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 <rmk+kernel@arm.linux.org.uk>
Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Acked-by: Chris Metcalf <cmetcalf@tilera.com>
Acked-by: Jesper Nilsson <jesper.nilsson@axis.com>
Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
Reviewed-by: Frank Rowand <frank.rowand@am.sony.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Nick Piggin <npiggin@kernel.dk>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20110405152728.744338123@chello.nl

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 <linux/irq.h>
 #include <linux/ratelimit.h>
 #include <linux/acpi.h>
+#include <linux/sched.h>
 
 #include <asm/delay.h>
 #include <asm/intrinsics.h>
@@ -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 <linux/sched.h>
+
 /* 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 <linux/delay.h>
 #include <linux/smp.h>
 #include <linux/kernel_stat.h>
+#include <linux/sched.h>
 
 #include <asm/mmu_context.h>
 #include <asm/io.h>
@@ -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 <linux/interrupt.h>
 #include <linux/smp.h>
 #include <linux/kernel_stat.h>
+#include <linux/sched.h>
 
 #include <asm/mmu_context.h>
 #include <asm/io.h>
@@ -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 <linux/module.h>
 #include <linux/cpu.h>
 #include <linux/interrupt.h>
+#include <linux/sched.h>
 #include <asm/atomic.h>
 #include <asm/processor.h>
 #include <asm/system.h>
@@ -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)
 {