From f123c98e7f168e949b283690693695f988332c3d Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 6 Jan 2011 15:08:29 -0500 Subject: rtmutex: Fix comment about why new_owner can be NULL in wake_futex_pi() The comment about why rt_mutex_next_owner() can return NULL in wake_futex_pi() is not the normal case. Tracing the cause of why this occurs is more likely that waiter simply timedout. But because it originally caused contention with the futex, the owner will go into the kernel when it unlocks the lock. Then it will hit this code path and rt_mutex_next_owner() will return NULL. Cc: Thomas Gleixner Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar --- kernel/futex.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/futex.c b/kernel/futex.c index 3019b92e6917..5696d38cc71d 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -791,10 +791,9 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this) new_owner = rt_mutex_next_owner(&pi_state->pi_mutex); /* - * This happens when we have stolen the lock and the original - * pending owner did not enqueue itself back on the rt_mutex. - * Thats not a tragedy. We know that way, that a lock waiter - * is on the fly. We make the futex_q waiter the pending owner. + * It is possible that the next waiter (the one that brought + * this owner to the kernel) timed out and is no longer + * waiting on the lock. */ if (!new_owner) new_owner = this->task; -- cgit v1.2.3 From 5fdade95f26372154459347dfb9f60721d22cfc7 Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Tue, 11 Jan 2011 12:18:12 -0500 Subject: time: Rename misnamed minsec argument of clocks_calc_mult_shift() The minsec argument to clocks_calc_mult_shift() is misnamed. It is used to clamp the magnitude of the mult factor so that a multiplication with any value in the given range won't overflow a 64 bit result. Let's rename it to match the actual usage. Signed-off-by: Nicolas Pitre Acked-by: John Stultz LKML-Reference: Signed-off-by: Thomas Gleixner --- kernel/time/clocksource.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index c18d7efa1b4b..8588abcac07b 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -113,7 +113,7 @@ EXPORT_SYMBOL_GPL(timecounter_cyc2time); * @shift: pointer to shift variable * @from: frequency to convert from * @to: frequency to convert to - * @minsec: guaranteed runtime conversion range in seconds + * @maxsec: guaranteed runtime conversion range in seconds * * The function evaluates the shift/mult pair for the scaled math * operations of clocksources and clockevents. @@ -122,7 +122,7 @@ EXPORT_SYMBOL_GPL(timecounter_cyc2time); * NSEC_PER_SEC == 1GHz and @from is the counter frequency. For clock * event @to is the counter frequency and @from is NSEC_PER_SEC. * - * The @minsec conversion range argument controls the time frame in + * The @maxsec conversion range argument controls the time frame in * seconds which must be covered by the runtime conversion with the * calculated mult and shift factors. This guarantees that no 64bit * overflow happens when the input value of the conversion is @@ -131,7 +131,7 @@ EXPORT_SYMBOL_GPL(timecounter_cyc2time); * factors. */ void -clocks_calc_mult_shift(u32 *mult, u32 *shift, u32 from, u32 to, u32 minsec) +clocks_calc_mult_shift(u32 *mult, u32 *shift, u32 from, u32 to, u32 maxsec) { u64 tmp; u32 sft, sftacc= 32; @@ -140,7 +140,7 @@ clocks_calc_mult_shift(u32 *mult, u32 *shift, u32 from, u32 to, u32 minsec) * Calculate the shift factor which is limiting the conversion * range: */ - tmp = ((u64)minsec * from) >> 32; + tmp = ((u64)maxsec * from) >> 32; while (tmp) { tmp >>=1; sftacc--; -- cgit v1.2.3 From afa14e7c553ebe45844d76208f66017a43abd0e2 Mon Sep 17 00:00:00 2001 From: H Hartley Sweeten Date: Tue, 11 Jan 2011 17:59:38 -0600 Subject: timekeeping: Make local variables static Signed-off-by: H Hartley Sweeten Cc: John Stultz LKML-Reference: <0D753D10438DA54287A00B027084269764CE0E54B7@AUSP01VMBX24.collaborationhost.net> Signed-off-by: Thomas Gleixner --- kernel/time/timekeeping.