From f4ad9bd208c98f32a6f9136618e0b8bebe3fb370 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Fri, 8 Apr 2011 12:53:09 +0800 Subject: [PATCH 01/22] sched: Eliminate dead code from wakeup_gran() calc_delta_fair() checks NICE_0_LOAD already, delete duplicate check. Signed-off-by: Shaohua Li Signed-off-by: Peter Zijlstra Cc: Mike Galbraith Link: http://lkml.kernel.org/r/1302238389.3981.92.camel@sli10-conroe Signed-off-by: Ingo Molnar --- kernel/sched_fair.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 6fa833ab2cb8..4ee50f0af8d1 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -1789,10 +1789,7 @@ wakeup_gran(struct sched_entity *curr, struct sched_entity *se) * This is especially important for buddies when the leftmost * task is higher priority than the buddy. */ - if (unlikely(se->load.weight != NICE_0_LOAD)) - gran = calc_delta_fair(gran, se); - - return gran; + return calc_delta_fair(gran, se); } /* From 184748cc50b2dceb8287f9fb657eda48ff8fcfe7 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 5 Apr 2011 17:23:39 +0200 Subject: [PATCH 02/22] sched: Provide scheduler_ipi() callback in response to smp_send_reschedule() For future rework of try_to_wake_up() we'd like to push part of that function onto the CPU the task is actually going to run on. In order to do so we need a generic callback from the existing scheduler IPI. This patch introduces such a generic callback: scheduler_ipi() and implements it as a NOP. BenH notes: PowerPC might use this IPI on offline CPUs under rare conditions! Acked-by: Russell King Acked-by: Martin Schwidefsky Acked-by: Chris Metcalf Acked-by: Jesper Nilsson Acked-by: Benjamin Herrenschmidt Signed-off-by: Ralf Baechle Reviewed-by: Frank Rowand Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Signed-off-by: Ingo Molnar Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20110405152728.744338123@chello.nl --- arch/alpha/kernel/smp.c | 3 +-- arch/arm/kernel/smp.c | 5 +---- arch/blackfin/mach-common/smp.c | 3 +++ arch/cris/arch-v32/kernel/smp.c | 13 ++++++++----- arch/ia64/kernel/irq_ia64.c | 2 ++ arch/ia64/xen/irq_xen.c | 10 +++++++++- arch/m32r/kernel/smp.c | 4 +--- arch/mips/cavium-octeon/smp.c | 2 ++ arch/mips/kernel/smtc.c | 2 +- arch/mips/mti-malta/malta-int.c | 2 ++ arch/mips/pmc-sierra/yosemite/smp.c | 4 ++++ arch/mips/sgi-ip27/ip27-irq.c | 2 ++ arch/mips/sibyte/bcm1480/smp.c | 7 +++---- arch/mips/sibyte/sb1250/smp.c | 7 +++---- arch/mn10300/kernel/smp.c | 5 +---- arch/parisc/kernel/smp.c | 5 +---- arch/powerpc/kernel/smp.c | 4 ++-- arch/s390/kernel/smp.c | 6 +++--- arch/sh/kernel/smp.c | 2 ++ arch/sparc/kernel/smp_32.c | 4 +++- arch/sparc/kernel/smp_64.c | 1 + arch/tile/kernel/smp.c | 6 +----- arch/um/kernel/smp.c | 2 +- arch/x86/kernel/smp.c | 5 ++--- arch/x86/xen/smp.c | 5 ++--- include/linux/sched.h | 2 ++ 26 files changed, 63 insertions(+), 50 deletions(-) diff --git a/arch/alpha/kernel/smp.c b/arch/alpha/kernel/smp.c index 42aa078a5e4d..5a621c6d22ab 100644 --- a/arch/alpha/kernel/smp.c +++ b/arch/alpha/kernel/smp.c @@ -585,8 +585,7 @@ handle_ipi(struct pt_regs *regs) switch (which) { case IPI_RESCHEDULE: - /* Reschedule callback. Everything to be done - is done by the interrupt return path. */ + scheduler_ipi(); break; case IPI_CALL_FUNC: diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 8fe05ad932e4..7a561eb731ea 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -560,10 +560,7 @@ asmlinkage void __exception_irq_entry do_IPI(int ipinr, struct pt_regs *regs) break; case IPI_RESCHEDULE: - /* - * nothing more to do - eveything is - * done on the interrupt return path - */ + scheduler_ipi(); break; case IPI_CALL_FUNC: diff --git a/arch/blackfin/mach-common/smp.c b/arch/blackfin/mach-common/smp.c index 6e17a265c4d3..326bb86f4d29 100644 --- a/arch/blackfin/mach-common/smp.c +++ b/arch/blackfin/mach-common/smp.c @@ -164,6 +164,9 @@ static irqreturn_t ipi_handler_int1(int irq, void *dev_instance) while (msg_queue->count) { msg = &msg_queue->ipi_message[msg_queue->head]; switch (msg->type) { + case BFIN_IPI_RESCHEDULE: + scheduler_ipi(); + break; case BFIN_IPI_CALL_FUNC: spin_unlock_irqrestore(&msg_queue->lock, flags); ipi_call_function(cpu, msg); diff --git a/arch/cris/arch-v32/kernel/smp.c b/arch/cris/arch-v32/kernel/smp.c index 4c9e3e1ba5d1..66cc75657e2f 100644 --- a/arch/cris/arch-v32/kernel/smp.c +++ b/arch/cris/arch-v32/kernel/smp.c @@ -342,15 +342,18 @@ irqreturn_t crisv32_ipi_interrupt(int irq, void *dev_id) ipi = REG_RD(intr_vect, irq_regs[smp_processor_id()], rw_ipi); + if (ipi.vector & IPI_SCHEDULE) { + scheduler_ipi(); + } if (ipi.vector & IPI_CALL) { - func(info); + func(info); } if (ipi.vector & IPI_FLUSH_TLB) { - if (flush_mm == FLUSH_ALL) - __flush_tlb_all(); - else if (flush_vma == FLUSH_ALL) + if (flush_mm == FLUSH_ALL) + __flush_tlb_all(); + else if (flush_vma == FLUSH_ALL) __flush_tlb_mm(flush_mm); - else + else __flush_tlb_page(flush_vma, flush_addr); } diff --git a/arch/ia64/kernel/irq_ia64.c b/arch/ia64/kernel/irq_ia64.c index 5b704740f160..782c3a357f24 100644 --- a/arch/ia64/kernel/irq_ia64.c +++ b/arch/ia64/kernel/irq_ia64.c @@ -31,6 +31,7 @@ #include #include #include +#include #include #include @@ -496,6 +497,7 @@ ia64_handle_irq (ia64_vector vector, struct pt_regs *regs) smp_local_flush_tlb(); kstat_incr_irqs_this_cpu(irq, desc); } else if (unlikely(IS_RESCHEDULE(vector))) { + scheduler_ipi(); kstat_incr_irqs_this_cpu(irq, desc); } else { ia64_setreg(_IA64_REG_CR_TPR, vector); diff --git a/arch/ia64/xen/irq_xen.c b/arch/ia64/xen/irq_xen.c index 108bb858acf2..b279e142c633 100644 --- a/arch/ia64/xen/irq_xen.c +++ b/arch/ia64/xen/irq_xen.c @@ -92,6 +92,8 @@ static unsigned short saved_irq_cnt; static int xen_slab_ready; #ifdef CONFIG_SMP +#include + /* Dummy stub. Though we may check XEN_RESCHEDULE_VECTOR before __do_IRQ, * it ends up to issue several memory accesses upon percpu data and * thus adds unnecessary traffic to other paths. @@ -99,7 +101,13 @@ static int xen_slab_ready; static irqreturn_t xen_dummy_handler(int irq, void *dev_id) { + return IRQ_HANDLED; +} +static irqreturn_t +xen_resched_handler(int irq, void *dev_id) +{ + scheduler_ipi(); return IRQ_HANDLED; } @@ -110,7 +118,7 @@ static struct irqaction xen_ipi_irqaction = { }; static struct irqaction xen_resched_irqaction = { - .handler = xen_dummy_handler, + .handler = xen_resched_handler, .flags = IRQF_DISABLED, .name = "resched" }; diff --git a/arch/m32r/kernel/smp.c b/arch/m32r/kernel/smp.c index 31cef20b2996..fc10b39893d4 100644 --- a/arch/m32r/kernel/smp.c +++ b/arch/m32r/kernel/smp.c @@ -122,8 +122,6 @@ void smp_send_reschedule(int cpu_id) * * Description: This routine executes on CPU which received * 'RESCHEDULE_IPI'. - * Rescheduling is processed at the exit of interrupt - * operation. * * Born on Date: 2002.02.05 * @@ -138,7 +136,7 @@ void smp_send_reschedule(int cpu_id) *==========================================================================*/ void smp_reschedule_interrupt(void) { - /* nothing to do */ + scheduler_ipi(); } /*==========================================================================* diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c index ba78b21cc8d0..76923eeb58b9 100644 --- a/arch/mips/cavium-octeon/smp.c +++ b/arch/mips/cavium-octeon/smp.c @@ -44,6 +44,8 @@ static irqreturn_t mailbox_interrupt(int irq, void *dev_id) if (action & SMP_CALL_FUNCTION) smp_call_function_interrupt(); + if (action & SMP_RESCHEDULE_YOURSELF) + scheduler_ipi(); /* Check if we've been told to flush the icache */ if (action & SMP_ICACHE_FLUSH) diff --git a/arch/mips/kernel/smtc.c b/arch/mips/kernel/smtc.c index 5a88cc4ccd5a..cedac4633741 100644 --- a/arch/mips/kernel/smtc.c +++ b/arch/mips/kernel/smtc.c @@ -929,7 +929,7 @@ static void post_direct_ipi(int cpu, struct smtc_ipi *pipi) static void ipi_resched_interrupt(void) { - /* Return from interrupt should be enough to cause scheduler check */ + scheduler_ipi(); } static void ipi_call_interrupt(void) diff --git a/arch/mips/mti-malta/malta-int.c b/arch/mips/mti-malta/malta-int.c index 9027061f0ead..7d93e6fbfa5a 100644 --- a/arch/mips/mti-malta/malta-int.c +++ b/arch/mips/mti-malta/malta-int.c @@ -309,6 +309,8 @@ static void ipi_call_dispatch(void) static irqreturn_t ipi_resched_interrupt(int irq, void *dev_id) { + scheduler_ipi(); + return IRQ_HANDLED; } diff --git a/arch/mips/pmc-sierra/yosemite/smp.c b/arch/mips/pmc-sierra/yosemite/smp.c index efc9e889b349..2608752898c0 100644 --- a/arch/mips/pmc-sierra/yosemite/smp.c +++ b/arch/mips/pmc-sierra/yosemite/smp.c @@ -55,6 +55,8 @@ void titan_mailbox_irq(void) if (status & 0x2) smp_call_function_interrupt(); + if (status & 0x4) + scheduler_ipi(); break; case 1: @@ -63,6 +65,8 @@ void titan_mailbox_irq(void) if (status & 0x2) smp_call_function_interrupt(); + if (status & 0x4) + scheduler_ipi(); break; } } diff --git a/arch/mips/sgi-ip27/ip27-irq.c b/arch/mips/sgi-ip27/ip27-irq.c index 0a04603d577c..b18b04e48577 100644 --- a/arch/mips/sgi-ip27/ip27-irq.c +++ b/arch/mips/sgi-ip27/ip27-irq.c @@ -147,8 +147,10 @@ static void ip27_do_irq_mask0(void) #ifdef CONFIG_SMP if (pend0 & (1UL << CPU_RESCHED_A_IRQ)) { LOCAL_HUB_CLR_INTR(CPU_RESCHED_A_IRQ); + scheduler_ipi(); } else if (pend0 & (1UL << CPU_RESCHED_B_IRQ)) { LOCAL_HUB_CLR_INTR(CPU_RESCHED_B_IRQ); + scheduler_ipi(); } else if (pend0 & (1UL << CPU_CALL_A_IRQ)) { LOCAL_HUB_CLR_INTR(CPU_CALL_A_IRQ); smp_call_function_interrupt(); diff --git a/arch/mips/sibyte/bcm1480/smp.c b/arch/mips/sibyte/bcm1480/smp.c index 47b347c992ea..d667875be564 100644 --- a/arch/mips/sibyte/bcm1480/smp.c +++ b/arch/mips/sibyte/bcm1480/smp.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include @@ -189,10 +190,8 @@ void bcm1480_mailbox_interrupt(void) /* Clear the mailbox to clear the interrupt */ __raw_writeq(((u64)action)<<48, mailbox_0_clear_regs[cpu]); - /* - * Nothing to do for SMP_RESCHEDULE_YOURSELF; returning from the - * interrupt will do the reschedule for us - */ + if (action & SMP_RESCHEDULE_YOURSELF) + scheduler_ipi(); if (action & SMP_CALL_FUNCTION) smp_call_function_interrupt(); diff --git a/arch/mips/sibyte/sb1250/smp.c b/arch/mips/sibyte/sb1250/smp.c index c00a5cb1128d..38e7f6bd7922 100644 --- a/arch/mips/sibyte/sb1250/smp.c +++ b/arch/mips/sibyte/sb1250/smp.