Merge branch 'generic-ipi-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'generic-ipi-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (22 commits)
  generic-ipi: more merge fallout
  generic-ipi: merge fix
  x86, visws: use mach-default/entry_arch.h
  x86, visws: fix generic-ipi build
  generic-ipi: fixlet
  generic-ipi: fix s390 build bug
  generic-ipi: fix linux-next tree build failure
  fix: "smp_call_function: get rid of the unused nonatomic/retry argument"
  fix: "smp_call_function: get rid of the unused nonatomic/retry argument"
  fix "smp_call_function: get rid of the unused nonatomic/retry argument"
  on_each_cpu(): kill unused 'retry' parameter
  smp_call_function: get rid of the unused nonatomic/retry argument
  sh: convert to generic helpers for IPI function calls
  parisc: convert to generic helpers for IPI function calls
  mips: convert to generic helpers for IPI function calls
  m32r: convert to generic helpers for IPI function calls
  arm: convert to generic helpers for IPI function calls
  alpha: convert to generic helpers for IPI function calls
  ia64: convert to generic helpers for IPI function calls
  powerpc: convert to generic helpers for IPI function calls
  ...

Fix trivial conflicts due to rcu updates in kernel/rcupdate.c manually

9 files changed, 30 insertions, 254 deletions

diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 16be41446b5b..18bcc10903b4 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -303,6 +303,7 @@ config VIRT_CPU_ACCOUNTING
 
 config SMP
         bool "Symmetric multi-processing support"
+        select USE_GENERIC_SMP_HELPERS
         help
           This enables support for systems with more than one CPU. If you have
           a system with only one CPU, say N.  If you have a system with more
diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c
index 705176b434b3..7dd96c127177 100644
--- a/arch/ia64/kernel/mca.c
+++ b/arch/ia64/kernel/mca.c
@@ -707,7 +707,7 @@ ia64_mca_cmc_vector_enable (void *dummy)
 static void
 ia64_mca_cmc_vector_disable_keventd(struct work_struct *unused)
 {
-        on_each_cpu(ia64_mca_cmc_vector_disable, NULL, 1, 0);
+        on_each_cpu(ia64_mca_cmc_vector_disable, NULL, 0);
 }
 
 /*
@@ -719,7 +719,7 @@ ia64_mca_cmc_vector_disable_keventd(struct work_struct *unused)
 static void
 ia64_mca_cmc_vector_enable_keventd(struct work_struct *unused)
 {
-        on_each_cpu(ia64_mca_cmc_vector_enable, NULL, 1, 0);
+        on_each_cpu(ia64_mca_cmc_vector_enable, NULL, 0);
 }
 
 /*
@@ -1881,7 +1881,7 @@ static int __cpuinit mca_cpu_callback(struct notifier_block *nfb,
         case CPU_ONLINE:
         case CPU_ONLINE_FROZEN:
                 smp_call_function_single(hotcpu, ia64_mca_cmc_vector_adjust,
-                                         NULL, 1, 0);
+                                         NULL, 0);
                 break;
         }
         return NOTIFY_OK;
diff --git a/arch/ia64/kernel/palinfo.c b/arch/ia64/kernel/palinfo.c
index 9dc00f7fe10e..e5c57f413ca2 100644
--- a/arch/ia64/kernel/palinfo.c
+++ b/arch/ia64/kernel/palinfo.c
@@ -921,7 +921,7 @@ int palinfo_handle_smp(pal_func_cpu_u_t *f, char *page)
 
 
         /* will send IPI to other CPU and wait for completion of remote call */
-        if ((ret=smp_call_function_single(f->req_cpu, palinfo_smp_call, &ptr, 0, 1))) {
+        if ((ret=smp_call_function_single(f->req_cpu, palinfo_smp_call, &ptr, 1))) {
                 printk(KERN_ERR "palinfo: remote CPU call from %d to %d on function %d: "
                        "error %d\n", smp_processor_id(), f->req_cpu, f->func_id, ret);
                 return 0;
diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c
index 7714a97b0104..19d4493c6193 100644
--- a/arch/ia64/kernel/perfmon.c
+++ b/arch/ia64/kernel/perfmon.c
@@ -1820,7 +1820,7 @@ pfm_syswide_cleanup_other_cpu(pfm_context_t *ctx)
         int ret;
 
