From 951069e311a2a931bf7c9d838db860f90bf14c45 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 31 Jan 2006 10:16:55 -0800 Subject: Don't try to "validate" a non-existing timeval. settime() with a NULL timeval is silly but legal. Noticed by Dave Jones Signed-off-by: Linus Torvalds --- kernel/time.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/time.c b/kernel/time.c index 7477b1d2079e..1f23e683d6aa 100644 --- a/kernel/time.c +++ b/kernel/time.c @@ -155,7 +155,7 @@ int do_sys_settimeofday(struct timespec *tv, struct timezone *tz) static int firsttime = 1; int error = 0; - if (!timespec_valid(tv)) + if (tv && !timespec_valid(tv)) return -EINVAL; error = security_settime(tv, tz); -- cgit v1.2.2 From 70b4d63e98fd93fb9742708a54f872cba24e0fea Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 30 Jan 2006 20:24:38 +0100 Subject: [PATCH] Fix boot-time slowdown for measure_migration_cost This reduces the amount of time the migration cost calculations cost during bootup. Based on numbers by Tony Luck . Signed-off-by: Ingo Molnar --- kernel/sched.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/sched.c b/kernel/sched.c index 3ee2ae45125f..ec7fd9cee306 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -5141,7 +5141,7 @@ static void init_sched_build_groups(struct sched_group groups[], cpumask_t span, #define SEARCH_SCOPE 2 #define MIN_CACHE_SIZE (64*1024U) #define DEFAULT_CACHE_SIZE (5*1024*1024U) -#define ITERATIONS 2 +#define ITERATIONS 1 #define SIZE_THRESH 130 #define COST_THRESH 130 @@ -5480,9 +5480,9 @@ static unsigned long long measure_migration_cost(int cpu1, int cpu2) break; } /* - * Increase the cachesize in 5% steps: + * Increase the cachesize in 10% steps: */ - size = size * 20 / 19; + size = size * 10 / 9; } if (migration_debug) -- cgit v1.2.2 From 4021cb279a532728c3208a16b9b09b0ca8016850 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 25 Jan 2006 15:23:07 +0100 Subject: [PATCH] fix uidhash_lock <-> RCU deadlock RCU task-struct freeing can call free_uid(), which is taking uidhash_lock - while other users of uidhash_lock are softirq-unsafe. The fix is to always take the uidhash_spinlock in a softirq-safe manner. Signed-off-by: Ingo Molnar Acked-by: Paul E. McKenney Signed-off-by: Linus Torvalds --- kernel/user.c | 25 +++++++++++++++++-------- 1 file changed, 17 insertions(+), 8 deletions(-) (limited to 'kernel') diff --git a/kernel/user.c b/kernel/user.c index 89e562feb1b1..d1ae2349347e 100644 --- a/kernel/user.c +++ b/kernel/user.c @@ -13,6 +13,7 @@ #include #include #include +#include /* * UID task count cache, to get fast user lookup in "alloc_uid" @@ -27,6 +28,12 @@ static kmem_cache_t *uid_cachep; static struct list_head uidhash_table[UIDHASH_SZ]; + +/* + * The uidhash_lock is mostly taken from process context, but it is + * occasionally also taken from softirq/tasklet context, when + * task-structs get RCU-freed. Hence all locking must be softirq-safe. + */ static DEFINE_SPINLOCK(uidhash_lock); struct user_struct root_user = { @@ -83,14 +90,15 @@ struct user_struct *find_user(uid_t uid) { struct user_struct *ret; - spin_lock(&uidhash_lock); + spin_lock_bh(&uidhash_lock); ret = uid_hash_find(uid, uidhashentry(uid)); - spin_unlock(&uidhash_lock); + spin_unlock_bh(&uidhash_lock); return ret; } void free_uid(struct user_struct *up) { + local_bh_disable(); if (up && atomic_dec_and_lock(&up->__count, &uidhash_lock)) { uid_hash_remove(up); key_put(up->uid_keyring); @@ -98,6 +106,7 @@ void free_uid(struct user_struct *up) kmem_cache_free(uid_cachep, up); spin_unlock(&uidhash_lock); } + local_bh_enable(); } struct user_struct * alloc_uid(uid_t uid) @@ -105,9 +114,9 @@ struct user_struct * alloc_uid(uid_t uid) struct list_head *hashent = uidhashentry(uid); struct user_struct *up; - spin_lock(&uidhash_lock); + spin_lock_bh(&uidhash_lock); up = uid_hash_find(uid, hashent); - spin_unlock(&uidhash_lock); + spin_unlock_bh(&uidhash_lock); if (!up) { struct user_struct *new; @@ -137,7 +146,7 @@ struct user_struct * alloc_uid(uid_t uid) * Before adding this, check whether we raced * on adding the same user already.. */ - spin_lock(&uidhash_lock); + spin_lock_bh(&uidhash_lock); up = uid_hash_find(uid, hashent); if (up) { key_put(new->uid_keyring); @@ -147,7 +156,7 @@ struct user_struct * alloc_uid(uid_t uid) uid_hash_insert(new, hashent); up = new; } - spin_unlock(&uidhash_lock); + spin_unlock_bh(&uidhash_lock); } return up; @@ -183,9 +192,9 @@ static int __init uid_cache_init(void) INIT_LIST_HEAD(uidhash_table + n); /* Insert the root user immediately (init already runs as root) */ - spin_lock(&uidhash_lock); + spin_lock_bh(&uidhash_lock); uid_hash_insert(&root_user, uidhashentry(0)); - spin_unlock(&uidhash_lock); + spin_unlock_bh(&uidhash_lock); return 0; } -- cgit v1.2.2 From adac1665234dd966990af846eccd20b7f4923279 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 25 Jan 2006 19:50:12 +0100 Subject: [PATCH] rcu_torture_lock deadlock fix rcu_torture_lock is used in a softirq-unsafe manner, but it is also taken by rcu_torture_cb(), which may execute in softirq-context, resulting in potential deadlocks. The fix is to acquire rcu_torture_lock in a softirq-safe manner. With this fix applied, the rcu-torture code passes validation. Signed-off-by: Ingo Molnar Acked-by: Paul E. McKenney Signed-off-by: Linus Torvalds --- kernel/rcutorture.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c index 773219907dd8..7712912dbc84 100644 --- a/kernel/rcutorture.c +++ b/kernel/rcutorture.c @@ -114,16 +114,16 @@ rcu_torture_alloc(void) { struct list_head *p; - spin_lock(&rcu_torture_lock); + spin_lock_bh(&rcu_torture_lock); if (list_empty(&rcu_torture_freelist)) { atomic_inc(&n_rcu_torture_alloc_fail); - spin_unlock(&rcu_torture_lock); + spin_unlock_bh(&rcu_torture_lock); return NULL; } atomic_inc(&n_rcu_torture_alloc); p = rcu_torture_freelist.next; list_del_init(p); - spin_unlock(&rcu_torture_lock); + spin_unlock_bh(&rcu_torture_lock); return container_of(p, struct rcu_torture, rtort_free); } @@ -134,9 +134,9 @@ static void rcu_torture_free(struct rcu_torture *p) { atomic_inc(&n_rcu_torture_free); - spin_lock(&rcu_torture_lock); + spin_lock_bh(&rcu_torture_lock); list_add_tail(&p->rtort_free, &rcu_torture_freelist); - spin_unlock(&rcu_torture_lock); + spin_unlock_bh(&rcu_torture_lock); } static void -- cgit v1.2.2 From 3fa97c9db4f6f93f41f7a40d08872dbfd8dc907e Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Tue, 31 Jan 2006 16:34:26 -0800 Subject: [PATCH] "Fix uidhash_lock <-> RXU deadlock" fix I get storms of warnings from local_bh_enable(). Better-tested patches, please. Cc: Ingo Molnar Cc: "Paul E. McKenney" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/user.c | 27 +++++++++++++++++---------- 1 file changed, 17 insertions(+), 10 deletions(-) (limited to 'kernel') diff --git a/kernel/user.c b/kernel/user.c index d1ae2349347e..d9deae43a9ab 100644 --- a/kernel/user.c +++ b/kernel/user.c @@ -33,6 +33,10 @@ static struct list_head uidhash_table[UIDHASH_SZ]; * The uidhash_lock is mostly taken from process context, but it is * occasionally also taken from softirq/tasklet context, when * task-structs get RCU-freed. Hence all locking must be softirq-safe. + * But free_uid() is also called with local interrupts disabled, and running + * local_bh_enable() with local interrupts disabled is an error - we'll run + * softirq callbacks, and they can unconditionally enable interrupts, and + * the caller of free_uid() didn't expect that.. */ static DEFINE_SPINLOCK(uidhash_lock); @@ -89,16 +93,19 @@ static inline struct user_struct *uid_hash_find(uid_t uid, struct list_head *has struct user_struct *find_user(uid_t uid) { struct user_struct *ret; + unsigned long flags; - spin_lock_bh(&uidhash_lock); + spin_lock_irqsave(&uidhash_lock, flags); ret = uid_hash_find(uid, uidhashentry(uid)); - spin_unlock_bh(&uidhash_lock); + spin_unlock_irqrestore(&uidhash_lock, flags); return ret; } void free_uid(struct user_struct *up) { - local_bh_disable(); + unsigned long flags; + + local_irq_save(flags); if (up && atomic_dec_and_lock(&up->__count, &uidhash_lock)) { uid_hash_remove(up); key_put(up->uid_keyring); @@ -106,7 +113,7 @@ void free_uid(struct user_struct *up) kmem_cache_free(uid_cachep, up); spin_unlock(&uidhash_lock); } - local_bh_enable(); + local_irq_restore(flags); } struct user_struct * alloc_uid(uid_t uid) @@ -114,9 +121,9 @@ struct user_struct * alloc_uid(uid_t uid) struct list_head *hashent = uidhashentry(uid); struct user_struct *up; - spin_lock_bh(&uidhash_lock); + spin_lock_irq(&uidhash_lock); up = uid_hash_find(uid, hashent); - spin_unlock_bh(&uidhash_lock); + spin_unlock_irq(&uidhash_lock); if (!up) { struct user_struct *new; @@ -146,7 +153,7 @@ struct user_struct * alloc_uid(uid_t uid) * Before adding this, check whether we raced * on adding the same user already.. */ - spin_lock_bh(&uidhash_lock); + spin_lock_irq(&uidhash_lock); up = uid_hash_find(uid, hashent); if (up) { key_put(new->uid_keyring); @@ -156,7 +163,7 @@ struct user_struct * alloc_uid(uid_t uid) uid_hash_insert(new, hashent); up = new; } - spin_unlock_bh(&uidhash_lock); + spin_unlock_irq(&uidhash_lock); } return up; @@ -192,9 +199,9 @@ static int __init uid_cache_init(void) INIT_LIST_HEAD(uidhash_table + n); /* Insert the root user immediately (init already runs as root) */ - spin_lock_bh(&uidhash_lock); + spin_lock_irq(&uidhash_lock); uid_hash_insert(&root_user, uidhashentry(0)); - spin_unlock_bh(&uidhash_lock); + spin_unlock_irq(&uidhash_lock); return 0; } -- cgit v1.2.2 From 853609b61ef88b414ffd1613741aa59894334320 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 1 Feb 2006 03:05:07 -0800 Subject: [PATCH] swsusp: use bytes as image size units Make swsusp use bytes as the image size units, which is needed for future compatibility. Signed-off-by: Rafael J. Wysocki Acked-by: Pavel Machek Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/power/disk.c | 6 +++--- kernel/power/power.h | 4 ++-- kernel/power/swsusp.c | 8 ++++---- 3 files changed, 9 insertions(+), 9 deletions(-) (limited to 'kernel') diff --git a/kernel/power/disk.c b/kernel/power/disk.c index e24446f8d8cd..f2b3b0ea512a 100644 --- a/kernel/power/disk.c +++ b/kernel/power/disk.c @@ -367,14 +367,14 @@ power_attr(resume); static ssize_t image_size_show(struct subsystem * subsys, char *buf) { - return sprintf(buf, "%u\n", image_size); + return sprintf(buf, "%lu\n", image_size); } static ssize_t image_size_store(struct subsystem * subsys, const char * buf, size_t n) { - unsigned int size; + unsigned long size; - if (sscanf(buf, "%u", &size) == 1) { + if (sscanf(buf, "%lu", &size) == 1) { image_size = size; return n; } diff --git a/kernel/power/power.h b/kernel/power/power.h index 7e8492fd1423..61beb5e0e927 100644 --- a/kernel/power/power.h +++ b/kernel/power/power.h @@ -51,8 +51,8 @@ extern const void __nosave_begin, __nosave_end; extern unsigned int nr_copy_pages; extern struct pbe *pagedir_nosave; -/* Preferred image size in MB (default 500) */ -extern unsigned int image_size; +/* Preferred image size in bytes (default 500 MB) */ +extern unsigned long image_size; extern asmlinkage int swsusp_arch_suspend(void); extern asmlinkage int swsusp_arch_resume(void); diff --git a/kernel/power/swsusp.c b/kernel/power/swsusp.c index 55a18d26abed..59c91c148e82 100644 --- a/kernel/power/swsusp.c +++ b/kernel/power/swsusp.c @@ -70,12 +70,12 @@ #include "power.h" /* - * Preferred image size in MB (tunable via /sys/power/image_size). + * Preferred image size in bytes (tunable via /sys/power/image_size). * When it is set to N, swsusp will do its best to ensure the image - * size will not exceed N MB, but if that is impossible, it will + * size will not exceed N bytes, but if that is impossible, it will * try to create the smallest image possible. */ -unsigned int image_size = 500; +unsigned long image_size = 500 * 1024 * 1024; #ifdef CONFIG_HIGHMEM unsigned int count_highmem_pages(void); @@ -590,7 +590,7 @@ int swsusp_shrink_memory(void) if (!tmp) return -ENOMEM; pages += tmp; - } else if (size > (image_size * 1024 * 1024) / PAGE_SIZE) { + } else if (size > image_size / PAGE_SIZE) { tmp = shrink_all_memory(SHRINK_BITE); pages += tmp; } -- cgit v1.2.2 From bc1978d404befacd272d0321ef749cc3192e488b Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 1 Feb 2006 03:05:08 -0800 Subject: [PATCH] hrtimers: fixup itimer conversion The itimer conversion removed the locking which protects the timer and variables in the shared signal structure. Steven Rostedt found the problem in the latest -rt patches. Signed-off-by: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/itimer.