Merge branch 'devel-stable' into devel

Conflicts:
	arch/arm/mach-pxa/clock.c
	arch/arm/mach-pxa/clock.h

11 files changed, 538 insertions, 296 deletions

diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index 7c33e6f29bc..185ee822c93 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -54,6 +54,7 @@ AFLAGS_crunch-bits.o		:= -Wa,-mcpu=ep9312
 obj-$(CONFIG_CPU_XSCALE)        += xscale-cp0.o
 obj-$(CONFIG_CPU_XSC3)          += xscale-cp0.o
 obj-$(CONFIG_CPU_MOHAWK)        += xscale-cp0.o
+obj-$(CONFIG_CPU_PJ4)           += pj4-cp0.o
 obj-$(CONFIG_IWMMXT)            += iwmmxt.o
 obj-$(CONFIG_CPU_HAS_PMU)       += pmu.o
 obj-$(CONFIG_HW_PERF_EVENTS)    += perf_event.o
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index 27f64489c1c..2b46fea36c9 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -178,6 +178,7 @@ __dabt_svc:
         @
         @ set desired IRQ state, then call main handler
         @
+        debug_entry r1
         msr     cpsr_c, r9
         mov     r2, sp
         bl      do_DataAbort
@@ -304,6 +305,7 @@ __pabt_svc:
 #else
         bl      CPU_PABORT_HANDLER
 #endif
+        debug_entry r1
         msr     cpsr_c, r9                      @ Maybe enable interrupts
         mov     r2, sp                          @ regs
         bl      do_PrefetchAbort                @ call abort handler
@@ -419,6 +421,7 @@ __dabt_usr:
         @
         @ IRQs on, then call the main handler
         @
+        debug_entry r1
         enable_irq
         mov     r2, sp
         adr     lr, BSYM(ret_from_exception)
@@ -683,6 +686,7 @@ __pabt_usr:
 #else
         bl      CPU_PABORT_HANDLER
 #endif
+        debug_entry r1
         enable_irq                              @ Enable interrupts
         mov     r2, sp                          @ regs
         bl      do_PrefetchAbort                @ call abort handler
diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S
index d93f976fb38..ae946490016 100644
--- a/arch/arm/kernel/entry-header.S
+++ b/arch/arm/kernel/entry-header.S
@@ -165,6 +165,25 @@
         .endm
 #endif  /* !CONFIG_THUMB2_KERNEL */
 
+        @
+        @ Debug exceptions are taken as prefetch or data aborts.
+        @ We must disable preemption during the handler so that
+        @ we can access the debug registers safely.
+        @
+        .macro  debug_entry, fsr
+#if defined(CONFIG_HAVE_HW_BREAKPOINT) && defined(CONFIG_PREEMPT)
+        ldr     r4, =0x40f              @ mask out fsr.fs
+        and     r5, r4, \fsr
+        cmp     r5, #2                  @ debug exception
+        bne     1f
+        get_thread_info r10
+        ldr     r6, [r10, #TI_PREEMPT]  @ get preempt count
+        add     r11, r6, #1             @ increment it
+        str     r11, [r10, #TI_PREEMPT]
+1:
+#endif
+        .endm
+
 /*
  * These are the registers used in the syscall handler, and allow us to
  * have in theory up to 7 arguments to a function - r0 to r6.
diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c
index 21e3a4ab3b8..c9f3f046757 100644
--- a/arch/arm/kernel/hw_breakpoint.c
+++ b/arch/arm/kernel/hw_breakpoint.c
@@ -24,6 +24,7 @@
 #define pr_fmt(fmt) "hw-breakpoint: " fmt
 
 #include <linux/errno.h>
+#include <linux/hardirq.h>
 #include <linux/perf_event.h>
 #include <linux/hw_breakpoint.h>
 #include <linux/smp.h>
@@ -44,6 +45,7 @@ static DEFINE_PER_CPU(struct perf_event *, wp_on_reg[ARM_MAX_WRP]);
 
 /* Number of BRP/WRP registers on this CPU. */
 static int core_num_brps;
+static int core_num_reserved_brps;
 static int core_num_wrps;
 
 /* Debug architecture version. */
@@ -52,87 +54,6 @@ static u8 debug_arch;
 /* Maximum supported watchpoint length. */
 static u8 max_watchpoint_len;
 
