From d0959024d8fb6555ba8bfdc6624cc7b7c2e675fd Mon Sep 17 00:00:00 2001 From: Richard Kennedy Date: Wed, 20 Oct 2010 15:57:30 -0700 Subject: timer_list: Remove alignment padding on 64 bit when CONFIG_TIMER_STATS Reorder struct timer_list to remove 8 bytes of alignment padding on 64 bit builds when CONFIG_TIMER_STATS is selected. timer_list is widely used across the kernel so many structures will benefit and shrink in size. For example, with my config on x86_64 per_cpu_dm_data shrinks from 136 to 128 bytes and ahci_port_priv shrinks from 1032 to 968 bytes. Signed-off-by: Richard Kennedy Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Thomas Gleixner --- include/linux/timer.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/timer.h b/include/linux/timer.h index 38cf093ef62c..f3dccdb44f95 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -24,9 +24,9 @@ struct timer_list { int slack; #ifdef CONFIG_TIMER_STATS + int start_pid; void *start_site; char start_comm[16]; - int start_pid; #endif #ifdef CONFIG_LOCKDEP struct lockdep_map lockdep_map; -- cgit v1.2.3 From aaabe31c25a439b92cc281b14ca18b85bae7e7a6 Mon Sep 17 00:00:00 2001 From: Changli Gao Date: Wed, 20 Oct 2010 15:57:30 -0700 Subject: timer: Initialize the field slack of timer_list TIMER_INITIALIZER() should initialize the field slack of timer_list as __init_timer() does. Signed-off-by: Changli Gao Cc: Arjan van de Ven Signed-off-by: Andrew Morton Signed-off-by: Thomas Gleixner --- include/linux/timer.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/timer.h b/include/linux/timer.h index f3dccdb44f95..1794674c1a52 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -54,6 +54,7 @@ extern struct tvec_base boot_tvec_bases; .expires = (_expires), \ .data = (_data), \ .base = &boot_tvec_bases, \ + .slack = -1, \ __TIMER_LOCKDEP_MAP_INITIALIZER( \ __FILE__ ":" __stringify(__LINE__)) \ } -- cgit v1.2.3 From dd6414b50fa2b1cd247a8aa8f8bd42414b7453e1 Mon Sep 17 00:00:00 2001 From: Phil Carmody Date: Wed, 20 Oct 2010 15:57:33 -0700 Subject: timer: Permit statically-declared work with deferrable timers Currently, you have to just define a delayed_work uninitialised, and then initialise it before first use. That's a tad clumsy. At risk of playing mind-games with the compiler, fooling it into doing pointer arithmetic with compile-time-constants, this lets clients properly initialise delayed work with deferrable timers statically. This patch was inspired by the issues which lead Artem Bityutskiy to commit 8eab945c5616fc984 ("sunrpc: make the cache cleaner workqueue deferrable"). Signed-off-by: Phil Carmody Acked-by: Artem Bityutskiy Cc: Arjan van de Ven Signed-off-by: Andrew Morton Signed-off-by: Thomas Gleixner --- include/linux/timer.h | 25 +++++++++++++++++++++++++ include/linux/workqueue.h | 8 ++++++++ kernel/timer.c | 15 +-------------- 3 files changed, 34 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timer.h b/include/linux/timer.h index 1794674c1a52..cbfb7a355d30 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -48,6 +48,18 @@ extern struct tvec_base boot_tvec_bases; #define __TIMER_LOCKDEP_MAP_INITIALIZER(_kn) #endif +/* + * Note that all tvec_bases are 2 byte aligned and lower bit of + * base in timer_list is guaranteed to be zero. Use the LSB to + * indicate whether the timer is deferrable. + * + * A deferrable timer will work normally when the system is busy, but + * will not cause a CPU to come out of idle just to service it; instead, + * the timer will be serviced when the CPU eventually wakes up with a + * subsequent non-deferrable timer. + */ +#define TBASE_DEFERRABLE_FLAG (0x1) + #define TIMER_INITIALIZER(_function, _expires, _data) { \ .entry = { .prev = TIMER_ENTRY_STATIC }, \ .function = (_function), \ @@ -59,6 +71,19 @@ extern struct tvec_base boot_tvec_bases; __FILE__ ":" __stringify(__LINE__)) \ } +#define TBASE_MAKE_DEFERRED(ptr) ((struct tvec_base *) \ + ((unsigned char *)(ptr) + TBASE_DEFERRABLE_FLAG)) + +#define TIMER_DEFERRED_INITIALIZER(_function, _expires, _data) {\ + .entry = { .prev = TIMER_ENTRY_STATIC }, \ + .function = (_function), \ + .expires = (_expires), \ + .data = (_data), \ + .base = TBASE_MAKE_DEFERRED(&boot_tvec_bases), \ + __TIMER_LOCKDEP_MAP_INITIALIZER( \ + __FILE__ ":" __stringify(__LINE__)) \ + } + #define DEFINE_TIMER(_name, _function, _expires, _data) \ struct timer_list _name = \ TIMER_INITIALIZER(_function, _expires, _data) diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index f11100f96482..88238c15ec3e 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -127,12 +127,20 @@ struct execute_work { .timer = TIMER_INITIALIZER(NULL, 0, 0), \ } +#define __DEFERRED_WORK_INITIALIZER(n, f) { \ + .work = __WORK_INITIALIZER((n).work, (f)), \ + .timer = TIMER_DEFERRED_INITIALIZER(NULL, 0, 0), \ + } + #define DECLARE_WORK(n, f) \ struct work_struct n = __WORK_INITIALIZER(n, f) #define DECLARE_DELAYED_WORK(n, f) \ struct delayed_work n = __DELAYED_WORK_INITIALIZER(n, f) +#define DECLARE_DEFERRED_WORK(n, f) \ + struct delayed_work n = __DEFERRED_WORK_INITIALIZER(n, f) + /* * initialize a work item's function pointer */ diff --git a/kernel/timer.c b/kernel/timer.c index 97bf05baade7..72853b256ff2 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -88,18 +88,6 @@ struct tvec_base boot_tvec_bases; EXPORT_SYMBOL(boot_tvec_bases); static DEFINE_PER_CPU(struct tvec_base *, tvec_bases) = &boot_tvec_bases; -/* - * Note that all tvec_bases are 2 byte aligned and lower bit of - * base in timer_list is guaranteed to be zero. Use the LSB to - * indicate whether the timer is deferrable. - * - * A deferrable timer will work normally when the system is busy, but - * will not cause a CPU to come out of idle just to service it; instead, - * the timer will be serviced when the CPU eventually wakes up with a - * subsequent non-deferrable timer. - */ -#define TBASE_DEFERRABLE_FLAG (0x1) - /* Functions below help us manage 'deferrable' flag */ static inline unsigned int tbase_get_deferrable(struct tvec_base *base) { @@ -113,8 +101,7 @@ static inline struct tvec_base *tbase_get_base(struct tvec_base *base) static inline void timer_set_deferrable(struct timer_list *timer) { - timer->base = ((struct tvec_base *)((unsigned long)(timer->base) | - TBASE_DEFERRABLE_FLAG)); + timer->base = TBASE_MAKE_DEFERRED(timer->base); } static inline void -- cgit v1.2.3 From 6f1bc451e6a79470b122a37ee1fc6bbca450f444 Mon Sep 17 00:00:00 2001 From: Yong Zhang Date: Wed, 20 Oct 2010 15:57:31 -0700 Subject: timer: Make try_to_del_timer_sync() the same on SMP and UP On UP try_to_del_timer_sync() is mapped to del_timer() which does not take the running timer callback into account, so it has different semantics. Remove the SMP dependency of try_to_del_timer_sync() by using base->running_timer in the UP case as well. [ tglx: Removed set_running_timer() inline and tweaked the changelog ] Signed-off-by: Yong Zhang Cc: Ingo Molnar Cc: Peter Zijlstra Acked-by: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Thomas Gleixner --- include/linux/timer.h | 4 ++-- kernel/timer.c | 17 +++-------------- 2 files changed, 5 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timer.h b/include/linux/timer.h index cbfb7a355d30..6abd9138beda 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -274,11 +274,11 @@ static inline void timer_stats_timer_clear_start_info(struct timer_list *timer) extern void add_timer(struct timer_list *timer); +extern int try_to_del_timer_sync(struct timer_list *timer); + #ifdef CONFIG_SMP - extern int try_to_del_timer_sync(struct timer_list *timer); extern int del_timer_sync(struct timer_list *timer); #else -# define try_to_del_timer_sync(t) del_timer(t) # define del_timer_sync(t) del_timer(t) #endif diff --git a/kernel/timer.c b/kernel/timer.c index 72853b256ff2..47b86c1e3226 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -330,15 +330,6 @@ void set_timer_slack(struct timer_list *timer, int slack_hz) } EXPORT_SYMBOL_GPL(set_timer_slack); - -static inline void set_running_timer(struct tvec_base *base, - struct timer_list *timer) -{ -#ifdef CONFIG_SMP - base->running_timer = timer; -#endif -} - static void internal_add_timer(struct tvec_base *base, struct timer_list *timer) { unsigned long expires = timer->expires; @@ -923,15 +914,12 @@ int del_timer(struct timer_list *timer) } EXPORT_SYMBOL(del_timer); -#ifdef CONFIG_SMP /** * try_to_del_timer_sync - Try to deactivate a timer * @timer: timer do del * * This function tries to deactivate a timer. Upon successful (ret >= 0) * exit the timer is not queued and the handler is not running on any CPU. - * - * It must not be called from interrupt contexts. */ int try_to_del_timer_sync(struct timer_list *timer) { @@ -960,6 +948,7 @@ out: } EXPORT_SYMBOL(try_to_del_timer_sync); +#ifdef CONFIG_SMP /** * del_timer_sync - deactivate a timer and wait for the handler to finish. * @timer: the timer to be deactivated @@ -1098,7 +1087,7 @@ static inline void __run_timers(struct tvec_base *base) timer_stats_account_timer(timer); - set_running_timer(base, timer); + base->running_timer = timer; detach_timer(timer, 1); spin_unlock_irq(&base->lock); @@ -1106,7 +1095,7 @@ static inline void __run_timers(struct tvec_base *base) spin_lock_irq(&base->lock); } } - set_running_timer(base, NULL); + base->running_timer = NULL; spin_unlock_irq(&base->lock); } -- cgit v1.2.3 From fe7de49f9d4e53f24ec9ef762a503f70b562341c Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Wed, 20 Oct 2010 16:01:12 -0700 Subject: sched: Make sched_param argument static in sched_setscheduler() callers Andrew Morton pointed out almost all sched_setscheduler() callers are using fixed parameters and can be converted to static. It reduces runtime memory use a little. Signed-off-by: KOSAKI Motohiro Reported-by: Andrew Morton Acked-by: James Morris Cc: Ingo Molnar Cc: Steven Rostedt Signed-off-by: Andrew Morton Signed-off-by: Thomas Gleixner Signed-off-by: Ingo Molnar --- include/linux/sched.h | 5 +++-- kernel/irq/manage.c | 4 +++- kernel/kthread.c | 2 +- kernel/sched.c | 6 +++--- kernel/softirq.c | 4 +++- kernel/trace/trace_selftest.c | 2 +- kernel/watchdog.c | 2 +- 7 files changed, 15 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 0383601a927c..849c8670583d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1942,9 +1942,10 @@ extern int task_nice(const struct task_struct *p); extern int can_nice(const struct task_struct *p, const int nice); extern int task_curr(const struct task_struct *p); extern int idle_cpu(int cpu); -extern int sched_setscheduler(struct task_struct *, int, struct sched_param *); +extern int sched_setscheduler(struct task_struct *, int, + const struct sched_param *); extern int sched_setscheduler_nocheck(struct task_struct *, int, - struct sched_param *); + const struct sched_param *); extern struct task_struct *idle_task(int cpu); extern struct task_struct *curr_task(int cpu); extern void set_curr_task(int cpu, struct task_struct *p); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 644e8d5fa367..850f030fa0c2 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -573,7 +573,9 @@ irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action) { } */ static int irq_thread(void *data) { - struct sched_param param = { .sched_priority = MAX_USER_RT_PRIO/2, }; + static struct sched_param param = { + .sched_priority = MAX_USER_RT_PRIO/2, + }; struct irqaction *action = data; struct irq_desc *desc = irq_to_desc(action->irq); int wake, oneshot = desc->status & IRQ_ONESHOT; diff --git a/kernel/kthread.c b/kernel/kthread.c index 2dc3786349d1..74cf6f5e7ade 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -148,7 +148,7 @@ struct task_struct *kthread_create(int (*threadfn)(void *data), wait_for_completion(&create.done); if (!IS_ERR(create.result)) { - struct sched_param param = { .sched_priority = 0 }; + static struct sched_param param = { .sched_priority = 0 }; va_list args; va_start(args, namefmt); diff --git a/kernel/sched.c b/kernel/sched.c index d42992bccdfa..51944e8c38a8 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -4701,7 +4701,7 @@ static bool check_same_owner(struct task_struct *p) } static int __sched_setscheduler(struct task_struct *p, int policy, - struct sched_param *param, bool user) + const struct sched_param *param, bool user) { int retval, oldprio, oldpolicy = -1, on_rq, running; unsigned long flags; @@ -4856,7 +4856,7 @@ recheck: * NOTE that the task may be already dead. */ int sched_setscheduler(struct task_struct *p, int policy, - struct sched_param *param) + const struct sched_param *param) { return __sched_setscheduler(p, policy, param, true); } @@ -4874,7 +4874,7 @@ EXPORT_SYMBOL_GPL(sched_setscheduler); * but our caller might not have that capability. */ int sched_setscheduler_nocheck(struct task_struct *p, int policy, - struct sched_param *param) + const struct sched_param *param) { return __sched_setscheduler(p, policy, param, false); } diff --git a/kernel/softirq.c b/kernel/softirq.c index fc978889b194..081869ed3a9f 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -851,7 +851,9 @@ static int __cpuinit cpu_callback(struct notifier_block *nfb, cpumask_any(cpu_online_mask)); case CPU_DEAD: case CPU_DEAD_FROZEN: { - struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 }; + static struct sched_param param = { + .sched_priority = MAX_RT_PRIO-1 + }; p = per_cpu(ksoftirqd, hotcpu); per_cpu(ksoftirqd, hotcpu) = NULL; diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index 155a415b3209..562c56e048fd 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -558,7 +558,7 @@ trace_selftest_startup_nop(struct tracer *trace, struct trace_array *tr) static int trace_wakeup_test_thread(void *data) { /* Make this a RT thread, doesn't need to be too high */ - struct sched_param param = { .sched_priority = 5 }; + static struct sched_param param = { .sched_priority = 5 }; struct completion *x = data; sched_setscheduler(current, SCHED_FIFO, ¶m); diff --git a/kernel/watchdog.c b/kernel/watchdog.c index bafba687a6d8..94ca779aa9c2 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -307,7 +307,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) */ static int watchdog(void *unused) { - struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 }; + static struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 }; struct hrtimer *hrtimer = &__raw_get_cpu_var(watchdog_hrtimer); sched_setscheduler(current, SCHED_FIFO, ¶m); -- cgit v1.2.3 From fc766e4c4965915ab52a1d1fa3c7a7b3e7bc07f0 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 29 Oct 2010 03:09:24 +0000 Subject: decnet: RCU conversion and get rid of dev_base_lock While tracking dev_base_lock users, I found decnet used it in dnet_select_source(), but for a wrong purpose: Writers only hold RTNL, not dev_base_lock, so readers must use RCU if they cannot use RTNL. Adds an rcu_head in struct dn_ifaddr and handle proper RCU management. Adds __rcu annotation in dn_route as well. Signed-off-by: Eric Dumazet Acked-by: Steven Whitehouse Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- include/net/dn_dev.h | 27 ++++++++----- include/net/dst.h | 8 ++-- net/decnet/af_decnet.c | 2 +- net/decnet/dn_dev.c | 100 +++++++++++++++++++++++++++------------------- net/decnet/dn_fib.c | 6 ++- net/decnet/dn_neigh.c | 2 +- net/decnet/dn_route.c | 68 +++++++++++++++++-------------- 8 files changed, 127 insertions(+), 88 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d8fd2c23a1b9..578debb801f4 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -951,7 +951,7 @@ struct net_device { #endif void *atalk_ptr; /* AppleTalk link */ struct in_device __rcu *ip_ptr; /* IPv4 specific data */ - void *dn_ptr; /* DECnet specific data */ + struct dn_dev __rcu *dn_ptr; /* DECnet specific data */ struct inet6_dev __rcu *ip6_ptr; /* IPv6 specific data */ void *ec_ptr; /* Econet specific data */ void *ax25_ptr; /* AX.25 specific data */ diff --git a/include/net/dn_dev.h b/include/net/dn_dev.h index 0916bbf3bdff..b9e32db03f20 100644 --- a/include/net/dn_dev.h +++ b/include/net/dn_dev.h @@ -5,13 +5,14 @@ struct dn_dev; struct dn_ifaddr { - struct dn_ifaddr *ifa_next; + struct dn_ifaddr __rcu *ifa_next; struct dn_dev *ifa_dev; __le16 ifa_local; __le16 ifa_address; __u8 ifa_flags; __u8 ifa_scope; char ifa_label[IFNAMSIZ]; + struct rcu_head rcu; }; #define DN_DEV_S_RU 0 /* Run - working normally */ @@ -83,7 +84,7 @@ struct dn_dev_parms { struct dn_dev { - struct dn_ifaddr *ifa_list; + struct dn_ifaddr __rcu *ifa_list; struct net_device *dev; struct dn_dev_parms parms; char use_long; @@ -171,19 +172,27 @@ extern int unregister_dnaddr_notifier(struct notifier_block *nb); static inline int dn_dev_islocal(struct net_device *dev, __le16 addr) { - struct dn_dev *dn_db = dev->dn_ptr; + struct dn_dev *dn_db; struct dn_ifaddr *ifa; + int res = 0; + rcu_read_lock(); + dn_db = rcu_dereference(dev->dn_ptr); if (dn_db == NULL) { printk(KERN_DEBUG "dn_dev_islocal: Called for non DECnet device\n"); - return 0; + goto out; } - for(ifa = dn_db->ifa_list; ifa; ifa = ifa->ifa_next) - if ((addr ^ ifa->ifa_local) == 0) - return 1; - - return 0; + for (ifa = rcu_dereference(dn_db->ifa_list); + ifa != NULL; + ifa = rcu_dereference(ifa->ifa_next)) + if ((addr ^ ifa->ifa_local) == 0) { + res = 1; + break; + } +out: + rcu_read_unlock(); + return res; } #endif /* _NET_DN_DEV_H */ diff --git a/include/net/dst.h b/include/net/dst.h index ffe9cb719c0e..a5bd72646d65 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -94,10 +94,10 @@ struct dst_entry { int __use; unsigned long lastuse; union { - struct dst_entry *next; - struct rtable __rcu *rt_next; - struct rt6_info *rt6_next; - struct dn_route *dn_next; + struct dst_entry *next; + struct rtable __rcu *rt_next; + struct rt6_info *rt6_next; + struct dn_route __rcu *dn_next; }; }; diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index d6b93d19790f..18b8a2cbdf77 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -1848,7 +1848,7 @@ unsigned dn_mss_from_pmtu(struct net_device *dev, int mtu) { unsigned mss = 230 - DN_MAX_NSP_DATA_HEADER; if (dev) { - struct dn_dev *dn_db = dev->dn_ptr; + struct dn_dev *dn_db = rcu_dereference_raw(dev->dn_ptr); mtu -= LL_RESERVED_SPACE(dev); if (dn_db->use_long) mtu -= 21; diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index 4c409b46aa35..0ba15633c418 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -267,7 +267,7 @@ static int dn_forwarding_proc(ctl_table *table, int write, if (table->extra1 == NULL) return -EINVAL; - dn_db = dev->dn_ptr; + dn_db = rcu_dereference_raw(dev->dn_ptr); old = dn_db->parms.forwarding; err = proc_dointvec(table, write, buffer, lenp, ppos); @@ -332,14 +332,19 @@ static struct dn_ifaddr *dn_dev_alloc_ifa(void) return ifa; } -static __inline__ void dn_dev_free_ifa(struct dn_ifaddr *ifa) +static void dn_dev_free_ifa_rcu(struct rcu_head *head) { - kfree(ifa); + kfree(container_of(head, struct dn_ifaddr, rcu)); } -static void dn_dev_del_ifa(struct dn_dev *dn_db, struct dn_ifaddr **ifap, int destroy) +static void dn_dev_free_ifa(struct dn_ifaddr *ifa) { - struct dn_ifaddr *ifa1 = *ifap; + call_rcu(&ifa->rcu, dn_dev_free_ifa_rcu); +} + +static void dn_dev_del_ifa(struct dn_dev *dn_db, struct dn_ifaddr __rcu **ifap, int destroy) +{ + struct dn_ifaddr *ifa1 = rtnl_dereference(*ifap); unsigned char mac_addr[6]; struct net_device *dev = dn_db->dev; @@ -373,7 +378,9 @@ static int dn_dev_insert_ifa(struct dn_dev *dn_db, struct dn_ifaddr *ifa) ASSERT_RTNL(); /* Check for duplicates */ - for(ifa1 = dn_db->ifa_list; ifa1; ifa1 = ifa1->ifa_next) { + for (ifa1 = rtnl_dereference(dn_db->ifa_list); + ifa1 != NULL; + ifa1 = rtnl_dereference(ifa1->ifa_next)) { if (ifa1->ifa_local == ifa->ifa_local) return -EEXIST; } @@ -386,7 +393,7 @@ static int dn_dev_insert_ifa(struct dn_dev *dn_db, struct dn_ifaddr *ifa) } ifa->ifa_next = dn_db->ifa_list; - dn_db->ifa_list = ifa; + rcu_assign_pointer(dn_db->ifa_list, ifa); dn_ifaddr_notify(RTM_NEWADDR, ifa); blocking_notifier_call_chain(&dnaddr_chain, NETDEV_UP, ifa); @@ -396,7 +403,7 @@ static int dn_dev_insert_ifa(struct dn_dev *dn_db, struct dn_ifaddr *ifa) static int dn_dev_set_ifa(struct net_device *dev, struct dn_ifaddr *ifa) { - struct dn_dev *dn_db = dev->dn_ptr; + struct dn_dev *dn_db = rtnl_dereference(dev->dn_ptr); int rv; if (dn_db == NULL) { @@ -425,7 +432,8 @@ int dn_dev_ioctl(unsigned int cmd, void __user *arg) struct sockaddr_dn *sdn = (struct sockaddr_dn *)&ifr->ifr_addr; struct dn_dev *dn_db; struct net_device *dev; - struct dn_ifaddr *ifa = NULL, **ifap = NULL; + struct dn_ifaddr *ifa = NULL; + struct dn_ifaddr __rcu **ifap = NULL; int ret = 0; if (copy_from_user(ifr, arg, DN_IFREQ_SIZE)) @@ -454,8 +462,10 @@ int dn_dev_ioctl(unsigned int cmd, void __user *arg) goto done; } - if ((dn_db = dev->dn_ptr) != NULL) { - for (ifap = &dn_db->ifa_list; (ifa=*ifap) != NULL; ifap = &ifa->ifa_next) + if ((dn_db = rtnl_dereference(dev->dn_ptr)) != NULL) { + for (ifap = &dn_db->ifa_list; + (ifa = rtnl_dereference(*ifap)) != NULL; + ifap = &ifa->ifa_next) if (strcmp(ifr->ifr_name, ifa->ifa_label) == 0) break; } @@ -558,7 +568,7 @@ static struct dn_dev *dn_dev_by_index(int ifindex) dev = __dev_get_by_index(&init_net, ifindex); if (dev) - dn_dev = dev->dn_ptr; + dn_dev = rtnl_dereference(dev->dn_ptr); return dn_dev; } @@ -576,7 +586,8 @@ static int dn_nl_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) struct nlattr *tb[IFA_MAX+1]; struct dn_dev *dn_db; struct ifaddrmsg *ifm; - struct dn_ifaddr *ifa, **ifap; + struct dn_ifaddr *ifa; + struct dn_ifaddr __rcu **ifap; int err = -EINVAL; if (!net_eq(net, &init_net)) @@ -592,7 +603,9 @@ static int dn_nl_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) goto errout; err = -EADDRNOTAVAIL; - for (ifap = &dn_db->ifa_list; (ifa = *ifap); ifap = &ifa->ifa_next) { + for (ifap = &dn_db->ifa_list; + (ifa = rtnl_dereference(*ifap)) != NULL; + ifap = &ifa->ifa_next) { if (tb[IFA_LOCAL] && nla_memcmp(tb[IFA_LOCAL], &ifa->ifa_local, 2)) continue; @@ -632,7 +645,7 @@ static int dn_nl_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) if ((dev = __dev_get_by_index(&init_net, ifm->ifa_index)) == NULL) return -ENODEV; - if ((dn_db = dev->dn_ptr) == NULL) { + if ((dn_db = rtnl_dereference(dev->dn_ptr)) == NULL) { dn_db = dn_dev_create(dev, &err); if (!dn_db) return err; @@ -748,11 +761,11 @@ static int dn_nl_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) skip_naddr = 0; } - if ((dn_db = dev->dn_ptr) == NULL) + if ((dn_db = rtnl_dereference(dev->dn_ptr)) == NULL) goto cont; - for (ifa = dn_db->ifa_list, dn_idx = 0; ifa; - ifa = ifa->ifa_next, dn_idx++) { + for (ifa = rtnl_dereference(dn_db->ifa_list), dn_idx = 0; ifa; + ifa = rtnl_dereference(ifa->ifa_next), dn_idx++) { if (dn_idx < skip_naddr) continue; @@ -773,21 +786,22 @@ done: static int dn_dev_get_first(struct net_device *dev, __le16 *addr) { - struct dn_dev *dn_db = (struct dn_dev *)dev->dn_ptr; + struct dn_dev *dn_db; struct dn_ifaddr *ifa; int rv = -ENODEV; + rcu_read_lock(); + dn_db = rcu_dereference(dev->dn_ptr); if (dn_db == NULL) goto out; - rtnl_lock(); - ifa = dn_db->ifa_list; + ifa = rcu_dereference(dn_db->ifa_list); if (ifa != NULL) { *addr = ifa->ifa_local; rv = 0; } - rtnl_unlock(); out: + rcu_read_unlock(); return rv; } @@ -823,7 +837,7 @@ static void dn_send_endnode_hello(struct net_device *dev, struct dn_ifaddr *ifa) struct endnode_hello_message *msg; struct sk_buff *skb = NULL; __le16 *pktlen; - struct dn_dev *dn_db = (struct dn_dev *)dev->dn_ptr; + struct dn_dev *dn_db = rcu_dereference_raw(dev->dn_ptr); if ((skb = dn_alloc_skb(NULL, sizeof(*msg), GFP_ATOMIC)) == NULL) return; @@ -889,7 +903,7 @@ static int dn_am_i_a_router(struct dn_neigh *dn, struct dn_dev *dn_db, struct dn static void dn_send_router_hello(struct net_device *dev, struct dn_ifaddr *ifa) { int n; - struct dn_dev *dn_db = dev->dn_ptr; + struct dn_dev *dn_db = rcu_dereference_raw(dev->dn_ptr); struct dn_neigh *dn = (struct dn_neigh *)dn_db->router; struct sk_buff *skb; size_t size; @@ -960,7 +974,7 @@ static void dn_send_router_hello(struct net_device *dev, struct dn_ifaddr *ifa) static void dn_send_brd_hello(struct net_device *dev, struct dn_ifaddr *ifa) { - struct dn_dev *dn_db = (struct dn_dev *)dev->dn_ptr; + struct dn_dev *dn_db = rcu_dereference_raw(dev->dn_ptr); if (dn_db->parms.forwarding == 0) dn_send_endnode_hello(dev, ifa); @@ -998,7 +1012,7 @@ static void dn_send_ptp_hello(struct net_device *dev, struct dn_ifaddr *ifa) static int dn_eth_up(struct net_device *dev) { - struct dn_dev *dn_db = dev->dn_ptr; + struct dn_dev *dn_db = rcu_dereference_raw(dev->dn_ptr); if (dn_db->parms.forwarding == 0) dev_mc_add(dev, dn_rt_all_end_mcast); @@ -1012,7 +1026,7 @@ static int dn_eth_up(struct net_device *dev) static void dn_eth_down(struct net_device *dev) { - struct dn_dev *dn_db = dev->dn_ptr; + struct dn_dev *dn_db = rcu_dereference_raw(dev->dn_ptr); if (dn_db->parms.forwarding == 0) dev_mc_del(dev, dn_rt_all_end_mcast); @@ -1025,12 +1039,16 @@ static void dn_dev_set_timer(struct net_device *dev); static void dn_dev_timer_func(unsigned long arg) { struct net_device *dev = (struct net_device *)arg; - struct dn_dev *dn_db = dev->dn_ptr; + struct dn_dev *dn_db; struct dn_ifaddr *ifa; + rcu_read_lock(); + dn_db = rcu_dereference(dev->dn_ptr); if (dn_db->t3 <= dn_db->parms.t2) { if (dn_db->parms.timer3) { - for(ifa = dn_db->ifa_list; ifa; ifa = ifa->ifa_next) { + for (ifa = rcu_dereference(dn_db->ifa_list); + ifa; + ifa = rcu_dereference(ifa->ifa_next)) { if (!(ifa->ifa_flags & IFA_F_SECONDARY)) dn_db->parms.timer3(dev, ifa); } @@ -1039,13 +1057,13 @@ static void dn_dev_timer_func(unsigned long arg) } else { dn_db->t3 -= dn_db->parms.t2; } - + rcu_read_unlock(); dn_dev_set_timer(dev); } static void dn_dev_set_timer(struct net_device *dev) { - struct dn_dev *dn_db = dev->dn_ptr; + struct dn_dev *dn_db = rcu_dereference_raw(dev->dn_ptr); if (dn_db->parms.t2 > dn_db->parms.t3) dn_db->parms.t2 = dn_db->parms.t3; @@ -1077,8 +1095,8 @@ static struct dn_dev *dn_dev_create(struct net_device *dev, int *err) return NULL; memcpy(&dn_db->parms, p, sizeof(struct dn_dev_parms)); - smp_wmb(); - dev->dn_ptr = dn_db; + + rcu_assign_pointer(dev->dn_ptr, dn_db); dn_db->dev = dev; init_timer(&dn_db->timer); @@ -1086,7 +1104,7 @@ static struct dn_dev *dn_dev_create(struct net_device *dev, int *err) dn_db->neigh_parms = neigh_parms_alloc(dev, &dn_neigh_table); if (!dn_db->neigh_parms) { - dev->dn_ptr = NULL; + rcu_assign_pointer(dev->dn_ptr, NULL); kfree(dn_db); return NULL; } @@ -1125,7 +1143,7 @@ void dn_dev_up(struct net_device *dev) struct dn_ifaddr *ifa; __le16 addr = decnet_address; int maybe_default = 0; - struct dn_dev *dn_db = (struct dn_dev *)dev->dn_ptr; + struct dn_dev *dn_db = rtnl_dereference(dev->dn_ptr); if ((dev->type != ARPHRD_ETHER) && (dev->type != ARPHRD_LOOPBACK)) return; @@ -1176,7 +1194,7 @@ void dn_dev_up(struct net_device *dev) static void dn_dev_delete(struct net_device *dev) { - struct dn_dev *dn_db = dev->dn_ptr; + struct dn_dev *dn_db = rtnl_dereference(dev->dn_ptr); if (dn_db == NULL) return; @@ -1204,13 +1222,13 @@ static void dn_dev_delete(struct net_device *dev) void dn_dev_down(struct net_device *dev) { - struct dn_dev *dn_db = dev->dn_ptr; + struct dn_dev *dn_db = rtnl_dereference(dev->dn_ptr); struct dn_ifaddr *ifa; if (dn_db == NULL) return; - while((ifa = dn_db->ifa_list) != NULL) { + while ((ifa = rtnl_dereference(dn_db->ifa_list)) != NULL) { dn_dev_del_ifa(dn_db, &dn_db->ifa_list, 0); dn_dev_free_ifa(ifa); } @@ -1270,7 +1288,7 @@ static inline int is_dn_dev(struct net_device *dev) } static void *dn_dev_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(rcu) + __acquires(RCU) { int i; struct net_device *dev; @@ -1313,7 +1331,7 @@ static void *dn_dev_seq_next(struct seq_file *seq, void *v, loff_t *pos) } static void dn_dev_seq_stop(struct seq_file *seq, void *v) - __releases(rcu) + __releases(RCU) { rcu_read_unlock(); } @@ -1340,7 +1358,7 @@ static int dn_dev_seq_show(struct seq_file *seq, void *v) struct net_device *dev = v; char peer_buf[DN_ASCBUF_LEN]; char router_buf[DN_ASCBUF_LEN]; - struct dn_dev *dn_db = dev->dn_ptr; + struct dn_dev *dn_db = rcu_dereference(dev->dn_ptr); seq_printf(seq, "%-8s %1s %04u %04u %04lu %04lu" " %04hu %03d %02x %-10s %-7s %-7s\n", diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c index 4ab96c15166d..0ef0a81bcd72 100644 --- a/net/decnet/dn_fib.c +++ b/net/decnet/dn_fib.c @@ -610,10 +610,12 @@ static void dn_fib_del_ifaddr(struct dn_ifaddr *ifa) /* Scan device list */ rcu_read_lock(); for_each_netdev_rcu(&init_net, dev) { - dn_db = dev->dn_ptr; + dn_db = rcu_dereference(dev->dn_ptr); if (dn_db == NULL) continue; - for(ifa2 = dn_db->ifa_list; ifa2; ifa2 = ifa2->ifa_next) { + for (ifa2 = rcu_dereference(dn_db->ifa_list); + ifa2 != NULL; + ifa2 = rcu_dereference(ifa2->ifa_next)) { if (ifa2->ifa_local == ifa->ifa_local) { found_it = 1; break; diff --git a/net/decnet/dn_neigh.c b/net/decnet/dn_neigh.c index a085dbcf5c7f..602dade7e9a3 100644 --- a/net/decnet/dn_neigh.c +++ b/net/decnet/dn_neigh.c @@ -391,7 +391,7 @@ int dn_neigh_router_hello(struct sk_buff *skb) write_lock(&neigh->lock); neigh->used = jiffies; - dn_db = (struct dn_dev *)neigh->dev->dn_ptr; + dn_db = rcu_dereference(neigh->dev->dn_ptr); if (!(neigh->nud_state & NUD_PERMANENT)) { neigh->updated = jiffies; diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index df0f3e54ff8a..94a9eb1d313e 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -93,7 +93,7 @@ struct dn_rt_hash_bucket { - struct dn_route *chain; + struct dn_route __rcu *chain; spinlock_t lock; }; @@ -157,15 +157,17 @@ static inline void dnrt_drop(struct dn_route *rt) static void dn_dst_check_expire(unsigned long dummy) { int i; - struct dn_route *rt, **rtp; + struct dn_route *rt; + struct dn_route __rcu **rtp; unsigned long now = jiffies; unsigned long expire = 120 * HZ; - for(i = 0; i <= dn_rt_hash_mask; i++) { + for (i = 0; i <= dn_rt_hash_mask; i++) { rtp = &dn_rt_hash_table[i].chain; spin_lock(&dn_rt_hash_table[i].lock); - while((rt=*rtp) != NULL) { + while ((rt = rcu_dereference_protected(*rtp, + lockdep_is_held(&dn_rt_hash_table[i].lock))) != NULL) { if (atomic_read(&rt->dst.__refcnt) || (now - rt->dst.lastuse) < expire) { rtp = &rt->dst.dn_next; @@ -186,17 +188,19 @@ static void dn_dst_check_expire(unsigned long dummy) static int dn_dst_gc(struct dst_ops *ops) { - struct dn_route *rt, **rtp; + struct dn_route *rt; + struct dn_route __rcu **rtp; int i; unsigned long now = jiffies; unsigned long expire = 10 * HZ; - for(i = 0; i <= dn_rt_hash_mask; i++) { + for (i = 0; i <= dn_rt_hash_mask; i++) { spin_lock_bh(&dn_rt_hash_table[i].lock); rtp = &dn_rt_hash_table[i].chain; - while((rt=*rtp) != NULL) { + while ((rt = rcu_dereference_protected(*rtp, + lockdep_is_held(&dn_rt_hash_table[i].lock))) != NULL) { if (atomic_read(&rt->dst.__refcnt) || (now - rt->dst.lastuse) < expire) { rtp = &rt->dst.dn_next; @@ -227,7 +231,7 @@ static void dn_dst_update_pmtu(struct dst_entry *dst, u32 mtu) { u32 min_mtu = 230; struct dn_dev *dn = dst->neighbour ? - (struct dn_dev *)dst->neighbour->dev->dn_ptr : NULL; + rcu_dereference_raw(dst->neighbour->dev->dn_ptr) : NULL; if (dn && dn->use_long == 0) min_mtu -= 6; @@ -277,13 +281,15 @@ static inline int compare_keys(struct flowi *fl1, struct flowi *fl2) static int dn_insert_route(struct dn_route *rt, unsigned hash, struct dn_route **rp) { - struct dn_route *rth, **rthp; + struct dn_route *rth; + struct dn_route __rcu **rthp; unsigned long now = jiffies; rthp = &dn_rt_hash_table[hash].chain; spin_lock_bh(&dn_rt_hash_table[hash].lock); - while((rth = *rthp) != NULL) { + while ((rth = rcu_dereference_protected(*rthp, + lockdep_is_held(&dn_rt_hash_table[hash].lock))) != NULL) { if (compare_keys(&rth->fl, &rt->fl)) { /* Put it first */ *rthp = rth->dst.dn_next; @@ -315,15 +321,15 @@ static void dn_run_flush(unsigned long dummy) int i; struct dn_route *rt, *next; - for(i = 0; i < dn_rt_hash_mask; i++) { + for (i = 0; i < dn_rt_hash_mask; i++) { spin_lock_bh(&dn_rt_hash_table[i].lock); - if ((rt = xchg(&dn_rt_hash_table[i].chain, NULL)) == NULL) + if ((rt = xchg((struct dn_route **)&dn_rt_hash_table[i].chain, NULL)) == NULL) goto nothing_to_declare; - for(; rt; rt=next) { - next = rt->dst.dn_next; - rt->dst.dn_next = NULL; + for(; rt; rt = next) { + next = rcu_dereference_raw(rt->dst.dn_next); + RCU_INIT_POINTER(rt->dst.dn_next, NULL); dst_free((struct dst_entry *)rt); } @@ -458,15 +464,16 @@ static int dn_return_long(struct sk_buff *skb) */ static int dn_route_rx_packet(struct sk_buff *skb) { - struct dn_skb_cb *cb = DN_SKB_CB(skb); + struct dn_skb_cb *cb; int err; if ((err = dn_route_input(skb)) == 0) return dst_input(skb); + cb = DN_SKB_CB(skb); if (decnet_debug_level & 4) { char *devname = skb->dev ? skb->dev->name : "???"; - struct dn_skb_cb *cb = DN_SKB_CB(skb); + printk(KERN_DEBUG "DECnet: dn_route_rx_packet: rt_flags=0x%02x dev=%s len=%d src=0x%04hx dst=0x%04hx err=%d type=%d\n", (int)cb->rt_flags, devname, skb->len, @@ -573,7 +580,7 @@ int dn_route_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type struct dn_skb_cb *cb; unsigned char flags = 0; __u16 len = le16_to_cpu(*(__le16 *)skb->data); - struct dn_dev *dn = (struct dn_dev *)dev->dn_ptr; + struct dn_dev *dn = rcu_dereference(dev->dn_ptr); unsigned char padlen = 0; if (!net_eq(dev_net(dev), &init_net)) @@ -728,7 +735,7 @@ static int dn_forward(struct sk_buff *skb) { struct dn_skb_cb *cb = DN_SKB_CB(skb); struct dst_entry *dst = skb_dst(skb); - struct dn_dev *dn_db = dst->dev->dn_ptr; + struct dn_dev *dn_db = rcu_dereference(dst->dev->dn_ptr); struct dn_route *rt; struct neighbour *neigh = dst->neighbour; int header_len; @@ -835,13 +842,16 @@ static inline int dn_match_addr(__le16 addr1, __le16 addr2) static __le16 dnet_select_source(const struct net_device *dev, __le16 daddr, int scope) { __le16 saddr = 0; - struct dn_dev *dn_db = dev->dn_ptr; + struct dn_dev *dn_db; struct dn_ifaddr *ifa; int best_match = 0; int ret; - read_lock(&dev_base_lock); - for(ifa = dn_db->ifa_list; ifa; ifa = ifa->ifa_next) { + rcu_read_lock(); + dn_db = rcu_dereference(dev->dn_ptr); + for (ifa = rcu_dereference(dn_db->ifa_list); + ifa != NULL; + ifa = rcu_dereference(ifa->ifa_next)) { if (ifa->ifa_scope > scope) continue; if (!daddr) { @@ -854,7 +864,7 @@ static __le16 dnet_select_source(const struct net_device *dev, __le16 daddr, int if (best_match == 0) saddr = ifa->ifa_local; } - read_unlock(&dev_base_lock); + rcu_read_unlock(); return saddr; } @@ -1020,7 +1030,7 @@ source_ok: err = -ENODEV; if (dev_out == NULL) goto out; - dn_db = dev_out->dn_ptr; + dn_db = rcu_dereference_raw(dev_out->dn_ptr); /* Possible improvement - check all devices for local addr */ if (dn_dev_islocal(dev_out, fl.fld_dst)) { dev_put(dev_out); @@ -1233,7 +1243,7 @@ static int dn_route_input_slow(struct sk_buff *skb) dev_hold(in_dev); - if ((dn_db = in_dev->dn_ptr) == NULL) + if ((dn_db = rcu_dereference(in_dev->dn_ptr)) == NULL) goto out; /* Zero source addresses are not allowed */ @@ -1677,15 +1687,15 @@ static struct dn_route *dn_rt_cache_get_next(struct seq_file *seq, struct dn_rou { struct dn_rt_cache_iter_state *s = seq->private; - rt = rt->dst.dn_next; - while(!rt) { + rt = rcu_dereference_bh(rt->dst.dn_next); + while (!rt) { rcu_read_unlock_bh(); if (--s->bucket < 0) break; rcu_read_lock_bh(); - rt = dn_rt_hash_table[s->bucket].chain; + rt = rcu_dereference_bh(dn_rt_hash_table[s->bucket].chain); } - return rcu_dereference_bh(rt); + return rt; } static void *dn_rt_cache_seq_start(struct seq_file *seq, loff_t *pos) -- cgit v1.2.3 From 1da4b1c6a4dfb5a13d7147a27c1ac53fed09befd Mon Sep 17 00:00:00 2001 From: Feng Tang Date: Tue, 9 Nov 2010 11:22:58 +0000 Subject: x86/mrst: Add SFI platform device parsing code MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit SFI provides a series of tables. These describe the platform devices present including SPI and I²C devices, as well as various sensors, keypads and other glue as well as interfaces provided via the SCU IPC mechanism (intel_scu_ipc.c) This patch is a merge of the core elements and relevant fixes from the Intel development code by Feng, Alek, myself into a single coherent patch for upstream submission. It provides the needed infrastructure to register I2C, SPI and platform devices described by the tables, as well as handlers for some of the hardware already supported in kernel. The 0.8 firmware also provides GPIO tables. Devices are created at boot time or if they are SCU dependant at the point an SCU is discovered. The existing Linux device mechanisms will then handle the device binding. At an abstract level this is an SFI to Linux device translator. Device/platform specific setup/glue is in this file. This is done so that the drivers for the generic I²C and SPI bus devices remain cross platform as they should. (Updated from RFC version to correct the emc1403 name used by the firmware and a wrongly used #define) Signed-off-by: Alek Du LKML-Reference: <20101109112158.20013.6158.stgit@localhost.localdomain> [Clean ups, removal of 0.7 support] Signed-off-by: Feng Tang [Clean ups] Signed-off-by: Alan Cox Signed-off-by: Thomas Gleixner --- arch/x86/Kconfig | 2 + arch/x86/include/asm/mrst.h | 4 + arch/x86/platform/mrst/mrst.c | 515 ++++++++++++++++++++++++++++++++++- drivers/platform/x86/intel_scu_ipc.c | 5 + include/linux/sfi.h | 8 +- 5 files changed, 527 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index e8327686d3c5..b306b84fc8c8 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -385,6 +385,8 @@ config X86_MRST depends on X86_EXTENDED_PLATFORM depends on X86_IO_APIC select APB_TIMER + select I2C + select SPI ---help--- Moorestown is Intel's Low Power Intel Architecture (LPIA) based Moblin Internet Device(MID) platform. Moorestown consists of two chips: diff --git a/arch/x86/include/asm/mrst.h b/arch/x86/include/asm/mrst.h index 4a711a684b17..283debd29fc0 100644 --- a/arch/x86/include/asm/mrst.h +++ b/arch/x86/include/asm/mrst.h @@ -50,4 +50,8 @@ extern void mrst_early_console_init(void); extern struct console early_hsu_console; extern void hsu_early_console_init(void); + +extern void intel_scu_devices_create(void); +extern void intel_scu_devices_destroy(void); + #endif /* _ASM_X86_MRST_H */ diff --git a/arch/x86/platform/mrst/mrst.c b/arch/x86/platform/mrst/mrst.c index 79ae68154e87..cfa1af24edd5 100644 --- a/arch/x86/platform/mrst/mrst.c +++ b/arch/x86/platform/mrst/mrst.c @@ -9,9 +9,19 @@ * as published by the Free Software Foundation; version 2 * of the License. */ + +#define pr_fmt(fmt) "mrst: " fmt + #include #include #include +#include +#include +#include +#include +#include +#include +#include #include #include @@ -23,8 +33,10 @@ #include #include #include +#include #include + /* * the clockevent devices on Moorestown/Medfield can be APBT or LAPIC clock, * cmdline option x86_mrst_timer can be used to override the configuration @@ -102,10 +114,10 @@ static int __init sfi_parse_mtmr(struct sfi_table_header *table) memcpy(sfi_mtimer_array, pentry, totallen); } - printk(KERN_INFO "SFI: MTIMER info (num = %d):\n", sfi_mtimer_num); + pr_debug("SFI MTIMER info (num = %d):\n", sfi_mtimer_num); pentry = sfi_mtimer_array; for (totallen = 0; totallen < sfi_mtimer_num; totallen++, pentry++) { - printk(KERN_INFO "timer[%d]: paddr = 0x%08x, freq = %dHz," + pr_debug("timer[%d]: paddr = 0x%08x, freq = %dHz," " irq = %d\n", totallen, (u32)pentry->phys_addr, pentry->freq_hz, pentry->irq); if (!pentry->irq) @@ -176,10 +188,10 @@ int __init sfi_parse_mrtc(struct sfi_table_header *table) memcpy(sfi_mrtc_array, pentry, totallen); } - printk(KERN_INFO "SFI: RTC info (num = %d):\n", sfi_mrtc_num); + pr_debug("SFI RTC info (num = %d):\n", sfi_mrtc_num); pentry = sfi_mrtc_array; for (totallen = 0; totallen < sfi_mrtc_num; totallen++, pentry++) { - printk(KERN_INFO "RTC[%d]: paddr = 0x%08x, irq = %d\n", + pr_debug("RTC[%d]: paddr = 0x%08x, irq = %d\n", totallen, (u32)pentry->phys_addr, pentry->irq); mp_irq.type = MP_IOAPIC; mp_irq.irqtype = mp_INT; @@ -309,3 +321,498 @@ static inline int __init setup_x86_mrst_timer(char *arg) return 0; } __setup("x86_mrst_timer=", setup_x86_mrst_timer); + +/* + * Parsing GPIO table first, since the DEVS table will need this table + * to map the pin name to the actual pin. + */ +static struct sfi_gpio_table_entry *gpio_table; +static int gpio_num_entry; + +static int __init sfi_parse_gpio(struct sfi_table_header *table) +{ + struct sfi_table_simple *sb; + struct sfi_gpio_table_entry *pentry; + int num, i; + + if (gpio_table) + return 0; + sb = (struct sfi_table_simple *)table; + num = SFI_GET_NUM_ENTRIES(sb, struct sfi_gpio_table_entry); + pentry = (struct sfi_gpio_table_entry *)sb->pentry; + + gpio_table = (struct sfi_gpio_table_entry *) + kmalloc(num * sizeof(*pentry), GFP_KERNEL); + if (!gpio_table) + return -1; + memcpy(gpio_table, pentry, num * sizeof(*pentry)); + gpio_num_entry = num; + + pr_debug("GPIO pin info:\n"); + for (i = 0; i < num; i++, pentry++) + pr_debug("info[%2d]: controller = %16.16s, pin_name = %16.16s," + " pin = %d\n", i, + pentry->controller_name, + pentry->pin_name, + pentry->pin_no); + return 0; +} + +static int get_gpio_by_name(const char *name) +{ + struct sfi_gpio_table_entry *pentry = gpio_table; + int i; + + if (!pentry) + return -1; + for (i = 0; i < gpio_num_entry; i++, pentry++) { + if (!strncmp(name, pentry->pin_name, SFI_NAME_LEN)) + return pentry->pin_no; + } + return -1; +} + +/* + * Here defines the array of devices platform data that IAFW would export + * through SFI "DEVS" table, we use name and type to match the device and + * its platform data. + */ +struct devs_id { + char name[SFI_NAME_LEN + 1]; + u8 type; + u8 delay; + void *(*get_platform_data)(void *info); +}; + +/* the offset for the mapping of global gpio pin to irq */ +#define MRST_IRQ_OFFSET 0x100 + +static void __init *pmic_gpio_platform_data(void *info) +{ + static struct intel_pmic_gpio_platform_data pmic_gpio_pdata; + int gpio_base = get_gpio_by_name("pmic_gpio_base"); + + if (gpio_base == -1) + gpio_base = 64; + pmic_gpio_pdata.gpio_base = gpio_base; + pmic_gpio_pdata.irq_base = gpio_base + MRST_IRQ_OFFSET; + pmic_gpio_pdata.gpiointr = 0xffffeff8; + + return &pmic_gpio_pdata; +} + +static void __init *max3111_platform_data(void *info) +{ + struct spi_board_info *spi_info = info; + int intr = get_gpio_by_name("max3111_int"); + + if (intr == -1) + return NULL; + spi_info->irq = intr + MRST_IRQ_OFFSET; + return NULL; +} + +/* we have multiple max7315 on the board ... */ +#define MAX7315_NUM 2 +static void __init *max7315_platform_data(void *info) +{ + static struct pca953x_platform_data max7315_pdata[MAX7315_NUM]; + static int nr; + struct pca953x_platform_data *max7315 = &max7315_pdata[nr]; + struct i2c_board_info *i2c_info = info; + int gpio_base, intr; + char base_pin_name[SFI_NAME_LEN + 1]; + char intr_pin_name[SFI_NAME_LEN + 1]; + + if (nr == MAX7315_NUM) { + pr_err("too many max7315s, we only support %d\n", + MAX7315_NUM); + return NULL; + } + /* we have several max7315 on the board, we only need load several + * instances of the same pca953x driver to cover them + */ + strcpy(i2c_info->type, "max7315"); + if (nr++) { + sprintf(base_pin_name, "max7315_%d_base", nr); + sprintf(intr_pin_name, "max7315_%d_int", nr); + } else { + strcpy(base_pin_name, "max7315_base"); + strcpy(intr_pin_name, "max7315_int"); + } + + gpio_base = get_gpio_by_name(base_pin_name); + intr = get_gpio_by_name(intr_pin_name); + + if (gpio_base == -1) + return NULL; + max7315->gpio_base = gpio_base; + if (intr != -1) { + i2c_info->irq = intr + MRST_IRQ_OFFSET; + max7315->irq_base = gpio_base + MRST_IRQ_OFFSET; + } else { + i2c_info->irq = -1; + max7315->irq_base = -1; + } + return max7315; +} + +static void __init *emc1403_platform_data(void *info) +{ + static short intr2nd_pdata; + struct i2c_board_info *i2c_info = info; + int intr = get_gpio_by_name("thermal_int"); + int intr2nd = get_gpio_by_name("thermal_alert"); + + if (intr == -1 || intr2nd == -1) + return NULL; + + i2c_info->irq = intr + MRST_IRQ_OFFSET; + intr2nd_pdata = intr2nd + MRST_IRQ_OFFSET; + + return &intr2nd_pdata; +} + +static void __init *lis331dl_platform_data(void *info) +{ + static short intr2nd_pdata; + struct i2c_board_info *i2c_info = info; + int intr = get_gpio_by_name("accel_int"); + int intr2nd = get_gpio_by_name("accel_2"); + + if (intr == -1 || intr2nd == -1) + return NULL; + + i2c_info->irq = intr + MRST_IRQ_OFFSET; + intr2nd_pdata = intr2nd + MRST_IRQ_OFFSET; + + return &intr2nd_pdata; +} + +static const struct devs_id __initconst device_ids[] = { + {"pmic_gpio", SFI_DEV_TYPE_SPI, 1, &pmic_gpio_platform_data}, + {"spi_max3111", SFI_DEV_TYPE_SPI, 0, &max3111_platform_data}, + {"i2c_max7315", SFI_DEV_TYPE_I2C, 1, &max7315_platform_data}, + {"i2c_max7315_2", SFI_DEV_TYPE_I2C, 1, &max7315_platform_data}, + {"emc1403", SFI_DEV_TYPE_I2C, 1, &emc1403_platform_data}, + {"i2c_accel", SFI_DEV_TYPE_I2C, 0, &lis331dl_platform_data}, + {}, +}; + +#define MAX_IPCDEVS 24 +static struct platform_device *ipc_devs[MAX_IPCDEVS]; +static int ipc_next_dev; + +#define MAX_SCU_SPI 24 +static struct spi_board_info *spi_devs[MAX_SCU_SPI]; +static int spi_next_dev; + +#define MAX_SCU_I2C 24 +static struct i2c_board_info *i2c_devs[MAX_SCU_I2C]; +static int i2c_bus[MAX_SCU_I2C]; +static int i2c_next_dev; + +static void __init intel_scu_device_register(struct platform_device *pdev) +{ + if(ipc_next_dev == MAX_IPCDEVS) + pr_err("too many SCU IPC devices"); + else + ipc_devs[ipc_next_dev++] = pdev; +} + +static void __init intel_scu_spi_device_register(struct spi_board_info *sdev) +{ + struct spi_board_info *new_dev; + + if (spi_next_dev == MAX_SCU_SPI) { + pr_err("too many SCU SPI devices"); + return; + } + + new_dev = kzalloc(sizeof(*sdev), GFP_KERNEL); + if (!new_dev) { + pr_err("failed to alloc mem for delayed spi dev %s\n", + sdev->modalias); + return; + } + memcpy(new_dev, sdev, sizeof(*sdev)); + + spi_devs[spi_next_dev++] = new_dev; +} + +static void __init intel_scu_i2c_device_register(int bus, + struct i2c_board_info *idev) +{ + struct i2c_board_info *new_dev; + + if (i2c_next_dev == MAX_SCU_I2C) { + pr_err("too many SCU I2C devices"); + return; + } + + new_dev = kzalloc(sizeof(*idev), GFP_KERNEL); + if (!new_dev) { + pr_err("failed to alloc mem for delayed i2c dev %s\n", + idev->type); + return; + } + memcpy(new_dev, idev, sizeof(*idev)); + + i2c_bus[i2c_next_dev] = bus; + i2c_devs[i2c_next_dev++] = new_dev; +} + +/* Called by IPC driver */ +void intel_scu_devices_create(void) +{ + int i; + + for (i = 0; i < ipc_next_dev; i++) + platform_device_add(ipc_devs[i]); + + for (i = 0; i < spi_next_dev; i++) + spi_register_board_info(spi_devs[i], 1); + + for (i = 0; i < i2c_next_dev; i++) { + struct i2c_adapter *adapter; + struct i2c_client *client; + + adapter = i2c_get_adapter(i2c_bus[i]); + if (adapter) { + client = i2c_new_device(adapter, i2c_devs[i]); + if (!client) + pr_err("can't create i2c device %s\n", + i2c_devs[i]->type); + } else + i2c_register_board_info(i2c_bus[i], i2c_devs[i], 1); + } +} +EXPORT_SYMBOL_GPL(intel_scu_devices_create); + +/* Called by IPC driver */ +void intel_scu_devices_destroy(void) +{ + int i; + + for (i = 0; i < ipc_next_dev; i++) + platform_device_del(ipc_devs[i]); +} +EXPORT_SYMBOL_GPL(intel_scu_devices_destroy); + +static void __init install_irq_resource(struct platform_device *pdev, int irq) +{ + /* Single threaded */ + static struct resource __initdata res = { + .name = "IRQ", + .flags = IORESOURCE_IRQ, + }; + res.start = irq; + platform_device_add_resources(pdev, &res, 1); +} + +static void __init sfi_handle_ipc_dev(struct platform_device *pdev) +{ + const struct devs_id *dev = device_ids; + void *pdata = NULL; + + while (dev->name[0]) { + if (dev->type == SFI_DEV_TYPE_IPC && + !strncmp(dev->name, pdev->name, SFI_NAME_LEN)) { + pdata = dev->get_platform_data(pdev); + break; + } + dev++; + } + pdev->dev.platform_data = pdata; + intel_scu_device_register(pdev); +} + +static void __init sfi_handle_spi_dev(struct spi_board_info *spi_info) +{ + const struct devs_id *dev = device_ids; + void *pdata = NULL; + + while (dev->name[0]) { + if (dev->type == SFI_DEV_TYPE_SPI && + !strncmp(dev->name, spi_info->modalias, SFI_NAME_LEN)) { + pdata = dev->get_platform_data(spi_info); + break; + } + dev++; + } + spi_info->platform_data = pdata; + if (dev->delay) + intel_scu_spi_device_register(spi_info); + else + spi_register_board_info(spi_info, 1); +} + +static void __init sfi_handle_i2c_dev(int bus, struct i2c_board_info *i2c_info) +{ + const struct devs_id *dev = device_ids; + void *pdata = NULL; + + while (dev->name[0]) { + if (dev->type == SFI_DEV_TYPE_I2C && + !strncmp(dev->name, i2c_info->type, SFI_NAME_LEN)) { + pdata = dev->get_platform_data(i2c_info); + break; + } + dev++; + } + i2c_info->platform_data = pdata; + + if (dev->delay) + intel_scu_i2c_device_register(bus, i2c_info); + else + i2c_register_board_info(bus, i2c_info, 1); + } + + +static int __init sfi_parse_devs(struct sfi_table_header *table) +{ + struct sfi_table_simple *sb; + struct sfi_device_table_entry *pentry; + struct spi_board_info spi_info; + struct i2c_board_info i2c_info; + struct platform_device *pdev; + int num, i, bus; + int ioapic; + struct io_apic_irq_attr irq_attr; + + sb = (struct sfi_table_simple *)table; + num = SFI_GET_NUM_ENTRIES(sb, struct sfi_device_table_entry); + pentry = (struct sfi_device_table_entry *)sb->pentry; + + for (i = 0; i < num; i++, pentry++) { + if (pentry->irq != (u8)0xff) { /* native RTE case */ + /* these SPI2 devices are not exposed to system as PCI + * devices, but they have separate RTE entry in IOAPIC + * so we have to enable them one by one here + */ + ioapic = mp_find_ioapic(pentry->irq); + irq_attr.ioapic = ioapic; + irq_attr.ioapic_pin = pentry->irq; + irq_attr.trigger = 1; + irq_attr.polarity = 1; + io_apic_set_pci_routing(NULL, pentry->irq, &irq_attr); + } + switch (pentry->type) { + case SFI_DEV_TYPE_IPC: + /* ID as IRQ is a hack that will go away */ + pdev = platform_device_alloc(pentry->name, pentry->irq); + if (pdev == NULL) { + pr_err("out of memory for SFI platform device '%s'.\n", + pentry->name); + continue; + } + install_irq_resource(pdev, pentry->irq); + pr_debug("info[%2d]: IPC bus, name = %16.16s, " + "irq = 0x%2x\n", i, pentry->name, pentry->irq); + sfi_handle_ipc_dev(pdev); + break; + case SFI_DEV_TYPE_SPI: + memset(&spi_info, 0, sizeof(spi_info)); + strncpy(spi_info.modalias, pentry->name, SFI_NAME_LEN); + spi_info.irq = pentry->irq; + spi_info.bus_num = pentry->host_num; + spi_info.chip_select = pentry->addr; + spi_info.max_speed_hz = pentry->max_freq; + pr_debug("info[%2d]: SPI bus = %d, name = %16.16s, " + "irq = 0x%2x, max_freq = %d, cs = %d\n", i, + spi_info.bus_num, + spi_info.modalias, + spi_info.irq, + spi_info.max_speed_hz, + spi_info.chip_select); + sfi_handle_spi_dev(&spi_info); + break; + case SFI_DEV_TYPE_I2C: + memset(&i2c_info, 0, sizeof(i2c_info)); + bus = pentry->host_num; + strncpy(i2c_info.type, pentry->name, SFI_NAME_LEN); + i2c_info.irq = pentry->irq; + i2c_info.addr = pentry->addr; + pr_debug("info[%2d]: I2C bus = %d, name = %16.16s, " + "irq = 0x%2x, addr = 0x%x\n", i, bus, + i2c_info.type, + i2c_info.irq, + i2c_info.addr); + sfi_handle_i2c_dev(bus, &i2c_info); + break; + case SFI_DEV_TYPE_UART: + case SFI_DEV_TYPE_HSI: + default: + ; + } + } + return 0; +} + +static int __init mrst_platform_init(void) +{ + sfi_table_parse(SFI_SIG_GPIO, NULL, NULL, sfi_parse_gpio); + sfi_table_parse(SFI_SIG_DEVS, NULL, NULL, sfi_parse_devs); + return 0; +} +arch_initcall(mrst_platform_init); + +/* + * we will search these buttons in SFI GPIO table (by name) + * and register them dynamically. Please add all possible + * buttons here, we will shrink them if no GPIO found. + */ +static struct gpio_keys_button gpio_button[] = { + {KEY_POWER, -1, 1, "power_btn", EV_KEY, 0, 3000}, + {KEY_PROG1, -1, 1, "prog_btn1", EV_KEY, 0, 20}, + {KEY_PROG2, -1, 1, "prog_btn2", EV_KEY, 0, 20}, + {SW_LID, -1, 1, "lid_switch", EV_SW, 0, 20}, + {KEY_VOLUMEUP, -1, 1, "vol_up", EV_KEY, 0, 20}, + {KEY_VOLUMEDOWN, -1, 1, "vol_down", EV_KEY, 0, 20}, + {KEY_CAMERA, -1, 1, "camera_full", EV_KEY, 0, 20}, + {KEY_CAMERA_FOCUS, -1, 1, "camera_half", EV_KEY, 0, 20}, + {SW_KEYPAD_SLIDE, -1, 1, "MagSw1", EV_SW, 0, 20}, + {SW_KEYPAD_SLIDE, -1, 1, "MagSw2", EV_SW, 0, 20}, +}; + +static struct gpio_keys_platform_data mrst_gpio_keys = { + .buttons = gpio_button, + .rep = 1, + .nbuttons = -1, /* will fill it after search */ +}; + +static struct platform_device pb_device = { + .name = "gpio-keys", + .id = -1, + .dev = { + .platform_data = &mrst_gpio_keys, + }, +}; + +/* + * Shrink the non-existent buttons, register the gpio button + * device if there is some + */ +static int __init pb_keys_init(void) +{ + struct gpio_keys_button *gb = gpio_button; + int i, num, good = 0; + + num = sizeof(gpio_button) / sizeof(struct gpio_keys_button); + for (i = 0; i < num; i++) { + gb[i].gpio = get_gpio_by_name(gb[i].desc); + if (gb[i].gpio == -1) + continue; + + if (i != good) + gb[good] = gb[i]; + good++; + } + + if (good) { + mrst_gpio_keys.nbuttons = good; + return platform_device_register(&pb_device); + } + return 0; +} +late_initcall(pb_keys_init); diff --git a/drivers/platform/x86/intel_scu_ipc.c b/drivers/platform/x86/intel_scu_ipc.c index 41a9e34899ac..ca35b0ce944a 100644 --- a/drivers/platform/x86/intel_scu_ipc.c +++ b/drivers/platform/x86/intel_scu_ipc.c @@ -26,6 +26,7 @@ #include #include #include +#include /* IPC defines the following message types */ #define IPCMSG_WATCHDOG_TIMER 0xF8 /* Set Kernel Watchdog Threshold */ @@ -699,6 +700,9 @@ static int ipc_probe(struct pci_dev *dev, const struct pci_device_id *id) iounmap(ipcdev.ipc_base); return -ENOMEM; } + + intel_scu_devices_create(); + return 0; } @@ -720,6 +724,7 @@ static void ipc_remove(struct pci_dev *pdev) iounmap(ipcdev.ipc_base); iounmap(ipcdev.i2c_base); ipcdev.pdev = NULL; + intel_scu_devices_destroy(); } static const struct pci_device_id pci_ids[] = { diff --git a/include/linux/sfi.h b/include/linux/sfi.h index 7f770c638e99..fe817918b30e 100644 --- a/include/linux/sfi.h +++ b/include/linux/sfi.h @@ -77,6 +77,8 @@ #define SFI_OEM_ID_SIZE 6 #define SFI_OEM_TABLE_ID_SIZE 8 +#define SFI_NAME_LEN 16 + #define SFI_SYST_SEARCH_BEGIN 0x000E0000 #define SFI_SYST_SEARCH_END 0x000FFFFF @@ -156,13 +158,13 @@ struct sfi_device_table_entry { u16 addr; u8 irq; u32 max_freq; - char name[16]; + char name[SFI_NAME_LEN]; } __packed; struct sfi_gpio_table_entry { - char controller_name[16]; + char controller_name[SFI_NAME_LEN]; u16 pin_no; - char pin_name[16]; + char pin_name[SFI_NAME_LEN]; } __packed; typedef int (*sfi_table_handler) (struct sfi_table_header *table); -- cgit v1.2.3 From 751305d9b2fd3e03eaab7808e976241d85ca4353 Mon Sep 17 00:00:00 2001 From: Daniel Drake Date: Thu, 28 Oct 2010 18:23:01 +0100 Subject: viafb: General power management infrastructure Multiple devices need S/R hooks (framebuffer, GPIO, camera). Add infrastructure and convert existing framebuffer code to the new model. This patch should create no functional change. Based on earlier work by Jonathan Corbet. Signed-off-by: Daniel Drake Acked-by: Jonathan Corbet Signed-off-by: Florian Tobias Schandinat --- drivers/video/via/via-core.c | 79 ++++++++++++++++++++++++++++++++++++++++++-- drivers/video/via/viafbdev.c | 34 +++++++++---------- drivers/video/via/viafbdev.h | 2 -- include/linux/via-core.h | 15 +++++++++ 4 files changed, 107 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/drivers/video/via/via-core.c b/drivers/video/via/via-core.c index 31e30338e893..42be3d955887 100644 --- a/drivers/video/via/via-core.c +++ b/drivers/video/via/via-core.c @@ -15,6 +15,8 @@ #include #include #include +#include +#include /* * The default port config. @@ -563,6 +565,78 @@ static void via_teardown_subdevs(void) } } +/* + * Power management functions + */ +#ifdef CONFIG_PM +static LIST_HEAD(viafb_pm_hooks); +static DEFINE_MUTEX(viafb_pm_hooks_lock); + +void viafb_pm_register(struct viafb_pm_hooks *hooks) +{ + INIT_LIST_HEAD(&hooks->list); + + mutex_lock(&viafb_pm_hooks_lock); + list_add_tail(&hooks->list, &viafb_pm_hooks); + mutex_unlock(&viafb_pm_hooks_lock); +} +EXPORT_SYMBOL_GPL(viafb_pm_register); + +void viafb_pm_unregister(struct viafb_pm_hooks *hooks) +{ + mutex_lock(&viafb_pm_hooks_lock); + list_del(&hooks->list); + mutex_unlock(&viafb_pm_hooks_lock); +} +EXPORT_SYMBOL_GPL(viafb_pm_unregister); + +static int via_suspend(struct pci_dev *pdev, pm_message_t state) +{ + struct viafb_pm_hooks *hooks; + + if (state.event != PM_EVENT_SUSPEND) + return 0; + /* + * "I've occasionally hit a few drivers that caused suspend + * failures, and each and every time it was a driver bug, and + * the right thing to do was to just ignore the error and suspend + * anyway - returning an error code and trying to undo the suspend + * is not what anybody ever really wants, even if our model + *_allows_ for it." + * -- Linus Torvalds, Dec. 7, 2009 + */ + mutex_lock(&viafb_pm_hooks_lock); + list_for_each_entry_reverse(hooks, &viafb_pm_hooks, list) + hooks->suspend(hooks->private); + mutex_unlock(&viafb_pm_hooks_lock); + + pci_save_state(pdev); + pci_disable_device(pdev); + pci_set_power_state(pdev, pci_choose_state(pdev, state)); + return 0; +} + +static int via_resume(struct pci_dev *pdev) +{ + struct viafb_pm_hooks *hooks; + + /* Get the bus side powered up */ + pci_set_power_state(pdev, PCI_D0); + pci_restore_state(pdev); + if (pci_enable_device(pdev)) + return 0; + + pci_set_master(pdev); + + /* Now bring back any subdevs */ + mutex_lock(&viafb_pm_hooks_lock); + list_for_each_entry(hooks, &viafb_pm_hooks, list) + hooks->resume(hooks->private); + mutex_unlock(&viafb_pm_hooks_lock); + + return 0; +} +#endif /* CONFIG_PM */ static int __devinit via_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) @@ -572,6 +646,7 @@ static int __devinit via_pci_probe(struct pci_dev *pdev, ret = pci_enable_device(pdev); if (ret) return ret; + /* * Global device initialization. */ @@ -651,8 +726,8 @@ static struct pci_driver via_driver = { .probe = via_pci_probe, .remove = __devexit_p(via_pci_remove), #ifdef CONFIG_PM - .suspend = viafb_suspend, - .resume = viafb_resume, + .suspend = via_suspend, + .resume = via_resume, #endif }; diff --git a/drivers/video/via/viafbdev.c b/drivers/video/via/viafbdev.c index d298cfccd6fc..289edd519527 100644 --- a/drivers/video/via/viafbdev.c +++ b/drivers/video/via/viafbdev.c @@ -1672,31 +1672,19 @@ static int parse_mode(const char *str, u32 *xres, u32 *yres) #ifdef CONFIG_PM -int viafb_suspend(struct pci_dev *pdev, pm_message_t state) +static int viafb_suspend(void *unused) { - if (state.event == PM_EVENT_SUSPEND) { - acquire_console_sem(); - fb_set_suspend(viafbinfo, 1); - - viafb_sync(viafbinfo); - - pci_save_state(pdev); - pci_disable_device(pdev); - pci_set_power_state(pdev, pci_choose_state(pdev, state)); - release_console_sem(); - } + acquire_console_sem(); + fb_set_suspend(viafbinfo, 1); + viafb_sync(viafbinfo); + release_console_sem(); return 0; } -int viafb_resume(struct pci_dev *pdev) +static int viafb_resume(void *unused) { acquire_console_sem(); - pci_set_power_state(pdev, PCI_D0); - pci_restore_state(pdev); - if (pci_enable_device(pdev)) - goto fail; - pci_set_master(pdev); if (viaparinfo->shared->vdev->engine_mmio) viafb_reset_engine(viaparinfo); viafb_set_par(viafbinfo); @@ -1704,11 +1692,15 @@ int viafb_resume(struct pci_dev *pdev) viafb_set_par(viafbinfo1); fb_set_suspend(viafbinfo, 0); -fail: release_console_sem(); return 0; } +static struct viafb_pm_hooks viafb_fb_pm_hooks = { + .suspend = viafb_suspend, + .resume = viafb_resume +}; + #endif @@ -1899,6 +1891,10 @@ int __devinit via_fb_pci_probe(struct viafb_dev *vdev) viafb_init_proc(viaparinfo->shared); viafb_init_dac(IGA2); + +#ifdef CONFIG_PM + viafb_pm_register(&viafb_fb_pm_hooks); +#endif return 0; out_fb_unreg: diff --git a/drivers/video/via/viafbdev.h b/drivers/video/via/viafbdev.h index 4960e3da6645..d66f963e930e 100644 --- a/drivers/video/via/viafbdev.h +++ b/drivers/video/via/viafbdev.h @@ -108,6 +108,4 @@ void via_fb_pci_remove(struct pci_dev *pdev); /* Temporary */ int viafb_init(void); void viafb_exit(void); -int viafb_suspend(struct pci_dev *pdev, pm_message_t state); -int viafb_resume(struct pci_dev *pdev); #endif /* __VIAFBDEV_H__ */ diff --git a/include/linux/via-core.h b/include/linux/via-core.h index 7ffb521e1a7a..a4327a0c8efc 100644 --- a/include/linux/via-core.h +++ b/include/linux/via-core.h @@ -59,6 +59,21 @@ struct via_port_cfg { u8 ioport_index; }; +/* + * Allow subdevs to register suspend/resume hooks. + */ +#ifdef CONFIG_PM +struct viafb_pm_hooks { + struct list_head list; + int (*suspend)(void *private); + int (*resume)(void *private); + void *private; +}; + +void viafb_pm_register(struct viafb_pm_hooks *hooks); +void viafb_pm_unregister(struct viafb_pm_hooks *hooks); +#endif /* CONFIG_PM */ + /* * This is the global viafb "device" containing stuff needed by * all subdevs. -- cgit v1.2.3 From f6cd24777513fcc673d432cc29ef59881d3e4df1 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 4 Nov 2010 11:13:48 +0100 Subject: irq: Better struct irqaction layout We currently use kmalloc-96 slab for struct irqaction allocations on 64bit arches. This is unfortunate because of possible false sharing and two cache lines accesses. Move 'name' and 'dir' fields at the end of the structure, and force a suitable alignement. Hot path fields now use one cache line on x86_64. Signed-off-by: Eric Dumazet Reviewed-by: Andi Kleen Cc: Peter Zijlstra LKML-Reference: <1288865628.2659.69.camel@edumazet-laptop> Signed-off-by: Thomas Gleixner --- include/linux/interrupt.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 79d0c4f6d071..55e0d4253e49 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -114,15 +114,15 @@ typedef irqreturn_t (*irq_handler_t)(int, void *); struct irqaction { irq_handler_t handler; unsigned long flags; - const char *name; void *dev_id; struct irqaction *next; int irq; - struct proc_dir_entry *dir; irq_handler_t thread_fn; struct task_struct *thread; unsigned long thread_flags; -}; + const char *name; + struct proc_dir_entry *dir; +} ____cacheline_internodealigned_in_smp; extern irqreturn_t no_action(int cpl, void *dev_id); -- cgit v1.2.3 From 5e4f083f78d03e9f8d2e327daccde16976f9bb00 Mon Sep 17 00:00:00 2001 From: Yong Zhang Date: Sun, 24 Oct 2010 11:50:53 +0800 Subject: hrtimer: Remove stale comment on curr_timer curr_timer doesn't resident in struct hrtimer_cpu_base anymore. Signed-off-by: Yong Zhang LKML-Reference: <1287892253-2587-1-git-send-email-yong.zhang0@gmail.com> Signed-off-by: Thomas Gleixner --- include/linux/hrtimer.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index fd0c1b857d3d..dd9954b79342 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -158,7 +158,6 @@ struct hrtimer_clock_base { * @lock: lock protecting the base and associated clock bases * and timers * @clock_base: array of clock bases for this cpu - * @curr_timer: the timer which is executing a callback right now * @expires_next: absolute time of the next event which was scheduled * via clock_set_next_event() * @hres_active: State of high resolution mode -- cgit v1.2.3 From 1d7138de878d1d4210727c1200193e69596f93b3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 12 Nov 2010 05:46:50 +0000 Subject: igmp: RCU conversion of in_dev->mc_list MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit in_dev->mc_list is protected by one rwlock (in_dev->mc_list_lock). This can easily be converted to a RCU protection. Writers hold RTNL, so mc_list_lock is removed, not replaced by a spinlock. Signed-off-by: Eric Dumazet Cc: Cypher Wu Cc: Américo Wang Signed-off-by: David S. Miller --- include/linux/igmp.h | 12 ++- include/linux/inetdevice.h | 5 +- include/net/inet_sock.h | 2 +- net/ipv4/igmp.c | 223 +++++++++++++++++++++------------------------ 4 files changed, 115 insertions(+), 127 deletions(-) (limited to 'include/linux') diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 93fc2449af10..7d164670f264 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -167,10 +167,10 @@ struct ip_sf_socklist { */ struct ip_mc_socklist { - struct ip_mc_socklist *next; + struct ip_mc_socklist __rcu *next_rcu; struct ip_mreqn multi; unsigned int sfmode; /* MCAST_{INCLUDE,EXCLUDE} */ - struct ip_sf_socklist *sflist; + struct ip_sf_socklist __rcu *sflist; struct rcu_head rcu; }; @@ -186,11 +186,14 @@ struct ip_sf_list { struct ip_mc_list { struct in_device *interface; __be32 multiaddr; + unsigned int sfmode; struct ip_sf_list *sources; struct ip_sf_list *tomb; - unsigned int sfmode; unsigned long sfcount[2]; - struct ip_mc_list *next; + union { + struct ip_mc_list *next; + struct ip_mc_list __rcu *next_rcu; + }; struct timer_list timer; int users; atomic_t refcnt; @@ -201,6 +204,7 @@ struct ip_mc_list { char loaded; unsigned char gsquery; /* check source marks? */ unsigned char crcount; + struct rcu_head rcu; }; /* V3 exponential field decoding */ diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index ccd5b07d678d..380ba6bc5db1 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -52,9 +52,8 @@ struct in_device { atomic_t refcnt; int dead; struct in_ifaddr *ifa_list; /* IP ifaddr chain */ - rwlock_t mc_list_lock; - struct ip_mc_list *mc_list; /* IP multicast filter chain */ - int mc_count; /* Number of installed mcasts */ + struct ip_mc_list __rcu *mc_list; /* IP multicast filter chain */ + int mc_count; /* Number of installed mcasts */ spinlock_t mc_tomb_lock; struct ip_mc_list *mc_tomb; unsigned long mr_v1_seen; diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 1989cfd7405f..8945f9fb192a 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -141,7 +141,7 @@ struct inet_sock { nodefrag:1; int mc_index; __be32 mc_addr; - struct ip_mc_socklist *mc_list; + struct ip_mc_socklist __rcu *mc_list; struct { unsigned int flags; unsigned int fragsize; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 08d0d81ffc15..6f49d6c087da 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -149,11 +149,17 @@ static void ip_mc_clear_src(struct ip_mc_list *pmc); static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, int sfcount, __be32 *psfsrc, int delta); + +static void ip_mc_list_reclaim(struct rcu_head *head) +{ + kfree(container_of(head, struct ip_mc_list, rcu)); +} + static void ip_ma_put(struct ip_mc_list *im) { if (atomic_dec_and_test(&im->refcnt)) { in_dev_put(im->interface); - kfree(im); + call_rcu(&im->rcu, ip_mc_list_reclaim); } } @@ -163,7 +169,7 @@ static void ip_ma_put(struct ip_mc_list *im) * Timer management */ -static __inline__ void igmp_stop_timer(struct ip_mc_list *im) +static void igmp_stop_timer(struct ip_mc_list *im) { spin_lock_bh(&im->lock); if (del_timer(&im->timer)) @@ -496,14 +502,24 @@ empty_source: return skb; } +#define for_each_pmc_rcu(in_dev, pmc) \ + for (pmc = rcu_dereference(in_dev->mc_list); \ + pmc != NULL; \ + pmc = rcu_dereference(pmc->next_rcu)) + +#define for_each_pmc_rtnl(in_dev, pmc) \ + for (pmc = rtnl_dereference(in_dev->mc_list); \ + pmc != NULL; \ + pmc = rtnl_dereference(pmc->next_rcu)) + static int igmpv3_send_report(struct in_device *in_dev, struct ip_mc_list *pmc) { struct sk_buff *skb = NULL; int type; if (!pmc) { - read_lock(&in_dev->mc_list_lock); - for (pmc=in_dev->mc_list; pmc; pmc=pmc->next) { + rcu_read_lock(); + for_each_pmc_rcu(in_dev, pmc) { if (pmc->multiaddr == IGMP_ALL_HOSTS) continue; spin_lock_bh(&pmc->lock); @@ -514,7 +530,7 @@ static int igmpv3_send_report(struct in_device *in_dev, struct ip_mc_list *pmc) skb = add_grec(skb, pmc, type, 0, 0); spin_unlock_bh(&pmc->lock); } - read_unlock(&in_dev->mc_list_lock); + rcu_read_unlock(); } else { spin_lock_bh(&pmc->lock); if (pmc->sfcount[MCAST_EXCLUDE]) @@ -556,7 +572,7 @@ static void igmpv3_send_cr(struct in_device *in_dev) struct sk_buff *skb = NULL; int type, dtype; - read_lock(&in_dev->mc_list_lock); + rcu_read_lock(); spin_lock_bh(&in_dev->mc_tomb_lock); /* deleted MCA's */ @@ -593,7 +609,7 @@ static void igmpv3_send_cr(struct in_device *in_dev) spin_unlock_bh(&in_dev->mc_tomb_lock); /* change recs */ - for (pmc=in_dev->mc_list; pmc; pmc=pmc->next) { + for_each_pmc_rcu(in_dev, pmc) { spin_lock_bh(&pmc->lock); if (pmc->sfcount[MCAST_EXCLUDE]) { type = IGMPV3_BLOCK_OLD_SOURCES; @@ -616,7 +632,7 @@ static void igmpv3_send_cr(struct in_device *in_dev) } spin_unlock_bh(&pmc->lock); } - read_unlock(&in_dev->mc_list_lock); + rcu_read_unlock(); if (!skb) return; @@ -813,14 +829,14 @@ static void igmp_heard_report(struct in_device *in_dev, __be32 group) if (group == IGMP_ALL_HOSTS) return; - read_lock(&in_dev->mc_list_lock); - for (im=in_dev->mc_list; im!=NULL; im=im->next) { + rcu_read_lock(); + for_each_pmc_rcu(in_dev, im) { if (im->multiaddr == group) { igmp_stop_timer(im); break; } } - read_unlock(&in_dev->mc_list_lock); + rcu_read_unlock(); } static void igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, @@ -906,8 +922,8 @@ static void igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, * - Use the igmp->igmp_code field as the maximum * delay possible */ - read_lock(&in_dev->mc_list_lock); - for (im=in_dev->mc_list; im!=NULL; im=im->next) { + rcu_read_lock(); + for_each_pmc_rcu(in_dev, im) { int changed; if (group && group != im->multiaddr) @@ -925,7 +941,7 @@ static void igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, if (changed) igmp_mod_timer(im, max_delay); } - read_unlock(&in_dev->mc_list_lock); + rcu_read_unlock(); } /* called in rcu_read_lock() section */ @@ -1110,8 +1126,8 @@ static void igmpv3_clear_delrec(struct in_device *in_dev) kfree(pmc); } /* clear dead sources, too */ - read_lock(&in_dev->mc_list_lock); - for (pmc=in_dev->mc_list; pmc; pmc=pmc->next) { + rcu_read_lock(); + for_each_pmc_rcu(in_dev, pmc) { struct ip_sf_list *psf, *psf_next; spin_lock_bh(&pmc->lock); @@ -1123,7 +1139,7 @@ static void igmpv3_clear_delrec(struct in_device *in_dev) kfree(psf); } } - read_unlock(&in_dev->mc_list_lock); + rcu_read_unlock(); } #endif @@ -1209,7 +1225,7 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) ASSERT_RTNL(); - for (im=in_dev->mc_list; im; im=im->next) { + for_each_pmc_rtnl(in_dev, im) { if (im->multiaddr == addr) { im->users++; ip_mc_add_src(in_dev, &addr, MCAST_EXCLUDE, 0, NULL, 0); @@ -1217,7 +1233,7 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) } } - im = kmalloc(sizeof(*im), GFP_KERNEL); + im = kzalloc(sizeof(*im), GFP_KERNEL); if (!im) goto out; @@ -1227,26 +1243,18 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) im->multiaddr = addr; /* initial mode is (EX, empty) */ im->sfmode = MCAST_EXCLUDE; - im->sfcount[MCAST_INCLUDE] = 0; im->sfcount[MCAST_EXCLUDE] = 1; - im->sources = NULL; - im->tomb = NULL; - im->crcount = 0; atomic_set(&im->refcnt, 1); spin_lock_init(&im->lock); #ifdef CONFIG_IP_MULTICAST - im->tm_running = 0; setup_timer(&im->timer, &igmp_timer_expire, (unsigned long)im); im->unsolicit_count = IGMP_Unsolicited_Report_Count; - im->reporter = 0; - im->gsquery = 0; #endif - im->loaded = 0; - write_lock_bh(&in_dev->mc_list_lock); - im->next = in_dev->mc_list; - in_dev->mc_list = im; + + im->next_rcu = in_dev->mc_list; in_dev->mc_count++; - write_unlock_bh(&in_dev->mc_list_lock); + rcu_assign_pointer(in_dev->mc_list, im); + #ifdef CONFIG_IP_MULTICAST igmpv3_del_delrec(in_dev, im->multiaddr); #endif @@ -1287,17 +1295,18 @@ EXPORT_SYMBOL(ip_mc_rejoin_group); void ip_mc_dec_group(struct in_device *in_dev, __be32 addr) { - struct ip_mc_list *i, **ip; + struct ip_mc_list *i; + struct ip_mc_list __rcu **ip; ASSERT_RTNL(); - for (ip=&in_dev->mc_list; (i=*ip)!=NULL; ip=&i->next) { + for (ip = &in_dev->mc_list; + (i = rtnl_dereference(*ip)) != NULL; + ip = &i->next_rcu) { if (i->multiaddr == addr) { if (--i->users == 0) { - write_lock_bh(&in_dev->mc_list_lock); - *ip = i->next; + *ip = i->next_rcu; in_dev->mc_count--; - write_unlock_bh(&in_dev->mc_list_lock); igmp_group_dropped(i); if (!in_dev->dead) @@ -1316,34 +1325,34 @@ EXPORT_SYMBOL(ip_mc_dec_group); void ip_mc_unmap(struct in_device *in_dev) { - struct ip_mc_list *i; + struct ip_mc_list *pmc; ASSERT_RTNL(); - for (i = in_dev->mc_list; i; i = i->next) - igmp_group_dropped(i); + for_each_pmc_rtnl(in_dev, pmc) + igmp_group_dropped(pmc); } void ip_mc_remap(struct in_device *in_dev) { - struct ip_mc_list *i; + struct ip_mc_list *pmc; ASSERT_RTNL(); - for (i = in_dev->mc_list; i; i = i->next) - igmp_group_added(i); + for_each_pmc_rtnl(in_dev, pmc) + igmp_group_added(pmc); } /* Device going down */ void ip_mc_down(struct in_device *in_dev) { - struct ip_mc_list *i; + struct ip_mc_list *pmc; ASSERT_RTNL(); - for (i=in_dev->mc_list; i; i=i->next) - igmp_group_dropped(i); + for_each_pmc_rtnl(in_dev, pmc) + igmp_group_dropped(pmc); #ifdef CONFIG_IP_MULTICAST in_dev->mr_ifc_count = 0; @@ -1374,7 +1383,6 @@ void ip_mc_init_dev(struct in_device *in_dev) in_dev->mr_qrv = IGMP_Unsolicited_Report_Count; #endif - rwlock_init(&in_dev->mc_list_lock); spin_lock_init(&in_dev->mc_tomb_lock); } @@ -1382,14 +1390,14 @@ void ip_mc_init_dev(struct in_device *in_dev) void ip_mc_up(struct in_device *in_dev) { - struct ip_mc_list *i; + struct ip_mc_list *pmc; ASSERT_RTNL(); ip_mc_inc_group(in_dev, IGMP_ALL_HOSTS); - for (i=in_dev->mc_list; i; i=i->next) - igmp_group_added(i); + for_each_pmc_rtnl(in_dev, pmc) + igmp_group_added(pmc); } /* @@ -1405,17 +1413,13 @@ void ip_mc_destroy_dev(struct in_device *in_dev) /* Deactivate timers */ ip_mc_down(in_dev); - write_lock_bh(&in_dev->mc_list_lock); - while ((i = in_dev->mc_list) != NULL) { - in_dev->mc_list = i->next; + while ((i = rtnl_dereference(in_dev->mc_list)) != NULL) { + in_dev->mc_list = i->next_rcu; in_dev->mc_count--; - write_unlock_bh(&in_dev->mc_list_lock); + igmp_group_dropped(i); ip_ma_put(i); - - write_lock_bh(&in_dev->mc_list_lock); } - write_unlock_bh(&in_dev->mc_list_lock); } /* RTNL is locked */ @@ -1513,18 +1517,18 @@ static int ip_mc_del_src(struct in_device *in_dev, __be32 *pmca, int sfmode, if (!in_dev) return -ENODEV; - read_lock(&in_dev->mc_list_lock); - for (pmc=in_dev->mc_list; pmc; pmc=pmc->next) { + rcu_read_lock(); + for_each_pmc_rcu(in_dev, pmc) { if (*pmca == pmc->multiaddr) break; } if (!pmc) { /* MCA not found?? bug */ - read_unlock(&in_dev->mc_list_lock); + rcu_read_unlock(); return -ESRCH; } spin_lock_bh(&pmc->lock); - read_unlock(&in_dev->mc_list_lock); + rcu_read_unlock(); #ifdef CONFIG_IP_MULTICAST sf_markstate(pmc); #endif @@ -1685,18 +1689,18 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, if (!in_dev) return -ENODEV; - read_lock(&in_dev->mc_list_lock); - for (pmc=in_dev->mc_list; pmc; pmc=pmc->next) { + rcu_read_lock(); + for_each_pmc_rcu(in_dev, pmc) { if (*pmca == pmc->multiaddr) break; } if (!pmc) { /* MCA not found?? bug */ - read_unlock(&in_dev->mc_list_lock); + rcu_read_unlock(); return -ESRCH; } spin_lock_bh(&pmc->lock); - read_unlock(&in_dev->mc_list_lock); + rcu_read_unlock(); #ifdef CONFIG_IP_MULTICAST sf_markstate(pmc); @@ -1793,7 +1797,7 @@ int ip_mc_join_group(struct sock *sk , struct ip_mreqn *imr) err = -EADDRINUSE; ifindex = imr->imr_ifindex; - for (i = inet->mc_list; i; i = i->next) { + for_each_pmc_rtnl(inet, i) { if (i->multi.imr_multiaddr.s_addr == addr && i->multi.imr_ifindex == ifindex) goto done; @@ -1807,7 +1811,7 @@ int ip_mc_join_group(struct sock *sk , struct ip_mreqn *imr) goto done; memcpy(&iml->multi, imr, sizeof(*imr)); - iml->next = inet->mc_list; + iml->next_rcu = inet->mc_list; iml->sflist = NULL; iml->sfmode = MCAST_EXCLUDE; rcu_assign_pointer(inet->mc_list, iml); @@ -1821,17 +1825,14 @@ EXPORT_SYMBOL(ip_mc_join_group); static void ip_sf_socklist_reclaim(struct rcu_head *rp) { - struct ip_sf_socklist *psf; - - psf = container_of(rp, struct ip_sf_socklist, rcu); + kfree(container_of(rp, struct ip_sf_socklist, rcu)); /* sk_omem_alloc should have been decreased by the caller*/ - kfree(psf); } static int ip_mc_leave_src(struct sock *sk, struct ip_mc_socklist *iml, struct in_device *in_dev) { - struct ip_sf_socklist *psf = iml->sflist; + struct ip_sf_socklist *psf = rtnl_dereference(iml->sflist); int err; if (psf == NULL) { @@ -1851,11 +1852,8 @@ static int ip_mc_leave_src(struct sock *sk, struct ip_mc_socklist *iml, static void ip_mc_socklist_reclaim(struct rcu_head *rp) { - struct ip_mc_socklist *iml; - - iml = container_of(rp, struct ip_mc_socklist, rcu); + kfree(container_of(rp, struct ip_mc_socklist, rcu)); /* sk_omem_alloc should have been decreased by the caller*/ - kfree(iml); } @@ -1866,7 +1864,8 @@ static void ip_mc_socklist_reclaim(struct rcu_head *rp) int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr) { struct inet_sock *inet = inet_sk(sk); - struct ip_mc_socklist *iml, **imlp; + struct ip_mc_socklist *iml; + struct ip_mc_socklist __rcu **imlp; struct in_device *in_dev; struct net *net = sock_net(sk); __be32 group = imr->imr_multiaddr.s_addr; @@ -1876,7 +1875,9 @@ int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr) rtnl_lock(); in_dev = ip_mc_find_dev(net, imr); ifindex = imr->imr_ifindex; - for (imlp = &inet->mc_list; (iml = *imlp) != NULL; imlp = &iml->next) { + for (imlp = &inet->mc_list; + (iml = rtnl_dereference(*imlp)) != NULL; + imlp = &iml->next_rcu) { if (iml->multi.imr_multiaddr.s_addr != group) continue; if (ifindex) { @@ -1888,7 +1889,7 @@ int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr) (void) ip_mc_leave_src(sk, iml, in_dev); - rcu_assign_pointer(*imlp, iml->next); + *imlp = iml->next_rcu; if (in_dev) ip_mc_dec_group(in_dev, group); @@ -1934,7 +1935,7 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct } err = -EADDRNOTAVAIL; - for (pmc=inet->mc_list; pmc; pmc=pmc->next) { + for_each_pmc_rtnl(inet, pmc) { if ((pmc->multi.imr_multiaddr.s_addr == imr.imr_multiaddr.s_addr) && (pmc->multi.imr_ifindex == imr.imr_ifindex)) @@ -1958,7 +1959,7 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct pmc->sfmode = omode; } - psl = pmc->sflist; + psl = rtnl_dereference(pmc->sflist); if (!add) { if (!psl) goto done; /* err = -EADDRNOTAVAIL */ @@ -2077,7 +2078,7 @@ int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex) goto done; } - for (pmc=inet->mc_list; pmc; pmc=pmc->next) { + for_each_pmc_rtnl(inet, pmc) { if (pmc->multi.imr_multiaddr.s_addr == msf->imsf_multiaddr && pmc->multi.imr_ifindex == imr.imr_ifindex) break; @@ -2107,7 +2108,7 @@ int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex) (void) ip_mc_add_src(in_dev, &msf->imsf_multiaddr, msf->imsf_fmode, 0, NULL, 0); } - psl = pmc->sflist; + psl = rtnl_dereference(pmc->sflist); if (psl) { (void) ip_mc_del_src(in_dev, &msf->imsf_multiaddr, pmc->sfmode, psl->sl_count, psl->sl_addr, 0); @@ -2155,7 +2156,7 @@ int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf, } err = -EADDRNOTAVAIL; - for (pmc=inet->mc_list; pmc; pmc=pmc->next) { + for_each_pmc_rtnl(inet, pmc) { if (pmc->multi.imr_multiaddr.s_addr == msf->imsf_multiaddr && pmc->multi.imr_ifindex == imr.imr_ifindex) break; @@ -2163,7 +2164,7 @@ int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf, if (!pmc) /* must have a prior join */ goto done; msf->imsf_fmode = pmc->sfmode; - psl = pmc->sflist; + psl = rtnl_dereference(pmc->sflist); rtnl_unlock(); if (!psl) { len = 0; @@ -2208,7 +2209,7 @@ int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf, err = -EADDRNOTAVAIL; - for (pmc=inet->mc_list; pmc; pmc=pmc->next) { + for_each_pmc_rtnl(inet, pmc) { if (pmc->multi.imr_multiaddr.s_addr == addr && pmc->multi.imr_ifindex == gsf->gf_interface) break; @@ -2216,7 +2217,7 @@ int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf, if (!pmc) /* must have a prior join */ goto done; gsf->gf_fmode = pmc->sfmode; - psl = pmc->sflist; + psl = rtnl_dereference(pmc->sflist); rtnl_unlock(); count = psl ? psl->sl_count : 0; copycount = count < gsf->gf_numsrc ? count : gsf->gf_numsrc; @@ -2257,7 +2258,7 @@ int ip_mc_sf_allow(struct sock *sk, __be32 loc_addr, __be32 rmt_addr, int dif) goto out; rcu_read_lock(); - for (pmc=rcu_dereference(inet->mc_list); pmc; pmc=rcu_dereference(pmc->next)) { + for_each_pmc_rcu(inet, pmc) { if (pmc->multi.imr_multiaddr.s_addr == loc_addr && pmc->multi.imr_ifindex == dif) break; @@ -2265,7 +2266,7 @@ int ip_mc_sf_allow(struct sock *sk, __be32 loc_addr, __be32 rmt_addr, int dif) ret = inet->mc_all; if (!pmc) goto unlock; - psl = pmc->sflist; + psl = rcu_dereference(pmc->sflist); ret = (pmc->sfmode == MCAST_EXCLUDE); if (!psl) goto unlock; @@ -2300,10 +2301,10 @@ void ip_mc_drop_socket(struct sock *sk) return; rtnl_lock(); - while ((iml = inet->mc_list) != NULL) { + while ((iml = rtnl_dereference(inet->mc_list)) != NULL) { struct in_device *in_dev; - rcu_assign_pointer(inet->mc_list, iml->next); + inet->mc_list = iml->next_rcu; in_dev = inetdev_by_index(net, iml->multi.imr_ifindex); (void) ip_mc_leave_src(sk, iml, in_dev); if (in_dev != NULL) { @@ -2323,8 +2324,8 @@ int ip_check_mc(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u16 p struct ip_sf_list *psf; int rv = 0; - read_lock(&in_dev->mc_list_lock); - for (im=in_dev->mc_list; im; im=im->next) { + rcu_read_lock(); + for_each_pmc_rcu(in_dev, im) { if (im->multiaddr == mc_addr) break; } @@ -2345,7 +2346,7 @@ int ip_check_mc(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u16 p } else rv = 1; /* unspecified source; tentatively allow */ } - read_unlock(&in_dev->mc_list_lock); + rcu_read_unlock(); return rv; } @@ -2371,13 +2372,11 @@ static inline struct ip_mc_list *igmp_mc_get_first(struct seq_file *seq) in_dev = __in_dev_get_rcu(state->dev); if (!in_dev) continue; - read_lock(&in_dev->mc_list_lock); - im = in_dev->mc_list; + im = rcu_dereference(in_dev->mc_list); if (im) { state->in_dev = in_dev; break; } - read_unlock(&in_dev->mc_list_lock); } return im; } @@ -2385,11 +2384,9 @@ static inline struct ip_mc_list *igmp_mc_get_first(struct seq_file *seq) static struct ip_mc_list *igmp_mc_get_next(struct seq_file *seq, struct ip_mc_list *im) { struct igmp_mc_iter_state *state = igmp_mc_seq_private(seq); - im = im->next; - while (!im) { - if (likely(state->in_dev != NULL)) - read_unlock(&state->in_dev->mc_list_lock); + im = rcu_dereference(im->next_rcu); + while (!im) { state->dev = next_net_device_rcu(state->dev); if (!state->dev) { state->in_dev = NULL; @@ -2398,8 +2395,7 @@ static struct ip_mc_list *igmp_mc_get_next(struct seq_file *seq, struct ip_mc_li state->in_dev = __in_dev_get_rcu(state->dev); if (!state->in_dev) continue; - read_lock(&state->in_dev->mc_list_lock); - im = state->in_dev->mc_list; + im = rcu_dereference(state->in_dev->mc_list); } return im; } @@ -2435,10 +2431,8 @@ static void igmp_mc_seq_stop(struct seq_file *seq, void *v) __releases(rcu) { struct igmp_mc_iter_state *state = igmp_mc_seq_private(seq); - if (likely(state->in_dev != NULL)) { - read_unlock(&state->in_dev->mc_list_lock); - state->in_dev = NULL; - } + + state->in_dev = NULL; state->dev = NULL; rcu_read_unlock(); } @@ -2460,7 +2454,7 @@ static int igmp_mc_seq_show(struct seq_file *seq, void *v) querier = "NONE"; #endif - if (state->in_dev->mc_list == im) { + if (rcu_dereference(state->in_dev->mc_list) == im) { seq_printf(seq, "%d\t%-10s: %5d %7s\n", state->dev->ifindex, state->dev->name, state->in_dev->mc_count, querier); } @@ -2519,8 +2513,7 @@ static inline struct ip_sf_list *igmp_mcf_get_first(struct seq_file *seq) idev = __in_dev_get_rcu(state->dev); if (unlikely(idev == NULL)) continue; - read_lock(&idev->mc_list_lock); - im = idev->mc_list; + im = rcu_dereference(idev->mc_list); if (likely(im != NULL)) { spin_lock_bh(&im->lock); psf = im->sources; @@ -2531,7 +2524,6 @@ static inline struct ip_sf_list *igmp_mcf_get_first(struct seq_file *seq) } spin_unlock_bh(&im->lock); } - read_unlock(&idev->mc_list_lock); } return psf; } @@ -2545,9 +2537,6 @@ static struct ip_sf_list *igmp_mcf_get_next(struct seq_file *seq, struct ip_sf_l spin_unlock_bh(&state->im->lock); state->im = state->im->next; while (!state->im) { - if (likely(state->idev != NULL)) - read_unlock(&state->idev->mc_list_lock); - state->dev = next_net_device_rcu(state->dev); if (!state->dev) { state->idev = NULL; @@ -2556,8 +2545,7 @@ static struct ip_sf_list *igmp_mcf_get_next(struct seq_file *seq, struct ip_sf_l state->idev = __in_dev_get_rcu(state->dev); if (!state->idev) continue; - read_lock(&state->idev->mc_list_lock); - state->im = state->idev->mc_list; + state->im = rcu_dereference(state->idev->mc_list); } if (!state->im) break; @@ -2603,10 +2591,7 @@ static void igmp_mcf_seq_stop(struct seq_file *seq, void *v) spin_unlock_bh(&state->im->lock); state->im = NULL; } - if (likely(state->idev != NULL)) { - read_unlock(&state->idev->mc_list_lock); - state->idev = NULL; - } + state->idev = NULL; state->dev = NULL; rcu_read_unlock(); } -- cgit v1.2.3 From 9fbbdde93231ad7f35c217aa6bbbc7995133f483 Mon Sep 17 00:00:00 2001 From: Erik Gilling Date: Thu, 11 Nov 2010 15:44:43 +0100 Subject: video: add fb_edid_add_monspecs for parsing extended edid information Modern monitors/tvs have more extended EDID information blocks which can contain extra detailed modes. This adds a fb_edid_add_monspecs function which drivers can use to parse those additions blocks. Signed-off-by: Erik Gilling Signed-off-by: Guennadi Liakhovetski Signed-off-by: Paul Mundt --- drivers/video/fbmon.c | 57 +++++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/fb.h | 2 ++ 2 files changed, 59 insertions(+) (limited to 'include/linux') diff --git a/drivers/video/fbmon.c b/drivers/video/fbmon.c index 563a98b88e9b..a0b5a93b72d2 100644 --- a/drivers/video/fbmon.c +++ b/drivers/video/fbmon.c @@ -973,6 +973,63 @@ void fb_edid_to_monspecs(unsigned char *edid, struct fb_monspecs *specs) DPRINTK("========================================\n"); } +void fb_edid_add_monspecs(unsigned char *edid, struct fb_monspecs *specs) +{ + unsigned char *block; + struct fb_videomode *mode, *m; + int num = 0, i, first = 1; + + if (edid == NULL) + return; + + if (!edid_checksum(edid)) + return; + + if (edid[0] != 0x2) + return; + + mode = kzalloc(50 * sizeof(struct fb_videomode), GFP_KERNEL); + if (mode == NULL) + return; + + block = edid + edid[0x2]; + + DPRINTK(" Extended Detailed Timings\n"); + + for (i = 0; i < (128 - edid[0x2]) / DETAILED_TIMING_DESCRIPTION_SIZE; + i++, block += DETAILED_TIMING_DESCRIPTION_SIZE) { + if (!(block[0] == 0x00 && block[1] == 0x00)) { + get_detailed_timing(block, &mode[num]); + if (first) { + mode[num].flag |= FB_MODE_IS_FIRST; + first = 0; + } + num++; + } + } + + /* Yikes, EDID data is totally useless */ + if (!num) { + kfree(mode); + return; + } + + m = kzalloc((specs->modedb_len + num) * + sizeof(struct fb_videomode), GFP_KERNEL); + + if (!m) { + kfree(mode); + return; + } + + memmove(m, specs->modedb, specs->modedb_len * sizeof(struct fb_videomode)); + memmove(m + specs->modedb_len, mode, num * sizeof(struct fb_videomode)); + kfree(mode); + kfree(specs->modedb); + specs->modedb = m; + specs->modedb_len = specs->modedb_len + num; +} + /* * VESA Generalized Timing Formula (GTF) */ diff --git a/include/linux/fb.h b/include/linux/fb.h index 7fca3dc4e475..6f0274d96f0c 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -1092,6 +1092,8 @@ extern int fb_parse_edid(unsigned char *edid, struct fb_var_screeninfo *var); extern const unsigned char *fb_firmware_edid(struct device *device); extern void fb_edid_to_monspecs(unsigned char *edid, struct fb_monspecs *specs); +extern void fb_edid_add_monspecs(unsigned char *edid, + struct fb_monspecs *specs); extern void fb_destroy_modedb(struct fb_videomode *modedb); extern int fb_find_mode_cvt(struct fb_videomode *mode, int margins, int rb); extern unsigned char *fb_ddc_read(struct i2c_adapter *adapter); -- cgit v1.2.3 From 0ad83f6882c41df1a7fa387086029e162038c1f2 Mon Sep 17 00:00:00 2001 From: Guennadi Liakhovetski Date: Thu, 11 Nov 2010 15:45:04 +0100 Subject: fbdev: when parsing E-EDID blocks, also use SVD entries Add parsing of E-EDID SVD entries. In this first version only a few CEA/EIA-861E modes are implemented, more can be added as needed. Signed-off-by: Guennadi Liakhovetski Signed-off-by: Paul Mundt --- drivers/video/fbmon.c | 37 +++++++++++++++++++++++++++++++++---- drivers/video/modedb.c | 43 +++++++++++++++++++++++++++++++++++++++++++ include/linux/fb.h | 1 + 3 files changed, 77 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/video/fbmon.c b/drivers/video/fbmon.c index b25399abcf49..4f57485f8c54 100644 --- a/drivers/video/fbmon.c +++ b/drivers/video/fbmon.c @@ -983,7 +983,8 @@ void fb_edid_add_monspecs(unsigned char *edid, struct fb_monspecs *specs) unsigned char *block; struct fb_videomode *m; int num = 0, i; - u8 edt[(128 - 4) / DETAILED_TIMING_DESCRIPTION_SIZE]; + u8 svd[64], edt[(128 - 4) / DETAILED_TIMING_DESCRIPTION_SIZE]; + u8 pos = 4, svd_n = 0; if (!edid) return; @@ -995,6 +996,21 @@ void fb_edid_add_monspecs(unsigned char *edid, struct fb_monspecs *specs) edid[2] < 4 || edid[2] > 128 - DETAILED_TIMING_DESCRIPTION_SIZE) return; + DPRINTK(" Short Video Descriptors\n"); + + while (pos < edid[2]) { + u8 len = edid[pos] & 0x1f, type = (edid[pos] >> 5) & 7; + pr_debug("Data block %u of %u bytes\n", type, len); + if (type == 2) + for (i = pos; i < pos + len; i++) { + u8 idx = edid[pos + i] & 0x7f; + svd[svd_n++] = idx; + pr_debug("N%sative mode #%d\n", + edid[pos + i] & 0x80 ? "" : "on-n", idx); + } + pos += len + 1; + } + block = edid + edid[2]; DPRINTK(" Extended Detailed Timings\n"); @@ -1005,10 +1021,10 @@ void fb_edid_add_monspecs(unsigned char *edid, struct fb_monspecs *specs) edt[num++] = block - edid; /* Yikes, EDID data is totally useless */ - if (!num) + if (!(num + svd_n)) return; - m = kzalloc((specs->modedb_len + num) * + m = kzalloc((specs->modedb_len + num + svd_n) * sizeof(struct fb_videomode), GFP_KERNEL); if (!m) @@ -1023,9 +1039,22 @@ void fb_edid_add_monspecs(unsigned char *edid, struct fb_monspecs *specs) pr_debug("Adding %ux%u@%u\n", m[i].xres, m[i].yres, m[i].refresh); } + for (i = specs->modedb_len + num; i < specs->modedb_len + num + svd_n; i++) { + int idx = svd[i - specs->modedb_len - num]; + if (!idx || idx > 63) { + pr_warning("Reserved SVD code %d\n", idx); + } else if (idx > ARRAY_SIZE(cea_modes) || !cea_modes[idx].xres) { + pr_warning("Unimplemented SVD code %d\n", idx); + } else { + memcpy(&m[i], cea_modes + idx, sizeof(m[i])); + pr_debug("Adding SVD #%d: %ux%u@%u\n", idx, + m[i].xres, m[i].yres, m[i].refresh); + } + } + kfree(specs->modedb); specs->modedb = m; - specs->modedb_len = specs->modedb_len + num; + specs->modedb_len = specs->modedb_len + num + svd_n; } /* diff --git a/drivers/video/modedb.c b/drivers/video/modedb.c index 0a4dbdc1693a..9a0ae6ca5427 100644 --- a/drivers/video/modedb.c +++ b/drivers/video/modedb.c @@ -278,6 +278,49 @@ static const struct fb_videomode modedb[] = { }; #ifdef CONFIG_FB_MODE_HELPERS +const struct fb_videomode cea_modes[64] = { + /* #1: 640x480p@59.94/60Hz */ + [1] = { + NULL, 60, 640, 480, 39722, 48, 16, 33, 10, 96, 2, 0, FB_VMODE_NONINTERLACED, 0, + }, + /* #3: 720x480p@59.94/60Hz */ + [3] = { + NULL, 60, 720, 480, 37037, 60, 16, 30, 9, 62, 6, 0, FB_VMODE_NONINTERLACED, 0, + }, + /* #5: 1920x1080i@59.94/60Hz */ + [5] = { + NULL, 60, 1920, 1080, 13763, 148, 88, 15, 2, 44, 5, 0, FB_VMODE_INTERLACED, 0, + }, + /* #7: 720(1440)x480iH@59.94/60Hz */ + [7] = { + NULL, 60, 1440, 480, 18554/*37108*/, 114, 38, 15, 4, 124, 3, 0, FB_VMODE_INTERLACED, 0, + }, + /* #9: 720(1440)x240pH@59.94/60Hz */ + [9] = { + NULL, 60, 1440, 240, 18554, 114, 38, 16, 4, 124, 3, 0, FB_VMODE_NONINTERLACED, 0, + }, + /* #18: 720x576pH@50Hz */ + [18] = { + NULL, 50, 720, 576, 37037, 68, 12, 39, 5, 64, 5, 0, FB_VMODE_NONINTERLACED, 0, + }, + /* #19: 1280x720p@50Hz */ + [19] = { + NULL, 50, 1280, 720, 13468, 220, 440, 20, 5, 40, 5, 0, FB_VMODE_NONINTERLACED, 0, + }, + /* #20: 1920x1080i@50Hz */ + [20] = { + NULL, 50, 1920, 1080, 13480, 148, 528, 15, 5, 528, 5, 0, FB_VMODE_INTERLACED, 0, + }, + /* #32: 1920x1080p@23.98/24Hz */ + [32] = { + NULL, 24, 1920, 1080, 13468, 148, 638, 36, 4, 44, 5, 0, FB_VMODE_NONINTERLACED, 0, + }, + /* #35: (2880)x480p4x@59.94/60Hz */ + [35] = { + NULL, 50, 2880, 480, 11100, 240, 64, 30, 9, 248, 6, 0, FB_VMODE_NONINTERLACED, 0, + }, +}; + const struct fb_videomode vesa_modes[] = { /* 0 640x350-85 VESA */ { NULL, 85, 640, 350, 31746, 96, 32, 60, 32, 64, 3, diff --git a/include/linux/fb.h b/include/linux/fb.h index 6f0274d96f0c..e154a79b8322 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -1151,6 +1151,7 @@ struct fb_videomode { extern const char *fb_mode_option; extern const struct fb_videomode vesa_modes[]; +extern const struct fb_videomode cea_modes[64]; struct fb_modelist { struct list_head list; -- cgit v1.2.3 From d83447f0944e73d690218d79c07762ffa4ceb9e4 Mon Sep 17 00:00:00 2001 From: Gerrit Renker Date: Sun, 14 Nov 2010 17:25:46 +0100 Subject: dccp ccid-2: Schedule Sync as out-of-band mechanism The problem with Ack Vectors is that i) their length is variable and can in principle grow quite large, ii) it is hard to predict exactly how large they will be. Due to the second point it seems not a good idea to reduce the MPS; in particular when on average there is enough room for the Ack Vector and an increase in length is momentarily due to some burst loss, after which the Ack Vector returns to its normal/average length. The solution taken by this patch is to subtract a minimum-expected Ack Vector length from the MPS, and to defer any larger Ack Vectors onto a separate Sync - but only if indeed there is no space left on the skb. This patch provides the infrastructure to schedule Sync-packets for transporting (urgent) out-of-band data. Its signalling is quicker than scheduling an Ack, since it does not need to wait for new application data. Signed-off-by: Gerrit Renker --- include/linux/dccp.h | 2 ++ net/dccp/options.c | 24 ++++++++++++++++++++---- net/dccp/output.c | 15 +++++++++++++++ 3 files changed, 37 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dccp.h b/include/linux/dccp.h index 749f01ccd26e..eed52bcd35d0 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -462,6 +462,7 @@ struct dccp_ackvec; * @dccps_hc_rx_insert_options - receiver wants to add options when acking * @dccps_hc_tx_insert_options - sender wants to add options when sending * @dccps_server_timewait - server holds timewait state on close (RFC 4340, 8.3) + * @dccps_sync_scheduled - flag which signals "send out-of-band message soon" * @dccps_xmitlet - tasklet scheduled by the TX CCID to dequeue data packets * @dccps_xmit_timer - used by the TX CCID to delay sending (rate-based pacing) * @dccps_syn_rtt - RTT sample from Request/Response exchange (in usecs) @@ -503,6 +504,7 @@ struct dccp_sock { __u8 dccps_hc_rx_insert_options:1; __u8 dccps_hc_tx_insert_options:1; __u8 dccps_server_timewait:1; + __u8 dccps_sync_scheduled:1; struct tasklet_struct dccps_xmitlet; struct timer_list dccps_xmit_timer; }; diff --git a/net/dccp/options.c b/net/dccp/options.c index 7743df00f5b1..dabd6ee34d45 100644 --- a/net/dccp/options.c +++ b/net/dccp/options.c @@ -427,6 +427,7 @@ static int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb) { struct dccp_sock *dp = dccp_sk(sk); struct dccp_ackvec *av = dp->dccps_hc_rx_ackvec; + struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb); const u16 buflen = dccp_ackvec_buflen(av); /* Figure out how many options do we need to represent the ackvec */ const u8 nr_opts = DIV_ROUND_UP(buflen, DCCP_SINGLE_OPT_MAXLEN); @@ -435,10 +436,25 @@ static int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb) const unsigned char *tail, *from; unsigned char *to; - if (DCCP_SKB_CB(skb)->dccpd_opt_len + len > DCCP_MAX_OPT_LEN) + if (dcb->dccpd_opt_len + len > DCCP_MAX_OPT_LEN) { + DCCP_WARN("Lacking space for %u bytes on %s packet\n", len, + dccp_packet_name(dcb->dccpd_type)); return -1; - - DCCP_SKB_CB(skb)->dccpd_opt_len += len; + } + /* + * Since Ack Vectors are variable-length, we can not always predict + * their size. To catch exception cases where the space is running out + * on the skb, a separate Sync is scheduled to carry the Ack Vector. + */ + if (len > DCCPAV_MIN_OPTLEN && + len + dcb->dccpd_opt_len + skb->len > dp->dccps_mss_cache) { + DCCP_WARN("No space left for Ack Vector (%u) on skb (%u+%u), " + "MPS=%u ==> reduce payload size?\n", len, skb->len, + dcb->dccpd_opt_len, dp->dccps_mss_cache); + dp->dccps_sync_scheduled = 1; + return 0; + } + dcb->dccpd_opt_len += len; to = skb_push(skb, len); len = buflen; @@ -479,7 +495,7 @@ static int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb) /* * Each sent Ack Vector is recorded in the list, as per A.2 of RFC 4340. */ - if (dccp_ackvec_update_records(av, DCCP_SKB_CB(skb)->dccpd_seq, nonce)) + if (dccp_ackvec_update_records(av, dcb->dccpd_seq, nonce)) return -ENOBUFS; return 0; } diff --git a/net/dccp/output.c b/net/dccp/output.c index 45b91853f5ae..d96dd9d362ae 100644 --- a/net/dccp/output.c +++ b/net/dccp/output.c @@ -283,6 +283,15 @@ static void dccp_xmit_packet(struct sock *sk) * any local drop will eventually be reported via receiver feedback. */ ccid_hc_tx_packet_sent(dp->dccps_hc_tx_ccid, sk, len); + + /* + * If the CCID needs to transfer additional header options out-of-band + * (e.g. Ack Vectors or feature-negotiation options), it activates this + * flag to schedule a Sync. The Sync will automatically incorporate all + * currently pending header options, thus clearing the backlog. + */ + if (dp->dccps_sync_scheduled) + dccp_send_sync(sk, dp->dccps_gsr, DCCP_PKT_SYNC); } /** @@ -636,6 +645,12 @@ void dccp_send_sync(struct sock *sk, const u64 ackno, DCCP_SKB_CB(skb)->dccpd_type = pkt_type; DCCP_SKB_CB(skb)->dccpd_ack_seq = ackno; + /* + * Clear the flag in case the Sync was scheduled for out-of-band data, + * such as carrying a long Ack Vector. + */ + dccp_sk(sk)->dccps_sync_scheduled = 0; + dccp_transmit_skb(sk, skb); } -- cgit v1.2.3 From 58e998c6d23988490162cef0784b19ea274d90bb Mon Sep 17 00:00:00 2001 From: Jesse Gross Date: Fri, 29 Oct 2010 12:14:55 +0000 Subject: offloading: Force software GSO for multiple vlan tags. We currently use vlan_features to check for TSO support if there is a vlan tag. However, it's quite likely that the NIC is not able to do TSO when there is an arbitrary number of tags. Therefore if there is more than one tag (in-band or out-of-band), fall back to software emulation. Signed-off-by: Jesse Gross CC: Ben Hutchings Signed-off-by: David S. Miller --- include/linux/netdevice.h | 7 +++---- net/core/dev.c | 16 ++++++++++++++++ 2 files changed, 19 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 578debb801f4..6e4cfbc53d4c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2239,6 +2239,8 @@ unsigned long netdev_fix_features(unsigned long features, const char *name); void netif_stacked_transfer_operstate(const struct net_device *rootdev, struct net_device *dev); +int netif_get_vlan_features(struct sk_buff *skb, struct net_device *dev); + static inline int net_gso_ok(int features, int gso_type) { int feature = gso_type << NETIF_F_GSO_SHIFT; @@ -2254,10 +2256,7 @@ static inline int skb_gso_ok(struct sk_buff *skb, int features) static inline int netif_needs_gso(struct net_device *dev, struct sk_buff *skb) { if (skb_is_gso(skb)) { - int features = dev->features; - - if (skb->protocol == htons(ETH_P_8021Q) || skb->vlan_tci) - features &= dev->vlan_features; + int features = netif_get_vlan_features(skb, dev); return (!skb_gso_ok(skb, features) || unlikely(skb->ip_summed != CHECKSUM_PARTIAL)); diff --git a/net/core/dev.c b/net/core/dev.c index 368930a988e3..8b500c3e0297 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1968,6 +1968,22 @@ static inline void skb_orphan_try(struct sk_buff *skb) } } +int netif_get_vlan_features(struct sk_buff *skb, struct net_device *dev) +{ + __be16 protocol = skb->protocol; + + if (protocol == htons(ETH_P_8021Q)) { + struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data; + protocol = veh->h_vlan_encapsulated_proto; + } else if (!skb->vlan_tci) + return dev->features; + + if (protocol != htons(ETH_P_8021Q)) + return dev->features & dev->vlan_features; + else + return 0; +} + /* * Returns true if either: * 1. skb has frag_list and the device doesn't support FRAGLIST, or -- cgit v1.2.3 From 2e48928d8a0f38c1b5c81eb3f1294de8a6382c68 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Wed, 20 Oct 2010 10:16:58 -0700 Subject: rfkill: remove dead code The following code is defined but never used. Signed-off-by: Stephen Hemminger Signed-off-by: John W. Linville --- include/linux/rfkill.h | 31 ------------------------------- net/rfkill/core.c | 14 -------------- 2 files changed, 45 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rfkill.h b/include/linux/rfkill.h index 08c32e4f261a..c6c608482cba 100644 --- a/include/linux/rfkill.h +++ b/include/linux/rfkill.h @@ -354,37 +354,6 @@ static inline bool rfkill_blocked(struct rfkill *rfkill) } #endif /* RFKILL || RFKILL_MODULE */ - -#ifdef CONFIG_RFKILL_LEDS -/** - * rfkill_get_led_trigger_name - Get the LED trigger name for the button's LED. - * This function might return a NULL pointer if registering of the - * LED trigger failed. Use this as "default_trigger" for the LED. - */ -const char *rfkill_get_led_trigger_name(struct rfkill *rfkill); - -/** - * rfkill_set_led_trigger_name -- set the LED trigger name - * @rfkill: rfkill struct - * @name: LED trigger name - * - * This function sets the LED trigger name of the radio LED - * trigger that rfkill creates. It is optional, but if called - * must be called before rfkill_register() to be effective. - */ -void rfkill_set_led_trigger_name(struct rfkill *rfkill, const char *name); -#else -static inline const char *rfkill_get_led_trigger_name(struct rfkill *rfkill) -{ - return NULL; -} - -static inline void -rfkill_set_led_trigger_name(struct rfkill *rfkill, const char *name) -{ -} -#endif - #endif /* __KERNEL__ */ #endif /* RFKILL_H */ diff --git a/net/rfkill/core.c b/net/rfkill/core.c index 04f599089e6d..0198191b756d 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -149,20 +149,6 @@ static void rfkill_led_trigger_activate(struct led_classdev *led) rfkill_led_trigger_event(rfkill); } -const char *rfkill_get_led_trigger_name(struct rfkill *rfkill) -{ - return rfkill->led_trigger.name; -} -EXPORT_SYMBOL(rfkill_get_led_trigger_name); - -void rfkill_set_led_trigger_name(struct rfkill *rfkill, const char *name) -{ - BUG_ON(!rfkill); - - rfkill->ledtrigname = name; -} -EXPORT_SYMBOL(rfkill_set_led_trigger_name); - static int rfkill_led_trigger_register(struct rfkill *rfkill) { rfkill->led_trigger.name = rfkill->ledtrigname -- cgit v1.2.3 From ca4ffe8f2848169a8ded0ea8a60b2d81925564c9 Mon Sep 17 00:00:00 2001 From: "Luis R. Rodriguez" Date: Wed, 20 Oct 2010 10:18:55 -0700 Subject: cfg80211: fix disabling channels based on hints After a module loads you will have loaded the world roaming regulatory domain or a custom regulatory domain. Further regulatory hints are welcomed and should be respected unless the regulatory hint is coming from a country IE as the IEEE spec allows for a country IE to be a subset of what is allowed by the local regulatory agencies. So disable all channels that do not fit a regulatory domain sent from a unless the hint is from a country IE and the country IE had no information about the band we are currently processing. This fixes a few regulatory issues, for example for drivers that depend on CRDA and had no 5 GHz freqencies allowed were not properly disabling 5 GHz at all, furthermore it also allows users to restrict devices further as was intended. If you recieve a country IE upon association we will also disable the channels that are not allowed if the country IE had at least one channel on the respective band we are procesing. This was the original intention behind this design but it was completely overlooked... Cc: David Quan Cc: Jouni Malinen cc: Easwar Krishnan Cc: stable@kernel.org Signed-off-by: Luis R. Rodriguez Signed-off-by: John W. Linville --- include/linux/nl80211.h | 6 +++++- net/wireless/reg.c | 20 +++++++++++++++++++- 2 files changed, 24 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 0edb2566c14c..fb877b5621b7 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -1307,7 +1307,11 @@ enum nl80211_bitrate_attr { * wireless core it thinks its knows the regulatory domain we should be in. * @NL80211_REGDOM_SET_BY_COUNTRY_IE: the wireless core has received an * 802.11 country information element with regulatory information it - * thinks we should consider. + * thinks we should consider. cfg80211 only processes the country + * code from the IE, and relies on the regulatory domain information + * structure pased by userspace (CRDA) from our wireless-regdb. + * If a channel is enabled but the country code indicates it should + * be disabled we disable the channel and re-enable it upon disassociation. */ enum nl80211_reg_initiator { NL80211_REGDOM_SET_BY_CORE, diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 1bc8131a5185..8ab65f2afe70 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -750,8 +750,26 @@ static void handle_channel(struct wiphy *wiphy, desired_bw_khz, ®_rule); - if (r) + if (r) { + /* + * We will disable all channels that do not match our + * recieved regulatory rule unless the hint is coming + * from a Country IE and the Country IE had no information + * about a band. The IEEE 802.11 spec allows for an AP + * to send only a subset of the regulatory rules allowed, + * so an AP in the US that only supports 2.4 GHz may only send + * a country IE with information for the 2.4 GHz band + * while 5 GHz is still supported. + */ + if (initiator == NL80211_REGDOM_SET_BY_COUNTRY_IE && + r == -ERANGE) + return; + + REG_DBG_PRINT("cfg80211: Disabling freq %d MHz\n", + chan->center_freq); + chan->flags = IEEE80211_CHAN_DISABLED; return; + } power_rule = ®_rule->power_rule; freq_range = ®_rule->freq_range; -- cgit v1.2.3 From c8aea565e8f715d9f10064b1cbfbc15bf75df501 Mon Sep 17 00:00:00 2001 From: Gery Kahn Date: Tue, 5 Oct 2010 16:09:05 +0200 Subject: wl1271: ref_clock cosmetic changes Cosmetic cleanup for ref_clock code while configured by board. Signed-off-by: Gery Kahn Signed-off-by: Luciano Coelho --- drivers/net/wireless/wl12xx/wl1271_boot.c | 10 ++++------ include/linux/wl12xx.h | 8 ++++++++ 2 files changed, 12 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/wireless/wl12xx/wl1271_boot.c b/drivers/net/wireless/wl12xx/wl1271_boot.c index b91021242098..5b190728ca55 100644 --- a/drivers/net/wireless/wl12xx/wl1271_boot.c +++ b/drivers/net/wireless/wl12xx/wl1271_boot.c @@ -471,20 +471,19 @@ int wl1271_boot(struct wl1271 *wl) { int ret = 0; u32 tmp, clk, pause; - int ref_clock = wl->ref_clock; wl1271_boot_hw_version(wl); - if (ref_clock == 0 || ref_clock == 2 || ref_clock == 4) + if (wl->ref_clock == 0 || wl->ref_clock == 2 || wl->ref_clock == 4) /* ref clk: 19.2/38.4/38.4-XTAL */ clk = 0x3; - else if (ref_clock == 1 || ref_clock == 3) + else if (wl->ref_clock == 1 || wl->ref_clock == 3) /* ref clk: 26/52 */ clk = 0x5; else return -EINVAL; - if (ref_clock != 0) { + if (wl->ref_clock != 0) { u16 val; /* Set clock type (open drain) */ val = wl1271_top_reg_read(wl, OCP_REG_CLK_TYPE); @@ -529,8 +528,7 @@ int wl1271_boot(struct wl1271 *wl) wl1271_debug(DEBUG_BOOT, "clk2 0x%x", clk); - /* 2 */ - clk |= (ref_clock << 1) << 4; + clk |= (wl->ref_clock << 1) << 4; wl1271_write32(wl, DRPW_SCRATCH_START, clk); wl1271_set_partition(wl, &part_table[PART_WORK]); diff --git a/include/linux/wl12xx.h b/include/linux/wl12xx.h index 4f902e1908aa..bebb8efea0a6 100644 --- a/include/linux/wl12xx.h +++ b/include/linux/wl12xx.h @@ -24,6 +24,14 @@ #ifndef _LINUX_WL12XX_H #define _LINUX_WL12XX_H +/* The board reference clock values */ +enum { + WL12XX_REFCLOCK_19 = 0, /* 19.2 MHz */ + WL12XX_REFCLOCK_26 = 1, /* 26 MHz */ + WL12XX_REFCLOCK_38 = 2, /* 38.4 MHz */ + WL12XX_REFCLOCK_54 = 3, /* 54 MHz */ +}; + struct wl12xx_platform_data { void (*set_power)(bool enable); /* SDIO only: IRQ number if WLAN_IRQ line is used, 0 for SDIO IRQs */ -- cgit v1.2.3 From 7919a57bc608140aa8614c19eac40c6916fb61d2 Mon Sep 17 00:00:00 2001 From: Andreas Herrmann Date: Mon, 30 Aug 2010 19:04:01 +0000 Subject: bitops: Provide generic sign_extend32 function This patch moves code out from wireless drivers where two different functions are defined in three code locations for the same purpose and provides a common function to sign extend a 32-bit value. Signed-off-by: Andreas Herrmann Signed-off-by: John W. Linville --- drivers/net/wireless/ath/ath5k/phy.c | 8 +------- drivers/net/wireless/ath/ath9k/ar5008_phy.c | 12 ++++++------ drivers/net/wireless/ath/ath9k/ar9002_phy.c | 8 ++++---- drivers/net/wireless/ath/ath9k/ar9003_phy.c | 12 ++++++------ drivers/net/wireless/ath/ath9k/hw.h | 6 ------ drivers/net/wireless/iwlwifi/iwl-4965.c | 20 ++------------------ include/linux/bitops.h | 11 +++++++++++ 7 files changed, 30 insertions(+), 47 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/wireless/ath/ath5k/phy.c b/drivers/net/wireless/ath/ath5k/phy.c index 219367884e64..6b43f535ff53 100644 --- a/drivers/net/wireless/ath/ath5k/phy.c +++ b/drivers/net/wireless/ath/ath5k/phy.c @@ -1102,18 +1102,12 @@ int ath5k_hw_channel(struct ath5k_hw *ah, struct ieee80211_channel *channel) PHY calibration \*****************/ -static int sign_extend(int val, const int nbits) -{ - int order = BIT(nbits-1); - return (val ^ order) - order; -} - static s32 ath5k_hw_read_measured_noise_floor(struct ath5k_hw *ah) { s32 val; val = ath5k_hw_reg_read(ah, AR5K_PHY_NF); - return sign_extend(AR5K_REG_MS(val, AR5K_PHY_NF_MINCCA_PWR), 9); + return sign_extend32(AR5K_REG_MS(val, AR5K_PHY_NF_MINCCA_PWR), 8); } void ath5k_hw_init_nfcal_hist(struct ath5k_hw *ah) diff --git a/drivers/net/wireless/ath/ath9k/ar5008_phy.c b/drivers/net/wireless/ath/ath9k/ar5008_phy.c index 777a602176f2..c83a22cfbe1e 100644 --- a/drivers/net/wireless/ath/ath9k/ar5008_phy.c +++ b/drivers/net/wireless/ath/ath9k/ar5008_phy.c @@ -1490,25 +1490,25 @@ static void ar5008_hw_do_getnf(struct ath_hw *ah, int16_t nf; nf = MS(REG_READ(ah, AR_PHY_CCA), AR_PHY_MINCCA_PWR); - nfarray[0] = sign_extend(nf, 9); + nfarray[0] = sign_extend32(nf, 8); nf = MS(REG_READ(ah, AR_PHY_CH1_CCA), AR_PHY_CH1_MINCCA_PWR); - nfarray[1] = sign_extend(nf, 9); + nfarray[1] = sign_extend32(nf, 8); nf = MS(REG_READ(ah, AR_PHY_CH2_CCA), AR_PHY_CH2_MINCCA_PWR); - nfarray[2] = sign_extend(nf, 9); + nfarray[2] = sign_extend32(nf, 8); if (!IS_CHAN_HT40(ah->curchan)) return; nf = MS(REG_READ(ah, AR_PHY_EXT_CCA), AR_PHY_EXT_MINCCA_PWR); - nfarray[3] = sign_extend(nf, 9); + nfarray[3] = sign_extend32(nf, 8); nf = MS(REG_READ(ah, AR_PHY_CH1_EXT_CCA), AR_PHY_CH1_EXT_MINCCA_PWR); - nfarray[4] = sign_extend(nf, 9); + nfarray[4] = sign_extend32(nf, 8); nf = MS(REG_READ(ah, AR_PHY_CH2_EXT_CCA), AR_PHY_CH2_EXT_MINCCA_PWR); - nfarray[5] = sign_extend(nf, 9); + nfarray[5] = sign_extend32(nf, 8); } /* diff --git a/drivers/net/wireless/ath/ath9k/ar9002_phy.c b/drivers/net/wireless/ath/ath9k/ar9002_phy.c index c00cdc67b55b..3fb97fdc1240 100644 --- a/drivers/net/wireless/ath/ath9k/ar9002_phy.c +++ b/drivers/net/wireless/ath/ath9k/ar9002_phy.c @@ -473,21 +473,21 @@ static void ar9002_hw_do_getnf(struct ath_hw *ah, int16_t nf; nf = MS(REG_READ(ah, AR_PHY_CCA), AR9280_PHY_MINCCA_PWR); - nfarray[0] = sign_extend(nf, 9); + nfarray[0] = sign_extend32(nf, 8); nf = MS(REG_READ(ah, AR_PHY_EXT_CCA), AR9280_PHY_EXT_MINCCA_PWR); if (IS_CHAN_HT40(ah->curchan)) - nfarray[3] = sign_extend(nf, 9); + nfarray[3] = sign_extend32(nf, 8); if (AR_SREV_9285(ah) || AR_SREV_9271(ah)) return; nf = MS(REG_READ(ah, AR_PHY_CH1_CCA), AR9280_PHY_CH1_MINCCA_PWR); - nfarray[1] = sign_extend(nf, 9); + nfarray[1] = sign_extend32(nf, 8); nf = MS(REG_READ(ah, AR_PHY_CH1_EXT_CCA), AR9280_PHY_CH1_EXT_MINCCA_PWR); if (IS_CHAN_HT40(ah->curchan)) - nfarray[4] = sign_extend(nf, 9); + nfarray[4] = sign_extend32(nf, 8); } static void ar9002_hw_set_nf_limits(struct ath_hw *ah) diff --git a/drivers/net/wireless/ath/ath9k/ar9003_phy.c b/drivers/net/wireless/ath/ath9k/ar9003_phy.c index 06a9c4cd2f44..44c5454b2ad8 100644 --- a/drivers/net/wireless/ath/ath9k/ar9003_phy.c +++ b/drivers/net/wireless/ath/ath9k/ar9003_phy.c @@ -1023,25 +1023,25 @@ static void ar9003_hw_do_getnf(struct ath_hw *ah, int16_t nf; nf = MS(REG_READ(ah, AR_PHY_CCA_0), AR_PHY_MINCCA_PWR); - nfarray[0] = sign_extend(nf, 9); + nfarray[0] = sign_extend32(nf, 8); nf = MS(REG_READ(ah, AR_PHY_CCA_1), AR_PHY_CH1_MINCCA_PWR); - nfarray[1] = sign_extend(nf, 9); + nfarray[1] = sign_extend32(nf, 8); nf = MS(REG_READ(ah, AR_PHY_CCA_2), AR_PHY_CH2_MINCCA_PWR); - nfarray[2] = sign_extend(nf, 9); + nfarray[2] = sign_extend32(nf, 8); if (!IS_CHAN_HT40(ah->curchan)) return; nf = MS(REG_READ(ah, AR_PHY_EXT_CCA), AR_PHY_EXT_MINCCA_PWR); - nfarray[3] = sign_extend(nf, 9); + nfarray[3] = sign_extend32(nf, 8); nf = MS(REG_READ(ah, AR_PHY_EXT_CCA_1), AR_PHY_CH1_EXT_MINCCA_PWR); - nfarray[4] = sign_extend(nf, 9); + nfarray[4] = sign_extend32(nf, 8); nf = MS(REG_READ(ah, AR_PHY_EXT_CCA_2), AR_PHY_CH2_EXT_MINCCA_PWR); - nfarray[5] = sign_extend(nf, 9); + nfarray[5] = sign_extend32(nf, 8); } static void ar9003_hw_set_nf_limits(struct ath_hw *ah) diff --git a/drivers/net/wireless/ath/ath9k/hw.h b/drivers/net/wireless/ath/ath9k/hw.h index e5b72262fd96..f821a28bcda3 100644 --- a/drivers/net/wireless/ath/ath9k/hw.h +++ b/drivers/net/wireless/ath/ath9k/hw.h @@ -825,12 +825,6 @@ static inline struct ath_hw_ops *ath9k_hw_ops(struct ath_hw *ah) return &ah->ops; } -static inline int sign_extend(int val, const int nbits) -{ - int order = BIT(nbits-1); - return (val ^ order) - order; -} - /* Initialization, Detach, Reset */ const char *ath9k_hw_probe(u16 vendorid, u16 devid); void ath9k_hw_deinit(struct ath_hw *ah); diff --git a/drivers/net/wireless/iwlwifi/iwl-4965.c b/drivers/net/wireless/iwlwifi/iwl-4965.c index cd14843878ae..4748d067eb1d 100644 --- a/drivers/net/wireless/iwlwifi/iwl-4965.c +++ b/drivers/net/wireless/iwlwifi/iwl-4965.c @@ -1686,22 +1686,6 @@ static void iwl4965_txq_update_byte_cnt_tbl(struct iwl_priv *priv, tfd_offset[TFD_QUEUE_SIZE_MAX + write_ptr] = bc_ent; } -/** - * sign_extend - Sign extend a value using specified bit as sign-bit - * - * Example: sign_extend(9, 3) would return -7 as bit3 of 1001b is 1 - * and bit0..2 is 001b which when sign extended to 1111111111111001b is -7. - * - * @param oper value to sign extend - * @param index 0 based bit index (0<=index<32) to sign bit - */ -static s32 sign_extend(u32 oper, int index) -{ - u8 shift = 31 - index; - - return (s32)(oper << shift) >> shift; -} - /** * iwl4965_hw_get_temperature - return the calibrated temperature (in Kelvin) * @statistics: Provides the temperature reading from the uCode @@ -1739,9 +1723,9 @@ static int iwl4965_hw_get_temperature(struct iwl_priv *priv) * "initialize" ALIVE response. */ if (!test_bit(STATUS_TEMPERATURE, &priv->status)) - vt = sign_extend(R4, 23); + vt = sign_extend32(R4, 23); else - vt = sign_extend(le32_to_cpu(priv->_agn.statistics. + vt = sign_extend32(le32_to_cpu(priv->_agn.statistics. general.common.temperature), 23); IWL_DEBUG_TEMP(priv, "Calib values R[1-3]: %d %d %d R4: %d\n", R1, R2, R3, vt); diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 827cc95711ef..2184c6b97aeb 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -109,6 +109,17 @@ static inline __u8 ror8(__u8 word, unsigned int shift) return (word >> shift) | (word << (8 - shift)); } +/** + * sign_extend32 - sign extend a 32-bit value using specified bit as sign-bit + * @value: value to sign extend + * @index: 0 based bit index (0<=index<32) to sign bit + */ +static inline __s32 sign_extend32(__u32 value, int index) +{ + __u8 shift = 31 - index; + return (__s32)(value << shift) >> shift; +} + static inline unsigned fls_long(unsigned long l) { if (sizeof(l) == 4) -- cgit v1.2.3 From fe8222406c8277a21172479d3a8283d31c209028 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Tue, 9 Nov 2010 10:47:38 +0000 Subject: net: Simplify RX queue allocation This patch move RX queue allocation to alloc_netdev_mq and freeing of the queues to free_netdev (symmetric to TX queue allocation). Each kobject RX queue takes a reference to the queue's device so that the device can't be freed before all the kobjects have been released-- this obviates the need for reference counts specific to RX queues. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 +-- net/core/dev.c | 19 ++++++++++--------- net/core/net-sysfs.c | 7 ++----- 3 files changed, 13 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 6e4cfbc53d4c..fccb11f879e5 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -592,8 +592,7 @@ struct netdev_rx_queue { struct rps_map __rcu *rps_map; struct rps_dev_flow_table __rcu *rps_flow_table; struct kobject kobj; - struct netdev_rx_queue *first; - atomic_t count; + struct net_device *dev; } ____cacheline_aligned_in_smp; #endif /* CONFIG_RPS */ diff --git a/net/core/dev.c b/net/core/dev.c index 75490670e0a9..8725d168d1f5 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5051,12 +5051,8 @@ static int netif_alloc_rx_queues(struct net_device *dev) } dev->_rx = rx; - /* - * Set a pointer to first element in the array which holds the - * reference count. - */ for (i = 0; i < count; i++) - rx[i].first = rx; + rx[i].dev = dev; #endif return 0; } @@ -5132,10 +5128,6 @@ int register_netdevice(struct net_device *dev) dev->iflink = -1; - ret = netif_alloc_rx_queues(dev); - if (ret) - goto out; - netdev_init_queues(dev); /* Init, if this function is available */ @@ -5601,6 +5593,8 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, #ifdef CONFIG_RPS dev->num_rx_queues = queue_count; dev->real_num_rx_queues = queue_count; + if (netif_alloc_rx_queues(dev)) + goto free_pcpu; #endif dev->gso_max_size = GSO_MAX_SIZE; @@ -5618,6 +5612,10 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, free_pcpu: free_percpu(dev->pcpu_refcnt); kfree(dev->_tx); +#ifdef CONFIG_RPS + kfree(dev->_rx); +#endif + free_p: kfree(p); return NULL; @@ -5639,6 +5637,9 @@ void free_netdev(struct net_device *dev) release_net(dev_net(dev)); kfree(dev->_tx); +#ifdef CONFIG_RPS + kfree(dev->_rx); +#endif kfree(rcu_dereference_raw(dev->ingress_queue)); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index a5ff5a89f376..3ba526b56fe3 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -706,7 +706,6 @@ static struct attribute *rx_queue_default_attrs[] = { static void rx_queue_release(struct kobject *kobj) { struct netdev_rx_queue *queue = to_rx_queue(kobj); - struct netdev_rx_queue *first = queue->first; struct rps_map *map; struct rps_dev_flow_table *flow_table; @@ -719,8 +718,7 @@ static void rx_queue_release(struct kobject *kobj) if (flow_table) call_rcu(&flow_table->rcu, rps_dev_flow_table_release); - if (atomic_dec_and_test(&first->count)) - kfree(first); + dev_put(queue->dev); } static struct kobj_type rx_queue_ktype = { @@ -732,7 +730,6 @@ static struct kobj_type rx_queue_ktype = { static int rx_queue_add_kobject(struct net_device *net, int index) { struct netdev_rx_queue *queue = net->_rx + index; - struct netdev_rx_queue *first = queue->first; struct kobject *kobj = &queue->kobj; int error = 0; @@ -745,7 +742,7 @@ static int rx_queue_add_kobject(struct net_device *net, int index) } kobject_uevent(kobj, KOBJ_ADD); - atomic_inc(&first->count); + dev_hold(queue->dev); return error; } -- cgit v1.2.3 From c59504ebc5baa628706d10c2d3c7e1f4bc3c2147 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Sun, 14 Nov 2010 17:04:57 +0000 Subject: include/linux/if_macvlan.h: Remove unnecessary semicolons Signed-off-by: Joe Perches Signed-off-by: David S. Miller --- include/linux/if_macvlan.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index 8a2fd66a8b5f..ac96a2d76291 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -69,7 +69,7 @@ static inline void macvlan_count_rx(const struct macvlan_dev *vlan, rx_stats = this_cpu_ptr(vlan->rx_stats); if (likely(success)) { u64_stats_update_begin(&rx_stats->syncp); - rx_stats->rx_packets++;; + rx_stats->rx_packets++; rx_stats->rx_bytes += len; if (multicast) rx_stats->rx_multicast++; -- cgit v1.2.3 From a386f99025f13b32502fe5dedf223c20d7283826 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 15 Nov 2010 06:38:11 +0000 Subject: bridge: add proper RCU annotation to should_route_hook Add br_should_route_hook_t typedef, this is the only way we can get a clean RCU implementation for function pointer. Move route_hook to location where it is used. Signed-off-by: Eric Dumazet Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/if_bridge.h | 4 +++- net/bridge/br.c | 4 ---- net/bridge/br_input.c | 10 +++++++--- net/bridge/netfilter/ebtable_broute.c | 3 ++- 4 files changed, 12 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 0d241a5c4909..f7e73c338c40 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -102,7 +102,9 @@ struct __fdb_entry { #include extern void brioctl_set(int (*ioctl_hook)(struct net *, unsigned int, void __user *)); -extern int (*br_should_route_hook)(struct sk_buff *skb); + +typedef int (*br_should_route_hook_t)(struct sk_buff *skb); +extern br_should_route_hook_t __rcu *br_should_route_hook; #endif diff --git a/net/bridge/br.c b/net/bridge/br.c index c8436fa31344..84bbb82599b2 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -22,8 +22,6 @@ #include "br_private.h" -int (*br_should_route_hook)(struct sk_buff *skb); - static const struct stp_proto br_stp_proto = { .rcv = br_stp_rcv, }; @@ -102,8 +100,6 @@ static void __exit br_deinit(void) br_fdb_fini(); } -EXPORT_SYMBOL(br_should_route_hook); - module_init(br_init) module_exit(br_deinit) MODULE_LICENSE("GPL"); diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 25207a1f182b..6f6d8e1b776f 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -21,6 +21,10 @@ /* Bridge group multicast address 802.1d (pg 51). */ const u8 br_group_address[ETH_ALEN] = { 0x01, 0x80, 0xc2, 0x00, 0x00, 0x00 }; +/* Hook for brouter */ +br_should_route_hook_t __rcu *br_should_route_hook __read_mostly; +EXPORT_SYMBOL(br_should_route_hook); + static int br_pass_frame_up(struct sk_buff *skb) { struct net_device *indev, *brdev = BR_INPUT_SKB_CB(skb)->brdev; @@ -139,7 +143,7 @@ struct sk_buff *br_handle_frame(struct sk_buff *skb) { struct net_bridge_port *p; const unsigned char *dest = eth_hdr(skb)->h_dest; - int (*rhook)(struct sk_buff *skb); + br_should_route_hook_t *rhook; if (unlikely(skb->pkt_type == PACKET_LOOPBACK)) return skb; @@ -173,8 +177,8 @@ forward: switch (p->state) { case BR_STATE_FORWARDING: rhook = rcu_dereference(br_should_route_hook); - if (rhook != NULL) { - if (rhook(skb)) + if (rhook) { + if ((*rhook)(skb)) return skb; dest = eth_hdr(skb)->h_dest; } diff --git a/net/bridge/netfilter/ebtable_broute.c b/net/bridge/netfilter/ebtable_broute.c index ae3f106c3908..1bcaf36ad612 100644 --- a/net/bridge/netfilter/ebtable_broute.c +++ b/net/bridge/netfilter/ebtable_broute.c @@ -87,7 +87,8 @@ static int __init ebtable_broute_init(void) if (ret < 0) return ret; /* see br_input.c */ - rcu_assign_pointer(br_should_route_hook, ebt_broute); + rcu_assign_pointer(br_should_route_hook, + (br_should_route_hook_t *)ebt_broute); return 0; } -- cgit v1.2.3 From 61391cde9eefac5cfcf6d214aa80c77e58b1626b Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Mon, 15 Nov 2010 06:38:12 +0000 Subject: netdev: add rcu annotations to receive handler hook Suggested by Eric's bridge RCU changes. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index fccb11f879e5..b45c1b8b1d19 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -994,8 +994,8 @@ struct net_device { unsigned int real_num_rx_queues; #endif - rx_handler_func_t *rx_handler; - void *rx_handler_data; + rx_handler_func_t __rcu *rx_handler; + void __rcu *rx_handler_data; struct netdev_queue __rcu *ingress_queue; -- cgit v1.2.3 From 8ffab51b3dfc54876f145f15b351c41f3f703195 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 10 Nov 2010 21:14:04 +0000 Subject: macvlan: lockless tx path macvlan is a stacked device, like tunnels. We should use the lockless mechanism we are using in tunnels and loopback. This patch completely removes locking in TX path. tx stat counters are added into existing percpu stat structure, renamed from rx_stats to pcpu_stats. Note : this reverts commit 2c11455321f37 (macvlan: add multiqueue capability) Note : rx_errors converted to a 32bit counter, like tx_dropped, since they dont need 64bit range. Signed-off-by: Eric Dumazet Cc: Patrick McHardy Cc: Ben Greear Cc: Ben Hutchings Acked-by: Patrick McHardy Signed-off-by: David S. Miller --- drivers/net/macvlan.c | 80 ++++++++++++++++++++-------------------------- include/linux/if_macvlan.h | 34 ++++++++++++-------- 2 files changed, 55 insertions(+), 59 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 0fc9dc7f20db..93f0ba25c808 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -243,18 +243,22 @@ xmit_world: netdev_tx_t macvlan_start_xmit(struct sk_buff *skb, struct net_device *dev) { - int i = skb_get_queue_mapping(skb); - struct netdev_queue *txq = netdev_get_tx_queue(dev, i); unsigned int len = skb->len; int ret; + const struct macvlan_dev *vlan = netdev_priv(dev); ret = macvlan_queue_xmit(skb, dev); if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) { - txq->tx_packets++; - txq->tx_bytes += len; - } else - txq->tx_dropped++; + struct macvlan_pcpu_stats *pcpu_stats; + pcpu_stats = this_cpu_ptr(vlan->pcpu_stats); + u64_stats_update_begin(&pcpu_stats->syncp); + pcpu_stats->tx_packets++; + pcpu_stats->tx_bytes += len; + u64_stats_update_end(&pcpu_stats->syncp); + } else { + this_cpu_inc(vlan->pcpu_stats->tx_dropped); + } return ret; } EXPORT_SYMBOL_GPL(macvlan_start_xmit); @@ -414,14 +418,15 @@ static int macvlan_init(struct net_device *dev) dev->state = (dev->state & ~MACVLAN_STATE_MASK) | (lowerdev->state & MACVLAN_STATE_MASK); dev->features = lowerdev->features & MACVLAN_FEATURES; + dev->features |= NETIF_F_LLTX; dev->gso_max_size = lowerdev->gso_max_size; dev->iflink = lowerdev->ifindex; dev->hard_header_len = lowerdev->hard_header_len; macvlan_set_lockdep_class(dev); - vlan->rx_stats = alloc_percpu(struct macvlan_rx_stats); - if (!vlan->rx_stats) + vlan->pcpu_stats = alloc_percpu(struct macvlan_pcpu_stats); + if (!vlan->pcpu_stats) return -ENOMEM; return 0; @@ -431,7 +436,7 @@ static void macvlan_uninit(struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); - free_percpu(vlan->rx_stats); + free_percpu(vlan->pcpu_stats); } static struct rtnl_link_stats64 *macvlan_dev_get_stats64(struct net_device *dev, @@ -439,33 +444,38 @@ static struct rtnl_link_stats64 *macvlan_dev_get_stats64(struct net_device *dev, { struct macvlan_dev *vlan = netdev_priv(dev); - dev_txq_stats_fold(dev, stats); - - if (vlan->rx_stats) { - struct macvlan_rx_stats *p, accum = {0}; - u64 rx_packets, rx_bytes, rx_multicast; + if (vlan->pcpu_stats) { + struct macvlan_pcpu_stats *p; + u64 rx_packets, rx_bytes, rx_multicast, tx_packets, tx_bytes; + u32 rx_errors = 0, tx_dropped = 0; unsigned int start; int i; for_each_possible_cpu(i) { - p = per_cpu_ptr(vlan->rx_stats, i); + p = per_cpu_ptr(vlan->pcpu_stats, i); do { start = u64_stats_fetch_begin_bh(&p->syncp); rx_packets = p->rx_packets; rx_bytes = p->rx_bytes; rx_multicast = p->rx_multicast; + tx_packets = p->tx_packets; + tx_bytes = p->tx_bytes; } while (u64_stats_fetch_retry_bh(&p->syncp, start)); - accum.rx_packets += rx_packets; - accum.rx_bytes += rx_bytes; - accum.rx_multicast += rx_multicast; - /* rx_errors is an ulong, updated without syncp protection */ - accum.rx_errors += p->rx_errors; + + stats->rx_packets += rx_packets; + stats->rx_bytes += rx_bytes; + stats->multicast += rx_multicast; + stats->tx_packets += tx_packets; + stats->tx_bytes += tx_bytes; + /* rx_errors & tx_dropped are u32, updated + * without syncp protection. + */ + rx_errors += p->rx_errors; + tx_dropped += p->tx_dropped; } - stats->rx_packets = accum.rx_packets; - stats->rx_bytes = accum.rx_bytes; - stats->rx_errors = accum.rx_errors; - stats->rx_dropped = accum.rx_errors; - stats->multicast = accum.rx_multicast; + stats->rx_errors = rx_errors; + stats->rx_dropped = rx_errors; + stats->tx_dropped = tx_dropped; } return stats; } @@ -601,25 +611,6 @@ static int macvlan_validate(struct nlattr *tb[], struct nlattr *data[]) return 0; } -static int macvlan_get_tx_queues(struct net *net, - struct nlattr *tb[], - unsigned int *num_tx_queues, - unsigned int *real_num_tx_queues) -{ - struct net_device *real_dev; - - if (!tb[IFLA_LINK]) - return -EINVAL; - - real_dev = __dev_get_by_index(net, nla_get_u32(tb[IFLA_LINK])); - if (!real_dev) - return -ENODEV; - - *num_tx_queues = real_dev->num_tx_queues; - *real_num_tx_queues = real_dev->real_num_tx_queues; - return 0; -} - int macvlan_common_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], int (*receive)(struct sk_buff *skb), @@ -743,7 +734,6 @@ int macvlan_link_register(struct rtnl_link_ops *ops) { /* common fields */ ops->priv_size = sizeof(struct macvlan_dev); - ops->get_tx_queues = macvlan_get_tx_queues; ops->validate = macvlan_validate; ops->maxtype = IFLA_MACVLAN_MAX; ops->policy = macvlan_policy; diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index ac96a2d76291..e28b2e4959d4 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -25,19 +25,25 @@ struct macvlan_port; struct macvtap_queue; /** - * struct macvlan_rx_stats - MACVLAN percpu rx stats + * struct macvlan_pcpu_stats - MACVLAN percpu stats * @rx_packets: number of received packets * @rx_bytes: number of received bytes * @rx_multicast: number of received multicast packets + * @tx_packets: number of transmitted packets + * @tx_bytes: number of transmitted bytes * @syncp: synchronization point for 64bit counters - * @rx_errors: number of errors + * @rx_errors: number of rx errors + * @tx_dropped: number of tx dropped packets */ -struct macvlan_rx_stats { +struct macvlan_pcpu_stats { u64 rx_packets; u64 rx_bytes; u64 rx_multicast; + u64 tx_packets; + u64 tx_bytes; struct u64_stats_sync syncp; - unsigned long rx_errors; + u32 rx_errors; + u32 tx_dropped; }; /* @@ -52,7 +58,7 @@ struct macvlan_dev { struct hlist_node hlist; struct macvlan_port *port; struct net_device *lowerdev; - struct macvlan_rx_stats __percpu *rx_stats; + struct macvlan_pcpu_stats __percpu *pcpu_stats; enum macvlan_mode mode; int (*receive)(struct sk_buff *skb); int (*forward)(struct net_device *dev, struct sk_buff *skb); @@ -64,18 +70,18 @@ static inline void macvlan_count_rx(const struct macvlan_dev *vlan, unsigned int len, bool success, bool multicast) { - struct macvlan_rx_stats *rx_stats; - - rx_stats = this_cpu_ptr(vlan->rx_stats); if (likely(success)) { - u64_stats_update_begin(&rx_stats->syncp); - rx_stats->rx_packets++; - rx_stats->rx_bytes += len; + struct macvlan_pcpu_stats *pcpu_stats; + + pcpu_stats = this_cpu_ptr(vlan->pcpu_stats); + u64_stats_update_begin(&pcpu_stats->syncp); + pcpu_stats->rx_packets++; + pcpu_stats->rx_bytes += len; if (multicast) - rx_stats->rx_multicast++; - u64_stats_update_end(&rx_stats->syncp); + pcpu_stats->rx_multicast++; + u64_stats_update_end(&pcpu_stats->syncp); } else { - rx_stats->rx_errors++; + this_cpu_inc(vlan->pcpu_stats->rx_errors); } } -- cgit v1.2.3 From afe0cbf87500f0585d217deb8c6fd329793a7957 Mon Sep 17 00:00:00 2001 From: Bruno Randolf Date: Wed, 10 Nov 2010 12:50:50 +0900 Subject: cfg80211: Add nl80211 antenna configuration Allow setting of TX and RX antennas configuration via nl80211. The antenna configuration is defined as a bitmap of allowed antennas to use. This API can be used to mask out antennas which are not attached or should not be used for other reasons like regulatory concerns or special setups. Separate bitmaps are used for RX and TX to allow configuring different antennas for receiving and transmitting. Each bitmap is 32 bit long, each bit representing one antenna, starting with antenna 1 at the first bit. If an antenna bit is set, this means the driver is allowed to use this antenna for RX or TX respectively; if the bit is not set the hardware is not allowed to use this antenna. Using bitmaps has the benefit of allowing for a flexible configuration interface which can support many different configurations and which can be used for 802.11n as well as non-802.11n devices. Instead of relying on some hardware specific assumptions, drivers can use this information to know which antennas are actually attached to the system and derive their capabilities based on that. 802.11n devices should enable or disable chains, based on which antennas are present (If all antennas belonging to a particular chain are disabled, the entire chain should be disabled). HT capabilities (like STBC, TX Beamforming, Antenna selection) should be calculated based on the available chains after applying the antenna masks. Should a 802.11n device have diversity antennas attached to one of their chains, diversity can be enabled or disabled based on the antenna information. Non-802.11n drivers can use the antenna masks to select RX and TX antennas and to enable or disable antenna diversity. While covering chainmasks for 802.11n and the standard "legacy" modes "fixed antenna 1", "fixed antenna 2" and "diversity" this API also allows more rare, but useful configurations as follows: 1) Send on antenna 1, receive on antenna 2 (or vice versa). This can be used to have a low gain antenna for TX in order to keep within the regulatory constraints and a high gain antenna for RX in order to receive weaker signals ("speak softly, but listen harder"). This can be useful for building long-shot outdoor links. Another usage of this setup is having a low-noise pre-amplifier on antenna 1 and a power amplifier on the other antenna. This way transmit noise is mostly kept out of the low noise receive channel. (This would be bitmaps: tx 1 rx 2). 2) Another similar setup is: Use RX diversity on both antennas, but always send on antenna 1. Again that would allow us to benefit from a higher gain RX antenna, while staying within the legal limits. (This would be: tx 0 rx 3). 