         DPRINT(("calling CPU%d for cleanup\n", ctx->ctx_cpu));
-        ret = smp_call_function_single(ctx->ctx_cpu, pfm_syswide_force_stop, ctx, 0, 1);
+        ret = smp_call_function_single(ctx->ctx_cpu, pfm_syswide_force_stop, ctx, 1);
         DPRINT(("called CPU%d for cleanup ret=%d\n", ctx->ctx_cpu, ret));
 }
 #endif /* CONFIG_SMP */
@@ -6508,7 +6508,7 @@ pfm_install_alt_pmu_interrupt(pfm_intr_handler_desc_t *hdl)
         }
 
         /* save the current system wide pmu states */
-        ret = on_each_cpu(pfm_alt_save_pmu_state, NULL, 0, 1);
+        ret = on_each_cpu(pfm_alt_save_pmu_state, NULL, 1);
         if (ret) {
                 DPRINT(("on_each_cpu() failed: %d\n", ret));
                 goto cleanup_reserve;
@@ -6553,7 +6553,7 @@ pfm_remove_alt_pmu_interrupt(pfm_intr_handler_desc_t *hdl)
 
         pfm_alt_intr_handler = NULL;
 
-        ret = on_each_cpu(pfm_alt_restore_pmu_state, NULL, 0, 1);
+        ret = on_each_cpu(pfm_alt_restore_pmu_state, NULL, 1);
         if (ret) {
                 DPRINT(("on_each_cpu() failed: %d\n", ret));
         }
diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c
index a3a34b4eb038..fabaf08d9a69 100644
--- a/arch/ia64/kernel/process.c
+++ b/arch/ia64/kernel/process.c
@@ -286,7 +286,7 @@ void cpu_idle_wait(void)
 {
         smp_mb();
         /* kick all the CPUs so that they exit out of pm_idle */
-        smp_call_function(do_nothing, NULL, 0, 1);
+        smp_call_function(do_nothing, NULL, 1);
 }
 EXPORT_SYMBOL_GPL(cpu_idle_wait);
 
diff --git a/arch/ia64/kernel/smp.c b/arch/ia64/kernel/smp.c
index 983296f1c813..3676468612b6 100644
--- a/arch/ia64/kernel/smp.c
+++ b/arch/ia64/kernel/smp.c
@@ -60,25 +60,9 @@ static struct local_tlb_flush_counts {
 
 static DEFINE_PER_CPU(unsigned int, shadow_flush_counts[NR_CPUS]) ____cacheline_aligned;
 
-
-/*
- * Structure and data for smp_call_function(). This is designed to minimise static memory
- * requirements. It also looks cleaner.
- */
-static  __cacheline_aligned DEFINE_SPINLOCK(call_lock);
-
-struct call_data_struct {
-        void (*func) (void *info);
-        void *info;
-        long wait;
-        atomic_t started;
-        atomic_t finished;
-};
-
-static volatile struct call_data_struct *call_data;
-
 #define IPI_CALL_FUNC           0
 #define IPI_CPU_STOP            1
+#define IPI_CALL_FUNC_SINGLE    2
 #define IPI_KDUMP_CPU_STOP      3
 
 /* This needs to be cacheline aligned because it is written to by *other* CPUs.  */
@@ -86,43 +70,6 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(u64, ipi_operation);
 
 extern void cpu_halt (void);
 