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/itimer.c b/kernel/itimer.c index c2c05c4ff28d..6433d0685506 100644 --- a/kernel/itimer.c +++ b/kernel/itimer.c @@ -49,9 +49,11 @@ int do_getitimer(int which, struct itimerval *value) switch (which) { case ITIMER_REAL: + spin_lock_irq(&tsk->sighand->siglock); value->it_value = itimer_get_remtime(&tsk->signal->real_timer); value->it_interval = ktime_to_timeval(tsk->signal->it_real_incr); + spin_unlock_irq(&tsk->sighand->siglock); break; case ITIMER_VIRTUAL: read_lock(&tasklist_lock); @@ -150,8 +152,14 @@ int do_setitimer(int which, struct itimerval *value, struct itimerval *ovalue) switch (which) { case ITIMER_REAL: +again: + spin_lock_irq(&tsk->sighand->siglock); timer = &tsk->signal->real_timer; - hrtimer_cancel(timer); + /* We are sharing ->siglock with it_real_fn() */ + if (hrtimer_try_to_cancel(timer) < 0) { + spin_unlock_irq(&tsk->sighand->siglock); + goto again; + } if (ovalue) { ovalue->it_value = itimer_get_remtime(timer); ovalue->it_interval @@ -162,6 +170,7 @@ int do_setitimer(int which, struct itimerval *value, struct itimerval *ovalue) expires = timeval_to_ktime(value->it_value); if (expires.tv64 != 0) hrtimer_start(timer, expires, HRTIMER_REL); + spin_unlock_irq(&tsk->sighand->siglock); break; case ITIMER_VIRTUAL: nval = timeval_to_cputime(&value->it_value); -- cgit v1.2.2 From b6557fbca805217588a412f391a65ceafcf1a1af Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 1 Feb 2006 03:05:09 -0800 Subject: [PATCH] hrtimers: fix possible use of NULL pointer in posix-timers Fixup the conversion of posix-timers to hrtimers. Signed-off-by: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/posix-timers.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c index 197208b3aa2a..3b606d361b52 100644 --- a/kernel/posix-timers.c +++ b/kernel/posix-timers.c @@ -290,7 +290,8 @@ void do_schedule_next_timer(struct siginfo *info) info->si_overrun = timr->it_overrun_last; } - unlock_timer(timr, flags); + if (timr) + unlock_timer(timr, flags); } int posix_timer_event(struct k_itimer *timr,int si_private) -- cgit v1.2.2 From a16a1c095a2392d49fafea22f3a508e268ef7167 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 1 Feb 2006 03:05:09 -0800 Subject: [PATCH] hrtimers: fix oldvalue return in setitimer This resolves bugzilla bug#5617. The oldvalue of the timer was read after the timer was cancelled, so the remaining time was always zero. Signed-off-by: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/itimer.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/itimer.c b/kernel/itimer.c index 6433d0685506..379be2f8c84c 100644 --- a/kernel/itimer.c +++ b/kernel/itimer.c @@ -155,16 +155,16 @@ int do_setitimer(int which, struct itimerval *value, struct itimerval *ovalue) again: spin_lock_irq(&tsk->sighand->siglock); timer = &tsk->signal->real_timer; - /* We are sharing ->siglock with it_real_fn() */ - if (hrtimer_try_to_cancel(timer) < 0) { - spin_unlock_irq(&tsk->sighand->siglock); - goto again; - } if (ovalue) { ovalue->it_value = itimer_get_remtime(timer); ovalue->it_interval = ktime_to_timeval(tsk->signal->it_real_incr); } + /* We are sharing ->siglock with it_real_fn() */ + if (hrtimer_try_to_cancel(timer) < 0) { + spin_unlock_irq(&tsk->sighand->siglock); + goto again; + } tsk->signal->it_real_incr = timeval_to_ktime(value->it_interval); expires = timeval_to_ktime(value->it_value); -- cgit v1.2.2 From ff60a5dc4fa584d47022d2533bc5c53b80096fb5 Mon Sep 17 00:00:00 2001 From: "akpm@osdl.org" Date: Wed, 1 Feb 2006 03:05:10 -0800 Subject: [PATCH] hrtimers: fix posix-timer requeue race From: Steven Rostedtrostedt@goodmis.org CPU0 expires a posix-timer and runs the callback function. The signal is queued. After releasing the posix-timer lock and before returning to hrtimer_run_queue CPU0 gets interrupted. CPU1 delivers the queued signal and rearms the timer. CPU0 comes back to hrtimer_run_queue and sets the timer state to expired. The next modification of the timer can result in an oops, because the state information is wrong. Keep track of state = RUNNING and check if the state has been in the return path of hrtimer_run_queue. In case the state has been changed, ignore a restart request and do not touch the state variable. Signed-off-by: Steven Rostedt Signed-off-by: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/hrtimer.