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 5bb86da82003..eef7452bd8a9 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -49,7 +49,7 @@ struct timekeeper { u32 mult; }; -struct timekeeper timekeeper; +static struct timekeeper timekeeper; /** * timekeeper_setup_internals - Set up internals to use clocksource clock. @@ -164,7 +164,7 @@ static struct timespec total_sleep_time; /* * The raw monotonic time for the CLOCK_MONOTONIC_RAW posix clock. */ -struct timespec raw_time; +static struct timespec raw_time; /* flag for if timekeeping is suspended */ int __read_mostly timekeeping_suspended; -- cgit v1.2.3 From c072a388d59a1d48e36864d0e66f42d71745be1c Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 7 Jan 2011 02:33:47 -0800 Subject: rcu: demote SRCU_SYNCHRONIZE_DELAY from kernel-parameter status Because the adaptive synchronize_srcu_expedited() approach has worked very well in testing, remove the kernel parameter and replace it by a C-preprocessor macro. If someone finds problems with this approach, a more complex and aggressively adaptive approach might be required. Longer term, SRCU will be merged with the other RCU implementations, at which point synchronize_srcu_expedited() will be event driven, just as synchronize_sched_expedited() currently is. At that point, there will be no need for this adaptive approach. Reported-by: Linus Torvalds Signed-off-by: Paul E. McKenney --- init/Kconfig | 15 --------------- kernel/srcu.c | 15 +++++++++++++-- 2 files changed, 13 insertions(+), 17 deletions(-) (limited to 'kernel') diff --git a/init/Kconfig b/init/Kconfig index 526ec1c7456a..e11bc793a91d 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -497,21 +497,6 @@ config RCU_BOOST_DELAY Accept the default if unsure. -config SRCU_SYNCHRONIZE_DELAY - int "Microseconds to delay before waiting for readers" - range 0 20 - default 10 - help - This option controls how long SRCU delays before entering its - loop waiting on SRCU readers. The purpose of this loop is - to avoid the unconditional context-switch penalty that would - otherwise be incurred if there was an active SRCU reader, - in a manner similar to adaptive locking schemes. This should - be set to be a bit longer than the common-case SRCU read-side - critical-section overhead. - - Accept the default if unsure. - endmenu # "RCU Subsystem" config IKCONFIG diff --git a/kernel/srcu.c b/kernel/srcu.c index 98d8c1e80edb..73ce23feaea9 100644 --- a/kernel/srcu.c +++ b/kernel/srcu.c @@ -155,6 +155,16 @@ void __srcu_read_unlock(struct srcu_struct *sp, int idx) } EXPORT_SYMBOL_GPL(__srcu_read_unlock); +/* + * We use an adaptive strategy for synchronize_srcu() and especially for + * synchronize_srcu_expedited(). We spin for a fixed time period + * (defined below) to allow SRCU readers to exit their read-side critical + * sections. If there are still some readers after 10 microseconds, + * we repeatedly block for 1-millisecond time periods. This approach + * has done well in testing, so there is no need for a config parameter. + */ +#define SYNCHRONIZE_SRCU_READER_DELAY 10 + /* * Helper function for synchronize_srcu() and synchronize_srcu_expedited(). */ @@ -207,11 +217,12 @@ static void __synchronize_srcu(struct srcu_struct *sp, void (*sync_func)(void)) * will have finished executing. We initially give readers * an arbitrarily chosen 10 microseconds to get out of their * SRCU read-side critical sections, then loop waiting 1/HZ - * seconds per iteration. + * seconds per iteration. The 10-microsecond value has done + * very well in testing. */ if (srcu_readers_active_idx(sp, idx)) - udelay(CONFIG_SRCU_SYNCHRONIZE_DELAY); + udelay(SYNCHRONIZE_SRCU_READER_DELAY); while (srcu_readers_active_idx(sp, idx)) schedule_timeout_interruptible(1); -- cgit v1.2.3 From b24efdfdf679cf9b05947c531971905fc727dd40 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 12 Jan 2011 14:18:11 -0800 Subject: rcu: avoid pointless blocked-task warnings If the RCU callback-processing kthread has nothing to do, it parks in a wait_event(). If RCU remains idle for more than two minutes, the kernel complains about this. This commit changes from wait_event() to wait_event_interruptible() to prevent the kernel from complaining just because RCU is idle. Reported-by: Russell King Signed-off-by: Paul E. McKenney Signed-off-by: Paul E. McKenney Tested-by: Thomas Weber Tested-by: Russell King --- kernel/rcutiny.