3) And finally there can be special experimental setups in research and development even with pre 802.11n hardware where more than 2 antennas are available. It's good to keep the API simple, yet flexible. Signed-off-by: Bruno Randolf -- v7: Made bitmasks 32 bit wide and rebased to latest wireless-testing. Signed-off-by: John W. Linville --- include/linux/nl80211.h | 25 +++++++++++++++++++++++++ include/net/cfg80211.h | 3 +++ net/wireless/nl80211.c | 31 ++++++++++++++++++++++++++++++- 3 files changed, 58 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index fb877b5621b7..17c5c8849250 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -804,6 +804,28 @@ enum nl80211_commands { * @NL80211_ATTR_SUPPORT_IBSS_RSN: The device supports IBSS RSN, which mostly * means support for per-station GTKs. * + * @NL80211_ATTR_WIPHY_ANTENNA_TX: Bitmap of allowed antennas for transmitting. + * This can be used to mask out antennas which are not attached or should + * not be used for transmitting. If an antenna is not selected in this + * bitmap the hardware is not allowed to transmit on this antenna. + * + * Each bit represents one antenna, starting with antenna 1 at the first + * bit. Depending on which antennas are selected in the bitmap, 802.11n + * drivers can derive which chainmasks to use (if all antennas belonging to + * a particular chain are disabled this chain should be disabled) and if + * a chain has diversity antennas wether diversity should be used or not. + * HT capabilities (STBC, TX Beamforming, Antenna selection) can be + * derived from the available chains after applying the antenna mask. + * Non-802.11n drivers can derive wether to use diversity or not. + * Drivers may reject configurations or RX/TX mask combinations they cannot + * support by returning -EINVAL. + * + * @NL80211_ATTR_WIPHY_ANTENNA_RX: Bitmap of allowed antennas for receiving. + * This can be used to mask out antennas which are not attached or should + * not be used for receiving. If an antenna is not selected in this bitmap + * the hardware should not be configured to receive on this antenna. + * For a more detailed descripton see @NL80211_ATTR_WIPHY_ANTENNA_TX. + * * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use */ @@ -973,6 +995,9 @@ enum nl80211_attrs { NL80211_ATTR_SUPPORT_IBSS_RSN, + NL80211_ATTR_WIPHY_ANTENNA_TX, + NL80211_ATTR_WIPHY_ANTENNA_RX, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index e5702f5ac57c..07425e648a09 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1304,6 +1304,9 @@ struct cfg80211_ops { void (*mgmt_frame_register)(struct wiphy *wiphy, struct net_device *dev, u16 frame_type, bool reg); + + int (*set_antenna)(struct wiphy *wiphy, u32 tx_ant, u32 rx_ant); + int (*get_antenna)(struct wiphy *wiphy, u32 *tx_ant, u32 *rx_ant); }; /* diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index c506241f8637..5e4dda4c0fd3 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -166,7 +166,11 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = { [NL80211_ATTR_WIPHY_TX_POWER_SETTING] = { .type = NLA_U32 }, [NL80211_ATTR_WIPHY_TX_POWER_LEVEL] = { .type = NLA_U32 }, + [NL80211_ATTR_FRAME_TYPE] = { .type = NLA_U16 }, + + [NL80211_ATTR_WIPHY_ANTENNA_TX] = { .type = NLA_U32 }, + [NL80211_ATTR_WIPHY_ANTENNA_RX] = { .type = NLA_U32 }, }; /* policy for the key attributes */ @@ -526,7 +530,6 @@ static int nl80211_send_wiphy(struct sk_buff *msg, u32 pid, u32 seq, int flags, dev->wiphy.rts_threshold); NLA_PUT_U8(msg, NL80211_ATTR_WIPHY_COVERAGE_CLASS, dev->wiphy.coverage_class); - NLA_PUT_U8(msg, NL80211_ATTR_MAX_NUM_SCAN_SSIDS, dev->wiphy.max_scan_ssids); NLA_PUT_U16(msg, NL80211_ATTR_MAX_SCAN_IE_LEN, @@ -545,6 +548,16 @@ static int nl80211_send_wiphy(struct sk_buff *msg, u32 pid, u32 seq, int flags, if (dev->wiphy.flags & WIPHY_FLAG_CONTROL_PORT_PROTOCOL) NLA_PUT_FLAG(msg, NL80211_ATTR_CONTROL_PORT_ETHERTYPE); + if (dev->ops->get_antenna) { + u32 tx_ant = 0, rx_ant = 0; + int res; + res = dev->ops->get_antenna(&dev->wiphy, &tx_ant, &rx_ant); + if (!res) { + NLA_PUT_U32(msg, NL80211_ATTR_WIPHY_ANTENNA_TX, tx_ant); + NLA_PUT_U32(msg, NL80211_ATTR_WIPHY_ANTENNA_RX, rx_ant); + } + } + nl_modes = nla_nest_start(msg, NL80211_ATTR_SUPPORTED_IFTYPES); if (!nl_modes) goto nla_put_failure; @@ -1024,6 +1037,22 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) goto bad_res; } + if (info->attrs[NL80211_ATTR_WIPHY_ANTENNA_TX] && + info->attrs[NL80211_ATTR_WIPHY_ANTENNA_RX]) { + u32 tx_ant, rx_ant; + if (!rdev->ops->set_antenna) { + result = -EOPNOTSUPP; + goto bad_res; + } + + tx_ant = nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_ANTENNA_TX]); + rx_ant = nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_ANTENNA_RX]); + + result = rdev->ops->set_antenna(&rdev->wiphy, tx_ant, rx_ant); + if (result) + goto bad_res; + } + changed = 0; if (info->attrs[NL80211_ATTR_WIPHY_RETRY_SHORT]) { -- cgit v1.2.3 From 885a46d0f7942d76c2f3860acb45f75237d3bb42 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Thu, 11 Nov 2010 15:07:22 +0100 Subject: cfg80211: add support for setting the ad-hoc multicast rate Signed-off-by: Felix Fietkau Signed-off-by: John W. Linville --- include/linux/nl80211.h | 4 ++++ include/net/cfg80211.h | 2 ++ net/wireless/nl80211.c | 5 +++++ 3 files changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 17c5c8849250..037b4e498890 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -826,6 +826,8 @@ enum nl80211_commands { * the hardware should not be configured to receive on this antenna. * For a more detailed descripton see @NL80211_ATTR_WIPHY_ANTENNA_TX. * + * @NL80211_ATTR_MCAST_RATE: Multicast tx rate (in 100 kbps) for IBSS + * * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use */ @@ -998,6 +1000,8 @@ enum nl80211_attrs { NL80211_ATTR_WIPHY_ANTENNA_TX, NL80211_ATTR_WIPHY_ANTENNA_RX, + NL80211_ATTR_MCAST_RATE, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 07425e648a09..8fd9eebd0cc9 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -923,6 +923,7 @@ struct cfg80211_disassoc_request { * @privacy: this is a protected network, keys will be configured * after joining * @basic_rates: bitmap of basic rates to use when creating the IBSS + * @mcast_rate: multicast tx rate (in 100 kbps) */ struct cfg80211_ibss_params { u8 *ssid; @@ -934,6 +935,7 @@ struct cfg80211_ibss_params { u32 basic_rates; bool channel_fixed; bool privacy; + int mcast_rate; }; /** diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 5e4dda4c0fd3..605553842226 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -171,6 +171,8 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = { [NL80211_ATTR_WIPHY_ANTENNA_TX] = { .type = NLA_U32 }, [NL80211_ATTR_WIPHY_ANTENNA_RX] = { .type = NLA_U32 }, + + [NL80211_ATTR_MCAST_RATE] = { .type = NLA_U32 }, }; /* policy for the key attributes */ @@ -3681,6 +3683,9 @@ static int nl80211_join_ibss(struct sk_buff *skb, struct genl_info *info) return -EINVAL; } } + if (info->attrs[NL80211_ATTR_MCAST_RATE]) + ibss.mcast_rate = + nla_get_u32(info->attrs[NL80211_ATTR_MCAST_RATE]); if (ibss.privacy && info->attrs[NL80211_ATTR_KEYS]) { connkeys = nl80211_parse_connkeys(rdev, -- cgit v1.2.3 From da6836500414ae734cd9873c2d553db594f831e9 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Tue, 16 Nov 2010 11:52:38 +0000 Subject: netfilter: allow hooks to pass error code back up the stack SELinux would like to pass certain fatal errors back up the stack. This patch implements the generic netfilter support for this functionality. Based-on-patch-by: Patrick McHardy Signed-off-by: Eric Paris Signed-off-by: David S. Miller --- include/linux/netfilter.h | 2 ++ net/netfilter/core.c | 6 ++++-- 2 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 03317c8d4077..1893837b3966 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -33,6 +33,8 @@ #define NF_QUEUE_NR(x) ((((x) << NF_VERDICT_BITS) & NF_VERDICT_QMASK) | NF_QUEUE) +#define NF_DROP_ERR(x) (((-x) << NF_VERDICT_BITS) | NF_DROP) + /* only for userspace compatibility */ #ifndef __KERNEL__ /* Generic cache responses from hook functions. diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 85dabb86be6f..32fcbe290c04 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -173,9 +173,11 @@ next_hook: outdev, &elem, okfn, hook_thresh); if (verdict == NF_ACCEPT || verdict == NF_STOP) { ret = 1; - } else if (verdict == NF_DROP) { + } else if ((verdict & NF_VERDICT_MASK) == NF_DROP) { kfree_skb(skb); - ret = -EPERM; + ret = -(verdict >> NF_VERDICT_BITS); + if (ret == 0) + ret = -EPERM; } else if ((verdict & NF_VERDICT_MASK) == NF_QUEUE) { if (!nf_queue(skb, elem, pf, hook, indev, outdev, okfn, verdict >> NF_VERDICT_BITS)) -- cgit v1.2.3 From f8ff182c716c6f11ca3061961f5722f26a14e101 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Tue, 16 Nov 2010 04:30:14 +0000 Subject: rtnetlink: Link address family API Each net_device contains address family specific data such as per device settings and statistics. We already expose this data via procfs/sysfs and partially netlink. The netlink method requires the requester to send one RTM_GETLINK request for each address family it wishes to receive data of and then merge this data itself. This patch implements a new API which combines all address family specific link data in a new netlink attribute IFLA_AF_SPEC. IFLA_AF_SPEC contains a sequence of nested attributes, one for each address family which in turn defines the structure of its own attribute. Example: [IFLA_AF_SPEC] = { [AF_INET] = { [IFLA_INET_CONF] = ..., }, [AF_INET6] = { [IFLA_INET6_FLAGS] = ..., [IFLA_INET6_CONF] = ..., } } The API also allows for address families to implement a function which parses the IFLA_AF_SPEC attribute sent by userspace to implement address family specific link options. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/if_link.h | 19 +++++++ include/net/rtnetlink.h | 31 ++++++++++ net/core/rtnetlink.c | 147 +++++++++++++++++++++++++++++++++++++++++++++++- 3 files changed, 195 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_link.h b/include/linux/if_link.h index 2fc66dd783ee..443d04a66a79 100644 --- a/include/linux/if_link.h +++ b/include/linux/if_link.h @@ -80,6 +80,24 @@ struct rtnl_link_ifmap { __u8 port; }; +/* + * IFLA_AF_SPEC + * Contains nested attributes for address family specific attributes. + * Each address family may create a attribute with the address family + * number as type and create its own attribute structure in it. + * + * Example: + * [IFLA_AF_SPEC] = { + * [AF_INET] = { + * [IFLA_INET_CONF] = ..., + * }, + * [AF_INET6] = { + * [IFLA_INET6_FLAGS] = ..., + * [IFLA_INET6_CONF] = ..., + * } + * } + */ + enum { IFLA_UNSPEC, IFLA_ADDRESS, @@ -116,6 +134,7 @@ enum { IFLA_STATS64, IFLA_VF_PORTS, IFLA_PORT_SELF, + IFLA_AF_SPEC, __IFLA_MAX }; diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index e013c68bfb00..35be0bbcd7da 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -83,6 +83,37 @@ extern void __rtnl_link_unregister(struct rtnl_link_ops *ops); extern int rtnl_link_register(struct rtnl_link_ops *ops); extern void rtnl_link_unregister(struct rtnl_link_ops *ops); +/** + * struct rtnl_af_ops - rtnetlink address family operations + * + * @list: Used internally + * @family: Address family + * @fill_link_af: Function to fill IFLA_AF_SPEC with address family + * specific netlink attributes. + * @get_link_af_size: Function to calculate size of address family specific + * netlink attributes exlusive the container attribute. + * @parse_link_af: Function to parse a IFLA_AF_SPEC attribute and modify + * net_device accordingly. + */ +struct rtnl_af_ops { + struct list_head list; + int family; + + int (*fill_link_af)(struct sk_buff *skb, + const struct net_device *dev); + size_t (*get_link_af_size)(const struct net_device *dev); + + int (*parse_link_af)(struct net_device *dev, + const struct nlattr *attr); +}; + +extern int __rtnl_af_register(struct rtnl_af_ops *ops); +extern void __rtnl_af_unregister(struct rtnl_af_ops *ops); + +extern int rtnl_af_register(struct rtnl_af_ops *ops); +extern void rtnl_af_unregister(struct rtnl_af_ops *ops); + + extern struct net *rtnl_link_get_net(struct net *src_net, struct nlattr *tb[]); extern struct net_device *rtnl_create_link(struct net *src_net, struct net *net, char *ifname, const struct rtnl_link_ops *ops, struct nlattr *tb[]); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 841c287ef40a..bf69e5871b1a 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -362,6 +362,95 @@ static size_t rtnl_link_get_size(const struct net_device *dev) return size; } +static LIST_HEAD(rtnl_af_ops); + +static const struct rtnl_af_ops *rtnl_af_lookup(const int family) +{ + const struct rtnl_af_ops *ops; + + list_for_each_entry(ops, &rtnl_af_ops, list) { + if (ops->family == family) + return ops; + } + + return NULL; +} + +/** + * __rtnl_af_register - Register rtnl_af_ops with rtnetlink. + * @ops: struct rtnl_af_ops * to register + * + * The caller must hold the rtnl_mutex. + * + * Returns 0 on success or a negative error code. + */ +int __rtnl_af_register(struct rtnl_af_ops *ops) +{ + list_add_tail(&ops->list, &rtnl_af_ops); + return 0; +} +EXPORT_SYMBOL_GPL(__rtnl_af_register); + +/** + * rtnl_af_register - Register rtnl_af_ops with rtnetlink. + * @ops: struct rtnl_af_ops * to register + * + * Returns 0 on success or a negative error code. + */ +int rtnl_af_register(struct rtnl_af_ops *ops) +{ + int err; + + rtnl_lock(); + err = __rtnl_af_register(ops); + rtnl_unlock(); + return err; +} +EXPORT_SYMBOL_GPL(rtnl_af_register); + +/** + * __rtnl_af_unregister - Unregister rtnl_af_ops from rtnetlink. + * @ops: struct rtnl_af_ops * to unregister + * + * The caller must hold the rtnl_mutex. + */ +void __rtnl_af_unregister(struct rtnl_af_ops *ops) +{ + list_del(&ops->list); +} +EXPORT_SYMBOL_GPL(__rtnl_af_unregister); + +/** + * rtnl_af_unregister - Unregister rtnl_af_ops from rtnetlink. + * @ops: struct rtnl_af_ops * to unregister + */ +void rtnl_af_unregister(struct rtnl_af_ops *ops) +{ + rtnl_lock(); + __rtnl_af_unregister(ops); + rtnl_unlock(); +} +EXPORT_SYMBOL_GPL(rtnl_af_unregister); + +static size_t rtnl_link_get_af_size(const struct net_device *dev) +{ + struct rtnl_af_ops *af_ops; + size_t size; + + /* IFLA_AF_SPEC */ + size = nla_total_size(sizeof(struct nlattr)); + + list_for_each_entry(af_ops, &rtnl_af_ops, list) { + if (af_ops->get_link_af_size) { + /* AF_* + nested data */ + size += nla_total_size(sizeof(struct nlattr)) + + af_ops->get_link_af_size(dev); + } + } + + return size; +} + static int rtnl_link_fill(struct sk_buff *skb, const struct net_device *dev) { const struct rtnl_link_ops *ops = dev->rtnl_link_ops; @@ -671,7 +760,8 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev) + nla_total_size(4) /* IFLA_NUM_VF */ + rtnl_vfinfo_size(dev) /* IFLA_VFINFO_LIST */ + rtnl_port_size(dev) /* IFLA_VF_PORTS + IFLA_PORT_SELF */ - + rtnl_link_get_size(dev); /* IFLA_LINKINFO */ + + rtnl_link_get_size(dev) /* IFLA_LINKINFO */ + + rtnl_link_get_af_size(dev); /* IFLA_AF_SPEC */ } static int rtnl_vf_ports_fill(struct sk_buff *skb, struct net_device *dev) @@ -757,7 +847,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, struct nlmsghdr *nlh; struct rtnl_link_stats64 temp; const struct rtnl_link_stats64 *stats; - struct nlattr *attr; + struct nlattr *attr, *af_spec; + struct rtnl_af_ops *af_ops; nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ifm), flags); if (nlh == NULL) @@ -866,6 +957,36 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, goto nla_put_failure; } + if (!(af_spec = nla_nest_start(skb, IFLA_AF_SPEC))) + goto nla_put_failure; + + list_for_each_entry(af_ops, &rtnl_af_ops, list) { + if (af_ops->fill_link_af) { + struct nlattr *af; + int err; + + if (!(af = nla_nest_start(skb, af_ops->family))) + goto nla_put_failure; + + err = af_ops->fill_link_af(skb, dev); + + /* + * Caller may return ENODATA to indicate that there + * was no data to be dumped. This is not an error, it + * means we should trim the attribute header and + * continue. + */ + if (err == -ENODATA) + nla_nest_cancel(skb, af); + else if (err < 0) + goto nla_put_failure; + + nla_nest_end(skb, af); + } + } + + nla_nest_end(skb, af_spec); + return nlmsg_end(skb, nlh); nla_put_failure: @@ -924,6 +1045,7 @@ const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_VFINFO_LIST] = {. type = NLA_NESTED }, [IFLA_VF_PORTS] = { .type = NLA_NESTED }, [IFLA_PORT_SELF] = { .type = NLA_NESTED }, + [IFLA_AF_SPEC] = { .type = NLA_NESTED }, }; EXPORT_SYMBOL(ifla_policy); @@ -1225,6 +1347,27 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, goto errout; modified = 1; } + + if (tb[IFLA_AF_SPEC]) { + struct nlattr *af; + int rem; + + nla_for_each_nested(af, tb[IFLA_AF_SPEC], rem) { + const struct rtnl_af_ops *af_ops; + + if (!(af_ops = rtnl_af_lookup(nla_type(af)))) + continue; + + if (!af_ops->parse_link_af) + continue; + + err = af_ops->parse_link_af(dev, af); + if (err < 0) + goto errout; + + modified = 1; + } + } err = 0; errout: -- cgit v1.2.3 From ca7479ebbd9f7621646bf2792cb7143647f035bb Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Tue, 16 Nov 2010 04:31:20 +0000 Subject: inet: Define IPV4_DEVCONF_MAX Define IPV4_DEVCONF_MAX to get rid of MAX - 1 notation. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/inetdevice.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index 380ba6bc5db1..2b86eaf11773 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -41,10 +41,12 @@ enum __IPV4_DEVCONF_MAX }; +#define IPV4_DEVCONF_MAX (__IPV4_DEVCONF_MAX - 1) + struct ipv4_devconf { void *sysctl; - int data[__IPV4_DEVCONF_MAX - 1]; - DECLARE_BITMAP(state, __IPV4_DEVCONF_MAX - 1); + int data[IPV4_DEVCONF_MAX]; + DECLARE_BITMAP(state, IPV4_DEVCONF_MAX); }; struct in_device { @@ -90,7 +92,7 @@ static inline void ipv4_devconf_set(struct in_device *in_dev, int index, static inline void ipv4_devconf_setall(struct in_device *in_dev) { - bitmap_fill(in_dev->cnf.state, __IPV4_DEVCONF_MAX - 1); + bitmap_fill(in_dev->cnf.state, IPV4_DEVCONF_MAX); } #define IN_DEV_CONF_GET(in_dev, attr) \ -- cgit v1.2.3 From 9f0f7272ac9506f4c8c05cc597b7e376b0b9f3e4 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Tue, 16 Nov 2010 04:32:48 +0000 Subject: ipv4: AF_INET link address family Implements the AF_INET link address family exposing the per device configuration settings via netlink using the attribute IFLA_INET_CONF. The format of IFLA_INET_CONF differs depending on the direction the attribute is sent. The attribute sent by the kernel consists of a u32 array, basically a 1:1 copy of in_device->cnf.data[]. The attribute expected by the kernel must consist of a sequence of nested u32 attributes, each representing a change request, e.g. [IFLA_INET_CONF] = { [IPV4_DEVCONF_FORWARDING] = 1, [IPV4_DEVCONF_NOXFRM] = 0, } libnl userspace API documentation and example available from: http://www.infradead.org/~tgr/libnl/doc-git/group__link__inet.html Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/if_link.h | 8 ++++++ net/ipv4/devinet.c | 75 +++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 83 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if_link.h b/include/linux/if_link.h index 443d04a66a79..2e02e4d7b11e 100644 --- a/include/linux/if_link.h +++ b/include/linux/if_link.h @@ -147,6 +147,14 @@ enum { #define IFLA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct ifinfomsg)) #endif +enum { + IFLA_INET_UNSPEC, + IFLA_INET_CONF, + __IFLA_INET_MAX, +}; + +#define IFLA_INET_MAX (__IFLA_INET_MAX - 1) + /* ifi_flags. IFF_* flags. diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index dc94b0316b78..71afc26c2df8 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1256,6 +1256,72 @@ errout: rtnl_set_sk_err(net, RTNLGRP_IPV4_IFADDR, err); } +static size_t inet_get_link_af_size(const struct net_device *dev) +{ + struct in_device *in_dev = __in_dev_get_rcu(dev); + + if (!in_dev) + return 0; + + return nla_total_size(IPV4_DEVCONF_MAX * 4); /* IFLA_INET_CONF */ +} + +static int inet_fill_link_af(struct sk_buff *skb, const struct net_device *dev) +{ + struct in_device *in_dev = __in_dev_get_rcu(dev); + struct nlattr *nla; + int i; + + if (!in_dev) + return -ENODATA; + + nla = nla_reserve(skb, IFLA_INET_CONF, IPV4_DEVCONF_MAX * 4); + if (nla == NULL) + return -EMSGSIZE; + + for (i = 0; i < IPV4_DEVCONF_MAX; i++) + ((u32 *) nla_data(nla))[i] = in_dev->cnf.data[i]; + + return 0; +} + +static const struct nla_policy inet_af_policy[IFLA_INET_MAX+1] = { + [IFLA_INET_CONF] = { .type = NLA_NESTED }, +}; + +static int inet_parse_link_af(struct net_device *dev, const struct nlattr *nla) +{ + struct in_device *in_dev = __in_dev_get_rcu(dev); + struct nlattr *a, *tb[IFLA_INET_MAX+1]; + int err, rem; + + if (!in_dev) + return -EOPNOTSUPP; + + err = nla_parse_nested(tb, IFLA_INET_MAX, nla, inet_af_policy); + if (err < 0) + return err; + + if (tb[IFLA_INET_CONF]) { + nla_for_each_nested(a, tb[IFLA_INET_CONF], rem) { + int cfgid = nla_type(a); + + if (nla_len(a) < 4) + return -EINVAL; + + if (cfgid <= 0 || cfgid > IPV4_DEVCONF_MAX) + return -EINVAL; + } + } + + if (tb[IFLA_INET_CONF]) { + nla_for_each_nested(a, tb[IFLA_INET_CONF], rem) + ipv4_devconf_set(in_dev, nla_type(a), nla_get_u32(a)); + } + + return 0; +} + #ifdef CONFIG_SYSCTL static void devinet_copy_dflt_conf(struct net *net, int i) @@ -1619,6 +1685,13 @@ static __net_initdata struct pernet_operations devinet_ops = { .exit = devinet_exit_net, }; +static struct rtnl_af_ops inet_af_ops = { + .family = AF_INET, + .fill_link_af = inet_fill_link_af, + .get_link_af_size = inet_get_link_af_size, + .parse_link_af = inet_parse_link_af, +}; + void __init devinet_init(void) { register_pernet_subsys(&devinet_ops); @@ -1626,6 +1699,8 @@ void __init devinet_init(void) register_gifconf(PF_INET, inet_gifconf); register_netdevice_notifier(&ip_netdev_notifier); + rtnl_af_register(&inet_af_ops); + rtnl_register(PF_INET, RTM_NEWADDR, inet_rtm_newaddr, NULL); rtnl_register(PF_INET, RTM_DELADDR, inet_rtm_deladdr, NULL); rtnl_register(PF_INET, RTM_GETADDR, NULL, inet_dump_ifaddr); -- cgit v1.2.3 From b2c0710c464ede15e1fc52fb1e7ee9ba54cea186 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 9 Sep 2010 13:40:39 -0700 Subject: rcu: move TINY_RCU from softirq to kthread If RCU priority boosting is to be meaningful, callback invocation must be boosted in addition to preempted RCU readers. Otherwise, in presence of CPU real-time threads, the grace period ends, but the callbacks don't get invoked. If the callbacks don't get invoked, the associated memory doesn't get freed, so the system is still subject to OOM. But it is not reasonable to priority-boost RCU_SOFTIRQ, so this commit moves the callback invocations to a kthread, which can be boosted easily. Signed-off-by: Paul E. McKenney Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 1 - include/linux/rcutiny.h | 8 ++---- include/linux/rcutree.h | 1 + kernel/rcutiny.c | 71 +++++++++++++++++++++++++++++++++++++++--------- kernel/rcutiny_plugin.h | 15 +++++----- 5 files changed, 70 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 03cda7bed985..7142ee3304ab 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -118,7 +118,6 @@ static inline int rcu_preempt_depth(void) #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ /* Internal to kernel */ -extern void rcu_init(void); extern void rcu_sched_qs(int cpu); extern void rcu_bh_qs(int cpu); extern void rcu_check_callbacks(int cpu, int user); diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 13877cb93a60..ea025a611fcc 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -27,7 +27,9 @@ #include -#define rcu_init_sched() do { } while (0) +static inline void rcu_init(void) +{ +} #ifdef CONFIG_TINY_RCU @@ -125,16 +127,12 @@ static inline void rcu_cpu_stall_reset(void) } #ifdef CONFIG_DEBUG_LOCK_ALLOC - extern int rcu_scheduler_active __read_mostly; extern void rcu_scheduler_starting(void); - #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ - static inline void rcu_scheduler_starting(void) { } - #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ #endif /* __LINUX_RCUTINY_H */ diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 95518e628794..c0e96833aa73 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -30,6 +30,7 @@ #ifndef __LINUX_RCUTREE_H #define __LINUX_RCUTREE_H +extern void rcu_init(void); extern void rcu_note_context_switch(int cpu); extern int rcu_needs_cpu(int cpu); extern void rcu_cpu_stall_reset(void); diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c index d806735342ac..86eef29cdfb2 100644 --- a/kernel/rcutiny.c +++ b/kernel/rcutiny.c @@ -59,8 +59,15 @@ int rcu_scheduler_active __read_mostly; EXPORT_SYMBOL_GPL(rcu_scheduler_active); #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ +/* Controls for rcu_cbs() kthread, replacing RCU_SOFTIRQ used previously. */ +static struct task_struct *rcu_cbs_task; +static DECLARE_WAIT_QUEUE_HEAD(rcu_cbs_wq); +static unsigned long have_rcu_cbs; +static void invoke_rcu_cbs(void); + /* Forward declarations for rcutiny_plugin.h. */ -static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp); +static void rcu_process_callbacks(struct rcu_ctrlblk *rcp); +static int rcu_cbs(void *arg); static void __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), struct rcu_ctrlblk *rcp); @@ -123,7 +130,7 @@ void rcu_sched_qs(int cpu) { if (rcu_qsctr_help(&rcu_sched_ctrlblk) + rcu_qsctr_help(&rcu_bh_ctrlblk)) - raise_softirq(RCU_SOFTIRQ); + invoke_rcu_cbs(); } /* @@ -132,7 +139,7 @@ void rcu_sched_qs(int cpu) void rcu_bh_qs(int cpu) { if (rcu_qsctr_help(&rcu_bh_ctrlblk)) - raise_softirq(RCU_SOFTIRQ); + invoke_rcu_cbs(); } /* @@ -152,10 +159,10 @@ void rcu_check_callbacks(int cpu, int user) } /* - * Helper function for rcu_process_callbacks() that operates on the - * specified rcu_ctrlkblk structure. + * Invoke the RCU callbacks on the specified rcu_ctrlkblk structure + * whose grace period has elapsed. */ -static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp) +static void rcu_process_callbacks(struct rcu_ctrlblk *rcp) { struct rcu_head *next, *list; unsigned long flags; @@ -180,19 +187,52 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp) next = list->next; prefetch(next); debug_rcu_head_unqueue(list); + local_bh_disable(); list->func(list); + local_bh_enable(); list = next; } } /* - * Invoke any callbacks whose grace period has completed. + * This kthread invokes RCU callbacks whose grace periods have + * elapsed. It is awakened as needed, and takes the place of the + * RCU_SOFTIRQ that was used previously for this purpose. + * This is a kthread, but it is never stopped, at least not until + * the system goes down. + */ +static int rcu_cbs(void *arg) +{ + unsigned long work; + unsigned long flags; + + for (;;) { + wait_event(rcu_cbs_wq, have_rcu_cbs != 0); + local_irq_save(flags); + work = have_rcu_cbs; + have_rcu_cbs = 0; + local_irq_restore(flags); + if (work) { + rcu_process_callbacks(&rcu_sched_ctrlblk); + rcu_process_callbacks(&rcu_bh_ctrlblk); + rcu_preempt_process_callbacks(); + } + } + + return 0; /* Not reached, but needed to shut gcc up. */ +} + +/* + * Wake up rcu_cbs() to process callbacks now eligible for invocation. */ -static void rcu_process_callbacks(struct softirq_action *unused) +static void invoke_rcu_cbs(void) { - __rcu_process_callbacks(&rcu_sched_ctrlblk); - __rcu_process_callbacks(&rcu_bh_ctrlblk); - rcu_preempt_process_callbacks(); + unsigned long flags; + + local_irq_save(flags); + have_rcu_cbs = 1; + wake_up(&rcu_cbs_wq); + local_irq_restore(flags); } /* @@ -282,7 +322,12 @@ void rcu_barrier_sched(void) } EXPORT_SYMBOL_GPL(rcu_barrier_sched); -void __init rcu_init(void) +/* + * Spawn the kthread that invokes RCU callbacks. + */ +static int __init rcu_spawn_kthreads(void) { - open_softirq(RCU_SOFTIRQ, rcu_process_callbacks); + rcu_cbs_task = kthread_run(rcu_cbs, NULL, "rcu_cbs"); + return 0; } +early_initcall(rcu_spawn_kthreads); diff --git a/kernel/rcutiny_plugin.h b/kernel/rcutiny_plugin.h index 6ceca4f745ff..95f9239df512 100644 --- a/kernel/rcutiny_plugin.h +++ b/kernel/rcutiny_plugin.h @@ -22,6 +22,8 @@ * Author: Paul E. McKenney */ +#include + #ifdef CONFIG_TINY_PREEMPT_RCU #include @@ -164,9 +166,9 @@ static void rcu_preempt_cpu_qs(void) if (!rcu_preempt_blocked_readers_any()) rcu_preempt_ctrlblk.rcb.donetail = rcu_preempt_ctrlblk.nexttail; - /* If there are done callbacks, make RCU_SOFTIRQ process them. */ + /* If there are done callbacks, cause them to be invoked. */ if (*rcu_preempt_ctrlblk.rcb.donetail != NULL) - raise_softirq(RCU_SOFTIRQ); + invoke_rcu_cbs(); } /* @@ -374,7 +376,7 @@ static void rcu_preempt_check_callbacks(void) rcu_preempt_cpu_qs(); if (&rcu_preempt_ctrlblk.rcb.rcucblist != rcu_preempt_ctrlblk.rcb.donetail) - raise_softirq(RCU_SOFTIRQ); + invoke_rcu_cbs(); if (rcu_preempt_gp_in_progress() && rcu_cpu_blocking_cur_gp() && rcu_preempt_running_reader()) @@ -383,7 +385,7 @@ static void rcu_preempt_check_callbacks(void) /* * TINY_PREEMPT_RCU has an extra callback-list tail pointer to - * update, so this is invoked from __rcu_process_callbacks() to + * update, so this is invoked from rcu_process_callbacks() to * handle that case. Of course, it is invoked for all flavors of * RCU, but RCU callbacks can appear only on one of the lists, and * neither ->nexttail nor ->donetail can possibly be NULL, so there @@ -400,7 +402,7 @@ static void rcu_preempt_remove_callbacks(struct rcu_ctrlblk *rcp) */ static void rcu_preempt_process_callbacks(void) { - __rcu_process_callbacks(&rcu_preempt_ctrlblk.rcb); + rcu_process_callbacks(&rcu_preempt_ctrlblk.rcb); } /* @@ -599,14 +601,13 @@ static void rcu_preempt_process_callbacks(void) #endif /* #else #ifdef CONFIG_TINY_PREEMPT_RCU */ #ifdef CONFIG_DEBUG_LOCK_ALLOC - #include /* * During boot, we forgive RCU lockdep issues. After this function is * invoked, we start taking RCU lockdep issues seriously. */ -void rcu_scheduler_starting(void) +void __init rcu_scheduler_starting(void) { WARN_ON(nr_context_switches() > 0); rcu_scheduler_active = 1; -- cgit v1.2.3 From 5f2b0ba4d94b3ac23cbc4b7f675d98eb677a760a Mon Sep 17 00:00:00 2001 From: Don Zickus Date: Fri, 12 Nov 2010 11:22:23 -0500 Subject: x86, nmi_watchdog: Remove the old nmi_watchdog Now that we have a new nmi_watchdog that is more generic and sits on top of the perf subsystem, we really do not need the old nmi_watchdog any more. In addition, the old nmi_watchdog doesn't really work if you are using the default clocksource, hpet. The old nmi_watchdog code relied on local apic interrupts to determine if the cpu is still alive. With hpet as the clocksource, these interrupts don't increment any more and the old nmi_watchdog triggers false postives. This piece removes the old nmi_watchdog code and stubs out any variables and functions calls. The stubs are the same ones used by the new nmi_watchdog code, so it should be well tested. Signed-off-by: Don Zickus Cc: fweisbec@gmail.com Cc: gorcunov@openvz.org LKML-Reference: <1289578944-28564-2-git-send-email-dzickus@redhat.com> Signed-off-by: Ingo Molnar --- arch/x86/include/asm/nmi.h | 4 - arch/x86/kernel/apic/Makefile | 5 +- arch/x86/kernel/apic/hw_nmi.c | 6 +- arch/x86/kernel/apic/nmi.c | 567 ------------------------------------------ arch/x86/kernel/traps.c | 9 - include/linux/nmi.h | 6 +- kernel/sysctl.c | 16 -- 7 files changed, 5 insertions(+), 608 deletions(-) delete mode 100644 arch/x86/kernel/apic/nmi.c (limited to 'include/linux') diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h index 932f0f86b4b7..33292ec848ca 100644 --- a/arch/x86/include/asm/nmi.h +++ b/arch/x86/include/asm/nmi.h @@ -17,9 +17,6 @@ int do_nmi_callback(struct pt_regs *regs, int cpu); extern void die_nmi(char *str, struct pt_regs *regs, int do_panic); extern int check_nmi_watchdog(void); -#if !defined(CONFIG_LOCKUP_DETECTOR) -extern int nmi_watchdog_enabled; -#endif extern int avail_to_resrv_perfctr_nmi_bit(unsigned int); extern int reserve_perfctr_nmi(unsigned int); extern void release_perfctr_nmi(unsigned int); @@ -30,7 +27,6 @@ extern void setup_apic_nmi_watchdog(void *); extern void stop_apic_nmi_watchdog(void *); extern void disable_timer_nmi_watchdog(void); extern void enable_timer_nmi_watchdog(void); -extern int nmi_watchdog_tick(struct pt_regs *regs, unsigned reason); extern void cpu_nmi_set_wd_enabled(void); extern atomic_t nmi_active; diff --git a/arch/x86/kernel/apic/Makefile b/arch/x86/kernel/apic/Makefile index 910f20b457c4..3966b564ea47 100644 --- a/arch/x86/kernel/apic/Makefile +++ b/arch/x86/kernel/apic/Makefile @@ -3,10 +3,7 @@ # obj-$(CONFIG_X86_LOCAL_APIC) += apic.o apic_noop.o probe_$(BITS).o ipi.o -ifneq ($(CONFIG_HARDLOCKUP_DETECTOR),y) -obj-$(CONFIG_X86_LOCAL_APIC) += nmi.o -endif -obj-$(CONFIG_HARDLOCKUP_DETECTOR) += hw_nmi.o +obj-y += hw_nmi.o obj-$(CONFIG_X86_IO_APIC) += io_apic.o obj-$(CONFIG_SMP) += ipi.o diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c index cefd6942f0e9..b68b17460016 100644 --- a/arch/x86/kernel/apic/hw_nmi.c +++ b/arch/x86/kernel/apic/hw_nmi.c @@ -20,12 +20,14 @@ /* For reliability, we're prepared to waste bits here. */ static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly; +#ifdef CONFIG_HARDLOCKUP_DETECTOR u64 hw_nmi_get_sample_period(void) { return (u64)(cpu_khz) * 1000 * 60; } +#endif -#ifdef ARCH_HAS_NMI_WATCHDOG +#ifdef arch_trigger_all_cpu_backtrace void arch_trigger_all_cpu_backtrace(void) { int i; @@ -95,8 +97,6 @@ early_initcall(register_trigger_all_cpu_backtrace); #if defined(CONFIG_X86_LOCAL_APIC) unsigned int nmi_watchdog = NMI_NONE; EXPORT_SYMBOL(nmi_watchdog); -void acpi_nmi_enable(void) { return; } -void acpi_nmi_disable(void) { return; } #endif atomic_t nmi_active = ATOMIC_INIT(0); /* oprofile uses this */ EXPORT_SYMBOL(nmi_active); diff --git a/arch/x86/kernel/apic/nmi.c b/arch/x86/kernel/apic/nmi.c deleted file mode 100644 index c90041ccb742..000000000000 --- a/arch/x86/kernel/apic/nmi.c +++ /dev/null @@ -1,567 +0,0 @@ -/* - * NMI watchdog support on APIC systems - * - * Started by Ingo Molnar - * - * Fixes: - * Mikael Pettersson : AMD K7 support for local APIC NMI watchdog. - * Mikael Pettersson : Power Management for local APIC NMI watchdog. - * Mikael Pettersson : Pentium 4 support for local APIC NMI watchdog. - * Pavel Machek and - * Mikael Pettersson : PM converted to driver model. Disable/enable API. - */ - -#include - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include - -#include - -#include - -int unknown_nmi_panic; -int nmi_watchdog_enabled; - -/* For reliability, we're prepared to waste bits here. */ -static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly; - -/* nmi_active: - * >0: the lapic NMI watchdog is active, but can be disabled - * <0: the lapic NMI watchdog has not been set up, and cannot - * be enabled - * 0: the lapic NMI watchdog is disabled, but can be enabled - */ -atomic_t nmi_active = ATOMIC_INIT(0); /* oprofile uses this */ -EXPORT_SYMBOL(nmi_active); - -unsigned int nmi_watchdog = NMI_NONE; -EXPORT_SYMBOL(nmi_watchdog); - -static int panic_on_timeout; - -static unsigned int nmi_hz = HZ; -static DEFINE_PER_CPU(short, wd_enabled); -static int endflag __initdata; - -static inline unsigned int get_nmi_count(int cpu) -{ - return per_cpu(irq_stat, cpu).__nmi_count; -} - -static inline int mce_in_progress(void) -{ -#if defined(CONFIG_X86_MCE) - return atomic_read(&mce_entry) > 0; -#endif - return 0; -} - -/* - * Take the local apic timer and PIT/HPET into account. We don't - * know which one is active, when we have highres/dyntick on - */ -static inline unsigned int get_timer_irqs(int cpu) -{ - return per_cpu(irq_stat, cpu).apic_timer_irqs + - per_cpu(irq_stat, cpu).irq0_irqs; -} - -#ifdef CONFIG_SMP -/* - * The performance counters used by NMI_LOCAL_APIC don't trigger when - * the CPU is idle. To make sure the NMI watchdog really ticks on all - * CPUs during the test make them busy. - */ -static __init void nmi_cpu_busy(void *data) -{ - local_irq_enable_in_hardirq(); - /* - * Intentionally don't use cpu_relax here. This is - * to make sure that the performance counter really ticks, - * even if there is a simulator or similar that catches the - * pause instruction. On a real HT machine this is fine because - * all other CPUs are busy with "useless" delay loops and don't - * care if they get somewhat less cycles. - */ - while (endflag == 0) - mb(); -} -#endif - -static void report_broken_nmi(int cpu, unsigned int *prev_nmi_count) -{ - printk(KERN_CONT "\n"); - - printk(KERN_WARNING - "WARNING: CPU#%d: NMI appears to be stuck (%d->%d)!\n", - cpu, prev_nmi_count[cpu], get_nmi_count(cpu)); - - printk(KERN_WARNING - "Please report this to bugzilla.kernel.org,\n"); - printk(KERN_WARNING - "and attach the output of the 'dmesg' command.\n"); - - per_cpu(wd_enabled, cpu) = 0; - atomic_dec(&nmi_active); -} - -static void __acpi_nmi_disable(void *__unused) -{ - apic_write(APIC_LVT0, APIC_DM_NMI | APIC_LVT_MASKED); -} - -int __init check_nmi_watchdog(void) -{ - unsigned int *prev_nmi_count; - int cpu; - - if (!nmi_watchdog_active() || !atomic_read(&nmi_active)) - return 0; - - prev_nmi_count = kmalloc(nr_cpu_ids * sizeof(int), GFP_KERNEL); - if (!prev_nmi_count) - goto error; - - printk(KERN_INFO "Testing NMI watchdog ... "); - -#ifdef CONFIG_SMP - if (nmi_watchdog == NMI_LOCAL_APIC) - smp_call_function(nmi_cpu_busy, (void *)&endflag, 0); -#endif - - for_each_possible_cpu(cpu) - prev_nmi_count[cpu] = get_nmi_count(cpu); - local_irq_enable(); - mdelay((20 * 1000) / nmi_hz); /* wait 20 ticks */ - - for_each_online_cpu(cpu) { - if (!per_cpu(wd_enabled, cpu)) - continue; - if (get_nmi_count(cpu) - prev_nmi_count[cpu] <= 5) - report_broken_nmi(cpu, prev_nmi_count); - } - endflag = 1; - if (!atomic_read(&nmi_active)) { - kfree(prev_nmi_count); - atomic_set(&nmi_active, -1); - goto error; - } - printk("OK.\n"); - - /* - * now that we know it works we can reduce NMI frequency to - * something more reasonable; makes a difference in some configs - */ - if (nmi_watchdog == NMI_LOCAL_APIC) - nmi_hz = lapic_adjust_nmi_hz(1); - - kfree(prev_nmi_count); - return 0; -error: - if (nmi_watchdog == NMI_IO_APIC) { - if (!timer_through_8259) - legacy_pic->mask(0); - on_each_cpu(__acpi_nmi_disable, NULL, 1); - } - -#ifdef CONFIG_X86_32 - timer_ack = 0; -#endif - return -1; -} - -static int __init setup_nmi_watchdog(char *str) -{ - unsigned int nmi; - - if (!strncmp(str, "panic", 5)) { - panic_on_timeout = 1; - str = strchr(str, ','); - if (!str) - return 1; - ++str; - } - - if (!strncmp(str, "lapic", 5)) - nmi_watchdog = NMI_LOCAL_APIC; - else if (!strncmp(str, "ioapic", 6)) - nmi_watchdog = NMI_IO_APIC; - else { - get_option(&str, &nmi); - if (nmi >= NMI_INVALID) - return 0; - nmi_watchdog = nmi; - } - - return 1; -} -__setup("nmi_watchdog=", setup_nmi_watchdog); - -/* - * Suspend/resume support - */ -#ifdef CONFIG_PM - -static int nmi_pm_active; /* nmi_active before suspend */ - -static int lapic_nmi_suspend(struct sys_device *dev, pm_message_t state) -{ - /* only CPU0 goes here, other CPUs should be offline */ - nmi_pm_active = atomic_read(&nmi_active); - stop_apic_nmi_watchdog(NULL); - BUG_ON(atomic_read(&nmi_active) != 0); - return 0; -} - -static int lapic_nmi_resume(struct sys_device *dev) -{ - /* only CPU0 goes here, other CPUs should be offline */ - if (nmi_pm_active > 0) { - setup_apic_nmi_watchdog(NULL); - touch_nmi_watchdog(); - } - return 0; -} - -static struct sysdev_class nmi_sysclass = { - .name = "lapic_nmi", - .resume = lapic_nmi_resume, - .suspend = lapic_nmi_suspend, -}; - -static struct sys_device device_lapic_nmi = { - .id = 0, - .cls = &nmi_sysclass, -}; - -static int __init init_lapic_nmi_sysfs(void) -{ - int error; - - /* - * should really be a BUG_ON but b/c this is an - * init call, it just doesn't work. -dcz - */ - if (nmi_watchdog != NMI_LOCAL_APIC) - return 0; - - if (atomic_read(&nmi_active) < 0) - return 0; - - error = sysdev_class_register(&nmi_sysclass); - if (!error) - error = sysdev_register(&device_lapic_nmi); - return error; -} - -/* must come after the local APIC's device_initcall() */ -late_initcall(init_lapic_nmi_sysfs); - -#endif /* CONFIG_PM */ - -static void __acpi_nmi_enable(void *__unused) -{ - apic_write(APIC_LVT0, APIC_DM_NMI); -} - -/* - * Enable timer based NMIs on all CPUs: - */ -void acpi_nmi_enable(void) -{ - if (atomic_read(&nmi_active) && nmi_watchdog == NMI_IO_APIC) - on_each_cpu(__acpi_nmi_enable, NULL, 1); -} - -/* - * Disable timer based NMIs on all CPUs: - */ -void acpi_nmi_disable(void) -{ - if (atomic_read(&nmi_active) && nmi_watchdog == NMI_IO_APIC) - on_each_cpu(__acpi_nmi_disable, NULL, 1); -} - -/* - * This function is called as soon the LAPIC NMI watchdog driver has everything - * in place and it's ready to check if the NMIs belong to the NMI watchdog - */ -void cpu_nmi_set_wd_enabled(void) -{ - __get_cpu_var(wd_enabled) = 1; -} - -void setup_apic_nmi_watchdog(void *unused) -{ - if (__get_cpu_var(wd_enabled)) - return; - - /* cheap hack to support suspend/resume */ - /* if cpu0 is not active neither should the other cpus */ - if (smp_processor_id() != 0 && atomic_read(&nmi_active) <= 0) - return; - - switch (nmi_watchdog) { - case NMI_LOCAL_APIC: - if (lapic_watchdog_init(nmi_hz) < 0) { - __get_cpu_var(wd_enabled) = 0; - return; - } - /* FALL THROUGH */ - case NMI_IO_APIC: - __get_cpu_var(wd_enabled) = 1; - atomic_inc(&nmi_active); - } -} - -void stop_apic_nmi_watchdog(void *unused) -{ - /* only support LOCAL and IO APICs for now */ - if (!nmi_watchdog_active()) - return; - if (__get_cpu_var(wd_enabled) == 0) - return; - if (nmi_watchdog == NMI_LOCAL_APIC) - lapic_watchdog_stop(); - else - __acpi_nmi_disable(NULL); - __get_cpu_var(wd_enabled) = 0; - atomic_dec(&nmi_active); -} - -/* - * the best way to detect whether a CPU has a 'hard lockup' problem - * is to check it's local APIC timer IRQ counts. If they are not - * changing then that CPU has some problem. - * - * as these watchdog NMI IRQs are generated on every CPU, we only - * have to check the current processor. - * - * since NMIs don't listen to _any_ locks, we have to be extremely - * careful not to rely on unsafe variables. The printk might lock - * up though, so we have to break up any console locks first ... - * [when there will be more tty-related locks, break them up here too!] - */ - -static DEFINE_PER_CPU(unsigned, last_irq_sum); -static DEFINE_PER_CPU(long, alert_counter); -static DEFINE_PER_CPU(int, nmi_touch); - -void touch_nmi_watchdog(void) -{ - if (nmi_watchdog_active()) { - unsigned cpu; - - /* - * Tell other CPUs to reset their alert counters. We cannot - * do it ourselves because the alert count increase is not - * atomic. - */ - for_each_present_cpu(cpu) { - if (per_cpu(nmi_touch, cpu) != 1) - per_cpu(nmi_touch, cpu) = 1; - } - } - - /* - * Tickle the softlockup detector too: - */ - touch_softlockup_watchdog(); -} -EXPORT_SYMBOL(touch_nmi_watchdog); - -notrace __kprobes int -nmi_watchdog_tick(struct pt_regs *regs, unsigned reason) -{ - /* - * Since current_thread_info()-> is always on the stack, and we - * always switch the stack NMI-atomically, it's safe to use - * smp_processor_id(). - */ - unsigned int sum; - int touched = 0; - int cpu = smp_processor_id(); - int rc = 0; - - sum = get_timer_irqs(cpu); - - if (__get_cpu_var(nmi_touch)) { - __get_cpu_var(nmi_touch) = 0; - touched = 1; - } - - /* We can be called before check_nmi_watchdog, hence NULL check. */ - if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) { - static DEFINE_RAW_SPINLOCK(lock); /* Serialise the printks */ - - raw_spin_lock(&lock); - printk(KERN_WARNING "NMI backtrace for cpu %d\n", cpu); - show_regs(regs); - dump_stack(); - raw_spin_unlock(&lock); - cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask)); - - rc = 1; - } - - /* Could check oops_in_progress here too, but it's safer not to */ - if (mce_in_progress()) - touched = 1; - - /* if the none of the timers isn't firing, this cpu isn't doing much */ - if (!touched && __get_cpu_var(last_irq_sum) == sum) { - /* - * Ayiee, looks like this CPU is stuck ... - * wait a few IRQs (5 seconds) before doing the oops ... - */ - __this_cpu_inc(alert_counter); - if (__this_cpu_read(alert_counter) == 5 * nmi_hz) - /* - * die_nmi will return ONLY if NOTIFY_STOP happens.. - */ - die_nmi("BUG: NMI Watchdog detected LOCKUP", - regs, panic_on_timeout); - } else { - __get_cpu_var(last_irq_sum) = sum; - __this_cpu_write(alert_counter, 0); - } - - /* see if the nmi watchdog went off */ - if (!__get_cpu_var(wd_enabled)) - return rc; - switch (nmi_watchdog) { - case NMI_LOCAL_APIC: - rc |= lapic_wd_event(nmi_hz); - break; - case NMI_IO_APIC: - /* - * don't know how to accurately check for this. - * just assume it was a watchdog timer interrupt - * This matches the old behaviour. - */ - rc = 1; - break; - } - return rc; -} - -#ifdef CONFIG_SYSCTL - -static void enable_ioapic_nmi_watchdog_single(void *unused) -{ - __get_cpu_var(wd_enabled) = 1; - atomic_inc(&nmi_active); - __acpi_nmi_enable(NULL); -} - -static void enable_ioapic_nmi_watchdog(void) -{ - on_each_cpu(enable_ioapic_nmi_watchdog_single, NULL, 1); - touch_nmi_watchdog(); -} - -static void disable_ioapic_nmi_watchdog(void) -{ - on_each_cpu(stop_apic_nmi_watchdog, NULL, 1); -} - -static int __init setup_unknown_nmi_panic(char *str) -{ - unknown_nmi_panic = 1; - return 1; -} -__setup("unknown_nmi_panic", setup_unknown_nmi_panic); - -static int unknown_nmi_panic_callback(struct pt_regs *regs, int cpu) -{ - unsigned char reason = get_nmi_reason(); - char buf[64]; - - sprintf(buf, "NMI received for unknown reason %02x\n", reason); - die_nmi(buf, regs, 1); /* Always panic here */ - return 0; -} - -/* - * proc handler for /proc/sys/kernel/nmi - */ -int proc_nmi_enabled(struct ctl_table *table, int write, - void __user *buffer, size_t *length, loff_t *ppos) -{ - int old_state; - - nmi_watchdog_enabled = (atomic_read(&nmi_active) > 0) ? 1 : 0; - old_state = nmi_watchdog_enabled; - proc_dointvec(table, write, buffer, length, ppos); - if (!!old_state == !!nmi_watchdog_enabled) - return 0; - - if (atomic_read(&nmi_active) < 0 || !nmi_watchdog_active()) { - printk(KERN_WARNING - "NMI watchdog is permanently disabled\n"); - return -EIO; - } - - if (nmi_watchdog == NMI_LOCAL_APIC) { - if (nmi_watchdog_enabled) - enable_lapic_nmi_watchdog(); - else - disable_lapic_nmi_watchdog(); - } else if (nmi_watchdog == NMI_IO_APIC) { - if (nmi_watchdog_enabled) - enable_ioapic_nmi_watchdog(); - else - disable_ioapic_nmi_watchdog(); - } else { - printk(KERN_WARNING - "NMI watchdog doesn't know what hardware to touch\n"); - return -EIO; - } - return 0; -} - -#endif /* CONFIG_SYSCTL */ - -int do_nmi_callback(struct pt_regs *regs, int cpu) -{ -#ifdef CONFIG_SYSCTL - if (unknown_nmi_panic) - return unknown_nmi_panic_callback(regs, cpu); -#endif - return 0; -} - -void arch_trigger_all_cpu_backtrace(void) -{ - int i; - - cpumask_copy(to_cpumask(backtrace_mask), cpu_online_mask); - - printk(KERN_INFO "sending NMI to all CPUs:\n"); - apic->send_IPI_all(NMI_VECTOR); - - /* Wait for up to 10 seconds for all CPUs to do the backtrace */ - for (i = 0; i < 10 * 1000; i++) { - if (cpumask_empty(to_cpumask(backtrace_mask))) - break; - mdelay(1); - } -} diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index cb838ca42c96..db30d9cb9dd6 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -398,15 +398,6 @@ static notrace __kprobes void default_do_nmi(struct pt_regs *regs) == NOTIFY_STOP) return; -#ifndef CONFIG_LOCKUP_DETECTOR - /* - * Ok, so this is none of the documented NMI sources, - * so it must be the NMI watchdog. - */ - if (nmi_watchdog_tick(regs, reason)) - return; - if (!do_nmi_callback(regs, cpu)) -#endif /* !CONFIG_LOCKUP_DETECTOR */ unknown_nmi_error(reason, regs); #else unknown_nmi_error(reason, regs); diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 06aab5eee134..0cb3e5c246d0 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -16,10 +16,7 @@ */ #ifdef ARCH_HAS_NMI_WATCHDOG #include -extern void touch_nmi_watchdog(void); -extern void acpi_nmi_disable(void); -extern void acpi_nmi_enable(void); -#else +#endif #ifndef CONFIG_HARDLOCKUP_DETECTOR static inline void touch_nmi_watchdog(void) { @@ -30,7 +27,6 @@ extern void touch_nmi_watchdog(void); #endif static inline void acpi_nmi_disable(void) { } static inline void acpi_nmi_enable(void) { } -#endif /* * Create trigger_all_cpu_backtrace() out of the arch-provided diff --git a/kernel/sysctl.c b/kernel/sysctl.c index b65bf634035e..ce33e2a2afea 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -746,22 +746,6 @@ static struct ctl_table kern_table[] = { .extra2 = &one, }, #endif -#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86) && !defined(CONFIG_LOCKUP_DETECTOR) - { - .procname = "unknown_nmi_panic", - .data = &unknown_nmi_panic, - .maxlen = sizeof (int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { - .procname = "nmi_watchdog", - .data = &nmi_watchdog_enabled, - .maxlen = sizeof (int), - .mode = 0644, - .proc_handler = proc_nmi_enabled, - }, -#endif #if defined(CONFIG_X86) { .procname = "panic_on_unrecovered_nmi", -- cgit v1.2.3 From 072b198a4ad48bd722ec6d203d65422a4698eae7 Mon Sep 17 00:00:00 2001 From: Don Zickus Date: Fri, 12 Nov 2010 11:22:24 -0500 Subject: x86, nmi_watchdog: Remove all stub function calls from old nmi_watchdog Now that the bulk of the old nmi_watchdog is gone, remove all the stub variables and hooks associated with it. This touches lots of files mainly because of how the io_apic nmi_watchdog was implemented. Now that the io_apic nmi_watchdog is forever gone, remove all its fingers. Most of this code was not being exercised by virtue of nmi_watchdog != NMI_IO_APIC, so there shouldn't be anything to risky here. Signed-off-by: Don Zickus Cc: fweisbec@gmail.com Cc: gorcunov@openvz.org LKML-Reference: <1289578944-28564-3-git-send-email-dzickus@redhat.com> Signed-off-by: Ingo Molnar --- arch/x86/include/asm/nmi.h | 47 --- arch/x86/include/asm/smpboot_hooks.h | 1 - arch/x86/include/asm/timer.h | 6 - arch/x86/kernel/apic/apic.c | 15 +- arch/x86/kernel/apic/hw_nmi.c | 10 - arch/x86/kernel/apic/io_apic.c | 46 --- arch/x86/kernel/cpu/perf_event.c | 9 - arch/x86/kernel/cpu/perfctr-watchdog.c | 642 --------------------------------- arch/x86/kernel/smpboot.c | 11 - arch/x86/kernel/time.c | 18 - arch/x86/kernel/traps.c | 2 - arch/x86/oprofile/nmi_timer_int.c | 3 - drivers/acpi/acpica/nsinit.c | 2 - drivers/watchdog/hpwdt.c | 7 +- include/linux/nmi.h | 2 - 15 files changed, 2 insertions(+), 819 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h index 33292ec848ca..3545838cddeb 100644 --- a/arch/x86/include/asm/nmi.h +++ b/arch/x86/include/asm/nmi.h @@ -7,35 +7,13 @@ #ifdef ARCH_HAS_NMI_WATCHDOG -/** - * do_nmi_callback - * - * Check to see if a callback exists and execute it. Return 1 - * if the handler exists and was handled successfully. - */ -int do_nmi_callback(struct pt_regs *regs, int cpu); - extern void die_nmi(char *str, struct pt_regs *regs, int do_panic); -extern int check_nmi_watchdog(void); extern int avail_to_resrv_perfctr_nmi_bit(unsigned int); extern int reserve_perfctr_nmi(unsigned int); extern void release_perfctr_nmi(unsigned int); extern int reserve_evntsel_nmi(unsigned int); extern void release_evntsel_nmi(unsigned int); -extern void setup_apic_nmi_watchdog(void *); -extern void stop_apic_nmi_watchdog(void *); -extern void disable_timer_nmi_watchdog(void); -extern void enable_timer_nmi_watchdog(void); -extern void cpu_nmi_set_wd_enabled(void); - -extern atomic_t nmi_active; -extern unsigned int nmi_watchdog; -#define NMI_NONE 0 -#define NMI_IO_APIC 1 -#define NMI_LOCAL_APIC 2 -#define NMI_INVALID 3 - struct ctl_table; extern int proc_nmi_enabled(struct ctl_table *, int , void __user *, size_t *, loff_t *); @@ -43,33 +21,8 @@ extern int unknown_nmi_panic; void arch_trigger_all_cpu_backtrace(void); #define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace - -static inline void localise_nmi_watchdog(void) -{ - if (nmi_watchdog == NMI_IO_APIC) - nmi_watchdog = NMI_LOCAL_APIC; -} - -/* check if nmi_watchdog is active (ie was specified at boot) */ -static inline int nmi_watchdog_active(void) -{ - /* - * actually it should be: - * return (nmi_watchdog == NMI_LOCAL_APIC || - * nmi_watchdog == NMI_IO_APIC) - * but since they are power of two we could use a - * cheaper way --cvg - */ - return nmi_watchdog & (NMI_LOCAL_APIC | NMI_IO_APIC); -} #endif -void lapic_watchdog_stop(void); -int lapic_watchdog_init(unsigned nmi_hz); -int lapic_wd_event(unsigned nmi_hz); -unsigned lapic_adjust_nmi_hz(unsigned hz); -void disable_lapic_nmi_watchdog(void); -void enable_lapic_nmi_watchdog(void); void stop_nmi(void); void restart_nmi(void); diff --git a/arch/x86/include/asm/smpboot_hooks.h b/arch/x86/include/asm/smpboot_hooks.h index 1def60114906..6c22bf353f26 100644 --- a/arch/x86/include/asm/smpboot_hooks.h +++ b/arch/x86/include/asm/smpboot_hooks.h @@ -48,7 +48,6 @@ static inline void __init smpboot_setup_io_apic(void) setup_IO_APIC(); else { nr_ioapics = 0; - localise_nmi_watchdog(); } #endif } diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h index 5469630b27f5..fa7b9176b76c 100644 --- a/arch/x86/include/asm/timer.h +++ b/arch/x86/include/asm/timer.h @@ -10,12 +10,6 @@ unsigned long long native_sched_clock(void); extern int recalibrate_cpu_khz(void); -#if defined(CONFIG_X86_32) && defined(CONFIG_X86_IO_APIC) -extern int timer_ack; -#else -# define timer_ack (0) -#endif - extern int no_timer_check; /* Accelerators for sched_clock() diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 3f838d537392..e9e2a93783f9 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -31,7 +31,6 @@ #include #include #include -#include #include #include @@ -799,11 +798,7 @@ void __init setup_boot_APIC_clock(void) * PIT/HPET going. Otherwise register lapic as a dummy * device. */ - if (nmi_watchdog != NMI_IO_APIC) - lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY; - else - pr_warning("APIC timer registered as dummy," - " due to nmi_watchdog=%d!\n", nmi_watchdog); + lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY; /* Setup the lapic or request the broadcast */ setup_APIC_timer(); @@ -1387,7 +1382,6 @@ void __cpuinit end_local_APIC_setup(void) } #endif - setup_apic_nmi_watchdog(NULL); apic_pm_activate(); } @@ -1750,17 +1744,10 @@ int __init APIC_init_uniprocessor(void) setup_IO_APIC(); else { nr_ioapics = 0; - localise_nmi_watchdog(); } -#else - localise_nmi_watchdog(); #endif x86_init.timers.setup_percpu_clockev(); -#ifdef CONFIG_X86_64 - check_nmi_watchdog(); -#endif - return 0; } diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c index b68b17460016..3e25afe9a62a 100644 --- a/arch/x86/kernel/apic/hw_nmi.c +++ b/arch/x86/kernel/apic/hw_nmi.c @@ -94,14 +94,4 @@ early_initcall(register_trigger_all_cpu_backtrace); #endif /* STUB calls to mimic old nmi_watchdog behaviour */ -#if defined(CONFIG_X86_LOCAL_APIC) -unsigned int nmi_watchdog = NMI_NONE; -EXPORT_SYMBOL(nmi_watchdog); -#endif -atomic_t nmi_active = ATOMIC_INIT(0); /* oprofile uses this */ -EXPORT_SYMBOL(nmi_active); int unknown_nmi_panic; -void cpu_nmi_set_wd_enabled(void) { return; } -void stop_apic_nmi_watchdog(void *unused) { return; } -void setup_apic_nmi_watchdog(void *unused) { return; } -int __init check_nmi_watchdog(void) { return 0; } diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 7cc0a721f628..e4a040c28de1 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -54,7 +54,6 @@ #include #include #include -#include #include #include #include @@ -2643,24 +2642,6 @@ static void lapic_register_intr(int irq) "edge"); } -static void __init setup_nmi(void) -{ - /* - * Dirty trick to enable the NMI watchdog ... - * We put the 8259A master into AEOI mode and - * unmask on all local APICs LVT0 as NMI. - * - * The idea to use the 8259A in AEOI mode ('8259A Virtual Wire') - * is from Maciej W. Rozycki - so we do not have to EOI from - * the NMI handler or the timer interrupt. - */ - apic_printk(APIC_VERBOSE, KERN_INFO "activating NMI Watchdog ..."); - - enable_NMI_through_LVT0(); - - apic_printk(APIC_VERBOSE, " done.\n"); -} - /* * This looks a bit hackish but it's about the only one way of sending * a few INTA cycles to 8259As and any associated glue logic. ICR does @@ -2766,15 +2747,6 @@ static inline void __init check_timer(void) */ apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT); legacy_pic->init(1); -#ifdef CONFIG_X86_32 - { - unsigned int ver; - - ver = apic_read(APIC_LVR); - ver = GET_APIC_VERSION(ver); - timer_ack = (nmi_watchdog == NMI_IO_APIC && !APIC_INTEGRATED(ver)); - } -#endif pin1 = find_isa_irq_pin(0, mp_INT); apic1 = find_isa_irq_apic(0, mp_INT); @@ -2822,10 +2794,6 @@ static inline void __init check_timer(void) unmask_ioapic(cfg); } if (timer_irq_works()) { - if (nmi_watchdog == NMI_IO_APIC) { - setup_nmi(); - legacy_pic->unmask(0); - } if (disable_timer_pin_1 > 0) clear_IO_APIC_pin(0, pin1); goto out; @@ -2851,11 +2819,6 @@ static inline void __init check_timer(void) if (timer_irq_works()) { apic_printk(APIC_QUIET, KERN_INFO "....... works.\n"); timer_through_8259 = 1; - if (nmi_watchdog == NMI_IO_APIC) { - legacy_pic->mask(0); - setup_nmi(); - legacy_pic->unmask(0); - } goto out; } /* @@ -2867,15 +2830,6 @@ static inline void __init check_timer(void) apic_printk(APIC_QUIET, KERN_INFO "....... failed.\n"); } - if (nmi_watchdog == NMI_IO_APIC) { - apic_printk(APIC_QUIET, KERN_WARNING "timer doesn't work " - "through the IO-APIC - disabling NMI Watchdog!\n"); - nmi_watchdog = NMI_NONE; - } -#ifdef CONFIG_X86_32 - timer_ack = 0; -#endif - apic_printk(APIC_QUIET, KERN_INFO "...trying to set up timer as Virtual Wire IRQ...\n"); diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index ed6310183efb..1f129a14e3a2 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -330,9 +330,6 @@ static bool reserve_pmc_hardware(void) { int i; - if (nmi_watchdog == NMI_LOCAL_APIC) - disable_lapic_nmi_watchdog(); - for (i = 0; i < x86_pmu.num_counters; i++) { if (!reserve_perfctr_nmi(x86_pmu.perfctr + i)) goto perfctr_fail; @@ -355,9 +352,6 @@ perfctr_fail: for (i--; i >= 0; i--) release_perfctr_nmi(x86_pmu.perfctr + i); - if (nmi_watchdog == NMI_LOCAL_APIC) - enable_lapic_nmi_watchdog(); - return false; } @@ -369,9 +363,6 @@ static void release_pmc_hardware(void) release_perfctr_nmi(x86_pmu.perfctr + i); release_evntsel_nmi(x86_pmu.eventsel + i); } - - if (nmi_watchdog == NMI_LOCAL_APIC) - enable_lapic_nmi_watchdog(); } #else diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c index d9f4ff8fcd69..14d45928c282 100644 --- a/arch/x86/kernel/cpu/perfctr-watchdog.c +++ b/arch/x86/kernel/cpu/perfctr-watchdog.c @@ -22,26 +22,6 @@ #include #include -struct nmi_watchdog_ctlblk { - unsigned int cccr_msr; - unsigned int perfctr_msr; /* the MSR to reset in NMI handler */ - unsigned int evntsel_msr; /* the MSR to select the events to handle */ -}; - -/* Interface defining a CPU specific perfctr watchdog */ -struct wd_ops { - int (*reserve)(void); - void (*unreserve)(void); - int (*setup)(unsigned nmi_hz); - void (*rearm)(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz); - void (*stop)(void); - unsigned perfctr; - unsigned evntsel; - u64 checkbit; -}; - -static const struct wd_ops *wd_ops; - /* * this number is calculated from Intel's MSR_P4_CRU_ESCR5 register and it's * offset from MSR_P4_BSU_ESCR0. @@ -60,8 +40,6 @@ static const struct wd_ops *wd_ops; static DECLARE_BITMAP(perfctr_nmi_owner, NMI_MAX_COUNTER_BITS); static DECLARE_BITMAP(evntsel_nmi_owner, NMI_MAX_COUNTER_BITS); -static DEFINE_PER_CPU(struct nmi_watchdog_ctlblk, nmi_watchdog_ctlblk); - /* converts an msr to an appropriate reservation bit */ static inline unsigned int nmi_perfctr_msr_to_bit(unsigned int msr) { @@ -172,623 +150,3 @@ void release_evntsel_nmi(unsigned int msr) clear_bit(counter, evntsel_nmi_owner); } EXPORT_SYMBOL(release_evntsel_nmi); - -void disable_lapic_nmi_watchdog(void) -{ - BUG_ON(nmi_watchdog != NMI_LOCAL_APIC); - - if (atomic_read(&nmi_active) <= 0) - return; - - on_each_cpu(stop_apic_nmi_watchdog, NULL, 1); - - if (wd_ops) - wd_ops->unreserve(); - - BUG_ON(atomic_read(&nmi_active) != 0); -} - -void enable_lapic_nmi_watchdog(void) -{ - BUG_ON(nmi_watchdog != NMI_LOCAL_APIC); - - /* are we already enabled */ - if (atomic_read(&nmi_active) != 0) - return; - - /* are we lapic aware */ - if (!wd_ops) - return; - if (!wd_ops->reserve()) { - printk(KERN_ERR "NMI watchdog: cannot reserve perfctrs\n"); - return; - } - - on_each_cpu(setup_apic_nmi_watchdog, NULL, 1); - touch_nmi_watchdog(); -} - -/* - * Activate the NMI watchdog via the local APIC. - */ - -static unsigned int adjust_for_32bit_ctr(unsigned int hz) -{ - u64 counter_val; - unsigned int retval = hz; - - /* - * On Intel CPUs with P6/ARCH_PERFMON only 32 bits in the counter - * are writable, with higher bits sign extending from bit 31. - * So, we can only program the counter with 31 bit values and - * 32nd bit should be 1, for 33.. to be 1. - * Find the appropriate nmi_hz - */ - counter_val = (u64)cpu_khz * 1000; - do_div(counter_val, retval); - if (counter_val > 0x7fffffffULL) { - u64 count = (u64)cpu_khz * 1000; - do_div(count, 0x7fffffffUL); - retval = count + 1; - } - return retval; -} - -static void write_watchdog_counter(unsigned int perfctr_msr, - const char *descr, unsigned nmi_hz) -{ - u64 count = (u64)cpu_khz * 1000; - - do_div(count, nmi_hz); - if (descr) - pr_debug("setting %s to -0x%08Lx\n", descr, count); - wrmsrl(perfctr_msr, 0 - count); -} - -static void write_watchdog_counter32(unsigned int perfctr_msr, - const char *descr, unsigned nmi_hz) -{ - u64 count = (u64)cpu_khz * 1000; - - do_div(count, nmi_hz); - if (descr) - pr_debug("setting %s to -0x%08Lx\n", descr, count); - wrmsr(perfctr_msr, (u32)(-count), 0); -} - -/* - * AMD K7/K8/Family10h/Family11h support. - * AMD keeps this interface nicely stable so there is not much variety - */ -#define K7_EVNTSEL_ENABLE (1 << 22) -#define K7_EVNTSEL_INT (1 << 20) -#define K7_EVNTSEL_OS (1 << 17) -#define K7_EVNTSEL_USR (1 << 16) -#define K7_EVENT_CYCLES_PROCESSOR_IS_RUNNING 0x76 -#define K7_NMI_EVENT K7_EVENT_CYCLES_PROCESSOR_IS_RUNNING - -static int setup_k7_watchdog(unsigned nmi_hz) -{ - unsigned int perfctr_msr, evntsel_msr; - unsigned int evntsel; - struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); - - perfctr_msr = wd_ops->perfctr; - evntsel_msr = wd_ops->evntsel; - - wrmsrl(perfctr_msr, 0UL); - - evntsel = K7_EVNTSEL_INT - | K7_EVNTSEL_OS - | K7_EVNTSEL_USR - | K7_NMI_EVENT; - - /* setup the timer */ - wrmsr(evntsel_msr, evntsel, 0); - write_watchdog_counter(perfctr_msr, "K7_PERFCTR0", nmi_hz); - - /* initialize the wd struct before enabling */ - wd->perfctr_msr = perfctr_msr; - wd->evntsel_msr = evntsel_msr; - wd->cccr_msr = 0; /* unused */ - - /* ok, everything is initialized, announce that we're set */ - cpu_nmi_set_wd_enabled(); - - apic_write(APIC_LVTPC, APIC_DM_NMI); - evntsel |= K7_EVNTSEL_ENABLE; - wrmsr(evntsel_msr, evntsel, 0); - - return 1; -} - -static void single_msr_stop_watchdog(void) -{ - struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); - - wrmsr(wd->evntsel_msr, 0, 0); -} - -static int single_msr_reserve(void) -{ - if (!reserve_perfctr_nmi(wd_ops->perfctr)) - return 0; - - if (!reserve_evntsel_nmi(wd_ops->evntsel)) { - release_perfctr_nmi(wd_ops->perfctr); - return 0; - } - return 1; -} - -static void single_msr_unreserve(void) -{ - release_evntsel_nmi(wd_ops->evntsel); - release_perfctr_nmi(wd_ops->perfctr); -} - -static void __kprobes -single_msr_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz) -{ - /* start the cycle over again */ - write_watchdog_counter(wd->perfctr_msr, NULL, nmi_hz); -} - -static const struct wd_ops k7_wd_ops = { - .reserve = single_msr_reserve, - .unreserve = single_msr_unreserve, - .setup = setup_k7_watchdog, - .rearm = single_msr_rearm, - .stop = single_msr_stop_watchdog, - .perfctr = MSR_K7_PERFCTR0, - .evntsel = MSR_K7_EVNTSEL0, - .checkbit = 1ULL << 47, -}; - -/* - * Intel Model 6 (PPro+,P2,P3,P-M,Core1) - */ -#define P6_EVNTSEL0_ENABLE (1 << 22) -#define P6_EVNTSEL_INT (1 << 20) -#define P6_EVNTSEL_OS (1 << 17) -#define P6_EVNTSEL_USR (1 << 16) -#define P6_EVENT_CPU_CLOCKS_NOT_HALTED 0x79 -#define P6_NMI_EVENT P6_EVENT_CPU_CLOCKS_NOT_HALTED - -static int setup_p6_watchdog(unsigned nmi_hz) -{ - unsigned int perfctr_msr, evntsel_msr; - unsigned int evntsel; - struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); - - perfctr_msr = wd_ops->perfctr; - evntsel_msr = wd_ops->evntsel; - - /* KVM doesn't implement this MSR */ - if (wrmsr_safe(perfctr_msr, 0, 0) < 0) - return 0; - - evntsel = P6_EVNTSEL_INT - | P6_EVNTSEL_OS - | P6_EVNTSEL_USR - | P6_NMI_EVENT; - - /* setup the timer */ - wrmsr(evntsel_msr, evntsel, 0); - nmi_hz = adjust_for_32bit_ctr(nmi_hz); - write_watchdog_counter32(perfctr_msr, "P6_PERFCTR0", nmi_hz); - - /* initialize the wd struct before enabling */ - wd->perfctr_msr = perfctr_msr; - wd->evntsel_msr = evntsel_msr; - wd->cccr_msr = 0; /* unused */ - - /* ok, everything is initialized, announce that we're set */ - cpu_nmi_set_wd_enabled(); - - apic_write(APIC_LVTPC, APIC_DM_NMI); - evntsel |= P6_EVNTSEL0_ENABLE; - wrmsr(evntsel_msr, evntsel, 0); - - return 1; -} - -static void __kprobes p6_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz) -{ - /* - * P6 based Pentium M need to re-unmask - * the apic vector but it doesn't hurt - * other P6 variant. - * ArchPerfom/Core Duo also needs this - */ - apic_write(APIC_LVTPC, APIC_DM_NMI); - - /* P6/ARCH_PERFMON has 32 bit counter write */ - write_watchdog_counter32(wd->perfctr_msr, NULL, nmi_hz); -} - -static const struct wd_ops p6_wd_ops = { - .reserve = single_msr_reserve, - .unreserve = single_msr_unreserve, - .setup = setup_p6_watchdog, - .rearm = p6_rearm, - .stop = single_msr_stop_watchdog, - .perfctr = MSR_P6_PERFCTR0, - .evntsel = MSR_P6_EVNTSEL0, - .checkbit = 1ULL << 39, -}; - -/* - * Intel P4 performance counters. - * By far the most complicated of all. - */ -#define MSR_P4_MISC_ENABLE_PERF_AVAIL (1 << 7) -#define P4_ESCR_EVENT_SELECT(N) ((N) << 25) -#define P4_ESCR_OS (1 << 3) -#define P4_ESCR_USR (1 << 2) -#define P4_CCCR_OVF_PMI0 (1 << 26) -#define P4_CCCR_OVF_PMI1 (1 << 27) -#define P4_CCCR_THRESHOLD(N) ((N) << 20) -#define P4_CCCR_COMPLEMENT (1 << 19) -#define P4_CCCR_COMPARE (1 << 18) -#define P4_CCCR_REQUIRED (3 << 16) -#define P4_CCCR_ESCR_SELECT(N) ((N) << 13) -#define P4_CCCR_ENABLE (1 << 12) -#define P4_CCCR_OVF (1 << 31) - -#define P4_CONTROLS 18 -static unsigned int p4_controls[18] = { - MSR_P4_BPU_CCCR0, - MSR_P4_BPU_CCCR1, - MSR_P4_BPU_CCCR2, - MSR_P4_BPU_CCCR3, - MSR_P4_MS_CCCR0, - MSR_P4_MS_CCCR1, - MSR_P4_MS_CCCR2, - MSR_P4_MS_CCCR3, - MSR_P4_FLAME_CCCR0, - MSR_P4_FLAME_CCCR1, - MSR_P4_FLAME_CCCR2, - MSR_P4_FLAME_CCCR3, - MSR_P4_IQ_CCCR0, - MSR_P4_IQ_CCCR1, - MSR_P4_IQ_CCCR2, - MSR_P4_IQ_CCCR3, - MSR_P4_IQ_CCCR4, - MSR_P4_IQ_CCCR5, -}; -/* - * Set up IQ_COUNTER0 to behave like a clock, by having IQ_CCCR0 filter - * CRU_ESCR0 (with any non-null event selector) through a complemented - * max threshold. [IA32-Vol3, Section 14.9.9] - */ -static int setup_p4_watchdog(unsigned nmi_hz) -{ - unsigned int perfctr_msr, evntsel_msr, cccr_msr; - unsigned int evntsel, cccr_val; - unsigned int misc_enable, dummy; - unsigned int ht_num; - struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); - - rdmsr(MSR_IA32_MISC_ENABLE, misc_enable, dummy); - if (!(misc_enable & MSR_P4_MISC_ENABLE_PERF_AVAIL)) - return 0; - -#ifdef CONFIG_SMP - /* detect which hyperthread we are on */ - if (smp_num_siblings == 2) { - unsigned int ebx, apicid; - - ebx = cpuid_ebx(1); - apicid = (ebx >> 24) & 0xff; - ht_num = apicid & 1; - } else -#endif - ht_num = 0; - - /* - * performance counters are shared resources - * assign each hyperthread its own set - * (re-use the ESCR0 register, seems safe - * and keeps the cccr_val the same) - */ - if (!ht_num) { - /* logical cpu 0 */ - perfctr_msr = MSR_P4_IQ_PERFCTR0; - evntsel_msr = MSR_P4_CRU_ESCR0; - cccr_msr = MSR_P4_IQ_CCCR0; - cccr_val = P4_CCCR_OVF_PMI0 | P4_CCCR_ESCR_SELECT(4); - - /* - * If we're on the kdump kernel or other situation, we may - * still have other performance counter registers set to - * interrupt and they'll keep interrupting forever because - * of the P4_CCCR_OVF quirk. So we need to ACK all the - * pending interrupts and disable all the registers here, - * before reenabling the NMI delivery. Refer to p4_rearm() - * about the P4_CCCR_OVF quirk. - */ - if (reset_devices) { - unsigned int low, high; - int i; - - for (i = 0; i < P4_CONTROLS; i++) { - rdmsr(p4_controls[i], low, high); - low &= ~(P4_CCCR_ENABLE | P4_CCCR_OVF); - wrmsr(p4_controls[i], low, high); - } - } - } else { - /* logical cpu 1 */ - perfctr_msr = MSR_P4_IQ_PERFCTR1; - evntsel_msr = MSR_P4_CRU_ESCR0; - cccr_msr = MSR_P4_IQ_CCCR1; - - /* Pentium 4 D processors don't support P4_CCCR_OVF_PMI1 */ - if (boot_cpu_data.x86_model == 4 && boot_cpu_data.x86_mask == 4) - cccr_val = P4_CCCR_OVF_PMI0; - else - cccr_val = P4_CCCR_OVF_PMI1; - cccr_val |= P4_CCCR_ESCR_SELECT(4); - } - - evntsel = P4_ESCR_EVENT_SELECT(0x3F) - | P4_ESCR_OS - | P4_ESCR_USR; - - cccr_val |= P4_CCCR_THRESHOLD(15) - | P4_CCCR_COMPLEMENT - | P4_CCCR_COMPARE - | P4_CCCR_REQUIRED; - - wrmsr(evntsel_msr, evntsel, 0); - wrmsr(cccr_msr, cccr_val, 0); - write_watchdog_counter(perfctr_msr, "P4_IQ_COUNTER0", nmi_hz); - - wd->perfctr_msr = perfctr_msr; - wd->evntsel_msr = evntsel_msr; - wd->cccr_msr = cccr_msr; - - /* ok, everything is initialized, announce that we're set */ - cpu_nmi_set_wd_enabled(); - - apic_write(APIC_LVTPC, APIC_DM_NMI); - cccr_val |= P4_CCCR_ENABLE; - wrmsr(cccr_msr, cccr_val, 0); - return 1; -} - -static void stop_p4_watchdog(void) -{ - struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); - wrmsr(wd->cccr_msr, 0, 0); - wrmsr(wd->evntsel_msr, 0, 0); -} - -static int p4_reserve(void) -{ - if (!reserve_perfctr_nmi(MSR_P4_IQ_PERFCTR0)) - return 0; -#ifdef CONFIG_SMP - if (smp_num_siblings > 1 && !reserve_perfctr_nmi(MSR_P4_IQ_PERFCTR1)) - goto fail1; -#endif - if (!reserve_evntsel_nmi(MSR_P4_CRU_ESCR0)) - goto fail2; - /* RED-PEN why is ESCR1 not reserved here? */ - return 1; - fail2: -#ifdef CONFIG_SMP - if (smp_num_siblings > 1) - release_perfctr_nmi(MSR_P4_IQ_PERFCTR1); - fail1: -#endif - release_perfctr_nmi(MSR_P4_IQ_PERFCTR0); - return 0; -} - -static void p4_unreserve(void) -{ -#ifdef CONFIG_SMP - if (smp_num_siblings > 1) - release_perfctr_nmi(MSR_P4_IQ_PERFCTR1); -#endif - release_evntsel_nmi(MSR_P4_CRU_ESCR0); - release_perfctr_nmi(MSR_P4_IQ_PERFCTR0); -} - -static void __kprobes p4_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz) -{ - unsigned dummy; - /* - * P4 quirks: - * - An overflown perfctr will assert its interrupt - * until the OVF flag in its CCCR is cleared. - * - LVTPC is masked on interrupt and must be - * unmasked by the LVTPC handler. - */ - rdmsrl(wd->cccr_msr, dummy); - dummy &= ~P4_CCCR_OVF; - wrmsrl(wd->cccr_msr, dummy); - apic_write(APIC_LVTPC, APIC_DM_NMI); - /* start the cycle over again */ - write_watchdog_counter(wd->perfctr_msr, NULL, nmi_hz); -} - -static const struct wd_ops p4_wd_ops = { - .reserve = p4_reserve, - .unreserve = p4_unreserve, - .setup = setup_p4_watchdog, - .rearm = p4_rearm, - .stop = stop_p4_watchdog, - /* RED-PEN this is wrong for the other sibling */ - .perfctr = MSR_P4_BPU_PERFCTR0, - .evntsel = MSR_P4_BSU_ESCR0, - .checkbit = 1ULL << 39, -}; - -/* - * Watchdog using the Intel architected PerfMon. - * Used for Core2 and hopefully all future Intel CPUs. - */ -#define ARCH_PERFMON_NMI_EVENT_SEL ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL -#define ARCH_PERFMON_NMI_EVENT_UMASK ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK - -static struct wd_ops intel_arch_wd_ops; - -static int setup_intel_arch_watchdog(unsigned nmi_hz) -{ - unsigned int ebx; - union cpuid10_eax eax; - unsigned int unused; - unsigned int perfctr_msr, evntsel_msr; - unsigned int evntsel; - struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); - - /* - * Check whether the Architectural PerfMon supports - * Unhalted Core Cycles Event or not. - * NOTE: Corresponding bit = 0 in ebx indicates event present. - */ - cpuid(10, &(eax.full), &ebx, &unused, &unused); - if ((eax.split.mask_length < - (ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX+1)) || - (ebx & ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT)) - return 0; - - perfctr_msr = wd_ops->perfctr; - evntsel_msr = wd_ops->evntsel; - - wrmsrl(perfctr_msr, 0UL); - - evntsel = ARCH_PERFMON_EVENTSEL_INT - | ARCH_PERFMON_EVENTSEL_OS - | ARCH_PERFMON_EVENTSEL_USR - | ARCH_PERFMON_NMI_EVENT_SEL - | ARCH_PERFMON_NMI_EVENT_UMASK; - - /* setup the timer */ - wrmsr(evntsel_msr, evntsel, 0); - nmi_hz = adjust_for_32bit_ctr(nmi_hz); - write_watchdog_counter32(perfctr_msr, "INTEL_ARCH_PERFCTR0", nmi_hz); - - wd->perfctr_msr = perfctr_msr; - wd->evntsel_msr = evntsel_msr; - wd->cccr_msr = 0; /* unused */ - - /* ok, everything is initialized, announce that we're set */ - cpu_nmi_set_wd_enabled(); - - apic_write(APIC_LVTPC, APIC_DM_NMI); - evntsel |= ARCH_PERFMON_EVENTSEL_ENABLE; - wrmsr(evntsel_msr, evntsel, 0); - intel_arch_wd_ops.checkbit = 1ULL << (eax.split.bit_width - 1); - return 1; -} - -static struct wd_ops intel_arch_wd_ops __read_mostly = { - .reserve = single_msr_reserve, - .unreserve = single_msr_unreserve, - .setup = setup_intel_arch_watchdog, - .rearm = p6_rearm, - .stop = single_msr_stop_watchdog, - .perfctr = MSR_ARCH_PERFMON_PERFCTR1, - .evntsel = MSR_ARCH_PERFMON_EVENTSEL1, -}; - -static void probe_nmi_watchdog(void) -{ - switch (boot_cpu_data.x86_vendor) { - case X86_VENDOR_AMD: - if (boot_cpu_data.x86 == 6 || - (boot_cpu_data.x86 >= 0xf && boot_cpu_data.x86 <= 0x15)) - wd_ops = &k7_wd_ops; - return; - case X86_VENDOR_INTEL: - /* Work around where perfctr1 doesn't have a working enable - * bit as described in the following errata: - * AE49 Core Duo and Intel Core Solo 65 nm - * AN49 Intel Pentium Dual-Core - * AF49 Dual-Core Intel Xeon Processor LV - */ - if ((boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 14) || - ((boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 15 && - boot_cpu_data.x86_mask == 4))) { - intel_arch_wd_ops.perfctr = MSR_ARCH_PERFMON_PERFCTR0; - intel_arch_wd_ops.evntsel = MSR_ARCH_PERFMON_EVENTSEL0; - } - if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) { - wd_ops = &intel_arch_wd_ops; - break; - } - switch (boot_cpu_data.x86) { - case 6: - if (boot_cpu_data.x86_model > 13) - return; - - wd_ops = &p6_wd_ops; - break; - case 15: - wd_ops = &p4_wd_ops; - break; - default: - return; - } - break; - } -} - -/* Interface to nmi.c */ - -int lapic_watchdog_init(unsigned nmi_hz) -{ - if (!wd_ops) { - probe_nmi_watchdog(); - if (!wd_ops) { - printk(KERN_INFO "NMI watchdog: CPU not supported\n"); - return -1; - } - - if (!wd_ops->reserve()) { - printk(KERN_ERR - "NMI watchdog: cannot reserve perfctrs\n"); - return -1; - } - } - - if (!(wd_ops->setup(nmi_hz))) { - printk(KERN_ERR "Cannot setup NMI watchdog on CPU %d\n", - raw_smp_processor_id()); - return -1; - } - - return 0; -} - -void lapic_watchdog_stop(void) -{ - if (wd_ops) - wd_ops->stop(); -} - -unsigned lapic_adjust_nmi_hz(unsigned hz) -{ - struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); - if (wd->perfctr_msr == MSR_P6_PERFCTR0 || - wd->perfctr_msr == MSR_ARCH_PERFMON_PERFCTR1) - hz = adjust_for_32bit_ctr(hz); - return hz; -} - -int __kprobes lapic_wd_event(unsigned nmi_hz) -{ - struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); - u64 ctr; - - rdmsrl(wd->perfctr_msr, ctr); - if (ctr & wd_ops->checkbit) /* perfctr still running? */ - return 0; - - wd_ops->rearm(wd, nmi_hz); - return 1; -} diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 083e99d1b7df..f0a0624eea55 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -316,12 +316,6 @@ notrace static void __cpuinit start_secondary(void *unused) */ check_tsc_sync_target(); - if (nmi_watchdog == NMI_IO_APIC) { - legacy_pic->mask(0); - enable_NMI_through_LVT0(); - legacy_pic->unmask(0); - } - /* This must be done before setting cpu_online_mask */ set_cpu_sibling_map(raw_smp_processor_id()); wmb(); @@ -1061,8 +1055,6 @@ static int __init smp_sanity_check(unsigned max_cpus) printk(KERN_INFO "SMP mode deactivated.\n"); smpboot_clear_io_apic(); - localise_nmi_watchdog(); - connect_bsp_APIC(); setup_local_APIC(); end_local_APIC_setup(); @@ -1196,7 +1188,6 @@ void __init native_smp_cpus_done(unsigned int max_cpus) #ifdef CONFIG_X86_IO_APIC setup_ioapic_dest(); #endif - check_nmi_watchdog(); mtrr_aps_init(); } @@ -1341,8 +1332,6 @@ int native_cpu_disable(void) if (cpu == 0) return -EBUSY; - if (nmi_watchdog == NMI_LOCAL_APIC) - stop_apic_nmi_watchdog(NULL); clear_local_APIC(); cpu_disable_common(); diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c index fb5cc5e14cfa..25a28a245937 100644 --- a/arch/x86/kernel/time.c +++ b/arch/x86/kernel/time.c @@ -22,10 +22,6 @@ #include #include -#if defined(CONFIG_X86_32) && defined(CONFIG_X86_IO_APIC) -int timer_ack; -#endif - #ifdef CONFIG_X86_64 volatile unsigned long __jiffies __section_jiffies = INITIAL_JIFFIES; #endif @@ -63,20 +59,6 @@ static irqreturn_t timer_interrupt(int irq, void *dev_id) /* Keep nmi watchdog up to date */ inc_irq_stat(irq0_irqs); - /* Optimized out for !IO_APIC and x86_64 */ - if (timer_ack) { - /* - * Subtle, when I/O APICs are used we have to ack timer IRQ - * manually to deassert NMI lines for the watchdog if run - * on an 82489DX-based system. - */ - raw_spin_lock(&i8259A_lock); - outb(0x0c, PIC_MASTER_OCW3); - /* Ack the IRQ; AEOI will end it automatically. */ - inb(PIC_MASTER_POLL); - raw_spin_unlock(&i8259A_lock); - } - global_clock_event->event_handler(global_clock_event); /* MCA bus quirk: Acknowledge irq0 by setting bit 7 in port 0x61 */ diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index db30d9cb9dd6..f02c179c2552 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -437,14 +437,12 @@ do_nmi(struct pt_regs *regs, long error_code) void stop_nmi(void) { - acpi_nmi_disable(); ignore_nmis++; } void restart_nmi(void) { ignore_nmis--; - acpi_nmi_enable(); } /* May run on IST stack. */ diff --git a/arch/x86/oprofile/nmi_timer_int.c b/arch/x86/oprofile/nmi_timer_int.c index e3ecb71b5790..0636dd93cef8 100644 --- a/arch/x86/oprofile/nmi_timer_int.c +++ b/arch/x86/oprofile/nmi_timer_int.c @@ -58,9 +58,6 @@ static void timer_stop(void) int __init op_nmi_timer_init(struct oprofile_operations *ops) { - if ((nmi_watchdog != NMI_IO_APIC) || (atomic_read(&nmi_active) <= 0)) - return -ENODEV; - ops->start = timer_start; ops->stop = timer_stop; ops->cpu_type = "timer"; diff --git a/drivers/acpi/acpica/nsinit.c b/drivers/acpi/acpica/nsinit.c index 660a2728908d..0cac7ec0d2ec 100644 --- a/drivers/acpi/acpica/nsinit.c +++ b/drivers/acpi/acpica/nsinit.c @@ -577,9 +577,7 @@ acpi_ns_init_one_device(acpi_handle obj_handle, * as possible (without an NMI being received in the middle of * this) - so disable NMIs and initialize the device: */ - acpi_nmi_disable(); status = acpi_ns_evaluate(info); - acpi_nmi_enable(); if (ACPI_SUCCESS(status)) { walk_info->num_INI++; diff --git a/drivers/watchdog/hpwdt.c b/drivers/watchdog/hpwdt.c index 3d77116e4634..c19f4a20794a 100644 --- a/drivers/watchdog/hpwdt.c +++ b/drivers/watchdog/hpwdt.c @@ -649,12 +649,7 @@ static void __devinit hpwdt_check_nmi_decoding(struct pci_dev *dev) * If nmi_watchdog is turned off then we can turn on * our nmi decoding capability. */ - if (!nmi_watchdog_active()) - hpwdt_nmi_decoding = 1; - else - dev_warn(&dev->dev, "NMI decoding is disabled. To enable this " - "functionality you must reboot with nmi_watchdog=0 " - "and load the hpwdt driver with priority=1.\n"); + hpwdt_nmi_decoding = 1; } #else static void __devinit hpwdt_check_nmi_decoding(struct pci_dev *dev) diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 0cb3e5c246d0..1c451e6ecc17 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -25,8 +25,6 @@ static inline void touch_nmi_watchdog(void) #else extern void touch_nmi_watchdog(void); #endif -static inline void acpi_nmi_disable(void) { } -static inline void acpi_nmi_enable(void) { } /* * Create trigger_all_cpu_backtrace() out of the arch-provided -- cgit v1.2.3 From 48c5ccae88dcd989d9de507e8510313c6cbd352b Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Sat, 13 Nov 2010 19:32:29 +0100 Subject: sched: Simplify cpu-hot-unplug task migration While discussing the need for sched_idle_next(), Oleg remarked that since try_to_wake_up() ensures sleeping tasks will end up running on a sane cpu, we can do away with migrate_live_tasks(). If we then extend the existing hack of migrating current from CPU_DYING to migrating the full rq worth of tasks from CPU_DYING, the need for the sched_idle_next() abomination disappears as well, since idle will be the only possible thread left after the migration thread stops. This greatly simplifies the hot-unplug task migration path, as can be seen from the resulting code reduction (and about half the new lines are comments). Suggested-by: Oleg Nesterov Signed-off-by: Peter Zijlstra LKML-Reference: <1289851597.2109.547.camel@laptop> Signed-off-by: Ingo Molnar --- include/linux/sched.h | 3 - kernel/cpu.c | 16 ++-- kernel/sched.c | 206 +++++++++++++++----------------------------------- 3 files changed, 67 insertions(+), 158 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 3cd70cf91fde..29d953abb5ad 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1871,14 +1871,11 @@ extern void sched_clock_idle_sleep_event(void); extern void sched_clock_idle_wakeup_event(u64 delta_ns); #ifdef CONFIG_HOTPLUG_CPU -extern void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p); extern void idle_task_exit(void); #else static inline void idle_task_exit(void) {} #endif -extern void sched_idle_next(void); - #if defined(CONFIG_NO_HZ) && defined(CONFIG_SMP) extern void wake_up_idle_cpu(int cpu); #else diff --git a/kernel/cpu.c b/kernel/cpu.c index f6e726f18491..8615aa65d927 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -189,7 +189,6 @@ static inline void check_for_tasks(int cpu) } struct take_cpu_down_param { - struct task_struct *caller; unsigned long mod; void *hcpu; }; @@ -208,11 +207,6 @@ static int __ref take_cpu_down(void *_param) cpu_notify(CPU_DYING | param->mod, param->hcpu); - if (task_cpu(param->caller) == cpu) - move_task_off_dead_cpu(cpu, param->caller); - /* Force idle task to run as soon as we yield: it should - immediately notice cpu is offline and die quickly. */ - sched_idle_next(); return 0; } @@ -223,7 +217,6 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) void *hcpu = (void *)(long)cpu; unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0; struct take_cpu_down_param tcd_param = { - .caller = current, .mod = mod, .hcpu = hcpu, }; @@ -253,9 +246,12 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) } BUG_ON(cpu_online(cpu)); - /* Wait for it to sleep (leaving idle task). */ - while (!idle_cpu(cpu)) - yield(); + /* + * The migration_call() CPU_DYING callback will have removed all + * runnable tasks from the cpu, there's only the idle task left now + * that the migration thread is done doing the stop_machine thing. + */ + BUG_ON(!idle_cpu(cpu)); /* This actually kills the CPU. */ __cpu_die(cpu); diff --git a/kernel/sched.c b/kernel/sched.c index 41f18695b730..b0d5f1b24a39 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2366,18 +2366,15 @@ static int select_fallback_rq(int cpu, struct task_struct *p) return dest_cpu; /* No more Mr. Nice Guy. */ - if (unlikely(dest_cpu >= nr_cpu_ids)) { - dest_cpu = cpuset_cpus_allowed_fallback(p); - /* - * Don't tell them about moving exiting tasks or - * kernel threads (both mm NULL), since they never - * leave kernel. - */ - if (p->mm && printk_ratelimit()) { - printk(KERN_INFO "process %d (%s) no " - "longer affine to cpu%d\n", - task_pid_nr(p), p->comm, cpu); - } + dest_cpu = cpuset_cpus_allowed_fallback(p); + /* + * Don't tell them about moving exiting tasks or + * kernel threads (both mm NULL), since they never + * leave kernel. + */ + if (p->mm && printk_ratelimit()) { + printk(KERN_INFO "process %d (%s) no longer affine to cpu%d\n", + task_pid_nr(p), p->comm, cpu); } return dest_cpu; @@ -5712,29 +5709,20 @@ static int migration_cpu_stop(void *data) } #ifdef CONFIG_HOTPLUG_CPU + /* - * Figure out where task on dead CPU should go, use force if necessary. + * Ensures that the idle task is using init_mm right before its cpu goes + * offline. */ -void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p) +void idle_task_exit(void) { - struct rq *rq = cpu_rq(dead_cpu); - int needs_cpu, uninitialized_var(dest_cpu); - unsigned long flags; + struct mm_struct *mm = current->active_mm; - local_irq_save(flags); + BUG_ON(cpu_online(smp_processor_id())); - raw_spin_lock(&rq->lock); - needs_cpu = (task_cpu(p) == dead_cpu) && (p->state != TASK_WAKING); - if (needs_cpu) - dest_cpu = select_fallback_rq(dead_cpu, p); - raw_spin_unlock(&rq->lock); - /* - * It can only fail if we race with set_cpus_allowed(), - * in the racer should migrate the task anyway. - */ - if (needs_cpu) - __migrate_task(p, dead_cpu, dest_cpu); - local_irq_restore(flags); + if (mm != &init_mm) + switch_mm(mm, &init_mm, current); + mmdrop(mm); } /* @@ -5747,128 +5735,69 @@ void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p) static void migrate_nr_uninterruptible(struct rq *rq_src) { struct rq *rq_dest = cpu_rq(cpumask_any(cpu_active_mask)); - unsigned long flags; - local_irq_save(flags); - double_rq_lock(rq_src, rq_dest); rq_dest->nr_uninterruptible += rq_src->nr_uninterruptible; rq_src->nr_uninterruptible = 0; - double_rq_unlock(rq_src, rq_dest); - local_irq_restore(flags); -} - -/* Run through task list and migrate tasks from the dead cpu. */ -static void migrate_live_tasks(int src_cpu) -{ - struct task_struct *p, *t; - - read_lock(&tasklist_lock); - - do_each_thread(t, p) { - if (p == current) - continue; - - if (task_cpu(p) == src_cpu) - move_task_off_dead_cpu(src_cpu, p); - } while_each_thread(t, p); - - read_unlock(&tasklist_lock); } /* - * Schedules idle task to be the next runnable task on current CPU. - * It does so by boosting its priority to highest possible. - * Used by CPU offline code. + * remove the tasks which were accounted by rq from calc_load_tasks. */ -void sched_idle_next(void) +static void calc_global_load_remove(struct rq *rq) { - int this_cpu = smp_processor_id(); - struct rq *rq = cpu_rq(this_cpu); - struct task_struct *p = rq->idle; - unsigned long flags; - - /* cpu has to be offline */ - BUG_ON(cpu_online(this_cpu)); - - /* - * Strictly not necessary since rest of the CPUs are stopped by now - * and interrupts disabled on the current cpu. - */ - raw_spin_lock_irqsave(&rq->lock, flags); - - __setscheduler(rq, p, SCHED_FIFO, MAX_RT_PRIO-1); - - activate_task(rq, p, 0); - - raw_spin_unlock_irqrestore(&rq->lock, flags); + atomic_long_sub(rq->calc_load_active, &calc_load_tasks); + rq->calc_load_active = 0; } /* - * Ensures that the idle task is using init_mm right before its cpu goes - * offline. + * Migrate all tasks from the rq, sleeping tasks will be migrated by + * try_to_wake_up()->select_task_rq(). + * + * Called with rq->lock held even though we'er in stop_machine() and + * there's no concurrency possible, we hold the required locks anyway + * because of lock validation efforts. */ -void idle_task_exit(void) -{ - struct mm_struct *mm = current->active_mm; - - BUG_ON(cpu_online(smp_processor_id())); - - if (mm != &init_mm) - switch_mm(mm, &init_mm, current); - mmdrop(mm); -} - -/* called under rq->lock with disabled interrupts */ -static void migrate_dead(unsigned int dead_cpu, struct task_struct *p) +static void migrate_tasks(unsigned int dead_cpu) { struct rq *rq = cpu_rq(dead_cpu); - - /* Must be exiting, otherwise would be on tasklist. */ - BUG_ON(!p->exit_state); - - /* Cannot have done final schedule yet: would have vanished. */ - BUG_ON(p->state == TASK_DEAD); - - get_task_struct(p); + struct task_struct *next, *stop = rq->stop; + int dest_cpu; /* - * Drop lock around migration; if someone else moves it, - * that's OK. No task can be added to this CPU, so iteration is - * fine. + * Fudge the rq selection such that the below task selection loop + * doesn't get stuck on the currently eligible stop task. + * + * We're currently inside stop_machine() and the rq is either stuck + * in the stop_machine_cpu_stop() loop, or we're executing this code, + * either way we should never end up calling schedule() until we're + * done here. */ - raw_spin_unlock_irq(&rq->lock); - move_task_off_dead_cpu(dead_cpu, p); - raw_spin_lock_irq(&rq->lock); - - put_task_struct(p); -} - -/* release_task() removes task from tasklist, so we won't find dead tasks. */ -static void migrate_dead_tasks(unsigned int dead_cpu) -{ - struct rq *rq = cpu_rq(dead_cpu); - struct task_struct *next; + rq->stop = NULL; for ( ; ; ) { - if (!rq->nr_running) + /* + * There's this thread running, bail when that's the only + * remaining thread. + */ + if (rq->nr_running == 1) break; + next = pick_next_task(rq); - if (!next) - break; + BUG_ON(!next); next->sched_class->put_prev_task(rq, next); - migrate_dead(dead_cpu, next); + /* Find suitable destination for @next, with force if needed. */ + dest_cpu = select_fallback_rq(dead_cpu, next); + raw_spin_unlock(&rq->lock); + + __migrate_task(next, dead_cpu, dest_cpu); + + raw_spin_lock(&rq->lock); } -} -/* - * remove the tasks which were accounted by rq from calc_load_tasks. - */ -static void calc_global_load_remove(struct rq *rq) -{ - atomic_long_sub(rq->calc_load_active, &calc_load_tasks); - rq->calc_load_active = 0; + rq->stop = stop; } + #endif /* CONFIG_HOTPLUG_CPU */ #if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL) @@ -6078,15 +6007,13 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) unsigned long flags; struct rq *rq = cpu_rq(cpu); - switch (action) { + switch (action & ~CPU_TASKS_FROZEN) { case CPU_UP_PREPARE: - case CPU_UP_PREPARE_FROZEN: rq->calc_load_update = calc_load_update; break; case CPU_ONLINE: - case CPU_ONLINE_FROZEN: /* Update our root-domain */ raw_spin_lock_irqsave(&rq->lock, flags); if (rq->rd) { @@ -6098,30 +6025,19 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) break; #ifdef CONFIG_HOTPLUG_CPU - case CPU_DEAD: - case CPU_DEAD_FROZEN: - migrate_live_tasks(cpu); - /* Idle task back to normal (off runqueue, low prio) */ - raw_spin_lock_irq(&rq->lock); - deactivate_task(rq, rq->idle, 0); - __setscheduler(rq, rq->idle, SCHED_NORMAL, 0); - rq->idle->sched_class = &idle_sched_class; - migrate_dead_tasks(cpu); - raw_spin_unlock_irq(&rq->lock); - migrate_nr_uninterruptible(rq); - BUG_ON(rq->nr_running != 0); - calc_global_load_remove(rq); - break; - case CPU_DYING: - case CPU_DYING_FROZEN: /* Update our root-domain */ raw_spin_lock_irqsave(&rq->lock, flags); if (rq->rd) { BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span)); set_rq_offline(rq); } + migrate_tasks(cpu); + BUG_ON(rq->nr_running != 1); /* the migration thread */ raw_spin_unlock_irqrestore(&rq->lock, flags); + + migrate_nr_uninterruptible(rq); + calc_global_load_remove(rq); break; #endif } -- cgit v1.2.3 From 2069dd75c7d0f49355939e5586daf5a9ab216db7 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 15 Nov 2010 15:47:00 -0800 Subject: sched: Rewrite tg_shares_up) By tracking a per-cpu load-avg for each cfs_rq and folding it into a global task_group load on each tick we can rework tg_shares_up to be strictly per-cpu. This should improve cpu-cgroup performance for smp systems significantly. [ Paul: changed to use queueing cfs_rq + bug fixes ] Signed-off-by: Paul Turner Signed-off-by: Peter Zijlstra LKML-Reference: <20101115234937.580480400@google.com> Signed-off-by: Ingo Molnar --- include/linux/sched.h | 2 - kernel/sched.c | 173 ++++++++++++------------------------------------ kernel/sched_debug.c | 15 +++-- kernel/sched_fair.c | 164 +++++++++++++++++++++++++++++---------------- kernel/sched_features.h | 2 - kernel/sysctl.c | 19 ------ 6 files changed, 162 insertions(+), 213 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 29d953abb5ad..8abb8aa59664 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1885,8 +1885,6 @@ static inline void wake_up_idle_cpu(int cpu) { } extern unsigned int sysctl_sched_latency; extern unsigned int sysctl_sched_min_granularity; extern unsigned int sysctl_sched_wakeup_granularity; -extern unsigned int sysctl_sched_shares_ratelimit; -extern unsigned int sysctl_sched_shares_thresh; extern unsigned int sysctl_sched_child_runs_first; enum sched_tunable_scaling { diff --git a/kernel/sched.c b/kernel/sched.c index b0d5f1b24a39..e2f1a3024a99 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -253,6 +253,8 @@ struct task_group { /* runqueue "owned" by this group on each cpu */ struct cfs_rq **cfs_rq; unsigned long shares; + + atomic_t load_weight; #endif #ifdef CONFIG_RT_GROUP_SCHED @@ -359,15 +361,11 @@ struct cfs_rq { */ unsigned long h_load; - /* - * this cpu's part of tg->shares - */ - unsigned long shares; + u64 load_avg; + u64 load_period; + u64 load_stamp; - /* - * load.weight at the time we set shares - */ - unsigned long rq_weight; + unsigned long load_contribution; #endif #endif }; @@ -806,20 +804,6 @@ late_initcall(sched_init_debug); */ const_debug unsigned int sysctl_sched_nr_migrate = 32; -/* - * ratelimit for updating the group shares. - * default: 0.25ms - */ -unsigned int sysctl_sched_shares_ratelimit = 250000; -unsigned int normalized_sysctl_sched_shares_ratelimit = 250000; - -/* - * Inject some fuzzyness into changing the per-cpu group shares - * this avoids remote rq-locks at the expense of fairness. - * default: 4 - */ -unsigned int sysctl_sched_shares_thresh = 4; - /* * period over which we average the RT time consumption, measured * in ms. @@ -1369,6 +1353,12 @@ static inline void update_load_sub(struct load_weight *lw, unsigned long dec) lw->inv_weight = 0; } +static inline void update_load_set(struct load_weight *lw, unsigned long w) +{ + lw->weight = w; + lw->inv_weight = 0; +} + /* * To aid in avoiding the subversion of "niceness" due to uneven distribution * of tasks with abnormal "nice" values across CPUs the contribution that @@ -1557,97 +1547,44 @@ static unsigned long cpu_avg_load_per_task(int cpu) #ifdef CONFIG_FAIR_GROUP_SCHED -static __read_mostly unsigned long __percpu *update_shares_data; - -static void __set_se_shares(struct sched_entity *se, unsigned long shares); - -/* - * Calculate and set the cpu's group shares. - */ -static void update_group_shares_cpu(struct task_group *tg, int cpu, - unsigned long sd_shares, - unsigned long sd_rq_weight, - unsigned long *usd_rq_weight) -{ - unsigned long shares, rq_weight; - int boost = 0; - - rq_weight = usd_rq_weight[cpu]; - if (!rq_weight) { - boost = 1; - rq_weight = NICE_0_LOAD; - } - - /* - * \Sum_j shares_j * rq_weight_i - * shares_i = ----------------------------- - * \Sum_j rq_weight_j - */ - shares = (sd_shares * rq_weight) / sd_rq_weight; - shares = clamp_t(unsigned long, shares, MIN_SHARES, MAX_SHARES); - - if (abs(shares - tg->se[cpu]->load.weight) > - sysctl_sched_shares_thresh) { - struct rq *rq = cpu_rq(cpu); - unsigned long flags; - - raw_spin_lock_irqsave(&rq->lock, flags); - tg->cfs_rq[cpu]->rq_weight = boost ? 0 : rq_weight; - tg->cfs_rq[cpu]->shares = boost ? 0 : shares; - __set_se_shares(tg->se[cpu], shares); - raw_spin_unlock_irqrestore(&rq->lock, flags); - } -} +static void update_cfs_load(struct cfs_rq *cfs_rq); +static void update_cfs_shares(struct cfs_rq *cfs_rq); /* - * Re-compute the task group their per cpu shares over the given domain. - * This needs to be done in a bottom-up fashion because the rq weight of a - * parent group depends on the shares of its child groups. + * update tg->load_weight by folding this cpu's load_avg */ static int tg_shares_up(struct task_group *tg, void *data) { - unsigned long weight, rq_weight = 0, sum_weight = 0, shares = 0; - unsigned long *usd_rq_weight; - struct sched_domain *sd = data; + long load_avg; + struct cfs_rq *cfs_rq; unsigned long flags; - int i; + int cpu = (long)data; + struct rq *rq; - if (!tg->se[0]) + if (!tg->se[cpu]) return 0; - local_irq_save(flags); - usd_rq_weight = per_cpu_ptr(update_shares_data, smp_processor_id()); - - for_each_cpu(i, sched_domain_span(sd)) { - weight = tg->cfs_rq[i]->load.weight; - usd_rq_weight[i] = weight; - - rq_weight += weight; - /* - * If there are currently no tasks on the cpu pretend there - * is one of average load so that when a new task gets to - * run here it will not get delayed by group starvation. - */ - if (!weight) - weight = NICE_0_LOAD; + rq = cpu_rq(cpu); + cfs_rq = tg->cfs_rq[cpu]; - sum_weight += weight; - shares += tg->cfs_rq[i]->shares; - } + raw_spin_lock_irqsave(&rq->lock, flags); - if (!rq_weight) - rq_weight = sum_weight; + update_rq_clock(rq); + update_cfs_load(cfs_rq); - if ((!shares && rq_weight) || shares > tg->shares) - shares = tg->shares; + load_avg = div64_u64(cfs_rq->load_avg, cfs_rq->load_period+1); + load_avg -= cfs_rq->load_contribution; - if (!sd->parent || !(sd->parent->flags & SD_LOAD_BALANCE)) - shares = tg->shares; + atomic_add(load_avg, &tg->load_weight); + cfs_rq->load_contribution += load_avg; - for_each_cpu(i, sched_domain_span(sd)) - update_group_shares_cpu(tg, i, shares, rq_weight, usd_rq_weight); + /* + * We need to update shares after updating tg->load_weight in + * order to adjust the weight of groups with long running tasks. + */ + update_cfs_shares(cfs_rq); - local_irq_restore(flags); + raw_spin_unlock_irqrestore(&rq->lock, flags); return 0; } @@ -1666,7 +1603,7 @@ static int tg_load_down(struct task_group *tg, void *data) load = cpu_rq(cpu)->load.weight; } else { load = tg->parent->cfs_rq[cpu]->h_load; - load *= tg->cfs_rq[cpu]->shares; + load *= tg->se[cpu]->load.weight; load /= tg->parent->cfs_rq[cpu]->load.weight + 1; } @@ -1675,21 +1612,16 @@ static int tg_load_down(struct task_group *tg, void *data) return 0; } -static void update_shares(struct sched_domain *sd) +static void update_shares(long cpu) { - s64 elapsed; - u64 now; - if (root_task_group_empty()) return; - now = local_clock(); - elapsed = now - sd->last_update; + /* + * XXX: replace with an on-demand list + */ - if (elapsed >= (s64)(u64)sysctl_sched_shares_ratelimit) { - sd->last_update = now; - walk_tg_tree(tg_nop, tg_shares_up, sd); - } + walk_tg_tree(tg_nop, tg_shares_up, (void *)cpu); } static void update_h_load(long cpu) @@ -1699,7 +1631,7 @@ static void update_h_load(long cpu) #else -static inline void update_shares(struct sched_domain *sd) +static inline void update_shares(int cpu) { } @@ -1824,15 +1756,6 @@ static void double_rq_unlock(struct rq *rq1, struct rq *rq2) #endif -#ifdef CONFIG_FAIR_GROUP_SCHED -static void cfs_rq_set_shares(struct cfs_rq *cfs_rq, unsigned long shares) -{ -#ifdef CONFIG_SMP - cfs_rq->shares = shares; -#endif -} -#endif - static void calc_load_account_idle(struct rq *this_rq); static void update_sysctl(void); static int get_update_sysctl_factor(void); @@ -5551,7 +5474,6 @@ static void update_sysctl(void) SET_SYSCTL(sched_min_granularity); SET_SYSCTL(sched_latency); SET_SYSCTL(sched_wakeup_granularity); - SET_SYSCTL(sched_shares_ratelimit); #undef SET_SYSCTL } @@ -7787,8 +7709,7 @@ static void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq, se->cfs_rq = parent->my_q; se->my_q = cfs_rq; - se->load.weight = tg->shares; - se->load.inv_weight = 0; + update_load_set(&se->load, tg->shares); se->parent = parent; } #endif @@ -7881,10 +7802,6 @@ void __init sched_init(void) #endif /* CONFIG_CGROUP_SCHED */ -#if defined CONFIG_FAIR_GROUP_SCHED && defined CONFIG_SMP - update_shares_data = __alloc_percpu(nr_cpu_ids * sizeof(unsigned long), - __alignof__(unsigned long)); -#endif for_each_possible_cpu(i) { struct rq *rq; @@ -8452,8 +8369,7 @@ static void __set_se_shares(struct sched_entity *se, unsigned long shares) if (on_rq) dequeue_entity(cfs_rq, se, 0); - se->load.weight = shares; - se->load.inv_weight = 0; + update_load_set(&se->load, shares); if (on_rq) enqueue_entity(cfs_rq, se, 0); @@ -8510,7 +8426,6 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares) /* * force a rebalance */ - cfs_rq_set_shares(tg->cfs_rq[i], 0); set_se_shares(tg->se[i], shares); } diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c index 2e1b0d17dd9b..e6590e7312e8 100644 --- a/kernel/sched_debug.c +++ b/kernel/sched_debug.c @@ -202,15 +202,22 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) spread0 = min_vruntime - rq0_min_vruntime; SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "spread0", SPLIT_NS(spread0)); - SEQ_printf(m, " .%-30s: %ld\n", "nr_running", cfs_rq->nr_running); - SEQ_printf(m, " .%-30s: %ld\n", "load", cfs_rq->load.weight); - SEQ_printf(m, " .%-30s: %d\n", "nr_spread_over", cfs_rq->nr_spread_over); + SEQ_printf(m, " .%-30s: %ld\n", "nr_running", cfs_rq->nr_running); + SEQ_printf(m, " .%-30s: %ld\n", "load", cfs_rq->load.weight); #ifdef CONFIG_FAIR_GROUP_SCHED #ifdef CONFIG_SMP - SEQ_printf(m, " .%-30s: %lu\n", "shares", cfs_rq->shares); + SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "load_avg", + SPLIT_NS(cfs_rq->load_avg)); + SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "load_period", + SPLIT_NS(cfs_rq->load_period)); + SEQ_printf(m, " .%-30s: %ld\n", "load_contrib", + cfs_rq->load_contribution); + SEQ_printf(m, " .%-30s: %d\n", "load_tg", + atomic_read(&tg->load_weight)); #endif + print_cfs_group_stats(m, cpu, cfs_rq->tg); #endif } diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index f4f6a8326dd0..d86544b4151c 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -417,7 +417,6 @@ int sched_proc_update_handler(struct ctl_table *table, int write, WRT_SYSCTL(sched_min_granularity); WRT_SYSCTL(sched_latency); WRT_SYSCTL(sched_wakeup_granularity); - WRT_SYSCTL(sched_shares_ratelimit); #undef WRT_SYSCTL return 0; @@ -633,7 +632,6 @@ account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se) list_add(&se->group_node, &cfs_rq->tasks); } cfs_rq->nr_running++; - se->on_rq = 1; } static void @@ -647,9 +645,89 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se) list_del_init(&se->group_node); } cfs_rq->nr_running--; - se->on_rq = 0; } +#if defined CONFIG_SMP && defined CONFIG_FAIR_GROUP_SCHED +static void update_cfs_load(struct cfs_rq *cfs_rq) +{ + u64 period = sched_avg_period(); + u64 now, delta; + + if (!cfs_rq) + return; + + now = rq_of(cfs_rq)->clock; + delta = now - cfs_rq->load_stamp; + + cfs_rq->load_stamp = now; + cfs_rq->load_period += delta; + cfs_rq->load_avg += delta * cfs_rq->load.weight; + + while (cfs_rq->load_period > period) { + /* + * Inline assembly required to prevent the compiler + * optimising this loop into a divmod call. + * See __iter_div_u64_rem() for another example of this. + */ + asm("" : "+rm" (cfs_rq->load_period)); + cfs_rq->load_period /= 2; + cfs_rq->load_avg /= 2; + } +} + +static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, + unsigned long weight) +{ + if (se->on_rq) + account_entity_dequeue(cfs_rq, se); + + update_load_set(&se->load, weight); + + if (se->on_rq) + account_entity_enqueue(cfs_rq, se); +} + +static void update_cfs_shares(struct cfs_rq *cfs_rq) +{ + struct task_group *tg; + struct sched_entity *se; + long load_weight, load, shares; + + if (!cfs_rq) + return; + + tg = cfs_rq->tg; + se = tg->se[cpu_of(rq_of(cfs_rq))]; + if (!se) + return; + + load = cfs_rq->load.weight; + + load_weight = atomic_read(&tg->load_weight); + load_weight -= cfs_rq->load_contribution; + load_weight += load; + + shares = (tg->shares * load); + if (load_weight) + shares /= load_weight; + + if (shares < MIN_SHARES) + shares = MIN_SHARES; + if (shares > tg->shares) + shares = tg->shares; + + reweight_entity(cfs_rq_of(se), se, shares); +} +#else /* CONFIG_FAIR_GROUP_SCHED */ +static inline void update_cfs_load(struct cfs_rq *cfs_rq) +{ +} + +static inline void update_cfs_shares(struct cfs_rq *cfs_rq) +{ +} +#endif /* CONFIG_FAIR_GROUP_SCHED */ + static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se) { #ifdef CONFIG_SCHEDSTATS @@ -771,7 +849,9 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) * Update run-time statistics of the 'current'. */ update_curr(cfs_rq); + update_cfs_load(cfs_rq); account_entity_enqueue(cfs_rq, se); + update_cfs_shares(cfs_rq); if (flags & ENQUEUE_WAKEUP) { place_entity(cfs_rq, se, 0); @@ -782,6 +862,7 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) check_spread(cfs_rq, se); if (se != cfs_rq->curr) __enqueue_entity(cfs_rq, se); + se->on_rq = 1; } static void __clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se) @@ -825,8 +906,11 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) if (se != cfs_rq->curr) __dequeue_entity(cfs_rq, se); + se->on_rq = 0; + update_cfs_load(cfs_rq); account_entity_dequeue(cfs_rq, se); update_min_vruntime(cfs_rq); + update_cfs_shares(cfs_rq); /* * Normalize the entity after updating the min_vruntime because the @@ -1055,6 +1139,13 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) flags = ENQUEUE_WAKEUP; } + for_each_sched_entity(se) { + struct cfs_rq *cfs_rq = cfs_rq_of(se); + + update_cfs_load(cfs_rq); + update_cfs_shares(cfs_rq); + } + hrtick_update(rq); } @@ -1071,12 +1162,20 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) for_each_sched_entity(se) { cfs_rq = cfs_rq_of(se); dequeue_entity(cfs_rq, se, flags); + /* Don't dequeue parent if it has other entities besides us */ if (cfs_rq->load.weight) break; flags |= DEQUEUE_SLEEP; } + for_each_sched_entity(se) { + struct cfs_rq *cfs_rq = cfs_rq_of(se); + + update_cfs_load(cfs_rq); + update_cfs_shares(cfs_rq); + } + hrtick_update(rq); } @@ -1143,51 +1242,20 @@ static void task_waking_fair(struct rq *rq, struct task_struct *p) * Adding load to a group doesn't make a group heavier, but can cause movement * of group shares between cpus. Assuming the shares were perfectly aligned one * can calculate the shift in shares. - * - * The problem is that perfectly aligning the shares is rather expensive, hence - * we try to avoid doing that too often - see update_shares(), which ratelimits - * this change. - * - * We compensate this by not only taking the current delta into account, but - * also considering the delta between when the shares were last adjusted and - * now. - * - * We still saw a performance dip, some tracing learned us that between - * cgroup:/ and cgroup:/foo balancing the number of affine wakeups increased - * significantly. Therefore try to bias the error in direction of failing - * the affine wakeup. - * */ -static long effective_load(struct task_group *tg, int cpu, - long wl, long wg) +static long effective_load(struct task_group *tg, int cpu, long wl, long wg) { struct sched_entity *se = tg->se[cpu]; if (!tg->parent) return wl; - /* - * By not taking the decrease of shares on the other cpu into - * account our error leans towards reducing the affine wakeups. - */ - if (!wl && sched_feat(ASYM_EFF_LOAD)) - return wl; - for_each_sched_entity(se) { long S, rw, s, a, b; - long more_w; - - /* - * Instead of using this increment, also add the difference - * between when the shares were last updated and now. - */ - more_w = se->my_q->load.weight - se->my_q->rq_weight; - wl += more_w; - wg += more_w; S = se->my_q->tg->shares; - s = se->my_q->shares; - rw = se->my_q->rq_weight; + s = se->load.weight; + rw = se->my_q->load.weight; a = S*(rw + wl); b = S*rw + s*wg; @@ -1508,23 +1576,6 @@ select_task_rq_fair(struct rq *rq, struct task_struct *p, int sd_flag, int wake_ sd = tmp; } -#ifdef CONFIG_FAIR_GROUP_SCHED - if (sched_feat(LB_SHARES_UPDATE)) { - /* - * Pick the largest domain to update shares over - */ - tmp = sd; - if (affine_sd && (!tmp || affine_sd->span_weight > sd->span_weight)) - tmp = affine_sd; - - if (tmp) { - raw_spin_unlock(&rq->lock); - update_shares(tmp); - raw_spin_lock(&rq->lock); - } - } -#endif - if (affine_sd) { if (cpu == prev_cpu || wake_affine(affine_sd, p, sync)) return select_idle_sibling(p, cpu); @@ -3014,7 +3065,6 @@ static int load_balance(int this_cpu, struct rq *this_rq, schedstat_inc(sd, lb_count[idle]); redo: - update_shares(sd); group = find_busiest_group(sd, this_cpu, &imbalance, idle, &sd_idle, cpus, balance); @@ -3156,8 +3206,6 @@ out_one_pinned: else ld_moved = 0; out: - if (ld_moved) - update_shares(sd); return ld_moved; } @@ -3549,6 +3597,8 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle) int update_next_balance = 0; int need_serialize; + update_shares(cpu); + for_each_domain(cpu, sd) { if (!(sd->flags & SD_LOAD_BALANCE)) continue; diff --git a/kernel/sched_features.h b/kernel/sched_features.h index 185f920ec1a2..68e69acc29b9 100644 --- a/kernel/sched_features.h +++ b/kernel/sched_features.h @@ -52,8 +52,6 @@ SCHED_FEAT(ARCH_POWER, 0) SCHED_FEAT(HRTICK, 0) SCHED_FEAT(DOUBLE_TICK, 0) SCHED_FEAT(LB_BIAS, 1) -SCHED_FEAT(LB_SHARES_UPDATE, 1) -SCHED_FEAT(ASYM_EFF_LOAD, 1) /* * Spin-wait on mutex acquisition when the mutex owner is running on diff --git a/kernel/sysctl.c b/kernel/sysctl.c index b65bf634035e..3132b25193db 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -259,8 +259,6 @@ static int min_wakeup_granularity_ns; /* 0 usecs */ static int max_wakeup_granularity_ns = NSEC_PER_SEC; /* 1 second */ static int min_sched_tunable_scaling = SCHED_TUNABLESCALING_NONE; static int max_sched_tunable_scaling = SCHED_TUNABLESCALING_END-1; -static int min_sched_shares_ratelimit = 100000; /* 100 usec */ -static int max_sched_shares_ratelimit = NSEC_PER_SEC; /* 1 second */ #endif #ifdef CONFIG_COMPACTION @@ -304,15 +302,6 @@ static struct ctl_table kern_table[] = { .extra1 = &min_wakeup_granularity_ns, .extra2 = &max_wakeup_granularity_ns, }, - { - .procname = "sched_shares_ratelimit", - .data = &sysctl_sched_shares_ratelimit, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = sched_proc_update_handler, - .extra1 = &min_sched_shares_ratelimit, - .extra2 = &max_sched_shares_ratelimit, - }, { .procname = "sched_tunable_scaling", .data = &sysctl_sched_tunable_scaling, @@ -322,14 +311,6 @@ static struct ctl_table kern_table[] = { .extra1 = &min_sched_tunable_scaling, .extra2 = &max_sched_tunable_scaling, }, - { - .procname = "sched_shares_thresh", - .data = &sysctl_sched_shares_thresh, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, - }, { .procname = "sched_migration_cost", .data = &sysctl_sched_migration_cost, -- cgit v1.2.3 From a7a4f8a752ec734b2eab904fc863d5dc873de338 Mon Sep 17 00:00:00 2001 From: Paul Turner Date: Mon, 15 Nov 2010 15:47:06 -0800 Subject: sched: Add sysctl_sched_shares_window Introduce a new sysctl for the shares window and disambiguate it from sched_time_avg. A 10ms window appears to be a good compromise between accuracy and performance. Signed-off-by: Paul Turner Signed-off-by: Peter Zijlstra LKML-Reference: <20101115234938.112173964@google.com> Signed-off-by: Ingo Molnar --- include/linux/sched.h | 1 + kernel/sched_fair.c | 9 ++++++++- kernel/sysctl.c | 7 +++++++ 3 files changed, 16 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 8abb8aa59664..840f1277492f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1900,6 +1900,7 @@ extern unsigned int sysctl_sched_migration_cost; extern unsigned int sysctl_sched_nr_migrate; extern unsigned int sysctl_sched_time_avg; extern unsigned int sysctl_timer_migration; +extern unsigned int sysctl_sched_shares_window; int sched_proc_update_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index b320753aa6c9..6c84439ce987 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -89,6 +89,13 @@ unsigned int normalized_sysctl_sched_wakeup_granularity = 1000000UL; const_debug unsigned int sysctl_sched_migration_cost = 500000UL; +/* + * The exponential sliding window over which load is averaged for shares + * distribution. + * (default: 10msec) + */ +unsigned int __read_mostly sysctl_sched_shares_window = 10000000UL; + static const struct sched_class fair_sched_class; /************************************************************** @@ -688,7 +695,7 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se) #if defined CONFIG_SMP && defined CONFIG_FAIR_GROUP_SCHED static void update_cfs_load(struct cfs_rq *cfs_rq) { - u64 period = sched_avg_period(); + u64 period = sysctl_sched_shares_window; u64 now, delta; unsigned long load = cfs_rq->load.weight; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 3132b25193db..9b520d74f052 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -332,6 +332,13 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, + { + .procname = "sched_shares_window", + .data = &sysctl_sched_shares_window, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, { .procname = "timer_migration", .data = &sysctl_timer_migration, -- cgit v1.2.3 From 84e1c6bb38eb318e456558b610396d9f1afaabf0 Mon Sep 17 00:00:00 2001 From: matthieu castet Date: Tue, 16 Nov 2010 22:35:16 +0100 Subject: x86: Add RO/NX protection for loadable kernel modules This patch is a logical extension of the protection provided by CONFIG_DEBUG_RODATA to LKMs. The protection is provided by splitting module_core and module_init into three logical parts each and setting appropriate page access permissions for each individual section: 1. Code: RO+X 2. RO data: RO+NX 3. RW data: RW+NX In order to achieve proper protection, layout_sections() have been modified to align each of the three parts mentioned above onto page boundary. Next, the corresponding page access permissions are set right before successful exit from load_module(). Further, free_module() and sys_init_module have been modified to set module_core and module_init as RW+NX right before calling module_free(). By default, the original section layout and access flags are preserved. When compiled with CONFIG_DEBUG_SET_MODULE_RONX=y, the patch will page-align each group of sections to ensure that each page contains only one type of content and will enforce RO/NX for each group of pages. -v1: Initial proof-of-concept patch. -v2: The patch have been re-written to reduce the number of #ifdefs and to make it architecture-agnostic. Code formatting has also been corrected. -v3: Opportunistic RO/NX protection is now unconditional. Section page-alignment is enabled when CONFIG_DEBUG_RODATA=y. -v4: Removed most macros and improved coding style. -v5: Changed page-alignment and RO/NX section size calculation -v6: Fixed comments. Restricted RO/NX enforcement to x86 only -v7: Introduced CONFIG_DEBUG_SET_MODULE_RONX, added calls to set_all_modules_text_rw() and set_all_modules_text_ro() in ftrace -v8: updated for compatibility with linux 2.6.33-rc5 -v9: coding style fixes -v10: more coding style fixes -v11: minor adjustments for -tip -v12: minor adjustments for v2.6.35-rc2-tip -v13: minor adjustments for v2.6.37-rc1-tip Signed-off-by: Siarhei Liakh Signed-off-by: Xuxian Jiang Acked-by: Arjan van de Ven Reviewed-by: James Morris Signed-off-by: H. Peter Anvin Cc: Andi Kleen Cc: Rusty Russell Cc: Stephen Rothwell Cc: Dave Jones Cc: Kees Cook Cc: Linus Torvalds LKML-Reference: <4CE2F914.9070106@free.fr> [ minor cleanliness edits, -v14: build failure fix ] Signed-off-by: Ingo Molnar --- arch/x86/Kconfig.debug | 11 +++ arch/x86/kernel/ftrace.c | 3 + include/linux/module.h | 11 ++- kernel/module.c | 171 ++++++++++++++++++++++++++++++++++++++++++++++- 4 files changed, 193 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index b59ee765414e..45143bbcfe5e 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -117,6 +117,17 @@ config DEBUG_RODATA_TEST feature as well as for the change_page_attr() infrastructure. If in doubt, say "N" +config DEBUG_SET_MODULE_RONX + bool "Set loadable kernel module data as NX and text as RO" + depends on MODULES + ---help--- + This option helps catch unintended modifications to loadable + kernel module's text and read-only data. It also prevents execution + of module data. Such protection may interfere with run-time code + patching and dynamic kernel tracing - and they might also protect + against certain classes of kernel exploits. + If in doubt, say "N". + config DEBUG_NX_TEST tristate "Testcase for the NX non-executable stack feature" depends on DEBUG_KERNEL && m diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 3afb33f14d2d..298448656b60 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -19,6 +19,7 @@ #include #include #include +#include #include @@ -49,6 +50,7 @@ static DEFINE_PER_CPU(int, save_modifying_code); int ftrace_arch_code_modify_prepare(void) { set_kernel_text_rw(); + set_all_modules_text_rw(); modifying_code = 1; return 0; } @@ -56,6 +58,7 @@ int ftrace_arch_code_modify_prepare(void) int ftrace_arch_code_modify_post_process(void) { modifying_code = 0; + set_all_modules_text_ro(); set_kernel_text_ro(); return 0; } diff --git a/include/linux/module.h b/include/linux/module.h index b29e7458b966..ddaa689d71bd 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -308,6 +308,9 @@ struct module /* The size of the executable code in each section. */ unsigned int init_text_size, core_text_size; + /* Size of RO sections of the module (text+rodata) */ + unsigned int init_ro_size, core_ro_size; + /* Arch-specific module values */ struct mod_arch_specific arch; @@ -672,7 +675,6 @@ static inline int module_get_iter_tracepoints(struct tracepoint_iter *iter) { return 0; } - #endif /* CONFIG_MODULES */ #ifdef CONFIG_SYSFS @@ -687,6 +689,13 @@ extern int module_sysfs_initialized; #define __MODULE_STRING(x) __stringify(x) +#ifdef CONFIG_DEBUG_SET_MODULE_RONX +extern void set_all_modules_text_rw(void); +extern void set_all_modules_text_ro(void); +#else +static inline void set_all_modules_text_rw(void) { } +static inline void set_all_modules_text_ro(void) { } +#endif #ifdef CONFIG_GENERIC_BUG void module_bug_finalize(const Elf_Ehdr *, const Elf_Shdr *, diff --git a/kernel/module.c b/kernel/module.c index 437a74a7524a..ba421e6b4ada 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -56,6 +56,7 @@ #include #include #include +#include #define CREATE_TRACE_POINTS #include @@ -70,6 +71,26 @@ #define ARCH_SHF_SMALL 0 #endif +/* + * Modules' sections will be aligned on page boundaries + * to ensure complete separation of code and data, but + * only when CONFIG_DEBUG_SET_MODULE_RONX=y + */ +#ifdef CONFIG_DEBUG_SET_MODULE_RONX +# define debug_align(X) ALIGN(X, PAGE_SIZE) +#else +# define debug_align(X) (X) +#endif + +/* + * Given BASE and SIZE this macro calculates the number of pages the + * memory regions occupies + */ +#define MOD_NUMBER_OF_PAGES(BASE, SIZE) (((SIZE) > 0) ? \ + (PFN_DOWN((unsigned long)(BASE) + (SIZE) - 1) - \ + PFN_DOWN((unsigned long)BASE) + 1) \ + : (0UL)) + /* If this is set, the section belongs in the init part of the module */ #define INIT_OFFSET_MASK (1UL << (BITS_PER_LONG-1)) @@ -1542,6 +1563,115 @@ static int __unlink_module(void *_mod) return 0; } +#ifdef CONFIG_DEBUG_SET_MODULE_RONX +/* + * LKM RO/NX protection: protect module's text/ro-data + * from modification and any data from execution. + */ +void set_page_attributes(void *start, void *end, int (*set)(unsigned long start, int num_pages)) +{ + unsigned long begin_pfn = PFN_DOWN((unsigned long)start); + unsigned long end_pfn = PFN_DOWN((unsigned long)end); + + if (end_pfn > begin_pfn) + set(begin_pfn << PAGE_SHIFT, end_pfn - begin_pfn); +} + +static void set_section_ro_nx(void *base, + unsigned long text_size, + unsigned long ro_size, + unsigned long total_size) +{ + /* begin and end PFNs of the current subsection */ + unsigned long begin_pfn; + unsigned long end_pfn; + + /* + * Set RO for module text and RO-data: + * - Always protect first page. + * - Do not protect last partial page. + */ + if (ro_size > 0) + set_page_attributes(base, base + ro_size, set_memory_ro); + + /* + * Set NX permissions for module data: + * - Do not protect first partial page. + * - Always protect last page. + */ + if (total_size > text_size) { + begin_pfn = PFN_UP((unsigned long)base + text_size); + end_pfn = PFN_UP((unsigned long)base + total_size); + if (end_pfn > begin_pfn) + set_memory_nx(begin_pfn << PAGE_SHIFT, end_pfn - begin_pfn); + } +} + +/* Setting memory back to RW+NX before releasing it */ +void unset_section_ro_nx(struct module *mod, void *module_region) +{ + unsigned long total_pages; + + if (mod->module_core == module_region) { + /* Set core as NX+RW */ + total_pages = MOD_NUMBER_OF_PAGES(mod->module_core, mod->core_size); + set_memory_nx((unsigned long)mod->module_core, total_pages); + set_memory_rw((unsigned long)mod->module_core, total_pages); + + } else if (mod->module_init == module_region) { + /* Set init as NX+RW */ + total_pages = MOD_NUMBER_OF_PAGES(mod->module_init, mod->init_size); + set_memory_nx((unsigned long)mod->module_init, total_pages); + set_memory_rw((unsigned long)mod->module_init, total_pages); + } +} + +/* Iterate through all modules and set each module's text as RW */ +void set_all_modules_text_rw() +{ + struct module *mod; + + mutex_lock(&module_mutex); + list_for_each_entry_rcu(mod, &modules, list) { + if ((mod->module_core) && (mod->core_text_size)) { + set_page_attributes(mod->module_core, + mod->module_core + mod->core_text_size, + set_memory_rw); + } + if ((mod->module_init) && (mod->init_text_size)) { + set_page_attributes(mod->module_init, + mod->module_init + mod->init_text_size, + set_memory_rw); + } + } + mutex_unlock(&module_mutex); +} + +/* Iterate through all modules and set each module's text as RO */ +void set_all_modules_text_ro() +{ + struct module *mod; + + mutex_lock(&module_mutex); + list_for_each_entry_rcu(mod, &modules, list) { + if ((mod->module_core) && (mod->core_text_size)) { + set_page_attributes(mod->module_core, + mod->module_core + mod->core_text_size, + set_memory_ro); + } + if ((mod->module_init) && (mod->init_text_size)) { + set_page_attributes(mod->module_init, + mod->module_init + mod->init_text_size, + set_memory_ro); + } + } + mutex_unlock(&module_mutex); +} +#else +static inline void set_section_ro_nx(void *base, unsigned long text_size, unsigned long ro_size, unsigned long total_size) { } +static inline void unset_section_ro_nx(struct module *mod, void *module_region) { } +#endif + /* Free a module, remove from lists, etc. */ static void free_module(struct module *mod) { @@ -1566,6 +1696,7 @@ static void free_module(struct module *mod) destroy_params(mod->kp, mod->num_kp); /* This may be NULL, but that's OK */ + unset_section_ro_nx(mod, mod->module_init); module_free(mod, mod->module_init); kfree(mod->args); percpu_modfree(mod); @@ -1574,6 +1705,7 @@ static void free_module(struct module *mod) lockdep_free_key_range(mod->module_core, mod->core_size); /* Finally, free the core (containing the module structure) */ + unset_section_ro_nx(mod, mod->module_core); module_free(mod, mod->module_core); #ifdef CONFIG_MPU @@ -1777,8 +1909,19 @@ static void layout_sections(struct module *mod, struct load_info *info) s->sh_entsize = get_offset(mod, &mod->core_size, s, i); DEBUGP("\t%s\n", name); } - if (m == 0) + switch (m) { + case 0: /* executable */ + mod->core_size = debug_align(mod->core_size); mod->core_text_size = mod->core_size; + break; + case 1: /* RO: text and ro-data */ + mod->core_size = debug_align(mod->core_size); + mod->core_ro_size = mod->core_size; + break; + case 3: /* whole core */ + mod->core_size = debug_align(mod->core_size); + break; + } } DEBUGP("Init section allocation order:\n"); @@ -1796,8 +1939,19 @@ static void layout_sections(struct module *mod, struct load_info *info) | INIT_OFFSET_MASK); DEBUGP("\t%s\n", sname); } - if (m == 0) + switch (m) { + case 0: /* executable */ + mod->init_size = debug_align(mod->init_size); mod->init_text_size = mod->init_size; + break; + case 1: /* RO: text and ro-data */ + mod->init_size = debug_align(mod->init_size); + mod->init_ro_size = mod->init_size; + break; + case 3: /* whole init */ + mod->init_size = debug_align(mod->init_size); + break; + } } } @@ -2650,6 +2804,18 @@ static struct module *load_module(void __user *umod, kfree(info.strmap); free_copy(&info); + /* Set RO and NX regions for core */ + set_section_ro_nx(mod->module_core, + mod->core_text_size, + mod->core_ro_size, + mod->core_size); + + /* Set RO and NX regions for init */ + set_section_ro_nx(mod->module_init, + mod->init_text_size, + mod->init_ro_size, + mod->init_size); + /* Done! */ trace_module_load(mod); return mod; @@ -2753,6 +2919,7 @@ SYSCALL_DEFINE3(init_module, void __user *, umod, mod->symtab = mod->core_symtab; mod->strtab = mod->core_strtab; #endif + unset_section_ro_nx(mod, mod->module_init); module_free(mod, mod->module_init); mod->module_init = NULL; mod->init_size = 0; -- cgit v1.2.3 From 9c0729dc8062bed96189bd14ac6d4920f3958743 Mon Sep 17 00:00:00 2001 From: Soeren Sandmann Pedersen Date: Fri, 5 Nov 2010 05:59:39 -0400 Subject: x86: Eliminate bp argument from the stack tracing routines The various stack tracing routines take a 'bp' argument in which the caller is supposed to provide the base pointer to use, or 0 if doesn't have one. Since bp is garbage whenever CONFIG_FRAME_POINTER is not defined, this means all callers in principle should either always pass 0, or be conditional on CONFIG_FRAME_POINTER. However, there are only really three use cases for stack tracing: (a) Trace the current task, including IRQ stack if any (b) Trace the current task, but skip IRQ stack (c) Trace some other task In all cases, if CONFIG_FRAME_POINTER is not defined, bp should just be 0. If it _is_ defined, then - in case (a) bp should be gotten directly from the CPU's register, so the caller should pass NULL for regs, - in case (b) the caller should should pass the IRQ registers to dump_trace(), - in case (c) bp should be gotten from the top of the task's stack, so the caller should pass NULL for regs. Hence, the bp argument is not necessary because the combination of task and regs is sufficient to determine an appropriate value for bp. This patch introduces a new inline function stack_frame(task, regs) that computes the desired bp. This function is then called from the two versions of dump_stack(). Signed-off-by: Soren Sandmann Acked-by: Steven Rostedt Cc: Thomas Gleixner Cc: Ingo Molnar Cc: H. Peter Anvin Cc: Peter Zijlstra Cc: Arjan van de Ven , Cc: Frederic Weisbecker , Cc: Arnaldo Carvalho de Melo , LKML-Reference: > Signed-off-by: Frederic Weisbecker --- arch/x86/include/asm/kdebug.h | 2 +- arch/x86/include/asm/stacktrace.h | 33 ++++++++++++++++++++++++++++++--- arch/x86/kernel/cpu/perf_event.c | 2 +- arch/x86/kernel/dumpstack.c | 12 ++++++------ arch/x86/kernel/dumpstack_32.c | 25 +++++++------------------ arch/x86/kernel/dumpstack_64.c | 24 +++++++----------------- arch/x86/kernel/process.c | 3 +-- arch/x86/kernel/stacktrace.c | 8 ++++---- arch/x86/mm/kmemcheck/error.c | 2 +- arch/x86/oprofile/backtrace.c | 2 +- include/linux/stacktrace.h | 4 +++- 11 files changed, 62 insertions(+), 55 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/include/asm/kdebug.h b/arch/x86/include/asm/kdebug.h index 5bdfca86581b..f23eb2528464 100644 --- a/arch/x86/include/asm/kdebug.h +++ b/arch/x86/include/asm/kdebug.h @@ -28,7 +28,7 @@ extern void die(const char *, struct pt_regs *,long); extern int __must_check __die(const char *, struct pt_regs *, long); extern void show_registers(struct pt_regs *regs); extern void show_trace(struct task_struct *t, struct pt_regs *regs, - unsigned long *sp, unsigned long bp); + unsigned long *sp); extern void __show_regs(struct pt_regs *regs, int all); extern void show_regs(struct pt_regs *regs); extern unsigned long oops_begin(void); diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h index 2b16a2ad23dc..52b5c7ed3608 100644 --- a/arch/x86/include/asm/stacktrace.h +++ b/arch/x86/include/asm/stacktrace.h @@ -7,6 +7,7 @@ #define _ASM_X86_STACKTRACE_H #include +#include extern int kstack_depth_to_print; @@ -46,7 +47,7 @@ struct stacktrace_ops { }; void dump_trace(struct task_struct *tsk, struct pt_regs *regs, - unsigned long *stack, unsigned long bp, + unsigned long *stack, const struct stacktrace_ops *ops, void *data); #ifdef CONFIG_X86_32 @@ -57,13 +58,39 @@ void dump_trace(struct task_struct *tsk, struct pt_regs *regs, #define get_bp(bp) asm("movq %%rbp, %0" : "=r" (bp) :) #endif +#ifdef CONFIG_FRAME_POINTER +static inline unsigned long +stack_frame(struct task_struct *task, struct pt_regs *regs) +{ + unsigned long bp; + + if (regs) + return regs->bp; + + if (task == current) { + /* Grab bp right from our regs */ + get_bp(bp); + return bp; + } + + /* bp is the last reg pushed by switch_to */ + return *(unsigned long *)task->thread.sp; +} +#else +static inline unsigned long +stack_frame(struct task_struct *task, struct pt_regs *regs) +{ + return 0; +} +#endif + extern void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, - unsigned long *stack, unsigned long bp, char *log_lvl); + unsigned long *stack, char *log_lvl); extern void show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, - unsigned long *sp, unsigned long bp, char *log_lvl); + unsigned long *sp, char *log_lvl); extern unsigned int code_bytes; diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index ed6310183efb..461a85dcaba4 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1666,7 +1666,7 @@ perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs) perf_callchain_store(entry, regs->ip); - dump_trace(NULL, regs, NULL, regs->bp, &backtrace_ops, entry); + dump_trace(NULL, regs, NULL, &backtrace_ops, entry); } #ifdef CONFIG_COMPAT diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 6e8752c1bd52..8474c998cbd4 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -175,21 +175,21 @@ static const struct stacktrace_ops print_trace_ops = { void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, - unsigned long *stack, unsigned long bp, char *log_lvl) + unsigned long *stack, char *log_lvl) { printk("%sCall Trace:\n", log_lvl); - dump_trace(task, regs, stack, bp, &print_trace_ops, log_lvl); + dump_trace(task, regs, stack, &print_trace_ops, log_lvl); } void show_trace(struct task_struct *task, struct pt_regs *regs, - unsigned long *stack, unsigned long bp) + unsigned long *stack) { - show_trace_log_lvl(task, regs, stack, bp, ""); + show_trace_log_lvl(task, regs, stack, ""); } void show_stack(struct task_struct *task, unsigned long *sp) { - show_stack_log_lvl(task, NULL, sp, 0, ""); + show_stack_log_lvl(task, NULL, sp, ""); } /* @@ -210,7 +210,7 @@ void dump_stack(void) init_utsname()->release, (int)strcspn(init_utsname()->version, " "), init_utsname()->version); - show_trace(NULL, NULL, &stack, bp); + show_trace(NULL, NULL, &stack); } EXPORT_SYMBOL(dump_stack); diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c index 1bc7f75a5bda..74cc1eda384b 100644 --- a/arch/x86/kernel/dumpstack_32.c +++ b/arch/x86/kernel/dumpstack_32.c @@ -17,11 +17,12 @@ #include -void dump_trace(struct task_struct *task, struct pt_regs *regs, - unsigned long *stack, unsigned long bp, +void dump_trace(struct task_struct *task, + struct pt_regs *regs, unsigned long *stack, const struct stacktrace_ops *ops, void *data) { int graph = 0; + unsigned long bp; if (!task) task = current; @@ -34,18 +35,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, stack = (unsigned long *)task->thread.sp; } -#ifdef CONFIG_FRAME_POINTER - if (!bp) { - if (task == current) { - /* Grab bp right from our regs */ - get_bp(bp); - } else { - /* bp is the last reg pushed by switch_to */ - bp = *(unsigned long *) task->thread.sp; - } - } -#endif - + bp = stack_frame(task, regs); for (;;) { struct thread_info *context; @@ -65,7 +55,7 @@ EXPORT_SYMBOL(dump_trace); void show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, - unsigned long *sp, unsigned long bp, char *log_lvl) + unsigned long *sp, char *log_lvl) { unsigned long *stack; int i; @@ -87,7 +77,7 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, touch_nmi_watchdog(); } printk(KERN_CONT "\n"); - show_trace_log_lvl(task, regs, sp, bp, log_lvl); + show_trace_log_lvl(task, regs, sp, log_lvl); } @@ -112,8 +102,7 @@ void show_registers(struct pt_regs *regs) u8 *ip; printk(KERN_EMERG "Stack:\n"); - show_stack_log_lvl(NULL, regs, ®s->sp, - 0, KERN_EMERG); + show_stack_log_lvl(NULL, regs, ®s->sp, KERN_EMERG); printk(KERN_EMERG "Code: "); diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 6a340485249a..64101335de19 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -139,8 +139,8 @@ fixup_bp_irq_link(unsigned long bp, unsigned long *stack, * severe exception (double fault, nmi, stack fault, debug, mce) hardware stack */ -void dump_trace(struct task_struct *task, struct pt_regs *regs, - unsigned long *stack, unsigned long bp, +void dump_trace(struct task_struct *task, + struct pt_regs *regs, unsigned long *stack, const struct stacktrace_ops *ops, void *data) { const unsigned cpu = get_cpu(); @@ -149,6 +149,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, unsigned used = 0; struct thread_info *tinfo; int graph = 0; + unsigned long bp; if (!task) task = current; @@ -160,18 +161,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, stack = (unsigned long *)task->thread.sp; } -#ifdef CONFIG_FRAME_POINTER - if (!bp) { - if (task == current) { - /* Grab bp right from our regs */ - get_bp(bp); - } else { - /* bp is the last reg pushed by switch_to */ - bp = *(unsigned long *) task->thread.sp; - } - } -#endif - + bp = stack_frame(task, regs); /* * Print function call entries in all stacks, starting at the * current stack address. If the stacks consist of nested @@ -235,7 +225,7 @@ EXPORT_SYMBOL(dump_trace); void show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, - unsigned long *sp, unsigned long bp, char *log_lvl) + unsigned long *sp, char *log_lvl) { unsigned long *irq_stack_end; unsigned long *irq_stack; @@ -279,7 +269,7 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, preempt_enable(); printk(KERN_CONT "\n"); - show_trace_log_lvl(task, regs, sp, bp, log_lvl); + show_trace_log_lvl(task, regs, sp, log_lvl); } void show_registers(struct pt_regs *regs) @@ -308,7 +298,7 @@ void show_registers(struct pt_regs *regs) printk(KERN_EMERG "Stack:\n"); show_stack_log_lvl(NULL, regs, (unsigned long *)sp, - regs->bp, KERN_EMERG); + KERN_EMERG); printk(KERN_EMERG "Code: "); diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 57d1868a86aa..96ed1aac543a 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -91,8 +91,7 @@ void exit_thread(void) void show_regs(struct pt_regs *regs) { show_registers(regs); - show_trace(NULL, regs, (unsigned long *)kernel_stack_pointer(regs), - regs->bp); + show_trace(NULL, regs, (unsigned long *)kernel_stack_pointer(regs)); } void show_regs_common(void) diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c index b53c525368a7..938c8e10a19a 100644 --- a/arch/x86/kernel/stacktrace.c +++ b/arch/x86/kernel/stacktrace.c @@ -73,22 +73,22 @@ static const struct stacktrace_ops save_stack_ops_nosched = { */ void save_stack_trace(struct stack_trace *trace) { - dump_trace(current, NULL, NULL, 0, &save_stack_ops, trace); + dump_trace(current, NULL, NULL, &save_stack_ops, trace); if (trace->nr_entries < trace->max_entries) trace->entries[trace->nr_entries++] = ULONG_MAX; } EXPORT_SYMBOL_GPL(save_stack_trace); -void save_stack_trace_bp(struct stack_trace *trace, unsigned long bp) +void save_stack_trace_regs(struct stack_trace *trace, struct pt_regs *regs) { - dump_trace(current, NULL, NULL, bp, &save_stack_ops, trace); + dump_trace(current, regs, NULL, &save_stack_ops, trace); if (trace->nr_entries < trace->max_entries) trace->entries[trace->nr_entries++] = ULONG_MAX; } void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) { - dump_trace(tsk, NULL, NULL, 0, &save_stack_ops_nosched, trace); + dump_trace(tsk, NULL, NULL, &save_stack_ops_nosched, trace); if (trace->nr_entries < trace->max_entries) trace->entries[trace->nr_entries++] = ULONG_MAX; } diff --git a/arch/x86/mm/kmemcheck/error.c b/arch/x86/mm/kmemcheck/error.c index af3b6c8a436f..704a37cedddb 100644 --- a/arch/x86/mm/kmemcheck/error.c +++ b/arch/x86/mm/kmemcheck/error.c @@ -185,7 +185,7 @@ void kmemcheck_error_save(enum kmemcheck_shadow state, e->trace.entries = e->trace_entries; e->trace.max_entries = ARRAY_SIZE(e->trace_entries); e->trace.skip = 0; - save_stack_trace_bp(&e->trace, regs->bp); + save_stack_trace_regs(&e->trace, regs); /* Round address down to nearest 16 bytes */ shadow_copy = kmemcheck_shadow_lookup(address diff --git a/arch/x86/oprofile/backtrace.c b/arch/x86/oprofile/backtrace.c index 2d49d4e19a36..72cbec14d783 100644 --- a/arch/x86/oprofile/backtrace.c +++ b/arch/x86/oprofile/backtrace.c @@ -126,7 +126,7 @@ x86_backtrace(struct pt_regs * const regs, unsigned int depth) if (!user_mode_vm(regs)) { unsigned long stack = kernel_stack_pointer(regs); if (depth) - dump_trace(NULL, regs, (unsigned long *)stack, 0, + dump_trace(NULL, regs, (unsigned long *)stack, &backtrace_ops, &depth); return; } diff --git a/include/linux/stacktrace.h b/include/linux/stacktrace.h index 51efbef38fb0..25310f1d7f37 100644 --- a/include/linux/stacktrace.h +++ b/include/linux/stacktrace.h @@ -2,6 +2,7 @@ #define __LINUX_STACKTRACE_H struct task_struct; +struct pt_regs; #ifdef CONFIG_STACKTRACE struct task_struct; @@ -13,7 +14,8 @@ struct stack_trace { }; extern void save_stack_trace(struct stack_trace *trace); -extern void save_stack_trace_bp(struct stack_trace *trace, unsigned long bp); +extern void save_stack_trace_regs(struct stack_trace *trace, + struct pt_regs *regs); extern void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace); -- cgit v1.2.3 From 61c32659b12c44e62de32fbf99f7e4ca783dc38b Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 18 Nov 2010 01:39:17 +0100 Subject: tracing: New flag to allow non privileged users to use a trace event This adds a new trace event internal flag that allows them to be used in perf by non privileged users in case of task bound tracing. This is desired for syscalls tracepoint because they don't leak global system informations, like some other tracepoints. Signed-off-by: Frederic Weisbecker Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Thomas Gleixner Cc: Steven Rostedt Cc: Li Zefan Cc: Jason Baron --- include/linux/ftrace_event.h | 2 ++ kernel/perf_event.c | 9 --------- kernel/trace/trace_event_perf.c | 31 ++++++++++++++++++++++++++++++- 3 files changed, 32 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 8beabb958f61..312dce7e0d52 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -154,12 +154,14 @@ enum { TRACE_EVENT_FL_ENABLED_BIT, TRACE_EVENT_FL_FILTERED_BIT, TRACE_EVENT_FL_RECORDED_CMD_BIT, + TRACE_EVENT_FL_CAP_ANY_BIT, }; enum { TRACE_EVENT_FL_ENABLED = (1 << TRACE_EVENT_FL_ENABLED_BIT), TRACE_EVENT_FL_FILTERED = (1 << TRACE_EVENT_FL_FILTERED_BIT), TRACE_EVENT_FL_RECORDED_CMD = (1 << TRACE_EVENT_FL_RECORDED_CMD_BIT), + TRACE_EVENT_FL_CAP_ANY = (1 << TRACE_EVENT_FL_CAP_ANY_BIT), }; struct ftrace_event_call { diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 517d827f4982..ee1e903f983c 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -4747,15 +4747,6 @@ static int perf_tp_event_init(struct perf_event *event) if (event->attr.type != PERF_TYPE_TRACEPOINT) return -ENOENT; - /* - * Raw tracepoint data is a severe data leak, only allow root to - * have these. - */ - if ((event->attr.sample_type & PERF_SAMPLE_RAW) && - perf_paranoid_tracepoint_raw() && - !capable(CAP_SYS_ADMIN)) - return -EPERM; - err = perf_trace_init(event); if (err) return err; diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index 39c059ca670e..19a359d5e6d5 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -21,17 +21,46 @@ typedef typeof(unsigned long [PERF_MAX_TRACE_SIZE / sizeof(unsigned long)]) /* Count the events in use (per event id, not per instance) */ static int total_ref_count; +static int perf_trace_event_perm(struct ftrace_event_call *tp_event, + struct perf_event *p_event) +{ + /* No tracing, just counting, so no obvious leak */ + if (!