-void
-lock_ipi_calllock(void)
-{
-        spin_lock_irq(&call_lock);
-}
-
-void
-unlock_ipi_calllock(void)
-{
-        spin_unlock_irq(&call_lock);
-}
-
-static inline void
-handle_call_data(void)
-{
-        struct call_data_struct *data;
-        void (*func)(void *info);
-        void *info;
-        int wait;
-
-        /* release the 'pointer lock' */
-        data = (struct call_data_struct *)call_data;
-        func = data->func;
-        info = data->info;
-        wait = data->wait;
-
-        mb();
-        atomic_inc(&data->started);
-        /* At this point the structure may be gone unless wait is true. */
-        (*func)(info);
-
-        /* Notify the sending CPU that the task is done. */
-        mb();
-        if (wait)
-                atomic_inc(&data->finished);
-}
-
 static void
 stop_this_cpu(void)
 {
@@ -163,13 +110,15 @@ handle_IPI (int irq, void *dev_id)
                         ops &= ~(1 << which);
 
                         switch (which) {
-                        case IPI_CALL_FUNC:
-                                handle_call_data();
-                                break;
-
                         case IPI_CPU_STOP:
                                 stop_this_cpu();
                                 break;
+                        case IPI_CALL_FUNC:
+                                generic_smp_call_function_interrupt();
+                                break;
+                        case IPI_CALL_FUNC_SINGLE:
+                                generic_smp_call_function_single_interrupt();
+                                break;
 #ifdef CONFIG_KEXEC
                         case IPI_KDUMP_CPU_STOP:
                                 unw_init_running(kdump_cpu_freeze, NULL);
@@ -187,6 +136,8 @@ handle_IPI (int irq, void *dev_id)
         return IRQ_HANDLED;
 }
 
+
+
 /*
  * Called with preemption disabled.
  */
@@ -334,7 +285,7 @@ smp_flush_tlb_cpumask(cpumask_t xcpumask)
 void
 smp_flush_tlb_all (void)
 {
-        on_each_cpu((void (*)(void *))local_flush_tlb_all, NULL, 1, 1);
+        on_each_cpu((void (*)(void *))local_flush_tlb_all, NULL, 1);
 }
 
 void
@@ -357,193 +308,18 @@ smp_flush_tlb_mm (struct mm_struct *mm)
          * anyhow, and once a CPU is interrupted, the cost of local_flush_tlb_all() is
          * rather trivial.
          */
-        on_each_cpu((void (*)(void *))local_finish_flush_tlb_mm, mm, 1, 1);
+        on_each_cpu((void (*)(void *))local_finish_flush_tlb_mm, mm, 1);
 }
 
