9 files changed, 334 insertions, 40 deletions

diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index 11a5197a221f..ff89d0b3abc5 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -22,6 +22,8 @@ obj-$(CONFIG_ARTHUR)		+= arthur.o
 obj-$(CONFIG_ISA_DMA)           += dma-isa.o
 obj-$(CONFIG_PCI)               += bios32.o isa.o
 obj-$(CONFIG_SMP)               += smp.o
+obj-$(CONFIG_HAVE_ARM_SCU)      += smp_scu.o
+obj-$(CONFIG_HAVE_ARM_TWD)      += smp_twd.o
 obj-$(CONFIG_DYNAMIC_FTRACE)    += ftrace.o
 obj-$(CONFIG_KEXEC)             += machine_kexec.o relocate_kernel.o
 obj-$(CONFIG_KPROBES)           += kprobes.o kprobes-decode.o
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index 83b1da6b7baa..fc8af43c5000 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -482,6 +482,9 @@ __und_usr:
         subeq   r4, r2, #4                      @ ARM instr at LR - 4
         subne   r4, r2, #2                      @ Thumb instr at LR - 2
 1:      ldreqt  r0, [r4]
+#ifdef CONFIG_CPU_ENDIAN_BE8
+        reveq   r0, r0                          @ little endian instruction
+#endif
         beq     call_fpe
         @ Thumb instruction
 #if __LINUX_ARM_ARCH__ >= 7
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index b55cb0331809..366e5097a41a 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -210,6 +210,9 @@ ENTRY(vector_swi)
   A710( teq     ip, #0x0f000000                                         )
   A710( bne     .Larm710bug                                             )
 #endif
+#ifdef CONFIG_CPU_ENDIAN_BE8
+        rev     r10, r10                        @ little endian instruction
+#endif
 
 #elif defined(CONFIG_AEABI)
 
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index c3265a2e7cd4..1585423699ee 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -365,7 +365,7 @@ pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags)
         regs.ARM_r2 = (unsigned long)fn;
         regs.ARM_r3 = (unsigned long)do_exit;
         regs.ARM_pc = (unsigned long)kernel_thread_helper;
-        regs.ARM_cpsr = SVC_MODE;
+        regs.ARM_cpsr = SVC_MODE | PSR_ENDSTATE;
 
         return do_fork(flags|CLONE_VM|CLONE_UNTRACED, 0, &regs, 0, NULL, NULL);
 }
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index 80b8b5c7e07a..442b87476f97 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -426,9 +426,13 @@ setup_return(struct pt_regs *regs, struct k_sigaction *ka,
                  */
                 thumb = handler & 1;
 
-                if (thumb)
+                if (thumb) {
                         cpsr |= PSR_T_BIT;
-                else
+#if __LINUX_ARM_ARCH__ >= 7
+                        /* clear the If-Then Thumb-2 execution state */
+                        cpsr &= ~PSR_IT_MASK;
+#endif
+                } else
                         cpsr &= ~PSR_T_BIT;
         }
 #endif
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 6014dfd22af4..de885fd256c5 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -22,16 +22,20 @@
 #include <linux/smp.h>
 #include <linux/seq_file.h>
 #include <linux/irq.h>
+#include <linux/percpu.h>
+#include <linux/clockchips.h>
 
 #include <asm/atomic.h>
 #include <asm/cacheflush.h>
 #include <asm/cpu.h>
+#include <asm/cputype.h>
 #include <asm/mmu_context.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <asm/processor.h>
 #include <asm/tlbflush.h>
 #include <asm/ptrace.h>
+#include <asm/localtimer.h>
 
 /*
  * as from 2.5, kernels no longer have an init_tasks structure
@@ -163,7 +167,7 @@ int __cpuexit __cpu_disable(void)
          * Take this CPU offline.  Once we clear this, we can't return,
          * and we must not schedule until we're ready to give up the cpu.
          */
-        cpu_clear(cpu, cpu_online_map);
+        set_cpu_online(cpu, false);
 