(p_event->attr.sample_type & PERF_SAMPLE_RAW)) + return 0; + + /* Some events are ok to be traced by non-root users... */ + if (p_event->attach_state == PERF_ATTACH_TASK) { + if (tp_event->flags & TRACE_EVENT_FL_CAP_ANY) + return 0; + } + + /* + * ...otherwise raw tracepoint data can be a severe data leak, + * only allow root to have these. + */ + if (perf_paranoid_tracepoint_raw() && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + return 0; +} + static int perf_trace_event_init(struct ftrace_event_call *tp_event, struct perf_event *p_event) { struct hlist_head __percpu *list; - int ret = -ENOMEM; + int ret; int cpu; + ret = perf_trace_event_perm(tp_event, p_event); + if (ret) + return ret; + p_event->tp_event = tp_event; if (tp_event->perf_refcount++ > 0) return 0; + ret = -ENOMEM; + list = alloc_percpu(struct hlist_head); if (!list) goto fail; -- cgit v1.2.3 From 1ed0c5971159974185653170543a764cc061c857 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 18 Nov 2010 01:46:57 +0100 Subject: tracing: New macro to set up initial event flags value This introduces the new TRACE_EVENT_FLAGS() macro in order to set up initial event flags value. This macro must simply follow the definition of a trace event and take the event name and the flag value as parameters: TRACE_EVENT(my_event, ..... .... ); TRACE_EVENT_FLAGS(my_event, 1) This will set up 1 as the initial my_event->flags value. Signed-off-by: Frederic Weisbecker Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Thomas Gleixner Cc: Steven Rostedt Cc: Li Zefan Cc: Jason Baron --- include/linux/tracepoint.h | 4 ++++ include/trace/ftrace.h | 12 ++++++++++++ 2 files changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index a4a90b6726ce..5a6074fcd81d 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -234,6 +234,8 @@ do_trace: \ PARAMS(void *__data, proto), \ PARAMS(__data, args)) +#define TRACE_EVENT_FLAGS(event, flag) + #endif /* DECLARE_TRACE */ #ifndef TRACE_EVENT @@ -354,4 +356,6 @@ do_trace: \ assign, print, reg, unreg) \ DECLARE_TRACE(name, PARAMS(proto), PARAMS(args)) +#define TRACE_EVENT_FLAGS(event, flag) + #endif /* ifdef TRACE_EVENT (see note above) */ diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h index a9377c0083ad..6f540123d43e 100644 --- a/include/trace/ftrace.h +++ b/include/trace/ftrace.h @@ -82,6 +82,15 @@ TRACE_EVENT(name, PARAMS(proto), PARAMS(args), \ PARAMS(tstruct), PARAMS(assign), PARAMS(print)) \ +#undef TRACE_EVENT_FLAGS +#define TRACE_EVENT_FLAGS(name, value) \ + static int __init trace_init_flags_##name(void) \ + { \ + event_##name.flags = value; \ + return 0; \ + } \ + early_initcall(trace_init_flags_##name); + #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) @@ -129,6 +138,9 @@ #define DEFINE_EVENT_PRINT(template, name, proto, args, print) \ DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args)) +#undef TRACE_EVENT_FLAGS +#define TRACE_EVENT_FLAGS(event, flag) + #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) /* -- cgit v1.2.3 From 53cf810b1934f08a68e131aeeb16267a778f43df Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 18 Nov 2010 02:11:42 +0100 Subject: tracing: Allow syscall trace events for non privileged users As for the raw syscalls events, individual syscall events won't leak system wide information on task bound tracing. Allow non privileged users to use them in such workflow. Signed-off-by: Frederic Weisbecker Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Thomas Gleixner Cc: Steven Rostedt Cc: Li Zefan Cc: Jason Baron --- include/linux/ftrace_event.h | 8 ++++++++ include/linux/syscalls.h | 6 ++++-- include/trace/ftrace.h | 7 +------ 3 files changed, 13 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 312dce7e0d52..725bf6bd39f7 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -198,6 +198,14 @@ struct ftrace_event_call { #endif }; +#define __TRACE_EVENT_FLAGS(name, value) \ + static int __init trace_init_flags_##name(void) \ + { \ + event_##name.flags = value; \ + return 0; \ + } \ + early_initcall(trace_init_flags_##name); + #define PERF_MAX_TRACE_SIZE 2048 #define MAX_FILTER_PRED 32 diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index cacc27a0e285..13b9731d30cf 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -137,7 +137,8 @@ extern struct trace_event_functions exit_syscall_print_funcs; .class = &event_class_syscall_enter, \ .event.funcs = &enter_syscall_print_funcs, \ .data = (void *)&__syscall_meta_##sname,\ - } + }; \ + __TRACE_EVENT_FLAGS(enter_##sname, TRACE_EVENT_FL_CAP_ANY) #define SYSCALL_TRACE_EXIT_EVENT(sname) \ static struct syscall_metadata \ @@ -152,7 +153,8 @@ extern struct trace_event_functions exit_syscall_print_funcs; .class = &event_class_syscall_exit, \ .event.funcs = &exit_syscall_print_funcs, \ .data = (void *)&__syscall_meta_##sname,\ - } + }; \ + __TRACE_EVENT_FLAGS(exit_##sname, TRACE_EVENT_FL_CAP_ANY) #define SYSCALL_METADATA(sname, nb) \ SYSCALL_TRACE_ENTER_EVENT(sname); \ diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h index 6f540123d43e..e718a917d897 100644 --- a/include/trace/ftrace.h +++ b/include/trace/ftrace.h @@ -84,12 +84,7 @@ #undef TRACE_EVENT_FLAGS #define TRACE_EVENT_FLAGS(name, value) \ - static int __init trace_init_flags_##name(void) \ - { \ - event_##name.flags = value; \ - return 0; \ - } \ - early_initcall(trace_init_flags_##name); + __TRACE_EVENT_FLAGS(name, value) #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) -- cgit v1.2.3 From 423478cde453eebdfcfebf4b8d378d8f5d49b853 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 18 Nov 2010 02:21:26 +0100 Subject: tracing: Remove useless syscall ftrace_event_call declaration It is defined right after, which makes the declaration completely useless. Signed-off-by: Frederic Weisbecker Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Thomas Gleixner Cc: Steven Rostedt Cc: Li Zefan Cc: Jason Baron --- include/linux/syscalls.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 13b9731d30cf..18cd0684fc4e 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -127,8 +127,6 @@ extern struct trace_event_functions exit_syscall_print_funcs; #define SYSCALL_TRACE_ENTER_EVENT(sname) \ static struct syscall_metadata \ __attribute__((__aligned__(4))) __syscall_meta_##sname; \ - static struct ftrace_event_call \ - __attribute__((__aligned__(4))) event_enter_##sname; \ static struct ftrace_event_call __used \ __attribute__((__aligned__(4))) \ __attribute__((section("_ftrace_events"))) \ @@ -143,8 +141,6 @@ extern struct trace_event_functions exit_syscall_print_funcs; #define SYSCALL_TRACE_EXIT_EVENT(sname) \ static struct syscall_metadata \ __attribute__((__aligned__(4))) __syscall_meta_##sname; \ - static struct ftrace_event_call \ - __attribute__((__aligned__(4))) event_exit_##sname; \ static struct ftrace_event_call __used \ __attribute__((__aligned__(4))) \ __attribute__((section("_ftrace_events"))) \ -- cgit v1.2.3 From 866f3b25a2eb60d7529c227a0ecd80c3aba443fd Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 18 Nov 2010 09:33:19 -0800 Subject: bonding: IGMP handling cleanup Instead of iterating in_dev->mc_list from bonding driver, its better to call a helper function provided by igmp.c Details of implementation (locking) are private to igmp code. ip_mc_rejoin_group(struct ip_mc_list *im) becomes ip_mc_rejoin_groups(struct in_device *in_dev); Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 8 ++------ include/linux/igmp.h | 2 +- net/ipv4/igmp.c | 32 +++++++++++++++++++------------- 3 files changed, 22 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 518844852f06..e588b2e1c3b3 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -873,15 +873,11 @@ static void bond_mc_del(struct bonding *bond, void *addr) static void __bond_resend_igmp_join_requests(struct net_device *dev) { struct in_device *in_dev; - struct ip_mc_list *im; rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); - if (in_dev) { - for (im = in_dev->mc_list; im; im = im->next) - ip_mc_rejoin_group(im); - } - + if (in_dev) + ip_mc_rejoin_groups(in_dev); rcu_read_unlock(); } diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 7d164670f264..c4987f265109 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -238,7 +238,7 @@ extern void ip_mc_unmap(struct in_device *); extern void ip_mc_remap(struct in_device *); extern void ip_mc_dec_group(struct in_device *in_dev, __be32 addr); extern void ip_mc_inc_group(struct in_device *in_dev, __be32 addr); -extern void ip_mc_rejoin_group(struct ip_mc_list *im); +extern void ip_mc_rejoin_groups(struct in_device *in_dev); #endif #endif diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index afb1e82a59f9..50f6bc1a002a 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -1267,26 +1267,32 @@ EXPORT_SYMBOL(ip_mc_inc_group); /* * Resend IGMP JOIN report; used for bonding. + * Called with rcu_read_lock() */ -void ip_mc_rejoin_group(struct ip_mc_list *im) +void ip_mc_rejoin_groups(struct in_device *in_dev) { #ifdef CONFIG_IP_MULTICAST - struct in_device *in_dev = im->interface; + struct ip_mc_list *im; + int type; - if (im->multiaddr == IGMP_ALL_HOSTS) - return; + for_each_pmc_rcu(in_dev, im) { + if (im->multiaddr == IGMP_ALL_HOSTS) + continue; - /* a failover is happening and switches - * must be notified immediately */ - if (IGMP_V1_SEEN(in_dev)) - igmp_send_report(in_dev, im, IGMP_HOST_MEMBERSHIP_REPORT); - else if (IGMP_V2_SEEN(in_dev)) - igmp_send_report(in_dev, im, IGMPV2_HOST_MEMBERSHIP_REPORT); - else - igmp_send_report(in_dev, im, IGMPV3_HOST_MEMBERSHIP_REPORT); + /* a failover is happening and switches + * must be notified immediately + */ + if (IGMP_V1_SEEN(in_dev)) + type = IGMP_HOST_MEMBERSHIP_REPORT; + else if (IGMP_V2_SEEN(in_dev)) + type = IGMPV2_HOST_MEMBERSHIP_REPORT; + else + type = IGMPV3_HOST_MEMBERSHIP_REPORT; + igmp_send_report(in_dev, im, type); + } #endif } -EXPORT_SYMBOL(ip_mc_rejoin_group); +EXPORT_SYMBOL(ip_mc_rejoin_groups); /* * A socket has left a multicast group on device dev -- cgit v1.2.3 From 4c3710afbc333c33100739dec10662b4ee64e219 Mon Sep 17 00:00:00 2001 From: Changli Gao Date: Tue, 16 Nov 2010 20:28:24 +0000 Subject: net: move definitions of BPF_S_* to net/core/filter.c BPF_S_* are used internally, should not be exposed to the others. Signed-off-by: Changli Gao Acked-by: Eric Dumazet Acked-by: Hagen Paul Pfeifer Signed-off-by: David S. Miller --- include/linux/filter.h | 48 ------------------------------------------------ net/core/filter.c | 48 ++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 48 insertions(+), 48 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 69b43dbea6c6..151f5d703b7e 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -91,54 +91,6 @@ struct sock_fprog { /* Required for SO_ATTACH_FILTER. */ #define BPF_TAX 0x00 #define BPF_TXA 0x80 -enum { - BPF_S_RET_K = 0, - BPF_S_RET_A, - BPF_S_ALU_ADD_K, - BPF_S_ALU_ADD_X, - BPF_S_ALU_SUB_K, - BPF_S_ALU_SUB_X, - BPF_S_ALU_MUL_K, - BPF_S_ALU_MUL_X, - BPF_S_ALU_DIV_X, - BPF_S_ALU_AND_K, - BPF_S_ALU_AND_X, - BPF_S_ALU_OR_K, - BPF_S_ALU_OR_X, - BPF_S_ALU_LSH_K, - BPF_S_ALU_LSH_X, - BPF_S_ALU_RSH_K, - BPF_S_ALU_RSH_X, - BPF_S_ALU_NEG, - BPF_S_LD_W_ABS, - BPF_S_LD_H_ABS, - BPF_S_LD_B_ABS, - BPF_S_LD_W_LEN, - BPF_S_LD_W_IND, - BPF_S_LD_H_IND, - BPF_S_LD_B_IND, - BPF_S_LD_IMM, - BPF_S_LDX_W_LEN, - BPF_S_LDX_B_MSH, - BPF_S_LDX_IMM, - BPF_S_MISC_TAX, - BPF_S_MISC_TXA, - BPF_S_ALU_DIV_K, - BPF_S_LD_MEM, - BPF_S_LDX_MEM, - BPF_S_ST, - BPF_S_STX, - BPF_S_JMP_JA, - BPF_S_JMP_JEQ_K, - BPF_S_JMP_JEQ_X, - BPF_S_JMP_JGE_K, - BPF_S_JMP_JGE_X, - BPF_S_JMP_JGT_K, - BPF_S_JMP_JGT_X, - BPF_S_JMP_JSET_K, - BPF_S_JMP_JSET_X, -}; - #ifndef BPF_MAXINSNS #define BPF_MAXINSNS 4096 #endif diff --git a/net/core/filter.c b/net/core/filter.c index 03dc0710194f..15a545d39cd3 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -38,6 +38,54 @@ #include #include +enum { + BPF_S_RET_K = 0, + BPF_S_RET_A, + BPF_S_ALU_ADD_K, + BPF_S_ALU_ADD_X, + BPF_S_ALU_SUB_K, + BPF_S_ALU_SUB_X, + BPF_S_ALU_MUL_K, + BPF_S_ALU_MUL_X, + BPF_S_ALU_DIV_X, + BPF_S_ALU_AND_K, + BPF_S_ALU_AND_X, + BPF_S_ALU_OR_K, + BPF_S_ALU_OR_X, + BPF_S_ALU_LSH_K, + BPF_S_ALU_LSH_X, + BPF_S_ALU_RSH_K, + BPF_S_ALU_RSH_X, + BPF_S_ALU_NEG, + BPF_S_LD_W_ABS, + BPF_S_LD_H_ABS, + BPF_S_LD_B_ABS, + BPF_S_LD_W_LEN, + BPF_S_LD_W_IND, + BPF_S_LD_H_IND, + BPF_S_LD_B_IND, + BPF_S_LD_IMM, + BPF_S_LDX_W_LEN, + BPF_S_LDX_B_MSH, + BPF_S_LDX_IMM, + BPF_S_MISC_TAX, + BPF_S_MISC_TXA, + BPF_S_ALU_DIV_K, + BPF_S_LD_MEM, + BPF_S_LDX_MEM, + BPF_S_ST, + BPF_S_STX, + BPF_S_JMP_JA, + BPF_S_JMP_JEQ_K, + BPF_S_JMP_JEQ_X, + BPF_S_JMP_JGE_K, + BPF_S_JMP_JGE_X, + BPF_S_JMP_JGT_K, + BPF_S_JMP_JGT_X, + BPF_S_JMP_JSET_K, + BPF_S_JMP_JSET_X, +}; + /* No hurry in this branch */ static void *__load_pointer(struct sk_buff *skb, int k) { -- cgit v1.2.3 From c5485a7e7569ab32eea240c850198519e2a765ef Mon Sep 17 00:00:00 2001 From: Bruno Randolf Date: Tue, 16 Nov 2010 10:58:37 +0900 Subject: lib: Add generic exponentially weighted moving average (EWMA) function This adds generic functions for calculating Exponentially Weighted Moving Averages (EWMA). This implementation makes use of a structure which keeps the EWMA parameters and a scaled up internal representation to reduce rounding errors. The original idea for this implementation came from the rt2x00 driver (rt2x00link.c). I would like to use it in several places in the mac80211 and ath5k code and I hope it can be useful in many other places in the kernel code. Signed-off-by: Bruno Randolf Reviewed-by: KOSAKI Motohiro Signed-off-by: John W. Linville --- include/linux/average.h | 32 +++++++++++++++++++++++++++ lib/Kconfig | 3 +++ lib/Makefile | 2 ++ lib/average.c | 57 +++++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 94 insertions(+) create mode 100644 include/linux/average.h create mode 100644 lib/average.c (limited to 'include/linux') diff --git a/include/linux/average.h b/include/linux/average.h new file mode 100644 index 000000000000..7706e40f95fa --- /dev/null +++ b/include/linux/average.h @@ -0,0 +1,32 @@ +#ifndef _LINUX_AVERAGE_H +#define _LINUX_AVERAGE_H + +#include + +/* Exponentially weighted moving average (EWMA) */ + +/* For more documentation see lib/average.c */ + +struct ewma { + unsigned long internal; + unsigned long factor; + unsigned long weight; +}; + +extern void ewma_init(struct ewma *avg, unsigned long factor, + unsigned long weight); + +extern struct ewma *ewma_add(struct ewma *avg, unsigned long val); + +/** + * ewma_read() - Get average value + * @avg: Average structure + * + * Returns the average value held in @avg. + */ +static inline unsigned long ewma_read(const struct ewma *avg) +{ + return DIV_ROUND_CLOSEST(avg->internal, avg->factor); +} + +#endif /* _LINUX_AVERAGE_H */ diff --git a/lib/Kconfig b/lib/Kconfig index fa9bf2c06199..3116aa631af6 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -210,4 +210,7 @@ config GENERIC_ATOMIC64 config LRU_CACHE tristate +config AVERAGE + bool + endmenu diff --git a/lib/Makefile b/lib/Makefile index e6a3763b8212..76d3b8514903 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -106,6 +106,8 @@ obj-$(CONFIG_GENERIC_ATOMIC64) += atomic64.o obj-$(CONFIG_ATOMIC64_SELFTEST) += atomic64_test.o +obj-$(CONFIG_AVERAGE) += average.o + hostprogs-y := gen_crc32table clean-files := crc32table.h diff --git a/lib/average.c b/lib/average.c new file mode 100644 index 000000000000..f1d1b4660c42 --- /dev/null +++ b/lib/average.c @@ -0,0 +1,57 @@ +/* + * lib/average.c + * + * This source code is licensed under the GNU General Public License, + * Version 2. See the file COPYING for more details. + */ + +#include +#include +#include + +/** + * DOC: Exponentially Weighted Moving Average (EWMA) + * + * These are generic functions for calculating Exponentially Weighted Moving + * Averages (EWMA). We keep a structure with the EWMA parameters and a scaled + * up internal representation of the average value to prevent rounding errors. + * The factor for scaling up and the exponential weight (or decay rate) have to + * be specified thru the init fuction. The structure should not be accessed + * directly but only thru the helper functions. + */ + +/** + * ewma_init() - Initialize EWMA parameters + * @avg: Average structure + * @factor: Factor to use for the scaled up internal value. The maximum value + * of averages can be ULONG_MAX/(factor*weight). + * @weight: Exponential weight, or decay rate. This defines how fast the + * influence of older values decreases. Has to be bigger than 1. + * + * Initialize the EWMA parameters for a given struct ewma @avg. + */ +void ewma_init(struct ewma *avg, unsigned long factor, unsigned long weight) +{ + WARN_ON(weight <= 1 || factor == 0); + avg->internal = 0; + avg->weight = weight; + avg->factor = factor; +} +EXPORT_SYMBOL(ewma_init); + +/** + * ewma_add() - Exponentially weighted moving average (EWMA) + * @avg: Average structure + * @val: Current value + * + * Add a sample to the average. + */ +struct ewma *ewma_add(struct ewma *avg, unsigned long val) +{ + avg->internal = avg->internal ? + (((avg->internal * (avg->weight - 1)) + + (val * avg->factor)) / avg->weight) : + (val * avg->factor); + return avg; +} +EXPORT_SYMBOL(ewma_add); -- cgit v1.2.3 From 86107fd170bc379869250eb7e1bd393a3a70e8ae Mon Sep 17 00:00:00 2001 From: Bruno Randolf Date: Tue, 16 Nov 2010 10:58:48 +0900 Subject: nl80211/mac80211: Report signal average Extend nl80211 to report an exponential weighted moving average (EWMA) of the signal value. Since the signal value usually fluctuates between different packets, an average can be more useful than the value of the last packet. This uses the recently added generic EWMA library function. Signed-off-by: Bruno Randolf Signed-off-by: John W. Linville --- include/linux/nl80211.h | 2 ++ include/net/cfg80211.h | 4 ++++ net/mac80211/Kconfig | 1 + net/mac80211/cfg.c | 3 ++- net/mac80211/rx.c | 1 + net/mac80211/sta_info.c | 2 ++ net/mac80211/sta_info.h | 3 +++ net/wireless/nl80211.c | 3 +++ 8 files changed, 18 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 037b4e498890..1ce3775e9e26 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -1161,6 +1161,7 @@ enum nl80211_rate_info { * @__NL80211_STA_INFO_AFTER_LAST: internal * @NL80211_STA_INFO_MAX: highest possible station info attribute * @NL80211_STA_INFO_SIGNAL: signal strength of last received PPDU (u8, dBm) + * @NL80211_STA_INFO_SIGNAL_AVG: signal strength average (u8, dBm) * @NL80211_STA_INFO_TX_BITRATE: current unicast tx rate, nested attribute * containing info as possible, see &enum nl80211_sta_info_txrate. * @NL80211_STA_INFO_RX_PACKETS: total received packet (u32, from this station) @@ -1178,6 +1179,7 @@ enum nl80211_sta_info { NL80211_STA_INFO_PLID, NL80211_STA_INFO_PLINK_STATE, NL80211_STA_INFO_SIGNAL, + NL80211_STA_INFO_SIGNAL_AVG, NL80211_STA_INFO_TX_BITRATE, NL80211_STA_INFO_RX_PACKETS, NL80211_STA_INFO_TX_PACKETS, diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 8fd9eebd0cc9..69e2364889f1 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -424,6 +424,7 @@ struct station_parameters { * @STATION_INFO_TX_RETRIES: @tx_retries filled * @STATION_INFO_TX_FAILED: @tx_failed filled * @STATION_INFO_RX_DROP_MISC: @rx_dropped_misc filled + * @STATION_INFO_SIGNAL_AVG: @signal_avg filled */ enum station_info_flags { STATION_INFO_INACTIVE_TIME = 1<<0, @@ -439,6 +440,7 @@ enum station_info_flags { STATION_INFO_TX_RETRIES = 1<<10, STATION_INFO_TX_FAILED = 1<<11, STATION_INFO_RX_DROP_MISC = 1<<12, + STATION_INFO_SIGNAL_AVG = 1<<13, }; /** @@ -485,6 +487,7 @@ struct rate_info { * @plid: mesh peer link id * @plink_state: mesh peer link state * @signal: signal strength of last received packet in dBm + * @signal_avg: signal strength average in dBm * @txrate: current unicast bitrate to this station * @rx_packets: packets received from this station * @tx_packets: packets transmitted to this station @@ -505,6 +508,7 @@ struct station_info { u16 plid; u8 plink_state; s8 signal; + s8 signal_avg; struct rate_info txrate; u32 rx_packets; u32 tx_packets; diff --git a/net/mac80211/Kconfig b/net/mac80211/Kconfig index 4d6f8653ec88..798d9b9462e2 100644 --- a/net/mac80211/Kconfig +++ b/net/mac80211/Kconfig @@ -6,6 +6,7 @@ config MAC80211 select CRYPTO_ARC4 select CRYPTO_AES select CRC32 + select AVERAGE ---help--- This option enables the hardware independent IEEE 802.11 networking stack. diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 0c544074479e..92c9cf6a7d1c 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -343,8 +343,9 @@ static void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo) if ((sta->local->hw.flags & IEEE80211_HW_SIGNAL_DBM) || (sta->local->hw.flags & IEEE80211_HW_SIGNAL_UNSPEC)) { - sinfo->filled |= STATION_INFO_SIGNAL; + sinfo->filled |= STATION_INFO_SIGNAL | STATION_INFO_SIGNAL_AVG; sinfo->signal = (s8)sta->last_signal; + sinfo->signal_avg = (s8) -ewma_read(&sta->avg_signal); } sinfo->txrate.flags = 0; diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index d2fcd22ab06d..9dd60a74181f 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -1156,6 +1156,7 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx) sta->rx_fragments++; sta->rx_bytes += rx->skb->len; sta->last_signal = status->signal; + ewma_add(&sta->avg_signal, -status->signal); /* * Change STA power saving mode only at the end of a frame diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index eff58571fd7e..f43fca8907f7 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -244,6 +244,8 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, sta->local = local; sta->sdata = sdata; + ewma_init(&sta->avg_signal, 1000, 8); + if (sta_prepare_rate_control(local, sta, gfp)) { kfree(sta); return NULL; diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 9265acadef32..84062e2c782c 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -13,6 +13,7 @@ #include #include #include +#include #include "key.h" /** @@ -224,6 +225,7 @@ enum plink_state { * @rx_fragments: number of received MPDUs * @rx_dropped: number of dropped MPDUs from this STA * @last_signal: signal of last received frame from this STA + * @avg_signal: moving average of signal of received frames from this STA * @last_seq_ctrl: last received seq/frag number from this STA (per RX queue) * @tx_filtered_count: number of frames the hardware filtered for this STA * @tx_retry_failed: number of frames that failed retry @@ -291,6 +293,7 @@ struct sta_info { unsigned long rx_fragments; unsigned long rx_dropped; int last_signal; + struct ewma avg_signal; __le16 last_seq_ctrl[NUM_RX_DATA_QUEUES]; /* Updated from TX status path only, no locking requirements */ diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 605553842226..d06a40d17002 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -1872,6 +1872,9 @@ static int nl80211_send_station(struct sk_buff *msg, u32 pid, u32 seq, if (sinfo->filled & STATION_INFO_SIGNAL) NLA_PUT_U8(msg, NL80211_STA_INFO_SIGNAL, sinfo->signal); + if (sinfo->filled & STATION_INFO_SIGNAL_AVG) + NLA_PUT_U8(msg, NL80211_STA_INFO_SIGNAL_AVG, + sinfo->signal_avg); if (sinfo->filled & STATION_INFO_TX_BITRATE) { txrate = nla_nest_start(msg, NL80211_STA_INFO_TX_BITRATE); if (!txrate) -- cgit v1.2.3 From 042957801626465492b9428860de39a3cb2a8219 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 12 Nov 2010 22:32:11 -0500 Subject: tracing/events: Show real number in array fields Currently we have in something like the sched_switch event: field:char prev_comm[TASK_COMM_LEN]; offset:12; size:16; signed:1; When a userspace tool such as perf tries to parse this, the TASK_COMM_LEN is meaningless. This is done because the TRACE_EVENT() macro simply uses a #len to show the string of the length. When the length is an enum, we get a string that means nothing for tools. By adding a static buffer and a mutex to protect it, we can store the string into that buffer with snprintf and show the actual number. Now we get: field:char prev_comm[16]; offset:12; size:16; signed:1; Something much more useful. Signed-off-by: Steven Rostedt --- include/linux/ftrace_event.h | 4 ++++ include/trace/ftrace.h | 14 ++++++++++---- kernel/trace/trace_events.c | 6 ++++++ kernel/trace/trace_export.c | 14 ++++++++++---- 4 files changed, 30 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 725bf6bd39f7..47e3997f7b5c 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -225,6 +225,10 @@ enum { FILTER_PTR_STRING, }; +#define EVENT_STORAGE_SIZE 128 +extern struct mutex event_storage_mutex; +extern char event_storage[EVENT_STORAGE_SIZE]; + extern int trace_event_raw_init(struct ftrace_event_call *call); extern int trace_define_field(struct ftrace_event_call *call, const char *type, const char *name, int offset, int size, diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h index e718a917d897..e16610c208c9 100644 --- a/include/trace/ftrace.h +++ b/include/trace/ftrace.h @@ -296,13 +296,19 @@ static struct trace_event_functions ftrace_event_type_funcs_##call = { \ #undef __array #define __array(type, item, len) \ - BUILD_BUG_ON(len > MAX_FILTER_STR_VAL); \ - ret = trace_define_field(event_call, #type "[" #len "]", #item, \ + do { \ + mutex_lock(&event_storage_mutex); \ + BUILD_BUG_ON(len > MAX_FILTER_STR_VAL); \ + snprintf(event_storage, sizeof(event_storage), \ + "%s[%d]", #type, len); \ + ret = trace_define_field(event_call, event_storage, #item, \ offsetof(typeof(field), item), \ sizeof(field.item), \ is_signed_type(type), FILTER_OTHER); \ - if (ret) \ - return ret; + mutex_unlock(&event_storage_mutex); \ + if (ret) \ + return ret; \ + } while (0); #undef __dynamic_array #define __dynamic_array(type, item, len) \ diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 0725eeab1937..35fde09b81de 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -27,6 +27,12 @@ DEFINE_MUTEX(event_mutex); +DEFINE_MUTEX(event_storage_mutex); +EXPORT_SYMBOL_GPL(event_storage_mutex); + +char event_storage[EVENT_STORAGE_SIZE]; +EXPORT_SYMBOL_GPL(event_storage); + LIST_HEAD(ftrace_events); LIST_HEAD(ftrace_common_fields); diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c index 4ba44deaac25..4b74d71705c0 100644 --- a/kernel/trace/trace_export.c +++ b/kernel/trace/trace_export.c @@ -83,13 +83,19 @@ static void __always_unused ____ftrace_check_##name(void) \ #undef __array #define __array(type, item, len) \ - BUILD_BUG_ON(len > MAX_FILTER_STR_VAL); \ - ret = trace_define_field(event_call, #type "[" #len "]", #item, \ + do { \ + BUILD_BUG_ON(len > MAX_FILTER_STR_VAL); \ + mutex_lock(&event_storage_mutex); \ + snprintf(event_storage, sizeof(event_storage), \ + "%s[%d]", #type, len); \ + ret = trace_define_field(event_call, event_storage, #item, \ offsetof(typeof(field), item), \ sizeof(field.item), \ is_signed_type(type), FILTER_OTHER); \ - if (ret) \ - return ret; + mutex_unlock(&event_storage_mutex); \ + if (ret) \ + return ret; \ + } while (0); #undef __array_desc #define __array_desc(type, container, item, len) \ -- cgit v1.2.3 From 93aaae2e01e57483256b7da05c9a7ebd65ad4686 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 19 Nov 2010 09:49:59 -0800 Subject: filter: optimize sk_run_filter Remove pc variable to avoid arithmetic to compute fentry at each filter instruction. Jumps directly manipulate fentry pointer. As the last instruction of filter[] is guaranteed to be a RETURN, and all jumps are before the last instruction, we dont need to check filter bounds (number of instructions in filter array) at each iteration, so we remove it from sk_run_filter() params. On x86_32 remove f_k var introduced in commit 57fe93b374a6b871 (filter: make sure filters dont read uninitialized memory) Note : We could use a CONFIG_ARCH_HAS_{FEW|MANY}_REGISTERS in order to avoid too many ifdefs in this code. This helps compiler to use cpu registers to hold fentry and A accumulator. On x86_32, this saves 401 bytes, and more important, sk_run_filter() runs much faster because less register pressure (One less conditional branch per BPF instruction) # size net/core/filter.o net/core/filter_pre.o text data bss dec hex filename 2948 0 0 2948 b84 net/core/filter.o 3349 0 0 3349 d15 net/core/filter_pre.o on x86_64 : # size net/core/filter.o net/core/filter_pre.o text data bss dec hex filename 5173 0 0 5173 1435 net/core/filter.o 5224 0 0 5224 1468 net/core/filter_pre.o Signed-off-by: Eric Dumazet Acked-by: Changli Gao Signed-off-by: David S. Miller --- drivers/isdn/i4l/isdn_ppp.c | 14 +++---- drivers/net/ppp_generic.c | 12 ++---- include/linux/filter.h | 2 +- net/core/filter.c | 93 +++++++++++++++++++++++---------------------- net/core/timestamping.c | 2 +- net/packet/af_packet.c | 2 +- 6 files changed, 61 insertions(+), 64 deletions(-) (limited to 'include/linux') diff --git a/drivers/isdn/i4l/isdn_ppp.c b/drivers/isdn/i4l/isdn_ppp.c index 97c5cc2997f5..9e8162c80bb0 100644 --- a/drivers/isdn/i4l/isdn_ppp.c +++ b/drivers/isdn/i4l/isdn_ppp.c @@ -1147,15 +1147,14 @@ isdn_ppp_push_higher(isdn_net_dev * net_dev, isdn_net_local * lp, struct sk_buff } if (is->pass_filter - && sk_run_filter(skb, is->pass_filter, is->pass_len) == 0) { + && sk_run_filter(skb, is->pass_filter) == 0) { if (is->debug & 0x2) printk(KERN_DEBUG "IPPP: inbound frame filtered.\n"); kfree_skb(skb); return; } if (!(is->active_filter - && sk_run_filter(skb, is->active_filter, - is->active_len) == 0)) { + && sk_run_filter(skb, is->active_filter) == 0)) { if (is->debug & 0x2) printk(KERN_DEBUG "IPPP: link-active filter: reseting huptimer.\n"); lp->huptimer = 0; @@ -1294,15 +1293,14 @@ isdn_ppp_xmit(struct sk_buff *skb, struct net_device *netdev) } if (ipt->pass_filter - && sk_run_filter(skb, ipt->pass_filter, ipt->pass_len) == 0) { + && sk_run_filter(skb, ipt->pass_filter) == 0) { if (ipt->debug & 0x4) printk(KERN_DEBUG "IPPP: outbound frame filtered.\n"); kfree_skb(skb); goto unlock; } if (!(ipt->active_filter - && sk_run_filter(skb, ipt->active_filter, - ipt->active_len) == 0)) { + && sk_run_filter(skb, ipt->active_filter) == 0)) { if (ipt->debug & 0x4) printk(KERN_DEBUG "IPPP: link-active filter: reseting huptimer.\n"); lp->huptimer = 0; @@ -1492,9 +1490,9 @@ int isdn_ppp_autodial_filter(struct sk_buff *skb, isdn_net_local *lp) } drop |= is->pass_filter - && sk_run_filter(skb, is->pass_filter, is->pass_len) == 0; + && sk_run_filter(skb, is->pass_filter) == 0; drop |= is->active_filter - && sk_run_filter(skb, is->active_filter, is->active_len) == 0; + && sk_run_filter(skb, is->active_filter) == 0; skb_push(skb, IPPP_MAX_HEADER - 4); return drop; diff --git a/drivers/net/ppp_generic.c b/drivers/net/ppp_generic.c index 09cf56d0416a..0c91598ae280 100644 --- a/drivers/net/ppp_generic.c +++ b/drivers/net/ppp_generic.c @@ -1136,8 +1136,7 @@ ppp_send_frame(struct ppp *ppp, struct sk_buff *skb) a four-byte PPP header on each packet */ *skb_push(skb, 2) = 1; if (ppp->pass_filter && - sk_run_filter(skb, ppp->pass_filter, - ppp->pass_len) == 0) { + sk_run_filter(skb, ppp->pass_filter) == 0) { if (ppp->debug & 1) printk(KERN_DEBUG "PPP: outbound frame not passed\n"); kfree_skb(skb); @@ -1145,8 +1144,7 @@ ppp_send_frame(struct ppp *ppp, struct sk_buff *skb) } /* if this packet passes the active filter, record the time */ if (!(ppp->active_filter && - sk_run_filter(skb, ppp->active_filter, - ppp->active_len) == 0)) + sk_run_filter(skb, ppp->active_filter) == 0)) ppp->last_xmit = jiffies; skb_pull(skb, 2); #else @@ -1758,8 +1756,7 @@ ppp_receive_nonmp_frame(struct ppp *ppp, struct sk_buff *skb) *skb_push(skb, 2) = 0; if (ppp->pass_filter && - sk_run_filter(skb, ppp->pass_filter, - ppp->pass_len) == 0) { + sk_run_filter(skb, ppp->pass_filter) == 0) { if (ppp->debug & 1) printk(KERN_DEBUG "PPP: inbound frame " "not passed\n"); @@ -1767,8 +1764,7 @@ ppp_receive_nonmp_frame(struct ppp *ppp, struct sk_buff *skb) return; } if (!(ppp->active_filter && - sk_run_filter(skb, ppp->active_filter, - ppp->active_len) == 0)) + sk_run_filter(skb, ppp->active_filter) == 0)) ppp->last_recv = jiffies; __skb_pull(skb, 2); } else diff --git a/include/linux/filter.h b/include/linux/filter.h index 151f5d703b7e..447a775878fb 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -147,7 +147,7 @@ struct sock; extern int sk_filter(struct sock *sk, struct sk_buff *skb); extern unsigned int sk_run_filter(struct sk_buff *skb, - struct sock_filter *filter, int flen); + const struct sock_filter *filter); extern int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk); extern int sk_detach_filter(struct sock *sk); extern int sk_chk_filter(struct sock_filter *filter, int flen); diff --git a/net/core/filter.c b/net/core/filter.c index 15a545d39cd3..9e77b3c816c5 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -137,7 +137,7 @@ int sk_filter(struct sock *sk, struct sk_buff *skb) rcu_read_lock_bh(); filter = rcu_dereference_bh(sk->sk_filter); if (filter) { - unsigned int pkt_len = sk_run_filter(skb, filter->insns, filter->len); + unsigned int pkt_len = sk_run_filter(skb, filter->insns); err = pkt_len ? pskb_trim(skb, pkt_len) : -EPERM; } @@ -151,14 +151,15 @@ EXPORT_SYMBOL(sk_filter); * sk_run_filter - run a filter on a socket * @skb: buffer to run the filter on * @filter: filter to apply - * @flen: length of filter * * Decode and apply filter instructions to the skb->data. - * Return length to keep, 0 for none. skb is the data we are - * filtering, filter is the array of filter instructions, and - * len is the number of filter blocks in the array. + * Return length to keep, 0 for none. @skb is the data we are + * filtering, @filter is the array of filter instructions. + * Because all jumps are guaranteed to be before last instruction, + * and last instruction guaranteed to be a RET, we dont need to check + * flen. (We used to pass to this function the length of filter) */ -unsigned int sk_run_filter(struct sk_buff *skb, struct sock_filter *filter, int flen) +unsigned int sk_run_filter(struct sk_buff *skb, const struct sock_filter *fentry) { void *ptr; u32 A = 0; /* Accumulator */ @@ -167,34 +168,36 @@ unsigned int sk_run_filter(struct sk_buff *skb, struct sock_filter *filter, int unsigned long memvalid = 0; u32 tmp; int k; - int pc; BUILD_BUG_ON(BPF_MEMWORDS > BITS_PER_LONG); /* * Process array of filter instructions. */ - for (pc = 0; pc < flen; pc++) { - const struct sock_filter *fentry = &filter[pc]; - u32 f_k = fentry->k; + for (;; fentry++) { +#if defined(CONFIG_X86_32) +#define K (fentry->k) +#else + const u32 K = fentry->k; +#endif switch (fentry->code) { case BPF_S_ALU_ADD_X: A += X; continue; case BPF_S_ALU_ADD_K: - A += f_k; + A += K; continue; case BPF_S_ALU_SUB_X: A -= X; continue; case BPF_S_ALU_SUB_K: - A -= f_k; + A -= K; continue; case BPF_S_ALU_MUL_X: A *= X; continue; case BPF_S_ALU_MUL_K: - A *= f_k; + A *= K; continue; case BPF_S_ALU_DIV_X: if (X == 0) @@ -202,64 +205,64 @@ unsigned int sk_run_filter(struct sk_buff *skb, struct sock_filter *filter, int A /= X; continue; case BPF_S_ALU_DIV_K: - A /= f_k; + A /= K; continue; case BPF_S_ALU_AND_X: A &= X; continue; case BPF_S_ALU_AND_K: - A &= f_k; + A &= K; continue; case BPF_S_ALU_OR_X: A |= X; continue; case BPF_S_ALU_OR_K: - A |= f_k; + A |= K; continue; case BPF_S_ALU_LSH_X: A <<= X; continue; case BPF_S_ALU_LSH_K: - A <<= f_k; + A <<= K; continue; case BPF_S_ALU_RSH_X: A >>= X; continue; case BPF_S_ALU_RSH_K: - A >>= f_k; + A >>= K; continue; case BPF_S_ALU_NEG: A = -A; continue; case BPF_S_JMP_JA: - pc += f_k; + fentry += K; continue; case BPF_S_JMP_JGT_K: - pc += (A > f_k) ? fentry->jt : fentry->jf; + fentry += (A > K) ? fentry->jt : fentry->jf; continue; case BPF_S_JMP_JGE_K: - pc += (A >= f_k) ? fentry->jt : fentry->jf; + fentry += (A >= K) ? fentry->jt : fentry->jf; continue; case BPF_S_JMP_JEQ_K: - pc += (A == f_k) ? fentry->jt : fentry->jf; + fentry += (A == K) ? fentry->jt : fentry->jf; continue; case BPF_S_JMP_JSET_K: - pc += (A & f_k) ? fentry->jt : fentry->jf; + fentry += (A & K) ? fentry->jt : fentry->jf; continue; case BPF_S_JMP_JGT_X: - pc += (A > X) ? fentry->jt : fentry->jf; + fentry += (A > X) ? fentry->jt : fentry->jf; continue; case BPF_S_JMP_JGE_X: - pc += (A >= X) ? fentry->jt : fentry->jf; + fentry += (A >= X) ? fentry->jt : fentry->jf; continue; case BPF_S_JMP_JEQ_X: - pc += (A == X) ? fentry->jt : fentry->jf; + fentry += (A == X) ? fentry->jt : fentry->jf; continue; case BPF_S_JMP_JSET_X: - pc += (A & X) ? fentry->jt : fentry->jf; + fentry += (A & X) ? fentry->jt : fentry->jf; continue; case BPF_S_LD_W_ABS: - k = f_k; + k = K; load_w: ptr = load_pointer(skb, k, 4, &tmp); if (ptr != NULL) { @@ -268,7 +271,7 @@ load_w: } break; case BPF_S_LD_H_ABS: - k = f_k; + k = K; load_h: ptr = load_pointer(skb, k, 2, &tmp); if (ptr != NULL) { @@ -277,7 +280,7 @@ load_h: } break; case BPF_S_LD_B_ABS: - k = f_k; + k = K; load_b: ptr = load_pointer(skb, k, 1, &tmp); if (ptr != NULL) { @@ -292,34 +295,34 @@ load_b: X = skb->len; continue; case BPF_S_LD_W_IND: - k = X + f_k; + k = X + K; goto load_w; case BPF_S_LD_H_IND: - k = X + f_k; + k = X + K; goto load_h; case BPF_S_LD_B_IND: - k = X + f_k; + k = X + K; goto load_b; case BPF_S_LDX_B_MSH: - ptr = load_pointer(skb, f_k, 1, &tmp); + ptr = load_pointer(skb, K, 1, &tmp); if (ptr != NULL) { X = (*(u8 *)ptr & 0xf) << 2; continue; } return 0; case BPF_S_LD_IMM: - A = f_k; + A = K; continue; case BPF_S_LDX_IMM: - X = f_k; + X = K; continue; case BPF_S_LD_MEM: - A = (memvalid & (1UL << f_k)) ? - mem[f_k] : 0; + A = (memvalid & (1UL << K)) ? + mem[K] : 0; continue; case BPF_S_LDX_MEM: - X = (memvalid & (1UL << f_k)) ? - mem[f_k] : 0; + X = (memvalid & (1UL << K)) ? + mem[K] : 0; continue; case BPF_S_MISC_TAX: X = A; @@ -328,16 +331,16 @@ load_b: A = X; continue; case BPF_S_RET_K: - return f_k; + return K; case BPF_S_RET_A: return A; case BPF_S_ST: - memvalid |= 1UL << f_k; - mem[f_k] = A; + memvalid |= 1UL << K; + mem[K] = A; continue; case BPF_S_STX: - memvalid |= 1UL << f_k; - mem[f_k] = X; + memvalid |= 1UL << K; + mem[K] = X; continue; default: WARN_ON(1); diff --git a/net/core/timestamping.c b/net/core/timestamping.c index 0ae6c22da85b..dac7ed687f60 100644 --- a/net/core/timestamping.c +++ b/net/core/timestamping.c @@ -31,7 +31,7 @@ static unsigned int classify(struct sk_buff *skb) if (likely(skb->dev && skb->dev->phydev && skb->dev->phydev->drv)) - return sk_run_filter(skb, ptp_filter, ARRAY_SIZE(ptp_filter)); + return sk_run_filter(skb, ptp_filter); else return PTP_CLASS_NONE; } diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 20964560a0ed..b6372dd128d7 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -519,7 +519,7 @@ static inline unsigned int run_filter(struct sk_buff *skb, struct sock *sk, rcu_read_lock_bh(); filter = rcu_dereference_bh(sk->sk_filter); if (filter != NULL) - res = sk_run_filter(skb, filter->insns, filter->len); + res = sk_run_filter(skb, filter->insns); rcu_read_unlock_bh(); return res; -- cgit v1.2.3 From eb06acdc85585f28864261f28659157848762ee4 Mon Sep 17 00:00:00 2001 From: Sridhar Samudrala Date: Thu, 28 Oct 2010 13:10:50 +0000 Subject: macvlan: Introduce 'passthru' mode to takeover the underlying device With the current default 'vepa' mode, a KVM guest using virtio with macvtap backend has the following limitations. - cannot change/add a mac address on the guest virtio-net - cannot create a vlan device on the guest virtio-net - cannot enable promiscuous mode on guest virtio-net To address these limitations, this patch introduces a new mode called 'passthru' when creating a macvlan device which allows takeover of the underlying device and passing it to a guest using virtio with macvtap backend. Only one macvlan device is allowed in passthru mode and it inherits the mac address from the underlying device and sets it in promiscuous mode to receive and forward all the packets. Signed-off-by: Sridhar Samudrala ------------------------------------------------------------------------- Signed-off-by: David S. Miller --- drivers/net/macvlan.c | 33 ++++++++++++++++++++++++++++++++- include/linux/if_link.h | 1 + 2 files changed, 33 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 93f0ba25c808..6ed577b065df 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -38,6 +38,7 @@ struct macvlan_port { struct hlist_head vlan_hash[MACVLAN_HASH_SIZE]; struct list_head vlans; struct rcu_head rcu; + bool passthru; }; #define macvlan_port_get_rcu(dev) \ @@ -169,6 +170,7 @@ static struct sk_buff *macvlan_handle_frame(struct sk_buff *skb) macvlan_broadcast(skb, port, NULL, MACVLAN_MODE_PRIVATE | MACVLAN_MODE_VEPA | + MACVLAN_MODE_PASSTHRU| MACVLAN_MODE_BRIDGE); else if (src->mode == MACVLAN_MODE_VEPA) /* flood to everyone except source */ @@ -185,7 +187,10 @@ static struct sk_buff *macvlan_handle_frame(struct sk_buff *skb) return skb; } - vlan = macvlan_hash_lookup(port, eth->h_dest); + if (port->passthru) + vlan = list_first_entry(&port->vlans, struct macvlan_dev, list); + else + vlan = macvlan_hash_lookup(port, eth->h_dest); if (vlan == NULL) return skb; @@ -288,6 +293,11 @@ static int macvlan_open(struct net_device *dev) struct net_device *lowerdev = vlan->lowerdev; int err; + if (vlan->port->passthru) { + dev_set_promiscuity(lowerdev, 1); + goto hash_add; + } + err = -EBUSY; if (macvlan_addr_busy(vlan->port, dev->dev_addr)) goto out; @@ -300,6 +310,8 @@ static int macvlan_open(struct net_device *dev) if (err < 0) goto del_unicast; } + +hash_add: macvlan_hash_add(vlan); return 0; @@ -314,12 +326,18 @@ static int macvlan_stop(struct net_device *dev) struct macvlan_dev *vlan = netdev_priv(dev); struct net_device *lowerdev = vlan->lowerdev; + if (vlan->port->passthru) { + dev_set_promiscuity(lowerdev, -1); + goto hash_del; + } + dev_mc_unsync(lowerdev, dev); if (dev->flags & IFF_ALLMULTI) dev_set_allmulti(lowerdev, -1); dev_uc_del(lowerdev, dev->dev_addr); +hash_del: macvlan_hash_del(vlan); return 0; } @@ -559,6 +577,7 @@ static int macvlan_port_create(struct net_device *dev) if (port == NULL) return -ENOMEM; + port->passthru = false; port->dev = dev; INIT_LIST_HEAD(&port->vlans); for (i = 0; i < MACVLAN_HASH_SIZE; i++) @@ -603,6 +622,7 @@ static int macvlan_validate(struct nlattr *tb[], struct nlattr *data[]) case MACVLAN_MODE_PRIVATE: case MACVLAN_MODE_VEPA: case MACVLAN_MODE_BRIDGE: + case MACVLAN_MODE_PASSTHRU: break; default: return -EINVAL; @@ -652,6 +672,10 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev, } port = macvlan_port_get(lowerdev); + /* Only 1 macvlan device can be created in passthru mode */ + if (port->passthru) + return -EINVAL; + vlan->lowerdev = lowerdev; vlan->dev = dev; vlan->port = port; @@ -662,6 +686,13 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev, if (data && data[IFLA_MACVLAN_MODE]) vlan->mode = nla_get_u32(data[IFLA_MACVLAN_MODE]); + if (vlan->mode == MACVLAN_MODE_PASSTHRU) { + if (!list_empty(&port->vlans)) + return -EINVAL; + port->passthru = true; + memcpy(dev->dev_addr, lowerdev->dev_addr, ETH_ALEN); + } + err = register_netdevice(dev); if (err < 0) goto destroy_port; diff --git a/include/linux/if_link.h b/include/linux/if_link.h index 2e02e4d7b11e..6485d2a89bec 100644 --- a/include/linux/if_link.h +++ b/include/linux/if_link.h @@ -259,6 +259,7 @@ enum macvlan_mode { MACVLAN_MODE_PRIVATE = 1, /* don't talk to other macvlans */ MACVLAN_MODE_VEPA = 2, /* talk to other ports through ext bridge */ MACVLAN_MODE_BRIDGE = 4, /* talk to bridge ports directly */ + MACVLAN_MODE_PASSTHRU = 8,/* take over the underlying device */ }; /* SR-IOV virtual function management section */ -- cgit v1.2.3 From 293bb1c41b728d4aa248fe8a0acd2b9066ff5c34 Mon Sep 17 00:00:00 2001 From: Giuseppe CAVALLARO Date: Wed, 24 Nov 2010 02:38:05 +0000 Subject: stmmac: add init/exit callback in plat_stmmacenet_data struct This patch adds in the plat_stmmacenet_data the init and exit callbacks that can be used for invoking specific platform functions. For example, on ST targets, these call the PAD manager functions to set PIO lines and syscfg registers. The patch removes the stmmac_claim_resource only used on STM Kernels as well. Signed-off-by: Giuseppe Cavallaro Signed-off-by: David S. Miller --- drivers/net/stmmac/stmmac.h | 22 ---------------------- drivers/net/stmmac/stmmac_main.c | 18 +++++++++++++----- include/linux/stmmac.h | 6 +++--- 3 files changed, 16 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/stmmac/stmmac.h b/drivers/net/stmmac/stmmac.h index 31575670d862..8ae76501eb74 100644 --- a/drivers/net/stmmac/stmmac.h +++ b/drivers/net/stmmac/stmmac.h @@ -87,28 +87,6 @@ struct stmmac_priv { struct plat_stmmacenet_data *plat; }; -#ifdef CONFIG_STM_DRIVERS -#include -static inline int stmmac_claim_resource(struct platform_device *pdev) -{ - int ret = 0; - struct plat_stmmacenet_data *plat_dat = pdev->dev.platform_data; - - /* Pad routing setup */ - if (IS_ERR(devm_stm_pad_claim(&pdev->dev, plat_dat->pad_config, - dev_name(&pdev->dev)))) { - printk(KERN_ERR "%s: Failed to request pads!\n", __func__); - ret = -ENODEV; - } - return ret; -} -#else -static inline int stmmac_claim_resource(struct platform_device *pdev) -{ - return 0; -} -#endif - extern int stmmac_mdio_unregister(struct net_device *ndev); extern int stmmac_mdio_register(struct net_device *ndev); extern void stmmac_set_ethtool_ops(struct net_device *netdev); diff --git a/drivers/net/stmmac/stmmac_main.c b/drivers/net/stmmac/stmmac_main.c index 29ba28660fa9..b806cd3515b4 100644 --- a/drivers/net/stmmac/stmmac_main.c +++ b/drivers/net/stmmac/stmmac_main.c @@ -1643,7 +1643,7 @@ static int stmmac_dvr_probe(struct platform_device *pdev) struct resource *res; void __iomem *addr = NULL; struct net_device *ndev = NULL; - struct stmmac_priv *priv; + struct stmmac_priv *priv = NULL; struct plat_stmmacenet_data *plat_dat; pr_info("STMMAC driver:\n\tplatform registration... "); @@ -1708,10 +1708,12 @@ static int stmmac_dvr_probe(struct platform_device *pdev) /* Set the I/O base addr */ ndev->base_addr = (unsigned long)addr; - /* Verify embedded resource for the platform */ - ret = stmmac_claim_resource(pdev); - if (ret < 0) - goto out; + /* Custom initialisation */ + if (priv->plat->init) { + ret = priv->plat->init(pdev); + if (unlikely(ret)) + goto out; + } /* MAC HW revice detection */ ret = stmmac_mac_device_setup(ndev); @@ -1745,6 +1747,9 @@ static int stmmac_dvr_probe(struct platform_device *pdev) out: if (ret < 0) { + if (priv->plat->exit) + priv->plat->exit(pdev); + platform_set_drvdata(pdev, NULL); release_mem_region(res->start, resource_size(res)); if (addr != NULL) @@ -1778,6 +1783,9 @@ static int stmmac_dvr_remove(struct platform_device *pdev) stmmac_mdio_unregister(ndev); + if (priv->plat->exit) + priv->plat->exit(pdev); + platform_set_drvdata(pdev, NULL); unregister_netdev(ndev); diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index d66c61774d95..e10352915698 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -40,9 +40,9 @@ struct plat_stmmacenet_data { int pmt; void (*fix_mac_speed)(void *priv, unsigned int speed); void (*bus_setup)(void __iomem *ioaddr); -#ifdef CONFIG_STM_DRIVERS - struct stm_pad_config *pad_config; -#endif + int (*init)(struct platform_device *pdev); + void (*exit)(struct platform_device *pdev); + void *custom_cfg; void *bsp_priv; }; -- cgit v1.2.3 From 456b61bca8ee324ab6c18b065e632c9a8c88aa39 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 23 Nov 2010 13:12:15 +0000 Subject: ipv6: mcast: RCU conversion ipv6_sk_mc_lock rwlock becomes a spinlock. readers (inet6_mc_check()) now takes rcu_read_lock() instead of read lock. Writers dont need to disable BH anymore. struct ipv6_mc_socklist objects are reclaimed after one RCU grace period. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/ipv6.h | 2 +- include/net/if_inet6.h | 3 +- net/ipv6/mcast.c | 75 +++++++++++++++++++++++++++++--------------------- 3 files changed, 47 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 8e429d0e0405..0c997767429a 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -364,7 +364,7 @@ struct ipv6_pinfo { __u32 dst_cookie; - struct ipv6_mc_socklist *ipv6_mc_list; + struct ipv6_mc_socklist __rcu *ipv6_mc_list; struct ipv6_ac_socklist *ipv6_ac_list; struct ipv6_fl_socklist *ipv6_fl_list; diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h index f95ff8d9aa47..04977eefb0ee 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -89,10 +89,11 @@ struct ip6_sf_socklist { struct ipv6_mc_socklist { struct in6_addr addr; int ifindex; - struct ipv6_mc_socklist *next; + struct ipv6_mc_socklist __rcu *next; rwlock_t sflock; unsigned int sfmode; /* MCAST_{INCLUDE,EXCLUDE} */ struct ip6_sf_socklist *sflist; + struct rcu_head rcu; }; struct ip6_sf_list { diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 9c5074528a71..49f986d626a0 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -82,7 +82,7 @@ static void *__mld2_query_bugs[] __attribute__((__unused__)) = { static struct in6_addr mld2_all_mcr = MLD2_ALL_MCR_INIT; /* Big mc list lock for all the sockets */ -static DEFINE_RWLOCK(ipv6_sk_mc_lock); +static DEFINE_SPINLOCK(ipv6_sk_mc_lock); static void igmp6_join_group(struct ifmcaddr6 *ma); static void igmp6_leave_group(struct ifmcaddr6 *ma); @@ -123,6 +123,11 @@ int sysctl_mld_max_msf __read_mostly = IPV6_MLD_MAX_MSF; * socket join on multicast group */ +#define for_each_pmc_rcu(np, pmc) \ + for (pmc = rcu_dereference(np->ipv6_mc_list); \ + pmc != NULL; \ + pmc = rcu_dereference(pmc->next)) + int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) { struct net_device *dev = NULL; @@ -134,15 +139,15 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) if (!ipv6_addr_is_multicast(addr)) return -EINVAL; - read_lock_bh(&ipv6_sk_mc_lock); - for (mc_lst=np->ipv6_mc_list; mc_lst; mc_lst=mc_lst->next) { + rcu_read_lock(); + for_each_pmc_rcu(np, mc_lst) { if ((ifindex == 0 || mc_lst->ifindex == ifindex) && ipv6_addr_equal(&mc_lst->addr, addr)) { - read_unlock_bh(&ipv6_sk_mc_lock); + rcu_read_unlock(); return -EADDRINUSE; } } - read_unlock_bh(&ipv6_sk_mc_lock); + rcu_read_unlock(); mc_lst = sock_kmalloc(sk, sizeof(struct ipv6_mc_socklist), GFP_KERNEL); @@ -186,33 +191,41 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) return err; } - write_lock_bh(&ipv6_sk_mc_lock); + spin_lock(&ipv6_sk_mc_lock); mc_lst->next = np->ipv6_mc_list; - np->ipv6_mc_list = mc_lst; - write_unlock_bh(&ipv6_sk_mc_lock); + rcu_assign_pointer(np->ipv6_mc_list, mc_lst); + spin_unlock(&ipv6_sk_mc_lock); rcu_read_unlock(); return 0; } +static void ipv6_mc_socklist_reclaim(struct rcu_head *head) +{ + kfree(container_of(head, struct ipv6_mc_socklist, rcu)); +} /* * socket leave on multicast group */ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) { struct ipv6_pinfo *np = inet6_sk(sk); - struct ipv6_mc_socklist *mc_lst, **lnk; + struct ipv6_mc_socklist *mc_lst; + struct ipv6_mc_socklist __rcu **lnk; struct net *net = sock_net(sk); - write_lock_bh(&ipv6_sk_mc_lock); - for (lnk = &np->ipv6_mc_list; (mc_lst = *lnk) !=NULL ; lnk = &mc_lst->next) { + spin_lock(&ipv6_sk_mc_lock); + for (lnk = &np->ipv6_mc_list; + (mc_lst = rcu_dereference_protected(*lnk, + lockdep_is_held(&ipv6_sk_mc_lock))) !=NULL ; + lnk = &mc_lst->next) { if ((ifindex == 0 || mc_lst->ifindex == ifindex) && ipv6_addr_equal(&mc_lst->addr, addr)) { struct net_device *dev; *lnk = mc_lst->next; - write_unlock_bh(&ipv6_sk_mc_lock); + spin_unlock(&ipv6_sk_mc_lock); rcu_read_lock(); dev = dev_get_by_index_rcu(net, mc_lst->ifindex); @@ -225,11 +238,12 @@ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) } else (void) ip6_mc_leave_src(sk, mc_lst, NULL); rcu_read_unlock(); - sock_kfree_s(sk, mc_lst, sizeof(*mc_lst)); + atomic_sub(sizeof(*mc_lst), &sk->sk_omem_alloc); + call_rcu(&mc_lst->rcu, ipv6_mc_socklist_reclaim); return 0; } } - write_unlock_bh(&ipv6_sk_mc_lock); + spin_unlock(&ipv6_sk_mc_lock); return -EADDRNOTAVAIL; } @@ -272,12 +286,13 @@ void ipv6_sock_mc_close(struct sock *sk) struct ipv6_mc_socklist *mc_lst; struct net *net = sock_net(sk); - write_lock_bh(&ipv6_sk_mc_lock); - while ((mc_lst = np->ipv6_mc_list) != NULL) { + spin_lock(&ipv6_sk_mc_lock); + while ((mc_lst = rcu_dereference_protected(np->ipv6_mc_list, + lockdep_is_held(&ipv6_sk_mc_lock))) != NULL) { struct net_device *dev; np->ipv6_mc_list = mc_lst->next; - write_unlock_bh(&ipv6_sk_mc_lock); + spin_unlock(&ipv6_sk_mc_lock); rcu_read_lock(); dev = dev_get_by_index_rcu(net, mc_lst->ifindex); @@ -290,11 +305,13 @@ void ipv6_sock_mc_close(struct sock *sk) } else (void) ip6_mc_leave_src(sk, mc_lst, NULL); rcu_read_unlock(); - sock_kfree_s(sk, mc_lst, sizeof(*mc_lst)); - write_lock_bh(&ipv6_sk_mc_lock); + atomic_sub(sizeof(*mc_lst), &sk->sk_omem_alloc); + call_rcu(&mc_lst->rcu, ipv6_mc_socklist_reclaim); + + spin_lock(&ipv6_sk_mc_lock); } - write_unlock_bh(&ipv6_sk_mc_lock); + spin_unlock(&ipv6_sk_mc_lock); } int ip6_mc_source(int add, int omode, struct sock *sk, @@ -328,8 +345,7 @@ int ip6_mc_source(int add, int omode, struct sock *sk, err = -EADDRNOTAVAIL; - read_lock(&ipv6_sk_mc_lock); - for (pmc=inet6->ipv6_mc_list; pmc; pmc=pmc->next) { + for_each_pmc_rcu(inet6, pmc) { if (pgsr->gsr_interface && pmc->ifindex != pgsr->gsr_interface) continue; if (ipv6_addr_equal(&pmc->addr, group)) @@ -428,7 +444,6 @@ int ip6_mc_source(int add, int omode, struct sock *sk, done: if (pmclocked) write_unlock(&pmc->sflock); - read_unlock(&ipv6_sk_mc_lock); read_unlock_bh(&idev->lock); rcu_read_unlock(); if (leavegroup) @@ -466,14 +481,13 @@ int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf) dev = idev->dev; err = 0; - read_lock(&ipv6_sk_mc_lock); if (gsf->gf_fmode == MCAST_INCLUDE && gsf->gf_numsrc == 0) { leavegroup = 1; goto done; } - for (pmc=inet6->ipv6_mc_list; pmc; pmc=pmc->next) { + for_each_pmc_rcu(inet6, pmc) { if (pmc->ifindex != gsf->gf_interface) continue; if (ipv6_addr_equal(&pmc->addr, group)) @@ -521,7 +535,6 @@ int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf) write_unlock(&pmc->sflock); err = 0; done: - read_unlock(&ipv6_sk_mc_lock); read_unlock_bh(&idev->lock); rcu_read_unlock(); if (leavegroup) @@ -562,7 +575,7 @@ int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf, * so reading the list is safe. */ - for (pmc=inet6->ipv6_mc_list; pmc; pmc=pmc->next) { + for_each_pmc_rcu(inet6, pmc) { if (pmc->ifindex != gsf->gf_interface) continue; if (ipv6_addr_equal(group, &pmc->addr)) @@ -612,13 +625,13 @@ int inet6_mc_check(struct sock *sk, const struct in6_addr *mc_addr, struct ip6_sf_socklist *psl; int rv = 1; - read_lock(&ipv6_sk_mc_lock); - for (mc = np->ipv6_mc_list; mc; mc = mc->next) { + rcu_read_lock(); + for_each_pmc_rcu(np, mc) { if (ipv6_addr_equal(&mc->addr, mc_addr)) break; } if (!mc) { - read_unlock(&ipv6_sk_mc_lock); + rcu_read_unlock(); return 1; } read_lock(&mc->sflock); @@ -638,7 +651,7 @@ int inet6_mc_check(struct sock *sk, const struct in6_addr *mc_addr, rv = 0; } read_unlock(&mc->sflock); - read_unlock(&ipv6_sk_mc_lock); + rcu_read_unlock(); return rv; } -- cgit v1.2.3 From 3853b5841c01a3f492fe137afaad9c209e5162c6 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Sun, 21 Nov 2010 13:17:29 +0000 Subject: xps: Improvements in TX queue selection In dev_pick_tx, don't do work in calculating queue index or setting the index in the sock unless the device has more than one queue. This allows the sock to be set only with a queue index of a multi-queue device which is desirable if device are stacked like in a tunnel. We also allow the mapping of a socket to queue to be changed. To maintain in order packet transmission a flag (ooo_okay) has been added to the sk_buff structure. If a transport layer sets this flag on a packet, the transmit queue can be changed for the socket. Presumably, the transport would set this if there was no possbility of creating OOO packets (for instance, there are no packets in flight for the socket). This patch includes the modification in TCP output for setting this flag. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/skbuff.h | 3 ++- net/core/dev.c | 18 +++++++++++------- net/ipv4/tcp_output.c | 5 ++++- 3 files changed, 17 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index e6ba898de61c..19f37a6ee6c4 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -386,9 +386,10 @@ struct sk_buff { #else __u8 deliver_no_wcard:1; #endif + __u8 ooo_okay:1; kmemcheck_bitfield_end(flags2); - /* 0/14 bit hole */ + /* 0/13 bit hole */ #ifdef CONFIG_NET_DMA dma_cookie_t dma_cookie; diff --git a/net/core/dev.c b/net/core/dev.c index 381b8e280162..7b17674a29ec 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2148,20 +2148,24 @@ static struct netdev_queue *dev_pick_tx(struct net_device *dev, int queue_index; const struct net_device_ops *ops = dev->netdev_ops; - if (ops->ndo_select_queue) { + if (dev->real_num_tx_queues == 1) + queue_index = 0; + else if (ops->ndo_select_queue) { queue_index = ops->ndo_select_queue(dev, skb); queue_index = dev_cap_txqueue(dev, queue_index); } else { struct sock *sk = skb->sk; queue_index = sk_tx_queue_get(sk); - if (queue_index < 0 || queue_index >= dev->real_num_tx_queues) { - queue_index = 0; - if (dev->real_num_tx_queues > 1) - queue_index = skb_tx_hash(dev, skb); + if (queue_index < 0 || skb->ooo_okay || + queue_index >= dev->real_num_tx_queues) { + int old_index = queue_index; - if (sk) { - struct dst_entry *dst = rcu_dereference_check(sk->sk_dst_cache, 1); + queue_index = skb_tx_hash(dev, skb); + + if (queue_index != old_index && sk) { + struct dst_entry *dst = + rcu_dereference_check(sk->sk_dst_cache, 1); if (dst && skb_dst(skb) == dst) sk_tx_queue_set(sk, queue_index); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index bb8f547fc7d2..5f29b2e20e23 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -822,8 +822,11 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, &md5); tcp_header_size = tcp_options_size + sizeof(struct tcphdr); - if (tcp_packets_in_flight(tp) == 0) + if (tcp_packets_in_flight(tp) == 0) { tcp_ca_event(sk, CA_EVENT_TX_START); + skb->ooo_okay = 1; + } else + skb->ooo_okay = 0; skb_push(skb, tcp_header_size); skb_reset_transport_header(skb); -- cgit v1.2.3 From 1d24eb4815d1e0e8b451ecc546645f8ef1176d4f Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Sun, 21 Nov 2010 13:17:27 +0000 Subject: xps: Transmit Packet Steering This patch implements transmit packet steering (XPS) for multiqueue devices. XPS selects a transmit queue during packet transmission based on configuration. This is done by mapping the CPU transmitting the packet to a queue. This is the transmit side analogue to RPS-- where RPS is selecting a CPU based on receive queue, XPS selects a queue based on the CPU (previously there was an XPS patch from Eric Dumazet, but that might more appropriately be called transmit completion steering). Each transmit queue can be associated with a number of CPUs which will use the queue to send packets. This is configured as a CPU mask on a per queue basis in: /sys/class/net/eth/queues/tx-/xps_cpus The mappings are stored per device in an inverted data structure that maps CPUs to queues. In the netdevice structure this is an array of num_possible_cpu structures where each structure holds and array of queue_indexes for queues which that CPU can use. The benefits of XPS are improved locality in the per queue data structures. Also, transmit completions are more likely to be done nearer to the sending thread, so this should promote locality back to the socket on free (e.g. UDP). The benefits of XPS are dependent on cache hierarchy, application load, and other factors. XPS would nominally be configured so that a queue would only be shared by CPUs which are sharing a cache, the degenerative configuration woud be that each CPU has it's own queue. Below are some benchmark results which show the potential benfit of this patch. The netperf test has 500 instances of netperf TCP_RR test with 1 byte req. and resp. bnx2x on 16 core AMD XPS (16 queues, 1 TX queue per CPU) 1234K at 100% CPU No XPS (16 queues) 996K at 100% CPU Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/netdevice.h | 30 ++++ net/core/dev.c | 53 ++++++- net/core/net-sysfs.c | 369 +++++++++++++++++++++++++++++++++++++++++++++- net/core/net-sysfs.h | 3 + 4 files changed, 447 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b45c1b8b1d19..badf9285fe0d 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -503,6 +503,10 @@ struct netdev_queue { struct Qdisc *qdisc; unsigned long state; struct Qdisc *qdisc_sleeping; +#ifdef CONFIG_RPS + struct kobject kobj; +#endif + /* * write mostly part */ @@ -529,6 +533,30 @@ struct rps_map { }; #define RPS_MAP_SIZE(_num) (sizeof(struct rps_map) + (_num * sizeof(u16))) +/* + * This structure holds an XPS map which can be of variable length. The + * map is an array of queues. + */ +struct xps_map { + unsigned int len; + unsigned int alloc_len; + struct rcu_head rcu; + u16 queues[0]; +}; +#define XPS_MAP_SIZE(_num) (sizeof(struct xps_map) + (_num * sizeof(u16))) +#define XPS_MIN_MAP_ALLOC ((L1_CACHE_BYTES - sizeof(struct xps_map)) \ + / sizeof(u16)) + +/* + * This structure holds all XPS maps for device. Maps are indexed by CPU. + */ +struct xps_dev_maps { + struct rcu_head rcu; + struct xps_map *cpu_map[0]; +}; +#define XPS_DEV_MAPS_SIZE (sizeof(struct xps_dev_maps) + \ + (nr_cpu_ids * sizeof(struct xps_map *))) + /* * The rps_dev_flow structure contains the mapping of a flow to a CPU and the * tail pointer for that CPU's input queue at the time of last enqueue. @@ -1016,6 +1044,8 @@ struct net_device { unsigned long tx_queue_len; /* Max frames per queue allowed */ spinlock_t tx_global_lock; + struct xps_dev_maps *xps_maps; + /* These may be needed for future network-power-down code. */ /* diff --git a/net/core/dev.c b/net/core/dev.c index 7b17674a29ec..c852f0038a08 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1557,12 +1557,16 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) */ int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq) { + int rc; + if (txq < 1 || txq > dev->num_tx_queues) return -EINVAL; if (dev->reg_state == NETREG_REGISTERED) { ASSERT_RTNL(); + rc = netdev_queue_update_kobjects(dev, dev->real_num_tx_queues, + txq); if (txq < dev->real_num_tx_queues) qdisc_reset_all_tx_gt(dev, txq); } @@ -2142,6 +2146,44 @@ static inline u16 dev_cap_txqueue(struct net_device *dev, u16 queue_index) return queue_index; } +static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb) +{ +#ifdef CONFIG_RPS + struct xps_dev_maps *dev_maps; + struct xps_map *map; + int queue_index = -1; + + rcu_read_lock(); + dev_maps = rcu_dereference(dev->xps_maps); + if (dev_maps) { + map = rcu_dereference( + dev_maps->cpu_map[raw_smp_processor_id()]); + if (map) { + if (map->len == 1) + queue_index = map->queues[0]; + else { + u32 hash; + if (skb->sk && skb->sk->sk_hash) + hash = skb->sk->sk_hash; + else + hash = (__force u16) skb->protocol ^ + skb->rxhash; + hash = jhash_1word(hash, hashrnd); + queue_index = map->queues[ + ((u64)hash * map->len) >> 32]; + } + if (unlikely(queue_index >= dev->real_num_tx_queues)) + queue_index = -1; + } + } + rcu_read_unlock(); + + return queue_index; +#else + return -1; +#endif +} + static struct netdev_queue *dev_pick_tx(struct net_device *dev, struct sk_buff *skb) { @@ -2161,7 +2203,9 @@ static struct netdev_queue *dev_pick_tx(struct net_device *dev, queue_index >= dev->real_num_tx_queues) { int old_index = queue_index; - queue_index = skb_tx_hash(dev, skb); + queue_index = get_xps_queue(dev, skb); + if (queue_index < 0) + queue_index = skb_tx_hash(dev, skb); if (queue_index != old_index && sk) { struct dst_entry *dst = @@ -5066,6 +5110,7 @@ static int netif_alloc_netdev_queues(struct net_device *dev) { unsigned int count = dev->num_tx_queues; struct netdev_queue *tx; + int i; BUG_ON(count < 1); @@ -5076,6 +5121,10 @@ static int netif_alloc_netdev_queues(struct net_device *dev) return -ENOMEM; } dev->_tx = tx; + + for (i = 0; i < count; i++) + tx[i].dev = dev; + return 0; } @@ -5083,8 +5132,6 @@ static void netdev_init_one_queue(struct net_device *dev, struct netdev_queue *queue, void *_unused) { - queue->dev = dev; - /* Initialize queue lock */ spin_lock_init(&queue->_xmit_lock); netdev_set_xmit_lockdep_class(&queue->_xmit_lock, dev->type); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 7abeb7ceaa4c..68dbbfdee274 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -772,18 +772,377 @@ net_rx_queue_update_kobjects(struct net_device *net, int old_num, int new_num) return error; } -static int rx_queue_register_kobjects(struct net_device *net) +/* + * netdev_queue sysfs structures and functions. + */ +struct netdev_queue_attribute { + struct attribute attr; + ssize_t (*show)(struct netdev_queue *queue, + struct netdev_queue_attribute *attr, char *buf); + ssize_t (*store)(struct netdev_queue *queue, + struct netdev_queue_attribute *attr, const char *buf, size_t len); +}; +#define to_netdev_queue_attr(_attr) container_of(_attr, \ + struct netdev_queue_attribute, attr) + +#define to_netdev_queue(obj) container_of(obj, struct netdev_queue, kobj) + +static ssize_t netdev_queue_attr_show(struct kobject *kobj, + struct attribute *attr, char *buf) +{ + struct netdev_queue_attribute *attribute = to_netdev_queue_attr(attr); + struct netdev_queue *queue = to_netdev_queue(kobj); + + if (!attribute->show) + return -EIO; + + return attribute->show(queue, attribute, buf); +} + +static ssize_t netdev_queue_attr_store(struct kobject *kobj, + struct attribute *attr, + const char *buf, size_t count) +{ + struct netdev_queue_attribute *attribute = to_netdev_queue_attr(attr); + struct netdev_queue *queue = to_netdev_queue(kobj); + + if (!attribute->store) + return -EIO; + + return attribute->store(queue, attribute, buf, count); +} + +static const struct sysfs_ops netdev_queue_sysfs_ops = { + .show = netdev_queue_attr_show, + .store = netdev_queue_attr_store, +}; + +static inline unsigned int get_netdev_queue_index(struct netdev_queue *queue) { + struct net_device *dev = queue->dev; + int i; + + for (i = 0; i < dev->num_tx_queues; i++) + if (queue == &dev->_tx[i]) + break; + + BUG_ON(i >= dev->num_tx_queues); + + return i; +} + + +static ssize_t show_xps_map(struct netdev_queue *queue, + struct netdev_queue_attribute *attribute, char *buf) +{ + struct net_device *dev = queue->dev; + struct xps_dev_maps *dev_maps; + cpumask_var_t mask; + unsigned long index; + size_t len = 0; + int i; + + if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) + return -ENOMEM; + + index = get_netdev_queue_index(queue); + + rcu_read_lock(); + dev_maps = rcu_dereference(dev->xps_maps); + if (dev_maps) { + for_each_possible_cpu(i) { + struct xps_map *map = + rcu_dereference(dev_maps->cpu_map[i]); + if (map) { + int j; + for (j = 0; j < map->len; j++) { + if (map->queues[j] == index) { + cpumask_set_cpu(i, mask); + break; + } + } + } + } + } + rcu_read_unlock(); + + len += cpumask_scnprintf(buf + len, PAGE_SIZE, mask); + if (PAGE_SIZE - len < 3) { + free_cpumask_var(mask); + return -EINVAL; + } + + free_cpumask_var(mask); + len += sprintf(buf + len, "\n"); + return len; +} + +static void xps_map_release(struct rcu_head *rcu) +{ + struct xps_map *map = container_of(rcu, struct xps_map, rcu); + + kfree(map); +} + +static void xps_dev_maps_release(struct rcu_head *rcu) +{ + struct xps_dev_maps *dev_maps = + container_of(rcu, struct xps_dev_maps, rcu); + + kfree(dev_maps); +} + +static DEFINE_MUTEX(xps_map_mutex); + +static ssize_t store_xps_map(struct netdev_queue *queue, + struct netdev_queue_attribute *attribute, + const char *buf, size_t len) +{ + struct net_device *dev = queue->dev; + cpumask_var_t mask; + int err, i, cpu, pos, map_len, alloc_len, need_set; + unsigned long index; + struct xps_map *map, *new_map; + struct xps_dev_maps *dev_maps, *new_dev_maps; + int nonempty = 0; + + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + + if (!alloc_cpumask_var(&mask, GFP_KERNEL)) + return -ENOMEM; + + index = get_netdev_queue_index(queue); + + err = bitmap_parse(buf, len, cpumask_bits(mask), nr_cpumask_bits); + if (err) { + free_cpumask_var(mask); + return err; + } + + new_dev_maps = kzalloc(max_t(unsigned, + XPS_DEV_MAPS_SIZE, L1_CACHE_BYTES), GFP_KERNEL); + if (!new_dev_maps) { + free_cpumask_var(mask); + return -ENOMEM; + } + + mutex_lock(&xps_map_mutex); + + dev_maps = dev->xps_maps; + + for_each_possible_cpu(cpu) { + new_map = map = dev_maps ? dev_maps->cpu_map[cpu] : NULL; + + if (map) { + for (pos = 0; pos < map->len; pos++) + if (map->queues[pos] == index) + break; + map_len = map->len; + alloc_len = map->alloc_len; + } else + pos = map_len = alloc_len = 0; + + need_set = cpu_isset(cpu, *mask) && cpu_online(cpu); + + if (need_set && pos >= map_len) { + /* Need to add queue to this CPU's map */ + if (map_len >= alloc_len) { + alloc_len = alloc_len ? + 2 * alloc_len : XPS_MIN_MAP_ALLOC; + new_map = kzalloc(XPS_MAP_SIZE(alloc_len), + GFP_KERNEL); + if (!new_map) + goto error; + new_map->alloc_len = alloc_len; + for (i = 0; i < map_len; i++) + new_map->queues[i] = map->queues[i]; + new_map->len = map_len; + } + new_map->queues[new_map->len++] = index; + } else if (!need_set && pos < map_len) { + /* Need to remove queue from this CPU's map */ + if (map_len > 1) + new_map->queues[pos] = + new_map->queues[--new_map->len]; + else + new_map = NULL; + } + new_dev_maps->cpu_map[cpu] = new_map; + } + + /* Cleanup old maps */ + for_each_possible_cpu(cpu) { + map = dev_maps ? dev_maps->cpu_map[cpu] : NULL; + if (map && new_dev_maps->cpu_map[cpu] != map) + call_rcu(&map->rcu, xps_map_release); + if (new_dev_maps->cpu_map[cpu]) + nonempty = 1; + } + + if (nonempty) + rcu_assign_pointer(dev->xps_maps, new_dev_maps); + else { + kfree(new_dev_maps); + rcu_assign_pointer(dev->xps_maps, NULL); + } + + if (dev_maps) + call_rcu(&dev_maps->rcu, xps_dev_maps_release); + + mutex_unlock(&xps_map_mutex); + + free_cpumask_var(mask); + return len; + +error: + mutex_unlock(&xps_map_mutex); + + if (new_dev_maps) + for_each_possible_cpu(i) + kfree(new_dev_maps->cpu_map[i]); + kfree(new_dev_maps); + free_cpumask_var(mask); + return -ENOMEM; +} + +static struct netdev_queue_attribute xps_cpus_attribute = + __ATTR(xps_cpus, S_IRUGO | S_IWUSR, show_xps_map, store_xps_map); + +static struct attribute *netdev_queue_default_attrs[] = { + &xps_cpus_attribute.attr, + NULL +}; + +static void netdev_queue_release(struct kobject *kobj) +{ + struct netdev_queue *queue = to_netdev_queue(kobj); + struct net_device *dev = queue->dev; + struct xps_dev_maps *dev_maps; + struct xps_map *map; + unsigned long index; + int i, pos, nonempty = 0; + + index = get_netdev_queue_index(queue); + + mutex_lock(&xps_map_mutex); + dev_maps = dev->xps_maps; + + if (dev_maps) { + for_each_possible_cpu(i) { + map = dev_maps->cpu_map[i]; + if (!map) + continue; + + for (pos = 0; pos < map->len; pos++) + if (map->queues[pos] == index) + break; + + if (pos < map->len) { + if (map->len > 1) + map->queues[pos] = + map->queues[--map->len]; + else { + RCU_INIT_POINTER(dev_maps->cpu_map[i], + NULL); + call_rcu(&map->rcu, xps_map_release); + map = NULL; + } + } + if (map) + nonempty = 1; + } + + if (!nonempty) { + RCU_INIT_POINTER(dev->xps_maps, NULL); + call_rcu(&dev_maps->rcu, xps_dev_maps_release); + } + } + + mutex_unlock(&xps_map_mutex); + + memset(kobj, 0, sizeof(*kobj)); + dev_put(queue->dev); +} + +static struct kobj_type netdev_queue_ktype = { + .sysfs_ops = &netdev_queue_sysfs_ops, + .release = netdev_queue_release, + .default_attrs = netdev_queue_default_attrs, +}; + +static int netdev_queue_add_kobject(struct net_device *net, int index) +{ + struct netdev_queue *queue = net->_tx + index; + struct kobject *kobj = &queue->kobj; + int error = 0; + + kobj->kset = net->queues_kset; + error = kobject_init_and_add(kobj, &netdev_queue_ktype, NULL, + "tx-%u", index); + if (error) { + kobject_put(kobj); + return error; + } + + kobject_uevent(kobj, KOBJ_ADD); + dev_hold(queue->dev); + + return error; +} + +int +netdev_queue_update_kobjects(struct net_device *net, int old_num, int new_num) +{ + int i; + int error = 0; + + for (i = old_num; i < new_num; i++) { + error = netdev_queue_add_kobject(net, i); + if (error) { + new_num = old_num; + break; + } + } + + while (--i >= new_num) + kobject_put(&net->_tx[i].kobj); + + return error; +} + +static int register_queue_kobjects(struct net_device *net) +{ + int error = 0, txq = 0, rxq = 0; + net->queues_kset = kset_create_and_add("queues", NULL, &net->dev.kobj); if (!net->queues_kset) return -ENOMEM; - return net_rx_queue_update_kobjects(net, 0, net->real_num_rx_queues); + + error = net_rx_queue_update_kobjects(net, 0, net->real_num_rx_queues); + if (error) + goto error; + rxq = net->real_num_rx_queues; + + error = netdev_queue_update_kobjects(net, 0, + net->real_num_tx_queues); + if (error) + goto error; + txq = net->real_num_tx_queues; + + return 0; + +error: + netdev_queue_update_kobjects(net, txq, 0); + net_rx_queue_update_kobjects(net, rxq, 0); + return error; } -static void rx_queue_remove_kobjects(struct net_device *net) +static void remove_queue_kobjects(struct net_device *net) { net_rx_queue_update_kobjects(net, net->real_num_rx_queues, 0); + netdev_queue_update_kobjects(net, net->real_num_tx_queues, 0); kset_unregister(net->queues_kset); } #endif /* CONFIG_RPS */ @@ -886,7 +1245,7 @@ void netdev_unregister_kobject(struct net_device * net) kobject_get(&dev->kobj); #ifdef CONFIG_RPS - rx_queue_remove_kobjects(net); + remove_queue_kobjects(net); #endif device_del(dev); @@ -927,7 +1286,7 @@ int netdev_register_kobject(struct net_device *net) return error; #ifdef CONFIG_RPS - error = rx_queue_register_kobjects(net); + error = register_queue_kobjects(net); if (error) { device_del(dev); return error; diff --git a/net/core/net-sysfs.h b/net/core/net-sysfs.h index 778e1571548d..25ec2ee57df7 100644 --- a/net/core/net-sysfs.h +++ b/net/core/net-sysfs.h @@ -6,6 +6,9 @@ int netdev_register_kobject(struct net_device *); void netdev_unregister_kobject(struct net_device *); #ifdef CONFIG_RPS int net_rx_queue_update_kobjects(struct net_device *, int old_num, int new_num); +int netdev_queue_update_kobjects(struct net_device *net, + int old_num, int new_num); + #endif #endif -- cgit v1.2.3 From ccb14354017272ddac002e859a2711610b6af174 Mon Sep 17 00:00:00 2001 From: "John W. Linville" Date: Wed, 24 Nov 2010 16:18:36 -0500 Subject: Revert "nl80211/mac80211: Report signal average" This reverts commit 86107fd170bc379869250eb7e1bd393a3a70e8ae. This patch inadvertantly changed the userland ABI. Signed-off-by: John W. Linville --- include/linux/nl80211.h | 2 -- include/net/cfg80211.h | 4 ---- net/mac80211/Kconfig | 1 - net/mac80211/cfg.c | 3 +-- net/mac80211/rx.c | 1 - net/mac80211/sta_info.c | 2 -- net/mac80211/sta_info.h | 3 --- net/wireless/nl80211.c | 3 --- 8 files changed, 1 insertion(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 1ce3775e9e26..037b4e498890 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -1161,7 +1161,6 @@ enum nl80211_rate_info { * @__NL80211_STA_INFO_AFTER_LAST: internal * @NL80211_STA_INFO_MAX: highest possible station info attribute * @NL80211_STA_INFO_SIGNAL: signal strength of last received PPDU (u8, dBm) - * @NL80211_STA_INFO_SIGNAL_AVG: signal strength average (u8, dBm) * @NL80211_STA_INFO_TX_BITRATE: current unicast tx rate, nested attribute * containing info as possible, see &enum nl80211_sta_info_txrate. * @NL80211_STA_INFO_RX_PACKETS: total received packet (u32, from this station) @@ -1179,7 +1178,6 @@ enum nl80211_sta_info { NL80211_STA_INFO_PLID, NL80211_STA_INFO_PLINK_STATE, NL80211_STA_INFO_SIGNAL, - NL80211_STA_INFO_SIGNAL_AVG, NL80211_STA_INFO_TX_BITRATE, NL80211_STA_INFO_RX_PACKETS, NL80211_STA_INFO_TX_PACKETS, diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 69e2364889f1..8fd9eebd0cc9 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -424,7 +424,6 @@ struct station_parameters { * @STATION_INFO_TX_RETRIES: @tx_retries filled * @STATION_INFO_TX_FAILED: @tx_failed filled * @STATION_INFO_RX_DROP_MISC: @rx_dropped_misc filled - * @STATION_INFO_SIGNAL_AVG: @signal_avg filled */ enum station_info_flags { STATION_INFO_INACTIVE_TIME = 1<<0, @@ -440,7 +439,6 @@ enum station_info_flags { STATION_INFO_TX_RETRIES = 1<<10, STATION_INFO_TX_FAILED = 1<<11, STATION_INFO_RX_DROP_MISC = 1<<12, - STATION_INFO_SIGNAL_AVG = 1<<13, }; /** @@ -487,7 +485,6 @@ struct rate_info { * @plid: mesh peer link id * @plink_state: mesh peer link state * @signal: signal strength of last received packet in dBm - * @signal_avg: signal strength average in dBm * @txrate: current unicast bitrate to this station * @rx_packets: packets received from this station * @tx_packets: packets transmitted to this station @@ -508,7 +505,6 @@ struct station_info { u16 plid; u8 plink_state; s8 signal; - s8 signal_avg; struct rate_info txrate; u32 rx_packets; u32 tx_packets; diff --git a/net/mac80211/Kconfig b/net/mac80211/Kconfig index 798d9b9462e2..4d6f8653ec88 100644 --- a/net/mac80211/Kconfig +++ b/net/mac80211/Kconfig @@ -6,7 +6,6 @@ config MAC80211 select CRYPTO_ARC4 select CRYPTO_AES select CRC32 - select AVERAGE ---help--- This option enables the hardware independent IEEE 802.11 networking stack. diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 92c9cf6a7d1c..0c544074479e 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -343,9 +343,8 @@ static void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo) if ((sta->local->hw.flags & IEEE80211_HW_SIGNAL_DBM) || (sta->local->hw.flags & IEEE80211_HW_SIGNAL_UNSPEC)) { - sinfo->filled |= STATION_INFO_SIGNAL | STATION_INFO_SIGNAL_AVG; + sinfo->filled |= STATION_INFO_SIGNAL; sinfo->signal = (s8)sta->last_signal; - sinfo->signal_avg = (s8) -ewma_read(&sta->avg_signal); } sinfo->txrate.flags = 0; diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 9dd60a74181f..d2fcd22ab06d 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -1156,7 +1156,6 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx) sta->rx_fragments++; sta->rx_bytes += rx->skb->len; sta->last_signal = status->signal; - ewma_add(&sta->avg_signal, -status->signal); /* * Change STA power saving mode only at the end of a frame diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index f43fca8907f7..eff58571fd7e 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -244,8 +244,6 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, sta->local = local; sta->sdata = sdata; - ewma_init(&sta->avg_signal, 1000, 8); - if (sta_prepare_rate_control(local, sta, gfp)) { kfree(sta); return NULL; diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 84062e2c782c..9265acadef32 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -13,7 +13,6 @@ #include #include #include -#include #include "key.h" /** @@ -225,7 +224,6 @@ enum plink_state { * @rx_fragments: number of received MPDUs * @rx_dropped: number of dropped MPDUs from this STA * @last_signal: signal of last received frame from this STA - * @avg_signal: moving average of signal of received frames from this STA * @last_seq_ctrl: last received seq/frag number from this STA (per RX queue) * @tx_filtered_count: number of frames the hardware filtered for this STA * @tx_retry_failed: number of frames that failed retry @@ -293,7 +291,6 @@ struct sta_info { unsigned long rx_fragments; unsigned long rx_dropped; int last_signal; - struct ewma avg_signal; __le16 last_seq_ctrl[NUM_RX_DATA_QUEUES]; /* Updated from TX status path only, no locking requirements */ diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index d06a40d17002..605553842226 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -1872,9 +1872,6 @@ static int nl80211_send_station(struct sk_buff *msg, u32 pid, u32 seq, if (sinfo->filled & STATION_INFO_SIGNAL) NLA_PUT_U8(msg, NL80211_STA_INFO_SIGNAL, sinfo->signal); - if (sinfo->filled & STATION_INFO_SIGNAL_AVG) - NLA_PUT_U8(msg, NL80211_STA_INFO_SIGNAL_AVG, - sinfo->signal_avg); if (sinfo->filled & STATION_INFO_TX_BITRATE) { txrate = nla_nest_start(msg, NL80211_STA_INFO_TX_BITRATE); if (!txrate) -- cgit v1.2.3 From c063dbf52b998b852122dff07a8b8dd430b38437 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 24 Nov 2010 08:10:05 +0100 Subject: cfg80211: allow using CQM event to notify packet loss This adds the ability for drivers to use CQM events to notify about packet loss for specific stations (which could be the AP for the managed mode case). Since the threshold might be determined by the driver (it isn't passed in right now) it will be passed out of the driver to userspace in the event. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/linux/nl80211.h | 3 +++ include/net/cfg80211.h | 12 ++++++++++++ net/wireless/mlme.c | 12 ++++++++++++ net/wireless/nl80211.c | 45 +++++++++++++++++++++++++++++++++++++++++++++ net/wireless/nl80211.h | 4 ++++ 5 files changed, 76 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 037b4e498890..d706bf3badc8 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -1819,6 +1819,8 @@ enum nl80211_ps_state { * the minimum amount the RSSI level must change after an event before a * new event may be issued (to reduce effects of RSSI oscillation). * @NL80211_ATTR_CQM_RSSI_THRESHOLD_EVENT: RSSI threshold event + * @NL80211_ATTR_CQM_PKT_LOSS_EVENT: a u32 value indicating that this many + * consecutive packets were not acknowledged by the peer * @__NL80211_ATTR_CQM_AFTER_LAST: internal * @NL80211_ATTR_CQM_MAX: highest key attribute */ @@ -1827,6 +1829,7 @@ enum nl80211_attr_cqm { NL80211_ATTR_CQM_RSSI_THOLD, NL80211_ATTR_CQM_RSSI_HYST, NL80211_ATTR_CQM_RSSI_THRESHOLD_EVENT, + NL80211_ATTR_CQM_PKT_LOSS_EVENT, /* keep last */ __NL80211_ATTR_CQM_AFTER_LAST, diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index dd4c43f512e2..0663945cfa48 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -2601,6 +2601,18 @@ void cfg80211_cqm_rssi_notify(struct net_device *dev, enum nl80211_cqm_rssi_threshold_event rssi_event, gfp_t gfp); +/** + * cfg80211_cqm_pktloss_notify - notify userspace about packetloss to peer + * @dev: network device + * @peer: peer's MAC address + * @num_packets: how many packets were lost -- should be a fixed threshold + * but probably no less than maybe 50, or maybe a throughput dependent + * threshold (to account for temporary interference) + * @gfp: context flags + */ +void cfg80211_cqm_pktloss_notify(struct net_device *dev, + const u8 *peer, u32 num_packets, gfp_t gfp); + /* Logging, debugging and troubleshooting/diagnostic helpers. */ /* wiphy_printk helpers, similar to dev_printk */ diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index 26838d903b9a..6980a0c315b2 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -1028,3 +1028,15 @@ void cfg80211_cqm_rssi_notify(struct net_device *dev, nl80211_send_cqm_rssi_notify(rdev, dev, rssi_event, gfp); } EXPORT_SYMBOL(cfg80211_cqm_rssi_notify); + +void cfg80211_cqm_pktloss_notify(struct net_device *dev, + const u8 *peer, u32 num_packets, gfp_t gfp) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct wiphy *wiphy = wdev->wiphy; + struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); + + /* Indicate roaming trigger event to user space */ + nl80211_send_cqm_pktloss_notify(rdev, dev, peer, num_packets, gfp); +} +EXPORT_SYMBOL(cfg80211_cqm_pktloss_notify); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 8734efa663d1..67ff7e92cb99 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -5715,6 +5715,51 @@ nl80211_send_cqm_rssi_notify(struct cfg80211_registered_device *rdev, nlmsg_free(msg); } +void +nl80211_send_cqm_pktloss_notify(struct cfg80211_registered_device *rdev, + struct net_device *netdev, const u8 *peer, + u32 num_packets, gfp_t gfp) +{ + struct sk_buff *msg; + struct nlattr *pinfoattr; + void *hdr; + + msg = nlmsg_new(NLMSG_GOODSIZE, gfp); + if (!msg) + return; + + hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_NOTIFY_CQM); + if (!hdr) { + nlmsg_free(msg); + return; + } + + NLA_PUT_U32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx); + NLA_PUT_U32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex); + NLA_PUT(msg, NL80211_ATTR_MAC, ETH_ALEN, peer); + + pinfoattr = nla_nest_start(msg, NL80211_ATTR_CQM); + if (!pinfoattr) + goto nla_put_failure; + + NLA_PUT_U32(msg, NL80211_ATTR_CQM_PKT_LOSS_EVENT, num_packets); + + nla_nest_end(msg, pinfoattr); + + if (genlmsg_end(msg, hdr) < 0) { + nlmsg_free(msg); + return; + } + + genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0, + nl80211_mlme_mcgrp.id, gfp); + return; + + nla_put_failure: + genlmsg_cancel(msg, hdr); + nlmsg_free(msg); +} + static int nl80211_netlink_notify(struct notifier_block * nb, unsigned long state, void *_notify) diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h index 30d2f939150d..16c2f7190768 100644 --- a/net/wireless/nl80211.h +++ b/net/wireless/nl80211.h @@ -87,5 +87,9 @@ nl80211_send_cqm_rssi_notify(struct cfg80211_registered_device *rdev, struct net_device *netdev, enum nl80211_cqm_rssi_threshold_event rssi_event, gfp_t gfp); +void +nl80211_send_cqm_pktloss_notify(struct cfg80211_registered_device *rdev, + struct net_device *netdev, const u8 *peer, + u32 num_packets, gfp_t gfp); #endif /* __NET_WIRELESS_NL80211_H */ -- cgit v1.2.3 From 6d803ba736abb5e122dede70a4720e4843dd6df4 Mon Sep 17 00:00:00 2001 From: Jean-Christop PLAGNIOL-VILLARD Date: Wed, 17 Nov 2010 10:04:33 +0100 Subject: ARM: 6483/1: arm & sh: factorised duplicated clkdev.c factorise some generic infrastructure to assist looking up struct clks for the ARM & SH architecture. as the code is identical at 99% put the arch specific code for allocation as example in asm/clkdev.h Signed-off-by: Jean-Christophe PLAGNIOL-VILLARD Acked-by: Paul Mundt Signed-off-by: Russell King --- arch/arm/Kconfig | 42 +++--- arch/arm/common/Kconfig | 4 - arch/arm/common/Makefile | 1 - arch/arm/common/clkdev.c | 179 -------------------------- arch/arm/include/asm/clkdev.h | 22 +--- arch/arm/mach-bcmring/clock.c | 3 +- arch/arm/mach-bcmring/core.c | 2 +- arch/arm/mach-davinci/clock.h | 2 +- arch/arm/mach-ep93xx/clock.c | 2 +- arch/arm/mach-imx/clock-imx1.c | 3 +- arch/arm/mach-imx/clock-imx21.c | 2 +- arch/arm/mach-imx/clock-imx27.c | 2 +- arch/arm/mach-integrator/core.c | 3 +- arch/arm/mach-integrator/impd1.c | 3 +- arch/arm/mach-integrator/integrator_cp.c | 3 +- arch/arm/mach-lpc32xx/clock.c | 3 +- arch/arm/mach-mmp/clock.h | 2 +- arch/arm/mach-mx25/clock.c | 3 +- arch/arm/mach-mx3/clock-imx31.c | 2 +- arch/arm/mach-mx3/clock-imx35.c | 3 +- arch/arm/mach-mx5/clock-mx51.c | 2 +- arch/arm/mach-mxc91231/clock.c | 2 +- arch/arm/mach-nomadik/clock.c | 2 +- arch/arm/mach-nuc93x/clock.h | 2 +- arch/arm/mach-omap1/clock.c | 2 +- arch/arm/mach-omap2/dpll3xxx.c | 2 +- arch/arm/mach-pnx4008/clock.c | 3 +- arch/arm/mach-pxa/clock.c | 2 +- arch/arm/mach-pxa/clock.h | 2 +- arch/arm/mach-realview/core.c | 3 +- arch/arm/mach-shmobile/Kconfig | 6 +- arch/arm/mach-shmobile/clock-sh7367.c | 2 +- arch/arm/mach-shmobile/clock-sh7372.c | 2 +- arch/arm/mach-shmobile/clock-sh7377.c | 2 +- arch/arm/mach-tcc8k/clock.c | 3 +- arch/arm/mach-tegra/clock.c | 2 +- arch/arm/mach-tegra/clock.h | 2 +- arch/arm/mach-tegra/tegra2_clocks.c | 3 +- arch/arm/mach-u300/clock.c | 2 +- arch/arm/mach-ux500/clock.c | 3 +- arch/arm/mach-versatile/core.c | 3 +- arch/arm/mach-vexpress/ct-ca9x4.c | 3 +- arch/arm/mach-vexpress/v2m.c | 3 +- arch/arm/mach-w90x900/clock.h | 2 +- arch/arm/plat-omap/Kconfig | 4 +- arch/arm/plat-omap/include/plat/clkdev_omap.h | 2 +- arch/arm/plat-spear/include/plat/clock.h | 2 +- arch/arm/plat-stmp3xxx/clock.c | 2 +- arch/sh/Kconfig | 2 +- arch/sh/boards/mach-highlander/setup.c | 2 +- arch/sh/include/asm/clkdev.h | 38 +++--- arch/sh/kernel/Makefile | 2 +- arch/sh/kernel/clkdev.c | 171 ------------------------ arch/sh/kernel/cpu/clock-cpg.c | 2 +- arch/sh/kernel/cpu/clock.c | 16 --- arch/sh/kernel/cpu/sh4/clock-sh4-202.c | 2 +- arch/sh/kernel/cpu/sh4a/clock-sh7343.c | 2 +- arch/sh/kernel/cpu/sh4a/clock-sh7366.c | 2 +- arch/sh/kernel/cpu/sh4a/clock-sh7722.c | 2 +- arch/sh/kernel/cpu/sh4a/clock-sh7723.c | 2 +- arch/sh/kernel/cpu/sh4a/clock-sh7724.c | 2 +- arch/sh/kernel/cpu/sh4a/clock-sh7757.c | 2 +- arch/sh/kernel/cpu/sh4a/clock-sh7763.c | 2 +- arch/sh/kernel/cpu/sh4a/clock-sh7780.c | 2 +- arch/sh/kernel/cpu/sh4a/clock-sh7785.c | 2 +- arch/sh/kernel/cpu/sh4a/clock-sh7786.c | 2 +- arch/sh/kernel/cpu/sh4a/clock-shx3.c | 2 +- drivers/Kconfig | 2 + drivers/Makefile | 2 + drivers/clk/Kconfig | 4 + drivers/clk/Makefile | 2 + drivers/clk/clkdev.c | 176 +++++++++++++++++++++++++ include/linux/clkdev.h | 36 ++++++ 73 files changed, 328 insertions(+), 507 deletions(-) delete mode 100644 arch/arm/common/clkdev.c delete mode 100644 arch/sh/kernel/clkdev.c create mode 100644 drivers/clk/Kconfig create mode 100644 drivers/clk/Makefile create mode 100644 drivers/clk/clkdev.c create mode 100644 include/linux/clkdev.h (limited to 'include/linux') diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index a19a5266d5fc..0e51342b3c02 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -221,7 +221,7 @@ config ARCH_INTEGRATOR bool "ARM Ltd. Integrator family" select ARM_AMBA select ARCH_HAS_CPUFREQ - select COMMON_CLKDEV + select CLKDEV_LOOKUP select ICST select GENERIC_CLOCKEVENTS select PLAT_VERSATILE @@ -231,7 +231,7 @@ config ARCH_INTEGRATOR config ARCH_REALVIEW bool "ARM Ltd. RealView family" select ARM_AMBA - select COMMON_CLKDEV + select CLKDEV_LOOKUP select ICST select GENERIC_CLOCKEVENTS select ARCH_WANT_OPTIONAL_GPIOLIB @@ -245,7 +245,7 @@ config ARCH_VERSATILE bool "ARM Ltd. Versatile family" select ARM_AMBA select ARM_VIC - select COMMON_CLKDEV + select CLKDEV_LOOKUP select ICST select GENERIC_CLOCKEVENTS select ARCH_WANT_OPTIONAL_GPIOLIB @@ -259,7 +259,7 @@ config ARCH_VEXPRESS select ARCH_WANT_OPTIONAL_GPIOLIB select ARM_AMBA select ARM_TIMER_SP804 - select COMMON_CLKDEV + select CLKDEV_LOOKUP select GENERIC_CLOCKEVENTS select HAVE_CLK select ICST @@ -280,7 +280,7 @@ config ARCH_BCMRING depends on MMU select CPU_V6 select ARM_AMBA - select COMMON_CLKDEV + select CLKDEV_LOOKUP select GENERIC_CLOCKEVENTS select ARCH_WANT_OPTIONAL_GPIOLIB help @@ -327,7 +327,7 @@ config ARCH_EP93XX select CPU_ARM920T select ARM_AMBA select ARM_VIC - select COMMON_CLKDEV + select CLKDEV_LOOKUP select ARCH_REQUIRE_GPIOLIB select ARCH_HAS_HOLES_MEMORYMODEL select ARCH_USES_GETTIMEOFFSET @@ -347,14 +347,14 @@ config ARCH_MXC bool "Freescale MXC/iMX-based" select GENERIC_CLOCKEVENTS select ARCH_REQUIRE_GPIOLIB - select COMMON_CLKDEV + select CLKDEV_LOOKUP help Support for Freescale MXC/iMX-based family of processors config ARCH_STMP3XXX bool "Freescale STMP3xxx" select CPU_ARM926T - select COMMON_CLKDEV + select CLKDEV_LOOKUP select ARCH_REQUIRE_GPIOLIB select GENERIC_CLOCKEVENTS select USB_ARCH_HAS_EHCI @@ -472,7 +472,7 @@ config ARCH_LPC32XX select HAVE_IDE select ARM_AMBA select USB_ARCH_HAS_OHCI - select COMMON_CLKDEV + select CLKDEV_LOOKUP select GENERIC_TIME select GENERIC_CLOCKEVENTS help @@ -506,7 +506,7 @@ config ARCH_MMP bool "Marvell PXA168/910/MMP2" depends on MMU select ARCH_REQUIRE_GPIOLIB - select COMMON_CLKDEV + select CLKDEV_LOOKUP select GENERIC_CLOCKEVENTS select TICK_ONESHOT select PLAT_PXA @@ -539,7 +539,7 @@ config ARCH_W90X900 bool "Nuvoton W90X900 CPU" select CPU_ARM926T select ARCH_REQUIRE_GPIOLIB - select COMMON_CLKDEV + select CLKDEV_LOOKUP select GENERIC_CLOCKEVENTS help Support for Nuvoton (Winbond logic dept.) ARM9 processor, @@ -553,7 +553,7 @@ config ARCH_W90X900 config ARCH_NUC93X bool "Nuvoton NUC93X CPU" select CPU_ARM926T - select COMMON_CLKDEV + select CLKDEV_LOOKUP help Support for Nuvoton (Winbond logic dept.) NUC93X MCU,The NUC93X is a low-power and high performance MPEG-4/JPEG multimedia controller chip. @@ -564,7 +564,7 @@ config ARCH_TEGRA select GENERIC_CLOCKEVENTS select GENERIC_GPIO select HAVE_CLK - select COMMON_CLKDEV + select CLKDEV_LOOKUP select ARCH_HAS_BARRIERS if CACHE_L2X0 select ARCH_HAS_CPUFREQ help @@ -574,7 +574,7 @@ config ARCH_TEGRA config ARCH_PNX4008 bool "Philips Nexperia PNX4008 Mobile" select CPU_ARM926T - select COMMON_CLKDEV + select CLKDEV_LOOKUP select ARCH_USES_GETTIMEOFFSET help This enables support for Philips PNX4008 mobile platform. @@ -584,7 +584,7 @@ config ARCH_PXA depends on MMU select ARCH_MTD_XIP select ARCH_HAS_CPUFREQ - select COMMON_CLKDEV + select CLKDEV_LOOKUP select ARCH_REQUIRE_GPIOLIB select GENERIC_CLOCKEVENTS select TICK_ONESHOT @@ -761,7 +761,7 @@ config ARCH_TCC_926 bool "Telechips TCC ARM926-based systems" select CPU_ARM926T select HAVE_CLK - select COMMON_CLKDEV + select CLKDEV_LOOKUP select GENERIC_CLOCKEVENTS help Support for Telechips TCC ARM926-based systems. @@ -785,7 +785,7 @@ config ARCH_U300 select ARM_AMBA select ARM_VIC select GENERIC_CLOCKEVENTS - select COMMON_CLKDEV + select CLKDEV_LOOKUP select GENERIC_GPIO help Support for ST-Ericsson U300 series mobile platforms. @@ -795,7 +795,7 @@ config ARCH_U8500 select CPU_V7 select ARM_AMBA select GENERIC_CLOCKEVENTS - select COMMON_CLKDEV + select CLKDEV_LOOKUP select ARCH_REQUIRE_GPIOLIB help Support for ST-Ericsson's Ux500 architecture @@ -805,7 +805,7 @@ config ARCH_NOMADIK select ARM_AMBA select ARM_VIC select CPU_ARM926T - select COMMON_CLKDEV + select CLKDEV_LOOKUP select GENERIC_CLOCKEVENTS select ARCH_REQUIRE_GPIOLIB help @@ -817,7 +817,7 @@ config ARCH_DAVINCI select ARCH_REQUIRE_GPIOLIB select ZONE_DMA select HAVE_IDE - select COMMON_CLKDEV + select CLKDEV_LOOKUP select GENERIC_ALLOCATOR select ARCH_HAS_HOLES_MEMORYMODEL help @@ -837,7 +837,7 @@ config PLAT_SPEAR bool "ST SPEAr" select ARM_AMBA select ARCH_REQUIRE_GPIOLIB - select COMMON_CLKDEV + select CLKDEV_LOOKUP select GENERIC_CLOCKEVENTS select HAVE_CLK help diff --git a/arch/arm/common/Kconfig b/arch/arm/common/Kconfig index 0a34c8186924..778655f0257a 100644 --- a/arch/arm/common/Kconfig +++ b/arch/arm/common/Kconfig @@ -37,7 +37,3 @@ config SHARP_PARAM config SHARP_SCOOP bool - -config COMMON_CLKDEV - bool - select HAVE_CLK diff --git a/arch/arm/common/Makefile b/arch/arm/common/Makefile index e6e8664a9413..799e140274f1 100644 --- a/arch/arm/common/Makefile +++ b/arch/arm/common/Makefile @@ -16,4 +16,3 @@ obj-$(CONFIG_SHARP_SCOOP) += scoop.o obj-$(CONFIG_ARCH_IXP2000) += uengine.o obj-$(CONFIG_ARCH_IXP23XX) += uengine.o obj-$(CONFIG_PCI_HOST_ITE8152) += it8152.o -obj-$(CONFIG_COMMON_CLKDEV) += clkdev.o diff --git a/arch/arm/common/clkdev.c b/arch/arm/common/clkdev.c deleted file mode 100644 index e2b2bb66e094..000000000000 --- a/arch/arm/common/clkdev.c +++ /dev/null @@ -1,179 +0,0 @@ -/* - * arch/arm/common/clkdev.c - * - * Copyright (C) 2008 Russell King. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * Helper for the clk API to assist looking up a struct clk. - */ -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include - -static LIST_HEAD(clocks); -static DEFINE_MUTEX(clocks_mutex); - -/* - * Find the correct struct clk for the device and connection ID. - * We do slightly fuzzy matching here: - * An entry with a NULL ID is assumed to be a wildcard. - * If an entry has a device ID, it must match - * If an entry has a connection ID, it must match - * Then we take the most specific entry - with the following - * order of precedence: dev+con > dev only > con only. - */ -static struct clk *clk_find(const char *dev_id, const char *con_id) -{ - struct clk_lookup *p; - struct clk *clk = NULL; - int match, best = 0; - - list_for_each_entry(p, &clocks, node) { - match = 0; - if (p->dev_id) { - if (!dev_id || strcmp(p->dev_id, dev_id)) - continue; - match += 2; - } - if (p->con_id) { - if (!con_id || strcmp(p->con_id, con_id)) - continue; - match += 1; - } - - if (match > best) { - clk = p->clk; - if (match != 3) - best = match; - else - break; - } - } - return clk; -} - -struct clk *clk_get_sys(const char *dev_id, const char *con_id) -{ - struct clk *clk; - - mutex_lock(&clocks_mutex); - clk = clk_find(dev_id, con_id); - if (clk && !__clk_get(clk)) - clk = NULL; - mutex_unlock(&clocks_mutex); - - return clk ? clk : ERR_PTR(-ENOENT); -} -EXPORT_SYMBOL(clk_get_sys); - -struct clk *clk_get(struct device *dev, const char *con_id) -{ - const char *dev_id = dev ? dev_name(dev) : NULL; - - return clk_get_sys(dev_id, con_id); -} -EXPORT_SYMBOL(clk_get); - -void clk_put(struct clk *clk) -{ - __clk_put(clk); -} -EXPORT_SYMBOL(clk_put); - -void clkdev_add(struct clk_lookup *cl) -{ - mutex_lock(&clocks_mutex); - list_add_tail(&cl->node, &clocks); - mutex_unlock(&clocks_mutex); -} -EXPORT_SYMBOL(clkdev_add); - -void __init clkdev_add_table(struct clk_lookup *cl, size_t num) -{ - mutex_lock(&clocks_mutex); - while (num--) { - list_add_tail(&cl->node, &clocks); - cl++; - } - mutex_unlock(&clocks_mutex); -} - -#define MAX_DEV_ID 20 -#define MAX_CON_ID 16 - -struct clk_lookup_alloc { - struct clk_lookup cl; - char dev_id[MAX_DEV_ID]; - char con_id[MAX_CON_ID]; -}; - -struct clk_lookup *clkdev_alloc(struct clk *clk, const char *con_id, - const char *dev_fmt, ...) -{ - struct clk_lookup_alloc *cla; - - cla = kzalloc(sizeof(*cla), GFP_KERNEL); - if (!cla) - return NULL; - - cla->cl.clk = clk; - if (con_id) { - strlcpy(cla->con_id, con_id, sizeof(cla->con_id)); - cla->cl.con_id = cla->con_id; - } - - if (dev_fmt) { - va_list ap; - - va_start(ap, dev_fmt); - vscnprintf(cla->dev_id, sizeof(cla->dev_id), dev_fmt, ap); - cla->cl.dev_id = cla->dev_id; - va_end(ap); - } - - return &cla->cl; -} -EXPORT_SYMBOL(clkdev_alloc); - -int clk_add_alias(const char *alias, const char *alias_dev_name, char *id, - struct device *dev) -{ - struct clk *r = clk_get(dev, id); - struct clk_lookup *l; - - if (IS_ERR(r)) - return PTR_ERR(r); - - l = clkdev_alloc(r, alias, alias_dev_name); - clk_put(r); - if (!l) - return -ENODEV; - clkdev_add(l); - return 0; -} -EXPORT_SYMBOL(clk_add_alias); - -/* - * clkdev_drop - remove a clock dynamically allocated - */ -void clkdev_drop(struct clk_lookup *cl) -{ - mutex_lock(&clocks_mutex); - list_del(&cl->node); - mutex_unlock(&clocks_mutex); - kfree(cl); -} -EXPORT_SYMBOL(clkdev_drop); diff --git a/arch/arm/include/asm/clkdev.h b/arch/arm/include/asm/clkdev.h index b56c1389b6fa..765d33222369 100644 --- a/arch/arm/include/asm/clkdev.h +++ b/arch/arm/include/asm/clkdev.h @@ -12,23 +12,13 @@ #ifndef __ASM_CLKDEV_H #define __ASM_CLKDEV_H -struct clk; -struct device; +#include -struct clk_lookup { - struct list_head node; - const char *dev_id; - const char *con_id; - struct clk *clk; -}; +#include -struct clk_lookup *clkdev_alloc(struct clk *clk, const char *con_id, - const char *dev_fmt, ...); - -void clkdev_add(struct clk_lookup *cl); -void clkdev_drop(struct clk_lookup *cl); - -void clkdev_add_table(struct clk_lookup *, size_t); -int clk_add_alias(const char *, const char *, char *, struct device *); +static inline struct clk_lookup_alloc *__clkdev_alloc(size_t size) +{ + return kzalloc(size, GFP_KERNEL); +} #endif diff --git a/arch/arm/mach-bcmring/clock.c b/arch/arm/mach-bcmring/clock.c index 14bafc38f2dc..ad237a42d265 100644 --- a/arch/arm/mach-bcmring/clock.c +++ b/arch/arm/mach-bcmring/clock.c @@ -21,13 +21,12 @@ #include #include #include +#include #include #include #include #include -#include - #include "clock.h" #define clk_is_primary(x) ((x)->type & CLK_TYPE_PRIMARY) diff --git a/arch/arm/mach-bcmring/core.c b/arch/arm/mach-bcmring/core.c index d3f959e92b2d..ed96ef400474 100644 --- a/arch/arm/mach-bcmring/core.c +++ b/arch/arm/mach-bcmring/core.c @@ -30,10 +30,10 @@ #include #include #include +#include #include #include -#include #include #include #include diff --git a/arch/arm/mach-davinci/clock.h b/arch/arm/mach-davinci/clock.h index 11099980b58b..0dd22031ec62 100644 --- a/arch/arm/mach-davinci/clock.h +++ b/arch/arm/mach-davinci/clock.h @@ -68,7 +68,7 @@ #ifndef __ASSEMBLER__ #include -#include +#include #define PLLSTAT_GOSTAT BIT(0) #define PLLCMD_GOSET BIT(0) diff --git a/arch/arm/mach-ep93xx/clock.c b/arch/arm/mach-ep93xx/clock.c index ef06c66a6f16..ca4de7105097 100644 --- a/arch/arm/mach-ep93xx/clock.c +++ b/arch/arm/mach-ep93xx/clock.c @@ -19,10 +19,10 @@ #include #include #include +#include #include -#include #include diff --git a/arch/arm/mach-imx/clock-imx1.c b/arch/arm/mach-imx/clock-imx1.c index daca30b2d5b1..3938a563b280 100644 --- a/arch/arm/mach-imx/clock-imx1.c +++ b/arch/arm/mach-imx/clock-imx1.c @@ -22,8 +22,7 @@ #include #include #include - -#include +#include #include #include diff --git a/arch/arm/mach-imx/clock-imx21.c b/arch/arm/mach-imx/clock-imx21.c index cf15ea516a72..d7056559715a 100644 --- a/arch/arm/mach-imx/clock-imx21.c +++ b/arch/arm/mach-imx/clock-imx21.c @@ -21,11 +21,11 @@ #include #include #include +#include #include #include #include -#include #include #define IO_ADDR_CCM(off) (MX21_IO_ADDRESS(MX21_CCM_BASE_ADDR + (off))) diff --git a/arch/arm/mach-imx/clock-imx27.c b/arch/arm/mach-imx/clock-imx27.c index 98a25bada783..ca1017b9028d 100644 --- a/arch/arm/mach-imx/clock-imx27.c +++ b/arch/arm/mach-imx/clock-imx27.c @@ -21,8 +21,8 @@ #include #include #include +#include -#include #include #include diff --git a/arch/arm/mach-integrator/core.c b/arch/arm/mach-integrator/core.c index 8f4fb6d638f7..b8e884b450da 100644 --- a/arch/arm/mach-integrator/core.c +++ b/arch/arm/mach-integrator/core.c @@ -21,9 +21,8 @@ #include #include #include +#include -#include -#include #include #include #include diff --git a/arch/arm/mach-integrator/impd1.c b/arch/arm/mach-integrator/impd1.c index fd684bf205e5..5db574f8ae3f 100644 --- a/arch/arm/mach-integrator/impd1.c +++ b/arch/arm/mach-integrator/impd1.c @@ -22,9 +22,8 @@ #include #include #include +#include -#include -#include #include #include #include diff --git a/arch/arm/mach-integrator/integrator_cp.c b/arch/arm/mach-integrator/integrator_cp.c index 6258c90d020c..9403d2fa13a3 100644 --- a/arch/arm/mach-integrator/integrator_cp.c +++ b/arch/arm/mach-integrator/integrator_cp.c @@ -21,9 +21,8 @@ #include #include #include +#include -#include -#include #include #include #include diff --git a/arch/arm/mach-lpc32xx/clock.c b/arch/arm/mach-lpc32xx/clock.c index 32d63796430a..da0e6498110a 100644 --- a/arch/arm/mach-lpc32xx/clock.c +++ b/arch/arm/mach-lpc32xx/clock.c @@ -90,10 +90,9 @@ #include #include #include +#include #include -#include -#include #include #include "clock.h" #include "common.h" diff --git a/arch/arm/mach-mmp/clock.h b/arch/arm/mach-mmp/clock.h index 016ae94691c0..9b027d7491f5 100644 --- a/arch/arm/mach-mmp/clock.h +++ b/arch/arm/mach-mmp/clock.h @@ -6,7 +6,7 @@ * published by the Free Software Foundation. */ -#include +#include struct clkops { void (*enable)(struct clk *); diff --git a/arch/arm/mach-mx25/clock.c b/arch/arm/mach-mx25/clock.c index 9e4a5578c2fb..00dcb08019e9 100644 --- a/arch/arm/mach-mx25/clock.c +++ b/arch/arm/mach-mx25/clock.c @@ -21,8 +21,7 @@ #include #include #include - -#include +#include #include #include diff --git a/arch/arm/mach-mx3/clock-imx31.c b/arch/arm/mach-mx3/clock-imx31.c index 109e98f323e0..1cd8b40b7676 100644 --- a/arch/arm/mach-mx3/clock-imx31.c +++ b/arch/arm/mach-mx3/clock-imx31.c @@ -23,8 +23,8 @@ #include #include #include +#include -#include #include #include diff --git a/arch/arm/mach-mx3/clock-imx35.c b/arch/arm/mach-mx3/clock-imx35.c index 61e4a318980a..819dd809615a 100644 --- a/arch/arm/mach-mx3/clock-imx35.c +++ b/arch/arm/mach-mx3/clock-imx35.c @@ -21,8 +21,7 @@ #include #include #include - -#include +#include #include #include diff --git a/arch/arm/mach-mx5/clock-mx51.c b/arch/arm/mach-mx5/clock-mx51.c index 8ac36d882927..5975edb47de8 100644 --- a/arch/arm/mach-mx5/clock-mx51.c +++ b/arch/arm/mach-mx5/clock-mx51.c @@ -14,8 +14,8 @@ #include #include #include +#include -#include #include #include diff --git a/arch/arm/mach-mxc91231/clock.c b/arch/arm/mach-mxc91231/clock.c index 5c85075d8a56..9fab505f1eb1 100644 --- a/arch/arm/mach-mxc91231/clock.c +++ b/arch/arm/mach-mxc91231/clock.c @@ -2,12 +2,12 @@ #include #include #include +#include #include #include #include -#include #include #include diff --git a/arch/arm/mach-nomadik/clock.c b/arch/arm/mach-nomadik/clock.c index 89f793adf776..48a59f24e10c 100644 --- a/arch/arm/mach-nomadik/clock.c +++ b/arch/arm/mach-nomadik/clock.c @@ -7,7 +7,7 @@ #include #include #include -#include +#include #include "clock.h" /* diff --git a/arch/arm/mach-nuc93x/clock.h b/arch/arm/mach-nuc93x/clock.h index 18e51be4816f..4de1f1da9dc5 100644 --- a/arch/arm/mach-nuc93x/clock.h +++ b/arch/arm/mach-nuc93x/clock.h @@ -10,7 +10,7 @@ * the Free Software Foundation; either version 2 of the License. */ -#include +#include void nuc93x_clk_enable(struct clk *clk, int enable); void clks_register(struct clk_lookup *clks, size_t num); diff --git a/arch/arm/mach-omap1/clock.c b/arch/arm/mach-omap1/clock.c index b8c7fb9d7921..84ef70476b51 100644 --- a/arch/arm/mach-omap1/clock.c +++ b/arch/arm/mach-omap1/clock.c @@ -17,9 +17,9 @@ #include #include #include +#include #include -#include #include #include diff --git a/arch/arm/mach-omap2/dpll3xxx.c b/arch/arm/mach-omap2/dpll3xxx.c index ed8d330522f1..ebb888f59365 100644 --- a/arch/arm/mach-omap2/dpll3xxx.c +++ b/arch/arm/mach-omap2/dpll3xxx.c @@ -26,10 +26,10 @@ #include #include #include +#include #include #include -#include #include "clock.h" #include "prm.h" diff --git a/arch/arm/mach-pnx4008/clock.c b/arch/arm/mach-pnx4008/clock.c index 9d1975fa4d9f..a4a3819c96cb 100644 --- a/arch/arm/mach-pnx4008/clock.c +++ b/arch/arm/mach-pnx4008/clock.c @@ -21,8 +21,7 @@ #include #include #include - -#include +#include #include #include diff --git a/arch/arm/mach-pxa/clock.c b/arch/arm/mach-pxa/clock.c index abba0089a2ae..4e4a84be96ba 100644 --- a/arch/arm/mach-pxa/clock.c +++ b/arch/arm/mach-pxa/clock.c @@ -11,8 +11,8 @@ #include #include #include +#include -#include #include #include diff --git a/arch/arm/mach-pxa/clock.h b/arch/arm/mach-pxa/clock.h index d8488742b807..12cc0e87e6c4 100644 --- a/arch/arm/mach-pxa/clock.h +++ b/arch/arm/mach-pxa/clock.h @@ -1,4 +1,4 @@ -#include +#include struct clkops { void (*enable)(struct clk *); diff --git a/arch/arm/mach-realview/core.c b/arch/arm/mach-realview/core.c index 07c08151dfe6..3d915b1ccdb5 100644 --- a/arch/arm/mach-realview/core.c +++ b/arch/arm/mach-realview/core.c @@ -30,8 +30,8 @@ #include #include #include +#include -#include #include #include #include @@ -47,7 +47,6 @@ #include -#include #include #include #include diff --git a/arch/arm/mach-shmobile/Kconfig b/arch/arm/mach-shmobile/Kconfig index 54b479c35ee0..f8f06e9fec35 100644 --- a/arch/arm/mach-shmobile/Kconfig +++ b/arch/arm/mach-shmobile/Kconfig @@ -6,7 +6,7 @@ config ARCH_SH7367 bool "SH-Mobile G3 (SH7367)" select CPU_V6 select HAVE_CLK - select COMMON_CLKDEV + select CLKDEV_LOOKUP select SH_CLK_CPG select GENERIC_CLOCKEVENTS @@ -14,7 +14,7 @@ config ARCH_SH7377 bool "SH-Mobile G4 (SH7377)" select CPU_V7 select HAVE_CLK - select COMMON_CLKDEV + select CLKDEV_LOOKUP select SH_CLK_CPG select GENERIC_CLOCKEVENTS @@ -22,7 +22,7 @@ config ARCH_SH7372 bool "SH-Mobile AP4 (SH7372)" select CPU_V7 select HAVE_CLK - select COMMON_CLKDEV + select CLKDEV_LOOKUP select SH_CLK_CPG select GENERIC_CLOCKEVENTS diff --git a/arch/arm/mach-shmobile/clock-sh7367.c b/arch/arm/mach-shmobile/clock-sh7367.c index 9f78729098f2..6b186aefcbd6 100644 --- a/arch/arm/mach-shmobile/clock-sh7367.c +++ b/arch/arm/mach-shmobile/clock-sh7367.c @@ -20,8 +20,8 @@ #include #include #include +#include #include -#include /* SH7367 registers */ #define RTFRQCR 0xe6150000 diff --git a/arch/arm/mach-shmobile/clock-sh7372.c b/arch/arm/mach-shmobile/clock-sh7372.c index 8565aefa21fd..445112adba46 100644 --- a/arch/arm/mach-shmobile/clock-sh7372.c +++ b/arch/arm/mach-shmobile/clock-sh7372.c @@ -20,8 +20,8 @@ #include #include #include +#include #include -#include /* SH7372 registers */ #define FRQCRA 0xe6150000 diff --git a/arch/arm/mach-shmobile/clock-sh7377.c b/arch/arm/mach-shmobile/clock-sh7377.c index f91395aeb9ab..95942466e63f 100644 --- a/arch/arm/mach-shmobile/clock-sh7377.c +++ b/arch/arm/mach-shmobile/clock-sh7377.c @@ -20,8 +20,8 @@ #include #include #include +#include #include -#include /* SH7377 registers */ #define RTFRQCR 0xe6150000 diff --git a/arch/arm/mach-tcc8k/clock.c b/arch/arm/mach-tcc8k/clock.c index ba32a15127ab..3970a9cdce26 100644 --- a/arch/arm/mach-tcc8k/clock.c +++ b/arch/arm/mach-tcc8k/clock.c @@ -12,8 +12,7 @@ #include #include #include - -#include +#include #include #include diff --git a/arch/arm/mach-tegra/clock.c b/arch/arm/mach-tegra/clock.c index ae19f95585be..77948e0f4909 100644 --- a/arch/arm/mach-tegra/clock.c +++ b/arch/arm/mach-tegra/clock.c @@ -25,7 +25,7 @@ #include #include #include -#include +#include #include "clock.h" #include "board.h" diff --git a/arch/arm/mach-tegra/clock.h b/arch/arm/mach-tegra/clock.h index 94fd859770f1..083a4cfc6cf0 100644 --- a/arch/arm/mach-tegra/clock.h +++ b/arch/arm/mach-tegra/clock.h @@ -21,7 +21,7 @@ #define __MACH_TEGRA_CLOCK_H #include -#include +#include #define DIV_BUS (1 << 0) #define DIV_U71 (1 << 1) diff --git a/arch/arm/mach-tegra/tegra2_clocks.c b/arch/arm/mach-tegra/tegra2_clocks.c index ae3b308e22a4..f0dae6d8ba52 100644 --- a/arch/arm/mach-tegra/tegra2_clocks.c +++ b/arch/arm/mach-tegra/tegra2_clocks.c @@ -24,8 +24,7 @@ #include #include #include - -#include +#include #include diff --git a/arch/arm/mach-u300/clock.c b/arch/arm/mach-u300/clock.c index 7458fc6df5c6..fabcc49abe80 100644 --- a/arch/arm/mach-u300/clock.c +++ b/arch/arm/mach-u300/clock.c @@ -25,8 +25,8 @@ #include #include #include +#include -#include #include #include diff --git a/arch/arm/mach-ux500/clock.c b/arch/arm/mach-ux500/clock.c index 1675047daf20..531de5c63641 100644 --- a/arch/arm/mach-ux500/clock.c +++ b/arch/arm/mach-ux500/clock.c @@ -13,8 +13,7 @@ #include #include #include - -#include +#include #include #include diff --git a/arch/arm/mach-versatile/core.c b/arch/arm/mach-versatile/core.c index e38acb0f89c8..8c1ca1d63538 100644 --- a/arch/arm/mach-versatile/core.c +++ b/arch/arm/mach-versatile/core.c @@ -31,8 +31,8 @@ #include #include #include +#include -#include #include #include #include @@ -46,7 +46,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/arm/mach-vexpress/ct-ca9x4.c b/arch/arm/mach-vexpress/ct-ca9x4.c index c2e405a9e025..26a02eb57571 100644 --- a/arch/arm/mach-vexpress/ct-ca9x4.c +++ b/arch/arm/mach-vexpress/ct-ca9x4.c @@ -8,8 +8,8 @@ #include #include #include +#include -#include #include #include #include @@ -18,7 +18,6 @@ #include #include -#include #include #include diff --git a/arch/arm/mach-vexpress/v2m.c b/arch/arm/mach-vexpress/v2m.c index 7eaa232180a5..d374a78986e8 100644 --- a/arch/arm/mach-vexpress/v2m.c +++ b/arch/arm/mach-vexpress/v2m.c @@ -11,15 +11,14 @@ #include #include #include +#include -#include #include #include #include #include #include -#include #include #include diff --git a/arch/arm/mach-w90x900/clock.h b/arch/arm/mach-w90x900/clock.h index c56ddab3d912..b88a1b16b2e9 100644 --- a/arch/arm/mach-w90x900/clock.h +++ b/arch/arm/mach-w90x900/clock.h @@ -10,7 +10,7 @@ * the Free Software Foundation; either version 2 of the License. */ -#include +#include void nuc900_clk_enable(struct clk *clk, int enable); void nuc900_subclk_enable(struct clk *clk, int enable); diff --git a/arch/arm/plat-omap/Kconfig b/arch/arm/plat-omap/Kconfig index 92c5bb7909f5..c9408434a855 100644 --- a/arch/arm/plat-omap/Kconfig +++ b/arch/arm/plat-omap/Kconfig @@ -11,13 +11,13 @@ choice config ARCH_OMAP1 bool "TI OMAP1" - select COMMON_CLKDEV + select CLKDEV_LOOKUP help "Systems based on omap7xx, omap15xx or omap16xx" config ARCH_OMAP2PLUS bool "TI OMAP2/3/4" - select COMMON_CLKDEV + select CLKDEV_LOOKUP help "Systems based on OMAP2, OMAP3 or OMAP4" diff --git a/arch/arm/plat-omap/include/plat/clkdev_omap.h b/arch/arm/plat-omap/include/plat/clkdev_omap.h index bb937f3fabed..4b2028ab4d2b 100644 --- a/arch/arm/plat-omap/include/plat/clkdev_omap.h +++ b/arch/arm/plat-omap/include/plat/clkdev_omap.h @@ -8,7 +8,7 @@ #ifndef __ARCH_ARM_PLAT_OMAP_INCLUDE_PLAT_CLKDEV_OMAP_H #define __ARCH_ARM_PLAT_OMAP_INCLUDE_PLAT_CLKDEV_OMAP_H -#include +#include struct omap_clk { u16 cpu; diff --git a/arch/arm/plat-spear/include/plat/clock.h b/arch/arm/plat-spear/include/plat/clock.h index 298bafc0a52f..2572260f990f 100644 --- a/arch/arm/plat-spear/include/plat/clock.h +++ b/arch/arm/plat-spear/include/plat/clock.h @@ -15,7 +15,7 @@ #define __PLAT_CLOCK_H #include -#include +#include #include /* clk structure flags */ diff --git a/arch/arm/plat-stmp3xxx/clock.c b/arch/arm/plat-stmp3xxx/clock.c index e593a2a801c6..2e712e17ce72 100644 --- a/arch/arm/plat-stmp3xxx/clock.c +++ b/arch/arm/plat-stmp3xxx/clock.c @@ -25,9 +25,9 @@ #include #include #include +#include #include -#include #include #include diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 5c075f562eba..cfc510608039 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -1,7 +1,7 @@ config SUPERH def_bool y select EMBEDDED - select HAVE_CLK + select CLKDEV_LOOKUP select HAVE_IDE if HAS_IOPORT select HAVE_MEMBLOCK select HAVE_OPROFILE diff --git a/arch/sh/boards/mach-highlander/setup.c b/arch/sh/boards/mach-highlander/setup.c index a5ecfbacaf36..87618c91d178 100644 --- a/arch/sh/boards/mach-highlander/setup.c +++ b/arch/sh/boards/mach-highlander/setup.c @@ -24,10 +24,10 @@ #include #include #include +#include #include #include #include -#include #include #include #include diff --git a/arch/sh/include/asm/clkdev.h b/arch/sh/include/asm/clkdev.h index 5645f358128b..6ba91868201c 100644 --- a/arch/sh/include/asm/clkdev.h +++ b/arch/sh/include/asm/clkdev.h @@ -1,9 +1,5 @@ /* - * arch/sh/include/asm/clkdev.h - * - * Cloned from arch/arm/include/asm/clkdev.h: - * - * Copyright (C) 2008 Russell King. + * Copyright (C) 2010 Paul Mundt * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -11,25 +7,25 @@ * * Helper for the clk API to assist looking up a struct clk. */ -#ifndef __ASM_CLKDEV_H -#define __ASM_CLKDEV_H -struct clk; +#ifndef __CLKDEV__H_ +#define __CLKDEV__H_ -struct clk_lookup { - struct list_head node; - const char *dev_id; - const char *con_id; - struct clk *clk; -}; +#include +#include +#include -struct clk_lookup *clkdev_alloc(struct clk *clk, const char *con_id, - const char *dev_fmt, ...); +#include -void clkdev_add(struct clk_lookup *cl); -void clkdev_drop(struct clk_lookup *cl); +static inline struct clk_lookup_alloc *__clkdev_alloc(size_t size) +{ + if (!slab_is_available()) + return alloc_bootmem_low_pages(size); + else + return kzalloc(size, GFP_KERNEL); +} -void clkdev_add_table(struct clk_lookup *, size_t); -int clk_add_alias(const char *, const char *, char *, struct device *); +#define __clk_put(clk) +#define __clk_get(clk) ({ 1; }) -#endif +#endif /* __CLKDEV_H__ */ diff --git a/arch/sh/kernel/Makefile b/arch/sh/kernel/Makefile index 8eed6a485446..cf6522179523 100644 --- a/arch/sh/kernel/Makefile +++ b/arch/sh/kernel/Makefile @@ -11,7 +11,7 @@ endif CFLAGS_REMOVE_return_address.o = -pg -obj-y := clkdev.o debugtraps.o dma-nommu.o dumpstack.o \ +obj-y := debugtraps.o dma-nommu.o dumpstack.o \ idle.o io.o irq.o irq_$(BITS).o kdebugfs.o \ machvec.o nmi_debug.o process.o \ process_$(BITS).o ptrace.o ptrace_$(BITS).o \ diff --git a/arch/sh/kernel/clkdev.c b/arch/sh/kernel/clkdev.c deleted file mode 100644 index 1f800ef4a735..000000000000 --- a/arch/sh/kernel/clkdev.c +++ /dev/null @@ -1,171 +0,0 @@ -/* - * arch/sh/kernel/clkdev.c - * - * Cloned from arch/arm/common/clkdev.c: - * - * Copyright (C) 2008 Russell King. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * Helper for the clk API to assist looking up a struct clk. - */ -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -static LIST_HEAD(clocks); -static DEFINE_MUTEX(clocks_mutex); - -/* - * Find the correct struct clk for the device and connection ID. - * We do slightly fuzzy matching here: - * An entry with a NULL ID is assumed to be a wildcard. - * If an entry has a device ID, it must match - * If an entry has a connection ID, it must match - * Then we take the most specific entry - with the following - * order of precedence: dev+con > dev only > con only. - */ -static struct clk *clk_find(const char *dev_id, const char *con_id) -{ - struct clk_lookup *p; - struct clk *clk = NULL; - int match, best = 0; - - list_for_each_entry(p, &clocks, node) { - match = 0; - if (p->dev_id) { - if (!dev_id || strcmp(p->dev_id, dev_id)) - continue; - match += 2; - } - if (p->con_id) { - if (!con_id || strcmp(p->con_id, con_id)) - continue; - match += 1; - } - if (match == 0) - continue; - - if (match > best) { - clk = p->clk; - best = match; - } - } - return clk; -} - -struct clk *clk_get_sys(const char *dev_id, const char *con_id) -{ - struct clk *clk; - - mutex_lock(&clocks_mutex); - clk = clk_find(dev_id, con_id); - mutex_unlock(&clocks_mutex); - - return clk ? clk : ERR_PTR(-ENOENT); -} -EXPORT_SYMBOL(clk_get_sys); - -void clkdev_add(struct clk_lookup *cl) -{ - mutex_lock(&clocks_mutex); - list_add_tail(&cl->node, &clocks); - mutex_unlock(&clocks_mutex); -} -EXPORT_SYMBOL(clkdev_add); - -void __init clkdev_add_table(struct clk_lookup *cl, size_t num) -{ - mutex_lock(&clocks_mutex); - while (num--) { - list_add_tail(&cl->node, &clocks); - cl++; - } - mutex_unlock(&clocks_mutex); -} - -#define MAX_DEV_ID 20 -#define MAX_CON_ID 16 - -struct clk_lookup_alloc { - struct clk_lookup cl; - char dev_id[MAX_DEV_ID]; - char con_id[MAX_CON_ID]; -}; - -struct clk_lookup * __init_refok -clkdev_alloc(struct clk *clk, const char *con_id, const char *dev_fmt, ...) -{ - struct clk_lookup_alloc *cla; - - if (!slab_is_available()) - cla = alloc_bootmem_low_pages(sizeof(*cla)); - else - cla = kzalloc(sizeof(*cla), GFP_KERNEL); - - if (!cla) - return NULL; - - cla->cl.clk = clk; - if (con_id) { - strlcpy(cla->con_id, con_id, sizeof(cla->con_id)); - cla->cl.con_id = cla->con_id; - } - - if (dev_fmt) { - va_list ap; - - va_start(ap, dev_fmt); - vscnprintf(cla->dev_id, sizeof(cla->dev_id), dev_fmt, ap); - cla->cl.dev_id = cla->dev_id; - va_end(ap); - } - - return &cla->cl; -} -EXPORT_SYMBOL(clkdev_alloc); - -int clk_add_alias(const char *alias, const char *alias_dev_name, char *id, - struct device *dev) -{ - struct clk *r = clk_get(dev, id); - struct clk_lookup *l; - - if (IS_ERR(r)) - return PTR_ERR(r); - - l = clkdev_alloc(r, alias, alias_dev_name); - clk_put(r); - if (!l) - return -ENODEV; - clkdev_add(l); - return 0; -} -EXPORT_SYMBOL(clk_add_alias); - -/* - * clkdev_drop - remove a clock dynamically allocated - */ -void clkdev_drop(struct clk_lookup *cl) -{ - struct clk_lookup_alloc *cla = container_of(cl, struct clk_lookup_alloc, cl); - - mutex_lock(&clocks_mutex); - list_del(&cl->node); - mutex_unlock(&clocks_mutex); - kfree(cla); -} -EXPORT_SYMBOL(clkdev_drop); diff --git a/arch/sh/kernel/cpu/clock-cpg.c b/arch/sh/kernel/cpu/clock-cpg.c index e2f63d68da51..dd0e0f211359 100644 --- a/arch/sh/kernel/cpu/clock-cpg.c +++ b/arch/sh/kernel/cpu/clock-cpg.c @@ -2,7 +2,7 @@ #include #include #include -#include +#include #include static struct clk master_clk = { diff --git a/arch/sh/kernel/cpu/clock.c b/arch/sh/kernel/cpu/clock.c index 50f887dda565..4187cf4fe185 100644 --- a/arch/sh/kernel/cpu/clock.c +++ b/arch/sh/kernel/cpu/clock.c @@ -48,20 +48,4 @@ int __init clk_init(void) return ret; } -/* - * Returns a clock. Note that we first try to use device id on the bus - * and clock name. If this fails, we try to use clock name only. - */ -struct clk *clk_get(struct device *dev, const char *con_id) -{ - const char *dev_id = dev ? dev_name(dev) : NULL; - - return clk_get_sys(dev_id, con_id); -} -EXPORT_SYMBOL_GPL(clk_get); - -void clk_put(struct clk *clk) -{ -} -EXPORT_SYMBOL_GPL(clk_put); diff --git a/arch/sh/kernel/cpu/sh4/clock-sh4-202.c b/arch/sh/kernel/cpu/sh4/clock-sh4-202.c index 4eabc68cd753..6c1492b8431a 100644 --- a/arch/sh/kernel/cpu/sh4/clock-sh4-202.c +++ b/arch/sh/kernel/cpu/sh4/clock-sh4-202.c @@ -13,7 +13,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7343.c b/arch/sh/kernel/cpu/sh4a/clock-sh7343.c index 71291ae201b9..93c646072c1b 100644 --- a/arch/sh/kernel/cpu/sh4a/clock-sh7343.c +++ b/arch/sh/kernel/cpu/sh4a/clock-sh7343.c @@ -21,7 +21,7 @@ #include #include #include -#include +#include #include /* SH7343 registers */ diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7366.c b/arch/sh/kernel/cpu/sh4a/clock-sh7366.c index 7ce5bbcd4084..049dc0628ccc 100644 --- a/arch/sh/kernel/cpu/sh4a/clock-sh7366.c +++ b/arch/sh/kernel/cpu/sh4a/clock-sh7366.c @@ -21,7 +21,7 @@ #include #include #include -#include +#include #include /* SH7366 registers */ diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7722.c b/arch/sh/kernel/cpu/sh4a/clock-sh7722.c index 2030f3d9fac7..9d23a36f0647 100644 --- a/arch/sh/kernel/cpu/sh4a/clock-sh7722.c +++ b/arch/sh/kernel/cpu/sh4a/clock-sh7722.c @@ -21,7 +21,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7723.c b/arch/sh/kernel/cpu/sh4a/clock-sh7723.c index d3938f0d3702..55493cd5bd8f 100644 --- a/arch/sh/kernel/cpu/sh4a/clock-sh7723.c +++ b/arch/sh/kernel/cpu/sh4a/clock-sh7723.c @@ -22,7 +22,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7724.c b/arch/sh/kernel/cpu/sh4a/clock-sh7724.c index 2d9700c6b53a..527936bb3ce0 100644 --- a/arch/sh/kernel/cpu/sh4a/clock-sh7724.c +++ b/arch/sh/kernel/cpu/sh4a/clock-sh7724.c @@ -22,7 +22,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7757.c b/arch/sh/kernel/cpu/sh4a/clock-sh7757.c index ce39a2ae8c6c..e073e3eb4c3d 100644 --- a/arch/sh/kernel/cpu/sh4a/clock-sh7757.c +++ b/arch/sh/kernel/cpu/sh4a/clock-sh7757.c @@ -12,7 +12,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7763.c b/arch/sh/kernel/cpu/sh4a/clock-sh7763.c index 1f1df48008cd..599630fc4d3b 100644 --- a/arch/sh/kernel/cpu/sh4a/clock-sh7763.c +++ b/arch/sh/kernel/cpu/sh4a/clock-sh7763.c @@ -13,7 +13,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7780.c b/arch/sh/kernel/cpu/sh4a/clock-sh7780.c index 62d706350060..8894926479a6 100644 --- a/arch/sh/kernel/cpu/sh4a/clock-sh7780.c +++ b/arch/sh/kernel/cpu/sh4a/clock-sh7780.c @@ -12,7 +12,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7785.c b/arch/sh/kernel/cpu/sh4a/clock-sh7785.c index c3e458aaa2b7..2d960247f3eb 100644 --- a/arch/sh/kernel/cpu/sh4a/clock-sh7785.c +++ b/arch/sh/kernel/cpu/sh4a/clock-sh7785.c @@ -14,7 +14,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7786.c b/arch/sh/kernel/cpu/sh4a/clock-sh7786.c index 597c9fbe49c6..42e403be9076 100644 --- a/arch/sh/kernel/cpu/sh4a/clock-sh7786.c +++ b/arch/sh/kernel/cpu/sh4a/clock-sh7786.c @@ -13,7 +13,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/sh/kernel/cpu/sh4a/clock-shx3.c b/arch/sh/kernel/cpu/sh4a/clock-shx3.c index 4f70df6b6169..1afdb93b8ccb 100644 --- a/arch/sh/kernel/cpu/sh4a/clock-shx3.c +++ b/arch/sh/kernel/cpu/sh4a/clock-shx3.c @@ -14,7 +14,7 @@ #include #include #include -#include +#include #include #include diff --git a/drivers/Kconfig b/drivers/Kconfig index a2b902f4d437..3d93b3a3d630 100644 --- a/drivers/Kconfig +++ b/drivers/Kconfig @@ -111,4 +111,6 @@ source "drivers/xen/Kconfig" source "drivers/staging/Kconfig" source "drivers/platform/Kconfig" + +source "drivers/clk/Kconfig" endmenu diff --git a/drivers/Makefile b/drivers/Makefile index 14cf9077bb2b..4af7d5b124ce 100644 --- a/drivers/Makefile +++ b/drivers/Makefile @@ -114,3 +114,5 @@ obj-$(CONFIG_VLYNQ) += vlynq/ obj-$(CONFIG_STAGING) += staging/ obj-y += platform/ obj-y += ieee802154/ +#common clk code +obj-y += clk/ diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig new file mode 100644 index 000000000000..4168c8896e16 --- /dev/null +++ b/drivers/clk/Kconfig @@ -0,0 +1,4 @@ + +config CLKDEV_LOOKUP + bool + select HAVE_CLK diff --git a/drivers/clk/Makefile b/drivers/clk/Makefile new file mode 100644 index 000000000000..07613fa172c9 --- /dev/null +++ b/drivers/clk/Makefile @@ -0,0 +1,2 @@ + +obj-$(CONFIG_CLKDEV_LOOKUP) += clkdev.o diff --git a/drivers/clk/clkdev.c b/drivers/clk/clkdev.c new file mode 100644 index 000000000000..0fc0a79852de --- /dev/null +++ b/drivers/clk/clkdev.c @@ -0,0 +1,176 @@ +/* + * drivers/clk/clkdev.c + * + * Copyright (C) 2008 Russell King. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * Helper for the clk API to assist looking up a struct clk. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static LIST_HEAD(clocks); +static DEFINE_MUTEX(clocks_mutex); + +/* + * Find the correct struct clk for the device and connection ID. + * We do slightly fuzzy matching here: + * An entry with a NULL ID is assumed to be a wildcard. + * If an entry has a device ID, it must match + * If an entry has a connection ID, it must match + * Then we take the most specific entry - with the following + * order of precedence: dev+con > dev only > con only. + */ +static struct clk *clk_find(const char *dev_id, const char *con_id) +{ + struct clk_lookup *p; + struct clk *clk = NULL; + int match, best = 0; + + list_for_each_entry(p, &clocks, node) { + match = 0; + if (p->dev_id) { + if (!dev_id || strcmp(p->dev_id, dev_id)) + continue; + match += 2; + } + if (p->con_id) { + if (!con_id || strcmp(p->con_id, con_id)) + continue; + match += 1; + } + + if (match > best) { + clk = p->clk; + if (match != 3) + best = match; + else + break; + } + } + return clk; +} + +struct clk *clk_get_sys(const char *dev_id, const char *con_id) +{ + struct clk *clk; + + mutex_lock(&clocks_mutex); + clk = clk_find(dev_id, con_id); + if (clk && !__clk_get(clk)) + clk = NULL; + mutex_unlock(&clocks_mutex); + + return clk ? clk : ERR_PTR(-ENOENT); +} +EXPORT_SYMBOL(clk_get_sys); + +struct clk *clk_get(struct device *dev, const char *con_id) +{ + const char *dev_id = dev ? dev_name(dev) : NULL; + + return clk_get_sys(dev_id, con_id); +} +EXPORT_SYMBOL(clk_get); + +void clk_put(struct clk *clk) +{ + __clk_put(clk); +} +EXPORT_SYMBOL(clk_put); + +void clkdev_add(struct clk_lookup *cl) +{ + mutex_lock(&clocks_mutex); + list_add_tail(&cl->node, &clocks); + mutex_unlock(&clocks_mutex); +} +EXPORT_SYMBOL(clkdev_add); + +void __init clkdev_add_table(struct clk_lookup *cl, size_t num) +{ + mutex_lock(&clocks_mutex); + while (num--) { + list_add_tail(&cl->node, &clocks); + cl++; + } + mutex_unlock(&clocks_mutex); +} + +#define MAX_DEV_ID 20 +#define MAX_CON_ID 16 + +struct clk_lookup_alloc { + struct clk_lookup cl; + char dev_id[MAX_DEV_ID]; + char con_id[MAX_CON_ID]; +}; + +struct clk_lookup * __init_refok +clkdev_alloc(struct clk *clk, const char *con_id, const char *dev_fmt, ...) +{ + struct clk_lookup_alloc *cla; + + cla = __clkdev_alloc(sizeof(*cla)); + if (!cla) + return NULL; + + cla->cl.clk = clk; + if (con_id) { + strlcpy(cla->con_id, con_id, sizeof(cla->con_id)); + cla->cl.con_id = cla->con_id; + } + + if (dev_fmt) { + va_list ap; + + va_start(ap, dev_fmt); + vscnprintf(cla->dev_id, sizeof(cla->dev_id), dev_fmt, ap); + cla->cl.dev_id = cla->dev_id; + va_end(ap); + } + + return &cla->cl; +} +EXPORT_SYMBOL(clkdev_alloc); + +int clk_add_alias(const char *alias, const char *alias_dev_name, char *id, + struct device *dev) +{ + struct clk *r = clk_get(dev, id); + struct clk_lookup *l; + + if (IS_ERR(r)) + return PTR_ERR(r); + + l = clkdev_alloc(r, alias, alias_dev_name); + clk_put(r); + if (!l) + return -ENODEV; + clkdev_add(l); + return 0; +} +EXPORT_SYMBOL(clk_add_alias); + +/* + * clkdev_drop - remove a clock dynamically allocated + */ +void clkdev_drop(struct clk_lookup *cl) +{ + mutex_lock(&clocks_mutex); + list_del(&cl->node); + mutex_unlock(&clocks_mutex); + kfree(cl); +} +EXPORT_SYMBOL(clkdev_drop); diff --git a/include/linux/clkdev.h b/include/linux/clkdev.h new file mode 100644 index 000000000000..457bcb0a310a --- /dev/null +++ b/include/linux/clkdev.h @@ -0,0 +1,36 @@ +/* + * include/linux/clkdev.h + * + * Copyright (C) 2008 Russell King. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * Helper for the clk API to assist looking up a struct clk. + */ +#ifndef __CLKDEV_H +#define __CLKDEV_H + +#include + +struct clk; +struct device; + +struct clk_lookup { + struct list_head node; + const char *dev_id; + const char *con_id; + struct clk *clk; +}; + +struct clk_lookup *clkdev_alloc(struct clk *clk, const char *con_id, + const char *dev_fmt, ...); + +void clkdev_add(struct clk_lookup *cl); +void clkdev_drop(struct clk_lookup *cl); + +void clkdev_add_table(struct clk_lookup *, size_t); +int clk_add_alias(const char *, const char *, char *, struct device *); + +#endif -- cgit v1.2.3 From 65500fa94aaeb3475e39c0c5180f188014164ca4 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Thu, 4 Nov 2010 13:06:59 +0100 Subject: ARM: 6467/1: amba: optional PrimeCell core voltage switch On some contemporary sub-micron SoCs, peripherals on the chip have power domain switches, i.e. the voltage to the core may be turned off to conserve power. In the Ux500 we have this for out PrimeCell derivates. This patch makes it possible to specify an (optional) regulator to handle the voltage domain switch on AMBA PrimeCells, modeled very similar to how block clocks are handled. Additional amba_vcore_[enable|disable] calls are supplied to make it possible introduce optional powering off of the core voltage. Using this will require code to spool/unspool any core HW state. Cc: Rabin Vincent Cc: Bengt Jonsson Cc: Jonas Aaberg Signed-off-by: Linus Walleij Signed-off-by: Russell King --- drivers/amba/bus.c | 39 +++++++++++++++++++++++++++++++++++++++ include/linux/amba/bus.h | 8 ++++++++ 2 files changed, 47 insertions(+) (limited to 'include/linux') diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c index 2737b9752205..e7df019d29d4 100644 --- a/drivers/amba/bus.c +++ b/drivers/amba/bus.c @@ -147,6 +147,39 @@ static void amba_put_disable_pclk(struct amba_device *pcdev) clk_put(pclk); } +static int amba_get_enable_vcore(struct amba_device *pcdev) +{ + struct regulator *vcore = regulator_get(&pcdev->dev, "vcore"); + int ret; + + pcdev->vcore = vcore; + + if (IS_ERR(vcore)) { + /* It is OK not to supply a vcore regulator */ + if (PTR_ERR(vcore) == -ENODEV) + return 0; + return PTR_ERR(vcore); + } + + ret = regulator_enable(vcore); + if (ret) { + regulator_put(vcore); + pcdev->vcore = ERR_PTR(-ENODEV); + } + + return ret; +} + +static void amba_put_disable_vcore(struct amba_device *pcdev) +{ + struct regulator *vcore = pcdev->vcore; + + if (!IS_ERR(vcore)) { + regulator_disable(vcore); + regulator_put(vcore); + } +} + /* * These are the device model conversion veneers; they convert the * device model structures to our more specific structures. @@ -159,6 +192,10 @@ static int amba_probe(struct device *dev) int ret; do { + ret = amba_get_enable_vcore(pcdev); + if (ret) + break; + ret = amba_get_enable_pclk(pcdev); if (ret) break; @@ -168,6 +205,7 @@ static int amba_probe(struct device *dev) break; amba_put_disable_pclk(pcdev); + amba_put_disable_vcore(pcdev); } while (0); return ret; @@ -180,6 +218,7 @@ static int amba_remove(struct device *dev) int ret = drv->remove(pcdev); amba_put_disable_pclk(pcdev); + amba_put_disable_vcore(pcdev); return ret; } diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h index c6454cca0447..9e7f259346e1 100644 --- a/include/linux/amba/bus.h +++ b/include/linux/amba/bus.h @@ -18,6 +18,7 @@ #include #include #include +#include #define AMBA_NR_IRQS 2 #define AMBA_CID 0xb105f00d @@ -28,6 +29,7 @@ struct amba_device { struct device dev; struct resource res; struct clk *pclk; + struct regulator *vcore; u64 dma_mask; unsigned int periphid; unsigned int irq[AMBA_NR_IRQS]; @@ -71,6 +73,12 @@ void amba_release_regions(struct amba_device *); #define amba_pclk_disable(d) \ do { if (!IS_ERR((d)->pclk)) clk_disable((d)->pclk); } while (0) +#define amba_vcore_enable(d) \ + (IS_ERR((d)->vcore) ? 