From 80a05b9ffa7dc13f6693902dd8999a2b61a3a0d7 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 12 Mar 2010 17:34:14 +0100 Subject: clockevents: Sanitize min_delta_ns adjustment and prevent overflows The current logic which handles clock events programming failures can increase min_delta_ns unlimited and even can cause overflows. Sanitize it by: - prevent zero increase when min_delta_ns == 1 - limiting min_delta_ns to a jiffie - bail out if the jiffie limit is hit - add retries stats for /proc/timer_list so we can gather data Reported-by: Uwe Kleine-Koenig Signed-off-by: Thomas Gleixner --- include/linux/clockchips.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h index 0cf725bdd2a1..fc53492b6ad7 100644 --- a/include/linux/clockchips.h +++ b/include/linux/clockchips.h @@ -73,6 +73,7 @@ enum clock_event_nofitiers { * @list: list head for the management code * @mode: operating mode assigned by the management code * @next_event: local storage for the next event in oneshot mode + * @retries: number of forced programming retries */ struct clock_event_device { const char *name; @@ -93,6 +94,7 @@ struct clock_event_device { struct list_head list; enum clock_event_mode mode; ktime_t next_event; + unsigned long retries; }; /* -- cgit From e3818b8dce2a934cd1521dbc4827e5238d8f45d8 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 15 Mar 2010 17:03:43 -0700 Subject: rcu: Make rcu_read_lock_bh_held() allow for disabled BH Disabling BH can stand in for rcu_read_lock_bh(), and this patch updates rcu_read_lock_bh_held() to allow for this. In order to avoid include-file hell, this function is moved out of line to kernel/rcupdate.c. This fixes a false positive RCU warning. Reported-by: Arnd Bergmann Reported-by: Eric Dumazet Signed-off-by: Paul E. McKenney Acked-by: Lai Jiangshan Cc: dipankar@in.ibm.com Cc: mathieu.desnoyers@polymtl.ca Cc: josh@joshtriplett.org Cc: dvhltc@us.ibm.com Cc: niv@us.ibm.com Cc: peterz@infradead.org Cc: rostedt@goodmis.org Cc: Valdis.Kletnieks@vt.edu Cc: dhowells@redhat.com LKML-Reference: <20100316000343.GA25857@linux.vnet.ibm.com> Signed-off-by: Ingo Molnar --- include/linux/rcupdate.h | 19 ++++--------------- kernel/rcupdate.c | 23 +++++++++++++++++++++++ 2 files changed, 27 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 3024050c82a1..e1bdc4bfd275 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -123,22 +123,11 @@ static inline int rcu_read_lock_held(void) return lock_is_held(&rcu_lock_map); } -/** - * rcu_read_lock_bh_held - might we be in RCU-bh read-side critical section? - * - * If CONFIG_PROVE_LOCKING is selected and enabled, returns nonzero iff in - * an RCU-bh read-side critical section. In absence of CONFIG_PROVE_LOCKING, - * this assumes we are in an RCU-bh read-side critical section unless it can - * prove otherwise. - * - * Check rcu_scheduler_active to prevent false positives during boot. +/* + * rcu_read_lock_bh_held() is defined out of line to avoid #include-file + * hell. */ -static inline int rcu_read_lock_bh_held(void) -{ - if (!debug_lockdep_rcu_enabled()) - return 1; - return lock_is_held(&rcu_bh_lock_map); -} +extern int rcu_read_lock_bh_held(void); /** * rcu_read_lock_sched_held - might we be in RCU-sched read-side critical section? diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c index f1125c1a6321..63fe25433980 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -45,6 +45,7 @@ #include #include #include +#include #ifdef CONFIG_DEBUG_LOCK_ALLOC static struct lock_class_key rcu_lock_key; @@ -66,6 +67,28 @@ EXPORT_SYMBOL_GPL(rcu_sched_lock_map); int rcu_scheduler_active __read_mostly; EXPORT_SYMBOL_GPL(rcu_scheduler_active); +#ifdef CONFIG_DEBUG_LOCK_ALLOC + +/** + * rcu_read_lock_bh_held - might we be in RCU-bh read-side critical section? + * + * Check for bottom half being disabled, which covers both the + * CONFIG_PROVE_RCU and not cases. Note that if someone uses + * rcu_read_lock_bh(), but then later enables BH, lockdep (if enabled) + * will show the situation. + * + * Check debug_lockdep_rcu_enabled() to prevent false positives during boot. + */ +int rcu_read_lock_bh_held(void) +{ + if (!debug_lockdep_rcu_enabled()) + return 1; + return in_softirq(); +} +EXPORT_SYMBOL_GPL(rcu_read_lock_bh_held); + +#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ + /* * This function is invoked towards the end of the scheduler's initialization * process. Before this is called, the idle task might contain -- cgit From 7f5b774275df8c76a959eae7488128b637fcbfc8 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Tue, 16 Mar 2010 17:00:29 +0800 Subject: rcu: Fix tracepoints & lockdep false positive tracepoint.h uses rcu_dereference(), which triggers this warning: [ 0.701161] =================================================== [ 0.702211] [ INFO: suspicious rcu_dereference_check() usage. ] [ 0.702716] --------------------------------------------------- [ 0.703203] include/trace/events/workqueue.h:68 invoked rcu_dereference_check() without protection! [ 0.703971] [ 0.703990] other info that might help us debug this: [ 0.703993] [ 0.705590] [ 0.705604] rcu_scheduler_active = 1, debug_locks = 0 [ 0.706712] 1 lock held by swapper/1: [ 0.707229] #0: (cpu_add_remove_lock){+.+.+.}, at: [] cpu_maps_update_begin+0x14/0x20 [ 0.710097] [ 0.710106] stack backtrace: [ 0.712602] Pid: 1, comm: swapper Not tainted 2.6.34-rc1-tip-01613-g72662bb #168 [ 0.713231] Call Trace: [ 0.713997] [] lockdep_rcu_dereference+0x9d/0xb0 [ 0.714746] [] create_workqueue_thread+0x107/0x110 [ 0.715353] [] ? worker_thread+0x0/0x340 [ 0.715845] [] __create_workqueue_key+0x138/0x240 [ 0.716427] [] ? cpu_maps_update_done+0x12/0x20 [ 0.717012] [] init_workqueues+0x6f/0x80 [ 0.717530] [] kernel_init+0x102/0x1f0 [ 0.717570] [] ? kernel_init+0x0/0x1f0 [ 0.718944] [] kernel_thread_helper+0x6/0x10 Signed-off-by: Lai Jiangshan Cc: Paul E. McKenney Cc: Mathieu Desnoyers Cc: Steven Rostedt Cc: Frederic Weisbecker LKML-Reference: <4B9F48AD.4000404@cn.fujitsu.com> Signed-off-by: Ingo Molnar --- include/linux/tracepoint.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index f59604ed0ec6..78b4bd3be496 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -49,7 +49,7 @@ struct tracepoint { void **it_func; \ \ rcu_read_lock_sched_notrace(); \ - it_func = rcu_dereference((tp)->funcs); \ + it_func = rcu_dereference_sched((tp)->funcs); \ if (it_func) { \ do { \ ((void(*)(proto))(*it_func))(args); \ -- cgit From 0cff810f54b3b52075c27f7a7021d5b195264b6c Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Thu, 18 Mar 2010 12:25:33 -0700 Subject: rcu: Fix local_irq_disable() CONFIG_PROVE_RCU=y false positives It is documented that local_irq_disable() also delimits RCU_SCHED read-site critical sections. See the document of synchronize_sched() or Documentation/RCU/whatisRCU.txt. So we have to test irqs_disabled() in rcu_read_lock_sched_held(). Otherwise rcu-lockdep brings incorrect complaint. Signed-off-by: Lai Jiangshan Signed-off-by: Paul E. McKenney Cc: dipankar@in.ibm.com Cc: mathieu.desnoyers@polymtl.ca Cc: josh@joshtriplett.org Cc: dvhltc@us.ibm.com Cc: niv@us.ibm.com Cc: peterz@infradead.org Cc: rostedt@goodmis.org Cc: Valdis.Kletnieks@vt.edu Cc: dhowells@redhat.com Cc: eric.dumazet@gmail.com LKML-Reference: <1268940334-10892-1-git-send-email-paulmck@linux.vnet.ibm.com> Signed-off-by: Ingo Molnar --- include/linux/rcupdate.