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'kernel') diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index f1c4155b49ac..f580dd9db286 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -550,6 +550,7 @@ static inline void run_hrtimer_queue(struct hrtimer_base *base) fn = timer->function; data = timer->data; set_curr_timer(base, timer); + timer->state = HRTIMER_RUNNING; __remove_hrtimer(timer, base); spin_unlock_irq(&base->lock); @@ -565,6 +566,10 @@ static inline void run_hrtimer_queue(struct hrtimer_base *base) spin_lock_irq(&base->lock); + /* Another CPU has added back the timer */ + if (timer->state != HRTIMER_RUNNING) + continue; + if (restart == HRTIMER_RESTART) enqueue_hrtimer(timer, base); else -- cgit v1.2.2 From 7978672c4d9a1e6a6081de3a9d9ba5e5b24904a0 Mon Sep 17 00:00:00 2001 From: George Anzinger Date: Wed, 1 Feb 2006 03:05:11 -0800 Subject: [PATCH] hrtimers: cleanups and simplifications Clean up the interface to hrtimers by changing the init code to pass the mode as well as the clock. This allow the init code to select the correct base and eliminates extra timer re-init code in posix-timers. We also simplify the restart interface nanosleep use. Signed-off-by: George Anzinger Signed-off-by: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/fork.c | 2 +- kernel/hrtimer.c | 59 +++++++++++++++++++++------------------------------ kernel/posix-timers.c | 37 ++++++++------------------------ 3 files changed, 34 insertions(+), 64 deletions(-) (limited to 'kernel') diff --git a/kernel/fork.c b/kernel/fork.c index 4ae8cfc1c89c..7f0ab5ee948c 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -802,7 +802,7 @@ static inline int copy_signal(unsigned long clone_flags, struct task_struct * ts init_sigpending(&sig->shared_pending); INIT_LIST_HEAD(&sig->posix_timers); - hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC); + hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC, HRTIMER_REL); sig->it_real_incr.tv64 = 0; sig->real_timer.function = it_real_fn; sig->real_timer.data = tsk; diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index f580dd9db286..efff9496b2fa 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -66,6 +66,12 @@ EXPORT_SYMBOL_GPL(ktime_get_real); /* * The timer bases: + * + * Note: If we want to add new timer bases, we have to skip the two + * clock ids captured by the cpu-timers. We do this by holding empty + * entries rather than doing math adjustment of the clock ids. + * This ensures that we capture erroneous accesses to these clock ids + * rather than moving them into the range of valid clock id's. */ #define MAX_HRTIMER_BASES 2 @@ -483,29 +489,25 @@ ktime_t hrtimer_get_remaining(const struct hrtimer *timer) } /** - * hrtimer_rebase - rebase an initialized hrtimer to a different base + * hrtimer_init - initialize a timer to the given clock * - * @timer: the timer to be rebased + * @timer: the timer to be initialized * @clock_id: the clock to be used + * @mode: timer mode abs/rel */ -void hrtimer_rebase(struct hrtimer *timer, const clockid_t clock_id) +void hrtimer_init(struct hrtimer *timer, clockid_t clock_id, + enum hrtimer_mode mode) { struct hrtimer_base *bases; + memset(timer, 0, sizeof(struct hrtimer)); + bases = per_cpu(hrtimer_bases, raw_smp_processor_id()); - timer->base = &bases[clock_id]; -} -/** - * hrtimer_init - initialize a timer to the given clock - * - * @timer: the timer to be initialized - * @clock_id: the clock to be used - */ -void hrtimer_init(struct hrtimer *timer, const clockid_t clock_id) -{ - memset(timer, 0, sizeof(struct hrtimer)); - hrtimer_rebase(timer, clock_id); + if (clock_id == CLOCK_REALTIME && mode != HRTIMER_ABS) + clock_id = CLOCK_MONOTONIC; + + timer->base = &bases[clock_id]; } /** @@ -643,8 +645,7 @@ schedule_hrtimer_interruptible(struct hrtimer *timer, return schedule_hrtimer(timer, mode); } -static long __sched -nanosleep_restart(struct restart_block *restart, clockid_t clockid) +static long __sched nanosleep_restart(struct restart_block *restart) { struct timespec __user *rmtp; struct timespec tu; @@ -654,7 +655,7 @@ nanosleep_restart(struct restart_block *restart, clockid_t clockid) restart->fn = do_no_restart_syscall; - hrtimer_init(&timer, clockid); + hrtimer_init(&timer, (clockid_t) restart->arg3, HRTIMER_ABS); timer.expires.tv64 = ((u64)restart->arg1 << 32) | (u64) restart->arg0; @@ -674,16 +675,6 @@ nanosleep_restart(struct restart_block *restart, clockid_t clockid) return -ERESTART_RESTARTBLOCK; } -static long __sched nanosleep_restart_mono(struct restart_block *restart) -{ - return nanosleep_restart(restart, CLOCK_MONOTONIC); -} - -static