8 files changed, 159 insertions, 97 deletions

diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
index cf02cad62d9a..d238c082c3c5 100644
--- a/arch/powerpc/kernel/dma.c
+++ b/arch/powerpc/kernel/dma.c
@@ -179,3 +179,21 @@ static int __init dma_init(void)
        return 0;
 }
 fs_initcall(dma_init);
+
+int dma_mmap_coherent(struct device *dev, struct vm_area_struct *vma,
+                      void *cpu_addr, dma_addr_t handle, size_t size)
+{
+        unsigned long pfn;
+
+#ifdef CONFIG_NOT_COHERENT_CACHE
+        vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+        pfn = __dma_get_coherent_pfn((unsigned long)cpu_addr);
+#else
+        pfn = page_to_pfn(virt_to_page(cpu_addr));
+#endif
+        return remap_pfn_range(vma, vma->vm_start,
+                               pfn + vma->vm_pgoff,
+                               vma->vm_end - vma->vm_start,
+                               vma->vm_page_prot);
+}
+EXPORT_SYMBOL_GPL(dma_mmap_coherent);
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 8a817995b4cd..c532cb2c927a 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -977,20 +977,6 @@ _GLOBAL(do_stab_bolted)
         rfid
         b       .       /* prevent speculative execution */
 
-/*
- * Space for CPU0's segment table.
- *
- * On iSeries, the hypervisor must fill in at least one entry before
- * we get control (with relocate on).  The address is given to the hv
- * as a page number (see xLparMap below), so this must be at a
- * fixed address (the linker can't compute (u64)&initial_stab >>
- * PAGE_SHIFT).
- */
-        . = STAB0_OFFSET        /* 0x6000 */
-        .globl initial_stab
-initial_stab:
-        .space  4096
-
 #ifdef CONFIG_PPC_PSERIES
 /*
  * Data area reserved for FWNMI option.
@@ -1027,3 +1013,17 @@ xLparMap:
 #ifdef CONFIG_PPC_PSERIES
         . = 0x8000
 #endif /* CONFIG_PPC_PSERIES */
+
+/*
+ * Space for CPU0's segment table.
+ *
+ * On iSeries, the hypervisor must fill in at least one entry before
+ * we get control (with relocate on).  The address is given to the hv
+ * as a page number (see xLparMap above), so this must be at a
+ * fixed address (the linker can't compute (u64)&initial_stab >>
+ * PAGE_SHIFT).
+ */
+        . = STAB0_OFFSET        /* 0x8000 */
+        .globl initial_stab
+initial_stab:
+        .space  4096
diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S
index 98c4b29a56f4..c5c24beb8387 100644
--- a/arch/powerpc/kernel/head_32.S
+++ b/arch/powerpc/kernel/head_32.S
@@ -890,6 +890,15 @@ __secondary_start:
         mtspr   SPRN_SRR1,r4
         SYNC
         RFI
+
+_GLOBAL(start_secondary_resume)
+        /* Reset stack */
+        rlwinm  r1,r1,0,0,(31-THREAD_SHIFT)     /* current_thread_info() */
+        addi    r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD
+        li      r3,0
+        std     r3,0(r1)                /* Zero the stack frame pointer */
+        bl      start_secondary
+        b       .
 #endif /* CONFIG_SMP */
 
 #ifdef CONFIG_KVM_BOOK3S_HANDLER
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index 782f23df7c85..271140b38b6f 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -536,6 +536,13 @@ _GLOBAL(pmac_secondary_start)
         add     r13,r13,r4              /* for this processor.          */
         mtspr   SPRN_SPRG_PACA,r13      /* Save vaddr of paca in an SPRG*/
 