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c index 034493724749..0c343b9a46d5 100644 --- a/kernel/rcutiny.c +++ b/kernel/rcutiny.c @@ -189,7 +189,8 @@ static int rcu_kthread(void *arg) unsigned long flags; for (;;) { - wait_event(rcu_kthread_wq, have_rcu_kthread_work != 0); + wait_event_interruptible(rcu_kthread_wq, + have_rcu_kthread_work != 0); morework = rcu_boost(); local_irq_save(flags); work = have_rcu_kthread_work; -- cgit v1.2.3 From 7f85803a26f304e698c673838aab06cc6d4d6e59 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Fri, 14 Jan 2011 17:49:02 +0800 Subject: tracing: Remove syscall_exit_fields There is no need for syscall_exit_fields as the syscall exit event class can already host the fields in its structure, like most other trace events do by default. Use that default behavior instead. Following this scheme, we don't need anymore to override the get_fields() callback of the syscall exit event class either. Hence both syscall_exit_fields and syscall_get_exit_fields() can be removed. Also changed some indentation to keep the following under 80 characters: ".fields = LIST_HEAD_INIT(event_class_syscall_exit.fields)," Acked-by: Frederic Weisbecker Signed-off-by: Lai Jiangshan LKML-Reference: <4D301C0E.8090408@cn.fujitsu.com> Signed-off-by: Steven Rostedt --- kernel/trace/trace_syscalls.c | 33 ++++++++++++--------------------- 1 file changed, 12 insertions(+), 21 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index bac752f0cfb5..b706529b4fc7 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -23,9 +23,6 @@ static int syscall_exit_register(struct ftrace_event_call *event, static int syscall_enter_define_fields(struct ftrace_event_call *call); static int syscall_exit_define_fields(struct ftrace_event_call *call); -/* All syscall exit events have the same fields */ -static LIST_HEAD(syscall_exit_fields); - static struct list_head * syscall_get_enter_fields(struct ftrace_event_call *call) { @@ -34,34 +31,28 @@ syscall_get_enter_fields(struct ftrace_event_call *call) return &entry->enter_fields; } -static struct list_head * -syscall_get_exit_fields(struct ftrace_event_call *call) -{ - return &syscall_exit_fields; -} - struct trace_event_functions enter_syscall_print_funcs = { - .trace = print_syscall_enter, + .trace = print_syscall_enter, }; struct trace_event_functions exit_syscall_print_funcs = { - .trace = print_syscall_exit, + .trace = print_syscall_exit, }; struct ftrace_event_class event_class_syscall_enter = { - .system = "syscalls", - .reg = syscall_enter_register, - .define_fields = syscall_enter_define_fields, - .get_fields = syscall_get_enter_fields, - .raw_init = init_syscall_trace, + .system = "syscalls", + .reg = syscall_enter_register, + .define_fields = syscall_enter_define_fields, + .get_fields = syscall_get_enter_fields, + .raw_init = init_syscall_trace, }; struct ftrace_event_class event_class_syscall_exit = { - .system = "syscalls", - .reg = syscall_exit_register, - .define_fields = syscall_exit_define_fields, - .get_fields = syscall_get_exit_fields, - .raw_init = init_syscall_trace, + .system = "syscalls", + .reg = syscall_exit_register, + .define_fields = syscall_exit_define_fields, + .fields = LIST_HEAD_INIT(event_class_syscall_exit.fields), + .raw_init = init_syscall_trace, }; extern unsigned long __start_syscalls_metadata[]; -- cgit v1.2.3