         /*
          * OK - migrate IRQs away from this CPU
@@ -274,9 +278,9 @@ asmlinkage void __cpuinit secondary_start_kernel(void)
         local_fiq_enable();
 
         /*
-         * Setup local timer for this CPU.
+         * Setup the percpu timer for this CPU.
          */
-        local_timer_setup();
+        percpu_timer_setup();
 
         calibrate_delay();
 
@@ -285,7 +289,7 @@ asmlinkage void __cpuinit secondary_start_kernel(void)
         /*
          * OK, now it's safe to let the boot CPU continue
          */
-        cpu_set(cpu, cpu_online_map);
+        set_cpu_online(cpu, true);
 
         /*
          * OK, it's off to the idle thread for us
@@ -383,10 +387,16 @@ void show_local_irqs(struct seq_file *p)
         seq_putc(p, '\n');
 }
 
+/*
+ * Timer (local or broadcast) support
+ */
+static DEFINE_PER_CPU(struct clock_event_device, percpu_clockevent);
+
 static void ipi_timer(void)
 {
+        struct clock_event_device *evt = &__get_cpu_var(percpu_clockevent);
         irq_enter();
-        local_timer_interrupt();
+        evt->event_handler(evt);
         irq_exit();
 }
 
@@ -405,6 +415,42 @@ asmlinkage void __exception do_local_timer(struct pt_regs *regs)
 }
 #endif
 
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+static void smp_timer_broadcast(const struct cpumask *mask)
+{
+        send_ipi_message(mask, IPI_TIMER);
+}
+
+static void broadcast_timer_set_mode(enum clock_event_mode mode,
+        struct clock_event_device *evt)
+{
+}
+
+static void local_timer_setup(struct clock_event_device *evt)
+{
+        evt->name       = "dummy_timer";
+        evt->features   = CLOCK_EVT_FEAT_ONESHOT |
+                          CLOCK_EVT_FEAT_PERIODIC |
+                          CLOCK_EVT_FEAT_DUMMY;
+        evt->rating     = 400;
+        evt->mult       = 1;
+        evt->set_mode   = broadcast_timer_set_mode;
+        evt->broadcast  = smp_timer_broadcast;
+
+        clockevents_register_device(evt);
+}
+#endif
+
+void __cpuinit percpu_timer_setup(void)
+{
+        unsigned int cpu = smp_processor_id();
+        struct clock_event_device *evt = &per_cpu(percpu_clockevent, cpu);
+
+        evt->cpumask = cpumask_of(cpu);
+
+        local_timer_setup(evt);
+}
+
 static DEFINE_SPINLOCK(stop_lock);
 
 /*
@@ -417,7 +463,7 @@ static void ipi_cpu_stop(unsigned int cpu)
         dump_stack();
         spin_unlock(&stop_lock);
 
-        cpu_clear(cpu, cpu_online_map);
+        set_cpu_online(cpu, false);
 
         local_fiq_disable();
         local_irq_disable();
@@ -501,11 +547,6 @@ void smp_send_reschedule(int cpu)
         send_ipi_message(cpumask_of(cpu), IPI_RESCHEDULE);
 }
 
-void smp_timer_broadcast(const struct cpumask *mask)
-{
-        send_ipi_message(mask, IPI_TIMER);
-}
-
 void smp_send_stop(void)
 {
         cpumask_t mask = cpu_online_map;
@@ -545,6 +586,12 @@ struct tlb_args {
         unsigned long ta_end;
 };
 