+        /* Mark interrupts soft and hard disabled (they might be enabled
+         * in the PACA when doing hotplug)
+         */
+        li      r0,0
+        stb     r0,PACASOFTIRQEN(r13)
+        stb     r0,PACAHARDIRQEN(r13)
+
         /* Create a temp kernel stack for use before relocation is on.  */
         ld      r1,PACAEMERGSP(r13)
         subi    r1,r1,STACK_FRAME_OVERHEAD
diff --git a/arch/powerpc/kernel/idle_power4.S b/arch/powerpc/kernel/idle_power4.S
index 5328709eeedc..ba3195478600 100644
--- a/arch/powerpc/kernel/idle_power4.S
+++ b/arch/powerpc/kernel/idle_power4.S
@@ -53,24 +53,3 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
         isync
         b       1b
 
-_GLOBAL(power4_cpu_offline_powersave)
-        /* Go to NAP now */
-        mfmsr   r7
-        rldicl  r0,r7,48,1
-        rotldi  r0,r0,16
-        mtmsrd  r0,1                    /* hard-disable interrupts */
-        li      r0,1
-        li      r6,0
-        stb     r0,PACAHARDIRQEN(r13)   /* we'll hard-enable shortly */
-        stb     r6,PACASOFTIRQEN(r13)   /* soft-disable irqs */
-BEGIN_FTR_SECTION
-        DSSALL
-        sync
-END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
-        ori     r7,r7,MSR_EE
-        oris    r7,r7,MSR_POW@h
-        sync
-        isync
-        mtmsrd  r7
-        isync
-        blr
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 63625e0650b5..f621b7d2d869 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -246,12 +246,13 @@ u64 arch_irq_stat_cpu(unsigned int cpu)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-void fixup_irqs(const struct cpumask *map)
+void migrate_irqs(void)
 {
         struct irq_desc *desc;
         unsigned int irq;
         static int warned;
         cpumask_var_t mask;
+        const struct cpumask *map = cpu_online_mask;
 
         alloc_cpumask_var(&mask, GFP_KERNEL);
 
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 981360509172..cbdbb14be4b0 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -57,6 +57,25 @@
 #define DBG(fmt...)
 #endif
 
+
+/* Store all idle threads, this can be reused instead of creating
+* a new thread. Also avoids complicated thread destroy functionality
+* for idle threads.
+*/
+#ifdef CONFIG_HOTPLUG_CPU
+/*
+ * Needed only for CONFIG_HOTPLUG_CPU because __cpuinitdata is
+ * removed after init for !CONFIG_HOTPLUG_CPU.
+ */
+static DEFINE_PER_CPU(struct task_struct *, idle_thread_array);
+#define get_idle_for_cpu(x)      (per_cpu(idle_thread_array, x))
+#define set_idle_for_cpu(x, p)   (per_cpu(idle_thread_array, x) = (p))
+#else
+static struct task_struct *idle_thread_array[NR_CPUS] __cpuinitdata ;
+#define get_idle_for_cpu(x)      (idle_thread_array[(x)])
+#define set_idle_for_cpu(x, p)   (idle_thread_array[(x)] = (p))
+#endif
+
 struct thread_info *secondary_ti;
 
 DEFINE_PER_CPU(cpumask_var_t, cpu_sibling_map);
@@ -238,23 +257,6 @@ static void __devinit smp_store_cpu_info(int id)
         per_cpu(cpu_pvr, id) = mfspr(SPRN_PVR);
 }
 
-static void __init smp_create_idle(unsigned int cpu)
-{
-        struct task_struct *p;
-
-        /* create a process for the processor */
-        p = fork_idle(cpu);
-        if (IS_ERR(p))
-                panic("failed fork for CPU %u: %li", cpu, PTR_ERR(p));
-#ifdef CONFIG_PPC64
-        paca[cpu].__current = p;
-        paca[cpu].kstack = (unsigned long) task_thread_info(p)
-                + THREAD_SIZE - STACK_FRAME_OVERHEAD;
-#endif
-        current_set[cpu] = task_thread_info(p);
-        task_thread_info(p)->cpu = cpu;
-}
-
 void __init smp_prepare_cpus(unsigned int max_cpus)
 {
         unsigned int cpu;
@@ -288,10 +290,6 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
                         max_cpus = NR_CPUS;
         else
                 max_cpus = 1;
-
-        for_each_possible_cpu(cpu)
-                if (cpu != boot_cpuid)
-                        smp_create_idle(cpu);
 }
 
 void __devinit smp_prepare_boot_cpu(void)
@@ -305,7 +303,7 @@ void __devinit smp_prepare_boot_cpu(void)
 