-/* Determine number of BRP registers available. */
-static int get_num_brps(void)
-{
-        u32 didr;
-        ARM_DBG_READ(c0, 0, didr);
-        return ((didr >> 24) & 0xf) + 1;
-}
-
-/* Determine number of WRP registers available. */
-static int get_num_wrps(void)
-{
-        /*
-         * FIXME: When a watchpoint fires, the only way to work out which
-         * watchpoint it was is by disassembling the faulting instruction
-         * and working out the address of the memory access.
-         *
-         * Furthermore, we can only do this if the watchpoint was precise
-         * since imprecise watchpoints prevent us from calculating register
-         * based addresses.
-         *
-         * For the time being, we only report 1 watchpoint register so we
-         * always know which watchpoint fired. In the future we can either
-         * add a disassembler and address generation emulator, or we can
-         * insert a check to see if the DFAR is set on watchpoint exception
-         * entry [the ARM ARM states that the DFAR is UNKNOWN, but
-         * experience shows that it is set on some implementations].
-         */
-
-#if 0
-        u32 didr, wrps;
-        ARM_DBG_READ(c0, 0, didr);
-        return ((didr >> 28) & 0xf) + 1;
-#endif
-
-        return 1;
-}
-
-int hw_breakpoint_slots(int type)
-{
-        /*
-         * We can be called early, so don't rely on
-         * our static variables being initialised.
-         */
-        switch (type) {
-        case TYPE_INST:
-                return get_num_brps();
-        case TYPE_DATA:
-                return get_num_wrps();
-        default:
-                pr_warning("unknown slot type: %d\n", type);
-                return 0;
-        }
-}
-
-/* Determine debug architecture. */
-static u8 get_debug_arch(void)
-{
-        u32 didr;
-
-        /* Do we implement the extended CPUID interface? */
-        if (((read_cpuid_id() >> 16) & 0xf) != 0xf) {
-                pr_warning("CPUID feature registers not supported. "
-                                "Assuming v6 debug is present.\n");
-                return ARM_DEBUG_ARCH_V6;
-        }
-
-        ARM_DBG_READ(c0, 0, didr);
-        return (didr >> 16) & 0xf;
-}
-
-/* Does this core support mismatch breakpoints? */
-static int core_has_mismatch_bps(void)
-{
-        return debug_arch >= ARM_DEBUG_ARCH_V7_ECP14 && core_num_brps > 1;
-}
-
-u8 arch_get_debug_arch(void)
-{
-        return debug_arch;
-}
-
 #define READ_WB_REG_CASE(OP2, M, VAL)           \
         case ((OP2 << 4) + M):                  \
                 ARM_DBG_READ(c ## M, OP2, VAL); \
@@ -210,6 +131,94 @@ static void write_wb_reg(int n, u32 val)
         isb();
 }
 
+/* Determine debug architecture. */
+static u8 get_debug_arch(void)
+{
+        u32 didr;
+
+        /* Do we implement the extended CPUID interface? */
+        if (((read_cpuid_id() >> 16) & 0xf) != 0xf) {
+                pr_warning("CPUID feature registers not supported. "
+                                "Assuming v6 debug is present.\n");
+                return ARM_DEBUG_ARCH_V6;
+        }
+
+        ARM_DBG_READ(c0, 0, didr);
+        return (didr >> 16) & 0xf;
+}
+
+u8 arch_get_debug_arch(void)
+{
+        return debug_arch;
+}
+
+/* Determine number of BRP register available. */
+static int get_num_brp_resources(void)
+{
+        u32 didr;
+        ARM_DBG_READ(c0, 0, didr);
+        return ((didr >> 24) & 0xf) + 1;
+}
+
+/* Does this core support mismatch breakpoints? */
+static int core_has_mismatch_brps(void)
+{
+        return (get_debug_arch() >= ARM_DEBUG_ARCH_V7_ECP14 &&
+                get_num_brp_resources() > 1);
+}
+
+/* Determine number of usable WRPs available. */
+static int get_num_wrps(void)
+{
+        /*
+         * FIXME: When a watchpoint fires, the only way to work out which
+         * watchpoint it was is by disassembling the faulting instruction
+         * and working out the address of the memory access.
+         *
+         * Furthermore, we can only do this if the watchpoint was precise
+         * since imprecise watchpoints prevent us from calculating register
+         * based addresses.
+         *
+         * Providing we have more than 1 breakpoint register, we only report
+         * a single watchpoint register for the time being. This way, we always
+         * know which watchpoint fired. In the future we can either add a
+         * disassembler and address generation emulator, or we can insert a
+         * check to see if the DFAR is set on watchpoint exception entry
+         * [the ARM ARM states that the DFAR is UNKNOWN, but experience shows
+         * that it is set on some implementations].
+         */
+
+#if 0
+        int wrps;
+        u32 didr;
+        ARM_DBG_READ(c0, 0, didr);
+        wrps = ((didr >> 28) & 0xf) + 1;
+#endif
+        int wrps = 1;
+
+        if (core_has_mismatch_brps() && wrps >= get_num_brp_resources())
+                wrps = get_num_brp_resources() - 1;
+
+        return wrps;
+}
+
+/* We reserve one breakpoint for each watchpoint. */
+static int get_num_reserved_brps(void)
+{
+        if (core_has_mismatch_brps())
+                return get_num_wrps();
+        return 0;
+}
+
+/* Determine number of usable BRPs available. */
+static int get_num_brps(void)
+{
+        int brps = get_num_brp_resources();
+        if (core_has_mismatch_brps())
+                brps -= get_num_reserved_brps();
+        return brps;
+}
+
 /*
  * In order to access the breakpoint/watchpoint control registers,
  * we must be running in debug monitor mode. Unfortunately, we can
@@ -230,8 +239,12 @@ static int enable_monitor_mode(void)
                 goto out;
         }
 