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index e1bdc4bfd275..872a98e13d6a 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -149,7 +149,7 @@ static inline int rcu_read_lock_sched_held(void) return 1; if (debug_locks) lockdep_opinion = lock_is_held(&rcu_sched_lock_map); - return lockdep_opinion || preempt_count() != 0; + return lockdep_opinion || preempt_count() != 0 || irqs_disabled(); } #else /* #ifdef CONFIG_PREEMPT */ static inline int rcu_read_lock_sched_held(void) @@ -180,7 +180,7 @@ static inline int rcu_read_lock_bh_held(void) #ifdef CONFIG_PREEMPT static inline int rcu_read_lock_sched_held(void) { - return !rcu_scheduler_active || preempt_count() != 0; + return !rcu_scheduler_active || preempt_count() != 0 || irqs_disabled(); } #else /* #ifdef CONFIG_PREEMPT */ static inline int rcu_read_lock_sched_held(void) -- cgit From 0641e4fbf2f824faee00ea74c459a088d94905fd Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 18 Mar 2010 21:16:45 -0700 Subject: net: Potential null skb->dev dereference When doing "ifenslave -d bond0 eth0", there is chance to get NULL dereference in netif_receive_skb(), because dev->master suddenly becomes NULL after we tested it. We should use ACCESS_ONCE() to avoid this (or rcu_dereference()) Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 8 ++++---- net/8021q/vlan_core.c | 4 ++-- net/core/dev.c | 8 +++++--- 3 files changed, 11 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index c79a88be7c33..fa8b47637997 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2059,12 +2059,12 @@ static inline void skb_bond_set_mac_by_master(struct sk_buff *skb, * duplicates except for 802.3ad ETH_P_SLOW, alb non-mcast/bcast, and * ARP on active-backup slaves with arp_validate enabled. */ -static inline int skb_bond_should_drop(struct sk_buff *skb) +static inline int skb_bond_should_drop(struct sk_buff *skb, + struct net_device *master) { - struct net_device *dev = skb->dev; - struct net_device *master = dev->master; - if (master) { + struct net_device *dev = skb->dev; + if (master->priv_flags & IFF_MASTER_ARPMON) dev->last_rx = jiffies; diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index c0316e0ca6e8..c584a0af77d3 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -11,7 +11,7 @@ int __vlan_hwaccel_rx(struct sk_buff *skb, struct vlan_group *grp, if (netpoll_rx(skb)) return NET_RX_DROP; - if (skb_bond_should_drop(skb)) + if (skb_bond_should_drop(skb, ACCESS_ONCE(skb->dev->master))) goto drop; skb->skb_iif = skb->dev->ifindex; @@ -83,7 +83,7 @@ vlan_gro_common(struct napi_struct *napi, struct vlan_group *grp, { struct sk_buff *p; - if (skb_bond_should_drop(skb)) + if (skb_bond_should_drop(skb, ACCESS_ONCE(skb->dev->master))) goto drop; skb->skb_iif = skb->dev->ifindex; diff --git a/net/core/dev.c b/net/core/dev.c index bcc490cc9452..59d4394d2ce8 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2483,6 +2483,7 @@ int netif_receive_skb(struct sk_buff *skb) { struct packet_type *ptype, *pt_prev; struct net_device *orig_dev; + struct net_device *master; struct net_device *null_or_orig; struct net_device *null_or_bond; int ret = NET_RX_DROP; @@ -2503,11 +2504,12 @@ int netif_receive_skb(struct sk_buff *skb) null_or_orig = NULL; orig_dev = skb->dev; - if (orig_dev->master) { - if (skb_bond_should_drop(skb)) + master = ACCESS_ONCE(orig_dev->master); + if (master) { + if (skb_bond_should_drop(skb, master)) null_or_orig = orig_dev; /* deliver only exact match */ else - skb->dev = orig_dev->master; + skb->dev = master; } __get_cpu_var(netdev_rx_stat).total++; -- cgit From 1a50307ba1826e4da0024e64b245ce4eadf7688a Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 18 Mar 2010 14:24:42 +0000 Subject: netlink: fix NETLINK_RECV_NO_ENOBUFS in netlink_set_err() Currently, ENOBUFS errors are reported to the socket via netlink_set_err() even if NETLINK_RECV_NO_ENOBUFS is set. However, that should not happen. This fixes this problem and it changes the prototype of netlink_set_err() to return the number of sockets that have set the NETLINK_RECV_NO_ENOBUFS socket option. This return value is used in the next patch in these bugfix series. Signed-off-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- include/linux/netlink.h | 2 +- net/netlink/af_netlink.c | 17 ++++++++++++++--- 2 files changed, 15 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index fde27c017326..6eaca5e1e8ca 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -188,7 +188,7 @@ extern int netlink_has_listeners(struct sock *sk, unsigned int group); extern int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 pid, int nonblock); extern int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, __u32 pid, __u32 group, gfp_t allocation); -extern void netlink_set_err(struct sock *ssk, __u32 pid, __u32 group, int code); +extern int netlink_set_err(struct sock *ssk, __u32 pid, __u32 group, int code); extern int netlink_register_notifier(struct notifier_block *nb); extern int netlink_unregister_notifier(struct notifier_block *nb); diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 320d0423a240..acbbae1e89b5 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1093,6 +1093,7 @@ static inline int do_one_set_err(struct sock *sk, struct netlink_set_err_data *p) { struct netlink_sock *nlk = nlk_sk(sk); + int ret = 0; if (sk == p->exclude_sk) goto out; @@ -1104,10 +1105,15 @@ static inline int do_one_set_err(struct sock *sk, !test_bit(p->group - 1, nlk->groups)) goto out; + if (p->code == ENOBUFS && nlk->flags & NETLINK_RECV_NO_ENOBUFS) { + ret = 1; + goto out; + } + sk->sk_err = p->code; sk->sk_error_report(sk); out: - return 0; + return ret; } /** @@ -1116,12 +1122,16 @@ out: * @pid: the PID of a process that we want to skip (if any) * @groups: the broadcast group that will notice the error * @code: error code, must be negative (as usual in kernelspace) + * + * This function returns the number of broadcast listeners that have set the + * NETLINK_RECV_NO_ENOBUFS socket option. */ -void netlink_set_err(struct sock *ssk, u32 pid, u32 group, int code) +int netlink_set_err(struct sock *ssk, u32 pid, u32 group, int