 #ifdef CONFIG_HOTPLUG_CPU
 /* State of each CPU during hotplug phases */
-DEFINE_PER_CPU(int, cpu_state) = { 0 };
+static DEFINE_PER_CPU(int, cpu_state) = { 0 };
 
 int generic_cpu_disable(void)
 {
@@ -317,30 +315,8 @@ int generic_cpu_disable(void)
         set_cpu_online(cpu, false);
 #ifdef CONFIG_PPC64
         vdso_data->processorCount--;
-        fixup_irqs(cpu_online_mask);
-#endif
-        return 0;
-}
-
-int generic_cpu_enable(unsigned int cpu)
-{
-        /* Do the normal bootup if we haven't
-         * already bootstrapped. */
-        if (system_state != SYSTEM_RUNNING)
-                return -ENOSYS;
-
-        /* get the target out of it's holding state */
-        per_cpu(cpu_state, cpu) = CPU_UP_PREPARE;
-        smp_wmb();
-
-        while (!cpu_online(cpu))
-                cpu_relax();
-
-#ifdef CONFIG_PPC64
-        fixup_irqs(cpu_online_mask);
-        /* counter the irq disable in fixup_irqs */
-        local_irq_enable();
 #endif
+        migrate_irqs();
         return 0;
 }
 
@@ -362,37 +338,89 @@ void generic_mach_cpu_die(void)
         unsigned int cpu;
 
         local_irq_disable();
+        idle_task_exit();
         cpu = smp_processor_id();
         printk(KERN_DEBUG "CPU%d offline\n", cpu);
         __get_cpu_var(cpu_state) = CPU_DEAD;
         smp_wmb();
         while (__get_cpu_var(cpu_state) != CPU_UP_PREPARE)
                 cpu_relax();
-        set_cpu_online(cpu, true);
-        local_irq_enable();
+}
+
+void generic_set_cpu_dead(unsigned int cpu)
+{
+        per_cpu(cpu_state, cpu) = CPU_DEAD;
 }
 #endif
 
-static int __devinit cpu_enable(unsigned int cpu)
+struct create_idle {
+        struct work_struct work;
+        struct task_struct *idle;
+        struct completion done;
+        int cpu;
+};
+
+static void __cpuinit do_fork_idle(struct work_struct *work)
 {
-        if (smp_ops && smp_ops->cpu_enable)
-                return smp_ops->cpu_enable(cpu);
+        struct create_idle *c_idle =
+                container_of(work, struct create_idle, work);
+
+        c_idle->idle = fork_idle(c_idle->cpu);
+        complete(&c_idle->done);
+}
+
+static int __cpuinit create_idle(unsigned int cpu)
+{
+        struct thread_info *ti;
+        struct create_idle c_idle = {
+                .cpu    = cpu,
+                .done   = COMPLETION_INITIALIZER_ONSTACK(c_idle.done),
+        };
+        INIT_WORK_ONSTACK(&c_idle.work, do_fork_idle);
+
+        c_idle.idle = get_idle_for_cpu(cpu);
+
+        /* We can't use kernel_thread since we must avoid to
+         * reschedule the child. We use a workqueue because
+         * we want to fork from a kernel thread, not whatever
+         * userspace process happens to be trying to online us.
+         */
+        if (!c_idle.idle) {
+                schedule_work(&c_idle.work);
+                wait_for_completion(&c_idle.done);
+        } else
+                init_idle(c_idle.idle, cpu);
+        if (IS_ERR(c_idle.idle)) {              
+                pr_err("Failed fork for CPU %u: %li", cpu, PTR_ERR(c_idle.idle));
+                return PTR_ERR(c_idle.idle);
+        }
+        ti = task_thread_info(c_idle.idle);
+
+#ifdef CONFIG_PPC64
+        paca[cpu].__current = c_idle.idle;
+        paca[cpu].kstack = (unsigned long)ti + THREAD_SIZE - STACK_FRAME_OVERHEAD;
+#endif
+        ti->cpu = cpu;
+        current_set[cpu] = ti;
 