long __sched nanosleep_restart_real(struct restart_block *restart) -{ - return nanosleep_restart(restart, CLOCK_REALTIME); -} - long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp, const enum hrtimer_mode mode, const clockid_t clockid) { @@ -692,7 +683,7 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp, struct timespec tu; ktime_t rem; - hrtimer_init(&timer, clockid); + hrtimer_init(&timer, clockid, mode); timer.expires = timespec_to_ktime(*rqtp); @@ -700,7 +691,7 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp, if (rem.tv64 <= 0) return 0; - /* Absolute timers do not update the rmtp value: */ + /* Absolute timers do not update the rmtp value and restart: */ if (mode == HRTIMER_ABS) return -ERESTARTNOHAND; @@ -710,11 +701,11 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp, return -EFAULT; restart = ¤t_thread_info()->restart_block; - restart->fn = (clockid == CLOCK_MONOTONIC) ? - nanosleep_restart_mono : nanosleep_restart_real; + restart->fn = nanosleep_restart; restart->arg0 = timer.expires.tv64 & 0xFFFFFFFF; restart->arg1 = timer.expires.tv64 >> 32; restart->arg2 = (unsigned long) rmtp; + restart->arg3 = (unsigned long) timer.base->index; return -ERESTART_RESTARTBLOCK; } @@ -741,10 +732,8 @@ static void __devinit init_hrtimers_cpu(int cpu) struct hrtimer_base *base = per_cpu(hrtimer_bases, cpu); int i; - for (i = 0; i < MAX_HRTIMER_BASES; i++) { + for (i = 0; i < MAX_HRTIMER_BASES; i++, base++) spin_lock_init(&base->lock); - base++; - } } #ifdef CONFIG_HOTPLUG_CPU diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c index 3b606d361b52..28e72fd0029f 100644 --- a/kernel/posix-timers.c +++ b/kernel/posix-timers.c @@ -194,9 +194,7 @@ static inline int common_clock_set(const clockid_t which_clock, static int common_timer_create(struct k_itimer *new_timer) { - hrtimer_init(&new_timer->it.real.timer, new_timer->it_clock); - new_timer->it.real.timer.data = new_timer; - new_timer->it.real.timer.function = posix_timer_fn; + hrtimer_init(&new_timer->it.real.timer, new_timer->it_clock, 0); return 0; } @@ -693,6 +691,7 @@ common_timer_set(struct k_itimer *timr, int flags, struct itimerspec *new_setting, struct itimerspec *old_setting) { struct hrtimer *timer = &timr->it.real.timer; + enum hrtimer_mode mode; if (old_setting) common_timer_get(timr, old_setting); @@ -714,14 +713,10 @@ common_timer_set(struct k_itimer *timr, int flags, if (!new_setting->it_value.tv_sec && !new_setting->it_value.tv_nsec) return 0; - /* Posix madness. Only absolute CLOCK_REALTIME timers - * are affected by clock sets. So we must reiniatilize - * the timer. - */ - if (timr->it_clock == CLOCK_REALTIME && (flags & TIMER_ABSTIME)) - hrtimer_rebase(timer, CLOCK_REALTIME); - else - hrtimer_rebase(timer, CLOCK_MONOTONIC); + mode = flags & TIMER_ABSTIME ? HRTIMER_ABS : HRTIMER_REL; + hrtimer_init(&timr->it.real.timer, timr->it_clock, mode); + timr->it.real.timer.data = timr; + timr->it.real.timer.function = posix_timer_fn; timer->expires = timespec_to_ktime(new_setting->it_value); @@ -732,8 +727,7 @@ common_timer_set(struct k_itimer *timr, int flags, if (((timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE)) return 0; - hrtimer_start(timer, timer->expires, (flags & TIMER_ABSTIME) ? - HRTIMER_ABS : HRTIMER_REL); + hrtimer_start(timer, timer->expires, mode); return 0; } @@ -948,21 +942,8 @@ sys_clock_getres(const clockid_t which_clock, struct timespec __user *tp) static int common_nsleep(const clockid_t which_clock, int flags, struct timespec *tsave, struct timespec __user *rmtp) { - int mode = flags & TIMER_ABSTIME ? HRTIMER_ABS : HRTIMER_REL; - int clockid = which_clock; - - switch (which_clock) { - case CLOCK_REALTIME: - /* Posix madness. Only absolute timers on clock realtime - are affected by clock set. */ - if (mode != HRTIMER_ABS) - clockid = CLOCK_MONOTONIC; - case CLOCK_MONOTONIC: - break; - default: - return -EINVAL; - } - return hrtimer_nanosleep(tsave, rmtp, mode, clockid); + return hrtimer_nanosleep(tsave, rmtp, flags & TIMER_ABSTIME ? + HRTIMER_ABS : HRTIMER_REL, which_clock); } asmlinkage long -- cgit v1.2.2 From 66188fae3bf7f8dd951e2291d2a81888ed1b65de Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 1 Feb 2006 03:05:13 -0800 Subject: [PATCH] hrtimers: add back lost credit lines At some point we added credits to people who actively helped to bring k/hr-timers along. This was lost in the big code revamp. Add it back. Signed-off-by: Thomas Gleixner Signed-off-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/hrtimer.