code) { struct netlink_set_err_data info; struct hlist_node *node; struct sock *sk; + int ret = 0; info.exclude_sk = ssk; info.pid = pid; @@ -1132,9 +1142,10 @@ void netlink_set_err(struct sock *ssk, u32 pid, u32 group, int code) read_lock(&nl_table_lock); sk_for_each_bound(sk, node, &nl_table[ssk->sk_protocol].mc_list) - do_one_set_err(sk, &info); + ret += do_one_set_err(sk, &info); read_unlock(&nl_table_lock); + return ret; } EXPORT_SYMBOL(netlink_set_err); -- cgit From 37b7ef7203240b3aba577bb1ff6765fe15225976 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 16 Mar 2010 13:30:21 +0000 Subject: netfilter: ctnetlink: fix reliable event delivery if message building fails This patch fixes a bug that allows to lose events when reliable event delivery mode is used, ie. if NETLINK_BROADCAST_SEND_ERROR and NETLINK_RECV_NO_ENOBUFS socket options are set. Signed-off-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- include/linux/netfilter/nfnetlink.h | 2 +- net/netfilter/nf_conntrack_netlink.c | 4 +++- net/netfilter/nfnetlink.c | 4 ++-- 3 files changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index 53923868c9bd..361d6b5630ee 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -76,7 +76,7 @@ extern int nfnetlink_subsys_unregister(const struct nfnetlink_subsystem *n); extern int nfnetlink_has_listeners(struct net *net, unsigned int group); extern int nfnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, unsigned group, int echo, gfp_t flags); -extern void nfnetlink_set_err(struct net *net, u32 pid, u32 group, int error); +extern int nfnetlink_set_err(struct net *net, u32 pid, u32 group, int error); extern int nfnetlink_unicast(struct sk_buff *skb, struct net *net, u_int32_t pid, int flags); extern void nfnl_lock(void); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 2b2af631d2b8..569410a85953 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -582,7 +582,9 @@ nla_put_failure: nlmsg_failure: kfree_skb(skb); errout: - nfnetlink_set_err(net, 0, group, -ENOBUFS); + if (nfnetlink_set_err(net, 0, group, -ENOBUFS) > 0) + return -ENOBUFS; + return 0; } #endif /* CONFIG_NF_CONNTRACK_EVENTS */ diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 8eb0cc23ada3..6afa3d52ea5f 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -113,9 +113,9 @@ int nfnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, } EXPORT_SYMBOL_GPL(nfnetlink_send); -void nfnetlink_set_err(struct net *net, u32 pid, u32 group, int error) +int nfnetlink_set_err(struct net *net, u32 pid, u32 group, int error) { - netlink_set_err(net->nfnl, pid, group, error); + return netlink_set_err(net->nfnl, pid, group, error); } EXPORT_SYMBOL_GPL(nfnetlink_set_err); -- cgit From 9bf35c8dddd56f7f247a27346f74f5adc18071f4 Mon Sep 17 00:00:00 2001 From: Paulius Zaleckas Date: Sun, 21 Mar 2010 21:19:02 -0700 Subject: if_tunnel.h: add missing ams/byteorder.h include When compiling userspace application which includes if_tunnel.h and uses GRE_* defines you will get undefined reference to __cpu_to_be16. Fix this by adding missing #include Cc: stable@kernel.org Signed-off-by: Paulius Zaleckas Signed-off-by: David S. Miller --- include/linux/if_tunnel.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/if_tunnel.h b/include/linux/if_tunnel.h index 1822d635be6b..16b92d008bed 100644 --- a/include/linux/if_tunnel.h +++ b/include/linux/if_tunnel.h @@ -2,6 +2,7 @@ #define _IF_TUNNEL_H_ #include +#include #ifdef __KERNEL__ #include -- cgit From c9acb42ef1904d15d0fb315061cefbe638f67f3a Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 19 Mar 2010 15:36:22 -0400 Subject: SUNRPC: Fix a use after free bug with the NFSv4.1 backchannel The ->release_request() callback was designed to allow the transport layer to do housekeeping after the RPC call is done. It cannot be used to free the request itself, and doing so leads to a use-after-free bug in xprt_release(). Signed-off-by: Trond Myklebust --- include/linux/sunrpc/bc_xprt.h | 5 ++++- net/sunrpc/bc_svc.c | 15 --------------- net/sunrpc/xprt.c | 22 +++++++++------------- net/sunrpc/xprtsock.c | 3 --- 4 files changed, 13 insertions(+), 32 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/bc_xprt.h b/include/linux/sunrpc/bc_xprt.h index d7152b451e21..7c91260c44a9 100644 --- a/include/linux/sunrpc/bc_xprt.h +++ b/include/linux/sunrpc/bc_xprt.h @@ -36,7 +36,6 @@ struct rpc_rqst *xprt_alloc_bc_request(struct rpc_xprt *xprt); void xprt_free_bc_request(struct rpc_rqst *req); int xprt_setup_backchannel(struct rpc_xprt *, unsigned int min_reqs); void xprt_destroy_backchannel(struct rpc_xprt *, int max_reqs); -void bc_release_request(struct rpc_task *); int bc_send(struct rpc_rqst *req); /* @@ -59,6 +58,10 @@ static inline int svc_is_backchannel(const struct svc_rqst *rqstp) { return 0; } + +static inline void xprt_free_bc_request(struct rpc_rqst *req) +{ +} #endif /* CONFIG_NFS_V4_1 */ #endif /* _LINUX_SUNRPC_BC_XPRT_H */ diff --git a/net/sunrpc/bc_svc.c b/net/sunrpc/bc_svc.c index 13f214f53120..f0c05d3311c1 100644 --- a/net/sunrpc/bc_svc.c +++ b/net/sunrpc/bc_svc.c @@ -37,21 +37,6 @@ SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. #define RPCDBG_FACILITY RPCDBG_SVCDSP -void bc_release_request(struct rpc_task *task) -{ - struct rpc_rqst *req = task->tk_rqstp; - - dprintk("RPC: bc_release_request: task= %p\n", task); - - /* - * Release this request only if it's a backchannel - * preallocated request - */ - if (!bc_prealloc(req)) - return; - xprt_free_bc_request(req); -} - /* Empty callback ops */ static const struct rpc_call_ops nfs41_callback_ops = { }; diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 469de292c23c..42f09ade0044 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -46,6 +46,7 @@ #include #include +#include #include "sunrpc.h" @@ -1032,21 +1033,16 @@ void xprt_release(struct rpc_task *task) if (req->rq_release_snd_buf) req->rq_release_snd_buf(req); - /* - * Early exit if this is a backchannel preallocated request. - * There is no need to have it added to the RPC slot list. - */ - if (is_bc_request) - return; - - memset(req, 0, sizeof(*req)); /* mark unused */ - dprintk("RPC: %5u release request %p\n", task->tk_pid, req); + if (likely(!is_bc_request)) { + memset(req, 0, sizeof(*req)); /* mark unused */ - spin_lock(&xprt->reserve_lock); - list_add(&req->rq_list, &xprt->free); - rpc_wake_up_next(&xprt->backlog); - spin_unlock(&xprt->reserve_lock); + spin_lock(&xprt->reserve_lock); + list_add(&req->rq_list, &xprt->free); + rpc_wake_up_next(&xprt->backlog); + spin_unlock(&xprt->reserve_lock); + } else + xprt_free_bc_request(req); } /** diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index e4839c07c913..9847c30b5001 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -2251,9 +2251,6 @@ static struct rpc_xprt_ops xs_tcp_ops = { .buf_free = rpc_free, .send_request = xs_tcp_send_request, .set_retrans_timeout = xprt_set_retrans_timeout_def, -#if defined(CONFIG_NFS_V4_1) - .release_request = bc_release_request, -#endif /* CONFIG_NFS_V4_1 */ .close = xs_tcp_close, .destroy = xs_destroy, .print_stats = xs_tcp_print_stats, -- cgit From ae6be51ed01d6c4aaf249a207b4434bc7785853b Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 22 Mar 2010 13:12:33 -0700 Subject: Fix up prototype for sys_ipc breakage Commit 45575f5a426c ("ppc64 sys_ipc breakage in 2.6.34-rc2") fixed the definition of the sys_ipc() helper, but didn't fix the prototype in Reported-and-tested-by: Andreas Schwab Signed-off-by: Linus Torvalds --- include/linux/syscalls.