-        return -ENOSYS;
+        return 0;
 }
 
 int __cpuinit __cpu_up(unsigned int cpu)
 {
-        int c;
+        int rc, c;
 
         secondary_ti = current_set[cpu];
-        if (!cpu_enable(cpu))
-                return 0;
 
         if (smp_ops == NULL ||
             (smp_ops->cpu_bootable && !smp_ops->cpu_bootable(cpu)))
                 return -EINVAL;
 
+        /* Make sure we have an idle thread */
+        rc = create_idle(cpu);
+        if (rc)
+                return rc;
+
         /* Make sure callin-map entry is 0 (can be leftover a CPU
          * hotplug
          */
@@ -502,7 +530,7 @@ static struct device_node *cpu_to_l2cache(int cpu)
 }
 
 /* Activate a secondary processor. */
-int __devinit start_secondary(void *unused)
+void __devinit start_secondary(void *unused)
 {
         unsigned int cpu = smp_processor_id();
         struct device_node *l2_cache;
@@ -523,6 +551,10 @@ int __devinit start_secondary(void *unused)
 
         secondary_cpu_time_init();
 
+#ifdef CONFIG_PPC64
+        if (system_state == SYSTEM_RUNNING)
+                vdso_data->processorCount++;
+#endif
         ipi_call_lock();
         notify_cpu_starting(cpu);
         set_cpu_online(cpu, true);
@@ -558,7 +590,8 @@ int __devinit start_secondary(void *unused)
         local_irq_enable();
 
         cpu_idle();
-        return 0;
+
+        BUG();
 }
 
 int setup_profiling_timer(unsigned int multiplier)
@@ -585,7 +618,11 @@ void __init smp_cpus_done(unsigned int max_cpus)
 
         free_cpumask_var(old_mask);
 
+        if (smp_ops && smp_ops->bringup_done)
+                smp_ops->bringup_done();
+
         dump_numa_cpu_topology();
+
 }
 
 int arch_sd_sibling_asym_packing(void)
@@ -660,5 +697,9 @@ void cpu_die(void)
 {
         if (ppc_md.cpu_die)
                 ppc_md.cpu_die();
+
+        /* If we return, we re-enter start_secondary */
+        start_secondary_resume();
 }
+
 #endif
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 09d31dbf43f9..375480c56eb9 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -356,7 +356,7 @@ void account_system_vtime(struct task_struct *tsk)
         }
         get_paca()->user_time_scaled += user_scaled;
 
-        if (in_irq() || idle_task(smp_processor_id()) != tsk) {
+        if (in_interrupt() || idle_task(smp_processor_id()) != tsk) {
                 account_system_time(tsk, 0, delta, sys_scaled);
                 if (stolen)
                         account_steal_time(stolen);
@@ -577,14 +577,21 @@ void timer_interrupt(struct pt_regs * regs)
         struct clock_event_device *evt = &decrementer->event;
         u64 now;
 
+        /* Ensure a positive value is written to the decrementer, or else
+         * some CPUs will continue to take decrementer exceptions.
+         */
+        set_dec(DECREMENTER_MAX);
+
+        /* Some implementations of hotplug will get timer interrupts while
+         * offline, just ignore these
+         */
+        if (!cpu_online(smp_processor_id()))
+                return;
+
         trace_timer_interrupt_entry(regs);
 
         __get_cpu_var(irq_stat).timer_irqs++;
 
-        /* Ensure a positive value is written to the decrementer, or else
-         * some CPUs will continuue to take decrementer exceptions */
-        set_dec(DECREMENTER_MAX);
-
 #if defined(CONFIG_PPC32) && defined(CONFIG_PMAC)
         if (atomic_read(&ppc_n_lost_interrupts) != 0)
                 do_IRQ(regs);