+        /* If monitor mode is already enabled, just return. */
+        if (dscr & ARM_DSCR_MDBGEN)
+                goto out;
+
         /* Write to the corresponding DSCR. */
-        switch (debug_arch) {
+        switch (get_debug_arch()) {
         case ARM_DEBUG_ARCH_V6:
         case ARM_DEBUG_ARCH_V6_1:
                 ARM_DBG_WRITE(c1, 0, (dscr | ARM_DSCR_MDBGEN));
@@ -246,15 +259,30 @@ static int enable_monitor_mode(void)
 
         /* Check that the write made it through. */
         ARM_DBG_READ(c1, 0, dscr);
-        if (WARN_ONCE(!(dscr & ARM_DSCR_MDBGEN),
-                                "failed to enable monitor mode.")) {
+        if (!(dscr & ARM_DSCR_MDBGEN))
                 ret = -EPERM;
-        }
 
 out:
         return ret;
 }
 
+int hw_breakpoint_slots(int type)
+{
+        /*
+         * We can be called early, so don't rely on
+         * our static variables being initialised.
+         */
+        switch (type) {
+        case TYPE_INST:
+                return get_num_brps();
+        case TYPE_DATA:
+                return get_num_wrps();
+        default:
+                pr_warning("unknown slot type: %d\n", type);
+                return 0;
+        }
+}
+
 /*
  * Check if 8-bit byte-address select is available.
  * This clobbers WRP 0.
@@ -268,9 +296,6 @@ static u8 get_max_wp_len(void)
         if (debug_arch < ARM_DEBUG_ARCH_V7_ECP14)
                 goto out;
 
-        if (enable_monitor_mode())
-                goto out;
-
         memset(&ctrl, 0, sizeof(ctrl));
         ctrl.len = ARM_BREAKPOINT_LEN_8;
         ctrl_reg = encode_ctrl_reg(ctrl);
@@ -290,23 +315,6 @@ u8 arch_get_max_wp_len(void)
 }
 
 /*
- * Handler for reactivating a suspended watchpoint when the single
- * step `mismatch' breakpoint is triggered.
- */
-static void wp_single_step_handler(struct perf_event *bp, int unused,
-                                   struct perf_sample_data *data,
-                                   struct pt_regs *regs)
-{
-        perf_event_enable(counter_arch_bp(bp)->suspended_wp);
-        unregister_hw_breakpoint(bp);
-}
-
-static int bp_is_single_step(struct perf_event *bp)
-{
-        return bp->overflow_handler == wp_single_step_handler;
-}
-
-/*
  * Install a perf counter breakpoint.
  */
 int arch_install_hw_breakpoint(struct perf_event *bp)
@@ -314,30 +322,41 @@ int arch_install_hw_breakpoint(struct perf_event *bp)
         struct arch_hw_breakpoint *info = counter_arch_bp(bp);
         struct perf_event **slot, **slots;
         int i, max_slots, ctrl_base, val_base, ret = 0;
+        u32 addr, ctrl;
 