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'kernel') diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index efff9496b2fa..2b6e1757aedd 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -21,6 +21,12 @@ * Credits: * based on kernel/timer.c * + * Help, testing, suggestions, bugfixes, improvements were + * provided by: + * + * George Anzinger, Andrew Morton, Steven Rostedt, Roman Zippel + * et. al. + * * For licencing details see kernel-base/COPYING */ -- cgit v1.2.2 From 952bbc87f01f552ef091a62ea2a721b5b2670e74 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 1 Feb 2006 03:05:13 -0800 Subject: [PATCH] hrtimers: set correct initial expiry time for relative SIGEV_NONE timers The expiry time for relative timers with SIGEV_NONE set was never updated to the correct value. Pointed out by George Anzinger. Signed-off-by: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/posix-timers.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c index 28e72fd0029f..aad6f138d5c9 100644 --- a/kernel/posix-timers.c +++ b/kernel/posix-timers.c @@ -724,8 +724,13 @@ common_timer_set(struct k_itimer *timr, int flags, timr->it.real.interval = timespec_to_ktime(new_setting->it_interval); /* SIGEV_NONE timers are not queued ! See common_timer_get */ - if (((timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE)) + if (((timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE)) { + /* Setup correct expiry time for relative timers */ + if (mode == HRTIMER_REL) + timer->expires = ktime_add(timer->expires, + timer->base->get_time()); return 0; + } hrtimer_start(timer, timer->expires, mode); return 0; -- cgit v1.2.2 From 493f01d1d0699ddafc30067d33fcc18d0b95b624 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Wed, 1 Feb 2006 03:05:14 -0800 Subject: [PATCH] kernel/posix-timers.c: remove do_posix_clock_notimer_create() This function is neither used nor has any real contents. Signed-off-by: Adrian Bunk Acked-by: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/posix-timers.c | 6 ------ 1 file changed, 6 deletions(-) (limited to 'kernel') diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c index aad6f138d5c9..216f574b5ffb 100644 --- a/kernel/posix-timers.c +++ b/kernel/posix-timers.c @@ -875,12 +875,6 @@ int do_posix_clock_nosettime(const clockid_t clockid, struct timespec *tp) } EXPORT_SYMBOL_GPL(do_posix_clock_nosettime); -int do_posix_clock_notimer_create(struct k_itimer *timer) -{ - return -EINVAL; -} -EXPORT_SYMBOL_GPL(do_posix_clock_notimer_create); - int do_posix_clock_nonanosleep(const clockid_t clock, int flags, struct timespec *t, struct timespec __user *r) { -- cgit v1.2.2 From 2f7016d917faef8f1e016b4a7bd7f594694480b6 Mon Sep 17 00:00:00 2001 From: Jack Steiner Date: Wed, 1 Feb 2006 03:05:18 -0800 Subject: [PATCH] sys_sched_getaffinity() & hotplug Change sched_getaffinity() so that it returns a bitmap that indicates the legally schedulable cpus that a task is allowed to run on. Without this patch, if CONFIG_HOTPLUG_CPU is enabled, sched_getaffinity() unconditionally returns (at least on IA64) a mask with NR_CPUS bits set. This conveys no useful infornmation except for a kernel compile option. This fixes a breakage we obseved running recent kernels. We have MPI jobs that use sched_getaffinity() to determine where to place their threads. Placing them on non-existant cpus is problematic :-) Signed-off-by: Jack Steiner Acked-by: Ingo Molnar Cc: Nathan Lynch Cc: Paul Jackson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sched.