0 : regulator_enable((d)->vcore)) + +#define amba_vcore_disable(d) \ + do { if (!IS_ERR((d)->vcore)) regulator_disable((d)->vcore); } while (0) + /* Some drivers don't use the struct amba_device */ #define AMBA_CONFIG_BITS(a) (((a) >> 24) & 0xff) #define AMBA_REV_BITS(a) (((a) >> 20) & 0x0f) -- cgit v1.2.3 From 335d7afbfb71faac833734a94240c1e07cf0ead8 Mon Sep 17 00:00:00 2001 From: Gerald Schaefer Date: Mon, 22 Nov 2010 15:47:36 +0100 Subject: mutexes, sched: Introduce arch_mutex_cpu_relax() The spinning mutex implementation uses cpu_relax() in busy loops as a compiler barrier. Depending on the architecture, cpu_relax() may do more than needed in this specific mutex spin loops. On System z we also give up the time slice of the virtual cpu in cpu_relax(), which prevents effective spinning on the mutex. This patch replaces cpu_relax() in the spinning mutex code with arch_mutex_cpu_relax(), which can be defined by each architecture that selects HAVE_ARCH_MUTEX_CPU_RELAX. The default is still cpu_relax(), so this patch should not affect other architectures than System z for now. Signed-off-by: Gerald Schaefer Signed-off-by: Peter Zijlstra LKML-Reference: <1290437256.7455.4.camel@thinkpad> Signed-off-by: Ingo Molnar --- arch/Kconfig | 3 +++ arch/s390/Kconfig | 1 + arch/s390/include/asm/mutex.h | 2 ++ include/linux/mutex.h | 4 ++++ kernel/mutex.c | 2 +- kernel/sched.c | 3 ++- 6 files changed, 13 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/arch/Kconfig b/arch/Kconfig index 8bf0fa652eb6..f78c2be4242b 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -175,4 +175,7 @@ config HAVE_PERF_EVENTS_NMI config HAVE_ARCH_JUMP_LABEL bool +config HAVE_ARCH_MUTEX_CPU_RELAX + bool + source "kernel/gcov/Kconfig" diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index e0b98e71ff47..6c6d7b339aae 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -99,6 +99,7 @@ config S390 select HAVE_KERNEL_LZMA select HAVE_KERNEL_LZO select HAVE_GET_USER_PAGES_FAST + select HAVE_ARCH_MUTEX_CPU_RELAX select ARCH_INLINE_SPIN_TRYLOCK select ARCH_INLINE_SPIN_TRYLOCK_BH select ARCH_INLINE_SPIN_LOCK diff --git a/arch/s390/include/asm/mutex.h b/arch/s390/include/asm/mutex.h index 458c1f7fbc18..688271f5f2e4 100644 --- a/arch/s390/include/asm/mutex.h +++ b/arch/s390/include/asm/mutex.h @@ -7,3 +7,5 @@ */ #include + +#define arch_mutex_cpu_relax() barrier() diff --git a/include/linux/mutex.h b/include/linux/mutex.h index f363bc8fdc74..94b48bd40dd7 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -160,4 +160,8 @@ extern int mutex_trylock(struct mutex *lock); extern void mutex_unlock(struct mutex *lock); extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock); +#ifndef CONFIG_HAVE_ARCH_MUTEX_CPU_RELAX +#define arch_mutex_cpu_relax() cpu_relax() +#endif + #endif diff --git a/kernel/mutex.c b/kernel/mutex.c index 200407c1502f..a5889fb28ecf 100644 --- a/kernel/mutex.c +++ b/kernel/mutex.c @@ -199,7 +199,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, * memory barriers as we'll eventually observe the right * values at the cost of a few extra spins. */ - cpu_relax(); + arch_mutex_cpu_relax(); } #endif spin_lock_mutex(&lock->wait_lock, flags); diff --git a/kernel/sched.c b/kernel/sched.c index 3e8a7db951a6..abe7aec55763 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -75,6 +75,7 @@ #include #include +#include #include "sched_cpupri.h" #include "workqueue_sched.h" @@ -3888,7 +3889,7 @@ int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner) if (task_thread_info(rq->curr) != owner || need_resched()) return 0; - cpu_relax(); + arch_mutex_cpu_relax(); } return 1; -- cgit v1.2.3 From 6c7e550f13f8ad82efb6a5653ae628c2543c1768 Mon Sep 17 00:00:00 2001 From: Franck Bui-Huu Date: Tue, 23 Nov 2010 16:21:43 +0100 Subject: perf: Introduce is_sampling_event() and use it when appropriate. Signed-off-by: Franck Bui-Huu Signed-off-by: Peter Zijlstra LKML-Reference: <1290525705-6265-1-git-send-email-fbuihuu@gmail.com> Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event.c | 2 +- include/linux/perf_event.h | 5 +++++ kernel/perf_event.c | 10 +++++----- 3 files changed, 11 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 7c1a4c35fd41..c01dfec635db 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -442,7 +442,7 @@ static int x86_setup_perfctr(struct perf_event *event) struct hw_perf_event *hwc = &event->hw; u64 config; - if (!hwc->sample_period) { + if (!is_sampling_event(event)) { hwc->sample_period = x86_pmu.max_period; hwc->last_period = hwc->sample_period; local64_set(&hwc->period_left, hwc->sample_period); diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index de2c41758e29..cbf04cc1e630 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -969,6 +969,11 @@ extern int perf_event_overflow(struct perf_event *event, int nmi, struct perf_sample_data *data, struct pt_regs *regs); +static inline bool is_sampling_event(struct perf_event *event) +{ + return event->attr.sample_period != 0; +} + /* * Return 1 for a software event, 0 for a hardware event */ diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 43f757ccf831..880698488c91 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -2514,7 +2514,7 @@ static int perf_event_period(struct perf_event *event, u64 __user *arg) int ret = 0; u64 value; - if (!event->attr.sample_period) + if (!is_sampling_event(event)) return -EINVAL; if (copy_from_user(&value, arg, sizeof(value))) @@ -4385,7 +4385,7 @@ static void perf_swevent_event(struct perf_event *event, u64 nr, if (!regs) return; - if (!hwc->sample_period) + if (!is_sampling_event(event)) return; if (nr == 1 && hwc->sample_period == 1 && !event->attr.freq) @@ -4548,7 +4548,7 @@ static int perf_swevent_add(struct perf_event *event, int flags) struct hw_perf_event *hwc = &event->hw; struct hlist_head *head; - if (hwc->sample_period) { + if (is_sampling_event(event)) { hwc->last_period = hwc->sample_period; perf_swevent_set_period(event); } @@ -4920,7 +4920,7 @@ static void perf_swevent_start_hrtimer(struct perf_event *event) hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); hwc->hrtimer.function = perf_swevent_hrtimer; - if (hwc->sample_period) { + if (is_sampling_event(event)) { s64 period = local64_read(&hwc->period_left); if (period) { @@ -4941,7 +4941,7 @@ static void perf_swevent_cancel_hrtimer(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; - if (hwc->sample_period) { + if (is_sampling_event(event)) { ktime_t remaining = hrtimer_get_remaining(&hwc->hrtimer); local64_set(&hwc->period_left, ktime_to_ns(remaining)); -- cgit v1.2.3 From 004417a6d468e24399e383645c068b498eed84ad Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 25 Nov 2010 18:38:29 +0100 Subject: perf, arch: Cleanup perf-pmu init vs lockup-detector The perf hardware pmu got initialized at various points in the boot, some before early_initcall() some after (notably arch_initcall). The problem is that the NMI lockup detector is ran from early_initcall() and expects the hardware pmu to be present. Sanitize this by moving all architecture hardware pmu implementations to initialize at early_initcall() and move the lockup detector to an explicit initcall right after that. Cc: paulus Cc: davem Cc: Michael Cree Cc: Deng-Cheng Zhu Acked-by: Paul Mundt Acked-by: Will Deacon Signed-off-by: Peter Zijlstra LKML-Reference: <1290707759.2145.119.camel@laptop> Signed-off-by: Ingo Molnar --- arch/alpha/include/asm/perf_event.h | 6 ------ arch/alpha/kernel/irq_alpha.c | 2 -- arch/alpha/kernel/perf_event.c | 9 ++++++--- arch/arm/kernel/perf_event.c | 2 +- arch/mips/kernel/perf_event_mipsxx.c | 2 +- arch/powerpc/kernel/e500-pmu.c | 2 +- arch/powerpc/kernel/mpc7450-pmu.c | 2 +- arch/powerpc/kernel/power4-pmu.c | 2 +- arch/powerpc/kernel/power5+-pmu.c | 2 +- arch/powerpc/kernel/power5-pmu.c | 2 +- arch/powerpc/kernel/power6-pmu.c | 2 +- arch/powerpc/kernel/power7-pmu.c | 2 +- arch/powerpc/kernel/ppc970-pmu.c | 2 +- arch/sh/kernel/cpu/sh4/perf_event.c | 2 +- arch/sh/kernel/cpu/sh4a/perf_event.c | 2 +- arch/sparc/include/asm/perf_event.h | 4 ---- arch/sparc/kernel/nmi.c | 2 -- arch/sparc/kernel/perf_event.c | 7 +++++-- arch/x86/include/asm/perf_event.h | 2 -- arch/x86/kernel/cpu/common.c | 1 - arch/x86/kernel/cpu/perf_event.c | 11 +++++++---- include/linux/sched.h | 4 ++++ init/main.c | 1 + kernel/watchdog.c | 7 +++---- 24 files changed, 38 insertions(+), 42 deletions(-) (limited to 'include/linux') diff --git a/arch/alpha/include/asm/perf_event.h b/arch/alpha/include/asm/perf_event.h index fe792ca818f6..5996e7a6757e 100644 --- a/arch/alpha/include/asm/perf_event.h +++ b/arch/alpha/include/asm/perf_event.h @@ -1,10 +1,4 @@ #ifndef __ASM_ALPHA_PERF_EVENT_H #define __ASM_ALPHA_PERF_EVENT_H -#ifdef CONFIG_PERF_EVENTS -extern void init_hw_perf_events(void); -#else -static inline void init_hw_perf_events(void) { } -#endif - #endif /* __ASM_ALPHA_PERF_EVENT_H */ diff --git a/arch/alpha/kernel/irq_alpha.c b/arch/alpha/kernel/irq_alpha.c index 5f77afb88e89..4c8bb374eb0a 100644 --- a/arch/alpha/kernel/irq_alpha.c +++ b/arch/alpha/kernel/irq_alpha.c @@ -112,8 +112,6 @@ init_IRQ(void) wrent(entInt, 0); alpha_mv.init_irq(); - - init_hw_perf_events(); } /* diff --git a/arch/alpha/kernel/perf_event.c b/arch/alpha/kernel/perf_event.c index 1cc49683fb69..3283059b6e85 100644 --- a/arch/alpha/kernel/perf_event.c +++ b/arch/alpha/kernel/perf_event.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include @@ -863,13 +864,13 @@ static void alpha_perf_event_irq_handler(unsigned long la_ptr, /* * Init call to initialise performance events at kernel startup. */ -void __init init_hw_perf_events(void) +int __init init_hw_perf_events(void) { pr_info("Performance events: "); if (!supported_cpu()) { pr_cont("No support for your CPU.\n"); - return; + return 0; } pr_cont("Supported CPU type!\n"); @@ -882,5 +883,7 @@ void __init init_hw_perf_events(void) alpha_pmu = &ev67_pmu; perf_pmu_register(&pmu); -} + return 0; +} +early_initcall(init_hw_perf_events); diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c index 07a50357492a..d45f70e5f2ee 100644 --- a/arch/arm/kernel/perf_event.c +++ b/arch/arm/kernel/perf_event.c @@ -3038,7 +3038,7 @@ init_hw_perf_events(void) return 0; } -arch_initcall(init_hw_perf_events); +early_initcall(init_hw_perf_events); /* * Callchain handling code. diff --git a/arch/mips/kernel/perf_event_mipsxx.c b/arch/mips/kernel/perf_event_mipsxx.c index 5c7c6fc07565..183e0d226669 100644 --- a/arch/mips/kernel/perf_event_mipsxx.c +++ b/arch/mips/kernel/perf_event_mipsxx.c @@ -1047,6 +1047,6 @@ init_hw_perf_events(void) return 0; } -arch_initcall(init_hw_perf_events); +early_initcall(init_hw_perf_events); #endif /* defined(CONFIG_CPU_MIPS32)... */ diff --git a/arch/powerpc/kernel/e500-pmu.c b/arch/powerpc/kernel/e500-pmu.c index 7c07de0d8943..b150b510510f 100644 --- a/arch/powerpc/kernel/e500-pmu.c +++ b/arch/powerpc/kernel/e500-pmu.c @@ -126,4 +126,4 @@ static int init_e500_pmu(void) return register_fsl_emb_pmu(&e500_pmu); } -arch_initcall(init_e500_pmu); +early_initcall(init_e500_pmu); diff --git a/arch/powerpc/kernel/mpc7450-pmu.c b/arch/powerpc/kernel/mpc7450-pmu.c index 09d72028f317..2cc5e0301d0b 100644 --- a/arch/powerpc/kernel/mpc7450-pmu.c +++ b/arch/powerpc/kernel/mpc7450-pmu.c @@ -414,4 +414,4 @@ static int init_mpc7450_pmu(void) return register_power_pmu(&mpc7450_pmu); } -arch_initcall(init_mpc7450_pmu); +early_initcall(init_mpc7450_pmu); diff --git a/arch/powerpc/kernel/power4-pmu.c b/arch/powerpc/kernel/power4-pmu.c index 2a361cdda635..ead8b3c2649e 100644 --- a/arch/powerpc/kernel/power4-pmu.c +++ b/arch/powerpc/kernel/power4-pmu.c @@ -613,4 +613,4 @@ static int init_power4_pmu(void) return register_power_pmu(&power4_pmu); } -arch_initcall(init_power4_pmu); +early_initcall(init_power4_pmu); diff --git a/arch/powerpc/kernel/power5+-pmu.c b/arch/powerpc/kernel/power5+-pmu.c index 199de527d411..eca0ac595cb6 100644 --- a/arch/powerpc/kernel/power5+-pmu.c +++ b/arch/powerpc/kernel/power5+-pmu.c @@ -682,4 +682,4 @@ static int init_power5p_pmu(void) return register_power_pmu(&power5p_pmu); } -arch_initcall(init_power5p_pmu); +early_initcall(init_power5p_pmu); diff --git a/arch/powerpc/kernel/power5-pmu.c b/arch/powerpc/kernel/power5-pmu.c index 98b6a729a9dd..d5ff0f64a5e6 100644 --- a/arch/powerpc/kernel/power5-pmu.c +++ b/arch/powerpc/kernel/power5-pmu.c @@ -621,4 +621,4 @@ static int init_power5_pmu(void) return register_power_pmu(&power5_pmu); } -arch_initcall(init_power5_pmu); +early_initcall(init_power5_pmu); diff --git a/arch/powerpc/kernel/power6-pmu.c b/arch/powerpc/kernel/power6-pmu.c index 84a607bda8fb..31603927e376 100644 --- a/arch/powerpc/kernel/power6-pmu.c +++ b/arch/powerpc/kernel/power6-pmu.c @@ -544,4 +544,4 @@ static int init_power6_pmu(void) return register_power_pmu(&power6_pmu); } -arch_initcall(init_power6_pmu); +early_initcall(init_power6_pmu); diff --git a/arch/powerpc/kernel/power7-pmu.c b/arch/powerpc/kernel/power7-pmu.c index 852f7b7f6b40..593740fcb799 100644 --- a/arch/powerpc/kernel/power7-pmu.c +++ b/arch/powerpc/kernel/power7-pmu.c @@ -369,4 +369,4 @@ static int init_power7_pmu(void) return register_power_pmu(&power7_pmu); } -arch_initcall(init_power7_pmu); +early_initcall(init_power7_pmu); diff --git a/arch/powerpc/kernel/ppc970-pmu.c b/arch/powerpc/kernel/ppc970-pmu.c index 3fee685de4df..9a6e093858fe 100644 --- a/arch/powerpc/kernel/ppc970-pmu.c +++ b/arch/powerpc/kernel/ppc970-pmu.c @@ -494,4 +494,4 @@ static int init_ppc970_pmu(void) return register_power_pmu(&ppc970_pmu); } -arch_initcall(init_ppc970_pmu); +early_initcall(init_ppc970_pmu); diff --git a/arch/sh/kernel/cpu/sh4/perf_event.c b/arch/sh/kernel/cpu/sh4/perf_event.c index dbf3b4bb71fe..748955df018d 100644 --- a/arch/sh/kernel/cpu/sh4/perf_event.c +++ b/arch/sh/kernel/cpu/sh4/perf_event.c @@ -250,4 +250,4 @@ static int __init sh7750_pmu_init(void) return register_sh_pmu(&sh7750_pmu); } -arch_initcall(sh7750_pmu_init); +early_initcall(sh7750_pmu_init); diff --git a/arch/sh/kernel/cpu/sh4a/perf_event.c b/arch/sh/kernel/cpu/sh4a/perf_event.c index 580276525731..17e6bebfede0 100644 --- a/arch/sh/kernel/cpu/sh4a/perf_event.c +++ b/arch/sh/kernel/cpu/sh4a/perf_event.c @@ -284,4 +284,4 @@ static int __init sh4a_pmu_init(void) return register_sh_pmu(&sh4a_pmu); } -arch_initcall(sh4a_pmu_init); +early_initcall(sh4a_pmu_init); diff --git a/arch/sparc/include/asm/perf_event.h b/arch/sparc/include/asm/perf_event.h index 6e8bfa1786da..4d3dbe3703e9 100644 --- a/arch/sparc/include/asm/perf_event.h +++ b/arch/sparc/include/asm/perf_event.h @@ -4,8 +4,6 @@ #ifdef CONFIG_PERF_EVENTS #include -extern void init_hw_perf_events(void); - #define perf_arch_fetch_caller_regs(regs, ip) \ do { \ unsigned long _pstate, _asi, _pil, _i7, _fp; \ @@ -26,8 +24,6 @@ do { \ (regs)->u_regs[UREG_I6] = _fp; \ (regs)->u_regs[UREG_I7] = _i7; \ } while (0) -#else -static inline void init_hw_perf_events(void) { } #endif #endif diff --git a/arch/sparc/kernel/nmi.c b/arch/sparc/kernel/nmi.c index a4bd7ba74c89..300f810142f5 100644 --- a/arch/sparc/kernel/nmi.c +++ b/arch/sparc/kernel/nmi.c @@ -270,8 +270,6 @@ int __init nmi_init(void) atomic_set(&nmi_active, -1); } } - if (!err) - init_hw_perf_events(); return err; } diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c index 0d6deb55a2ae..75c5b1263970 100644 --- a/arch/sparc/kernel/perf_event.c +++ b/arch/sparc/kernel/perf_event.c @@ -1307,20 +1307,23 @@ static bool __init supported_pmu(void) return false; } -void __init init_hw_perf_events(void) +int __init init_hw_perf_events(void) { pr_info("Performance events: "); if (!supported_pmu()) { pr_cont("No support for PMU type '%s'\n", sparc_pmu_type); - return; + return 0; } pr_cont("Supported PMU type is '%s'\n", sparc_pmu_type); perf_pmu_register(&pmu); register_die_notifier(&perf_event_nmi_notifier); + + return 0; } +early_initcall(init_hw_perf_event); void perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs) diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 550e26b1dbb3..d9d4dae305f6 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -125,7 +125,6 @@ union cpuid10_edx { #define IBS_OP_MAX_CNT_EXT 0x007FFFFFULL /* not a register bit mask */ #ifdef CONFIG_PERF_EVENTS -extern void init_hw_perf_events(void); extern void perf_events_lapic_init(void); #define PERF_EVENT_INDEX_OFFSET 0 @@ -156,7 +155,6 @@ extern unsigned long perf_misc_flags(struct pt_regs *regs); } #else -static inline void init_hw_perf_events(void) { } static inline void perf_events_lapic_init(void) { } #endif diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 4b68bda30938..1d59834396bd 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -894,7 +894,6 @@ void __init identify_boot_cpu(void) #else vgetcpu_set_mode(); #endif - init_hw_perf_events(); } void __cpuinit identify_secondary_cpu(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index c01dfec635db..817d2b195e8e 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1353,7 +1353,7 @@ static void __init pmu_check_apic(void) pr_info("no hardware sampling interrupt available.\n"); } -void __init init_hw_perf_events(void) +int __init init_hw_perf_events(void) { struct event_constraint *c; int err; @@ -1368,11 +1368,11 @@ void __init init_hw_perf_events(void) err = amd_pmu_init(); break; default: - return; + return 0; } if (err != 0) { pr_cont("no PMU driver, software events only.\n"); - return; + return 0; } pmu_check_apic(); @@ -1380,7 +1380,7 @@ void __init init_hw_perf_events(void) /* sanity check that the hardware exists or is emulated */ if (!check_hw_exists()) { pr_cont("Broken PMU hardware detected, software events only.\n"); - return; + return 0; } pr_cont("%s PMU driver.\n", x86_pmu.name); @@ -1431,7 +1431,10 @@ void __init init_hw_perf_events(void) perf_pmu_register(&pmu); perf_cpu_notifier(x86_pmu_notifier); + + return 0; } +early_initcall(init_hw_perf_events); static inline void x86_pmu_read(struct perf_event *event) { diff --git a/include/linux/sched.h b/include/linux/sched.h index 2c79e921a68b..d2e63d1e725c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -316,6 +316,7 @@ extern int proc_dowatchdog_thresh(struct ctl_table *table, int write, size_t *lenp, loff_t *ppos); extern unsigned int softlockup_panic; extern int softlockup_thresh; +void lockup_detector_init(void); #else static inline void touch_softlockup_watchdog(void) { @@ -326,6 +327,9 @@ static inline void touch_softlockup_watchdog_sync(void) static inline void touch_all_softlockup_watchdogs(void) { } +static inline void lockup_detector_init(void) +{ +} #endif #ifdef CONFIG_DETECT_HUNG_TASK diff --git a/init/main.c b/init/main.c index 8646401f7a0e..261ad7b3fe0b 100644 --- a/init/main.c +++ b/init/main.c @@ -882,6 +882,7 @@ static int __init kernel_init(void * unused) smp_prepare_cpus(setup_max_cpus); do_pre_smp_initcalls(); + lockup_detector_init(); smp_init(); sched_init_smp(); diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 6e3c41a4024c..cad4e42060a9 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -547,13 +547,13 @@ static struct notifier_block __cpuinitdata cpu_nfb = { .notifier_call = cpu_callback }; -static int __init spawn_watchdog_task(void) +void __init lockup_detector_init(void) { void *cpu = (void *)(long)smp_processor_id(); int err; if (no_watchdog) - return 0; + return; err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu); WARN_ON(notifier_to_errno(err)); @@ -561,6 +561,5 @@ static int __init spawn_watchdog_task(void) cpu_callback(&cpu_nfb, CPU_ONLINE, cpu); register_cpu_notifier(&cpu_nfb); - return 0; + return; } -early_initcall(spawn_watchdog_task); -- cgit v1.2.3 From 5a0d2268d259886f0c87131639d19eb4a67b4532 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 23 Nov 2010 10:42:02 +0000 Subject: net: add netif_tx_queue_frozen_or_stopped When testing struct netdev_queue state against FROZEN bit, we also test XOFF bit. We can test both bits at once and save some cycles. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 6 ++++-- net/core/netpoll.c | 3 +-- net/core/pktgen.c | 2 +- net/sched/sch_generic.c | 8 +++----- net/sched/sch_teql.c | 3 +-- 5 files changed, 10 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index badf9285fe0d..7c6ae2f4b9ab 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -493,6 +493,8 @@ static inline void napi_synchronize(const struct napi_struct *n) enum netdev_queue_state_t { __QUEUE_STATE_XOFF, __QUEUE_STATE_FROZEN, +#define QUEUE_STATE_XOFF_OR_FROZEN ((1 << __QUEUE_STATE_XOFF) | \ + (1 << __QUEUE_STATE_FROZEN)) }; struct netdev_queue { @@ -1629,9 +1631,9 @@ static inline int netif_queue_stopped(const struct net_device *dev) return netif_tx_queue_stopped(netdev_get_tx_queue(dev, 0)); } -static inline int netif_tx_queue_frozen(const struct netdev_queue *dev_queue) +static inline int netif_tx_queue_frozen_or_stopped(const struct netdev_queue *dev_queue) { - return test_bit(__QUEUE_STATE_FROZEN, &dev_queue->state); + return dev_queue->state & QUEUE_STATE_XOFF_OR_FROZEN; } /** diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 4e98ffac3af0..ee38acb6d463 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -76,8 +76,7 @@ static void queue_process(struct work_struct *work) local_irq_save(flags); __netif_tx_lock(txq, smp_processor_id()); - if (netif_tx_queue_stopped(txq) || - netif_tx_queue_frozen(txq) || + if (netif_tx_queue_frozen_or_stopped(txq) || ops->ndo_start_xmit(skb, dev) != NETDEV_TX_OK) { skb_queue_head(&npinfo->txq, skb); __netif_tx_unlock(txq); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 2e57830cbeb2..2953b2abc971 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -3527,7 +3527,7 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev) __netif_tx_lock_bh(txq); - if (unlikely(netif_tx_queue_stopped(txq) || netif_tx_queue_frozen(txq))) { + if (unlikely(netif_tx_queue_frozen_or_stopped(txq))) { ret = NETDEV_TX_BUSY; pkt_dev->last_ok = 0; goto unlock; diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 5dbb3cd96e59..7f0bd8952646 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -60,8 +60,7 @@ static inline struct sk_buff *dequeue_skb(struct Qdisc *q) /* check the reason of requeuing without tx lock first */ txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb)); - if (!netif_tx_queue_stopped(txq) && - !netif_tx_queue_frozen(txq)) { + if (!netif_tx_queue_frozen_or_stopped(txq)) { q->gso_skb = NULL; q->q.qlen--; } else @@ -122,7 +121,7 @@ int sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q, spin_unlock(root_lock); HARD_TX_LOCK(dev, txq, smp_processor_id()); - if (!netif_tx_queue_stopped(txq) && !netif_tx_queue_frozen(txq)) + if (!netif_tx_queue_frozen_or_stopped(txq)) ret = dev_hard_start_xmit(skb, dev, txq); HARD_TX_UNLOCK(dev, txq); @@ -144,8 +143,7 @@ int sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q, ret = dev_requeue_skb(skb, q); } - if (ret && (netif_tx_queue_stopped(txq) || - netif_tx_queue_frozen(txq))) + if (ret && netif_tx_queue_frozen_or_stopped(txq)) ret = 0; return ret; diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index 401af9596709..106479a7c94a 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -309,8 +309,7 @@ restart: if (__netif_tx_trylock(slave_txq)) { unsigned int length = qdisc_pkt_len(skb); - if (!netif_tx_queue_stopped(slave_txq) && - !netif_tx_queue_frozen(slave_txq) && + if (!netif_tx_queue_frozen_or_stopped(slave_txq) && slave_ops->ndo_start_xmit(skb, slave) == NETDEV_TX_OK) { txq_trans_update(slave_txq); __netif_tx_unlock(slave_txq); -- cgit v1.2.3 From bf26414510103448ad3dc069c7422462f03ea3d7 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Fri, 26 Nov 2010 08:36:09 +0000 Subject: xps: Add CONFIG_XPS This patch adds XPS_CONFIG option to enable and disable XPS. This is done in the same manner as RPS_CONFIG. This is also fixes build failure in XPS code when SMP is not enabled. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/netdevice.h | 52 +++++++++++++++++++++++++---------------------- net/Kconfig | 5 +++++ net/core/dev.c | 9 +++++--- net/core/net-sysfs.c | 47 ++++++++++++++++++++++++++++++------------ net/core/net-sysfs.h | 3 --- 5 files changed, 73 insertions(+), 43 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7c6ae2f4b9ab..9ae4544f0cf0 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -535,30 +535,6 @@ struct rps_map { }; #define RPS_MAP_SIZE(_num) (sizeof(struct rps_map) + (_num * sizeof(u16))) -/* - * This structure holds an XPS map which can be of variable length. The - * map is an array of queues. - */ -struct xps_map { - unsigned int len; - unsigned int alloc_len; - struct rcu_head rcu; - u16 queues[0]; -}; -#define XPS_MAP_SIZE(_num) (sizeof(struct xps_map) + (_num * sizeof(u16))) -#define XPS_MIN_MAP_ALLOC ((L1_CACHE_BYTES - sizeof(struct xps_map)) \ - / sizeof(u16)) - -/* - * This structure holds all XPS maps for device. Maps are indexed by CPU. - */ -struct xps_dev_maps { - struct rcu_head rcu; - struct xps_map *cpu_map[0]; -}; -#define XPS_DEV_MAPS_SIZE (sizeof(struct xps_dev_maps) + \ - (nr_cpu_ids * sizeof(struct xps_map *))) - /* * The rps_dev_flow structure contains the mapping of a flow to a CPU and the * tail pointer for that CPU's input queue at the time of last enqueue. @@ -626,6 +602,32 @@ struct netdev_rx_queue { } ____cacheline_aligned_in_smp; #endif /* CONFIG_RPS */ +#ifdef CONFIG_XPS +/* + * This structure holds an XPS map which can be of variable length. The + * map is an array of queues. + */ +struct xps_map { + unsigned int len; + unsigned int alloc_len; + struct rcu_head rcu; + u16 queues[0]; +}; +#define XPS_MAP_SIZE(_num) (sizeof(struct xps_map) + (_num * sizeof(u16))) +#define XPS_MIN_MAP_ALLOC ((L1_CACHE_BYTES - sizeof(struct xps_map)) \ + / sizeof(u16)) + +/* + * This structure holds all XPS maps for device. Maps are indexed by CPU. + */ +struct xps_dev_maps { + struct rcu_head rcu; + struct xps_map *cpu_map[0]; +}; +#define XPS_DEV_MAPS_SIZE (sizeof(struct xps_dev_maps) + \ + (nr_cpu_ids * sizeof(struct xps_map *))) +#endif /* CONFIG_XPS */ + /* * This structure defines the management hooks for network devices. * The following hooks can be defined; unless noted otherwise, they are @@ -1046,7 +1048,9 @@ struct net_device { unsigned long tx_queue_len; /* Max frames per queue allowed */ spinlock_t tx_global_lock; +#ifdef CONFIG_XPS struct xps_dev_maps *xps_maps; +#endif /* These may be needed for future network-power-down code. */ diff --git a/net/Kconfig b/net/Kconfig index 55fd82e9ffd9..126c2af0fc1f 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -220,6 +220,11 @@ config RPS depends on SMP && SYSFS && USE_GENERIC_SMP_HELPERS default y +config XPS + boolean + depends on SMP && SYSFS && USE_GENERIC_SMP_HELPERS + default y + menu "Network testing" config NET_PKTGEN diff --git a/net/core/dev.c b/net/core/dev.c index c852f0038a08..3259d2c323a6 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1567,6 +1567,9 @@ int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq) rc = netdev_queue_update_kobjects(dev, dev->real_num_tx_queues, txq); + if (rc) + return rc; + if (txq < dev->real_num_tx_queues) qdisc_reset_all_tx_gt(dev, txq); } @@ -2148,7 +2151,7 @@ static inline u16 dev_cap_txqueue(struct net_device *dev, u16 queue_index) static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb) { -#ifdef CONFIG_RPS +#ifdef CONFIG_XPS struct xps_dev_maps *dev_maps; struct xps_map *map; int queue_index = -1; @@ -5085,9 +5088,9 @@ void netif_stacked_transfer_operstate(const struct net_device *rootdev, } EXPORT_SYMBOL(netif_stacked_transfer_operstate); +#ifdef CONFIG_RPS static int netif_alloc_rx_queues(struct net_device *dev) { -#ifdef CONFIG_RPS unsigned int i, count = dev->num_rx_queues; struct netdev_rx_queue *rx; @@ -5102,9 +5105,9 @@ static int netif_alloc_rx_queues(struct net_device *dev) for (i = 0; i < count; i++) rx[i].dev = dev; -#endif return 0; } +#endif static int netif_alloc_netdev_queues(struct net_device *dev) { diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 68dbbfdee274..99c11294623f 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -751,10 +751,12 @@ static int rx_queue_add_kobject(struct net_device *net, int index) return error; } +#endif /* CONFIG_RPS */ int net_rx_queue_update_kobjects(struct net_device *net, int old_num, int new_num) { +#ifdef CONFIG_RPS int i; int error = 0; @@ -770,8 +772,12 @@ net_rx_queue_update_kobjects(struct net_device *net, int old_num, int new_num) kobject_put(&net->_rx[i].kobj); return error; +#else + return 0; +#endif } +#ifdef CONFIG_XPS /* * netdev_queue sysfs structures and functions. */ @@ -1090,10 +1096,12 @@ static int netdev_queue_add_kobject(struct net_device *net, int index) return error; } +#endif /* CONFIG_XPS */ int netdev_queue_update_kobjects(struct net_device *net, int old_num, int new_num) { +#ifdef CONFIG_XPS int i; int error = 0; @@ -1109,27 +1117,36 @@ netdev_queue_update_kobjects(struct net_device *net, int old_num, int new_num) kobject_put(&net->_tx[i].kobj); return error; +#else + return 0; +#endif } static int register_queue_kobjects(struct net_device *net) { - int error = 0, txq = 0, rxq = 0; + int error = 0, txq = 0, rxq = 0, real_rx = 0, real_tx = 0; +#if defined(CONFIG_RPS) || defined(CONFIG_XPS) net->queues_kset = kset_create_and_add("queues", NULL, &net->dev.kobj); if (!net->queues_kset) return -ENOMEM; +#endif + +#ifdef CONFIG_RPS + real_rx = net->real_num_rx_queues; +#endif + real_tx = net->real_num_tx_queues; - error = net_rx_queue_update_kobjects(net, 0, net->real_num_rx_queues); + error = net_rx_queue_update_kobjects(net, 0, real_rx); if (error) goto error; - rxq = net->real_num_rx_queues; + rxq = real_rx; - error = netdev_queue_update_kobjects(net, 0, - net->real_num_tx_queues); + error = netdev_queue_update_kobjects(net, 0, real_tx); if (error) goto error; - txq = net->real_num_tx_queues; + txq = real_tx; return 0; @@ -1141,11 +1158,19 @@ error: static void remove_queue_kobjects(struct net_device *net) { - net_rx_queue_update_kobjects(net, net->real_num_rx_queues, 0); - netdev_queue_update_kobjects(net, net->real_num_tx_queues, 0); + int real_rx = 0, real_tx = 0; + +#ifdef CONFIG_RPS + real_rx = net->real_num_rx_queues; +#endif + real_tx = net->real_num_tx_queues; + + net_rx_queue_update_kobjects(net, real_rx, 0); + netdev_queue_update_kobjects(net, real_tx, 0); +#if defined(CONFIG_RPS) || defined(CONFIG_XPS) kset_unregister(net->queues_kset); +#endif } -#endif /* CONFIG_RPS */ static const void *net_current_ns(void) { @@ -1244,9 +1269,7 @@ void netdev_unregister_kobject(struct net_device * net) kobject_get(&dev->kobj); -#ifdef CONFIG_RPS remove_queue_kobjects(net); -#endif device_del(dev); } @@ -1285,13 +1308,11 @@ int netdev_register_kobject(struct net_device *net) if (error) return error; -#ifdef CONFIG_RPS error = register_queue_kobjects(net); if (error) { device_del(dev); return error; } -#endif return error; } diff --git a/net/core/net-sysfs.h b/net/core/net-sysfs.h index 25ec2ee57df7..bd7751ec1c4d 100644 --- a/net/core/net-sysfs.h +++ b/net/core/net-sysfs.h @@ -4,11 +4,8 @@ int netdev_kobject_init(void); int netdev_register_kobject(struct net_device *); void netdev_unregister_kobject(struct net_device *); -#ifdef CONFIG_RPS int net_rx_queue_update_kobjects(struct net_device *, int old_num, int new_num); int netdev_queue_update_kobjects(struct net_device *net, int old_num, int new_num); #endif - -#endif -- cgit v1.2.3 From a41778694806ac1ccd4b1dafed1abef8d5ba98ac Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 28 Nov 2010 21:43:02 +0000 Subject: xps: add __rcu annotations Avoid sparse warnings : add __rcu annotations and use rcu_dereference_protected() where necessary. Signed-off-by: Eric Dumazet Cc: Tom Herbert Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 ++-- net/core/net-sysfs.c | 24 +++++++++++++++--------- 2 files changed, 17 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9ae4544f0cf0..4b0c7f3aa32b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -622,7 +622,7 @@ struct xps_map { */ struct xps_dev_maps { struct rcu_head rcu; - struct xps_map *cpu_map[0]; + struct xps_map __rcu *cpu_map[0]; }; #define XPS_DEV_MAPS_SIZE (sizeof(struct xps_dev_maps) + \ (nr_cpu_ids * sizeof(struct xps_map *))) @@ -1049,7 +1049,7 @@ struct net_device { spinlock_t tx_global_lock; #ifdef CONFIG_XPS - struct xps_dev_maps *xps_maps; + struct xps_dev_maps __rcu *xps_maps; #endif /* These may be needed for future network-power-down code. */ diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 35ef42fa0cf3..f85cee3d869e 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -899,6 +899,8 @@ static void xps_dev_maps_release(struct rcu_head *rcu) } static DEFINE_MUTEX(xps_map_mutex); +#define xmap_dereference(P) \ + rcu_dereference_protected((P), lockdep_is_held(&xps_map_mutex)) static ssize_t store_xps_map(struct netdev_queue *queue, struct netdev_queue_attribute *attribute, @@ -935,11 +937,12 @@ static ssize_t store_xps_map(struct netdev_queue *queue, mutex_lock(&xps_map_mutex); - dev_maps = dev->xps_maps; + dev_maps = xmap_dereference(dev->xps_maps); for_each_possible_cpu(cpu) { - new_map = map = dev_maps ? dev_maps->cpu_map[cpu] : NULL; - + map = dev_maps ? + xmap_dereference(dev_maps->cpu_map[cpu]) : NULL; + new_map = map; if (map) { for (pos = 0; pos < map->len; pos++) if (map->queues[pos] == index) @@ -975,13 +978,14 @@ static ssize_t store_xps_map(struct netdev_queue *queue, else new_map = NULL; } - new_dev_maps->cpu_map[cpu] = new_map; + RCU_INIT_POINTER(new_dev_maps->cpu_map[cpu], new_map); } /* Cleanup old maps */ for_each_possible_cpu(cpu) { - map = dev_maps ? dev_maps->cpu_map[cpu] : NULL; - if (map && new_dev_maps->cpu_map[cpu] != map) + map = dev_maps ? + xmap_dereference(dev_maps->cpu_map[cpu]) : NULL; + if (map && xmap_dereference(new_dev_maps->cpu_map[cpu]) != map) call_rcu(&map->rcu, xps_map_release); if (new_dev_maps->cpu_map[cpu]) nonempty = 1; @@ -1007,7 +1011,9 @@ error: if (new_dev_maps) for_each_possible_cpu(i) - kfree(new_dev_maps->cpu_map[i]); + kfree(rcu_dereference_protected( + new_dev_maps->cpu_map[i], + 1)); kfree(new_dev_maps); free_cpumask_var(mask); return -ENOMEM; @@ -1033,11 +1039,11 @@ static void netdev_queue_release(struct kobject *kobj) index = get_netdev_queue_index(queue); mutex_lock(&xps_map_mutex); - dev_maps = dev->xps_maps; + dev_maps = xmap_dereference(dev->xps_maps); if (dev_maps) { for_each_possible_cpu(i) { - map = dev_maps->cpu_map[i]; + map = xmap_dereference(dev_maps->cpu_map[i]); if (!map) continue; -- cgit v1.2.3 From f7ca38dfe58c20cb1aa2ed9643187e8b194b5bae Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 25 Nov 2010 10:02:29 +0100 Subject: nl80211/cfg80211: extend mgmt-tx API for off-channel With p2p, it is sometimes necessary to transmit a frame (typically an action frame) on another channel than the current channel. Enable this through the CMD_FRAME API, and allow it to wait for a response. A new command allows that wait to be aborted. However, allow userspace to specify whether or not it wants to allow off-channel TX, it may actually want to use the same channel only. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/linux/nl80211.h | 25 +++++++++++++++++----- include/net/cfg80211.h | 11 +++++++--- net/mac80211/cfg.c | 7 ++++-- net/wireless/core.h | 4 ++-- net/wireless/mlme.c | 9 ++++---- net/wireless/nl80211.c | 57 +++++++++++++++++++++++++++++++++++++++++++------ 6 files changed, 91 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index d706bf3badc8..5cfa579df476 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -358,11 +358,16 @@ * user space application). %NL80211_ATTR_FRAME is used to specify the * frame contents (including header). %NL80211_ATTR_WIPHY_FREQ (and * optionally %NL80211_ATTR_WIPHY_CHANNEL_TYPE) is used to indicate on - * which channel the frame is to be transmitted or was received. This - * channel has to be the current channel (remain-on-channel or the - * operational channel). When called, this operation returns a cookie - * (%NL80211_ATTR_COOKIE) that will be included with the TX status event - * pertaining to the TX request. + * which channel the frame is to be transmitted or was received. If this + * channel is not the current channel (remain-on-channel or the + * operational channel) the device will switch to the given channel and + * transmit the frame, optionally waiting for a response for the time + * specified using %NL80211_ATTR_DURATION. When called, this operation + * returns a cookie (%NL80211_ATTR_COOKIE) that will be included with the + * TX status event pertaining to the TX request. + * @NL80211_CMD_FRAME_WAIT_CANCEL: When an off-channel TX was requested, this + * command may be used with the corresponding cookie to cancel the wait + * time if it is known that it is no longer necessary. * @NL80211_CMD_ACTION: Alias for @NL80211_CMD_FRAME for backward compatibility. * @NL80211_CMD_FRAME_TX_STATUS: Report TX status of a management frame * transmitted with %NL80211_CMD_FRAME. %NL80211_ATTR_COOKIE identifies @@ -493,6 +498,8 @@ enum nl80211_commands { NL80211_CMD_SET_CHANNEL, NL80211_CMD_SET_WDS_PEER, + NL80211_CMD_FRAME_WAIT_CANCEL, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ @@ -828,6 +835,12 @@ enum nl80211_commands { * * @NL80211_ATTR_MCAST_RATE: Multicast tx rate (in 100 kbps) for IBSS * + * @NL80211_ATTR_OFFCHANNEL_TX_OK: For management frame TX, the frame may be + * transmitted on another channel when the channel given doesn't match + * the current channel. If the current channel doesn't match and this + * flag isn't set, the frame will be rejected. This is also used as an + * nl80211 capability flag. + * * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use */ @@ -1002,6 +1015,8 @@ enum nl80211_attrs { NL80211_ATTR_MCAST_RATE, + NL80211_ATTR_OFFCHANNEL_TX_OK, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 0663945cfa48..49a7c53a48ca 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1134,7 +1134,9 @@ struct cfg80211_pmksa { * @cancel_remain_on_channel: Cancel an on-going remain-on-channel operation. * This allows the operation to be terminated prior to timeout based on * the duration value. - * @mgmt_tx: Transmit a management frame + * @mgmt_tx: Transmit a management frame. + * @mgmt_tx_cancel_wait: Cancel the wait time from transmitting a management + * frame on another channel * * @testmode_cmd: run a test mode command * @@ -1291,10 +1293,13 @@ struct cfg80211_ops { u64 cookie); int (*mgmt_tx)(struct wiphy *wiphy, struct net_device *dev, - struct ieee80211_channel *chan, + struct ieee80211_channel *chan, bool offchan, enum nl80211_channel_type channel_type, - bool channel_type_valid, + bool channel_type_valid, unsigned int wait, const u8 *buf, size_t len, u64 *cookie); + int (*mgmt_tx_cancel_wait)(struct wiphy *wiphy, + struct net_device *dev, + u64 cookie); int (*set_power_mgmt)(struct wiphy *wiphy, struct net_device *dev, bool enabled, int timeout); diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 0c544074479e..aac2d7de828e 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1552,9 +1552,9 @@ static int ieee80211_cancel_remain_on_channel(struct wiphy *wiphy, } static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct net_device *dev, - struct ieee80211_channel *chan, + struct ieee80211_channel *chan, bool offchan, enum nl80211_channel_type channel_type, - bool channel_type_valid, + bool channel_type_valid, unsigned int wait, const u8 *buf, size_t len, u64 *cookie) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); @@ -1565,6 +1565,9 @@ static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct net_device *dev, u32 flags = IEEE80211_TX_INTFL_NL80211_FRAME_TX | IEEE80211_TX_CTL_REQ_TX_STATUS; + if (offchan) + return -EOPNOTSUPP; + /* Check that we are on the requested channel for transmission */ if (chan != local->tmp_channel && chan != local->oper_channel) diff --git a/net/wireless/core.h b/net/wireless/core.h index 6583cca0e2ee..ee80ad8dc655 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -341,9 +341,9 @@ void cfg80211_mlme_unregister_socket(struct wireless_dev *wdev, u32 nlpid); void cfg80211_mlme_purge_registrations(struct wireless_dev *wdev); int cfg80211_mlme_mgmt_tx(struct cfg80211_registered_device *rdev, struct net_device *dev, - struct ieee80211_channel *chan, + struct ieee80211_channel *chan, bool offchan, enum nl80211_channel_type channel_type, - bool channel_type_valid, + bool channel_type_valid, unsigned int wait, const u8 *buf, size_t len, u64 *cookie); /* SME */ diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index 6980a0c315b2..d7680f2a4c5b 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -864,9 +864,9 @@ void cfg80211_mlme_purge_registrations(struct wireless_dev *wdev) int cfg80211_mlme_mgmt_tx(struct cfg80211_registered_device *rdev, struct net_device *dev, - struct ieee80211_channel *chan, + struct ieee80211_channel *chan, bool offchan, enum nl80211_channel_type channel_type, - bool channel_type_valid, + bool channel_type_valid, unsigned int wait, const u8 *buf, size_t len, u64 *cookie) { struct wireless_dev *wdev = dev->ieee80211_ptr; @@ -946,8 +946,9 @@ int cfg80211_mlme_mgmt_tx(struct cfg80211_registered_device *rdev, return -EINVAL; /* Transmit the Action frame as requested by user space */ - return rdev->ops->mgmt_tx(&rdev->wiphy, dev, chan, channel_type, - channel_type_valid, buf, len, cookie); + return rdev->ops->mgmt_tx(&rdev->wiphy, dev, chan, offchan, + channel_type, channel_type_valid, + wait, buf, len, cookie); } bool cfg80211_rx_mgmt(struct net_device *dev, int freq, const u8 *buf, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 67ff7e92cb99..960be4e650f0 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -163,16 +163,13 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = { [NL80211_ATTR_CQM] = { .type = NLA_NESTED, }, [NL80211_ATTR_LOCAL_STATE_CHANGE] = { .type = NLA_FLAG }, [NL80211_ATTR_AP_ISOLATE] = { .type = NLA_U8 }, - [NL80211_ATTR_WIPHY_TX_POWER_SETTING] = { .type = NLA_U32 }, [NL80211_ATTR_WIPHY_TX_POWER_LEVEL] = { .type = NLA_U32 }, - [NL80211_ATTR_FRAME_TYPE] = { .type = NLA_U16 }, - [NL80211_ATTR_WIPHY_ANTENNA_TX] = { .type = NLA_U32 }, [NL80211_ATTR_WIPHY_ANTENNA_RX] = { .type = NLA_U32 }, - [NL80211_ATTR_MCAST_RATE] = { .type = NLA_U32 }, + [NL80211_ATTR_OFFCHANNEL_TX_OK] = { .type = NLA_FLAG }, }; /* policy for the key attributes */ @@ -677,6 +674,7 @@ static int nl80211_send_wiphy(struct sk_buff *msg, u32 pid, u32 seq, int flags, CMD(remain_on_channel, REMAIN_ON_CHANNEL); CMD(set_bitrate_mask, SET_TX_BITRATE_MASK); CMD(mgmt_tx, FRAME); + CMD(mgmt_tx_cancel_wait, FRAME_WAIT_CANCEL); if (dev->wiphy.flags & WIPHY_FLAG_NETNS_OK) { i++; NLA_PUT_U32(msg, i, NL80211_CMD_SET_WIPHY_NETNS); @@ -698,6 +696,10 @@ static int nl80211_send_wiphy(struct sk_buff *msg, u32 pid, u32 seq, int flags, nla_nest_end(msg, nl_cmds); + /* for now at least assume all drivers have it */ + if (dev->ops->mgmt_tx) + NLA_PUT_FLAG(msg, NL80211_ATTR_OFFCHANNEL_TX_OK); + if (mgmt_stypes) { u16 stypes; struct nlattr *nl_ftypes, *nl_ifs; @@ -4244,6 +4246,8 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info) void *hdr; u64 cookie; struct sk_buff *msg; + unsigned int wait = 0; + bool offchan; if (!info->attrs[NL80211_ATTR_FRAME] || !info->attrs[NL80211_ATTR_WIPHY_FREQ]) @@ -4260,6 +4264,12 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info) dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_GO) return -EOPNOTSUPP; + if (info->attrs[NL80211_ATTR_DURATION]) { + if (!rdev->ops->mgmt_tx_cancel_wait) + return -EINVAL; + wait = nla_get_u32(info->attrs[NL80211_ATTR_DURATION]); + } + if (info->attrs[NL80211_ATTR_WIPHY_CHANNEL_TYPE]) { channel_type = nla_get_u32( info->attrs[NL80211_ATTR_WIPHY_CHANNEL_TYPE]); @@ -4271,6 +4281,8 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info) channel_type_valid = true; } + offchan = info->attrs[NL80211_ATTR_OFFCHANNEL_TX_OK]; + freq = nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ]); chan = rdev_freq_to_chan(rdev, freq, channel_type); if (chan == NULL) @@ -4287,8 +4299,8 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info) err = PTR_ERR(hdr); goto free_msg; } - err = cfg80211_mlme_mgmt_tx(rdev, dev, chan, channel_type, - channel_type_valid, + err = cfg80211_mlme_mgmt_tx(rdev, dev, chan, offchan, channel_type, + channel_type_valid, wait, nla_data(info->attrs[NL80211_ATTR_FRAME]), nla_len(info->attrs[NL80211_ATTR_FRAME]), &cookie); @@ -4307,6 +4319,31 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info) return err; } +static int nl80211_tx_mgmt_cancel_wait(struct sk_buff *skb, struct genl_info *info) +{ + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; + u64 cookie; + + if (!info->attrs[NL80211_ATTR_COOKIE]) + return -EINVAL; + + if (!rdev->ops->mgmt_tx_cancel_wait) + return -EOPNOTSUPP; + + if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_STATION && + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_ADHOC && + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_CLIENT && + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_AP && + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_AP_VLAN && + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_GO) + return -EOPNOTSUPP; + + cookie = nla_get_u64(info->attrs[NL80211_ATTR_COOKIE]); + + return rdev->ops->mgmt_tx_cancel_wait(&rdev->wiphy, dev, cookie); +} + static int nl80211_set_power_save(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; @@ -4879,6 +4916,14 @@ static struct genl_ops nl80211_ops[] = { .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, }, + { + .cmd = NL80211_CMD_FRAME_WAIT_CANCEL, + .doit = nl80211_tx_mgmt_cancel_wait, + .policy = nl80211_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | + NL80211_FLAG_NEED_RTNL, + }, { .cmd = NL80211_CMD_SET_POWER_SAVE, .doit = nl80211_set_power_save, -- cgit v1.2.3 From 24278d148316d2180be6df40e06db013d8b232b8 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 27 Sep 2010 17:25:23 -0700 Subject: rcu: priority boosting for TINY_PREEMPT_RCU Add priority boosting, but only for TINY_PREEMPT_RCU. This is enabled by the default-off RCU_BOOST kernel parameter. The priority to which to boost preempted RCU readers is controlled by the RCU_BOOST_PRIO kernel parameter (defaulting to real-time priority 1) and the time to wait before boosting the readers blocking a given grace period is controlled by the RCU_BOOST_DELAY kernel parameter (defaulting to 500 milliseconds). Signed-off-by: Paul E. McKenney Signed-off-by: Paul E. McKenney --- include/linux/init_task.h | 9 +- include/linux/sched.h | 11 ++- init/Kconfig | 39 +++++++++ kernel/rcutiny.c | 66 ++++++--------- kernel/rcutiny_plugin.h | 208 +++++++++++++++++++++++++++++++++++++++++++--- 5 files changed, 280 insertions(+), 53 deletions(-) (limited to 'include/linux') diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 2fea6c8ef6ba..69f91aacdeee 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -81,6 +81,12 @@ extern struct group_info init_groups; */ # define CAP_INIT_BSET CAP_FULL_SET +#ifdef CONFIG_RCU_BOOST +#define INIT_TASK_RCU_BOOST() \ + .rcu_boost_mutex = NULL, +#else +#define INIT_TASK_RCU_BOOST() +#endif #ifdef CONFIG_TREE_PREEMPT_RCU #define INIT_TASK_RCU_TREE_PREEMPT() \ .rcu_blocked_node = NULL, @@ -92,7 +98,8 @@ extern struct group_info init_groups; .rcu_read_lock_nesting = 0, \ .rcu_read_unlock_special = 0, \ .rcu_node_entry = LIST_HEAD_INIT(tsk.rcu_node_entry), \ - INIT_TASK_RCU_TREE_PREEMPT() + INIT_TASK_RCU_TREE_PREEMPT() \ + INIT_TASK_RCU_BOOST() #else #define INIT_TASK_RCU_PREEMPT(tsk) #endif diff --git a/include/linux/sched.h b/include/linux/sched.h index e18473f0eb78..ed1a9bc52b2f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1210,6 +1210,9 @@ struct task_struct { #ifdef CONFIG_TREE_PREEMPT_RCU struct rcu_node *rcu_blocked_node; #endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ +#ifdef CONFIG_RCU_BOOST + struct rt_mutex *rcu_boost_mutex; +#endif /* #ifdef CONFIG_RCU_BOOST */ #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) struct sched_info sched_info; @@ -1745,7 +1748,8 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t * #ifdef CONFIG_PREEMPT_RCU #define RCU_READ_UNLOCK_BLOCKED (1 << 0) /* blocked while in RCU read-side. */ -#define RCU_READ_UNLOCK_NEED_QS (1 << 1) /* RCU core needs CPU response. */ +#define RCU_READ_UNLOCK_BOOSTED (1 << 1) /* boosted while in RCU read-side. */ +#define RCU_READ_UNLOCK_NEED_QS (1 << 2) /* RCU core needs CPU response. */ static inline void rcu_copy_process(struct task_struct *p) { @@ -1753,7 +1757,10 @@ static inline void rcu_copy_process(struct task_struct *p) p->rcu_read_unlock_special = 0; #ifdef CONFIG_TREE_PREEMPT_RCU p->rcu_blocked_node = NULL; -#endif +#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ +#ifdef CONFIG_RCU_BOOST + p->rcu_boost_mutex = NULL; +#endif /* #ifdef CONFIG_RCU_BOOST */ INIT_LIST_HEAD(&p->rcu_node_entry); } diff --git a/init/Kconfig b/init/Kconfig index a619a1ac7f4c..48efefcac12a 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -450,6 +450,45 @@ config TREE_RCU_TRACE TREE_PREEMPT_RCU implementations, permitting Makefile to trivially select kernel/rcutree_trace.c. +config RCU_BOOST + bool "Enable RCU priority boosting" + depends on RT_MUTEXES && TINY_PREEMPT_RCU + default n + help + This option boosts the priority of preempted RCU readers that + block the current preemptible RCU grace period for too long. + This option also prevents heavy loads from blocking RCU + callback invocation for all flavors of RCU. + + Say Y here if you are working with real-time apps or heavy loads + Say N here if you are unsure. + +config RCU_BOOST_PRIO + int "Real-time priority to boost RCU readers to" + range 1 99 + depends on RCU_BOOST + default 1 + help + This option specifies the real-time priority to which preempted + RCU readers are to be boosted. If you are working with CPU-bound + real-time applications, you should specify a priority higher then + the highest-priority CPU-bound application. + + Specify the real-time priority, or take the default if unsure. + +config RCU_BOOST_DELAY + int "Milliseconds to delay boosting after RCU grace-period start" + range 0 3000 + depends on RCU_BOOST + default 500 + help + This option specifies the time to wait after the beginning of + a given grace period before priority-boosting preempted RCU + readers blocking that grace period. Note that any RCU reader + blocking an expedited RCU grace period is boosted immediately. + + Accept the default if unsure. + endmenu # "RCU Subsystem" config IKCONFIG diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c index 86eef29cdfb2..93d166582cbb 100644 --- a/kernel/rcutiny.c +++ b/kernel/rcutiny.c @@ -36,38 +36,16 @@ #include #include -/* Global control variables for rcupdate callback mechanism. */ -struct rcu_ctrlblk { - struct rcu_head *rcucblist; /* List of pending callbacks (CBs). */ - struct rcu_head **donetail; /* ->next pointer of last "done" CB. */ - struct rcu_head **curtail; /* ->next pointer of last CB. */ -}; - -/* Definition for rcupdate control block. */ -static struct rcu_ctrlblk rcu_sched_ctrlblk = { - .donetail = &rcu_sched_ctrlblk.rcucblist, - .curtail = &rcu_sched_ctrlblk.rcucblist, -}; - -static struct rcu_ctrlblk rcu_bh_ctrlblk = { - .donetail = &rcu_bh_ctrlblk.rcucblist, - .curtail = &rcu_bh_ctrlblk.rcucblist, -}; - -#ifdef CONFIG_DEBUG_LOCK_ALLOC -int rcu_scheduler_active __read_mostly; -EXPORT_SYMBOL_GPL(rcu_scheduler_active); -#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ - -/* Controls for rcu_cbs() kthread, replacing RCU_SOFTIRQ used previously. */ -static struct task_struct *rcu_cbs_task; -static DECLARE_WAIT_QUEUE_HEAD(rcu_cbs_wq); -static unsigned long have_rcu_cbs; -static void invoke_rcu_cbs(void); +/* Controls for rcu_kthread() kthread, replacing RCU_SOFTIRQ used previously. */ +static struct task_struct *rcu_kthread_task; +static DECLARE_WAIT_QUEUE_HEAD(rcu_kthread_wq); +static unsigned long have_rcu_kthread_work; +static void invoke_rcu_kthread(void); /* Forward declarations for rcutiny_plugin.h. */ +struct rcu_ctrlblk; static void rcu_process_callbacks(struct rcu_ctrlblk *rcp); -static int rcu_cbs(void *arg); +static int rcu_kthread(void *arg); static void __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), struct rcu_ctrlblk *rcp); @@ -130,7 +108,7 @@ void rcu_sched_qs(int cpu) { if (rcu_qsctr_help(&rcu_sched_ctrlblk) + rcu_qsctr_help(&rcu_bh_ctrlblk)) - invoke_rcu_cbs(); + invoke_rcu_kthread(); } /* @@ -139,7 +117,7 @@ void rcu_sched_qs(int cpu) void rcu_bh_qs(int cpu) { if (rcu_qsctr_help(&rcu_bh_ctrlblk)) - invoke_rcu_cbs(); + invoke_rcu_kthread(); } /* @@ -201,37 +179,41 @@ static void rcu_process_callbacks(struct rcu_ctrlblk *rcp) * This is a kthread, but it is never stopped, at least not until * the system goes down. */ -static int rcu_cbs(void *arg) +static int rcu_kthread(void *arg) { unsigned long work; + unsigned long morework; unsigned long flags; for (;;) { - wait_event(rcu_cbs_wq, have_rcu_cbs != 0); + wait_event(rcu_kthread_wq, have_rcu_kthread_work != 0); + morework = rcu_boost(); local_irq_save(flags); - work = have_rcu_cbs; - have_rcu_cbs = 0; + work = have_rcu_kthread_work; + have_rcu_kthread_work = morework; local_irq_restore(flags); if (work) { rcu_process_callbacks(&rcu_sched_ctrlblk); rcu_process_callbacks(&rcu_bh_ctrlblk); rcu_preempt_process_callbacks(); } + schedule_timeout_interruptible(1); /* Leave CPU for others. */ } return 0; /* Not reached, but needed to shut gcc up. */ } /* - * Wake up rcu_cbs() to process callbacks now eligible for invocation. + * Wake up rcu_kthread() to process callbacks now eligible for invocation + * or to boost readers. */ -static void invoke_rcu_cbs(void) +static void invoke_rcu_kthread(void) { unsigned long flags; local_irq_save(flags); - have_rcu_cbs = 1; - wake_up(&rcu_cbs_wq); + have_rcu_kthread_work = 1; + wake_up(&rcu_kthread_wq); local_irq_restore(flags); } @@ -327,7 +309,11 @@ EXPORT_SYMBOL_GPL(rcu_barrier_sched); */ static int __init rcu_spawn_kthreads(void) { - rcu_cbs_task = kthread_run(rcu_cbs, NULL, "rcu_cbs"); + struct sched_param sp; + + rcu_kthread_task = kthread_run(rcu_kthread, NULL, "rcu_kthread"); + sp.sched_priority = RCU_BOOST_PRIO; + sched_setscheduler_nocheck(rcu_kthread_task, SCHED_FIFO, &sp); return 0; } early_initcall(rcu_spawn_kthreads); diff --git a/kernel/rcutiny_plugin.h b/kernel/rcutiny_plugin.h index 95f9239df512..24f43165f222 100644 --- a/kernel/rcutiny_plugin.h +++ b/kernel/rcutiny_plugin.h @@ -24,6 +24,29 @@ #include +/* Global control variables for rcupdate callback mechanism. */ +struct rcu_ctrlblk { + struct rcu_head *rcucblist; /* List of pending callbacks (CBs). */ + struct rcu_head **donetail; /* ->next pointer of last "done" CB. */ + struct rcu_head **curtail; /* ->next pointer of last CB. */ +}; + +/* Definition for rcupdate control block. */ +static struct rcu_ctrlblk rcu_sched_ctrlblk = { + .donetail = &rcu_sched_ctrlblk.rcucblist, + .curtail = &rcu_sched_ctrlblk.rcucblist, +}; + +static struct rcu_ctrlblk rcu_bh_ctrlblk = { + .donetail = &rcu_bh_ctrlblk.rcucblist, + .curtail = &rcu_bh_ctrlblk.rcucblist, +}; + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +int rcu_scheduler_active __read_mostly; +EXPORT_SYMBOL_GPL(rcu_scheduler_active); +#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ + #ifdef CONFIG_TINY_PREEMPT_RCU #include @@ -48,17 +71,27 @@ struct rcu_preempt_ctrlblk { struct list_head *gp_tasks; /* Pointer to the first task blocking the */ /* current grace period, or NULL if there */ - /* is not such task. */ + /* is no such task. */ struct list_head *exp_tasks; /* Pointer to first task blocking the */ /* current expedited grace period, or NULL */ /* if there is no such task. If there */ /* is no current expedited grace period, */ /* then there cannot be any such task. */ +#ifdef CONFIG_RCU_BOOST + struct list_head *boost_tasks; + /* Pointer to first task that needs to be */ + /* priority-boosted, or NULL if no priority */ + /* boosting is needed. If there is no */ + /* current or expedited grace period, there */ + /* can be no such task. */ +#endif /* #ifdef CONFIG_RCU_BOOST */ u8 gpnum; /* Current grace period. */ u8 gpcpu; /* Last grace period blocked by the CPU. */ u8 completed; /* Last grace period completed. */ /* If all three are equal, RCU is idle. */ + s8 boosted_this_gp; /* Has boosting already happened? */ + unsigned long boost_time; /* When to start boosting (jiffies) */ }; static struct rcu_preempt_ctrlblk rcu_preempt_ctrlblk = { @@ -123,6 +156,130 @@ static int rcu_preempt_gp_in_progress(void) return rcu_preempt_ctrlblk.completed != rcu_preempt_ctrlblk.gpnum; } +/* + * Advance a ->blkd_tasks-list pointer to the next entry, instead + * returning NULL if at the end of the list. + */ +static struct list_head *rcu_next_node_entry(struct task_struct *t) +{ + struct list_head *np; + + np = t->rcu_node_entry.next; + if (np == &rcu_preempt_ctrlblk.blkd_tasks) + np = NULL; + return np; +} + +#ifdef CONFIG_RCU_BOOST + +#include "rtmutex_common.h" + +/* + * Carry out RCU priority boosting on the task indicated by ->boost_tasks, + * and advance ->boost_tasks to the next task in the ->blkd_tasks list. + */ +static int rcu_boost(void) +{ + unsigned long flags; + struct rt_mutex mtx; + struct list_head *np; + struct task_struct *t; + + if (rcu_preempt_ctrlblk.boost_tasks == NULL) + return 0; /* Nothing to boost. */ + raw_local_irq_save(flags); + rcu_preempt_ctrlblk.boosted_this_gp++; + t = container_of(rcu_preempt_ctrlblk.boost_tasks, struct task_struct, + rcu_node_entry); + np = rcu_next_node_entry(t); + rt_mutex_init_proxy_locked(&mtx, t); + t->rcu_boost_mutex = &mtx; + t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BOOSTED; + raw_local_irq_restore(flags); + rt_mutex_lock(&mtx); + rt_mutex_unlock(&mtx); + return rcu_preempt_ctrlblk.boost_tasks != NULL; +} + +/* + * Check to see if it is now time to start boosting RCU readers blocking + * the current grace period, and, if so, tell the rcu_kthread_task to + * start boosting them. If there is an expedited boost in progress, + * we wait for it to complete. + */ +static void rcu_initiate_boost(void) +{ + if (rcu_preempt_ctrlblk.gp_tasks != NULL && + rcu_preempt_ctrlblk.boost_tasks == NULL && + rcu_preempt_ctrlblk.boosted_this_gp == 0 && + ULONG_CMP_GE(jiffies, rcu_preempt_ctrlblk.boost_time)) { + rcu_preempt_ctrlblk.boost_tasks = rcu_preempt_ctrlblk.gp_tasks; + invoke_rcu_kthread(); + } +} + +/* + * Initiate boosting for an expedited grace period. + */ +static void rcu_initiate_expedited_boost(void) +{ + unsigned long flags; + + raw_local_irq_save(flags); + if (!list_empty(&rcu_preempt_ctrlblk.blkd_tasks)) { + rcu_preempt_ctrlblk.boost_tasks = + rcu_preempt_ctrlblk.blkd_tasks.next; + rcu_preempt_ctrlblk.boosted_this_gp = -1; + invoke_rcu_kthread(); + } + raw_local_irq_restore(flags); +} + +#define RCU_BOOST_DELAY_JIFFIES DIV_ROUND_UP(CONFIG_RCU_BOOST_DELAY * HZ, 1000); + +/* + * Do priority-boost accounting for the start of a new grace period. + */ +static void rcu_preempt_boost_start_gp(void) +{ + rcu_preempt_ctrlblk.boost_time = jiffies + RCU_BOOST_DELAY_JIFFIES; + if (rcu_preempt_ctrlblk.boosted_this_gp > 0) + rcu_preempt_ctrlblk.boosted_this_gp = 0; +} + +#else /* #ifdef CONFIG_RCU_BOOST */ + +/* + * If there is no RCU priority boosting, we don't boost. + */ +static int rcu_boost(void) +{ + return 0; +} + +/* + * If there is no RCU priority boosting, we don't initiate boosting. + */ +static void rcu_initiate_boost(void) +{ +} + +/* + * If there is no RCU priority boosting, we don't initiate expedited boosting. + */ +static void rcu_initiate_expedited_boost(void) +{ +} + +/* + * If there is no RCU priority boosting, nothing to do at grace-period start. + */ +static void rcu_preempt_boost_start_gp(void) +{ +} + +#endif /* else #ifdef CONFIG_RCU_BOOST */ + /* * Record a preemptible-RCU quiescent state for the specified CPU. Note * that this just means that the task currently running on the CPU is @@ -150,12 +307,14 @@ static void rcu_preempt_cpu_qs(void) rcu_preempt_ctrlblk.gpcpu = rcu_preempt_ctrlblk.gpnum; current->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS; - /* - * If there is no GP, or if blocked readers are still blocking GP, - * then there is nothing more to do. - */ + /* If there is no GP then there is nothing more to do. */ if (!rcu_preempt_gp_in_progress() || rcu_preempt_blocked_readers_cgp()) return; + /* If there are blocked readers, go check up on boosting. */ + if (rcu_preempt_blocked_readers_cgp()) { + rcu_initiate_boost(); + return; + } /* Advance callbacks. */ rcu_preempt_ctrlblk.completed = rcu_preempt_ctrlblk.gpnum; @@ -168,7 +327,7 @@ static void rcu_preempt_cpu_qs(void) /* If there are done callbacks, cause them to be invoked. */ if (*rcu_preempt_ctrlblk.rcb.donetail != NULL) - invoke_rcu_cbs(); + invoke_rcu_kthread(); } /* @@ -186,6 +345,9 @@ static void rcu_preempt_start_gp(void) rcu_preempt_ctrlblk.gp_tasks = rcu_preempt_ctrlblk.blkd_tasks.next; + /* Set up for RCU priority boosting. */ + rcu_preempt_boost_start_gp(); + /* If there is no running reader, CPU is done with GP. */ if (!rcu_preempt_running_reader()) rcu_preempt_cpu_qs(); @@ -306,14 +468,16 @@ static void rcu_read_unlock_special(struct task_struct *t) */ empty = !rcu_preempt_blocked_readers_cgp(); empty_exp = rcu_preempt_ctrlblk.exp_tasks == NULL; - np = t->rcu_node_entry.next; - if (np == &rcu_preempt_ctrlblk.blkd_tasks) - np = NULL; + np = rcu_next_node_entry(t); list_del(&t->rcu_node_entry); if (&t->rcu_node_entry == rcu_preempt_ctrlblk.gp_tasks) rcu_preempt_ctrlblk.gp_tasks = np; if (&t->rcu_node_entry == rcu_preempt_ctrlblk.exp_tasks) rcu_preempt_ctrlblk.exp_tasks = np; +#ifdef CONFIG_RCU_BOOST + if (&t->rcu_node_entry == rcu_preempt_ctrlblk.boost_tasks) + rcu_preempt_ctrlblk.boost_tasks = np; +#endif /* #ifdef CONFIG_RCU_BOOST */ INIT_LIST_HEAD(&t->rcu_node_entry); /* @@ -333,6 +497,14 @@ static void rcu_read_unlock_special(struct task_struct *t) if (!empty_exp && rcu_preempt_ctrlblk.exp_tasks == NULL) rcu_report_exp_done(); } +#ifdef CONFIG_RCU_BOOST + /* Unboost self if was boosted. */ + if (special & RCU_READ_UNLOCK_BOOSTED) { + t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_BOOSTED; + rt_mutex_unlock(t->rcu_boost_mutex); + t->rcu_boost_mutex = NULL; + } +#endif /* #ifdef CONFIG_RCU_BOOST */ local_irq_restore(flags); } @@ -376,7 +548,7 @@ static void rcu_preempt_check_callbacks(void) rcu_preempt_cpu_qs(); if (&rcu_preempt_ctrlblk.rcb.rcucblist != rcu_preempt_ctrlblk.rcb.donetail) - invoke_rcu_cbs(); + invoke_rcu_kthread(); if (rcu_preempt_gp_in_progress() && rcu_cpu_blocking_cur_gp() && rcu_preempt_running_reader()) @@ -534,6 +706,7 @@ void synchronize_rcu_expedited(void) /* Wait for tail of ->blkd_tasks list to drain. */ if (rcu_preempted_readers_exp()) + rcu_initiate_expedited_boost(); wait_event(sync_rcu_preempt_exp_wq, !rcu_preempted_readers_exp()); @@ -574,6 +747,15 @@ void exit_rcu(void) #else /* #ifdef CONFIG_TINY_PREEMPT_RCU */ +/* + * Because preemptible RCU does not exist, it is never necessary to + * boost preempted RCU readers. + */ +static int rcu_boost(void) +{ + return 0; +} + /* * Because preemptible RCU does not exist, it never has any callbacks * to check. @@ -614,3 +796,9 @@ void __init rcu_scheduler_starting(void) } #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ + +#ifdef CONFIG_RCU_BOOST +#define RCU_BOOST_PRIO CONFIG_RCU_BOOST_PRIO +#else /* #ifdef CONFIG_RCU_BOOST */ +#define RCU_BOOST_PRIO 1 +#endif /* #else #ifdef CONFIG_RCU_BOOST */ -- cgit v1.2.3 From 7b27d5475f86186914e54e4a6bb994e9a985337b Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Thu, 21 Oct 2010 11:29:05 +0800 Subject: rcu,cleanup: move synchronize_sched_expedited() out of sched.c The first version of synchronize_sched_expedited() used the migration code in the scheduler, and was therefore implemented in kernel/sched.c. However, the more recent version of this code no longer uses the migration code, so this commit moves it to the main RCU source files. Signed-off-by: Lai Jiangshan Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 1 - include/linux/rcutiny.h | 5 ++++ include/linux/rcutree.h | 1 + kernel/rcutree_plugin.h | 71 ++++++++++++++++++++++++++++++++++++++++++++++++ kernel/sched.c | 69 ---------------------------------------------- 5 files changed, 77 insertions(+), 70 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 7142ee3304ab..49e8e16308e1 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -66,7 +66,6 @@ extern void call_rcu_sched(struct rcu_head *head, extern void synchronize_sched(void); extern void rcu_barrier_bh(void); extern void rcu_barrier_sched(void); -extern void synchronize_sched_expedited(void); extern int sched_expedited_torture_stats(char *page); static inline void __rcu_read_lock_bh(void) diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index ea025a611fcc..30ebd7c8d874 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -60,6 +60,11 @@ static inline void synchronize_rcu_bh_expedited(void) synchronize_sched(); } +static inline void synchronize_sched_expedited(void) +{ + synchronize_sched(); +} + #ifdef CONFIG_TINY_RCU static inline void rcu_preempt_note_context_switch(void) diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index c0e96833aa73..3a933482734a 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -48,6 +48,7 @@ static inline void exit_rcu(void) #endif /* #else #ifdef CONFIG_TREE_PREEMPT_RCU */ extern void synchronize_rcu_bh(void); +extern void synchronize_sched_expedited(void); extern void synchronize_rcu_expedited(void); static inline void synchronize_rcu_bh_expedited(void) diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index 71a4147473f9..21df7f3e7273 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -25,6 +25,7 @@ */ #include +#include /* * Check the RCU kernel configuration parameters and print informative @@ -1014,6 +1015,76 @@ static void __init __rcu_init_preempt(void) #endif /* #else #ifdef CONFIG_TREE_PREEMPT_RCU */ +#ifndef CONFIG_SMP + +void synchronize_sched_expedited(void) +{ + cond_resched(); +} +EXPORT_SYMBOL_GPL(synchronize_sched_expedited); + +#else /* #ifndef CONFIG_SMP */ + +static atomic_t synchronize_sched_expedited_count = ATOMIC_INIT(0); + +static int synchronize_sched_expedited_cpu_stop(void *data) +{ + /* + * There must be a full memory barrier on each affected CPU + * between the time that try_stop_cpus() is called and the + * time that it returns. + * + * In the current initial implementation of cpu_stop, the + * above condition is already met when the control reaches + * this point and the following smp_mb() is not strictly + * necessary. Do smp_mb() anyway for documentation and + * robustness against future implementation changes. + */ + smp_mb(); /* See above comment block. */ + return 0; +} + +/* + * Wait for an rcu-sched grace period to elapse, but use "big hammer" + * approach to force grace period to end quickly. This consumes + * significant time on all CPUs, and is thus not recommended for + * any sort of common-case code. + * + * Note that it is illegal to call this function while holding any + * lock that is acquired by a CPU-hotplug notifier. Failing to + * observe this restriction will result in deadlock. + */ +void synchronize_sched_expedited(void) +{ + int snap, trycount = 0; + + smp_mb(); /* ensure prior mod happens before capturing snap. */ + snap = atomic_read(&synchronize_sched_expedited_count) + 1; + get_online_cpus(); + while (try_stop_cpus(cpu_online_mask, + synchronize_sched_expedited_cpu_stop, + NULL) == -EAGAIN) { + put_online_cpus(); + if (trycount++ < 10) + udelay(trycount * num_online_cpus()); + else { + synchronize_sched(); + return; + } + if (atomic_read(&synchronize_sched_expedited_count) - snap > 0) { + smp_mb(); /* ensure test happens before caller kfree */ + return; + } + get_online_cpus(); + } + atomic_inc(&synchronize_sched_expedited_count); + smp_mb__after_atomic_inc(); /* ensure post-GP actions seen after GP. */ + put_online_cpus(); +} +EXPORT_SYMBOL_GPL(synchronize_sched_expedited); + +#endif /* #else #ifndef CONFIG_SMP */ + #if !defined(CONFIG_RCU_FAST_NO_HZ) /* diff --git a/kernel/sched.c b/kernel/sched.c index ae8f75a5ceb4..d1e8889872a1 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -9131,72 +9131,3 @@ struct cgroup_subsys cpuacct_subsys = { }; #endif /* CONFIG_CGROUP_CPUACCT */ -#ifndef CONFIG_SMP - -void synchronize_sched_expedited(void) -{ - barrier(); -} -EXPORT_SYMBOL_GPL(synchronize_sched_expedited); - -#else /* #ifndef CONFIG_SMP */ - -static atomic_t synchronize_sched_expedited_count = ATOMIC_INIT(0); - -static int synchronize_sched_expedited_cpu_stop(void *data) -{ - /* - * There must be a full memory barrier on each affected CPU - * between the time that try_stop_cpus() is called and the - * time that it returns. - * - * In the current initial implementation of cpu_stop, the - * above condition is already met when the control reaches - * this point and the following smp_mb() is not strictly - * necessary. Do smp_mb() anyway for documentation and - * robustness against future implementation changes. - */ - smp_mb(); /* See above comment block. */ - return 0; -} - -/* - * Wait for an rcu-sched grace period to elapse, but use "big hammer" - * approach to force grace period to end quickly. This consumes - * significant time on all CPUs, and is thus not recommended for - * any sort of common-case code. - * - * Note that it is illegal to call this function while holding any - * lock that is acquired by a CPU-hotplug notifier. Failing to - * observe this restriction will result in deadlock. - */ -void synchronize_sched_expedited(void) -{ - int snap, trycount = 0; - - smp_mb(); /* ensure prior mod happens before capturing snap. */ - snap = atomic_read(&synchronize_sched_expedited_count) + 1; - get_online_cpus(); - while (try_stop_cpus(cpu_online_mask, - synchronize_sched_expedited_cpu_stop, - NULL) == -EAGAIN) { - put_online_cpus(); - if (trycount++ < 10) - udelay(trycount * num_online_cpus()); - else { - synchronize_sched(); - return; - } - if (atomic_read(&synchronize_sched_expedited_count) - snap > 0) { - smp_mb(); /* ensure test happens before caller kfree */ - return; - } - get_online_cpus(); - } - atomic_inc(&synchronize_sched_expedited_count); - smp_mb__after_atomic_inc(); /* ensure post-GP actions seen after GP. */ - put_online_cpus(); -} -EXPORT_SYMBOL_GPL(synchronize_sched_expedited); - -#endif /* #else #ifndef CONFIG_SMP */ -- cgit v1.2.3 From 9833c39400c3e6ee19daeded6910df648741611e Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Fri, 19 Nov 2010 09:29:24 +0100 Subject: ARM: 6485/5: proc/vmcore - allow archs to override vmcore_elf_check_arch() Allow architectures to redefine this macro if needed. This is useful for example in architectures where 64-bit ELF vmcores are not supported. Specifying zero vmcore_elf64_check_arch() allows compiler to optimize away unnecessary parts of parse_crash_elf64_headers(). We also rename the macro to vmcore_elf64_check_arch() to reflect that it is used for 64-bit vmcores only. Signed-off-by: Mika Westerberg Signed-off-by: Russell King --- fs/proc/vmcore.c | 2 +- include/linux/crash_dump.h | 9 ++++++++- 2 files changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index 2367fb3f70bc..74802bc5ded9 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -499,7 +499,7 @@ static int __init parse_crash_elf64_headers(void) /* Do some basic Verification. */ if (memcmp(ehdr.e_ident, ELFMAG, SELFMAG) != 0 || (ehdr.e_type != ET_CORE) || - !vmcore_elf_check_arch(&ehdr) || + !vmcore_elf64_check_arch(&ehdr) || ehdr.e_ident[EI_CLASS] != ELFCLASS64 || ehdr.e_ident[EI_VERSION] != EV_CURRENT || ehdr.e_version != EV_CURRENT || diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index 0026f267da20..088cd4ace4ef 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -20,7 +20,14 @@ extern ssize_t copy_oldmem_page(unsigned long, char *, size_t, #define vmcore_elf_check_arch_cross(x) 0 #endif -#define vmcore_elf_check_arch(x) (elf_check_arch(x) || vmcore_elf_check_arch_cross(x)) +/* + * Architecture code can redefine this if there are any special checks + * needed for 64-bit ELF vmcores. In case of 32-bit only architecture, + * this can be set to zero. + */ +#ifndef vmcore_elf64_check_arch +#define vmcore_elf64_check_arch(x) (elf_check_arch(x) || vmcore_elf_check_arch_cross(x)) +#endif /* * is_kdump_kernel() checks whether this kernel is booting after a panic of -- cgit v1.2.3 From 5091faa449ee0b7d73bc296a93bca9540fc51d0a Mon Sep 17 00:00:00 2001 From: Mike Galbraith Date: Tue, 30 Nov 2010 14:18:03 +0100 Subject: sched: Add 'autogroup' scheduling feature: automated per session task groups A recurring complaint from CFS users is that parallel kbuild has a negative impact on desktop interactivity. This patch implements an idea from Linus, to automatically create task groups. Currently, only per session autogroups are implemented, but the patch leaves the way open for enhancement. Implementation: each task's signal struct contains an inherited pointer to a refcounted autogroup struct containing a task group pointer, the default for all tasks pointing to the init_task_group. When a task calls setsid(), a new task group is created, the process is moved into the new task group, and a reference to the preveious task group is dropped. Child processes inherit this task group thereafter, and increase it's refcount. When the last thread of a process exits, the process's reference is dropped, such that when the last process referencing an autogroup exits, the autogroup is destroyed. At runqueue selection time, IFF a task has no cgroup assignment, its current autogroup is used. Autogroup bandwidth is controllable via setting it's nice level through the proc filesystem: cat /proc//autogroup Displays the task's group and the group's nice level. echo > /proc//autogroup Sets the task group's shares to the weight of nice task. Setting nice level is rate limited for !admin users due to the abuse risk of task group locking. The feature is enabled from boot by default if CONFIG_SCHED_AUTOGROUP=y is selected, but can be disabled via the boot option noautogroup, and can also be turned on/off on the fly via: echo [01] > /proc/sys/kernel/sched_autogroup_enabled ... which will automatically move tasks to/from the root task group. Signed-off-by: Mike Galbraith Acked-by: Linus Torvalds Acked-by: Peter Zijlstra Cc: Markus Trippelsdorf Cc: Mathieu Desnoyers Cc: Paul Turner Cc: Oleg Nesterov [ Removed the task_group_path() debug code, and fixed !EVENTFD build failure. ] Signed-off-by: Ingo Molnar LKML-Reference: <1290281700.28711.9.camel@maggy.simson.net> Signed-off-by: Ingo Molnar --- Documentation/kernel-parameters.txt | 2 + fs/proc/base.c | 79 +++++++++++++ include/linux/sched.h | 23 ++++ init/Kconfig | 13 ++ kernel/fork.c | 5 +- kernel/sched.c | 13 +- kernel/sched_autogroup.c | 229 ++++++++++++++++++++++++++++++++++++ kernel/sched_autogroup.h | 32 +++++ kernel/sched_debug.c | 47 +------- kernel/sys.c | 4 +- kernel/sysctl.c | 11 ++ 11 files changed, 409 insertions(+), 49 deletions(-) create mode 100644 kernel/sched_autogroup.c create mode 100644 kernel/sched_autogroup.h (limited to 'include/linux') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 92e83e53148f..86820a727b0b 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -1622,6 +1622,8 @@ and is between 256 and 4096 characters. It is defined in the file noapic [SMP,APIC] Tells the kernel to not make use of any IOAPICs that may be present in the system. + noautogroup Disable scheduler automatic task group creation. + nobats [PPC] Do not use BATs for mapping kernel lowmem on "Classic" PPC cores. diff --git a/fs/proc/base.c b/fs/proc/base.c index f3d02ca461ec..2fa0ce29b6dc 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1407,6 +1407,82 @@ static const struct file_operations proc_pid_sched_operations = { #endif +#ifdef CONFIG_SCHED_AUTOGROUP +/* + * Print out autogroup related information: + */ +static int sched_autogroup_show(struct seq_file *m, void *v) +{ + struct inode *inode = m->private; + struct task_struct *p; + + p = get_proc_task(inode); + if (!p) + return -ESRCH; + proc_sched_autogroup_show_task(p, m); + + put_task_struct(p); + + return 0; +} + +static ssize_t +sched_autogroup_write(struct file *file, const char __user *buf, + size_t count, loff_t *offset) +{ + struct inode *inode = file->f_path.dentry->d_inode; + struct task_struct *p; + char buffer[PROC_NUMBUF]; + long nice; + int err; + + memset(buffer, 0, sizeof(buffer)); + if (count > sizeof(buffer) - 1) + count = sizeof(buffer) - 1; + if (copy_from_user(buffer, buf, count)) + return -EFAULT; + + err = strict_strtol(strstrip(buffer), 0, &nice); + if (err) + return -EINVAL; + + p = get_proc_task(inode); + if (!p) + return -ESRCH; + + err = nice; + err = proc_sched_autogroup_set_nice(p, &err); + if (err) + count = err; + + put_task_struct(p); + + return count; +} + +static int sched_autogroup_open(struct inode *inode, struct file *filp) +{ + int ret; + + ret = single_open(filp, sched_autogroup_show, NULL); + if (!ret) { + struct seq_file *m = filp->private_data; + + m->private = inode; + } + return ret; +} + +static const struct file_operations proc_pid_sched_autogroup_operations = { + .open = sched_autogroup_open, + .read = seq_read, + .write = sched_autogroup_write, + .llseek = seq_lseek, + .release = single_release, +}; + +#endif /* CONFIG_SCHED_AUTOGROUP */ + static ssize_t comm_write(struct file *file, const char __user *buf, size_t count, loff_t *offset) { @@ -2732,6 +2808,9 @@ static const struct pid_entry tgid_base_stuff[] = { INF("limits", S_IRUGO, proc_pid_limits), #ifdef CONFIG_SCHED_DEBUG REG("sched", S_IRUGO|S_IWUSR, proc_pid_sched_operations), +#endif +#ifdef CONFIG_SCHED_AUTOGROUP + REG("autogroup", S_IRUGO|S_IWUSR, proc_pid_sched_autogroup_operations), #endif REG("comm", S_IRUGO|S_IWUSR, proc_pid_set_comm_operations), #ifdef CONFIG_HAVE_ARCH_TRACEHOOK diff --git a/include/linux/sched.h b/include/linux/sched.h index a5b92c70c737..9c2d46da486e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -509,6 +509,8 @@ struct thread_group_cputimer { spinlock_t lock; }; +struct autogroup; + /* * NOTE! "signal_struct" does not have it's own * locking, because a shared signal_struct always @@ -576,6 +578,9 @@ struct signal_struct { struct tty_struct *tty; /* NULL if no tty */ +#ifdef CONFIG_SCHED_AUTOGROUP + struct autogroup *autogroup; +#endif /* * Cumulative resource counters for dead threads in the group, * and for reaped dead child processes forked by this group. @@ -1927,6 +1932,24 @@ int sched_rt_handler(struct ctl_table *table, int write, extern unsigned int sysctl_sched_compat_yield; +#ifdef CONFIG_SCHED_AUTOGROUP +extern unsigned int sysctl_sched_autogroup_enabled; + +extern void sched_autogroup_create_attach(struct task_struct *p); +extern void sched_autogroup_detach(struct task_struct *p); +extern void sched_autogroup_fork(struct signal_struct *sig); +extern void sched_autogroup_exit(struct signal_struct *sig); +#ifdef CONFIG_PROC_FS +extern void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m); +extern int proc_sched_autogroup_set_nice(struct task_struct *p, int *nice); +#endif +#else +static inline void sched_autogroup_create_attach(struct task_struct *p) { } +static inline void sched_autogroup_detach(struct task_struct *p) { } +static inline void sched_autogroup_fork(struct signal_struct *sig) { } +static inline void sched_autogroup_exit(struct signal_struct *sig) { } +#endif + #ifdef CONFIG_RT_MUTEXES extern int rt_mutex_getprio(struct task_struct *p); extern void rt_mutex_setprio(struct task_struct *p, int prio); diff --git a/init/Kconfig b/init/Kconfig index 88c10468db46..f1bba0a1b051 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -728,6 +728,19 @@ config NET_NS endif # NAMESPACES +config SCHED_AUTOGROUP + bool "Automatic process group scheduling" + select EVENTFD + select CGROUPS + select CGROUP_SCHED + select FAIR_GROUP_SCHED + help + This option optimizes the scheduler for common desktop workloads by + automatically creating and populating task groups. This separation + of workloads isolates aggressive CPU burners (like build jobs) from + desktop applications. Task group autogeneration is currently based + upon task session. + config MM_OWNER bool diff --git a/kernel/fork.c b/kernel/fork.c index 3b159c5991b7..b6f2475f1e83 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -174,8 +174,10 @@ static inline void free_signal_struct(struct signal_struct *sig) static inline void put_signal_struct(struct signal_struct *sig) { - if (atomic_dec_and_test(&sig->sigcnt)) + if (atomic_dec_and_test(&sig->sigcnt)) { + sched_autogroup_exit(sig); free_signal_struct(sig); + } } void __put_task_struct(struct task_struct *tsk) @@ -904,6 +906,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) posix_cpu_timers_init_group(sig); tty_audit_fork(sig); + sched_autogroup_fork(sig); sig->oom_adj = current->signal->oom_adj; sig->oom_score_adj = current->signal->oom_score_adj; diff --git a/kernel/sched.c b/kernel/sched.c index 66ef5790d932..b646dad4a40e 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -79,6 +79,7 @@ #include "sched_cpupri.h" #include "workqueue_sched.h" +#include "sched_autogroup.h" #define CREATE_TRACE_POINTS #include @@ -271,6 +272,10 @@ struct task_group { struct task_group *parent; struct list_head siblings; struct list_head children; + +#ifdef CONFIG_SCHED_AUTOGROUP + struct autogroup *autogroup; +#endif }; #define root_task_group init_task_group @@ -603,11 +608,14 @@ static inline int cpu_of(struct rq *rq) */ static inline struct task_group *task_group(struct task_struct *p) { + struct task_group *tg; struct cgroup_subsys_state *css; css = task_subsys_state_check(p, cpu_cgroup_subsys_id, lockdep_is_held(&task_rq(p)->lock)); - return container_of(css, struct task_group, css); + tg = container_of(css, struct task_group, css); + + return autogroup_task_group(p, tg); } /* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */ @@ -1869,6 +1877,7 @@ static void sched_irq_time_avg_update(struct rq *rq, u64 curr_irq_time) { } #include "sched_idletask.c" #include "sched_fair.c" #include "sched_rt.c" +#include "sched_autogroup.c" #include "sched_stoptask.c" #ifdef CONFIG_SCHED_DEBUG # include "sched_debug.c" @@ -7750,7 +7759,7 @@ void __init sched_init(void) #ifdef CONFIG_CGROUP_SCHED list_add(&init_task_group.list, &task_groups); INIT_LIST_HEAD(&init_task_group.children); - + autogroup_init(&init_task); #endif /* CONFIG_CGROUP_SCHED */ for_each_possible_cpu(i) { diff --git a/kernel/sched_autogroup.c b/kernel/sched_autogroup.c new file mode 100644 index 000000000000..57a7ac286a02 --- /dev/null +++ b/kernel/sched_autogroup.c @@ -0,0 +1,229 @@ +#ifdef CONFIG_SCHED_AUTOGROUP + +#include +#include +#include +#include + +unsigned int __read_mostly sysctl_sched_autogroup_enabled = 1; +static struct autogroup autogroup_default; +static atomic_t autogroup_seq_nr; + +static void autogroup_init(struct task_struct *init_task) +{ + autogroup_default.tg = &init_task_group; + init_task_group.autogroup = &autogroup_default; + kref_init(&autogroup_default.kref); + init_rwsem(&autogroup_default.lock); + init_task->signal->autogroup = &autogroup_default; +} + +static inline void autogroup_free(struct task_group *tg) +{ + kfree(tg->autogroup); +} + +static inline void autogroup_destroy(struct kref *kref) +{ + struct autogroup *ag = container_of(kref, struct autogroup, kref); + + sched_destroy_group(ag->tg); +} + +static inline void autogroup_kref_put(struct autogroup *ag) +{ + kref_put(&ag->kref, autogroup_destroy); +} + +static inline struct autogroup *autogroup_kref_get(struct autogroup *ag) +{ + kref_get(&ag->kref); + return ag; +} + +static inline struct autogroup *autogroup_create(void) +{ + struct autogroup *ag = kzalloc(sizeof(*ag), GFP_KERNEL); + struct task_group *tg; + + if (!ag) + goto out_fail; + + tg = sched_create_group(&init_task_group); + + if (IS_ERR(tg)) + goto out_free; + + kref_init(&ag->kref); + init_rwsem(&ag->lock); + ag->id = atomic_inc_return(&autogroup_seq_nr); + ag->tg = tg; + tg->autogroup = ag; + + return ag; + +out_free: + kfree(ag); +out_fail: + if (printk_ratelimit()) { + printk(KERN_WARNING "autogroup_create: %s failure.\n", + ag ? "sched_create_group()" : "kmalloc()"); + } + + return autogroup_kref_get(&autogroup_default); +} + +static inline bool +task_wants_autogroup(struct task_struct *p, struct task_group *tg) +{ + if (tg != &root_task_group) + return false; + + if (p->sched_class != &fair_sched_class) + return false; + + /* + * We can only assume the task group can't go away on us if + * autogroup_move_group() can see us on ->thread_group list. + */ + if (p->flags & PF_EXITING) + return false; + + return true; +} + +static inline struct task_group * +autogroup_task_group(struct task_struct *p, struct task_group *tg) +{ + int enabled = ACCESS_ONCE(sysctl_sched_autogroup_enabled); + + if (enabled && task_wants_autogroup(p, tg)) + return p->signal->autogroup->tg; + + return tg; +} + +static void +autogroup_move_group(struct task_struct *p, struct autogroup *ag) +{ + struct autogroup *prev; + struct task_struct *t; + unsigned long flags; + + BUG_ON(!lock_task_sighand(p, &flags)); + + prev = p->signal->autogroup; + if (prev == ag) { + unlock_task_sighand(p, &flags); + return; + } + + p->signal->autogroup = autogroup_kref_get(ag); + + t = p; + do { + sched_move_task(t); + } while_each_thread(p, t); + + unlock_task_sighand(p, &flags); + autogroup_kref_put(prev); +} + +/* Allocates GFP_KERNEL, cannot be called under any spinlock */ +void sched_autogroup_create_attach(struct task_struct *p) +{ + struct autogroup *ag = autogroup_create(); + + autogroup_move_group(p, ag); + /* drop extra refrence added by autogroup_create() */ + autogroup_kref_put(ag); +} +EXPORT_SYMBOL(sched_autogroup_create_attach); + +/* Cannot be called under siglock. Currently has no users */ +void sched_autogroup_detach(struct task_struct *p) +{ + autogroup_move_group(p, &autogroup_default); +} +EXPORT_SYMBOL(sched_autogroup_detach); + +void sched_autogroup_fork(struct signal_struct *sig) +{ + struct task_struct *p = current; + + spin_lock_irq(&p->sighand->siglock); + sig->autogroup = autogroup_kref_get(p->signal->autogroup); + spin_unlock_irq(&p->sighand->siglock); +} + +void sched_autogroup_exit(struct signal_struct *sig) +{ + autogroup_kref_put(sig->autogroup); +} + +static int __init setup_autogroup(char *str) +{ + sysctl_sched_autogroup_enabled = 0; + + return 1; +} + +__setup("noautogroup", setup_autogroup); + +#ifdef CONFIG_PROC_FS + +/* Called with siglock held. */ +int proc_sched_autogroup_set_nice(struct task_struct *p, int *nice) +{ + static unsigned long next = INITIAL_JIFFIES; + struct autogroup *ag; + int err; + + if (*nice < -20 || *nice > 19) + return -EINVAL; + + err = security_task_setnice(current, *nice); + if (err) + return err; + + if (*nice < 0 && !can_nice(current, *nice)) + return -EPERM; + + /* this is a heavy operation taking global locks.. */ + if (!capable(CAP_SYS_ADMIN) && time_before(jiffies, next)) + return -EAGAIN; + + next = HZ / 10 + jiffies; + ag = autogroup_kref_get(p->signal->autogroup); + + down_write(&ag->lock); + err = sched_group_set_shares(ag->tg, prio_to_weight[*nice + 20]); + if (!err) + ag->nice = *nice; + up_write(&ag->lock); + + autogroup_kref_put(ag); + + return err; +} + +void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m) +{ + struct autogroup *ag = autogroup_kref_get(p->signal->autogroup); + + down_read(&ag->lock); + seq_printf(m, "/autogroup-%ld nice %d\n", ag->id, ag->nice); + up_read(&ag->lock); + + autogroup_kref_put(ag); +} +#endif /* CONFIG_PROC_FS */ + +#ifdef CONFIG_SCHED_DEBUG +static inline int autogroup_path(struct task_group *tg, char *buf, int buflen) +{ + return snprintf(buf, buflen, "%s-%ld", "/autogroup", tg->autogroup->id); +} +#endif /* CONFIG_SCHED_DEBUG */ + +#endif /* CONFIG_SCHED_AUTOGROUP */ diff --git a/kernel/sched_autogroup.h b/kernel/sched_autogroup.h new file mode 100644 index 000000000000..5358e241cb20 --- /dev/null +++ b/kernel/sched_autogroup.h @@ -0,0 +1,32 @@ +#ifdef CONFIG_SCHED_AUTOGROUP + +struct autogroup { + struct kref kref; + struct task_group *tg; + struct rw_semaphore lock; + unsigned long id; + int nice; +}; + +static inline struct task_group * +autogroup_task_group(struct task_struct *p, struct task_group *tg); + +#else /* !CONFIG_SCHED_AUTOGROUP */ + +static inline void autogroup_init(struct task_struct *init_task) { } +static inline void autogroup_free(struct task_group *tg) { } + +static inline struct task_group * +autogroup_task_group(struct task_struct *p, struct task_group *tg) +{ + return tg; +} + +#ifdef CONFIG_SCHED_DEBUG +static inline int autogroup_path(struct task_group *tg, char *buf, int buflen) +{ + return 0; +} +#endif + +#endif /* CONFIG_SCHED_AUTOGROUP */ diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c index e95b77414a99..1dfae3d014b5 100644 --- a/kernel/sched_debug.c +++ b/kernel/sched_debug.c @@ -54,8 +54,7 @@ static unsigned long nsec_low(unsigned long long nsec) #define SPLIT_NS(x) nsec_high(x), nsec_low(x) #ifdef CONFIG_FAIR_GROUP_SCHED -static void print_cfs_group_stats(struct seq_file *m, int cpu, - struct task_group *tg) +static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group *tg) { struct sched_entity *se = tg->se[cpu]; if (!se) @@ -110,16 +109,6 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p) 0LL, 0LL, 0LL, 0L, 0LL, 0L, 0LL, 0L); #endif -#ifdef CONFIG_CGROUP_SCHED - { - char path[64]; - - rcu_read_lock(); - cgroup_path(task_group(p)->css.cgroup, path, sizeof(path)); - rcu_read_unlock(); - SEQ_printf(m, " %s", path); - } -#endif SEQ_printf(m, "\n"); } @@ -147,19 +136,6 @@ static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu) read_unlock_irqrestore(&tasklist_lock, flags); } -#if defined(CONFIG_CGROUP_SCHED) && \ - (defined(CONFIG_FAIR_GROUP_SCHED) || defined(CONFIG_RT_GROUP_SCHED)) -static void task_group_path(struct task_group *tg, char *buf, int buflen) -{ - /* may be NULL if the underlying cgroup isn't fully-created yet */ - if (!tg->css.cgroup) { - buf[0] = '\0'; - return; - } - cgroup_path(tg->css.cgroup, buf, buflen); -} -#endif - void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) { s64 MIN_vruntime = -1, min_vruntime, max_vruntime = -1, @@ -168,16 +144,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) struct sched_entity *last; unsigned long flags; -#if defined(CONFIG_CGROUP_SCHED) && defined(CONFIG_FAIR_GROUP_SCHED) - char path[128]; - struct task_group *tg = cfs_rq->tg; - - task_group_path(tg, path, sizeof(path)); - - SEQ_printf(m, "\ncfs_rq[%d]:%s\n", cpu, path); -#else SEQ_printf(m, "\ncfs_rq[%d]:\n", cpu); -#endif SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "exec_clock", SPLIT_NS(cfs_rq->exec_clock)); @@ -215,7 +182,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) SEQ_printf(m, " .%-30s: %ld\n", "load_contrib", cfs_rq->load_contribution); SEQ_printf(m, " .%-30s: %d\n", "load_tg", - atomic_read(&tg->load_weight)); + atomic_read(&cfs_rq->tg->load_weight)); #endif print_cfs_group_stats(m, cpu, cfs_rq->tg); @@ -224,17 +191,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq) { -#if defined(CONFIG_CGROUP_SCHED) && defined(CONFIG_RT_GROUP_SCHED) - char path[128]; - struct task_group *tg = rt_rq->tg; - - task_group_path(tg, path, sizeof(path)); - - SEQ_printf(m, "\nrt_rq[%d]:%s\n", cpu, path); -#else SEQ_printf(m, "\nrt_rq[%d]:\n", cpu); -#endif - #define P(x) \ SEQ_printf(m, " .%-30s: %Ld\n", #x, (long long)(rt_rq->x)) diff --git a/kernel/sys.c b/kernel/sys.c index 7f5a0cd296a9..2745dcdb6c6c 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1080,8 +1080,10 @@ SYSCALL_DEFINE0(setsid) err = session; out: write_unlock_irq(&tasklist_lock); - if (err > 0) + if (err > 0) { proc_sid_connector(group_leader); + sched_autogroup_create_attach(group_leader); + } return err; } diff --git a/kernel/sysctl.c b/kernel/sysctl.c index a00fdefd24ce..121e4fff03d1 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -370,6 +370,17 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, +#ifdef CONFIG_SCHED_AUTOGROUP + { + .procname = "sched_autogroup_enabled", + .data = &sysctl_sched_autogroup_enabled, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + .extra1 = &zero, + .extra2 = &one, + }, +#endif #ifdef CONFIG_PROVE_LOCKING { .procname = "prove_locking", -- cgit v1.2.3 From c320c7b7d380e630f595de1236d9d085b035d5b4 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 20 Oct 2010 12:50:11 -0200 Subject: perf events: Precalculate the header space for PERF_SAMPLE_ fields MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit PERF_SAMPLE_{CALLCHAIN,RAW} have variable lenghts per sample, but the others can be precalculated, reducing a bit the per sample cost. Acked-by: Peter Zijlstra Cc: Frédéric Weisbecker Cc: Ian Munsie Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Paul Mackerras Cc: Stephane Eranian LKML-Reference: Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/perf_event.h | 2 + kernel/perf_event.c | 150 +++++++++++++++++++++++++++------------------ 2 files changed, 93 insertions(+), 59 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index cbf04cc1e630..adf6d9931643 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -758,6 +758,8 @@ struct perf_event { u64 shadow_ctx_time; struct perf_event_attr attr; + u16 header_size; + u16 read_size; struct hw_perf_event hw; struct perf_event_context *ctx; diff --git a/kernel/perf_event.c b/kernel/perf_event.c index af1e63f249f3..aede71245e9f 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -312,9 +312,75 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx) ctx->nr_stat++; } +/* + * Called at perf_event creation and when events are attached/detached from a + * group. + */ +static void perf_event__read_size(struct perf_event *event) +{ + int entry = sizeof(u64); /* value */ + int size = 0; + int nr = 1; + + if (event->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + size += sizeof(u64); + + if (event->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + size += sizeof(u64); + + if (event->attr.read_format & PERF_FORMAT_ID) + entry += sizeof(u64); + + if (event->attr.read_format & PERF_FORMAT_GROUP) { + nr += event->group_leader->nr_siblings; + size += sizeof(u64); + } + + size += entry * nr; + event->read_size = size; +} + +static void perf_event__header_size(struct perf_event *event) +{ + struct perf_sample_data *data; + u64 sample_type = event->attr.sample_type; + u16 size = 0; + + perf_event__read_size(event); + + if (sample_type & PERF_SAMPLE_IP) + size += sizeof(data->ip); + + if (sample_type & PERF_SAMPLE_TID) + size += sizeof(data->tid_entry); + + if (sample_type & PERF_SAMPLE_TIME) + size += sizeof(data->time); + + if (sample_type & PERF_SAMPLE_ADDR) + size += sizeof(data->addr); + + if (sample_type & PERF_SAMPLE_ID) + size += sizeof(data->id); + + if (sample_type & PERF_SAMPLE_STREAM_ID) + size += sizeof(data->stream_id); + + if (sample_type & PERF_SAMPLE_CPU) + size += sizeof(data->cpu_entry); + + if (sample_type & PERF_SAMPLE_PERIOD) + size += sizeof(data->period); + + if (sample_type & PERF_SAMPLE_READ) + size += event->read_size; + + event->header_size = size; +} + static void perf_group_attach(struct perf_event *event) { - struct perf_event *group_leader = event->group_leader; + struct perf_event *group_leader = event->group_leader, *pos; /* * We can have double attach due to group movement in perf_event_open. @@ -333,6 +399,11 @@ static void perf_group_attach(struct perf_event *event) list_add_tail(&event->group_entry, &group_leader->sibling_list); group_leader->nr_siblings++; + + perf_event__header_size(group_leader); + + list_for_each_entry(pos, &group_leader->sibling_list, group_entry) + perf_event__header_size(pos); } /* @@ -391,7 +462,7 @@ static void perf_group_detach(struct perf_event *event) if (event->group_leader != event) { list_del_init(&event->group_entry); event->group_leader->nr_siblings--; - return; + goto out; } if (!list_empty(&event->group_entry)) @@ -410,6 +481,12 @@ static void perf_group_detach(struct perf_event *event) /* Inherit group flags from the previous leader */ sibling->group_flags = event->group_flags; } + +out: + perf_event__header_size(event->group_leader); + + list_for_each_entry(tmp, &event->group_leader->sibling_list, group_entry) + perf_event__header_size(tmp); } static inline int @@ -2289,31 +2366,6 @@ static int perf_release(struct inode *inode, struct file *file) return perf_event_release_kernel(event); } -static int perf_event_read_size(struct perf_event *event) -{ - int entry = sizeof(u64); /* value */ - int size = 0; - int nr = 1; - - if (event->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) - size += sizeof(u64); - - if (event->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) - size += sizeof(u64); - - if (event->attr.read_format & PERF_FORMAT_ID) - entry += sizeof(u64); - - if (event->attr.read_format & PERF_FORMAT_GROUP) { - nr += event->group_leader->nr_siblings; - size += sizeof(u64); - } - - size += entry * nr; - - return size; -} - u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running) { struct perf_event *child; @@ -2428,7 +2480,7 @@ perf_read_hw(struct perf_event *event, char __user *buf, size_t count) if (event->state == PERF_EVENT_STATE_ERROR) return 0; - if (count < perf_event_read_size(event)) + if (count < event->read_size) return -ENOSPC; WARN_ON_ONCE(event->ctx->parent_ctx); @@ -3606,59 +3658,34 @@ void perf_prepare_sample(struct perf_event_header *header, data->type = sample_type; header->type = PERF_RECORD_SAMPLE; - header->size = sizeof(*header); + header->size = sizeof(*header) + event->header_size; header->misc = 0; header->misc |= perf_misc_flags(regs); - if (sample_type & PERF_SAMPLE_IP) { + if (sample_type & PERF_SAMPLE_IP) data->ip = perf_instruction_pointer(regs); - header->size += sizeof(data->ip); - } - if (sample_type & PERF_SAMPLE_TID) { /* namespace issues */ data->tid_entry.pid = perf_event_pid(event, current); data->tid_entry.tid = perf_event_tid(event, current); - - header->size += sizeof(data->tid_entry); } - if (sample_type & PERF_SAMPLE_TIME) { + if (sample_type & PERF_SAMPLE_TIME) data->time = perf_clock(); - header->size += sizeof(data->time); - } - - if (sample_type & PERF_SAMPLE_ADDR) - header->size += sizeof(data->addr); - - if (sample_type & PERF_SAMPLE_ID) { + if (sample_type & PERF_SAMPLE_ID) data->id = primary_event_id(event); - header->size += sizeof(data->id); - } - - if (sample_type & PERF_SAMPLE_STREAM_ID) { + if (sample_type & PERF_SAMPLE_STREAM_ID) data->stream_id = event->id; - header->size += sizeof(data->stream_id); - } - if (sample_type & PERF_SAMPLE_CPU) { data->cpu_entry.cpu = raw_smp_processor_id(); data->cpu_entry.reserved = 0; - - header->size += sizeof(data->cpu_entry); } - if (sample_type & PERF_SAMPLE_PERIOD) - header->size += sizeof(data->period); - - if (sample_type & PERF_SAMPLE_READ) - header->size += perf_event_read_size(event); - if (sample_type & PERF_SAMPLE_CALLCHAIN) { int size = 1; @@ -3726,7 +3753,7 @@ perf_event_read_event(struct perf_event *event, .header = { .type = PERF_RECORD_READ, .misc = 0, - .size = sizeof(read_event) + perf_event_read_size(event), + .size = sizeof(read_event) + event->read_size, }, .pid = perf_event_pid(event, task), .tid = perf_event_tid(event, task), @@ -5714,6 +5741,11 @@ SYSCALL_DEFINE5(perf_event_open, list_add_tail(&event->owner_entry, ¤t->perf_event_list); mutex_unlock(¤t->perf_event_mutex); + /* + * Precalculate sample_data sizes + */ + perf_event__header_size(event); + /* * Drop the reference on the group_event after placing the * new event on the sibling_list. This ensures destruction -- cgit v1.2.3 From f2cd2d3e9b3ef960612e362f0ad129d735452df2 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 29 Nov 2010 08:14:37 +0000 Subject: net sched: use xps information for qdisc NUMA affinity Allocate qdisc memory according to NUMA properties of cpus included in xps map. To be effective, qdisc should be (re)setup after changes of /sys/class/net/eth/queues/tx-/xps_cpus I added a numa_node field in struct netdev_queue, containing NUMA node if all cpus included in xps_cpus share same node, else -1. Signed-off-by: Eric Dumazet Cc: Ben Hutchings Cc: Tom Herbert Signed-off-by: David S. Miller --- include/linux/netdevice.h | 20 +++++++++++++++++++- net/core/dev.c | 5 +++-- net/core/net-sysfs.c | 12 +++++++++++- net/sched/sch_generic.c | 4 +++- 4 files changed, 36 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 4b0c7f3aa32b..a9ac5dc26e3c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -508,7 +508,9 @@ struct netdev_queue { #ifdef CONFIG_RPS struct kobject kobj; #endif - +#if defined(CONFIG_XPS) && defined(CONFIG_NUMA) + int numa_node; +#endif /* * write mostly part */ @@ -523,6 +525,22 @@ struct netdev_queue { u64 tx_dropped; } ____cacheline_aligned_in_smp; +static inline int netdev_queue_numa_node_read(const struct netdev_queue *q) +{ +#if defined(CONFIG_XPS) && defined(CONFIG_NUMA) + return q->numa_node; +#else + return -1; +#endif +} + +static inline void netdev_queue_numa_node_write(struct netdev_queue *q, int node) +{ +#if defined(CONFIG_XPS) && defined(CONFIG_NUMA) + q->numa_node = node; +#endif +} + #ifdef CONFIG_RPS /* * This structure holds an RPS map which can be of variable length. The diff --git a/net/core/dev.c b/net/core/dev.c index 3259d2c323a6..cd2437495428 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5125,9 +5125,10 @@ static int netif_alloc_netdev_queues(struct net_device *dev) } dev->_tx = tx; - for (i = 0; i < count; i++) + for (i = 0; i < count; i++) { + netdev_queue_numa_node_write(&tx[i], -1); tx[i].dev = dev; - + } return 0; } diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index f85cee3d869e..85e8b5326dd6 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -913,6 +913,7 @@ static ssize_t store_xps_map(struct netdev_queue *queue, struct xps_map *map, *new_map; struct xps_dev_maps *dev_maps, *new_dev_maps; int nonempty = 0; + int numa_node = -2; if (!capable(CAP_NET_ADMIN)) return -EPERM; @@ -953,7 +954,14 @@ static ssize_t store_xps_map(struct netdev_queue *queue, pos = map_len = alloc_len = 0; need_set = cpu_isset(cpu, *mask) && cpu_online(cpu); - +#ifdef CONFIG_NUMA + if (need_set) { + if (numa_node == -2) + numa_node = cpu_to_node(cpu); + else if (numa_node != cpu_to_node(cpu)) + numa_node = -1; + } +#endif if (need_set && pos >= map_len) { /* Need to add queue to this CPU's map */ if (map_len >= alloc_len) { @@ -1001,6 +1009,8 @@ static ssize_t store_xps_map(struct netdev_queue *queue, if (dev_maps) call_rcu(&dev_maps->rcu, xps_dev_maps_release); + netdev_queue_numa_node_write(queue, (numa_node >= 0) ? numa_node : -1); + mutex_unlock(&xps_map_mutex); free_cpumask_var(mask); diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 7f0bd8952646..0918834ee4a1 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -553,7 +553,9 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, size = QDISC_ALIGN(sizeof(*sch)); size += ops->priv_size + (QDISC_ALIGNTO - 1); - p = kzalloc(size, GFP_KERNEL); + p = kzalloc_node(size, GFP_KERNEL, + netdev_queue_numa_node_read(dev_queue)); + if (!p) goto errout; sch = (struct Qdisc *) QDISC_ALIGN((unsigned long) p); -- cgit v1.2.3 From 172c69a47675dc1ca9c7243c031d8d77701bccc0 Mon Sep 17 00:00:00 2001 From: Rafał Miłecki Date: Sun, 28 Nov 2010 10:39:35 +0100 Subject: ssb: extract indexes for power tables MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Rafał Miłecki Acked-by: Michael Buesch Signed-off-by: John W. Linville --- drivers/ssb/pci.c | 44 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/ssb/ssb.h | 4 ++++ include/linux/ssb/ssb_regs.h | 40 ++++++++++++++++++++++++++++++++++++++++ 3 files changed, 88 insertions(+) (limited to 'include/linux') diff --git a/drivers/ssb/pci.c b/drivers/ssb/pci.c index f52966305e05..158449e55044 100644 --- a/drivers/ssb/pci.c +++ b/drivers/ssb/pci.c @@ -406,6 +406,46 @@ static void sprom_extract_r123(struct ssb_sprom *out, const u16 *in) out->antenna_gain.ghz5.a3 = gain; } +/* Revs 4 5 and 8 have partially shared layout */ +static void sprom_extract_r458(struct ssb_sprom *out, const u16 *in) +{ + SPEX(txpid2g[0], SSB_SPROM4_TXPID2G01, + SSB_SPROM4_TXPID2G0, SSB_SPROM4_TXPID2G0_SHIFT); + SPEX(txpid2g[1], SSB_SPROM4_TXPID2G01, + SSB_SPROM4_TXPID2G1, SSB_SPROM4_TXPID2G1_SHIFT); + SPEX(txpid2g[2], SSB_SPROM4_TXPID2G23, + SSB_SPROM4_TXPID2G2, SSB_SPROM4_TXPID2G2_SHIFT); + SPEX(txpid2g[3], SSB_SPROM4_TXPID2G23, + SSB_SPROM4_TXPID2G3, SSB_SPROM4_TXPID2G3_SHIFT); + + SPEX(txpid5gl[0], SSB_SPROM4_TXPID5GL01, + SSB_SPROM4_TXPID5GL0, SSB_SPROM4_TXPID5GL0_SHIFT); + SPEX(txpid5gl[1], SSB_SPROM4_TXPID5GL01, + SSB_SPROM4_TXPID5GL1, SSB_SPROM4_TXPID5GL1_SHIFT); + SPEX(txpid5gl[2], SSB_SPROM4_TXPID5GL23, + SSB_SPROM4_TXPID5GL2, SSB_SPROM4_TXPID5GL2_SHIFT); + SPEX(txpid5gl[3], SSB_SPROM4_TXPID5GL23, + SSB_SPROM4_TXPID5GL3, SSB_SPROM4_TXPID5GL3_SHIFT); + + SPEX(txpid5g[0], SSB_SPROM4_TXPID5G01, + SSB_SPROM4_TXPID5G0, SSB_SPROM4_TXPID5G0_SHIFT); + SPEX(txpid5g[1], SSB_SPROM4_TXPID5G01, + SSB_SPROM4_TXPID5G1, SSB_SPROM4_TXPID5G1_SHIFT); + SPEX(txpid5g[2], SSB_SPROM4_TXPID5G23, + SSB_SPROM4_TXPID5G2, SSB_SPROM4_TXPID5G2_SHIFT); + SPEX(txpid5g[3], SSB_SPROM4_TXPID5G23, + SSB_SPROM4_TXPID5G3, SSB_SPROM4_TXPID5G3_SHIFT); + + SPEX(txpid5gh[0], SSB_SPROM4_TXPID5GH01, + SSB_SPROM4_TXPID5GH0, SSB_SPROM4_TXPID5GH0_SHIFT); + SPEX(txpid5gh[1], SSB_SPROM4_TXPID5GH01, + SSB_SPROM4_TXPID5GH1, SSB_SPROM4_TXPID5GH1_SHIFT); + SPEX(txpid5gh[2], SSB_SPROM4_TXPID5GH23, + SSB_SPROM4_TXPID5GH2, SSB_SPROM4_TXPID5GH2_SHIFT); + SPEX(txpid5gh[3], SSB_SPROM4_TXPID5GH23, + SSB_SPROM4_TXPID5GH3, SSB_SPROM4_TXPID5GH3_SHIFT); +} + static void sprom_extract_r45(struct ssb_sprom *out, const u16 *in) { int i; @@ -471,6 +511,8 @@ static void sprom_extract_r45(struct ssb_sprom *out, const u16 *in) memcpy(&out->antenna_gain.ghz5, &out->antenna_gain.ghz24, sizeof(out->antenna_gain.ghz5)); + sprom_extract_r458(out, in); + /* TODO - get remaining rev 4 stuff needed */ } @@ -561,6 +603,8 @@ static void sprom_extract_r8(struct ssb_sprom *out, const u16 *in) memcpy(&out->antenna_gain.ghz5, &out->antenna_gain.ghz24, sizeof(out->antenna_gain.ghz5)); + sprom_extract_r458(out, in); + /* TODO - get remaining rev 8 stuff needed */ } diff --git a/include/linux/ssb/ssb.h b/include/linux/ssb/ssb.h index 623b704fdc42..9659eff52ca2 100644 --- a/include/linux/ssb/ssb.h +++ b/include/linux/ssb/ssb.h @@ -55,6 +55,10 @@ struct ssb_sprom { u8 tri5gl; /* 5.2GHz TX isolation */ u8 tri5g; /* 5.3GHz TX isolation */ u8 tri5gh; /* 5.8GHz TX isolation */ + u8 txpid2g[4]; /* 2GHz TX power index */ + u8 txpid5gl[4]; /* 4.9 - 5.1GHz TX power index */ + u8 txpid5g[4]; /* 5.1 - 5.5GHz TX power index */ + u8 txpid5gh[4]; /* 5.5 - ...GHz TX power index */ u8 rxpo2g; /* 2GHz RX power offset */ u8 rxpo5g; /* 5GHz RX power offset */ u8 rssisav2g; /* 2GHz RSSI params */ diff --git a/include/linux/ssb/ssb_regs.h b/include/linux/ssb/ssb_regs.h index 11daf9c140e7..489f7b6d61c5 100644 --- a/include/linux/ssb/ssb_regs.h +++ b/include/linux/ssb/ssb_regs.h @@ -299,6 +299,46 @@ #define SSB_SPROM4_AGAIN2_SHIFT 0 #define SSB_SPROM4_AGAIN3 0xFF00 /* Antenna 3 */ #define SSB_SPROM4_AGAIN3_SHIFT 8 +#define SSB_SPROM4_TXPID2G01 0x0062 /* TX Power Index 2GHz */ +#define SSB_SPROM4_TXPID2G0 0x00FF +#define SSB_SPROM4_TXPID2G0_SHIFT 0 +#define SSB_SPROM4_TXPID2G1 0xFF00 +#define SSB_SPROM4_TXPID2G1_SHIFT 8 +#define SSB_SPROM4_TXPID2G23 0x0064 /* TX Power Index 2GHz */ +#define SSB_SPROM4_TXPID2G2 0x00FF +#define SSB_SPROM4_TXPID2G2_SHIFT 0 +#define SSB_SPROM4_TXPID2G3 0xFF00 +#define SSB_SPROM4_TXPID2G3_SHIFT 8 +#define SSB_SPROM4_TXPID5G01 0x0066 /* TX Power Index 5GHz middle subband */ +#define SSB_SPROM4_TXPID5G0 0x00FF +#define SSB_SPROM4_TXPID5G0_SHIFT 0 +#define SSB_SPROM4_TXPID5G1 0xFF00 +#define SSB_SPROM4_TXPID5G1_SHIFT 8 +#define SSB_SPROM4_TXPID5G23 0x0068 /* TX Power Index 5GHz middle subband */ +#define SSB_SPROM4_TXPID5G2 0x00FF +#define SSB_SPROM4_TXPID5G2_SHIFT 0 +#define SSB_SPROM4_TXPID5G3 0xFF00 +#define SSB_SPROM4_TXPID5G3_SHIFT 8 +#define SSB_SPROM4_TXPID5GL01 0x006A /* TX Power Index 5GHz low subband */ +#define SSB_SPROM4_TXPID5GL0 0x00FF +#define SSB_SPROM4_TXPID5GL0_SHIFT 0 +#define SSB_SPROM4_TXPID5GL1 0xFF00 +#define SSB_SPROM4_TXPID5GL1_SHIFT 8 +#define SSB_SPROM4_TXPID5GL23 0x006C /* TX Power Index 5GHz low subband */ +#define SSB_SPROM4_TXPID5GL2 0x00FF +#define SSB_SPROM4_TXPID5GL2_SHIFT 0 +#define SSB_SPROM4_TXPID5GL3 0xFF00 +#define SSB_SPROM4_TXPID5GL3_SHIFT 8 +#define SSB_SPROM4_TXPID5GH01 0x006E /* TX Power Index 5GHz high subband */ +#define SSB_SPROM4_TXPID5GH0 0x00FF +#define SSB_SPROM4_TXPID5GH0_SHIFT 0 +#define SSB_SPROM4_TXPID5GH1 0xFF00 +#define SSB_SPROM4_TXPID5GH1_SHIFT 8 +#define SSB_SPROM4_TXPID5GH23 0x0070 /* TX Power Index 5GHz high subband */ +#define SSB_SPROM4_TXPID5GH2 0x00FF +#define SSB_SPROM4_TXPID5GH2_SHIFT 0 +#define SSB_SPROM4_TXPID5GH3 0xFF00 +#define SSB_SPROM4_TXPID5GH3_SHIFT 8 #define SSB_SPROM4_MAXP_BG 0x0080 /* Max Power BG in path 1 */ #define SSB_SPROM4_MAXP_BG_MASK 0x00FF /* Mask for Max Power BG */ #define SSB_SPROM4_ITSSI_BG 0xFF00 /* Mask for path 1 itssi_bg */ -- cgit v1.2.3 From 87de5ac782761a3ebf806e434e8c9cc205a87274 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Mon, 20 Sep 2010 17:42:46 -0700 Subject: timers: Introduce timerlist infrastructure. The timerlist infrastructure is a thin layer over the rbtree code that implements a simple list of timers sorted by an expires value, and a getnext function that provides a pointer to the earliest timer. This infrastructure allows drivers and other kernel infrastructure to easily implement timers without duplicating code. Signed-off-by: John Stultz LKML Reference: <1290136329-18291-2-git-send-email-john.stultz@linaro.org> Reviewed-by: Thomas Gleixner CC: Alessandro Zummo CC: Thomas Gleixner CC: Richard Cochran --- include/linux/timerlist.h | 37 +++++++++++++++ lib/Makefile | 2 +- lib/timerlist.c | 118 ++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 156 insertions(+), 1 deletion(-) create mode 100644 include/linux/timerlist.h create mode 100644 lib/timerlist.c (limited to 'include/linux') diff --git a/include/linux/timerlist.h b/include/linux/timerlist.h new file mode 100644 index 000000000000..c46b28ae6e4d --- /dev/null +++ b/include/linux/timerlist.h @@ -0,0 +1,37 @@ +#ifndef _LINUX_TIMERLIST_H +#define _LINUX_TIMERLIST_H + +#include +#include + + +struct timerlist_node { + struct rb_node node; + ktime_t expires; +}; + +struct timerlist_head { + struct rb_root head; + struct timerlist_node *next; +}; + + +extern void timerlist_add(struct timerlist_head *head, + struct timerlist_node *node); +extern void timerlist_del(struct timerlist_head *head, + struct timerlist_node *node); +extern struct timerlist_node *timerlist_getnext(struct timerlist_head *head); +extern struct timerlist_node *timerlist_iterate_next( + struct timerlist_node *node); + +static inline void timerlist_init(struct timerlist_node *node) +{ + RB_CLEAR_NODE(&node->node); +} + +static inline void timerlist_init_head(struct timerlist_head *head) +{ + head->head = RB_ROOT; + head->next = NULL; +} +#endif /* _LINUX_TIMERLIST_H */ diff --git a/lib/Makefile b/lib/Makefile index e6a3763b8212..8b475cfb8195 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -8,7 +8,7 @@ KBUILD_CFLAGS = $(subst -pg,,$(ORIG_CFLAGS)) endif lib-y := ctype.o string.o vsprintf.o cmdline.o \ - rbtree.o radix-tree.o dump_stack.o \ + rbtree.o radix-tree.o dump_stack.o timerlist.o\ idr.o int_sqrt.o extable.o prio_tree.o \ sha1.o irq_regs.o reciprocal_div.o argv_split.o \ proportions.o prio_heap.o ratelimit.o show_mem.o \ diff --git a/lib/timerlist.c b/lib/timerlist.c new file mode 100644 index 000000000000..9101b42fd13d --- /dev/null +++ b/lib/timerlist.c @@ -0,0 +1,118 @@ +/* + * Generic Timer-list + * + * Manages a simple list of timers, ordered by expiration time. + * Uses rbtrees for quick list adds and expiration. + * + * NOTE: All of the following functions need to be serialized + * to avoid races. No locking is done by this libary code. + * + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#include +#include + +/** + * timerlist_add - Adds timer to timerlist. + * + * @head: head of timerlist + * @node: timer node to be added + * + * Adds the timer node to the timerlist, sorted by the + * node's expires value. + */ +void timerlist_add(struct timerlist_head *head, struct timerlist_node *node) +{ + struct rb_node **p = &head->head.rb_node; + struct rb_node *parent = NULL; + struct timerlist_node *ptr; + + /* Make sure we don't add nodes that are already added */ + WARN_ON_ONCE(!RB_EMPTY_NODE(&node->node)); + + while (*p) { + parent = *p; + ptr = rb_entry(parent, struct timerlist_node, node); + if (node->expires.tv64 < ptr->expires.tv64) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + rb_link_node(&node->node, parent, p); + rb_insert_color(&node->node, &head->head); + + if (!head->next || node->expires.tv64 < head->next->expires.tv64) + head->next = node; +} + +/** + * timerlist_del - Removes a timer from the timerlist. + * + * @head: head of timerlist + * @node: timer node to be removed + * + * Removes the timer node from the timerlist. + */ +void timerlist_del(struct timerlist_head *head, struct timerlist_node *node) +{ + WARN_ON_ONCE(RB_EMPTY_NODE(&node->node)); + + /* update next pointer */ + if (head->next == node) { + struct rb_node *rbn = rb_next(&node->node); + + head->next = rbn ? + rb_entry(rbn, struct timerlist_node, node) : NULL; + } + rb_erase(&node->node, &head->head); + RB_CLEAR_NODE(&node->node); +} + + +/** + * timerlist_getnext - Returns the timer with the earlies expiration time + * + * @head: head of timerlist + * + * Returns a pointer to the timer node that has the + * earliest expiration time. + */ +struct timerlist_node *timerlist_getnext(struct timerlist_head *head) +{ + return head->next; +} + + +/** + * timerlist_iterate_next - Returns the timer after the provided timer + * + * @node: Pointer to a timer. + * + * Provides the timer that is after the given node. This is used, when + * necessary, to iterate through the list of timers in a timer list + * without modifying the list. + */ +struct timerlist_node *timerlist_iterate_next(struct timerlist_node *node) +{ + struct rb_node *next; + + if (!node) + return NULL; + next = rb_next(&node->node); + if (!next) + return NULL; + return container_of(next, struct timerlist_node, node); +} -- cgit v1.2.3 From 287050d390264402e11bea8b811859e42e8faa29 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 2 Dec 2010 16:46:18 -0500 Subject: tracing: Add TRACE_EVENT_CONDITIONAL() There are instances in the kernel that we only want to trace a tracepoint when a certain condition is set. But we do not want to test for that condition in the core kernel. If we test for that condition before calling the tracepoin, then we will be performing that test even when tracing is not enabled. This is 99.99% of the time. We currently can just filter out on that condition, but that happens after we write to the trace buffer. We just wasted time writing to the ring buffer for an event we never cared about. This patch adds: TRACE_EVENT_CONDITION() and DEFINE_EVENT_CONDITION() These have a new TP_CONDITION() argument that comes right after the TP_ARGS(). This condition can use the parameters of TP_ARGS() in the TRACE_EVENT() to determine if the tracepoint should be traced or not. The TP_CONDITION() will be placed in a if (cond) trace; For example, for the tracepoint sched_wakeup, it is useless to trace a wakeup event where the caller never actually wakes anything up (where success == 0). So adding: TP_CONDITION(success), which uses the "success" parameter of the wakeup tracepoint will have it only trace when we have successfully woken up a task. Acked-by: Mathieu Desnoyers Acked-by: Frederic Weisbecker Cc: Arjan van de Ven Cc: Thomas Gleixner Signed-off-by: Steven Rostedt --- include/linux/tracepoint.h | 29 +++++++++++++++++++++++------ include/trace/define_trace.h | 15 +++++++++++++++ 2 files changed, 38 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 5a6074fcd81d..d3e4f87e95c0 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -106,6 +106,7 @@ static inline void tracepoint_update_probe_range(struct tracepoint *begin, #define TP_PROTO(args...) args #define TP_ARGS(args...) args +#define TP_CONDITION(args...) args #ifdef CONFIG_TRACEPOINTS @@ -119,12 +120,14 @@ static inline void tracepoint_update_probe_range(struct tracepoint *begin, * as "(void *, void)". The DECLARE_TRACE_NOARGS() will pass in just * "void *data", where as the DECLARE_TRACE() will pass in "void *data, proto". */ -#define __DO_TRACE(tp, proto, args) \ +#define __DO_TRACE(tp, proto, args, cond) \ do { \ struct tracepoint_func *it_func_ptr; \ void *it_func; \ void *__data; \ \ + if (!(cond)) \ + return; \ rcu_read_lock_sched_notrace(); \ it_func_ptr = rcu_dereference_sched((tp)->funcs); \ if (it_func_ptr) { \ @@ -142,7 +145,7 @@ static inline void tracepoint_update_probe_range(struct tracepoint *begin, * not add unwanted padding between the beginning of the section and the * structure. Force alignment to the same alignment as the section start. */ -#define __DECLARE_TRACE(name, proto, args, data_proto, data_args) \ +#define __DECLARE_TRACE(name, proto, args, cond, data_proto, data_args) \ extern struct tracepoint __tracepoint_##name; \ static inline void trace_##name(proto) \ { \ @@ -151,7 +154,8 @@ static inline void tracepoint_update_probe_range(struct tracepoint *begin, do_trace: \ __DO_TRACE(&__tracepoint_##name, \ TP_PROTO(data_proto), \ - TP_ARGS(data_args)); \ + TP_ARGS(data_args), \ + TP_CONDITION(cond)); \ } \ static inline int \ register_trace_##name(void (*probe)(data_proto), void *data) \ @@ -186,7 +190,7 @@ do_trace: \ EXPORT_SYMBOL(__tracepoint_##name) #else /* !CONFIG_TRACEPOINTS */ -#define __DECLARE_TRACE(name, proto, args, data_proto, data_args) \ +#define __DECLARE_TRACE(name, proto, args, cond, data_proto, data_args) \ static inline void trace_##name(proto) \ { } \ static inline int \ @@ -227,13 +231,18 @@ do_trace: \ * "void *__data, proto" as the callback prototype. */ #define DECLARE_TRACE_NOARGS(name) \ - __DECLARE_TRACE(name, void, , void *__data, __data) + __DECLARE_TRACE(name, void, , 1, void *__data, __data) #define DECLARE_TRACE(name, proto, args) \ - __DECLARE_TRACE(name, PARAMS(proto), PARAMS(args), \ + __DECLARE_TRACE(name, PARAMS(proto), PARAMS(args), 1, \ PARAMS(void *__data, proto), \ PARAMS(__data, args)) +#define DECLARE_TRACE_CONDITION(name, proto, args, cond) \ + __DECLARE_TRACE(name, PARAMS(proto), PARAMS(args), PARAMS(cond), \ + PARAMS(void *__data, proto), \ + PARAMS(__data, args)) + #define TRACE_EVENT_FLAGS(event, flag) #endif /* DECLARE_TRACE */ @@ -349,12 +358,20 @@ do_trace: \ DECLARE_TRACE(name, PARAMS(proto), PARAMS(args)) #define DEFINE_EVENT_PRINT(template, name, proto, args, print) \ DECLARE_TRACE(name, PARAMS(proto), PARAMS(args)) +#define DEFINE_EVENT_CONDITION(template, name, proto, \ + args, cond) \ + DECLARE_TRACE_CONDITION(name, PARAMS(proto), \ + PARAMS(args), PARAMS(cond)) #define TRACE_EVENT(name, proto, args, struct, assign, print) \ DECLARE_TRACE(name, PARAMS(proto), PARAMS(args)) #define TRACE_EVENT_FN(name, proto, args, struct, \ assign, print, reg, unreg) \ DECLARE_TRACE(name, PARAMS(proto), PARAMS(args)) +#define TRACE_EVENT_CONDITION(name, proto, args, cond, \ + struct, assign, print) \ + DECLARE_TRACE_CONDITION(name, PARAMS(proto), \ + PARAMS(args), PARAMS(cond)) #define TRACE_EVENT_FLAGS(event, flag) diff --git a/include/trace/define_trace.h b/include/trace/define_trace.h index 1dfab5401511..b0b4eb24d592 100644 --- a/include/trace/define_trace.h +++ b/include/trace/define_trace.h @@ -26,6 +26,15 @@ #define TRACE_EVENT(name, proto, args, tstruct, assign, print) \ DEFINE_TRACE(name) +#undef TRACE_EVENT_CONDITION +#define TRACE_EVENT_CONDITION(name, proto, args, cond, tstruct, assign, print) \ + TRACE_EVENT(name, \ + PARAMS(proto), \ + PARAMS(args), \ + PARAMS(tstruct), \ + PARAMS(assign), \ + PARAMS(print)) + #undef TRACE_EVENT_FN #define TRACE_EVENT_FN(name, proto, args, tstruct, \ assign, print, reg, unreg) \ @@ -39,6 +48,10 @@ #define DEFINE_EVENT_PRINT(template, name, proto, args, print) \ DEFINE_TRACE(name) +#undef DEFINE_EVENT_CONDITION +#define DEFINE_EVENT_CONDITION(template, name, proto, args, cond) \ + DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args)) + #undef DECLARE_TRACE #define DECLARE_TRACE(name, proto, args) \ DEFINE_TRACE(name) @@ -75,9 +88,11 @@ #undef TRACE_EVENT #undef TRACE_EVENT_FN +#undef TRACE_EVENT_CONDITION #undef DECLARE_EVENT_CLASS #undef DEFINE_EVENT #undef DEFINE_EVENT_PRINT +#undef DEFINE_EVENT_CONDITION #undef TRACE_HEADER_MULTI_READ #undef DECLARE_TRACE -- cgit v1.2.3 From 6844c09d849aeb00e8ddfe9525e8567a531c22d0 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 3 Dec 2010 16:36:35 -0200 Subject: perf events: Separate the routines handling the PERF_SAMPLE_ identity fields MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Those will be made available in sample like events like MMAP, EXEC, etc in a followup patch. So precalculate the extra id header space and have a separate routine to fill them up. V2: Thomas noticed that the id header needs to be precalculated at inherit_events too: LKML-Reference: Tested-by: Thomas Gleixner Reviewed-by: Thomas Gleixner Acked-by: Ian Munsie Acked-by: Peter Zijlstra Acked-by: Thomas Gleixner Cc: Frédéric Weisbecker Cc: Ian Munsie Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Paul Mackerras Cc: Stephane Eranian Cc: Thomas Gleixner LKML-Reference: <1291318772-30880-2-git-send-email-acme@infradead.org> Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/perf_event.h | 1 + kernel/perf_event.c | 129 ++++++++++++++++++++++++++------------------- 2 files changed, 76 insertions(+), 54 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index adf6d9931643..b9950b1620d8 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -759,6 +759,7 @@ struct perf_event { struct perf_event_attr attr; u16 header_size; + u16 id_header_size; u16 read_size; struct hw_perf_event hw; diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 7961b27aceea..a04799769566 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -133,6 +133,28 @@ static void unclone_ctx(struct perf_event_context *ctx) } } +static u32 perf_event_pid(struct perf_event *event, struct task_struct *p) +{ + /* + * only top level events have the pid namespace they were created in + */ + if (event->parent) + event = event->parent; + + return task_tgid_nr_ns(p, event->ns); +} + +static u32 perf_event_tid(struct perf_event *event, struct task_struct *p) +{ + /* + * only top level events have the pid namespace they were created in + */ + if (event->parent) + event = event->parent; + + return task_pid_nr_ns(p, event->ns); +} + /* * If we inherit events we want to return the parent event id * to userspace. @@ -351,15 +373,30 @@ static void perf_event__header_size(struct perf_event *event) if (sample_type & PERF_SAMPLE_IP) size += sizeof(data->ip); + if (sample_type & PERF_SAMPLE_ADDR) + size += sizeof(data->addr); + + if (sample_type & PERF_SAMPLE_PERIOD) + size += sizeof(data->period); + + if (sample_type & PERF_SAMPLE_READ) + size += event->read_size; + + event->header_size = size; +} + +static void perf_event__id_header_size(struct perf_event *event) +{ + struct perf_sample_data *data; + u64 sample_type = event->attr.sample_type; + u16 size = 0; + if (sample_type & PERF_SAMPLE_TID) size += sizeof(data->tid_entry); if (sample_type & PERF_SAMPLE_TIME) size += sizeof(data->time); - if (sample_type & PERF_SAMPLE_ADDR) - size += sizeof(data->addr); - if (sample_type & PERF_SAMPLE_ID) size += sizeof(data->id); @@ -369,13 +406,7 @@ static void perf_event__header_size(struct perf_event *event) if (sample_type & PERF_SAMPLE_CPU) size += sizeof(data->cpu_entry); - if (sample_type & PERF_SAMPLE_PERIOD) - size += sizeof(data->period); - - if (sample_type & PERF_SAMPLE_READ) - size += event->read_size; - - event->header_size = size; + event->id_header_size = size; } static void perf_group_attach(struct perf_event *event) @@ -3357,6 +3388,36 @@ __always_inline void perf_output_copy(struct perf_output_handle *handle, } while (len); } +static void perf_event_header__init_id(struct perf_event_header *header, + struct perf_sample_data *data, + struct perf_event *event) +{ + u64 sample_type = event->attr.sample_type; + + data->type = sample_type; + header->size += event->id_header_size; + + if (sample_type & PERF_SAMPLE_TID) { + /* namespace issues */ + data->tid_entry.pid = perf_event_pid(event, current); + data->tid_entry.tid = perf_event_tid(event, current); + } + + if (sample_type & PERF_SAMPLE_TIME) + data->time = perf_clock(); + + if (sample_type & PERF_SAMPLE_ID) + data->id = primary_event_id(event); + + if (sample_type & PERF_SAMPLE_STREAM_ID) + data->stream_id = event->id; + + if (sample_type & PERF_SAMPLE_CPU) { + data->cpu_entry.cpu = raw_smp_processor_id(); + data->cpu_entry.reserved = 0; + } +} + int perf_output_begin(struct perf_output_handle *handle, struct perf_event *event, unsigned int size, int nmi, int sample) @@ -3459,28 +3520,6 @@ void perf_output_end(struct perf_output_handle *handle) rcu_read_unlock(); } -static u32 perf_event_pid(struct perf_event *event, struct task_struct *p) -{ - /* - * only top level events have the pid namespace they were created in - */ - if (event->parent) - event = event->parent; - - return task_tgid_nr_ns(p, event->ns); -} - -static u32 perf_event_tid(struct perf_event *event, struct task_struct *p) -{ - /* - * only top level events have the pid namespace they were created in - */ - if (event->parent) - event = event->parent; - - return task_pid_nr_ns(p, event->ns); -} - static void perf_output_read_one(struct perf_output_handle *handle, struct perf_event *event, u64 enabled, u64 running) @@ -3655,37 +3694,17 @@ void perf_prepare_sample(struct perf_event_header *header, { u64 sample_type = event->attr.sample_type; - data->type = sample_type; - header->type = PERF_RECORD_SAMPLE; header->size = sizeof(*header) + event->header_size; header->misc = 0; header->misc |= perf_misc_flags(regs); + perf_event_header__init_id(header, data, event); + if (sample_type & PERF_SAMPLE_IP) data->ip = perf_instruction_pointer(regs); - if (sample_type & PERF_SAMPLE_TID) { - /* namespace issues */ - data->tid_entry.pid = perf_event_pid(event, current); - data->tid_entry.tid = perf_event_tid(event, current); - } - - if (sample_type & PERF_SAMPLE_TIME) - data->time = perf_clock(); - - if (sample_type & PERF_SAMPLE_ID) - data->id = primary_event_id(event); - - if (sample_type & PERF_SAMPLE_STREAM_ID) - data->stream_id = event->id; - - if (sample_type & PERF_SAMPLE_CPU) { - data->cpu_entry.cpu = raw_smp_processor_id(); - data->cpu_entry.reserved = 0; - } - if (sample_type & PERF_SAMPLE_CALLCHAIN) { int size = 1; @@ -5745,6 +5764,7 @@ SYSCALL_DEFINE5(perf_event_open, * Precalculate sample_data sizes */ perf_event__header_size(event); + perf_event__id_header_size(event); /* * Drop the reference on the group_event after placing the @@ -6102,6 +6122,7 @@ inherit_event(struct perf_event *parent_event, * Precalculate sample_data sizes */ perf_event__header_size(child_event); + perf_event__id_header_size(child_event); /* * Link it up in the child's context: -- cgit v1.2.3 From c980d1091810df13f21aabbce545fd98f545bbf7 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Sat, 4 Dec 2010 23:02:20 -0200 Subject: perf events: Make sample_type identity fields available in all PERF_RECORD_ events MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If perf_event_attr.sample_id_all is set it will add the PERF_SAMPLE_ identity info: TID, TIME, ID, CPU, STREAM_ID As a trailer, so that older perf tools can process new files, just ignoring the extra payload. With this its possible to do further analysis on problems in the event stream, like detecting reordering of MMAP and FORK events, etc. V2: Fixup header size in comm, mmap and task processing, as we have to take into account different sample_types for each matching event, noticed by Thomas Gleixner. Thomas also noticed a problem in v2 where if we didn't had space in the buffer we wouldn't restore the header size. Tested-by: Thomas Gleixner Reviewed-by: Thomas Gleixner Acked-by: Ian Munsie Acked-by: Peter Zijlstra Acked-by: Thomas Gleixner Cc: Frédéric Weisbecker Cc: Ian Munsie Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Paul Mackerras Cc: Stephane Eranian Cc: Thomas Gleixner LKML-Reference: Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/perf_event.h | 12 ++++- kernel/perf_event.c | 108 ++++++++++++++++++++++++++++++++++++++------- 2 files changed, 102 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index b9950b1620d8..2814ead4adb8 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -215,8 +215,9 @@ struct perf_event_attr { */ precise_ip : 2, /* skid constraint */ mmap_data : 1, /* non-exec mmap data */ + sample_id_all : 1, /* sample_type all events */ - __reserved_1 : 46; + __reserved_1 : 45; union { __u32 wakeup_events; /* wakeup every n events */ @@ -327,6 +328,15 @@ struct perf_event_header { enum perf_event_type { /* + * If perf_event_attr.sample_id_all is set then all event types will + * have the sample_type selected fields related to where/when + * (identity) an event took place (TID, TIME, ID, CPU, STREAM_ID) + * described in PERF_RECORD_SAMPLE below, it will be stashed just after + * the perf_event_header and the fields already present for the existing + * fields, i.e. at the end of the payload. That way a newer perf.data + * file will be supported by older perf tools, with these new optional + * fields being ignored. + * * The MMAP events record the PROT_EXEC mappings so that we can * correlate userspace IPs to code. They have the following structure: * diff --git a/kernel/perf_event.c b/kernel/perf_event.c index a04799769566..77ad22c00b9d 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -3388,9 +3388,9 @@ __always_inline void perf_output_copy(struct perf_output_handle *handle, } while (len); } -static void perf_event_header__init_id(struct perf_event_header *header, - struct perf_sample_data *data, - struct perf_event *event) +static void __perf_event_header__init_id(struct perf_event_header *header, + struct perf_sample_data *data, + struct perf_event *event) { u64 sample_type = event->attr.sample_type; @@ -3418,6 +3418,43 @@ static void perf_event_header__init_id(struct perf_event_header *header, } } +static void perf_event_header__init_id(struct perf_event_header *header, + struct perf_sample_data *data, + struct perf_event *event) +{ + if (event->attr.sample_id_all) + __perf_event_header__init_id(header, data, event); +} + +static void __perf_event__output_id_sample(struct perf_output_handle *handle, + struct perf_sample_data *data) +{ + u64 sample_type = data->type; + + if (sample_type & PERF_SAMPLE_TID) + perf_output_put(handle, data->tid_entry); + + if (sample_type & PERF_SAMPLE_TIME) + perf_output_put(handle, data->time); + + if (sample_type & PERF_SAMPLE_ID) + perf_output_put(handle, data->id); + + if (sample_type & PERF_SAMPLE_STREAM_ID) + perf_output_put(handle, data->stream_id); + + if (sample_type & PERF_SAMPLE_CPU) + perf_output_put(handle, data->cpu_entry); +} + +static void perf_event__output_id_sample(struct perf_event *event, + struct perf_output_handle *handle, + struct perf_sample_data *sample) +{ + if (event->attr.sample_id_all) + __perf_event__output_id_sample(handle, sample); +} + int perf_output_begin(struct perf_output_handle *handle, struct perf_event *event, unsigned int size, int nmi, int sample) @@ -3425,6 +3462,7 @@ int perf_output_begin(struct perf_output_handle *handle, struct perf_buffer *buffer; unsigned long tail, offset, head; int have_lost; + struct perf_sample_data sample_data; struct { struct perf_event_header header; u64 id; @@ -3451,8 +3489,12 @@ int perf_output_begin(struct perf_output_handle *handle, goto out; have_lost = local_read(&buffer->lost); - if (have_lost) - size += sizeof(lost_event); + if (have_lost) { + lost_event.header.size = sizeof(lost_event); + perf_event_header__init_id(&lost_event.header, &sample_data, + event); + size += lost_event.header.size; + } perf_output_get_handle(handle); @@ -3483,11 +3525,11 @@ int perf_output_begin(struct perf_output_handle *handle, if (have_lost) { lost_event.header.type = PERF_RECORD_LOST; lost_event.header.misc = 0; - lost_event.header.size = sizeof(lost_event); lost_event.id = event->id; lost_event.lost = local_xchg(&buffer->lost, 0); perf_output_put(handle, lost_event); + perf_event__output_id_sample(event, handle, &sample_data); } return 0; @@ -3700,7 +3742,7 @@ void perf_prepare_sample(struct perf_event_header *header, header->misc = 0; header->misc |= perf_misc_flags(regs); - perf_event_header__init_id(header, data, event); + __perf_event_header__init_id(header, data, event); if (sample_type & PERF_SAMPLE_IP) data->ip = perf_instruction_pointer(regs); @@ -3768,6 +3810,7 @@ perf_event_read_event(struct perf_event *event, struct task_struct *task) { struct perf_output_handle handle; + struct perf_sample_data sample; struct perf_read_event read_event = { .header = { .type = PERF_RECORD_READ, @@ -3779,12 +3822,14 @@ perf_event_read_event(struct perf_event *event, }; int ret; + perf_event_header__init_id(&read_event.header, &sample, event); ret = perf_output_begin(&handle, event, read_event.header.size, 0, 0); if (ret) return; perf_output_put(&handle, read_event); perf_output_read(&handle, event); + perf_event__output_id_sample(event, &handle, &sample); perf_output_end(&handle); } @@ -3814,14 +3859,16 @@ static void perf_event_task_output(struct perf_event *event, struct perf_task_event *task_event) { struct perf_output_handle handle; + struct perf_sample_data sample; struct task_struct *task = task_event->task; - int size, ret; + int ret, size = task_event->event_id.header.size; - size = task_event->event_id.header.size; - ret = perf_output_begin(&handle, event, size, 0, 0); + perf_event_header__init_id(&task_event->event_id.header, &sample, event); + ret = perf_output_begin(&handle, event, + task_event->event_id.header.size, 0, 0); if (ret) - return; + goto out; task_event->event_id.pid = perf_event_pid(event, task); task_event->event_id.ppid = perf_event_pid(event, current); @@ -3831,7 +3878,11 @@ static void perf_event_task_output(struct perf_event *event, perf_output_put(&handle, task_event->event_id); + perf_event__output_id_sample(event, &handle, &sample); + perf_output_end(&handle); +out: + task_event->event_id.header.size = size; } static int perf_event_task_match(struct perf_event *event) @@ -3944,11 +3995,16 @@ static void perf_event_comm_output(struct perf_event *event, struct perf_comm_event *comm_event) { struct perf_output_handle handle; + struct perf_sample_data sample; int size = comm_event->event_id.header.size; - int ret = perf_output_begin(&handle, event, size, 0, 0); + int ret; + + perf_event_header__init_id(&comm_event->event_id.header, &sample, event); + ret = perf_output_begin(&handle, event, + comm_event->event_id.header.size, 0, 0); if (ret) - return; + goto out; comm_event->event_id.pid = perf_event_pid(event, comm_event->task); comm_event->event_id.tid = perf_event_tid(event, comm_event->task); @@ -3956,7 +4012,12 @@ static void perf_event_comm_output(struct perf_event *event, perf_output_put(&handle, comm_event->event_id); perf_output_copy(&handle, comm_event->comm, comm_event->comm_size); + + perf_event__output_id_sample(event, &handle, &sample); + perf_output_end(&handle); +out: + comm_event->event_id.header.size = size; } static int perf_event_comm_match(struct perf_event *event) @@ -4001,7 +4062,6 @@ static void perf_event_comm_event(struct perf_comm_event *comm_event) comm_event->comm_size = size; comm_event->event_id.header.size = sizeof(comm_event->event_id) + size; - rcu_read_lock(); list_for_each_entry_rcu(pmu, &pmus, entry) { cpuctx = get_cpu_ptr(pmu->pmu_cpu_context); @@ -4080,11 +4140,15 @@ static void perf_event_mmap_output(struct perf_event *event, struct perf_mmap_event *mmap_event) { struct perf_output_handle handle; + struct perf_sample_data sample; int size = mmap_event->event_id.header.size; - int ret = perf_output_begin(&handle, event, size, 0, 0); + int ret; + perf_event_header__init_id(&mmap_event->event_id.header, &sample, event); + ret = perf_output_begin(&handle, event, + mmap_event->event_id.header.size, 0, 0); if (ret) - return; + goto out; mmap_event->event_id.pid = perf_event_pid(event, current); mmap_event->event_id.tid = perf_event_tid(event, current); @@ -4092,7 +4156,12 @@ static void perf_event_mmap_output(struct perf_event *event, perf_output_put(&handle, mmap_event->event_id); perf_output_copy(&handle, mmap_event->file_name, mmap_event->file_size); + + perf_event__output_id_sample(event, &handle, &sample); + perf_output_end(&handle); +out: + mmap_event->event_id.header.size = size; } static int perf_event_mmap_match(struct perf_event *event, @@ -4245,6 +4314,7 @@ void perf_event_mmap(struct vm_area_struct *vma) static void perf_log_throttle(struct perf_event *event, int enable) { struct perf_output_handle handle; + struct perf_sample_data sample; int ret; struct { @@ -4266,11 +4336,15 @@ static void perf_log_throttle(struct perf_event *event, int enable) if (enable) throttle_event.header.type = PERF_RECORD_UNTHROTTLE; - ret = perf_output_begin(&handle, event, sizeof(throttle_event), 1, 0); + perf_event_header__init_id(&throttle_event.header, &sample, event); + + ret = perf_output_begin(&handle, event, + throttle_event.header.size, 1, 0); if (ret) return; perf_output_put(&handle, throttle_event); + perf_event__output_id_sample(event, &handle, &sample); perf_output_end(&handle); } -- cgit v1.2.3 From cd7ebe2298ff1c3112232878678ce5fe6be8a15b Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Fri, 3 Dec 2010 18:54:28 +0900 Subject: kprobes: Use text_poke_smp_batch for optimizing Use text_poke_smp_batch() in optimization path for reducing the number of stop_machine() issues. If the number of optimizing probes is more than MAX_OPTIMIZE_PROBES(=256), kprobes optimizes first MAX_OPTIMIZE_PROBES probes and kicks optimizer for remaining probes. Changes in v5: - Use kick_kprobe_optimizer() instead of directly calling schedule_delayed_work(). - Rescheduling optimizer outside of kprobe mutex lock. Changes in v2: - Allocate code buffer and parameters in arch_init_kprobes() instead of using static arraies. - Merge previous max optimization limit patch into this patch. So, this patch introduces upper limit of optimization at once. Signed-off-by: Masami Hiramatsu Cc: Rusty Russell Cc: Frederic Weisbecker Cc: Ananth N Mavinakayanahalli Cc: Jason Baron Cc: Mathieu Desnoyers Cc: 2nddept-manager@sdl.hitachi.co.jp Cc: Peter Zijlstra Cc: Steven Rostedt LKML-Reference: <20101203095428.2961.8994.stgit@ltc236.sdl.hitachi.co.jp> Signed-off-by: Ingo Molnar --- arch/x86/kernel/kprobes.c | 69 +++++++++++++++++++++++++++++++++++++++++------ include/linux/kprobes.h | 2 +- kernel/kprobes.c | 17 +++++------- 3 files changed, 69 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index da51dc8e77cb..25a8af76feb5 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -1405,10 +1405,16 @@ int __kprobes arch_prepare_optimized_kprobe(struct optimized_kprobe *op) return 0; } -/* Replace a breakpoint (int3) with a relative jump. */ -int __kprobes arch_optimize_kprobe(struct optimized_kprobe *op) +#define MAX_OPTIMIZE_PROBES 256 +static struct text_poke_param *jump_poke_params; +static struct jump_poke_buffer { + u8 buf[RELATIVEJUMP_SIZE]; +} *jump_poke_bufs; + +static void __kprobes setup_optimize_kprobe(struct text_poke_param *tprm, + u8 *insn_buf, + struct optimized_kprobe *op) { - unsigned char jmp_code[RELATIVEJUMP_SIZE]; s32 rel = (s32)((long)op->optinsn.insn - ((long)op->kp.addr + RELATIVEJUMP_SIZE)); @@ -1416,16 +1422,39 @@ int __kprobes arch_optimize_kprobe(struct optimized_kprobe *op) memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_SIZE, RELATIVE_ADDR_SIZE); - jmp_code[0] = RELATIVEJUMP_OPCODE; - *(s32 *)(&jmp_code[1]) = rel; + insn_buf[0] = RELATIVEJUMP_OPCODE; + *(s32 *)(&insn_buf[1]) = rel; + + tprm->addr = op->kp.addr; + tprm->opcode = insn_buf; + tprm->len = RELATIVEJUMP_SIZE; +} + +/* + * Replace breakpoints (int3) with relative jumps. + * Caller must call with locking kprobe_mutex and text_mutex. + */ +void __kprobes arch_optimize_kprobes(struct list_head *oplist) +{ + struct optimized_kprobe *op, *tmp; + int c = 0; + + list_for_each_entry_safe(op, tmp, oplist, list) { + WARN_ON(kprobe_disabled(&op->kp)); + /* Setup param */ + setup_optimize_kprobe(&jump_poke_params[c], + jump_poke_bufs[c].buf, op); + list_del_init(&op->list); + if (++c >= MAX_OPTIMIZE_PROBES) + break; + } /* * text_poke_smp doesn't support NMI/MCE code modifying. * However, since kprobes itself also doesn't support NMI/MCE * code probing, it's not a problem. */ - text_poke_smp(op->kp.addr, jmp_code, RELATIVEJUMP_SIZE); - return 0; + text_poke_smp_batch(jump_poke_params, c); } /* Replace a relative jump with a breakpoint (int3). */ @@ -1457,11 +1486,35 @@ static int __kprobes setup_detour_execution(struct kprobe *p, } return 0; } + +static int __kprobes init_poke_params(void) +{ + /* Allocate code buffer and parameter array */ + jump_poke_bufs = kmalloc(sizeof(struct jump_poke_buffer) * + MAX_OPTIMIZE_PROBES, GFP_KERNEL); + if (!jump_poke_bufs) + return -ENOMEM; + + jump_poke_params = kmalloc(sizeof(struct text_poke_param) * + MAX_OPTIMIZE_PROBES, GFP_KERNEL); + if (!jump_poke_params) { + kfree(jump_poke_bufs); + jump_poke_bufs = NULL; + return -ENOMEM; + } + + return 0; +} +#else /* !CONFIG_OPTPROBES */ +static int __kprobes init_poke_params(void) +{ + return 0; +} #endif int __init arch_init_kprobes(void) { - return 0; + return init_poke_params(); } int __kprobes arch_trampoline_kprobe(struct kprobe *p) diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index e7d1b2e0070d..fe157ba6aa0e 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -275,7 +275,7 @@ extern int arch_prepared_optinsn(struct arch_optimized_insn *optinsn); extern int arch_check_optimized_kprobe(struct optimized_kprobe *op); extern int arch_prepare_optimized_kprobe(struct optimized_kprobe *op); extern void arch_remove_optimized_kprobe(struct optimized_kprobe *op); -extern int arch_optimize_kprobe(struct optimized_kprobe *op); +extern void arch_optimize_kprobes(struct list_head *oplist); extern void arch_unoptimize_kprobe(struct optimized_kprobe *op); extern kprobe_opcode_t *get_optinsn_slot(void); extern void free_optinsn_slot(kprobe_opcode_t *slot, int dirty); diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 134754d18bb4..531e10164836 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -480,8 +480,6 @@ static DECLARE_COMPLETION(optimizer_comp); */ static __kprobes void do_optimize_kprobes(void) { - struct optimized_kprobe *op, *tmp; - /* Optimization never be done when disarmed */ if (kprobes_all_disarmed || !kprobes_allow_optimization || list_empty(&optimizing_list)) @@ -499,12 +497,7 @@ static __kprobes void do_optimize_kprobes(void) */ get_online_cpus(); mutex_lock(&text_mutex); - list_for_each_entry_safe(op, tmp, &optimizing_list, list) { - WARN_ON(kprobe_disabled(&op->kp)); - if (arch_optimize_kprobe(op) < 0) - op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED; - list_del_init(&op->list); - } + arch_optimize_kprobes(&optimizing_list); mutex_unlock(&text_mutex); put_online_cpus(); } @@ -598,8 +591,12 @@ static __kprobes void kprobe_optimizer(struct work_struct *work) mutex_unlock(&kprobe_mutex); mutex_unlock(&module_mutex); - /* Wake up all waiters */ - complete_all(&optimizer_comp); + /* Step 5: Kick optimizer again if needed */ + if (!list_empty(&optimizing_list)) + kick_kprobe_optimizer(); + else + /* Wake up all waiters */ + complete_all(&optimizer_comp); } /* Wait for completing optimization and unoptimization */ -- cgit v1.2.3 From f984ba4eb575e4a27ed28a76d4126d2aa9233c32 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Fri, 3 Dec 2010 18:54:34 +0900 Subject: kprobes: Use text_poke_smp_batch for unoptimizing Use text_poke_smp_batch() on unoptimization path for reducing the number of stop_machine() issues. If the number of unoptimizing probes is more than MAX_OPTIMIZE_PROBES(=256), kprobes unoptimizes first MAX_OPTIMIZE_PROBES probes and kicks optimizer for remaining probes. Signed-off-by: Masami Hiramatsu Cc: Rusty Russell Cc: Frederic Weisbecker Cc: Ananth N Mavinakayanahalli Cc: Jason Baron Cc: Mathieu Desnoyers Cc: 2nddept-manager@sdl.hitachi.co.jp Cc: Peter Zijlstra Cc: Steven Rostedt LKML-Reference: <20101203095434.2961.22657.stgit@ltc236.sdl.hitachi.co.jp> Signed-off-by: Ingo Molnar --- arch/x86/kernel/kprobes.c | 40 ++++++++++++++++++++++++++++++++++++++++ include/linux/kprobes.h | 2 ++ kernel/kprobes.c | 10 ++++------ 3 files changed, 46 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index 25a8af76feb5..5940282bd2f9 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -1457,6 +1457,46 @@ void __kprobes arch_optimize_kprobes(struct list_head *oplist) text_poke_smp_batch(jump_poke_params, c); } +static void __kprobes setup_unoptimize_kprobe(struct text_poke_param *tprm, + u8 *insn_buf, + struct optimized_kprobe *op) +{ + /* Set int3 to first byte for kprobes */ + insn_buf[0] = BREAKPOINT_INSTRUCTION; + memcpy(insn_buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE); + + tprm->addr = op->kp.addr; + tprm->opcode = insn_buf; + tprm->len = RELATIVEJUMP_SIZE; +} + +/* + * Recover original instructions and breakpoints from relative jumps. + * Caller must call with locking kprobe_mutex. + */ +extern void arch_unoptimize_kprobes(struct list_head *oplist, + struct list_head *done_list) +{ + struct optimized_kprobe *op, *tmp; + int c = 0; + + list_for_each_entry_safe(op, tmp, oplist, list) { + /* Setup param */ + setup_unoptimize_kprobe(&jump_poke_params[c], + jump_poke_bufs[c].buf, op); + list_move(&op->list, done_list); + if (++c >= MAX_OPTIMIZE_PROBES) + break; + } + + /* + * text_poke_smp doesn't support NMI/MCE code modifying. + * However, since kprobes itself also doesn't support NMI/MCE + * code probing, it's not a problem. + */ + text_poke_smp_batch(jump_poke_params, c); +} + /* Replace a relative jump with a breakpoint (int3). */ void __kprobes arch_unoptimize_kprobe(struct optimized_kprobe *op) { diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index fe157ba6aa0e..b78edb58ee66 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -276,6 +276,8 @@ extern int arch_check_optimized_kprobe(struct optimized_kprobe *op); extern int arch_prepare_optimized_kprobe(struct optimized_kprobe *op); extern void arch_remove_optimized_kprobe(struct optimized_kprobe *op); extern void arch_optimize_kprobes(struct list_head *oplist); +extern void arch_unoptimize_kprobes(struct list_head *oplist, + struct list_head *done_list); extern void arch_unoptimize_kprobe(struct optimized_kprobe *op); extern kprobe_opcode_t *get_optinsn_slot(void); extern void free_optinsn_slot(kprobe_opcode_t *slot, int dirty); diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 531e10164836..7663e5df0e6f 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -517,9 +517,9 @@ static __kprobes void do_unoptimize_kprobes(struct list_head *free_list) /* Ditto to do_optimize_kprobes */ get_online_cpus(); mutex_lock(&text_mutex); - list_for_each_entry_safe(op, tmp, &unoptimizing_list, list) { - /* Unoptimize kprobes */ - arch_unoptimize_kprobe(op); + arch_unoptimize_kprobes(&unoptimizing_list, free_list); + /* Loop free_list for disarming */ + list_for_each_entry_safe(op, tmp, free_list, list) { /* Disarm probes if marked disabled */ if (kprobe_disabled(&op->kp)) arch_disarm_kprobe(&op->kp); @@ -530,8 +530,6 @@ static __kprobes void do_unoptimize_kprobes(struct list_head *free_list) * (reclaiming is done by do_free_cleaned_kprobes.) */ hlist_del_rcu(&op->kp.hlist); - /* Move only unused probes on free_list */ - list_move(&op->list, free_list); } else list_del_init(&op->list); } @@ -592,7 +590,7 @@ static __kprobes void kprobe_optimizer(struct work_struct *work) mutex_unlock(&module_mutex); /* Step 5: Kick optimizer again if needed */ - if (!list_empty(&optimizing_list)) + if (!list_empty(&optimizing_list) || !list_empty(&unoptimizing_list)) kick_kprobe_optimizer(); else /* Wake up all waiters */ -- cgit v1.2.3 From 3110f5f5545a645c50ef66b1f705d08dfd1df404 Mon Sep 17 00:00:00 2001 From: Matt Carlson Date: Mon, 6 Dec 2010 08:28:50 +0000 Subject: tg3: Move EEE definitions into mdio.h In commit 52b02d04c801fff51ca49ad033210846d1713253 entitled "tg3: Add EEE support", Ben Hutchings had commented that the EEE advertisement register will be in a standard location. This patch moves that definition into mdio.h and changes the code to use it. Signed-off-by: Matt Carlson Reviewed-by: Benjamin Li Signed-off-by: David S. Miller --- drivers/net/tg3.c | 16 ++++++++-------- drivers/net/tg3.h | 3 --- include/linux/mdio.h | 5 +++++ 3 files changed, 13 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c index b8ae5e19ced5..1e7a135de7b3 100644 --- a/drivers/net/tg3.c +++ b/drivers/net/tg3.c @@ -32,6 +32,7 @@ #include #include #include +#include #include #include #include @@ -1781,7 +1782,8 @@ static void tg3_phy_eee_adjust(struct tg3 *tp, u32 current_link_up) tw32(TG3_CPMU_EEE_CTRL, eeectl); - tg3_phy_cl45_read(tp, 0x7, TG3_CL45_D7_EEERES_STAT, &val); + tg3_phy_cl45_read(tp, MDIO_MMD_AN, + TG3_CL45_D7_EEERES_STAT, &val); if (val == TG3_CL45_D7_EEERES_STAT_LP_1000T || val == TG3_CL45_D7_EEERES_STAT_LP_100TX) @@ -2987,16 +2989,14 @@ static void tg3_phy_copper_begin(struct tg3 *tp) if (tp->link_config.autoneg == AUTONEG_ENABLE) { /* Advertise 100-BaseTX EEE ability */ if (tp->link_config.advertising & - (ADVERTISED_100baseT_Half | - ADVERTISED_100baseT_Full)) - val |= TG3_CL45_D7_EEEADV_CAP_100TX; + ADVERTISED_100baseT_Full) + val |= MDIO_AN_EEE_ADV_100TX; /* Advertise 1000-BaseT EEE ability */ if (tp->link_config.advertising & - (ADVERTISED_1000baseT_Half | - ADVERTISED_1000baseT_Full)) - val |= TG3_CL45_D7_EEEADV_CAP_1000T; + ADVERTISED_1000baseT_Full) + val |= MDIO_AN_EEE_ADV_1000T; } - tg3_phy_cl45_write(tp, 0x7, TG3_CL45_D7_EEEADV_CAP, val); + tg3_phy_cl45_write(tp, MDIO_MMD_AN, MDIO_AN_EEE_ADV, val); /* Turn off SM_DSP clock. */ val = MII_TG3_AUXCTL_SHDWSEL_AUXCTL | diff --git a/drivers/net/tg3.h b/drivers/net/tg3.h index 59b0e096149e..6e72c6bd2675 100644 --- a/drivers/net/tg3.h +++ b/drivers/net/tg3.h @@ -2172,9 +2172,6 @@ #define MII_TG3_TEST1_CRC_EN 0x8000 /* Clause 45 expansion registers */ -#define TG3_CL45_D7_EEEADV_CAP 0x003c -#define TG3_CL45_D7_EEEADV_CAP_100TX 0x0002 -#define TG3_CL45_D7_EEEADV_CAP_1000T 0x0004 #define TG3_CL45_D7_EEERES_STAT 0x803e #define TG3_CL45_D7_EEERES_STAT_LP_100TX 0x0002 #define TG3_CL45_D7_EEERES_STAT_LP_1000T 0x0004 diff --git a/include/linux/mdio.h b/include/linux/mdio.h index c779b49a1fda..b1494aced217 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -55,6 +55,7 @@ #define MDIO_PCS_10GBRT_STAT2 33 /* 10GBASE-R/-T PCS status 2 */ #define MDIO_AN_10GBT_CTRL 32 /* 10GBASE-T auto-negotiation control */ #define MDIO_AN_10GBT_STAT 33 /* 10GBASE-T auto-negotiation status */ +#define MDIO_AN_EEE_ADV 60 /* EEE advertisement */ /* LASI (Link Alarm Status Interrupt) registers, defined by XENPAK MSA. */ #define MDIO_PMA_LASI_RXCTRL 0x9000 /* RX_ALARM control */ @@ -235,6 +236,10 @@ #define MDIO_AN_10GBT_STAT_MS 0x4000 /* Master/slave config */ #define MDIO_AN_10GBT_STAT_MSFLT 0x8000 /* Master/slave config fault */ +/* AN EEE Advertisement register. */ +#define MDIO_AN_EEE_ADV_100TX 0x0002 /* Advertise 100TX EEE cap */ +#define MDIO_AN_EEE_ADV_1000T 0x0004 /* Advertise 1000T EEE cap */ + /* LASI RX_ALARM control/status registers. */ #define MDIO_PMA_LASI_RX_PHYXSLFLT 0x0001 /* PHY XS RX local fault */ #define MDIO_PMA_LASI_RX_PCSLFLT 0x0008 /* PCS RX local fault */ -- cgit v1.2.3 From af5568843594fb71055debe36e521fa8072fcecc Mon Sep 17 00:00:00 2001 From: Bruno Randolf Date: Thu, 2 Dec 2010 19:50:37 +0900 Subject: lib: Improve EWMA efficiency by using bitshifts Using bitshifts instead of division and multiplication should improve performance. That requires weight and factor to be powers of two, but i think this is something we can live with. Thanks to Peter Zijlstra for the improved formula! Signed-off-by: Bruno Randolf -- v2: use log2.h functions Signed-off-by: John W. Linville --- include/linux/average.h | 4 +--- lib/average.c | 20 ++++++++++++-------- 2 files changed, 13 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/average.h b/include/linux/average.h index 7706e40f95fa..c6028fd742c1 100644 --- a/include/linux/average.h +++ b/include/linux/average.h @@ -1,8 +1,6 @@ #ifndef _LINUX_AVERAGE_H #define _LINUX_AVERAGE_H -#include - /* Exponentially weighted moving average (EWMA) */ /* For more documentation see lib/average.c */ @@ -26,7 +24,7 @@ extern struct ewma *ewma_add(struct ewma *avg, unsigned long val); */ static inline unsigned long ewma_read(const struct ewma *avg) { - return DIV_ROUND_CLOSEST(avg->internal, avg->factor); + return avg->internal >> avg->factor; } #endif /* _LINUX_AVERAGE_H */ diff --git a/lib/average.c b/lib/average.c index f1d1b4660c42..5576c2841496 100644 --- a/lib/average.c +++ b/lib/average.c @@ -8,6 +8,7 @@ #include #include #include +#include /** * DOC: Exponentially Weighted Moving Average (EWMA) @@ -24,18 +25,21 @@ * ewma_init() - Initialize EWMA parameters * @avg: Average structure * @factor: Factor to use for the scaled up internal value. The maximum value - * of averages can be ULONG_MAX/(factor*weight). + * of averages can be ULONG_MAX/(factor*weight). For performance reasons + * factor has to be a power of 2. * @weight: Exponential weight, or decay rate. This defines how fast the - * influence of older values decreases. Has to be bigger than 1. + * influence of older values decreases. For performance reasons weight has + * to be a power of 2. * * Initialize the EWMA parameters for a given struct ewma @avg. */ void ewma_init(struct ewma *avg, unsigned long factor, unsigned long weight) { - WARN_ON(weight <= 1 || factor == 0); + WARN_ON(!is_power_of_2(weight) || !is_power_of_2(factor)); + + avg->weight = ilog2(weight); + avg->factor = ilog2(factor); avg->internal = 0; - avg->weight = weight; - avg->factor = factor; } EXPORT_SYMBOL(ewma_init); @@ -49,9 +53,9 @@ EXPORT_SYMBOL(ewma_init); struct ewma *ewma_add(struct ewma *avg, unsigned long val) { avg->internal = avg->internal ? - (((avg->internal * (avg->weight - 1)) + - (val * avg->factor)) / avg->weight) : - (val * avg->factor); + (((avg->internal << avg->weight) - avg->internal) + + (val << avg->factor)) >> avg->weight : + (val << avg->factor); return avg; } EXPORT_SYMBOL(ewma_add); -- cgit v1.2.3 From 073285fd392f6dc901da7c698d46e1e2a7e26436 Mon Sep 17 00:00:00 2001 From: Alexey Orishko Date: Mon, 29 Nov 2010 23:23:27 +0000 Subject: usbnet: changes for upcoming cdc_ncm driver Changes: include/linux/usb/usbnet.h: - a new flag to indicate driver's capability to accumulate IP packets in Tx direction and extract several packets from single skb in Rx direction. drivers/net/usb/usbnet.c: - the procedure of counting packets in usbnet was updated due to the accumulating of IP packets in the driver - no short packets are sent if indicated by the flag in driver_info structure Signed-off-by: Alexey Orishko Signed-off-by: David S. Miller --- drivers/net/usb/usbnet.c | 45 +++++++++++++++++++++++++++++++-------------- include/linux/usb/usbnet.h | 6 ++++++ 2 files changed, 37 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index c04d49e31f81..cff74b81a7d2 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -391,14 +391,19 @@ static inline void rx_process (struct usbnet *dev, struct sk_buff *skb) goto error; // else network stack removes extra byte if we forced a short packet - if (skb->len) - usbnet_skb_return (dev, skb); - else { - netif_dbg(dev, rx_err, dev->net, "drop\n"); -error: - dev->net->stats.rx_errors++; - skb_queue_tail (&dev->done, skb); + if (skb->len) { + /* all data was already cloned from skb inside the driver */ + if (dev->driver_info->flags & FLAG_MULTI_PACKET) + dev_kfree_skb_any(skb); + else + usbnet_skb_return(dev, skb); + return; } + + netif_dbg(dev, rx_err, dev->net, "drop\n"); +error: + dev->net->stats.rx_errors++; + skb_queue_tail(&dev->done, skb); } /*-------------------------------------------------------------------------*/ @@ -971,7 +976,8 @@ static void tx_complete (struct urb *urb) struct usbnet *dev = entry->dev; if (urb->status == 0) { - dev->net->stats.tx_packets++; + if (!