         /* Ensure that we are in monitor mode and halting mode is disabled. */
         ret = enable_monitor_mode();
         if (ret)
                 goto out;
 
+        addr = info->address;
+        ctrl = encode_ctrl_reg(info->ctrl) | 0x1;
+
         if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE) {
                 /* Breakpoint */
                 ctrl_base = ARM_BASE_BCR;
                 val_base = ARM_BASE_BVR;
-                slots = __get_cpu_var(bp_on_reg);
-                max_slots = core_num_brps - 1;
-
-                if (bp_is_single_step(bp)) {
-                        info->ctrl.mismatch = 1;
-                        i = max_slots;
-                        slots[i] = bp;
-                        goto setup;
+                slots = (struct perf_event **)__get_cpu_var(bp_on_reg);
+                max_slots = core_num_brps;
+                if (info->step_ctrl.enabled) {
+                        /* Override the breakpoint data with the step data. */
+                        addr = info->trigger & ~0x3;
+                        ctrl = encode_ctrl_reg(info->step_ctrl);
                 }
         } else {
                 /* Watchpoint */
-                ctrl_base = ARM_BASE_WCR;
-                val_base = ARM_BASE_WVR;
-                slots = __get_cpu_var(wp_on_reg);
+                if (info->step_ctrl.enabled) {
+                        /* Install into the reserved breakpoint region. */
+                        ctrl_base = ARM_BASE_BCR + core_num_brps;
+                        val_base = ARM_BASE_BVR + core_num_brps;
+                        /* Override the watchpoint data with the step data. */
+                        addr = info->trigger & ~0x3;
+                        ctrl = encode_ctrl_reg(info->step_ctrl);
+                } else {
+                        ctrl_base = ARM_BASE_WCR;
+                        val_base = ARM_BASE_WVR;
+                }
+                slots = (struct perf_event **)__get_cpu_var(wp_on_reg);
                 max_slots = core_num_wrps;
         }
 
@@ -355,12 +374,11 @@ int arch_install_hw_breakpoint(struct perf_event *bp)
                 goto out;
         }
 
-setup:
         /* Setup the address register. */
-        write_wb_reg(val_base + i, info->address);
+        write_wb_reg(val_base + i, addr);
 
         /* Setup the control register. */
-        write_wb_reg(ctrl_base + i, encode_ctrl_reg(info->ctrl) | 0x1);
+        write_wb_reg(ctrl_base + i, ctrl);
 
 out:
         return ret;
@@ -375,18 +393,15 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp)
         if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE) {
                 /* Breakpoint */
                 base = ARM_BASE_BCR;
-                slots = __get_cpu_var(bp_on_reg);
-                max_slots = core_num_brps - 1;
-
-                if (bp_is_single_step(bp)) {
-                        i = max_slots;
-                        slots[i] = NULL;
-                        goto reset;
-                }
+                slots = (struct perf_event **)__get_cpu_var(bp_on_reg);
+                max_slots = core_num_brps;
         } else {
                 /* Watchpoint */
-                base = ARM_BASE_WCR;
-                slots = __get_cpu_var(wp_on_reg);
+                if (info->step_ctrl.enabled)
+                        base = ARM_BASE_BCR + core_num_brps;
+                else
+                        base = ARM_BASE_WCR;
+                slots = (struct perf_event **)__get_cpu_var(wp_on_reg);
                 max_slots = core_num_wrps;
         }
 
@@ -403,7 +418,6 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp)
         if (WARN_ONCE(i == max_slots, "Can't find any breakpoint slot"))
                 return;
 
-reset:
         /* Reset the control register. */
         write_wb_reg(base + i, 0);
 }
@@ -537,12 +551,23 @@ static int arch_build_bp_info(struct perf_event *bp)
                 return -EINVAL;
         }
 
+        /*
+         * Breakpoints must be of length 2 (thumb) or 4 (ARM) bytes.
+         * Watchpoints can be of length 1, 2, 4 or 8 bytes if supported
+         * by the hardware and must be aligned to the appropriate number of
+         * bytes.
+         */
+        if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE &&
+            info->ctrl.len != ARM_BREAKPOINT_LEN_2 &&
+            info->ctrl.len != ARM_BREAKPOINT_LEN_4)
+                return -EINVAL;
+
         /* Address */
         info->address = bp->attr.bp_addr;
 