+/* all SMP configurations have the extended CPUID registers */
+static inline int tlb_ops_need_broadcast(void)
+{
+        return ((read_cpuid_ext(CPUID_EXT_MMFR3) >> 12) & 0xf) < 2;
+}
+
 static inline void ipi_flush_tlb_all(void *ignored)
 {
         local_flush_tlb_all();
@@ -587,51 +634,61 @@ static inline void ipi_flush_tlb_kernel_range(void *arg)
 
 void flush_tlb_all(void)
 {
-        on_each_cpu(ipi_flush_tlb_all, NULL, 1);
+        if (tlb_ops_need_broadcast())
+                on_each_cpu(ipi_flush_tlb_all, NULL, 1);
+        else
+                local_flush_tlb_all();
 }
 
 void flush_tlb_mm(struct mm_struct *mm)
 {
-        on_each_cpu_mask(ipi_flush_tlb_mm, mm, 1, &mm->cpu_vm_mask);
+        if (tlb_ops_need_broadcast())
+                on_each_cpu_mask(ipi_flush_tlb_mm, mm, 1, &mm->cpu_vm_mask);
+        else
+                local_flush_tlb_mm(mm);
 }
 
 void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
 {
-        struct tlb_args ta;
-
-        ta.ta_vma = vma;
-        ta.ta_start = uaddr;
-
-        on_each_cpu_mask(ipi_flush_tlb_page, &ta, 1, &vma->vm_mm->cpu_vm_mask);
+        if (tlb_ops_need_broadcast()) {
+                struct tlb_args ta;
+                ta.ta_vma = vma;
+                ta.ta_start = uaddr;
+                on_each_cpu_mask(ipi_flush_tlb_page, &ta, 1, &vma->vm_mm->cpu_vm_mask);
+        } else
+                local_flush_tlb_page(vma, uaddr);
 }
 
 void flush_tlb_kernel_page(unsigned long kaddr)
 {
-        struct tlb_args ta;
-
-        ta.ta_start = kaddr;
-
-        on_each_cpu(ipi_flush_tlb_kernel_page, &ta, 1);
+        if (tlb_ops_need_broadcast()) {
+                struct tlb_args ta;
+                ta.ta_start = kaddr;
+                on_each_cpu(ipi_flush_tlb_kernel_page, &ta, 1);
+        } else
+                local_flush_tlb_kernel_page(kaddr);
 }
 
 void flush_tlb_range(struct vm_area_struct *vma,
                      unsigned long start, unsigned long end)
 {
-        struct tlb_args ta;
-
-        ta.ta_vma = vma;
-        ta.ta_start = start;
-        ta.ta_end = end;
-
-        on_each_cpu_mask(ipi_flush_tlb_range, &ta, 1, &vma->vm_mm->cpu_vm_mask);
+        if (tlb_ops_need_broadcast()) {
+                struct tlb_args ta;
+                ta.ta_vma = vma;
+                ta.ta_start = start;
+                ta.ta_end = end;
+                on_each_cpu_mask(ipi_flush_tlb_range, &ta, 1, &vma->vm_mm->cpu_vm_mask);
+        } else
+                local_flush_tlb_range(vma, start, end);
 }
 