-/*
- * Run a function on a specific CPU
- *  <func>      The function to run. This must be fast and non-blocking.
- *  <info>      An arbitrary pointer to pass to the function.
- *  <nonatomic> Currently unused.
- *  <wait>      If true, wait until function has completed on other CPUs.
- *  [RETURNS]   0 on success, else a negative status code.
- *
- * Does not return until the remote CPU is nearly ready to execute <func>
- * or is or has executed.
- */
-
-int
-smp_call_function_single (int cpuid, void (*func) (void *info), void *info, int nonatomic,
-                          int wait)
-{
-        struct call_data_struct data;
-        int cpus = 1;
-        int me = get_cpu(); /* prevent preemption and reschedule on another processor */
-
-        if (cpuid == me) {
-                local_irq_disable();
-                func(info);
-                local_irq_enable();
-                put_cpu();
-                return 0;
-        }
-
-        data.func = func;
-        data.info = info;
-        atomic_set(&data.started, 0);
-        data.wait = wait;
-        if (wait)
-                atomic_set(&data.finished, 0);
-
-        spin_lock_bh(&call_lock);
-
-        call_data = &data;
-        mb();   /* ensure store to call_data precedes setting of IPI_CALL_FUNC */
-        send_IPI_single(cpuid, IPI_CALL_FUNC);
-
-        /* Wait for response */
-        while (atomic_read(&data.started) != cpus)
-                cpu_relax();
-
-        if (wait)
-                while (atomic_read(&data.finished) != cpus)
-                        cpu_relax();
-        call_data = NULL;
-
-        spin_unlock_bh(&call_lock);
-        put_cpu();
-        return 0;
-}
-EXPORT_SYMBOL(smp_call_function_single);
-
-/**
- * smp_call_function_mask(): Run a function on a set of other CPUs.
- * <mask>       The set of cpus to run on.  Must not include the current cpu.
- * <func>       The function to run. This must be fast and non-blocking.
- * <info>       An arbitrary pointer to pass to the function.
- * <wait>       If true, wait (atomically) until function
- *              has completed on other CPUs.
- *
- * Returns 0 on success, else a negative status code.
- *
- * If @wait is true, then returns once @func has returned; otherwise
- * it returns just before the target cpu calls @func.
- *
- * You must not call this function with disabled interrupts or from a
- * hardware interrupt handler or from a bottom half handler.
- */
-int smp_call_function_mask(cpumask_t mask,
-                           void (*func)(void *), void *info,
-                           int wait)
+void arch_send_call_function_single_ipi(int cpu)
 {
-        struct call_data_struct data;
-        cpumask_t allbutself;
-        int cpus;
-
-        spin_lock(&call_lock);
-        allbutself = cpu_online_map;
-        cpu_clear(smp_processor_id(), allbutself);
-
-        cpus_and(mask, mask, allbutself);
-        cpus = cpus_weight(mask);
-        if (!cpus) {
-                spin_unlock(&call_lock);
-                return 0;
-        }
-
-        /* Can deadlock when called with interrupts disabled */
-        WARN_ON(irqs_disabled());
-
-        data.func = func;
-        data.info = info;
-        atomic_set(&data.started, 0);
-        data.wait = wait;
-        if (wait)
-                atomic_set(&data.finished, 0);
-
-        call_data = &data;
-        mb(); /* ensure store to call_data precedes setting of IPI_CALL_FUNC*/
-
-        /* Send a message to other CPUs */
-        if (cpus_equal(mask, allbutself))
-                send_IPI_allbutself(IPI_CALL_FUNC);
-        else
-                send_IPI_mask(mask, IPI_CALL_FUNC);
-
-        /* Wait for response */
-        while (atomic_read(&data.started) != cpus)
-                cpu_relax();
-
-        if (wait)
-                while (atomic_read(&data.finished) != cpus)
-                        cpu_relax();
-        call_data = NULL;
-
-        spin_unlock(&call_lock);
-        return 0;
-
+        send_IPI_single(cpu, IPI_CALL_FUNC_SINGLE);
 }
-EXPORT_SYMBOL(smp_call_function_mask);
 
-/*
- * this function sends a 'generic call function' IPI to all other CPUs
- * in the system.
- */
-
-/*
- *  [SUMMARY]   Run a function on all other CPUs.
- *  <func>      The function to run. This must be fast and non-blocking.
- *  <info>      An arbitrary pointer to pass to the function.
- *  <nonatomic> currently unused.
- *  <wait>      If true, wait (atomically) until function has completed on other CPUs.
- *  [RETURNS]   0 on success, else a negative status code.
- *
- * Does not return until remote CPUs are nearly ready to execute <func> or are or have
- * executed.
- *
- * You must not call this function with disabled interrupts or from a
- * hardware interrupt handler or from a bottom half handler.
- */
-int
-smp_call_function (void (*func) (void *info), void *info, int nonatomic, int wait)
+void arch_send_call_function_ipi(cpumask_t mask)
 {
-        struct call_data_struct data;
-        int cpus;
-
-        spin_lock(&call_lock);
-        cpus = num_online_cpus() - 1;
-        if (!cpus) {
-                spin_unlock(&call_lock);
-                return 0;
-        }
-
-        /* Can deadlock when called with interrupts disabled */
-        WARN_ON(irqs_disabled());
-
-        data.func = func;
-        data.info = info;
-        atomic_set(&data.started, 0);
-        data.wait = wait;
-        if (wait)
-                atomic_set(&data.finished, 0);
-
-        call_data = &data;
-        mb();   /* ensure store to call_data precedes setting of IPI_CALL_FUNC */
-        send_IPI_allbutself(IPI_CALL_FUNC);
-
-        /* Wait for response */
-        while (atomic_read(&data.started) != cpus)
-                cpu_relax();
-
-        if (wait)
-                while (atomic_read(&data.finished) != cpus)
-                        cpu_relax();
-        call_data = NULL;
-
-        spin_unlock(&call_lock);
-        return 0;
+        send_IPI_mask(mask, IPI_CALL_FUNC);
 }
-EXPORT_SYMBOL(smp_call_function);
 