         /* Privilege */
         info->ctrl.privilege = ARM_BREAKPOINT_USER;
-        if (arch_check_bp_in_kernelspace(bp) && !bp_is_single_step(bp))
+        if (arch_check_bp_in_kernelspace(bp))
                 info->ctrl.privilege |= ARM_BREAKPOINT_PRIV;
 
         /* Enabled? */
@@ -561,7 +586,7 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 {
         struct arch_hw_breakpoint *info = counter_arch_bp(bp);
         int ret = 0;
-        u32 bytelen, max_len, offset, alignment_mask = 0x3;
+        u32 offset, alignment_mask = 0x3;
 
         /* Build the arch_hw_breakpoint. */
         ret = arch_build_bp_info(bp);
@@ -571,84 +596,85 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
         /* Check address alignment. */
         if (info->ctrl.len == ARM_BREAKPOINT_LEN_8)
                 alignment_mask = 0x7;
-        if (info->address & alignment_mask) {
-                /*
-                 * Try to fix the alignment. This may result in a length
-                 * that is too large, so we must check for that.
-                 */
-                bytelen = get_hbp_len(info->ctrl.len);
-                max_len = info->ctrl.type == ARM_BREAKPOINT_EXECUTE ? 4 :
-                                max_watchpoint_len;
-
-                if (max_len >= 8)
-                        offset = info->address & 0x7;
-                else
-                        offset = info->address & 0x3;
-
-                if (bytelen > (1 << ((max_len - (offset + 1)) >> 1))) {
-                        ret = -EFBIG;
-                        goto out;
-                }
-
-                info->ctrl.len <<= offset;
-                info->address &= ~offset;
-
-                pr_debug("breakpoint alignment fixup: length = 0x%x, "
-                        "address = 0x%x\n", info->ctrl.len, info->address);
+        offset = info->address & alignment_mask;
+        switch (offset) {
+        case 0:
+                /* Aligned */
+                break;
+        case 1:
+                /* Allow single byte watchpoint. */
+                if (info->ctrl.len == ARM_BREAKPOINT_LEN_1)
+                        break;
+        case 2:
+                /* Allow halfword watchpoints and breakpoints. */
+                if (info->ctrl.len == ARM_BREAKPOINT_LEN_2)
+                        break;
+        default:
+                ret = -EINVAL;
+                goto out;
         }
 
+        info->address &= ~alignment_mask;
+        info->ctrl.len <<= offset;
+
         /*
          * Currently we rely on an overflow handler to take
          * care of single-stepping the breakpoint when it fires.
          * In the case of userspace breakpoints on a core with V7 debug,
-         * we can use the mismatch feature as a poor-man's hardware single-step.
+         * we can use the mismatch feature as a poor-man's hardware
+         * single-step, but this only works for per-task breakpoints.
          */
         if (WARN_ONCE(!bp->overflow_handler &&
-                (arch_check_bp_in_kernelspace(bp) || !core_has_mismatch_bps()),
+                (arch_check_bp_in_kernelspace(bp) || !core_has_mismatch_brps()
+                 || !bp->hw.bp_target),
                         "overflow handler required but none found")) {
                 ret = -EINVAL;
-                goto out;
         }
 out:
         return ret;
 }
 
-static void update_mismatch_flag(int idx, int flag)
+/*
+ * Enable/disable single-stepping over the breakpoint bp at address addr.
+ */
+static void enable_single_step(struct perf_event *bp, u32 addr)
 {
-        struct perf_event *bp = __get_cpu_var(bp_on_reg[idx]);
-        struct arch_hw_breakpoint *info;
-
-        if (bp == NULL)
-                return;
+        struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 
-        info = counter_arch_bp(bp);
+        arch_uninstall_hw_breakpoint(bp);
+        info->step_ctrl.mismatch  = 1;
+        info->step_ctrl.len       = ARM_BREAKPOINT_LEN_4;
+        info->step_ctrl.type      = ARM_BREAKPOINT_EXECUTE;
+        info->step_ctrl.privilege = info->ctrl.privilege;
+        info->step_ctrl.enabled   = 1;
+        info->trigger             = addr;
+        arch_install_hw_breakpoint(bp);
+}
 