(dev->driver_info->flags & FLAG_MULTI_PACKET)) + dev->net->stats.tx_packets++; dev->net->stats.tx_bytes += entry->length; } else { dev->net->stats.tx_errors++; @@ -1044,8 +1050,13 @@ netdev_tx_t usbnet_start_xmit (struct sk_buff *skb, if (info->tx_fixup) { skb = info->tx_fixup (dev, skb, GFP_ATOMIC); if (!skb) { - netif_dbg(dev, tx_err, dev->net, "can't tx_fixup skb\n"); - goto drop; + if (netif_msg_tx_err(dev)) { + netif_dbg(dev, tx_err, dev->net, "can't tx_fixup skb\n"); + goto drop; + } else { + /* cdc_ncm collected packet; waits for more */ + goto not_drop; + } } } length = skb->len; @@ -1067,13 +1078,18 @@ netdev_tx_t usbnet_start_xmit (struct sk_buff *skb, /* don't assume the hardware handles USB_ZERO_PACKET * NOTE: strictly conforming cdc-ether devices should expect * the ZLP here, but ignore the one-byte packet. + * NOTE2: CDC NCM specification is different from CDC ECM when + * handling ZLP/short packets, so cdc_ncm driver will make short + * packet itself if needed. */ if (length % dev->maxpacket == 0) { if (!(info->flags & FLAG_SEND_ZLP)) { - urb->transfer_buffer_length++; - if (skb_tailroom(skb)) { - skb->data[skb->len] = 0; - __skb_put(skb, 1); + if (!(info->flags & FLAG_MULTI_PACKET)) { + urb->transfer_buffer_length++; + if (skb_tailroom(skb)) { + skb->data[skb->len] = 0; + __skb_put(skb, 1); + } } } else urb->transfer_flags |= URB_ZERO_PACKET; @@ -1122,6 +1138,7 @@ netdev_tx_t usbnet_start_xmit (struct sk_buff *skb, netif_dbg(dev, tx_err, dev->net, "drop, code %d\n", retval); drop: dev->net->stats.tx_dropped++; +not_drop: if (skb) dev_kfree_skb_any (skb); usb_free_urb (urb); diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index 7ae27a473818..44842c8d38c0 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -97,6 +97,12 @@ struct driver_info { #define FLAG_LINK_INTR 0x0800 /* updates link (carrier) status */ +/* + * Indicates to usbnet, that USB driver accumulates multiple IP packets. + * Affects statistic (counters) and short packet handling. + */ +#define FLAG_MULTI_PACKET 0x1000 + /* init device ... can sleep, or cause probe() failure */ int (*bind)(struct usbnet *, struct usb_interface *); -- cgit v1.2.3 From da2033c282264bfba4e339b7cb3df62adb5c5fc8 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 30 Nov 2010 21:45:56 +0000 Subject: filter: add SKF_AD_RXHASH and SKF_AD_CPU Add SKF_AD_RXHASH and SKF_AD_CPU to filter ancillary mechanism, to be able to build advanced filters. This can help spreading packets on several sockets with a fast selection, after RPS dispatch to N cpus for example, or to catch a percentage of flows in one queue. tcpdump -s 500 "cpu = 1" : [0] ld CPU [1] jeq #1 jt 2 jf 3 [2] ret #500 [3] ret #0 # take 12.5 % of flows (average) tcpdump -s 1000 "rxhash & 7 = 2" : [0] ld RXHASH [1] and #7 [2] jeq #2 jt 3 jf 4 [3] ret #1000 [4] ret #0 Signed-off-by: Eric Dumazet Cc: Rui Acked-by: Changli Gao Signed-off-by: David S. Miller --- include/linux/filter.h | 4 +++- net/core/filter.c | 6 ++++++ 2 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 447a775878fb..5334adaf4072 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -124,7 +124,9 @@ struct sock_fprog { /* Required for SO_ATTACH_FILTER. */ #define SKF_AD_MARK 20 #define SKF_AD_QUEUE 24 #define SKF_AD_HATYPE 28 -#define SKF_AD_MAX 32 +#define SKF_AD_RXHASH 32 +#define SKF_AD_CPU 36 +#define SKF_AD_MAX 40 #define SKF_NET_OFF (-0x100000) #define SKF_LL_OFF (-0x200000) diff --git a/net/core/filter.c b/net/core/filter.c index a44d27f9f0f0..054e286861d2 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -375,6 +375,12 @@ load_b: return 0; A = skb->dev->type; continue; + case SKF_AD_RXHASH: + A = skb->rxhash; + continue; + case SKF_AD_CPU: + A = raw_smp_processor_id(); + continue; case SKF_AD_NLATTR: { struct nlattr *nla; -- cgit v1.2.3 From 06a9701f4b3e3381dea96fee1cc8a3bb41b0a1f1 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 1 Dec 2010 01:37:42 +0000 Subject: __in_dev_get_rtnl() can use rtnl_dereference() If caller holds RTNL, we dont need a memory barrier (smp_read_barrier_depends) included in rcu_dereference(). Just use rtnl_dereference() to properly document the assertions. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/inetdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index 2b86eaf11773..ae8fdc54e0c0 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -222,7 +222,7 @@ static inline struct in_device *in_dev_get(const struct net_device *dev) static inline struct in_device *__in_dev_get_rtnl(const struct net_device *dev) { - return rcu_dereference_check(dev->ip_ptr, lockdep_rtnl_is_held()); + return rtnl_dereference(dev->ip_ptr); } extern void in_dev_finish_destroy(struct in_device *idev); -- cgit v1.2.3 From 45904f21655cf4f0ae7d0fab5906fe51bf56ecf4 Mon Sep 17 00:00:00 2001 From: Javier Cardona Date: Fri, 3 Dec 2010 09:20:40 +0100 Subject: nl80211/mac80211: define and allow configuring mesh element TTL The TTL in path selection information elements is different from the mesh ttl used in mesh data frames. Version 7.03 of the 11s draft calls this ttl 'Element TTL'. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/linux/nl80211.h | 4 ++++ include/net/cfg80211.h | 2 ++ net/mac80211/cfg.c | 2 ++ net/mac80211/debugfs_netdev.c | 2 ++ net/mac80211/mesh.c | 1 + net/mac80211/mesh.h | 2 ++ net/mac80211/mesh_hwmp.c | 9 +++++---- net/mac80211/mesh_pathtbl.c | 7 ++++--- net/wireless/nl80211.c | 5 +++++ 9 files changed, 27 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 5cfa579df476..9e541452d805 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -1547,6 +1547,9 @@ enum nl80211_mntr_flags { * @NL80211_MESHCONF_TTL: specifies the value of TTL field set at a source mesh * point. * + * @NL80211_MESHCONF_ELEMENT_TTL: specifies the value of TTL field set at a + * source mesh point for path selection elements. + * * @NL80211_MESHCONF_AUTO_OPEN_PLINKS: whether we should automatically * open peer links when we detect compatible mesh peers. * @@ -1593,6 +1596,7 @@ enum nl80211_meshconf_params { NL80211_MESHCONF_HWMP_PREQ_MIN_INTERVAL, NL80211_MESHCONF_HWMP_NET_DIAM_TRVS_TIME, NL80211_MESHCONF_HWMP_ROOTMODE, + NL80211_MESHCONF_ELEMENT_TTL, /* keep last */ __NL80211_MESHCONF_ATTR_AFTER_LAST, diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 6b2af7aeddd3..93a4b2068334 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -624,6 +624,8 @@ struct mesh_config { u16 dot11MeshMaxPeerLinks; u8 dot11MeshMaxRetries; u8 dot11MeshTTL; + /* ttl used in path selection information elements */ + u8 element_ttl; bool auto_open_plinks; /* HWMP parameters */ u8 dot11MeshHWMPmaxPREQretries; diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index db134b500caa..ce6936890c26 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1024,6 +1024,8 @@ static int ieee80211_set_mesh_params(struct wiphy *wiphy, conf->dot11MeshMaxRetries = nconf->dot11MeshMaxRetries; if (_chg_mesh_attr(NL80211_MESHCONF_TTL, mask)) conf->dot11MeshTTL = nconf->dot11MeshTTL; + if (_chg_mesh_attr(NL80211_MESHCONF_ELEMENT_TTL, mask)) + conf->dot11MeshTTL = nconf->element_ttl; if (_chg_mesh_attr(NL80211_MESHCONF_AUTO_OPEN_PLINKS, mask)) conf->auto_open_plinks = nconf->auto_open_plinks; if (_chg_mesh_attr(NL80211_MESHCONF_HWMP_MAX_PREQ_RETRIES, mask)) diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c index cbdf36d7841c..2dabdf7680d0 100644 --- a/net/mac80211/debugfs_netdev.c +++ b/net/mac80211/debugfs_netdev.c @@ -251,6 +251,7 @@ IEEE80211_IF_FILE(dot11MeshConfirmTimeout, IEEE80211_IF_FILE(dot11MeshHoldingTimeout, u.mesh.mshcfg.dot11MeshHoldingTimeout, DEC); IEEE80211_IF_FILE(dot11MeshTTL, u.mesh.mshcfg.dot11MeshTTL, DEC); +IEEE80211_IF_FILE(element_ttl, u.mesh.mshcfg.element_ttl, DEC); IEEE80211_IF_FILE(auto_open_plinks, u.mesh.mshcfg.auto_open_plinks, DEC); IEEE80211_IF_FILE(dot11MeshMaxPeerLinks, u.mesh.mshcfg.dot11MeshMaxPeerLinks, DEC); @@ -355,6 +356,7 @@ static void add_mesh_config(struct ieee80211_sub_if_data *sdata) MESHPARAMS_ADD(dot11MeshConfirmTimeout); MESHPARAMS_ADD(dot11MeshHoldingTimeout); MESHPARAMS_ADD(dot11MeshTTL); + MESHPARAMS_ADD(element_ttl); MESHPARAMS_ADD(auto_open_plinks); MESHPARAMS_ADD(dot11MeshMaxPeerLinks); MESHPARAMS_ADD(dot11MeshHWMPactivePathTimeout); diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index c8a4f19ed13b..78a36c79bdcc 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -668,6 +668,7 @@ void ieee80211_mesh_init_sdata(struct ieee80211_sub_if_data *sdata) ifmsh->mshcfg.dot11MeshHoldingTimeout = MESH_HOLD_T; ifmsh->mshcfg.dot11MeshMaxRetries = MESH_MAX_RETR; ifmsh->mshcfg.dot11MeshTTL = MESH_TTL; + ifmsh->mshcfg.element_ttl = MESH_DEFAULT_ELEMENT_TTL; ifmsh->mshcfg.auto_open_plinks = true; ifmsh->mshcfg.dot11MeshMaxPeerLinks = MESH_MAX_ESTAB_PLINKS; diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h index 58e741128968..182942eeac4d 100644 --- a/net/mac80211/mesh.h +++ b/net/mac80211/mesh.h @@ -216,6 +216,8 @@ struct mesh_rmc { #define PERR_RCODE_NO_ROUTE 12 #define PERR_RCODE_DEST_UNREACH 13 +#define MESH_DEFAULT_ELEMENT_TTL 31 + /* Public interfaces */ /* Various */ int ieee80211_fill_mesh_addresses(struct ieee80211_hdr *hdr, __le16 *fc, diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index 829e08a657d0..5bf64d7112b3 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -232,7 +232,7 @@ int mesh_path_error_tx(u8 ttl, u8 *target, __le32 target_sn, *pos++ = WLAN_EID_PERR; *pos++ = ie_len; /* ttl */ - *pos++ = MESH_TTL; + *pos++ = ttl; /* number of destinations */ *pos++ = 1; /* @@ -522,7 +522,7 @@ static void hwmp_preq_frame_process(struct ieee80211_sub_if_data *sdata, if (reply) { lifetime = PREQ_IE_LIFETIME(preq_elem); - ttl = ifmsh->mshcfg.dot11MeshTTL; + ttl = ifmsh->mshcfg.element_ttl; if (ttl != 0) { mhwmp_dbg("replying to the PREQ\n"); mesh_path_sel_frame_tx(MPATH_PREP, 0, target_addr, @@ -877,7 +877,7 @@ void mesh_path_start_discovery(struct ieee80211_sub_if_data *sdata) sdata->u.mesh.last_sn_update = jiffies; } lifetime = default_lifetime(sdata); - ttl = sdata->u.mesh.mshcfg.dot11MeshTTL; + ttl = sdata->u.mesh.mshcfg.element_ttl; if (ttl == 0) { sdata->u.mesh.mshstats.dropped_frames_ttl++; spin_unlock_bh(&mpath->state_lock); @@ -1013,5 +1013,6 @@ mesh_path_tx_root_frame(struct ieee80211_sub_if_data *sdata) mesh_path_sel_frame_tx(MPATH_RANN, 0, sdata->vif.addr, cpu_to_le32(++ifmsh->sn), 0, NULL, 0, broadcast_addr, - 0, MESH_TTL, 0, 0, 0, sdata); + 0, sdata->u.mesh.mshcfg.element_ttl, + 0, 0, 0, sdata); } diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index 349e466cf08b..8d65b47d9837 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -467,8 +467,8 @@ void mesh_plink_broken(struct sta_info *sta) mpath->flags &= ~MESH_PATH_ACTIVE; ++mpath->sn; spin_unlock_bh(&mpath->state_lock); - mesh_path_error_tx(MESH_TTL, mpath->dst, - cpu_to_le32(mpath->sn), + mesh_path_error_tx(sdata->u.mesh.mshcfg.element_ttl, + mpath->dst, cpu_to_le32(mpath->sn), cpu_to_le16(PERR_RCODE_DEST_UNREACH), bcast, sdata); } else @@ -614,7 +614,8 @@ void mesh_path_discard_frame(struct sk_buff *skb, mpath = mesh_path_lookup(da, sdata); if (mpath) sn = ++mpath->sn; - mesh_path_error_tx(MESH_TTL, skb->data, cpu_to_le32(sn), + mesh_path_error_tx(sdata->u.mesh.mshcfg.element_ttl, skb->data, + cpu_to_le32(sn), cpu_to_le16(PERR_RCODE_NO_ROUTE), ra, sdata); } diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 960be4e650f0..0b90cab5da2f 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -2582,6 +2582,8 @@ static int nl80211_get_mesh_params(struct sk_buff *skb, cur_params.dot11MeshMaxRetries); NLA_PUT_U8(msg, NL80211_MESHCONF_TTL, cur_params.dot11MeshTTL); + NLA_PUT_U8(msg, NL80211_MESHCONF_ELEMENT_TTL, + cur_params.element_ttl); NLA_PUT_U8(msg, NL80211_MESHCONF_AUTO_OPEN_PLINKS, cur_params.auto_open_plinks); NLA_PUT_U8(msg, NL80211_MESHCONF_HWMP_MAX_PREQ_RETRIES, @@ -2623,6 +2625,7 @@ static const struct nla_policy nl80211_meshconf_params_policy[NL80211_MESHCONF_A [NL80211_MESHCONF_MAX_PEER_LINKS] = { .type = NLA_U16 }, [NL80211_MESHCONF_MAX_RETRIES] = { .type = NLA_U8 }, [NL80211_MESHCONF_TTL] = { .type = NLA_U8 }, + [NL80211_MESHCONF_ELEMENT_TTL] = { .type = NLA_U8 }, [NL80211_MESHCONF_AUTO_OPEN_PLINKS] = { .type = NLA_U8 }, [NL80211_MESHCONF_HWMP_MAX_PREQ_RETRIES] = { .type = NLA_U8 }, @@ -2670,6 +2673,8 @@ static int nl80211_set_mesh_params(struct sk_buff *skb, struct genl_info *info) mask, NL80211_MESHCONF_MAX_RETRIES, nla_get_u8); FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshTTL, mask, NL80211_MESHCONF_TTL, nla_get_u8); + FILL_IN_MESH_PARAM_IF_SET(tb, cfg, element_ttl, + mask, NL80211_MESHCONF_ELEMENT_TTL, nla_get_u8); FILL_IN_MESH_PARAM_IF_SET(tb, cfg, auto_open_plinks, mask, NL80211_MESHCONF_AUTO_OPEN_PLINKS, nla_get_u8); FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshHWMPmaxPREQretries, -- cgit v1.2.3 From 29cbe68c516a48a9a88b3226878570c6cbd83c02 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 3 Dec 2010 09:20:44 +0100 Subject: cfg80211/mac80211: add mesh join/leave commands Instead of tying mesh activity to interface up, add join and leave commands for mesh. Since we must be backward compatible, let cfg80211 handle joining a mesh if a mesh ID was pre-configured when the device goes up. Note that this therefore must modify mac80211 as well since mac80211 needs to lose the logic to start the mesh on interface up. We now allow querying mesh parameters before the mesh is connected, which simply returns defaults. Setting them (internally renamed to "update") is only allowed while connected. Specify them with the new mesh join command instead where needed. In mac80211, beaconing must now also follow the mesh enabled/not enabled state, which is done by testing the mesh ID. Signed-off-by: Javier Cardona Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/linux/nl80211.h | 8 +++ include/net/cfg80211.h | 38 +++++++++--- net/mac80211/cfg.c | 39 ++++++++++--- net/mac80211/ieee80211_i.h | 13 ----- net/mac80211/iface.c | 14 +---- net/mac80211/main.c | 3 +- net/mac80211/mesh.c | 26 ++------- net/mac80211/mesh.h | 25 -------- net/wireless/Makefile | 2 +- net/wireless/core.c | 15 ++++- net/wireless/core.h | 13 +++++ net/wireless/mesh.c | 140 +++++++++++++++++++++++++++++++++++++++++++++ net/wireless/nl80211.c | 137 +++++++++++++++++++++++++++++++++++++------- net/wireless/util.c | 1 + 14 files changed, 359 insertions(+), 115 deletions(-) create mode 100644 net/wireless/mesh.c (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 9e541452d805..410a06ea551b 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -394,6 +394,11 @@ * * @NL80211_CMD_SET_WDS_PEER: Set the MAC address of the peer on a WDS interface. * + * @NL80211_CMD_JOIN_MESH: Join a mesh. The mesh ID must be given, and initial + * mesh config parameters may be given. + * @NL80211_CMD_LEAVE_MESH: Leave the mesh network -- no special arguments, the + * network is determined by the network interface. + * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use */ @@ -500,6 +505,9 @@ enum nl80211_commands { NL80211_CMD_FRAME_WAIT_CANCEL, + NL80211_CMD_JOIN_MESH, + NL80211_CMD_LEAVE_MESH, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 902895dfbd49..788c3989a9e8 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -258,13 +258,9 @@ struct ieee80211_supported_band { /** * struct vif_params - describes virtual interface parameters - * @mesh_id: mesh ID to use - * @mesh_id_len: length of the mesh ID * @use_4addr: use 4-address frames */ struct vif_params { - u8 *mesh_id; - int mesh_id_len; int use_4addr; }; @@ -615,6 +611,11 @@ struct bss_parameters { int ap_isolate; }; +/* + * struct mesh_config - 802.11s mesh configuration + * + * These parameters can be changed while the mesh is active. + */ struct mesh_config { /* Timeouts in ms */ /* Mesh plink management parameters */ @@ -637,6 +638,18 @@ struct mesh_config { u8 dot11MeshHWMPRootMode; }; +/** + * struct mesh_setup - 802.11s mesh setup configuration + * @mesh_id: the mesh ID + * @mesh_id_len: length of the mesh ID, at least 1 and at most 32 bytes + * + * These parameters are fixed when the mesh is created. + */ +struct mesh_setup { + const u8 *mesh_id; + u8 mesh_id_len; +}; + /** * struct ieee80211_txq_params - TX queue parameters * @queue: TX queue identifier (NL80211_TXQ_Q_*) @@ -1078,7 +1091,7 @@ struct cfg80211_pmksa { * * @get_mesh_params: Put the current mesh parameters into *params * - * @set_mesh_params: Set mesh parameters. + * @update_mesh_params: Update mesh parameters on a running mesh. * The mask is a bitfield which tells us which parameters to * set, and which to leave alone. * @@ -1229,9 +1242,14 @@ struct cfg80211_ops { int (*get_mesh_params)(struct wiphy *wiphy, struct net_device *dev, struct mesh_config *conf); - int (*set_mesh_params)(struct wiphy *wiphy, - struct net_device *dev, - const struct mesh_config *nconf, u32 mask); + int (*update_mesh_params)(struct wiphy *wiphy, + struct net_device *dev, u32 mask, + const struct mesh_config *nconf); + int (*join_mesh)(struct wiphy *wiphy, struct net_device *dev, + const struct mesh_config *conf, + const struct mesh_setup *setup); + int (*leave_mesh)(struct wiphy *wiphy, struct net_device *dev); + int (*change_bss)(struct wiphy *wiphy, struct net_device *dev, struct bss_parameters *params); @@ -1647,6 +1665,8 @@ struct cfg80211_cached_keys; * @bssid: (private) Used by the internal configuration code * @ssid: (private) Used by the internal configuration code * @ssid_len: (private) Used by the internal configuration code + * @mesh_id_len: (private) Used by the internal configuration code + * @mesh_id_up_len: (private) Used by the internal configuration code * @wext: (private) Used by the internal wireless extensions compat code * @use_4addr: indicates 4addr mode is used on this interface, must be * set by driver (if supported) on add_interface BEFORE registering the @@ -1676,7 +1696,7 @@ struct wireless_dev { /* currently used for IBSS and SME - might be rearranged later */ u8 ssid[IEEE80211_MAX_SSID_LEN]; - u8 ssid_len; + u8 ssid_len, mesh_id_len, mesh_id_up_len; enum { CFG80211_SME_IDLE, CFG80211_SME_CONNECTING, diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index d34c7c3dd762..68329d713c02 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -60,11 +60,6 @@ static int ieee80211_change_iface(struct wiphy *wiphy, if (ret) return ret; - if (ieee80211_vif_is_mesh(&sdata->vif) && params->mesh_id_len) - ieee80211_sdata_set_mesh_id(sdata, - params->mesh_id_len, - params->mesh_id); - if (type == NL80211_IFTYPE_AP_VLAN && params && params->use_4addr == 0) rcu_assign_pointer(sdata->u.vlan.sta, NULL); @@ -1003,9 +998,9 @@ static inline bool _chg_mesh_attr(enum nl80211_meshconf_params parm, u32 mask) return (mask >> (parm-1)) & 0x1; } -static int ieee80211_set_mesh_params(struct wiphy *wiphy, - struct net_device *dev, - const struct mesh_config *nconf, u32 mask) +static int ieee80211_update_mesh_params(struct wiphy *wiphy, + struct net_device *dev, u32 mask, + const struct mesh_config *nconf) { struct mesh_config *conf; struct ieee80211_sub_if_data *sdata; @@ -1056,6 +1051,30 @@ static int ieee80211_set_mesh_params(struct wiphy *wiphy, return 0; } +static int ieee80211_join_mesh(struct wiphy *wiphy, struct net_device *dev, + const struct mesh_config *conf, + const struct mesh_setup *setup) +{ + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; + + memcpy(&sdata->u.mesh.mshcfg, conf, sizeof(struct mesh_config)); + ifmsh->mesh_id_len = setup->mesh_id_len; + memcpy(ifmsh->mesh_id, setup->mesh_id, ifmsh->mesh_id_len); + + ieee80211_start_mesh(sdata); + + return 0; +} + +static int ieee80211_leave_mesh(struct wiphy *wiphy, struct net_device *dev) +{ + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + + ieee80211_stop_mesh(sdata); + + return 0; +} #endif static int ieee80211_change_bss(struct wiphy *wiphy, @@ -1760,8 +1779,10 @@ struct cfg80211_ops mac80211_config_ops = { .change_mpath = ieee80211_change_mpath, .get_mpath = ieee80211_get_mpath, .dump_mpath = ieee80211_dump_mpath, - .set_mesh_params = ieee80211_set_mesh_params, + .update_mesh_params = ieee80211_update_mesh_params, .get_mesh_params = ieee80211_get_mesh_params, + .join_mesh = ieee80211_join_mesh, + .leave_mesh = ieee80211_leave_mesh, #endif .change_bss = ieee80211_change_bss, .set_txq_params = ieee80211_set_txq_params, diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index e7c880725639..72499fe5fc36 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -609,19 +609,6 @@ struct ieee80211_sub_if_data *vif_to_sdata(struct ieee80211_vif *p) return container_of(p, struct ieee80211_sub_if_data, vif); } -static inline void -ieee80211_sdata_set_mesh_id(struct ieee80211_sub_if_data *sdata, - u8 mesh_id_len, u8 *mesh_id) -{ -#ifdef CONFIG_MAC80211_MESH - struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; - ifmsh->mesh_id_len = mesh_id_len; - memcpy(ifmsh->mesh_id, mesh_id, mesh_id_len); -#else - WARN_ON(1); -#endif -} - enum sdata_queue_type { IEEE80211_SDATA_QUEUE_TYPE_FRAME = 0, IEEE80211_SDATA_QUEUE_AGG_START = 1, diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 96e27f1e79fb..f0f11bb794af 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -268,9 +268,7 @@ static int ieee80211_do_open(struct net_device *dev, bool coming_up) goto err_stop; } - if (ieee80211_vif_is_mesh(&sdata->vif)) { - ieee80211_start_mesh(sdata); - } else if (sdata->vif.type == NL80211_IFTYPE_AP) { + if (sdata->vif.type == NL80211_IFTYPE_AP) { local->fif_pspoll++; local->fif_probe_req++; @@ -495,10 +493,6 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, ieee80211_adjust_monitor_flags(sdata, -1); ieee80211_configure_filter(local); break; - case NL80211_IFTYPE_MESH_POINT: - if (ieee80211_vif_is_mesh(&sdata->vif)) - ieee80211_stop_mesh(sdata); - /* fall through */ default: flush_work(&sdata->work); /* @@ -1188,12 +1182,6 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, if (ret) goto fail; - if (ieee80211_vif_is_mesh(&sdata->vif) && - params && params->mesh_id_len) - ieee80211_sdata_set_mesh_id(sdata, - params->mesh_id_len, - params->mesh_id); - mutex_lock(&local->iflist_mtx); list_add_tail_rcu(&sdata->list, &local->interfaces); mutex_unlock(&local->iflist_mtx); diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 107a0cbe52ac..2de69766c6aa 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -246,7 +246,8 @@ void ieee80211_bss_info_change_notify(struct ieee80211_sub_if_data *sdata, !!sdata->u.ibss.presp; break; case NL80211_IFTYPE_MESH_POINT: - sdata->vif.bss_conf.enable_beacon = true; + sdata->vif.bss_conf.enable_beacon = + !!sdata->u.mesh.mesh_id_len; break; default: /* not reached */ diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index 0d3234875ac5..63e1188d5062 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -530,6 +530,11 @@ void ieee80211_start_mesh(struct ieee80211_sub_if_data *sdata) void ieee80211_stop_mesh(struct ieee80211_sub_if_data *sdata) { struct ieee80211_local *local = sdata->local; + struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; + + ifmsh->mesh_id_len = 0; + ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON_ENABLED); + sta_info_flush(local, NULL); del_timer_sync(&sdata->u.mesh.housekeeping_timer); del_timer_sync(&sdata->u.mesh.mesh_path_root_timer); @@ -674,27 +679,6 @@ void ieee80211_mesh_init_sdata(struct ieee80211_sub_if_data *sdata) ieee80211_mesh_housekeeping_timer, (unsigned long) sdata); - ifmsh->mshcfg.dot11MeshRetryTimeout = MESH_RET_T; - ifmsh->mshcfg.dot11MeshConfirmTimeout = MESH_CONF_T; - ifmsh->mshcfg.dot11MeshHoldingTimeout = MESH_HOLD_T; - ifmsh->mshcfg.dot11MeshMaxRetries = MESH_MAX_RETR; - ifmsh->mshcfg.dot11MeshTTL = MESH_TTL; - ifmsh->mshcfg.element_ttl = MESH_DEFAULT_ELEMENT_TTL; - ifmsh->mshcfg.auto_open_plinks = true; - ifmsh->mshcfg.dot11MeshMaxPeerLinks = - MESH_MAX_ESTAB_PLINKS; - ifmsh->mshcfg.dot11MeshHWMPactivePathTimeout = - MESH_PATH_TIMEOUT; - ifmsh->mshcfg.dot11MeshHWMPpreqMinInterval = - MESH_PREQ_MIN_INT; - ifmsh->mshcfg.dot11MeshHWMPnetDiameterTraversalTime = - MESH_DIAM_TRAVERSAL_TIME; - ifmsh->mshcfg.dot11MeshHWMPmaxPREQretries = - MESH_MAX_PREQ_RETRIES; - ifmsh->mshcfg.path_refresh_time = - MESH_PATH_REFRESH_TIME; - ifmsh->mshcfg.min_discovery_timeout = - MESH_MIN_DISCOVERY_TIMEOUT; ifmsh->accepting_plinks = true; ifmsh->preq_id = 0; ifmsh->sn = 0; diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h index 182942eeac4d..039d7fa0af74 100644 --- a/net/mac80211/mesh.h +++ b/net/mac80211/mesh.h @@ -175,33 +175,10 @@ struct mesh_rmc { */ #define MESH_CFG_CMP_LEN (IEEE80211_MESH_CONFIG_LEN - 2) -/* Default values, timeouts in ms */ -#define MESH_TTL 31 -#define MESH_MAX_RETR 3 -#define MESH_RET_T 100 -#define MESH_CONF_T 100 -#define MESH_HOLD_T 100 - -#define MESH_PATH_TIMEOUT 5000 -/* Minimum interval between two consecutive PREQs originated by the same - * interface - */ -#define MESH_PREQ_MIN_INT 10 -#define MESH_DIAM_TRAVERSAL_TIME 50 -/* A path will be refreshed if it is used PATH_REFRESH_TIME milliseconds before - * timing out. This way it will remain ACTIVE and no data frames will be - * unnecesarily held in the pending queue. - */ -#define MESH_PATH_REFRESH_TIME 1000 -#define MESH_MIN_DISCOVERY_TIMEOUT (2 * MESH_DIAM_TRAVERSAL_TIME) #define MESH_DEFAULT_BEACON_INTERVAL 1000 /* in 1024 us units */ -#define MESH_MAX_PREQ_RETRIES 4 #define MESH_PATH_EXPIRE (600 * HZ) -/* Default maximum number of established plinks per interface */ -#define MESH_MAX_ESTAB_PLINKS 32 - /* Default maximum number of plinks per interface */ #define MESH_MAX_PLINKS 256 @@ -216,8 +193,6 @@ struct mesh_rmc { #define PERR_RCODE_NO_ROUTE 12 #define PERR_RCODE_DEST_UNREACH 13 -#define MESH_DEFAULT_ELEMENT_TTL 31 - /* Public interfaces */ /* Various */ int ieee80211_fill_mesh_addresses(struct ieee80211_hdr *hdr, __le16 *fc, diff --git a/net/wireless/Makefile b/net/wireless/Makefile index e77e508126fa..55a28ab21db9 100644 --- a/net/wireless/Makefile +++ b/net/wireless/Makefile @@ -10,7 +10,7 @@ obj-$(CONFIG_WEXT_SPY) += wext-spy.o obj-$(CONFIG_WEXT_PRIV) += wext-priv.o cfg80211-y += core.o sysfs.o radiotap.o util.o reg.o scan.o nl80211.o -cfg80211-y += mlme.o ibss.o sme.o chan.o ethtool.o +cfg80211-y += mlme.o ibss.o sme.o chan.o ethtool.o mesh.o cfg80211-$(CONFIG_CFG80211_DEBUGFS) += debugfs.o cfg80211-$(CONFIG_CFG80211_WEXT) += wext-compat.o wext-sme.o cfg80211-$(CONFIG_CFG80211_INTERNAL_REGDB) += regdb.o diff --git a/net/wireless/core.c b/net/wireless/core.c index 630bcf0a2f04..79772fcc37bc 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -332,6 +332,7 @@ struct wiphy *wiphy_new(const struct cfg80211_ops *ops, int sizeof_priv) WARN_ON(ops->add_virtual_intf && !ops->del_virtual_intf); WARN_ON(ops->add_station && !ops->del_station); WARN_ON(ops->add_mpath && !ops->del_mpath); + WARN_ON(ops->join_mesh && !ops->leave_mesh); alloc_size = sizeof(*rdev) + sizeof_priv; @@ -752,6 +753,9 @@ static int cfg80211_netdev_notifier_call(struct notifier_block * nb, cfg80211_mlme_down(rdev, dev); wdev_unlock(wdev); break; + case NL80211_IFTYPE_MESH_POINT: + cfg80211_leave_mesh(rdev, dev); + break; default: break; } @@ -775,20 +779,27 @@ static int cfg80211_netdev_notifier_call(struct notifier_block * nb, } cfg80211_lock_rdev(rdev); mutex_lock(&rdev->devlist_mtx); -#ifdef CONFIG_CFG80211_WEXT wdev_lock(wdev); switch (wdev->iftype) { +#ifdef CONFIG_CFG80211_WEXT case NL80211_IFTYPE_ADHOC: cfg80211_ibss_wext_join(rdev, wdev); break; case NL80211_IFTYPE_STATION: cfg80211_mgd_wext_connect(rdev, wdev); break; +#endif + case NL80211_IFTYPE_MESH_POINT: + /* backward compat code ... */ + if (wdev->mesh_id_up_len) + __cfg80211_join_mesh(rdev, dev, wdev->ssid, + wdev->mesh_id_up_len, + &default_mesh_config); + break; default: break; } wdev_unlock(wdev); -#endif rdev->opencount++; mutex_unlock(&rdev->devlist_mtx); cfg80211_unlock_rdev(rdev); diff --git a/net/wireless/core.h b/net/wireless/core.h index ee80ad8dc655..743203bb61ac 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -285,6 +285,19 @@ void __cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid); int cfg80211_ibss_wext_join(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev); +/* mesh */ +extern const struct mesh_config default_mesh_config; +int __cfg80211_join_mesh(struct cfg80211_registered_device *rdev, + struct net_device *dev, + const u8 *mesh_id, u8 mesh_id_len, + const struct mesh_config *conf); +int cfg80211_join_mesh(struct cfg80211_registered_device *rdev, + struct net_device *dev, + const u8 *mesh_id, u8 mesh_id_len, + const struct mesh_config *conf); +int cfg80211_leave_mesh(struct cfg80211_registered_device *rdev, + struct net_device *dev); + /* MLME */ int __cfg80211_mlme_auth(struct cfg80211_registered_device *rdev, struct net_device *dev, diff --git a/net/wireless/mesh.c b/net/wireless/mesh.c new file mode 100644 index 000000000000..e0b9747fe50a --- /dev/null +++ b/net/wireless/mesh.c @@ -0,0 +1,140 @@ +#include +#include +#include "core.h" + +/* Default values, timeouts in ms */ +#define MESH_TTL 31 +#define MESH_DEFAULT_ELEMENT_TTL 31 +#define MESH_MAX_RETR 3 +#define MESH_RET_T 100 +#define MESH_CONF_T 100 +#define MESH_HOLD_T 100 + +#define MESH_PATH_TIMEOUT 5000 + +/* + * Minimum interval between two consecutive PREQs originated by the same + * interface + */ +#define MESH_PREQ_MIN_INT 10 +#define MESH_DIAM_TRAVERSAL_TIME 50 + +/* + * A path will be refreshed if it is used PATH_REFRESH_TIME milliseconds + * before timing out. This way it will remain ACTIVE and no data frames + * will be unnecessarily held in the pending queue. + */ +#define MESH_PATH_REFRESH_TIME 1000 +#define MESH_MIN_DISCOVERY_TIMEOUT (2 * MESH_DIAM_TRAVERSAL_TIME) + +/* Default maximum number of established plinks per interface */ +#define MESH_MAX_ESTAB_PLINKS 32 + +#define MESH_MAX_PREQ_RETRIES 4 + + +const struct mesh_config default_mesh_config = { + .dot11MeshRetryTimeout = MESH_RET_T, + .dot11MeshConfirmTimeout = MESH_CONF_T, + .dot11MeshHoldingTimeout = MESH_HOLD_T, + .dot11MeshMaxRetries = MESH_MAX_RETR, + .dot11MeshTTL = MESH_TTL, + .element_ttl = MESH_DEFAULT_ELEMENT_TTL, + .auto_open_plinks = true, + .dot11MeshMaxPeerLinks = MESH_MAX_ESTAB_PLINKS, + .dot11MeshHWMPactivePathTimeout = MESH_PATH_TIMEOUT, + .dot11MeshHWMPpreqMinInterval = MESH_PREQ_MIN_INT, + .dot11MeshHWMPnetDiameterTraversalTime = MESH_DIAM_TRAVERSAL_TIME, + .dot11MeshHWMPmaxPREQretries = MESH_MAX_PREQ_RETRIES, + .path_refresh_time = MESH_PATH_REFRESH_TIME, + .min_discovery_timeout = MESH_MIN_DISCOVERY_TIMEOUT, +}; + + +int __cfg80211_join_mesh(struct cfg80211_registered_device *rdev, + struct net_device *dev, + const u8 *mesh_id, u8 mesh_id_len, + const struct mesh_config *conf) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct mesh_setup setup = { + .mesh_id = mesh_id, + .mesh_id_len = mesh_id_len, + }; + int err; + + BUILD_BUG_ON(IEEE80211_MAX_SSID_LEN != IEEE80211_MAX_MESH_ID_LEN); + + ASSERT_WDEV_LOCK(wdev); + + if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_MESH_POINT) + return -EOPNOTSUPP; + + if (wdev->mesh_id_len) + return -EALREADY; + + if (!mesh_id_len) + return -EINVAL; + + if (!rdev->ops->join_mesh) + return -EOPNOTSUPP; + + err = rdev->ops->join_mesh(&rdev->wiphy, dev, conf, &setup); + if (!err) { + memcpy(wdev->ssid, mesh_id, mesh_id_len); + wdev->mesh_id_len = mesh_id_len; + } + + return err; +} + +int cfg80211_join_mesh(struct cfg80211_registered_device *rdev, + struct net_device *dev, + const u8 *mesh_id, u8 mesh_id_len, + const struct mesh_config *conf) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + int err; + + wdev_lock(wdev); + err = __cfg80211_join_mesh(rdev, dev, mesh_id, mesh_id_len, conf); + wdev_unlock(wdev); + + return err; +} + +static int __cfg80211_leave_mesh(struct cfg80211_registered_device *rdev, + struct net_device *dev) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + int err; + + ASSERT_WDEV_LOCK(wdev); + + if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_MESH_POINT) + return -EOPNOTSUPP; + + if (!rdev->ops->leave_mesh) + return -EOPNOTSUPP; + + if (!wdev->mesh_id_len) + return -ENOTCONN; + + err = rdev->ops->leave_mesh(&rdev->wiphy, dev); + if (!err) + wdev->mesh_id_len = 0; + return err; +} + +int cfg80211_leave_mesh(struct cfg80211_registered_device *rdev, + struct net_device *dev) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + int err; + + wdev_lock(wdev); + err = __cfg80211_leave_mesh(rdev, dev); + wdev_unlock(wdev); + + return err; +} diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index c8d4d53fc450..56508d40c740 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -661,13 +661,14 @@ static int nl80211_send_wiphy(struct sk_buff *msg, u32 pid, u32 seq, int flags, CMD(add_beacon, NEW_BEACON); CMD(add_station, NEW_STATION); CMD(add_mpath, NEW_MPATH); - CMD(set_mesh_params, SET_MESH_PARAMS); + CMD(update_mesh_params, SET_MESH_PARAMS); CMD(change_bss, SET_BSS); CMD(auth, AUTHENTICATE); CMD(assoc, ASSOCIATE); CMD(deauth, DEAUTHENTICATE); CMD(disassoc, DISASSOCIATE); CMD(join_ibss, JOIN_IBSS); + CMD(join_mesh, JOIN_MESH); CMD(set_pmksa, SET_PMKSA); CMD(del_pmksa, DEL_PMKSA); CMD(flush_pmksa, FLUSH_PMKSA); @@ -1324,11 +1325,21 @@ static int nl80211_set_interface(struct sk_buff *skb, struct genl_info *info) } if (info->attrs[NL80211_ATTR_MESH_ID]) { + struct wireless_dev *wdev = dev->ieee80211_ptr; + if (ntype != NL80211_IFTYPE_MESH_POINT) return -EINVAL; - params.mesh_id = nla_data(info->attrs[NL80211_ATTR_MESH_ID]); - params.mesh_id_len = nla_len(info->attrs[NL80211_ATTR_MESH_ID]); - change = true; + if (netif_running(dev)) + return -EBUSY; + + wdev_lock(wdev); + BUILD_BUG_ON(IEEE80211_MAX_SSID_LEN != + IEEE80211_MAX_MESH_ID_LEN); + wdev->mesh_id_up_len = + nla_len(info->attrs[NL80211_ATTR_MESH_ID]); + memcpy(wdev->ssid, nla_data(info->attrs[NL80211_ATTR_MESH_ID]), + wdev->mesh_id_up_len); + wdev_unlock(wdev); } if (info->attrs[NL80211_ATTR_4ADDR]) { @@ -1388,12 +1399,6 @@ static int nl80211_new_interface(struct sk_buff *skb, struct genl_info *info) !(rdev->wiphy.interface_modes & (1 << type))) return -EOPNOTSUPP; - if (type == NL80211_IFTYPE_MESH_POINT && - info->attrs[NL80211_ATTR_MESH_ID]) { - params.mesh_id = nla_data(info->attrs[NL80211_ATTR_MESH_ID]); - params.mesh_id_len = nla_len(info->attrs[NL80211_ATTR_MESH_ID]); - } - if (info->attrs[NL80211_ATTR_4ADDR]) { params.use_4addr = !!nla_get_u8(info->attrs[NL80211_ATTR_4ADDR]); err = nl80211_valid_4addr(rdev, NULL, params.use_4addr, type); @@ -1410,6 +1415,20 @@ static int nl80211_new_interface(struct sk_buff *skb, struct genl_info *info) if (IS_ERR(dev)) return PTR_ERR(dev); + if (type == NL80211_IFTYPE_MESH_POINT && + info->attrs[NL80211_ATTR_MESH_ID]) { + struct wireless_dev *wdev = dev->ieee80211_ptr; + + wdev_lock(wdev); + BUILD_BUG_ON(IEEE80211_MAX_SSID_LEN != + IEEE80211_MAX_MESH_ID_LEN); + wdev->mesh_id_up_len = + nla_len(info->attrs[NL80211_ATTR_MESH_ID]); + memcpy(wdev->ssid, nla_data(info->attrs[NL80211_ATTR_MESH_ID]), + wdev->mesh_id_up_len); + wdev_unlock(wdev); + } + return 0; } @@ -2543,21 +2562,32 @@ static int nl80211_req_set_reg(struct sk_buff *skb, struct genl_info *info) } static int nl80211_get_mesh_params(struct sk_buff *skb, - struct genl_info *info) + struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; - struct mesh_config cur_params; - int err; struct net_device *dev = info->user_ptr[1]; + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct mesh_config cur_params; + int err = 0; void *hdr; struct nlattr *pinfoattr; struct sk_buff *msg; + if (wdev->iftype != NL80211_IFTYPE_MESH_POINT) + return -EOPNOTSUPP; + if (!rdev->ops->get_mesh_params) return -EOPNOTSUPP; - /* Get the mesh params */ - err = rdev->ops->get_mesh_params(&rdev->wiphy, dev, &cur_params); + wdev_lock(wdev); + /* If not connected, get default parameters */ + if (!wdev->mesh_id_len) + memcpy(&cur_params, &default_mesh_config, sizeof(cur_params)); + else + err = rdev->ops->get_mesh_params(&rdev->wiphy, dev, + &cur_params); + wdev_unlock(wdev); + if (err) return err; @@ -2705,23 +2735,37 @@ do {\ #undef FILL_IN_MESH_PARAM_IF_SET } -static int nl80211_set_mesh_params(struct sk_buff *skb, struct genl_info *info) +static int nl80211_update_mesh_params(struct sk_buff *skb, + struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; + struct wireless_dev *wdev = dev->ieee80211_ptr; struct mesh_config cfg; u32 mask; int err; - if (!rdev->ops->set_mesh_params) + if (wdev->iftype != NL80211_IFTYPE_MESH_POINT) + return -EOPNOTSUPP; + + if (!rdev->ops->update_mesh_params) return -EOPNOTSUPP; err = nl80211_parse_mesh_params(info, &cfg, &mask); if (err) return err; - /* Apply changes */ - return rdev->ops->set_mesh_params(&rdev->wiphy, dev, &cfg, mask); + wdev_lock(wdev); + if (!wdev->mesh_id_len) + err = -ENOLINK; + + if (!err) + err = rdev->ops->update_mesh_params(&rdev->wiphy, dev, + mask, &cfg); + + wdev_unlock(wdev); + + return err; } static int nl80211_get_reg(struct sk_buff *skb, struct genl_info *info) @@ -4505,6 +4549,41 @@ out: return err; } +static int nl80211_join_mesh(struct sk_buff *skb, struct genl_info *info) +{ + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; + struct mesh_config cfg; + int err; + + /* start with default */ + memcpy(&cfg, &default_mesh_config, sizeof(cfg)); + + if (info->attrs[NL80211_ATTR_MESH_PARAMS]) { + /* and parse parameters if given */ + err = nl80211_parse_mesh_params(info, &cfg, NULL); + if (err) + return err; + } + + if (!info->attrs[NL80211_ATTR_MESH_ID] || + !nla_len(info->attrs[NL80211_ATTR_MESH_ID])) + return -EINVAL; + + return cfg80211_join_mesh(rdev, dev, + nla_data(info->attrs[NL80211_ATTR_MESH_ID]), + nla_len(info->attrs[NL80211_ATTR_MESH_ID]), + &cfg); +} + +static int nl80211_leave_mesh(struct sk_buff *skb, struct genl_info *info) +{ + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; + + return cfg80211_leave_mesh(rdev, dev); +} + #define NL80211_FLAG_NEED_WIPHY 0x01 #define NL80211_FLAG_NEED_NETDEV 0x02 #define NL80211_FLAG_NEED_RTNL 0x04 @@ -4769,10 +4848,10 @@ static struct genl_ops nl80211_ops[] = { }, { .cmd = NL80211_CMD_SET_MESH_PARAMS, - .doit = nl80211_set_mesh_params, + .doit = nl80211_update_mesh_params, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV | + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, }, { @@ -4987,6 +5066,22 @@ static struct genl_ops nl80211_ops[] = { .internal_flags = NL80211_FLAG_NEED_NETDEV | NL80211_FLAG_NEED_RTNL, }, + { + .cmd = NL80211_CMD_JOIN_MESH, + .doit = nl80211_join_mesh, + .policy = nl80211_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | + NL80211_FLAG_NEED_RTNL, + }, + { + .cmd = NL80211_CMD_LEAVE_MESH, + .doit = nl80211_leave_mesh, + .policy = nl80211_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | + NL80211_FLAG_NEED_RTNL, + }, }; static struct genl_multicast_group nl80211_mlme_mcgrp = { diff --git a/net/wireless/util.c b/net/wireless/util.c index fee020b15a4e..4de624ca4c63 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -792,6 +792,7 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev, if (ntype != otype) { dev->ieee80211_ptr->use_4addr = false; + dev->ieee80211_ptr->mesh_id_up_len = 0; switch (otype) { case NL80211_IFTYPE_ADHOC: -- cgit v1.2.3 From 871a2c16c21b988688b4ab1a78eadd969765c0a3 Mon Sep 17 00:00:00 2001 From: Tomasz Grobelny Date: Sat, 4 Dec 2010 13:38:01 +0100 Subject: dccp: Policy-based packet dequeueing infrastructure This patch adds a generic infrastructure for policy-based dequeueing of TX packets and provides two policies: * a simple FIFO policy (which is the default) and * a priority based policy (set via socket options). Both policies honour the tx_qlen sysctl for the maximum size of the write queue (can be overridden via socket options). The priority policy uses skb->priority internally to assign an u32 priority identifier, using the same ranking as SO_PRIORITY. The skb->priority field is set to 0 when the packet leaves DCCP. The priority is supplied as ancillary data using cmsg(3), the patch also provides the requisite parsing routines. Signed-off-by: Tomasz Grobelny Signed-off-by: Gerrit Renker --- Documentation/networking/dccp.txt | 20 ++++++ include/linux/dccp.h | 21 +++++++ net/dccp/Makefile | 4 +- net/dccp/dccp.h | 12 ++++ net/dccp/output.c | 7 +-- net/dccp/proto.c | 67 +++++++++++++++++++- net/dccp/qpolicy.c | 126 ++++++++++++++++++++++++++++++++++++++ 7 files changed, 248 insertions(+), 9 deletions(-) create mode 100644 net/dccp/qpolicy.c (limited to 'include/linux') diff --git a/Documentation/networking/dccp.txt b/Documentation/networking/dccp.txt index 271d524a4c8d..b395ca6a49f2 100644 --- a/Documentation/networking/dccp.txt +++ b/Documentation/networking/dccp.txt @@ -47,6 +47,26 @@ http://linux-net.osdl.org/index.php/DCCP_Testing#Experimental_DCCP_source_tree Socket options ============== +DCCP_SOCKOPT_QPOLICY_ID sets the dequeuing policy for outgoing packets. It takes +a policy ID as argument and can only be set before the connection (i.e. changes +during an established connection are not supported). Currently, two policies are +defined: the "simple" policy (DCCPQ_POLICY_SIMPLE), which does nothing special, +and a priority-based variant (DCCPQ_POLICY_PRIO). The latter allows to pass an +u32 priority value as ancillary data to sendmsg(), where higher numbers indicate +a higher packet priority (similar to SO_PRIORITY). This ancillary data needs to +be formatted using a cmsg(3) message header filled in as follows: + cmsg->cmsg_level = SOL_DCCP; + cmsg->cmsg_type = DCCP_SCM_PRIORITY; + cmsg->cmsg_len = CMSG_LEN(sizeof(uint32_t)); /* or CMSG_LEN(4) */ + +DCCP_SOCKOPT_QPOLICY_TXQLEN sets the maximum length of the output queue. A zero +value is always interpreted as unbounded queue length. If different from zero, +the interpretation of this parameter depends on the current dequeuing policy +(see above): the "simple" policy will enforce a fixed queue size by returning +EAGAIN, whereas the "prio" policy enforces a fixed queue length by dropping the +lowest-priority packet first. The default value for this parameter is +initialised from /proc/sys/net/dccp/default/tx_qlen. + DCCP_SOCKOPT_SERVICE sets the service. The specification mandates use of service codes (RFC 4340, sec. 8.1.2); if this socket option is not set, the socket will fall back to 0 (which means that no meaningful service code diff --git a/include/linux/dccp.h b/include/linux/dccp.h index eed52bcd35d0..010e2d87ed75 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -197,6 +197,21 @@ enum dccp_feature_numbers { DCCPF_MAX_CCID_SPECIFIC = 255, }; +/* DCCP socket control message types for cmsg */ +enum dccp_cmsg_type { + DCCP_SCM_PRIORITY = 1, + DCCP_SCM_QPOLICY_MAX = 0xFFFF, + /* ^-- Up to here reserved exclusively for qpolicy parameters */ + DCCP_SCM_MAX +}; + +/* DCCP priorities for outgoing/queued packets */ +enum dccp_packet_dequeueing_policy { + DCCPQ_POLICY_SIMPLE, + DCCPQ_POLICY_PRIO, + DCCPQ_POLICY_MAX +}; + /* DCCP socket options */ #define DCCP_SOCKOPT_PACKET_SIZE 1 /* XXX deprecated, without effect */ #define DCCP_SOCKOPT_SERVICE 2 @@ -210,6 +225,8 @@ enum dccp_feature_numbers { #define DCCP_SOCKOPT_CCID 13 #define DCCP_SOCKOPT_TX_CCID 14 #define DCCP_SOCKOPT_RX_CCID 15 +#define DCCP_SOCKOPT_QPOLICY_ID 16 +#define DCCP_SOCKOPT_QPOLICY_TXQLEN 17 #define DCCP_SOCKOPT_CCID_RX_INFO 128 #define DCCP_SOCKOPT_CCID_TX_INFO 192 @@ -458,6 +475,8 @@ struct dccp_ackvec; * @dccps_hc_rx_ccid - CCID used for the receiver (or receiving half-connection) * @dccps_hc_tx_ccid - CCID used for the sender (or sending half-connection) * @dccps_options_received - parsed set of retrieved options + * @dccps_qpolicy - TX dequeueing policy, one of %dccp_packet_dequeueing_policy + * @dccps_tx_qlen - maximum length of the TX queue * @dccps_role - role of this sock, one of %dccp_role * @dccps_hc_rx_insert_options - receiver wants to add options when acking * @dccps_hc_tx_insert_options - sender wants to add options when sending @@ -500,6 +519,8 @@ struct dccp_sock { struct ccid *dccps_hc_rx_ccid; struct ccid *dccps_hc_tx_ccid; struct dccp_options_received dccps_options_received; + __u8 dccps_qpolicy; + __u32 dccps_tx_qlen; enum dccp_role dccps_role:2; __u8 dccps_hc_rx_insert_options:1; __u8 dccps_hc_tx_insert_options:1; diff --git a/net/dccp/Makefile b/net/dccp/Makefile index 2991efcc8dea..5c8362b037ed 100644 --- a/net/dccp/Makefile +++ b/net/dccp/Makefile @@ -1,7 +1,7 @@ obj-$(CONFIG_IP_DCCP) += dccp.o dccp_ipv4.o -dccp-y := ccid.o feat.o input.o minisocks.o options.o output.o proto.o timer.o - +dccp-y := ccid.o feat.o input.o minisocks.o options.o output.o proto.o timer.o \ + qpolicy.o # # CCID algorithms to be used by dccp.ko # diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index 19fafd597465..d008da91cec2 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -243,6 +243,18 @@ extern void dccp_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, extern void dccp_send_sync(struct sock *sk, const u64 seq, const enum dccp_pkt_type pkt_type); +/* + * TX Packet Dequeueing Interface + */ +extern void dccp_qpolicy_push(struct sock *sk, struct sk_buff *skb); +extern bool dccp_qpolicy_full(struct sock *sk); +extern void dccp_qpolicy_drop(struct sock *sk, struct sk_buff *skb); +extern struct sk_buff *dccp_qpolicy_top(struct sock *sk); +extern struct sk_buff *dccp_qpolicy_pop(struct sock *sk); + +/* + * TX Packet Output and TX Timers + */ extern void dccp_write_xmit(struct sock *sk); extern void dccp_write_space(struct sock *sk); extern void dccp_flush_write_queue(struct sock *sk, long *time_budget); diff --git a/net/dccp/output.c b/net/dccp/output.c index d96dd9d362ae..784d30210543 100644 --- a/net/dccp/output.c +++ b/net/dccp/output.c @@ -242,7 +242,7 @@ static void dccp_xmit_packet(struct sock *sk) { int err, len; struct dccp_sock *dp = dccp_sk(sk); - struct sk_buff *skb = skb_dequeue(&sk->sk_write_queue); + struct sk_buff *skb = dccp_qpolicy_pop(sk); if (unlikely(skb == NULL)) return; @@ -345,7 +345,7 @@ void dccp_write_xmit(struct sock *sk) struct dccp_sock *dp = dccp_sk(sk); struct sk_buff *skb; - while ((skb = skb_peek(&sk->sk_write_queue))) { + while ((skb = dccp_qpolicy_top(sk))) { int rc = ccid_hc_tx_send_packet(dp->dccps_hc_tx_ccid, sk, skb); switch (ccid_packet_dequeue_eval(rc)) { @@ -359,8 +359,7 @@ void dccp_write_xmit(struct sock *sk) dccp_xmit_packet(sk); break; case CCID_PACKET_ERR: - skb_dequeue(&sk->sk_write_queue); - kfree_skb(skb); + dccp_qpolicy_drop(sk, skb); dccp_pr_debug("packet discarded due to err=%d\n", rc); } } diff --git a/net/dccp/proto.c b/net/dccp/proto.c index ef343d53fcea..d6a224982bb5 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -185,6 +185,7 @@ int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized) dp->dccps_role = DCCP_ROLE_UNDEFINED; dp->dccps_service = DCCP_SERVICE_CODE_IS_ABSENT; dp->dccps_l_ack_ratio = dp->dccps_r_ack_ratio = 1; + dp->dccps_tx_qlen = sysctl_dccp_tx_qlen; dccp_init_xmit_timers(sk); @@ -532,6 +533,20 @@ static int do_dccp_setsockopt(struct sock *sk, int level, int optname, case DCCP_SOCKOPT_RECV_CSCOV: err = dccp_setsockopt_cscov(sk, val, true); break; + case DCCP_SOCKOPT_QPOLICY_ID: + if (sk->sk_state != DCCP_CLOSED) + err = -EISCONN; + else if (val < 0 || val >= DCCPQ_POLICY_MAX) + err = -EINVAL; + else + dp->dccps_qpolicy = val; + break; + case DCCP_SOCKOPT_QPOLICY_TXQLEN: + if (val < 0) + err = -EINVAL; + else + dp->dccps_tx_qlen = val; + break; default: err = -ENOPROTOOPT; break; @@ -639,6 +654,12 @@ static int do_dccp_getsockopt(struct sock *sk, int level, int optname, case DCCP_SOCKOPT_RECV_CSCOV: val = dp->dccps_pcrlen; break; + case DCCP_SOCKOPT_QPOLICY_ID: + val = dp->dccps_qpolicy; + break; + case DCCP_SOCKOPT_QPOLICY_TXQLEN: + val = dp->dccps_tx_qlen; + break; case 128 ... 191: return ccid_hc_rx_getsockopt(dp->dccps_hc_rx_ccid, sk, optname, len, (u32 __user *)optval, optlen); @@ -681,6 +702,43 @@ int compat_dccp_getsockopt(struct sock *sk, int level, int optname, EXPORT_SYMBOL_GPL(compat_dccp_getsockopt); #endif +static int dccp_msghdr_parse(struct msghdr *msg, struct sk_buff *skb) +{ + struct cmsghdr *cmsg = CMSG_FIRSTHDR(msg); + + /* + * Assign an (opaque) qpolicy priority value to skb->priority. + * + * We are overloading this skb field for use with the qpolicy subystem. + * The skb->priority is normally used for the SO_PRIORITY option, which + * is initialised from sk_priority. Since the assignment of sk_priority + * to skb->priority happens later (on layer 3), we overload this field + * for use with queueing priorities as long as the skb is on layer 4. + * The default priority value (if nothing is set) is 0. + */ + skb->priority = 0; + + for (; cmsg != NULL; cmsg = CMSG_NXTHDR(msg, cmsg)) { + + if (!CMSG_OK(msg, cmsg)) + return -EINVAL; + + if (cmsg->cmsg_level != SOL_DCCP) + continue; + + switch (cmsg->cmsg_type) { + case DCCP_SCM_PRIORITY: + if (cmsg->cmsg_len != CMSG_LEN(sizeof(__u32))) + return -EINVAL; + skb->priority = *(__u32 *)CMSG_DATA(cmsg); + break; + default: + return -EINVAL; + } + } + return 0; +} + int dccp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t len) { @@ -696,8 +754,7 @@ int dccp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, lock_sock(sk); - if (sysctl_dccp_tx_qlen && - (sk->sk_write_queue.qlen >= sysctl_dccp_tx_qlen)) { + if (dccp_qpolicy_full(sk)) { rc = -EAGAIN; goto out_release; } @@ -725,7 +782,11 @@ int dccp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, if (rc != 0) goto out_discard; - skb_queue_tail(&sk->sk_write_queue, skb); + rc = dccp_msghdr_parse(msg, skb); + if (rc != 0) + goto out_discard; + + dccp_qpolicy_push(sk, skb); /* * The xmit_timer is set if the TX CCID is rate-based and will expire * when congestion control permits to release further packets into the diff --git a/net/dccp/qpolicy.c b/net/dccp/qpolicy.c new file mode 100644 index 000000000000..4b0fd6b11f6d --- /dev/null +++ b/net/dccp/qpolicy.c @@ -0,0 +1,126 @@ +/* + * net/dccp/qpolicy.c + * + * Policy-based packet dequeueing interface for DCCP. + * + * Copyright (c) 2008 Tomasz Grobelny + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License v2 + * as published by the Free Software Foundation. + */ +#include "dccp.h" + +/* + * Simple Dequeueing Policy: + * If tx_qlen is different from 0, enqueue up to tx_qlen elements. + */ +static void qpolicy_simple_push(struct sock *sk, struct sk_buff *skb) +{ + skb_queue_tail(&sk->sk_write_queue, skb); +} + +static bool qpolicy_simple_full(struct sock *sk) +{ + return dccp_sk(sk)->dccps_tx_qlen && + sk->sk_write_queue.qlen >= dccp_sk(sk)->dccps_tx_qlen; +} + +static struct sk_buff *qpolicy_simple_top(struct sock *sk) +{ + return skb_peek(&sk->sk_write_queue); +} + +/* + * Priority-based Dequeueing Policy: + * If tx_qlen is different from 0 and the queue has reached its upper bound + * of tx_qlen elements, replace older packets lowest-priority-first. + */ +static struct sk_buff *qpolicy_prio_best_skb(struct sock *sk) +{ + struct sk_buff *skb, *best = NULL; + + skb_queue_walk(&sk->sk_write_queue, skb) + if (best == NULL || skb->priority > best->priority) + best = skb; + return best; +} + +static struct sk_buff *qpolicy_prio_worst_skb(struct sock *sk) +{ + struct sk_buff *skb, *worst = NULL; + + skb_queue_walk(&sk->sk_write_queue, skb) + if (worst == NULL || skb->priority < worst->priority) + worst = skb; + return worst; +} + +static bool qpolicy_prio_full(struct sock *sk) +{ + if (qpolicy_simple_full(sk)) + dccp_qpolicy_drop(sk, qpolicy_prio_worst_skb(sk)); + return false; +} + +/** + * struct dccp_qpolicy_operations - TX Packet Dequeueing Interface + * @push: add a new @skb to the write queue + * @full: indicates that no more packets will be admitted + * @top: peeks at whatever the queueing policy defines as its `top' + */ +static struct dccp_qpolicy_operations { + void (*push) (struct sock *sk, struct sk_buff *skb); + bool (*full) (struct sock *sk); + struct sk_buff* (*top) (struct sock *sk); + +} qpol_table[DCCPQ_POLICY_MAX] = { + [DCCPQ_POLICY_SIMPLE] = { + .push = qpolicy_simple_push, + .full = qpolicy_simple_full, + .top = qpolicy_simple_top, + }, + [DCCPQ_POLICY_PRIO] = { + .push = qpolicy_simple_push, + .full = qpolicy_prio_full, + .top = qpolicy_prio_best_skb, + }, +}; + +/* + * Externally visible interface + */ +void dccp_qpolicy_push(struct sock *sk, struct sk_buff *skb) +{ + qpol_table[dccp_sk(sk)->dccps_qpolicy].push(sk, skb); +} + +bool dccp_qpolicy_full(struct sock *sk) +{ + return qpol_table[dccp_sk(sk)->dccps_qpolicy].full(sk); +} + +void dccp_qpolicy_drop(struct sock *sk, struct sk_buff *skb) +{ + if (skb != NULL) { + skb_unlink(skb, &sk->sk_write_queue); + kfree_skb(skb); + } +} + +struct sk_buff *dccp_qpolicy_top(struct sock *sk) +{ + return qpol_table[dccp_sk(sk)->dccps_qpolicy].top(sk); +} + +struct sk_buff *dccp_qpolicy_pop(struct sock *sk) +{ + struct sk_buff *skb = dccp_qpolicy_top(sk); + + if (skb != NULL) { + /* Clear any skb fields that we used internally */ + skb->priority = 0; + skb_unlink(skb, &sk->sk_write_queue); + } + return skb; +} -- cgit v1.2.3 From 541a45a142df281c974d74eac2066138fc107b23 Mon Sep 17 00:00:00 2001 From: Bruno Randolf Date: Thu, 2 Dec 2010 19:12:43 +0900 Subject: nl80211/mac80211: Report signal average Extend nl80211 to report an exponential weighted moving average (EWMA) of the signal value. Since the signal value usually fluctuates between different packets, an average can be more useful than the value of the last packet. This uses the recently added generic EWMA library function. -- v2: fix ABI breakage and change factor to be a power of 2. Signed-off-by: Bruno Randolf Signed-off-by: John W. Linville --- include/linux/nl80211.h | 2 ++ include/net/cfg80211.h | 4 ++++ net/mac80211/Kconfig | 1 + net/mac80211/cfg.c | 3 ++- net/mac80211/rx.c | 1 + net/mac80211/sta_info.c | 2 ++ net/mac80211/sta_info.h | 3 +++ net/wireless/nl80211.c | 3 +++ 8 files changed, 18 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 410a06ea551b..8e28053ea423 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -1191,6 +1191,7 @@ enum nl80211_rate_info { * station) * @NL80211_STA_INFO_TX_RETRIES: total retries (u32, to this station) * @NL80211_STA_INFO_TX_FAILED: total failed packets (u32, to this station) + * @NL80211_STA_INFO_SIGNAL_AVG: signal strength average (u8, dBm) */ enum nl80211_sta_info { __NL80211_STA_INFO_INVALID, @@ -1206,6 +1207,7 @@ enum nl80211_sta_info { NL80211_STA_INFO_TX_PACKETS, NL80211_STA_INFO_TX_RETRIES, NL80211_STA_INFO_TX_FAILED, + NL80211_STA_INFO_SIGNAL_AVG, /* keep last */ __NL80211_STA_INFO_AFTER_LAST, diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 788c3989a9e8..8764c9a5bab7 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -420,6 +420,7 @@ struct station_parameters { * @STATION_INFO_TX_RETRIES: @tx_retries filled * @STATION_INFO_TX_FAILED: @tx_failed filled * @STATION_INFO_RX_DROP_MISC: @rx_dropped_misc filled + * @STATION_INFO_SIGNAL_AVG: @signal_avg filled */ enum station_info_flags { STATION_INFO_INACTIVE_TIME = 1<<0, @@ -435,6 +436,7 @@ enum station_info_flags { STATION_INFO_TX_RETRIES = 1<<10, STATION_INFO_TX_FAILED = 1<<11, STATION_INFO_RX_DROP_MISC = 1<<12, + STATION_INFO_SIGNAL_AVG = 1<<13, }; /** @@ -481,6 +483,7 @@ struct rate_info { * @plid: mesh peer link id * @plink_state: mesh peer link state * @signal: signal strength of last received packet in dBm + * @signal_avg: signal strength average in dBm * @txrate: current unicast bitrate to this station * @rx_packets: packets received from this station * @tx_packets: packets transmitted to this station @@ -501,6 +504,7 @@ struct station_info { u16 plid; u8 plink_state; s8 signal; + s8 signal_avg; struct rate_info txrate; u32 rx_packets; u32 tx_packets; diff --git a/net/mac80211/Kconfig b/net/mac80211/Kconfig index 4d6f8653ec88..798d9b9462e2 100644 --- a/net/mac80211/Kconfig +++ b/net/mac80211/Kconfig @@ -6,6 +6,7 @@ config MAC80211 select CRYPTO_ARC4 select CRYPTO_AES select CRC32 + select AVERAGE ---help--- This option enables the hardware independent IEEE 802.11 networking stack. diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 68329d713c02..af9620406321 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -342,8 +342,9 @@ static void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo) if ((sta->local->hw.flags & IEEE80211_HW_SIGNAL_DBM) || (sta->local->hw.flags & IEEE80211_HW_SIGNAL_UNSPEC)) { - sinfo->filled |= STATION_INFO_SIGNAL; + sinfo->filled |= STATION_INFO_SIGNAL | STATION_INFO_SIGNAL_AVG; sinfo->signal = (s8)sta->last_signal; + sinfo->signal_avg = (s8) -ewma_read(&sta->avg_signal); } sinfo->txrate.flags = 0; diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 6289525c0998..2fe8f5f86499 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -1163,6 +1163,7 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx) sta->rx_fragments++; sta->rx_bytes += rx->skb->len; sta->last_signal = status->signal; + ewma_add(&sta->avg_signal, -status->signal); /* * Change STA power saving mode only at the end of a frame diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index eff58571fd7e..c426504ed1cf 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -244,6 +244,8 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, sta->local = local; sta->sdata = sdata; + ewma_init(&sta->avg_signal, 1024, 8); + if (sta_prepare_rate_control(local, sta, gfp)) { kfree(sta); return NULL; diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 05f11302443b..fdca52cf88de 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -13,6 +13,7 @@ #include #include #include +#include #include "key.h" /** @@ -223,6 +224,7 @@ enum plink_state { * @rx_fragments: number of received MPDUs * @rx_dropped: number of dropped MPDUs from this STA * @last_signal: signal of last received frame from this STA + * @avg_signal: moving average of signal of received frames from this STA * @last_seq_ctrl: last received seq/frag number from this STA (per RX queue) * @tx_filtered_count: number of frames the hardware filtered for this STA * @tx_retry_failed: number of frames that failed retry @@ -291,6 +293,7 @@ struct sta_info { unsigned long rx_fragments; unsigned long rx_dropped; int last_signal; + struct ewma avg_signal; __le16 last_seq_ctrl[NUM_RX_DATA_QUEUES]; /* Updated from TX status path only, no locking requirements */ diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 56508d40c740..2cf03331d4a2 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -1896,6 +1896,9 @@ static int nl80211_send_station(struct sk_buff *msg, u32 pid, u32 seq, if (sinfo->filled & STATION_INFO_SIGNAL) NLA_PUT_U8(msg, NL80211_STA_INFO_SIGNAL, sinfo->signal); + if (sinfo->filled & STATION_INFO_SIGNAL_AVG) + NLA_PUT_U8(msg, NL80211_STA_INFO_SIGNAL_AVG, + sinfo->signal_avg); if (sinfo->filled & STATION_INFO_TX_BITRATE) { txrate = nla_nest_start(msg, NL80211_STA_INFO_TX_BITRATE); if (!txrate) -- cgit v1.2.3 From 88d60c32765716289abeb362c44adf6c35c6824c Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Mon, 8 Nov 2010 18:19:22 -0500 Subject: fanotify: remove packed from access response message Since fanotify has decided to be careful about alignment and packing rather than rely on __attribute__((packed)) for multiarch support. Since this attribute isn't doing anything on fanotify_response we just drop it. This does not break API/ABI. Suggested-by: Tvrtko Ursulin Signed-off-by: Eric Paris --- include/linux/fanotify.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index 0f0121467fc4..bdbf9bb29b54 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -96,7 +96,7 @@ struct fanotify_event_metadata { struct fanotify_response { __s32 fd; __u32 response; -} __attribute__ ((packed)); +}; /* Legit userspace responses to a _PERM event */ #define FAN_ALLOW 0x01 -- cgit v1.2.3 From b1085ba80cd2784400a7beec3fda5099198ed01c Mon Sep 17 00:00:00 2001 From: Lino Sanfilippo Date: Fri, 5 Nov 2010 17:05:27 +0100 Subject: fanotify: if set by user unset FMODE_NONOTIFY before fsnotify_perm() is called Unsetting FMODE_NONOTIFY in fsnotify_open() is too late, since fsnotify_perm() is called before. If FMODE_NONOTIFY is set fsnotify_perm() will skip permission checks, so a user can still disable permission checks by setting this flag in an open() call. This patch corrects this by unsetting the flag before fsnotify_perm is called. Signed-off-by: Lino Sanfilippo Signed-off-by: Eric Paris --- fs/namei.c | 3 +++ include/linux/fsnotify.h | 3 --- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/fs/namei.c b/fs/namei.c index 5362af9b7372..4ff7ca530533 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1748,6 +1748,9 @@ struct file *do_filp_open(int dfd, const char *pathname, if (!(open_flag & O_CREAT)) mode = 0; + /* Must never be set by userspace */ + open_flag &= ~FMODE_NONOTIFY; + /* * O_SYNC is implemented as __O_SYNC|O_DSYNC. As many places only * check for O_DSYNC if the need any syncing at all we enforce it's diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 5c185fa27089..b10bcdeaef76 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -235,9 +235,6 @@ static inline void fsnotify_open(struct file *file) if (S_ISDIR(inode->i_mode)) mask |= FS_ISDIR; - /* FMODE_NONOTIFY must never be set from user */ - file->f_mode &= ~FMODE_NONOTIFY; - fsnotify_parent(path, NULL, mask); fsnotify(inode, mask, path, FSNOTIFY_EVENT_PATH, NULL, 0); } -- cgit v1.2.3 From 09e5f14e57c70f9d357862bb56e57026c51092a1 Mon Sep 17 00:00:00 2001 From: Lino Sanfilippo Date: Fri, 19 Nov 2010 10:58:07 +0100 Subject: fanotify: on group destroy allow all waiters to bypass permission check When fanotify_release() is called, there may still be processes waiting for access permission. Currently only processes for which an event has already been queued into the groups access list will be woken up. Processes for which no event has been queued will continue to sleep and thus cause a deadlock when fsnotify_put_group() is called. Furthermore there is a race allowing further processes to be waiting on the access wait queue after wake_up (if they arrive before clear_marks_by_group() is called). This patch corrects this by setting a flag to inform processes that the group is about to be destroyed and thus not to wait for access permission. [additional changelog from eparis] Lets think about the 4 relevant code paths from the PoV of the 'operator' 'listener' 'responder' and 'closer'. Where operator is the process doing an action (like open/read) which could require permission. Listener is the task (or in this case thread) slated with reading from the fanotify file descriptor. The 'responder' is the thread responsible for responding to access requests. 'Closer' is the thread attempting to close the fanotify file descriptor. The 'operator' is going to end up in: fanotify_handle_event() get_response_from_access() (THIS BLOCKS WAITING ON USERSPACE) The 'listener' interesting code path fanotify_read() copy_event_to_user() prepare_for_access_response() (THIS CREATES AN fanotify_response_event) The 'responder' code path: fanotify_write() process_access_response() (REMOVE A fanotify_response_event, SET RESPONSE, WAKE UP 'operator') The 'closer': fanotify_release() (SUPPOSED TO CLEAN UP THE REST OF THIS MESS) What we have today is that in the closer we remove all of the fanotify_response_events and set a bit so no more response events are ever created in prepare_for_access_response(). The bug is that we never wake all of the operators up and tell them to move along. You fix that in fanotify_get_response_from_access(). You also fix other operators which haven't gotten there yet. So I agree that's a good fix. [/additional changelog from eparis] [remove additional changes to minimize patch size] [move initialization so it was inside CONFIG_FANOTIFY_PERMISSION] Signed-off-by: Lino Sanfilippo Signed-off-by: Eric Paris --- fs/notify/fanotify/fanotify.c | 6 +++++- fs/notify/fanotify/fanotify_user.c | 5 +++-- include/linux/fsnotify_backend.h | 2 +- 3 files changed, 9 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index b04f88eed09e..f35794b97e8e 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -92,7 +92,11 @@ static int fanotify_get_response_from_access(struct fsnotify_group *group, pr_debug("%s: group=%p event=%p\n", __func__, group, event); - wait_event(group->fanotify_data.access_waitq, event->response); + wait_event(group->fanotify_data.access_waitq, event->response || + atomic_read(&group->fanotify_data.bypass_perm)); + + if (!event->response) /* bypass_perm set */ + return 0; /* userspace responded, convert to something usable */ spin_lock(&event->lock); diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 480434c5ee5f..01fffe62a2d4 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -200,7 +200,7 @@ static int prepare_for_access_response(struct fsnotify_group *group, mutex_lock(&group->fanotify_data.access_mutex); - if (group->fanotify_data.bypass_perm) { + if (atomic_read(&group->fanotify_data.bypass_perm)) { mutex_unlock(&group->fanotify_data.access_mutex); kmem_cache_free(fanotify_response_event_cache, re); event->response = FAN_ALLOW; @@ -390,7 +390,7 @@ static int fanotify_release(struct inode *ignored, struct file *file) mutex_lock(&group->fanotify_data.access_mutex); - group->fanotify_data.bypass_perm = true; + atomic_inc(&group->fanotify_data.bypass_perm); list_for_each_entry_safe(re, lre, &group->fanotify_data.access_list, list) { pr_debug("%s: found group=%p re=%p event=%p\n", __func__, group, @@ -703,6 +703,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) mutex_init(&group->fanotify_data.access_mutex); init_waitqueue_head(&group->fanotify_data.access_waitq); INIT_LIST_HEAD(&group->fanotify_data.access_list); + atomic_set(&group->fanotify_data.bypass_perm, 0); #endif switch (flags & FAN_ALL_CLASS_BITS) { case FAN_CLASS_NOTIF: diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 0a68f924f06f..7380763595d3 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -166,7 +166,7 @@ struct fsnotify_group { struct mutex access_mutex; struct list_head access_list; wait_queue_head_t access_waitq; - bool bypass_perm; /* protected by access_mutex */ + atomic_t bypass_perm; #endif /* CONFIG_FANOTIFY_ACCESS_PERMISSIONS */ int f_flags; unsigned int max_marks; -- cgit v1.2.3 From e9a3854fd4ff3907e6c200a3980e19365ee695e9 Mon Sep 17 00:00:00 2001 From: Lino Sanfilippo Date: Wed, 24 Nov 2010 18:22:09 +0100 Subject: fanotify: Introduce FAN_NOFD FAN_NOFD is used in fanotify events that do not provide an open file descriptor (like the overflow_event). Signed-off-by: Lino Sanfilippo Signed-off-by: Eric Paris --- include/linux/fanotify.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index bdbf9bb29b54..c73224315aee 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -101,6 +101,8 @@ struct fanotify_response { /* Legit userspace responses to a _PERM event */ #define FAN_ALLOW 0x01 #define FAN_DENY 0x02 +/* No fd set in event */ +#define FAN_NOFD -1 /* Helper functions to deal with fanotify_event_metadata buffers */ #define FAN_EVENT_METADATA_LEN (sizeof(struct fanotify_event_metadata)) -- cgit v1.2.3 From 941666c2e3e0f9f6a1cb5808d02352d445bd702c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 5 Dec 2010 01:23:53 +0000 Subject: net: RCU conversion of dev_getbyhwaddr() and arp_ioctl() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Le dimanche 05 décembre 2010 à 09:19 +0100, Eric Dumazet a écrit : > Hmm.. > > If somebody can explain why RTNL is held in arp_ioctl() (and therefore > in arp_req_delete()), we might first remove RTNL use in arp_ioctl() so > that your patch can be applied. > > Right now it is not good, because RTNL wont be necessarly held when you > are going to call arp_invalidate() ? While doing this analysis, I found a refcount bug in llc, I'll send a patch for net-2.6 Meanwhile, here is the patch for net-next-2.6 Your patch then can be applied after mine. Thanks [PATCH] net: RCU conversion of dev_getbyhwaddr() and arp_ioctl() dev_getbyhwaddr() was called under RTNL. Rename it to dev_getbyhwaddr_rcu() and change all its caller to now use RCU locking instead of RTNL. Change arp_ioctl() to use RCU instead of RTNL locking. Note: this fix a dev refcount bug in llc Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 ++- net/core/dev.c | 17 +++++++---------- net/ieee802154/af_ieee802154.c | 6 +++--- net/ipv4/arp.c | 17 +++++++++-------- net/llc/af_llc.c | 11 ++++++----- 5 files changed, 27 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index a9ac5dc26e3c..d31bc3c94717 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1360,7 +1360,8 @@ static inline struct net_device *first_net_device(struct net *net) extern int netdev_boot_setup_check(struct net_device *dev); extern unsigned long netdev_boot_base(const char *prefix, int unit); -extern struct net_device *dev_getbyhwaddr(struct net *net, unsigned short type, char *hwaddr); +extern struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type, + const char *hwaddr); extern struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type); extern struct net_device *__dev_getfirstbyhwtype(struct net *net, unsigned short type); extern void dev_add_pack(struct packet_type *pt); diff --git a/net/core/dev.c b/net/core/dev.c index ee605c0867e7..822b15b8d11c 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -743,34 +743,31 @@ struct net_device *dev_get_by_index(struct net *net, int ifindex) EXPORT_SYMBOL(dev_get_by_index); /** - * dev_getbyhwaddr - find a device by its hardware address + * dev_getbyhwaddr_rcu - find a device by its hardware address * @net: the applicable net namespace * @type: media type of device * @ha: hardware address * * Search for an interface by MAC address. Returns NULL if the device - * is not found or a pointer to the device. The caller must hold the - * rtnl semaphore. The returned device has not had its ref count increased + * is not found or a pointer to the device. The caller must hold RCU + * The returned device has not had its ref count increased * and the caller must therefore be careful about locking * - * BUGS: - * If the API was consistent this would be __dev_get_by_hwaddr */ -struct net_device *dev_getbyhwaddr(struct net *net, unsigned short type, char *ha) +struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type, + const char *ha) { struct net_device *dev; - ASSERT_RTNL(); - - for_each_netdev(net, dev) + for_each_netdev_rcu(net, dev) if (dev->type == type && !memcmp(dev->dev_addr, ha, dev->addr_len)) return dev; return NULL; } -EXPORT_SYMBOL(dev_getbyhwaddr); +EXPORT_SYMBOL(dev_getbyhwaddr_rcu); struct net_device *__dev_getfirstbyhwtype(struct net *net, unsigned short type) { diff --git a/net/ieee802154/af_ieee802154.c b/net/ieee802154/af_ieee802154.c index 93c91b633a56..6df6ecf49708 100644 --- a/net/ieee802154/af_ieee802154.c +++ b/net/ieee802154/af_ieee802154.c @@ -52,11 +52,11 @@ struct net_device *ieee802154_get_dev(struct net *net, switch (addr->addr_type) { case IEEE802154_ADDR_LONG: - rtnl_lock(); - dev = dev_getbyhwaddr(net, ARPHRD_IEEE802154, addr->hwaddr); + rcu_read_lock(); + dev = dev_getbyhwaddr_rcu(net, ARPHRD_IEEE802154, addr->hwaddr); if (dev) dev_hold(dev); - rtnl_unlock(); + rcu_read_unlock(); break; case IEEE802154_ADDR_SHORT: if (addr->pan_id == 0xffff || diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 10af759f2630..a2fc7b961dbc 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1017,13 +1017,14 @@ static int arp_req_set_proxy(struct net *net, struct net_device *dev, int on) IPV4_DEVCONF_ALL(net, PROXY_ARP) = on; return 0; } - if (__in_dev_get_rtnl(dev)) { - IN_DEV_CONF_SET(__in_dev_get_rtnl(dev), PROXY_ARP, on); + if (__in_dev_get_rcu(dev)) { + IN_DEV_CONF_SET(__in_dev_get_rcu(dev), PROXY_ARP, on); return 0; } return -ENXIO; } +/* must be called with rcu_read_lock() */ static int arp_req_set_public(struct net *net, struct arpreq *r, struct net_device *dev) { @@ -1033,7 +1034,7 @@ static int arp_req_set_public(struct net *net, struct arpreq *r, if (mask && mask != htonl(0xFFFFFFFF)) return -EINVAL; if (!dev && (r->arp_flags & ATF_COM)) { - dev = dev_getbyhwaddr(net, r->arp_ha.sa_family, + dev = dev_getbyhwaddr_rcu(net, r->arp_ha.sa_family, r->arp_ha.sa_data); if (!dev) return -ENODEV; @@ -1225,10 +1226,10 @@ int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg) if (!(r.arp_flags & ATF_NETMASK)) ((struct sockaddr_in *)&r.arp_netmask)->sin_addr.s_addr = htonl(0xFFFFFFFFUL); - rtnl_lock(); + rcu_read_lock(); if (r.arp_dev[0]) { err = -ENODEV; - dev = __dev_get_by_name(net, r.arp_dev); + dev = dev_get_by_name_rcu(net, r.arp_dev); if (dev == NULL) goto out; @@ -1252,12 +1253,12 @@ int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg) break; case SIOCGARP: err = arp_req_get(&r, dev); - if (!err && copy_to_user(arg, &r, sizeof(r))) - err = -EFAULT; break; } out: - rtnl_unlock(); + rcu_read_unlock(); + if (cmd == SIOCGARP && !err && copy_to_user(arg, &r, sizeof(r))) + err = -EFAULT; return err; } diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 582612998211..dfd3a648a551 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -316,9 +316,9 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen) if (unlikely(addr->sllc_family != AF_LLC)) goto out; rc = -ENODEV; - rtnl_lock(); + rcu_read_lock(); if (sk->sk_bound_dev_if) { - llc->dev = dev_get_by_index(&init_net, sk->sk_bound_dev_if); + llc->dev = dev_get_by_index_rcu(&init_net, sk->sk_bound_dev_if); if (llc->dev) { if (!addr->sllc_arphrd) addr->sllc_arphrd = llc->dev->type; @@ -329,14 +329,15 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen) !llc_mac_match(addr->sllc_mac, llc->dev->dev_addr)) { rc = -EINVAL; - dev_put(llc->dev); llc->dev = NULL; } } } else - llc->dev = dev_getbyhwaddr(&init_net, addr->sllc_arphrd, + llc->dev = dev_getbyhwaddr_rcu(&init_net, addr->sllc_arphrd, addr->sllc_mac); - rtnl_unlock(); + if (llc->dev) + dev_hold(llc->dev); + rcu_read_unlock(); if (!llc->dev) goto out; if (!addr->sllc_sap) { -- cgit v1.2.3 From 62ab0812137ec4f9884dd7de346238841ac03283 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 6 Dec 2010 20:50:09 +0000 Subject: filter: constify sk_run_filter() sk_run_filter() doesnt write on skb, change its prototype to reflect this. Fix two af_packet comments. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/filter.h | 2 +- net/core/filter.c | 7 ++++--- net/core/timestamping.c | 2 +- net/packet/af_packet.c | 31 ++++++++++++++++--------------- 4 files changed, 22 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 5334adaf4072..45266b75409a 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -148,7 +148,7 @@ struct sk_buff; struct sock; extern int sk_filter(struct sock *sk, struct sk_buff *skb); -extern unsigned int sk_run_filter(struct sk_buff *skb, +extern unsigned int sk_run_filter(const struct sk_buff *skb, const struct sock_filter *filter); extern int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk); extern int sk_detach_filter(struct sock *sk); diff --git a/net/core/filter.c b/net/core/filter.c index ac4920a87be5..25500f16a18a 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -88,7 +88,7 @@ enum { }; /* No hurry in this branch */ -static void *__load_pointer(struct sk_buff *skb, int k) +static void *__load_pointer(const struct sk_buff *skb, int k) { u8 *ptr = NULL; @@ -102,7 +102,7 @@ static void *__load_pointer(struct sk_buff *skb, int k) return NULL; } -static inline void *load_pointer(struct sk_buff *skb, int k, +static inline void *load_pointer(const struct sk_buff *skb, int k, unsigned int size, void *buffer) { if (k >= 0) @@ -160,7 +160,8 @@ EXPORT_SYMBOL(sk_filter); * and last instruction guaranteed to be a RET, we dont need to check * flen. (We used to pass to this function the length of filter) */ -unsigned int sk_run_filter(struct sk_buff *skb, const struct sock_filter *fentry) +unsigned int sk_run_filter(const struct sk_buff *skb, + const struct sock_filter *fentry) { void *ptr; u32 A = 0; /* Accumulator */ diff --git a/net/core/timestamping.c b/net/core/timestamping.c index dac7ed687f60..b124d28ff1c8 100644 --- a/net/core/timestamping.c +++ b/net/core/timestamping.c @@ -26,7 +26,7 @@ static struct sock_filter ptp_filter[] = { PTP_FILTER }; -static unsigned int classify(struct sk_buff *skb) +static unsigned int classify(const struct sk_buff *skb) { if (likely(skb->dev && skb->dev->phydev && diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index a11c731d2ee4..17eafe5b48c6 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -517,7 +517,8 @@ out_free: return err; } -static inline unsigned int run_filter(struct sk_buff *skb, struct sock *sk, +static inline unsigned int run_filter(const struct sk_buff *skb, + const struct sock *sk, unsigned int res) { struct sk_filter *filter; @@ -532,15 +533,15 @@ static inline unsigned int run_filter(struct sk_buff *skb, struct sock *sk, } /* - This function makes lazy skb cloning in hope that most of packets - are discarded by BPF. - - Note tricky part: we DO mangle shared skb! skb->data, skb->len - and skb->cb are mangled. It works because (and until) packets - falling here are owned by current CPU. Output packets are cloned - by dev_queue_xmit_nit(), input packets are processed by net_bh - sequencially, so that if we return skb to original state on exit, - we will not harm anyone. + * This function makes lazy skb cloning in hope that most of packets + * are discarded by BPF. + * + * Note tricky part: we DO mangle shared skb! skb->data, skb->len + * and skb->cb are mangled. It works because (and until) packets + * falling here are owned by current CPU. Output packets are cloned + * by dev_queue_xmit_nit(), input packets are processed by net_bh + * sequencially, so that if we return skb to original state on exit, + * we will not harm anyone. */ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, @@ -566,11 +567,11 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, if (dev->header_ops) { /* The device has an explicit notion of ll header, - exported to higher levels. - - Otherwise, the device hides datails of it frame - structure, so that corresponding packet head - never delivered to user. + * exported to higher levels. + * + * Otherwise, the device hides details of its frame + * structure, so that corresponding packet head is + * never delivered to user. */ if (sk->sk_type != SOCK_DGRAM) skb_push(skb, skb->data - skb_mac_header(skb)); -- cgit v1.2.3 From 5167695753c63444a9e6cbbef136200a16c7a225 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 7 Dec 2010 14:18:20 +0100 Subject: perf: Fix duplicate events with multiple-pmu vs software events Because the multi-pmu bits can share contexts between struct pmu instances we could get duplicate events by iterating the pmu list. Signed-off-by: Peter Zijlstra Signed-off-by: Thomas Gleixner LKML-Reference: Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 1 + kernel/perf_event.c | 35 +++++++++++++++++++++++++++++------ 2 files changed, 30 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index de2c41758e29..4f1279e105ee 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -887,6 +887,7 @@ struct perf_cpu_context { int exclusive; struct list_head rotation_list; int jiffies_interval; + struct pmu *active_pmu; }; struct perf_output_handle { diff --git a/kernel/perf_event.c b/kernel/perf_event.c index eac7e3364335..7b870174c56d 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -3824,6 +3824,8 @@ static void perf_event_task_event(struct perf_task_event *task_event) rcu_read_lock(); list_for_each_entry_rcu(pmu, &pmus, entry) { cpuctx = get_cpu_ptr(pmu->pmu_cpu_context); + if (cpuctx->active_pmu != pmu) + goto next; perf_event_task_ctx(&cpuctx->ctx, task_event); ctx = task_event->task_ctx; @@ -3959,6 +3961,8 @@ static void perf_event_comm_event(struct perf_comm_event *comm_event) rcu_read_lock(); list_for_each_entry_rcu(pmu, &pmus, entry) { cpuctx = get_cpu_ptr(pmu->pmu_cpu_context); + if (cpuctx->active_pmu != pmu) + goto next; perf_event_comm_ctx(&cpuctx->ctx, comm_event); ctxn = pmu->task_ctx_nr; @@ -4144,6 +4148,8 @@ got_name: rcu_read_lock(); list_for_each_entry_rcu(pmu, &pmus, entry) { cpuctx = get_cpu_ptr(pmu->pmu_cpu_context); + if (cpuctx->active_pmu != pmu) + goto next; perf_event_mmap_ctx(&cpuctx->ctx, mmap_event, vma->vm_flags & VM_EXEC); @@ -5145,20 +5151,36 @@ static void *find_pmu_context(int ctxn) return NULL; } -static void free_pmu_context(void * __percpu cpu_context) +static void update_pmu_context(struct pmu *pmu, struct pmu *old_pmu) { - struct pmu *pmu; + int cpu; + + for_each_possible_cpu(cpu) { + struct perf_cpu_context *cpuctx; + + cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu); + + if (cpuctx->active_pmu == old_pmu) + cpuctx->active_pmu = pmu; + } +} + +static void free_pmu_context(struct pmu *pmu) +{ + struct pmu *i; mutex_lock(&pmus_lock); /* * Like a real lame refcount. */ - list_for_each_entry(pmu, &pmus, entry) { - if (pmu->pmu_cpu_context == cpu_context) + list_for_each_entry(i, &pmus, entry) { + if (i->pmu_cpu_context == pmu->pmu_cpu_context) { + update_pmu_context(i, pmu); goto out; + } } - free_percpu(cpu_context); + free_percpu(pmu->pmu_cpu_context); out: mutex_unlock(&pmus_lock); } @@ -5190,6 +5212,7 @@ int perf_pmu_register(struct pmu *pmu) cpuctx->ctx.pmu = pmu; cpuctx->jiffies_interval = 1; INIT_LIST_HEAD(&cpuctx->rotation_list); + cpuctx->active_pmu = pmu; } got_cpu_context: @@ -5241,7 +5264,7 @@ void perf_pmu_unregister(struct pmu *pmu) synchronize_rcu(); free_percpu(pmu->pmu_disable_count); - free_pmu_context(pmu->pmu_cpu_context); + free_pmu_context(pmu); } struct pmu *perf_init_event(struct perf_event *event) -- cgit v1.2.3 From 0f004f5a696a9434b7214d0d3cbd0525ee77d428 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 30 Nov 2010 19:48:45 +0100 Subject: sched: Cure more NO_HZ load average woes There's a long-running regression that proved difficult to fix and which is hitting certain people and is rather annoying in its effects. Damien reported that after 74f5187ac8 (sched: Cure load average vs NO_HZ woes) his load average is unnaturally high, he also noted that even with that patch reverted the load avgerage numbers are not correct. The problem is that the previous patch only solved half the NO_HZ problem, it addressed the part of going into NO_HZ mode, not of comming out of NO_HZ mode. This patch implements that missing half. When comming out of NO_HZ mode there are two important things to take care of: - Folding the pending idle delta into the global active count. - Correctly aging the averages for the idle-duration. So with this patch the NO_HZ interaction should be complete and behaviour between CONFIG_NO_HZ=[yn] should be equivalent. Furthermore, this patch slightly changes the load average computation by adding a rounding term to the fixed point multiplication. Reported-by: Damien Wyart Reported-by: Tim McGrath Tested-by: Damien Wyart Tested-by: Orion Poplawski Tested-by: Kyle McMartin Signed-off-by: Peter Zijlstra Cc: stable@kernel.org Cc: Chase Douglas LKML-Reference: <1291129145.32004.874.camel@laptop> Signed-off-by: Ingo Molnar --- include/linux/sched.h | 2 +- kernel/sched.c | 150 ++++++++++++++++++++++++++++++++++++++++++++++---- kernel/timer.c | 2 +- 3 files changed, 141 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 2c79e921a68b..223874538b33 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -143,7 +143,7 @@ extern unsigned long nr_iowait_cpu(int cpu); extern unsigned long this_cpu_load(void); -extern void calc_global_load(void); +extern void calc_global_load(unsigned long ticks); extern unsigned long get_parent_ip(unsigned long addr); diff --git a/kernel/sched.c b/kernel/sched.c index dc91a4d09ac3..6b7c26a1a097 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -3119,6 +3119,15 @@ static long calc_load_fold_active(struct rq *this_rq) return delta; } +static unsigned long +calc_load(unsigned long load, unsigned long exp, unsigned long active) +{ + load *= exp; + load += active * (FIXED_1 - exp); + load += 1UL << (FSHIFT - 1); + return load >> FSHIFT; +} + #ifdef CONFIG_NO_HZ /* * For NO_HZ we delay the active fold to the next LOAD_FREQ update. @@ -3148,6 +3157,128 @@ static long calc_load_fold_idle(void) return delta; } + +/** + * fixed_power_int - compute: x^n, in O(log n) time + * + * @x: base of the power + * @frac_bits: fractional bits of @x + * @n: power to raise @x to. + * + * By exploiting the relation between the definition of the natural power + * function: x^n := x*x*...*x (x multiplied by itself for n times), and + * the binary encoding of numbers used by computers: n := \Sum n_i * 2^i, + * (where: n_i \elem {0, 1}, the binary vector representing n), + * we find: x^n := x^(\Sum n_i * 2^i) := \Prod x^(n_i * 2^i), which is + * of course trivially computable in O(log_2 n), the length of our binary + * vector. + */ +static unsigned long +fixed_power_int(unsigned long x, unsigned int frac_bits, unsigned int n) +{ + unsigned long result = 1UL << frac_bits; + + if (n) for (;;) { + if (n & 1) { + result *= x; + result += 1UL << (frac_bits - 1); + result >>= frac_bits; + } + n >>= 1; + if (!n) + break; + x *= x; + x += 1UL << (frac_bits - 1); + x >>= frac_bits; + } + + return result; +} + +/* + * a1 = a0 * e + a * (1 - e) + * + * a2 = a1 * e + a * (1 - e) + * = (a0 * e + a * (1 - e)) * e + a * (1 - e) + * = a0 * e^2 + a * (1 - e) * (1 + e) + * + * a3 = a2 * e + a * (1 - e) + * = (a0 * e^2 + a * (1 - e) * (1 + e)) * e + a * (1 - e) + * = a0 * e^3 + a * (1 - e) * (1 + e + e^2) + * + * ... + * + * an = a0 * e^n + a * (1 - e) * (1 + e + ... + e^n-1) [1] + * = a0 * e^n + a * (1 - e) * (1 - e^n)/(1 - e) + * = a0 * e^n + a * (1 - e^n) + * + * [1] application of the geometric series: + * + * n 1 - x^(n+1) + * S_n := \Sum x^i = ------------- + * i=0 1 - x + */ +static unsigned long +calc_load_n(unsigned long load, unsigned long exp, + unsigned long active, unsigned int n) +{ + + return calc_load(load, fixed_power_int(exp, FSHIFT, n), active); +} + +/* + * NO_HZ can leave us missing all per-cpu ticks calling + * calc_load_account_active(), but since an idle CPU folds its delta into + * calc_load_tasks_idle per calc_load_account_idle(), all we need to do is fold + * in the pending idle delta if our idle period crossed a load cycle boundary. + * + * Once we've updated the global active value, we need to apply the exponential + * weights adjusted to the number of cycles missed. + */ +static void calc_global_nohz(unsigned long ticks) +{ + long delta, active, n; + + if (time_before(jiffies, calc_load_update)) + return; + + /* + * If we crossed a calc_load_update boundary, make sure to fold + * any pending idle changes, the respective CPUs might have + * missed the tick driven calc_load_account_active() update + * due to NO_HZ. + */ + delta = calc_load_fold_idle(); + if (delta) + atomic_long_add(delta, &calc_load_tasks); + + /* + * If we were idle for multiple load cycles, apply them. + */ + if (ticks >= LOAD_FREQ) { + n = ticks / LOAD_FREQ; + + active = atomic_long_read(&calc_load_tasks); + active = active > 0 ? active * FIXED_1 : 0; + + avenrun[0] = calc_load_n(avenrun[0], EXP_1, active, n); + avenrun[1] = calc_load_n(avenrun[1], EXP_5, active, n); + avenrun[2] = calc_load_n(avenrun[2], EXP_15, active, n); + + calc_load_update += n * LOAD_FREQ; + } + + /* + * Its possible the remainder of the above division also crosses + * a LOAD_FREQ period, the regular check in calc_global_load() + * which comes after this will take care of that. + * + * Consider us being 11 ticks before a cycle completion, and us + * sleeping for 4*LOAD_FREQ + 22 ticks, then the above code will + * age us 4 cycles, and the test in calc_global_load() will + * pick up the final one. + */ +} #else static void calc_load_account_idle(struct rq *this_rq) { @@ -3157,6 +3288,10 @@ static inline long calc_load_fold_idle(void) { return 0; } + +static void calc_global_nohz(unsigned long ticks) +{ +} #endif /** @@ -3174,24 +3309,17 @@ void get_avenrun(unsigned long *loads, unsigned long offset, int shift) loads[2] = (avenrun[2] + offset) << shift; } -static unsigned long -calc_load(unsigned long load, unsigned long exp, unsigned long active) -{ - load *= exp; - load += active * (FIXED_1 - exp); - return load >> FSHIFT; -} - /* * calc_load - update the avenrun load estimates 10 ticks after the * CPUs have updated calc_load_tasks. */ -void calc_global_load(void) +void calc_global_load(unsigned long ticks) { - unsigned long upd = calc_load_update + 10; long active; - if (time_before(jiffies, upd)) + calc_global_nohz(ticks); + + if (time_before(jiffies, calc_load_update + 10)) return; active = atomic_long_read(&calc_load_tasks); diff --git a/kernel/timer.c b/kernel/timer.c index 68a9ae7679b7..7bd715fda974 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -1319,7 +1319,7 @@ void do_timer(unsigned long ticks) { jiffies_64 += ticks; update_wall_time(); - calc_global_load(); + calc_global_load(ticks); } #ifdef __ARCH_WANT_SYS_ALARM -- cgit v1.2.3 From 806c09a7db457be3758e14b1f152761135d89af5 Mon Sep 17 00:00:00 2001 From: Dario Faggioli Date: Tue, 30 Nov 2010 19:51:33 +0100 Subject: sched: Make pushable_tasks CONFIG_SMP dependant As noted by Peter Zijlstra at https://lkml.org/lkml/2010/11/10/391 (while reviewing other stuff, though), tracking pushable tasks only makes sense on SMP systems. Signed-off-by: Dario Faggioli Acked-by: Steven Rostedt Acked-by: Gregory Haskins Signed-off-by: Peter Zijlstra LKML-Reference: <1291143093.2697.298.camel@Palantir> Signed-off-by: Ingo Molnar --- include/linux/init_task.h | 9 ++++++++- include/linux/sched.h | 2 ++ kernel/sched.c | 2 ++ 3 files changed, 12 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 1f8c06ce0fa6..6ed8812bfe2d 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -12,6 +12,13 @@ #include #include +#ifdef CONFIG_SMP +# define INIT_PUSHABLE_TASKS(tsk) \ + .pushable_tasks = PLIST_NODE_INIT(tsk.pushable_tasks, MAX_PRIO), +#else +# define INIT_PUSHABLE_TASKS(tsk) +#endif + extern struct files_struct init_files; extern struct fs_struct init_fs; @@ -137,7 +144,7 @@ extern struct cred init_cred; .nr_cpus_allowed = NR_CPUS, \ }, \ .tasks = LIST_HEAD_INIT(tsk.tasks), \ - .pushable_tasks = PLIST_NODE_INIT(tsk.pushable_tasks, MAX_PRIO), \ + INIT_PUSHABLE_TASKS(tsk) \ .ptraced = LIST_HEAD_INIT(tsk.ptraced), \ .ptrace_entry = LIST_HEAD_INIT(tsk.ptrace_entry), \ .real_parent = &tsk, \ diff --git a/include/linux/sched.h b/include/linux/sched.h index 9c2d46da486e..4f92a239c14d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1240,7 +1240,9 @@ struct task_struct { #endif struct list_head tasks; +#ifdef CONFIG_SMP struct plist_node pushable_tasks; +#endif struct mm_struct *mm, *active_mm; #if defined(SPLIT_RSS_COUNTING) diff --git a/kernel/sched.c b/kernel/sched.c index b646dad4a40e..3925a1bbf5dd 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2595,7 +2595,9 @@ void sched_fork(struct task_struct *p, int clone_flags) /* Want to start with kernel preemption disabled. */ task_thread_info(p)->preempt_count = 1; #endif +#ifdef CONFIG_SMP plist_node_init(&p->pushable_tasks, MAX_PRIO); +#endif put_cpu(); } -- cgit v1.2.3 From 50b12f597be354a5a224f05c65c54c0667e57aec Mon Sep 17 00:00:00 2001 From: Helmut Schaa Date: Fri, 19 Nov 2010 12:40:25 +0100 Subject: cfg80211: Add new BSS attribute ht_opmode Add a new BSS attribute to allow hostapd to set the current HT opmode. Otherwise drivers won't be able to set up protection for HT rates in AP mode. Cc: Johannes Berg Signed-off-by: Helmut Schaa Signed-off-by: John W. Linville --- include/linux/nl80211.h | 4 ++++ include/net/cfg80211.h | 3 +++ net/wireless/nl80211.c | 5 +++++ 3 files changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 8e28053ea423..380421253d16 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -849,6 +849,8 @@ enum nl80211_commands { * flag isn't set, the frame will be rejected. This is also used as an * nl80211 capability flag. * + * @NL80211_ATTR_BSS_HTOPMODE: HT operation mode (u16) + * * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use */ @@ -1025,6 +1027,8 @@ enum nl80211_attrs { NL80211_ATTR_OFFCHANNEL_TX_OK, + NL80211_ATTR_BSS_HT_OPMODE, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 8764c9a5bab7..0d5979924be3 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -605,6 +605,8 @@ struct mpath_info { * (or NULL for no change) * @basic_rates_len: number of basic rates * @ap_isolate: do not forward packets between connected stations + * @ht_opmode: HT Operation mode + * (u16 = opmode, -1 = do not change) */ struct bss_parameters { int use_cts_prot; @@ -613,6 +615,7 @@ struct bss_parameters { u8 *basic_rates; u8 basic_rates_len; int ap_isolate; + int ht_opmode; }; /* diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 2cf03331d4a2..c3f80e565365 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -121,6 +121,7 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = { [NL80211_ATTR_BSS_SHORT_SLOT_TIME] = { .type = NLA_U8 }, [NL80211_ATTR_BSS_BASIC_RATES] = { .type = NLA_BINARY, .len = NL80211_MAX_SUPP_RATES }, + [NL80211_ATTR_BSS_HT_OPMODE] = { .type = NLA_U16 }, [NL80211_ATTR_MESH_PARAMS] = { .type = NLA_NESTED }, @@ -2462,6 +2463,7 @@ static int nl80211_set_bss(struct sk_buff *skb, struct genl_info *info) params.use_short_preamble = -1; params.use_short_slot_time = -1; params.ap_isolate = -1; + params.ht_opmode = -1; if (info->attrs[NL80211_ATTR_BSS_CTS_PROT]) params.use_cts_prot = @@ -2480,6 +2482,9 @@ static int nl80211_set_bss(struct sk_buff *skb, struct genl_info *info) } if (info->attrs[NL80211_ATTR_AP_ISOLATE]) params.ap_isolate = !!nla_get_u8(info->attrs[NL80211_ATTR_AP_ISOLATE]); + if (info->attrs[NL80211_ATTR_BSS_HT_OPMODE]) + params.ht_opmode = + nla_get_u16(info->attrs[NL80211_ATTR_BSS_HT_OPMODE]); if (!rdev->ops->change_bss) return -EOPNOTSUPP; -- cgit v1.2.3 From b7e8941b2df518186d9f7679c007f6b619bb4e89 Mon Sep 17 00:00:00 2001 From: Amitkumar Karwar Date: Tue, 7 Dec 2010 13:43:03 -0800 Subject: cfg80211: add some element IDs in enum ieee80211_eid 1)WLAN_EID_BSS_COEX_2040 2)WLAN_EID_OVERLAP_BSS_SCAN_PARAM 3)WLAN_EID_EXT_CAPABILITY Signed-off-by: Amitkumar Karwar Signed-off-by: John W. Linville --- include/linux/ieee80211.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index ed5a03cbe184..351c0ab4e284 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1223,6 +1223,9 @@ enum ieee80211_eid { WLAN_EID_BSS_AC_ACCESS_DELAY = 68, WLAN_EID_RRM_ENABLED_CAPABILITIES = 70, WLAN_EID_MULTIPLE_BSSID = 71, + WLAN_EID_BSS_COEX_2040 = 72, + WLAN_EID_OVERLAP_BSS_SCAN_PARAM = 74, + WLAN_EID_EXT_CAPABILITY = 127, WLAN_EID_MOBILITY_DOMAIN = 54, WLAN_EID_FAST_BSS_TRANSITION = 55, -- cgit v1.2.3 From 96a84c20d635fb1e98ab92f9fc517c4441f5c424 Mon Sep 17 00:00:00 2001 From: Don Zickus Date: Mon, 29 Nov 2010 17:07:16 -0500 Subject: lockup detector: Compile fixes from removing the old x86 nmi watchdog My patch that removed the old x86 nmi watchdog broke other arches. This change reverts a piece of that patch and puts the change in the correct spot. Signed-off-by: Don Zickus Reviewed-by: Cyrill Gorcunov Cc: fweisbec@gmail.com Cc: yinghai@kernel.org LKML-Reference: <1291068437-5331-2-git-send-email-dzickus@redhat.com> Signed-off-by: Ingo Molnar --- arch/x86/kernel/apic/hw_nmi.c | 8 +++++++- include/linux/nmi.h | 4 +++- 2 files changed, 10 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c index 057f1ebebe0c..2e94eb493591 100644 --- a/arch/x86/kernel/apic/hw_nmi.c +++ b/arch/x86/kernel/apic/hw_nmi.c @@ -24,8 +24,14 @@ u64 hw_nmi_get_sample_period(void) } #endif +#ifndef CONFIG_HARDLOCKUP_DETECTOR +void touch_nmi_watchdog(void) +{ + touch_softlockup_watchdog(); +} +EXPORT_SYMBOL(touch_nmi_watchdog); +#endif #ifdef arch_trigger_all_cpu_backtrace - /* For reliability, we're prepared to waste bits here. */ static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly; diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 1c451e6ecc17..17ccf44e7dcb 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -16,7 +16,8 @@ */ #ifdef ARCH_HAS_NMI_WATCHDOG #include -#endif +extern void touch_nmi_watchdog(void); +#else #ifndef CONFIG_HARDLOCKUP_DETECTOR static inline void touch_nmi_watchdog(void) { @@ -25,6 +26,7 @@ static inline void touch_nmi_watchdog(void) #else extern void touch_nmi_watchdog(void); #endif +#endif /* * Create trigger_all_cpu_backtrace() out of the arch-provided -- cgit v1.2.3 From 60d509c823cca21e77d537bd356785f7cfe8f0d1 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Fri, 3 Dec 2010 02:39:01 +0000 Subject: The new jhash implementation The current jhash.h implements the lookup2() hash function by Bob Jenkins. However, lookup2() is outdated as Bob wrote a new hash function called lookup3(). The patch replaces the lookup2() implementation of the 'jhash*' functions with that of lookup3(). You can read a longer comparison of the two and other hash functions at http://burtleburtle.net/bob/hash/doobs.html. Signed-off-by: Jozsef Kadlecsik Acked-by: Rusty Russell Signed-off-by: David S. Miller --- include/linux/jhash.h | 183 +++++++++++++++++++++++++++++--------------------- 1 file changed, 105 insertions(+), 78 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jhash.h b/include/linux/jhash.h index ced1159fa4f2..47cb09edec1a 100644 --- a/include/linux/jhash.h +++ b/include/linux/jhash.h @@ -3,129 +3,156 @@ /* jhash.h: Jenkins hash support. * - * Copyright (C) 1996 Bob Jenkins (bob_jenkins@burtleburtle.net) + * Copyright (C) 2006. Bob Jenkins (bob_jenkins@burtleburtle.net) * * http://burtleburtle.net/bob/hash/ * * These are the credits from Bob's sources: * - * lookup2.c, by Bob Jenkins, December 1996, Public Domain. - * hash(), hash2(), hash3, and mix() are externally useful functions. - * Routines to test the hash are included if SELF_TEST is defined. - * You can use this free for any purpose. It has no warranty. + * lookup3.c, by Bob Jenkins, May 2006, Public Domain. * - * Copyright (C) 2003 David S. Miller (davem@redhat.com) + * These are functions for producing 32-bit hashes for hash table lookup. + * hashword(), hashlittle(), hashlittle2(), hashbig(), mix(), and final() + * are externally useful functions. Routines to test the hash are included + * if SELF_TEST is defined. You can use this free for any purpose. It's in + * the public domain. It has no warranty. + * + * Copyright (C) 2009-2010 Jozsef Kadlecsik (kadlec@blackhole.kfki.hu) * * I've modified Bob's hash to be useful in the Linux kernel, and - * any bugs present are surely my fault. -DaveM + * any bugs present are my fault. + * Jozsef */ +#include +#include + +/* Best hash sizes are of power of two */ +#define jhash_size(n) ((u32)1<<(n)) +/* Mask the hash value, i.e (value & jhash_mask(n)) instead of (value % n) */ +#define jhash_mask(n) (jhash_size(n)-1) + +/* __jhash_mix -- mix 3 32-bit values reversibly. */ +#define __jhash_mix(a, b, c) \ +{ \ + a -= c; a ^= rol32(c, 4); c += b; \ + b -= a; b ^= rol32(a, 6); a += c; \ + c -= b; c ^= rol32(b, 8); b += a; \ + a -= c; a ^= rol32(c, 16); c += b; \ + b -= a; b ^= rol32(a, 19); a += c; \ + c -= b; c ^= rol32(b, 4); b += a; \ +} -/* NOTE: Arguments are modified. */ -#define __jhash_mix(a, b, c) \ -{ \ - a -= b; a -= c; a ^= (c>>13); \ - b -= c; b -= a; b ^= (a<<8); \ - c -= a; c -= b; c ^= (b>>13); \ - a -= b; a -= c; a ^= (c>>12); \ - b -= c; b -= a; b ^= (a<<16); \ - c -= a; c -= b; c ^= (b>>5); \ - a -= b; a -= c; a ^= (c>>3); \ - b -= c; b -= a; b ^= (a<<10); \ - c -= a; c -= b; c ^= (b>>15); \ +/* __jhash_final - final mixing of 3 32-bit values (a,b,c) into c */ +#define __jhash_final(a, b, c) \ +{ \ + c ^= b; c -= rol32(b, 14); \ + a ^= c; a -= rol32(c, 11); \ + b ^= a; b -= rol32(a, 25); \ + c ^= b; c -= rol32(b, 16); \ + a ^= c; a -= rol32(c, 4); \ + b ^= a; b -= rol32(a, 14); \ + c ^= b; c -= rol32(b, 24); \ } -/* The golden ration: an arbitrary value */ -#define JHASH_GOLDEN_RATIO 0x9e3779b9 +/* An arbitrary initial parameter */ +#define JHASH_INITVAL 0xdeadbeef -/* The most generic version, hashes an arbitrary sequence - * of bytes. No alignment or length assumptions are made about - * the input key. +/* jhash - hash an arbitrary key + * @k: sequence of bytes as key + * @length: the length of the key + * @initval: the previous hash, or an arbitray value + * + * The generic version, hashes an arbitrary sequence of bytes. + * No alignment or length assumptions are made about the input key. + * + * Returns the hash value of the key. The result depends on endianness. */ static inline u32 jhash(const void *key, u32 length, u32 initval) { - u32 a, b, c, len; + u32 a, b, c; const u8 *k = key; - len = length; - a = b = JHASH_GOLDEN_RATIO; - c = initval; - - while (len >= 12) { - a += (k[0] +((u32)k[1]<<8) +((u32)k[2]<<16) +((u32)k[3]<<24)); - b += (k[4] +((u32)k[5]<<8) +((u32)k[6]<<16) +((u32)k[7]<<24)); - c += (k[8] +((u32)k[9]<<8) +((u32)k[10]<<16)+((u32)k[11]<<24)); - - __jhash_mix(a,b,c); + /* Set up the internal state */ + a = b = c = JHASH_INITVAL + length + initval; + /* All but the last block: affect some 32 bits of (a,b,c) */ + while (length > 12) { + a += __get_unaligned_cpu32(k); + b += __get_unaligned_cpu32(k + 4); + c += __get_unaligned_cpu32(k + 8); + __jhash_mix(a, b, c); + length -= 12; k += 12; - len -= 12; } - - c += length; - switch (len) { - case 11: c += ((u32)k[10]<<24); - case 10: c += ((u32)k[9]<<16); - case 9 : c += ((u32)k[8]<<8); - case 8 : b += ((u32)k[7]<<24); - case 7 : b += ((u32)k[6]<<16); - case 6 : b += ((u32)k[5]<<8); - case 5 : b += k[4]; - case 4 : a += ((u32)k[3]<<24); - case 3 : a += ((u32)k[2]<<16); - case 2 : a += ((u32)k[1]<<8); - case 1 : a += k[0]; - }; - - __jhash_mix(a,b,c); + /* Last block: affect all 32 bits of (c) */ + /* All the case statements fall through */ + switch (length) { + case 12: c += (u32)k[11]<<24; + case 11: c += (u32)k[10]<<16; + case 10: c += (u32)k[9]<<8; + case 9: c += k[8]; + case 8: b += (u32)k[7]<<24; + case 7: b += (u32)k[6]<<16; + case 6: b += (u32)k[5]<<8; + case 5: b += k[4]; + case 4: a += (u32)k[3]<<24; + case 3: a += (u32)k[2]<<16; + case 2: a += (u32)k[1]<<8; + case 1: a += k[0]; + __jhash_final(a, b, c); + case 0: /* Nothing left to add */ + break; + } return c; } -/* A special optimized version that handles 1 or more of u32s. - * The length parameter here is the number of u32s in the key. +/* jhash2 - hash an array of u32's + * @k: the key which must be an array of u32's + * @length: the number of u32's in the key + * @initval: the previous hash, or an arbitray value + * + * Returns the hash value of the key. */ static inline u32 jhash2(const u32 *k, u32 length, u32 initval) { - u32 a, b, c, len; + u32 a, b, c; - a = b = JHASH_GOLDEN_RATIO; - c = initval; - len = length; + /* Set up the internal state */ + a = b = c = JHASH_INITVAL + (length<<2) + initval; - while (len >= 3) { + /* Handle most of the key */ + while (length > 3) { a += k[0]; b += k[1]; c += k[2]; __jhash_mix(a, b, c); - k += 3; len -= 3; + length -= 3; + k += 3; } - c += length * 4; - - switch (len) { - case 2 : b += k[1]; - case 1 : a += k[0]; - }; - - __jhash_mix(a,b,c); + /* Handle the last 3 u32's: all the case statements fall through */ + switch (length) { + case 3: c += k[2]; + case 2: b += k[1]; + case 1: a += k[0]; + __jhash_final(a, b, c); + case 0: /* Nothing left to add */ + break; + } return c; } -/* A special ultra-optimized versions that knows they are hashing exactly - * 3, 2 or 1 word(s). - * - * NOTE: In particular the "c += length; __jhash_mix(a,b,c);" normally - * done at the end is not done here. - */ +/* jhash_3words - hash exactly 3, 2 or 1 word(s) */ static inline u32 jhash_3words(u32 a, u32 b, u32 c, u32 initval) { - a += JHASH_GOLDEN_RATIO; - b += JHASH_GOLDEN_RATIO; + a += JHASH_INITVAL; + b += JHASH_INITVAL; c += initval; - __jhash_mix(a, b, c); + __jhash_final(a, b, c); return c; } -- cgit v1.2.3 From 1f5a24794a54588ea3a9efd521be31d826e0b9d7 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Thu, 9 Dec 2010 12:02:18 -0800 Subject: timers: Rename timerlist infrastructure to timerqueue Thomas pointed out a namespace collision between the new timerlist infrastructure I introduced and the existing timer_list.c So to avoid confusion, I've renamed the timerlist infrastructure to timerqueue. Reported-by: Thomas Gleixner Signed-off-by: John Stultz --- include/linux/timerlist.h | 37 -------------- include/linux/timerqueue.h | 37 ++++++++++++++ lib/Makefile | 2 +- lib/timerlist.c | 118 --------------------------------------------- lib/timerqueue.c | 118 +++++++++++++++++++++++++++++++++++++++++++++ 5 files changed, 156 insertions(+), 156 deletions(-) delete mode 100644 include/linux/timerlist.h create mode 100644 include/linux/timerqueue.h delete mode 100644 lib/timerlist.c create mode 100644 lib/timerqueue.c (limited to 'include/linux') diff --git a/include/linux/timerlist.h b/include/linux/timerlist.h deleted file mode 100644 index c46b28ae6e4d..000000000000 --- a/include/linux/timerlist.h +++ /dev/null @@ -1,37 +0,0 @@ -#ifndef _LINUX_TIMERLIST_H -#define _LINUX_TIMERLIST_H - -#include -#include - - -struct timerlist_node { - struct rb_node node; - ktime_t expires; -}; - -struct timerlist_head { - struct rb_root head; - struct timerlist_node *next; -}; - - -extern void timerlist_add(struct timerlist_head *head, - struct timerlist_node *node); -extern void timerlist_del(struct timerlist_head *head, - struct timerlist_node *node); -extern struct timerlist_node *timerlist_getnext(struct timerlist_head *head); -extern struct timerlist_node *timerlist_iterate_next( - struct timerlist_node *node); - -static inline void timerlist_init(struct timerlist_node *node) -{ - RB_CLEAR_NODE(&node->node); -} - -static inline void timerlist_init_head(struct timerlist_head *head) -{ - head->head = RB_ROOT; - head->next = NULL; -} -#endif /* _LINUX_TIMERLIST_H */ diff --git a/include/linux/timerqueue.h b/include/linux/timerqueue.h new file mode 100644 index 000000000000..406b103894bd --- /dev/null +++ b/include/linux/timerqueue.h @@ -0,0 +1,37 @@ +#ifndef _LINUX_TIMERQUEUE_H +#define _LINUX_TIMERQUEUE_H + +#include +#include + + +struct timerqueue_node { + struct rb_node node; + ktime_t expires; +}; + +struct timerqueue_head { + struct rb_root head; + struct timerqueue_node *next; +}; + + +extern void timerqueue_add(struct timerqueue_head *head, + struct timerqueue_node *node); +extern void timerqueue_del(struct timerqueue_head *head, + struct timerqueue_node *node); +extern struct timerqueue_node *timerqueue_getnext(struct timerqueue_head *head); +extern struct timerqueue_node *timerqueue_iterate_next( + struct timerqueue_node *node); + +static inline void timerqueue_init(struct timerqueue_node *node) +{ + RB_CLEAR_NODE(&node->node); +} + +static inline void timerqueue_init_head(struct timerqueue_head *head) +{ + head->head = RB_ROOT; + head->next = NULL; +} +#endif /* _LINUX_TIMERQUEUE_H */ diff --git a/lib/Makefile b/lib/Makefile index 8b475cfb8195..9e2db72d128e 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -8,7 +8,7 @@ KBUILD_CFLAGS = $(subst -pg,,$(ORIG_CFLAGS)) endif lib-y := ctype.o string.o vsprintf.o cmdline.o \ - rbtree.o radix-tree.o dump_stack.o timerlist.o\ + rbtree.o radix-tree.o dump_stack.o timerqueue.o\ idr.o int_sqrt.o extable.o prio_tree.o \ sha1.o irq_regs.o reciprocal_div.o argv_split.o \ proportions.o prio_heap.o ratelimit.o show_mem.o \ diff --git a/lib/timerlist.c b/lib/timerlist.c deleted file mode 100644 index 9101b42fd13d..000000000000 --- a/lib/timerlist.c +++ /dev/null @@ -1,118 +0,0 @@ -/* - * Generic Timer-list - * - * Manages a simple list of timers, ordered by expiration time. - * Uses rbtrees for quick list adds and expiration. - * - * NOTE: All of the following functions need to be serialized - * to avoid races. No locking is done by this libary code. - * - * 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. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ - -#include -#include - -/** - * timerlist_add - Adds timer to timerlist. - * - * @head: head of timerlist - * @node: timer node to be added - * - * Adds the timer node to the timerlist, sorted by the - * node's expires value. - */ -void timerlist_add(struct timerlist_head *head, struct timerlist_node *node) -{ - struct rb_node **p = &head->head.rb_node; - struct rb_node *parent = NULL; - struct timerlist_node *ptr; - - /* Make sure we don't add nodes that are already added */ - WARN_ON_ONCE(!RB_EMPTY_NODE(&node->node)); - - while (*p) { - parent = *p; - ptr = rb_entry(parent, struct timerlist_node, node); - if (node->expires.tv64 < ptr->expires.tv64) - p = &(*p)->rb_left; - else - p = &(*p)->rb_right; - } - rb_link_node(&node->node, parent, p); - rb_insert_color(&node->node, &head->head); - - if (!head->next || node->expires.tv64 < head->next->expires.tv64) - head->next = node; -} - -/** - * timerlist_del - Removes a timer from the timerlist. - * - * @head: head of timerlist - * @node: timer node to be removed - * - * Removes the timer node from the timerlist. - */ -void timerlist_del(struct timerlist_head *head, struct timerlist_node *node) -{ - WARN_ON_ONCE(RB_EMPTY_NODE(&node->node)); - - /* update next pointer */ - if (head->next == node) { - struct rb_node *rbn = rb_next(&node->node); - - head->next = rbn ? - rb_entry(rbn, struct timerlist_node, node) : NULL; - } - rb_erase(&node->node, &head->head); - RB_CLEAR_NODE(&node->node); -} - - -/** - * timerlist_getnext - Returns the timer with the earlies expiration time - * - * @head: head of timerlist - * - * Returns a pointer to the timer node that has the - * earliest expiration time. - */ -struct timerlist_node *timerlist_getnext(struct timerlist_head *head) -{ - return head->next; -} - - -/** - * timerlist_iterate_next - Returns the timer after the provided timer - * - * @node: Pointer to a timer. - * - * Provides the timer that is after the given node. This is used, when - * necessary, to iterate through the list of timers in a timer list - * without modifying the list. - */ -struct timerlist_node *timerlist_iterate_next(struct timerlist_node *node) -{ - struct rb_node *next; - - if (!node) - return NULL; - next = rb_next(&node->node); - if (!next) - return NULL; - return container_of(next, struct timerlist_node, node); -} diff --git a/lib/timerqueue.c b/lib/timerqueue.c new file mode 100644 index 000000000000..f46de84d9467 --- /dev/null +++ b/lib/timerqueue.c @@ -0,0 +1,118 @@ +/* + * Generic Timer-queue + * + * Manages a simple queue of timers, ordered by expiration time. + * Uses rbtrees for quick list adds and expiration. + * + * NOTE: All of the following functions need to be serialized + * to avoid races. No locking is done by this libary code. + * + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#include +#include + +/** + * timerqueue_add - Adds timer to timerqueue. + * + * @head: head of timerqueue + * @node: timer node to be added + * + * Adds the timer node to the timerqueue, sorted by the + * node's expires value. + */ +void timerqueue_add(struct timerqueue_head *head, struct timerqueue_node *node) +{ + struct rb_node **p = &head->head.rb_node; + struct rb_node *parent = NULL; + struct timerqueue_node *ptr; + + /* Make sure we don't add nodes that are already added */ + WARN_ON_ONCE(!RB_EMPTY_NODE(&node->node)); + + while (*p) { + parent = *p; + ptr = rb_entry(parent, struct timerqueue_node, node); + if (node->expires.tv64 < ptr->expires.tv64) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + rb_link_node(&node->node, parent, p); + rb_insert_color(&node->node, &head->head); + + if (!head->next || node->expires.tv64 < head->next->expires.tv64) + head->next = node; +} + +/** + * timerqueue_del - Removes a timer from the timerqueue. + * + * @head: head of timerqueue + * @node: timer node to be removed + * + * Removes the timer node from the timerqueue. + */ +void timerqueue_del(struct timerqueue_head *head, struct timerqueue_node *node) +{ + WARN_ON_ONCE(RB_EMPTY_NODE(&node->node)); + + /* update next pointer */ + if (head->next == node) { + struct rb_node *rbn = rb_next(&node->node); + + head->next = rbn ? + rb_entry(rbn, struct timerqueue_node, node) : NULL; + } + rb_erase(&node->node, &head->head); + RB_CLEAR_NODE(&node->node); +} + + +/** + * timerqueue_getnext - Returns the timer with the earlies expiration time + * + * @head: head of timerqueue + * + * Returns a pointer to the timer node that has the + * earliest expiration time. + */ +struct timerqueue_node *timerqueue_getnext(struct timerqueue_head *head) +{ + return head->next; +} + + +/** + * timerqueue_iterate_next - Returns the timer after the provided timer + * + * @node: Pointer to a timer. + * + * Provides the timer that is after the given node. This is used, when + * necessary, to iterate through the list of timers in a timer list + * without modifying the list. + */ +struct timerqueue_node *timerqueue_iterate_next(struct timerqueue_node *node) +{ + struct rb_node *next; + + if (!node) + return NULL; + next = rb_next(&node->node); + if (!next) + return NULL; + return container_of(next, struct timerqueue_node, node); +} -- cgit v1.2.3 From 998adc3dda59f811966b3ccb21eb223680b25ec4 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Mon, 20 Sep 2010 19:19:17 -0700 Subject: hrtimers: Convert hrtimers to use timerlist infrastructure Converts the hrtimer code to use the new timerlist infrastructure Signed-off-by: John Stultz LKML Reference: <1290136329-18291-3-git-send-email-john.stultz@linaro.org> Reviewed-by: Thomas Gleixner CC: Alessandro Zummo CC: Thomas Gleixner CC: Richard Cochran --- include/linux/hrtimer.h | 32 +++++++++--------- kernel/hrtimer.c | 86 +++++++++++++++++------------------------------- kernel/time/timer_list.c | 8 ++--- 3 files changed, 49 insertions(+), 77 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index dd9954b79342..330586ffffbb 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -22,7 +22,7 @@ #include #include #include - +#include struct hrtimer_clock_base; struct hrtimer_cpu_base; @@ -79,8 +79,8 @@ enum hrtimer_restart { /** * struct hrtimer - the basic hrtimer structure - * @node: red black tree node for time ordered insertion - * @_expires: the absolute expiry time in the hrtimers internal + * @node: timerqueue node, which also manages node.expires, + * the absolute expiry time in the hrtimers internal * representation. The time is related to the clock on * which the timer is based. Is setup by adding * slack to the _softexpires value. For non range timers @@ -101,8 +101,7 @@ enum hrtimer_restart { * The hrtimer structure must be initialized by hrtimer_init() */ struct hrtimer { - struct rb_node node; - ktime_t _expires; + struct timerqueue_node node; ktime_t _softexpires; enum hrtimer_restart (*function)(struct hrtimer *); struct hrtimer_clock_base *base; @@ -141,8 +140,7 @@ struct hrtimer_sleeper { struct hrtimer_clock_base { struct hrtimer_cpu_base *cpu_base; clockid_t index; - struct rb_root active; - struct rb_node *first; + struct timerqueue_head active; ktime_t resolution; ktime_t (*get_time)(void); ktime_t softirq_time; @@ -183,43 +181,43 @@ struct hrtimer_cpu_base { static inline void hrtimer_set_expires(struct hrtimer *timer, ktime_t time) { - timer->_expires = time; + timer->node.expires = time; timer->_softexpires = time; } static inline void hrtimer_set_expires_range(struct hrtimer *timer, ktime_t time, ktime_t delta) { timer->_softexpires = time; - timer->_expires = ktime_add_safe(time, delta); + timer->node.expires = ktime_add_safe(time, delta); } static inline void hrtimer_set_expires_range_ns(struct hrtimer *timer, ktime_t time, unsigned long delta) { timer->_softexpires = time; - timer->_expires = ktime_add_safe(time, ns_to_ktime(delta)); + timer->node.expires = ktime_add_safe(time, ns_to_ktime(delta)); } static inline void hrtimer_set_expires_tv64(struct hrtimer *timer, s64 tv64) { - timer->_expires.tv64 = tv64; + timer->node.expires.tv64 = tv64; timer->_softexpires.tv64 = tv64; } static inline void hrtimer_add_expires(struct hrtimer *timer, ktime_t time) { - timer->_expires = ktime_add_safe(timer->_expires, time); + timer->node.expires = ktime_add_safe(timer->node.expires, time); timer->_softexpires = ktime_add_safe(timer->_softexpires, time); } static inline void hrtimer_add_expires_ns(struct hrtimer *timer, u64 ns) { - timer->_expires = ktime_add_ns(timer->_expires, ns); + timer->node.expires = ktime_add_ns(timer->node.expires, ns); timer->_softexpires = ktime_add_ns(timer->_softexpires, ns); } static inline ktime_t hrtimer_get_expires(const struct hrtimer *timer) { - return timer->_expires; + return timer->node.expires; } static inline ktime_t hrtimer_get_softexpires(const struct hrtimer *timer) @@ -229,7 +227,7 @@ static inline ktime_t hrtimer_get_softexpires(const struct hrtimer *timer) static inline s64 hrtimer_get_expires_tv64(const struct hrtimer *timer) { - return timer->_expires.tv64; + return timer->node.expires.tv64; } static inline s64 hrtimer_get_softexpires_tv64(const struct hrtimer *timer) { @@ -238,12 +236,12 @@ static inline s64 hrtimer_get_softexpires_tv64(const struct hrtimer *timer) static inline s64 hrtimer_get_expires_ns(const struct hrtimer *timer) { - return ktime_to_ns(timer->_expires); + return ktime_to_ns(timer->node.expires); } static inline ktime_t hrtimer_expires_remaining(const struct hrtimer *timer) { - return ktime_sub(timer->_expires, timer->base->get_time()); + return ktime_sub(timer->node.expires, timer->base->get_time()); } #ifdef CONFIG_HIGH_RES_TIMERS diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index ce669174f355..93976ad42f5a 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -516,10 +516,13 @@ hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal) for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) { struct hrtimer *timer; + struct timerqueue_node *next; - if (!base->first) + next = timerqueue_getnext(&base->active); + if (!next) continue; - timer = rb_entry(base->first, struct hrtimer, node); + timer = container_of(next, struct hrtimer, node); + expires = ktime_sub(hrtimer_get_expires(timer), base->offset); /* * clock_was_set() has changed base->offset so the @@ -840,48 +843,17 @@ EXPORT_SYMBOL_GPL(hrtimer_forward); static int enqueue_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base) { - struct rb_node **link = &base->active.rb_node; - struct rb_node *parent = NULL; - struct hrtimer *entry; - int leftmost = 1; - debug_activate(timer); - /* - * Find the right place in the rbtree: - */ - while (*link) { - parent = *link; - entry = rb_entry(parent, struct hrtimer, node); - /* - * We dont care about collisions. Nodes with - * the same expiry time stay together. - */ - if (hrtimer_get_expires_tv64(timer) < - hrtimer_get_expires_tv64(entry)) { - link = &(*link)->rb_left; - } else { - link = &(*link)->rb_right; - leftmost = 0; - } - } + timerqueue_add(&base->active, &timer->node); - /* - * Insert the timer to the rbtree and check whether it - * replaces the first pending timer - */ - if (leftmost) - base->first = &timer->node; - - rb_link_node(&timer->node, parent, link); - rb_insert_color(&timer->node, &base->active); /* * HRTIMER_STATE_ENQUEUED is or'ed to the current state to preserve the * state of a possibly running callback. */ timer->state |= HRTIMER_STATE_ENQUEUED; - return leftmost; + return (&timer->node == base->active.next); } /* @@ -901,12 +873,7 @@ static void __remove_hrtimer(struct hrtimer *timer, if (!