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index f994ae58a002..057929b0a651 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -688,7 +688,7 @@ asmlinkage long sys_shmat(int shmid, char __user *shmaddr, int shmflg); asmlinkage long sys_shmget(key_t key, size_t size, int flag); asmlinkage long sys_shmdt(char __user *shmaddr); asmlinkage long sys_shmctl(int shmid, int cmd, struct shmid_ds __user *buf); -asmlinkage long sys_ipc(unsigned int call, int first, int second, +asmlinkage long sys_ipc(unsigned int call, int first, unsigned long second, unsigned long third, void __user *ptr, long fifth); asmlinkage long sys_mq_open(const char __user *name, int oflag, mode_t mode, struct mq_attr __user *attr); -- cgit From 66f1207bce10fd80ee8ce99b67d617644612f05e Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Thu, 11 Mar 2010 17:01:09 -0700 Subject: resources: add interfaces that return conflict information request_resource() and insert_resource() only return success or failure, which no information about what existing resource conflicted with the proposed new reservation. This patch adds request_resource_conflict() and insert_resource_conflict(), which return the conflicting resource. Callers may use this for better error messages or to adjust the new resource and retry the request. Signed-off-by: Bjorn Helgaas Signed-off-by: Jesse Barnes --- include/linux/ioport.h | 2 ++ kernel/resource.c | 44 +++++++++++++++++++++++++++++++++++++------- 2 files changed, 39 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ioport.h b/include/linux/ioport.h index 71ab79da7e7f..26fad187d661 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -112,12 +112,14 @@ struct resource_list { extern struct resource ioport_resource; extern struct resource iomem_resource; +extern struct resource *request_resource_conflict(struct resource *root, struct resource *new); extern int request_resource(struct resource *root, struct resource *new); extern int release_resource(struct resource *new); void release_child_resources(struct resource *new); extern void reserve_region_with_split(struct resource *root, resource_size_t start, resource_size_t end, const char *name); +extern struct resource *insert_resource_conflict(struct resource *parent, struct resource *new); extern int insert_resource(struct resource *parent, struct resource *new); extern void insert_resource_expand_to_fit(struct resource *root, struct resource *new); extern int allocate_resource(struct resource *root, struct resource *new, diff --git a/kernel/resource.c b/kernel/resource.c index 2d5be5d9bf5f..9c358e263534 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -219,19 +219,34 @@ void release_child_resources(struct resource *r) } /** - * request_resource - request and reserve an I/O or memory resource + * request_resource_conflict - request and reserve an I/O or memory resource * @root: root resource descriptor * @new: resource descriptor desired by caller * - * Returns 0 for success, negative error code on error. + * Returns 0 for success, conflict resource on error. */ -int request_resource(struct resource *root, struct resource *new) +struct resource *request_resource_conflict(struct resource *root, struct resource *new) { struct resource *conflict; write_lock(&resource_lock); conflict = __request_resource(root, new); write_unlock(&resource_lock); + return conflict; +} + +/** + * request_resource - request and reserve an I/O or memory resource + * @root: root resource descriptor + * @new: resource descriptor desired by caller + * + * Returns 0 for success, negative error code on error. + */ +int request_resource(struct resource *root, struct resource *new) +{ + struct resource *conflict; + + conflict = request_resource_conflict(root, new); return conflict ? -EBUSY : 0; } @@ -474,25 +489,40 @@ static struct resource * __insert_resource(struct resource *parent, struct resou } /** - * insert_resource - Inserts a resource in the resource tree + * insert_resource_conflict - Inserts resource in the resource tree * @parent: parent of the new resource * @new: new resource to insert * - * Returns 0 on success, -EBUSY if the resource can't be inserted. + * Returns 0 on success, conflict resource if the resource can't be inserted. * - * This function is equivalent to request_resource when no conflict + * This function is equivalent to request_resource_conflict when no conflict * happens. If a conflict happens, and the conflicting resources * entirely fit within the range of the new resource, then the new * resource is inserted and the conflicting resources become children of * the new resource. */ -int insert_resource(struct resource *parent, struct resource *new) +struct resource *insert_resource_conflict(struct resource *parent, struct resource *new) { struct resource *conflict; write_lock(&resource_lock); conflict = __insert_resource(parent, new); write_unlock(&resource_lock); + return conflict; +} + +/** + * insert_resource - Inserts a resource in the resource tree + * @parent: parent of the new resource + * @new: new resource to insert + * + * Returns 0 on success, -EBUSY if the resource can't be inserted. + */ +int insert_resource(struct resource *parent, struct resource *new) +{ + struct resource *conflict; + + conflict = insert_resource_conflict(parent, new); return conflict ? -EBUSY : 0; } -- cgit From 03e6d819c2cb2cc8ce5642669a0a7c72336ee7a2 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Tue, 23 Mar 2010 20:40:50 +0000 Subject: skbuff: remove unused dma_head & dma_maps fields The dma map fields in the skb_shared_info structure no longer has any users and can be dropped since it is making the skb_shared_info unecessarily larger. Running slabtop show that we were using 4K slabs for the skb->head on x86_64 w/ an allocation size of 1522. It turns out that the dma_head and dma_maps array made skb_shared large enough that we had crossed over the 2k boundary with standard frames and as such we were using 4k blocks of memory for all