv6/udp.c | 5 +++-- 5 files changed, 62 insertions(+), 16 deletions(-) (limited to 'include/net') diff --git a/include/net/sock.h b/include/net/sock.h index d2a71b04a5ae..ca241ea14875 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1026,15 +1026,23 @@ extern void release_sock(struct sock *sk); SINGLE_DEPTH_NESTING) #define bh_unlock_sock(__sk) spin_unlock(&((__sk)->sk_lock.slock)) -static inline void lock_sock_bh(struct sock *sk) +extern bool lock_sock_fast(struct sock *sk); +/** + * unlock_sock_fast - complement of lock_sock_fast + * @sk: socket + * @slow: slow mode + * + * fast unlock socket for user context. + * If slow mode is on, we call regular release_sock() + */ +static inline void unlock_sock_fast(struct sock *sk, bool slow) { - spin_lock_bh(&sk->sk_lock.slock); + if (slow) + release_sock(sk); + else + spin_unlock_bh(&sk->sk_lock.slock); } -static inline void unlock_sock_bh(struct sock *sk) -{ - spin_unlock_bh(&sk->sk_lock.slock); -} extern struct sock *sk_alloc(struct net *net, int family, gfp_t priority, diff --git a/net/core/datagram.c b/net/core/datagram.c index e0097531417a..f5b6f43a4c2e 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -229,15 +229,17 @@ EXPORT_SYMBOL(skb_free_datagram); void skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb) { + bool slow; + if (likely(atomic_read(&skb->users) == 1)) smp_rmb(); else if (likely(!atomic_dec_and_test(&skb->users))) return; - lock_sock_bh(sk); + slow = lock_sock_fast(sk); skb_orphan(skb); sk_mem_reclaim_partial(sk); - unlock_sock_bh(sk); + unlock_sock_fast(sk, slow); /* skb is now orphaned, can be freed outside of locked section */ __kfree_skb(skb); diff --git a/net/core/sock.c b/net/core/sock.c index 37fe9b6adade..2cf7f9f7e775 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2007,6 +2007,39 @@ void release_sock(struct sock *sk) } EXPORT_SYMBOL(release_sock); +/** + * lock_sock_fast - fast version of lock_sock + * @sk: socket + * + * This version should be used for very small section, where process wont block + * return false if fast path is taken + * sk_lock.slock locked, owned = 0, BH disabled + * return true if slow path is taken + * sk_lock.slock unlocked, owned = 1, BH enabled + */ +bool lock_sock_fast(struct sock *sk) +{ + might_sleep(); + spin_lock_bh(&sk->sk_lock.slock); + + if (!sk->sk_lock.owned) + /* + * Note : We must disable BH + */ + return false; + + __lock_sock(sk); + sk->sk_lock.owned = 1; + spin_unlock(&sk->sk_lock.slock); + /* + * The sk_lock has mutex_lock() semantics here: + */ + mutex_acquire(&sk->sk_lock.dep_map, 0, 0, _RET_IP_); + local_bh_enable(); + return true; +} +EXPORT_SYMBOL(lock_sock_fast); + int sock_get_timestamp(struct sock *sk, struct timeval __user *userstamp) { struct timeval tv; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 9de6a698f91d..b9d0d409516f 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1063,10 +1063,11 @@ static unsigned int first_packet_length(struct sock *sk) spin_unlock_bh(&rcvq->lock); if (!skb_queue_empty(&list_kill)) { - lock_sock_bh(sk); + bool slow = lock_sock_fast(sk); + __skb_queue_purge(&list_kill); sk_mem_reclaim_partial(sk); - unlock_sock_bh(sk); + unlock_sock_fast(sk, slow); } return res; } @@ -1123,6 +1124,7 @@ int udp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, int peeked; int err; int is_udplite = IS_UDPLITE(sk); + bool slow; /* * Check any passed addresses @@ -1197,10 +1199,10 @@ out: return err; csum_copy_err: - lock_sock_bh(sk); + slow = lock_sock_fast(sk); if (!skb_kill_datagram(sk, skb, flags)) UDP_INC_STATS_USER(sock_net(sk), UDP_MIB_INERRORS, is_udplite); - unlock_sock_bh(sk); + unlock_sock_fast(sk, slow); if (noblock) return -EAGAIN; @@ -1625,9 +1627,9 @@ int udp_rcv(struct sk_buff *skb) void udp_destroy_sock(struct sock *sk) { - lock_sock_bh(sk); + bool slow = lock_sock_fast(sk); udp_flush_pending_frames(sk); - unlock_sock_bh(sk); + unlock_sock_fast(sk, slow); } /* diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 3d7a2c0b836a..87be58673b55 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -328,6 +328,7 @@ int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk, int err; int is_udplite = IS_UDPLITE(sk); int is_udp4; + bool slow; if (addr_len) *addr_len=sizeof(struct sockaddr_in6); @@ -424,7 +425,7 @@ out: return err; csum_copy_err: - lock_sock_bh(sk); + slow = lock_sock_fast(sk); if (!skb_kill_datagram(sk, skb, flags)) { if (is_udp4) UDP_INC_STATS_USER(sock_net(sk), @@ -433,7 +434,7 @@ csum_copy_err: UDP6_INC_STATS_USER(sock_net(sk), UDP_MIB_INERRORS, is_udplite); } - unlock_sock_bh(sk); + unlock_sock_fast(sk, slow); if (flags & MSG_DONTWAIT) return -EAGAIN; -- cgit v1.3-8-gc7d7