(timer->state & HRTIMER_STATE_ENQUEUED)) goto out; - /* - * Remove the timer from the rbtree and replace the first - * entry pointer if necessary. - */ - if (base->first == &timer->node) { - base->first = rb_next(&timer->node); + if (&timer->node == timerqueue_getnext(&base->active)) { #ifdef CONFIG_HIGH_RES_TIMERS /* Reprogram the clock event device. if enabled */ if (reprogram && hrtimer_hres_active()) { @@ -919,7 +886,7 @@ static void __remove_hrtimer(struct hrtimer *timer, } #endif } - rb_erase(&timer->node, &base->active); + timerqueue_del(&base->active, &timer->node); out: timer->state = newstate; } @@ -1123,11 +1090,13 @@ ktime_t hrtimer_get_next_event(void) if (!hrtimer_hres_active()) { for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) { struct hrtimer *timer; + struct timerqueue_node *next; - if (!base->first) + next = timerqueue_getnext(&base->active); + if (!next) continue; - timer = rb_entry(base->first, struct hrtimer, node); + timer = container_of(next, struct hrtimer, node); delta.tv64 = hrtimer_get_expires_tv64(timer); delta = ktime_sub(delta, base->get_time()); if (delta.tv64 < mindelta.tv64) @@ -1157,6 +1126,7 @@ static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id, timer->base = &cpu_base->clock_base[clock_id]; hrtimer_init_timer_hres(timer); + timerqueue_init(&timer->node); #ifdef CONFIG_TIMER_STATS timer->start_site = NULL; @@ -1270,14 +1240,14 @@ retry: for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) { ktime_t basenow; - struct rb_node *node; + struct timerqueue_node *node; basenow = ktime_add(now, base->offset); - while ((node = base->first)) { + while ((node = timerqueue_getnext(&base->active))) { struct hrtimer *timer; - timer = rb_entry(node, struct hrtimer, node); + timer = container_of(node, struct hrtimer, node); /* * The immediate goal for using the softexpires is @@ -1433,7 +1403,7 @@ void hrtimer_run_pending(void) */ void hrtimer_run_queues(void) { - struct rb_node *node; + struct timerqueue_node *node; struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases); struct hrtimer_clock_base *base; int index, gettime = 1; @@ -1442,9 +1412,11 @@ void hrtimer_run_queues(void) return; for (index = 0; index < HRTIMER_MAX_CLOCK_BASES; index++) { - base = &cpu_base->clock_base[index]; + struct timerqueue_node *next; - if (!base->first) + base = &cpu_base->clock_base[index]; + next = timerqueue_getnext(&base->active); + if (!next) continue; if (gettime) { @@ -1454,10 +1426,10 @@ void hrtimer_run_queues(void) raw_spin_lock(&cpu_base->lock); - while ((node = base->first)) { + while ((node = next)) { struct hrtimer *timer; - timer = rb_entry(node, struct hrtimer, node); + timer = container_of(node, struct hrtimer, node); if (base->softirq_time.tv64 <= hrtimer_get_expires_tv64(timer)) break; @@ -1622,8 +1594,10 @@ static void __cpuinit init_hrtimers_cpu(int cpu) raw_spin_lock_init(&cpu_base->lock); - for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) + for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) { cpu_base->clock_base[i].cpu_base = cpu_base; + timerqueue_init_head(&cpu_base->clock_base[i].active); + } hrtimer_init_hres(cpu_base); } @@ -1634,10 +1608,10 @@ static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base, struct hrtimer_clock_base *new_base) { struct hrtimer *timer; - struct rb_node *node; + struct timerqueue_node *node; - while ((node = rb_first(&old_base->active))) { - timer = rb_entry(node, struct hrtimer, node); + while ((node = timerqueue_getnext(&old_base->active))) { + timer = container_of(node, struct hrtimer, node); BUG_ON(hrtimer_callback_running(timer)); debug_deactivate(timer); diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c index ab8f5e33fa92..32a19f9397fc 100644 --- a/kernel/time/timer_list.c +++ b/kernel/time/timer_list.c @@ -79,26 +79,26 @@ print_active_timers(struct seq_file *m, struct hrtimer_clock_base *base, { struct hrtimer *timer, tmp; unsigned long next = 0, i; - struct rb_node *curr; + struct timerqueue_node *curr; unsigned long flags; next_one: i = 0; raw_spin_lock_irqsave(&base->cpu_base->lock, flags); - curr = base->first; + curr = timerqueue_getnext(&base->active); /* * Crude but we have to do this O(N*N) thing, because * we have to unlock the base when printing: */ while (curr && i < next) { - curr = rb_next(curr); + curr = timerqueue_iterate_next(curr); i++; } if (curr) { - timer = rb_entry(curr, struct hrtimer, node); + timer = container_of(curr, struct hrtimer, node); tmp = *timer; raw_spin_unlock_irqrestore(&base->cpu_base->lock, flags); -- cgit v1.2.3 From 35d2856b4693e8de5d616307b56cef296b839157 Mon Sep 17 00:00:00 2001 From: Martin Willi Date: Wed, 8 Dec 2010 04:37:49 +0000 Subject: xfrm: Add Traffic Flow Confidentiality padding XFRM attribute The XFRMA_TFCPAD attribute for XFRM state installation configures Traffic Flow Confidentiality by padding ESP packets to a specified length. Signed-off-by: Martin Willi Acked-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/xfrm.h | 1 + include/net/xfrm.h | 1 + net/xfrm/xfrm_user.c | 19 +++++++++++++++++-- 3 files changed, 19 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/xfrm.h b/include/linux/xfrm.h index b971e3848493..930fdd2de79c 100644 --- a/include/linux/xfrm.h +++ b/include/linux/xfrm.h @@ -283,6 +283,7 @@ enum xfrm_attr_type_t { XFRMA_KMADDRESS, /* struct xfrm_user_kmaddress */ XFRMA_ALG_AUTH_TRUNC, /* struct xfrm_algo_auth */ XFRMA_MARK, /* struct xfrm_mark */ + XFRMA_TFCPAD, /* __u32 */ __XFRMA_MAX #define XFRMA_MAX (__XFRMA_MAX - 1) diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 7fa5b005893e..b9f385da758e 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -143,6 +143,7 @@ struct xfrm_state { struct xfrm_id id; struct xfrm_selector sel; struct xfrm_mark mark; + u32 tfcpad; u32 genid; diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 8bae6b22c846..8eb889510916 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -148,7 +148,8 @@ static int verify_newsa_info(struct xfrm_usersa_info *p, !attrs[XFRMA_ALG_AUTH_TRUNC]) || attrs[XFRMA_ALG_AEAD] || attrs[XFRMA_ALG_CRYPT] || - attrs[XFRMA_ALG_COMP]) + attrs[XFRMA_ALG_COMP] || + attrs[XFRMA_TFCPAD]) goto out; break; @@ -165,6 +166,9 @@ static int verify_newsa_info(struct xfrm_usersa_info *p, attrs[XFRMA_ALG_CRYPT]) && attrs[XFRMA_ALG_AEAD]) goto out; + if (attrs[XFRMA_TFCPAD] && + p->mode != XFRM_MODE_TUNNEL) + goto out; break; case IPPROTO_COMP: @@ -172,7 +176,8 @@ static int verify_newsa_info(struct xfrm_usersa_info *p, attrs[XFRMA_ALG_AEAD] || attrs[XFRMA_ALG_AUTH] || attrs[XFRMA_ALG_AUTH_TRUNC] || - attrs[XFRMA_ALG_CRYPT]) + attrs[XFRMA_ALG_CRYPT] || + attrs[XFRMA_TFCPAD]) goto out; break; @@ -186,6 +191,7 @@ static int verify_newsa_info(struct xfrm_usersa_info *p, attrs[XFRMA_ALG_CRYPT] || attrs[XFRMA_ENCAP] || attrs[XFRMA_SEC_CTX] || + attrs[XFRMA_TFCPAD] || !attrs[XFRMA_COADDR]) goto out; break; @@ -439,6 +445,9 @@ static struct xfrm_state *xfrm_state_construct(struct net *net, goto error; } + if (attrs[XFRMA_TFCPAD]) + x->tfcpad = nla_get_u32(attrs[XFRMA_TFCPAD]); + if (attrs[XFRMA_COADDR]) { x->coaddr = kmemdup(nla_data(attrs[XFRMA_COADDR]), sizeof(*x->coaddr), GFP_KERNEL); @@ -688,6 +697,9 @@ static int copy_to_user_state_extra(struct xfrm_state *x, if (x->encap) NLA_PUT(skb, XFRMA_ENCAP, sizeof(*x->encap), x->encap); + if (x->tfcpad) + NLA_PUT_U32(skb, XFRMA_TFCPAD, x->tfcpad); + if (xfrm_mark_put(skb, &x->mark)) goto nla_put_failure; @@ -2122,6 +2134,7 @@ static const struct nla_policy xfrma_policy[XFRMA_MAX+1] = { [XFRMA_MIGRATE] = { .len = sizeof(struct xfrm_user_migrate) }, [XFRMA_KMADDRESS] = { .len = sizeof(struct xfrm_user_kmaddress) }, [XFRMA_MARK] = { .len = sizeof(struct xfrm_mark) }, + [XFRMA_TFCPAD] = { .type = NLA_U32 }, }; static struct xfrm_link { @@ -2301,6 +2314,8 @@ static inline size_t xfrm_sa_len(struct xfrm_state *x) l += nla_total_size(sizeof(*x->calg)); if (x->encap) l += nla_total_size(sizeof(*x->encap)); + if (x->tfcpad) + l += nla_total_size(sizeof(x->tfcpad)); if (x->security) l += nla_total_size(sizeof(struct xfrm_user_sec_ctx) + x->security->ctx_len); -- cgit v1.2.3 From e596e6e4d578f2639416e620d367a3af34814a40 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Thu, 9 Dec 2010 12:08:35 +0000 Subject: ethtool: Report link-down while interface is down While an interface is down, many implementations of ethtool_ops::get_link, including the default, ethtool_op_get_link(), will report the last link state seen while the interface was up. In general the current physical link state is not available if the interface is down. Define ETHTOOL_GLINK to reflect whether the interface *and* any physical port have a working link, and consistently return 0 when the interface is down. Signed-off-by: Ben Hutchings Signed-off-by: David S. Miller --- include/linux/ethtool.h | 4 +++- net/core/ethtool.c | 17 +++++++++++++++-- 2 files changed, 18 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 6628a507fd3b..1908929204a9 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -691,7 +691,9 @@ struct ethtool_ops { #define ETHTOOL_GMSGLVL 0x00000007 /* Get driver message level */ #define ETHTOOL_SMSGLVL 0x00000008 /* Set driver msg level. */ #define ETHTOOL_NWAY_RST 0x00000009 /* Restart autonegotiation. */ -#define ETHTOOL_GLINK 0x0000000a /* Get link status (ethtool_value) */ +/* Get link status for host, i.e. whether the interface *and* the + * physical port (if there is one) are up (ethtool_value). */ +#define ETHTOOL_GLINK 0x0000000a #define ETHTOOL_GEEPROM 0x0000000b /* Get EEPROM data */ #define ETHTOOL_SEEPROM 0x0000000c /* Set EEPROM data. */ #define ETHTOOL_GCOALESCE 0x0000000e /* Get coalesce config */ diff --git a/net/core/ethtool.c b/net/core/ethtool.c index d5bc28818883..17741782a345 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -891,6 +891,20 @@ static int ethtool_nway_reset(struct net_device *dev) return dev->ethtool_ops->nway_reset(dev); } +static int ethtool_get_link(struct net_device *dev, char __user *useraddr) +{ + struct ethtool_value edata = { .cmd = ETHTOOL_GLINK }; + + if (!dev->ethtool_ops->get_link) + return -EOPNOTSUPP; + + edata.data = netif_running(dev) && dev->ethtool_ops->get_link(dev); + + if (copy_to_user(useraddr, &edata, sizeof(edata))) + return -EFAULT; + return 0; +} + static int ethtool_get_eeprom(struct net_device *dev, void __user *useraddr) { struct ethtool_eeprom eeprom; @@ -1530,8 +1544,7 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) rc = ethtool_nway_reset(dev); break; case ETHTOOL_GLINK: - rc = ethtool_get_value(dev, useraddr, ethcmd, - dev->ethtool_ops->get_link); + rc = ethtool_get_link(dev, useraddr); break; case ETHTOOL_GEEPROM: rc = ethtool_get_eeprom(dev, useraddr); -- cgit v1.2.3 From 45f74264e18449cf3c93cccaf098ee6e9524ab78 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sat, 11 Dec 2010 12:34:34 +0100 Subject: timerqueue: Make timerqueue_getnext() static inline No point in calling a function just to dereference a pointer. Signed-off-by: Thomas Gleixner Cc: John Stultz --- include/linux/timerqueue.h | 15 ++++++++++++++- lib/timerqueue.c | 14 -------------- 2 files changed, 14 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timerqueue.h b/include/linux/timerqueue.h index 406b103894bd..d24aabaca474 100644 --- a/include/linux/timerqueue.h +++ b/include/linux/timerqueue.h @@ -20,10 +20,23 @@ extern void timerqueue_add(struct timerqueue_head *head, struct timerqueue_node *node); extern void timerqueue_del(struct timerqueue_head *head, struct timerqueue_node *node); -extern struct timerqueue_node *timerqueue_getnext(struct timerqueue_head *head); extern struct timerqueue_node *timerqueue_iterate_next( struct timerqueue_node *node); +/** + * timerqueue_getnext - Returns the timer with the earlies expiration time + * + * @head: head of timerqueue + * + * Returns a pointer to the timer node that has the + * earliest expiration time. + */ +static inline +struct timerqueue_node *timerqueue_getnext(struct timerqueue_head *head) +{ + return head->next; +} + static inline void timerqueue_init(struct timerqueue_node *node) { RB_CLEAR_NODE(&node->node); diff --git a/lib/timerqueue.c b/lib/timerqueue.c index 444b0934af92..e3a1050e6820 100644 --- a/lib/timerqueue.c +++ b/lib/timerqueue.c @@ -84,20 +84,6 @@ void timerqueue_del(struct timerqueue_head *head, struct timerqueue_node *node) } EXPORT_SYMBOL_GPL(timerqueue_del); -/** - * timerqueue_getnext - Returns the timer with the earlies expiration time - * - * @head: head of timerqueue - * - * Returns a pointer to the timer node that has the - * earliest expiration time. - */ -struct timerqueue_node *timerqueue_getnext(struct timerqueue_head *head) -{ - return head->next; -} -EXPORT_SYMBOL_GPL(timerqueue_getnext); - /** * timerqueue_iterate_next - Returns the timer after the provided timer * -- cgit v1.2.3 From dbd2fd656f2060abfd3a16257f8b51ec60f6d2ed Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 9 Dec 2010 19:58:59 +0100 Subject: cfg80211/nl80211: separate unicast/multicast default TX keys Allow userspace to specify that a given key is default only for unicast and/or multicast transmissions. Only WEP keys are for both, WPA/RSN keys set here are GTKs for multicast only. For more future flexibility, allow to specify all combiations. Wireless extensions can only set both so use nl80211; WEP keys (connect keys) must be set as default for both (but 802.1X WEP is still possible). Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- drivers/net/wireless/iwmc3200wifi/cfg80211.c | 3 +- drivers/net/wireless/libertas/cfg.c | 3 +- drivers/net/wireless/rndis_wlan.c | 4 +- include/linux/nl80211.h | 27 ++++++ include/net/cfg80211.h | 5 +- net/mac80211/cfg.c | 3 +- net/wireless/nl80211.c | 125 +++++++++++++++++++++++---- net/wireless/util.c | 3 +- net/wireless/wext-compat.c | 8 +- 9 files changed, 152 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/wireless/iwmc3200wifi/cfg80211.c b/drivers/net/wireless/iwmc3200wifi/cfg80211.c index c6c0eff9b5ed..5a4982271e96 100644 --- a/drivers/net/wireless/iwmc3200wifi/cfg80211.c +++ b/drivers/net/wireless/iwmc3200wifi/cfg80211.c @@ -225,7 +225,8 @@ static int iwm_cfg80211_del_key(struct wiphy *wiphy, struct net_device *ndev, static int iwm_cfg80211_set_default_key(struct wiphy *wiphy, struct net_device *ndev, - u8 key_index) + u8 key_index, bool unicast, + bool multicast) { struct iwm_priv *iwm = ndev_to_iwm(ndev); diff --git a/drivers/net/wireless/libertas/cfg.c b/drivers/net/wireless/libertas/cfg.c index dee32d3681a5..300be1931826 100644 --- a/drivers/net/wireless/libertas/cfg.c +++ b/drivers/net/wireless/libertas/cfg.c @@ -1422,7 +1422,8 @@ static int lbs_cfg_disconnect(struct wiphy *wiphy, struct net_device *dev, static int lbs_cfg_set_default_key(struct wiphy *wiphy, struct net_device *netdev, - u8 key_index) + u8 key_index, bool unicast, + bool multicast) { struct lbs_private *priv = wiphy_priv(wiphy); diff --git a/drivers/net/wireless/rndis_wlan.c b/drivers/net/wireless/rndis_wlan.c index 19f3d568f700..4a4f00591447 100644 --- a/drivers/net/wireless/rndis_wlan.c +++ b/drivers/net/wireless/rndis_wlan.c @@ -554,7 +554,7 @@ static int rndis_del_key(struct wiphy *wiphy, struct net_device *netdev, u8 key_index, bool pairwise, const u8 *mac_addr); static int rndis_set_default_key(struct wiphy *wiphy, struct net_device *netdev, - u8 key_index); + u8 key_index, bool unicast, bool multicast); static int rndis_get_station(struct wiphy *wiphy, struct net_device *dev, u8 *mac, struct station_info *sinfo); @@ -2381,7 +2381,7 @@ static int rndis_del_key(struct wiphy *wiphy, struct net_device *netdev, } static int rndis_set_default_key(struct wiphy *wiphy, struct net_device *netdev, - u8 key_index) + u8 key_index, bool unicast, bool multicast) { struct rndis_wlan_private *priv = wiphy_priv(wiphy); struct usbnet *usbdev = priv->usbdev; diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 380421253d16..b8fa25d741ba 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -851,6 +851,10 @@ enum nl80211_commands { * * @NL80211_ATTR_BSS_HTOPMODE: HT operation mode (u16) * + * @NL80211_ATTR_KEY_DEFAULT_TYPES: A nested attribute containing flags + * attributes, specifying what a key should be set as default as. + * See &enum nl80211_key_default_types. + * * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use */ @@ -1029,6 +1033,8 @@ enum nl80211_attrs { NL80211_ATTR_BSS_HT_OPMODE, + NL80211_ATTR_KEY_DEFAULT_TYPES, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -1774,6 +1780,23 @@ enum nl80211_wpa_versions { NL80211_WPA_VERSION_2 = 1 << 1, }; +/** + * enum nl80211_key_default_types - key default types + * @__NL80211_KEY_DEFAULT_TYPE_INVALID: invalid + * @NL80211_KEY_DEFAULT_TYPE_UNICAST: key should be used as default + * unicast key + * @NL80211_KEY_DEFAULT_TYPE_MULTICAST: key should be used as default + * multicast key + * @NUM_NL80211_KEY_DEFAULT_TYPES: number of default types + */ +enum nl80211_key_default_types { + __NL80211_KEY_DEFAULT_TYPE_INVALID, + NL80211_KEY_DEFAULT_TYPE_UNICAST, + NL80211_KEY_DEFAULT_TYPE_MULTICAST, + + NUM_NL80211_KEY_DEFAULT_TYPES +}; + /** * enum nl80211_key_attributes - key attributes * @__NL80211_KEY_INVALID: invalid @@ -1790,6 +1813,9 @@ enum nl80211_wpa_versions { * @NL80211_KEY_TYPE: the key type from enum nl80211_key_type, if not * specified the default depends on whether a MAC address was * given with the command using the key or not (u32) + * @NL80211_KEY_DEFAULT_TYPES: A nested attribute containing flags + * attributes, specifying what a key should be set as default as. + * See &enum nl80211_key_default_types. * @__NL80211_KEY_AFTER_LAST: internal * @NL80211_KEY_MAX: highest key attribute */ @@ -1802,6 +1828,7 @@ enum nl80211_key_attributes { NL80211_KEY_DEFAULT, NL80211_KEY_DEFAULT_MGMT, NL80211_KEY_TYPE, + NL80211_KEY_DEFAULT_TYPES, /* keep last */ __NL80211_KEY_AFTER_LAST, diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 4d5acb013636..22be7c625b70 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1211,7 +1211,7 @@ struct cfg80211_ops { u8 key_index, bool pairwise, const u8 *mac_addr); int (*set_default_key)(struct wiphy *wiphy, struct net_device *netdev, - u8 key_index); + u8 key_index, bool unicast, bool multicast); int (*set_default_mgmt_key)(struct wiphy *wiphy, struct net_device *netdev, u8 key_index); @@ -1393,6 +1393,8 @@ struct cfg80211_ops { * control port protocol ethertype. The device also honours the * control_port_no_encrypt flag. * @WIPHY_FLAG_IBSS_RSN: The device supports IBSS RSN. + * @WIPHY_FLAG_SUPPORTS_SEPARATE_DEFAULT_KEYS: The device supports separate + * unicast and multicast TX keys. */ enum wiphy_flags { WIPHY_FLAG_CUSTOM_REGULATORY = BIT(0), @@ -1404,6 +1406,7 @@ enum wiphy_flags { WIPHY_FLAG_4ADDR_STATION = BIT(6), WIPHY_FLAG_CONTROL_PORT_PROTOCOL = BIT(7), WIPHY_FLAG_IBSS_RSN = BIT(8), + WIPHY_FLAG_SUPPORTS_SEPARATE_DEFAULT_KEYS= BIT(9), }; struct mac_address { diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index c30b8b72eedb..12f7dc048d34 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -295,7 +295,8 @@ static int ieee80211_get_key(struct wiphy *wiphy, struct net_device *dev, static int ieee80211_config_default_key(struct wiphy *wiphy, struct net_device *dev, - u8 key_idx) + u8 key_idx, bool uni, + bool multi) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 73a7f6d354c9..53f044370cde 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -171,6 +171,7 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = { [NL80211_ATTR_WIPHY_ANTENNA_RX] = { .type = NLA_U32 }, [NL80211_ATTR_MCAST_RATE] = { .type = NLA_U32 }, [NL80211_ATTR_OFFCHANNEL_TX_OK] = { .type = NLA_FLAG }, + [NL80211_ATTR_KEY_DEFAULT_TYPES] = { .type = NLA_NESTED }, }; /* policy for the key attributes */ @@ -182,6 +183,14 @@ static const struct nla_policy nl80211_key_policy[NL80211_KEY_MAX + 1] = { [NL80211_KEY_DEFAULT] = { .type = NLA_FLAG }, [NL80211_KEY_DEFAULT_MGMT] = { .type = NLA_FLAG }, [NL80211_KEY_TYPE] = { .type = NLA_U32 }, + [NL80211_KEY_DEFAULT_TYPES] = { .type = NLA_NESTED }, +}; + +/* policy for the key default flags */ +static const struct nla_policy +nl80211_key_default_policy[NUM_NL80211_KEY_DEFAULT_TYPES] = { + [NL80211_KEY_DEFAULT_TYPE_UNICAST] = { .type = NLA_FLAG }, + [NL80211_KEY_DEFAULT_TYPE_MULTICAST] = { .type = NLA_FLAG }, }; /* ifidx get helper */ @@ -314,6 +323,7 @@ struct key_parse { int idx; int type; bool def, defmgmt; + bool def_uni, def_multi; }; static int nl80211_parse_key_new(struct nlattr *key, struct key_parse *k) @@ -327,6 +337,13 @@ static int nl80211_parse_key_new(struct nlattr *key, struct key_parse *k) k->def = !!tb[NL80211_KEY_DEFAULT]; k->defmgmt = !!tb[NL80211_KEY_DEFAULT_MGMT]; + if (k->def) { + k->def_uni = true; + k->def_multi = true; + } + if (k->defmgmt) + k->def_multi = true; + if (tb[NL80211_KEY_IDX]) k->idx = nla_get_u8(tb[NL80211_KEY_IDX]); @@ -349,6 +366,19 @@ static int nl80211_parse_key_new(struct nlattr *key, struct key_parse *k) return -EINVAL; } + if (tb[NL80211_KEY_DEFAULT_TYPES]) { + struct nlattr *kdt[NUM_NL80211_KEY_DEFAULT_TYPES]; + int err = nla_parse_nested(kdt, + NUM_NL80211_KEY_DEFAULT_TYPES - 1, + tb[NL80211_KEY_DEFAULT_TYPES], + nl80211_key_default_policy); + if (err) + return err; + + k->def_uni = kdt[NL80211_KEY_DEFAULT_TYPE_UNICAST]; + k->def_multi = kdt[NL80211_KEY_DEFAULT_TYPE_MULTICAST]; + } + return 0; } @@ -373,12 +403,32 @@ static int nl80211_parse_key_old(struct genl_info *info, struct key_parse *k) k->def = !!info->attrs[NL80211_ATTR_KEY_DEFAULT]; k->defmgmt = !!info->attrs[NL80211_ATTR_KEY_DEFAULT_MGMT]; + if (k->def) { + k->def_uni = true; + k->def_multi = true; + } + if (k->defmgmt) + k->def_multi = true; + if (info->attrs[NL80211_ATTR_KEY_TYPE]) { k->type = nla_get_u32(info->attrs[NL80211_ATTR_KEY_TYPE]); if (k->type < 0 || k->type >= NUM_NL80211_KEYTYPES) return -EINVAL; } + if (info->attrs[NL80211_ATTR_KEY_DEFAULT_TYPES]) { + struct nlattr *kdt[NUM_NL80211_KEY_DEFAULT_TYPES]; + int err = nla_parse_nested( + kdt, NUM_NL80211_KEY_DEFAULT_TYPES - 1, + info->attrs[NL80211_ATTR_KEY_DEFAULT_TYPES], + nl80211_key_default_policy); + if (err) + return err; + + k->def_uni = kdt[NL80211_KEY_DEFAULT_TYPE_UNICAST]; + k->def_multi = kdt[NL80211_KEY_DEFAULT_TYPE_MULTICAST]; + } + return 0; } @@ -401,6 +451,11 @@ static int nl80211_parse_key(struct genl_info *info, struct key_parse *k) if (k->def && k->defmgmt) return -EINVAL; + if (k->defmgmt) { + if (k->def_uni || !k->def_multi) + return -EINVAL; + } + if (k->idx != -1) { if (k->defmgmt) { if (k->idx < 4 || k->idx > 5) @@ -450,6 +505,8 @@ nl80211_parse_connkeys(struct cfg80211_registered_device *rdev, goto error; def = 1; result->def = parse.idx; + if (!parse.def_uni || !parse.def_multi) + goto error; } else if (parse.defmgmt) goto error; err = cfg80211_validate_key_settings(rdev, &parse.p, @@ -1586,8 +1643,6 @@ static int nl80211_set_key(struct sk_buff *skb, struct genl_info *info) struct key_parse key; int err; struct net_device *dev = info->user_ptr[1]; - int (*func)(struct wiphy *wiphy, struct net_device *netdev, - u8 key_index); err = nl80211_parse_key(info, &key); if (err) @@ -1600,27 +1655,61 @@ static int nl80211_set_key(struct sk_buff *skb, struct genl_info *info) if (!key.def && !key.defmgmt) return -EINVAL; - if (key.def) - func = rdev->ops->set_default_key; - else - func = rdev->ops->set_default_mgmt_key; + wdev_lock(dev->ieee80211_ptr); - if (!func) - return -EOPNOTSUPP; + if (key.def) { + if (!rdev->ops->set_default_key) { + err = -EOPNOTSUPP; + goto out; + } - wdev_lock(dev->ieee80211_ptr); - err = nl80211_key_allowed(dev->ieee80211_ptr); - if (!err) - err = func(&rdev->wiphy, dev, key.idx); + err = nl80211_key_allowed(dev->ieee80211_ptr); + if (err) + goto out; + + if (!(rdev->wiphy.flags & + WIPHY_FLAG_SUPPORTS_SEPARATE_DEFAULT_KEYS)) { + if (!key.def_uni || !key.def_multi) { + err = -EOPNOTSUPP; + goto out; + } + } + + err = rdev->ops->set_default_key(&rdev->wiphy, dev, key.idx, + key.def_uni, key.def_multi); + + if (err) + goto out; #ifdef CONFIG_CFG80211_WEXT - if (!err) { - if (func == rdev->ops->set_default_key) - dev->ieee80211_ptr->wext.default_key = key.idx; - else - dev->ieee80211_ptr->wext.default_mgmt_key = key.idx; - } + dev->ieee80211_ptr->wext.default_key = key.idx; +#endif + } else { + if (key.def_uni || !key.def_multi) { + err = -EINVAL; + goto out; + } + + if (!rdev->ops->set_default_mgmt_key) { + err = -EOPNOTSUPP; + goto out; + } + + err = nl80211_key_allowed(dev->ieee80211_ptr); + if (err) + goto out; + + err = rdev->ops->set_default_mgmt_key(&rdev->wiphy, + dev, key.idx); + if (err) + goto out; + +#ifdef CONFIG_CFG80211_WEXT + dev->ieee80211_ptr->wext.default_mgmt_key = key.idx; #endif + } + + out: wdev_unlock(dev->ieee80211_ptr); return err; diff --git a/net/wireless/util.c b/net/wireless/util.c index 4de624ca4c63..7620ae2fcf18 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -689,7 +689,8 @@ void cfg80211_upload_connect_keys(struct wireless_dev *wdev) continue; } if (wdev->connect_keys->def == i) - if (rdev->ops->set_default_key(wdev->wiphy, dev, i)) { + if (rdev->ops->set_default_key(wdev->wiphy, dev, + i, true, true)) { netdev_err(dev, "failed to set defkey %d\n", i); continue; } diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c index 12222ee6ebf2..3e5dbd4e4cd5 100644 --- a/net/wireless/wext-compat.c +++ b/net/wireless/wext-compat.c @@ -548,8 +548,8 @@ static int __cfg80211_set_encryption(struct cfg80211_registered_device *rdev, __cfg80211_leave_ibss(rdev, wdev->netdev, true); rejoin = true; } - err = rdev->ops->set_default_key(&rdev->wiphy, - dev, idx); + err = rdev->ops->set_default_key(&rdev->wiphy, dev, + idx, true, true); } if (!err) { wdev->wext.default_key = idx; @@ -627,8 +627,8 @@ int cfg80211_wext_siwencode(struct net_device *dev, err = 0; wdev_lock(wdev); if (wdev->current_bss) - err = rdev->ops->set_default_key(&rdev->wiphy, - dev, idx); + err = rdev->ops->set_default_key(&rdev->wiphy, dev, + idx, true, true); if (!err) wdev->wext.default_key = idx; wdev_unlock(wdev); -- cgit v1.2.3 From 44316cb1e97a1e7f76eb3f07e5b0ba91d72e9693 Mon Sep 17 00:00:00 2001 From: Bing Zhao Date: Thu, 9 Dec 2010 18:24:41 -0800 Subject: ieee80211: add Parameter Set Count bitmask WMM IE QoS Info field lower 4 bits: Parameter Set Count Signed-off-by: Bing Zhao Signed-off-by: John W. Linville --- include/linux/ieee80211.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 351c0ab4e284..7f2354534242 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -122,6 +122,7 @@ /* U-APSD queue for WMM IEs sent by AP */ #define IEEE80211_WMM_IE_AP_QOSINFO_UAPSD (1<<7) +#define IEEE80211_WMM_IE_AP_QOSINFO_PARAM_SET_CNT_MASK 0x0f /* U-APSD queues for WMM IEs sent by STA */ #define IEEE80211_WMM_IE_STA_QOSINFO_AC_VO (1<<0) -- cgit v1.2.3 From 53dde5f385bc56e312f78b7cb25ffaf8efd4735d Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Tue, 16 Nov 2010 13:23:50 -0800 Subject: bootmem: Add alloc_bootmem_align() Add an alloc_bootmem_align() interface to allocate bootmem with specified alignment. This is necessary to be able to allocate the xsave area in a subsequent patch. Signed-off-by: Suresh Siddha LKML-Reference: <20101116212441.977574826@sbsiddha-MOBL3.sc.intel.com> Acked-by: H. Peter Anvin Signed-off-by: H. Peter Anvin Cc: --- include/linux/bootmem.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 266ab9291232..499dfe982a0e 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -105,6 +105,8 @@ extern void *__alloc_bootmem_low_node(pg_data_t *pgdat, #define alloc_bootmem(x) \ __alloc_bootmem(x, SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS)) +#define alloc_bootmem_align(x, align) \ + __alloc_bootmem(x, align, __pa(MAX_DMA_ADDRESS)) #define alloc_bootmem_nopanic(x) \ __alloc_bootmem_nopanic(x, SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS)) #define alloc_bootmem_pages(x) \ -- cgit v1.2.3 From 62731fa0c893515dc6cbc3e0a2879a92793c735f Mon Sep 17 00:00:00 2001 From: Alexey Zaytsev Date: Mon, 22 Nov 2010 00:33:03 +0000 Subject: fanotify: split version into version and metadata_len To implement per event type optional headers we are interested in knowing how long the metadata structure is. This patch slits the __u32 version field into a __u8 version and a __u16 metadata_len field (with __u8 left over). This should allow for backwards compat ABI. Signed-off-by: Alexey Zaytsev [rewrote descrtion and changed object sizes and ordering - eparis] Signed-off-by: Eric Paris --- include/linux/fanotify.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index c73224315aee..6c6133f76e16 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -83,11 +83,13 @@ FAN_ALL_PERM_EVENTS |\ FAN_Q_OVERFLOW) -#define FANOTIFY_METADATA_VERSION 2 +#define FANOTIFY_METADATA_VERSION 3 struct fanotify_event_metadata { __u32 event_len; - __u32 vers; + __u8 vers; + __u8 reserved; + __u16 metadata_len; __aligned_u64 mask; __s32 fd; __s32 pid; -- cgit v1.2.3 From a293911d4fd5e8593dbf478399a77f990d466269 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 14 Dec 2010 17:54:28 +0100 Subject: nl80211: advertise maximum remain-on-channel duration With the upcoming hardware offload implementation, some devices will have a different maximum duration for the remain-on-channel command. Advertise the maximum duration in mac80211, and make mac80211 set it. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/linux/nl80211.h | 5 +++++ include/net/cfg80211.h | 5 +++++ net/mac80211/main.c | 2 ++ net/wireless/nl80211.c | 7 ++++++- 4 files changed, 18 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index b8fa25d741ba..1cee56b3a79a 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -773,6 +773,9 @@ enum nl80211_commands { * cache, a wiphy attribute. * * @NL80211_ATTR_DURATION: Duration of an operation in milliseconds, u32. + * @NL80211_ATTR_MAX_REMAIN_ON_CHANNEL_DURATION: Device attribute that + * specifies the maximum duration that can be requested with the + * remain-on-channel operation, in milliseconds, u32. * * @NL80211_ATTR_COOKIE: Generic 64-bit cookie to identify objects. * @@ -1035,6 +1038,8 @@ enum nl80211_attrs { NL80211_ATTR_KEY_DEFAULT_TYPES, + NL80211_ATTR_MAX_REMAIN_ON_CHANNEL_DURATION, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 22be7c625b70..f45e15f12446 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1474,6 +1474,9 @@ struct ieee80211_txrx_stypes { * * @available_antennas: bitmap of antennas which are available to configure. * antenna configuration commands will be rejected unless this is set. + * + * @max_remain_on_channel_duration: Maximum time a remain-on-channel operation + * may request, if implemented. */ struct wiphy { /* assign these fields before you register the wiphy */ @@ -1511,6 +1514,8 @@ struct wiphy { char fw_version[ETHTOOL_BUSINFO_LEN]; u32 hw_version; + u16 max_remain_on_channel_duration; + u8 max_num_pmkids; u32 available_antennas; diff --git a/net/mac80211/main.c b/net/mac80211/main.c index f7bdb7c78879..d87eb005690f 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -745,6 +745,8 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) } } + local->hw.wiphy->max_remain_on_channel_duration = 5000; + result = wiphy_register(local->hw.wiphy); if (result < 0) goto fail_wiphy_register; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 53f044370cde..594a6ac8b9d2 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -755,6 +755,10 @@ static int nl80211_send_wiphy(struct sk_buff *msg, u32 pid, u32 seq, int flags, nla_nest_end(msg, nl_cmds); + if (dev->ops->remain_on_channel) + NLA_PUT_U32(msg, NL80211_ATTR_MAX_REMAIN_ON_CHANNEL_DURATION, + dev->wiphy.max_remain_on_channel_duration); + /* for now at least assume all drivers have it */ if (dev->ops->mgmt_tx) NLA_PUT_FLAG(msg, NL80211_ATTR_OFFCHANNEL_TX_OK); @@ -4228,7 +4232,8 @@ static int nl80211_remain_on_channel(struct sk_buff *skb, * We should be on that channel for at least one jiffie, * and more than 5 seconds seems excessive. */ - if (!duration || !msecs_to_jiffies(duration) || duration > 5000) + if (!duration || !msecs_to_jiffies(duration) || + duration > rdev->wiphy.max_remain_on_channel_duration) return -EINVAL; if (!rdev->ops->remain_on_channel) -- cgit v1.2.3 From 2e80a82a49c4c7eca4e35734380f28298ba5db19 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 17 Nov 2010 23:17:36 +0100 Subject: perf: Dynamic pmu types Extend the perf_pmu_register() interface to allow for named and dynamic pmu types. Because we need to support the existing static types we cannot use dynamic types for everything, hence provide a type argument. If we want to enumerate the PMUs they need a name, provide one. Signed-off-by: Peter Zijlstra LKML-Reference: <20101117222056.259707703@chello.nl> Signed-off-by: Ingo Molnar --- arch/alpha/kernel/perf_event.c | 2 +- arch/arm/kernel/perf_event.c | 2 +- arch/powerpc/kernel/perf_event.c | 2 +- arch/powerpc/kernel/perf_event_fsl_emb.c | 2 +- arch/sh/kernel/perf_event.c | 2 +- arch/sparc/kernel/perf_event.c | 2 +- arch/x86/kernel/cpu/perf_event.c | 2 +- include/linux/perf_event.h | 5 +++- kernel/hw_breakpoint.c | 2 +- kernel/perf_event.c | 48 ++++++++++++++++++++++++++++---- 10 files changed, 54 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/arch/alpha/kernel/perf_event.c b/arch/alpha/kernel/perf_event.c index 3283059b6e85..90561c45e7d8 100644 --- a/arch/alpha/kernel/perf_event.c +++ b/arch/alpha/kernel/perf_event.c @@ -882,7 +882,7 @@ int __init init_hw_perf_events(void) /* And set up PMU specification */ alpha_pmu = &ev67_pmu; - perf_pmu_register(&pmu); + perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW); return 0; } diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c index d45f70e5f2ee..fdfa4976b0bf 100644 --- a/arch/arm/kernel/perf_event.c +++ b/arch/arm/kernel/perf_event.c @@ -3034,7 +3034,7 @@ init_hw_perf_events(void) pr_info("no hardware support available\n"); } - perf_pmu_register(&pmu); + perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW); return 0; } diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/kernel/perf_event.c index 3129c855933c..567480705789 100644 --- a/arch/powerpc/kernel/perf_event.c +++ b/arch/powerpc/kernel/perf_event.c @@ -1379,7 +1379,7 @@ int register_power_pmu(struct power_pmu *pmu) freeze_events_kernel = MMCR0_FCHV; #endif /* CONFIG_PPC64 */ - perf_pmu_register(&power_pmu); + perf_pmu_register(&power_pmu, "cpu", PERF_TYPE_RAW); perf_cpu_notifier(power_pmu_notifier); return 0; diff --git a/arch/powerpc/kernel/perf_event_fsl_emb.c b/arch/powerpc/kernel/perf_event_fsl_emb.c index 7ecca59ddf77..4dcf5f831e9d 100644 --- a/arch/powerpc/kernel/perf_event_fsl_emb.c +++ b/arch/powerpc/kernel/perf_event_fsl_emb.c @@ -681,7 +681,7 @@ int register_fsl_emb_pmu(struct fsl_emb_pmu *pmu) pr_info("%s performance monitor hardware support registered\n", pmu->name); - perf_pmu_register(&fsl_emb_pmu); + perf_pmu_register(&fsl_emb_pmu, "cpu", PERF_TYPE_RAW); return 0; } diff --git a/arch/sh/kernel/perf_event.c b/arch/sh/kernel/perf_event.c index 5a4b33435650..2ee21a47b5af 100644 --- a/arch/sh/kernel/perf_event.c +++ b/arch/sh/kernel/perf_event.c @@ -389,7 +389,7 @@ int __cpuinit register_sh_pmu(struct sh_pmu *_pmu) WARN_ON(_pmu->num_events > MAX_HWEVENTS); - perf_pmu_register(&pmu); + perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW); perf_cpu_notifier(sh_pmu_notifier); return 0; } diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c index 39348b1cebd3..760578687e7c 100644 --- a/arch/sparc/kernel/perf_event.c +++ b/arch/sparc/kernel/perf_event.c @@ -1318,7 +1318,7 @@ int __init init_hw_perf_events(void) pr_cont("Supported PMU type is '%s'\n", sparc_pmu_type); - perf_pmu_register(&pmu); + perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW); register_die_notifier(&perf_event_nmi_notifier); return 0; diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index ce27c547fe78..0a360d146596 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1465,7 +1465,7 @@ int __init init_hw_perf_events(void) pr_info("... fixed-purpose events: %d\n", x86_pmu.num_counters_fixed); pr_info("... event mask: %016Lx\n", x86_pmu.intel_ctrl); - perf_pmu_register(&pmu); + perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW); perf_cpu_notifier(x86_pmu_notifier); return 0; diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 30e50e2c7f30..21206d27466b 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -588,6 +588,9 @@ struct perf_event; struct pmu { struct list_head entry; + char *name; + int type; + int * __percpu pmu_disable_count; struct perf_cpu_context * __percpu pmu_cpu_context; int task_ctx_nr; @@ -916,7 +919,7 @@ struct perf_output_handle { #ifdef CONFIG_PERF_EVENTS -extern int perf_pmu_register(struct pmu *pmu); +extern int perf_pmu_register(struct pmu *pmu, char *name, int type); extern void perf_pmu_unregister(struct pmu *pmu); extern int perf_num_counters(void); diff --git a/kernel/hw_breakpoint.c b/kernel/hw_breakpoint.c index e5325825aeb6..086adf25a55e 100644 --- a/kernel/hw_breakpoint.c +++ b/kernel/hw_breakpoint.c @@ -641,7 +641,7 @@ int __init init_hw_breakpoint(void) constraints_initialized = 1; - perf_pmu_register(&perf_breakpoint); + perf_pmu_register(&perf_breakpoint, "breakpoint", PERF_TYPE_BREAKPOINT); return register_die_notifier(&hw_breakpoint_exceptions_nb); diff --git a/kernel/perf_event.c b/kernel/perf_event.c index a3d568fbacc6..8f09bc877a30 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -4961,7 +4962,7 @@ static struct pmu perf_tracepoint = { static inline void perf_tp_register(void) { - perf_pmu_register(&perf_tracepoint); + perf_pmu_register(&perf_tracepoint, "tracepoint", PERF_TYPE_TRACEPOINT); } static int perf_event_set_filter(struct perf_event *event, void __user *arg) @@ -5305,8 +5306,9 @@ static void free_pmu_context(struct pmu *pmu) out: mutex_unlock(&pmus_lock); } +static struct idr pmu_idr; -int perf_pmu_register(struct pmu *pmu) +int perf_pmu_register(struct pmu *pmu, char *name, int type) { int cpu, ret; @@ -5316,13 +5318,32 @@ int perf_pmu_register(struct pmu *pmu) if (!pmu->pmu_disable_count) goto unlock; + pmu->type = -1; + if (!name) + goto skip_type; + pmu->name = name; + + if (type < 0) { + int err = idr_pre_get(&pmu_idr, GFP_KERNEL); + if (!err) + goto free_pdc; + + err = idr_get_new_above(&pmu_idr, pmu, PERF_TYPE_MAX, &type); + if (err) { + ret = err; + goto free_pdc; + } + } + pmu->type = type; + +skip_type: pmu->pmu_cpu_context = find_pmu_context(pmu->task_ctx_nr); if (pmu->pmu_cpu_context) goto got_cpu_context; pmu->pmu_cpu_context = alloc_percpu(struct perf_cpu_context); if (!pmu->pmu_cpu_context) - goto free_pdc; + goto free_ird; for_each_possible_cpu(cpu) { struct perf_cpu_context *cpuctx; @@ -5366,6 +5387,10 @@ unlock: return ret; +free_idr: + if (pmu->type >= PERF_TYPE_MAX) + idr_remove(&pmu_idr, pmu->type); + free_pdc: free_percpu(pmu->pmu_disable_count); goto unlock; @@ -5385,6 +5410,8 @@ void perf_pmu_unregister(struct pmu *pmu) synchronize_rcu(); free_percpu(pmu->pmu_disable_count); + if (pmu->type >= PERF_TYPE_MAX) + idr_remove(&pmu_idr, pmu->type); free_pmu_context(pmu); } @@ -5394,6 +5421,13 @@ struct pmu *perf_init_event(struct perf_event *event) int idx; idx = srcu_read_lock(&pmus_srcu); + + rcu_read_lock(); + pmu = idr_find(&pmu_idr, event->attr.type); + rcu_read_unlock(); + if (pmu) + goto unlock; + list_for_each_entry_rcu(pmu, &pmus, entry) { int ret = pmu->event_init(event); if (!ret) @@ -6555,11 +6589,13 @@ void __init perf_event_init(void) { int ret; + idr_init(&pmu_idr); + perf_event_init_all_cpus(); init_srcu_struct(&pmus_srcu); - perf_pmu_register(&perf_swevent); - perf_pmu_register(&perf_cpu_clock); - perf_pmu_register(&perf_task_clock); + perf_pmu_register(&perf_swevent, "software", PERF_TYPE_SOFTWARE); + perf_pmu_register(&perf_cpu_clock, NULL, -1); + perf_pmu_register(&perf_task_clock, NULL, -1); perf_tp_register(); perf_cpu_notifier(perf_cpu_notify); register_reboot_notifier(&perf_reboot_notifier); -- cgit v1.2.3 From abe43400579d5de0078c2d3a760e6598e183f871 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 17 Nov 2010 23:17:37 +0100 Subject: perf: Sysfs enumeration Simple sysfs emumeration of the PMUs. Use a "event_source" bus, and add PMU devices using their name. Each PMU device has a type attribute which contrains the value needed for perf_event_attr::type to identify this PMU. This is the minimal stub needed to start using this interface, we'll consider extending the sysfs usage later. Cc: Kay Sievers Cc: Greg KH Signed-off-by: Peter Zijlstra LKML-Reference: <20101117222056.316982569@chello.nl> Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 1 + kernel/perf_event.c | 95 +++++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 95 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 21206d27466b..dda5b0a3ff60 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -588,6 +588,7 @@ struct perf_event; struct pmu { struct list_head entry; + struct device *dev; char *name; int type; diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 8f09bc877a30..11847bf1e8cc 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include #include @@ -5308,6 +5309,58 @@ out: } static struct idr pmu_idr; +static ssize_t +type_show(struct device *dev, struct device_attribute *attr, char *page) +{ + struct pmu *pmu = dev_get_drvdata(dev); + + return snprintf(page, PAGE_SIZE-1, "%d\n", pmu->type); +} + +static struct device_attribute pmu_dev_attrs[] = { + __ATTR_RO(type), + __ATTR_NULL, +}; + +static int pmu_bus_running; +static struct bus_type pmu_bus = { + .name = "event_source", + .dev_attrs = pmu_dev_attrs, +}; + +static void pmu_dev_release(struct device *dev) +{ + kfree(dev); +} + +static int pmu_dev_alloc(struct pmu *pmu) +{ + int ret = -ENOMEM; + + pmu->dev = kzalloc(sizeof(struct device), GFP_KERNEL); + if (!pmu->dev) + goto out; + + device_initialize(pmu->dev); + ret = dev_set_name(pmu->dev, "%s", pmu->name); + if (ret) + goto free_dev; + + dev_set_drvdata(pmu->dev, pmu); + pmu->dev->bus = &pmu_bus; + pmu->dev->release = pmu_dev_release; + ret = device_add(pmu->dev); + if (ret) + goto free_dev; + +out: + return ret; + +free_dev: + put_device(pmu->dev); + goto out; +} + int perf_pmu_register(struct pmu *pmu, char *name, int type) { int cpu, ret; @@ -5336,6 +5389,12 @@ int perf_pmu_register(struct pmu *pmu, char *name, int type) } pmu->type = type; + if (pmu_bus_running) { + ret = pmu_dev_alloc(pmu); + if (ret) + goto free_idr; + } + skip_type: pmu->pmu_cpu_context = find_pmu_context(pmu->task_ctx_nr); if (pmu->pmu_cpu_context) @@ -5343,7 +5402,7 @@ skip_type: pmu->pmu_cpu_context = alloc_percpu(struct perf_cpu_context); if (!pmu->pmu_cpu_context) - goto free_ird; + goto free_dev; for_each_possible_cpu(cpu) { struct perf_cpu_context *cpuctx; @@ -5387,6 +5446,10 @@ unlock: return ret; +free_dev: + device_del(pmu->dev); + put_device(pmu->dev); + free_idr: if (pmu->type >= PERF_TYPE_MAX) idr_remove(&pmu_idr, pmu->type); @@ -5412,6 +5475,8 @@ void perf_pmu_unregister(struct pmu *pmu) free_percpu(pmu->pmu_disable_count); if (pmu->type >= PERF_TYPE_MAX) idr_remove(&pmu_idr, pmu->type); + device_del(pmu->dev); + put_device(pmu->dev); free_pmu_context(pmu); } @@ -6603,3 +6668,31 @@ void __init perf_event_init(void) ret = init_hw_breakpoint(); WARN(ret, "hw_breakpoint initialization failed with: %d", ret); } + +static int __init perf_event_sysfs_init(void) +{ + struct pmu *pmu; + int ret; + + mutex_lock(&pmus_lock); + + ret = bus_register(&pmu_bus); + if (ret) + goto unlock; + + list_for_each_entry(pmu, &pmus, entry) { + if (!pmu->name || pmu->type < 0) + continue; + + ret = pmu_dev_alloc(pmu); + WARN(ret, "Failed to register pmu: %s, reason %d\n", pmu->name, ret); + } + pmu_bus_running = 1; + ret = 0; + +unlock: + mutex_unlock(&pmus_lock); + + return ret; +} +device_initcall(perf_event_sysfs_init); -- cgit v1.2.3 From f08f5a0add20834d3f3d876dfe08005a5df656db Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 16 Dec 2010 17:11:58 +0100 Subject: PM / Runtime: Fix pm_runtime_suspended() There are some situations (e.g. in __pm_generic_call()), where pm_runtime_suspended() is used to decide whether or not to execute a device's (system) ->suspend() callback. The callback is not executed if pm_runtime_suspended() returns true, but it does so for devices that don't even support runtime PM, because the power.disable_depth device field is ignored by it. This leads to problems (i.e. devices are not suspened when they should), so rework pm_runtime_suspended() so that it returns false if the device's power.disable_depth field is different from zero. Signed-off-by: Rafael J. Wysocki Cc: stable@kernel.org --- Documentation/power/runtime_pm.txt | 4 ++-- include/linux/pm_runtime.h | 3 ++- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/Documentation/power/runtime_pm.txt b/Documentation/power/runtime_pm.txt index 489e9bacd165..41cc7b30d7dd 100644 --- a/Documentation/power/runtime_pm.txt +++ b/Documentation/power/runtime_pm.txt @@ -379,8 +379,8 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h: zero) bool pm_runtime_suspended(struct device *dev); - - return true if the device's runtime PM status is 'suspended', or false - otherwise + - return true if the device's runtime PM status is 'suspended' and its + 'power.disable_depth' field is equal to zero, or false otherwise void pm_runtime_allow(struct device *dev); - set the power.runtime_auto flag for the device and decrease its usage diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 3ec2358f8692..d19f1cca7f74 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -77,7 +77,8 @@ static inline void device_set_run_wake(struct device *dev, bool enable) static inline bool pm_runtime_suspended(struct device *dev) { - return dev->power.runtime_status == RPM_SUSPENDED; + return dev->power.runtime_status == RPM_SUSPENDED + && !dev->power.disable_depth; } static inline void pm_runtime_mark_last_busy(struct device *dev) -- cgit v1.2.3 From 3f84622d7c7818077f5e6cf4b8a0d1b10dc65147 Mon Sep 17 00:00:00 2001 From: Hauke Mehrtens Date: Sat, 27 Nov 2010 19:26:32 +0100 Subject: SSB: Fix nvram_get on BCM47xx platform The nvram_get function was never in the mainline kernel, it only existed in an external OpenWrt patch. Use nvram_getenv function, which is in mainline and use an include instead of an extra function declaration. et0macaddr contains the mac address in text from like 00:11:22:33:44:55. We have to parse it before adding it into macaddr. nvram_parse_macaddr will be merged into asm/mach-bcm47xx/nvram.h through the MIPS git tree and will be available soon. It will not build now without nvram_parse_macaddr, but it hasn't before either. Signed-off-by: Hauke Mehrtens To: linux-mips@linux-mips.org Cc: mb@bu3sch.de Cc: netdev@vger.kernel.org Cc: Hauke Mehrtens Acked-by: Michael Buesch Patchwork: https://patchwork.linux-mips.org/patch/1849/ Signed-off-by: Ralf Baechle --- include/linux/ssb/ssb_driver_gige.h | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ssb/ssb_driver_gige.h b/include/linux/ssb/ssb_driver_gige.h index 942e38736901..eba52a100533 100644 --- a/include/linux/ssb/ssb_driver_gige.h +++ b/include/linux/ssb/ssb_driver_gige.h @@ -96,16 +96,21 @@ static inline bool ssb_gige_must_flush_posted_writes(struct pci_dev *pdev) return 0; } -extern char * nvram_get(const char *name); +#ifdef CONFIG_BCM47XX +#include /* Get the device MAC address */ static inline void ssb_gige_get_macaddr(struct pci_dev *pdev, u8 *macaddr) { -#ifdef CONFIG_BCM47XX - char *res = nvram_get("et0macaddr"); - if (res) - memcpy(macaddr, res, 6); -#endif + char buf[20]; + if (nvram_getenv("et0macaddr", buf, sizeof(buf)) < 0) + return; + nvram_parse_macaddr(buf, macaddr); } +#else +static inline void ssb_gige_get_macaddr(struct pci_dev *pdev, u8 *macaddr) +{ +} +#endif extern int ssb_gige_pcibios_plat_dev_init(struct ssb_device *sdev, struct pci_dev *pdev); -- cgit v1.2.3 From cf4e594ea7e55555e81647b74a3a8e8b2826a529 Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Thu, 16 Dec 2010 00:52:40 +0200 Subject: nl80211: Add notification for dropped Deauth/Disassoc Add a new notification to indicate that a received, unprotected Deauthentication or Disassociation frame was dropped due to management frame protection being in use. This notification is needed to allow user space (e.g., wpa_supplicant) to implement SA Query procedure to recover from association state mismatch between an AP and STA. This is needed to avoid getting stuck in non-working state when MFP (IEEE 802.11w) is used and a protected Deauthentication or Disassociation frame is dropped for any reason. After that, the station would silently discard any unprotected Deauthentication or Disassociation frame that could be indicating that the AP does not have association for the STA (when the Reason Code would be 6 or 7). IEEE Std 802.11w-2009, 11.13 describes this recovery mechanism. Signed-off-by: Jouni Malinen Signed-off-by: John W. Linville --- include/linux/nl80211.h | 10 ++++++++++ include/net/cfg80211.h | 26 ++++++++++++++++++++++++++ net/mac80211/rx.c | 22 ++++++++++++++++++++-- net/wireless/mlme.c | 22 ++++++++++++++++++++++ net/wireless/nl80211.c | 16 ++++++++++++++++ net/wireless/nl80211.h | 6 ++++++ 6 files changed, 100 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 1cee56b3a79a..7483a89cee8f 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -399,6 +399,13 @@ * @NL80211_CMD_LEAVE_MESH: Leave the mesh network -- no special arguments, the * network is determined by the network interface. * + * @NL80211_CMD_UNPROT_DEAUTHENTICATE: Unprotected deauthentication frame + * notification. This event is used to indicate that an unprotected + * deauthentication frame was dropped when MFP is in use. + * @NL80211_CMD_UNPROT_DISASSOCIATE: Unprotected disassociation frame + * notification. This event is used to indicate that an unprotected + * disassociation frame was dropped when MFP is in use. + * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use */ @@ -508,6 +515,9 @@ enum nl80211_commands { NL80211_CMD_JOIN_MESH, NL80211_CMD_LEAVE_MESH, + NL80211_CMD_UNPROT_DEAUTHENTICATE, + NL80211_CMD_UNPROT_DISASSOCIATE, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index f45e15f12446..3d1c09b777e8 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -2359,6 +2359,32 @@ void cfg80211_send_disassoc(struct net_device *dev, const u8 *buf, size_t len); void __cfg80211_send_disassoc(struct net_device *dev, const u8 *buf, size_t len); +/** + * cfg80211_send_unprot_deauth - notification of unprotected deauthentication + * @dev: network device + * @buf: deauthentication frame (header + body) + * @len: length of the frame data + * + * This function is called whenever a received Deauthentication frame has been + * dropped in station mode because of MFP being used but the Deauthentication + * frame was not protected. This function may sleep. + */ +void cfg80211_send_unprot_deauth(struct net_device *dev, const u8 *buf, + size_t len); + +/** + * cfg80211_send_unprot_disassoc - notification of unprotected disassociation + * @dev: network device + * @buf: disassociation frame (header + body) + * @len: length of the frame data + * + * This function is called whenever a received Disassociation frame has been + * dropped in station mode because of MFP being used but the Disassociation + * frame was not protected. This function may sleep. + */ +void cfg80211_send_unprot_disassoc(struct net_device *dev, const u8 *buf, + size_t len); + /** * cfg80211_michael_mic_failure - notification of Michael MIC failure (TKIP) * @dev: network device diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 052789ef4745..4573ce1e1d15 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -1540,12 +1540,30 @@ ieee80211_drop_unencrypted_mgmt(struct ieee80211_rx_data *rx) if (rx->sta && test_sta_flags(rx->sta, WLAN_STA_MFP)) { if (unlikely(!ieee80211_has_protected(fc) && ieee80211_is_unicast_robust_mgmt_frame(rx->skb) && - rx->key)) + rx->key)) { + if (ieee80211_is_deauth(fc)) + cfg80211_send_unprot_deauth(rx->sdata->dev, + rx->skb->data, + rx->skb->len); + else if (ieee80211_is_disassoc(fc)) + cfg80211_send_unprot_disassoc(rx->sdata->dev, + rx->skb->data, + rx->skb->len); return -EACCES; + } /* BIP does not use Protected field, so need to check MMIE */ if (unlikely(ieee80211_is_multicast_robust_mgmt_frame(rx->skb) && - ieee80211_get_mmie_keyidx(rx->skb) < 0)) + ieee80211_get_mmie_keyidx(rx->skb) < 0)) { + if (ieee80211_is_deauth(fc)) + cfg80211_send_unprot_deauth(rx->sdata->dev, + rx->skb->data, + rx->skb->len); + else if (ieee80211_is_disassoc(fc)) + cfg80211_send_unprot_disassoc(rx->sdata->dev, + rx->skb->data, + rx->skb->len); return -EACCES; + } /* * When using MFP, Action frames are not allowed prior to * having configured keys. diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index d7680f2a4c5b..aa5df8865ff7 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -263,6 +263,28 @@ void cfg80211_send_disassoc(struct net_device *dev, const u8 *buf, size_t len) } EXPORT_SYMBOL(cfg80211_send_disassoc); +void cfg80211_send_unprot_deauth(struct net_device *dev, const u8 *buf, + size_t len) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct wiphy *wiphy = wdev->wiphy; + struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); + + nl80211_send_unprot_deauth(rdev, dev, buf, len, GFP_ATOMIC); +} +EXPORT_SYMBOL(cfg80211_send_unprot_deauth); + +void cfg80211_send_unprot_disassoc(struct net_device *dev, const u8 *buf, + size_t len) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct wiphy *wiphy = wdev->wiphy; + struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); + + nl80211_send_unprot_disassoc(rdev, dev, buf, len, GFP_ATOMIC); +} +EXPORT_SYMBOL(cfg80211_send_unprot_disassoc); + static void __cfg80211_auth_remove(struct wireless_dev *wdev, const u8 *addr) { int i; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 594a6ac8b9d2..aefce54d47e2 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -5473,6 +5473,22 @@ void nl80211_send_disassoc(struct cfg80211_registered_device *rdev, NL80211_CMD_DISASSOCIATE, gfp); } +void nl80211_send_unprot_deauth(struct cfg80211_registered_device *rdev, + struct net_device *netdev, const u8 *buf, + size_t len, gfp_t gfp) +{ + nl80211_send_mlme_event(rdev, netdev, buf, len, + NL80211_CMD_UNPROT_DEAUTHENTICATE, gfp); +} + +void nl80211_send_unprot_disassoc(struct cfg80211_registered_device *rdev, + struct net_device *netdev, const u8 *buf, + size_t len, gfp_t gfp) +{ + nl80211_send_mlme_event(rdev, netdev, buf, len, + NL80211_CMD_UNPROT_DISASSOCIATE, gfp); +} + static void nl80211_send_mlme_timeout(struct cfg80211_registered_device *rdev, struct net_device *netdev, int cmd, const u8 *addr, gfp_t gfp) diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h index 16c2f7190768..e3f7fa886966 100644 --- a/net/wireless/nl80211.h +++ b/net/wireless/nl80211.h @@ -25,6 +25,12 @@ void nl80211_send_deauth(struct cfg80211_registered_device *rdev, void nl80211_send_disassoc(struct cfg80211_registered_device *rdev, struct net_device *netdev, const u8 *buf, size_t len, gfp_t gfp); +void nl80211_send_unprot_deauth(struct cfg80211_registered_device *rdev, + struct net_device *netdev, + const u8 *buf, size_t len, gfp_t gfp); +void nl80211_send_unprot_disassoc(struct cfg80211_registered_device *rdev, + struct net_device *netdev, + const u8 *buf, size_t len, gfp_t gfp); void nl80211_send_auth_timeout(struct cfg80211_registered_device *rdev, struct net_device *netdev, const u8 *addr, gfp_t gfp); -- cgit v1.2.3 From a3d22a68d752ccc1a01bb0a64dd70b7a98bf9e23 Mon Sep 17 00:00:00 2001 From: Vladislav Zolotarov Date: Mon, 13 Dec 2010 06:27:10 +0000 Subject: bnx2x: Take the distribution range definition out of skb_tx_hash() Move the calcualation of the Tx hash for a given hash range into a separate function and define the skb_tx_hash(), which calculates a Tx hash for a [0; dev->real_num_tx_queues - 1] hash values range, using this function (__skb_tx_hash()). Signed-off-by: Vladislav Zolotarov Signed-off-by: Eilon Greenstein Signed-off-by: David S. Miller --- include/linux/netdevice.h | 10 ++++++++++ include/linux/skbuff.h | 5 +++-- net/core/dev.c | 15 ++++++++++----- 3 files changed, 23 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d31bc3c94717..445e6825f8eb 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1747,6 +1747,16 @@ static inline void netif_wake_subqueue(struct net_device *dev, u16 queue_index) __netif_schedule(txq->qdisc); } +/* + * Returns a Tx hash for the given packet when dev->real_num_tx_queues is used + * as a distribution range limit for the returned value. + */ +static inline u16 skb_tx_hash(const struct net_device *dev, + const struct sk_buff *skb) +{ + return __skb_tx_hash(dev, skb, dev->real_num_tx_queues); +} + /** * netif_is_multiqueue - test if device has multiple transmit queues * @dev: network device diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 19f37a6ee6c4..4c4bec6316d9 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2165,8 +2165,9 @@ static inline bool skb_rx_queue_recorded(const struct sk_buff *skb) return skb->queue_mapping != 0; } -extern u16 skb_tx_hash(const struct net_device *dev, - const struct sk_buff *skb); +extern u16 __skb_tx_hash(const struct net_device *dev, + const struct sk_buff *skb, + unsigned int num_tx_queues); #ifdef CONFIG_XFRM static inline struct sec_path *skb_sec_path(struct sk_buff *skb) diff --git a/net/core/dev.c b/net/core/dev.c index d28b3a023bb2..b25dd087f06a 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2112,14 +2112,19 @@ out: static u32 hashrnd __read_mostly; -u16 skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb) +/* + * Returns a Tx hash based on the given packet descriptor a Tx queues' number + * to be used as a distribution range. + */ +u16 __skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb, + unsigned int num_tx_queues) { u32 hash; if (skb_rx_queue_recorded(skb)) { hash = skb_get_rx_queue(skb); - while (unlikely(hash >= dev->real_num_tx_queues)) - hash -= dev->real_num_tx_queues; + while (unlikely(hash >= num_tx_queues)) + hash -= num_tx_queues; return hash; } @@ -2129,9 +2134,9 @@ u16 skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb) hash = (__force u16) skb->protocol ^ skb->rxhash; hash = jhash_1word(hash, hashrnd); - return (u16) (((u64) hash * dev->real_num_tx_queues) >> 32); + return (u16) (((u64) hash * num_tx_queues) >> 32); } -EXPORT_SYMBOL(skb_tx_hash); +EXPORT_SYMBOL(__skb_tx_hash); static inline u16 dev_cap_txqueue(struct net_device *dev, u16 queue_index) { -- cgit v1.2.3 From b236da6931e2482bfe44a7865dd4e7bb036f3496 Mon Sep 17 00:00:00 2001 From: Changli Gao Date: Tue, 14 Dec 2010 03:09:15 +0000 Subject: net: use NUMA_NO_NODE instead of the magic number -1 Signed-off-by: Changli Gao Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- net/core/dev.c | 2 +- net/core/net-sysfs.c | 3 ++- 3 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 445e6825f8eb..cc916c5c3279 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -530,7 +530,7 @@ static inline int netdev_queue_numa_node_read(const struct netdev_queue *q) #if defined(CONFIG_XPS) && defined(CONFIG_NUMA) return q->numa_node; #else - return -1; + return NUMA_NO_NODE; #endif } diff --git a/net/core/dev.c b/net/core/dev.c index b25dd087f06a..7ac26d2b9722 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5121,7 +5121,7 @@ static void netdev_init_one_queue(struct net_device *dev, spin_lock_init(&queue->_xmit_lock); netdev_set_xmit_lockdep_class(&queue->_xmit_lock, dev->type); queue->xmit_lock_owner = -1; - netdev_queue_numa_node_write(queue, -1); + netdev_queue_numa_node_write(queue, NUMA_NO_NODE); queue->dev = dev; } diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 85e8b5326dd6..e23c01be5a5b 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -1009,7 +1009,8 @@ static ssize_t store_xps_map(struct netdev_queue *queue, if (dev_maps) call_rcu(&dev_maps->rcu, xps_dev_maps_release); - netdev_queue_numa_node_write(queue, (numa_node >= 0) ? numa_node : -1); + netdev_queue_numa_node_write(queue, (numa_node >= 0) ? numa_node : + NUMA_NO_NODE); mutex_unlock(&xps_map_mutex); -- cgit v1.2.3 From 04fb451eff978ca059399eab83d5594b073caf6f Mon Sep 17 00:00:00 2001 From: Michał Mirosław Date: Tue, 14 Dec 2010 15:24:08 +0000 Subject: net: Introduce skb_checksum_start_offset() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Introduce skb_checksum_start_offset() to replace repetitive calculation. Signed-off-by: Michał Mirosław Signed-off-by: David S. Miller --- include/linux/skbuff.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 4c4bec6316d9..20ec0a64cb9f 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1355,6 +1355,11 @@ static inline void skb_set_mac_header(struct sk_buff *skb, const int offset) } #endif /* NET_SKBUFF_DATA_USES_OFFSET */ +static inline int skb_checksum_start_offset(const struct sk_buff *skb) +{ + return skb->csum_start - skb_headroom(skb); +} + static inline int skb_transport_offset(const struct sk_buff *skb) { return skb_transport_header(skb) - skb->data; -- cgit v1.2.3 From e692cb668fdd5a712c6ed2a2d6f2a36ee83997b4 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Wed, 1 Dec 2010 19:41:49 +0100 Subject: block: Deprecate QUEUE_FLAG_CLUSTER and use queue_limits instead When stacking devices, a request_queue is not always available. This forced us to have a no_cluster flag in the queue_limits that could be used as a carrier until the request_queue had been set up for a metadevice. There were several problems with that approach. First of all it was up to the stacking device to remember to set queue flag after stacking had completed. Also, the queue flag and the queue limits had to be kept in sync at all times. We got that wrong, which could lead to us issuing commands that went beyond the max scatterlist limit set by the driver. The proper fix is to avoid having two flags for tracking the same thing. We deprecate QUEUE_FLAG_CLUSTER and use the queue limit directly in the block layer merging functions. The queue_limit 'no_cluster' is turned into 'cluster' to avoid double negatives and to ease stacking. Clustering defaults to being enabled as before. The queue flag logic is removed from the stacking function, and explicitly setting the cluster flag is no longer necessary in DM and MD. Reported-by: Ed Lin Signed-off-by: Martin K. Petersen Acked-by: Mike Snitzer Cc: stable@kernel.org Signed-off-by: Jens Axboe --- block/blk-merge.c | 6 +++--- block/blk-settings.c | 25 ++----------------------- block/blk-sysfs.c | 2 +- drivers/md/dm-table.c | 5 ----- drivers/md/md.c | 3 --- drivers/scsi/scsi_lib.c | 3 +-- include/linux/blkdev.h | 9 ++++++--- 7 files changed, 13 insertions(+), 40 deletions(-) (limited to 'include/linux') diff --git a/block/blk-merge.c b/block/blk-merge.c index 77b7c26df6b5..74bc4a768f32 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -21,7 +21,7 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q, return 0; fbio = bio; - cluster = test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags); + cluster = blk_queue_cluster(q); seg_size = 0; nr_phys_segs = 0; for_each_bio(bio) { @@ -87,7 +87,7 @@ EXPORT_SYMBOL(blk_recount_segments); static int blk_phys_contig_segment(struct request_queue *q, struct bio *bio, struct bio *nxt) { - if (!test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags)) + if (!blk_queue_cluster(q)) return 0; if (bio->bi_seg_back_size + nxt->bi_seg_front_size > @@ -123,7 +123,7 @@ int blk_rq_map_sg(struct request_queue *q, struct request *rq, int nsegs, cluster; nsegs = 0; - cluster = test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags); + cluster = blk_queue_cluster(q); /* * for each bio in rq diff --git a/block/blk-settings.c b/block/blk-settings.c index 701859fb9647..e55f5fc4ca22 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -126,7 +126,7 @@ void blk_set_default_limits(struct queue_limits *lim) lim->alignment_offset = 0; lim->io_opt = 0; lim->misaligned = 0; - lim->no_cluster = 0; + lim->cluster = 1; } EXPORT_SYMBOL(blk_set_default_limits); @@ -464,15 +464,6 @@ EXPORT_SYMBOL(blk_queue_io_opt); void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b) { blk_stack_limits(&t->limits, &b->limits, 0); - - if (!t->queue_lock) - WARN_ON_ONCE(1); - else if (!test_bit(QUEUE_FLAG_CLUSTER, &b->queue_flags)) { - unsigned long flags; - spin_lock_irqsave(t->queue_lock, flags); - queue_flag_clear(QUEUE_FLAG_CLUSTER, t); - spin_unlock_irqrestore(t->queue_lock, flags); - } } EXPORT_SYMBOL(blk_queue_stack_limits); @@ -545,7 +536,7 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, t->io_min = max(t->io_min, b->io_min); t->io_opt = lcm(t->io_opt, b->io_opt); - t->no_cluster |= b->no_cluster; + t->cluster &= b->cluster; t->discard_zeroes_data &= b->discard_zeroes_data; /* Physical block size a multiple of the logical block size? */ @@ -641,7 +632,6 @@ void disk_stack_limits(struct gendisk *disk, struct block_device *bdev, sector_t offset) { struct request_queue *t = disk->queue; - struct request_queue *b = bdev_get_queue(bdev); if (bdev_stack_limits(&t->limits, bdev, offset >> 9) < 0) { char top[BDEVNAME_SIZE], bottom[BDEVNAME_SIZE]; @@ -652,17 +642,6 @@ void disk_stack_limits(struct gendisk *disk, struct block_device *bdev, printk(KERN_NOTICE "%s: Warning: Device %s is misaligned\n", top, bottom); } - - if (!t->queue_lock) - WARN_ON_ONCE(1); - else if (!test_bit(QUEUE_FLAG_CLUSTER, &b->queue_flags)) { - unsigned long flags; - - spin_lock_irqsave(t->queue_lock, flags); - if (!test_bit(QUEUE_FLAG_CLUSTER, &b->queue_flags)) - queue_flag_clear(QUEUE_FLAG_CLUSTER, t); - spin_unlock_irqrestore(t->queue_lock, flags); - } } EXPORT_SYMBOL(disk_stack_limits); diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 013457f47fdc..41fb69150b4d 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -119,7 +119,7 @@ static ssize_t queue_max_integrity_segments_show(struct request_queue *q, char * static ssize_t queue_max_segment_size_show(struct request_queue *q, char *page) { - if (test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags)) + if (blk_queue_cluster(q)) return queue_var_show(queue_max_segment_size(q), (page)); return queue_var_show(PAGE_CACHE_SIZE, (page)); diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 90267f8d64ee..e2da1912a2cb 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -1131,11 +1131,6 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, */ q->limits = *limits; - if (limits->no_cluster) - queue_flag_clear_unlocked(QUEUE_FLAG_CLUSTER, q); - else - queue_flag_set_unlocked(QUEUE_FLAG_CLUSTER, q); - if (!dm_table_supports_discards(t)) queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, q); else diff --git a/drivers/md/md.c b/drivers/md/md.c index 84c46a161927..52694d29663d 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -4296,9 +4296,6 @@ static int md_alloc(dev_t dev, char *name) goto abort; mddev->queue->queuedata = mddev; - /* Can be unlocked because the queue is new: no concurrency */ - queue_flag_set_unlocked(QUEUE_FLAG_CLUSTER, mddev->queue); - blk_queue_make_request(mddev->queue, md_make_request); disk = alloc_disk(1 << shift); diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index eafeeda6e194..9d7ba07dc5ef 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1642,9 +1642,8 @@ struct request_queue *__scsi_alloc_queue(struct Scsi_Host *shost, blk_queue_max_segment_size(q, dma_get_max_seg_size(dev)); - /* New queue, no concurrency on queue_flags */ if (!shost->use_clustering) - queue_flag_clear_unlocked(QUEUE_FLAG_CLUSTER, q); + q->limits.cluster = 0; /* * set a reasonable default alignment on word boundaries: the diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index aae86fd10c4f..95aeeeb49e8b 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -250,7 +250,7 @@ struct queue_limits { unsigned char misaligned; unsigned char discard_misaligned; - unsigned char no_cluster; + unsigned char cluster; signed char discard_zeroes_data; }; @@ -380,7 +380,6 @@ struct request_queue #endif }; -#define QUEUE_FLAG_CLUSTER 0 /* cluster several segments into 1 */ #define QUEUE_FLAG_QUEUED 1 /* uses generic tag queueing */ #define QUEUE_FLAG_STOPPED 2 /* queue is stopped */ #define QUEUE_FLAG_SYNCFULL 3 /* read queue has been filled */ @@ -403,7 +402,6 @@ struct request_queue #define QUEUE_FLAG_SECDISCARD 19 /* supports SECDISCARD */ #define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ - (1 << QUEUE_FLAG_CLUSTER) | \ (1 << QUEUE_FLAG_STACKABLE) | \ (1 << QUEUE_FLAG_SAME_COMP) | \ (1 << QUEUE_FLAG_ADD_RANDOM)) @@ -510,6 +508,11 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q) #define rq_data_dir(rq) ((rq)->cmd_flags & 1) +static inline unsigned int blk_queue_cluster(struct request_queue *q) +{ + return q->limits.cluster; +} + /* * We regard a request as sync, if either a read or a sync write */ -- cgit v1.2.3 From 72d4cd9f38b5ed96b75df4c622be25e1c2648dd3 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Fri, 17 Dec 2010 08:34:20 +0100 Subject: block: max hardware sectors limit wrapper Implement blk_limits_max_hw_sectors() and make blk_queue_max_hw_sectors() a wrapper around it. DM needs this to avoid setting queue_limits' max_hw_sectors and max_sectors directly. dm_set_device_limits() now leverages blk_limits_max_hw_sectors() logic to establish the appropriate max_hw_sectors minimum (PAGE_SIZE). Fixes issue where DM was incorrectly setting max_sectors rather than max_hw_sectors (which caused dm_merge_bvec()'s max_hw_sectors check to be ineffective). Signed-off-by: Mike Snitzer Cc: stable@kernel.org Acked-by: Martin K. Petersen Signed-off-by: Jens Axboe --- block/blk-settings.c | 26 ++++++++++++++++++++------ drivers/md/dm-table.c | 5 ++--- include/linux/blkdev.h | 1 + 3 files changed, 23 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/block/blk-settings.c b/block/blk-settings.c index e55f5fc4ca22..36c8c1f2af18 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -229,8 +229,8 @@ void blk_queue_bounce_limit(struct request_queue *q, u64 dma_mask) EXPORT_SYMBOL(blk_queue_bounce_limit); /** - * blk_queue_max_hw_sectors - set max sectors for a request for this queue - * @q: the request queue for the device + * blk_limits_max_hw_sectors - set hard and soft limit of max sectors for request + * @limits: the queue limits * @max_hw_sectors: max hardware sectors in the usual 512b unit * * Description: @@ -244,7 +244,7 @@ EXPORT_SYMBOL(blk_queue_bounce_limit); * per-device basis in /sys/block//queue/max_sectors_kb. * The soft limit can not exceed max_hw_sectors. **/ -void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_sectors) +void blk_limits_max_hw_sectors(struct queue_limits *limits, unsigned int max_hw_sectors) { if ((max_hw_sectors << 9) < PAGE_CACHE_SIZE) { max_hw_sectors = 1 << (PAGE_CACHE_SHIFT - 9); @@ -252,9 +252,23 @@ void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_secto __func__, max_hw_sectors); } - q->limits.max_hw_sectors = max_hw_sectors; - q->limits.max_sectors = min_t(unsigned int, max_hw_sectors, - BLK_DEF_MAX_SECTORS); + limits->max_hw_sectors = max_hw_sectors; + limits->max_sectors = min_t(unsigned int, max_hw_sectors, + BLK_DEF_MAX_SECTORS); +} +EXPORT_SYMBOL(blk_limits_max_hw_sectors); + +/** + * blk_queue_max_hw_sectors - set max sectors for a request for this queue + * @q: the request queue for the device + * @max_hw_sectors: max hardware sectors in the usual 512b unit + * + * Description: + * See description for blk_limits_max_hw_sectors(). + **/ +void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_sectors) +{ + blk_limits_max_hw_sectors(&q->limits, max_hw_sectors); } EXPORT_SYMBOL(blk_queue_max_hw_sectors); diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index e2da1912a2cb..4d705cea0f8c 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -517,9 +517,8 @@ int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev, */ if (q->merge_bvec_fn && !ti->type->merge) - limits->max_sectors = - min_not_zero(limits->max_sectors, - (unsigned int) (PAGE_SIZE >> 9)); + blk_limits_max_hw_sectors(limits, + (unsigned int) (PAGE_SIZE >> 9)); return 0; } EXPORT_SYMBOL_GPL(dm_set_device_limits); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 95aeeeb49e8b..36ab42c9bb99 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -808,6 +808,7 @@ extern struct request_queue *blk_init_allocated_queue(struct request_queue *, extern void blk_cleanup_queue(struct request_queue *); extern void blk_queue_make_request(struct request_queue *, make_request_fn *); extern void blk_queue_bounce_limit(struct request_queue *, u64); +extern void blk_limits_max_hw_sectors(struct queue_limits *, unsigned int); extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int); extern void blk_queue_max_segments(struct request_queue *, unsigned short); extern void blk_queue_max_segment_size(struct request_queue *, unsigned int); -- cgit v1.2.3 From b6aa5901c7a2bd90d0b6b9866300d2648b2568f3 Mon Sep 17 00:00:00 2001 From: Henry C Chang Date: Wed, 15 Dec 2010 20:45:41 -0800 Subject: ceph: mark user pages dirty on direct-io reads For read operation, we have to set the argument _write_ of get_user_pages to 1 since we will write data to pages. Also, we need to SetPageDirty before releasing these pages. Signed-off-by: Henry C Chang Signed-off-by: Sage Weil --- fs/ceph/file.c | 8 ++++---- include/linux/ceph/libceph.h | 6 ++++-- net/ceph/pagevec.c | 11 +++++++---- 3 files changed, 15 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/fs/ceph/file.c b/fs/ceph/file.c index e860d8f1bb45..7d0e4a82d898 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -384,7 +384,7 @@ static ssize_t ceph_sync_read(struct file *file, char __user *data, if (file->f_flags & O_DIRECT) { num_pages = calc_pages_for((unsigned long)data, len); - pages = ceph_get_direct_page_vector(data, num_pages); + pages = ceph_get_direct_page_vector(data, num_pages, true); } else { num_pages = calc_pages_for(off, len); pages = ceph_alloc_page_vector(num_pages, GFP_NOFS); @@ -413,7 +413,7 @@ static ssize_t ceph_sync_read(struct file *file, char __user *data, done: if (file->f_flags & O_DIRECT) - ceph_put_page_vector(pages, num_pages); + ceph_put_page_vector(pages, num_pages, true); else ceph_release_page_vector(pages, num_pages); dout("sync_read result %d\n", ret); @@ -522,7 +522,7 @@ more: return -ENOMEM; if (file->f_flags & O_DIRECT) { - pages = ceph_get_direct_page_vector(data, num_pages); + pages = ceph_get_direct_page_vector(data, num_pages, false); if (IS_ERR(pages)) { ret = PTR_ERR(pages); goto out; @@ -572,7 +572,7 @@ more: } if (file->f_flags & O_DIRECT) - ceph_put_page_vector(pages, num_pages); + ceph_put_page_vector(pages, num_pages, false); else if (file->f_flags & O_SYNC) ceph_release_page_vector(pages, num_pages); diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 9e76d35670d2..72c72bfccb88 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -227,8 +227,10 @@ extern int ceph_open_session(struct ceph_client *client); extern void ceph_release_page_vector(struct page **pages, int num_pages); extern struct page **ceph_get_direct_page_vector(const char __user *data, - int num_pages); -extern void ceph_put_page_vector(struct page **pages, int num_pages); + int num_pages, + bool write_page); +extern void ceph_put_page_vector(struct page **pages, int num_pages, + bool dirty); extern void ceph_release_page_vector(struct page **pages, int num_pages); extern struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags); extern int ceph_copy_user_to_page_vector(struct page **pages, diff --git a/net/ceph/pagevec.c b/net/ceph/pagevec.c index ac34feeb2b3a..01947a5d03b7 100644 --- a/net/ceph/pagevec.c +++ b/net/ceph/pagevec.c @@ -13,7 +13,7 @@ * build a vector of user pages */ struct page **ceph_get_direct_page_vector(const char __user *data, - int num_pages) + int num_pages, bool write_page) { struct page **pages; int rc; @@ -24,7 +24,7 @@ struct page **ceph_get_direct_page_vector(const char __user *data, down_read(¤t->mm->mmap_sem); rc = get_user_pages(current, current->mm, (unsigned long)data, - num_pages, 0, 0, pages, NULL); + num_pages, write_page, 0, pages, NULL); up_read(¤t->mm->mmap_sem); if (rc < 0) goto fail; @@ -36,12 +36,15 @@ fail: } EXPORT_SYMBOL(ceph_get_direct_page_vector); -void ceph_put_page_vector(struct page **pages, int num_pages) +void ceph_put_page_vector(struct page **pages, int num_pages, bool dirty) { int i; - for (i = 0; i < num_pages; i++) + for (i = 0; i < num_pages; i++) { + if (dirty) + set_page_dirty_lock(pages[i]); put_page(pages[i]); + } kfree(pages); } EXPORT_SYMBOL(ceph_put_page_vector); -- cgit v1.2.3 From c0f5ac5426f7fd82b23dd5c6a1e633b290294a08 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Thu, 16 Dec 2010 10:38:41 -0700 Subject: Revert "resources: support allocating space within a region from the top down" This reverts commit e7f8567db9a7f6b3151b0b275e245c1cef0d9c70. Acked-by: H. Peter Anvin Signed-off-by: Bjorn Helgaas Signed-off-by: Jesse Barnes --- Documentation/kernel-parameters.txt | 5 -- include/linux/ioport.h | 1 - kernel/resource.c | 98 ++----------------------------------- 3 files changed, 4 insertions(+), 100 deletions(-) (limited to 'include/linux') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index cdd2a6e8a3b7..8b61c9360999 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -2175,11 +2175,6 @@ and is between 256 and 4096 characters. It is defined in the file reset_devices [KNL] Force drivers to reset the underlying device during initialization. - resource_alloc_from_bottom - Allocate new resources from the beginning of available - space, not the end. If you need to use this, please - report a bug. - resume= [SWSUSP] Specify the partition device for software suspend diff --git a/include/linux/ioport.h b/include/linux/ioport.h index d377ea815d45..b22790268b64 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -112,7 +112,6 @@ struct resource_list { /* PC/ISA/whatever - the normal PC address spaces: IO and memory */ extern struct resource ioport_resource; extern struct resource iomem_resource; -extern int resource_alloc_from_bottom; extern struct resource *request_resource_conflict(struct resource *root, struct resource *new); extern int request_resource(struct resource *root, struct resource *new); diff --git a/kernel/resource.c b/kernel/resource.c index 9fad33efd0db..560659f7baef 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -40,23 +40,6 @@ EXPORT_SYMBOL(iomem_resource); static DEFINE_RWLOCK(resource_lock); -/* - * By default, we allocate free space bottom-up. The architecture can request - * top-down by clearing this flag. The user can override the architecture's - * choice with the "resource_alloc_from_bottom" kernel boot option, but that - * should only be a debugging tool. - */ -int resource_alloc_from_bottom = 1; - -static __init int setup_alloc_from_bottom(char *s) -{ - printk(KERN_INFO - "resource: allocating from bottom-up; please report a bug\n"); - resource_alloc_from_bottom = 1; - return 0; -} -early_param("resource_alloc_from_bottom", setup_alloc_from_bottom); - static void *r_next(struct seq_file *m, void *v, loff_t *pos) { struct resource *p = v; @@ -396,75 +379,8 @@ static bool resource_contains(struct resource *res1, struct resource *res2) return res1->start <= res2->start && res1->end >= res2->end; } -/* - * Find the resource before "child" in the sibling list of "root" children. - */ -static struct resource *find_sibling_prev(struct resource *root, struct resource *child) -{ - struct resource *this; - - for (this = root->child; this; this = this->sibling) - if (this->sibling == child) - return this; - - return NULL; -} - -/* - * Find empty slot in the resource tree given range and alignment. - * This version allocates from the end of the root resource first. - */ -static int find_resource_from_top(struct resource *root, struct resource *new, - resource_size_t size, resource_size_t min, - resource_size_t max, resource_size_t align, - resource_size_t (*alignf)(void *, - const struct resource *, - resource_size_t, - resource_size_t), - void *alignf_data) -{ - struct resource *this; - struct resource tmp, avail, alloc; - - tmp.start = root->end; - tmp.end = root->end; - - this = find_sibling_prev(root, NULL); - for (;;) { - if (this) { - if (this->end < root->end) - tmp.start = this->end + 1; - } else - tmp.start = root->start; - - resource_clip(&tmp, min, max); - - /* Check for overflow after ALIGN() */ - avail = *new; - avail.start = ALIGN(tmp.start, align); - avail.end = tmp.end; - if (avail.start >= tmp.start) { - alloc.start = alignf(alignf_data, &avail, size, align); - alloc.end = alloc.start + size - 1; - if (resource_contains(&avail, &alloc)) { - new->start = alloc.start; - new->end = alloc.end; - return 0; - } - } - - if (!this || this->start == root->start) - break; - - tmp.end = this->start - 1; - this = find_sibling_prev(root, this); - } - return -EBUSY; -} - /* * Find empty slot in the resource tree given range and alignment. - * This version allocates from the beginning of the root resource first. */ static int find_resource(struct resource *root, struct resource *new, resource_size_t size, resource_size_t min, @@ -480,15 +396,14 @@ static int find_resource(struct resource *root, struct resource *new, tmp.start = root->start; /* - * Skip past an allocated resource that starts at 0, since the - * assignment of this->start - 1 to tmp->end below would cause an - * underflow. + * Skip past an allocated resource that starts at 0, since the assignment + * of this->start - 1 to tmp->end below would cause an underflow. */ if (this && this->start == 0) { tmp.start = this->end + 1; this = this->sibling; } - for (;;) { + for(;;) { if (this) tmp.end = this->start - 1; else @@ -509,10 +424,8 @@ static int find_resource(struct resource *root, struct resource *new, return 0; } } - if (!this) break; - tmp.start = this->end + 1; this = this->sibling; } @@ -545,10 +458,7 @@ int allocate_resource(struct resource *root, struct resource *new, alignf = simple_align_resource; write_lock(&resource_lock); - if (resource_alloc_from_bottom) - err = find_resource(root, new, size, min, max, align, alignf, alignf_data); - else - err = find_resource_from_top(root, new, size, min, max, align, alignf, alignf_data); + err = find_resource(root, new, size, min, max, align, alignf, alignf_data); if (err >= 0 && __request_resource(root, new)) err = -EBUSY; write_unlock(&resource_lock); -- cgit v1.2.3 From fcb119183c73bf0781009713f303e28b1fb13d3e Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Thu, 16 Dec 2010 10:38:46 -0700 Subject: resources: add arch hook for preventing allocation in reserved areas This adds arch_remove_reservations(), which an arch can implement if it needs to protect part of the address space from allocation. Sometimes that can be done by just putting a region in the resource tree, but there are cases where that doesn't work well. For example, x86 BIOS E820 reservations are not related to devices, so they may overlap part of, all of, or more than a device resource, so they may not end up at the correct spot in the resource tree. Acked-by: H. Peter Anvin Signed-off-by: Bjorn Helgaas Signed-off-by: Jesse Barnes --- include/linux/ioport.h | 1 + kernel/resource.c | 6 ++++++ 2 files changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ioport.h b/include/linux/ioport.h index b22790268b64..e9bb22cba764 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -123,6 +123,7 @@ extern void reserve_region_with_split(struct resource *root, 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 void arch_remove_reservations(struct resource *avail); extern int allocate_resource(struct resource *root, struct resource *new, resource_size_t size, resource_size_t min, resource_size_t max, resource_size_t align, diff --git a/kernel/resource.c b/kernel/resource.c index 560659f7baef..798e2fae2a06 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -357,6 +357,10 @@ int __weak page_is_ram(unsigned long pfn) return walk_system_ram_range(pfn, 1, NULL, __is_ram) == 1; } +void __weak arch_remove_reservations(struct resource *avail) +{ +} + static resource_size_t simple_align_resource(void *data, const struct resource *avail, resource_size_t size, @@ -394,6 +398,7 @@ static int find_resource(struct resource *root, struct resource *new, struct resource *this = root->child; struct resource tmp = *new, avail, alloc; + tmp.flags = new->flags; tmp.start = root->start; /* * Skip past an allocated resource that starts at 0, since the assignment @@ -410,6 +415,7 @@ static int find_resource(struct resource *root, struct resource *new, tmp.end = root->end; resource_clip(&tmp, min, max); + arch_remove_reservations(&tmp); /* Check for overflow after ALIGN() */ avail = *new; -- cgit v1.2.3 From 4b8fe66300acb2fba8b16d62606e0d30204022fc Mon Sep 17 00:00:00 2001 From: "Dmitry V. Levin" Date: Fri, 17 Dec 2010 12:03:14 -0800 Subject: netlink: fix gcc -Wconversion compilation warning $ cat << EOF | gcc -Wconversion -xc -S -o/dev/null - unsigned f(void) {return NLMSG_HDRLEN;} EOF : In function 'f': :3:26: warning: negative integer implicitly converted to unsigned type Signed-off-by: Dmitry V. Levin Signed-off-by: Kirill A. Shutemov Signed-off-by: David S. Miller --- include/linux/netlink.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 123566912d73..e2b9e63afa68 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -70,7 +70,7 @@ struct nlmsghdr { Check NLM_F_EXCL */ -#define NLMSG_ALIGNTO 4 +#define NLMSG_ALIGNTO 4U #define NLMSG_ALIGN(len) ( ((len)+NLMSG_ALIGNTO-1) & ~(NLMSG_ALIGNTO-1) ) #define NLMSG_HDRLEN ((int) NLMSG_ALIGN(sizeof(struct nlmsghdr))) #define NLMSG_LENGTH(len) ((len)+NLMSG_ALIGN(NLMSG_HDRLEN)) -- cgit v1.2.3 From e27fc9641e8ddc8146f8e01f06e5eba2469698de Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 22 Nov 2010 21:36:11 -0800 Subject: rcu: increase synchronize_sched_expedited() batching The fix in commit #6a0cc49 requires more than three concurrent instances of synchronize_sched_expedited() before batching is possible. This patch uses a ticket-counter-like approach that is also not unrelated to Lai Jiangshan's Ring RCU to allow sharing of expedited grace periods even when there are only two concurrent instances of synchronize_sched_expedited(). This commit builds on Tejun's original posting, which may be found at http://lkml.org/lkml/2010/11/9/204, adding memory barriers, avoiding overflow of signed integers (other than via atomic_t), and fixing the detection of batching. Signed-off-by: Tejun Heo Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 2 ++ kernel/rcutree_plugin.h | 82 ++++++++++++++++++++++++++++++++++++------------ 2 files changed, 64 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 49e8e16308e1..af5614856285 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -47,6 +47,8 @@ extern int rcutorture_runnable; /* for sysctl */ #endif /* #ifdef CONFIG_RCU_TORTURE_TEST */ +#define UINT_CMP_GE(a, b) (UINT_MAX / 2 >= (a) - (b)) +#define UINT_CMP_LT(a, b) (UINT_MAX / 2 < (a) - (b)) #define ULONG_CMP_GE(a, b) (ULONG_MAX / 2 >= (a) - (b)) #define ULONG_CMP_LT(a, b) (ULONG_MAX / 2 < (a) - (b)) diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index c22c4ef2a0d0..a3638710dc67 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -1025,7 +1025,8 @@ EXPORT_SYMBOL_GPL(synchronize_sched_expedited); #else /* #ifndef CONFIG_SMP */ -static atomic_t synchronize_sched_expedited_count = ATOMIC_INIT(0); +static atomic_t sync_sched_expedited_started = ATOMIC_INIT(0); +static atomic_t sync_sched_expedited_done = ATOMIC_INIT(0); static int synchronize_sched_expedited_cpu_stop(void *data) { @@ -1041,8 +1042,6 @@ static int synchronize_sched_expedited_cpu_stop(void *data) * robustness against future implementation changes. */ smp_mb(); /* See above comment block. */ - if (cpumask_first(cpu_online_mask) == smp_processor_id()) - atomic_inc(&synchronize_sched_expedited_count); return 0; } @@ -1056,43 +1055,86 @@ static int synchronize_sched_expedited_cpu_stop(void *data) * lock that is acquired by a CPU-hotplug notifier. Failing to * observe this restriction will result in deadlock. * - * The synchronize_sched_expedited_cpu_stop() function is called - * in stop-CPU context, but in order to keep overhead down to a dull - * roar, we don't force this function to wait for its counterparts - * on other CPUs. One instance of this function will increment the - * synchronize_sched_expedited_count variable per call to - * try_stop_cpus(), but there is no guarantee what order this instance - * will occur in. The worst case is that it is last on one call - * to try_stop_cpus(), and the first on the next call. This means - * that piggybacking requires that synchronize_sched_expedited_count - * be incremented by 3: this guarantees that the piggybacking - * task has waited through an entire cycle of context switches, - * even in the worst case. + * This implementation can be thought of as an application of ticket + * locking to RCU, with sync_sched_expedited_started and + * sync_sched_expedited_done taking on the roles of the halves + * of the ticket-lock word. Each task atomically increments + * sync_sched_expedited_started upon entry, snapshotting the old value, + * then attempts to stop all the CPUs. If this succeeds, then each + * CPU will have executed a context switch, resulting in an RCU-sched + * grace period. We are then done, so we use atomic_cmpxchg() to + * update sync_sched_expedited_done to match our snapshot -- but + * only if someone else has not already advanced past our snapshot. + * + * On the other hand, if try_stop_cpus() fails, we check the value + * of sync_sched_expedited_done. If it has advanced past our + * initial snapshot, then someone else must have forced a grace period + * some time after we took our snapshot. In this case, our work is + * done for us, and we can simply return. Otherwise, we try again, + * but keep our initial snapshot for purposes of checking for someone + * doing our work for us. + * + * If we fail too many times in a row, we fall back to synchronize_sched(). */ void synchronize_sched_expedited(void) { - int snap, trycount = 0; + int firstsnap, s, snap, trycount = 0; - smp_mb(); /* ensure prior mod happens before capturing snap. */ - snap = atomic_read(&synchronize_sched_expedited_count) + 2; + /* Note that atomic_inc_return() implies full memory barrier. */ + firstsnap = snap = atomic_inc_return(&sync_sched_expedited_started); get_online_cpus(); + + /* + * Each pass through the following loop attempts to force a + * context switch on each CPU. + */ while (try_stop_cpus(cpu_online_mask, synchronize_sched_expedited_cpu_stop, NULL) == -EAGAIN) { put_online_cpus(); + + /* No joy, try again later. Or just synchronize_sched(). */ if (trycount++ < 10) udelay(trycount * num_online_cpus()); else { synchronize_sched(); return; } - if (atomic_read(&synchronize_sched_expedited_count) - snap > 0) { + + /* Check to see if someone else did our work for us. */ + s = atomic_read(&sync_sched_expedited_done); + if (UINT_CMP_GE((unsigned)s, (unsigned)firstsnap)) { smp_mb(); /* ensure test happens before caller kfree */ return; } + + /* + * Refetching sync_sched_expedited_started allows later + * callers to piggyback on our grace period. We subtract + * 1 to get the same token that the last incrementer got. + * We retry after they started, so our grace period works + * for them, and they started after our first try, so their + * grace period works for us. + */ get_online_cpus(); + snap = atomic_read(&sync_sched_expedited_started) - 1; + smp_mb(); /* ensure read is before try_stop_cpus(). */ } - smp_mb__after_atomic_inc(); /* ensure post-GP actions seen after GP. */ + + /* + * Everyone up to our most recent fetch is covered by our grace + * period. Update the counter, but only if our work is still + * relevant -- which it won't be if someone who started later + * than we did beat us to the punch. + */ + do { + s = atomic_read(&sync_sched_expedited_done); + if (UINT_CMP_GE((unsigned)s, (unsigned)snap)) { + smp_mb(); /* ensure test happens before caller kfree */ + break; + } + } while (atomic_cmpxchg(&sync_sched_expedited_done, s, snap) != s); + put_online_cpus(); } EXPORT_SYMBOL_GPL(synchronize_sched_expedited); -- cgit v1.2.3 From 8a9c1cee26c0ece23b38c45b92b724438878f842 Mon Sep 17 00:00:00 2001 From: Mariusz Kozlowski Date: Wed, 15 Dec 2010 23:11:12 +0100 Subject: rculist: fix borked __list_for_each_rcu() macro This restores parentheses blance. Signed-off-by: Mariusz Kozlowski Signed-off-by: Paul E. McKenney --- include/linux/rculist.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rculist.h b/include/linux/rculist.h index f31ef61f1c65..70d3ba504d17 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -244,7 +244,7 @@ static inline void list_splice_init_rcu(struct list_head *list, #define __list_for_each_rcu(pos, head) \ for (pos = rcu_dereference_raw(list_next_rcu(head)); \ pos != (head); \ - pos = rcu_dereference_raw(list_next_rcu((pos))) + pos = rcu_dereference_raw(list_next_rcu(pos))) /** * list_for_each_entry_rcu - iterate over rcu list of given type -- cgit v1.2.3 From 3c2dcf2aed5ea22ecf65a9a871c4963faec421b3 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 15 Dec 2010 21:12:15 -0800 Subject: rcu: remove unused __list_for_each_rcu() macro Signed-off-by: Paul E. McKenney --- include/linux/rculist.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rculist.h b/include/linux/rculist.h index 70d3ba504d17..2dea94fc4402 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -241,11 +241,6 @@ static inline void list_splice_init_rcu(struct list_head *list, #define list_first_entry_rcu(ptr, type, member) \ list_entry_rcu((ptr)->next, type, member) -#define __list_for_each_rcu(pos, head) \ - for (pos = rcu_dereference_raw(list_next_rcu(head)); \ - pos != (head); \ - pos = rcu_dereference_raw(list_next_rcu(pos))) - /** * list_for_each_entry_rcu - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. -- cgit v1.2.3 From c6eda6c5eeb357ff231121619fb49d2bc0605faf Mon Sep 17 00:00:00 2001 From: Sundar Iyer Date: Mon, 13 Dec 2010 09:33:12 +0530 Subject: mfd/tc35892: rename tc35892 header to tc3589x Rename the header file to include further variants within the same mfd core driver Acked-by: Samuel Ortiz Signed-off-by: Sundar Iyer Signed-off-by: Linus Walleij --- drivers/gpio/tc35892-gpio.c | 2 +- drivers/mfd/tc35892.c | 2 +- include/linux/mfd/tc35892.h | 136 -------------------------------------------- include/linux/mfd/tc3589x.h | 136 ++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 138 insertions(+), 138 deletions(-) delete mode 100644 include/linux/mfd/tc35892.h create mode 100644 include/linux/mfd/tc3589x.h (limited to 'include/linux') diff --git a/drivers/gpio/tc35892-gpio.c b/drivers/gpio/tc35892-gpio.c index 7e10c935a047..027b857c18ff 100644 --- a/drivers/gpio/tc35892-gpio.c +++ b/drivers/gpio/tc35892-gpio.c @@ -13,7 +13,7 @@ #include #include #include -#include +#include /* * These registers are modified under the irq bus lock and cached to avoid diff --git a/drivers/mfd/tc35892.c b/drivers/mfd/tc35892.c index e619e2a55997..f230235c3765 100644 --- a/drivers/mfd/tc35892.c +++ b/drivers/mfd/tc35892.c @@ -12,7 +12,7 @@ #include #include #include -#include +#include /** * tc35892_reg_read() - read a single TC35892 register diff --git a/include/linux/mfd/tc35892.h b/include/linux/mfd/tc35892.h deleted file mode 100644 index eff3094ca84e..000000000000 --- a/include/linux/mfd/tc35892.h +++ /dev/null @@ -1,136 +0,0 @@ -/* - * Copyright (C) ST-Ericsson SA 2010 - * - * License Terms: GNU General Public License, version 2 - */ - -#ifndef __LINUX_MFD_TC35892_H -#define __LINUX_MFD_TC35892_H - -#include - -#define TC35892_RSTCTRL_IRQRST (1 << 4) -#define TC35892_RSTCTRL_TIMRST (1 << 3) -#define TC35892_RSTCTRL_ROTRST (1 << 2) -#define TC35892_RSTCTRL_KBDRST (1 << 1) -#define TC35892_RSTCTRL_GPIRST (1 << 0) - -#define TC35892_IRQST 0x91 - -#define TC35892_MANFCODE_MAGIC 0x03 -#define TC35892_MANFCODE 0x80 -#define TC35892_VERSION 0x81 -#define TC35892_IOCFG 0xA7 - -#define TC35892_CLKMODE 0x88 -#define TC35892_CLKCFG 0x89 -#define TC35892_CLKEN 0x8A - -#define TC35892_RSTCTRL 0x82 -#define TC35892_EXTRSTN 0x83 -#define TC35892_RSTINTCLR 0x84 - -#define TC35892_GPIOIS0 0xC9 -#define TC35892_GPIOIS1 0xCA -#define TC35892_GPIOIS2 0xCB -#define TC35892_GPIOIBE0 0xCC -#define TC35892_GPIOIBE1 0xCD -#define TC35892_GPIOIBE2 0xCE -#define TC35892_GPIOIEV0 0xCF -#define TC35892_GPIOIEV1 0xD0 -#define TC35892_GPIOIEV2 0xD1 -#define TC35892_GPIOIE0 0xD2 -#define TC35892_GPIOIE1 0xD3 -#define TC35892_GPIOIE2 0xD4 -#define TC35892_GPIORIS0 0xD6 -#define TC35892_GPIORIS1 0xD7 -#define TC35892_GPIORIS2 0xD8 -#define TC35892_GPIOMIS0 0xD9 -#define TC35892_GPIOMIS1 0xDA -#define TC35892_GPIOMIS2 0xDB -#define TC35892_GPIOIC0 0xDC -#define TC35892_GPIOIC1 0xDD -#define TC35892_GPIOIC2 0xDE - -#define TC35892_GPIODATA0 0xC0 -#define TC35892_GPIOMASK0 0xc1 -#define TC35892_GPIODATA1 0xC2 -#define TC35892_GPIOMASK1 0xc3 -#define TC35892_GPIODATA2 0xC4 -#define TC35892_GPIOMASK2 0xC5 - -#define TC35892_GPIODIR0 0xC6 -#define TC35892_GPIODIR1 0xC7 -#define TC35892_GPIODIR2 0xC8 - -#define TC35892_GPIOSYNC0 0xE6 -#define TC35892_GPIOSYNC1 0xE7 -#define TC35892_GPIOSYNC2 0xE8 - -#define TC35892_GPIOWAKE0 0xE9 -#define TC35892_GPIOWAKE1 0xEA -#define TC35892_GPIOWAKE2 0xEB - -#define TC35892_GPIOODM0 0xE0 -#define TC35892_GPIOODE0 0xE1 -#define TC35892_GPIOODM1 0xE2 -#define TC35892_GPIOODE1 0xE3 -#define TC35892_GPIOODM2 0xE4 -#define TC35892_GPIOODE2 0xE5 - -#define TC35892_INT_GPIIRQ 0 -#define TC35892_INT_TI0IRQ 1 -#define TC35892_INT_TI1IRQ 2 -#define TC35892_INT_TI2IRQ 3 -#define TC35892_INT_ROTIRQ 5 -#define TC35892_INT_KBDIRQ 6 -#define TC35892_INT_PORIRQ 7 - -#define TC35892_NR_INTERNAL_IRQS 8 -#define TC35892_INT_GPIO(x) (TC35892_NR_INTERNAL_IRQS + (x)) - -struct tc35892 { - struct mutex lock; - struct device *dev; - struct i2c_client *i2c; - - int irq_base; - int num_gpio; - struct tc35892_platform_data *pdata; -}; - -extern int tc35892_reg_write(struct tc35892 *tc35892, u8 reg, u8 data); -extern int tc35892_reg_read(struct tc35892 *tc35892, u8 reg); -extern int tc35892_block_read(struct tc35892 *tc35892, u8 reg, u8 length, - u8 *values); -extern int tc35892_block_write(struct tc35892 *tc35892, u8 reg, u8 length, - const u8 *values); -extern int tc35892_set_bits(struct tc35892 *tc35892, u8 reg, u8 mask, u8 val); - -/** - * struct tc35892_gpio_platform_data - TC35892 GPIO platform data - * @gpio_base: first gpio number assigned to TC35892. A maximum of - * %TC35892_NR_GPIOS GPIOs will be allocated. - * @setup: callback for board-specific initialization - * @remove: callback for board-specific teardown - */ -struct tc35892_gpio_platform_data { - int gpio_base; - void (*setup)(struct tc35892 *tc35892, unsigned gpio_base); - void (*remove)(struct tc35892 *tc35892, unsigned gpio_base); -}; - -/** - * struct tc35892_platform_data - TC35892 platform data - * @irq_base: base IRQ number. %TC35892_NR_IRQS irqs will be used. - * @gpio: GPIO-specific platform data - */ -struct tc35892_platform_data { - int irq_base; - struct tc35892_gpio_platform_data *gpio; -}; - -#define TC35892_NR_GPIOS 24 -#define TC35892_NR_IRQS TC35892_INT_GPIO(TC35892_NR_GPIOS) - -#endif diff --git a/include/linux/mfd/tc3589x.h b/include/linux/mfd/tc3589x.h new file mode 100644 index 000000000000..eff3094ca84e --- /dev/null +++ b/include/linux/mfd/tc3589x.h @@ -0,0 +1,136 @@ +/* + * Copyright (C) ST-Ericsson SA 2010 + * + * License Terms: GNU General Public License, version 2 + */ + +#ifndef __LINUX_MFD_TC35892_H +#define __LINUX_MFD_TC35892_H + +#include + +#define TC35892_RSTCTRL_IRQRST (1 << 4) +#define TC35892_RSTCTRL_TIMRST (1 << 3) +#define TC35892_RSTCTRL_ROTRST (1 << 2) +#define TC35892_RSTCTRL_KBDRST (1 << 1) +#define TC35892_RSTCTRL_GPIRST (1 << 0) + +#define TC35892_IRQST 0x91 + +#define TC35892_MANFCODE_MAGIC 0x03 +#define TC35892_MANFCODE 0x80 +#define TC35892_VERSION 0x81 +#define TC35892_IOCFG 0xA7 + +#define TC35892_CLKMODE 0x88 +#define TC35892_CLKCFG 0x89 +#define TC35892_CLKEN 0x8A + +#define TC35892_RSTCTRL 0x82 +#define TC35892_EXTRSTN 0x83 +#define TC35892_RSTINTCLR 0x84 + +#define TC35892_GPIOIS0 0xC9 +#define TC35892_GPIOIS1 0xCA +#define TC35892_GPIOIS2 0xCB +#define TC35892_GPIOIBE0 0xCC +#define TC35892_GPIOIBE1 0xCD +#define TC35892_GPIOIBE2 0xCE +#define TC35892_GPIOIEV0 0xCF +#define TC35892_GPIOIEV1 0xD0 +#define TC35892_GPIOIEV2 0xD1 +#define TC35892_GPIOIE0 0xD2 +#define TC35892_GPIOIE1 0xD3 +#define TC35892_GPIOIE2 0xD4 +#define TC35892_GPIORIS0 0xD6 +#define TC35892_GPIORIS1 0xD7 +#define TC35892_GPIORIS2 0xD8 +#define TC35892_GPIOMIS0 0xD9 +#define TC35892_GPIOMIS1 0xDA +#define TC35892_GPIOMIS2 0xDB +#define TC35892_GPIOIC0 0xDC +#define TC35892_GPIOIC1 0xDD +#define TC35892_GPIOIC2 0xDE + +#define TC35892_GPIODATA0 0xC0 +#define TC35892_GPIOMASK0 0xc1 +#define TC35892_GPIODATA1 0xC2 +#define TC35892_GPIOMASK1 0xc3 +#define TC35892_GPIODATA2 0xC4 +#define TC35892_GPIOMASK2 0xC5 + +#define TC35892_GPIODIR0 0xC6 +#define TC35892_GPIODIR1 0xC7 +#define TC35892_GPIODIR2 0xC8 + +#define TC35892_GPIOSYNC0 0xE6 +#define TC35892_GPIOSYNC1 0xE7 +#define TC35892_GPIOSYNC2 0xE8 + +#define TC35892_GPIOWAKE0 0xE9 +#define TC35892_GPIOWAKE1 0xEA +#define TC35892_GPIOWAKE2 0xEB + +#define TC35892_GPIOODM0 0xE0 +#define TC35892_GPIOODE0 0xE1 +#define TC35892_GPIOODM1 0xE2 +#define TC35892_GPIOODE1 0xE3 +#define TC35892_GPIOODM2 0xE4 +#define TC35892_GPIOODE2 0xE5 + +#define TC35892_INT_GPIIRQ 0 +#define TC35892_INT_TI0IRQ 1 +#define TC35892_INT_TI1IRQ 2 +#define TC35892_INT_TI2IRQ 3 +#define TC35892_INT_ROTIRQ 5 +#define TC35892_INT_KBDIRQ 6 +#define TC35892_INT_PORIRQ 7 + +#define TC35892_NR_INTERNAL_IRQS 8 +#define TC35892_INT_GPIO(x) (TC35892_NR_INTERNAL_IRQS + (x)) + +struct tc35892 { + struct mutex lock; + struct device *dev; + struct i2c_client *i2c; + + int irq_base; + int num_gpio; + struct tc35892_platform_data *pdata; +}; + +extern int tc35892_reg_write(struct tc35892 *tc35892, u8 reg, u8 data); +extern int tc35892_reg_read(struct tc35892 *tc35892, u8 reg); +extern int tc35892_block_read(struct tc35892 *tc35892, u8 reg, u8 length, + u8 *values); +extern int tc35892_block_write(struct tc35892 *tc35892, u8 reg, u8 length, + const u8 *values); +extern int tc35892_set_bits(struct tc35892 *tc35892, u8 reg, u8 mask, u8 val); + +/** + * struct tc35892_gpio_platform_data - TC35892 GPIO platform data + * @gpio_base: first gpio number assigned to TC35892. A maximum of + * %TC35892_NR_GPIOS GPIOs will be allocated. + * @setup: callback for board-specific initialization + * @remove: callback for board-specific teardown + */ +struct tc35892_gpio_platform_data { + int gpio_base; + void (*setup)(struct tc35892 *tc35892, unsigned gpio_base); + void (*remove)(struct tc35892 *tc35892, unsigned gpio_base); +}; + +/** + * struct tc35892_platform_data - TC35892 platform data + * @irq_base: base IRQ number. %TC35892_NR_IRQS irqs will be used. + * @gpio: GPIO-specific platform data + */ +struct tc35892_platform_data { + int irq_base; + struct tc35892_gpio_platform_data *gpio; +}; + +#define TC35892_NR_GPIOS 24 +#define TC35892_NR_IRQS TC35892_INT_GPIO(TC35892_NR_GPIOS) + +#endif -- cgit v1.2.3 From 20406ebff4a298e6e3abbc1717a90bb3e55dc820 Mon Sep 17 00:00:00 2001 From: Sundar Iyer Date: Mon, 13 Dec 2010 09:33:14 +0530 Subject: mfd/tc3589x: rename tc35892 structs/registers to tc359x Most of the register layout, client IRQ numbers on the TC35892 is shared also by other variants. Make this generic as tc3589x Acked-by: Samuel Ortiz Signed-off-by: Sundar Iyer Signed-off-by: Linus Walleij --- arch/arm/mach-ux500/board-mop500.c | 12 +- drivers/gpio/tc3589x-gpio.c | 268 ++++++++++++++++++------------------- drivers/mfd/tc3589x.c | 222 +++++++++++++++--------------- include/linux/mfd/tc3589x.h | 202 ++++++++++++++-------------- 4 files changed, 351 insertions(+), 353 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/mach-ux500/board-mop500.c b/arch/arm/mach-ux500/board-mop500.c index a8220c5a6a69..5c950261968e 100644 --- a/arch/arm/mach-ux500/board-mop500.c +++ b/arch/arm/mach-ux500/board-mop500.c @@ -19,8 +19,7 @@ #include #include #include -#include -#include +#include #include #include @@ -112,24 +111,24 @@ static struct pl022_ssp_controller ssp0_platform_data = { * TC35892 */ -static void mop500_tc35892_init(struct tc35892 *tc35892, unsigned int base) +static void mop500_tc35892_init(struct tc3589x *tc3589x, unsigned int base) { mop500_sdi_tc35892_init(); } -static struct tc35892_gpio_platform_data mop500_tc35892_gpio_data = { +static struct tc3589x_gpio_platform_data mop500_tc35892_gpio_data = { .gpio_base = MOP500_EGPIO(0), .setup = mop500_tc35892_init, }; -static struct tc35892_platform_data mop500_tc35892_data = { +static struct tc3589x_platform_data mop500_tc35892_data = { .gpio = &mop500_tc35892_gpio_data, .irq_base = MOP500_EGPIO_IRQ_BASE, }; static struct i2c_board_info mop500_i2c0_devices[] = { { - I2C_BOARD_INFO("tc35892", 0x42), + I2C_BOARD_INFO("tc3589x", 0x42), .irq = NOMADIK_GPIO_TO_IRQ(217), .platform_data = &mop500_tc35892_data, }, @@ -302,7 +301,6 @@ static void __init u8500_init_machine(void) nmk_config_pins(mop500_pins, ARRAY_SIZE(mop500_pins)); - ux500_ske_keypad_device.dev.platform_data = &ske_keypad_board; platform_add_devices(platform_devs, ARRAY_SIZE(platform_devs)); mop500_i2c_init(); diff --git a/drivers/gpio/tc3589x-gpio.c b/drivers/gpio/tc3589x-gpio.c index 027b857c18ff..180d584454fb 100644 --- a/drivers/gpio/tc3589x-gpio.c +++ b/drivers/gpio/tc3589x-gpio.c @@ -24,9 +24,9 @@ enum { REG_IBE, REG_IEV, REG_IS, REG_IE }; #define CACHE_NR_REGS 4 #define CACHE_NR_BANKS 3 -struct tc35892_gpio { +struct tc3589x_gpio { struct gpio_chip chip; - struct tc35892 *tc35892; + struct tc3589x *tc3589x; struct device *dev; struct mutex irq_lock; @@ -37,179 +37,179 @@ struct tc35892_gpio { u8 oldregs[CACHE_NR_REGS][CACHE_NR_BANKS]; }; -static inline struct tc35892_gpio *to_tc35892_gpio(struct gpio_chip *chip) +static inline struct tc3589x_gpio *to_tc3589x_gpio(struct gpio_chip *chip) { - return container_of(chip, struct tc35892_gpio, chip); + return container_of(chip, struct tc3589x_gpio, chip); } -static int tc35892_gpio_get(struct gpio_chip *chip, unsigned offset) +static int tc3589x_gpio_get(struct gpio_chip *chip, unsigned offset) { - struct tc35892_gpio *tc35892_gpio = to_tc35892_gpio(chip); - struct tc35892 *tc35892 = tc35892_gpio->tc35892; - u8 reg = TC35892_GPIODATA0 + (offset / 8) * 2; + struct tc3589x_gpio *tc3589x_gpio = to_tc3589x_gpio(chip); + struct tc3589x *tc3589x = tc3589x_gpio->tc3589x; + u8 reg = TC3589x_GPIODATA0 + (offset / 8) * 2; u8 mask = 1 << (offset % 8); int ret; - ret = tc35892_reg_read(tc35892, reg); + ret = tc3589x_reg_read(tc3589x, reg); if (ret < 0) return ret; return ret & mask; } -static void tc35892_gpio_set(struct gpio_chip *chip, unsigned offset, int val) +static void tc3589x_gpio_set(struct gpio_chip *chip, unsigned offset, int val) { - struct tc35892_gpio *tc35892_gpio = to_tc35892_gpio(chip); - struct tc35892 *tc35892 = tc35892_gpio->tc35892; - u8 reg = TC35892_GPIODATA0 + (offset / 8) * 2; + struct tc3589x_gpio *tc3589x_gpio = to_tc3589x_gpio(chip); + struct tc3589x *tc3589x = tc3589x_gpio->tc3589x; + u8 reg = TC3589x_GPIODATA0 + (offset / 8) * 2; unsigned pos = offset % 8; u8 data[] = {!!val << pos, 1 << pos}; - tc35892_block_write(tc35892, reg, ARRAY_SIZE(data), data); + tc3589x_block_write(tc3589x, reg, ARRAY_SIZE(data), data); } -static int tc35892_gpio_direction_output(struct gpio_chip *chip, +static int tc3589x_gpio_direction_output(struct gpio_chip *chip, unsigned offset, int val) { - struct tc35892_gpio *tc35892_gpio = to_tc35892_gpio(chip); - struct tc35892 *tc35892 = tc35892_gpio->tc35892; - u8 reg = TC35892_GPIODIR0 + offset / 8; + struct tc3589x_gpio *tc3589x_gpio = to_tc3589x_gpio(chip); + struct tc3589x *tc3589x = tc3589x_gpio->tc3589x; + u8 reg = TC3589x_GPIODIR0 + offset / 8; unsigned pos = offset % 8; - tc35892_gpio_set(chip, offset, val); + tc3589x_gpio_set(chip, offset, val); - return tc35892_set_bits(tc35892, reg, 1 << pos, 1 << pos); + return tc3589x_set_bits(tc3589x, reg, 1 << pos, 1 << pos); } -static int tc35892_gpio_direction_input(struct gpio_chip *chip, +static int tc3589x_gpio_direction_input(struct gpio_chip *chip, unsigned offset) { - struct tc35892_gpio *tc35892_gpio = to_tc35892_gpio(chip); - struct tc35892 *tc35892 = tc35892_gpio->tc35892; - u8 reg = TC35892_GPIODIR0 + offset / 8; + struct tc3589x_gpio *tc3589x_gpio = to_tc3589x_gpio(chip); + struct tc3589x *tc3589x = tc3589x_gpio->tc3589x; + u8 reg = TC3589x_GPIODIR0 + offset / 8; unsigned pos = offset % 8; - return tc35892_set_bits(tc35892, reg, 1 << pos, 0); + return tc3589x_set_bits(tc3589x, reg, 1 << pos, 0); } -static int tc35892_gpio_to_irq(struct gpio_chip *chip, unsigned offset) +static int tc3589x_gpio_to_irq(struct gpio_chip *chip, unsigned offset) { - struct tc35892_gpio *tc35892_gpio = to_tc35892_gpio(chip); + struct tc3589x_gpio *tc3589x_gpio = to_tc3589x_gpio(chip); - return tc35892_gpio->irq_base + offset; + return tc3589x_gpio->irq_base + offset; } static struct gpio_chip template_chip = { - .label = "tc35892", + .label = "tc3589x", .owner = THIS_MODULE, - .direction_input = tc35892_gpio_direction_input, - .get = tc35892_gpio_get, - .direction_output = tc35892_gpio_direction_output, - .set = tc35892_gpio_set, - .to_irq = tc35892_gpio_to_irq, + .direction_input = tc3589x_gpio_direction_input, + .get = tc3589x_gpio_get, + .direction_output = tc3589x_gpio_direction_output, + .set = tc3589x_gpio_set, + .to_irq = tc3589x_gpio_to_irq, .can_sleep = 1, }; -static int tc35892_gpio_irq_set_type(unsigned int irq, unsigned int type) +static int tc3589x_gpio_irq_set_type(unsigned int irq, unsigned int type) { - struct tc35892_gpio *tc35892_gpio = get_irq_chip_data(irq); - int offset = irq - tc35892_gpio->irq_base; + struct tc3589x_gpio *tc3589x_gpio = get_irq_chip_data(irq); + int offset = irq - tc3589x_gpio->irq_base; int regoffset = offset / 8; int mask = 1 << (offset % 8); if (type == IRQ_TYPE_EDGE_BOTH) { - tc35892_gpio->regs[REG_IBE][regoffset] |= mask; + tc3589x_gpio->regs[REG_IBE][regoffset] |= mask; return 0; } - tc35892_gpio->regs[REG_IBE][regoffset] &= ~mask; + tc3589x_gpio->regs[REG_IBE][regoffset] &= ~mask; if (type == IRQ_TYPE_LEVEL_LOW || type == IRQ_TYPE_LEVEL_HIGH) - tc35892_gpio->regs[REG_IS][regoffset] |= mask; + tc3589x_gpio->regs[REG_IS][regoffset] |= mask; else - tc35892_gpio->regs[REG_IS][regoffset] &= ~mask; + tc3589x_gpio->regs[REG_IS][regoffset] &= ~mask; if (type == IRQ_TYPE_EDGE_RISING || type == IRQ_TYPE_LEVEL_HIGH) - tc35892_gpio->regs[REG_IEV][regoffset] |= mask; + tc3589x_gpio->regs[REG_IEV][regoffset] |= mask; else - tc35892_gpio->regs[REG_IEV][regoffset] &= ~mask; + tc3589x_gpio->regs[REG_IEV][regoffset] &= ~mask; return 0; } -static void tc35892_gpio_irq_lock(unsigned int irq) +static void tc3589x_gpio_irq_lock(unsigned int irq) { - struct tc35892_gpio *tc35892_gpio = get_irq_chip_data(irq); + struct tc3589x_gpio *tc3589x_gpio = get_irq_chip_data(irq); - mutex_lock(&tc35892_gpio->irq_lock); + mutex_lock(&tc3589x_gpio->irq_lock); } -static void tc35892_gpio_irq_sync_unlock(unsigned int irq) +static void tc3589x_gpio_irq_sync_unlock(unsigned int irq) { - struct tc35892_gpio *tc35892_gpio = get_irq_chip_data(irq); - struct tc35892 *tc35892 = tc35892_gpio->tc35892; + struct tc3589x_gpio *tc3589x_gpio = get_irq_chip_data(irq); + struct tc3589x *tc3589x = tc3589x_gpio->tc3589x; static const u8 regmap[] = { - [REG_IBE] = TC35892_GPIOIBE0, - [REG_IEV] = TC35892_GPIOIEV0, - [REG_IS] = TC35892_GPIOIS0, - [REG_IE] = TC35892_GPIOIE0, + [REG_IBE] = TC3589x_GPIOIBE0, + [REG_IEV] = TC3589x_GPIOIEV0, + [REG_IS] = TC3589x_GPIOIS0, + [REG_IE] = TC3589x_GPIOIE0, }; int i, j; for (i = 0; i < CACHE_NR_REGS; i++) { for (j = 0; j < CACHE_NR_BANKS; j++) { - u8 old = tc35892_gpio->oldregs[i][j]; - u8 new = tc35892_gpio->regs[i][j]; + u8 old = tc3589x_gpio->oldregs[i][j]; + u8 new = tc3589x_gpio->regs[i][j]; if (new == old) continue; - tc35892_gpio->oldregs[i][j] = new; - tc35892_reg_write(tc35892, regmap[i] + j * 8, new); + tc3589x_gpio->oldregs[i][j] = new; + tc3589x_reg_write(tc3589x, regmap[i] + j * 8, new); } } - mutex_unlock(&tc35892_gpio->irq_lock); + mutex_unlock(&tc3589x_gpio->irq_lock); } -static void tc35892_gpio_irq_mask(unsigned int irq) +static void tc3589x_gpio_irq_mask(unsigned int irq) { - struct tc35892_gpio *tc35892_gpio = get_irq_chip_data(irq); - int offset = irq - tc35892_gpio->irq_base; + struct tc3589x_gpio *tc3589x_gpio = get_irq_chip_data(irq); + int offset = irq - tc3589x_gpio->irq_base; int regoffset = offset / 8; int mask = 1 << (offset % 8); - tc35892_gpio->regs[REG_IE][regoffset] &= ~mask; + tc3589x_gpio->regs[REG_IE][regoffset] &= ~mask; } -static void tc35892_gpio_irq_unmask(unsigned int irq) +static void tc3589x_gpio_irq_unmask(unsigned int irq) { - struct tc35892_gpio *tc35892_gpio = get_irq_chip_data(irq); - int offset = irq - tc35892_gpio->irq_base; + struct tc3589x_gpio *tc3589x_gpio = get_irq_chip_data(irq); + int offset = irq - tc3589x_gpio->irq_base; int regoffset = offset / 8; int mask = 1 << (offset % 8); - tc35892_gpio->regs[REG_IE][regoffset] |= mask; + tc3589x_gpio->regs[REG_IE][regoffset] |= mask; } -static struct irq_chip tc35892_gpio_irq_chip = { - .name = "tc35892-gpio", - .bus_lock = tc35892_gpio_irq_lock, - .bus_sync_unlock = tc35892_gpio_irq_sync_unlock, - .mask = tc35892_gpio_irq_mask, - .unmask = tc35892_gpio_irq_unmask, - .set_type = tc35892_gpio_irq_set_type, +static struct irq_chip tc3589x_gpio_irq_chip = { + .name = "tc3589x-gpio", + .bus_lock = tc3589x_gpio_irq_lock, + .bus_sync_unlock = tc3589x_gpio_irq_sync_unlock, + .mask = tc3589x_gpio_irq_mask, + .unmask = tc3589x_gpio_irq_unmask, + .set_type = tc3589x_gpio_irq_set_type, }; -static irqreturn_t tc35892_gpio_irq(int irq, void *dev) +static irqreturn_t tc3589x_gpio_irq(int irq, void *dev) { - struct tc35892_gpio *tc35892_gpio = dev; - struct tc35892 *tc35892 = tc35892_gpio->tc35892; + struct tc3589x_gpio *tc3589x_gpio = dev; + struct tc3589x *tc3589x = tc3589x_gpio->tc3589x; u8 status[CACHE_NR_BANKS]; int ret; int i; - ret = tc35892_block_read(tc35892, TC35892_GPIOMIS0, + ret = tc3589x_block_read(tc3589x, TC3589x_GPIOMIS0, ARRAY_SIZE(status), status); if (ret < 0) return IRQ_NONE; @@ -223,24 +223,24 @@ static irqreturn_t tc35892_gpio_irq(int irq, void *dev) int bit = __ffs(stat); int line = i * 8 + bit; - handle_nested_irq(tc35892_gpio->irq_base + line); + handle_nested_irq(tc3589x_gpio->irq_base + line); stat &= ~(1 << bit); } - tc35892_reg_write(tc35892, TC35892_GPIOIC0 + i, status[i]); + tc3589x_reg_write(tc3589x, TC3589x_GPIOIC0 + i, status[i]); } return IRQ_HANDLED; } -static int tc35892_gpio_irq_init(struct tc35892_gpio *tc35892_gpio) +static int tc3589x_gpio_irq_init(struct tc3589x_gpio *tc3589x_gpio) { - int base = tc35892_gpio->irq_base; + int base = tc3589x_gpio->irq_base; int irq; - for (irq = base; irq < base + tc35892_gpio->chip.ngpio; irq++) { - set_irq_chip_data(irq, tc35892_gpio); - set_irq_chip_and_handler(irq, &tc35892_gpio_irq_chip, + for (irq = base; irq < base + tc3589x_gpio->chip.ngpio; irq++) { + set_irq_chip_data(irq, tc3589x_gpio); + set_irq_chip_and_handler(irq, &tc3589x_gpio_irq_chip, handle_simple_irq); set_irq_nested_thread(irq, 1); #ifdef CONFIG_ARM @@ -253,12 +253,12 @@ static int tc35892_gpio_irq_init(struct tc35892_gpio *tc35892_gpio) return 0; } -static void tc35892_gpio_irq_remove(struct tc35892_gpio *tc35892_gpio) +static void tc3589x_gpio_irq_remove(struct tc3589x_gpio *tc3589x_gpio) { - int base = tc35892_gpio->irq_base; + int base = tc3589x_gpio->irq_base; int irq; - for (irq = base; irq < base + tc35892_gpio->chip.ngpio; irq++) { + for (irq = base; irq < base + tc3589x_gpio->chip.ngpio; irq++) { #ifdef CONFIG_ARM set_irq_flags(irq, 0); #endif @@ -267,15 +267,15 @@ static void tc35892_gpio_irq_remove(struct tc35892_gpio *tc35892_gpio) } } -static int __devinit tc35892_gpio_probe(struct platform_device *pdev) +static int __devinit tc3589x_gpio_probe(struct platform_device *pdev) { - struct tc35892 *tc35892 = dev_get_drvdata(pdev->dev.parent); - struct tc35892_gpio_platform_data *pdata; - struct tc35892_gpio *tc35892_gpio; + struct tc3589x *tc3589x = dev_get_drvdata(pdev->dev.parent); + struct tc3589x_gpio_platform_data *pdata; + struct tc3589x_gpio *tc3589x_gpio; int ret; int irq; - pdata = tc35892->pdata->gpio; + pdata = tc3589x->pdata->gpio; if (!pdata) return -ENODEV; @@ -283,107 +283,107 @@ static int __devinit tc35892_gpio_probe(struct platform_device *pdev) if (irq < 0) return irq; - tc35892_gpio = kzalloc(sizeof(struct tc35892_gpio), GFP_KERNEL); - if (!tc35892_gpio) + tc3589x_gpio = kzalloc(sizeof(struct tc3589x_gpio), GFP_KERNEL); + if (!tc3589x_gpio) return -ENOMEM; - mutex_init(&tc35892_gpio->irq_lock); + mutex_init(&tc3589x_gpio->irq_lock); - tc35892_gpio->dev = &pdev->dev; - tc35892_gpio->tc35892 = tc35892; + tc3589x_gpio->dev = &pdev->dev; + tc3589x_gpio->tc3589x = tc3589x; - tc35892_gpio->chip = template_chip; - tc35892_gpio->chip.ngpio = tc35892->num_gpio; - tc35892_gpio->chip.dev = &pdev->dev; - tc35892_gpio->chip.base = pdata->gpio_base; + tc3589x_gpio->chip = template_chip; + tc3589x_gpio->chip.ngpio = tc3589x->num_gpio; + tc3589x_gpio->chip.dev = &pdev->dev; + tc3589x_gpio->chip.base = pdata->gpio_base; - tc35892_gpio->irq_base = tc35892->irq_base + TC35892_INT_GPIO(0); + tc3589x_gpio->irq_base = tc3589x->irq_base + TC3589x_INT_GPIO(0); /* Bring the GPIO module out of reset */ - ret = tc35892_set_bits(tc35892, TC35892_RSTCTRL, - TC35892_RSTCTRL_GPIRST, 0); + ret = tc3589x_set_bits(tc3589x, TC3589x_RSTCTRL, + TC3589x_RSTCTRL_GPIRST, 0); if (ret < 0) goto out_free; - ret = tc35892_gpio_irq_init(tc35892_gpio); + ret = tc3589x_gpio_irq_init(tc3589x_gpio); if (ret) goto out_free; - ret = request_threaded_irq(irq, NULL, tc35892_gpio_irq, IRQF_ONESHOT, - "tc35892-gpio", tc35892_gpio); + ret = request_threaded_irq(irq, NULL, tc3589x_gpio_irq, IRQF_ONESHOT, + "tc3589x-gpio", tc3589x_gpio); if (ret) { dev_err(&pdev->dev, "unable to get irq: %d\n", ret); goto out_removeirq; } - ret = gpiochip_add(&tc35892_gpio->chip); + ret = gpiochip_add(&tc3589x_gpio->chip); if (ret) { dev_err(&pdev->dev, "unable to add gpiochip: %d\n", ret); goto out_freeirq; } if (pdata->setup) - pdata->setup(tc35892, tc35892_gpio->chip.base); + pdata->setup(tc3589x, tc3589x_gpio->chip.base); - platform_set_drvdata(pdev, tc35892_gpio); + platform_set_drvdata(pdev, tc3589x_gpio); return 0; out_freeirq: - free_irq(irq, tc35892_gpio); + free_irq(irq, tc3589x_gpio); out_removeirq: - tc35892_gpio_irq_remove(tc35892_gpio); + tc3589x_gpio_irq_remove(tc3589x_gpio); out_free: - kfree(tc35892_gpio); + kfree(tc3589x_gpio); return ret; } -static int __devexit tc35892_gpio_remove(struct platform_device *pdev) +static int __devexit tc3589x_gpio_remove(struct platform_device *pdev) { - struct tc35892_gpio *tc35892_gpio = platform_get_drvdata(pdev); - struct tc35892 *tc35892 = tc35892_gpio->tc35892; - struct tc35892_gpio_platform_data *pdata = tc35892->pdata->gpio; + struct tc3589x_gpio *tc3589x_gpio = platform_get_drvdata(pdev); + struct tc3589x *tc3589x = tc3589x_gpio->tc3589x; + struct tc3589x_gpio_platform_data *pdata = tc3589x->pdata->gpio; int irq = platform_get_irq(pdev, 0); int ret; if (pdata->remove) - pdata->remove(tc35892, tc35892_gpio->chip.base); + pdata->remove(tc3589x, tc3589x_gpio->chip.base); - ret = gpiochip_remove(&tc35892_gpio->chip); + ret = gpiochip_remove(&tc3589x_gpio->chip); if (ret < 0) { - dev_err(tc35892_gpio->dev, + dev_err(tc3589x_gpio->dev, "unable to remove gpiochip: %d\n", ret); return ret; } - free_irq(irq, tc35892_gpio); - tc35892_gpio_irq_remove(tc35892_gpio); + free_irq(irq, tc3589x_gpio); + tc3589x_gpio_irq_remove(tc3589x_gpio); platform_set_drvdata(pdev, NULL); - kfree(tc35892_gpio); + kfree(tc3589x_gpio); return 0; } -static struct platform_driver tc35892_gpio_driver = { - .driver.name = "tc35892-gpio", +static struct platform_driver tc3589x_gpio_driver = { + .driver.name = "tc3589x-gpio", .driver.owner = THIS_MODULE, - .probe = tc35892_gpio_probe, - .remove = __devexit_p(tc35892_gpio_remove), + .probe = tc3589x_gpio_probe, + .remove = __devexit_p(tc3589x_gpio_remove), }; -static int __init tc35892_gpio_init(void) +static int __init tc3589x_gpio_init(void) { - return platform_driver_register(&tc35892_gpio_driver); + return platform_driver_register(&tc3589x_gpio_driver); } -subsys_initcall(tc35892_gpio_init); +subsys_initcall(tc3589x_gpio_init); -static void __exit tc35892_gpio_exit(void) +static void __exit tc3589x_gpio_exit(void) { - platform_driver_unregister(&tc35892_gpio_driver); + platform_driver_unregister(&tc3589x_gpio_driver); } -module_exit(tc35892_gpio_exit); +module_exit(tc3589x_gpio_exit); MODULE_LICENSE("GPL v2"); -MODULE_DESCRIPTION("TC35892 GPIO driver"); +MODULE_DESCRIPTION("TC3589x GPIO driver"); MODULE_AUTHOR("Hanumath Prasad, Rabin Vincent"); diff --git a/drivers/mfd/tc3589x.c b/drivers/mfd/tc3589x.c index f230235c3765..7deff53181d1 100644 --- a/drivers/mfd/tc3589x.c +++ b/drivers/mfd/tc3589x.c @@ -15,141 +15,141 @@ #include /** - * tc35892_reg_read() - read a single TC35892 register - * @tc35892: Device to read from + * tc3589x_reg_read() - read a single TC3589x register + * @tc3589x: Device to read from * @reg: Register to read */ -int tc35892_reg_read(struct tc35892 *tc35892, u8 reg) +int tc3589x_reg_read(struct tc3589x *tc3589x, u8 reg) { int ret; - ret = i2c_smbus_read_byte_data(tc35892->i2c, reg); + ret = i2c_smbus_read_byte_data(tc3589x->i2c, reg); if (ret < 0) - dev_err(tc35892->dev, "failed to read reg %#x: %d\n", + dev_err(tc3589x->dev, "failed to read reg %#x: %d\n", reg, ret); return ret; } -EXPORT_SYMBOL_GPL(tc35892_reg_read); +EXPORT_SYMBOL_GPL(tc3589x_reg_read); /** - * tc35892_reg_read() - write a single TC35892 register - * @tc35892: Device to write to + * tc3589x_reg_read() - write a single TC3589x register + * @tc3589x: Device to write to * @reg: Register to read * @data: Value to write */ -int tc35892_reg_write(struct tc35892 *tc35892, u8 reg, u8 data) +int tc3589x_reg_write(struct tc3589x *tc3589x, u8 reg, u8 data) { int ret; - ret = i2c_smbus_write_byte_data(tc35892->i2c, reg, data); + ret = i2c_smbus_write_byte_data(tc3589x->i2c, reg, data); if (ret < 0) - dev_err(tc35892->dev, "failed to write reg %#x: %d\n", + dev_err(tc3589x->dev, "failed to write reg %#x: %d\n", reg, ret); return ret; } -EXPORT_SYMBOL_GPL(tc35892_reg_write); +EXPORT_SYMBOL_GPL(tc3589x_reg_write); /** - * tc35892_block_read() - read multiple TC35892 registers - * @tc35892: Device to read from + * tc3589x_block_read() - read multiple TC3589x registers + * @tc3589x: Device to read from * @reg: First register * @length: Number of registers * @values: Buffer to write to */ -int tc35892_block_read(struct tc35892 *tc35892, u8 reg, u8 length, u8 *values) +int tc3589x_block_read(struct tc3589x *tc3589x, u8 reg, u8 length, u8 *values) { int ret; - ret = i2c_smbus_read_i2c_block_data(tc35892->i2c, reg, length, values); + ret = i2c_smbus_read_i2c_block_data(tc3589x->i2c, reg, length, values); if (ret < 0) - dev_err(tc35892->dev, "failed to read regs %#x: %d\n", + dev_err(tc3589x->dev, "failed to read regs %#x: %d\n", reg, ret); return ret; } -EXPORT_SYMBOL_GPL(tc35892_block_read); +EXPORT_SYMBOL_GPL(tc3589x_block_read); /** - * tc35892_block_write() - write multiple TC35892 registers - * @tc35892: Device to write to + * tc3589x_block_write() - write multiple TC3589x registers + * @tc3589x: Device to write to * @reg: First register * @length: Number of registers * @values: Values to write */ -int tc35892_block_write(struct tc35892 *tc35892, u8 reg, u8 length, +int tc3589x_block_write(struct tc3589x *tc3589x, u8 reg, u8 length, const u8 *values) { int ret; - ret = i2c_smbus_write_i2c_block_data(tc35892->i2c, reg, length, + ret = i2c_smbus_write_i2c_block_data(tc3589x->i2c, reg, length, values); if (ret < 0) - dev_err(tc35892->dev, "failed to write regs %#x: %d\n", + dev_err(tc3589x->dev, "failed to write regs %#x: %d\n", reg, ret); return ret; } -EXPORT_SYMBOL_GPL(tc35892_block_write); +EXPORT_SYMBOL_GPL(tc3589x_block_write); /** - * tc35892_set_bits() - set the value of a bitfield in a TC35892 register - * @tc35892: Device to write to + * tc3589x_set_bits() - set the value of a bitfield in a TC3589x register + * @tc3589x: Device to write to * @reg: Register to write * @mask: Mask of bits to set * @values: Value to set */ -int tc35892_set_bits(struct tc35892 *tc35892, u8 reg, u8 mask, u8 val) +int tc3589x_set_bits(struct tc3589x *tc3589x, u8 reg, u8 mask, u8 val) { int ret; - mutex_lock(&tc35892->lock); + mutex_lock(&tc3589x->lock); - ret = tc35892_reg_read(tc35892, reg); + ret = tc3589x_reg_read(tc3589x, reg); if (ret < 0) goto out; ret &= ~mask; ret |= val; - ret = tc35892_reg_write(tc35892, reg, ret); + ret = tc3589x_reg_write(tc3589x, reg, ret); out: - mutex_unlock(&tc35892->lock); + mutex_unlock(&tc3589x->lock); return ret; } -EXPORT_SYMBOL_GPL(tc35892_set_bits); +EXPORT_SYMBOL_GPL(tc3589x_set_bits); static struct resource gpio_resources[] = { { - .start = TC35892_INT_GPIIRQ, - .end = TC35892_INT_GPIIRQ, + .start = TC3589x_INT_GPIIRQ, + .end = TC3589x_INT_GPIIRQ, .flags = IORESOURCE_IRQ, }, }; -static struct mfd_cell tc35892_devs[] = { +static struct mfd_cell tc3589x_devs[] = { { - .name = "tc35892-gpio", + .name = "tc3589x-gpio", .num_resources = ARRAY_SIZE(gpio_resources), .resources = &gpio_resources[0], }, }; -static irqreturn_t tc35892_irq(int irq, void *data) +static irqreturn_t tc3589x_irq(int irq, void *data) { - struct tc35892 *tc35892 = data; + struct tc3589x *tc3589x = data; int status; - status = tc35892_reg_read(tc35892, TC35892_IRQST); + status = tc3589x_reg_read(tc3589x, TC3589x_IRQST); if (status < 0) return IRQ_NONE; while (status) { int bit = __ffs(status); - handle_nested_irq(tc35892->irq_base + bit); + handle_nested_irq(tc3589x->irq_base + bit); status &= ~(1 << bit); } @@ -158,30 +158,30 @@ static irqreturn_t tc35892_irq(int irq, void *data) * have the last interrupt clear (for example, GPIO IC write) take * effect. */ - tc35892_reg_read(tc35892, TC35892_IRQST); + tc3589x_reg_read(tc3589x, TC3589x_IRQST); return IRQ_HANDLED; } -static void tc35892_irq_dummy(unsigned int irq) +static void tc3589x_irq_dummy(unsigned int irq) { /* No mask/unmask at this level */ } -static struct irq_chip tc35892_irq_chip = { - .name = "tc35892", - .mask = tc35892_irq_dummy, - .unmask = tc35892_irq_dummy, +static struct irq_chip tc3589x_irq_chip = { + .name = "tc3589x", + .mask = tc3589x_irq_dummy, + .unmask = tc3589x_irq_dummy, }; -static int tc35892_irq_init(struct tc35892 *tc35892) +static int tc3589x_irq_init(struct tc3589x *tc3589x) { - int base = tc35892->irq_base; + int base = tc3589x->irq_base; int irq; - for (irq = base; irq < base + TC35892_NR_INTERNAL_IRQS; irq++) { - set_irq_chip_data(irq, tc35892); - set_irq_chip_and_handler(irq, &tc35892_irq_chip, + for (irq = base; irq < base + TC3589x_NR_INTERNAL_IRQS; irq++) { + set_irq_chip_data(irq, tc3589x); + set_irq_chip_and_handler(irq, &tc3589x_irq_chip, handle_edge_irq); set_irq_nested_thread(irq, 1); #ifdef CONFIG_ARM @@ -194,12 +194,12 @@ static int tc35892_irq_init(struct tc35892 *tc35892) return 0; } -static void tc35892_irq_remove(struct tc35892 *tc35892) +static void tc3589x_irq_remove(struct tc3589x *tc3589x) { - int base = tc35892->irq_base; + int base = tc3589x->irq_base; int irq; - for (irq = base; irq < base + TC35892_NR_INTERNAL_IRQS; irq++) { + for (irq = base; irq < base + TC3589x_NR_INTERNAL_IRQS; irq++) { #ifdef CONFIG_ARM set_irq_flags(irq, 0); #endif @@ -208,138 +208,138 @@ static void tc35892_irq_remove(struct tc35892 *tc35892) } } -static int tc35892_chip_init(struct tc35892 *tc35892) +static int tc3589x_chip_init(struct tc3589x *tc3589x) { int manf, ver, ret; - manf = tc35892_reg_read(tc35892, TC35892_MANFCODE); + manf = tc3589x_reg_read(tc3589x, TC3589x_MANFCODE); if (manf < 0) return manf; - ver = tc35892_reg_read(tc35892, TC35892_VERSION); + ver = tc3589x_reg_read(tc3589x, TC3589x_VERSION); if (ver < 0) return ver; - if (manf != TC35892_MANFCODE_MAGIC) { - dev_err(tc35892->dev, "unknown manufacturer: %#x\n", manf); + if (manf != TC3589x_MANFCODE_MAGIC) { + dev_err(tc3589x->dev, "unknown manufacturer: %#x\n", manf); return -EINVAL; } - dev_info(tc35892->dev, "manufacturer: %#x, version: %#x\n", manf, ver); + dev_info(tc3589x->dev, "manufacturer: %#x, version: %#x\n", manf, ver); /* Put everything except the IRQ module into reset */ - ret = tc35892_reg_write(tc35892, TC35892_RSTCTRL, - TC35892_RSTCTRL_TIMRST - | TC35892_RSTCTRL_ROTRST - | TC35892_RSTCTRL_KBDRST - | TC35892_RSTCTRL_GPIRST); + ret = tc3589x_reg_write(tc3589x, TC3589x_RSTCTRL, + TC3589x_RSTCTRL_TIMRST + | TC3589x_RSTCTRL_ROTRST + | TC3589x_RSTCTRL_KBDRST + | TC3589x_RSTCTRL_GPIRST); if (ret < 0) return ret; /* Clear the reset interrupt. */ - return tc35892_reg_write(tc35892, TC35892_RSTINTCLR, 0x1); + return tc3589x_reg_write(tc3589x, TC3589x_RSTINTCLR, 0x1); } -static int __devinit tc35892_probe(struct i2c_client *i2c, +static int __devinit tc3589x_probe(struct i2c_client *i2c, const struct i2c_device_id *id) { - struct tc35892_platform_data *pdata = i2c->dev.platform_data; - struct tc35892 *tc35892; + struct tc3589x_platform_data *pdata = i2c->dev.platform_data; + struct tc3589x *tc3589x; int ret; if (!i2c_check_functionality(i2c->adapter, I2C_FUNC_SMBUS_BYTE_DATA | I2C_FUNC_SMBUS_I2C_BLOCK)) return -EIO; - tc35892 = kzalloc(sizeof(struct tc35892), GFP_KERNEL); - if (!tc35892) + tc3589x = kzalloc(sizeof(struct tc3589x), GFP_KERNEL); + if (!tc3589x) return -ENOMEM; - mutex_init(&tc35892->lock); + mutex_init(&tc3589x->lock); - tc35892->dev = &i2c->dev; - tc35892->i2c = i2c; - tc35892->pdata = pdata; - tc35892->irq_base = pdata->irq_base; - tc35892->num_gpio = id->driver_data; + tc3589x->dev = &i2c->dev; + tc3589x->i2c = i2c; + tc3589x->pdata = pdata; + tc3589x->irq_base = pdata->irq_base; + tc3589x->num_gpio = id->driver_data; - i2c_set_clientdata(i2c, tc35892); + i2c_set_clientdata(i2c, tc3589x); - ret = tc35892_chip_init(tc35892); + ret = tc3589x_chip_init(tc3589x); if (ret) goto out_free; - ret = tc35892_irq_init(tc35892); + ret = tc3589x_irq_init(tc3589x); if (ret) goto out_free; - ret = request_threaded_irq(tc35892->i2c->irq, NULL, tc35892_irq, + ret = request_threaded_irq(tc3589x->i2c->irq, NULL, tc3589x_irq, IRQF_TRIGGER_FALLING | IRQF_ONESHOT, - "tc35892", tc35892); + "tc3589x", tc3589x); if (ret) { - dev_err(tc35892->dev, "failed to request IRQ: %d\n", ret); + dev_err(tc3589x->dev, "failed to request IRQ: %d\n", ret); goto out_removeirq; } - ret = mfd_add_devices(tc35892->dev, -1, tc35892_devs, - ARRAY_SIZE(tc35892_devs), NULL, - tc35892->irq_base); + ret = mfd_add_devices(tc3589x->dev, -1, tc3589x_devs, + ARRAY_SIZE(tc3589x_devs), NULL, + tc3589x->irq_base); if (ret) { - dev_err(tc35892->dev, "failed to add children\n"); + dev_err(tc3589x->dev, "failed to add children\n"); goto out_freeirq; } return 0; out_freeirq: - free_irq(tc35892->i2c->irq, tc35892); + free_irq(tc3589x->i2c->irq, tc3589x); out_removeirq: - tc35892_irq_remove(tc35892); + tc3589x_irq_remove(tc3589x); out_free: - kfree(tc35892); + kfree(tc3589x); return ret; } -static int __devexit tc35892_remove(struct i2c_client *client) +static int __devexit tc3589x_remove(struct i2c_client *client) { - struct tc35892 *tc35892 = i2c_get_clientdata(client); + struct tc3589x *tc3589x = i2c_get_clientdata(client); - mfd_remove_devices(tc35892->dev); + mfd_remove_devices(tc3589x->dev); - free_irq(tc35892->i2c->irq, tc35892); - tc35892_irq_remove(tc35892); + free_irq(tc3589x->i2c->irq, tc3589x); + tc3589x_irq_remove(tc3589x); - kfree(tc35892); + kfree(tc3589x); return 0; } -static const struct i2c_device_id tc35892_id[] = { - { "tc35892", 24 }, +static const struct i2c_device_id tc3589x_id[] = { + { "tc3589x", 24 }, { } }; -MODULE_DEVICE_TABLE(i2c, tc35892_id); +MODULE_DEVICE_TABLE(i2c, tc3589x_id); -static struct i2c_driver tc35892_driver = { - .driver.name = "tc35892", +static struct i2c_driver tc3589x_driver = { + .driver.name = "tc3589x", .driver.owner = THIS_MODULE, - .probe = tc35892_probe, - .remove = __devexit_p(tc35892_remove), - .id_table = tc35892_id, + .probe = tc3589x_probe, + .remove = __devexit_p(tc3589x_remove), + .id_table = tc3589x_id, }; -static int __init tc35892_init(void) +static int __init tc3589x_init(void) { - return i2c_add_driver(&tc35892_driver); + return i2c_add_driver(&tc3589x_driver); } -subsys_initcall(tc35892_init); +subsys_initcall(tc3589x_init); -static void __exit tc35892_exit(void) +static void __exit tc3589x_exit(void) { - i2c_del_driver(&tc35892_driver); + i2c_del_driver(&tc3589x_driver); } -module_exit(tc35892_exit); +module_exit(tc3589x_exit); MODULE_LICENSE("GPL v2"); -MODULE_DESCRIPTION("TC35892 MFD core driver"); +MODULE_DESCRIPTION("TC3589x MFD core driver"); MODULE_AUTHOR("Hanumath Prasad, Rabin Vincent"); diff --git a/include/linux/mfd/tc3589x.h b/include/linux/mfd/tc3589x.h index eff3094ca84e..ea1918896f5b 100644 --- a/include/linux/mfd/tc3589x.h +++ b/include/linux/mfd/tc3589x.h @@ -4,133 +4,133 @@ * License Terms: GNU General Public License, version 2 */ -#ifndef __LINUX_MFD_TC35892_H -#define __LINUX_MFD_TC35892_H +#ifndef __LINUX_MFD_TC3589x_H +#define __LINUX_MFD_TC3589x_H #include -#define TC35892_RSTCTRL_IRQRST (1 << 4) -#define TC35892_RSTCTRL_TIMRST (1 << 3) -#define TC35892_RSTCTRL_ROTRST (1 << 2) -#define TC35892_RSTCTRL_KBDRST (1 << 1) -#define TC35892_RSTCTRL_GPIRST (1 << 0) - -#define TC35892_IRQST 0x91 - -#define TC35892_MANFCODE_MAGIC 0x03 -#define TC35892_MANFCODE 0x80 -#define TC35892_VERSION 0x81 -#define TC35892_IOCFG 0xA7 - -#define TC35892_CLKMODE 0x88 -#define TC35892_CLKCFG 0x89 -#define TC35892_CLKEN 0x8A - -#define TC35892_RSTCTRL 