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include @@ -177,10 +178,8 @@ void sb1250_mailbox_interrupt(void) /* Clear the mailbox to clear the interrupt */ ____raw_writeq(((u64)action) << 48, mailbox_clear_regs[cpu]); - /* - * Nothing to do for SMP_RESCHEDULE_YOURSELF; returning from the - * interrupt will do the reschedule for us - */ + if (action & SMP_RESCHEDULE_YOURSELF) + scheduler_ipi(); if (action & SMP_CALL_FUNCTION) smp_call_function_interrupt(); diff --git a/arch/mn10300/kernel/smp.c b/arch/mn10300/kernel/smp.c index 226c826a2194..83fb27912231 100644 --- a/arch/mn10300/kernel/smp.c +++ b/arch/mn10300/kernel/smp.c @@ -494,14 +494,11 @@ void smp_send_stop(void) * @irq: The interrupt number. * @dev_id: The device ID. * - * We need do nothing here, since the scheduling will be effected on our way - * back through entry.S. - * * Returns IRQ_HANDLED to indicate we handled the interrupt successfully. */ static irqreturn_t smp_reschedule_interrupt(int irq, void *dev_id) { - /* do nothing */ + scheduler_ipi(); return IRQ_HANDLED; } diff --git a/arch/parisc/kernel/smp.c b/arch/parisc/kernel/smp.c index 69d63d354ef0..828305f19cff 100644 --- a/arch/parisc/kernel/smp.c +++ b/arch/parisc/kernel/smp.c @@ -155,10 +155,7 @@ ipi_interrupt(int irq, void *dev_id) case IPI_RESCHEDULE: smp_debug(100, KERN_DEBUG "CPU%d IPI_RESCHEDULE\n", this_cpu); - /* - * Reschedule callback. Everything to be - * done is done by the interrupt return path. - */ + scheduler_ipi(); break; case IPI_CALL_FUNC: diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index cbdbb14be4b0..9f9c204bef69 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -116,7 +116,7 @@ void smp_message_recv(int msg) generic_smp_call_function_interrupt(); break; case PPC_MSG_RESCHEDULE: - /* we notice need_resched on exit */ + scheduler_ipi(); break; case PPC_MSG_CALL_FUNC_SINGLE: generic_smp_call_function_single_interrupt(); @@ -146,7 +146,7 @@ static irqreturn_t call_function_action(int irq, void *data) static irqreturn_t reschedule_action(int irq, void *data) { - /* we just need the return path side effect of checking need_resched */ + scheduler_ipi(); return IRQ_HANDLED; } diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 63a97db83f96..63c7d9ff220d 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -165,12 +165,12 @@ static void do_ext_call_interrupt(unsigned int ext_int_code, kstat_cpu(smp_processor_id()).irqs[EXTINT_IPI]++; /* * handle bit signal external calls - * - * For the ec_schedule signal we have to do nothing. All the work - * is done automatically when we return from the interrupt. */ bits = xchg(&S390_lowcore.ext_call_fast, 0); + if (test_bit(ec_schedule, &bits)) + scheduler_ipi(); + if (test_bit(ec_call_function, &bits)) generic_smp_call_function_interrupt(); diff --git a/arch/sh/kernel/smp.c b/arch/sh/kernel/smp.c index 509b36b45115..6207561ea34a 100644 --- a/arch/sh/kernel/smp.c +++ b/arch/sh/kernel/smp.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include #include @@ -323,6 +324,7 @@ void smp_message_recv(unsigned int msg) generic_smp_call_function_interrupt(); break; case SMP_MSG_RESCHEDULE: + scheduler_ipi(); break; case SMP_MSG_FUNCTION_SINGLE: generic_smp_call_function_single_interrupt(); diff --git a/arch/sparc/kernel/smp_32.c b/arch/sparc/kernel/smp_32.c index 91c10fb70858..f95690c167b6 100644 --- a/arch/sparc/kernel/smp_32.c +++ b/arch/sparc/kernel/smp_32.c @@ -125,7 +125,9 @@ struct linux_prom_registers smp_penguin_ctable __cpuinitdata = { 0 }; void smp_send_reschedule(int cpu) { - /* See sparc64 */ + /* + * XXX missing reschedule IPI, see scheduler_ipi() + */ } void smp_send_stop(void) diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index 3e94a8c23238..9478da7fdb3e 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -1368,6 +1368,7 @@ void smp_send_reschedule(int cpu) void __irq_entry smp_receive_signal_client(int irq, struct pt_regs *regs) { clear_softint(1 << irq); + scheduler_ipi(); } /* This is a nop because we capture all other cpus diff --git a/arch/tile/kernel/smp.c b/arch/tile/kernel/smp.c index a4293102ef81..c52224d5ed45 100644 --- a/arch/tile/kernel/smp.c +++ b/arch/tile/kernel/smp.c @@ -189,12 +189,8 @@ void flush_icache_range(unsigned long start, unsigned long end) /* Called when smp_send_reschedule() triggers IRQ_RESCHEDULE. */ static irqreturn_t handle_reschedule_ipi(int irq, void *token) { - /* - * Nothing to do here; when we return from interrupt, the - * rescheduling will occur there. But do bump the interrupt - * profiler count in the meantime. - */ __get_cpu_var(irq_stat).irq_resched_count++; + scheduler_ipi(); return IRQ_HANDLED; } diff --git a/arch/um/kernel/smp.c b/arch/um/kernel/smp.c index 106bf27e2a9a..eefb107d2d73 100644 --- a/arch/um/kernel/smp.c +++ b/arch/um/kernel/smp.c @@ -173,7 +173,7 @@ void IPI_handler(int cpu) break; case 'R': - set_tsk_need_resched(current); + scheduler_ipi(); break; case 'S': diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c index 513deac7228d..013e7eba83bb 100644 --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -194,14 +194,13 @@ static void native_stop_other_cpus(int wait) } /* - * Reschedule call back. Nothing to do, - * all the work is done automatically when - * we return from the interrupt. + * Reschedule call back. */ void smp_reschedule_interrupt(struct pt_regs *regs) { ack_APIC_irq(); inc_irq_stat(irq_resched_count); + scheduler_ipi(); /* * KVM uses this interrupt to force a cpu out of guest mode */ diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 30612441ed99..762b46ab14d5 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -46,13 +46,12 @@ static irqreturn_t xen_call_function_interrupt(int irq, void *dev_id); static irqreturn_t xen_call_function_single_interrupt(int irq, void *dev_id); /* - * Reschedule call back. Nothing to do, - * all the work is done automatically when - * we return from the interrupt. + * Reschedule call back. */ static irqreturn_t xen_reschedule_interrupt(int irq, void *dev_id) { inc_irq_stat(irq_resched_count); + scheduler_ipi(); return IRQ_HANDLED; } diff --git a/include/linux/sched.h b/include/linux/sched.h index 4ec2c027e92c..758e27afcda5 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2189,8 +2189,10 @@ extern void set_task_comm(struct task_struct *tsk, char *from); extern char *get_task_comm(char *to, struct task_struct *tsk); #ifdef CONFIG_SMP +static inline void scheduler_ipi(void) { } extern unsigned long wait_task_inactive(struct task_struct *, long match_state); #else +static inline void scheduler_ipi(void) { } static inline unsigned long wait_task_inactive(struct task_struct *p, long match_state) { From 3ca7a440da394808571dad32d33d3bc0389982e6 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 5 Apr 2011 17:23:40 +0200 Subject: [PATCH 03/22] sched: Always provide p->on_cpu Always provide p->on_cpu so that we can determine if its on a cpu without having to lock the rq. Reviewed-by: Frank Rowand Signed-off-by: Peter Zijlstra Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Link: http://lkml.kernel.org/r/20110405152728.785452014@chello.nl Signed-off-by: Ingo Molnar --- include/linux/sched.h | 4 +--- kernel/sched.c | 46 +++++++++++++++++++++++++++---------------- 2 files changed, 30 insertions(+), 20 deletions(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index 758e27afcda5..3435837e89ff 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1200,9 +1200,7 @@ struct task_struct { int lock_depth; /* BKL lock depth */ #ifdef CONFIG_SMP -#ifdef __ARCH_WANT_UNLOCKED_CTXSW - int oncpu; -#endif + int on_cpu; #endif int prio, static_prio, normal_prio; diff --git a/kernel/sched.c b/kernel/sched.c index a187c3fe027b..cd2593e1a3ec 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -838,18 +838,39 @@ static inline int task_current(struct rq *rq, struct task_struct *p) return rq->curr == p; } -#ifndef __ARCH_WANT_UNLOCKED_CTXSW static inline int task_running(struct rq *rq, struct task_struct *p) { +#ifdef CONFIG_SMP + return p->on_cpu; +#else return task_current(rq, p); +#endif } +#ifndef __ARCH_WANT_UNLOCKED_CTXSW static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next) { +#ifdef CONFIG_SMP + /* + * We can optimise this out completely for !SMP, because the + * SMP rebalancing from interrupt is the only thing that cares + * here. + */ + next->on_cpu = 1; +#endif } static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) { +#ifdef CONFIG_SMP + /* + * After ->on_cpu is cleared, the task can be moved to a different CPU. + * We must ensure this doesn't happen until the switch is completely + * finished. + */ + smp_wmb(); + prev->on_cpu = 0; +#endif #ifdef CONFIG_DEBUG_SPINLOCK /* this is a valid case when another task releases the spinlock */ rq->lock.owner = current; @@ -865,15 +886,6 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) } #else /* __ARCH_WANT_UNLOCKED_CTXSW */ -static inline int task_running(struct rq *rq, struct task_struct *p) -{ -#ifdef CONFIG_SMP - return p->oncpu; -#else - return task_current(rq, p); -#endif -} - static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next) { #ifdef CONFIG_SMP @@ -882,7 +894,7 @@ static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next) * SMP rebalancing from interrupt is the only thing that cares * here. */ - next->oncpu = 1; + next->on_cpu = 1; #endif #ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW raw_spin_unlock_irq(&rq->lock); @@ -895,12 +907,12 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) { #ifdef CONFIG_SMP /* - * After ->oncpu is cleared, the task can be moved to a different CPU. + * After ->on_cpu is cleared, the task can be moved to a different CPU. * We must ensure this doesn't happen until the switch is completely * finished. */ smp_wmb(); - prev->oncpu = 0; + prev->on_cpu = 0; #endif #ifndef __ARCH_WANT_INTERRUPTS_ON_CTXSW local_irq_enable(); @@ -2686,8 +2698,8 @@ void sched_fork(struct task_struct *p, int clone_flags) if (likely(sched_info_on())) memset(&p->sched_info, 0, sizeof(p->sched_info)); #endif -#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW) - p->oncpu = 0; +#if defined(CONFIG_SMP) + p->on_cpu = 0; #endif #ifdef CONFIG_PREEMPT /* Want to start with kernel preemption disabled. */ @@ -5776,8 +5788,8 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu) rcu_read_unlock(); rq->curr = rq->idle = idle; -#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW) - idle->oncpu = 1; +#if defined(CONFIG_SMP) + idle->on_cpu = 1; #endif raw_spin_unlock_irqrestore(&rq->lock, flags); From c6eb3dda25892f1f974f5420f63e6721aab02f6f Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 5 Apr 2011 17:23:41 +0200 Subject: [PATCH 04/22] mutex: Use p->on_cpu for the adaptive spin Since we now have p->on_cpu unconditionally available, use it to re-implement mutex_spin_on_owner. Requested-by: Thomas Gleixner Reviewed-by: Frank Rowand Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Signed-off-by: Ingo Molnar Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20110405152728.826338173@chello.nl --- include/linux/mutex.h | 2 +- include/linux/sched.h | 2 +- kernel/mutex-debug.c | 2 +- kernel/mutex-debug.h | 2 +- kernel/mutex.c | 2 +- kernel/mutex.h | 2 +- kernel/sched.c | 85 +++++++++++++++++-------------------------- 7 files changed, 40 insertions(+), 57 deletions(-) diff --git a/include/linux/mutex.h b/include/linux/mutex.h index 94b48bd40dd7..c75471db576e 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -51,7 +51,7 @@ struct mutex { spinlock_t wait_lock; struct list_head wait_list; #if defined(CONFIG_DEBUG_MUTEXES) || defined(CONFIG_SMP) - struct thread_info *owner; + struct task_struct *owner; #endif #ifdef CONFIG_DEBUG_MUTEXES const char *name; diff --git a/include/linux/sched.h b/include/linux/sched.h index 3435837e89ff..173850479e2c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -360,7 +360,7 @@ extern signed long schedule_timeout_interruptible(signed long timeout); extern signed long schedule_timeout_killable(signed long timeout); extern signed long schedule_timeout_uninterruptible(signed long timeout); asmlinkage void schedule(void); -extern int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner); +extern int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner); struct nsproxy; struct user_namespace; diff --git a/kernel/mutex-debug.c b/kernel/mutex-debug.c index ec815a960b5d..73da83aff418 100644 --- a/kernel/mutex-debug.c +++ b/kernel/mutex-debug.c @@ -75,7 +75,7 @@ void debug_mutex_unlock(struct mutex *lock) return; DEBUG_LOCKS_WARN_ON(lock->magic != lock); - DEBUG_LOCKS_WARN_ON(lock->owner != current_thread_info()); + DEBUG_LOCKS_WARN_ON(lock->owner != current); DEBUG_LOCKS_WARN_ON(!lock->wait_list.prev && !lock->wait_list.next); mutex_clear_owner(lock); } diff --git a/kernel/mutex-debug.h b/kernel/mutex-debug.h index 57d527a16f9d..0799fd3e4cfa 100644 --- a/kernel/mutex-debug.h +++ b/kernel/mutex-debug.h @@ -29,7 +29,7 @@ extern void debug_mutex_init(struct mutex *lock, const char *name, static inline void mutex_set_owner(struct mutex *lock) { - lock->owner = current_thread_info(); + lock->owner = current; } static inline void mutex_clear_owner(struct mutex *lock) diff --git a/kernel/mutex.c b/kernel/mutex.c index c4195fa98900..fe4706cb0c5b 100644 --- a/kernel/mutex.c +++ b/kernel/mutex.c @@ -160,7 +160,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, */ for (;;) { - struct thread_info *owner; + struct task_struct *owner; /* * If we own the BKL, then don't spin. The owner of diff --git a/kernel/mutex.h b/kernel/mutex.h index 67578ca48f94..4115fbf83b12 100644 --- a/kernel/mutex.h +++ b/kernel/mutex.h @@ -19,7 +19,7 @@ #ifdef CONFIG_SMP static inline void mutex_set_owner(struct mutex *lock) { - lock->owner = current_thread_info(); + lock->owner = current; } static inline void mutex_clear_owner(struct mutex *lock) diff --git a/kernel/sched.c b/kernel/sched.c index cd2593e1a3ec..55cc50323ce1 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -4173,70 +4173,53 @@ need_resched: EXPORT_SYMBOL(schedule); #ifdef CONFIG_MUTEX_SPIN_ON_OWNER + +static inline bool owner_running(struct mutex *lock, struct task_struct *owner) +{ + bool ret = false; + + rcu_read_lock(); + if (lock->owner != owner) + goto fail; + + /* + * Ensure we emit the owner->on_cpu, dereference _after_ checking + * lock->owner still matches owner, if that fails, owner might + * point to free()d memory, if it still matches, the rcu_read_lock() + * ensures the memory stays valid. + */ + barrier(); + + ret = owner->on_cpu; +fail: + rcu_read_unlock(); + + return ret; +} + /* * Look out! "owner" is an entirely speculative pointer * access and not reliable. */ -int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner) +int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner) { - unsigned int cpu; - struct rq *rq; - if (!sched_feat(OWNER_SPIN)) return 0; -#ifdef CONFIG_DEBUG_PAGEALLOC - /* - * Need to access the cpu field knowing that - * DEBUG_PAGEALLOC could have unmapped it if - * the mutex owner just released it and exited. - */ - if (probe_kernel_address(&owner->cpu, cpu)) - return 0; -#else - cpu = owner->cpu; -#endif - - /* - * Even if the access succeeded (likely case), - * the cpu field may no longer be valid. - */ - if (cpu >= nr_cpumask_bits) - return 0; - - /* - * We need to validate that we can do a - * get_cpu() and that we have the percpu area. - */ - if (!cpu_online(cpu)) - return 0; - - rq = cpu_rq(cpu); - - for (;;) { - /* - * Owner changed, break to re-assess state. - */ - if (lock->owner != owner) { - /* - * If the lock has switched to a different owner, - * we likely have heavy contention. Return 0 to quit - * optimistic spinning and not contend further: - */ - if (lock->owner) - return 0; - break; - } - - /* - * Is that owner really running on that cpu? - */ - if (task_thread_info(rq->curr) != owner || need_resched()) + while (owner_running(lock, owner)) { + if (need_resched()) return 0; arch_mutex_cpu_relax(); } + /* + * If the owner changed to another task there is likely + * heavy contention, stop spinning. + */ + if (lock->owner) + return 0; + return 1; } #endif From c2f7115e2e52a6c187b8c1f54f0e4970bb677be0 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 13 Apr 2011 13:28:56 +0200 Subject: [PATCH 05/22] sched: Move wq_worker_waking to the correct site wq_worker_waking_up() needs to match wq_worker_sleeping(), since the latter is only called on deactivate, move the former near activate. Signed-off-by: Peter Zijlstra Cc: Tejun Heo Link: http://lkml.kernel.org/n/top-t3m7n70n9frmv4pv2n5fwmov@git.kernel.org Signed-off-by: Ingo Molnar --- kernel/sched.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/kernel/sched.c b/kernel/sched.c index 55cc50323ce1..81ab58efd788 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2421,6 +2421,10 @@ static inline void ttwu_activate(struct task_struct *p, struct rq *rq, schedstat_inc(p, se.statistics.nr_wakeups_remote); activate_task(rq, p, en_flags); + + /* if a worker is waking up, notify workqueue */ + if (p->flags & PF_WQ_WORKER) + wq_worker_waking_up(p, cpu_of(rq)); } static inline void ttwu_post_activation(struct task_struct *p, struct rq *rq, @@ -2445,9 +2449,6 @@ static inline void ttwu_post_activation(struct task_struct *p, struct rq *rq, rq->idle_stamp = 0; } #endif - /* if a worker is waking up, notify workqueue */ - if ((p->flags & PF_WQ_WORKER) && success) - wq_worker_waking_up(p, cpu_of(rq)); } /** From 893633817f5b58f5227365d74344e0170a718213 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 5 Apr 2011 17:23:42 +0200 Subject: [PATCH 06/22] sched: Change the ttwu() success details try_to_wake_up() would only return a success when it would have to place a task on a rq, change that to every time we change p->state to TASK_RUNNING, because that's the real measure of wakeups. This results in that success is always true for the tracepoints. Reviewed-by: Frank Rowand Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Signed-off-by: Ingo Molnar Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20110405152728.866866929@chello.nl --- kernel/sched.c | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-) diff --git a/kernel/sched.c b/kernel/sched.c index 81ab58efd788..3919aa419356 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2427,10 +2427,10 @@ static inline void ttwu_activate(struct task_struct *p, struct rq *rq, wq_worker_waking_up(p, cpu_of(rq)); } -static inline void ttwu_post_activation(struct task_struct *p, struct rq *rq, - int wake_flags, bool success) +static void +ttwu_post_activation(struct task_struct *p, struct rq *rq, int wake_flags) { - trace_sched_wakeup(p, success); + trace_sched_wakeup(p, true); check_preempt_curr(rq, p, wake_flags); p->state = TASK_RUNNING; @@ -2546,9 +2546,9 @@ out_activate: #endif /* CONFIG_SMP */ ttwu_activate(p, rq, wake_flags & WF_SYNC, orig_cpu != cpu, cpu == this_cpu, en_flags); - success = 1; out_running: - ttwu_post_activation(p, rq, wake_flags, success); + ttwu_post_activation(p, rq, wake_flags); + success = 1; out: task_rq_unlock(rq, &flags); put_cpu(); @@ -2567,7 +2567,6 @@ out: static void try_to_wake_up_local(struct task_struct *p) { struct rq *rq = task_rq(p); - bool success = false; BUG_ON(rq != this_rq()); BUG_ON(p == current); @@ -2582,9 +2581,8 @@ static void try_to_wake_up_local(struct task_struct *p) schedstat_inc(rq, ttwu_local); } ttwu_activate(p, rq, false, false, true, ENQUEUE_WAKEUP); - success = true; } - ttwu_post_activation(p, rq, 0, success); + ttwu_post_activation(p, rq, 0); } /** @@ -2747,7 +2745,7 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags) rq = task_rq_lock(p, &flags); activate_task(rq, p, 0); - trace_sched_wakeup_new(p, 1); + trace_sched_wakeup_new(p, true); check_preempt_curr(rq, p, WF_FORK); #ifdef CONFIG_SMP if (p->sched_class->task_woken) From d7c01d27ab767a30d672d1fd657aa8336ebdcbca Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 5 Apr 2011 17:23:43 +0200 Subject: [PATCH 07/22] sched: Clean up ttwu() stats Collect all ttwu() stat code into a single function and ensure its always called for an actual wakeup (changing p->state to TASK_RUNNING). Reviewed-by: Frank Rowand Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Signed-off-by: Ingo Molnar Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20110405152728.908177058@chello.nl --- kernel/sched.c | 81 +++++++++++++++++++++++++++----------------------- 1 file changed, 43 insertions(+), 38 deletions(-) diff --git a/kernel/sched.c b/kernel/sched.c index 3919aa419356..4481638f9178 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2406,20 +2406,43 @@ static void update_avg(u64 *avg, u64 sample) } #endif -static inline void ttwu_activate(struct task_struct *p, struct rq *rq, - bool is_sync, bool is_migrate, bool is_local, - unsigned long en_flags) +static void +ttwu_stat(struct rq *rq, struct task_struct *p, int cpu, int wake_flags) { - schedstat_inc(p, se.statistics.nr_wakeups); - if (is_sync) - schedstat_inc(p, se.statistics.nr_wakeups_sync); - if (is_migrate) - schedstat_inc(p, se.statistics.nr_wakeups_migrate); - if (is_local) - schedstat_inc(p, se.statistics.nr_wakeups_local); - else - schedstat_inc(p, se.statistics.nr_wakeups_remote); +#ifdef CONFIG_SCHEDSTATS +#ifdef CONFIG_SMP + int this_cpu = smp_processor_id(); + if (cpu == this_cpu) { + schedstat_inc(rq, ttwu_local); + schedstat_inc(p, se.statistics.nr_wakeups_local); + } else { + struct sched_domain *sd; + + schedstat_inc(p, se.statistics.nr_wakeups_remote); + for_each_domain(this_cpu, sd) { + if (cpumask_test_cpu(cpu, sched_domain_span(sd))) { + schedstat_inc(sd, ttwu_wake_remote); + break; + } + } + } +#endif /* CONFIG_SMP */ + + schedstat_inc(rq, ttwu_count); + schedstat_inc(p, se.statistics.nr_wakeups); + + if (wake_flags & WF_SYNC) + schedstat_inc(p, se.statistics.nr_wakeups_sync); + + if (cpu != task_cpu(p)) + schedstat_inc(p, se.statistics.nr_wakeups_migrate); + +#endif /* CONFIG_SCHEDSTATS */ +} + +static void ttwu_activate(struct rq *rq, struct task_struct *p, int en_flags) +{ activate_task(rq, p, en_flags); /* if a worker is waking up, notify workqueue */ @@ -2481,12 +2504,12 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, if (!(p->state & state)) goto out; + cpu = task_cpu(p); + if (p->se.on_rq) goto out_running; - cpu = task_cpu(p); orig_cpu = cpu; - #ifdef CONFIG_SMP if (unlikely(task_running(rq, p))) goto out_activate; @@ -2527,27 +2550,12 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, WARN_ON(task_cpu(p) != cpu); WARN_ON(p->state != TASK_WAKING); -#ifdef CONFIG_SCHEDSTATS - schedstat_inc(rq, ttwu_count); - if (cpu == this_cpu) - schedstat_inc(rq, ttwu_local); - else { - struct sched_domain *sd; - for_each_domain(this_cpu, sd) { - if (cpumask_test_cpu(cpu, sched_domain_span(sd))) { - schedstat_inc(sd, ttwu_wake_remote); - break; - } - } - } -#endif /* CONFIG_SCHEDSTATS */ - out_activate: #endif /* CONFIG_SMP */ - ttwu_activate(p, rq, wake_flags & WF_SYNC, orig_cpu != cpu, - cpu == this_cpu, en_flags); + ttwu_activate(rq, p, en_flags); out_running: ttwu_post_activation(p, rq, wake_flags); + ttwu_stat(rq, p, cpu, wake_flags); success = 1; out: task_rq_unlock(rq, &flags); @@ -2575,14 +2583,11 @@ static void try_to_wake_up_local(struct task_struct *p) if (!