skbs. Signed-off-by: Alexander Duyck Signed-off-by: Jeff Kirsher Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 03f816a9b659..124f90cd5a38 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -190,9 +190,6 @@ struct skb_shared_info { atomic_t dataref; unsigned short nr_frags; unsigned short gso_size; -#ifdef CONFIG_HAS_DMA - dma_addr_t dma_head; -#endif /* Warning: this field is not always filled in (UFO)! */ unsigned short gso_segs; unsigned short gso_type; @@ -201,9 +198,6 @@ struct skb_shared_info { struct sk_buff *frag_list; struct skb_shared_hwtstamps hwtstamps; skb_frag_t frags[MAX_SKB_FRAGS]; -#ifdef CONFIG_HAS_DMA - dma_addr_t dma_maps[MAX_SKB_FRAGS]; -#endif /* Intermediate layers must ensure that destructor_arg * remains valid until skb destructor */ void * destructor_arg; -- cgit From 4c87684d32e8f95715d53039dcd2d998dc63d1eb Mon Sep 17 00:00:00 2001 From: David Härdeman Date: Tue, 23 Mar 2010 13:35:22 -0700 Subject: kfifo: fix KFIFO_INIT in include/linux/kfifo.h MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit include/linux/kfifo.h first defines and then undefines __kfifo_initializer which is used by INIT_KFIFO (which is also a macro, so building a module which uses INIT_KFIFO will fail). Signed-off-by: David Härdeman Acked-by: Stefani Seibold Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kfifo.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kfifo.h b/include/linux/kfifo.h index bc0fc795bd35..ece0b1c33816 100644 --- a/include/linux/kfifo.h +++ b/include/linux/kfifo.h @@ -102,8 +102,6 @@ union { \ unsigned char name##kfifo_buffer[size]; \ struct kfifo name = __kfifo_initializer(size, name##kfifo_buffer) -#undef __kfifo_initializer - extern void kfifo_init(struct kfifo *fifo, void *buffer, unsigned int size); extern __must_check int kfifo_alloc(struct kfifo *fifo, unsigned int size, -- cgit From 6cb4aff0a77cc0e6bae9475d62205319e3ebbf3f Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Tue, 23 Mar 2010 13:35:38 -0700 Subject: reiserfs: fix oops while creating privroot with selinux enabled Commit 57fe60df ("reiserfs: add atomic addition of selinux attributes during inode creation") contains a bug that will cause it to oops when mounting a file system that didn't previously contain extended attributes on a system using security.* xattrs. The issue is that while creating the privroot during mount reiserfs_security_init calls reiserfs_xattr_jcreate_nblocks which dereferences the xattr root. The xattr root doesn't exist, so we get an oops. Addresses http://bugzilla.kernel.org/show_bug.cgi?id=15309 Signed-off-by: Jeff Mahoney Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/reiserfs/xattr_security.c | 2 +- include/linux/reiserfs_xattr.h | 5 +++++ 2 files changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/fs/reiserfs/xattr_security.c b/fs/reiserfs/xattr_security.c index d8b5bfcbdd30..de1fcffd906b 100644 --- a/fs/reiserfs/xattr_security.c +++ b/fs/reiserfs/xattr_security.c @@ -76,7 +76,7 @@ int reiserfs_security_init(struct inode *dir, struct inode *inode, return error; } - if (sec->length) { + if (sec->length && reiserfs_xattrs_initialized(inode->i_sb)) { blocks = reiserfs_xattr_jcreate_nblocks(inode) + reiserfs_xattr_nblocks(inode, sec->length); /* We don't want to count the directories twice if we have diff --git a/include/linux/reiserfs_xattr.h b/include/linux/reiserfs_xattr.h index 99928dce37ea..7fa02b4af838 100644 --- a/include/linux/reiserfs_xattr.h +++ b/include/linux/reiserfs_xattr.h @@ -70,6 +70,11 @@ int reiserfs_security_write(struct reiserfs_transaction_handle *th, void reiserfs_security_free(struct reiserfs_security_handle *sec); #endif +static inline int reiserfs_xattrs_initialized(struct super_block *sb) +{ + return REISERFS_SB(sb)->priv_root != NULL; +} + #define xattr_size(size) ((size) + sizeof(struct reiserfs_xattr_header)) static inline loff_t reiserfs_xattr_nblocks(struct inode *inode, loff_t size) { -- cgit From 7198f3c9b13c7aa1e5d9f7ff74c0ea303174feff Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 23 Mar 2010 13:35:40 -0700 Subject: mmc: fix incorrect interpretation of card type bits In the extended CSD register the CARD_TYPE is an 8-bit value of which the upper 6 bits were reserved in JEDEC specifications prior to version 4.4. In version 4.4 two of the reserved bits were designated for identifying support for the newly added High-Speed Dual Data Rate. Unfortunately the mmc_read_ext_csd() function required that the reserved bits be zero instead of ignoring them as it should. This patch makes mmc_read_ext_csd() ignore the CARD_TYPE bits that are reserved or not yet supported. It also stops the function jumping to the end as though an error occurred, when it is only warns that the CARD_TYPE bits (that it does interpret) are invalid. Signed-off-by: Adrian Hunter Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/mmc/core/mmc.c | 3 +-- include/linux/mmc/mmc.h | 1 + 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c index 0eac6c814904..e041c003db22 100644 --- a/drivers/mmc/core/mmc.c +++ b/drivers/mmc/core/mmc.c @@ -225,7 +225,7 @@ static int mmc_read_ext_csd(struct mmc_card *card) mmc_card_set_blockaddr(card); } - switch (ext_csd[EXT_CSD_CARD_TYPE]) { + switch (ext_csd[EXT_CSD_CARD_TYPE] & EXT_CSD_CARD_TYPE_MASK) { case EXT_CSD_CARD_TYPE_52 | EXT_CSD_CARD_TYPE_26: card->ext_csd.hs_max_dtr = 52000000; break; @@ -237,7 +237,6 @@ static int mmc_read_ext_csd(struct mmc_card *card) printk(KERN_WARNING "%s: card is mmc v4 but doesn't " "support any high-speed modes.\n", mmc_hostname(card->host)); - goto out; } if (card->ext_csd.rev >= 3) { diff --git a/include/linux/mmc/mmc.h b/include/linux/mmc/mmc.h index c02c8db73701..8a49cbf0376d 100644 --- a/include/linux/mmc/mmc.h +++ b/include/linux/mmc/mmc.h @@ -268,6 +268,7 @@ struct _mmc_csd { #define EXT_CSD_CARD_TYPE_26 (1<<0) /* Card can run at 26MHz */ #define EXT_CSD_CARD_TYPE_52 (1<<1) /* Card can run at 52MHz */ +#define EXT_CSD_CARD_TYPE_MASK 0x3 /* Mask out reserved and DDR bits */ #define EXT_CSD_BUS_WIDTH_1 0 /* Card is in 1 bit mode */ #define EXT_CSD_BUS_WIDTH_4 1 /* Card is in 4 bit mode */ -- cgit From 90fddabf5818367c6bd1fe1b256a10e01827862f Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 24 Mar 2010 09:43:00 +0000 Subject: Document Linux's circular buffering capabilities Document the circular buffering capabilities available in Linux. Signed-off-by: David Howells Signed-off-by: Paul E. McKenney Reviewed-by: Randy Dunlap Reviewed-by: Stefan Richter Signed-off-by: Linus Torvalds --- Documentation/circular-buffers.txt | 234 +++++++++++++++++++++++++++++++++++++ Documentation/memory-barriers.txt | 20 ++++ include/linux/circ_buf.h | 4 + 3 files changed, 258 insertions(+) create mode 100644 