 void flush_tlb_kernel_range(unsigned long start, unsigned long end)
 {
-        struct tlb_args ta;
-
-        ta.ta_start = start;
-        ta.ta_end = end;
-
-        on_each_cpu(ipi_flush_tlb_kernel_range, &ta, 1);
+        if (tlb_ops_need_broadcast()) {
+                struct tlb_args ta;
+                ta.ta_start = start;
+                ta.ta_end = end;
+                on_each_cpu(ipi_flush_tlb_kernel_range, &ta, 1);
+        } else
+                local_flush_tlb_kernel_range(start, end);
 }
diff --git a/arch/arm/kernel/smp_scu.c b/arch/arm/kernel/smp_scu.c
new file mode 100644
index 000000000000..d3831f616ee9
--- /dev/null
+++ b/arch/arm/kernel/smp_scu.c
@@ -0,0 +1,48 @@
+/*
+ *  linux/arch/arm/kernel/smp_scu.c
+ *
+ *  Copyright (C) 2002 ARM Ltd.
+ *  All Rights Reserved
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/init.h>
+#include <linux/io.h>
+
+#include <asm/smp_scu.h>
+#include <asm/cacheflush.h>
+
+#define SCU_CTRL                0x00
+#define SCU_CONFIG              0x04
+#define SCU_CPU_STATUS          0x08
+#define SCU_INVALIDATE          0x0c
+#define SCU_FPGA_REVISION       0x10
+
+/*
+ * Get the number of CPU cores from the SCU configuration
+ */
+unsigned int __init scu_get_core_count(void __iomem *scu_base)
+{
+        unsigned int ncores = __raw_readl(scu_base + SCU_CONFIG);
+        return (ncores & 0x03) + 1;
+}
+
+/*
+ * Enable the SCU
+ */
+void __init scu_enable(void __iomem *scu_base)
+{
+        u32 scu_ctrl;
+
+        scu_ctrl = __raw_readl(scu_base + SCU_CTRL);
+        scu_ctrl |= 1;
+        __raw_writel(scu_ctrl, scu_base + SCU_CTRL);
+
+        /*
+         * Ensure that the data accessed by CPU0 before the SCU was
+         * initialised is visible to the other CPUs.
+         */
+        flush_cache_all();
+}
diff --git a/arch/arm/kernel/smp_twd.c b/arch/arm/kernel/smp_twd.c
new file mode 100644
index 000000000000..d8c88c633c6f
--- /dev/null
+++ b/arch/arm/kernel/smp_twd.c
@@ -0,0 +1,175 @@
+/*
+ *  linux/arch/arm/kernel/smp_twd.c
+ *
+ *  Copyright (C) 2002 ARM Ltd.
+ *  All Rights Reserved
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/smp.h>
+#include <linux/jiffies.h>
+#include <linux/clockchips.h>
+#include <linux/irq.h>
+#include <linux/io.h>
+
+#include <asm/smp_twd.h>
+#include <asm/hardware/gic.h>
+
+#define TWD_TIMER_LOAD                  0x00
+#define TWD_TIMER_COUNTER               0x04
+#define TWD_TIMER_CONTROL               0x08
+#define TWD_TIMER_INTSTAT               0x0C
+
+#define TWD_WDOG_LOAD                   0x20
+#define TWD_WDOG_COUNTER                0x24
+#define TWD_WDOG_CONTROL                0x28
+#define TWD_WDOG_INTSTAT                0x2C
+#define TWD_WDOG_RESETSTAT              0x30
+#define TWD_WDOG_DISABLE                0x34
+
+#define TWD_TIMER_CONTROL_ENABLE        (1 << 0)
+#define TWD_TIMER_CONTROL_ONESHOT       (0 << 1)
+#define TWD_TIMER_CONTROL_PERIODIC      (1 << 1)
+#define TWD_TIMER_CONTROL_IT_ENABLE     (1 << 2)
+
+/* set up by the platform code */
+void __iomem *twd_base;
+
+static unsigned long twd_timer_rate;
+
+static void twd_set_mode(enum clock_event_mode mode,
+                        struct clock_event_device *clk)
+{
+        unsigned long ctrl;
+
+        switch (mode) {
+        case CLOCK_EVT_MODE_PERIODIC:
+                /* timer load already set up */
+                ctrl = TWD_TIMER_CONTROL_ENABLE | TWD_TIMER_CONTROL_IT_ENABLE
+                        | TWD_TIMER_CONTROL_PERIODIC;
+                break;
+        case CLOCK_EVT_MODE_ONESHOT:
+                /* period set, and timer enabled in 'next_event' hook */
+                ctrl = TWD_TIMER_CONTROL_IT_ENABLE | TWD_TIMER_CONTROL_ONESHOT;
+                break;
+        case CLOCK_EVT_MODE_UNUSED:
+        case CLOCK_EVT_MODE_SHUTDOWN:
+        default:
+                ctrl = 0;
+        }
+
+        __raw_writel(ctrl, twd_base + TWD_TIMER_CONTROL);