(p->state & TASK_NORMAL)) return; - if (!p->se.on_rq) { - if (likely(!task_running(rq, p))) { - schedstat_inc(rq, ttwu_count); - schedstat_inc(rq, ttwu_local); - } - ttwu_activate(p, rq, false, false, true, ENQUEUE_WAKEUP); - } + if (!p->se.on_rq) + ttwu_activate(rq, p, ENQUEUE_WAKEUP); + ttwu_post_activation(p, rq, 0); + ttwu_stat(rq, p, smp_processor_id(), 0); } /** From fd2f4419b4cbe8fe90796df9617c355762afd6a4 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 5 Apr 2011 17:23:44 +0200 Subject: [PATCH 08/22] sched: Provide p->on_rq Provide a generic p->on_rq because the p->se.on_rq semantics are unfavourable for lockless wakeups but needed for sched_fair. In particular, p->on_rq is only cleared when we actually dequeue the task in schedule() and not on any random dequeue as done by things like __migrate_task() and __sched_setscheduler(). This also allows us to remove p->se usage from !sched_fair code. Reviewed-by: Frank Rowand Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Signed-off-by: Ingo Molnar Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20110405152728.949545047@chello.nl --- include/linux/sched.h | 1 + kernel/sched.c | 38 ++++++++++++++++++++------------------ kernel/sched_debug.c | 2 +- kernel/sched_rt.c | 16 ++++++++-------- kernel/sched_stoptask.c | 2 +- 5 files changed, 31 insertions(+), 28 deletions(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index 173850479e2c..b33a700652dc 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1202,6 +1202,7 @@ struct task_struct { #ifdef CONFIG_SMP int on_cpu; #endif + int on_rq; int prio, static_prio, normal_prio; unsigned int rt_priority; diff --git a/kernel/sched.c b/kernel/sched.c index 4481638f9178..dece28e505c9 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -1785,7 +1785,6 @@ static void enqueue_task(struct rq *rq, struct task_struct *p, int flags) update_rq_clock(rq); sched_info_queued(p); p->sched_class->enqueue_task(rq, p, flags); - p->se.on_rq = 1; } static void dequeue_task(struct rq *rq, struct task_struct *p, int flags) @@ -1793,7 +1792,6 @@ static void dequeue_task(struct rq *rq, struct task_struct *p, int flags) update_rq_clock(rq); sched_info_dequeued(p); p->sched_class->dequeue_task(rq, p, flags); - p->se.on_rq = 0; } /* @@ -2128,7 +2126,7 @@ static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags) * A queue event has occurred, and we're going to schedule. In * this case, we can save a useless back to back clock update. */ - if (rq->curr->se.on_rq && test_tsk_need_resched(rq->curr)) + if (rq->curr->on_rq && test_tsk_need_resched(rq->curr)) rq->skip_clock_update = 1; } @@ -2203,7 +2201,7 @@ static bool migrate_task(struct task_struct *p, struct rq *rq) * If the task is not on a runqueue (and not running), then * the next wake-up will properly place the task. */ - return p->se.on_rq || task_running(rq, p); + return p->on_rq || task_running(rq, p); } /* @@ -2263,7 +2261,7 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state) rq = task_rq_lock(p, &flags); trace_sched_wait_task(p); running = task_running(rq, p); - on_rq = p->se.on_rq; + on_rq = p->on_rq; ncsw = 0; if (!match_state || p->state == match_state) ncsw = p->nvcsw | LONG_MIN; /* sets MSB */ @@ -2444,6 +2442,7 @@ ttwu_stat(struct rq *rq, struct task_struct *p, int cpu, int wake_flags) static void ttwu_activate(struct rq *rq, struct task_struct *p, int en_flags) { activate_task(rq, p, en_flags); + p->on_rq = 1; /* if a worker is waking up, notify workqueue */ if (p->flags & PF_WQ_WORKER) @@ -2506,7 +2505,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, cpu = task_cpu(p); - if (p->se.on_rq) + if (p->on_rq) goto out_running; orig_cpu = cpu; @@ -2583,7 +2582,7 @@ static void try_to_wake_up_local(struct task_struct *p) if (!(p->state & TASK_NORMAL)) return; - if (!p->se.on_rq) + if (!p->on_rq) ttwu_activate(rq, p, ENQUEUE_WAKEUP); ttwu_post_activation(p, rq, 0); @@ -2620,19 +2619,21 @@ int wake_up_state(struct task_struct *p, unsigned int state) */ static void __sched_fork(struct task_struct *p) { + p->on_rq = 0; + + p->se.on_rq = 0; p->se.exec_start = 0; p->se.sum_exec_runtime = 0; p->se.prev_sum_exec_runtime = 0; p->se.nr_migrations = 0; p->se.vruntime = 0; + INIT_LIST_HEAD(&p->se.group_node); #ifdef CONFIG_SCHEDSTATS memset(&p->se.statistics, 0, sizeof(p->se.statistics)); #endif INIT_LIST_HEAD(&p->rt.run_list); - p->se.on_rq = 0; - INIT_LIST_HEAD(&p->se.group_node); #ifdef CONFIG_PREEMPT_NOTIFIERS INIT_HLIST_HEAD(&p->preempt_notifiers); @@ -2750,6 +2751,7 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags) rq = task_rq_lock(p, &flags); activate_task(rq, p, 0); + p->on_rq = 1; trace_sched_wakeup_new(p, true); check_preempt_curr(rq, p, WF_FORK); #ifdef CONFIG_SMP @@ -4051,7 +4053,7 @@ static inline void schedule_debug(struct task_struct *prev) static void put_prev_task(struct rq *rq, struct task_struct *prev) { - if (prev->se.on_rq) + if (prev->on_rq) update_rq_clock(rq); prev->sched_class->put_prev_task(rq, prev); } @@ -4126,7 +4128,9 @@ need_resched: if (to_wakeup) try_to_wake_up_local(to_wakeup); } + deactivate_task(rq, prev, DEQUEUE_SLEEP); + prev->on_rq = 0; /* * If we are going to sleep and we have plugged IO queued, make @@ -4695,7 +4699,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio) trace_sched_pi_setprio(p, prio); oldprio = p->prio; prev_class = p->sched_class; - on_rq = p->se.on_rq; + on_rq = p->on_rq; running = task_current(rq, p); if (on_rq) dequeue_task(rq, p, 0); @@ -4743,7 +4747,7 @@ void set_user_nice(struct task_struct *p, long nice) p->static_prio = NICE_TO_PRIO(nice); goto out_unlock; } - on_rq = p->se.on_rq; + on_rq = p->on_rq; if (on_rq) dequeue_task(rq, p, 0); @@ -4877,8 +4881,6 @@ static struct task_struct *find_process_by_pid(pid_t pid) static void __setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio) { - BUG_ON(p->se.on_rq); - p->policy = policy; p->rt_priority = prio; p->normal_prio = normal_prio(p); @@ -5044,7 +5046,7 @@ recheck: raw_spin_unlock_irqrestore(&p->pi_lock, flags); goto recheck; } - on_rq = p->se.on_rq; + on_rq = p->on_rq; running = task_current(rq, p); if (on_rq) deactivate_task(rq, p, 0); @@ -5965,7 +5967,7 @@ static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu) * If we're not on a rq, the next wake-up will ensure we're * placed properly. */ - if (p->se.on_rq) { + if (p->on_rq) { deactivate_task(rq_src, p, 0); set_task_cpu(p, dest_cpu); activate_task(rq_dest, p, 0); @@ -8339,7 +8341,7 @@ static void normalize_task(struct rq *rq, struct task_struct *p) int old_prio = p->prio; int on_rq; - on_rq = p->se.on_rq; + on_rq = p->on_rq; if (on_rq) deactivate_task(rq, p, 0); __setscheduler(rq, p, SCHED_NORMAL, 0); @@ -8682,7 +8684,7 @@ void sched_move_task(struct task_struct *tsk) rq = task_rq_lock(tsk, &flags); running = task_current(rq, tsk); - on_rq = tsk->se.on_rq; + on_rq = tsk->on_rq; if (on_rq) dequeue_task(rq, tsk, 0); diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c index 7bacd83a4158..3669bec6e130 100644 --- a/kernel/sched_debug.c +++ b/kernel/sched_debug.c @@ -152,7 +152,7 @@ static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu) read_lock_irqsave(&tasklist_lock, flags); do_each_thread(g, p) { - if (!p->se.on_rq || task_cpu(p) != rq_cpu) + if (!p->on_rq || task_cpu(p) != rq_cpu) continue; print_task(m, rq, p); diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index e7cebdc65f82..9ca4f5f879c4 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -1136,7 +1136,7 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p) * The previous task needs to be made eligible for pushing * if it is still active */ - if (p->se.on_rq && p->rt.nr_cpus_allowed > 1) + if (on_rt_rq(&p->rt) && p->rt.nr_cpus_allowed > 1) enqueue_pushable_task(rq, p); } @@ -1287,7 +1287,7 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq) !cpumask_test_cpu(lowest_rq->cpu, &task->cpus_allowed) || task_running(rq, task) || - !task->se.on_rq)) { + !task->on_rq)) { raw_spin_unlock(&lowest_rq->lock); lowest_rq = NULL; @@ -1321,7 +1321,7 @@ static struct task_struct *pick_next_pushable_task(struct rq *rq) BUG_ON(task_current(rq, p)); BUG_ON(p->rt.nr_cpus_allowed <= 1); - BUG_ON(!p->se.on_rq); + BUG_ON(!p->on_rq); BUG_ON(!rt_task(p)); return p; @@ -1467,7 +1467,7 @@ static int pull_rt_task(struct rq *this_rq) */ if (p && (p->prio < this_rq->rt.highest_prio.curr)) { WARN_ON(p == src_rq->curr); - WARN_ON(!p->se.on_rq); + WARN_ON(!p->on_rq); /* * There's a chance that p is higher in priority @@ -1538,7 +1538,7 @@ static void set_cpus_allowed_rt(struct task_struct *p, * Update the migration status of the RQ if we have an RT task * which is running AND changing its weight value. */ - if (p->se.on_rq && (weight != p->rt.nr_cpus_allowed)) { + if (p->on_rq && (weight != p->rt.nr_cpus_allowed)) { struct rq *rq = task_rq(p); if (!task_current(rq, p)) { @@ -1608,7 +1608,7 @@ static void switched_from_rt(struct rq *rq, struct task_struct *p) * we may need to handle the pulling of RT tasks * now. */ - if (p->se.on_rq && !rq->rt.rt_nr_running) + if (p->on_rq && !rq->rt.rt_nr_running) pull_rt_task(rq); } @@ -1638,7 +1638,7 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p) * If that current running task is also an RT task * then see if we can move to another run queue. */ - if (p->se.on_rq && rq->curr != p) { + if (p->on_rq && rq->curr != p) { #ifdef CONFIG_SMP if (rq->rt.overloaded && push_rt_task(rq) && /* Don't resched if we changed runqueues */ @@ -1657,7 +1657,7 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p) static void prio_changed_rt(struct rq *rq, struct task_struct *p, int oldprio) { - if (!p->se.on_rq) + if (!p->on_rq) return; if (rq->curr == p) { diff --git a/kernel/sched_stoptask.c b/kernel/sched_stoptask.c index 1ba2bd40fdac..f607de42e6fc 100644 --- a/kernel/sched_stoptask.c +++ b/kernel/sched_stoptask.c @@ -26,7 +26,7 @@ static struct task_struct *pick_next_task_stop(struct rq *rq) { struct task_struct *stop = rq->stop; - if (stop && stop->se.on_rq) + if (stop && stop->on_rq) return stop; return NULL; From 013fdb8086acaae5f8eb96f9ad48fcd98882ac46 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 5 Apr 2011 17:23:45 +0200 Subject: [PATCH 09/22] sched: Serialize p->cpus_allowed and ttwu() using p->pi_lock Currently p->pi_lock already serializes p->sched_class, also put p->cpus_allowed and try_to_wake_up() under it, this prepares the way to do the first part of ttwu() without holding rq->lock. By having p->sched_class and p->cpus_allowed serialized by p->pi_lock, we prepare the way to call select_task_rq() without holding rq->lock. Reviewed-by: Frank Rowand Signed-off-by: Peter Zijlstra Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Link: http://lkml.kernel.org/r/20110405152728.990364093@chello.nl Signed-off-by: Ingo Molnar --- kernel/sched.c | 37 ++++++++++++++++--------------------- 1 file changed, 16 insertions(+), 21 deletions(-) diff --git a/kernel/sched.c b/kernel/sched.c index dece28e505c9..d398f2f0a3c9 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2340,7 +2340,7 @@ EXPORT_SYMBOL_GPL(kick_process); #ifdef CONFIG_SMP /* - * ->cpus_allowed is protected by either TASK_WAKING or rq->lock held. + * ->cpus_allowed is protected by both rq->lock and p->pi_lock */ static int select_fallback_rq(int cpu, struct task_struct *p) { @@ -2373,7 +2373,7 @@ static int select_fallback_rq(int cpu, struct task_struct *p) } /* - * The caller (fork, wakeup) owns TASK_WAKING, ->cpus_allowed is stable. + * The caller (fork, wakeup) owns p->pi_lock, ->cpus_allowed is stable. */ static inline int select_task_rq(struct rq *rq, struct task_struct *p, int sd_flags, int wake_flags) @@ -2499,7 +2499,8 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, this_cpu = get_cpu(); smp_wmb(); - rq = task_rq_lock(p, &flags); + raw_spin_lock_irqsave(&p->pi_lock, flags); + rq = __task_rq_lock(p); if (!