0x82 -#define TC35892_EXTRSTN 0x83 -#define TC35892_RSTINTCLR 0x84 - -#define TC35892_GPIOIS0 0xC9 -#define TC35892_GPIOIS1 0xCA -#define TC35892_GPIOIS2 0xCB -#define TC35892_GPIOIBE0 0xCC -#define TC35892_GPIOIBE1 0xCD -#define TC35892_GPIOIBE2 0xCE -#define TC35892_GPIOIEV0 0xCF -#define TC35892_GPIOIEV1 0xD0 -#define TC35892_GPIOIEV2 0xD1 -#define TC35892_GPIOIE0 0xD2 -#define TC35892_GPIOIE1 0xD3 -#define TC35892_GPIOIE2 0xD4 -#define TC35892_GPIORIS0 0xD6 -#define TC35892_GPIORIS1 0xD7 -#define TC35892_GPIORIS2 0xD8 -#define TC35892_GPIOMIS0 0xD9 -#define TC35892_GPIOMIS1 0xDA -#define TC35892_GPIOMIS2 0xDB -#define TC35892_GPIOIC0 0xDC -#define TC35892_GPIOIC1 0xDD -#define TC35892_GPIOIC2 0xDE - -#define TC35892_GPIODATA0 0xC0 -#define TC35892_GPIOMASK0 0xc1 -#define TC35892_GPIODATA1 0xC2 -#define TC35892_GPIOMASK1 0xc3 -#define TC35892_GPIODATA2 0xC4 -#define TC35892_GPIOMASK2 0xC5 - -#define TC35892_GPIODIR0 0xC6 -#define TC35892_GPIODIR1 0xC7 -#define TC35892_GPIODIR2 0xC8 - -#define TC35892_GPIOSYNC0 0xE6 -#define TC35892_GPIOSYNC1 0xE7 -#define TC35892_GPIOSYNC2 0xE8 - -#define TC35892_GPIOWAKE0 0xE9 -#define TC35892_GPIOWAKE1 0xEA -#define TC35892_GPIOWAKE2 0xEB - -#define TC35892_GPIOODM0 0xE0 -#define TC35892_GPIOODE0 0xE1 -#define TC35892_GPIOODM1 0xE2 -#define TC35892_GPIOODE1 0xE3 -#define TC35892_GPIOODM2 0xE4 -#define TC35892_GPIOODE2 0xE5 - -#define TC35892_INT_GPIIRQ 0 -#define TC35892_INT_TI0IRQ 1 -#define TC35892_INT_TI1IRQ 2 -#define TC35892_INT_TI2IRQ 3 -#define TC35892_INT_ROTIRQ 5 -#define TC35892_INT_KBDIRQ 6 -#define TC35892_INT_PORIRQ 7 - -#define TC35892_NR_INTERNAL_IRQS 8 -#define TC35892_INT_GPIO(x) (TC35892_NR_INTERNAL_IRQS + (x)) - -struct tc35892 { +#define TC3589x_RSTCTRL_IRQRST (1 << 4) +#define TC3589x_RSTCTRL_TIMRST (1 << 3) +#define TC3589x_RSTCTRL_ROTRST (1 << 2) +#define TC3589x_RSTCTRL_KBDRST (1 << 1) +#define TC3589x_RSTCTRL_GPIRST (1 << 0) + +#define TC3589x_IRQST 0x91 + +#define TC3589x_MANFCODE_MAGIC 0x03 +#define TC3589x_MANFCODE 0x80 +#define TC3589x_VERSION 0x81 +#define TC3589x_IOCFG 0xA7 + +#define TC3589x_CLKMODE 0x88 +#define TC3589x_CLKCFG 0x89 +#define TC3589x_CLKEN 0x8A + +#define TC3589x_RSTCTRL 0x82 +#define TC3589x_EXTRSTN 0x83 +#define TC3589x_RSTINTCLR 0x84 + +#define TC3589x_GPIOIS0 0xC9 +#define TC3589x_GPIOIS1 0xCA +#define TC3589x_GPIOIS2 0xCB +#define TC3589x_GPIOIBE0 0xCC +#define TC3589x_GPIOIBE1 0xCD +#define TC3589x_GPIOIBE2 0xCE +#define TC3589x_GPIOIEV0 0xCF +#define TC3589x_GPIOIEV1 0xD0 +#define TC3589x_GPIOIEV2 0xD1 +#define TC3589x_GPIOIE0 0xD2 +#define TC3589x_GPIOIE1 0xD3 +#define TC3589x_GPIOIE2 0xD4 +#define TC3589x_GPIORIS0 0xD6 +#define TC3589x_GPIORIS1 0xD7 +#define TC3589x_GPIORIS2 0xD8 +#define TC3589x_GPIOMIS0 0xD9 +#define TC3589x_GPIOMIS1 0xDA +#define TC3589x_GPIOMIS2 0xDB +#define TC3589x_GPIOIC0 0xDC +#define TC3589x_GPIOIC1 0xDD +#define TC3589x_GPIOIC2 0xDE + +#define TC3589x_GPIODATA0 0xC0 +#define TC3589x_GPIOMASK0 0xc1 +#define TC3589x_GPIODATA1 0xC2 +#define TC3589x_GPIOMASK1 0xc3 +#define TC3589x_GPIODATA2 0xC4 +#define TC3589x_GPIOMASK2 0xC5 + +#define TC3589x_GPIODIR0 0xC6 +#define TC3589x_GPIODIR1 0xC7 +#define TC3589x_GPIODIR2 0xC8 + +#define TC3589x_GPIOSYNC0 0xE6 +#define TC3589x_GPIOSYNC1 0xE7 +#define TC3589x_GPIOSYNC2 0xE8 + +#define TC3589x_GPIOWAKE0 0xE9 +#define TC3589x_GPIOWAKE1 0xEA +#define TC3589x_GPIOWAKE2 0xEB + +#define TC3589x_GPIOODM0 0xE0 +#define TC3589x_GPIOODE0 0xE1 +#define TC3589x_GPIOODM1 0xE2 +#define TC3589x_GPIOODE1 0xE3 +#define TC3589x_GPIOODM2 0xE4 +#define TC3589x_GPIOODE2 0xE5 + +#define TC3589x_INT_GPIIRQ 0 +#define TC3589x_INT_TI0IRQ 1 +#define TC3589x_INT_TI1IRQ 2 +#define TC3589x_INT_TI2IRQ 3 +#define TC3589x_INT_ROTIRQ 5 +#define TC3589x_INT_KBDIRQ 6 +#define TC3589x_INT_PORIRQ 7 + +#define TC3589x_NR_INTERNAL_IRQS 8 +#define TC3589x_INT_GPIO(x) (TC3589x_NR_INTERNAL_IRQS + (x)) + +struct tc3589x { struct mutex lock; struct device *dev; struct i2c_client *i2c; int irq_base; int num_gpio; - struct tc35892_platform_data *pdata; + struct tc3589x_platform_data *pdata; }; -extern int tc35892_reg_write(struct tc35892 *tc35892, u8 reg, u8 data); -extern int tc35892_reg_read(struct tc35892 *tc35892, u8 reg); -extern int tc35892_block_read(struct tc35892 *tc35892, u8 reg, u8 length, +extern int tc3589x_reg_write(struct tc3589x *tc3589x, u8 reg, u8 data); +extern int tc3589x_reg_read(struct tc3589x *tc3589x, u8 reg); +extern int tc3589x_block_read(struct tc3589x *tc3589x, u8 reg, u8 length, u8 *values); -extern int tc35892_block_write(struct tc35892 *tc35892, u8 reg, u8 length, +extern int tc3589x_block_write(struct tc3589x *tc3589x, u8 reg, u8 length, const u8 *values); -extern int tc35892_set_bits(struct tc35892 *tc35892, u8 reg, u8 mask, u8 val); +extern int tc3589x_set_bits(struct tc3589x *tc3589x, u8 reg, u8 mask, u8 val); /** - * struct tc35892_gpio_platform_data - TC35892 GPIO platform data - * @gpio_base: first gpio number assigned to TC35892. A maximum of - * %TC35892_NR_GPIOS GPIOs will be allocated. + * struct tc3589x_gpio_platform_data - TC3589x GPIO platform data + * @gpio_base: first gpio number assigned to TC3589x. A maximum of + * %TC3589x_NR_GPIOS GPIOs will be allocated. * @setup: callback for board-specific initialization * @remove: callback for board-specific teardown */ -struct tc35892_gpio_platform_data { +struct tc3589x_gpio_platform_data { int gpio_base; - void (*setup)(struct tc35892 *tc35892, unsigned gpio_base); - void (*remove)(struct tc35892 *tc35892, unsigned gpio_base); + void (*setup)(struct tc3589x *tc3589x, unsigned gpio_base); + void (*remove)(struct tc3589x *tc3589x, unsigned gpio_base); }; /** - * struct tc35892_platform_data - TC35892 platform data - * @irq_base: base IRQ number. %TC35892_NR_IRQS irqs will be used. + * struct tc3589x_platform_data - TC3589x platform data + * @irq_base: base IRQ number. %TC3589x_NR_IRQS irqs will be used. * @gpio: GPIO-specific platform data */ -struct tc35892_platform_data { +struct tc3589x_platform_data { int irq_base; - struct tc35892_gpio_platform_data *gpio; + struct tc3589x_gpio_platform_data *gpio; }; -#define TC35892_NR_GPIOS 24 -#define TC35892_NR_IRQS TC35892_INT_GPIO(TC35892_NR_GPIOS) +#define TC3589x_NR_GPIOS 24 +#define TC3589x_NR_IRQS TC3589x_INT_GPIO(TC3589x_NR_GPIOS) #endif -- cgit v1.2.3 From 611b7590afa6e6c6b0942b1d3efef17fbb348ef5 Mon Sep 17 00:00:00 2001 From: Sundar Iyer Date: Mon, 13 Dec 2010 09:33:15 +0530 Subject: mfd/tc3589x: add block identifier for multiple child devices Add block identifier to be able to add multiple mfd clients to the mfd core Acked-by: Samuel Ortiz Signed-off-by: Sundar Iyer Signed-off-by: Linus Walleij --- arch/arm/mach-ux500/board-mop500.c | 1 + drivers/mfd/tc3589x.c | 28 +++++++++++++++++++++++----- include/linux/mfd/tc3589x.h | 7 +++++++ 3 files changed, 31 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/mach-ux500/board-mop500.c b/arch/arm/mach-ux500/board-mop500.c index 5c950261968e..060b23aab8e4 100644 --- a/arch/arm/mach-ux500/board-mop500.c +++ b/arch/arm/mach-ux500/board-mop500.c @@ -122,6 +122,7 @@ static struct tc3589x_gpio_platform_data mop500_tc35892_gpio_data = { }; static struct tc3589x_platform_data mop500_tc35892_data = { + .block = TC3589x_BLOCK_GPIO, .gpio = &mop500_tc35892_gpio_data, .irq_base = MOP500_EGPIO_IRQ_BASE, }; diff --git a/drivers/mfd/tc3589x.c b/drivers/mfd/tc3589x.c index 7deff53181d1..0ed9669d95fa 100644 --- a/drivers/mfd/tc3589x.c +++ b/drivers/mfd/tc3589x.c @@ -129,7 +129,7 @@ static struct resource gpio_resources[] = { }, }; -static struct mfd_cell tc3589x_devs[] = { +static struct mfd_cell tc3589x_dev_gpio[] = { { .name = "tc3589x-gpio", .num_resources = ARRAY_SIZE(gpio_resources), @@ -240,6 +240,26 @@ static int tc3589x_chip_init(struct tc3589x *tc3589x) return tc3589x_reg_write(tc3589x, TC3589x_RSTINTCLR, 0x1); } +static int __devinit tc3589x_device_init(struct tc3589x *tc3589x) +{ + int ret = 0; + unsigned int blocks = tc3589x->pdata->block; + + if (blocks & TC3589x_BLOCK_GPIO) { + ret = mfd_add_devices(tc3589x->dev, -1, tc3589x_dev_gpio, + ARRAY_SIZE(tc3589x_dev_gpio), NULL, + tc3589x->irq_base); + if (ret) { + dev_err(tc3589x->dev, "failed to add gpio child\n"); + return ret; + } + dev_info(tc3589x->dev, "added gpio block\n"); + } + + return ret; + +} + static int __devinit tc3589x_probe(struct i2c_client *i2c, const struct i2c_device_id *id) { @@ -281,11 +301,9 @@ static int __devinit tc3589x_probe(struct i2c_client *i2c, goto out_removeirq; } - ret = mfd_add_devices(tc3589x->dev, -1, tc3589x_devs, - ARRAY_SIZE(tc3589x_devs), NULL, - tc3589x->irq_base); + ret = tc3589x_device_init(tc3589x); if (ret) { - dev_err(tc3589x->dev, "failed to add children\n"); + dev_err(tc3589x->dev, "failed to add child devices\n"); goto out_freeirq; } diff --git a/include/linux/mfd/tc3589x.h b/include/linux/mfd/tc3589x.h index ea1918896f5b..da00958b12d9 100644 --- a/include/linux/mfd/tc3589x.h +++ b/include/linux/mfd/tc3589x.h @@ -9,6 +9,11 @@ #include +enum tx3589x_block { + TC3589x_BLOCK_GPIO = 1 << 0, + TC3589x_BLOCK_KEYPAD = 1 << 1, +}; + #define TC3589x_RSTCTRL_IRQRST (1 << 4) #define TC3589x_RSTCTRL_TIMRST (1 << 3) #define TC3589x_RSTCTRL_ROTRST (1 << 2) @@ -122,10 +127,12 @@ struct tc3589x_gpio_platform_data { /** * struct tc3589x_platform_data - TC3589x platform data + * @block: bitmask of blocks to enable (use TC3589x_BLOCK_*) * @irq_base: base IRQ number. %TC3589x_NR_IRQS irqs will be used. * @gpio: GPIO-specific platform data */ struct tc3589x_platform_data { + unsigned int block; int irq_base; struct tc3589x_gpio_platform_data *gpio; }; -- cgit v1.2.3 From b8da46d3d55807037b58f14621a0949f18053bde Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Mon, 20 Dec 2010 00:29:32 -0500 Subject: clarify a usage constraint for cnt32_to_63() The cnt32_to_63 algorithm relies on proper counter data evaluation ordering to work properly. This was missing from the provided documentation. Let's augment the documentation with the missing usage constraint and fix the only instance that got it wrong. Signed-off-by: Nicolas Pitre Acked-by: David Howells Signed-off-by: Linus Torvalds --- arch/mn10300/kernel/time.c | 10 +++------- include/linux/cnt32_to_63.h | 20 +++++++++++++++++++- 2 files changed, 22 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/arch/mn10300/kernel/time.c b/arch/mn10300/kernel/time.c index f860a340acc9..75da468090b9 100644 --- a/arch/mn10300/kernel/time.c +++ b/arch/mn10300/kernel/time.c @@ -40,21 +40,17 @@ unsigned long long sched_clock(void) unsigned long long ll; unsigned l[2]; } tsc64, result; - unsigned long tsc, tmp; + unsigned long tmp; unsigned product[3]; /* 96-bit intermediate value */ /* cnt32_to_63() is not safe with preemption */ preempt_disable(); - /* read the TSC value - */ - tsc = get_cycles(); - - /* expand to 64-bits. + /* expand the tsc to 64-bits. * - sched_clock() must be called once a minute or better or the * following will go horribly wrong - see cnt32_to_63() */ - tsc64.ll = cnt32_to_63(tsc) & 0x7fffffffffffffffULL; + tsc64.ll = cnt32_to_63(get_cycles()) & 0x7fffffffffffffffULL; preempt_enable(); diff --git a/include/linux/cnt32_to_63.h b/include/linux/cnt32_to_63.h index 7605fdd1eb65..e3d8bf26e5eb 100644 --- a/include/linux/cnt32_to_63.h +++ b/include/linux/cnt32_to_63.h @@ -61,13 +61,31 @@ union cnt32_to_63 { * * 2) this code must not be preempted for a duration longer than the * 32-bit counter half period minus the longest period between two - * calls to this code. + * calls to this code; * * Those requirements ensure proper update to the state bit in memory. * This is usually not a problem in practice, but if it is then a kernel * timer should be scheduled to manage for this code to be executed often * enough. * + * And finally: + * + * 3) the cnt_lo argument must be seen as a globally incrementing value, + * meaning that it should be a direct reference to the counter data which + * can be evaluated according to a specific ordering within the macro, + * and not the result of a previous evaluation stored in a variable. + * + * For example, this is wrong: + * + * u32 partial = get_hw_count(); + * u64 full = cnt32_to_63(partial); + * return full; + * + * This is fine: + * + * u64 full = cnt32_to_63(get_hw_count()); + * return full; + * * Note that the top bit (bit 63) in the returned value should be considered * as garbage. It is not cleared here because callers are likely to use a * multiplier on the returned value which can get rid of the top bit -- cgit v1.2.3 From 24bdd9f4c9af75b33b438d60381a67626de0128d Mon Sep 17 00:00:00 2001 From: Javier Cardona Date: Thu, 16 Dec 2010 17:37:48 -0800 Subject: mac80211: Rename mesh_params to mesh_config to prepare for mesh_setup Mesh parameters can be to setup a mesh or to configure it. This patch renames the ambiguous name mesh_params to mesh_config in preparation for mesh_setup. Signed-off-by: Javier Cardona Signed-off-by: John W. Linville --- include/linux/nl80211.h | 15 ++++++++++----- include/net/cfg80211.h | 8 ++++---- net/mac80211/cfg.c | 8 ++++---- net/wireless/nl80211.c | 40 ++++++++++++++++++++-------------------- 4 files changed, 38 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 7483a89cee8f..11a1de67b618 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -172,10 +172,10 @@ * to the specified ISO/IEC 3166-1 alpha2 country code. The core will * store this as a valid request and then query userspace for it. * - * @NL80211_CMD_GET_MESH_PARAMS: Get mesh networking properties for the + * @NL80211_CMD_GET_MESH_CONFIG: Get mesh networking properties for the * interface identified by %NL80211_ATTR_IFINDEX * - * @NL80211_CMD_SET_MESH_PARAMS: Set mesh networking properties for the + * @NL80211_CMD_SET_MESH_CONFIG: Set mesh networking properties for the * interface identified by %NL80211_ATTR_IFINDEX * * @NL80211_CMD_SET_MGMT_EXTRA_IE: Set extra IEs for management frames. The @@ -448,8 +448,8 @@ enum nl80211_commands { NL80211_CMD_SET_REG, NL80211_CMD_REQ_SET_REG, - NL80211_CMD_GET_MESH_PARAMS, - NL80211_CMD_SET_MESH_PARAMS, + NL80211_CMD_GET_MESH_CONFIG, + NL80211_CMD_SET_MESH_CONFIG, NL80211_CMD_SET_MGMT_EXTRA_IE /* reserved; not used */, @@ -538,6 +538,10 @@ enum nl80211_commands { #define NL80211_CMD_DISASSOCIATE NL80211_CMD_DISASSOCIATE #define NL80211_CMD_REG_BEACON_HINT NL80211_CMD_REG_BEACON_HINT +/* source-level API compatibility */ +#define NL80211_CMD_GET_MESH_PARAMS NL80211_CMD_GET_MESH_CONFIG +#define NL80211_CMD_SET_MESH_PARAMS NL80211_CMD_SET_MESH_CONFIG + /** * enum nl80211_attrs - nl80211 netlink attributes * @@ -922,7 +926,7 @@ enum nl80211_attrs { NL80211_ATTR_REG_ALPHA2, NL80211_ATTR_REG_RULES, - NL80211_ATTR_MESH_PARAMS, + NL80211_ATTR_MESH_CONFIG, NL80211_ATTR_BSS_BASIC_RATES, @@ -1058,6 +1062,7 @@ enum nl80211_attrs { /* source-level API compatibility */ #define NL80211_ATTR_SCAN_GENERATION NL80211_ATTR_GENERATION +#define NL80211_ATTR_MESH_PARAMS NL80211_ATTR_MESH_CONFIG /* * Allow user space programs to use #ifdef on new attributes by defining them diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 6dc665a727c2..7283496c2d05 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1096,9 +1096,9 @@ struct cfg80211_pmksa { * @get_mpath: get a mesh path for the given parameters * @dump_mpath: dump mesh path callback -- resume dump at index @idx * - * @get_mesh_params: Put the current mesh parameters into *params + * @get_mesh_config: Get the current mesh configuration * - * @update_mesh_params: Update mesh parameters on a running mesh. + * @update_mesh_config: Update mesh parameters on a running mesh. * The mask is a bitfield which tells us which parameters to * set, and which to leave alone. * @@ -1246,10 +1246,10 @@ struct cfg80211_ops { int (*dump_mpath)(struct wiphy *wiphy, struct net_device *dev, int idx, u8 *dst, u8 *next_hop, struct mpath_info *pinfo); - int (*get_mesh_params)(struct wiphy *wiphy, + int (*get_mesh_config)(struct wiphy *wiphy, struct net_device *dev, struct mesh_config *conf); - int (*update_mesh_params)(struct wiphy *wiphy, + int (*update_mesh_config)(struct wiphy *wiphy, struct net_device *dev, u32 mask, const struct mesh_config *nconf); int (*join_mesh)(struct wiphy *wiphy, struct net_device *dev, diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index ea06f92801e9..1c94a2ae22ee 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -984,7 +984,7 @@ static int ieee80211_dump_mpath(struct wiphy *wiphy, struct net_device *dev, return 0; } -static int ieee80211_get_mesh_params(struct wiphy *wiphy, +static int ieee80211_get_mesh_config(struct wiphy *wiphy, struct net_device *dev, struct mesh_config *conf) { @@ -1000,7 +1000,7 @@ static inline bool _chg_mesh_attr(enum nl80211_meshconf_params parm, u32 mask) return (mask >> (parm-1)) & 0x1; } -static int ieee80211_update_mesh_params(struct wiphy *wiphy, +static int ieee80211_update_mesh_config(struct wiphy *wiphy, struct net_device *dev, u32 mask, const struct mesh_config *nconf) { @@ -1787,8 +1787,8 @@ struct cfg80211_ops mac80211_config_ops = { .change_mpath = ieee80211_change_mpath, .get_mpath = ieee80211_get_mpath, .dump_mpath = ieee80211_dump_mpath, - .update_mesh_params = ieee80211_update_mesh_params, - .get_mesh_params = ieee80211_get_mesh_params, + .update_mesh_config = ieee80211_update_mesh_config, + .get_mesh_config = ieee80211_get_mesh_config, .join_mesh = ieee80211_join_mesh, .leave_mesh = ieee80211_leave_mesh, #endif diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index aefce54d47e2..10be9350752e 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -123,7 +123,7 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = { .len = NL80211_MAX_SUPP_RATES }, [NL80211_ATTR_BSS_HT_OPMODE] = { .type = NLA_U16 }, - [NL80211_ATTR_MESH_PARAMS] = { .type = NLA_NESTED }, + [NL80211_ATTR_MESH_CONFIG] = { .type = NLA_NESTED }, [NL80211_ATTR_HT_CAPABILITY] = { .type = NLA_BINARY, .len = NL80211_HT_CAPABILITY_LEN }, @@ -719,7 +719,7 @@ static int nl80211_send_wiphy(struct sk_buff *msg, u32 pid, u32 seq, int flags, CMD(add_beacon, NEW_BEACON); CMD(add_station, NEW_STATION); CMD(add_mpath, NEW_MPATH); - CMD(update_mesh_params, SET_MESH_PARAMS); + CMD(update_mesh_config, SET_MESH_CONFIG); CMD(change_bss, SET_BSS); CMD(auth, AUTHENTICATE); CMD(assoc, ASSOCIATE); @@ -2673,7 +2673,7 @@ static int nl80211_req_set_reg(struct sk_buff *skb, struct genl_info *info) return r; } -static int nl80211_get_mesh_params(struct sk_buff *skb, +static int nl80211_get_mesh_config(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; @@ -2688,7 +2688,7 @@ static int nl80211_get_mesh_params(struct sk_buff *skb, if (wdev->iftype != NL80211_IFTYPE_MESH_POINT) return -EOPNOTSUPP; - if (!rdev->ops->get_mesh_params) + if (!rdev->ops->get_mesh_config) return -EOPNOTSUPP; wdev_lock(wdev); @@ -2696,7 +2696,7 @@ static int nl80211_get_mesh_params(struct sk_buff *skb, if (!wdev->mesh_id_len) memcpy(&cur_params, &default_mesh_config, sizeof(cur_params)); else - err = rdev->ops->get_mesh_params(&rdev->wiphy, dev, + err = rdev->ops->get_mesh_config(&rdev->wiphy, dev, &cur_params); wdev_unlock(wdev); @@ -2708,10 +2708,10 @@ static int nl80211_get_mesh_params(struct sk_buff *skb, if (!msg) return -ENOMEM; hdr = nl80211hdr_put(msg, info->snd_pid, info->snd_seq, 0, - NL80211_CMD_GET_MESH_PARAMS); + NL80211_CMD_GET_MESH_CONFIG); if (!hdr) goto nla_put_failure; - pinfoattr = nla_nest_start(msg, NL80211_ATTR_MESH_PARAMS); + pinfoattr = nla_nest_start(msg, NL80211_ATTR_MESH_CONFIG); if (!pinfoattr) goto nla_put_failure; NLA_PUT_U32(msg, NL80211_ATTR_IFINDEX, dev->ifindex); @@ -2773,7 +2773,7 @@ static const struct nla_policy nl80211_meshconf_params_policy[NL80211_MESHCONF_A [NL80211_MESHCONF_HWMP_NET_DIAM_TRVS_TIME] = { .type = NLA_U16 }, }; -static int nl80211_parse_mesh_params(struct genl_info *info, +static int nl80211_parse_mesh_config(struct genl_info *info, struct mesh_config *cfg, u32 *mask_out) { @@ -2789,10 +2789,10 @@ do {\ } while (0);\ - if (!info->attrs[NL80211_ATTR_MESH_PARAMS]) + if (!info->attrs[NL80211_ATTR_MESH_CONFIG]) return -EINVAL; if (nla_parse_nested(tb, NL80211_MESHCONF_ATTR_MAX, - info->attrs[NL80211_ATTR_MESH_PARAMS], + info->attrs[NL80211_ATTR_MESH_CONFIG], nl80211_meshconf_params_policy)) return -EINVAL; @@ -2847,7 +2847,7 @@ do {\ #undef FILL_IN_MESH_PARAM_IF_SET } -static int nl80211_update_mesh_params(struct sk_buff *skb, +static int nl80211_update_mesh_config(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; @@ -2860,10 +2860,10 @@ static int nl80211_update_mesh_params(struct sk_buff *skb, if (wdev->iftype != NL80211_IFTYPE_MESH_POINT) return -EOPNOTSUPP; - if (!rdev->ops->update_mesh_params) + if (!rdev->ops->update_mesh_config) return -EOPNOTSUPP; - err = nl80211_parse_mesh_params(info, &cfg, &mask); + err = nl80211_parse_mesh_config(info, &cfg, &mask); if (err) return err; @@ -2872,7 +2872,7 @@ static int nl80211_update_mesh_params(struct sk_buff *skb, err = -ENOLINK; if (!err) - err = rdev->ops->update_mesh_params(&rdev->wiphy, dev, + err = rdev->ops->update_mesh_config(&rdev->wiphy, dev, mask, &cfg); wdev_unlock(wdev); @@ -4672,9 +4672,9 @@ static int nl80211_join_mesh(struct sk_buff *skb, struct genl_info *info) /* start with default */ memcpy(&cfg, &default_mesh_config, sizeof(cfg)); - if (info->attrs[NL80211_ATTR_MESH_PARAMS]) { + if (info->attrs[NL80211_ATTR_MESH_CONFIG]) { /* and parse parameters if given */ - err = nl80211_parse_mesh_params(info, &cfg, NULL); + err = nl80211_parse_mesh_config(info, &cfg, NULL); if (err) return err; } @@ -4952,16 +4952,16 @@ static struct genl_ops nl80211_ops[] = { .flags = GENL_ADMIN_PERM, }, { - .cmd = NL80211_CMD_GET_MESH_PARAMS, - .doit = nl80211_get_mesh_params, + .cmd = NL80211_CMD_GET_MESH_CONFIG, + .doit = nl80211_get_mesh_config, .policy = nl80211_policy, /* can be retrieved by unprivileged users */ .internal_flags = NL80211_FLAG_NEED_NETDEV | NL80211_FLAG_NEED_RTNL, }, { - .cmd = NL80211_CMD_SET_MESH_PARAMS, - .doit = nl80211_update_mesh_params, + .cmd = NL80211_CMD_SET_MESH_CONFIG, + .doit = nl80211_update_mesh_config, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | -- cgit v1.2.3 From c80d545da3f7c0e534ccd4a780f322f80a92cff1 Mon Sep 17 00:00:00 2001 From: Javier Cardona Date: Thu, 16 Dec 2010 17:37:49 -0800 Subject: mac80211: Let userspace enable and configure vendor specific path selection. Userspace will now be allowed to toggle between the default path selection algorithm (HWMP, implemented in the kernel), and a vendor specific alternative. Also in the same patch, allow userspace to add information elements to mesh beacons. This is accordance with the Extensible Path Selection Framework specified in version 7.0 of the 802.11s draft. Signed-off-by: Javier Cardona Signed-off-by: John W. Linville --- include/linux/ieee80211.h | 25 ++++++++++++++++++ include/linux/nl80211.h | 47 +++++++++++++++++++++++++++++++--- include/net/cfg80211.h | 8 ++++++ net/mac80211/cfg.c | 39 +++++++++++++++++++++++++--- net/mac80211/ieee80211_i.h | 4 +-- net/mac80211/mesh.c | 7 ++++++ net/mac80211/mesh_plink.c | 3 ++- net/mac80211/tx.c | 3 ++- net/wireless/core.c | 22 +++++++++++----- net/wireless/core.h | 5 ++-- net/wireless/mesh.c | 24 ++++++++++-------- net/wireless/nl80211.c | 63 ++++++++++++++++++++++++++++++++++++++++++---- 12 files changed, 214 insertions(+), 36 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 7f2354534242..cd681681d211 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1291,6 +1291,31 @@ enum ieee80211_key_len { WLAN_KEY_LEN_AES_CMAC = 16, }; +/** + * enum - mesh path selection protocol identifier + * + * @IEEE80211_PATH_PROTOCOL_HWMP: the default path selection protocol + * @IEEE80211_PATH_PROTOCOL_VENDOR: a vendor specific protocol that will + * be specified in a vendor specific information element + */ +enum { + IEEE80211_PATH_PROTOCOL_HWMP = 0, + IEEE80211_PATH_PROTOCOL_VENDOR = 255, +}; + +/** + * enum - mesh path selection metric identifier + * + * @IEEE80211_PATH_METRIC_AIRTIME: the default path selection metric + * @IEEE80211_PATH_METRIC_VENDOR: a vendor specific metric that will be + * specified in a vendor specific information element + */ +enum { + IEEE80211_PATH_METRIC_AIRTIME = 0, + IEEE80211_PATH_METRIC_VENDOR = 255, +}; + + /* * IEEE 802.11-2007 7.3.2.9 Country information element * diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 11a1de67b618..69eaccac78c4 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -872,6 +872,9 @@ enum nl80211_commands { * attributes, specifying what a key should be set as default as. * See &enum nl80211_key_default_types. * + * @NL80211_ATTR_MESH_SETUP: Optional mesh setup parameters. These cannot be + * changed once the mesh is active. + * * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use */ @@ -1054,6 +1057,8 @@ enum nl80211_attrs { NL80211_ATTR_MAX_REMAIN_ON_CHANNEL_DURATION, + NL80211_ATTR_MESH_SETUP, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -1564,7 +1569,8 @@ enum nl80211_mntr_flags { /** * enum nl80211_meshconf_params - mesh configuration parameters * - * Mesh configuration parameters + * Mesh configuration parameters. These can be changed while the mesh is + * active. * * @__NL80211_MESHCONF_INVALID: internal use * @@ -1587,9 +1593,6 @@ enum nl80211_mntr_flags { * @NL80211_MESHCONF_TTL: specifies the value of TTL field set at a source mesh * point. * - * @NL80211_MESHCONF_ELEMENT_TTL: specifies the value of TTL field set at a - * source mesh point for path selection elements. - * * @NL80211_MESHCONF_AUTO_OPEN_PLINKS: whether we should automatically * open peer links when we detect compatible mesh peers. * @@ -1616,6 +1619,9 @@ enum nl80211_mntr_flags { * * @NL80211_MESHCONF_ROOTMODE: whether root mode is enabled or not * + * @NL80211_MESHCONF_ELEMENT_TTL: specifies the value of TTL field set at a + * source mesh point for path selection elements. + * * @NL80211_MESHCONF_ATTR_MAX: highest possible mesh configuration attribute * * @__NL80211_MESHCONF_ATTR_AFTER_LAST: internal use @@ -1643,6 +1649,39 @@ enum nl80211_meshconf_params { NL80211_MESHCONF_ATTR_MAX = __NL80211_MESHCONF_ATTR_AFTER_LAST - 1 }; +/** + * enum nl80211_mesh_setup_params - mesh setup parameters + * + * Mesh setup parameters. These are used to start/join a mesh and cannot be + * changed while the mesh is active. + * + * @__NL80211_MESH_SETUP_INVALID: Internal use + * + * @NL80211_MESH_SETUP_ENABLE_VENDOR_PATH_SEL: Enable this option to use a + * vendor specific path selection algorithm or disable it to use the default + * HWMP. + * + * @NL80211_MESH_SETUP_ENABLE_VENDOR_METRIC: Enable this option to use a + * vendor specific path metric or disable it to use the default Airtime + * metric. + * + * @NL80211_MESH_SETUP_VENDOR_PATH_SEL_IE: A vendor specific information + * element that vendors will use to identify the path selection methods and + * metrics in use. + * + * @__NL80211_MESH_SETUP_ATTR_AFTER_LAST: Internal use + */ +enum nl80211_mesh_setup_params { + __NL80211_MESH_SETUP_INVALID, + NL80211_MESH_SETUP_ENABLE_VENDOR_PATH_SEL, + NL80211_MESH_SETUP_ENABLE_VENDOR_METRIC, + NL80211_MESH_SETUP_VENDOR_PATH_SEL_IE, + + /* keep last */ + __NL80211_MESH_SETUP_ATTR_AFTER_LAST, + NL80211_MESH_SETUP_ATTR_MAX = __NL80211_MESH_SETUP_ATTR_AFTER_LAST - 1 +}; + /** * enum nl80211_txq_attr - TX queue parameter attributes * @__NL80211_TXQ_ATTR_INVALID: Attribute number 0 is reserved diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 7283496c2d05..924d60366233 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -649,12 +649,20 @@ struct mesh_config { * struct mesh_setup - 802.11s mesh setup configuration * @mesh_id: the mesh ID * @mesh_id_len: length of the mesh ID, at least 1 and at most 32 bytes + * @path_sel_proto: which path selection protocol to use + * @path_metric: which metric to use + * @vendor_ie: vendor information elements (optional) + * @vendor_ie_len: length of vendor information elements * * These parameters are fixed when the mesh is created. */ struct mesh_setup { const u8 *mesh_id; u8 mesh_id_len; + u8 path_sel_proto; + u8 path_metric; + const u8 *vendor_ie; + u8 vendor_ie_len; }; /** diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 1c94a2ae22ee..ae2c7127a8aa 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1000,6 +1000,36 @@ static inline bool _chg_mesh_attr(enum nl80211_meshconf_params parm, u32 mask) return (mask >> (parm-1)) & 0x1; } +static int copy_mesh_setup(struct ieee80211_if_mesh *ifmsh, + const struct mesh_setup *setup) +{ + u8 *new_ie; + const u8 *old_ie; + + /* first allocate the new vendor information element */ + new_ie = NULL; + old_ie = ifmsh->vendor_ie; + + ifmsh->vendor_ie_len = setup->vendor_ie_len; + if (setup->vendor_ie_len) { + new_ie = kmemdup(setup->vendor_ie, setup->vendor_ie_len, + GFP_KERNEL); + if (!new_ie) + return -ENOMEM; + } + + /* now copy the rest of the setup parameters */ + ifmsh->mesh_id_len = setup->mesh_id_len; + memcpy(ifmsh->mesh_id, setup->mesh_id, ifmsh->mesh_id_len); + ifmsh->mesh_pp_id = setup->path_sel_proto; + ifmsh->mesh_pm_id = setup->path_metric; + ifmsh->vendor_ie = new_ie; + + kfree(old_ie); + + return 0; +} + static int ieee80211_update_mesh_config(struct wiphy *wiphy, struct net_device *dev, u32 mask, const struct mesh_config *nconf) @@ -1059,11 +1089,12 @@ static int ieee80211_join_mesh(struct wiphy *wiphy, struct net_device *dev, { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; + int err; - memcpy(&sdata->u.mesh.mshcfg, conf, sizeof(struct mesh_config)); - ifmsh->mesh_id_len = setup->mesh_id_len; - memcpy(ifmsh->mesh_id, setup->mesh_id, ifmsh->mesh_id_len); - + memcpy(&ifmsh->mshcfg, conf, sizeof(struct mesh_config)); + err = copy_mesh_setup(ifmsh, setup); + if (err) + return err; ieee80211_start_mesh(sdata); return 0; diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index ce58b2a676e2..eadaa243a3da 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -484,6 +484,8 @@ struct ieee80211_if_mesh { struct mesh_config mshcfg; u32 mesh_seqnum; bool accepting_plinks; + const u8 *vendor_ie; + u8 vendor_ie_len; }; #ifdef CONFIG_MAC80211_MESH @@ -585,9 +587,7 @@ struct ieee80211_sub_if_data { struct ieee80211_if_vlan vlan; struct ieee80211_if_managed mgd; struct ieee80211_if_ibss ibss; -#ifdef CONFIG_MAC80211_MESH struct ieee80211_if_mesh mesh; -#endif u32 mntr_flags; } u; diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index 63e1188d5062..c326e009389d 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -287,6 +287,13 @@ void mesh_mgmt_ies_add(struct sk_buff *skb, struct ieee80211_sub_if_data *sdata) *pos++ |= sdata->u.mesh.accepting_plinks ? MESHCONF_CAPAB_ACCEPT_PLINKS : 0x00; *pos++ = 0x00; + + if (sdata->u.mesh.vendor_ie) { + int len = sdata->u.mesh.vendor_ie_len; + const u8 *data = sdata->u.mesh.vendor_ie; + if (skb_tailroom(skb) > len) + memcpy(skb_put(skb, len), data, len); + } } u32 mesh_table_hash(u8 *addr, struct ieee80211_sub_if_data *sdata, struct mesh_table *tbl) diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c index 1c91f0f3c307..44b53931ba5e 100644 --- a/net/mac80211/mesh_plink.c +++ b/net/mac80211/mesh_plink.c @@ -160,7 +160,8 @@ static int mesh_plink_frame_tx(struct ieee80211_sub_if_data *sdata, enum plink_frame_type action, u8 *da, __le16 llid, __le16 plid, __le16 reason) { struct ieee80211_local *local = sdata->local; - struct sk_buff *skb = dev_alloc_skb(local->hw.extra_tx_headroom + 400); + struct sk_buff *skb = dev_alloc_skb(local->hw.extra_tx_headroom + 400 + + sdata->u.mesh.vendor_ie_len); struct ieee80211_mgmt *mgmt; bool include_plid = false; static const u8 meshpeeringproto[] = { 0x00, 0x0F, 0xAC, 0x2A }; diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 157bde993ef5..f4b1b624ea9f 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -2290,7 +2290,8 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw, u8 *pos; /* headroom, head length, tail length and maximum TIM length */ - skb = dev_alloc_skb(local->tx_headroom + 400); + skb = dev_alloc_skb(local->tx_headroom + 400 + + sdata->u.mesh.vendor_ie_len); if (!skb) goto out; diff --git a/net/wireless/core.c b/net/wireless/core.c index 79772fcc37bc..e9a5f8ca4c27 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -789,13 +789,23 @@ static int cfg80211_netdev_notifier_call(struct notifier_block * nb, cfg80211_mgd_wext_connect(rdev, wdev); break; #endif +#ifdef CONFIG_MAC80211_MESH case NL80211_IFTYPE_MESH_POINT: - /* backward compat code ... */ - if (wdev->mesh_id_up_len) - __cfg80211_join_mesh(rdev, dev, wdev->ssid, - wdev->mesh_id_up_len, - &default_mesh_config); - break; + { + /* backward compat code... */ + struct mesh_setup setup; + memcpy(&setup, &default_mesh_setup, + sizeof(setup)); + /* back compat only needed for mesh_id */ + setup.mesh_id = wdev->ssid; + setup.mesh_id_len = wdev->mesh_id_up_len; + if (wdev->mesh_id_up_len) + __cfg80211_join_mesh(rdev, dev, + &setup, + &default_mesh_config); + break; + } +#endif default: break; } diff --git a/net/wireless/core.h b/net/wireless/core.h index 743203bb61ac..26a0a084e16b 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -287,13 +287,14 @@ int cfg80211_ibss_wext_join(struct cfg80211_registered_device *rdev, /* mesh */ extern const struct mesh_config default_mesh_config; +extern const struct mesh_setup default_mesh_setup; int __cfg80211_join_mesh(struct cfg80211_registered_device *rdev, struct net_device *dev, - const u8 *mesh_id, u8 mesh_id_len, + const struct mesh_setup *setup, const struct mesh_config *conf); int cfg80211_join_mesh(struct cfg80211_registered_device *rdev, struct net_device *dev, - const u8 *mesh_id, u8 mesh_id_len, + const struct mesh_setup *setup, const struct mesh_config *conf); int cfg80211_leave_mesh(struct cfg80211_registered_device *rdev, struct net_device *dev); diff --git a/net/wireless/mesh.c b/net/wireless/mesh.c index e0b9747fe50a..73e39c171ffb 100644 --- a/net/wireless/mesh.c +++ b/net/wireless/mesh.c @@ -50,17 +50,19 @@ const struct mesh_config default_mesh_config = { .min_discovery_timeout = MESH_MIN_DISCOVERY_TIMEOUT, }; +const struct mesh_setup default_mesh_setup = { + .path_sel_proto = IEEE80211_PATH_PROTOCOL_HWMP, + .path_metric = IEEE80211_PATH_METRIC_AIRTIME, + .vendor_ie = NULL, + .vendor_ie_len = 0, +}; int __cfg80211_join_mesh(struct cfg80211_registered_device *rdev, struct net_device *dev, - const u8 *mesh_id, u8 mesh_id_len, + const struct mesh_setup *setup, const struct mesh_config *conf) { struct wireless_dev *wdev = dev->ieee80211_ptr; - struct mesh_setup setup = { - .mesh_id = mesh_id, - .mesh_id_len = mesh_id_len, - }; int err; BUILD_BUG_ON(IEEE80211_MAX_SSID_LEN != IEEE80211_MAX_MESH_ID_LEN); @@ -73,16 +75,16 @@ int __cfg80211_join_mesh(struct cfg80211_registered_device *rdev, if (wdev->mesh_id_len) return -EALREADY; - if (!mesh_id_len) + if (!setup->mesh_id_len) return -EINVAL; if (!rdev->ops->join_mesh) return -EOPNOTSUPP; - err = rdev->ops->join_mesh(&rdev->wiphy, dev, conf, &setup); + err = rdev->ops->join_mesh(&rdev->wiphy, dev, conf, setup); if (!err) { - memcpy(wdev->ssid, mesh_id, mesh_id_len); - wdev->mesh_id_len = mesh_id_len; + memcpy(wdev->ssid, setup->mesh_id, setup->mesh_id_len); + wdev->mesh_id_len = setup->mesh_id_len; } return err; @@ -90,14 +92,14 @@ int __cfg80211_join_mesh(struct cfg80211_registered_device *rdev, int cfg80211_join_mesh(struct cfg80211_registered_device *rdev, struct net_device *dev, - const u8 *mesh_id, u8 mesh_id_len, + const struct mesh_setup *setup, const struct mesh_config *conf) { struct wireless_dev *wdev = dev->ieee80211_ptr; int err; wdev_lock(wdev); - err = __cfg80211_join_mesh(rdev, dev, mesh_id, mesh_id_len, conf); + err = __cfg80211_join_mesh(rdev, dev, setup, conf); wdev_unlock(wdev); return err; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 10be9350752e..eef89d0b558b 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -2773,6 +2773,14 @@ static const struct nla_policy nl80211_meshconf_params_policy[NL80211_MESHCONF_A [NL80211_MESHCONF_HWMP_NET_DIAM_TRVS_TIME] = { .type = NLA_U16 }, }; +static const struct nla_policy + nl80211_mesh_setup_params_policy[NL80211_MESH_SETUP_ATTR_MAX+1] = { + [NL80211_MESH_SETUP_ENABLE_VENDOR_PATH_SEL] = { .type = NLA_U8 }, + [NL80211_MESH_SETUP_ENABLE_VENDOR_METRIC] = { .type = NLA_U8 }, + [NL80211_MESH_SETUP_VENDOR_PATH_SEL_IE] = { .type = NLA_BINARY, + .len = IEEE80211_MAX_DATA_LEN }, +}; + static int nl80211_parse_mesh_config(struct genl_info *info, struct mesh_config *cfg, u32 *mask_out) @@ -2839,14 +2847,50 @@ do {\ dot11MeshHWMPRootMode, mask, NL80211_MESHCONF_HWMP_ROOTMODE, nla_get_u8); - if (mask_out) *mask_out = mask; + return 0; #undef FILL_IN_MESH_PARAM_IF_SET } +static int nl80211_parse_mesh_setup(struct genl_info *info, + struct mesh_setup *setup) +{ + struct nlattr *tb[NL80211_MESH_SETUP_ATTR_MAX + 1]; + + if (!info->attrs[NL80211_ATTR_MESH_SETUP]) + return -EINVAL; + if (nla_parse_nested(tb, NL80211_MESH_SETUP_ATTR_MAX, + info->attrs[NL80211_ATTR_MESH_SETUP], + nl80211_mesh_setup_params_policy)) + return -EINVAL; + + if (tb[NL80211_MESH_SETUP_ENABLE_VENDOR_PATH_SEL]) + setup->path_sel_proto = + (nla_get_u8(tb[NL80211_MESH_SETUP_ENABLE_VENDOR_PATH_SEL])) ? + IEEE80211_PATH_PROTOCOL_VENDOR : + IEEE80211_PATH_PROTOCOL_HWMP; + + if (tb[NL80211_MESH_SETUP_ENABLE_VENDOR_METRIC]) + setup->path_metric = + (nla_get_u8(tb[NL80211_MESH_SETUP_ENABLE_VENDOR_METRIC])) ? + IEEE80211_PATH_METRIC_VENDOR : + IEEE80211_PATH_METRIC_AIRTIME; + + if (tb[NL80211_MESH_SETUP_VENDOR_PATH_SEL_IE]) { + struct nlattr *ieattr = + tb[NL80211_MESH_SETUP_VENDOR_PATH_SEL_IE]; + if (!is_valid_ie_attr(ieattr)) + return -EINVAL; + setup->vendor_ie = nla_data(ieattr); + setup->vendor_ie_len = nla_len(ieattr); + } + + return 0; +} + static int nl80211_update_mesh_config(struct sk_buff *skb, struct genl_info *info) { @@ -4667,10 +4711,12 @@ static int nl80211_join_mesh(struct sk_buff *skb, struct genl_info *info) struct cfg80211_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct mesh_config cfg; + struct mesh_setup setup; int err; /* start with default */ memcpy(&cfg, &default_mesh_config, sizeof(cfg)); + memcpy(&setup, &default_mesh_setup, sizeof(setup)); if (info->attrs[NL80211_ATTR_MESH_CONFIG]) { /* and parse parameters if given */ @@ -4683,10 +4729,17 @@ static int nl80211_join_mesh(struct sk_buff *skb, struct genl_info *info) !nla_len(info->attrs[NL80211_ATTR_MESH_ID])) return -EINVAL; - return cfg80211_join_mesh(rdev, dev, - nla_data(info->attrs[NL80211_ATTR_MESH_ID]), - nla_len(info->attrs[NL80211_ATTR_MESH_ID]), - &cfg); + setup.mesh_id = nla_data(info->attrs[NL80211_ATTR_MESH_ID]); + setup.mesh_id_len = nla_len(info->attrs[NL80211_ATTR_MESH_ID]); + + if (info->attrs[NL80211_ATTR_MESH_SETUP]) { + /* parse additional setup parameters if given */ + err = nl80211_parse_mesh_setup(info, &setup); + if (err) + return err; + } + + return cfg80211_join_mesh(rdev, dev, &setup, &cfg); } static int nl80211_leave_mesh(struct sk_buff *skb, struct genl_info *info) -- cgit v1.2.3 From 39fd5de4472b7b222c6cec78d72b069133f694e4 Mon Sep 17 00:00:00 2001 From: Bruno Randolf Date: Thu, 16 Dec 2010 11:30:28 +0900 Subject: nl80211: Export available antennas Export the information which antennas are available for configuration as TX or RX antennas via nl80211. Signed-off-by: Bruno Randolf Signed-off-by: John W. Linville --- include/linux/nl80211.h | 9 +++++++++ net/wireless/nl80211.c | 5 +++++ 2 files changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 69eaccac78c4..2b89b712565b 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -858,6 +858,12 @@ enum nl80211_commands { * the hardware should not be configured to receive on this antenna. * For a more detailed descripton see @NL80211_ATTR_WIPHY_ANTENNA_TX. * + * @NL80211_ATTR_WIPHY_ANTENNA_AVAIL_TX: Bitmap of antennas which are available + * for configuration as TX antennas via the above parameters. + * + * @NL80211_ATTR_WIPHY_ANTENNA_AVAIL_RX: Bitmap of antennas which are available + * for configuration as RX antennas via the above parameters. + * * @NL80211_ATTR_MCAST_RATE: Multicast tx rate (in 100 kbps) for IBSS * * @NL80211_ATTR_OFFCHANNEL_TX_OK: For management frame TX, the frame may be @@ -1059,6 +1065,9 @@ enum nl80211_attrs { NL80211_ATTR_MESH_SETUP, + NL80211_ATTR_WIPHY_ANTENNA_AVAIL_TX, + NL80211_ATTR_WIPHY_ANTENNA_AVAIL_RX, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 8d2f5f8d8080..9b62710891a2 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -605,6 +605,11 @@ static int nl80211_send_wiphy(struct sk_buff *msg, u32 pid, u32 seq, int flags, if (dev->wiphy.flags & WIPHY_FLAG_CONTROL_PORT_PROTOCOL) NLA_PUT_FLAG(msg, NL80211_ATTR_CONTROL_PORT_ETHERTYPE); + NLA_PUT_U32(msg, NL80211_ATTR_WIPHY_ANTENNA_AVAIL_TX, + dev->wiphy.available_antennas_tx); + NLA_PUT_U32(msg, NL80211_ATTR_WIPHY_ANTENNA_AVAIL_RX, + dev->wiphy.available_antennas_rx); + if ((dev->wiphy.available_antennas_tx || dev->wiphy.available_antennas_rx) && dev->ops->get_antenna) { u32 tx_ant = 0, rx_ant = 0; -- cgit v1.2.3 From 61ad5394590c5c5338ab4ec50553d809a9996d50 Mon Sep 17 00:00:00 2001 From: Javier Cardona Date: Thu, 16 Dec 2010 17:23:34 -0800 Subject: mac80211: Remove unused third address from mesh address extension header. The Mesh Control header only includes 0, 1 or 2 addresses. If there is one address, it should be interpreted as Address 4. If there are 2, they are interpreted as Addresses 5 and 6 (Address 4 being the 4th address in the 802.11 header). The address extension used to hold up to 3 addresses instead of the current 2. I'm not sure which draft version changed this, but it is very unlikely that it will change again given the state of the approval process of this draft. See section 7.1.3.6.3 in current draft (8.0). Also, note that the extra address that I'm removing was not being used, so this change has no effect on over-the-air frame formats. But I thought I better remove it before someone does start using it. Signed-off-by: Javier Cardona Signed-off-by: John W. Linville --- include/linux/ieee80211.h | 1 - net/mac80211/mesh.c | 32 +++++++++++++------------------- net/mac80211/mesh.h | 4 ++-- net/mac80211/tx.c | 4 +--- 4 files changed, 16 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index cd681681d211..6042228954a7 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -536,7 +536,6 @@ struct ieee80211s_hdr { __le32 seqnum; u8 eaddr1[6]; u8 eaddr2[6]; - u8 eaddr3[6]; } __attribute__ ((packed)); /* Mesh flags */ diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index 8b5906c83f93..ca3af4685b0a 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -410,39 +410,33 @@ int ieee80211_fill_mesh_addresses(struct ieee80211_hdr *hdr, __le16 *fc, * ieee80211_new_mesh_header - create a new mesh header * @meshhdr: uninitialized mesh header * @sdata: mesh interface to be used - * @addr4: addr4 of the mesh frame (1st in ae header) - * may be NULL - * @addr5: addr5 of the mesh frame (1st or 2nd in ae header) - * may be NULL unless addr6 is present - * @addr6: addr6 of the mesh frame (2nd or 3rd in ae header) - * may be NULL unless addr5 is present + * @addr4or5: 1st address in the ae header, which may correspond to address 4 + * (if addr6 is NULL) or address 5 (if addr6 is present). It may + * be NULL. + * @addr6: 2nd address in the ae header, which corresponds to addr6 of the + * mesh frame * * Return the header length. */ int ieee80211_new_mesh_header(struct ieee80211s_hdr *meshhdr, - struct ieee80211_sub_if_data *sdata, char *addr4, - char *addr5, char *addr6) + struct ieee80211_sub_if_data *sdata, char *addr4or5, + char *addr6) { int aelen = 0; + BUG_ON(!addr4or5 && addr6); memset(meshhdr, 0, sizeof(*meshhdr)); meshhdr->ttl = sdata->u.mesh.mshcfg.dot11MeshTTL; put_unaligned(cpu_to_le32(sdata->u.mesh.mesh_seqnum), &meshhdr->seqnum); sdata->u.mesh.mesh_seqnum++; - if (addr4) { + if (addr4or5 && !addr6) { meshhdr->flags |= MESH_FLAGS_AE_A4; aelen += ETH_ALEN; - memcpy(meshhdr->eaddr1, addr4, ETH_ALEN); - } - if (addr5 && addr6) { + memcpy(meshhdr->eaddr1, addr4or5, ETH_ALEN); + } else if (addr4or5 && addr6) { meshhdr->flags |= MESH_FLAGS_AE_A5_A6; aelen += 2 * ETH_ALEN; - if (!addr4) { - memcpy(meshhdr->eaddr1, addr5, ETH_ALEN); - memcpy(meshhdr->eaddr2, addr6, ETH_ALEN); - } else { - memcpy(meshhdr->eaddr2, addr5, ETH_ALEN); - memcpy(meshhdr->eaddr3, addr6, ETH_ALEN); - } + memcpy(meshhdr->eaddr1, addr4or5, ETH_ALEN); + memcpy(meshhdr->eaddr2, addr6, ETH_ALEN); } return 6 + aelen; } diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h index 890dd19c2eca..b99e230fe31c 100644 --- a/net/mac80211/mesh.h +++ b/net/mac80211/mesh.h @@ -187,8 +187,8 @@ struct mesh_rmc { int ieee80211_fill_mesh_addresses(struct ieee80211_hdr *hdr, __le16 *fc, const u8 *da, const u8 *sa); int ieee80211_new_mesh_header(struct ieee80211s_hdr *meshhdr, - struct ieee80211_sub_if_data *sdata, char *addr4, - char *addr5, char *addr6); + struct ieee80211_sub_if_data *sdata, char *addr4or5, + char *addr6); int mesh_rmc_check(u8 *addr, struct ieee80211s_hdr *mesh_hdr, struct ieee80211_sub_if_data *sdata); bool mesh_matches_local(struct ieee802_11_elems *ie, diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index f4b1b624ea9f..807dcd06e268 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1811,7 +1811,7 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, hdrlen = ieee80211_fill_mesh_addresses(&hdr, &fc, skb->data, skb->data + ETH_ALEN); meshhdrlen = ieee80211_new_mesh_header(&mesh_hdr, - sdata, NULL, NULL, NULL); + sdata, NULL, NULL); } else { /* packet from other interface */ struct mesh_path *mppath; @@ -1844,13 +1844,11 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, ieee80211_new_mesh_header(&mesh_hdr, sdata, skb->data + ETH_ALEN, - NULL, NULL); else meshhdrlen = ieee80211_new_mesh_header(&mesh_hdr, sdata, - NULL, skb->data, skb->data + ETH_ALEN); -- cgit v1.2.3 From 4f32e9b1f812fd6c00cc85a127583fefbdedaedc Mon Sep 17 00:00:00 2001 From: Yong Zhang Date: Wed, 22 Dec 2010 10:27:53 +0100 Subject: kthread_work: make lockdep happy spinlock in kthread_worker and wait_queue_head in kthread_work both should be lockdep sensible, so change the interface to make it suiltable for CONFIG_LOCKDEP. tj: comment update Reported-by: Nicolas Signed-off-by: Yong Zhang Signed-off-by: Andy Walls Tested-by: Andy Walls Cc: Tejun Heo Cc: Andrew Morton Signed-off-by: Tejun Heo --- include/linux/kthread.h | 45 +++++++++++++++++++++++++++++++++++---------- kernel/kthread.c | 11 +++++++++++ 2 files changed, 46 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kthread.h b/include/linux/kthread.h index 685ea65eb803..ce0775aa64c3 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -81,16 +81,41 @@ struct kthread_work { #define DEFINE_KTHREAD_WORK(work, fn) \ struct kthread_work work = KTHREAD_WORK_INIT(work, fn) -static inline void init_kthread_worker(struct kthread_worker *worker) -{ - *worker = (struct kthread_worker)KTHREAD_WORKER_INIT(*worker); -} - -static inline void init_kthread_work(struct kthread_work *work, - kthread_work_func_t fn) -{ - *work = (struct kthread_work)KTHREAD_WORK_INIT(*work, fn); -} +/* + * kthread_worker.lock and kthread_work.done need their own lockdep class + * keys if they are defined on stack with lockdep enabled. Use the + * following macros when defining them on stack. + */ +#ifdef CONFIG_LOCKDEP +# define KTHREAD_WORKER_INIT_ONSTACK(worker) \ + ({ init_kthread_worker(&worker); worker; }) +# define DEFINE_KTHREAD_WORKER_ONSTACK(worker) \ + struct kthread_worker worker = KTHREAD_WORKER_INIT_ONSTACK(worker) +# define KTHREAD_WORK_INIT_ONSTACK(work, fn) \ + ({ init_kthread_work((&work), fn); work; }) +# define DEFINE_KTHREAD_WORK_ONSTACK(work, fn) \ + struct kthread_work work = KTHREAD_WORK_INIT_ONSTACK(work, fn) +#else +# define DEFINE_KTHREAD_WORKER_ONSTACK(worker) DEFINE_KTHREAD_WORKER(worker) +# define DEFINE_KTHREAD_WORK_ONSTACK(work, fn) DEFINE_KTHREAD_WORK(work, fn) +#endif + +extern void __init_kthread_worker(struct kthread_worker *worker, + const char *name, struct lock_class_key *key); + +#define init_kthread_worker(worker) \ + do { \ + static struct lock_class_key __key; \ + __init_kthread_worker((worker), "("#worker")->lock", &__key); \ + } while (0) + +#define init_kthread_work(work, fn) \ + do { \ + memset((work), 0, sizeof(struct kthread_work)); \ + INIT_LIST_HEAD(&(work)->node); \ + (work)->func = (fn); \ + init_waitqueue_head(&(work)->done); \ + } while (0) int kthread_worker_fn(void *worker_ptr); diff --git a/kernel/kthread.c b/kernel/kthread.c index 2dc3786349d1..ca61bbdd44b2 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -265,6 +265,17 @@ int kthreadd(void *unused) return 0; } +void __init_kthread_worker(struct kthread_worker *worker, + const char *name, + struct lock_class_key *key) +{ + spin_lock_init(&worker->lock); + lockdep_set_class_and_name(&worker->lock, key, name); + INIT_LIST_HEAD(&worker->work_list); + worker->task = NULL; +} +EXPORT_SYMBOL_GPL(__init_kthread_worker); + /** * kthread_worker_fn - kthread function to process kthread_worker * @worker_ptr: pointer to initialized kthread_worker -- cgit v1.2.3 From 4a7863cc2eb5f9804f1c4e9156619a801cd7f14f Mon Sep 17 00:00:00 2001 From: Don Zickus Date: Wed, 22 Dec 2010 14:00:03 -0500 Subject: x86, nmi_watchdog: Remove ARCH_HAS_NMI_WATCHDOG and rely on CONFIG_HARDLOCKUP_DETECTOR The x86 arch has shifted its use of the nmi_watchdog from a local implementation to the global one provide by kernel/watchdog.c. This shift has caused a whole bunch of compile problems under different config options. I attempt to simplify things with the patch below. In order to simplify things, I had to come to terms with the meaning of two terms ARCH_HAS_NMI_WATCHDOG and CONFIG_HARDLOCKUP_DETECTOR. Basically they mean the same thing, the former on a local level and the latter on a global level. With the old x86 nmi watchdog gone, there is no need to rely on defining the ARCH_HAS_NMI_WATCHDOG variable because it doesn't make sense any more. x86 will now use the global implementation. The changes below do a few things. First it changes the few places that relied on ARCH_HAS_NMI_WATCHDOG to use CONFIG_X86_LOCAL_APIC (the former was an alias for the latter anyway, so nothing unusual here). Those pieces of code were relying more on local apic functionality the nmi watchdog functionality, so the change should make sense. Second, I removed the x86 implementation of touch_nmi_watchdog(). It isn't need now, instead x86 will rely on kernel/watchdog.c's implementation. Third, I removed the #define ARCH_HAS_NMI_WATCHDOG itself from x86. And tweaked the include/linux/nmi.h file to tell users to look for an externally defined touch_nmi_watchdog in the case of ARCH_HAS_NMI_WATCHDOG _or_ CONFIG_HARDLOCKUP_DETECTOR. This changes removes some of the ugliness in that file. Finally, I added a Kconfig dependency for CONFIG_HARDLOCKUP_DETECTOR that said you can't have ARCH_HAS_NMI_WATCHDOG _and_ CONFIG_HARDLOCKUP_DETECTOR. You can only have one nmi_watchdog. Tested with ARCH=i386: allnoconfig, defconfig, allyesconfig, (various broken configs) ARCH=x86_64: allnoconfig, defconfig, allyesconfig, (various broken configs) Hopefully, after this patch I won't get any more compile broken emails. :-) v3: changed a couple of 'linux/nmi.h' -> 'asm/nmi.h' to pick-up correct function prototypes when CONFIG_HARDLOCKUP_DETECTOR is not set. Signed-off-by: Don Zickus Cc: Peter Zijlstra Cc: fweisbec@gmail.com LKML-Reference: <1293044403-14117-1-git-send-email-dzickus@redhat.com> Signed-off-by: Ingo Molnar --- arch/x86/include/asm/irq.h | 4 ---- arch/x86/include/asm/nmi.h | 2 +- arch/x86/kernel/apic/hw_nmi.c | 10 ---------- arch/x86/kernel/cpu/perfctr-watchdog.c | 2 +- arch/x86/oprofile/op_model_p4.c | 2 +- drivers/watchdog/hpwdt.c | 4 ++-- include/linux/nmi.h | 6 +----- lib/Kconfig.debug | 3 ++- 8 files changed, 8 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h index 13b0ebaa512f..ba870bb6dd8e 100644 --- a/arch/x86/include/asm/irq.h +++ b/arch/x86/include/asm/irq.h @@ -15,10 +15,6 @@ static inline int irq_canonicalize(int irq) return ((irq == 2) ? 9 : irq); } -#ifdef CONFIG_X86_LOCAL_APIC -# define ARCH_HAS_NMI_WATCHDOG -#endif - #ifdef CONFIG_X86_32 extern void irq_ctx_init(int cpu); #else diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h index 3545838cddeb..c4021b953510 100644 --- a/arch/x86/include/asm/nmi.h +++ b/arch/x86/include/asm/nmi.h @@ -5,7 +5,7 @@ #include #include -#ifdef ARCH_HAS_NMI_WATCHDOG +#ifdef CONFIG_X86_LOCAL_APIC extern void die_nmi(char *str, struct pt_regs *regs, int do_panic); extern int avail_to_resrv_perfctr_nmi_bit(unsigned int); diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c index 93da91df5b38..c57d0b599448 100644 --- a/arch/x86/kernel/apic/hw_nmi.c +++ b/arch/x86/kernel/apic/hw_nmi.c @@ -17,7 +17,6 @@ #include #include -#ifdef ARCH_HAS_NMI_WATCHDOG #ifdef CONFIG_HARDLOCKUP_DETECTOR u64 hw_nmi_get_sample_period(void) { @@ -25,15 +24,6 @@ u64 hw_nmi_get_sample_period(void) } #endif -#ifndef CONFIG_HARDLOCKUP_DETECTOR -void touch_nmi_watchdog(void) -{ - touch_softlockup_watchdog(); -} -EXPORT_SYMBOL(touch_nmi_watchdog); -#endif -#endif - #ifdef arch_trigger_all_cpu_backtrace /* For reliability, we're prepared to waste bits here. */ static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly; diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c index 14d45928c282..d5a236615501 100644 --- a/arch/x86/kernel/cpu/perfctr-watchdog.c +++ b/arch/x86/kernel/cpu/perfctr-watchdog.c @@ -16,7 +16,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/x86/oprofile/op_model_p4.c b/arch/x86/oprofile/op_model_p4.c index 182558dd5515..9fadec074142 100644 --- a/arch/x86/oprofile/op_model_p4.c +++ b/arch/x86/oprofile/op_model_p4.c @@ -11,7 +11,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/drivers/watchdog/hpwdt.c b/drivers/watchdog/hpwdt.c index c19f4a20794a..dea7b5bf6e2c 100644 --- a/drivers/watchdog/hpwdt.c +++ b/drivers/watchdog/hpwdt.c @@ -642,7 +642,7 @@ static struct notifier_block die_notifier = { */ #ifdef CONFIG_HPWDT_NMI_DECODING -#ifdef ARCH_HAS_NMI_WATCHDOG +#ifdef CONFIG_X86_LOCAL_APIC static void __devinit hpwdt_check_nmi_decoding(struct pci_dev *dev) { /* @@ -657,7 +657,7 @@ static void __devinit hpwdt_check_nmi_decoding(struct pci_dev *dev) dev_warn(&dev->dev, "NMI decoding is disabled. " "Your kernel does not support a NMI Watchdog.\n"); } -#endif /* ARCH_HAS_NMI_WATCHDOG */ +#endif /* CONFIG_X86_LOCAL_APIC */ static int __devinit hpwdt_init_nmi_decoding(struct pci_dev *dev) { diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 17ccf44e7dcb..c536f8545f74 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -14,18 +14,14 @@ * may be used to reset the timeout - for code which intentionally * disables interrupts for a long time. This call is stateless. */ -#ifdef ARCH_HAS_NMI_WATCHDOG +#if defined(ARCH_HAS_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR) #include extern void touch_nmi_watchdog(void); #else -#ifndef CONFIG_HARDLOCKUP_DETECTOR static inline void touch_nmi_watchdog(void) { touch_softlockup_watchdog(); } -#else -extern void touch_nmi_watchdog(void); -#endif #endif /* diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 28b42b9274d0..2d05adb98401 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -173,7 +173,8 @@ config LOCKUP_DETECTOR An NMI is generated every 60 seconds or so to check for hardlockups. config HARDLOCKUP_DETECTOR - def_bool LOCKUP_DETECTOR && PERF_EVENTS && HAVE_PERF_EVENTS_NMI + def_bool LOCKUP_DETECTOR && PERF_EVENTS && HAVE_PERF_EVENTS_NMI && \ + !ARCH_HAS_NMI_WATCHDOG config BOOTPARAM_SOFTLOCKUP_PANIC bool "Panic (Reboot) On Soft Lockups" -- cgit v1.2.3 From 4e06fd14d5fa78826397c891654a37e5a36ee827 Mon Sep 17 00:00:00 2001 From: Will Newton Date: Tue, 21 Dec 2010 17:24:29 -0800 Subject: include/linux/unaligned: pack the whole struct rather than just the field The current packed struct implementation of unaligned access adds the packed attribute only to the field within the unaligned struct rather than to the struct as a whole. This is not sufficient to enforce proper behaviour on architectures with a default struct alignment of more than one byte. For example, the current implementation of __get_unaligned_cpu16 when compiled for arm with gcc -O1 -mstructure-size-boundary=32 assumes the struct is on a 4 byte boundary so performs the load of the 16bit packed field as if it were on a 4 byte boundary: __get_unaligned_cpu16: ldrh r0, [r0, #0] bx lr Moving the packed attribute to the struct rather than the field causes the proper unaligned access code to be generated: __get_unaligned_cpu16: ldrb r3, [r0, #0] @ zero_extendqisi2 ldrb r0, [r0, #1] @ zero_extendqisi2 orr r0, r3, r0, asl #8 bx lr Signed-off-by: Will Newton Cc: Arnd Bergmann Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/unaligned/packed_struct.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/unaligned/packed_struct.h b/include/linux/unaligned/packed_struct.h index 2498bb9fe002..c9a6abd972a1 100644 --- a/include/linux/unaligned/packed_struct.h +++ b/include/linux/unaligned/packed_struct.h @@ -3,9 +3,9 @@ #include -struct __una_u16 { u16 x __attribute__((packed)); }; -struct __una_u32 { u32 x __attribute__((packed)); }; -struct __una_u64 { u64 x __attribute__((packed)); }; +struct __una_u16 { u16 x; } __attribute__((packed)); +struct __una_u32 { u32 x; } __attribute__((packed)); +struct __una_u64 { u64 x; } __attribute__((packed)); static inline u16 __get_unaligned_cpu16(const void *p) { -- cgit v1.2.3 From 4be2c95d1f7706ca0e74499f2bd118e1cee19669 Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Tue, 21 Dec 2010 17:24:30 -0800 Subject: taskstats: pad taskstats netlink response for aligment issues on ia64 The taskstats structure is internally aligned on 8 byte boundaries but the layout of the aggregrate reply, with two NLA headers and the pid (each 4 bytes), actually force the entire structure to be unaligned. This causes the kernel to issue unaligned access warnings on some architectures like ia64. Unfortunately, some software out there doesn't properly unroll the NLA packet and assumes that the start of the taskstats structure will always be 20 bytes from the start of the netlink payload. Aligning the start of the taskstats structure breaks this software, which we don't want. So, for now the alignment only happens on architectures that require it and those users will have to update to fixed versions of those packages. Space is reserved in the packet only when needed. This ifdef should be removed in several years e.g. 2012 once we can be confident that fixed versions are installed on most systems. We add the padding before the aggregate since the aggregate is already a defined type. Commit 85893120 ("delayacct: align to 8 byte boundary on 64-bit systems") previously addressed the alignment issues by padding out the pid field. This was supposed to be a compatible change but the circumstances described above mean that it wasn't. This patch backs out that change, since it was a hack, and introduces a new NULL attribute type to provide the padding. Padding the response with 4 bytes avoids allocating an aligned taskstats structure and copying it back. Since the structure weighs in at 328 bytes, it's too big to do it on the stack. Signed-off-by: Jeff Mahoney Reported-by: Brian Rogers Cc: Jeff Mahoney Cc: Guillaume Chazarain Cc: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/accounting/getdelays.c | 1 + include/linux/taskstats.h | 3 +- kernel/taskstats.c | 57 ++++++++++++++++++++++++++++-------- 3 files changed, 47 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/Documentation/accounting/getdelays.c b/Documentation/accounting/getdelays.c index a2976a6de033..e9c77788a39d 100644 --- a/Documentation/accounting/getdelays.c +++ b/Documentation/accounting/getdelays.c @@ -516,6 +516,7 @@ int main(int argc, char *argv[]) default: fprintf(stderr, "Unknown nla_type %d\n", na->nla_type); + case TASKSTATS_TYPE_NULL: break; } na = (struct nlattr *) (GENLMSG_DATA(&msg) + len); diff --git a/include/linux/taskstats.h b/include/linux/taskstats.h index 341dddb55090..2466e550a41d 100644 --- a/include/linux/taskstats.h +++ b/include/linux/taskstats.h @@ -33,7 +33,7 @@ */ -#define TASKSTATS_VERSION 7 +#define TASKSTATS_VERSION 8 #define TS_COMM_LEN 32 /* should be >= TASK_COMM_LEN * in linux/sched.h */ @@ -188,6 +188,7 @@ enum { TASKSTATS_TYPE_STATS, /* taskstats structure */ TASKSTATS_TYPE_AGGR_PID, /* contains pid + stats */ TASKSTATS_TYPE_AGGR_TGID, /* contains tgid + stats */ + TASKSTATS_TYPE_NULL, /* contains nothing */ __TASKSTATS_TYPE_MAX, }; diff --git a/kernel/taskstats.c b/kernel/taskstats.c index c8231fb15708..3308fd7f1b52 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -349,25 +349,47 @@ static int parse(struct nlattr *na, struct cpumask *mask) return ret; } +#ifdef CONFIG_IA64 +#define TASKSTATS_NEEDS_PADDING 1 +#endif + static struct taskstats *mk_reply(struct sk_buff *skb, int type, u32 pid) { struct nlattr *na, *ret; int aggr; - /* If we don't pad, we end up with alignment on a 4 byte boundary. - * This causes lots of runtime warnings on systems requiring 8 byte - * alignment */ - u32 pids[2] = { pid, 0 }; - int pid_size = ALIGN(sizeof(pid), sizeof(long)); - aggr = (type == TASKSTATS_TYPE_PID) ? TASKSTATS_TYPE_AGGR_PID : TASKSTATS_TYPE_AGGR_TGID; + /* + * The taskstats structure is internally aligned on 8 byte + * boundaries but the layout of the aggregrate reply, with + * two NLA headers and the pid (each 4 bytes), actually + * force the entire structure to be unaligned. This causes + * the kernel to issue unaligned access warnings on some + * architectures like ia64. Unfortunately, some software out there + * doesn't properly unroll the NLA packet and assumes that the start + * of the taskstats structure will always be 20 bytes from the start + * of the netlink payload. Aligning the start of the taskstats + * structure breaks this software, which we don't want. So, for now + * the alignment only happens on architectures that require it + * and those users will have to update to fixed versions of those + * packages. Space is reserved in the packet only when needed. + * This ifdef should be removed in several years e.g. 2012 once + * we can be confident that fixed versions are installed on most + * systems. We add the padding before the aggregate since the + * aggregate is already a defined type. + */ +#ifdef TASKSTATS_NEEDS_PADDING + if (nla_put(skb, TASKSTATS_TYPE_NULL, 0, NULL) < 0) + goto err; +#endif na = nla_nest_start(skb, aggr); if (!na) goto err; - if (nla_put(skb, type, pid_size, pids) < 0) + + if (nla_put(skb, type, sizeof(pid), &pid) < 0) goto err; ret = nla_reserve(skb, TASKSTATS_TYPE_STATS, sizeof(struct taskstats)); if (!ret) @@ -456,6 +478,18 @@ out: return rc; } +static size_t taskstats_packet_size(void) +{ + size_t size; + + size = nla_total_size(sizeof(u32)) + + nla_total_size(sizeof(struct taskstats)) + nla_total_size(0); +#ifdef TASKSTATS_NEEDS_PADDING + size += nla_total_size(0); /* Padding for alignment */ +#endif + return size; +} + static int cmd_attr_pid(struct genl_info *info) { struct taskstats *stats; @@ -464,8 +498,7 @@ static int cmd_attr_pid(struct genl_info *info) u32 pid; int rc; - size = nla_total_size(sizeof(u32)) + - nla_total_size(sizeof(struct taskstats)) + nla_total_size(0); + size = taskstats_packet_size(); rc = prepare_reply(info, TASKSTATS_CMD_NEW, &rep_skb, size); if (rc < 0) @@ -494,8 +527,7 @@ static int cmd_attr_tgid(struct genl_info *info) u32 tgid; int rc; - size = nla_total_size(sizeof(u32)) + - nla_total_size(sizeof(struct taskstats)) + nla_total_size(0); + size = taskstats_packet_size(); rc = prepare_reply(info, TASKSTATS_CMD_NEW, &rep_skb, size); if (rc < 0) @@ -570,8 +602,7 @@ void taskstats_exit(struct task_struct *tsk, int group_dead) /* * Size includes space for nested attributes */ - size = nla_total_size(sizeof(u32)) + - nla_total_size(sizeof(struct taskstats)) + nla_total_size(0); + size = taskstats_packet_size(); is_thread_group = !!taskstats_tgid_alloc(tsk); if (is_thread_group) { -- cgit v1.2.3 From 09c730a488c32c2cadb31cdb8dcc4df528441197 Mon Sep 17 00:00:00 2001 From: Sundar Iyer Date: Tue, 21 Dec 2010 15:53:31 +0530 Subject: input/tc3589x: add tc3589x keypad support Add support for the keypad controller module found on the TC3589X devices. This driver default adds the support for TC35893 device. Signed-off-by: Sundar Iyer Acked-by: Dmitry Torokhov [Some minor fixups for compilation] Signed-off-by: Linus Walleij --- drivers/input/keyboard/Kconfig | 10 + drivers/input/keyboard/Makefile | 1 + drivers/input/keyboard/tc3589x-keypad.c | 472 ++++++++++++++++++++++++++++++++ drivers/mfd/tc3589x.c | 28 +- include/linux/mfd/tc3589x.h | 52 ++++ 5 files changed, 562 insertions(+), 1 deletion(-) create mode 100644 drivers/input/keyboard/tc3589x-keypad.c (limited to 'include/linux') diff --git a/drivers/input/keyboard/Kconfig b/drivers/input/keyboard/Kconfig index b8c51b9781db..85af3c3f7bcb 100644 --- a/drivers/input/keyboard/Kconfig +++ b/drivers/input/keyboard/Kconfig @@ -443,6 +443,16 @@ config KEYBOARD_OMAP4 To compile this driver as a module, choose M here: the module will be called omap4-keypad. +config KEYBOARD_TC3589X + tristate "TC3589X Keypad support" + depends on MFD_TC3589X + help + Say Y here if you want to use the keypad controller on + TC35892/3 I/O expander. + + To compile this driver as a module, choose M here: the + module will be called tc3589x-keypad. + config KEYBOARD_TNETV107X tristate "TI TNETV107X keypad support" depends on ARCH_DAVINCI_TNETV107X diff --git a/drivers/input/keyboard/Makefile b/drivers/input/keyboard/Makefile index a34452e8ebe2..4411c70db3b5 100644 --- a/drivers/input/keyboard/Makefile +++ b/drivers/input/keyboard/Makefile @@ -40,6 +40,7 @@ obj-$(CONFIG_KEYBOARD_SH_KEYSC) += sh_keysc.o obj-$(CONFIG_KEYBOARD_STMPE) += stmpe-keypad.o obj-$(CONFIG_KEYBOARD_STOWAWAY) += stowaway.o obj-$(CONFIG_KEYBOARD_SUNKBD) += sunkbd.o +obj-$(CONFIG_KEYBOARD_TC3589X) += tc3589x-keypad.o obj-$(CONFIG_KEYBOARD_TNETV107X) += tnetv107x-keypad.o obj-$(CONFIG_KEYBOARD_TWL4030) += twl4030_keypad.o obj-$(CONFIG_KEYBOARD_XTKBD) += xtkbd.o diff --git a/drivers/input/keyboard/tc3589x-keypad.c b/drivers/input/keyboard/tc3589x-keypad.c new file mode 100644 index 000000000000..69dc0cb20a00 --- /dev/null +++ b/drivers/input/keyboard/tc3589x-keypad.c @@ -0,0 +1,472 @@ +/* + * Copyright (C) ST-Ericsson SA 2010 + * + * Author: Jayeeta Banerjee + * Author: Sundar Iyer + * + * License Terms: GNU General Public License, version 2 + * + * TC35893 MFD Keypad Controller driver + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* Maximum supported keypad matrix row/columns size */ +#define TC3589x_MAX_KPROW 8 +#define TC3589x_MAX_KPCOL 12 + +/* keypad related Constants */ +#define TC3589x_MAX_DEBOUNCE_SETTLE 0xFF +#define DEDICATED_KEY_VAL 0xFF + +/* Pull up/down masks */ +#define TC3589x_NO_PULL_MASK 0x0 +#define TC3589x_PULL_DOWN_MASK 0x1 +#define TC3589x_PULL_UP_MASK 0x2 +#define TC3589x_PULLUP_ALL_MASK 0xAA +#define TC3589x_IO_PULL_VAL(index, mask) ((mask)<<((index)%4)*2)) + +/* Bit masks for IOCFG register */ +#define IOCFG_BALLCFG 0x01 +#define IOCFG_IG 0x08 + +#define KP_EVCODE_COL_MASK 0x0F +#define KP_EVCODE_ROW_MASK 0x70 +#define KP_RELEASE_EVT_MASK 0x80 + +#define KP_ROW_SHIFT 4 + +#define KP_NO_VALID_KEY_MASK 0x7F + +/* bit masks for RESTCTRL register */ +#define TC3589x_KBDRST 0x2 +#define TC3589x_IRQRST 0x10 +#define TC3589x_RESET_ALL 0x1B + +/* KBDMFS register bit mask */ +#define TC3589x_KBDMFS_EN 0x1 + +/* CLKEN register bitmask */ +#define KPD_CLK_EN 0x1 + +/* RSTINTCLR register bit mask */ +#define IRQ_CLEAR 0x1 + +/* bit masks for keyboard interrupts*/ +#define TC3589x_EVT_LOSS_INT 0x8 +#define TC3589x_EVT_INT 0x4 +#define TC3589x_KBD_LOSS_INT 0x2 +#define TC3589x_KBD_INT 0x1 + +/* bit masks for keyboard interrupt clear*/ +#define TC3589x_EVT_INT_CLR 0x2 +#define TC3589x_KBD_INT_CLR 0x1 + +#define TC3589x_KBD_KEYMAP_SIZE 64 + +/** + * struct tc_keypad - data structure used by keypad driver + * @input: pointer to input device object + * @board: keypad platform device + * @krow: number of rows + * @kcol: number of coloumns + * @keymap: matrix scan code table for keycodes + */ +struct tc_keypad { + struct tc3589x *tc3589x; + struct input_dev *input; + const struct tc3589x_keypad_platform_data *board; + unsigned int krow; + unsigned int kcol; + unsigned short keymap[TC3589x_KBD_KEYMAP_SIZE]; + bool keypad_stopped; +}; + +static int __devinit tc3589x_keypad_init_key_hardware(struct tc_keypad *keypad) +{ + int ret; + struct tc3589x *tc3589x = keypad->tc3589x; + u8 settle_time = keypad->board->settle_time; + u8 dbounce_period = keypad->board->debounce_period; + u8 rows = keypad->board->krow & 0xf; /* mask out the nibble */ + u8 column = keypad->board->kcol & 0xf; /* mask out the nibble */ + + /* validate platform configurations */ + if (keypad->board->kcol > TC3589x_MAX_KPCOL || + keypad->board->krow > TC3589x_MAX_KPROW || + keypad->board->debounce_period > TC3589x_MAX_DEBOUNCE_SETTLE || + keypad->board->settle_time > TC3589x_MAX_DEBOUNCE_SETTLE) + return -EINVAL; + + /* configure KBDSIZE 4 LSbits for cols and 4 MSbits for rows */ + ret = tc3589x_reg_write(tc3589x, TC3589x_KBDSIZE, + (rows << KP_ROW_SHIFT) | column); + if (ret < 0) + return ret; + + /* configure dedicated key config, no dedicated key selected */ + ret = tc3589x_reg_write(tc3589x, TC3589x_KBCFG_LSB, DEDICATED_KEY_VAL); + if (ret < 0) + return ret; + + ret = tc3589x_reg_write(tc3589x, TC3589x_KBCFG_MSB, DEDICATED_KEY_VAL); + if (ret < 0) + return ret; + + /* Configure settle time */ + ret = tc3589x_reg_write(tc3589x, TC3589x_KBDSETTLE_REG, settle_time); + if (ret < 0) + return ret; + + /* Configure debounce time */ + ret = tc3589x_reg_write(tc3589x, TC3589x_KBDBOUNCE, dbounce_period); + if (ret < 0) + return ret; + + /* Start of initialise keypad GPIOs */ + ret = tc3589x_set_bits(tc3589x, TC3589x_IOCFG, 0x0, IOCFG_IG); + if (ret < 0) + return ret; + + /* Configure pull-up resistors for all row GPIOs */ + ret = tc3589x_reg_write(tc3589x, TC3589x_IOPULLCFG0_LSB, + TC3589x_PULLUP_ALL_MASK); + if (ret < 0) + return ret; + + ret = tc3589x_reg_write(tc3589x, TC3589x_IOPULLCFG0_MSB, + TC3589x_PULLUP_ALL_MASK); + if (ret < 0) + return ret; + + /* Configure pull-up resistors for all column GPIOs */ + ret = tc3589x_reg_write(tc3589x, TC3589x_IOPULLCFG1_LSB, + TC3589x_PULLUP_ALL_MASK); + if (ret < 0) + return ret; + + ret = tc3589x_reg_write(tc3589x, TC3589x_IOPULLCFG1_MSB, + TC3589x_PULLUP_ALL_MASK); + if (ret < 0) + return ret; + + ret = tc3589x_reg_write(tc3589x, TC3589x_IOPULLCFG2_LSB, + TC3589x_PULLUP_ALL_MASK); + + return ret; +} + +#define TC35893_DATA_REGS 4 +#define TC35893_KEYCODE_FIFO_EMPTY 0x7f +#define TC35893_KEYCODE_FIFO_CLEAR 0xff +#define TC35893_KEYPAD_ROW_SHIFT 0x3 + +static irqreturn_t tc3589x_keypad_irq(int irq, void *dev) +{ + struct tc_keypad *keypad = dev; + struct tc3589x *tc3589x = keypad->tc3589x; + u8 i, row_index, col_index, kbd_code, up; + u8 code; + + for (i = 0; i < TC35893_DATA_REGS * 2; i++) { + kbd_code = tc3589x_reg_read(tc3589x, TC3589x_EVTCODE_FIFO); + + /* loop till fifo is empty and no more keys are pressed */ + if (kbd_code == TC35893_KEYCODE_FIFO_EMPTY || + kbd_code == TC35893_KEYCODE_FIFO_CLEAR) + continue; + + /* valid key is found */ + col_index = kbd_code & KP_EVCODE_COL_MASK; + row_index = (kbd_code & KP_EVCODE_ROW_MASK) >> KP_ROW_SHIFT; + code = MATRIX_SCAN_CODE(row_index, col_index, + TC35893_KEYPAD_ROW_SHIFT); + up = kbd_code & KP_RELEASE_EVT_MASK; + + input_event(keypad->input, EV_MSC, MSC_SCAN, code); + input_report_key(keypad->input, keypad->keymap[code], !up); + input_sync(keypad->input); + } + + /* clear IRQ */ + tc3589x_set_bits(tc3589x, TC3589x_KBDIC, + 0x0, TC3589x_EVT_INT_CLR | TC3589x_KBD_INT_CLR); + /* enable IRQ */ + tc3589x_set_bits(tc3589x, TC3589x_KBDMSK, + 0x0, TC3589x_EVT_LOSS_INT | TC3589x_EVT_INT); + + return IRQ_HANDLED; +} + +static int tc3589x_keypad_enable(struct tc_keypad *keypad) +{ + struct tc3589x *tc3589x = keypad->tc3589x; + int ret; + + /* pull the keypad module out of reset */ + ret = tc3589x_set_bits(tc3589x, TC3589x_RSTCTRL, TC3589x_KBDRST, 0x0); + if (ret < 0) + return ret; + + /* configure KBDMFS */ + ret = tc3589x_set_bits(tc3589x, TC3589x_KBDMFS, 0x0, TC3589x_KBDMFS_EN); + if (ret < 0) + return ret; + + /* enable the keypad clock */ + ret = tc3589x_set_bits(tc3589x, TC3589x_CLKEN, 0x0, KPD_CLK_EN); + if (ret < 0) + return ret; + + /* clear pending IRQs */ + ret = tc3589x_set_bits(tc3589x, TC3589x_RSTINTCLR, 0x0, 0x1); + if (ret < 0) + return ret; + + /* enable the IRQs */ + ret = tc3589x_set_bits(tc3589x, TC3589x_KBDMSK, 0x0, + TC3589x_EVT_LOSS_INT | TC3589x_EVT_INT); + if (ret < 0) + return ret; + + keypad->keypad_stopped = false; + + return ret; +} + +static int tc3589x_keypad_disable(struct tc_keypad *keypad) +{ + struct tc3589x *tc3589x = keypad->tc3589x; + int ret; + + /* clear IRQ */ + ret = tc3589x_set_bits(tc3589x, TC3589x_KBDIC, + 0x0, TC3589x_EVT_INT_CLR | TC3589x_KBD_INT_CLR); + if (ret < 0) + return ret; + + /* disable all interrupts */ + ret = tc3589x_set_bits(tc3589x, TC3589x_KBDMSK, + ~(TC3589x_EVT_LOSS_INT | TC3589x_EVT_INT), 0x0); + if (ret < 0) + return ret; + + /* disable the keypad module */ + ret = tc3589x_set_bits(tc3589x, TC3589x_CLKEN, 0x1, 0x0); + if (ret < 0) + return ret; + + /* put the keypad module into reset */ + ret = tc3589x_set_bits(tc3589x, TC3589x_RSTCTRL, TC3589x_KBDRST, 0x1); + + keypad->keypad_stopped = true; + + return ret; +} + +static int tc3589x_keypad_open(struct input_dev *input) +{ + int error; + struct tc_keypad *keypad = input_get_drvdata(input); + + /* enable the keypad module */ + error = tc3589x_keypad_enable(keypad); + if (error < 0) { + dev_err(&input->dev, "failed to enable keypad module\n"); + return error; + } + + error = tc3589x_keypad_init_key_hardware(keypad); + if (error < 0) { + dev_err(&input->dev, "failed to configure keypad module\n"); + return error; + } + + return 0; +} + +static void tc3589x_keypad_close(struct input_dev *input) +{ + struct tc_keypad *keypad = input_get_drvdata(input); + + /* disable the keypad module */ + tc3589x_keypad_disable(keypad); +} + +static int __devinit tc3589x_keypad_probe(struct platform_device *pdev) +{ + struct tc3589x *tc3589x = dev_get_drvdata(pdev->dev.parent); + struct tc_keypad *keypad; + struct input_dev *input; + const struct tc3589x_keypad_platform_data *plat; + int error, irq; + + plat = tc3589x->pdata->keypad; + if (!plat) { + dev_err(&pdev->dev, "invalid keypad platform data\n"); + return -EINVAL; + } + + irq = platform_get_irq(pdev, 0); + if (irq < 0) + return irq; + + keypad = kzalloc(sizeof(struct tc_keypad), GFP_KERNEL); + input = input_allocate_device(); + if (!keypad || !input) { + dev_err(&pdev->dev, "failed to allocate keypad memory\n"); + error = -ENOMEM; + goto err_free_mem; + } + + keypad->board = plat; + keypad->input = input; + keypad->tc3589x = tc3589x; + + input->id.bustype = BUS_I2C; + input->name = pdev->name; + input->dev.parent = &pdev->dev; + + input->keycode = keypad->keymap; + input->keycodesize = sizeof(keypad->keymap[0]); + input->keycodemax = ARRAY_SIZE(keypad->keymap); + + input->open = tc3589x_keypad_open; + input->close = tc3589x_keypad_close; + + input_set_drvdata(input, keypad); + + input_set_capability(input, EV_MSC, MSC_SCAN); + + __set_bit(EV_KEY, input->evbit); + if (!plat->no_autorepeat) + __set_bit(EV_REP, input->evbit); + + matrix_keypad_build_keymap(plat->keymap_data, 0x3, + input->keycode, input->keybit); + + error = request_threaded_irq(irq, NULL, + tc3589x_keypad_irq, plat->irqtype, + "tc3589x-keypad", keypad); + if (error < 0) { + dev_err(&pdev->dev, + "Could not allocate irq %d,error %d\n", + irq, error); + goto err_free_mem; + } + + error = input_register_device(input); + if (error) { + dev_err(&pdev->dev, "Could not register input device\n"); + goto err_free_irq; + } + + /* let platform decide if keypad is a wakeup source or not */ + device_init_wakeup(&pdev->dev, plat->enable_wakeup); + device_set_wakeup_capable(&pdev->dev, plat->enable_wakeup); + + platform_set_drvdata(pdev, keypad); + + return 0; + +err_free_irq: + free_irq(irq, keypad); +err_free_mem: + input_free_device(input); + kfree(keypad); + return error; +} + +static int __devexit tc3589x_keypad_remove(struct platform_device *pdev) +{ + struct tc_keypad *keypad = platform_get_drvdata(pdev); + int irq = platform_get_irq(pdev, 0); + + if (!keypad->keypad_stopped) + tc3589x_keypad_disable(keypad); + + free_irq(irq, keypad); + + input_unregister_device(keypad->input); + + kfree(keypad); + + return 0; +} + +#ifdef CONFIG_PM +static int tc3589x_keypad_suspend(struct device *dev) +{ + struct platform_device *pdev = to_platform_device(dev); + struct tc_keypad *keypad = platform_get_drvdata(pdev); + int irq = platform_get_irq(pdev, 0); + + /* keypad is already off; we do nothing */ + if (keypad->keypad_stopped) + return 0; + + /* if device is not a wakeup source, disable it for powersave */ + if (!device_may_wakeup(&pdev->dev)) + tc3589x_keypad_disable(keypad); + else + enable_irq_wake(irq); + + return 0; +} + +static int tc3589x_keypad_resume(struct device *dev) +{ + struct platform_device *pdev = to_platform_device(dev); + struct tc_keypad *keypad = platform_get_drvdata(pdev); + int irq = platform_get_irq(pdev, 0); + + if (!keypad->keypad_stopped) + return 0; + + /* enable the device to resume normal operations */ + if (!device_may_wakeup(&pdev->dev)) + tc3589x_keypad_enable(keypad); + else + disable_irq_wake(irq); + + return 0; +} + +static const SIMPLE_DEV_PM_OPS(tc3589x_keypad_dev_pm_ops, + tc3589x_keypad_suspend, tc3589x_keypad_resume); +#endif + +static struct platform_driver tc3589x_keypad_driver = { + .driver.name = "tc3589x-keypad", + .driver.owner = THIS_MODULE, +#ifdef CONFIG_PM + .driver.pm = &tc3589x_keypad_dev_pm_ops, +#endif + .probe = tc3589x_keypad_probe, + .remove = __devexit_p(tc3589x_keypad_remove), +}; + +static int __init tc3589x_keypad_init(void) +{ + return platform_driver_register(&tc3589x_keypad_driver); +} +module_init(tc3589x_keypad_init); + +static void __exit tc3589x_keypad_exit(void) +{ + return platform_driver_unregister(&tc3589x_keypad_driver); +} +module_exit(tc3589x_keypad_exit); + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Jayeeta Banerjee/Sundar Iyer"); +MODULE_DESCRIPTION("TC35893 Keypad Driver"); +MODULE_ALIAS("platform:tc3589x-keypad") diff --git a/drivers/mfd/tc3589x.c b/drivers/mfd/tc3589x.c index 112efd3c4940..729dbeed2ce0 100644 --- a/drivers/mfd/tc3589x.c +++ b/drivers/mfd/tc3589x.c @@ -132,6 +132,14 @@ static struct resource gpio_resources[] = { }, }; +static struct resource keypad_resources[] = { + { + .start = TC3589x_INT_KBDIRQ, + .end = TC3589x_INT_KBDIRQ, + .flags = IORESOURCE_IRQ, + }, +}; + static struct mfd_cell tc3589x_dev_gpio[] = { { .name = "tc3589x-gpio", @@ -140,6 +148,14 @@ static struct mfd_cell tc3589x_dev_gpio[] = { }, }; +static struct mfd_cell tc3589x_dev_keypad[] = { + { + .name = "tc3589x-keypad", + .num_resources = ARRAY_SIZE(keypad_resources), + .resources = &keypad_resources[0], + }, +}; + static irqreturn_t tc3589x_irq(int irq, void *data) { struct tc3589x *tc3589x = data; @@ -255,8 +271,18 @@ static int __devinit tc3589x_device_init(struct tc3589x *tc3589x) dev_info(tc3589x->dev, "added gpio block\n"); } - return ret; + if (blocks & TC3589x_BLOCK_KEYPAD) { + ret = mfd_add_devices(tc3589x->dev, -1, tc3589x_dev_keypad, + ARRAY_SIZE(tc3589x_dev_keypad), NULL, + tc3589x->irq_base); + if (ret) { + dev_err(tc3589x->dev, "failed to keypad child\n"); + return ret; + } + dev_info(tc3589x->dev, "added keypad block\n"); + } + return ret; } static int __devinit tc3589x_probe(struct i2c_client *i2c, diff --git a/include/linux/mfd/tc3589x.h b/include/linux/mfd/tc3589x.h index da00958b12d9..16c76e124f9c 100644 --- a/include/linux/mfd/tc3589x.h +++ b/include/linux/mfd/tc3589x.h @@ -20,6 +20,17 @@ enum tx3589x_block { #define TC3589x_RSTCTRL_KBDRST (1 << 1) #define TC3589x_RSTCTRL_GPIRST (1 << 0) +/* Keyboard Configuration Registers */ +#define TC3589x_KBDSETTLE_REG 0x01 +#define TC3589x_KBDBOUNCE 0x02 +#define TC3589x_KBDSIZE 0x03 +#define TC3589x_KBCFG_LSB 0x04 +#define TC3589x_KBCFG_MSB 0x05 +#define TC3589x_KBDIC 0x08 +#define TC3589x_KBDMSK 0x09 +#define TC3589x_EVTCODE_FIFO 0x10 +#define TC3589x_KBDMFS 0x8F + #define TC3589x_IRQST 0x91 #define TC3589x_MANFCODE_MAGIC 0x03 @@ -35,6 +46,14 @@ enum tx3589x_block { #define TC3589x_EXTRSTN 0x83 #define TC3589x_RSTINTCLR 0x84 +/* Pull up/down configuration registers */ +#define TC3589x_IOCFG 0xA7 +#define TC3589x_IOPULLCFG0_LSB 0xAA +#define TC3589x_IOPULLCFG0_MSB 0xAB +#define TC3589x_IOPULLCFG1_LSB 0xAC +#define TC3589x_IOPULLCFG1_MSB 0xAD +#define TC3589x_IOPULLCFG2_LSB 0xAE + #define TC3589x_GPIOIS0 0xC9 #define TC3589x_GPIOIS1 0xCA #define TC3589x_GPIOIS2 0xCB @@ -112,6 +131,37 @@ extern int tc3589x_block_write(struct tc3589x *tc3589x, u8 reg, u8 length, const u8 *values); extern int tc3589x_set_bits(struct tc3589x *tc3589x, u8 reg, u8 mask, u8 val); +/* + * Keypad related platform specific constants + * These values may be modified for fine tuning + */ +#define TC_KPD_ROWS 0x8 +#define TC_KPD_COLUMNS 0x8 +#define TC_KPD_DEBOUNCE_PERIOD 0xA3 +#define TC_KPD_SETTLE_TIME 0xA3 + +/** + * struct tc35893_platform_data - data structure for platform specific data + * @keymap_data: matrix scan code table for keycodes + * @krow: mask for available rows, value is 0xFF + * @kcol: mask for available columns, value is 0xFF + * @debounce_period: platform specific debounce time + * @settle_time: platform specific settle down time + * @irqtype: type of interrupt, falling or rising edge + * @enable_wakeup: specifies if keypad event can wake up system from sleep + * @no_autorepeat: flag for auto repetition + */ +struct tc3589x_keypad_platform_data { + const struct matrix_keymap_data *keymap_data; + u8 krow; + u8 kcol; + u8 debounce_period; + u8 settle_time; + unsigned long irqtype; + bool enable_wakeup; + bool no_autorepeat; +}; + /** * struct tc3589x_gpio_platform_data - TC3589x GPIO platform data * @gpio_base: first gpio number assigned to TC3589x. A maximum of @@ -130,11 +180,13 @@ struct tc3589x_gpio_platform_data { * @block: bitmask of blocks to enable (use TC3589x_BLOCK_*) * @irq_base: base IRQ number. %TC3589x_NR_IRQS irqs will be used. * @gpio: GPIO-specific platform data + * @keypad: keypad-specific platform data */ struct tc3589x_platform_data { unsigned int block; int irq_base; struct tc3589x_gpio_platform_data *gpio; + const struct tc3589x_keypad_platform_data *keypad; }; #define TC3589x_NR_GPIOS 24 -- cgit v1.2.3 From 3e29027af43728c2a91fe3f735ab2822edaf54a8 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Thu, 30 Dec 2010 09:25:46 +0000 Subject: dcbnl: add support for ieee8021Qaz attributes The IEEE8021Qaz is the IEEE standard version of CEE. The standard has had enough significant changes from the CEE version that many of the CEE attributes have no meaning in the new spec or do not easily map to IEEE standards. Rather then attempt to create a complicated mapping between CEE and IEEE standards this patch adds a nested IEEE attribute to the list of DCB attributes. The policy is, [DCB_ATTR_IFNAME] [DCB_ATTR_STATE] ... [DCB_ATTR_IEEE] [DCB_ATTR_IEEE_ETS] [DCB_ATTR_IEEE_PFC] [DCB_ATTR_IEEE_APP_TABLE] [DCB_ATTR_IEEE_APP] ... The following dcbnl_rtnl_ops routines were added to handle the IEEE standard, int (*ieee_getets) (struct net_device *, struct ieee_ets *); int (*ieee_setets) (struct net_device *, struct ieee_ets *); int (*ieee_getpfc) (struct net_device *, struct ieee_pfc *); int (*ieee_setpfc) (struct net_device *, struct ieee_pfc *); int (*ieee_getapp) (struct net_device *, struct dcb_app *); int (*ieee_setapp) (struct net_device *, struct dcb_app *); Signed-off-by: John Fastabend Signed-off-by: David S. Miller --- include/linux/dcbnl.h | 106 ++++++++++++++++++++++++++++++++++++++++ include/net/dcbnl.h | 11 +++++ net/dcb/dcbnl.c | 131 ++++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 248 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dcbnl.h b/include/linux/dcbnl.h index 8723491f7dfd..287b5618e296 100644 --- a/include/linux/dcbnl.h +++ b/include/linux/dcbnl.h @@ -22,6 +22,87 @@ #include +/* IEEE 802.1Qaz std supported values */ +#define IEEE_8021QAZ_MAX_TCS 8 + +/* This structure contains the IEEE 802.1Qaz ETS managed object + * + * @willing: willing bit in ETS configuratin TLV + * @ets_cap: indicates supported capacity of ets feature + * @cbs: credit based shaper ets algorithm supported + * @tc_tx_bw: tc tx bandwidth indexed by traffic class + * @tc_rx_bw: tc rx bandwidth indexed by traffic class + * @tc_tsa: TSA Assignment table, indexed by traffic class + * @prio_tc: priority assignment table mapping 8021Qp to traffic class + * @tc_reco_bw: recommended tc bandwidth indexed by traffic class for TLV + * @tc_reco_tsa: recommended tc bandwidth indexed by traffic class for TLV + * @reco_prio_tc: recommended tc tx bandwidth indexed by traffic class for TLV + * + * Recommended values are used to set fields in the ETS recommendation TLV + * with hardware offloaded LLDP. + * + * ---- + * TSA Assignment 8 bit identifiers + * 0 strict priority + * 1 credit-based shaper + * 2 enhanced transmission selection + * 3-254 reserved + * 255 vendor specific + */ +struct ieee_ets { + __u8 willing; + __u8 ets_cap; + __u8 cbs; + __u8 tc_tx_bw[IEEE_8021QAZ_MAX_TCS]; + __u8 tc_rx_bw[IEEE_8021QAZ_MAX_TCS]; + __u8 tc_tsa[IEEE_8021QAZ_MAX_TCS]; + __u8 prio_tc[IEEE_8021QAZ_MAX_TCS]; + __u8 tc_reco_bw[IEEE_8021QAZ_MAX_TCS]; + __u8 tc_reco_tsa[IEEE_8021QAZ_MAX_TCS]; + __u8 reco_prio_tc[IEEE_8021QAZ_MAX_TCS]; +}; + +/* This structure contains the IEEE 802.1Qaz PFC managed object + * + * @pfc_cap: Indicates the number of traffic classes on the local device + * that may simultaneously have PFC enabled. + * @pfc_en: bitmap indicating pfc enabled traffic classes + * @mbc: enable macsec bypass capability + * @delay: the allowance made for a round-trip propagation delay of the + * link in bits. + * @requests: count of the sent pfc frames + * @indications: count of the received pfc frames + */ +struct ieee_pfc { + __u8 pfc_cap; + __u8 pfc_en; + __u8 mbc; + __u16 delay; + __u64 requests[IEEE_8021QAZ_MAX_TCS]; + __u64 indications[IEEE_8021QAZ_MAX_TCS]; +}; + +/* This structure contains the IEEE 802.1Qaz APP managed object + * + * @selector: protocol identifier type + * @protocol: protocol of type indicated + * @priority: 3-bit unsigned integer indicating priority + * + * ---- + * Selector field values + * 0 Reserved + * 1 Ethertype + * 2 Well known port number over TCP or SCTP + * 3 Well known port number over UDP or DCCP + * 4 Well known port number over TCP, SCTP, UDP, or DCCP + * 5-7 Reserved + */ +struct dcb_app { + __u8 selector; + __u32 protocol; + __u8 priority; +}; + struct dcbmsg { __u8 dcb_family; __u8 cmd; @@ -50,6 +131,8 @@ struct dcbmsg { * @DCB_CMD_SBCN: get backward congestion notification configration. * @DCB_CMD_GAPP: get application protocol configuration * @DCB_CMD_SAPP: set application protocol configuration + * @DCB_CMD_IEEE_SET: set IEEE 802.1Qaz configuration + * @DCB_CMD_IEEE_GET: get IEEE 802.1Qaz configuration */ enum dcbnl_commands { DCB_CMD_UNDEFINED, @@ -83,6 +166,9 @@ enum dcbnl_commands { DCB_CMD_GAPP, DCB_CMD_SAPP, + DCB_CMD_IEEE_SET, + DCB_CMD_IEEE_GET, + __DCB_CMD_ENUM_MAX, DCB_CMD_MAX = __DCB_CMD_ENUM_MAX - 1, }; @@ -102,6 +188,7 @@ enum dcbnl_commands { * @DCB_ATTR_CAP: DCB capabilities of the device (NLA_NESTED) * @DCB_ATTR_NUMTCS: number of traffic classes supported (NLA_NESTED) * @DCB_ATTR_BCN: backward congestion notification configuration (NLA_NESTED) + * @DCB_ATTR_IEEE: IEEE 802.1Qaz supported attributes (NLA_NESTED) */ enum dcbnl_attrs { DCB_ATTR_UNDEFINED, @@ -119,10 +206,29 @@ enum dcbnl_attrs { DCB_ATTR_BCN, DCB_ATTR_APP, + /* IEEE std attributes */ + DCB_ATTR_IEEE, + __DCB_ATTR_ENUM_MAX, DCB_ATTR_MAX = __DCB_ATTR_ENUM_MAX - 1, }; +enum ieee_attrs { + DCB_ATTR_IEEE_UNSPEC, + DCB_ATTR_IEEE_ETS, + DCB_ATTR_IEEE_PFC, + DCB_ATTR_IEEE_APP_TABLE, + __DCB_ATTR_IEEE_MAX +}; +#define DCB_ATTR_IEEE_MAX (__DCB_ATTR_IEEE_MAX - 1) + +enum ieee_attrs_app { + DCB_ATTR_IEEE_APP_UNSPEC, + DCB_ATTR_IEEE_APP, + __DCB_ATTR_IEEE_APP_MAX +}; +#define DCB_ATTR_IEEE_APP_MAX (__DCB_ATTR_IEEE_APP_MAX - 1) + /** * enum dcbnl_pfc_attrs - DCB Priority Flow Control user priority nested attrs * diff --git a/include/net/dcbnl.h b/include/net/dcbnl.h index b36ac7e0914d..e2d841e963b3 100644 --- a/include/net/dcbnl.h +++ b/include/net/dcbnl.h @@ -20,11 +20,22 @@ #ifndef __NET_DCBNL_H__ #define __NET_DCBNL_H__ +#include + /* * Ops struct for the netlink callbacks. Used by DCB-enabled drivers through * the netdevice struct. */ struct dcbnl_rtnl_ops { + /* IEEE 802.1Qaz std */ + int (*ieee_getets) (struct net_device *, struct ieee_ets *); + int (*ieee_setets) (struct net_device *, struct ieee_ets *); + int (*ieee_getpfc) (struct net_device *, struct ieee_pfc *); + int (*ieee_setpfc) (struct net_device *, struct ieee_pfc *); + int (*ieee_getapp) (struct net_device *, struct dcb_app *); + int (*ieee_setapp) (struct net_device *, struct dcb_app *); + + /* CEE std */ u8 (*getstate)(struct net_device *); u8 (*setstate)(struct net_device *, u8); void (*getpermhwaddr)(struct net_device *, u8 *); diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index 19ac2b985485..2ff908498924 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -66,6 +66,7 @@ static const struct nla_policy dcbnl_rtnl_policy[DCB_ATTR_MAX + 1] = { [DCB_ATTR_PFC_STATE] = {.type = NLA_U8}, [DCB_ATTR_BCN] = {.type = NLA_NESTED}, [DCB_ATTR_APP] = {.type = NLA_NESTED}, + [DCB_ATTR_IEEE] = {.type = NLA_NESTED}, }; /* DCB priority flow control to User Priority nested attributes */ @@ -167,6 +168,17 @@ static const struct nla_policy dcbnl_app_nest[DCB_APP_ATTR_MAX + 1] = { [DCB_APP_ATTR_PRIORITY] = {.type = NLA_U8}, }; +/* IEEE 802.1Qaz nested attributes. */ +static const struct nla_policy dcbnl_ieee_policy[DCB_ATTR_IEEE_MAX + 1] = { + [DCB_ATTR_IEEE_ETS] = {.len = sizeof(struct ieee_ets)}, + [DCB_ATTR_IEEE_PFC] = {.len = sizeof(struct ieee_pfc)}, + [DCB_ATTR_IEEE_APP_TABLE] = {.type = NLA_NESTED}, +}; + +static const struct nla_policy dcbnl_ieee_app[DCB_ATTR_IEEE_APP_MAX + 1] = { + [DCB_ATTR_IEEE_APP] = {.len = sizeof(struct dcb_app)}, +}; + /* standard netlink reply call */ static int dcbnl_reply(u8 value, u8 event, u8 cmd, u8 attr, u32 pid, u32 seq, u16 flags) @@ -1118,6 +1130,117 @@ err: return ret; } +/* Handle IEEE 802.1Qaz SET commands. If any requested operation can not + * be completed the entire msg is aborted and error value is returned. + * No attempt is made to reconcile the case where only part of the + * cmd can be completed. + */ +static int dcbnl_ieee_set(struct net_device *netdev, struct nlattr **tb, + u32 pid, u32 seq, u16 flags) +{ + const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops; + struct nlattr *ieee[DCB_ATTR_IEEE_MAX + 1]; + int err = -EOPNOTSUPP; + + if (!ops) + goto err; + + err = nla_parse_nested(ieee, DCB_ATTR_IEEE_MAX, + tb[DCB_ATTR_IEEE], dcbnl_ieee_policy); + if (err) + goto err; + + if (ieee[DCB_ATTR_IEEE_ETS] && ops->ieee_setets) { + struct ieee_ets *ets = nla_data(ieee[DCB_ATTR_IEEE_ETS]); + err = ops->ieee_setets(netdev, ets); + if (err) + goto err; + } + + if (ieee[DCB_ATTR_IEEE_PFC] && ops->ieee_setets) { + struct ieee_pfc *pfc = nla_data(ieee[DCB_ATTR_IEEE_PFC]); + err = ops->ieee_setpfc(netdev, pfc); + if (err) + goto err; + } + + if (ieee[DCB_ATTR_IEEE_APP_TABLE] && ops->ieee_setapp) { + struct nlattr *attr; + int rem; + + nla_for_each_nested(attr, ieee[DCB_ATTR_IEEE_APP_TABLE], rem) { + struct dcb_app *app_data; + if (nla_type(attr) != DCB_ATTR_IEEE_APP) + continue; + app_data = nla_data(attr); + err = ops->ieee_setapp(netdev, app_data); + if (err) + goto err; + } + } + +err: + dcbnl_reply(err, RTM_SETDCB, DCB_CMD_IEEE_SET, DCB_ATTR_IEEE, + pid, seq, flags); + return err; +} + + +/* Handle IEEE 802.1Qaz GET commands. */ +static int dcbnl_ieee_get(struct net_device *netdev, struct nlattr **tb, + u32 pid, u32 seq, u16 flags) +{ + struct sk_buff *skb; + struct nlmsghdr *nlh; + struct dcbmsg *dcb; + struct nlattr *ieee; + const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops; + int err; + + if (!ops) + return -EOPNOTSUPP; + + skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!skb) + return -ENOBUFS; + + nlh = NLMSG_NEW(skb, pid, seq, RTM_GETDCB, sizeof(*dcb), flags); + + dcb = NLMSG_DATA(nlh); + dcb->dcb_family = AF_UNSPEC; + dcb->cmd = DCB_CMD_IEEE_GET; + + NLA_PUT_STRING(skb, DCB_ATTR_IFNAME, netdev->name); + + ieee = nla_nest_start(skb, DCB_ATTR_IEEE); + if (!ieee) + goto nla_put_failure; + + if (ops->ieee_getets) { + struct ieee_ets ets; + err = ops->ieee_getets(netdev, &ets); + if (!err) + NLA_PUT(skb, DCB_ATTR_IEEE_ETS, sizeof(ets), &ets); + } + + if (ops->ieee_getpfc) { + struct ieee_pfc pfc; + err = ops->ieee_getpfc(netdev, &pfc); + if (!err) + NLA_PUT(skb, DCB_ATTR_IEEE_PFC, sizeof(pfc), &pfc); + } + + nla_nest_end(skb, ieee); + nlmsg_end(skb, nlh); + + return rtnl_unicast(skb, &init_net, pid); +nla_put_failure: + nlmsg_cancel(skb, nlh); +nlmsg_failure: + kfree_skb(skb); + return -1; +} + static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { struct net *net = sock_net(skb->sk); @@ -1223,6 +1346,14 @@ static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) ret = dcbnl_setapp(netdev, tb, pid, nlh->nlmsg_seq, nlh->nlmsg_flags); goto out; + case DCB_CMD_IEEE_SET: + ret = dcbnl_ieee_set(netdev, tb, pid, nlh->nlmsg_seq, + nlh->nlmsg_flags); + goto out; + case DCB_CMD_IEEE_GET: + ret = dcbnl_ieee_get(netdev, tb, pid, nlh->nlmsg_seq, + nlh->nlmsg_flags); + goto out; default: goto errout; } -- cgit v1.2.3 From 9ab933ab2cc80f04690d6aa385b1110075c5e507 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Thu, 30 Dec 2010 09:26:31 +0000 Subject: dcbnl: add appliction tlv handlers This patch adds application tlv handlers. Networking stacks may use the application priority to set the skb priority of their stack using the negoatiated dcbx priority. This patch provides the dcb_{get|set}app() routines for the stack to query these parameters. Notice lower layer drivers can use the dcbnl_ops routines if additional handling is needed. Perhaps in the firmware case for example Signed-off-by: John Fastabend Signed-off-by: Shmulik Ravid Signed-off-by: David S. Miller --- include/linux/dcbnl.h | 4 +- include/net/dcbnl.h | 9 ++++ net/dcb/dcbnl.c | 133 ++++++++++++++++++++++++++++++++++++++++++++++---- 3 files changed, 135 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dcbnl.h b/include/linux/dcbnl.h index 287b5618e296..775bdb4465bf 100644 --- a/include/linux/dcbnl.h +++ b/include/linux/dcbnl.h @@ -82,7 +82,9 @@ struct ieee_pfc { __u64 indications[IEEE_8021QAZ_MAX_TCS]; }; -/* This structure contains the IEEE 802.1Qaz APP managed object +/* This structure contains the IEEE 802.1Qaz APP managed object. This + * object is also used for the CEE std as well. There is no difference + * between the objects. * * @selector: protocol identifier type * @protocol: protocol of type indicated diff --git a/include/net/dcbnl.h b/include/net/dcbnl.h index e2d841e963b3..ab7d623a2793 100644 --- a/include/net/dcbnl.h +++ b/include/net/dcbnl.h @@ -22,6 +22,15 @@ #include +struct dcb_app_type { + char name[IFNAMSIZ]; + struct dcb_app app; + struct list_head list; +}; + +u8 dcb_setapp(struct net_device *, struct dcb_app *); +u8 dcb_getapp(struct net_device *, struct dcb_app *); + /* * Ops struct for the netlink callbacks. Used by DCB-enabled drivers through * the netdevice struct. diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index 2ff908498924..cfd731faf6c6 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -179,6 +179,9 @@ static const struct nla_policy dcbnl_ieee_app[DCB_ATTR_IEEE_APP_MAX + 1] = { [DCB_ATTR_IEEE_APP] = {.len = sizeof(struct dcb_app)}, }; +static LIST_HEAD(dcb_app_list); +static DEFINE_SPINLOCK(dcb_lock); + /* standard netlink reply call */ static int dcbnl_reply(u8 value, u8 event, u8 cmd, u8 attr, u32 pid, u32 seq, u16 flags) @@ -634,12 +637,12 @@ out: static int dcbnl_setapp(struct net_device *netdev, struct nlattr **tb, u32 pid, u32 seq, u16 flags) { - int ret = -EINVAL; + int err, ret = -EINVAL; u16 id; u8 up, idtype; struct nlattr *app_tb[DCB_APP_ATTR_MAX + 1]; - if (!tb[DCB_ATTR_APP] || !netdev->dcbnl_ops->setapp) + if (!tb[DCB_ATTR_APP]) goto out; ret = nla_parse_nested(app_tb, DCB_APP_ATTR_MAX, tb[DCB_ATTR_APP], @@ -663,9 +666,18 @@ static int dcbnl_setapp(struct net_device *netdev, struct nlattr **tb, id = nla_get_u16(app_tb[DCB_APP_ATTR_ID]); up = nla_get_u8(app_tb[DCB_APP_ATTR_PRIORITY]); - ret = dcbnl_reply(netdev->dcbnl_ops->setapp(netdev, idtype, id, up), - RTM_SETDCB, DCB_CMD_SAPP, DCB_ATTR_APP, - pid, seq, flags); + if (netdev->dcbnl_ops->setapp) { + err = netdev->dcbnl_ops->setapp(netdev, idtype, id, up); + } else { + struct dcb_app app; + app.selector = idtype; + app.protocol = id; + app.priority = up; + err = dcb_setapp(netdev, &app); + } + + ret = dcbnl_reply(err, RTM_SETDCB, DCB_CMD_SAPP, DCB_ATTR_APP, + pid, seq, flags); out: return ret; } @@ -1164,7 +1176,7 @@ static int dcbnl_ieee_set(struct net_device *netdev, struct nlattr **tb, goto err; } - if (ieee[DCB_ATTR_IEEE_APP_TABLE] && ops->ieee_setapp) { + if (ieee[DCB_ATTR_IEEE_APP_TABLE]) { struct nlattr *attr; int rem; @@ -1173,7 +1185,10 @@ static int dcbnl_ieee_set(struct net_device *netdev, struct nlattr **tb, if (nla_type(attr) != DCB_ATTR_IEEE_APP) continue; app_data = nla_data(attr); - err = ops->ieee_setapp(netdev, app_data); + if (ops->ieee_setapp) + err = ops->ieee_setapp(netdev, app_data); + else + err = dcb_setapp(netdev, app_data); if (err) goto err; } @@ -1193,7 +1208,8 @@ static int dcbnl_ieee_get(struct net_device *netdev, struct nlattr **tb, struct sk_buff *skb; struct nlmsghdr *nlh; struct dcbmsg *dcb; - struct nlattr *ieee; + struct nlattr *ieee, *app; + struct dcb_app_type *itr; const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops; int err; @@ -1230,6 +1246,19 @@ static int dcbnl_ieee_get(struct net_device *netdev, struct nlattr **tb, NLA_PUT(skb, DCB_ATTR_IEEE_PFC, sizeof(pfc), &pfc); } + app = nla_nest_start(skb, DCB_ATTR_IEEE_APP_TABLE); + if (!app) + goto nla_put_failure; + + spin_lock(&dcb_lock); + list_for_each_entry(itr, &dcb_app_list, list) { + if (strncmp(itr->name, netdev->name, IFNAMSIZ) == 0) + NLA_PUT(skb, DCB_ATTR_IEEE_APP, + sizeof(itr->app), &itr->app); + } + spin_unlock(&dcb_lock); + nla_nest_end(skb, app); + nla_nest_end(skb, ieee); nlmsg_end(skb, nlh); @@ -1364,8 +1393,93 @@ out: return ret; } +/** + * dcb_getapp - retrieve the DCBX application user priority + * + * On success returns a non-zero 802.1p user priority bitmap + * otherwise returns 0 as the invalid user priority bitmap to + * indicate an error. + */ +u8 dcb_getapp(struct net_device *dev, struct dcb_app *app) +{ + struct dcb_app_type *itr; + u8 prio = 0; + + spin_lock(&dcb_lock); + list_for_each_entry(itr, &dcb_app_list, list) { + if (itr->app.selector == app->selector && + itr->app.protocol == app->protocol && + (strncmp(itr->name, dev->name, IFNAMSIZ) == 0)) { + prio = itr->app.priority; + break; + } + } + spin_unlock(&dcb_lock); + + return prio; +} +EXPORT_SYMBOL(dcb_getapp); + +/** + * ixgbe_dcbnl_setapp - add dcb application data to app list + * + * Priority 0 is the default priority this removes applications + * from the app list if the priority is set to zero. + */ +u8 dcb_setapp(struct net_device *dev, struct dcb_app *new) +{ + struct dcb_app_type *itr; + + spin_lock(&dcb_lock); + /* Search for existing match and replace */ + list_for_each_entry(itr, &dcb_app_list, list) { + if (itr->app.selector == new->selector && + itr->app.protocol == new->protocol && + (strncmp(itr->name, dev->name, IFNAMSIZ) == 0)) { + if (new->priority) + itr->app.priority = new->priority; + else { + list_del(&itr->list); + kfree(itr); + } + goto out; + } + } + /* App type does not exist add new application type */ + if (new->priority) { + struct dcb_app_type *entry; + entry = kmalloc(sizeof(struct dcb_app_type), GFP_ATOMIC); + if (!entry) { + spin_unlock(&dcb_lock); + return -ENOMEM; + } + + memcpy(&entry->app, new, sizeof(*new)); + strncpy(entry->name, dev->name, IFNAMSIZ); + list_add(&entry->list, &dcb_app_list); + } +out: + spin_unlock(&dcb_lock); + return 0; +} +EXPORT_SYMBOL(dcb_setapp); + +void dcb_flushapp(void) +{ + struct dcb_app_type *app; + + spin_lock(&dcb_lock); + list_for_each_entry(app, &dcb_app_list, list) { + list_del(&app->list); + kfree(app); + } + spin_unlock(&dcb_lock); +} + static int __init dcbnl_init(void) { + INIT_LIST_HEAD(&dcb_app_list); + rtnl_register(PF_UNSPEC, RTM_GETDCB, dcb_doit, NULL); rtnl_register(PF_UNSPEC, RTM_SETDCB, dcb_doit, NULL); @@ -1377,7 +1491,6 @@ static void __exit dcbnl_exit(void) { rtnl_unregister(PF_UNSPEC, RTM_GETDCB); rtnl_unregister(PF_UNSPEC, RTM_SETDCB); + dcb_flushapp(); } module_exit(dcbnl_exit); - - -- cgit v1.2.3 From 6241b6259b16aa390ff4bf50f520685b3801200b Mon Sep 17 00:00:00 2001 From: Shmulik Ravid Date: Thu, 30 Dec 2010 06:26:48 +0000 Subject: dcbnl: adding DCBX engine capability Adding an optional DCBX capability and a pair for get-set routines for setting the device DCBX mode. The DCBX capability is a bit field of supported attributes. The user is expected to set the DCBX mode with a subset of the advertised attributes. This patch is dependent on the following patches: [net-next-2.6 PATCH 1/3] dcbnl: add support for ieee8021Qaz attributes [net-next-2.6 PATCH 2/3] dcbnl: add appliction tlv handlers [net-next-2.6 PATCH 3/3] net_dcb: add application notifiers Signed-off-by: Shmulik Ravid Acked-by: John Fastabend Signed-off-by: David S. Miller --- include/linux/dcbnl.h | 43 +++++++++++++++++++++++++++++++++++++++++++ include/net/dcbnl.h | 5 +++++ net/dcb/dcbnl.c | 43 +++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 91 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dcbnl.h b/include/linux/dcbnl.h index 775bdb4465bf..16eea36d8934 100644 --- a/include/linux/dcbnl.h +++ b/include/linux/dcbnl.h @@ -135,6 +135,8 @@ struct dcbmsg { * @DCB_CMD_SAPP: set application protocol configuration * @DCB_CMD_IEEE_SET: set IEEE 802.1Qaz configuration * @DCB_CMD_IEEE_GET: get IEEE 802.1Qaz configuration + * @DCB_CMD_GDCBX: get DCBX engine configuration + * @DCB_CMD_SDCBX: set DCBX engine configuration */ enum dcbnl_commands { DCB_CMD_UNDEFINED, @@ -171,6 +173,9 @@ enum dcbnl_commands { DCB_CMD_IEEE_SET, DCB_CMD_IEEE_GET, + DCB_CMD_GDCBX, + DCB_CMD_SDCBX, + __DCB_CMD_ENUM_MAX, DCB_CMD_MAX = __DCB_CMD_ENUM_MAX - 1, }; @@ -191,6 +196,7 @@ enum dcbnl_commands { * @DCB_ATTR_NUMTCS: number of traffic classes supported (NLA_NESTED) * @DCB_ATTR_BCN: backward congestion notification configuration (NLA_NESTED) * @DCB_ATTR_IEEE: IEEE 802.1Qaz supported attributes (NLA_NESTED) + * @DCB_ATTR_DCBX: DCBX engine configuration in the device (NLA_U8) */ enum dcbnl_attrs { DCB_ATTR_UNDEFINED, @@ -211,6 +217,8 @@ enum dcbnl_attrs { /* IEEE std attributes */ DCB_ATTR_IEEE, + DCB_ATTR_DCBX, + __DCB_ATTR_ENUM_MAX, DCB_ATTR_MAX = __DCB_ATTR_ENUM_MAX - 1, }; @@ -370,6 +378,8 @@ enum dcbnl_tc_attrs { * @DCB_CAP_ATTR_GSP: (NLA_U8) device supports group strict priority * @DCB_CAP_ATTR_BCN: (NLA_U8) device supports Backwards Congestion * Notification + * @DCB_CAP_ATTR_DCBX: (NLA_U8) device supports DCBX engine + * */ enum dcbnl_cap_attrs { DCB_CAP_ATTR_UNDEFINED, @@ -381,11 +391,44 @@ enum dcbnl_cap_attrs { DCB_CAP_ATTR_PFC_TCS, DCB_CAP_ATTR_GSP, DCB_CAP_ATTR_BCN, + DCB_CAP_ATTR_DCBX, __DCB_CAP_ATTR_ENUM_MAX, DCB_CAP_ATTR_MAX = __DCB_CAP_ATTR_ENUM_MAX - 1, }; +/** + * DCBX capability flags + * + * @DCB_CAP_DCBX_HOST: DCBX negotiation is performed by the host LLDP agent. + * 'set' routines are used to configure the device with + * the negotiated parameters + * + * @DCB_CAP_DCBX_LLD_MANAGED: DCBX negotiation is not performed in the host but + * by another entity + * 'get' routines are used to retrieve the + * negotiated parameters + * 'set' routines can be used to set the initial + * negotiation configuration + * + * @DCB_CAP_DCBX_VER_CEE: for a non-host DCBX engine, indicates the engine + * supports the CEE protocol flavor + * + * @DCB_CAP_DCBX_VER_IEEE: for a non-host DCBX engine, indicates the engine + * supports the IEEE protocol flavor + * + * @DCB_CAP_DCBX_STATIC: for a non-host DCBX engine, indicates the engine + * supports static configuration (i.e no actual + * negotiation is performed negotiated parameters equal + * the initial configuration) + * + */ +#define DCB_CAP_DCBX_HOST 0x01 +#define DCB_CAP_DCBX_LLD_MANAGED 0x02 +#define DCB_CAP_DCBX_VER_CEE 0x04 +#define DCB_CAP_DCBX_VER_IEEE 0x08 +#define DCB_CAP_DCBX_STATIC 0x10 + /** * enum dcbnl_numtcs_attrs - number of traffic classes * diff --git a/include/net/dcbnl.h b/include/net/dcbnl.h index ab7d623a2793..c65347b3cbbf 100644 --- a/include/net/dcbnl.h +++ b/include/net/dcbnl.h @@ -70,6 +70,11 @@ struct dcbnl_rtnl_ops { void (*setbcnrp)(struct net_device *, int, u8); u8 (*setapp)(struct net_device *, u8, u16, u8); u8 (*getapp)(struct net_device *, u8, u16); + + /* DCBX configuration */ + u8 (*getdcbx)(struct net_device *); + u8 (*setdcbx)(struct net_device *, u8); + }; #endif /* __NET_DCBNL_H__ */ diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index 69144125fc4f..8f83ad859d9b 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -68,6 +68,7 @@ static const struct nla_policy dcbnl_rtnl_policy[DCB_ATTR_MAX + 1] = { [DCB_ATTR_BCN] = {.type = NLA_NESTED}, [DCB_ATTR_APP] = {.type = NLA_NESTED}, [DCB_ATTR_IEEE] = {.type = NLA_NESTED}, + [DCB_ATTR_DCBX] = {.type = NLA_U8}, }; /* DCB priority flow control to User Priority nested attributes */ @@ -124,6 +125,7 @@ static const struct nla_policy dcbnl_cap_nest[DCB_CAP_ATTR_MAX + 1] = { [DCB_CAP_ATTR_PFC_TCS] = {.type = NLA_U8}, [DCB_CAP_ATTR_GSP] = {.type = NLA_U8}, [DCB_CAP_ATTR_BCN] = {.type = NLA_U8}, + [DCB_CAP_ATTR_DCBX] = {.type = NLA_U8}, }; /* DCB capabilities nested attributes. */ @@ -1271,6 +1273,39 @@ nlmsg_failure: return -1; } +/* DCBX configuration */ +static int dcbnl_getdcbx(struct net_device *netdev, struct nlattr **tb, + u32 pid, u32 seq, u16 flags) +{ + int ret = -EINVAL; + + if (!netdev->dcbnl_ops->getdcbx) + return ret; + + ret = dcbnl_reply(netdev->dcbnl_ops->getdcbx(netdev), RTM_GETDCB, + DCB_CMD_GDCBX, DCB_ATTR_DCBX, pid, seq, flags); + + return ret; +} + +static int dcbnl_setdcbx(struct net_device *netdev, struct nlattr **tb, + u32 pid, u32 seq, u16 flags) +{ + int ret = -EINVAL; + u8 value; + + if (!tb[DCB_ATTR_DCBX] || !netdev->dcbnl_ops->setdcbx) + return ret; + + value = nla_get_u8(tb[DCB_ATTR_DCBX]); + + ret = dcbnl_reply(netdev->dcbnl_ops->setdcbx(netdev, value), + RTM_SETDCB, DCB_CMD_SDCBX, DCB_ATTR_DCBX, + pid, seq, flags); + + return ret; +} + static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { struct net *net = sock_net(skb->sk); @@ -1384,6 +1419,14 @@ static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) ret = dcbnl_ieee_get(netdev, tb, pid, nlh->nlmsg_seq, nlh->nlmsg_flags); goto out; + case DCB_CMD_GDCBX: + ret = dcbnl_getdcbx(netdev, tb, pid, nlh->nlmsg_seq, + nlh->nlmsg_flags); + goto out; + case DCB_CMD_SDCBX: + ret = dcbnl_setdcbx(netdev, tb, pid, nlh->nlmsg_seq, + nlh->nlmsg_flags); + goto out; default: goto errout; } -- cgit v1.2.3 From ea45fe4e176a42d2396878f530cfdc8265bef37b Mon Sep 17 00:00:00 2001 From: Shmulik Ravid Date: Thu, 30 Dec 2010 06:26:55 +0000 Subject: dcbnl: adding DCBX feature flags get-set Adding a pair of set-get routines to dcbnl for setting the negotiation flags of the various DCB features. Conforms to the CEE flavor of DCBX The user sets these flags (enable, advertise, willing) for each feature to be used by the DCBX engine. The 'get' routine returns which of the features is enabled after the negotiation. This patch is dependent on the following patches: [net-next-2.6 PATCH 1/3] dcbnl: add support for ieee8021Qaz attributes [net-next-2.6 PATCH 2/3] dcbnl: add appliction tlv handlers [net-next-2.6 PATCH 3/3] net_dcb: add application notifiers Signed-off-by: Shmulik Ravid Signed-off-by: David S. Miller --- include/linux/dcbnl.h | 33 +++++++++++++ include/net/dcbnl.h | 3 ++ net/dcb/dcbnl.c | 133 ++++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 169 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dcbnl.h b/include/linux/dcbnl.h index 16eea36d8934..68cd248f6d3e 100644 --- a/include/linux/dcbnl.h +++ b/include/linux/dcbnl.h @@ -137,6 +137,8 @@ struct dcbmsg { * @DCB_CMD_IEEE_GET: get IEEE 802.1Qaz configuration * @DCB_CMD_GDCBX: get DCBX engine configuration * @DCB_CMD_SDCBX: set DCBX engine configuration + * @DCB_CMD_GFEATCFG: get DCBX features flags + * @DCB_CMD_SFEATCFG: set DCBX features negotiation flags */ enum dcbnl_commands { DCB_CMD_UNDEFINED, @@ -176,6 +178,9 @@ enum dcbnl_commands { DCB_CMD_GDCBX, DCB_CMD_SDCBX, + DCB_CMD_GFEATCFG, + DCB_CMD_SFEATCFG, + __DCB_CMD_ENUM_MAX, DCB_CMD_MAX = __DCB_CMD_ENUM_MAX - 1, }; @@ -197,6 +202,7 @@ enum dcbnl_commands { * @DCB_ATTR_BCN: backward congestion notification configuration (NLA_NESTED) * @DCB_ATTR_IEEE: IEEE 802.1Qaz supported attributes (NLA_NESTED) * @DCB_ATTR_DCBX: DCBX engine configuration in the device (NLA_U8) + * @DCB_ATTR_FEATCFG: DCBX features flags (NLA_NESTED) */ enum dcbnl_attrs { DCB_ATTR_UNDEFINED, @@ -218,6 +224,7 @@ enum dcbnl_attrs { DCB_ATTR_IEEE, DCB_ATTR_DCBX, + DCB_ATTR_FEATCFG, __DCB_ATTR_ENUM_MAX, DCB_ATTR_MAX = __DCB_ATTR_ENUM_MAX - 1, @@ -506,4 +513,30 @@ enum dcbnl_app_attrs { DCB_APP_ATTR_MAX = __DCB_APP_ATTR_ENUM_MAX - 1, }; +/** + * enum dcbnl_featcfg_attrs - features conifiguration flags + * + * @DCB_FEATCFG_ATTR_UNDEFINED: unspecified attribute to catch errors + * @DCB_FEATCFG_ATTR_ALL: (NLA_FLAG) all features configuration attributes + * @DCB_FEATCFG_ATTR_PG: (NLA_U8) configuration flags for priority groups + * @DCB_FEATCFG_ATTR_PFC: (NLA_U8) configuration flags for priority + * flow control + * @DCB_FEATCFG_ATTR_APP: (NLA_U8) configuration flags for application TLV + * + */ +#define DCB_FEATCFG_ERROR 0x01 /* error in feature resolution */ +#define DCB_FEATCFG_ENABLE 0x02 /* enable feature */ +#define DCB_FEATCFG_WILLING 0x04 /* feature is willing */ +#define DCB_FEATCFG_ADVERTISE 0x08 /* advertise feature */ +enum dcbnl_featcfg_attrs { + DCB_FEATCFG_ATTR_UNDEFINED, + DCB_FEATCFG_ATTR_ALL, + DCB_FEATCFG_ATTR_PG, + DCB_FEATCFG_ATTR_PFC, + DCB_FEATCFG_ATTR_APP, + + __DCB_FEATCFG_ATTR_ENUM_MAX, + DCB_FEATCFG_ATTR_MAX = __DCB_FEATCFG_ATTR_ENUM_MAX - 1, +}; + #endif /* __LINUX_DCBNL_H__ */ diff --git a/include/net/dcbnl.h b/include/net/dcbnl.h index c65347b3cbbf..a8e7852b10ab 100644 --- a/include/net/dcbnl.h +++ b/include/net/dcbnl.h @@ -70,11 +70,14 @@ struct dcbnl_rtnl_ops { void (*setbcnrp)(struct net_device *, int, u8); u8 (*setapp)(struct net_device *, u8, u16, u8); u8 (*getapp)(struct net_device *, u8, u16); + u8 (*getfeatcfg)(struct net_device *, int, u8 *); + u8 (*setfeatcfg)(struct net_device *, int, u8); /* DCBX configuration */ u8 (*getdcbx)(struct net_device *); u8 (*setdcbx)(struct net_device *, u8); + }; #endif /* __NET_DCBNL_H__ */ diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index 8f83ad859d9b..075af0a08d84 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -69,6 +69,7 @@ static const struct nla_policy dcbnl_rtnl_policy[DCB_ATTR_MAX + 1] = { [DCB_ATTR_APP] = {.type = NLA_NESTED}, [DCB_ATTR_IEEE] = {.type = NLA_NESTED}, [DCB_ATTR_DCBX] = {.type = NLA_U8}, + [DCB_ATTR_FEATCFG] = {.type = NLA_NESTED}, }; /* DCB priority flow control to User Priority nested attributes */ @@ -182,6 +183,14 @@ static const struct nla_policy dcbnl_ieee_app[DCB_ATTR_IEEE_APP_MAX + 1] = { [DCB_ATTR_IEEE_APP] = {.len = sizeof(struct dcb_app)}, }; +/* DCB number of traffic classes nested attributes. */ +static const struct nla_policy dcbnl_featcfg_nest[DCB_FEATCFG_ATTR_MAX + 1] = { + [DCB_FEATCFG_ATTR_ALL] = {.type = NLA_FLAG}, + [DCB_FEATCFG_ATTR_PG] = {.type = NLA_U8}, + [DCB_FEATCFG_ATTR_PFC] = {.type = NLA_U8}, + [DCB_FEATCFG_ATTR_APP] = {.type = NLA_U8}, +}; + static LIST_HEAD(dcb_app_list); static DEFINE_SPINLOCK(dcb_lock); @@ -1306,6 +1315,122 @@ static int dcbnl_setdcbx(struct net_device *netdev, struct nlattr **tb, return ret; } +static int dcbnl_getfeatcfg(struct net_device *netdev, struct nlattr **tb, + u32 pid, u32 seq, u16 flags) +{ + struct sk_buff *dcbnl_skb; + struct nlmsghdr *nlh; + struct dcbmsg *dcb; + struct nlattr *data[DCB_FEATCFG_ATTR_MAX + 1], *nest; + u8 value; + int ret = -EINVAL; + int i; + int getall = 0; + + if (!tb[DCB_ATTR_FEATCFG] || !netdev->dcbnl_ops->getfeatcfg) + return ret; + + ret = nla_parse_nested(data, DCB_FEATCFG_ATTR_MAX, tb[DCB_ATTR_FEATCFG], + dcbnl_featcfg_nest); + if (ret) { + ret = -EINVAL; + goto err_out; + } + + dcbnl_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!dcbnl_skb) { + ret = -EINVAL; + goto err_out; + } + + nlh = NLMSG_NEW(dcbnl_skb, pid, seq, RTM_GETDCB, sizeof(*dcb), flags); + + dcb = NLMSG_DATA(nlh); + dcb->dcb_family = AF_UNSPEC; + dcb->cmd = DCB_CMD_GFEATCFG; + + nest = nla_nest_start(dcbnl_skb, DCB_ATTR_FEATCFG); + if (!nest) { + ret = -EINVAL; + goto err; + } + + if (data[DCB_FEATCFG_ATTR_ALL]) + getall = 1; + + for (i = DCB_FEATCFG_ATTR_ALL+1; i <= DCB_FEATCFG_ATTR_MAX; i++) { + if (!getall && !data[i]) + continue; + + ret = netdev->dcbnl_ops->getfeatcfg(netdev, i, &value); + if (!ret) { + ret = nla_put_u8(dcbnl_skb, i, value); + + if (ret) { + nla_nest_cancel(dcbnl_skb, nest); + ret = -EINVAL; + goto err; + } + } else + goto err; + } + nla_nest_end(dcbnl_skb, nest); + + nlmsg_end(dcbnl_skb, nlh); + + ret = rtnl_unicast(dcbnl_skb, &init_net, pid); + if (ret) { + ret = -EINVAL; + goto err_out; + } + + return 0; +nlmsg_failure: +err: + kfree_skb(dcbnl_skb); +err_out: + return ret; +} + +static int dcbnl_setfeatcfg(struct net_device *netdev, struct nlattr **tb, + u32 pid, u32 seq, u16 flags) +{ + struct nlattr *data[DCB_FEATCFG_ATTR_MAX + 1]; + int ret = -EINVAL; + u8 value; + int i; + + if (!tb[DCB_ATTR_FEATCFG] || !netdev->dcbnl_ops->setfeatcfg) + return ret; + + ret = nla_parse_nested(data, DCB_FEATCFG_ATTR_MAX, tb[DCB_ATTR_FEATCFG], + dcbnl_featcfg_nest); + + if (ret) { + ret = -EINVAL; + goto err; + } + + for (i = DCB_FEATCFG_ATTR_ALL+1; i <= DCB_FEATCFG_ATTR_MAX; i++) { + if (data[i] == NULL) + continue; + + value = nla_get_u8(data[i]); + + ret = netdev->dcbnl_ops->setfeatcfg(netdev, i, value); + + if (ret) + goto operr; + } + +operr: + ret = dcbnl_reply(!!ret, RTM_SETDCB, DCB_CMD_SFEATCFG, + DCB_ATTR_FEATCFG, pid, seq, flags); + +err: + return ret; +} + static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { struct net *net = sock_net(skb->sk); @@ -1427,6 +1552,14 @@ static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) ret = dcbnl_setdcbx(netdev, tb, pid, nlh->nlmsg_seq, nlh->nlmsg_flags); goto out; + case DCB_CMD_GFEATCFG: + ret = dcbnl_getfeatcfg(netdev, tb, pid, nlh->nlmsg_seq, + nlh->nlmsg_flags); + goto out; + case DCB_CMD_SFEATCFG: + ret = dcbnl_setfeatcfg(netdev, tb, pid, nlh->nlmsg_seq, + nlh->nlmsg_flags); + goto out; default: goto errout; } -- cgit v1.2.3 From 51f98a8d70583b18cb08b19353aeed5efb0244af Mon Sep 17 00:00:00 2001 From: Allan Stephens Date: Fri, 31 Dec 2010 18:59:16 +0000 Subject: tipc: Remove prototype code for supporting multiple zones Eliminates routines, data structures, and files that were intended to allows TIPC to support a network containing multiple zones. Currently, TIPC supports only networks consisting of a single cluster within a single zone, so this code is unnecessary. Signed-off-by: Allan Stephens Signed-off-by: Paul Gortmaker Signed-off-by: David S. Miller --- include/linux/tipc_config.h | 4 +- net/tipc/Kconfig | 12 ---- net/tipc/Makefile | 2 +- net/tipc/addr.c | 4 -- net/tipc/cluster.c | 14 +--- net/tipc/cluster.h | 12 ++-- net/tipc/config.c | 30 ++------- net/tipc/core.c | 6 -- net/tipc/core.h | 1 - net/tipc/net.c | 41 +++++++----- net/tipc/net.h | 8 ++- net/tipc/node.c | 7 +- net/tipc/node.h | 1 - net/tipc/zone.c | 159 -------------------------------------------- net/tipc/zone.h | 70 ------------------- 15 files changed, 46 insertions(+), 325 deletions(-) delete mode 100644 net/tipc/zone.c delete mode 100644 net/tipc/zone.h (limited to 'include/linux') diff --git a/include/linux/tipc_config.h b/include/linux/tipc_config.h index 9cde86c32412..fa3aeaafeab1 100644 --- a/include/linux/tipc_config.h +++ b/include/linux/tipc_config.h @@ -94,7 +94,7 @@ #define TIPC_CMD_GET_MAX_PORTS 0x4004 /* tx none, rx unsigned */ #define TIPC_CMD_GET_MAX_PUBL 0x4005 /* tx none, rx unsigned */ #define TIPC_CMD_GET_MAX_SUBSCR 0x4006 /* tx none, rx unsigned */ -#define TIPC_CMD_GET_MAX_ZONES 0x4007 /* tx none, rx unsigned */ +#define TIPC_CMD_GET_MAX_ZONES 0x4007 /* obsoleted */ #define TIPC_CMD_GET_MAX_CLUSTERS 0x4008 /* tx none, rx unsigned */ #define TIPC_CMD_GET_MAX_NODES 0x4009 /* tx none, rx unsigned */ #define TIPC_CMD_GET_MAX_SLAVES 0x400A /* tx none, rx unsigned */ @@ -130,7 +130,7 @@ #define TIPC_CMD_SET_MAX_PORTS 0x8004 /* tx unsigned, rx none */ #define TIPC_CMD_SET_MAX_PUBL 0x8005 /* tx unsigned, rx none */ #define TIPC_CMD_SET_MAX_SUBSCR 0x8006 /* tx unsigned, rx none */ -#define TIPC_CMD_SET_MAX_ZONES 0x8007 /* tx unsigned, rx none */ +#define TIPC_CMD_SET_MAX_ZONES 0x8007 /* obsoleted */ #define TIPC_CMD_SET_MAX_CLUSTERS 0x8008 /* tx unsigned, rx none */ #define TIPC_CMD_SET_MAX_NODES 0x8009 /* tx unsigned, rx none */ #define TIPC_CMD_SET_MAX_SLAVES 0x800A /* tx unsigned, rx none */ diff --git a/net/tipc/Kconfig b/net/tipc/Kconfig index b74f78d0c033..06d32908fcfb 100644 --- a/net/tipc/Kconfig +++ b/net/tipc/Kconfig @@ -29,18 +29,6 @@ config TIPC_ADVANCED Saying Y here will open some advanced configuration for TIPC. Most users do not need to bother; if unsure, just say N. -config TIPC_ZONES - int "Maximum number of zones in a network" - depends on TIPC_ADVANCED - range 1 255 - default "3" - help - Specifies how many zones can be supported in a TIPC network. - Can range from 1 to 255 zones; default is 3. - - Setting this to a smaller value saves some memory; - setting it to a higher value allows for more zones. - config TIPC_CLUSTERS int "Maximum number of clusters in a zone" depends on TIPC_ADVANCED diff --git a/net/tipc/Makefile b/net/tipc/Makefile index dceb7027946c..3d936f0560c7 100644 --- a/net/tipc/Makefile +++ b/net/tipc/Makefile @@ -8,6 +8,6 @@ tipc-y += addr.o bcast.o bearer.o config.o cluster.o \ core.o handler.o link.o discover.o msg.o \ name_distr.o subscr.o name_table.o net.o \ netlink.o node.o node_subscr.o port.o ref.o \ - socket.o user_reg.o zone.o dbg.o eth_media.o + socket.o user_reg.o dbg.o eth_media.o # End of file diff --git a/net/tipc/addr.c b/net/tipc/addr.c index 886715a75259..3d0f97da5b5f 100644 --- a/net/tipc/addr.c +++ b/net/tipc/addr.c @@ -35,8 +35,6 @@ */ #include "core.h" -#include "addr.h" -#include "zone.h" #include "cluster.h" /** @@ -61,8 +59,6 @@ int tipc_addr_domain_valid(u32 addr) return 0; if (c > tipc_max_clusters) return 0; - if (z > tipc_max_zones) - return 0; if (n && (!z || !c)) return 0; diff --git a/net/tipc/cluster.c b/net/tipc/cluster.c index 405be87157ba..996b2b67687e 100644 --- a/net/tipc/cluster.c +++ b/net/tipc/cluster.c @@ -47,7 +47,6 @@ u32 tipc_highest_allowed_slave = 0; struct cluster *tipc_cltr_create(u32 addr) { - struct _zone *z_ptr; struct cluster *c_ptr; int max_nodes; @@ -75,18 +74,7 @@ struct cluster *tipc_cltr_create(u32 addr) c_ptr->highest_slave = LOWEST_SLAVE - 1; c_ptr->highest_node = 0; - z_ptr = tipc_zone_find(tipc_zone(addr)); - if (!z_ptr) { - z_ptr = tipc_zone_create(addr); - } - if (!z_ptr) { - kfree(c_ptr->nodes); - kfree(c_ptr); - return NULL; - } - - tipc_zone_attach_cluster(z_ptr, c_ptr); - c_ptr->owner = z_ptr; + tipc_net.clusters[1] = c_ptr; return c_ptr; } diff --git a/net/tipc/cluster.h b/net/tipc/cluster.h index 32636d98c9c6..21493f7beb95 100644 --- a/net/tipc/cluster.h +++ b/net/tipc/cluster.h @@ -38,14 +38,13 @@ #define _TIPC_CLUSTER_H #include "addr.h" -#include "zone.h" +#include "net.h" #define LOWEST_SLAVE 2048u /** * struct cluster - TIPC cluster structure * @addr: network address of cluster - * @owner: pointer to zone that cluster belongs to * @nodes: array of pointers to all nodes within cluster * @highest_node: id of highest numbered node within cluster * @highest_slave: (used for secondary node support) @@ -53,7 +52,6 @@ struct cluster { u32 addr; - struct _zone *owner; struct tipc_node **nodes; u32 highest_node; u32 highest_slave; @@ -82,11 +80,9 @@ void tipc_cltr_bcast_lost_route(struct cluster *c_ptr, u32 dest, u32 lo, u32 hi) static inline struct cluster *tipc_cltr_find(u32 addr) { - struct _zone *z_ptr = tipc_zone_find(addr); - - if (z_ptr) - return z_ptr->clusters[1]; - return NULL; + if (!in_own_cluster(addr)) + return NULL; + return tipc_net.clusters[1]; } #endif diff --git a/net/tipc/config.c b/net/tipc/config.c index bdde39f0436b..8de97ddb0427 100644 --- a/net/tipc/config.c +++ b/net/tipc/config.c @@ -269,25 +269,6 @@ static struct sk_buff *cfg_set_max_ports(void) return tipc_cfg_reply_none(); } -static struct sk_buff *cfg_set_max_zones(void) -{ - u32 value; - - if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_UNSIGNED)) - return tipc_cfg_reply_error_string(TIPC_CFG_TLV_ERROR); - value = ntohl(*(__be32 *)TLV_DATA(req_tlv_area)); - if (value == tipc_max_zones) - return tipc_cfg_reply_none(); - if (value != delimit(value, 1, 255)) - return tipc_cfg_reply_error_string(TIPC_CFG_INVALID_VALUE - " (max zones must be 1-255)"); - if (tipc_mode == TIPC_NET_MODE) - return tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED - " (cannot change max zones once TIPC has joined a network)"); - tipc_max_zones = value; - return tipc_cfg_reply_none(); -} - static struct sk_buff *cfg_set_max_clusters(void) { u32 value; @@ -452,9 +433,6 @@ struct sk_buff *tipc_cfg_do_cmd(u32 orig_node, u16 cmd, const void *request_area case TIPC_CMD_SET_MAX_SUBSCR: rep_tlv_buf = cfg_set_max_subscriptions(); break; - case TIPC_CMD_SET_MAX_ZONES: - rep_tlv_buf = cfg_set_max_zones(); - break; case TIPC_CMD_SET_MAX_CLUSTERS: rep_tlv_buf = cfg_set_max_clusters(); break; @@ -479,9 +457,6 @@ struct sk_buff *tipc_cfg_do_cmd(u32 orig_node, u16 cmd, const void *request_area case TIPC_CMD_GET_MAX_SUBSCR: rep_tlv_buf = tipc_cfg_reply_unsigned(tipc_max_subscriptions); break; - case TIPC_CMD_GET_MAX_ZONES: - rep_tlv_buf = tipc_cfg_reply_unsigned(tipc_max_zones); - break; case TIPC_CMD_GET_MAX_CLUSTERS: rep_tlv_buf = tipc_cfg_reply_unsigned(tipc_max_clusters); break; @@ -498,6 +473,11 @@ struct sk_buff *tipc_cfg_do_cmd(u32 orig_node, u16 cmd, const void *request_area rep_tlv_buf = tipc_cfg_reply_error_string(TIPC_CFG_NOT_NET_ADMIN); break; + case TIPC_CMD_SET_MAX_ZONES: + case TIPC_CMD_GET_MAX_ZONES: + rep_tlv_buf = tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED + " (obsolete command)"); + break; default: rep_tlv_buf = tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED " (unknown command)"); diff --git a/net/tipc/core.c b/net/tipc/core.c index f5d62c174de2..13946331bd4d 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -48,10 +48,6 @@ #include "config.h" -#ifndef CONFIG_TIPC_ZONES -#define CONFIG_TIPC_ZONES 3 -#endif - #ifndef CONFIG_TIPC_CLUSTERS #define CONFIG_TIPC_CLUSTERS 1 #endif @@ -84,7 +80,6 @@ const char tipc_alphabet[] = /* configurable TIPC parameters */ u32 tipc_own_addr; -int tipc_max_zones; int tipc_max_clusters; int tipc_max_nodes; int tipc_max_slaves; @@ -209,7 +204,6 @@ static int __init tipc_init(void) tipc_max_publications = 10000; tipc_max_subscriptions = 2000; tipc_max_ports = CONFIG_TIPC_PORTS; - tipc_max_zones = CONFIG_TIPC_ZONES; tipc_max_clusters = CONFIG_TIPC_CLUSTERS; tipc_max_nodes = CONFIG_TIPC_NODES; tipc_max_slaves = CONFIG_TIPC_SLAVE_NODES; diff --git a/net/tipc/core.h b/net/tipc/core.h index ca7e171c1043..9403a226a570 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -184,7 +184,6 @@ void tipc_dump_dbg(struct print_buf *, const char *fmt, ...); */ extern u32 tipc_own_addr; -extern int tipc_max_zones; extern int tipc_max_clusters; extern int tipc_max_nodes; extern int tipc_max_slaves; diff --git a/net/tipc/net.c b/net/tipc/net.c index c2b4b86c2e6a..a25f8bb1e1d9 100644 --- a/net/tipc/net.c +++ b/net/tipc/net.c @@ -36,7 +36,6 @@ #include "core.h" #include "net.h" -#include "zone.h" #include "name_table.h" #include "name_distr.h" #include "subscr.h" @@ -111,46 +110,56 @@ */ DEFINE_RWLOCK(tipc_net_lock); -static struct _zone *tipc_zones[256] = { NULL, }; -struct network tipc_net = { tipc_zones }; +struct network tipc_net; struct tipc_node *tipc_net_select_remote_node(u32 addr, u32 ref) { - return tipc_zone_select_remote_node(tipc_net.zones[tipc_zone(addr)], addr, ref); + struct cluster *c_ptr; + + c_ptr = tipc_net.clusters[1]; + if (!c_ptr) + return NULL; + return tipc_cltr_select_node(c_ptr, ref); } u32 tipc_net_select_router(u32 addr, u32 ref) { - return tipc_zone_select_router(tipc_net.zones[tipc_zone(addr)], addr, ref); + struct cluster *c_ptr; + + c_ptr = tipc_net.clusters[1]; + if (!c_ptr) + return 0; + return tipc_cltr_select_router(c_ptr, ref); } void tipc_net_remove_as_router(u32 router) { - u32 z_num; + u32 c_num; - for (z_num = 1; z_num <= tipc_max_zones; z_num++) { - if (!tipc_net.zones[z_num]) + for (c_num = 1; c_num <= tipc_max_clusters; c_num++) { + if (!tipc_net.clusters[c_num]) continue; - tipc_zone_remove_as_router(tipc_net.zones[z_num], router); + tipc_cltr_remove_as_router(tipc_net.clusters[c_num], router); } } void tipc_net_send_external_routes(u32 dest) { - u32 z_num; + u32 c_num; - for (z_num = 1; z_num <= tipc_max_zones; z_num++) { - if (tipc_net.zones[z_num]) - tipc_zone_send_external_routes(tipc_net.zones[z_num], dest); + for (c_num = 1; c_num <= tipc_max_clusters; c_num++) { + if (tipc_net.clusters[c_num]) + tipc_cltr_send_ext_routes(tipc_net.clusters[c_num], + dest); } } static void net_stop(void) { - u32 z_num; + u32 c_num; - for (z_num = 1; z_num <= tipc_max_zones; z_num++) - tipc_zone_delete(tipc_net.zones[z_num]); + for (c_num = 1; c_num <= tipc_max_clusters; c_num++) + tipc_cltr_delete(tipc_net.clusters[c_num]); } static void net_route_named_msg(struct sk_buff *buf) diff --git a/net/tipc/net.h b/net/tipc/net.h index de2b9ad8f646..786c94007470 100644 --- a/net/tipc/net.h +++ b/net/tipc/net.h @@ -37,15 +37,17 @@ #ifndef _TIPC_NET_H #define _TIPC_NET_H -struct _zone; +struct cluster; /** * struct network - TIPC network structure - * @zones: array of pointers to all zones within network + * @clusters: array of pointers to all clusters within zone + * @links: number of (unicast) links to cluster */ struct network { - struct _zone **zones; + struct cluster *clusters[2]; /* currently limited to just 1 cluster */ + u32 links; }; diff --git a/net/tipc/node.c b/net/tipc/node.c index df71dfc3a9ae..c20bd851a44a 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -257,7 +257,7 @@ struct tipc_node *tipc_node_attach_link(struct link *l_ptr) if (!n_ptr->links[bearer_id]) { n_ptr->links[bearer_id] = l_ptr; - tipc_net.zones[tipc_zone(l_ptr->addr)]->links++; + tipc_net.links++; n_ptr->link_cnt++; return n_ptr; } @@ -271,7 +271,7 @@ struct tipc_node *tipc_node_attach_link(struct link *l_ptr) void tipc_node_detach_link(struct tipc_node *n_ptr, struct link *l_ptr) { n_ptr->links[l_ptr->b_ptr->identity] = NULL; - tipc_net.zones[tipc_zone(l_ptr->addr)]->links--; + tipc_net.links--; n_ptr->link_cnt--; } @@ -656,8 +656,7 @@ struct sk_buff *tipc_node_get_links(const void *req_tlv_area, int req_tlv_space) /* Get space for all unicast links + multicast link */ - payload_size = TLV_SPACE(sizeof(link_info)) * - (tipc_net.zones[tipc_zone(tipc_own_addr)]->links + 1); + payload_size = TLV_SPACE(sizeof(link_info)) * (tipc_net.links + 1); if (payload_size > 32768u) { read_unlock_bh(&tipc_net_lock); return tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED diff --git a/net/tipc/node.h b/net/tipc/node.h index fff331b2d26c..7bfaf5e8c201 100644 --- a/net/tipc/node.h +++ b/net/tipc/node.h @@ -38,7 +38,6 @@ #define _TIPC_NODE_H #include "node_subscr.h" -#include "addr.h" #include "cluster.h" #include "bearer.h" diff --git a/net/tipc/zone.c b/net/tipc/zone.c deleted file mode 100644 index 1b61ca8c48ef..000000000000 --- a/net/tipc/zone.c +++ /dev/null @@ -1,159 +0,0 @@ -/* - * net/tipc/zone.c: TIPC zone management routines - * - * Copyright (c) 2000-2006, Ericsson AB - * Copyright (c) 2005, Wind River Systems - * All rights reserved. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions are met: - * - * 1. Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * 2. Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * 3. Neither the names of the copyright holders nor the names of its - * contributors may be used to endorse or promote products derived from - * this software without specific prior written permission. - * - * Alternatively, this software may be distributed under the terms of the - * GNU General Public License ("GPL") version 2 as published by the Free - * Software Foundation. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" - * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE - * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE - * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE - * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR - * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF - * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS - * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN - * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) - * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE - * POSSIBILITY OF SUCH DAMAGE. - */ - -#include "core.h" -#include "zone.h" -#include "cluster.h" -#include "node.h" - -struct _zone *tipc_zone_create(u32 addr) -{ - struct _zone *z_ptr; - u32 z_num; - - if (!tipc_addr_domain_valid(addr)) { - err("Zone creation failed, invalid domain 0x%x\n", addr); - return NULL; - } - - z_ptr = kzalloc(sizeof(*z_ptr), GFP_ATOMIC); - if (!z_ptr) { - warn("Zone creation failed, insufficient memory\n"); - return NULL; - } - - z_num = tipc_zone(addr); - z_ptr->addr = tipc_addr(z_num, 0, 0); - tipc_net.zones[z_num] = z_ptr; - return z_ptr; -} - -void tipc_zone_delete(struct _zone *z_ptr) -{ - u32 c_num; - - if (!z_ptr) - return; - for (c_num = 1; c_num <= tipc_max_clusters; c_num++) { - tipc_cltr_delete(z_ptr->clusters[c_num]); - } - kfree(z_ptr); -} - -void tipc_zone_attach_cluster(struct _zone *z_ptr, struct cluster *c_ptr) -{ - u32 c_num = tipc_cluster(c_ptr->addr); - - assert(c_ptr->addr); - assert(c_num <= tipc_max_clusters); - assert(z_ptr->clusters[c_num] == NULL); - z_ptr->clusters[c_num] = c_ptr; -} - -void tipc_zone_remove_as_router(struct _zone *z_ptr, u32 router) -{ - u32 c_num; - - for (c_num = 1; c_num <= tipc_max_clusters; c_num++) { - if (z_ptr->clusters[c_num]) { - tipc_cltr_remove_as_router(z_ptr->clusters[c_num], - router); - } - } -} - -void tipc_zone_send_external_routes(struct _zone *z_ptr, u32 dest) -{ - u32 c_num; - - for (c_num = 1; c_num <= tipc_max_clusters; c_num++) { - if (z_ptr->clusters[c_num]) { - if (in_own_cluster(z_ptr->addr)) - continue; - tipc_cltr_send_ext_routes(z_ptr->clusters[c_num], dest); - } - } -} - -struct tipc_node *tipc_zone_select_remote_node(struct _zone *z_ptr, u32 addr, u32 ref) -{ - struct cluster *c_ptr; - struct tipc_node *n_ptr; - u32 c_num; - - if (!z_ptr) - return NULL; - c_ptr = z_ptr->clusters[tipc_cluster(addr)]; - if (!c_ptr) - return NULL; - n_ptr = tipc_cltr_select_node(c_ptr, ref); - if (n_ptr) - return n_ptr; - - /* Links to any other clusters within this zone ? */ - for (c_num = 1; c_num <= tipc_max_clusters; c_num++) { - c_ptr = z_ptr->clusters[c_num]; - if (!c_ptr) - return NULL; - n_ptr = tipc_cltr_select_node(c_ptr, ref); - if (n_ptr) - return n_ptr; - } - return NULL; -} - -u32 tipc_zone_select_router(struct _zone *z_ptr, u32 addr, u32 ref) -{ - struct cluster *c_ptr; - u32 c_num; - u32 router; - - if (!z_ptr) - return 0; - c_ptr = z_ptr->clusters[tipc_cluster(addr)]; - router = c_ptr ? tipc_cltr_select_router(c_ptr, ref) : 0; - if (router) - return router; - - /* Links to any other clusters within the zone? */ - for (c_num = 1; c_num <= tipc_max_clusters; c_num++) { - c_ptr = z_ptr->clusters[c_num]; - router = c_ptr ? tipc_cltr_select_router(c_ptr, ref) : 0; - if (router) - return router; - } - return 0; -} diff --git a/net/tipc/zone.h b/net/tipc/zone.h deleted file mode 100644 index bd1c20ce9d06..000000000000 --- a/net/tipc/zone.h +++ /dev/null @@ -1,70 +0,0 @@ -/* - * net/tipc/zone.h: Include file for TIPC zone management routines - * - * Copyright (c) 2000-2006, Ericsson AB - * Copyright (c) 2005-2006, Wind River Systems - * All rights reserved. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions are met: - * - * 1. Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * 2. Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * 3. Neither the names of the copyright holders nor the names of its - * contributors may be used to endorse or promote products derived from - * this software without specific prior written permission. - * - * Alternatively, this software may be distributed under the terms of the - * GNU General Public License ("GPL") version 2 as published by the Free - * Software Foundation. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" - * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE - * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE - * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE - * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR - * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF - * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS - * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN - * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) - * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE - * POSSIBILITY OF SUCH DAMAGE. - */ - -#ifndef _TIPC_ZONE_H -#define _TIPC_ZONE_H - -#include "node_subscr.h" -#include "net.h" - - -/** - * struct _zone - TIPC zone structure - * @addr: network address of zone - * @clusters: array of pointers to all clusters within zone - * @links: number of (unicast) links to zone - */ - -struct _zone { - u32 addr; - struct cluster *clusters[2]; /* currently limited to just 1 cluster */ - u32 links; -}; - -struct tipc_node *tipc_zone_select_remote_node(struct _zone *z_ptr, u32 addr, u32 ref); -u32 tipc_zone_select_router(struct _zone *z_ptr, u32 addr, u32 ref); -void tipc_zone_remove_as_router(struct _zone *z_ptr, u32 router); -void tipc_zone_send_external_routes(struct _zone *z_ptr, u32 dest); -struct _zone *tipc_zone_create(u32 addr); -void tipc_zone_delete(struct _zone *z_ptr); -void tipc_zone_attach_cluster(struct _zone *z_ptr, struct cluster *c_ptr); - -static inline struct _zone *tipc_zone_find(u32 addr) -{ - return tipc_net.zones[tipc_zone(addr)]; -} - -#endif -- cgit v1.2.3 From 08c80e9a031df0a8f0269477a32f5eae47d7a146 Mon Sep 17 00:00:00 2001 From: Allan Stephens Date: Fri, 31 Dec 2010 18:59:17 +0000 Subject: tipc: Remove prototype code for supporting slave nodes Simplifies routines and data structures that were intended to allow TIPC to support slave nodes (i.e. nodes that did not have links to all of the other nodes in its cluster, forcing TIPC to route messages that it could not deliver directly through a non-slave node). Currently, TIPC supports only networks containing non-slave nodes, so this code is unnecessary. Note: The latest edition of the TIPC 2.0 Specification has eliminated the concept of slave nodes entirely. Signed-off-by: Allan Stephens Signed-off-by: Paul Gortmaker Signed-off-by: David S. Miller --- include/linux/tipc_config.h | 4 +- net/tipc/addr.c | 2 - net/tipc/addr.h | 10 --- net/tipc/cluster.c | 166 ++++++-------------------------------------- net/tipc/cluster.h | 7 -- net/tipc/config.c | 21 +----- net/tipc/core.c | 6 -- net/tipc/core.h | 1 - net/tipc/discover.c | 4 -- net/tipc/msg.h | 2 +- net/tipc/node.c | 59 ++++------------ net/tipc/port.c | 5 +- 12 files changed, 40 insertions(+), 247 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tipc_config.h b/include/linux/tipc_config.h index fa3aeaafeab1..dcc2b8796d0a 100644 --- a/include/linux/tipc_config.h +++ b/include/linux/tipc_config.h @@ -97,7 +97,7 @@ #define TIPC_CMD_GET_MAX_ZONES 0x4007 /* obsoleted */ #define TIPC_CMD_GET_MAX_CLUSTERS 0x4008 /* tx none, rx unsigned */ #define TIPC_CMD_GET_MAX_NODES 0x4009 /* tx none, rx unsigned */ -#define TIPC_CMD_GET_MAX_SLAVES 0x400A /* tx none, rx unsigned */ +#define TIPC_CMD_GET_MAX_SLAVES 0x400A /* obsoleted */ #define TIPC_CMD_GET_NETID 0x400B /* tx none, rx unsigned */ #define TIPC_CMD_ENABLE_BEARER 0x4101 /* tx bearer_config, rx none */ @@ -133,7 +133,7 @@ #define TIPC_CMD_SET_MAX_ZONES 0x8007 /* obsoleted */ #define TIPC_CMD_SET_MAX_CLUSTERS 0x8008 /* tx unsigned, rx none */ #define TIPC_CMD_SET_MAX_NODES 0x8009 /* tx unsigned, rx none */ -#define TIPC_CMD_SET_MAX_SLAVES 0x800A /* tx unsigned, rx none */ +#define TIPC_CMD_SET_MAX_SLAVES 0x800A /* obsoleted */ #define TIPC_CMD_SET_NETID 0x800B /* tx unsigned, rx none */ /* diff --git a/net/tipc/addr.c b/net/tipc/addr.c index 3d0f97da5b5f..8823e03e52e0 100644 --- a/net/tipc/addr.c +++ b/net/tipc/addr.c @@ -53,8 +53,6 @@ int tipc_addr_domain_valid(u32 addr) u32 z = tipc_zone(addr); u32 max_nodes = tipc_max_nodes; - if (is_slave(addr)) - max_nodes = LOWEST_SLAVE + tipc_max_slaves; if (n > max_nodes) return 0; if (c > tipc_max_clusters) diff --git a/net/tipc/addr.h b/net/tipc/addr.h index c1cc5724d8cc..a16c6c87208e 100644 --- a/net/tipc/addr.h +++ b/net/tipc/addr.h @@ -57,16 +57,6 @@ static inline int in_own_cluster(u32 addr) return !