Documentation/circular-buffers.txt (limited to 'include/linux') diff --git a/Documentation/circular-buffers.txt b/Documentation/circular-buffers.txt new file mode 100644 index 000000000000..8117e5bf6065 --- /dev/null +++ b/Documentation/circular-buffers.txt @@ -0,0 +1,234 @@ + ================ + CIRCULAR BUFFERS + ================ + +By: David Howells + Paul E. McKenney + + +Linux provides a number of features that can be used to implement circular +buffering. There are two sets of such features: + + (1) Convenience functions for determining information about power-of-2 sized + buffers. + + (2) Memory barriers for when the producer and the consumer of objects in the + buffer don't want to share a lock. + +To use these facilities, as discussed below, there needs to be just one +producer and just one consumer. It is possible to handle multiple producers by +serialising them, and to handle multiple consumers by serialising them. + + +Contents: + + (*) What is a circular buffer? + + (*) Measuring power-of-2 buffers. + + (*) Using memory barriers with circular buffers. + - The producer. + - The consumer. + + +========================== +WHAT IS A CIRCULAR BUFFER? +========================== + +First of all, what is a circular buffer? A circular buffer is a buffer of +fixed, finite size into which there are two indices: + + (1) A 'head' index - the point at which the producer inserts items into the + buffer. + + (2) A 'tail' index - the point at which the consumer finds the next item in + the buffer. + +Typically when the tail pointer is equal to the head pointer, the buffer is +empty; and the buffer is full when the head pointer is one less than the tail +pointer. + +The head index is incremented when items are added, and the tail index when +items are removed. The tail index should never jump the head index, and both +indices should be wrapped to 0 when they reach the end of the buffer, thus +allowing an infinite amount of data to flow through the buffer. + +Typically, items will all be of the same unit size, but this isn't strictly +required to use the techniques below. The indices can be increased by more +than 1 if multiple items or variable-sized items are to be included in the +buffer, provided that neither index overtakes the other. The implementer must +be careful, however, as a region more than one unit in size may wrap the end of +the buffer and be broken into two segments. + + +============================ +MEASURING POWER-OF-2 BUFFERS +============================ + +Calculation of the occupancy or the remaining capacity of an arbitrarily sized +circular buffer would normally be a slow operation, requiring the use of a +modulus (divide) instruction. However, if the buffer is of a power-of-2 size, +then a much quicker bitwise-AND instruction can be used instead. + +Linux provides a set of macros for handling power-of-2 circular buffers. These +can be made use of by: + + #include + +The macros are: + + (*) Measure the remaining capacity of a buffer: + + CIRC_SPACE(head_index, tail_index, buffer_size); + + This returns the amount of space left in the buffer[1] into which items + can be inserted. + + + (*) Measure the maximum consecutive immediate space in a buffer: + + CIRC_SPACE_TO_END(head_index, tail_index, buffer_size); + + This returns the amount of consecutive space left in the buffer[1] into + which items can be immediately inserted without having to wrap back to the + beginning of the buffer. + + + (*) Measure the occupancy of a buffer: + + CIRC_CNT(head_index, tail_index, buffer_size); + + This returns the number of items currently occupying a buffer[2]. + + + (*) Measure the non-wrapping occupancy of a buffer: + + CIRC_CNT_TO_END(head_index, tail_index, buffer_size); + + This returns the number of consecutive items[2] that can be extracted from + the buffer without having to wrap back to the beginning of the buffer. + + +Each of these macros will nominally return a value between 0 and buffer_size-1, +however: + + [1] CIRC_SPACE*() are intended to be used in the producer. To the producer + they will return a lower bound as the producer controls the head index, + but the consumer may still be depleting the buffer on another CPU and + moving the tail index. + + To the consumer it will show an upper bound as the producer may be busy + depleting the space. + + [2] CIRC_CNT*() are intended to be used in the consumer. To the consumer they + will return a lower bound as the consumer controls the tail index, but the + producer may still be filling the buffer on another CPU and moving the + head index. + + To the producer it will show an upper bound as the consumer may be busy + emptying the buffer. + + [3] To a third party, the order in which the writes to the indices by the + producer and consumer become visible cannot be guaranteed as they are + independent and may be made on different CPUs - so the result in such a + situation will merely be a guess, and may even be negative. + + +=========================================== +USING MEMORY BARRIERS WITH CIRCULAR BUFFERS +=========================================== + +By using memory barriers in conjunction with circular buffers, you can avoid +the need to: + + (1) use a single lock to govern access to both ends of the buffer, thus + allowing the buffer to be filled and emptied at the same time; and + + (2) use atomic counter operations. + +There are two sides to this: the producer that fills the buffer, and the +consumer that empties it. Only one thing should be filling a buffer at any one +time, and only one thing should be emptying a buffer at any one time, but the +two sides can operate simultaneously. + + +THE PRODUCER +------------ + +The producer will look something like this: + + spin_lock(&producer_lock); + + unsigned long head = buffer->head; + unsigned long tail = ACCESS_ONCE(buffer->tail); + + if (CIRC_SPACE(head, tail, buffer->size) >= 1) { + /* insert one item into the buffer */ + struct item *item = buffer[head]; + + produce_item(item); + + smp_wmb(); /* commit the item before incrementing the head */ + + buffer->head = (head + 1) & (buffer->size - 1); + + /* wake_up() will make sure that the head is committed before + * waking anyone up */ + wake_up(consumer); + } + + spin_unlock(&producer_lock); + +This will instruct the CPU that the contents of the new item must be written +before the head index makes it available to the consumer and then instructs the +CPU that the revised head index must be written before the consumer is woken. + +Note that wake_up() doesn't have to be the exact mechanism used, but whatever +is used must guarantee a (write) memory barrier between the update of the head +index and the change of state of the consumer, if a change of state