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sched.c b/kernel/sched.c index ec7fd9cee306..f77f23f8f479 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -4031,7 +4031,7 @@ long sched_getaffinity(pid_t pid, cpumask_t *mask) goto out_unlock; retval = 0; - cpus_and(*mask, p->cpus_allowed, cpu_possible_map); + cpus_and(*mask, p->cpus_allowed, cpu_online_map); out_unlock: read_unlock(&tasklist_lock); -- cgit v1.2.2 From f7b8988ff50d99c99746f65f420364e91362c065 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 1 Feb 2006 03:05:21 -0800 Subject: [PATCH] swsusp: do not change log level during suspend/resume Prevent the kernel from setting the log level to 10 unconditionally during suspend/resume which was needed in the past for debugging, but generally is undesirable. Signed-off-by: Rafael J. Wysocki Acked-by: Pavel Machek Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/power/console.c | 12 +----------- kernel/power/power.h | 5 +++++ 2 files changed, 6 insertions(+), 11 deletions(-) (limited to 'kernel') diff --git a/kernel/power/console.c b/kernel/power/console.c index 7ff375e7c95f..579d239d129f 100644 --- a/kernel/power/console.c +++ b/kernel/power/console.c @@ -9,18 +9,11 @@ #include #include "power.h" -static int new_loglevel = 10; -static int orig_loglevel; #ifdef SUSPEND_CONSOLE static int orig_fgconsole, orig_kmsg; -#endif int pm_prepare_console(void) { - orig_loglevel = console_loglevel; - console_loglevel = new_loglevel; - -#ifdef SUSPEND_CONSOLE acquire_console_sem(); orig_fgconsole = fg_console; @@ -41,18 +34,15 @@ int pm_prepare_console(void) } orig_kmsg = kmsg_redirect; kmsg_redirect = SUSPEND_CONSOLE; -#endif return 0; } void pm_restore_console(void) { - console_loglevel = orig_loglevel; -#ifdef SUSPEND_CONSOLE acquire_console_sem(); set_console(orig_fgconsole); release_console_sem(); kmsg_redirect = orig_kmsg; -#endif return; } +#endif diff --git a/kernel/power/power.h b/kernel/power/power.h index 61beb5e0e927..d8f0d1a76bae 100644 --- a/kernel/power/power.h +++ b/kernel/power/power.h @@ -42,8 +42,13 @@ static struct subsys_attribute _name##_attr = { \ extern struct subsystem power_subsys; +#ifdef SUSPEND_CONSOLE extern int pm_prepare_console(void); extern void pm_restore_console(void); +#else +static int pm_prepare_console(void) { return 0; } +static void pm_restore_console(void) {} +#endif /* References to section boundaries */ extern const void __nosave_begin, __nosave_end; -- cgit v1.2.2 From c84db23c6e587d3ab00a41c51fedf758e1f6ecd4 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Wed, 1 Feb 2006 03:05:29 -0800 Subject: [PATCH] zone_reclaim: minor fixes - If we only reclaim nr_pages then its okay to stay on node. Switch from > to >= for the comparison. - vm_table[] entry for zone_reclaim_mode is a bit screwed up. - Add empty lines around shrink_zone to show that this is the central function to be called. Signed-off-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sysctl.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index cb99a42f8b37..c74f03bc0144 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -878,7 +878,8 @@ static ctl_table vm_table[] = { .maxlen = sizeof(zone_reclaim_mode), .mode = 0644, .proc_handler = &proc_dointvec, - .strategy = &zero, + .strategy = &sysctl_intvec, + .extra1 = &zero, }, #endif { .ctl_name = 0 } -- cgit v1.2.2 From 2a11ff06d7d12be5d1bbcf592fff649b45ac2388 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Wed, 1 Feb 2006 03:05:33 -0800 Subject: [PATCH] zone_reclaim: configurable off node allocation period. Currently the zone_reclaim code has a fixed window of 30 seconds of off node allocations should a local zone have no unused pagecache pages left. Reclaim will be attempted again after this timeout period to avoid repeated useless scans for memory. This is also useful to established sufficiently large off node allocation chunks to relieve the local node. It may be beneficial to adjust that time period for some special situations. For example if memory use was exceeding node capacity one may want to give up for longer periods of time. If memory spikes intermittendly then one may want to shorten the time period to reduce the number of off node allocations. This patch allows just that.... Signed-off-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sysctl.c | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'kernel') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index c74f03bc0144..71dd6f62efec 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -881,6 +881,15 @@ static ctl_table vm_table[] = { .strategy = &sysctl_intvec, .extra1 = &zero, }, + { + .ctl_name = VM_ZONE_RECLAIM_INTERVAL, + .procname = "zone_reclaim_interval", + .data = &zone_reclaim_interval, + .maxlen = sizeof(zone_reclaim_interval), + .mode = 0644, + .proc_handler = &proc_dointvec_jiffies, + .strategy = &sysctl_jiffies, + }, #endif { .ctl_name = 0 } }; -- cgit v1.2.2