((addr ^ tipc_own_addr) >> 12); } -static inline int is_slave(u32 addr) -{ - return addr & 0x800; -} - -static inline int may_route(u32 addr) -{ - return(addr ^ tipc_own_addr) >> 11; -} - /** * addr_domain - convert 2-bit scope value to equivalent message lookup domain * diff --git a/net/tipc/cluster.c b/net/tipc/cluster.c index 996b2b67687e..6bc9f07be945 100644 --- a/net/tipc/cluster.c +++ b/net/tipc/cluster.c @@ -43,7 +43,6 @@ static void tipc_cltr_multicast(struct cluster *c_ptr, struct sk_buff *buf, struct tipc_node **tipc_local_nodes = NULL; struct tipc_node_map tipc_cltr_bcast_nodes = {0,{0,}}; -u32 tipc_highest_allowed_slave = 0; struct cluster *tipc_cltr_create(u32 addr) { @@ -57,10 +56,7 @@ struct cluster *tipc_cltr_create(u32 addr) } c_ptr->addr = tipc_addr(tipc_zone(addr), tipc_cluster(addr), 0); - if (in_own_cluster(addr)) - max_nodes = LOWEST_SLAVE + tipc_max_slaves; - else - max_nodes = tipc_max_nodes + 1; + max_nodes = tipc_max_nodes + 1; c_ptr->nodes = kcalloc(max_nodes + 1, sizeof(void*), GFP_ATOMIC); if (c_ptr->nodes == NULL) { @@ -71,7 +67,6 @@ struct cluster *tipc_cltr_create(u32 addr) if (in_own_cluster(addr)) tipc_local_nodes = c_ptr->nodes; - c_ptr->highest_slave = LOWEST_SLAVE - 1; c_ptr->highest_node = 0; tipc_net.clusters[1] = c_ptr; @@ -87,9 +82,6 @@ void tipc_cltr_delete(struct cluster *c_ptr) for (n_num = 1; n_num <= c_ptr->highest_node; n_num++) { tipc_node_delete(c_ptr->nodes[n_num]); } - for (n_num = LOWEST_SLAVE; n_num <= c_ptr->highest_slave; n_num++) { - tipc_node_delete(c_ptr->nodes[n_num]); - } kfree(c_ptr->nodes); kfree(c_ptr); } @@ -100,8 +92,6 @@ void tipc_cltr_attach_node(struct cluster *c_ptr, struct tipc_node *n_ptr) u32 n_num = tipc_node(n_ptr->addr); u32 max_n_num = tipc_max_nodes; - if (in_own_cluster(n_ptr->addr)) - max_n_num = tipc_highest_allowed_slave; assert(n_num > 0); assert(n_num <= max_n_num); assert(c_ptr->nodes[n_num] == NULL); @@ -237,41 +227,6 @@ void tipc_cltr_bcast_lost_route(struct cluster *c_ptr, u32 dest, } } -void tipc_cltr_send_slave_routes(struct cluster *c_ptr, u32 dest) -{ - struct sk_buff *buf; - struct tipc_msg *msg; - u32 highest = c_ptr->highest_slave; - u32 n_num; - int send = 0; - - assert(!is_slave(dest)); - assert(in_own_cluster(dest)); - assert(in_own_cluster(c_ptr->addr)); - if (highest <= LOWEST_SLAVE) - return; - buf = tipc_cltr_prepare_routing_msg(highest - LOWEST_SLAVE + 1, - c_ptr->addr); - if (buf) { - msg = buf_msg(buf); - msg_set_remote_node(msg, c_ptr->addr); - msg_set_type(msg, SLAVE_ROUTING_TABLE); - for (n_num = LOWEST_SLAVE; n_num <= highest; n_num++) { - if (c_ptr->nodes[n_num] && - tipc_node_has_active_links(c_ptr->nodes[n_num])) { - send = 1; - msg_set_dataoctet(msg, n_num); - } - } - if (send) - tipc_link_send(buf, dest, dest); - else - buf_discard(buf); - } else { - warn("Memory squeeze: broadcast of lost route failed\n"); - } -} - void tipc_cltr_send_ext_routes(struct cluster *c_ptr, u32 dest) { struct sk_buff *buf; @@ -282,7 +237,6 @@ void tipc_cltr_send_ext_routes(struct cluster *c_ptr, u32 dest) if (in_own_cluster(c_ptr->addr)) return; - assert(!is_slave(dest)); assert(in_own_cluster(dest)); highest = c_ptr->highest_node; buf = tipc_cltr_prepare_routing_msg(highest + 1, c_ptr->addr); @@ -306,37 +260,6 @@ void tipc_cltr_send_ext_routes(struct cluster *c_ptr, u32 dest) } } -void tipc_cltr_send_local_routes(struct cluster *c_ptr, u32 dest) -{ - struct sk_buff *buf; - struct tipc_msg *msg; - u32 highest = c_ptr->highest_node; - u32 n_num; - int send = 0; - - assert(is_slave(dest)); - assert(in_own_cluster(c_ptr->addr)); - buf = tipc_cltr_prepare_routing_msg(highest, c_ptr->addr); - if (buf) { - msg = buf_msg(buf); - msg_set_remote_node(msg, c_ptr->addr); - msg_set_type(msg, LOCAL_ROUTING_TABLE); - for (n_num = 1; n_num <= highest; n_num++) { - if (c_ptr->nodes[n_num] && - tipc_node_has_active_links(c_ptr->nodes[n_num])) { - send = 1; - msg_set_dataoctet(msg, n_num); - } - } - if (send) - tipc_link_send(buf, dest, dest); - else - buf_discard(buf); - } else { - warn("Memory squeeze: broadcast of local route failed\n"); - } -} - void tipc_cltr_recv_routing_table(struct sk_buff *buf) { struct tipc_msg *msg = buf_msg(buf); @@ -366,8 +289,6 @@ void tipc_cltr_recv_routing_table(struct sk_buff *buf) c_num = tipc_cluster(rem_node); switch (msg_type(msg)) { - case LOCAL_ROUTING_TABLE: - assert(is_slave(tipc_own_addr)); case EXT_ROUTING_TABLE: for (n_num = 1; n_num < table_size; n_num++) { if (node_table[n_num]) { @@ -382,29 +303,10 @@ void tipc_cltr_recv_routing_table(struct sk_buff *buf) } break; case SLAVE_ROUTING_TABLE: - assert(!is_slave(tipc_own_addr)); assert(in_own_cluster(c_ptr->addr)); - for (n_num = 1; n_num < table_size; n_num++) { - if (node_table[n_num]) { - u32 slave_num = n_num + LOWEST_SLAVE; - u32 addr = tipc_addr(z_num, c_num, slave_num); - n_ptr = c_ptr->nodes[slave_num]; - if (!n_ptr) { - n_ptr = tipc_node_create(addr); - } - if (n_ptr) - tipc_node_add_router(n_ptr, router); - } - } break; case ROUTE_ADDITION: - if (!is_slave(tipc_own_addr)) { - assert(!in_own_cluster(c_ptr->addr) || - is_slave(rem_node)); - } else { - assert(in_own_cluster(c_ptr->addr) && - !is_slave(rem_node)); - } + assert(!in_own_cluster(c_ptr->addr)); n_ptr = c_ptr->nodes[tipc_node(rem_node)]; if (!n_ptr) n_ptr = tipc_node_create(rem_node); @@ -412,13 +314,7 @@ void tipc_cltr_recv_routing_table(struct sk_buff *buf) tipc_node_add_router(n_ptr, router); break; case ROUTE_REMOVAL: - if (!is_slave(tipc_own_addr)) { - assert(!in_own_cluster(c_ptr->addr) || - is_slave(rem_node)); - } else { - assert(in_own_cluster(c_ptr->addr) && - !is_slave(rem_node)); - } + assert(!in_own_cluster(c_ptr->addr)); n_ptr = c_ptr->nodes[tipc_node(rem_node)]; if (n_ptr) tipc_node_remove_router(n_ptr, router); @@ -431,22 +327,12 @@ void tipc_cltr_recv_routing_table(struct sk_buff *buf) void tipc_cltr_remove_as_router(struct cluster *c_ptr, u32 router) { - u32 start_entry; - u32 tstop; u32 n_num; - if (is_slave(router)) - return; /* Slave nodes can not be routers */ - - if (in_own_cluster(c_ptr->addr)) { - start_entry = LOWEST_SLAVE; - tstop = c_ptr->highest_slave; - } else { - start_entry = 1; - tstop = c_ptr->highest_node; - } + if (in_own_cluster(c_ptr->addr)) + return; - for (n_num = start_entry; n_num <= tstop; n_num++) { + for (n_num = 1; n_num <= c_ptr->highest_node; n_num++) { if (c_ptr->nodes[n_num]) { tipc_node_remove_router(c_ptr->nodes[n_num], router); } @@ -466,13 +352,11 @@ static void tipc_cltr_multicast(struct cluster *c_ptr, struct sk_buff *buf, u32 tstop; assert(lower <= upper); - assert(((lower >= 1) && (lower <= tipc_max_nodes)) || - ((lower >= LOWEST_SLAVE) && (lower <= tipc_highest_allowed_slave))); - assert(((upper >= 1) && (upper <= tipc_max_nodes)) || - ((upper >= LOWEST_SLAVE) && (upper <= tipc_highest_allowed_slave))); + assert((lower >= 1) && (lower <= tipc_max_nodes)); + assert((upper >= 1) && (upper <= tipc_max_nodes)); assert(in_own_cluster(c_ptr->addr)); - tstop = is_slave(upper) ? c_ptr->highest_slave : c_ptr->highest_node; + tstop = c_ptr->highest_node; if (tstop > upper) tstop = upper; for (n_num = lower; n_num <= tstop; n_num++) { @@ -498,32 +382,23 @@ void tipc_cltr_broadcast(struct sk_buff *buf) struct cluster *c_ptr; struct tipc_node *n_ptr; u32 n_num; - u32 tstart; - u32 tstop; - u32 node_type; if (tipc_mode == TIPC_NET_MODE) { c_ptr = tipc_cltr_find(tipc_own_addr); assert(in_own_cluster(c_ptr->addr)); /* For now */ - /* Send to standard nodes, then repeat loop sending to slaves */ - tstart = 1; - tstop = c_ptr->highest_node; - for (node_type = 1; node_type <= 2; node_type++) { - for (n_num = tstart; n_num <= tstop; n_num++) { - n_ptr = c_ptr->nodes[n_num]; - if (n_ptr && tipc_node_has_active_links(n_ptr)) { - buf_copy = skb_copy(buf, GFP_ATOMIC); - if (buf_copy == NULL) - goto exit; - msg_set_destnode(buf_msg(buf_copy), - n_ptr->addr); - tipc_link_send(buf_copy, n_ptr->addr, - n_ptr->addr); - } + /* Send to nodes */ + for (n_num = 1; n_num <= c_ptr->highest_node; n_num++) { + n_ptr = c_ptr->nodes[n_num]; + if (n_ptr && tipc_node_has_active_links(n_ptr)) { + buf_copy = skb_copy(buf, GFP_ATOMIC); + if (buf_copy == NULL) + goto exit; + msg_set_destnode(buf_msg(buf_copy), + n_ptr->addr); + tipc_link_send(buf_copy, n_ptr->addr, + n_ptr->addr); } - tstart = LOWEST_SLAVE; - tstop = c_ptr->highest_slave; } } exit: @@ -532,7 +407,6 @@ exit: int tipc_cltr_init(void) { - tipc_highest_allowed_slave = LOWEST_SLAVE + tipc_max_slaves; return tipc_cltr_create(tipc_own_addr) ? 0 : -ENOMEM; } diff --git a/net/tipc/cluster.h b/net/tipc/cluster.h index 21493f7beb95..aa1fd6ab4d11 100644 --- a/net/tipc/cluster.h +++ b/net/tipc/cluster.h @@ -40,26 +40,21 @@ #include "addr.h" #include "net.h" -#define LOWEST_SLAVE 2048u - /** * struct cluster - TIPC cluster structure * @addr: network address of cluster * @nodes: array of pointers to all nodes within cluster * @highest_node: id of highest numbered node within cluster - * @highest_slave: (used for secondary node support) */ struct cluster { u32 addr; struct tipc_node **nodes; u32 highest_node; - u32 highest_slave; }; extern struct tipc_node **tipc_local_nodes; -extern u32 tipc_highest_allowed_slave; extern struct tipc_node_map tipc_cltr_bcast_nodes; void tipc_cltr_remove_as_router(struct cluster *c_ptr, u32 router); @@ -70,12 +65,10 @@ void tipc_cltr_recv_routing_table(struct sk_buff *buf); struct cluster *tipc_cltr_create(u32 addr); void tipc_cltr_delete(struct cluster *c_ptr); void tipc_cltr_attach_node(struct cluster *c_ptr, struct tipc_node *n_ptr); -void tipc_cltr_send_slave_routes(struct cluster *c_ptr, u32 dest); void tipc_cltr_broadcast(struct sk_buff *buf); int tipc_cltr_init(void); void tipc_cltr_bcast_new_route(struct cluster *c_ptr, u32 dest, u32 lo, u32 hi); -void tipc_cltr_send_local_routes(struct cluster *c_ptr, u32 dest); void tipc_cltr_bcast_lost_route(struct cluster *c_ptr, u32 dest, u32 lo, u32 hi); static inline struct cluster *tipc_cltr_find(u32 addr) diff --git a/net/tipc/config.c b/net/tipc/config.c index 8de97ddb0427..05dc102300ae 100644 --- a/net/tipc/config.c +++ b/net/tipc/config.c @@ -301,19 +301,6 @@ static struct sk_buff *cfg_set_max_nodes(void) return tipc_cfg_reply_none(); } -static struct sk_buff *cfg_set_max_slaves(void) -{ - u32 value; - - if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_UNSIGNED)) - return tipc_cfg_reply_error_string(TIPC_CFG_TLV_ERROR); - value = ntohl(*(__be32 *)TLV_DATA(req_tlv_area)); - if (value != 0) - return tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED - " (max secondary nodes fixed at 0)"); - return tipc_cfg_reply_none(); -} - static struct sk_buff *cfg_set_netid(void) { u32 value; @@ -439,9 +426,6 @@ struct sk_buff *tipc_cfg_do_cmd(u32 orig_node, u16 cmd, const void *request_area case TIPC_CMD_SET_MAX_NODES: rep_tlv_buf = cfg_set_max_nodes(); break; - case TIPC_CMD_SET_MAX_SLAVES: - rep_tlv_buf = cfg_set_max_slaves(); - break; case TIPC_CMD_SET_NETID: rep_tlv_buf = cfg_set_netid(); break; @@ -463,9 +447,6 @@ struct sk_buff *tipc_cfg_do_cmd(u32 orig_node, u16 cmd, const void *request_area case TIPC_CMD_GET_MAX_NODES: rep_tlv_buf = tipc_cfg_reply_unsigned(tipc_max_nodes); break; - case TIPC_CMD_GET_MAX_SLAVES: - rep_tlv_buf = tipc_cfg_reply_unsigned(tipc_max_slaves); - break; case TIPC_CMD_GET_NETID: rep_tlv_buf = tipc_cfg_reply_unsigned(tipc_net_id); break; @@ -475,6 +456,8 @@ struct sk_buff *tipc_cfg_do_cmd(u32 orig_node, u16 cmd, const void *request_area break; case TIPC_CMD_SET_MAX_ZONES: case TIPC_CMD_GET_MAX_ZONES: + case TIPC_CMD_SET_MAX_SLAVES: + case TIPC_CMD_GET_MAX_SLAVES: rep_tlv_buf = tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED " (obsolete command)"); break; diff --git a/net/tipc/core.c b/net/tipc/core.c index 13946331bd4d..8b7af893971e 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -56,10 +56,6 @@ #define CONFIG_TIPC_NODES 255 #endif -#ifndef CONFIG_TIPC_SLAVE_NODES -#define CONFIG_TIPC_SLAVE_NODES 0 -#endif - #ifndef CONFIG_TIPC_PORTS #define CONFIG_TIPC_PORTS 8191 #endif @@ -82,7 +78,6 @@ const char tipc_alphabet[] = u32 tipc_own_addr; int tipc_max_clusters; int tipc_max_nodes; -int tipc_max_slaves; int tipc_max_ports; int tipc_max_subscriptions; int tipc_max_publications; @@ -206,7 +201,6 @@ static int __init tipc_init(void) tipc_max_ports = CONFIG_TIPC_PORTS; tipc_max_clusters = CONFIG_TIPC_CLUSTERS; tipc_max_nodes = CONFIG_TIPC_NODES; - tipc_max_slaves = CONFIG_TIPC_SLAVE_NODES; tipc_net_id = 4711; if ((res = tipc_core_start())) diff --git a/net/tipc/core.h b/net/tipc/core.h index 9403a226a570..8313a1689565 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -186,7 +186,6 @@ void tipc_dump_dbg(struct print_buf *, const char *fmt, ...); extern u32 tipc_own_addr; extern int tipc_max_clusters; extern int tipc_max_nodes; -extern int tipc_max_slaves; extern int tipc_max_ports; extern int tipc_max_subscriptions; extern int tipc_max_publications; diff --git a/net/tipc/discover.c b/net/tipc/discover.c index f2ce36baf42e..80799f6ba892 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -149,10 +149,6 @@ void tipc_disc_recv_msg(struct sk_buff *buf, struct bearer *b_ptr) } if (!tipc_in_scope(dest, tipc_own_addr)) return; - if (is_slave(tipc_own_addr) && is_slave(orig)) - return; - if (is_slave(orig) && !in_own_cluster(orig)) - return; if (in_own_cluster(orig)) { /* Always accept link here */ struct sk_buff *rbuf; diff --git a/net/tipc/msg.h b/net/tipc/msg.h index aee53864d7a0..c1b6217838e6 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -850,7 +850,7 @@ static inline void msg_set_dataoctet(struct tipc_msg *m, u32 pos) * Routing table message types */ #define EXT_ROUTING_TABLE 0 -#define LOCAL_ROUTING_TABLE 1 +#define LOCAL_ROUTING_TABLE 1 /* obsoleted */ #define SLAVE_ROUTING_TABLE 2 #define ROUTE_ADDITION 3 #define ROUTE_REMOVAL 4 diff --git a/net/tipc/node.c b/net/tipc/node.c index c20bd851a44a..8ffbdb33b2cb 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -333,8 +333,6 @@ static void node_established_contact(struct tipc_node *n_ptr) /* Syncronize broadcast acks */ n_ptr->bclink.acked = tipc_bclink_get_last_sent(); - if (is_slave(tipc_own_addr)) - return; if (!in_own_cluster(n_ptr->addr)) { /* Usage case 1 (see above) */ c_ptr = tipc_cltr_find(tipc_own_addr); @@ -347,13 +345,6 @@ static void node_established_contact(struct tipc_node *n_ptr) } c_ptr = n_ptr->owner; - if (is_slave(n_ptr->addr)) { - /* Usage case 2 (see above) */ - tipc_cltr_bcast_new_route(c_ptr, n_ptr->addr, 1, tipc_max_nodes); - tipc_cltr_send_local_routes(c_ptr, n_ptr->addr); - return; - } - if (n_ptr->bclink.supported) { tipc_nmap_add(&tipc_cltr_bcast_nodes, n_ptr->addr); if (n_ptr->addr < tipc_own_addr) @@ -362,9 +353,6 @@ static void node_established_contact(struct tipc_node *n_ptr) /* Case 3 (see above) */ tipc_net_send_external_routes(n_ptr->addr); - tipc_cltr_send_slave_routes(c_ptr, n_ptr->addr); - tipc_cltr_bcast_new_route(c_ptr, n_ptr->addr, LOWEST_SLAVE, - tipc_highest_allowed_slave); } static void node_cleanup_finished(unsigned long node_addr) @@ -404,33 +392,20 @@ static void node_lost_contact(struct tipc_node *n_ptr) } /* Update routing tables */ - if (is_slave(tipc_own_addr)) { - tipc_net_remove_as_router(n_ptr->addr); + if (!in_own_cluster(n_ptr->addr)) { + /* Case 4 (see above) */ + c_ptr = tipc_cltr_find(tipc_own_addr); + tipc_cltr_bcast_lost_route(c_ptr, n_ptr->addr, 1, + tipc_max_nodes); } else { - if (!in_own_cluster(n_ptr->addr)) { - /* Case 4 (see above) */ - c_ptr = tipc_cltr_find(tipc_own_addr); - tipc_cltr_bcast_lost_route(c_ptr, n_ptr->addr, 1, - tipc_max_nodes); - } else { - /* Case 5 (see above) */ - c_ptr = tipc_cltr_find(n_ptr->addr); - if (is_slave(n_ptr->addr)) { - tipc_cltr_bcast_lost_route(c_ptr, n_ptr->addr, 1, - tipc_max_nodes); - } else { - if (n_ptr->bclink.supported) { - tipc_nmap_remove(&tipc_cltr_bcast_nodes, - n_ptr->addr); - if (n_ptr->addr < tipc_own_addr) - tipc_own_tag--; - } - tipc_net_remove_as_router(n_ptr->addr); - tipc_cltr_bcast_lost_route(c_ptr, n_ptr->addr, - LOWEST_SLAVE, - tipc_highest_allowed_slave); - } + /* Case 5 (see above) */ + c_ptr = tipc_cltr_find(n_ptr->addr); + if (n_ptr->bclink.supported) { + tipc_nmap_remove(&tipc_cltr_bcast_nodes, n_ptr->addr); + if (n_ptr->addr < tipc_own_addr) + tipc_own_tag--; } + tipc_net_remove_as_router(n_ptr->addr); } if (tipc_node_has_active_routes(n_ptr)) return; @@ -482,7 +457,7 @@ struct tipc_node *tipc_node_select_next_hop(u32 addr, u32 selector) return n_ptr; /* Cluster local system nodes *must* have direct links */ - if (!is_slave(addr) && in_own_cluster(addr)) + if (in_own_cluster(addr)) return NULL; /* Look for cluster local router with direct link to node */ @@ -490,11 +465,6 @@ struct tipc_node *tipc_node_select_next_hop(u32 addr, u32 selector) if (router_addr) return tipc_node_select(router_addr, selector); - /* Slave nodes can only be accessed within own cluster via a - known router with direct link -- if no router was found,give up */ - if (is_slave(addr)) - return NULL; - /* Inter zone/cluster -- find any direct link to remote cluster */ addr = tipc_addr(tipc_zone(addr), tipc_cluster(addr), 0); n_ptr = tipc_net_select_remote_node(addr, selector); @@ -603,8 +573,7 @@ struct sk_buff *tipc_node_get_nodes(const void *req_tlv_area, int req_tlv_space) return tipc_cfg_reply_none(); } - /* For now, get space for all other nodes - (will need to modify this when slave nodes are supported */ + /* For now, get space for all other nodes */ payload_size = TLV_SPACE(sizeof(node_info)) * (tipc_max_nodes - 1); if (payload_size > 32768u) { diff --git a/net/tipc/port.c b/net/tipc/port.c index 7873283f4965..c033cb87b964 100644 --- a/net/tipc/port.c +++ b/net/tipc/port.c @@ -1110,10 +1110,7 @@ int tipc_connect2port(u32 ref, struct tipc_portid const *peer) msg_set_origport(msg, p_ptr->publ.ref); msg_set_transp_seqno(msg, 42); msg_set_type(msg, TIPC_CONN_MSG); - if (!may_route(peer->node)) - msg_set_hdr_sz(msg, SHORT_H_SIZE); - else - msg_set_hdr_sz(msg, LONG_H_SIZE); + msg_set_hdr_sz(msg, SHORT_H_SIZE); p_ptr->probing_interval = PROBING_INTERVAL; p_ptr->probing_state = CONFIRMED; -- cgit v1.2.3 From 51a8e4dee7653698ba4c6e7de71053665f075273 Mon Sep 17 00:00:00 2001 From: Allan Stephens Date: Fri, 31 Dec 2010 18:59:18 +0000 Subject: tipc: Remove prototype code for supporting inter-cluster routing Eliminates routines and data structures that were intended to allow TIPC to route messages to other clusters. Currently, TIPC supports only networks consisting of a single cluster within a single zone, so this code is unnecessary. Signed-off-by: Allan Stephens Signed-off-by: Paul Gortmaker Signed-off-by: David S. Miller --- include/linux/tipc_config.h | 5 - net/tipc/addr.h | 15 --- net/tipc/cluster.c | 279 +------------------------------------------- net/tipc/cluster.h | 8 -- net/tipc/link.c | 13 +-- net/tipc/msg.h | 7 +- net/tipc/net.c | 45 ------- net/tipc/net.h | 4 - net/tipc/node.c | 166 ++------------------------ net/tipc/node.h | 21 ---- 10 files changed, 15 insertions(+), 548 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tipc_config.h b/include/linux/tipc_config.h index dcc2b8796d0a..1f38df1202ba 100644 --- a/include/linux/tipc_config.h +++ b/include/linux/tipc_config.h @@ -254,11 +254,6 @@ struct tipc_link_create { struct tipc_media_addr peer_addr; char bearer_name[TIPC_MAX_BEARER_NAME]; }; - -struct tipc_route_info { - __u32 dest; - __u32 router; -}; #endif /* diff --git a/net/tipc/addr.h b/net/tipc/addr.h index a16c6c87208e..2490fadd0caf 100644 --- a/net/tipc/addr.h +++ b/net/tipc/addr.h @@ -37,21 +37,6 @@ #ifndef _TIPC_ADDR_H #define _TIPC_ADDR_H -static inline u32 own_node(void) -{ - return tipc_node(tipc_own_addr); -} - -static inline u32 own_cluster(void) -{ - return tipc_cluster(tipc_own_addr); -} - -static inline u32 own_zone(void) -{ - return tipc_zone(tipc_own_addr); -} - static inline int in_own_cluster(u32 addr) { return !((addr ^ tipc_own_addr) >> 12); diff --git a/net/tipc/cluster.c b/net/tipc/cluster.c index 6bc9f07be945..ba6f5bfa0cdb 100644 --- a/net/tipc/cluster.c +++ b/net/tipc/cluster.c @@ -38,9 +38,6 @@ #include "cluster.h" #include "link.h" -static void tipc_cltr_multicast(struct cluster *c_ptr, struct sk_buff *buf, - u32 lower, u32 upper); - struct tipc_node **tipc_local_nodes = NULL; struct tipc_node_map tipc_cltr_bcast_nodes = {0,{0,}}; @@ -65,8 +62,7 @@ struct cluster *tipc_cltr_create(u32 addr) return NULL; } - if (in_own_cluster(addr)) - tipc_local_nodes = c_ptr->nodes; + tipc_local_nodes = c_ptr->nodes; c_ptr->highest_node = 0; tipc_net.clusters[1] = c_ptr; @@ -100,278 +96,6 @@ void tipc_cltr_attach_node(struct cluster *c_ptr, struct tipc_node *n_ptr) c_ptr->highest_node = n_num; } -/** - * tipc_cltr_select_router - select router to a cluster - * - * Uses deterministic and fair algorithm. - */ - -u32 tipc_cltr_select_router(struct cluster *c_ptr, u32 ref) -{ - u32 n_num; - u32 ulim = c_ptr->highest_node; - u32 mask; - u32 tstart; - - assert(!in_own_cluster(c_ptr->addr)); - if (!ulim) - return 0; - - /* Start entry must be random */ - mask = tipc_max_nodes; - while (mask > ulim) - mask >>= 1; - tstart = ref & mask; - n_num = tstart; - - /* Lookup upwards with wrap-around */ - do { - if (tipc_node_is_up(c_ptr->nodes[n_num])) - break; - } while (++n_num <= ulim); - if (n_num > ulim) { - n_num = 1; - do { - if (tipc_node_is_up(c_ptr->nodes[n_num])) - break; - } while (++n_num < tstart); - if (n_num == tstart) - return 0; - } - assert(n_num <= ulim); - return tipc_node_select_router(c_ptr->nodes[n_num], ref); -} - -/** - * tipc_cltr_select_node - select destination node within a remote cluster - * - * Uses deterministic and fair algorithm. - */ - -struct tipc_node *tipc_cltr_select_node(struct cluster *c_ptr, u32 selector) -{ - u32 n_num; - u32 mask = tipc_max_nodes; - u32 start_entry; - - assert(!in_own_cluster(c_ptr->addr)); - if (!c_ptr->highest_node) - return NULL; - - /* Start entry must be random */ - while (mask > c_ptr->highest_node) { - mask >>= 1; - } - start_entry = (selector & mask) ? selector & mask : 1u; - assert(start_entry <= c_ptr->highest_node); - - /* Lookup upwards with wrap-around */ - for (n_num = start_entry; n_num <= c_ptr->highest_node; n_num++) { - if (tipc_node_has_active_links(c_ptr->nodes[n_num])) - return c_ptr->nodes[n_num]; - } - for (n_num = 1; n_num < start_entry; n_num++) { - if (tipc_node_has_active_links(c_ptr->nodes[n_num])) - return c_ptr->nodes[n_num]; - } - return NULL; -} - -/* - * Routing table management: See description in node.c - */ - -static struct sk_buff *tipc_cltr_prepare_routing_msg(u32 data_size, u32 dest) -{ - u32 size = INT_H_SIZE + data_size; - struct sk_buff *buf = tipc_buf_acquire(size); - struct tipc_msg *msg; - - if (buf) { - msg = buf_msg(buf); - memset((char *)msg, 0, size); - tipc_msg_init(msg, ROUTE_DISTRIBUTOR, 0, INT_H_SIZE, dest); - } - return buf; -} - -void tipc_cltr_bcast_new_route(struct cluster *c_ptr, u32 dest, - u32 lower, u32 upper) -{ - struct sk_buff *buf = tipc_cltr_prepare_routing_msg(0, c_ptr->addr); - struct tipc_msg *msg; - - if (buf) { - msg = buf_msg(buf); - msg_set_remote_node(msg, dest); - msg_set_type(msg, ROUTE_ADDITION); - tipc_cltr_multicast(c_ptr, buf, lower, upper); - } else { - warn("Memory squeeze: broadcast of new route failed\n"); - } -} - -void tipc_cltr_bcast_lost_route(struct cluster *c_ptr, u32 dest, - u32 lower, u32 upper) -{ - struct sk_buff *buf = tipc_cltr_prepare_routing_msg(0, c_ptr->addr); - struct tipc_msg *msg; - - if (buf) { - msg = buf_msg(buf); - msg_set_remote_node(msg, dest); - msg_set_type(msg, ROUTE_REMOVAL); - tipc_cltr_multicast(c_ptr, buf, lower, upper); - } else { - warn("Memory squeeze: broadcast of lost route failed\n"); - } -} - -void tipc_cltr_send_ext_routes(struct cluster *c_ptr, u32 dest) -{ - struct sk_buff *buf; - struct tipc_msg *msg; - u32 highest = c_ptr->highest_node; - u32 n_num; - int send = 0; - - if (in_own_cluster(c_ptr->addr)) - return; - assert(in_own_cluster(dest)); - highest = c_ptr->highest_node; - buf = tipc_cltr_prepare_routing_msg(highest + 1, c_ptr->addr); - if (buf) { - msg = buf_msg(buf); - msg_set_remote_node(msg, c_ptr->addr); - msg_set_type(msg, EXT_ROUTING_TABLE); - for (n_num = 1; n_num <= highest; n_num++) { - if (c_ptr->nodes[n_num] && - tipc_node_has_active_links(c_ptr->nodes[n_num])) { - send = 1; - msg_set_dataoctet(msg, n_num); - } - } - if (send) - tipc_link_send(buf, dest, dest); - else - buf_discard(buf); - } else { - warn("Memory squeeze: broadcast of external route failed\n"); - } -} - -void tipc_cltr_recv_routing_table(struct sk_buff *buf) -{ - struct tipc_msg *msg = buf_msg(buf); - struct cluster *c_ptr; - struct tipc_node *n_ptr; - unchar *node_table; - u32 table_size; - u32 router; - u32 rem_node = msg_remote_node(msg); - u32 z_num; - u32 c_num; - u32 n_num; - - c_ptr = tipc_cltr_find(rem_node); - if (!c_ptr) { - c_ptr = tipc_cltr_create(rem_node); - if (!c_ptr) { - buf_discard(buf); - return; - } - } - - node_table = buf->data + msg_hdr_sz(msg); - table_size = msg_size(msg) - msg_hdr_sz(msg); - router = msg_prevnode(msg); - z_num = tipc_zone(rem_node); - c_num = tipc_cluster(rem_node); - - switch (msg_type(msg)) { - case EXT_ROUTING_TABLE: - for (n_num = 1; n_num < table_size; n_num++) { - if (node_table[n_num]) { - u32 addr = tipc_addr(z_num, c_num, n_num); - n_ptr = c_ptr->nodes[n_num]; - if (!n_ptr) { - n_ptr = tipc_node_create(addr); - } - if (n_ptr) - tipc_node_add_router(n_ptr, router); - } - } - break; - case SLAVE_ROUTING_TABLE: - assert(in_own_cluster(c_ptr->addr)); - break; - case ROUTE_ADDITION: - assert(!in_own_cluster(c_ptr->addr)); - n_ptr = c_ptr->nodes[tipc_node(rem_node)]; - if (!n_ptr) - n_ptr = tipc_node_create(rem_node); - if (n_ptr) - tipc_node_add_router(n_ptr, router); - break; - case ROUTE_REMOVAL: - assert(!in_own_cluster(c_ptr->addr)); - n_ptr = c_ptr->nodes[tipc_node(rem_node)]; - if (n_ptr) - tipc_node_remove_router(n_ptr, router); - break; - default: - assert(!"Illegal routing manager message received\n"); - } - buf_discard(buf); -} - -void tipc_cltr_remove_as_router(struct cluster *c_ptr, u32 router) -{ - u32 n_num; - - if (in_own_cluster(c_ptr->addr)) - return; - - for (n_num = 1; n_num <= c_ptr->highest_node; n_num++) { - if (c_ptr->nodes[n_num]) { - tipc_node_remove_router(c_ptr->nodes[n_num], router); - } - } -} - -/** - * tipc_cltr_multicast - multicast message to local nodes - */ - -static void tipc_cltr_multicast(struct cluster *c_ptr, struct sk_buff *buf, - u32 lower, u32 upper) -{ - struct sk_buff *buf_copy; - struct tipc_node *n_ptr; - u32 n_num; - u32 tstop; - - assert(lower <= upper); - assert((lower >= 1) && (lower <= tipc_max_nodes)); - assert((upper >= 1) && (upper <= tipc_max_nodes)); - assert(in_own_cluster(c_ptr->addr)); - - tstop = c_ptr->highest_node; - if (tstop > upper) - tstop = upper; - for (n_num = lower; n_num <= tstop; n_num++) { - n_ptr = c_ptr->nodes[n_num]; - if (n_ptr && tipc_node_has_active_links(n_ptr)) { - buf_copy = skb_copy(buf, GFP_ATOMIC); - if (buf_copy == NULL) - break; - msg_set_destnode(buf_msg(buf_copy), n_ptr->addr); - tipc_link_send(buf_copy, n_ptr->addr, n_ptr->addr); - } - } - buf_discard(buf); -} - /** * tipc_cltr_broadcast - broadcast message to all nodes within cluster */ @@ -385,7 +109,6 @@ void tipc_cltr_broadcast(struct sk_buff *buf) if (tipc_mode == TIPC_NET_MODE) { c_ptr = tipc_cltr_find(tipc_own_addr); - assert(in_own_cluster(c_ptr->addr)); /* For now */ /* Send to nodes */ for (n_num = 1; n_num <= c_ptr->highest_node; n_num++) { diff --git a/net/tipc/cluster.h b/net/tipc/cluster.h index aa1fd6ab4d11..e4b6e4e27371 100644 --- a/net/tipc/cluster.h +++ b/net/tipc/cluster.h @@ -57,20 +57,12 @@ struct cluster { extern struct tipc_node **tipc_local_nodes; extern struct tipc_node_map tipc_cltr_bcast_nodes; -void tipc_cltr_remove_as_router(struct cluster *c_ptr, u32 router); -void tipc_cltr_send_ext_routes(struct cluster *c_ptr, u32 dest); -struct tipc_node *tipc_cltr_select_node(struct cluster *c_ptr, u32 selector); -u32 tipc_cltr_select_router(struct cluster *c_ptr, u32 ref); -void tipc_cltr_recv_routing_table(struct sk_buff *buf); struct cluster *tipc_cltr_create(u32 addr); void tipc_cltr_delete(struct cluster *c_ptr); void tipc_cltr_attach_node(struct cluster *c_ptr, struct tipc_node *n_ptr); void tipc_cltr_broadcast(struct sk_buff *buf); int tipc_cltr_init(void); -void tipc_cltr_bcast_new_route(struct cluster *c_ptr, u32 dest, u32 lo, u32 hi); -void tipc_cltr_bcast_lost_route(struct cluster *c_ptr, u32 dest, u32 lo, u32 hi); - static inline struct cluster *tipc_cltr_find(u32 addr) { if (!in_own_cluster(addr)) diff --git a/net/tipc/link.c b/net/tipc/link.c index cf414cf05e72..671ffd3c0e53 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -1061,7 +1061,7 @@ int tipc_link_send(struct sk_buff *buf, u32 dest, u32 selector) int res = -ELINKCONG; read_lock_bh(&tipc_net_lock); - n_ptr = tipc_node_select(dest, selector); + n_ptr = tipc_node_find(dest); if (n_ptr) { tipc_node_lock(n_ptr); l_ptr = n_ptr->active_links[selector & 1]; @@ -1137,7 +1137,7 @@ int tipc_send_buf_fast(struct sk_buff *buf, u32 destnode) return tipc_port_recv_msg(buf); read_lock_bh(&tipc_net_lock); - n_ptr = tipc_node_select(destnode, selector); + n_ptr = tipc_node_find(destnode); if (likely(n_ptr)) { tipc_node_lock(n_ptr); l_ptr = n_ptr->active_links[selector]; @@ -1186,7 +1186,7 @@ again: !sender->user_port, &buf); read_lock_bh(&tipc_net_lock); - node = tipc_node_select(destaddr, selector); + node = tipc_node_find(destaddr); if (likely(node)) { tipc_node_lock(node); l_ptr = node->active_links[selector]; @@ -1376,7 +1376,7 @@ error: * Now we have a buffer chain. Select a link and check * that packet size is still OK */ - node = tipc_node_select(destaddr, sender->publ.ref & 1); + node = tipc_node_find(destaddr); if (likely(node)) { tipc_node_lock(node); l_ptr = node->active_links[sender->publ.ref & 1]; @@ -1893,7 +1893,7 @@ deliver: continue; case ROUTE_DISTRIBUTOR: tipc_node_unlock(n_ptr); - tipc_cltr_recv_routing_table(buf); + buf_discard(buf); continue; case NAME_DISTRIBUTOR: tipc_node_unlock(n_ptr); @@ -2852,7 +2852,6 @@ void tipc_link_set_queue_limits(struct link *l_ptr, u32 window) l_ptr->queue_limit[TIPC_HIGH_IMPORTANCE + 4] = 900; l_ptr->queue_limit[TIPC_CRITICAL_IMPORTANCE + 4] = 1200; l_ptr->queue_limit[CONN_MANAGER] = 1200; - l_ptr->queue_limit[ROUTE_DISTRIBUTOR] = 1200; l_ptr->queue_limit[CHANGEOVER_PROTOCOL] = 2500; l_ptr->queue_limit[NAME_DISTRIBUTOR] = 3000; /* FRAGMENT and LAST_FRAGMENT packets */ @@ -3154,7 +3153,7 @@ u32 tipc_link_get_max_pkt(u32 dest, u32 selector) return MAX_MSG_SIZE; read_lock_bh(&tipc_net_lock); - n_ptr = tipc_node_select(dest, selector); + n_ptr = tipc_node_find(dest); if (n_ptr) { tipc_node_lock(n_ptr); l_ptr = n_ptr->active_links[selector & 1]; diff --git a/net/tipc/msg.h b/net/tipc/msg.h index c1b6217838e6..68b65ef3e74b 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -540,7 +540,7 @@ static inline struct tipc_msg *msg_get_wrapped(struct tipc_msg *m) #define MSG_BUNDLER 6 #define LINK_PROTOCOL 7 #define CONN_MANAGER 8 -#define ROUTE_DISTRIBUTOR 9 +#define ROUTE_DISTRIBUTOR 9 /* obsoleted */ #define CHANGEOVER_PROTOCOL 10 #define NAME_DISTRIBUTOR 11 #define MSG_FRAGMENTER 12 @@ -819,11 +819,6 @@ static inline void msg_set_remote_node(struct tipc_msg *m, u32 a) msg_set_word(m, msg_hdr_sz(m)/4, a); } -static inline void msg_set_dataoctet(struct tipc_msg *m, u32 pos) -{ - msg_data(m)[pos + 4] = 1; -} - /* * Segmentation message types */ diff --git a/net/tipc/net.c b/net/tipc/net.c index a25f8bb1e1d9..3967f1f6d97f 100644 --- a/net/tipc/net.c +++ b/net/tipc/net.c @@ -112,48 +112,6 @@ DEFINE_RWLOCK(tipc_net_lock); struct network tipc_net; -struct tipc_node *tipc_net_select_remote_node(u32 addr, u32 ref) -{ - struct cluster *c_ptr; - - c_ptr = tipc_net.clusters[1]; - if (!c_ptr) - return NULL; - return tipc_cltr_select_node(c_ptr, ref); -} - -u32 tipc_net_select_router(u32 addr, u32 ref) -{ - struct cluster *c_ptr; - - c_ptr = tipc_net.clusters[1]; - if (!c_ptr) - return 0; - return tipc_cltr_select_router(c_ptr, ref); -} - -void tipc_net_remove_as_router(u32 router) -{ - u32 c_num; - - for (c_num = 1; c_num <= tipc_max_clusters; c_num++) { - if (!tipc_net.clusters[c_num]) - continue; - tipc_cltr_remove_as_router(tipc_net.clusters[c_num], router); - } -} - -void tipc_net_send_external_routes(u32 dest) -{ - u32 c_num; - - for (c_num = 1; c_num <= tipc_max_clusters; c_num++) { - if (tipc_net.clusters[c_num]) - tipc_cltr_send_ext_routes(tipc_net.clusters[c_num], - dest); - } -} - static void net_stop(void) { u32 c_num; @@ -225,9 +183,6 @@ void tipc_net_route_msg(struct sk_buff *buf) return; } switch (msg_user(msg)) { - case ROUTE_DISTRIBUTOR: - tipc_cltr_recv_routing_table(buf); - break; case NAME_DISTRIBUTOR: tipc_named_recv(buf); break; diff --git a/net/tipc/net.h b/net/tipc/net.h index 786c94007470..6e402d9b33e0 100644 --- a/net/tipc/net.h +++ b/net/tipc/net.h @@ -54,11 +54,7 @@ struct network { extern struct network tipc_net; extern rwlock_t tipc_net_lock; -void tipc_net_remove_as_router(u32 router); -void tipc_net_send_external_routes(u32 dest); void tipc_net_route_msg(struct sk_buff *buf); -struct tipc_node *tipc_net_select_remote_node(u32 addr, u32 ref); -u32 tipc_net_select_router(u32 addr, u32 ref); int tipc_net_start(u32 addr); void tipc_net_stop(void); diff --git a/net/tipc/node.c b/net/tipc/node.c index 8ffbdb33b2cb..c47cc69eb575 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -95,11 +95,10 @@ struct tipc_node *tipc_node_create(u32 addr) } n_ptr->addr = addr; - spin_lock_init(&n_ptr->lock); + spin_lock_init(&n_ptr->lock); INIT_LIST_HEAD(&n_ptr->nsub); n_ptr->owner = c_ptr; tipc_cltr_attach_node(c_ptr, n_ptr); - n_ptr->last_router = -1; /* Insert node into ordered list */ for (curr_node = &tipc_nodes; *curr_node; @@ -229,14 +228,9 @@ int tipc_node_has_redundant_links(struct tipc_node *n_ptr) return n_ptr->working_links > 1; } -static int tipc_node_has_active_routes(struct tipc_node *n_ptr) -{ - return n_ptr && (n_ptr->last_router >= 0); -} - int tipc_node_is_up(struct tipc_node *n_ptr) { - return tipc_node_has_active_links(n_ptr) || tipc_node_has_active_routes(n_ptr); + return tipc_node_has_active_links(n_ptr); } struct tipc_node *tipc_node_attach_link(struct link *l_ptr) @@ -323,36 +317,17 @@ void tipc_node_detach_link(struct tipc_node *n_ptr, struct link *l_ptr) static void node_established_contact(struct tipc_node *n_ptr) { - struct cluster *c_ptr; - dbg("node_established_contact:-> %x\n", n_ptr->addr); - if (!tipc_node_has_active_routes(n_ptr) && in_own_cluster(n_ptr->addr)) { - tipc_k_signal((Handler)tipc_named_node_up, n_ptr->addr); - } + tipc_k_signal((Handler)tipc_named_node_up, n_ptr->addr); /* Syncronize broadcast acks */ n_ptr->bclink.acked = tipc_bclink_get_last_sent(); - if (!in_own_cluster(n_ptr->addr)) { - /* Usage case 1 (see above) */ - c_ptr = tipc_cltr_find(tipc_own_addr); - if (!c_ptr) - c_ptr = tipc_cltr_create(tipc_own_addr); - if (c_ptr) - tipc_cltr_bcast_new_route(c_ptr, n_ptr->addr, 1, - tipc_max_nodes); - return; - } - - c_ptr = n_ptr->owner; if (n_ptr->bclink.supported) { tipc_nmap_add(&tipc_cltr_bcast_nodes, n_ptr->addr); if (n_ptr->addr < tipc_own_addr) tipc_own_tag++; } - - /* Case 3 (see above) */ - tipc_net_send_external_routes(n_ptr->addr); } static void node_cleanup_finished(unsigned long node_addr) @@ -371,7 +346,6 @@ static void node_cleanup_finished(unsigned long node_addr) static void node_lost_contact(struct tipc_node *n_ptr) { - struct cluster *c_ptr; struct tipc_node_subscr *ns, *tns; char addr_string[16]; u32 i; @@ -392,23 +366,11 @@ static void node_lost_contact(struct tipc_node *n_ptr) } /* Update routing tables */ - if (!in_own_cluster(n_ptr->addr)) { - /* Case 4 (see above) */ - c_ptr = tipc_cltr_find(tipc_own_addr); - tipc_cltr_bcast_lost_route(c_ptr, n_ptr->addr, 1, - tipc_max_nodes); - } else { - /* Case 5 (see above) */ - c_ptr = tipc_cltr_find(n_ptr->addr); - if (n_ptr->bclink.supported) { - tipc_nmap_remove(&tipc_cltr_bcast_nodes, n_ptr->addr); - if (n_ptr->addr < tipc_own_addr) - tipc_own_tag--; - } - tipc_net_remove_as_router(n_ptr->addr); + if (n_ptr->bclink.supported) { + tipc_nmap_remove(&tipc_cltr_bcast_nodes, n_ptr->addr); + if (n_ptr->addr < tipc_own_addr) + tipc_own_tag--; } - if (tipc_node_has_active_routes(n_ptr)) - return; info("Lost contact with %s\n", tipc_addr_string_fill(addr_string, n_ptr->addr)); @@ -437,120 +399,6 @@ static void node_lost_contact(struct tipc_node *n_ptr) tipc_k_signal((Handler)node_cleanup_finished, n_ptr->addr); } -/** - * tipc_node_select_next_hop - find the next-hop node for a message - * - * Called by when cluster local lookup has failed. - */ - -struct tipc_node *tipc_node_select_next_hop(u32 addr, u32 selector) -{ - struct tipc_node *n_ptr; - u32 router_addr; - - if (!tipc_addr_domain_valid(addr)) - return NULL; - - /* Look for direct link to destination processsor */ - n_ptr = tipc_node_find(addr); - if (n_ptr && tipc_node_has_active_links(n_ptr)) - return n_ptr; - - /* Cluster local system nodes *must* have direct links */ - if (in_own_cluster(addr)) - return NULL; - - /* Look for cluster local router with direct link to node */ - router_addr = tipc_node_select_router(n_ptr, selector); - if (router_addr) - return tipc_node_select(router_addr, selector); - - /* Inter zone/cluster -- find any direct link to remote cluster */ - addr = tipc_addr(tipc_zone(addr), tipc_cluster(addr), 0); - n_ptr = tipc_net_select_remote_node(addr, selector); - if (n_ptr && tipc_node_has_active_links(n_ptr)) - return n_ptr; - - /* Last resort -- look for any router to anywhere in remote zone */ - router_addr = tipc_net_select_router(addr, selector); - if (router_addr) - return tipc_node_select(router_addr, selector); - - return NULL; -} - -/** - * tipc_node_select_router - select router to reach specified node - * - * Uses a deterministic and fair algorithm for selecting router node. - */ - -u32 tipc_node_select_router(struct tipc_node *n_ptr, u32 ref) -{ - u32 ulim; - u32 mask; - u32 start; - u32 r; - - if (!n_ptr) - return 0; - - if (n_ptr->last_router < 0) - return 0; - ulim = ((n_ptr->last_router + 1) * 32) - 1; - - /* Start entry must be random */ - mask = tipc_max_nodes; - while (mask > ulim) - mask >>= 1; - start = ref & mask; - r = start; - - /* Lookup upwards with wrap-around */ - do { - if (((n_ptr->routers[r / 32]) >> (r % 32)) & 1) - break; - } while (++r <= ulim); - if (r > ulim) { - r = 1; - do { - if (((n_ptr->routers[r / 32]) >> (r % 32)) & 1) - break; - } while (++r < start); - assert(r != start); - } - assert(r && (r <= ulim)); - return tipc_addr(own_zone(), own_cluster(), r); -} - -void tipc_node_add_router(struct tipc_node *n_ptr, u32 router) -{ - u32 r_num = tipc_node(router); - - n_ptr->routers[r_num / 32] = - ((1 << (r_num % 32)) | n_ptr->routers[r_num / 32]); - n_ptr->last_router = tipc_max_nodes / 32; - while ((--n_ptr->last_router >= 0) && - !n_ptr->routers[n_ptr->last_router]); -} - -void tipc_node_remove_router(struct tipc_node *n_ptr, u32 router) -{ - u32 r_num = tipc_node(router); - - if (n_ptr->last_router < 0) - return; /* No routes */ - - n_ptr->routers[r_num / 32] = - ((~(1 << (r_num % 32))) & (n_ptr->routers[r_num / 32])); - n_ptr->last_router = tipc_max_nodes / 32; - while ((--n_ptr->last_router >= 0) && - !n_ptr->routers[n_ptr->last_router]); - - if (!tipc_node_is_up(n_ptr)) - node_lost_contact(n_ptr); -} - struct sk_buff *tipc_node_get_nodes(const void *req_tlv_area, int req_tlv_space) { u32 domain; diff --git a/net/tipc/node.h b/net/tipc/node.h index 7bfaf5e8c201..3abaaa24c77d 100644 --- a/net/tipc/node.h +++ b/net/tipc/node.h @@ -54,8 +54,6 @@ * @cleanup_required: non-zero if cleaning up after a prior loss of contact * @link_cnt: number of links to node * @permit_changeover: non-zero if node has redundant links to this system - * @routers: bitmap (used for multicluster communication) - * @last_router: (used for multicluster communication) * @bclink: broadcast-related info * @supported: non-zero if node supports TIPC b'cast capability * @acked: sequence # of last outbound b'cast message acknowledged by node @@ -80,8 +78,6 @@ struct tipc_node { int working_links; int cleanup_required; int permit_changeover; - u32 routers[512/32]; - int last_router; struct { int supported; u32 acked; @@ -105,11 +101,7 @@ void tipc_node_link_down(struct tipc_node *n_ptr, struct link *l_ptr); void tipc_node_link_up(struct tipc_node *n_ptr, struct link *l_ptr); int tipc_node_has_active_links(struct tipc_node *n_ptr); int tipc_node_has_redundant_links(struct tipc_node *n_ptr); -u32 tipc_node_select_router(struct tipc_node *n_ptr, u32 ref); -struct tipc_node *tipc_node_select_next_hop(u32 addr, u32 selector); int tipc_node_is_up(struct tipc_node *n_ptr); -void tipc_node_add_router(struct tipc_node *n_ptr, u32 router); -void tipc_node_remove_router(struct tipc_node *n_ptr, u32 router); struct sk_buff *tipc_node_get_links(const void *req_tlv_area, int req_tlv_space); struct sk_buff *tipc_node_get_nodes(const void *req_tlv_area, int req_tlv_space); @@ -117,22 +109,9 @@ static inline struct tipc_node *tipc_node_find(u32 addr) { if (likely(in_own_cluster(addr))) return tipc_local_nodes[tipc_node(addr)]; - else if (tipc_addr_domain_valid(addr)) { - struct cluster *c_ptr = tipc_cltr_find(addr); - - if (c_ptr) - return c_ptr->nodes[tipc_node(addr)]; - } return NULL; } -static inline struct tipc_node *tipc_node_select(u32 addr, u32 selector) -{ - if (likely(in_own_cluster(addr))) - return tipc_local_nodes[tipc_node(addr)]; - return tipc_node_select_next_hop(addr, selector); -} - static inline void tipc_node_lock(struct tipc_node *n_ptr) { spin_lock_bh(&n_ptr->lock); -- cgit v1.2.3 From 8f92df6ad49da958d97e171762d0a97a3dc738f1 Mon Sep 17 00:00:00 2001 From: Allan Stephens Date: Fri, 31 Dec 2010 18:59:19 +0000 Subject: tipc: Remove prototype code for supporting multiple clusters Eliminates routines, data structures, and files that were intended to allow TIPC to support a network containing multiple clusters. Currently, TIPC supports only networks consisting of a single cluster within a single zone, so this code is unnecessary. Signed-off-by: Allan Stephens Signed-off-by: Paul Gortmaker Signed-off-by: David S. Miller --- include/linux/tipc_config.h | 4 +- net/tipc/Kconfig | 10 ---- net/tipc/Makefile | 2 +- net/tipc/addr.c | 5 +- net/tipc/bcast.c | 9 ++- net/tipc/bcast.h | 1 + net/tipc/cluster.c | 135 -------------------------------------------- net/tipc/cluster.h | 73 ------------------------ net/tipc/config.c | 21 +------ net/tipc/core.c | 6 -- net/tipc/core.h | 1 - net/tipc/name_distr.c | 28 +++++++-- net/tipc/net.c | 25 ++++++-- net/tipc/net.h | 8 ++- net/tipc/node.c | 37 ++++++------ net/tipc/node.h | 7 +-- 16 files changed, 83 insertions(+), 289 deletions(-) delete mode 100644 net/tipc/cluster.c delete mode 100644 net/tipc/cluster.h (limited to 'include/linux') diff --git a/include/linux/tipc_config.h b/include/linux/tipc_config.h index 1f38df1202ba..677aa13dc5d7 100644 --- a/include/linux/tipc_config.h +++ b/include/linux/tipc_config.h @@ -95,7 +95,7 @@ #define TIPC_CMD_GET_MAX_PUBL 0x4005 /* tx none, rx unsigned */ #define TIPC_CMD_GET_MAX_SUBSCR 0x4006 /* tx none, rx unsigned */ #define TIPC_CMD_GET_MAX_ZONES 0x4007 /* obsoleted */ -#define TIPC_CMD_GET_MAX_CLUSTERS 0x4008 /* tx none, rx unsigned */ +#define TIPC_CMD_GET_MAX_CLUSTERS 0x4008 /* obsoleted */ #define TIPC_CMD_GET_MAX_NODES 0x4009 /* tx none, rx unsigned */ #define TIPC_CMD_GET_MAX_SLAVES 0x400A /* obsoleted */ #define TIPC_CMD_GET_NETID 0x400B /* tx none, rx unsigned */ @@ -131,7 +131,7 @@ #define TIPC_CMD_SET_MAX_PUBL 0x8005 /* tx unsigned, rx none */ #define TIPC_CMD_SET_MAX_SUBSCR 0x8006 /* tx unsigned, rx none */ #define TIPC_CMD_SET_MAX_ZONES 0x8007 /* obsoleted */ -#define TIPC_CMD_SET_MAX_CLUSTERS 0x8008 /* tx unsigned, rx none */ +#define TIPC_CMD_SET_MAX_CLUSTERS 0x8008 /* obsoleted */ #define TIPC_CMD_SET_MAX_NODES 0x8009 /* tx unsigned, rx none */ #define TIPC_CMD_SET_MAX_SLAVES 0x800A /* obsoleted */ #define TIPC_CMD_SET_NETID 0x800B /* tx unsigned, rx none */ diff --git a/net/tipc/Kconfig b/net/tipc/Kconfig index 06d32908fcfb..c02d3e9c156d 100644 --- a/net/tipc/Kconfig +++ b/net/tipc/Kconfig @@ -29,16 +29,6 @@ config TIPC_ADVANCED Saying Y here will open some advanced configuration for TIPC. Most users do not need to bother; if unsure, just say N. -config TIPC_CLUSTERS - int "Maximum number of clusters in a zone" - depends on TIPC_ADVANCED - range 1 1 - default "1" - help - Specifies how many clusters can be supported in a TIPC zone. - - *** Currently TIPC only supports a single cluster per zone. *** - config TIPC_NODES int "Maximum number of nodes in a cluster" depends on TIPC_ADVANCED diff --git a/net/tipc/Makefile b/net/tipc/Makefile index 3d936f0560c7..849d819bfc74 100644 --- a/net/tipc/Makefile +++ b/net/tipc/Makefile @@ -4,7 +4,7 @@ obj-$(CONFIG_TIPC) := tipc.o -tipc-y += addr.o bcast.o bearer.o config.o cluster.o \ +tipc-y += addr.o bcast.o bearer.o config.o \ core.o handler.o link.o discover.o msg.o \ name_distr.o subscr.o name_table.o net.o \ netlink.o node.o node_subscr.o port.o ref.o \ diff --git a/net/tipc/addr.c b/net/tipc/addr.c index 8823e03e52e0..483868a75b88 100644 --- a/net/tipc/addr.c +++ b/net/tipc/addr.c @@ -35,7 +35,8 @@ */ #include "core.h" -#include "cluster.h" +#include "node.h" +#include "addr.h" /** * tipc_addr_domain_valid - validates a network domain address @@ -55,8 +56,6 @@ int tipc_addr_domain_valid(u32 addr) if (n > max_nodes) return 0; - if (c > tipc_max_clusters) - return 0; if (n && (!z || !c)) return 0; diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index 6d828d9eda42..110829eab96a 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -111,6 +111,9 @@ static struct bclink *bclink = NULL; static struct link *bcl = NULL; static DEFINE_SPINLOCK(bc_lock); +/* broadcast-capable node map */ +struct tipc_node_map tipc_bcast_nmap; + const char tipc_bclink_name[] = "broadcast-link"; static void tipc_nmap_diff(struct tipc_node_map *nm_a, @@ -566,8 +569,8 @@ static int tipc_bcbearer_send(struct sk_buff *buf, if (likely(!msg_non_seq(buf_msg(buf)))) { struct tipc_msg *msg; - assert(tipc_cltr_bcast_nodes.count != 0); - bcbuf_set_acks(buf, tipc_cltr_bcast_nodes.count); + assert(tipc_bcast_nmap.count != 0); + bcbuf_set_acks(buf, tipc_bcast_nmap.count); msg = buf_msg(buf); msg_set_non_seq(msg, 1); msg_set_mc_netid(msg, tipc_net_id); @@ -576,7 +579,7 @@ static int tipc_bcbearer_send(struct sk_buff *buf, /* Send buffer over bearers until all targets reached */ - bcbearer->remains = tipc_cltr_bcast_nodes; + bcbearer->remains = tipc_bcast_nmap; for (bp_index = 0; bp_index < MAX_BEARERS; bp_index++) { struct bearer *p = bcbearer->bpairs[bp_index].primary; diff --git a/net/tipc/bcast.h b/net/tipc/bcast.h index 011c03f0a4ab..51f8c5326ce6 100644 --- a/net/tipc/bcast.h +++ b/net/tipc/bcast.h @@ -51,6 +51,7 @@ struct tipc_node_map { u32 map[MAX_NODES / WSIZE]; }; +extern struct tipc_node_map tipc_bcast_nmap; #define PLSIZE 32 diff --git a/net/tipc/cluster.c b/net/tipc/cluster.c deleted file mode 100644 index ba6f5bfa0cdb..000000000000 --- a/net/tipc/cluster.c +++ /dev/null @@ -1,135 +0,0 @@ -/* - * net/tipc/cluster.c: TIPC cluster management routines - * - * Copyright (c) 2000-2006, Ericsson AB - * Copyright (c) 2005, Wind River Systems - * All rights reserved. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions are met: - * - * 1. Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * 2. Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * 3. Neither the names of the copyright holders nor the names of its - * contributors may be used to endorse or promote products derived from - * this software without specific prior written permission. - * - * Alternatively, this software may be distributed under the terms of the - * GNU General Public License ("GPL") version 2 as published by the Free - * Software Foundation. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" - * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE - * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE - * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE - * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR - * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF - * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS - * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN - * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) - * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE - * POSSIBILITY OF SUCH DAMAGE. - */ - -#include "core.h" -#include "cluster.h" -#include "link.h" - -struct tipc_node **tipc_local_nodes = NULL; -struct tipc_node_map tipc_cltr_bcast_nodes = {0,{0,}}; - -struct cluster *tipc_cltr_create(u32 addr) -{ - struct cluster *c_ptr; - int max_nodes; - - c_ptr = kzalloc(sizeof(*c_ptr), GFP_ATOMIC); - if (c_ptr == NULL) { - warn("Cluster creation failure, no memory\n"); - return NULL; - } - - c_ptr->addr = tipc_addr(tipc_zone(addr), tipc_cluster(addr), 0); - max_nodes = tipc_max_nodes + 1; - - c_ptr->nodes = kcalloc(max_nodes + 1, sizeof(void*), GFP_ATOMIC); - if (c_ptr->nodes == NULL) { - warn("Cluster creation failure, no memory for node area\n"); - kfree(c_ptr); - return NULL; - } - - tipc_local_nodes = c_ptr->nodes; - c_ptr->highest_node = 0; - - tipc_net.clusters[1] = c_ptr; - return c_ptr; -} - -void tipc_cltr_delete(struct cluster *c_ptr) -{ - u32 n_num; - - if (!c_ptr) - return; - for (n_num = 1; n_num <= c_ptr->highest_node; n_num++) { - tipc_node_delete(c_ptr->nodes[n_num]); - } - kfree(c_ptr->nodes); - kfree(c_ptr); -} - - -void tipc_cltr_attach_node(struct cluster *c_ptr, struct tipc_node *n_ptr) -{ - u32 n_num = tipc_node(n_ptr->addr); - u32 max_n_num = tipc_max_nodes; - - assert(n_num > 0); - assert(n_num <= max_n_num); - assert(c_ptr->nodes[n_num] == NULL); - c_ptr->nodes[n_num] = n_ptr; - if (n_num > c_ptr->highest_node) - c_ptr->highest_node = n_num; -} - -/** - * tipc_cltr_broadcast - broadcast message to all nodes within cluster - */ - -void tipc_cltr_broadcast(struct sk_buff *buf) -{ - struct sk_buff *buf_copy; - struct cluster *c_ptr; - struct tipc_node *n_ptr; - u32 n_num; - - if (tipc_mode == TIPC_NET_MODE) { - c_ptr = tipc_cltr_find(tipc_own_addr); - - /* Send to nodes */ - for (n_num = 1; n_num <= c_ptr->highest_node; n_num++) { - n_ptr = c_ptr->nodes[n_num]; - if (n_ptr && tipc_node_has_active_links(n_ptr)) { - buf_copy = skb_copy(buf, GFP_ATOMIC); - if (buf_copy == NULL) - goto exit; - msg_set_destnode(buf_msg(buf_copy), - n_ptr->addr); - tipc_link_send(buf_copy, n_ptr->addr, - n_ptr->addr); - } - } - } -exit: - buf_discard(buf); -} - -int tipc_cltr_init(void) -{ - return tipc_cltr_create(tipc_own_addr) ? 0 : -ENOMEM; -} - diff --git a/net/tipc/cluster.h b/net/tipc/cluster.h deleted file mode 100644 index e4b6e4e27371..000000000000 --- a/net/tipc/cluster.h +++ /dev/null @@ -1,73 +0,0 @@ -/* - * net/tipc/cluster.h: Include file for TIPC cluster management routines - * - * Copyright (c) 2000-2006, Ericsson AB - * Copyright (c) 2005, Wind River Systems - * All rights reserved. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions are met: - * - * 1. Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * 2. Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * 3. Neither the names of the copyright holders nor the names of its - * contributors may be used to endorse or promote products derived from - * this software without specific prior written permission. - * - * Alternatively, this software may be distributed under the terms of the - * GNU General Public License ("GPL") version 2 as published by the Free - * Software Foundation. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" - * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE - * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE - * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE - * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR - * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF - * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS - * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN - * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) - * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE - * POSSIBILITY OF SUCH DAMAGE. - */ - -#ifndef _TIPC_CLUSTER_H -#define _TIPC_CLUSTER_H - -#include "addr.h" -#include "net.h" - -/** - * struct cluster - TIPC cluster structure - * @addr: network address of cluster - * @nodes: array of pointers to all nodes within cluster - * @highest_node: id of highest numbered node within cluster - */ - -struct cluster { - u32 addr; - struct tipc_node **nodes; - u32 highest_node; -}; - - -extern struct tipc_node **tipc_local_nodes; -extern struct tipc_node_map tipc_cltr_bcast_nodes; - -struct cluster *tipc_cltr_create(u32 addr); -void tipc_cltr_delete(struct cluster *c_ptr); -void tipc_cltr_attach_node(struct cluster *c_ptr, struct tipc_node *n_ptr); -void tipc_cltr_broadcast(struct sk_buff *buf); -int tipc_cltr_init(void); - -static inline struct cluster *tipc_cltr_find(u32 addr) -{ - if (!in_own_cluster(addr)) - return NULL; - return tipc_net.clusters[1]; -} - -#endif diff --git a/net/tipc/config.c b/net/tipc/config.c index 05dc102300ae..bc512102eebd 100644 --- a/net/tipc/config.c +++ b/net/tipc/config.c @@ -269,19 +269,6 @@ static struct sk_buff *cfg_set_max_ports(void) return tipc_cfg_reply_none(); } -static struct sk_buff *cfg_set_max_clusters(void) -{ - u32 value; - - if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_UNSIGNED)) - return tipc_cfg_reply_error_string(TIPC_CFG_TLV_ERROR); - value = ntohl(*(__be32 *)TLV_DATA(req_tlv_area)); - if (value != delimit(value, 1, 1)) - return tipc_cfg_reply_error_string(TIPC_CFG_INVALID_VALUE - " (max clusters fixed at 1)"); - return tipc_cfg_reply_none(); -} - static struct sk_buff *cfg_set_max_nodes(void) { u32 value; @@ -420,9 +407,6 @@ struct sk_buff *tipc_cfg_do_cmd(u32 orig_node, u16 cmd, const void *request_area case TIPC_CMD_SET_MAX_SUBSCR: rep_tlv_buf = cfg_set_max_subscriptions(); break; - case TIPC_CMD_SET_MAX_CLUSTERS: - rep_tlv_buf = cfg_set_max_clusters(); - break; case TIPC_CMD_SET_MAX_NODES: rep_tlv_buf = cfg_set_max_nodes(); break; @@ -441,9 +425,6 @@ struct sk_buff *tipc_cfg_do_cmd(u32 orig_node, u16 cmd, const void *request_area case TIPC_CMD_GET_MAX_SUBSCR: rep_tlv_buf = tipc_cfg_reply_unsigned(tipc_max_subscriptions); break; - case TIPC_CMD_GET_MAX_CLUSTERS: - rep_tlv_buf = tipc_cfg_reply_unsigned(tipc_max_clusters); - break; case TIPC_CMD_GET_MAX_NODES: rep_tlv_buf = tipc_cfg_reply_unsigned(tipc_max_nodes); break; @@ -458,6 +439,8 @@ struct sk_buff *tipc_cfg_do_cmd(u32 orig_node, u16 cmd, const void *request_area case TIPC_CMD_GET_MAX_ZONES: case TIPC_CMD_SET_MAX_SLAVES: case TIPC_CMD_GET_MAX_SLAVES: + case TIPC_CMD_SET_MAX_CLUSTERS: + case TIPC_CMD_GET_MAX_CLUSTERS: rep_tlv_buf = tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED " (obsolete command)"); break; diff --git a/net/tipc/core.c b/net/tipc/core.c index 8b7af893971e..b9a3ef13f7e7 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -48,10 +48,6 @@ #include "config.h" -#ifndef CONFIG_TIPC_CLUSTERS -#define CONFIG_TIPC_CLUSTERS 1 -#endif - #ifndef CONFIG_TIPC_NODES #define CONFIG_TIPC_NODES 255 #endif @@ -76,7 +72,6 @@ const char tipc_alphabet[] = /* configurable TIPC parameters */ u32 tipc_own_addr; -int tipc_max_clusters; int tipc_max_nodes; int tipc_max_ports; int tipc_max_subscriptions; @@ -199,7 +194,6 @@ static int __init tipc_init(void) tipc_max_publications = 10000; tipc_max_subscriptions = 2000; tipc_max_ports = CONFIG_TIPC_PORTS; - tipc_max_clusters = CONFIG_TIPC_CLUSTERS; tipc_max_nodes = CONFIG_TIPC_NODES; tipc_net_id = 4711; diff --git a/net/tipc/core.h b/net/tipc/core.h index 8313a1689565..c44f955bd54a 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -184,7 +184,6 @@ void tipc_dump_dbg(struct print_buf *, const char *fmt, ...); */ extern u32 tipc_own_addr; -extern int tipc_max_clusters; extern int tipc_max_nodes; extern int tipc_max_ports; extern int tipc_max_subscriptions; diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c index 10ff48be3c01..c4583fe888d8 100644 --- a/net/tipc/name_distr.c +++ b/net/tipc/name_distr.c @@ -35,7 +35,7 @@ */ #include "core.h" -#include "cluster.h" +#include "addr.h" #include "link.h" #include "name_distr.h" @@ -107,6 +107,26 @@ static struct sk_buff *named_prepare_buf(u32 type, u32 size, u32 dest) return buf; } +static void named_cluster_distribute(struct sk_buff *buf) +{ + struct sk_buff *buf_copy; + struct tipc_node *n_ptr; + u32 n_num; + + for (n_num = 1; n_num <= tipc_net.highest_node; n_num++) { + n_ptr = tipc_net.nodes[n_num]; + if (n_ptr && tipc_node_has_active_links(n_ptr)) { + buf_copy = skb_copy(buf, GFP_ATOMIC); + if (!buf_copy) + break; + msg_set_destnode(buf_msg(buf_copy), n_ptr->addr); + tipc_link_send(buf_copy, n_ptr->addr, n_ptr->addr); + } + } + + buf_discard(buf); +} + /** * tipc_named_publish - tell other nodes about a new publication by this node */ @@ -127,8 +147,8 @@ void tipc_named_publish(struct publication *publ) item = (struct distr_item *)msg_data(buf_msg(buf)); publ_to_item(item, publ); - dbg("tipc_named_withdraw: broadcasting publish msg\n"); - tipc_cltr_broadcast(buf); + dbg("tipc_named_publish: broadcasting publish msg\n"); + named_cluster_distribute(buf); } /** @@ -152,7 +172,7 @@ void tipc_named_withdraw(struct publication *publ) item = (struct distr_item *)msg_data(buf_msg(buf)); publ_to_item(item, publ); dbg("tipc_named_withdraw: broadcasting withdraw msg\n"); - tipc_cltr_broadcast(buf); + named_cluster_distribute(buf); } /** diff --git a/net/tipc/net.c b/net/tipc/net.c index 3967f1f6d97f..3baf55ee0985 100644 --- a/net/tipc/net.c +++ b/net/tipc/net.c @@ -112,12 +112,23 @@ DEFINE_RWLOCK(tipc_net_lock); struct network tipc_net; +static int net_start(void) +{ + tipc_net.nodes = kcalloc(tipc_max_nodes + 1, + sizeof(*tipc_net.nodes), GFP_ATOMIC); + tipc_net.highest_node = 0; + + return tipc_net.nodes ? 0 : -ENOMEM; +} + static void net_stop(void) { - u32 c_num; + u32 n_num; - for (c_num = 1; c_num <= tipc_max_clusters; c_num++) - tipc_cltr_delete(tipc_net.clusters[c_num]); + for (n_num = 1; n_num <= tipc_net.highest_node; n_num++) + tipc_node_delete(tipc_net.nodes[n_num]); + kfree(tipc_net.nodes); + tipc_net.nodes = NULL; } static void net_route_named_msg(struct sk_buff *buf) @@ -218,10 +229,12 @@ int tipc_net_start(u32 addr) tipc_named_reinit(); tipc_port_reinit(); - if ((res = tipc_cltr_init()) || - (res = tipc_bclink_init())) { + res = net_start(); + if (res) + return res; + res = tipc_bclink_init(); + if (res) return res; - } tipc_k_signal((Handler)tipc_subscr_start, 0); tipc_k_signal((Handler)tipc_cfg_init, 0); diff --git a/net/tipc/net.h b/net/tipc/net.h index 6e402d9b33e0..4ae59ad04893 100644 --- a/net/tipc/net.h +++ b/net/tipc/net.h @@ -37,16 +37,18 @@ #ifndef _TIPC_NET_H #define _TIPC_NET_H -struct cluster; +struct tipc_node; /** * struct network - TIPC network structure - * @clusters: array of pointers to all clusters within zone + * @nodes: array of pointers to all nodes within cluster + * @highest_node: id of highest numbered node within cluster * @links: number of (unicast) links to cluster */ struct network { - struct cluster *clusters[2]; /* currently limited to just 1 cluster */ + struct tipc_node **nodes; + u32 highest_node; u32 links; }; diff --git a/net/tipc/node.c b/net/tipc/node.c index c47cc69eb575..58e189bf5c96 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -62,9 +62,9 @@ u32 tipc_own_tag = 0; struct tipc_node *tipc_node_create(u32 addr) { - struct cluster *c_ptr; struct tipc_node *n_ptr; struct tipc_node **curr_node; + u32 n_num; spin_lock_bh(&node_create_lock); @@ -84,21 +84,14 @@ struct tipc_node *tipc_node_create(u32 addr) return NULL; } - c_ptr = tipc_cltr_find(addr); - if (!c_ptr) { - c_ptr = tipc_cltr_create(addr); - } - if (!c_ptr) { - spin_unlock_bh(&node_create_lock); - kfree(n_ptr); - return NULL; - } - n_ptr->addr = addr; spin_lock_init(&n_ptr->lock); INIT_LIST_HEAD(&n_ptr->nsub); - n_ptr->owner = c_ptr; - tipc_cltr_attach_node(c_ptr, n_ptr); + + n_num = tipc_node(addr); + tipc_net.nodes[n_num] = n_ptr; + if (n_num > tipc_net.highest_node) + tipc_net.highest_node = n_num; /* Insert node into ordered list */ for (curr_node = &tipc_nodes; *curr_node; @@ -115,11 +108,19 @@ struct tipc_node *tipc_node_create(u32 addr) void tipc_node_delete(struct tipc_node *n_ptr) { + u32 n_num; + if (!n_ptr) return; dbg("node %x deleted\n", n_ptr->addr); + n_num = tipc_node(n_ptr->addr); + tipc_net.nodes[n_num] = NULL; kfree(n_ptr); + + while (!tipc_net.nodes[tipc_net.highest_node]) + if (--tipc_net.highest_node == 0) + break; } @@ -324,7 +325,7 @@ static void node_established_contact(struct tipc_node *n_ptr) n_ptr->bclink.acked = tipc_bclink_get_last_sent(); if (n_ptr->bclink.supported) { - tipc_nmap_add(&tipc_cltr_bcast_nodes, n_ptr->addr); + tipc_nmap_add(&tipc_bcast_nmap, n_ptr->addr); if (n_ptr->addr < tipc_own_addr) tipc_own_tag++; } @@ -361,13 +362,11 @@ static void node_lost_contact(struct tipc_node *n_ptr) buf_discard(n_ptr->bclink.defragm); n_ptr->bclink.defragm = NULL; } - if (in_own_cluster(n_ptr->addr) && n_ptr->bclink.supported) { - tipc_bclink_acknowledge(n_ptr, mod(n_ptr->bclink.acked + 10000)); - } - /* Update routing tables */ if (n_ptr->bclink.supported) { - tipc_nmap_remove(&tipc_cltr_bcast_nodes, n_ptr->addr); + tipc_bclink_acknowledge(n_ptr, + mod(n_ptr->bclink.acked + 10000)); + tipc_nmap_remove(&tipc_bcast_nmap, n_ptr->addr); if (n_ptr->addr < tipc_own_addr) tipc_own_tag--; } diff --git a/net/tipc/node.h b/net/tipc/node.h index 3abaaa24c77d..206a8efa410e 100644 --- a/net/tipc/node.h +++ b/net/tipc/node.h @@ -38,14 +38,14 @@ #define _TIPC_NODE_H #include "node_subscr.h" -#include "cluster.h" +#include "addr.h" +#include "net.h" #include "bearer.h" /** * struct tipc_node - TIPC node structure * @addr: network address of node * @lock: spinlock governing access to structure - * @owner: pointer to cluster that node belongs to * @next: pointer to next node in sorted list of cluster's nodes * @nsub: list of "node down" subscriptions monitoring node * @active_links: pointers to active links to node @@ -69,7 +69,6 @@ struct tipc_node { u32 addr; spinlock_t lock; - struct cluster *owner; struct tipc_node *next; struct list_head nsub; struct link *active_links[2]; @@ -108,7 +107,7 @@ struct sk_buff *tipc_node_get_nodes(const void *req_tlv_area, int req_tlv_space) static inline struct tipc_node *tipc_node_find(u32 addr) { if (likely(in_own_cluster(addr))) - return tipc_local_nodes[tipc_node(addr)]; + return tipc_net.nodes[tipc_node(addr)]; return NULL; } -- cgit v1.2.3 From 0e65967e33be61e5f67727edd4ea829b47676fc0 Mon Sep 17 00:00:00 2001 From: Allan Stephens Date: Fri, 31 Dec 2010 18:59:32 +0000 Subject: tipc: cleanup various cosmetic whitespace issues Cleans up TIPC's source code to eliminate deviations from generally accepted coding conventions relating to leading/trailing white space and white space around commas, braces, cases, and sizeof. These changes are purely cosmetic and do not alter the operation of TIPC in any way. Signed-off-by: Allan Stephens Signed-off-by: Paul Gortmaker Signed-off-by: David S. Miller --- include/linux/tipc.h | 18 +++++++------- include/linux/tipc_config.h | 59 ++++++++++++++++++++++----------------------- net/tipc/Kconfig | 2 +- net/tipc/bcast.c | 2 +- net/tipc/config.c | 3 +-- net/tipc/discover.c | 2 +- net/tipc/eth_media.c | 5 ++-- net/tipc/link.c | 31 +++++++++++------------- net/tipc/link.h | 4 +-- net/tipc/msg.c | 56 +++++++++++++++++++++--------------------- net/tipc/msg.h | 8 +++--- net/tipc/name_table.c | 14 +++++------ net/tipc/name_table.h | 2 +- net/tipc/node.c | 2 +- net/tipc/port.c | 15 ++++++------ net/tipc/port.h | 2 +- net/tipc/ref.c | 6 ++--- net/tipc/socket.c | 24 +++++++++--------- net/tipc/subscr.c | 2 +- 19 files changed, 124 insertions(+), 133 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tipc.h b/include/linux/tipc.h index d10614b29d59..1eefa3f6d1f4 100644 --- a/include/linux/tipc.h +++ b/include/linux/tipc.h @@ -1,6 +1,6 @@ /* * include/linux/tipc.h: Include file for TIPC socket interface - * + * * Copyright (c) 2003-2006, Ericsson AB * Copyright (c) 2005, Wind River Systems * All rights reserved. @@ -42,7 +42,7 @@ /* * TIPC addressing primitives */ - + struct tipc_portid { __u32 ref; __u32 node; @@ -89,7 +89,7 @@ static inline unsigned int tipc_node(__u32 addr) #define TIPC_TOP_SRV 1 /* topology service name type */ #define TIPC_RESERVED_TYPES 64 /* lowest user-publishable name type */ -/* +/* * Publication scopes when binding port names and port name sequences */ @@ -112,7 +112,7 @@ static inline unsigned int tipc_node(__u32 addr) #define TIPC_HIGH_IMPORTANCE 2 #define TIPC_CRITICAL_IMPORTANCE 3 -/* +/* * Msg rejection/connection shutdown reasons */ @@ -127,9 +127,9 @@ static inline unsigned int tipc_node(__u32 addr) * TIPC topology subscription service definitions */ -#define TIPC_SUB_PORTS 0x01 /* filter for port availability */ -#define TIPC_SUB_SERVICE 0x02 /* filter for service availability */ -#define TIPC_SUB_CANCEL 0x04 /* cancel a subscription */ +#define TIPC_SUB_PORTS 0x01 /* filter for port availability */ +#define TIPC_SUB_SERVICE 0x02 /* filter for service availability */ +#define TIPC_SUB_CANCEL 0x04 /* cancel a subscription */ #if 0 /* The following filter options are not currently implemented */ #define TIPC_SUB_NO_BIND_EVTS 0x04 /* filter out "publish" events */ @@ -137,12 +137,12 @@ static inline unsigned int tipc_node(__u32 addr) #define TIPC_SUB_SINGLE_EVT 0x10 /* expire after first event */ #endif -#define TIPC_WAIT_FOREVER ~0 /* timeout for permanent subscription */ +#define TIPC_WAIT_FOREVER (~0) /* timeout for permanent subscription */ struct tipc_subscr { struct tipc_name_seq seq; /* name sequence of interest */ __u32 timeout; /* subscription duration (in ms) */ - __u32 filter; /* bitmask of filter options */ + __u32 filter; /* bitmask of filter options */ char usr_handle[8]; /* available for subscriber use */ }; diff --git a/include/linux/tipc_config.h b/include/linux/tipc_config.h index 677aa13dc5d7..7d42460a5e3c 100644 --- a/include/linux/tipc_config.h +++ b/include/linux/tipc_config.h @@ -1,6 +1,6 @@ /* * include/linux/tipc_config.h: Include file for TIPC configuration interface - * + * * Copyright (c) 2003-2006, Ericsson AB * Copyright (c) 2005-2007, Wind River Systems * All rights reserved. @@ -54,19 +54,19 @@ * which specify parameters or results for the operation. * * For many operations, the request and reply messages have a fixed number - * of TLVs (usually zero or one); however, some reply messages may return + * of TLVs (usually zero or one); however, some reply messages may return * a variable number of TLVs. A failed request is denoted by the presence * of an "error string" TLV in the reply message instead of the TLV(s) the * reply should contain if the request succeeds. */ - -/* + +/* * Public commands: * May be issued by any process. - * Accepted by own node, or by remote node only if remote management enabled. + * Accepted by own node, or by remote node only if remote management enabled. */ - -#define TIPC_CMD_NOOP 0x0000 /* tx none, rx none */ + +#define TIPC_CMD_NOOP 0x0000 /* tx none, rx none */ #define TIPC_CMD_GET_NODES 0x0001 /* tx net_addr, rx node_info(s) */ #define TIPC_CMD_GET_MEDIA_NAMES 0x0002 /* tx none, rx media_name(s) */ #define TIPC_CMD_GET_BEARER_NAMES 0x0003 /* tx none, rx bearer_name(s) */ @@ -83,11 +83,11 @@ #define TIPC_CMD_GET_LINK_PEER 0x000D /* tx link_name, rx ? */ #endif -/* +/* * Protected commands: * May only be issued by "network administration capable" process. * Accepted by own node, or by remote node only if remote management enabled - * and this node is zone manager. + * and this node is zone manager. */ #define TIPC_CMD_GET_REMOTE_MNG 0x4003 /* tx none, rx unsigned */ @@ -116,10 +116,10 @@ #define TIPC_CMD_UNBLOCK_LINK 0x4106 /* tx link_name, rx none */ #endif -/* +/* * Private commands: * May only be issued by "network administration capable" process. - * Accepted by own node only; cannot be used on a remote node. + * Accepted by own node only; cannot be used on a remote node. */ #define TIPC_CMD_SET_NODE_ADDR 0x8001 /* tx net_addr, rx none */ @@ -156,20 +156,20 @@ #define TIPC_TLV_ULTRA_STRING 5 /* char[32768] (max) */ #define TIPC_TLV_ERROR_STRING 16 /* char[128] containing "error code" */ -#define TIPC_TLV_NET_ADDR 17 /* 32-bit integer denoting */ +#define TIPC_TLV_NET_ADDR 17 /* 32-bit integer denoting */ #define TIPC_TLV_MEDIA_NAME 18 /* char[TIPC_MAX_MEDIA_NAME] */ #define TIPC_TLV_BEARER_NAME 19 /* char[TIPC_MAX_BEARER_NAME] */ #define TIPC_TLV_LINK_NAME 20 /* char[TIPC_MAX_LINK_NAME] */ #define TIPC_TLV_NODE_INFO 21 /* struct tipc_node_info */ #define TIPC_TLV_LINK_INFO 22 /* struct tipc_link_info */ -#define TIPC_TLV_BEARER_CONFIG 23 /* struct tipc_bearer_config */ -#define TIPC_TLV_LINK_CONFIG 24 /* struct tipc_link_config */ +#define TIPC_TLV_BEARER_CONFIG 23 /* struct tipc_bearer_config */ +#define TIPC_TLV_LINK_CONFIG 24 /* struct tipc_link_config */ #define TIPC_TLV_NAME_TBL_QUERY 25 /* struct tipc_name_table_query */ -#define TIPC_TLV_PORT_REF 26 /* 32-bit port reference */ +#define TIPC_TLV_PORT_REF 26 /* 32-bit port reference */ /* * Maximum sizes of TIPC bearer-related names (including terminating NUL) - */ + */ #define TIPC_MAX_MEDIA_NAME 16 /* format = media */ #define TIPC_MAX_IF_NAME 16 /* format = interface */ @@ -234,7 +234,7 @@ struct tipc_name_table_query { }; /* - * The error string TLV is a null-terminated string describing the cause + * The error string TLV is a null-terminated string describing the cause * of the request failure. To simplify error processing (and to save space) * the first character of the string can be a special error code character * (lying by the range 0x80 to 0xFF) which represents a pre-defined reason. @@ -258,7 +258,7 @@ struct tipc_link_create { /* * A TLV consists of a descriptor, followed by the TLV value. - * TLV descriptor fields are stored in network byte order; + * TLV descriptor fields are stored in network byte order; * TLV values must also be stored in network byte order (where applicable). * TLV descriptors must be aligned to addresses which are multiple of 4, * so up to 3 bytes of padding may exist at the end of the TLV value area. @@ -294,7 +294,7 @@ static inline int TLV_OK(const void *tlv, __u16 space) static inline int TLV_CHECK(const void *tlv, __u16 space, __u16 exp_type) { - return TLV_OK(tlv, space) && + return TLV_OK(tlv, space) && (ntohs(((struct tlv_desc *)tlv)->tlv_type) == exp_type); } @@ -313,7 +313,7 @@ static inline int TLV_SET(void *tlv, __u16 type, void *data, __u16 len) } /* - * A TLV list descriptor simplifies processing of messages + * A TLV list descriptor simplifies processing of messages * containing multiple TLVs. */ @@ -322,15 +322,15 @@ struct tlv_list_desc { __u32 tlv_space; /* # bytes from curr TLV to list end */ }; -static inline void TLV_LIST_INIT(struct tlv_list_desc *list, +static inline void TLV_LIST_INIT(struct tlv_list_desc *list, void *data, __u32 space) { list->tlv_ptr = (struct tlv_desc *)data; list->tlv_space = space; } - + static inline int TLV_LIST_EMPTY(struct tlv_list_desc *list) -{ +{ return (list->tlv_space == 0); } @@ -348,7 +348,7 @@ static inline void TLV_LIST_STEP(struct tlv_list_desc *list) { __u16 tlv_space = TLV_ALIGN(ntohs(list->tlv_ptr->tlv_len)); - list->tlv_ptr = (struct tlv_desc *)((char *)list->tlv_ptr + tlv_space); + list->tlv_ptr = (struct tlv_desc *)((char *)list->tlv_ptr + tlv_space); list->tlv_space -= tlv_space; } @@ -372,15 +372,14 @@ struct tipc_genlmsghdr { #define TIPC_GENL_HDRLEN NLMSG_ALIGN(sizeof(struct tipc_genlmsghdr)) /* - * Configuration messages exchanged via TIPC sockets use the TIPC configuration - * message header, which is defined below. This structure is analogous - * to the Netlink message header, but fields are stored in network byte order - * and no padding is permitted between the header and the message data + * Configuration messages exchanged via TIPC sockets use the TIPC configuration + * message header, which is defined below. This structure is analogous + * to the Netlink message header, but fields are stored in network byte order + * and no padding is permitted between the header and the message data * that follows. */ -struct tipc_cfg_msg_hdr -{ +struct tipc_cfg_msg_hdr { __be32 tcm_len; /* Message length (including header) */ __be16 tcm_type; /* Command type */ __be16 tcm_flags; /* Additional flags */ diff --git a/net/tipc/Kconfig b/net/tipc/Kconfig index 0e7ce30fd567..0436927369f3 100644 --- a/net/tipc/Kconfig +++ b/net/tipc/Kconfig @@ -50,7 +50,7 @@ config TIPC_PORTS Specifies how many ports can be supported by a node. Can range from 127 to 65535 ports; default is 8191. - Setting this to a smaller value saves some memory, + Setting this to a smaller value saves some memory, setting it to higher allows for more ports. config TIPC_LOG diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index c0f3b096e7f5..9de32564984a 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -428,7 +428,7 @@ void tipc_bclink_recv_pkt(struct sk_buff *buf) static int rx_count = 0; #endif struct tipc_msg *msg = buf_msg(buf); - struct tipc_node* node = tipc_node_find(msg_prevnode(msg)); + struct tipc_node *node = tipc_node_find(msg_prevnode(msg)); u32 next_in; u32 seqno; struct sk_buff *deferred; diff --git a/net/tipc/config.c b/net/tipc/config.c index 6c67132f8652..e16750dcf3c1 100644 --- a/net/tipc/config.c +++ b/net/tipc/config.c @@ -322,8 +322,7 @@ struct sk_buff *tipc_cfg_do_cmd(u32 orig_node, u16 cmd, const void *request_area } else if (!tipc_remote_management) { rep_tlv_buf = tipc_cfg_reply_error_string(TIPC_CFG_NO_REMOTE); goto exit; - } - else if (cmd >= 0x4000) { + } else if (cmd >= 0x4000) { u32 domain = 0; if ((tipc_nametbl_translate(TIPC_ZM_SRV, 0, &domain) == 0) || diff --git a/net/tipc/discover.c b/net/tipc/discover.c index be28f5adc770..fa026bd91a68 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -130,7 +130,7 @@ void tipc_disc_recv_msg(struct sk_buff *buf, struct bearer *b_ptr) u32 net_id = msg_bc_netid(msg); u32 type = msg_type(msg); - msg_get_media_addr(msg,&media_addr); + msg_get_media_addr(msg, &media_addr); buf_discard(buf); if (net_id != tipc_net_id) diff --git a/net/tipc/eth_media.c b/net/tipc/eth_media.c index 101d9cb6a559..5dfe66357794 100644 --- a/net/tipc/eth_media.c +++ b/net/tipc/eth_media.c @@ -144,7 +144,7 @@ static int enable_bearer(struct tipc_bearer *tb_ptr) /* Find device with specified name */ - for_each_netdev(&init_net, pdev){ + for_each_netdev(&init_net, pdev) { if (!strncmp(pdev->name, driver_name, IFNAMSIZ)) { dev = pdev; break; @@ -155,7 +155,8 @@ static int enable_bearer(struct tipc_bearer *tb_ptr) /* Find Ethernet bearer for device (or create one) */ - for (;(eb_ptr != stop) && eb_ptr->dev && (eb_ptr->dev != dev); eb_ptr++); + while ((eb_ptr != stop) && eb_ptr->dev && (eb_ptr->dev != dev)) + eb_ptr++; if (eb_ptr == stop) return -EDQUOT; if (!eb_ptr->dev) { diff --git a/net/tipc/link.c b/net/tipc/link.c index 647f2ecfde50..ef203a1581cd 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -977,8 +977,7 @@ static int link_send_buf_fast(struct link *l_ptr, struct sk_buff *buf, l_ptr->next_out = buf; return res; } - } - else + } else *used_max_pkt = l_ptr->max_pkt; } return tipc_link_send_buf(l_ptr, buf); /* All other cases */ @@ -1132,10 +1131,10 @@ static int link_send_sections_long(struct port *sender, struct tipc_node *node; struct tipc_msg *hdr = &sender->publ.phdr; u32 dsz = msg_data_sz(hdr); - u32 max_pkt,fragm_sz,rest; + u32 max_pkt, fragm_sz, rest; struct tipc_msg fragm_hdr; - struct sk_buff *buf,*buf_chain,*prev; - u32 fragm_crs,fragm_rest,hsz,sect_rest; + struct sk_buff *buf, *buf_chain, *prev; + u32 fragm_crs, fragm_rest, hsz, sect_rest; const unchar *sect_crs; int curr_sect; u32 fragm_no; @@ -1212,7 +1211,7 @@ error: /* Initiate new fragment: */ if (rest <= fragm_sz) { fragm_sz = rest; - msg_set_type(&fragm_hdr,LAST_FRAGMENT); + msg_set_type(&fragm_hdr, LAST_FRAGMENT); } else { msg_set_type(&fragm_hdr, FRAGMENT); } @@ -1229,8 +1228,7 @@ error: fragm_crs = INT_H_SIZE; fragm_rest = fragm_sz; } - } - while (rest > 0); + } while (rest > 0); /* * Now we have a buffer chain. Select a link and check @@ -1333,7 +1331,7 @@ u32 tipc_link_push_packet(struct link *l_ptr) buf = l_ptr->proto_msg_queue; if (buf) { msg_set_ack(buf_msg(buf), mod(l_ptr->next_in_no - 1)); - msg_set_bcast_ack(buf_msg(buf),l_ptr->owner->bclink.last_in); + msg_set_bcast_ack(buf_msg(buf), l_ptr->owner->bclink.last_in); if (tipc_bearer_send(l_ptr->b_ptr, buf, &l_ptr->media_addr)) { l_ptr->unacked_window = 0; buf_discard(buf); @@ -1847,8 +1845,7 @@ u32 tipc_link_defer_pkt(struct sk_buff **head, } prev = crs; crs = crs->next; - } - while (crs); + } while (crs); /* Message is a duplicate of an existing message */ @@ -2215,11 +2212,11 @@ void tipc_link_changeover(struct link *l_ptr) if ((msg_user(msg) == MSG_BUNDLER) && split_bundles) { struct tipc_msg *m = msg_get_wrapped(msg); - unchar* pos = (unchar*)m; + unchar *pos = (unchar *)m; msgcount = msg_msgcnt(msg); while (msgcount--) { - msg_set_seqno(m,msg_seqno(msg)); + msg_set_seqno(m, msg_seqno(msg)); tipc_link_tunnel(l_ptr, &tunnel_hdr, m, msg_link_selector(m)); pos += align(msg_size(m)); @@ -2321,7 +2318,7 @@ static int link_recv_changeover_msg(struct link **l_ptr, if (msg_typ == DUPLICATE_MSG) { if (less(msg_seqno(msg), mod(dest_link->next_in_no))) goto exit; - *buf = buf_extract(tunnel_buf,INT_H_SIZE); + *buf = buf_extract(tunnel_buf, INT_H_SIZE); if (*buf == NULL) { warn("Link changeover error, duplicate msg dropped\n"); goto exit; @@ -2552,8 +2549,8 @@ int tipc_link_recv_fragment(struct sk_buff **pending, struct sk_buff **fb, /* Prepare buffer for subsequent fragments. */ set_long_msg_seqno(pbuf, long_msg_seq_no); - set_fragm_size(pbuf,fragm_sz); - set_expected_frags(pbuf,exp_fragm_cnt - 1); + set_fragm_size(pbuf, fragm_sz); + set_expected_frags(pbuf, exp_fragm_cnt - 1); } else { warn("Link unable to reassemble fragmented message\n"); } @@ -2580,7 +2577,7 @@ int tipc_link_recv_fragment(struct sk_buff **pending, struct sk_buff **fb, *m = buf_msg(pbuf); return 1; } - set_expected_frags(pbuf,exp_frags); + set_expected_frags(pbuf, exp_frags); return 0; } buf_discard(fbuf); diff --git a/net/tipc/link.h b/net/tipc/link.h index eca19c247b79..70967e637027 100644 --- a/net/tipc/link.h +++ b/net/tipc/link.h @@ -229,8 +229,8 @@ struct sk_buff *tipc_link_cmd_reset_stats(const void *req_tlv_area, int req_tlv_ void tipc_link_reset(struct link *l_ptr); int tipc_link_send(struct sk_buff *buf, u32 dest, u32 selector); int tipc_link_send_buf(struct link *l_ptr, struct sk_buff *buf); -u32 tipc_link_get_max_pkt(u32 dest,u32 selector); -int tipc_link_send_sections_fast(struct port* sender, +u32 tipc_link_get_max_pkt(u32 dest, u32 selector); +int tipc_link_send_sections_fast(struct port *sender, struct iovec const *msg_sect, const u32 num_sect, u32 destnode); diff --git a/net/tipc/msg.c b/net/tipc/msg.c index 2571ffb4d350..e81d43a8ea3d 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -91,7 +91,7 @@ int tipc_msg_calc_data_size(struct iovec const *msg_sect, u32 num_sect) int tipc_msg_build(struct tipc_msg *hdr, struct iovec const *msg_sect, u32 num_sect, - int max_size, int usrmem, struct sk_buff** buf) + int max_size, int usrmem, struct sk_buff **buf) { int dsz, sz, hsz, pos, res, cnt; @@ -161,10 +161,10 @@ void tipc_msg_dbg(struct print_buf *buf, struct tipc_msg *msg, const char *str) tipc_printf(buf, "LAST:"); break; default: - tipc_printf(buf, "UNKNOWN:%x",msg_type(msg)); + tipc_printf(buf, "UNKNOWN:%x", msg_type(msg)); } - tipc_printf(buf, "NO(%u/%u):",msg_long_msgno(msg), + tipc_printf(buf, "NO(%u/%u):", msg_long_msgno(msg), msg_fragm_no(msg)); break; case TIPC_LOW_IMPORTANCE: @@ -190,7 +190,7 @@ void tipc_msg_dbg(struct print_buf *buf, struct tipc_msg *msg, const char *str) tipc_printf(buf, "DIR:"); break; default: - tipc_printf(buf, "UNKNOWN TYPE %u",msg_type(msg)); + tipc_printf(buf, "UNKNOWN TYPE %u", msg_type(msg)); } if (msg_routed(msg) && !msg_non_seq(msg)) tipc_printf(buf, "ROUT:"); @@ -208,7 +208,7 @@ void tipc_msg_dbg(struct print_buf *buf, struct tipc_msg *msg, const char *str) tipc_printf(buf, "WDRW:"); break; default: - tipc_printf(buf, "UNKNOWN:%x",msg_type(msg)); + tipc_printf(buf, "UNKNOWN:%x", msg_type(msg)); } if (msg_routed(msg)) tipc_printf(buf, "ROUT:"); @@ -227,39 +227,39 @@ void tipc_msg_dbg(struct print_buf *buf, struct tipc_msg *msg, const char *str) break; case CONN_ACK: tipc_printf(buf, "CONN_ACK:"); - tipc_printf(buf, "ACK(%u):",msg_msgcnt(msg)); + tipc_printf(buf, "ACK(%u):", msg_msgcnt(msg)); break; default: - tipc_printf(buf, "UNKNOWN TYPE:%x",msg_type(msg)); + tipc_printf(buf, "UNKNOWN TYPE:%x", msg_type(msg)); } if (msg_routed(msg)) tipc_printf(buf, "ROUT:"); if (msg_reroute_cnt(msg)) - tipc_printf(buf, "REROUTED(%u):",msg_reroute_cnt(msg)); + tipc_printf(buf, "REROUTED(%u):", msg_reroute_cnt(msg)); break; case LINK_PROTOCOL: - tipc_printf(buf, "PROT:TIM(%u):",msg_timestamp(msg)); + tipc_printf(buf, "PROT:TIM(%u):", msg_timestamp(msg)); switch (msg_type(msg)) { case STATE_MSG: tipc_printf(buf, "STATE:"); - tipc_printf(buf, "%s:",msg_probe(msg) ? "PRB" :""); - tipc_printf(buf, "NXS(%u):",msg_next_sent(msg)); - tipc_printf(buf, "GAP(%u):",msg_seq_gap(msg)); - tipc_printf(buf, "LSTBC(%u):",msg_last_bcast(msg)); + tipc_printf(buf, "%s:", msg_probe(msg) ? "PRB" : ""); + tipc_printf(buf, "NXS(%u):", msg_next_sent(msg)); + tipc_printf(buf, "GAP(%u):", msg_seq_gap(msg)); + tipc_printf(buf, "LSTBC(%u):", msg_last_bcast(msg)); break; case RESET_MSG: tipc_printf(buf, "RESET:"); if (msg_size(msg) != msg_hdr_sz(msg)) - tipc_printf(buf, "BEAR:%s:",msg_data(msg)); + tipc_printf(buf, "BEAR:%s:", msg_data(msg)); break; case ACTIVATE_MSG: tipc_printf(buf, "ACTIVATE:"); break; default: - tipc_printf(buf, "UNKNOWN TYPE:%x",msg_type(msg)); + tipc_printf(buf, "UNKNOWN TYPE:%x", msg_type(msg)); } - tipc_printf(buf, "PLANE(%c):",msg_net_plane(msg)); - tipc_printf(buf, "SESS(%u):",msg_session(msg)); + tipc_printf(buf, "PLANE(%c):", msg_net_plane(msg)); + tipc_printf(buf, "SESS(%u):", msg_session(msg)); break; case CHANGEOVER_PROTOCOL: tipc_printf(buf, "TUNL:"); @@ -269,10 +269,10 @@ void tipc_msg_dbg(struct print_buf *buf, struct tipc_msg *msg, const char *str) break; case ORIGINAL_MSG: tipc_printf(buf, "ORIG:"); - tipc_printf(buf, "EXP(%u)",msg_msgcnt(msg)); + tipc_printf(buf, "EXP(%u)", msg_msgcnt(msg)); break; default: - tipc_printf(buf, "UNKNOWN TYPE:%x",msg_type(msg)); + tipc_printf(buf, "UNKNOWN TYPE:%x", msg_type(msg)); } break; case ROUTE_DISTRIBUTOR: @@ -280,26 +280,26 @@ void tipc_msg_dbg(struct print_buf *buf, struct tipc_msg *msg, const char *str) switch (msg_type(msg)) { case EXT_ROUTING_TABLE: tipc_printf(buf, "EXT_TBL:"); - tipc_printf(buf, "TO:%x:",msg_remote_node(msg)); + tipc_printf(buf, "TO:%x:", msg_remote_node(msg)); break; case LOCAL_ROUTING_TABLE: tipc_printf(buf, "LOCAL_TBL:"); - tipc_printf(buf, "TO:%x:",msg_remote_node(msg)); + tipc_printf(buf, "TO:%x:", msg_remote_node(msg)); break; case SLAVE_ROUTING_TABLE: tipc_printf(buf, "DP_TBL:"); - tipc_printf(buf, "TO:%x:",msg_remote_node(msg)); + tipc_printf(buf, "TO:%x:", msg_remote_node(msg)); break; case ROUTE_ADDITION: tipc_printf(buf, "ADD:"); - tipc_printf(buf, "TO:%x:",msg_remote_node(msg)); + tipc_printf(buf, "TO:%x:", msg_remote_node(msg)); break; case ROUTE_REMOVAL: tipc_printf(buf, "REMOVE:"); - tipc_printf(buf, "TO:%x:",msg_remote_node(msg)); + tipc_printf(buf, "TO:%x:", msg_remote_node(msg)); break; default: - tipc_printf(buf, "UNKNOWN TYPE:%x",msg_type(msg)); + tipc_printf(buf, "UNKNOWN TYPE:%x", msg_type(msg)); } break; case LINK_CONFIG: @@ -312,7 +312,7 @@ void tipc_msg_dbg(struct print_buf *buf, struct tipc_msg *msg, const char *str) tipc_printf(buf, "DSC_RESP:"); break; default: - tipc_printf(buf, "UNKNOWN TYPE:%x:",msg_type(msg)); + tipc_printf(buf, "UNKNOWN TYPE:%x:", msg_type(msg)); break; } break; @@ -393,8 +393,8 @@ void tipc_msg_dbg(struct print_buf *buf, struct tipc_msg *msg, const char *str) } if (msg_user(msg) == LINK_CONFIG) { - u32* raw = (u32*)msg; - struct tipc_media_addr* orig = (struct tipc_media_addr*)&raw[5]; + u32 *raw = (u32 *)msg; + struct tipc_media_addr *orig = (struct tipc_media_addr *)&raw[5]; tipc_printf(buf, ":REQL(%u):", msg_req_links(msg)); tipc_printf(buf, ":DDOM(%x):", msg_dest_domain(msg)); tipc_printf(buf, ":NETID(%u):", msg_bc_netid(msg)); diff --git a/net/tipc/msg.h b/net/tipc/msg.h index 68b65ef3e74b..92c4c4fd7b3f 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -174,7 +174,7 @@ static inline u32 msg_hdr_sz(struct tipc_msg *m) return msg_bits(m, 0, 21, 0xf) << 2; } -static inline void msg_set_hdr_sz(struct tipc_msg *m,u32 n) +static inline void msg_set_hdr_sz(struct tipc_msg *m, u32 n) { msg_set_bits(m, 0, 21, 0xf, n>>2); } @@ -425,7 +425,7 @@ static inline u32 msg_routed(struct tipc_msg *m) { if (likely(msg_short(m))) return 0; - return(msg_destnode(m) ^ msg_orignode(m)) >> 11; + return (msg_destnode(m) ^ msg_orignode(m)) >> 11; } static inline u32 msg_nametype(struct tipc_msg *m) @@ -863,7 +863,7 @@ void tipc_msg_init(struct tipc_msg *m, u32 user, u32 type, int tipc_msg_calc_data_size(struct iovec const *msg_sect, u32 num_sect); int tipc_msg_build(struct tipc_msg *hdr, struct iovec const *msg_sect, u32 num_sect, - int max_size, int usrmem, struct sk_buff** buf); + int max_size, int usrmem, struct sk_buff **buf); static inline void msg_set_media_addr(struct tipc_msg *m, struct tipc_media_addr *a) { @@ -872,7 +872,7 @@ static inline void msg_set_media_addr(struct tipc_msg *m, struct tipc_media_addr static inline void msg_get_media_addr(struct tipc_msg *m, struct tipc_media_addr *a) { - memcpy(a, &((int*)m)[5], sizeof(*a)); + memcpy(a, &((int *)m)[5], sizeof(*a)); } #endif diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index ddc2ad4c2d32..46b2f31f96a1 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -296,8 +296,8 @@ static struct publication *tipc_nameseq_insert_publ(struct name_seq *nseq, sseq = &nseq->sseqs[inspos]; freesseq = &nseq->sseqs[nseq->first_free]; - memmove(sseq + 1, sseq, (freesseq - sseq) * sizeof (*sseq)); - memset(sseq, 0, sizeof (*sseq)); + memmove(sseq + 1, sseq, (freesseq - sseq) * sizeof(*sseq)); + memset(sseq, 0, sizeof(*sseq)); nseq->first_free++; sseq->lower = lower; sseq->upper = upper; @@ -471,7 +471,7 @@ end_node: if (!sseq->zone_list) { free = &nseq->sseqs[nseq->first_free--]; - memmove(sseq, sseq + 1, (free - (sseq + 1)) * sizeof (*sseq)); + memmove(sseq, sseq + 1, (free - (sseq + 1)) * sizeof(*sseq)); removed_subseq = 1; } @@ -507,7 +507,7 @@ static void tipc_nameseq_subscribe(struct name_seq *nseq, struct subscription *s while (sseq != &nseq->sseqs[nseq->first_free]) { struct publication *zl = sseq->zone_list; - if (zl && tipc_subscr_overlap(s,sseq->lower,sseq->upper)) { + if (zl && tipc_subscr_overlap(s, sseq->lower, sseq->upper)) { struct publication *crs = zl; int must_report = 1; @@ -798,7 +798,7 @@ void tipc_nametbl_subscribe(struct subscription *s) if (!seq) { seq = tipc_nameseq_create(type, &table.types[hash(type)]); } - if (seq){ + if (seq) { spin_lock_bh(&seq->lock); tipc_nameseq_subscribe(seq, s); spin_unlock_bh(&seq->lock); @@ -819,7 +819,7 @@ void tipc_nametbl_unsubscribe(struct subscription *s) write_lock_bh(&tipc_nametbl_lock); seq = nametbl_find_seq(s->seq.type); - if (seq != NULL){ + if (seq != NULL) { spin_lock_bh(&seq->lock); list_del_init(&s->nameseq_list); spin_unlock_bh(&seq->lock); @@ -852,7 +852,7 @@ static void subseq_list(struct sub_seq *sseq, struct print_buf *buf, u32 depth, } do { - sprintf (portIdStr, "<%u.%u.%u:%u>", + sprintf(portIdStr, "<%u.%u.%u:%u>", tipc_zone(publ->node), tipc_cluster(publ->node), tipc_node(publ->node), publ->ref); tipc_printf(buf, "%-26s ", portIdStr); diff --git a/net/tipc/name_table.h b/net/tipc/name_table.h index 139882d4ed00..d228bd682655 100644 --- a/net/tipc/name_table.h +++ b/net/tipc/name_table.h @@ -46,7 +46,7 @@ struct port_list; * TIPC name types reserved for internal TIPC use (both current and planned) */ -#define TIPC_ZM_SRV 3 /* zone master service name type */ +#define TIPC_ZM_SRV 3 /* zone master service name type */ /** diff --git a/net/tipc/node.c b/net/tipc/node.c index 126d774883dd..2ed162f91a08 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -334,7 +334,7 @@ static void node_lost_contact(struct tipc_node *n_ptr) /* Clean up broadcast reception remains */ n_ptr->bclink.gap_after = n_ptr->bclink.gap_to = 0; while (n_ptr->bclink.deferred_head) { - struct sk_buff* buf = n_ptr->bclink.deferred_head; + struct sk_buff *buf = n_ptr->bclink.deferred_head; n_ptr->bclink.deferred_head = buf->next; buf_discard(buf); } diff --git a/net/tipc/port.c b/net/tipc/port.c index db14b7e0afdc..78fcb75bb082 100644 --- a/net/tipc/port.c +++ b/net/tipc/port.c @@ -54,8 +54,8 @@ static DEFINE_SPINLOCK(queue_lock); static LIST_HEAD(ports); static void port_handle_node_down(unsigned long ref); -static struct sk_buff* port_build_self_abort_msg(struct port *,u32 err); -static struct sk_buff* port_build_peer_abort_msg(struct port *,u32 err); +static struct sk_buff *port_build_self_abort_msg(struct port *, u32 err); +static struct sk_buff *port_build_peer_abort_msg(struct port *, u32 err); static void port_timeout(unsigned long ref); @@ -155,7 +155,7 @@ int tipc_multicast(u32 ref, struct tipc_name_seq const *seq, void tipc_port_recv_mcast(struct sk_buff *buf, struct port_list *dp) { - struct tipc_msg* msg; + struct tipc_msg *msg; struct port_list dports = {0, NULL, }; struct port_list *item = dp; int cnt = 0; @@ -193,7 +193,7 @@ void tipc_port_recv_mcast(struct sk_buff *buf, struct port_list *dp) if ((index == 0) && (cnt != 0)) { item = item->next; } - msg_set_destport(buf_msg(b),item->ports[index]); + msg_set_destport(buf_msg(b), item->ports[index]); tipc_port_recv_msg(b); } } @@ -484,7 +484,7 @@ static void port_timeout(unsigned long ref) static void port_handle_node_down(unsigned long ref) { struct port *p_ptr = tipc_port_lock(ref); - struct sk_buff* buf = NULL; + struct sk_buff *buf = NULL; if (!p_ptr) return; @@ -620,8 +620,7 @@ static void port_print(struct port *p_ptr, struct print_buf *buf, int full_id) tipc_printf(buf, " via {%u,%u}", p_ptr->publ.conn_type, p_ptr->publ.conn_instance); - } - else if (p_ptr->publ.published) { + } else if (p_ptr->publ.published) { tipc_printf(buf, " bound to"); list_for_each_entry(publ, &p_ptr->publications, pport_list) { if (publ->lower == publ->upper) @@ -1099,7 +1098,7 @@ int tipc_connect2port(u32 ref, struct tipc_portid const *peer) p_ptr->publ.connected = 1; k_start_timer(&p_ptr->timer, p_ptr->probing_interval); - tipc_nodesub_subscribe(&p_ptr->subscription,peer->node, + tipc_nodesub_subscribe(&p_ptr->subscription, peer->node, (void *)(unsigned long)ref, (net_ev_handler)port_handle_node_down); res = 0; diff --git a/net/tipc/port.h b/net/tipc/port.h index a9c528799f2f..8e84b989949c 100644 --- a/net/tipc/port.h +++ b/net/tipc/port.h @@ -258,7 +258,7 @@ static inline void tipc_port_unlock(struct port *p_ptr) spin_unlock_bh(p_ptr->publ.lock); } -static inline struct port* tipc_port_deref(u32 ref) +static inline struct port *tipc_port_deref(u32 ref) { return (struct port *)tipc_ref_deref(ref); } diff --git a/net/tipc/ref.c b/net/tipc/ref.c index ab8ad32d8c20..3974529a66e7 100644 --- a/net/tipc/ref.c +++ b/net/tipc/ref.c @@ -178,14 +178,12 @@ u32 tipc_ref_acquire(void *object, spinlock_t **lock) next_plus_upper = entry->ref; tipc_ref_table.first_free = next_plus_upper & index_mask; ref = (next_plus_upper & ~index_mask) + index; - } - else if (tipc_ref_table.init_point < tipc_ref_table.capacity) { + } else if (tipc_ref_table.init_point < tipc_ref_table.capacity) { index = tipc_ref_table.init_point++; entry = &(tipc_ref_table.entries[index]); spin_lock_init(&entry->lock); ref = tipc_ref_table.start_mask + index; - } - else { + } else { ref = 0; } write_unlock_bh(&ref_table_lock); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 1a2eb23c6223..e9fc5df79eb0 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -375,7 +375,7 @@ static int bind(struct socket *sock, struct sockaddr *uaddr, int uaddr_len) * * NOTE: This routine doesn't need to take the socket lock since it only * accesses socket information that is unchanging (or which changes in - * a completely predictable manner). + * a completely predictable manner). */ static int get_name(struct socket *sock, struct sockaddr *uaddr, @@ -570,14 +570,12 @@ static int send_msg(struct kiocb *iocb, struct socket *sock, dest->addr.name.domain, m->msg_iovlen, m->msg_iov); - } - else if (dest->addrtype == TIPC_ADDR_ID) { + } else if (dest->addrtype == TIPC_ADDR_ID) { res = tipc_send2port(tport->ref, &dest->addr.id, m->msg_iovlen, m->msg_iov); - } - else if (dest->addrtype == TIPC_ADDR_MCAST) { + } else if (dest->addrtype == TIPC_ADDR_MCAST) { if (needs_conn) { res = -EOPNOTSUPP; break; @@ -812,8 +810,8 @@ static void set_orig_addr(struct msghdr *m, struct tipc_msg *msg) addr->addrtype = TIPC_ADDR_ID; addr->addr.id.ref = msg_origport(msg); addr->addr.id.node = msg_orignode(msg); - addr->addr.name.domain = 0; /* could leave uninitialized */ - addr->scope = 0; /* could leave uninitialized */ + addr->addr.name.domain = 0; /* could leave uninitialized */ + addr->scope = 0; /* could leave uninitialized */ m->msg_namelen = sizeof(struct sockaddr_tipc); } } @@ -1743,10 +1741,10 @@ static int getsockopt(struct socket *sock, value = jiffies_to_msecs(tipc_sk(sk)->conn_timeout); /* no need to set "res", since already 0 at this point */ break; - case TIPC_NODE_RECVQ_DEPTH: + case TIPC_NODE_RECVQ_DEPTH: value = (u32)atomic_read(&tipc_queue_size); break; - case TIPC_SOCK_RECVQ_DEPTH: + case TIPC_SOCK_RECVQ_DEPTH: value = skb_queue_len(&sk->sk_receive_queue); break; default: @@ -1772,7 +1770,7 @@ static int getsockopt(struct socket *sock, */ static const struct proto_ops msg_ops = { - .owner = THIS_MODULE, + .owner = THIS_MODULE, .family = AF_TIPC, .release = release, .bind = bind, @@ -1793,7 +1791,7 @@ static const struct proto_ops msg_ops = { }; static const struct proto_ops packet_ops = { - .owner = THIS_MODULE, + .owner = THIS_MODULE, .family = AF_TIPC, .release = release, .bind = bind, @@ -1814,7 +1812,7 @@ static const struct proto_ops packet_ops = { }; static const struct proto_ops stream_ops = { - .owner = THIS_MODULE, + .owner = THIS_MODULE, .family = AF_TIPC, .release = release, .bind = bind, @@ -1835,7 +1833,7 @@ static const struct proto_ops stream_ops = { }; static const struct net_proto_family tipc_family_ops = { - .owner = THIS_MODULE, + .owner = THIS_MODULE, .family = AF_TIPC, .create = tipc_create }; diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c index 510271152165..acc30e1833c9 100644 --- a/net/tipc/subscr.c +++ b/net/tipc/subscr.c @@ -538,7 +538,7 @@ int tipc_subscr_start(void) struct tipc_name_seq seq = {TIPC_TOP_SRV, TIPC_TOP_SRV, TIPC_TOP_SRV}; int res; - memset(&topsrv, 0, sizeof (topsrv)); + memset(&topsrv, 0, sizeof(topsrv)); spin_lock_init(&topsrv.lock); INIT_LIST_HEAD(&topsrv.subscriber_list); -- cgit v1.2.3 From 8f33d5277fada0291ea495f7fd44a3e7b7aa41d3 Mon Sep 17 00:00:00 2001 From: Guennadi Liakhovetski Date: Wed, 22 Dec 2010 14:46:46 +0100 Subject: dmaengine: provide dummy functions for DMA_ENGINE=n This lets drivers, optionally using the dmaengine, build with DMA_ENGINE unselected. Signed-off-by: Guennadi Liakhovetski Signed-off-by: Dan Williams --- include/linux/dmaengine.h | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 9d8688b92d8b..8cd00ad98d37 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -824,6 +824,8 @@ enum dma_status dma_sync_wait(struct dma_chan *chan, dma_cookie_t cookie); #ifdef CONFIG_DMA_ENGINE enum dma_status dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx); void dma_issue_pending_all(void); +struct dma_chan *__dma_request_channel(dma_cap_mask_t *mask, dma_filter_fn fn, void *fn_param); +void dma_release_channel(struct dma_chan *chan); #else static inline enum dma_status dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx) { @@ -831,7 +833,14 @@ static inline enum dma_status dma_wait_for_async_tx(struct dma_async_tx_descript } static inline void dma_issue_pending_all(void) { - do { } while (0); +} +static inline struct dma_chan *__dma_request_channel(dma_cap_mask_t *mask, + dma_filter_fn fn, void *fn_param) +{ + return NULL; +} +static inline void dma_release_channel(struct dma_chan *chan) +{ } #endif @@ -842,8 +851,6 @@ void dma_async_device_unregister(struct dma_device *device); void dma_run_dependencies(struct dma_async_tx_descriptor *tx); struct dma_chan *dma_find_channel(enum dma_transaction_type tx_type); #define dma_request_channel(mask, x, y) __dma_request_channel(&(mask), x, y) -struct dma_chan *__dma_request_channel(dma_cap_mask_t *mask, dma_filter_fn fn, void *fn_param); -void dma_release_channel(struct dma_chan *chan); /* --- Helper iov-locking functions --- */ -- cgit v1.2.3 From 68763c890eb2a60f9b50a061502f94e0cf20fdfe Mon Sep 17 00:00:00 2001 From: Michal Simek Date: Sun, 2 Jan 2011 22:54:09 +0000 Subject: trivial: Fix typo fault in netdevice.h Signed-off-by: Michal Simek Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index cc916c5c3279..0f6b1c965815 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -732,7 +732,7 @@ struct xps_dev_maps { * neither operation. * * void (*ndo_vlan_rx_register)(struct net_device *dev, struct vlan_group *grp); - * If device support VLAN receive accleration + * If device support VLAN receive acceleration * (ie. dev->features & NETIF_F_HW_VLAN_RX), then this function is called * when vlan groups for the device changes. Note: grp is NULL * if no vlan's groups are being used. -- cgit v1.2.3 From 7b26e5ebd8b27b0126a84ae7f9a42aa8293d6c48 Mon Sep 17 00:00:00 2001 From: Francois-Xavier Le Bail Date: Tue, 4 Jan 2011 09:10:20 +0000 Subject: net: typos in comments in include/linux/igmp.h There are typos in comments in include/linux/igmp.h: 83 #define IGMP_HOST_MEMBERSHIP_QUERY 0x11 /* From RFC1112 */ 84 #define IGMP_HOST_MEMBERSHIP_REPORT 0x12 /* Ditto */ [snip] 88 #define IGMPV2_HOST_MEMBERSHIP_REPORT 0x16 /* V2 version of 0x11 */ 89 #define IGMP_HOST_LEAVE_MESSAGE 0x17 90 #define IGMPV3_HOST_MEMBERSHIP_REPORT 0x22 /* V3 version of 0x11 */ The line 88 and 90 are about REPORT messages. The IGMP_HOST_MEMBERSHIP_REPORT (IGMP V1) value is 0x12. So the comment on line 88 must be /* V2 version of 0x12 */, and the comment on line 90 must be /* V3 version of 0x12 */. Signed-off-by: Francois-Xavier Le Bail Signed-off-by: David S. Miller --- include/linux/igmp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/igmp.h b/include/linux/igmp.h index c4987f265109..74cfcff0148b 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -85,9 +85,9 @@ struct igmpv3_query { #define IGMP_DVMRP 0x13 /* DVMRP routing */ #define IGMP_PIM 0x14 /* PIM routing */ #define IGMP_TRACE 0x15 -#define IGMPV2_HOST_MEMBERSHIP_REPORT 0x16 /* V2 version of 0x11 */ +#define IGMPV2_HOST_MEMBERSHIP_REPORT 0x16 /* V2 version of 0x12 */ #define IGMP_HOST_LEAVE_MESSAGE 0x17 -#define IGMPV3_HOST_MEMBERSHIP_REPORT 0x22 /* V3 version of 0x11 */ +#define IGMPV3_HOST_MEMBERSHIP_REPORT 0x22 /* V3 version of 0x12 */ #define IGMP_MTRACE_RESP 0x1e #define IGMP_MTRACE 0x1f -- cgit v1.2.3 From 6bf4123760a5aece6e4829ce90b70b6ffd751d65 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Wed, 5 Jan 2011 12:50:16 +1100 Subject: sched: Change wait_for_completion_*_timeout() to return a signed long wait_for_completion_*_timeout() can return: 0: if the wait timed out -ve: if the wait was interrupted +ve: if the completion was completed. As they currently return an 'unsigned long', the last two cases are not easily distinguished which can easily result in buggy code, as is the case for the recently added wait_for_completion_interruptible_timeout() call in net/sunrpc/cache.c So change them both to return 'long'. As MAX_SCHEDULE_TIMEOUT is LONG_MAX, a large +ve return value should never overflow. Signed-off-by: NeilBrown Cc: Peter Zijlstra Cc: J. Bruce Fields Cc: Andrew Morton Cc: Linus Torvalds LKML-Reference: <20110105125016.64ccab0e@notabene.brown> Signed-off-by: Ingo Molnar --- include/linux/completion.h | 8 ++++---- kernel/sched.c | 4 ++-- 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/completion.h b/include/linux/completion.h index 36d57f74cd01..51494e6b5548 100644 --- a/include/linux/completion.h +++ b/include/linux/completion.h @@ -81,10 +81,10 @@ extern int wait_for_completion_interruptible(struct completion *x); extern int wait_for_completion_killable(struct completion *x); extern unsigned long wait_for_completion_timeout(struct completion *x, unsigned long timeout); -extern unsigned long wait_for_completion_interruptible_timeout( - struct completion *x, unsigned long timeout); -extern unsigned long wait_for_completion_killable_timeout( - struct completion *x, unsigned long timeout); +extern long wait_for_completion_interruptible_timeout( + struct completion *x, unsigned long timeout); +extern long wait_for_completion_killable_timeout( + struct completion *x, unsigned long timeout); extern bool try_wait_for_completion(struct completion *x); extern bool completion_done(struct completion *x); diff --git a/kernel/sched.c b/kernel/sched.c index f2f914e0c47c..114a0deb2b01 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -4395,7 +4395,7 @@ EXPORT_SYMBOL(wait_for_completion_interruptible); * This waits for either a completion of a specific task to be signaled or for a * specified timeout to expire. It is interruptible. The timeout is in jiffies. */ -unsigned long __sched +long __sched wait_for_completion_interruptible_timeout(struct completion *x, unsigned long timeout) { @@ -4428,7 +4428,7 @@ EXPORT_SYMBOL(wait_for_completion_killable); * signaled or for a specified timeout to expire. It can be * interrupted by a kill signal. The timeout is in jiffies. */ -unsigned long __sched +long __sched wait_for_completion_killable_timeout(struct completion *x, unsigned long timeout) { -- cgit v1.2.3 From 68b65f7305e54b822b2483c60de7d7b017526a92 Mon Sep 17 00:00:00 2001 From: Russell King Date: Wed, 22 Dec 2010 17:24:39 +0000 Subject: ARM: PL011: Add support for transmit DMA Add DMA engine support for transmit to the PL011 driver. Based on a patch from Linus Walliej, with the following changes: - remove RX DMA support. As PL011 doesn't give us receive timeout interrupts, we only get notified of received data when the RX DMA has completed. This rather sucks for interactive use of the TTY. - remove abuse of completions. Completions are supposed to be for events, not to tell what condition buffers are in. Replace it with a simple 'queued' bool. - fix locking - it is only safe to access the circular buffer with the port lock held. - only map the DMA buffer when required - if we're ever behind an IOMMU this helps keep IOMMU usage down, and also ensures that we're legal when we change the scatterlist entry length. - fix XON/XOFF sending - we must send XON/XOFF characters out as soon as possible - waiting for up to 4095 characters in the DMA buffer to be sent first is not acceptable. - fix XON/XOFF receive handling - we need to stop DMA when instructed to by the TTY layer, and restart it again when instructed to. There is a subtle problem here: we must not completely empty the circular buffer with DMA, otherwise we will not be notified of XON. - change the 'enable_dma' flag into a 'using DMA' flag, and track whether we can use TX DMA by whether the channel pointer is non-NULL. This gives us more control over whether we use DMA in the driver. - we don't need to have the TX DMA buffer continually allocated for each port - instead, allocate it when the port starts up, and free it when it's shut down. Update the 'using DMA' flag if we get the buffer, and adjust the TTY FIFO size appropriately. - if we're going to use PIO to send characters, use the existing IRQ based functionality rather than reimplementing it. This also ensures we call uart_write_wakeup() at the appropriate time, otherwise we'll stall. - use DMA engine helper functions for type safety. - fix init when built as a module - we can't have to initcall functions, so we must settle on one. This means we can eliminate the deferred DMA initialization. - there is no need to terminate transfers on a failed prep_slave_sg() call - nothing has been setup, so nothing needs to be terminated. This avoids a potential deadlock in the DMA engine code (tasklet->callback->failed prepare->terminate->tasklet_disable which then ends up waiting for the tasklet to finish running.) - Dan says that the submission callback should not return an error: | dma_submit_error() is something I should have removed after commit | a0587bcf "ioat1: move descriptor allocation from submit to prep" all | errors should be notified by prep failing to return a descriptor | handle. Negative dma_cookie_t values are only returned by the | dma_async_memcpy* calls which translate a prep failure into -ENOMEM. So remove the error handling at that point. This also solves the potential deadlock mentioned in the previous comment. Acked-by: Linus Walleij Signed-off-by: Russell King --- drivers/serial/amba-pl011.c | 508 +++++++++++++++++++++++++++++++++++++++++++- include/linux/amba/serial.h | 7 + 2 files changed, 513 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/serial/amba-pl011.c b/drivers/serial/amba-pl011.c index f741a8b51400..ab025dc52fa4 100644 --- a/drivers/serial/amba-pl011.c +++ b/drivers/serial/amba-pl011.c @@ -7,6 +7,7 @@ * * Copyright 1999 ARM Limited * Copyright (C) 2000 Deep Blue Solutions Ltd. + * Copyright (C) 2010 ST-Ericsson SA * * 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 @@ -48,6 +49,9 @@ #include #include #include +#include +#include +#include #include #include @@ -88,6 +92,14 @@ static struct vendor_data vendor_st = { .oversampling = true, }; +/* Deals with DMA transactions */ +struct pl011_dmatx_data { + struct dma_chan *chan; + struct scatterlist sg; + char *buf; + bool queued; +}; + /* * We wrap our port structure around the generic uart_port. */ @@ -95,6 +107,7 @@ struct uart_amba_port { struct uart_port port; struct clk *clk; const struct vendor_data *vendor; + unsigned int dmacr; /* dma control reg */ unsigned int im; /* interrupt mask */ unsigned int old_status; unsigned int fifosize; /* vendor-specific */ @@ -102,22 +115,500 @@ struct uart_amba_port { unsigned int lcrh_rx; /* vendor-specific */ bool autorts; char type[12]; +#ifdef CONFIG_DMA_ENGINE + /* DMA stuff */ + bool using_dma; + struct pl011_dmatx_data dmatx; +#endif +}; + +/* + * All the DMA operation mode stuff goes inside this ifdef. + * This assumes that you have a generic DMA device interface, + * no custom DMA interfaces are supported. + */ +#ifdef CONFIG_DMA_ENGINE + +#define PL011_DMA_BUFFER_SIZE PAGE_SIZE + +static void pl011_dma_probe_initcall(struct uart_amba_port *uap) +{ + /* DMA is the sole user of the platform data right now */ + struct amba_pl011_data *plat = uap->port.dev->platform_data; + struct dma_slave_config tx_conf = { + .dst_addr = uap->port.mapbase + UART01x_DR, + .dst_addr_width = DMA_SLAVE_BUSWIDTH_1_BYTE, + .direction = DMA_TO_DEVICE, + .dst_maxburst = uap->fifosize >> 1, + }; + struct dma_chan *chan; + dma_cap_mask_t mask; + + /* We need platform data */ + if (!plat || !plat->dma_filter) { + dev_info(uap->port.dev, "no DMA platform data\n"); + return; + } + + /* Try to acquire a generic DMA engine slave channel */ + dma_cap_zero(mask); + dma_cap_set(DMA_SLAVE, mask); + + chan = dma_request_channel(mask, plat->dma_filter, plat->dma_tx_param); + if (!chan) { + dev_err(uap->port.dev, "no TX DMA channel!\n"); + return; + } + + dmaengine_slave_config(chan, &tx_conf); + uap->dmatx.chan = chan; + + dev_info(uap->port.dev, "DMA channel TX %s\n", + dma_chan_name(uap->dmatx.chan)); +} + +#ifndef MODULE +/* + * Stack up the UARTs and let the above initcall be done at device + * initcall time, because the serial driver is called as an arch + * initcall, and at this time the DMA subsystem is not yet registered. + * At this point the driver will switch over to using DMA where desired. + */ +struct dma_uap { + struct list_head node; + struct uart_amba_port *uap; }; +static LIST_HEAD(pl011_dma_uarts); + +static int __init pl011_dma_initcall(void) +{ + struct list_head *node, *tmp; + + list_for_each_safe(node, tmp, &pl011_dma_uarts) { + struct dma_uap *dmau = list_entry(node, struct dma_uap, node); + pl011_dma_probe_initcall(dmau->uap); + list_del(node); + kfree(dmau); + } + return 0; +} + +device_initcall(pl011_dma_initcall); + +static void pl011_dma_probe(struct uart_amba_port *uap) +{ + struct dma_uap *dmau = kzalloc(sizeof(struct dma_uap), GFP_KERNEL); + if (dmau) { + dmau->uap = uap; + list_add_tail(&dmau->node, &pl011_dma_uarts); + } +} +#else +static void pl011_dma_probe(struct uart_amba_port *uap) +{ + pl011_dma_probe_initcall(uap); +} +#endif + +static void pl011_dma_remove(struct uart_amba_port *uap) +{ + /* TODO: remove the initcall if it has not yet executed */ + if (uap->dmatx.chan) + dma_release_channel(uap->dmatx.chan); +} + + +/* Forward declare this for the refill routine */ +static int pl011_dma_tx_refill(struct uart_amba_port *uap); + +/* + * The current DMA TX buffer has been sent. + * Try to queue up another DMA buffer. + */ +static void pl011_dma_tx_callback(void *data) +{ + struct uart_amba_port *uap = data; + struct pl011_dmatx_data *dmatx = &uap->dmatx; + unsigned long flags; + u16 dmacr; + + spin_lock_irqsave(&uap->port.lock, flags); + if (uap->dmatx.queued) + dma_unmap_sg(dmatx->chan->device->dev, &dmatx->sg, 1, + DMA_TO_DEVICE); + + dmacr = uap->dmacr; + uap->dmacr = dmacr & ~UART011_TXDMAE; + writew(uap->dmacr, uap->port.membase + UART011_DMACR); + + /* + * If TX DMA was disabled, it means that we've stopped the DMA for + * some reason (eg, XOFF received, or we want to send an X-char.) + * + * Note: we need to be careful here of a potential race between DMA + * and the rest of the driver - if the driver disables TX DMA while + * a TX buffer completing, we must update the tx queued status to + * get further refills (hence we check dmacr). + */ + if (!(dmacr & UART011_TXDMAE) || uart_tx_stopped(&uap->port) || + uart_circ_empty(&uap->port.state->xmit)) { + uap->dmatx.queued = false; + spin_unlock_irqrestore(&uap->port.lock, flags); + return; + } + + if (pl011_dma_tx_refill(uap) <= 0) { + /* + * We didn't queue a DMA buffer for some reason, but we + * have data pending to be sent. Re-enable the TX IRQ. + */ + uap->im |= UART011_TXIM; + writew(uap->im, uap->port.membase + UART011_IMSC); + } + spin_unlock_irqrestore(&uap->port.lock, flags); +} + +/* + * Try to refill the TX DMA buffer. + * Locking: called with port lock held and IRQs disabled. + * Returns: + * 1 if we queued up a TX DMA buffer. + * 0 if we didn't want to handle this by DMA + * <0 on error + */ +static int pl011_dma_tx_refill(struct uart_amba_port *uap) +{ + struct pl011_dmatx_data *dmatx = &uap->dmatx; + struct dma_chan *chan = dmatx->chan; + struct dma_device *dma_dev = chan->device; + struct dma_async_tx_descriptor *desc; + struct circ_buf *xmit = &uap->port.state->xmit; + unsigned int count; + + /* + * Try to avoid the overhead involved in using DMA if the + * transaction fits in the first half of the FIFO, by using + * the standard interrupt handling. This ensures that we + * issue a uart_write_wakeup() at the appropriate time. + */ + count = uart_circ_chars_pending(xmit); + if (count < (uap->fifosize >> 1)) { + uap->dmatx.queued = false; + return 0; + } + + /* + * Bodge: don't send the last character by DMA, as this + * will prevent XON from notifying us to restart DMA. + */ + count -= 1; + + /* Else proceed to copy the TX chars to the DMA buffer and fire DMA */ + if (count > PL011_DMA_BUFFER_SIZE) + count = PL011_DMA_BUFFER_SIZE; + + if (xmit->tail < xmit->head) + memcpy(&dmatx->buf[0], &xmit->buf[xmit->tail], count); + else { + size_t first = UART_XMIT_SIZE - xmit->tail; + size_t second = xmit->head; + + memcpy(&dmatx->buf[0], &xmit->buf[xmit->tail], first); + if (second) + memcpy(&dmatx->buf[first], &xmit->buf[0], second); + } + + dmatx->sg.length = count; + + if (dma_map_sg(dma_dev->dev, &dmatx->sg, 1, DMA_TO_DEVICE) != 1) { + uap->dmatx.queued = false; + dev_dbg(uap->port.dev, "unable to map TX DMA\n"); + return -EBUSY; + } + + desc = dma_dev->device_prep_slave_sg(chan, &dmatx->sg, 1, DMA_TO_DEVICE, + DMA_PREP_INTERRUPT | DMA_CTRL_ACK); + if (!desc) { + dma_unmap_sg(dma_dev->dev, &dmatx->sg, 1, DMA_TO_DEVICE); + uap->dmatx.queued = false; + /* + * If DMA cannot be used right now, we complete this + * transaction via IRQ and let the TTY layer retry. + */ + dev_dbg(uap->port.dev, "TX DMA busy\n"); + return -EBUSY; + } + + /* Some data to go along to the callback */ + desc->callback = pl011_dma_tx_callback; + desc->callback_param = uap; + + /* All errors should happen at prepare time */ + dmaengine_submit(desc); + + /* Fire the DMA transaction */ + dma_dev->device_issue_pending(chan); + + uap->dmacr |= UART011_TXDMAE; + writew(uap->dmacr, uap->port.membase + UART011_DMACR); + uap->dmatx.queued = true; + + /* + * Now we know that DMA will fire, so advance the ring buffer + * with the stuff we just dispatched. + */ + xmit->tail = (xmit->tail + count) & (UART_XMIT_SIZE - 1); + uap->port.icount.tx += count; + + if (uart_circ_chars_pending(xmit) < WAKEUP_CHARS) + uart_write_wakeup(&uap->port); + + return 1; +} + +/* + * We received a transmit interrupt without a pending X-char but with + * pending characters. + * Locking: called with port lock held and IRQs disabled. + * Returns: + * false if we want to use PIO to transmit + * true if we queued a DMA buffer + */ +static bool pl011_dma_tx_irq(struct uart_amba_port *uap) +{ + if (!uap->using_dma) + return false; + + /* + * If we already have a TX buffer queued, but received a + * TX interrupt, it will be because we've just sent an X-char. + * Ensure the TX DMA is enabled and the TX IRQ is disabled. + */ + if (uap->dmatx.queued) { + uap->dmacr |= UART011_TXDMAE; + writew(uap->dmacr, uap->port.membase + UART011_DMACR); + uap->im &= ~UART011_TXIM; + writew(uap->im, uap->port.membase + UART011_IMSC); + return true; + } + + /* + * We don't have a TX buffer queued, so try to queue one. + * If we succesfully queued a buffer, mask the TX IRQ. + */ + if (pl011_dma_tx_refill(uap) > 0) { + uap->im &= ~UART011_TXIM; + writew(uap->im, uap->port.membase + UART011_IMSC); + return true; + } + return false; +} + +/* + * Stop the DMA transmit (eg, due to received XOFF). + * Locking: called with port lock held and IRQs disabled. + */ +static inline void pl011_dma_tx_stop(struct uart_amba_port *uap) +{ + if (uap->dmatx.queued) { + uap->dmacr &= ~UART011_TXDMAE; + writew(uap->dmacr, uap->port.membase + UART011_DMACR); + } +} + +/* + * Try to start a DMA transmit, or in the case of an XON/OFF + * character queued for send, try to get that character out ASAP. + * Locking: called with port lock held and IRQs disabled. + * Returns: + * false if we want the TX IRQ to be enabled + * true if we have a buffer queued + */ +static inline bool pl011_dma_tx_start(struct uart_amba_port *uap) +{ + u16 dmacr; + + if (!uap->using_dma) + return false; + + if (!uap->port.x_char) { + /* no X-char, try to push chars out in DMA mode */ + bool ret = true; + + if (!uap->dmatx.queued) { + if (pl011_dma_tx_refill(uap) > 0) { + uap->im &= ~UART011_TXIM; + ret = true; + } else { + uap->im |= UART011_TXIM; + ret = false; + } + writew(uap->im, uap->port.membase + UART011_IMSC); + } else if (!(uap->dmacr & UART011_TXDMAE)) { + uap->dmacr |= UART011_TXDMAE; + writew(uap->dmacr, + uap->port.membase + UART011_DMACR); + } + return ret; + } + + /* + * We have an X-char to send. Disable DMA to prevent it loading + * the TX fifo, and then see if we can stuff it into the FIFO. + */ + dmacr = uap->dmacr; + uap->dmacr &= ~UART011_TXDMAE; + writew(uap->dmacr, uap->port.membase + UART011_DMACR); + + if (readw(uap->port.membase + UART01x_FR) & UART01x_FR_TXFF) { + /* + * No space in the FIFO, so enable the transmit interrupt + * so we know when there is space. Note that once we've + * loaded the character, we should just re-enable DMA. + */ + return false; + } + + writew(uap->port.x_char, uap->port.membase + UART01x_DR); + uap->port.icount.tx++; + uap->port.x_char = 0; + + /* Success - restore the DMA state */ + uap->dmacr = dmacr; + writew(dmacr, uap->port.membase + UART011_DMACR); + + return true; +} + +/* + * Flush the transmit buffer. + * Locking: called with port lock held and IRQs disabled. + */ +static void pl011_dma_flush_buffer(struct uart_port *port) +{ + struct uart_amba_port *uap = (struct uart_amba_port *)port; + + if (!uap->using_dma) + return; + + /* Avoid deadlock with the DMA engine callback */ + spin_unlock(&uap->port.lock); + dmaengine_terminate_all(uap->dmatx.chan); + spin_lock(&uap->port.lock); + if (uap->dmatx.queued) { + dma_unmap_sg(uap->dmatx.chan->device->dev, &uap->dmatx.sg, 1, + DMA_TO_DEVICE); + uap->dmatx.queued = false; + uap->dmacr &= ~UART011_TXDMAE; + writew(uap->dmacr, uap->port.membase + UART011_DMACR); + } +} + + +static void pl011_dma_startup(struct uart_amba_port *uap) +{ + if (!uap->dmatx.chan) + return; + + uap->dmatx.buf = kmalloc(PL011_DMA_BUFFER_SIZE, GFP_KERNEL); + if (!uap->dmatx.buf) { + dev_err(uap->port.dev, "no memory for DMA TX buffer\n"); + uap->port.fifosize = uap->fifosize; + return; + } + + sg_init_one(&uap->dmatx.sg, uap->dmatx.buf, PL011_DMA_BUFFER_SIZE); + + /* The DMA buffer is now the FIFO the TTY subsystem can use */ + uap->port.fifosize = PL011_DMA_BUFFER_SIZE; + uap->using_dma = true; + + /* Turn on DMA error (RX/TX will be enabled on demand) */ + uap->dmacr |= UART011_DMAONERR; + writew(uap->dmacr, uap->port.membase + UART011_DMACR); +} + +static void pl011_dma_shutdown(struct uart_amba_port *uap) +{ + if (!uap->using_dma) + return; + + /* Disable RX and TX DMA */ + while (readw(uap->port.membase + UART01x_FR) & UART01x_FR_BUSY) + barrier(); + + spin_lock_irq(&uap->port.lock); + uap->dmacr &= ~(UART011_DMAONERR | UART011_RXDMAE | UART011_TXDMAE); + writew(uap->dmacr, uap->port.membase + UART011_DMACR); + spin_unlock_irq(&uap->port.lock); + + /* In theory, this should already be done by pl011_dma_flush_buffer */ + dmaengine_terminate_all(uap->dmatx.chan); + if (uap->dmatx.queued) { + dma_unmap_sg(uap->dmatx.chan->device->dev, &uap->dmatx.sg, 1, + DMA_TO_DEVICE); + uap->dmatx.queued = false; + } + + kfree(uap->dmatx.buf); + + uap->using_dma = false; +} + +#else +/* Blank functions if the DMA engine is not available */ +static inline void pl011_dma_probe(struct uart_amba_port *uap) +{ +} + +static inline void pl011_dma_remove(struct uart_amba_port *uap) +{ +} + +static inline void pl011_dma_startup(struct uart_amba_port *uap) +{ +} + +static inline void pl011_dma_shutdown(struct uart_amba_port *uap) +{ +} + +static inline bool pl011_dma_tx_irq(struct uart_amba_port *uap) +{ + return false; +} + +static inline void pl011_dma_tx_stop(struct uart_amba_port *uap) +{ +} + +static inline bool pl011_dma_tx_start(struct uart_amba_port *uap) +{ + return false; +} + +#define pl011_dma_flush_buffer NULL +#endif + + static void pl011_stop_tx(struct uart_port *port) { struct uart_amba_port *uap = (struct uart_amba_port *)port; uap->im &= ~UART011_TXIM; writew(uap->im, uap->port.membase + UART011_IMSC); + pl011_dma_tx_stop(uap); } static void pl011_start_tx(struct uart_port *port) { struct uart_amba_port *uap = (struct uart_amba_port *)port; - uap->im |= UART011_TXIM; - writew(uap->im, uap->port.membase + UART011_IMSC); + if (!pl011_dma_tx_start(uap)) { + uap->im |= UART011_TXIM; + writew(uap->im, uap->port.membase + UART011_IMSC); + } } static void pl011_stop_rx(struct uart_port *port) @@ -204,6 +695,10 @@ static void pl011_tx_chars(struct uart_amba_port *uap) return; } + /* If we are using DMA mode, try to send some characters. */ + if (pl011_dma_tx_irq(uap)) + return; + count = uap->fifosize >> 1; do { writew(xmit->buf[xmit->tail], uap->port.membase + UART01x_DR); @@ -434,6 +929,9 @@ static int pl011_startup(struct uart_port *port) */ uap->old_status = readw(uap->port.membase + UART01x_FR) & UART01x_FR_MODEM_ANY; + /* Startup DMA */ + pl011_dma_startup(uap); + /* * Finally, enable interrupts */ @@ -473,6 +971,8 @@ static void pl011_shutdown(struct uart_port *port) writew(0xffff, uap->port.membase + UART011_ICR); spin_unlock_irq(&uap->port.lock); + pl011_dma_shutdown(uap); + /* * Free the interrupt */ @@ -691,6 +1191,7 @@ static struct uart_ops amba_pl011_pops = { .break_ctl = pl011_break_ctl, .startup = pl011_startup, .shutdown = pl011_shutdown, + .flush_buffer = pl011_dma_flush_buffer, .set_termios = pl011_set_termios, .type = pl011_type, .release_port = pl010_release_port, @@ -883,6 +1384,7 @@ static int pl011_probe(struct amba_device *dev, struct amba_id *id) uap->port.ops = &amba_pl011_pops; uap->port.flags = UPF_BOOT_AUTOCONF; uap->port.line = i; + pl011_dma_probe(uap); snprintf(uap->type, sizeof(uap->type), "PL011 rev%u", amba_rev(dev)); @@ -893,6 +1395,7 @@ static int pl011_probe(struct amba_device *dev, struct amba_id *id) if (ret) { amba_set_drvdata(dev, NULL); amba_ports[i] = NULL; + pl011_dma_remove(uap); clk_put(uap->clk); unmap: iounmap(base); @@ -916,6 +1419,7 @@ static int pl011_remove(struct amba_device *dev) if (amba_ports[i] == uap) amba_ports[i] = NULL; + pl011_dma_remove(uap); iounmap(uap->port.membase); clk_put(uap->clk); kfree(uap); diff --git a/include/linux/amba/serial.h b/include/linux/amba/serial.h index 6021588ba0a8..577f22eb9225 100644 --- a/include/linux/amba/serial.h +++ b/include/linux/amba/serial.h @@ -180,6 +180,13 @@ struct amba_device; /* in uncompress this is included but amba/bus.h is not */ struct amba_pl010_data { void (*set_mctrl)(struct amba_device *dev, void __iomem *base, unsigned int mctrl); }; + +struct dma_chan; +struct amba_pl011_data { + bool (*dma_filter)(struct dma_chan *chan, void *filter_param); + void *dma_rx_param; + void *dma_tx_param; +}; #endif #endif -- cgit v1.2.3 From 38d624361b2a82d6317c379aebf81b1b28210bb0 Mon Sep 17 00:00:00 2001 From: Russell King Date: Wed, 22 Dec 2010 17:59:16 +0000 Subject: ARM: PL011: add DMA burst threshold support for ST variants ST Micro variants has some specific dma burst threshold compensation, which allows them to make better use of a DMA controller. Add support to set this up. Based on a patch from Linus Walleij. Acked-by: Linus Walleij Signed-off-by: Russell King --- drivers/serial/amba-pl011.c | 12 ++++++++++++ include/linux/amba/serial.h | 15 +++++++++++++++ 2 files changed, 27 insertions(+) (limited to 'include/linux') diff --git a/drivers/serial/amba-pl011.c b/drivers/serial/amba-pl011.c index ab025dc52fa4..e76d7d000128 100644 --- a/drivers/serial/amba-pl011.c +++ b/drivers/serial/amba-pl011.c @@ -74,6 +74,7 @@ struct vendor_data { unsigned int lcrh_tx; unsigned int lcrh_rx; bool oversampling; + bool dma_threshold; }; static struct vendor_data vendor_arm = { @@ -82,6 +83,7 @@ static struct vendor_data vendor_arm = { .lcrh_tx = UART011_LCRH, .lcrh_rx = UART011_LCRH, .oversampling = false, + .dma_threshold = false, }; static struct vendor_data vendor_st = { @@ -90,6 +92,7 @@ static struct vendor_data vendor_st = { .lcrh_tx = ST_UART011_LCRH_TX, .lcrh_rx = ST_UART011_LCRH_RX, .oversampling = true, + .dma_threshold = true, }; /* Deals with DMA transactions */ @@ -527,6 +530,15 @@ static void pl011_dma_startup(struct uart_amba_port *uap) /* Turn on DMA error (RX/TX will be enabled on demand) */ uap->dmacr |= UART011_DMAONERR; writew(uap->dmacr, uap->port.membase + UART011_DMACR); + + /* + * ST Micro variants has some specific dma burst threshold + * compensation. Set this to 16 bytes, so burst will only + * be issued above/below 16 bytes. + */ + if (uap->vendor->dma_threshold) + writew(ST_UART011_DMAWM_RX_16 | ST_UART011_DMAWM_TX_16, + uap->port.membase + ST_UART011_DMAWM); } static void pl011_dma_shutdown(struct uart_amba_port *uap) diff --git a/include/linux/amba/serial.h b/include/linux/amba/serial.h index 577f22eb9225..5479fdc849e9 100644 --- a/include/linux/amba/serial.h +++ b/include/linux/amba/serial.h @@ -113,6 +113,21 @@ #define UART01x_LCRH_PEN 0x02 #define UART01x_LCRH_BRK 0x01 +#define ST_UART011_DMAWM_RX_1 (0 << 3) +#define ST_UART011_DMAWM_RX_2 (1 << 3) +#define ST_UART011_DMAWM_RX_4 (2 << 3) +#define ST_UART011_DMAWM_RX_8 (3 << 3) +#define ST_UART011_DMAWM_RX_16 (4 << 3) +#define ST_UART011_DMAWM_RX_32 (5 << 3) +#define ST_UART011_DMAWM_RX_48 (6 << 3) +#define ST_UART011_DMAWM_TX_1 0 +#define ST_UART011_DMAWM_TX_2 1 +#define ST_UART011_DMAWM_TX_4 2 +#define ST_UART011_DMAWM_TX_8 3 +#define ST_UART011_DMAWM_TX_16 4 +#define ST_UART011_DMAWM_TX_32 5 +#define ST_UART011_DMAWM_TX_48 6 + #define UART010_IIR_RTIS 0x08 #define UART010_IIR_TIS 0x04 #define UART010_IIR_RIS 0x02 -- cgit v1.2.3 From 3610cda53f247e176bcbb7a7cca64bc53b12acdb Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Wed, 5 Jan 2011 15:38:53 -0800 Subject: af_unix: Avoid socket->sk NULL OOPS in stream connect security hooks. unix_release() can asynchornously set socket->sk to NULL, and it does so without holding the unix_state_lock() on "other" during stream connects. However, the reverse mapping, sk->sk_socket, is only transitioned to NULL under the unix_state_lock(). Therefore make the security hooks follow the reverse mapping instead of the forward mapping. Reported-by: Jeremy Fitzhardinge Reported-by: Linus Torvalds Signed-off-by: David S. Miller --- include/linux/security.h | 15 +++++++-------- net/unix/af_unix.c | 2 +- security/capability.c | 2 +- security/security.c | 3 +-- security/selinux/hooks.c | 10 +++++----- security/smack/smack_lsm.c | 14 +++++++------- 6 files changed, 22 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index fd4d55fb8845..d47a4c24b3e4 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -796,8 +796,9 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts) * @unix_stream_connect: * Check permissions before establishing a Unix domain stream connection * between @sock and @other. - * @sock contains the socket structure. - * @other contains the peer socket structure. + * @sock contains the sock structure. + * @other contains the peer sock structure. + * @newsk contains the new sock structure. * Return 0 if permission is granted. * @unix_may_send: * Check permissions before connecting or sending datagrams from @sock to @@ -1568,8 +1569,7 @@ struct security_operations { int (*inode_getsecctx)(struct inode *inode, void **ctx, u32 *ctxlen); #ifdef CONFIG_SECURITY_NETWORK - int (*unix_stream_connect) (struct socket *sock, - struct socket *other, struct sock *newsk); + int (*unix_stream_connect) (struct sock *sock, struct sock *other, struct sock *newsk); int (*unix_may_send) (struct socket *sock, struct socket *other); int (*socket_create) (int family, int type, int protocol, int kern); @@ -2525,8 +2525,7 @@ static inline int security_inode_getsecctx(struct inode *inode, void **ctx, u32 #ifdef CONFIG_SECURITY_NETWORK -int security_unix_stream_connect(struct socket *sock, struct socket *other, - struct sock *newsk); +int security_unix_stream_connect(struct sock *sock, struct sock *other, struct sock *newsk); int security_unix_may_send(struct socket *sock, struct socket *other); int security_socket_create(int family, int type, int protocol, int kern); int security_socket_post_create(struct socket *sock, int family, @@ -2567,8 +2566,8 @@ void security_tun_dev_post_create(struct sock *sk); int security_tun_dev_attach(struct sock *sk); #else /* CONFIG_SECURITY_NETWORK */ -static inline int security_unix_stream_connect(struct socket *sock, - struct socket *other, +static inline int security_unix_stream_connect(struct sock *sock, + struct sock *other, struct sock *newsk) { return 0; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 417d7a6c36cf..dd419d286204 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1157,7 +1157,7 @@ restart: goto restart; } - err = security_unix_stream_connect(sock, other->sk_socket, newsk); + err = security_unix_stream_connect(sk, other, newsk); if (err) { unix_state_unlock(sk); goto out_unlock; diff --git a/security/capability.c b/security/capability.c index c773635ca3a0..2a5df2b7da83 100644 --- a/security/capability.c +++ b/security/capability.c @@ -548,7 +548,7 @@ static int cap_sem_semop(struct sem_array *sma, struct sembuf *sops, } #ifdef CONFIG_SECURITY_NETWORK -static int cap_unix_stream_connect(struct socket *sock, struct socket *other, +static int cap_unix_stream_connect(struct sock *sock, struct sock *other, struct sock *newsk) { return 0; diff --git a/security/security.c b/security/security.c index 1b798d3df710..e5fb07a3052d 100644 --- a/security/security.c +++ b/security/security.c @@ -977,8 +977,7 @@ EXPORT_SYMBOL(security_inode_getsecctx); #ifdef CONFIG_SECURITY_NETWORK -int security_unix_stream_connect(struct socket *sock, struct socket *other, - struct sock *newsk) +int security_unix_stream_connect(struct sock *sock, struct sock *other, struct sock *newsk) { return security_ops->unix_stream_connect(sock, other, newsk); } diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index c82538a4b1a4..6f637d2678ac 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -3921,18 +3921,18 @@ static int selinux_socket_shutdown(struct socket *sock, int how) return sock_has_perm(current, sock->sk, SOCKET__SHUTDOWN); } -static int selinux_socket_unix_stream_connect(struct socket *sock, - struct socket *other, +static int selinux_socket_unix_stream_connect(struct sock *sock, + struct sock *other, struct sock *newsk) { - struct sk_security_struct *sksec_sock = sock->sk->sk_security; - struct sk_security_struct *sksec_other = other->sk->sk_security; + struct sk_security_struct *sksec_sock = sock->sk_security; + struct sk_security_struct *sksec_other = other->sk_security; struct sk_security_struct *sksec_new = newsk->sk_security; struct common_audit_data ad; int err; COMMON_AUDIT_DATA_INIT(&ad, NET); - ad.u.net.sk = other->sk; + ad.u.net.sk = other; err = avc_has_perm(sksec_sock->sid, sksec_other->sid, sksec_other->sclass, diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index 489a85afa477..ccb71a044a1a 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -2408,22 +2408,22 @@ static int smack_setprocattr(struct task_struct *p, char *name, /** * smack_unix_stream_connect - Smack access on UDS - * @sock: one socket - * @other: the other socket + * @sock: one sock + * @other: the other sock * @newsk: unused * * Return 0 if a subject with the smack of sock could access * an object with the smack of other, otherwise an error code */ -static int smack_unix_stream_connect(struct socket *sock, - struct socket *other, struct sock *newsk) +static int smack_unix_stream_connect(struct sock *sock, + struct sock *other, struct sock *newsk) { - struct inode *sp = SOCK_INODE(sock); - struct inode *op = SOCK_INODE(other); + struct inode *sp = SOCK_INODE(sock->sk_socket); + struct inode *op = SOCK_INODE(other->sk_socket); struct smk_audit_info ad; smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_NET); - smk_ad_setfield_u_net_sk(&ad, other->sk); + smk_ad_setfield_u_net_sk(&ad, other); return smk_access(smk_of_inode(sp), smk_of_inode(op), MAY_READWRITE, &ad); } -- cgit v1.2.3 From 238c855805c853eaec95b0bc3065effb64f955a0 Mon Sep 17 00:00:00 2001 From: Henry Ptasinski Date: Tue, 4 Jan 2011 16:07:14 +0000 Subject: include/linux/if_ether.h: Add #define ETH_P_LINK_CTL for HPNA and wlan local tunnel Ethertype used by HPNA control protocols (LARQ, rate, link, etc) and by Broadcom wlan drivers for local signalling. Signed-off-by: Henry Ptasinski Signed-off-by: David S. Miller --- include/linux/if_ether.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/if_ether.h b/include/linux/if_ether.h index f9c3df03db0f..be69043d2896 100644 --- a/include/linux/if_ether.h +++ b/include/linux/if_ether.h @@ -72,6 +72,7 @@ #define ETH_P_MPLS_UC 0x8847 /* MPLS Unicast traffic */ #define ETH_P_MPLS_MC 0x8848 /* MPLS Multicast traffic */ #define ETH_P_ATMMPOA 0x884c /* MultiProtocol Over ATM */ +#define ETH_P_LINK_CTL 0x886c /* HPNA, wlan link local tunnel */ #define ETH_P_ATMFATE 0x8884 /* Frame-based ATM Transport * over Ethernet */ -- cgit v1.2.3 From 2ad0d9d413abc3380fc1d89a9da7f8db59d9746b Mon Sep 17 00:00:00 2001 From: Changli Gao Date: Thu, 6 Jan 2011 11:41:42 -0800 Subject: net: remove the duplicate #ifdef __KERNEL__ Since we are already in #ifdef __KERNEL__, we don't need to check it again. Signed-off-by: Changli Gao Signed-off-by: David S. Miller --- include/linux/socket.h | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index 86b652fabf6e..5f65f14c4f44 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -30,12 +30,10 @@ struct cred; #define __sockaddr_check_size(size) \ BUILD_BUG_ON(((size) > sizeof(struct __kernel_sockaddr_storage))) -#ifdef __KERNEL__ -# ifdef CONFIG_PROC_FS +#ifdef CONFIG_PROC_FS struct seq_file; extern void socket_seq_show(struct seq_file *seq); -# endif -#endif /* __KERNEL__ */ +#endif typedef unsigned short sa_family_t; @@ -311,7 +309,6 @@ struct ucred { /* IPX options */ #define IPX_TYPE 1 -#ifdef __KERNEL__ extern void cred_to_ucred(struct pid *pid, const struct cred *cred, struct ucred *ucred); extern int memcpy_fromiovec(unsigned char *kdata, struct iovec *iov, int len); @@ -333,6 +330,5 @@ struct timespec; extern int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, unsigned int flags, struct timespec *timeout); -#endif #endif /* not kernel and not glibc */ #endif /* _LINUX_SOCKET_H */ -- cgit v1.2.3