(p->state & state)) goto out; @@ -2557,7 +2558,8 @@ out_running: ttwu_stat(rq, p, cpu, wake_flags); success = 1; out: - task_rq_unlock(rq, &flags); + __task_rq_unlock(rq); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); put_cpu(); return success; @@ -4694,6 +4696,8 @@ void rt_mutex_setprio(struct task_struct *p, int prio) BUG_ON(prio < 0 || prio > MAX_PRIO); + lockdep_assert_held(&p->pi_lock); + rq = task_rq_lock(p, &flags); trace_sched_pi_setprio(p, prio); @@ -5317,7 +5321,6 @@ long sched_getaffinity(pid_t pid, struct cpumask *mask) { struct task_struct *p; unsigned long flags; - struct rq *rq; int retval; get_online_cpus(); @@ -5332,9 +5335,9 @@ long sched_getaffinity(pid_t pid, struct cpumask *mask) if (retval) goto out_unlock; - rq = task_rq_lock(p, &flags); + raw_spin_lock_irqsave(&p->pi_lock, flags); cpumask_and(mask, &p->cpus_allowed, cpu_online_mask); - task_rq_unlock(rq, &flags); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); out_unlock: rcu_read_unlock(); @@ -5882,18 +5885,8 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) unsigned int dest_cpu; int ret = 0; - /* - * Serialize against TASK_WAKING so that ttwu() and wunt() can - * drop the rq->lock and still rely on ->cpus_allowed. - */ -again: - while (task_is_waking(p)) - cpu_relax(); - rq = task_rq_lock(p, &flags); - if (task_is_waking(p)) { - task_rq_unlock(rq, &flags); - goto again; - } + raw_spin_lock_irqsave(&p->pi_lock, flags); + rq = __task_rq_lock(p); if (!cpumask_intersects(new_mask, cpu_active_mask)) { ret = -EINVAL; @@ -5921,13 +5914,15 @@ again: if (migrate_task(p, rq)) { struct migration_arg arg = { p, dest_cpu }; /* Need help from migration thread: drop lock and wait. */ - task_rq_unlock(rq, &flags); + __task_rq_unlock(rq); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg); tlb_migrate_finish(p->mm); return 0; } out: - task_rq_unlock(rq, &flags); + __task_rq_unlock(rq); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); return ret; } From 7608dec2ce2004c234339bef8c8074e5e601d0e9 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 5 Apr 2011 17:23:46 +0200 Subject: [PATCH 10/22] sched: Drop the rq argument to sched_class::select_task_rq() In preparation of calling select_task_rq() without rq->lock held, drop the dependency on the rq argument. Reviewed-by: Frank Rowand Signed-off-by: Peter Zijlstra Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Link: http://lkml.kernel.org/r/20110405152729.031077745@chello.nl Signed-off-by: Ingo Molnar --- include/linux/sched.h | 3 +-- kernel/sched.c | 20 +++++++++++--------- kernel/sched_fair.c | 2 +- kernel/sched_idletask.c | 2 +- kernel/sched_rt.c | 42 +++++++++++++++++++++++++++-------------- kernel/sched_stoptask.c | 3 +-- 6 files changed, 43 insertions(+), 29 deletions(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index b33a700652dc..ff4e2f9c24a7 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1067,8 +1067,7 @@ struct sched_class { void (*put_prev_task) (struct rq *rq, struct task_struct *p); #ifdef CONFIG_SMP - int (*select_task_rq)(struct rq *rq, struct task_struct *p, - int sd_flag, int flags); + int (*select_task_rq)(struct task_struct *p, int sd_flag, int flags); void (*pre_schedule) (struct rq *this_rq, struct task_struct *task); void (*post_schedule) (struct rq *this_rq); diff --git a/kernel/sched.c b/kernel/sched.c index d398f2f0a3c9..d4b815d345b3 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2195,13 +2195,15 @@ static int migration_cpu_stop(void *data); * The task's runqueue lock must be held. * Returns true if you have to wait for migration thread. */ -static bool migrate_task(struct task_struct *p, struct rq *rq) +static bool need_migrate_task(struct task_struct *p) { /* * If the task is not on a runqueue (and not running), then * the next wake-up will properly place the task. */ - return p->on_rq || task_running(rq, p); + bool running = p->on_rq || p->on_cpu; + smp_rmb(); /* finish_lock_switch() */ + return running; } /* @@ -2376,9 +2378,9 @@ static int select_fallback_rq(int cpu, struct task_struct *p) * The caller (fork, wakeup) owns p->pi_lock, ->cpus_allowed is stable. */ static inline -int select_task_rq(struct rq *rq, struct task_struct *p, int sd_flags, int wake_flags) +int select_task_rq(struct task_struct *p, int sd_flags, int wake_flags) { - int cpu = p->sched_class->select_task_rq(rq, p, sd_flags, wake_flags); + int cpu = p->sched_class->select_task_rq(p, sd_flags, wake_flags); /* * In order not to call set_task_cpu() on a blocking task we need @@ -2533,7 +2535,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, en_flags |= ENQUEUE_WAKING; } - cpu = select_task_rq(rq, p, SD_BALANCE_WAKE, wake_flags); + cpu = select_task_rq(p, SD_BALANCE_WAKE, wake_flags); if (cpu != orig_cpu) set_task_cpu(p, cpu); __task_rq_unlock(rq); @@ -2744,7 +2746,7 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags) * We set TASK_WAKING so that select_task_rq() can drop rq->lock * without people poking at ->cpus_allowed. */ - cpu = select_task_rq(rq, p, SD_BALANCE_FORK, 0); + cpu = select_task_rq(p, SD_BALANCE_FORK, 0); set_task_cpu(p, cpu); p->state = TASK_RUNNING; @@ -3474,7 +3476,7 @@ void sched_exec(void) int dest_cpu; rq = task_rq_lock(p, &flags); - dest_cpu = p->sched_class->select_task_rq(rq, p, SD_BALANCE_EXEC, 0); + dest_cpu = p->sched_class->select_task_rq(p, SD_BALANCE_EXEC, 0); if (dest_cpu == smp_processor_id()) goto unlock; @@ -3482,7 +3484,7 @@ void sched_exec(void) * select_task_rq() can race against ->cpus_allowed */ if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed) && - likely(cpu_active(dest_cpu)) && migrate_task(p, rq)) { + likely(cpu_active(dest_cpu)) && need_migrate_task(p)) { struct migration_arg arg = { p, dest_cpu }; task_rq_unlock(rq, &flags); @@ -5911,7 +5913,7 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) goto out; dest_cpu = cpumask_any_and(cpu_active_mask, new_mask); - if (migrate_task(p, rq)) { + if (need_migrate_task(p)) { struct migration_arg arg = { p, dest_cpu }; /* Need help from migration thread: drop lock and wait. */ __task_rq_unlock(rq); diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 4ee50f0af8d1..96b2c95ac356 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -1657,7 +1657,7 @@ static int select_idle_sibling(struct task_struct *p, int target) * preempt must be disabled. */ static int -select_task_rq_fair(struct rq *rq, struct task_struct *p, int sd_flag, int wake_flags) +select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags) { struct sched_domain *tmp, *affine_sd = NULL, *sd = NULL; int cpu = smp_processor_id(); diff --git a/kernel/sched_idletask.c b/kernel/sched_idletask.c index a776a6396427..0a51882534ea 100644 --- a/kernel/sched_idletask.c +++ b/kernel/sched_idletask.c @@ -7,7 +7,7 @@ #ifdef CONFIG_SMP static int -select_task_rq_idle(struct rq *rq, struct task_struct *p, int sd_flag, int flags) +select_task_rq_idle(struct task_struct *p, int sd_flag, int flags) { return task_cpu(p); /* IDLE tasks as never migrated */ } diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index 9ca4f5f879c4..19ecb3127379 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -977,13 +977,23 @@ static void yield_task_rt(struct rq *rq) static int find_lowest_rq(struct task_struct *task); static int -select_task_rq_rt(struct rq *rq, struct task_struct *p, int sd_flag, int flags) +select_task_rq_rt(struct task_struct *p, int sd_flag, int flags) { + struct task_struct *curr; + struct rq *rq; + int cpu; + if (sd_flag != SD_BALANCE_WAKE) return smp_processor_id(); + cpu = task_cpu(p); + rq = cpu_rq(cpu); + + rcu_read_lock(); + curr = ACCESS_ONCE(rq->curr); /* unlocked access */ + /* - * If the current task is an RT task, then + * If the current task on @p's runqueue is an RT task, then * try to see if we can wake this RT task up on another * runqueue. Otherwise simply start this RT task * on its current runqueue. @@ -997,21 +1007,25 @@ select_task_rq_rt(struct rq *rq, struct task_struct *p, int sd_flag, int flags) * lock? * * For equal prio tasks, we just let the scheduler sort it out. - */ - if (unlikely(rt_task(rq->curr)) && - (rq->curr->rt.nr_cpus_allowed < 2 || - rq->curr->prio < p->prio) && - (p->rt.nr_cpus_allowed > 1)) { - int cpu = find_lowest_rq(p); - - return (cpu == -1) ? task_cpu(p) : cpu; - } - - /* + * * Otherwise, just let it ride on the affined RQ and the * post-schedule router will push the preempted task away + * + * This test is optimistic, if we get it wrong the load-balancer + * will have to sort it out. */ - return task_cpu(p); + if (curr && unlikely(rt_task(curr)) && + (curr->rt.nr_cpus_allowed < 2 || + curr->prio < p->prio) && + (p->rt.nr_cpus_allowed > 1)) { + int target = find_lowest_rq(p); + + if (target != -1) + cpu = target; + } + rcu_read_unlock(); + + return cpu; } static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p) diff --git a/kernel/sched_stoptask.c b/kernel/sched_stoptask.c index f607de42e6fc..6f437632afab 100644 --- a/kernel/sched_stoptask.c +++ b/kernel/sched_stoptask.c @@ -9,8 +9,7 @@ #ifdef CONFIG_SMP static int -select_task_rq_stop(struct rq *rq, struct task_struct *p, - int sd_flag, int flags) +select_task_rq_stop(struct task_struct *p, int sd_flag, int flags) { return task_cpu(p); /* stop tasks as never migrate */ } From 74f8e4b2335de45485b8d5b31a504747f13c8070 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 5 Apr 2011 17:23:47 +0200 Subject: [PATCH 11/22] sched: Remove rq argument to sched_class::task_waking() In preparation of calling this without rq->lock held, remove the dependency on the rq argument. Reviewed-by: Frank Rowand Signed-off-by: Peter Zijlstra Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Link: http://lkml.kernel.org/r/20110405152729.071474242@chello.nl Signed-off-by: Ingo Molnar --- include/linux/sched.h | 10 +++++++--- kernel/sched.c | 2 +- kernel/sched_fair.c | 4 +++- 3 files changed, 11 insertions(+), 5 deletions(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index ff4e2f9c24a7..7f5732f8c618 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1048,8 +1048,12 @@ struct sched_domain; #define WF_FORK 0x02 /* child wakeup after fork */ #define ENQUEUE_WAKEUP 1 -#define ENQUEUE_WAKING 2 -#define ENQUEUE_HEAD 4 +#define ENQUEUE_HEAD 2 +#ifdef CONFIG_SMP +#define ENQUEUE_WAKING 4 /* sched_class::task_waking was called */ +#else +#define ENQUEUE_WAKING 0 +#endif #define DEQUEUE_SLEEP 1 @@ -1071,7 +1075,7 @@ struct sched_class { void (*pre_schedule) (struct rq *this_rq, struct task_struct *task); void (*post_schedule) (struct rq *this_rq); - void (*task_waking) (struct rq *this_rq, struct task_struct *task); + void (*task_waking) (struct task_struct *task); void (*task_woken) (struct rq *this_rq, struct task_struct *task); void (*set_cpus_allowed)(struct task_struct *p, diff --git a/kernel/sched.c b/kernel/sched.c index d4b815d345b3..46f42cac4eb1 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2531,7 +2531,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, p->state = TASK_WAKING; if (p->sched_class->task_waking) { - p->sched_class->task_waking(rq, p); + p->sched_class->task_waking(p); en_flags |= ENQUEUE_WAKING; } diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 96b2c95ac356..ad4c414f456d 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -1372,11 +1372,13 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) #ifdef CONFIG_SMP -static void task_waking_fair(struct rq *rq, struct task_struct *p) +static void task_waking_fair(struct task_struct *p) { struct sched_entity *se = &p->se; struct cfs_rq *cfs_rq = cfs_rq_of(se); + lockdep_assert_held(&task_rq(p)->lock); + se->vruntime -= cfs_rq->min_vruntime; } From 3fe1698b7fe05aeb063564e71e40d09f28d8e80c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 5 Apr 2011 17:23:48 +0200 Subject: [PATCH 12/22] sched: Deal with non-atomic min_vruntime reads on 32bits In order to avoid reading partial updated min_vruntime values on 32bit implement a seqcount like solution. Reviewed-by: Frank Rowand Signed-off-by: Peter Zijlstra Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Link: http://lkml.kernel.org/r/20110405152729.111378493@chello.nl Signed-off-by: Ingo Molnar --- kernel/sched.c | 3 +++ kernel/sched_fair.c | 19 +++++++++++++++++-- 2 files changed, 20 insertions(+), 2 deletions(-) diff --git a/kernel/sched.c b/kernel/sched.c index 46f42cac4eb1..7a5eb2620785 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -312,6 +312,9 @@ struct cfs_rq { u64 exec_clock; u64 min_vruntime; +#ifndef CONFIG_64BIT + u64 min_vruntime_copy; +#endif struct rb_root tasks_timeline; struct rb_node *rb_leftmost; diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index ad4c414f456d..054cebb81f7b 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -358,6 +358,10 @@ static void update_min_vruntime(struct cfs_rq *cfs_rq) } cfs_rq->min_vruntime = max_vruntime(cfs_rq->min_vruntime, vruntime); +#ifndef CONFIG_64BIT + smp_wmb(); + cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime; +#endif } /* @@ -1376,10 +1380,21 @@ static void task_waking_fair(struct task_struct *p) { struct sched_entity *se = &p->se; struct cfs_rq *cfs_rq = cfs_rq_of(se); + u64 min_vruntime; - lockdep_assert_held(&task_rq(p)->lock); +#ifndef CONFIG_64BIT + u64 min_vruntime_copy; - se->vruntime -= cfs_rq->min_vruntime; + do { + min_vruntime_copy = cfs_rq->min_vruntime_copy; + smp_rmb(); + min_vruntime = cfs_rq->min_vruntime; + } while (min_vruntime != min_vruntime_copy); +#else + min_vruntime = cfs_rq->min_vruntime; +#endif + + se->vruntime -= min_vruntime; } #ifdef CONFIG_FAIR_GROUP_SCHED From a8e4f2eaecc9bfa4954adf79a04f4f22fddd829c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 5 Apr 2011 17:23:49 +0200 Subject: [PATCH 13/22] sched: Delay task_contributes_to_load() In prepratation of having to call task_contributes_to_load() without holding rq->lock, we need to store the result until we do and can update the rq accounting accordingly. Reviewed-by: Frank Rowand Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Signed-off-by: Ingo Molnar Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20110405152729.151523907@chello.nl --- include/linux/sched.h | 1 + kernel/sched.c | 16 ++++------------ 2 files changed, 5 insertions(+), 12 deletions(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index 7f5732f8c618..25c50317ddc1 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1273,6 +1273,7 @@ struct task_struct { /* Revert to default priority/policy when forking */ unsigned sched_reset_on_fork:1; + unsigned sched_contributes_to_load:1; pid_t pid; pid_t tgid; diff --git a/kernel/sched.c b/kernel/sched.c index 7a5eb2620785..fd32b78c123c 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2519,18 +2519,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, if (unlikely(task_running(rq, p))) goto out_activate; - /* - * In order to handle concurrent wakeups and release the rq->lock - * we put the task in TASK_WAKING state. - * - * First fix up the nr_uninterruptible count: - */ - if (task_contributes_to_load(p)) { - if (likely(cpu_online(orig_cpu))) - rq->nr_uninterruptible--; - else - this_rq()->nr_uninterruptible--; - } + p->sched_contributes_to_load = !!task_contributes_to_load(p); p->state = TASK_WAKING; if (p->sched_class->task_waking) { @@ -2555,6 +2544,9 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, WARN_ON(task_cpu(p) != cpu); WARN_ON(p->state != TASK_WAKING); + if (p->sched_contributes_to_load) + rq->nr_uninterruptible--; + out_activate: #endif /* CONFIG_SMP */ ttwu_activate(rq, p, en_flags); From 2acca55ed98ad9b9aa25e7e587ebe306c0313dc7 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 5 Apr 2011 17:23:50 +0200 Subject: [PATCH 14/22] sched: Also serialize ttwu_local() with p->pi_lock Since we now serialize ttwu() using p->pi_lock, we also need to serialize ttwu_local() using that, otherwise, once we drop the rq->lock from ttwu() it can race with ttwu_local(). Reviewed-by: Frank Rowand Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Signed-off-by: Ingo Molnar Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20110405152729.192366907@chello.nl --- kernel/sched.c | 31 +++++++++++++++++++------------ 1 file changed, 19 insertions(+), 12 deletions(-) diff --git a/kernel/sched.c b/kernel/sched.c index fd32b78c123c..6b269b79c52c 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2566,9 +2566,9 @@ out: * try_to_wake_up_local - try to wake up a local task with rq lock held * @p: the thread to be awakened * - * Put @p on the run-queue if it's not already there. The caller must + * Put @p on the run-queue if it's not already there. The caller must * ensure that this_rq() is locked, @p is bound to this_rq() and not - * the current task. this_rq() stays locked over invocation. + * the current task. */ static void try_to_wake_up_local(struct task_struct *p) { @@ -2578,14 +2578,22 @@ static void try_to_wake_up_local(struct task_struct *p) BUG_ON(p == current); lockdep_assert_held(&rq->lock); + if (!raw_spin_trylock(&p->pi_lock)) { + raw_spin_unlock(&rq->lock); + raw_spin_lock(&p->pi_lock); + raw_spin_lock(&rq->lock); + } + if (!(p->state & TASK_NORMAL)) - return; + goto out; if (!p->on_rq) ttwu_activate(rq, p, ENQUEUE_WAKEUP); ttwu_post_activation(p, rq, 0); ttwu_stat(rq, p, smp_processor_id(), 0); +out: + raw_spin_unlock(&p->pi_lock); } /** @@ -4114,11 +4122,13 @@ need_resched: if (unlikely(signal_pending_state(prev->state, prev))) { prev->state = TASK_RUNNING; } else { + deactivate_task(rq, prev, DEQUEUE_SLEEP); + prev->on_rq = 0; + /* - * If a worker is going to sleep, notify and - * ask workqueue whether it wants to wake up a - * task to maintain concurrency. If so, wake - * up the task. + * If a worker went to sleep, notify and ask workqueue + * whether it wants to wake up a task to maintain + * concurrency. */ if (prev->flags & PF_WQ_WORKER) { struct task_struct *to_wakeup; @@ -4128,12 +4138,9 @@ need_resched: try_to_wake_up_local(to_wakeup); } - deactivate_task(rq, prev, DEQUEUE_SLEEP); - prev->on_rq = 0; - /* - * If we are going to sleep and we have plugged IO queued, make - * sure to submit it to avoid deadlocks. + * If we are going to sleep and we have plugged IO + * queued, make sure to submit it to avoid deadlocks. */ if (blk_needs_flush_plug(prev)) { raw_spin_unlock(&rq->lock); From 0122ec5b02f766c355b3168df53a6c038a24fa0d Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 5 Apr 2011 17:23:51 +0200 Subject: [PATCH 15/22] sched: Add p->pi_lock to task_rq_lock() In order to be able to call set_task_cpu() while either holding p->pi_lock or task_rq(p)->lock we need to hold both locks in order to stabilize task_rq(). This makes task_rq_lock() acquire both locks, and have __task_rq_lock() validate that p->pi_lock is held. This increases the locking overhead for most scheduler syscalls but allows reduction of rq->lock contention for some scheduler hot paths (ttwu). Reviewed-by: Frank Rowand Signed-off-by: Peter Zijlstra Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Link: http://lkml.kernel.org/r/20110405152729.232781355@chello.nl Signed-off-by: Ingo Molnar --- kernel/sched.c | 103 ++++++++++++++++++++++--------------------------- 1 file changed, 47 insertions(+), 56 deletions(-) diff --git a/kernel/sched.c b/kernel/sched.c index 6b269b79c52c..f1551271a685 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -599,7 +599,7 @@ static inline int cpu_of(struct rq *rq) * Return the group to which this tasks belongs. * * We use task_subsys_state_check() and extend the RCU verification - * with lockdep_is_held(&task_rq(p)->lock) because cpu_cgroup_attach() + * with lockdep_is_held(&p->pi_lock) because cpu_cgroup_attach() * holds that lock for each task it moves into the cgroup. Therefore * by holding that lock, we pin the task to the current cgroup. */ @@ -609,7 +609,7 @@ static inline struct task_group *task_group(struct task_struct *p) struct cgroup_subsys_state *css; css = task_subsys_state_check(p, cpu_cgroup_subsys_id, - lockdep_is_held(&task_rq(p)->lock)); + lockdep_is_held(&p->pi_lock)); tg = container_of(css, struct task_group, css); return autogroup_task_group(p, tg); @@ -924,23 +924,15 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) #endif /* __ARCH_WANT_UNLOCKED_CTXSW */ /* - * Check whether the task is waking, we use this to synchronize ->cpus_allowed - * against ttwu(). - */ -static inline int task_is_waking(struct task_struct *p) -{ - return unlikely(p->state == TASK_WAKING); -} - -/* - * __task_rq_lock - lock the runqueue a given task resides on. - * Must be called interrupts disabled. + * __task_rq_lock - lock the rq @p resides on. */ static inline struct rq *__task_rq_lock(struct task_struct *p) __acquires(rq->lock) { struct rq *rq; + lockdep_assert_held(&p->pi_lock); + for (;;) { rq = task_rq(p); raw_spin_lock(&rq->lock); @@ -951,22 +943,22 @@ static inline struct rq *__task_rq_lock(struct task_struct *p) } /* - * task_rq_lock - lock the runqueue a given task resides on and disable - * interrupts. Note the ordering: we can safely lookup the task_rq without - * explicitly disabling preemption. + * task_rq_lock - lock p->pi_lock and lock the rq @p resides on. */ static struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags) + __acquires(p->pi_lock) __acquires(rq->lock) { struct rq *rq; for (;;) { - local_irq_save(*flags); + raw_spin_lock_irqsave(&p->pi_lock, *flags); rq = task_rq(p); raw_spin_lock(&rq->lock); if (likely(rq == task_rq(p))) return rq; - raw_spin_unlock_irqrestore(&rq->lock, *flags); + raw_spin_unlock(&rq->lock); + raw_spin_unlock_irqrestore(&p->pi_lock, *flags); } } @@ -976,10 +968,13 @@ static void __task_rq_unlock(struct rq *rq) raw_spin_unlock(&rq->lock); } -static inline void task_rq_unlock(struct rq *rq, unsigned long *flags) +static inline void +task_rq_unlock(struct rq *rq, struct task_struct *p, unsigned long *flags) __releases(rq->lock) + __releases(p->pi_lock) { - raw_spin_unlock_irqrestore(&rq->lock, *flags); + raw_spin_unlock(&rq->lock); + raw_spin_unlock_irqrestore(&p->pi_lock, *flags); } /* @@ -2175,6 +2170,11 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu) */ WARN_ON_ONCE(p->state != TASK_RUNNING && p->state != TASK_WAKING && !(task_thread_info(p)->preempt_count & PREEMPT_ACTIVE)); + +#ifdef CONFIG_LOCKDEP + WARN_ON_ONCE(debug_locks && !(lockdep_is_held(&p->pi_lock) || + lockdep_is_held(&task_rq(p)->lock))); +#endif #endif trace_sched_migrate_task(p, new_cpu); @@ -2270,7 +2270,7 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state) ncsw = 0; if (!match_state || p->state == match_state) ncsw = p->nvcsw | LONG_MIN; /* sets MSB */ - task_rq_unlock(rq, &flags); + task_rq_unlock(rq, p, &flags); /* * If it changed from the expected state, bail out now. @@ -2652,6 +2652,7 @@ static void __sched_fork(struct task_struct *p) */ void sched_fork(struct task_struct *p, int clone_flags) { + unsigned long flags; int cpu = get_cpu(); __sched_fork(p); @@ -2702,9 +2703,9 @@ void sched_fork(struct task_struct *p, int clone_flags) * * Silence PROVE_RCU. */ - rcu_read_lock(); + raw_spin_lock_irqsave(&p->pi_lock, flags); set_task_cpu(p, cpu); - rcu_read_unlock(); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) if (likely(sched_info_on())) @@ -2753,7 +2754,7 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags) set_task_cpu(p, cpu); p->state = TASK_RUNNING; - task_rq_unlock(rq, &flags); + task_rq_unlock(rq, p, &flags); #endif rq = task_rq_lock(p, &flags); @@ -2765,7 +2766,7 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags) if (p->sched_class->task_woken) p->sched_class->task_woken(rq, p); #endif - task_rq_unlock(rq, &flags); + task_rq_unlock(rq, p, &flags); put_cpu(); } @@ -3490,12 +3491,12 @@ void sched_exec(void) likely(cpu_active(dest_cpu)) && need_migrate_task(p)) { struct migration_arg arg = { p, dest_cpu }; - task_rq_unlock(rq, &flags); + task_rq_unlock(rq, p, &flags); stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg); return; } unlock: - task_rq_unlock(rq, &flags); + task_rq_unlock(rq, p, &flags); } #endif @@ -3532,7 +3533,7 @@ unsigned long long task_delta_exec(struct task_struct *p) rq = task_rq_lock(p, &flags); ns = do_task_delta_exec(p, rq); - task_rq_unlock(rq, &flags); + task_rq_unlock(rq, p, &flags); return ns; } @@ -3550,7 +3551,7 @@ unsigned long long task_sched_runtime(struct task_struct *p) rq = task_rq_lock(p, &flags); ns = p->se.sum_exec_runtime + do_task_delta_exec(p, rq); - task_rq_unlock(rq, &flags); + task_rq_unlock(rq, p, &flags); return ns; } @@ -3574,7 +3575,7 @@ unsigned long long thread_group_sched_runtime(struct task_struct *p) rq = task_rq_lock(p, &flags); thread_group_cputime(p, &totals); ns = totals.sum_exec_runtime + do_task_delta_exec(p, rq); - task_rq_unlock(rq, &flags); + task_rq_unlock(rq, p, &flags); return ns; } @@ -4693,16 +4694,13 @@ EXPORT_SYMBOL(sleep_on_timeout); */ void rt_mutex_setprio(struct task_struct *p, int prio) { - unsigned long flags; int oldprio, on_rq, running; struct rq *rq; const struct sched_class *prev_class; BUG_ON(prio < 0 || prio > MAX_PRIO); - lockdep_assert_held(&p->pi_lock); - - rq = task_rq_lock(p, &flags); + rq = __task_rq_lock(p); trace_sched_pi_setprio(p, prio); oldprio = p->prio; @@ -4727,7 +4725,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio) enqueue_task(rq, p, oldprio < prio ? ENQUEUE_HEAD : 0); check_class_changed(rq, p, prev_class, oldprio); - task_rq_unlock(rq, &flags); + __task_rq_unlock(rq); } #endif @@ -4775,7 +4773,7 @@ void set_user_nice(struct task_struct *p, long nice) resched_task(rq->curr); } out_unlock: - task_rq_unlock(rq, &flags); + task_rq_unlock(rq, p, &flags); } EXPORT_SYMBOL(set_user_nice); @@ -5003,20 +5001,17 @@ recheck: /* * make sure no PI-waiters arrive (or leave) while we are * changing the priority of the task: - */ - raw_spin_lock_irqsave(&p->pi_lock, flags); - /* + * * To be able to change p->policy safely, the appropriate * runqueue lock must be held. */ - rq = __task_rq_lock(p); + rq = task_rq_lock(p, &flags); /* * Changing the policy of the stop threads its a very bad idea */ if (p == rq->stop) { - __task_rq_unlock(rq); - raw_spin_unlock_irqrestore(&p->pi_lock, flags); + task_rq_unlock(rq, p, &flags); return -EINVAL; } @@ -5040,8 +5035,7 @@ recheck: if (rt_bandwidth_enabled() && rt_policy(policy) && task_group(p)->rt_bandwidth.rt_runtime == 0 && !task_group_is_autogroup(task_group(p))) { - __task_rq_unlock(rq); - raw_spin_unlock_irqrestore(&p->pi_lock, flags); + task_rq_unlock(rq, p, &flags); return -EPERM; } } @@ -5050,8 +5044,7 @@ recheck: /* recheck policy now with rq lock held */ if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) { policy = oldpolicy = -1; - __task_rq_unlock(rq); - raw_spin_unlock_irqrestore(&p->pi_lock, flags); + task_rq_unlock(rq, p, &flags); goto recheck; } on_rq = p->on_rq; @@ -5073,8 +5066,7 @@ recheck: activate_task(rq, p, 0); check_class_changed(rq, p, prev_class, oldprio); - __task_rq_unlock(rq); - raw_spin_unlock_irqrestore(&p->pi_lock, flags); + task_rq_unlock(rq, p, &flags); rt_mutex_adjust_pi(p); @@ -5666,7 +5658,7 @@ SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid, rq = task_rq_lock(p, &flags); time_slice = p->sched_class->get_rr_interval(rq, p); - task_rq_unlock(rq, &flags); + task_rq_unlock(rq, p, &flags); rcu_read_unlock(); jiffies_to_timespec(time_slice, &t); @@ -5889,8 +5881,7 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) unsigned int dest_cpu; int ret = 0; - raw_spin_lock_irqsave(&p->pi_lock, flags); - rq = __task_rq_lock(p); + rq = task_rq_lock(p, &flags); if (!cpumask_intersects(new_mask, cpu_active_mask)) { ret = -EINVAL; @@ -5918,15 +5909,13 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) if (need_migrate_task(p)) { struct migration_arg arg = { p, dest_cpu }; /* Need help from migration thread: drop lock and wait. */ - __task_rq_unlock(rq); - raw_spin_unlock_irqrestore(&p->pi_lock, flags); + task_rq_unlock(rq, p, &flags); stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg); tlb_migrate_finish(p->mm); return 0; } out: - __task_rq_unlock(rq); - raw_spin_unlock_irqrestore(&p->pi_lock, flags); + task_rq_unlock(rq, p, &flags); return ret; } @@ -5954,6 +5943,7 @@ static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu) rq_src = cpu_rq(src_cpu); rq_dest = cpu_rq(dest_cpu); + raw_spin_lock(&p->pi_lock); double_rq_lock(rq_src, rq_dest); /* Already moved. */ if (task_cpu(p) != src_cpu) @@ -5976,6 +5966,7 @@ done: ret = 1; fail: double_rq_unlock(rq_src, rq_dest); + raw_spin_unlock(&p->pi_lock); return ret; } @@ -8702,7 +8693,7 @@ void sched_move_task(struct task_struct *tsk) if (on_rq) enqueue_task(rq, tsk, 0); - task_rq_unlock(rq, &flags); + task_rq_unlock(rq, tsk, &flags); } #endif /* CONFIG_CGROUP_SCHED */ From ab2515c4b98f7bc4fa11cad9fa0f811d63a72a26 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 5 Apr 2011 17:23:52 +0200 Subject: [PATCH 16/22] sched: Drop rq->lock from first part of wake_up_new_task() Since p->pi_lock now protects all things needed to call select_task_rq() avoid the double remote rq->lock acquisition and rely on p->pi_lock. Reviewed-by: Frank Rowand Signed-off-by: Peter Zijlstra Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Link: http://lkml.kernel.org/r/20110405152729.273362517@chello.nl Signed-off-by: Ingo Molnar --- kernel/sched.c | 17 +++-------------- 1 file changed, 3 insertions(+), 14 deletions(-) diff --git a/kernel/sched.c b/kernel/sched.c index f1551271a685..7c5494dccd39 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2736,28 +2736,18 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags) { unsigned long flags; struct rq *rq; - int cpu __maybe_unused = get_cpu(); + raw_spin_lock_irqsave(&p->pi_lock, flags); #ifdef CONFIG_SMP - rq = task_rq_lock(p, &flags); - p->state = TASK_WAKING; - /* * Fork balancing, do it here and not earlier because: * - cpus_allowed can change in the fork path * - any previously selected cpu might disappear through hotplug - * - * We set TASK_WAKING so that select_task_rq() can drop rq->lock - * without people poking at ->cpus_allowed. */ - cpu = select_task_rq(p, SD_BALANCE_FORK, 0); - set_task_cpu(p, cpu); - - p->state = TASK_RUNNING; - task_rq_unlock(rq, p, &flags); + set_task_cpu(p, select_task_rq(p, SD_BALANCE_FORK, 0)); #endif - rq = task_rq_lock(p, &flags); + rq = __task_rq_lock(p); activate_task(rq, p, 0); p->on_rq = 1; trace_sched_wakeup_new(p, true); @@ -2767,7 +2757,6 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags) p->sched_class->task_woken(rq, p); #endif task_rq_unlock(rq, p, &flags); - put_cpu(); } #ifdef CONFIG_PREEMPT_NOTIFIERS From 8f42ced974df7d5af2de4cf5ea21fe978c7e4478 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 5 Apr 2011 17:23:53 +0200 Subject: [PATCH 17/22] sched: Drop rq->lock from sched_exec() Since we can now call select_task_rq() and set_task_cpu() with only p->pi_lock held, and sched_exec() load-balancing has always been optimistic, drop all rq->lock usage. Oleg also noted that need_migrate_task() will always be true for current, so don't bother calling that at all. Reviewed-by: Frank Rowand Signed-off-by: Peter Zijlstra Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Link: http://lkml.kernel.org/r/20110405152729.314204889@chello.nl Signed-off-by: Ingo Molnar --- kernel/sched.c | 15 +++++---------- 1 file changed, 5 insertions(+), 10 deletions(-) diff --git a/kernel/sched.c b/kernel/sched.c index 7c5494dccd39..1be1a09b9dc9 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -3465,27 +3465,22 @@ void sched_exec(void) { struct task_struct *p = current; unsigned long flags; - struct rq *rq; int dest_cpu; - rq = task_rq_lock(p, &flags); + raw_spin_lock_irqsave(&p->pi_lock, flags); dest_cpu = p->sched_class->select_task_rq(p, SD_BALANCE_EXEC, 0); if (dest_cpu == smp_processor_id()) goto unlock; - /* - * select_task_rq() can race against ->cpus_allowed - */ - if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed) && - likely(cpu_active(dest_cpu)) && need_migrate_task(p)) { + if (likely(cpu_active(dest_cpu))) { struct migration_arg arg = { p, dest_cpu }; - task_rq_unlock(rq, p, &flags); - stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); + stop_one_cpu(task_cpu(p), migration_cpu_stop, &arg); return; } unlock: - task_rq_unlock(rq, p, &flags); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); } #endif From e4a52bcb9a18142d79e231b6733cabdbf2e67c1f Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 5 Apr 2011 17:23:54 +0200 Subject: [PATCH 18/22] sched: Remove rq->lock from the first half of ttwu() Currently ttwu() does two rq->lock acquisitions, once on the task's old rq, holding it over the p->state fiddling and load-balance pass. Then it drops the old rq->lock to acquire the new rq->lock. By having serialized ttwu(), p->sched_class, p->cpus_allowed with p->pi_lock, we can now drop the whole first rq->lock acquisition. The p->pi_lock serializing concurrent ttwu() calls protects p->state, which we will set to TASK_WAKING to bridge possible p->pi_lock to rq->lock gaps and serialize set_task_cpu() calls against task_rq_lock(). The p->pi_lock serialization of p->sched_class allows us to call scheduling class methods without holding the rq->lock, and the serialization of p->cpus_allowed allows us to do the load-balancing bits without races. Reviewed-by: Frank Rowand Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Signed-off-by: Ingo Molnar Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20110405152729.354401150@chello.nl --- kernel/sched.c | 65 ++++++++++++++++++++++++++++---------------------- 1 file changed, 37 insertions(+), 28 deletions(-) diff --git a/kernel/sched.c b/kernel/sched.c index 1be1a09b9dc9..871dd9e147a6 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2493,69 +2493,78 @@ ttwu_post_activation(struct task_struct *p, struct rq *rq, int wake_flags) * Returns %true if @p was woken up, %false if it was already running * or @state didn't match @p's state. */ -static int try_to_wake_up(struct task_struct *p, unsigned int state, - int wake_flags) +static int +try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) { - int cpu, orig_cpu, this_cpu, success = 0; + int cpu, this_cpu, success = 0; unsigned long flags; - unsigned long en_flags = ENQUEUE_WAKEUP; struct rq *rq; this_cpu = get_cpu(); smp_wmb(); raw_spin_lock_irqsave(&p->pi_lock, flags); - rq = __task_rq_lock(p); if (!(p->state & state)) goto out; cpu = task_cpu(p); - if (p->on_rq) - goto out_running; + if (p->on_rq) { + rq = __task_rq_lock(p); + if (p->on_rq) + goto out_running; + __task_rq_unlock(rq); + } - orig_cpu = cpu; #ifdef CONFIG_SMP - if (unlikely(task_running(rq, p))) - goto out_activate; + while (p->on_cpu) { +#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW + /* + * If called from interrupt context we could have landed in the + * middle of schedule(), in this case we should take care not + * to spin on ->on_cpu if p is current, since that would + * deadlock. + */ + if (p == current) + goto out_activate; +#endif + cpu_relax(); + } + /* + * Pairs with the smp_wmb() in finish_lock_switch(). + */ + smp_rmb(); p->sched_contributes_to_load = !!task_contributes_to_load(p); p->state = TASK_WAKING; - if (p->sched_class->task_waking) { + if (p->sched_class->task_waking) p->sched_class->task_waking(p); - en_flags |= ENQUEUE_WAKING; - } cpu = select_task_rq(p, SD_BALANCE_WAKE, wake_flags); - if (cpu != orig_cpu) - set_task_cpu(p, cpu); - __task_rq_unlock(rq); +#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW +out_activate: +#endif +#endif /* CONFIG_SMP */ rq = cpu_rq(cpu); raw_spin_lock(&rq->lock); - /* - * We migrated the task without holding either rq->lock, however - * since the task is not on the task list itself, nobody else - * will try and migrate the task, hence the rq should match the - * cpu we just moved it to. - */ - WARN_ON(task_cpu(p) != cpu); - WARN_ON(p->state != TASK_WAKING); +#ifdef CONFIG_SMP + if (cpu != task_cpu(p)) + set_task_cpu(p, cpu); if (p->sched_contributes_to_load) rq->nr_uninterruptible--; +#endif -out_activate: -#endif /* CONFIG_SMP */ - ttwu_activate(rq, p, en_flags); + ttwu_activate(rq, p, ENQUEUE_WAKEUP | ENQUEUE_WAKING); out_running: ttwu_post_activation(p, rq, wake_flags); ttwu_stat(rq, p, cpu, wake_flags); success = 1; -out: __task_rq_unlock(rq); +out: raw_spin_unlock_irqrestore(&p->pi_lock, flags); put_cpu(); From b84cb5df1f9ad6da3f214c638d5fb08d0c99de1f Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 5 Apr 2011 17:23:55 +0200 Subject: [PATCH 19/22] sched: Remove rq argument from ttwu_stat() In order to call ttwu_stat() without holding rq->lock we must remove its rq argument. Since we need to change rq stats, account to the local rq instead of the task rq, this is safe since we have IRQs disabled. Reviewed-by: Frank Rowand Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Signed-off-by: Ingo Molnar Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20110405152729.394638826@chello.nl --- kernel/sched.