-        /* Update the mismatch field to enter/exit `single-step' mode */
-        if (!bp->overflow_handler && info->ctrl.mismatch != flag) {
-                info->ctrl.mismatch = flag;
-                write_wb_reg(ARM_BASE_BCR + idx, encode_ctrl_reg(info->ctrl) | 0x1);
-        }
+static void disable_single_step(struct perf_event *bp)
+{
+        arch_uninstall_hw_breakpoint(bp);
+        counter_arch_bp(bp)->step_ctrl.enabled = 0;
+        arch_install_hw_breakpoint(bp);
 }
 
 static void watchpoint_handler(unsigned long unknown, struct pt_regs *regs)
 {
         int i;
-        struct perf_event *bp, **slots = __get_cpu_var(wp_on_reg);
+        struct perf_event *wp, **slots;
         struct arch_hw_breakpoint *info;
-        struct perf_event_attr attr;
+
+        slots = (struct perf_event **)__get_cpu_var(wp_on_reg);
 
         /* Without a disassembler, we can only handle 1 watchpoint. */
         BUG_ON(core_num_wrps > 1);
 
-        hw_breakpoint_init(&attr);
-        attr.bp_addr    = regs->ARM_pc & ~0x3;
-        attr.bp_len     = HW_BREAKPOINT_LEN_4;
-        attr.bp_type    = HW_BREAKPOINT_X;
-
         for (i = 0; i < core_num_wrps; ++i) {
                 rcu_read_lock();
 
-                if (slots[i] == NULL) {
+                wp = slots[i];
+
+                if (wp == NULL) {
                         rcu_read_unlock();
                         continue;
                 }
@@ -658,24 +684,51 @@ static void watchpoint_handler(unsigned long unknown, struct pt_regs *regs)
                  * single watchpoint, we can set the trigger to the lowest
                  * possible faulting address.
                  */
-                info = counter_arch_bp(slots[i]);
-                info->trigger = slots[i]->attr.bp_addr;
+                info = counter_arch_bp(wp);
+                info->trigger = wp->attr.bp_addr;
                 pr_debug("watchpoint fired: address = 0x%x\n", info->trigger);
-                perf_bp_event(slots[i], regs);
+                perf_bp_event(wp, regs);
 
                 /*
                  * If no overflow handler is present, insert a temporary
                  * mismatch breakpoint so we can single-step over the
                  * watchpoint trigger.
                  */
-                if (!slots[i]->overflow_handler) {
-                        bp = register_user_hw_breakpoint(&attr,
-                                                         wp_single_step_handler,
-                                                         current);
-                        counter_arch_bp(bp)->suspended_wp = slots[i];
-                        perf_event_disable(slots[i]);
-                }
+                if (!wp->overflow_handler)
+                        enable_single_step(wp, instruction_pointer(regs));
+
+                rcu_read_unlock();
+        }
+}
 
+static void watchpoint_single_step_handler(unsigned long pc)
+{
+        int i;
+        struct perf_event *wp, **slots;
+        struct arch_hw_breakpoint *info;
+
+        slots = (struct perf_event **)__get_cpu_var(wp_on_reg);
+
+        for (i = 0; i < core_num_reserved_brps; ++i) {
+                rcu_read_lock();
+
+                wp = slots[i];
+
+                if (wp == NULL)
+                        goto unlock;
+
+                info = counter_arch_bp(wp);
+                if (!info->step_ctrl.enabled)
+                        goto unlock;
+
+                /*
+                 * Restore the original watchpoint if we've completed the
+                 * single-step.
+                 */
+                if (info->trigger != pc)
+                        disable_single_step(wp);
+
+unlock:
                 rcu_read_unlock();
         }
 }
@@ -683,62 +736,69 @@ static void watchpoint_handler(unsigned long unknown, struct pt_regs *regs)
 static void breakpoint_handler(unsigned long unknown, struct pt_regs *regs)
 {
         int i;
-        int mismatch;
         u32 ctrl_reg, val, addr;
-        struct perf_event *bp, **slots = __get_cpu_var(bp_on_reg);
+        struct perf_event *bp, **slots;
         struct arch_hw_breakpoint *info;
         struct arch_hw_breakpoint_ctrl ctrl;
 
+        slots = (struct perf_event **)__get_cpu_var(bp_on_reg);
+
         /* The exception entry code places the amended lr in the PC. */
         addr = regs->ARM_pc;
 
+        /* Check the currently installed breakpoints first. */
         for (i = 0; i < core_num_brps; ++i) {
                 rcu_read_lock();
 
                 bp = slots[i];
 
-                if (bp == NULL) {
-                        rcu_read_unlock();
-                        continue;
-                }
+                if (bp == NULL)
+                        goto unlock;
 