occurs. + + +THE CONSUMER +------------ + +The consumer will look something like this: + + spin_lock(&consumer_lock); + + unsigned long head = ACCESS_ONCE(buffer->head); + unsigned long tail = buffer->tail; + + if (CIRC_CNT(head, tail, buffer->size) >= 1) { + /* read index before reading contents at that index */ + smp_read_barrier_depends(); + + /* extract one item from the buffer */ + struct item *item = buffer[tail]; + + consume_item(item); + + smp_mb(); /* finish reading descriptor before incrementing tail */ + + buffer->tail = (tail + 1) & (buffer->size - 1); + } + + spin_unlock(&consumer_lock); + +This will instruct the CPU to make sure the index is up to date before reading +the new item, and then it shall make sure the CPU has finished reading the item +before it writes the new tail pointer, which will erase the item. + + +Note the use of ACCESS_ONCE() in both algorithms to read the opposition index. +This prevents the compiler from discarding and reloading its cached value - +which some compilers will do across smp_read_barrier_depends(). This isn't +strictly needed if you can be sure that the opposition index will _only_ be +used the once. + + +=============== +FURTHER READING +=============== + +See also Documentation/memory-barriers.txt for a description of Linux's memory +barrier facilities. diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt index 7f5809eddee6..631ad2f1b229 100644 --- a/Documentation/memory-barriers.txt +++ b/Documentation/memory-barriers.txt @@ -3,6 +3,7 @@ ============================ By: David Howells + Paul E. McKenney Contents: @@ -60,6 +61,10 @@ Contents: - And then there's the Alpha. + (*) Example uses. + + - Circular buffers. + (*) References. @@ -2226,6 +2231,21 @@ The Alpha defines the Linux kernel's memory barrier model. See the subsection on "Cache Coherency" above. +============ +EXAMPLE USES +============ + +CIRCULAR BUFFERS +---------------- + +Memory barriers can be used to implement circular buffering without the need +of a lock to serialise the producer with the consumer. See: + + Documentation/circular-buffers.txt + +for details. + + ========== REFERENCES ========== diff --git a/include/linux/circ_buf.h b/include/linux/circ_buf.h index a2ed0591fb19..90f2471dc6f2 100644 --- a/include/linux/circ_buf.h +++ b/include/linux/circ_buf.h @@ -1,3 +1,7 @@ +/* + * See Documentation/circular-buffers.txt for more information. + */ + #ifndef _LINUX_CIRC_BUF_H #define _LINUX_CIRC_BUF_H 1 -- cgit From 9c13886665c43600bd0af4b38e33c654e648e078 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Thu, 25 Mar 2010 11:17:26 +0100 Subject: netfilter: ip6table_raw: fix table priority The order of the IPv6 raw table is currently reversed, that makes impossible to use the NOTRACK target in IPv6: for example if someone enters ip6tables -t raw -A PREROUTING -p tcp --dport 80 -j NOTRACK and if we receive fragmented packets then the first fragment will be untracked and thus skip nf_ct_frag6_gather (and conntrack), while all subsequent fragments enter nf_ct_frag6_gather and reassembly will never successfully be finished. Singed-off-by: Jozsef Kadlecsik Signed-off-by: Patrick McHardy --- include/linux/netfilter_ipv6.h | 1 + net/ipv6/netfilter/ip6table_raw.c | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h index d654873aa25a..1f7e300094cd 100644 --- a/include/linux/netfilter_ipv6.h +++ b/include/linux/netfilter_ipv6.h @@ -59,6 +59,7 @@ enum nf_ip6_hook_priorities { NF_IP6_PRI_FIRST = INT_MIN, NF_IP6_PRI_CONNTRACK_DEFRAG = -400, + NF_IP6_PRI_RAW = -300, NF_IP6_PRI_SELINUX_FIRST = -225, NF_IP6_PRI_CONNTRACK = -200, NF_IP6_PRI_MANGLE = -150, diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c index aef31a29de9e..b9cf7cd61923 100644 --- a/net/ipv6/netfilter/ip6table_raw.c +++ b/net/ipv6/netfilter/ip6table_raw.c @@ -13,7 +13,7 @@ static const struct xt_table packet_raw = { .valid_hooks = RAW_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_IPV6, - .priority = NF_IP6_PRI_FIRST, + .priority = NF_IP6_PRI_RAW, }; /* The work comes in here from netfilter.c. */ -- cgit From 71c5c1595c04852d6fbf3c4882b47b30b61a4d32 Mon Sep 17 00:00:00 2001 From: Brandon L Black Date: Fri, 26 Mar 2010 16:18:03 +0000 Subject: net: Add MSG_WAITFORONE flag to recvmmsg Add new flag MSG_WAITFORONE for the recvmmsg() syscall. When this flag is specified for a blocking socket, recvmmsg() will only block until at least 1 packet is available. The default behavior is to block until all vlen packets are available. This flag has no effect on non-blocking sockets or when used in combination with MSG_DONTWAIT. Signed-off-by: Brandon L Black Acked-by: Ulrich Drepper Acked-by: Eric Dumazet Acked-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/linux/socket.h | 1 + net/socket.c | 4 ++++ 2 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index 7b3aae2052a6..354cc5617f8b 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -255,6 +255,7 @@ struct ucred { #define MSG_ERRQUEUE 0x2000 /* Fetch message from error queue */ #define MSG_NOSIGNAL 0x4000 /* Do not generate SIGPIPE */ #define MSG_MORE 0x8000 /* Sender will send more */ +#define MSG_WAITFORONE 0x10000 /* recvmmsg(): block until 1+ packets avail */ #define MSG_EOF MSG_FIN diff --git a/net/socket.c b/net/socket.c index 769c386bd428..f55ffe9f8c87 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2135,6 +2135,10 @@ int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, break; ++datagrams; + /* MSG_WAITFORONE turns on MSG_DONTWAIT after one packet */ + if (flags & MSG_WAITFORONE) + flags |= MSG_DONTWAIT; + if (timeout) { ktime_get_ts(timeout); *timeout = timespec_sub(end_time, *timeout); -- cgit From a53f4f9efaeb1d87cfae066346979d4d70e1abe9 Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 29 Mar 2010 13:08:52 +0100 Subject: SLOW_WORK: CONFIG_SLOW_WORK_PROC should be CONFIG_SLOW_WORK_DEBUG CONFIG_SLOW_WORK_PROC was changed to CONFIG_SLOW_WORK_DEBUG, but not in all instances. Change the remaining instances. This makes the debugfs file display the time mark and the owner's description again. Signed-off-by: David Howells Signed-off-by: Linus Torvalds --- fs/fscache/object.c | 6 +++--- fs/fscache/operation.c | 4 ++-- include/linux/fscache-cache.h | 2 +- kernel/slow-work.h | 8 ++++---- 4 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/fs/fscache/object.c b/fs/fscache/object.c index e513ac599c8e..0b589a9b4ffc 100644 --- a/fs/fscache/object.c +++ b/fs/fscache/object.c @@ -53,7 +53,7 @@ const char fscache_object_states_short[FSCACHE_OBJECT__NSTATES][5] = { static void fscache_object_slow_work_put_ref(struct slow_work *); static int fscache_object_slow_work_get_ref(struct slow_work *); static void fscache_object_slow_work_execute(struct slow_work *); -#ifdef