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/kernel/sched.c b/kernel/sched.c index 871dd9e147a6..5ec2e8b4b01a 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2410,9 +2410,11 @@ static void update_avg(u64 *avg, u64 sample) #endif static void -ttwu_stat(struct rq *rq, struct task_struct *p, int cpu, int wake_flags) +ttwu_stat(struct task_struct *p, int cpu, int wake_flags) { #ifdef CONFIG_SCHEDSTATS + struct rq *rq = this_rq(); + #ifdef CONFIG_SMP int this_cpu = smp_processor_id(); @@ -2561,9 +2563,10 @@ out_activate: ttwu_activate(rq, p, ENQUEUE_WAKEUP | ENQUEUE_WAKING); out_running: ttwu_post_activation(p, rq, wake_flags); - ttwu_stat(rq, p, cpu, wake_flags); success = 1; __task_rq_unlock(rq); + + ttwu_stat(p, cpu, wake_flags); out: raw_spin_unlock_irqrestore(&p->pi_lock, flags); put_cpu(); @@ -2600,7 +2603,7 @@ static void try_to_wake_up_local(struct task_struct *p) ttwu_activate(rq, p, ENQUEUE_WAKEUP); ttwu_post_activation(p, rq, 0); - ttwu_stat(rq, p, smp_processor_id(), 0); + ttwu_stat(p, smp_processor_id(), 0); out: raw_spin_unlock(&p->pi_lock); } From 23f41eeb42ce7f6f1210904e49e84718f02cb61c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 5 Apr 2011 17:23:56 +0200 Subject: [PATCH 20/22] sched: Rename ttwu_post_activation() to ttwu_do_wakeup() The ttwu_post_activation() code does the core wakeup, it sets TASK_RUNNING and performs wakeup-preemption, so give is a more descriptive name. Reviewed-by: Frank Rowand Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Signed-off-by: Ingo Molnar Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20110405152729.434609705@chello.nl --- kernel/sched.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/kernel/sched.c b/kernel/sched.c index 5ec2e8b4b01a..e309dbad2038 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2456,8 +2456,11 @@ static void ttwu_activate(struct rq *rq, struct task_struct *p, int en_flags) wq_worker_waking_up(p, cpu_of(rq)); } +/* + * Mark the task runnable and perform wakeup-preemption. + */ static void -ttwu_post_activation(struct task_struct *p, struct rq *rq, int wake_flags) +ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags) { trace_sched_wakeup(p, true); check_preempt_curr(rq, p, wake_flags); @@ -2562,7 +2565,7 @@ out_activate: ttwu_activate(rq, p, ENQUEUE_WAKEUP | ENQUEUE_WAKING); out_running: - ttwu_post_activation(p, rq, wake_flags); + ttwu_do_wakeup(rq, p, wake_flags); success = 1; __task_rq_unlock(rq); @@ -2602,7 +2605,7 @@ static void try_to_wake_up_local(struct task_struct *p) if (!p->on_rq) ttwu_activate(rq, p, ENQUEUE_WAKEUP); - ttwu_post_activation(p, rq, 0); + ttwu_do_wakeup(rq, p, 0); ttwu_stat(p, smp_processor_id(), 0); out: raw_spin_unlock(&p->pi_lock); From c05fbafba1c5482bee399b360288fa405415e126 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 5 Apr 2011 17:23:57 +0200 Subject: [PATCH 21/22] sched: Restructure ttwu() some more Factor our helper functions to make the inner workings of try_to_wake_up() more obvious, this also allows for adding remote queues. Reviewed-by: Frank Rowand Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Signed-off-by: Ingo Molnar Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20110405152729.475848012@chello.nl --- kernel/sched.c | 91 ++++++++++++++++++++++++++++++++------------------ 1 file changed, 58 insertions(+), 33 deletions(-) diff --git a/kernel/sched.c b/kernel/sched.c index e309dbad2038..7d8b85fcdf06 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2483,6 +2483,48 @@ ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags) #endif } +static void +ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags) +{ +#ifdef CONFIG_SMP + if (p->sched_contributes_to_load) + rq->nr_uninterruptible--; +#endif + + ttwu_activate(rq, p, ENQUEUE_WAKEUP | ENQUEUE_WAKING); + ttwu_do_wakeup(rq, p, wake_flags); +} + +/* + * Called in case the task @p isn't fully descheduled from its runqueue, + * in this case we must do a remote wakeup. Its a 'light' wakeup though, + * since all we need to do is flip p->state to TASK_RUNNING, since + * the task is still ->on_rq. + */ +static int ttwu_remote(struct task_struct *p, int wake_flags) +{ + struct rq *rq; + int ret = 0; + + rq = __task_rq_lock(p); + if (p->on_rq) { + ttwu_do_wakeup(rq, p, wake_flags); + ret = 1; + } + __task_rq_unlock(rq); + + return ret; +} + +static void ttwu_queue(struct task_struct *p, int cpu) +{ + struct rq *rq = cpu_rq(cpu); + + raw_spin_lock(&rq->lock); + ttwu_do_activate(rq, p, 0); + raw_spin_unlock(&rq->lock); +} + /** * try_to_wake_up - wake up a thread * @p: the thread to be awakened @@ -2501,27 +2543,25 @@ ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags) static int try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) { - int cpu, this_cpu, success = 0; unsigned long flags; - struct rq *rq; - - this_cpu = get_cpu(); + int cpu, success = 0; smp_wmb(); raw_spin_lock_irqsave(&p->pi_lock, flags); if (!(p->state & state)) goto out; + success = 1; /* we're going to change ->state */ cpu = task_cpu(p); - if (p->on_rq) { - rq = __task_rq_lock(p); - if (p->on_rq) - goto out_running; - __task_rq_unlock(rq); - } + if (p->on_rq && ttwu_remote(p, wake_flags)) + goto stat; #ifdef CONFIG_SMP + /* + * If the owning (remote) cpu is still in the middle of schedule() with + * this task as prev, wait until its done referencing the task. + */ while (p->on_cpu) { #ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW /* @@ -2530,8 +2570,10 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) * to spin on ->on_cpu if p is current, since that would * deadlock. */ - if (p == current) - goto out_activate; + if (p == current) { + ttwu_queue(p, cpu); + goto stat; + } #endif cpu_relax(); } @@ -2547,32 +2589,15 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) p->sched_class->task_waking(p); cpu = select_task_rq(p, SD_BALANCE_WAKE, wake_flags); -#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW -out_activate: -#endif + if (task_cpu(p) != cpu) + set_task_cpu(p, cpu); #endif /* CONFIG_SMP */ - rq = cpu_rq(cpu); - raw_spin_lock(&rq->lock); - -#ifdef CONFIG_SMP - if (cpu != task_cpu(p)) - set_task_cpu(p, cpu); - - if (p->sched_contributes_to_load) - rq->nr_uninterruptible--; -#endif - - ttwu_activate(rq, p, ENQUEUE_WAKEUP | ENQUEUE_WAKING); -out_running: - ttwu_do_wakeup(rq, p, wake_flags); - success = 1; - __task_rq_unlock(rq); - + ttwu_queue(p, cpu); +stat: ttwu_stat(p, cpu, wake_flags); out: raw_spin_unlock_irqrestore(&p->pi_lock, flags); - put_cpu(); return success; } From 317f394160e9beb97d19a84c39b7e5eb3d7815a8 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 5 Apr 2011 17:23:58 +0200 Subject: [PATCH 22/22] sched: Move the second half of ttwu() to the remote cpu Now that we've removed the rq->lock requirement from the first part of ttwu() and can compute placement without holding any rq->lock, ensure we execute the second half of ttwu() on the actual cpu we want the task to run on. This avoids having to take rq->lock and doing the task enqueue remotely, saving lots on cacheline transfers. As measured using: http://oss.oracle.com/~mason/sembench.c $ for i in /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor ; do echo performance > $i; done $ echo 4096 32000 64 128 > /proc/sys/kernel/sem $ ./sembench -t 2048 -w 1900 -o 0 unpatched: run time 30 seconds 647278 worker burns per second patched: run time 30 seconds 816715 worker burns per second Reviewed-by: Frank Rowand Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Signed-off-by: Ingo Molnar Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20110405152729.515897185@chello.nl --- include/linux/sched.h | 3 ++- init/Kconfig | 5 ++++ kernel/sched.c | 56 +++++++++++++++++++++++++++++++++++++++++ kernel/sched_features.h | 6 +++++ 4 files changed, 69 insertions(+), 1 deletion(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index 25c50317ddc1..e09dafa6e149 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1203,6 +1203,7 @@ struct task_struct { int lock_depth; /* BKL lock depth */ #ifdef CONFIG_SMP + struct task_struct *wake_entry; int on_cpu; #endif int on_rq; @@ -2192,7 +2193,7 @@ extern void set_task_comm(struct task_struct *tsk, char *from); extern char *get_task_comm(char *to, struct task_struct *tsk); #ifdef CONFIG_SMP -static inline void scheduler_ipi(void) { } +void scheduler_ipi(void); extern unsigned long wait_task_inactive(struct task_struct *, long match_state); #else static inline void scheduler_ipi(void) { } diff --git a/init/Kconfig b/init/Kconfig index 56240e724d9a..32745bfe059e 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -827,6 +827,11 @@ config SCHED_AUTOGROUP desktop applications. Task group autogeneration is currently based upon task session. +config SCHED_TTWU_QUEUE + bool + depends on !SPARC32 + default y + config MM_OWNER bool diff --git a/kernel/sched.c b/kernel/sched.c index 7d8b85fcdf06..9e3ede120e81 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -556,6 +556,10 @@ struct rq { unsigned int ttwu_count; unsigned int ttwu_local; #endif + +#ifdef CONFIG_SMP + struct task_struct *wake_list; +#endif }; static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); @@ -2516,10 +2520,61 @@ static int ttwu_remote(struct task_struct *p, int wake_flags) return ret; } +#ifdef CONFIG_SMP +static void sched_ttwu_pending(void) +{ + struct rq *rq = this_rq(); + struct task_struct *list = xchg(&rq->wake_list, NULL); + + if (!list) + return; + + raw_spin_lock(&rq->lock); + + while (list) { + struct task_struct *p = list; + list = list->wake_entry; + ttwu_do_activate(rq, p, 0); + } + + raw_spin_unlock(&rq->lock); +} + +void scheduler_ipi(void) +{ + sched_ttwu_pending(); +} + +static void ttwu_queue_remote(struct task_struct *p, int cpu) +{ + struct rq *rq = cpu_rq(cpu); + struct task_struct *next = rq->wake_list; + + for (;;) { + struct task_struct *old = next; + + p->wake_entry = next; + next = cmpxchg(&rq->wake_list, old, p); + if (next == old) + break; + } + + if (!next) + smp_send_reschedule(cpu); +} +#endif + static void ttwu_queue(struct task_struct *p, int cpu) { struct rq *rq = cpu_rq(cpu); +#if defined(CONFIG_SMP) && defined(CONFIG_SCHED_TTWU_QUEUE) + if (sched_feat(TTWU_QUEUE) && cpu != smp_processor_id()) { + ttwu_queue_remote(p, cpu); + return; + } +#endif + raw_spin_lock(&rq->lock); ttwu_do_activate(rq, p, 0); raw_spin_unlock(&rq->lock); @@ -6331,6 +6386,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) #ifdef CONFIG_HOTPLUG_CPU case CPU_DYING: + sched_ttwu_pending(); /* Update our root-domain */ raw_spin_lock_irqsave(&rq->lock, flags); if (rq->rd) { diff --git a/kernel/sched_features.h b/kernel/sched_features.h index 68e69acc29b9..be40f7371ee1 100644 --- a/kernel/sched_features.h +++ b/kernel/sched_features.h @@ -64,3 +64,9 @@ SCHED_FEAT(OWNER_SPIN, 1) * Decrement CPU power based on irq activity */ SCHED_FEAT(NONIRQ_POWER, 1) + +/* + * Queue remote wakeups on the target CPU and process them + * using the scheduler IPI. Reduces rq->lock contention/bounces. + */ +SCHED_FEAT(TTWU_QUEUE, 1)