+}
+
+static int twd_set_next_event(unsigned long evt,
+                        struct clock_event_device *unused)
+{
+        unsigned long ctrl = __raw_readl(twd_base + TWD_TIMER_CONTROL);
+
+        ctrl |= TWD_TIMER_CONTROL_ENABLE;
+
+        __raw_writel(evt, twd_base + TWD_TIMER_COUNTER);
+        __raw_writel(ctrl, twd_base + TWD_TIMER_CONTROL);
+
+        return 0;
+}
+
+/*
+ * local_timer_ack: checks for a local timer interrupt.
+ *
+ * If a local timer interrupt has occurred, acknowledge and return 1.
+ * Otherwise, return 0.
+ */
+int twd_timer_ack(void)
+{
+        if (__raw_readl(twd_base + TWD_TIMER_INTSTAT)) {
+                __raw_writel(1, twd_base + TWD_TIMER_INTSTAT);
+                return 1;
+        }
+
+        return 0;
+}
+
+static void __cpuinit twd_calibrate_rate(void)
+{
+        unsigned long load, count;
+        u64 waitjiffies;
+
+        /*
+         * If this is the first time round, we need to work out how fast
+         * the timer ticks
+         */
+        if (twd_timer_rate == 0) {
+                printk(KERN_INFO "Calibrating local timer... ");
+
+                /* Wait for a tick to start */
+                waitjiffies = get_jiffies_64() + 1;
+
+                while (get_jiffies_64() < waitjiffies)
+                        udelay(10);
+
+                /* OK, now the tick has started, let's get the timer going */
+                waitjiffies += 5;
+
+                                 /* enable, no interrupt or reload */
+                __raw_writel(0x1, twd_base + TWD_TIMER_CONTROL);
+
+                                 /* maximum value */
+                __raw_writel(0xFFFFFFFFU, twd_base + TWD_TIMER_COUNTER);
+
+                while (get_jiffies_64() < waitjiffies)
+                        udelay(10);
+
+                count = __raw_readl(twd_base + TWD_TIMER_COUNTER);
+
+                twd_timer_rate = (0xFFFFFFFFU - count) * (HZ / 5);
+
+                printk("%lu.%02luMHz.\n", twd_timer_rate / 1000000,
+                        (twd_timer_rate / 100000) % 100);
+        }
+
+        load = twd_timer_rate / HZ;
+
+        __raw_writel(load, twd_base + TWD_TIMER_LOAD);
+}
+
+/*
+ * Setup the local clock events for a CPU.
+ */
+void __cpuinit twd_timer_setup(struct clock_event_device *clk)
+{
+        unsigned long flags;
+
+        twd_calibrate_rate();
+
+        clk->name = "local_timer";
+        clk->features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT;
+        clk->rating = 350;
+        clk->set_mode = twd_set_mode;
+        clk->set_next_event = twd_set_next_event;
+        clk->shift = 20;
+        clk->mult = div_sc(twd_timer_rate, NSEC_PER_SEC, clk->shift);
+        clk->max_delta_ns = clockevent_delta2ns(0xffffffff, clk);
+        clk->min_delta_ns = clockevent_delta2ns(0xf, clk);
+
+        /* Make sure our local interrupt controller has this enabled */
+        local_irq_save(flags);
+        get_irq_chip(clk->irq)->unmask(clk->irq);
+        local_irq_restore(flags);
+
+        clockevents_register_device(clk);
+}
+
+/*
+ * take a local timer down
+ */
+void __cpuexit twd_timer_stop(void)
+{
+        __raw_writel(0, twd_base + TWD_TIMER_CONTROL);
+}
diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index c90f27250ead..6c0779792546 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -141,6 +141,7 @@ SECTIONS
 
         .data : AT(__data_loc) {
                 _data = .;              /* address in memory */
+                _sdata = .;
 
                 /*
                  * first, the init task union, aligned
@@ -192,6 +193,7 @@ SECTIONS
                 __bss_start = .;        /* BSS                          */
                 *(.bss)
                 *(COMMON)
+                __bss_stop = .;
                 _end = .;
         }
                                         /* Stabs debugging sections.    */