CONFIG_SLOW_WORK_PROC +#ifdef CONFIG_SLOW_WORK_DEBUG static void fscache_object_slow_work_desc(struct slow_work *, struct seq_file *); #endif static void fscache_initialise_object(struct fscache_object *); @@ -69,7 +69,7 @@ const struct slow_work_ops fscache_object_slow_work_ops = { .get_ref = fscache_object_slow_work_get_ref, .put_ref = fscache_object_slow_work_put_ref, .execute = fscache_object_slow_work_execute, -#ifdef CONFIG_SLOW_WORK_PROC +#ifdef CONFIG_SLOW_WORK_DEBUG .desc = fscache_object_slow_work_desc, #endif }; @@ -364,7 +364,7 @@ static void fscache_object_slow_work_execute(struct slow_work *work) /* * describe an object for slow-work debugging */ -#ifdef CONFIG_SLOW_WORK_PROC +#ifdef CONFIG_SLOW_WORK_DEBUG static void fscache_object_slow_work_desc(struct slow_work *work, struct seq_file *m) { diff --git a/fs/fscache/operation.c b/fs/fscache/operation.c index 313e79a14266..9f6c928d4586 100644 --- a/fs/fscache/operation.c +++ b/fs/fscache/operation.c @@ -500,7 +500,7 @@ static void fscache_op_execute(struct slow_work *work) /* * describe an operation for slow-work debugging */ -#ifdef CONFIG_SLOW_WORK_PROC +#ifdef CONFIG_SLOW_WORK_DEBUG static void fscache_op_desc(struct slow_work *work, struct seq_file *m) { struct fscache_operation *op = @@ -517,7 +517,7 @@ const struct slow_work_ops fscache_op_slow_work_ops = { .get_ref = fscache_op_get_ref, .put_ref = fscache_op_put_ref, .execute = fscache_op_execute, -#ifdef CONFIG_SLOW_WORK_PROC +#ifdef CONFIG_SLOW_WORK_DEBUG .desc = fscache_op_desc, #endif }; diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index 7be0c6fbe880..c57db27ac861 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -105,7 +105,7 @@ struct fscache_operation { /* operation releaser */ fscache_operation_release_t release; -#ifdef CONFIG_SLOW_WORK_PROC +#ifdef CONFIG_SLOW_WORK_DEBUG const char *name; /* operation name */ const char *state; /* operation state */ #define fscache_set_op_name(OP, N) do { (OP)->name = (N); } while(0) diff --git a/kernel/slow-work.h b/kernel/slow-work.h index 321f3c59d732..a29ebd1ef41d 100644 --- a/kernel/slow-work.h +++ b/kernel/slow-work.h @@ -43,28 +43,28 @@ extern void slow_work_new_thread_desc(struct slow_work *, struct seq_file *); */ static inline void slow_work_set_thread_pid(int id, pid_t pid) { -#ifdef CONFIG_SLOW_WORK_PROC +#ifdef CONFIG_SLOW_WORK_DEBUG slow_work_pids[id] = pid; #endif } static inline void slow_work_mark_time(struct slow_work *work) { -#ifdef CONFIG_SLOW_WORK_PROC +#ifdef CONFIG_SLOW_WORK_DEBUG work->mark = CURRENT_TIME; #endif } static inline void slow_work_begin_exec(int id, struct slow_work *work) { -#ifdef CONFIG_SLOW_WORK_PROC +#ifdef CONFIG_SLOW_WORK_DEBUG slow_work_execs[id] = work; #endif } static inline void slow_work_end_exec(int id, struct slow_work *work) { -#ifdef CONFIG_SLOW_WORK_PROC +#ifdef CONFIG_SLOW_WORK_DEBUG write_lock(&slow_work_execs_lock); slow_work_execs[id] = NULL; write_unlock(&slow_work_execs_lock); -- cgit From de329820e920cd9cfbc2127cad26a37026260cce Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 29 Mar 2010 14:30:19 -0700 Subject: ext3: fix broken handling of EXT3_STATE_NEW In commit 9df93939b735 ("ext3: Use bitops to read/modify EXT3_I(inode)->i_state") ext3 changed its internal 'i_state' variable to use bitops for its state handling. However, unline the same ext4 change, it didn't actually change the name of the field when it changed the semantics of it. As a result, an old use of 'i_state' remained in fs/ext3/ialloc.c that initialized the field to EXT3_STATE_NEW. And that does not work _at_all_ when we're now working with individually named bits rather than values that get masked. So the code tried to mark the state to be new, but in actual fact set the field to EXT3_STATE_JDATA. Which makes no sense at all, and screws up all the code that checks whether the inode was newly allocated. In particular, it made the xattr code unhappy, and caused various random behavior, like apparently https://bugzilla.redhat.com/show_bug.cgi?id=577911 So fix the initialization, and rename the field to match ext4 so that we don't have this happen again. Cc: James Morris Cc: Stephen Smalley Cc: Daniel J Walsh Cc: Eric Paris Cc: Jan Kara Signed-off-by: Linus Torvalds --- fs/ext3/ialloc.c | 4 +++- fs/ext3/inode.c | 2 +- include/linux/ext3_fs.h | 6 +++--- include/linux/ext3_fs_i.h | 2 +- 4 files changed, 8 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/fs/ext3/ialloc.c b/fs/ext3/ialloc.c index ef9008b885b5..0d0e97ed3ff6 100644 --- a/fs/ext3/ialloc.c +++ b/fs/ext3/ialloc.c @@ -582,7 +582,9 @@ got: inode->i_generation = sbi->s_next_generation++; spin_unlock(&sbi->s_next_gen_lock); - ei->i_state = EXT3_STATE_NEW; + ei->i_state_flags = 0; + ext3_set_inode_state(inode, EXT3_STATE_NEW); + ei->i_extra_isize = (EXT3_INODE_SIZE(inode->i_sb) > EXT3_GOOD_OLD_INODE_SIZE) ? sizeof(struct ext3_inode) - EXT3_GOOD_OLD_INODE_SIZE : 0; diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index 7f920b7263a4..ea33bdf0a300 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -2811,7 +2811,7 @@ struct inode *ext3_iget(struct super_block *sb, unsigned long ino) inode->i_mtime.tv_sec = (signed)le32_to_cpu(raw_inode->i_mtime); inode->i_atime.tv_nsec = inode->i_ctime.tv_nsec = inode->i_mtime.tv_nsec = 0; - ei->i_state = 0; + ei->i_state_flags = 0; ei->i_dir_start_lookup = 0; ei->i_dtime = le32_to_cpu(raw_inode->i_dtime); /* We now have enough fields to check if the inode was active or not. diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h index cac84b006667..5f494b465097 100644 --- a/include/linux/ext3_fs.h +++ b/include/linux/ext3_fs.h @@ -565,17 +565,17 @@ enum { static inline int ext3_test_inode_state(struct inode *inode, int bit) { - return test_bit(bit, &EXT3_I(inode)->i_state); + return test_bit(bit, &EXT3_I(inode)->i_state_flags); } static inline void ext3_set_inode_state(struct inode *inode, int bit) { - set_bit(bit, &EXT3_I(inode)->i_state); + set_bit(bit, &EXT3_I(inode)->i_state_flags); } static inline void ext3_clear_inode_state(struct inode *inode, int bit) { - clear_bit(bit, &EXT3_I(inode)->i_state); + clear_bit(bit, &EXT3_I(inode)->i_state_flags); } #else /* Assume that user mode programs are passing in an ext3fs superblock, not diff --git a/include/linux/ext3_fs_i.h b/include/linux/ext3_fs_i.h index 7679acdb519a..f42c098aed8d 100644 --- a/include/linux/ext3_fs_i.h +++ b/include/linux/ext3_fs_i.h @@ -87,7 +87,7 @@ struct ext3_inode_info { * near to their parent directory's inode. */ __u32 i_block_group; - unsigned long i_state; /* Dynamic state flags for ext3 */ + unsigned long i_state_flags; /* Dynamic state flags for ext3 */ /* block reservation info */ struct ext3_block_alloc_info *i_block_alloc_info; -- cgit