-                mismatch = 0;
+                info = counter_arch_bp(bp);
 
                 /* Check if the breakpoint value matches. */
                 val = read_wb_reg(ARM_BASE_BVR + i);
                 if (val != (addr & ~0x3))
-                        goto unlock;
+                        goto mismatch;
 
                 /* Possible match, check the byte address select to confirm. */
                 ctrl_reg = read_wb_reg(ARM_BASE_BCR + i);
                 decode_ctrl_reg(ctrl_reg, &ctrl);
                 if ((1 << (addr & 0x3)) & ctrl.len) {
-                        mismatch = 1;
-                        info = counter_arch_bp(bp);
                         info->trigger = addr;
-                }
-
-unlock:
-                if ((mismatch && !info->ctrl.mismatch) || bp_is_single_step(bp)) {
                         pr_debug("breakpoint fired: address = 0x%x\n", addr);
                         perf_bp_event(bp, regs);
+                        if (!bp->overflow_handler)
+                                enable_single_step(bp, addr);
+                        goto unlock;
                 }
 
-                update_mismatch_flag(i, mismatch);
+mismatch:
+                /* If we're stepping a breakpoint, it can now be restored. */
+                if (info->step_ctrl.enabled)
+                        disable_single_step(bp);
+unlock:
                 rcu_read_unlock();
         }
+
+        /* Handle any pending watchpoint single-step breakpoints. */
+        watchpoint_single_step_handler(addr);
 }
 
 /*
  * Called from either the Data Abort Handler [watchpoint] or the
- * Prefetch Abort Handler [breakpoint].
+ * Prefetch Abort Handler [breakpoint] with preemption disabled.
  */
 static int hw_breakpoint_pending(unsigned long addr, unsigned int fsr,
                                  struct pt_regs *regs)
 {
-        int ret = 1; /* Unhandled fault. */
+        int ret = 0;
         u32 dscr;
 
+        /* We must be called with preemption disabled. */
+        WARN_ON(preemptible());
+
         /* We only handle watchpoints and hardware breakpoints. */
         ARM_DBG_READ(c1, 0, dscr);
 
@@ -753,25 +813,47 @@ static int hw_breakpoint_pending(unsigned long addr, unsigned int fsr,
                 watchpoint_handler(addr, regs);
                 break;
         default:
-                goto out;
+                ret = 1; /* Unhandled fault. */
         }
 
-        ret = 0;
-out:
+        /*
+         * Re-enable preemption after it was disabled in the
+         * low-level exception handling code.
+         */
+        preempt_enable();
+
         return ret;
 }
 
 /*
  * One-time initialisation.
  */
-static void __init reset_ctrl_regs(void *unused)
+static void reset_ctrl_regs(void *unused)
 {
         int i;
 
+        /*
+         * v7 debug contains save and restore registers so that debug state
+         * can be maintained across low-power modes without leaving
+         * the debug logic powered up. It is IMPLEMENTATION DEFINED whether
+         * we can write to the debug registers out of reset, so we must
+         * unlock the OS Lock Access Register to avoid taking undefined
+         * instruction exceptions later on.
+         */
+        if (debug_arch >= ARM_DEBUG_ARCH_V7_ECP14) {
+                /*
+                 * Unconditionally clear the lock by writing a value
+                 * other than 0xC5ACCE55 to the access register.
+                 */
+                asm volatile("mcr p14, 0, %0, c1, c0, 4" : : "r" (0));
+                isb();
+        }
+
         if (enable_monitor_mode())
                 return;
 
-        for (i = 0; i < core_num_brps; ++i) {
+        /* We must also reset any reserved registers. */
+        for (i = 0; i < core_num_brps + core_num_reserved_brps; ++i) {
                 write_wb_reg(ARM_BASE_BCR + i, 0UL);
                 write_wb_reg(ARM_BASE_BVR + i, 0UL);
         }
@@ -782,45 +864,57 @@ static void __init reset_ctrl_regs(void *unused)
         }
 }
 