 /*
  * this function calls the 'stop' function on all other CPUs in the system.
diff --git a/arch/ia64/kernel/smpboot.c b/arch/ia64/kernel/smpboot.c
index d7ad42b77d41..9d1d429c6c59 100644
--- a/arch/ia64/kernel/smpboot.c
+++ b/arch/ia64/kernel/smpboot.c
@@ -317,7 +317,7 @@ ia64_sync_itc (unsigned int master)
 
         go[MASTER] = 1;
 
-        if (smp_call_function_single(master, sync_master, NULL, 1, 0) < 0) {
+        if (smp_call_function_single(master, sync_master, NULL, 0) < 0) {
                 printk(KERN_ERR "sync_itc: failed to get attention of CPU %u!\n", master);
                 return;
         }
@@ -395,14 +395,14 @@ smp_callin (void)
 
         fix_b0_for_bsp();
 
-        lock_ipi_calllock();
+        ipi_call_lock_irq();
         spin_lock(&vector_lock);
         /* Setup the per cpu irq handling data structures */
         __setup_vector_irq(cpuid);
         cpu_set(cpuid, cpu_online_map);
         per_cpu(cpu_state, cpuid) = CPU_ONLINE;
         spin_unlock(&vector_lock);
-        unlock_ipi_calllock();
+        ipi_call_unlock_irq();
 
         smp_setup_percpu_timer();
 
diff --git a/arch/ia64/kernel/uncached.c b/arch/ia64/kernel/uncached.c
index e77995a6e3ed..8eff8c1d40a6 100644
--- a/arch/ia64/kernel/uncached.c
+++ b/arch/ia64/kernel/uncached.c
@@ -123,8 +123,7 @@ static int uncached_add_chunk(struct uncached_pool *uc_pool, int nid)
         status = ia64_pal_prefetch_visibility(PAL_VISIBILITY_PHYSICAL);
         if (status == PAL_VISIBILITY_OK_REMOTE_NEEDED) {
                 atomic_set(&uc_pool->status, 0);
-                status = smp_call_function(uncached_ipi_visibility, uc_pool,
-                                           0, 1);
+                status = smp_call_function(uncached_ipi_visibility, uc_pool, 1);
                 if (status || atomic_read(&uc_pool->status))
                         goto failed;
         } else if (status != PAL_VISIBILITY_OK)
@@ -146,7 +145,7 @@ static int uncached_add_chunk(struct uncached_pool *uc_pool, int nid)
         if (status != PAL_STATUS_SUCCESS)
                 goto failed;
         atomic_set(&uc_pool->status, 0);
-        status = smp_call_function(uncached_ipi_mc_drain, uc_pool, 0, 1);
+        status = smp_call_function(uncached_ipi_mc_drain, uc_pool, 1);
         if (status || atomic_read(&uc_pool->status))
                 goto failed;
 
diff --git a/arch/ia64/sn/kernel/sn2/sn_hwperf.c b/arch/ia64/sn/kernel/sn2/sn_hwperf.c
index 8cc0c4753d89..636588e7e068 100644
--- a/arch/ia64/sn/kernel/sn2/sn_hwperf.c
+++ b/arch/ia64/sn/kernel/sn2/sn_hwperf.c
@@ -629,7 +629,7 @@ static int sn_hwperf_op_cpu(struct sn_hwperf_op_info *op_info)
                 if (use_ipi) {
                         /* use an interprocessor interrupt to call SAL */
                         smp_call_function_single(cpu, sn_hwperf_call_sal,
-                                op_info, 1, 1);
+                                op_info, 1);
                 }
                 else {
                         /* migrate the task before calling SAL */