+static int __cpuinit dbg_reset_notify(struct notifier_block *self,
+                                      unsigned long action, void *cpu)
+{
+        if (action == CPU_ONLINE)
+                smp_call_function_single((int)cpu, reset_ctrl_regs, NULL, 1);
+        return NOTIFY_OK;
+}
+
+static struct notifier_block __cpuinitdata dbg_reset_nb = {
+        .notifier_call = dbg_reset_notify,
+};
+
 static int __init arch_hw_breakpoint_init(void)
 {
-        int ret = 0;
         u32 dscr;
 
         debug_arch = get_debug_arch();
 
         if (debug_arch > ARM_DEBUG_ARCH_V7_ECP14) {
                 pr_info("debug architecture 0x%x unsupported.\n", debug_arch);
-                ret = -ENODEV;
-                goto out;
+                return 0;
         }
 
         /* Determine how many BRPs/WRPs are available. */
         core_num_brps = get_num_brps();
+        core_num_reserved_brps = get_num_reserved_brps();
         core_num_wrps = get_num_wrps();
 
         pr_info("found %d breakpoint and %d watchpoint registers.\n",
-                        core_num_brps, core_num_wrps);
+                core_num_brps + core_num_reserved_brps, core_num_wrps);
 
-        if (core_has_mismatch_bps())
-                pr_info("1 breakpoint reserved for watchpoint single-step.\n");
+        if (core_num_reserved_brps)
+                pr_info("%d breakpoint(s) reserved for watchpoint "
+                                "single-step.\n", core_num_reserved_brps);
 
         ARM_DBG_READ(c1, 0, dscr);
         if (dscr & ARM_DSCR_HDBGEN) {
                 pr_warning("halting debug mode enabled. Assuming maximum "
                                 "watchpoint size of 4 bytes.");
         } else {
-                /* Work out the maximum supported watchpoint length. */
-                max_watchpoint_len = get_max_wp_len();
-                pr_info("maximum watchpoint size is %u bytes.\n",
-                                max_watchpoint_len);
-
                 /*
                  * Reset the breakpoint resources. We assume that a halting
                  * debugger will leave the world in a nice state for us.
                  */
                 smp_call_function(reset_ctrl_regs, NULL, 1);
                 reset_ctrl_regs(NULL);
+
+                /* Work out the maximum supported watchpoint length. */
+                max_watchpoint_len = get_max_wp_len();
+                pr_info("maximum watchpoint size is %u bytes.\n",
+                                max_watchpoint_len);
         }
 
         /* Register debug fault handler. */
@@ -829,8 +923,9 @@ static int __init arch_hw_breakpoint_init(void)
         hook_ifault_code(2, hw_breakpoint_pending, SIGTRAP, TRAP_HWBKPT,
                         "breakpoint debug exception");
 
-out:
-        return ret;
+        /* Register hotplug notifier. */
+        register_cpu_notifier(&dbg_reset_nb);
+        return 0;
 }
 arch_initcall(arch_hw_breakpoint_init);
 
diff --git a/arch/arm/kernel/iwmmxt.S b/arch/arm/kernel/iwmmxt.S
index b63b528f22a..7fa3bb0d239 100644
--- a/arch/arm/kernel/iwmmxt.S
+++ b/arch/arm/kernel/iwmmxt.S
@@ -19,6 +19,14 @@
 #include <asm/thread_info.h>
 #include <asm/asm-offsets.h>
 
+#if defined(CONFIG_CPU_PJ4)
+#define PJ4(code...)            code
+#define XSC(code...)
+#else
+#define PJ4(code...)
+#define XSC(code...)            code
+#endif
+
 #define MMX_WR0                 (0x00)
 #define MMX_WR1                 (0x08)
 #define MMX_WR2                 (0x10)
@@ -58,11 +66,17 @@
 
 ENTRY(iwmmxt_task_enable)
 
-        mrc     p15, 0, r2, c15, c1, 0
-        tst     r2, #0x3                        @ CP0 and CP1 accessible?
+        XSC(mrc p15, 0, r2, c15, c1, 0)
+        PJ4(mrc p15, 0, r2, c1, c0, 2)
+        @ CP0 and CP1 accessible?
+        XSC(tst r2, #0x3)
+        PJ4(tst r2, #0xf)
         movne   pc, lr                          @ if so no business here
-        orr     r2, r2, #0x3                    @ enable access to CP0 and CP1
-        mcr     p15, 0, r2, c15, c1, 0
+        @ enable access to CP0 and CP1
+        XSC(orr r2, r2, #0x3)
+        XSC(mcr p15, 0, r2, c15, c1, 0)
+        PJ4(orr r2, r2, #0xf)
+        PJ4(mcr p15, 0, r2, c1, c0, 2)
 
         ldr     r3, =concan_owner
         add     r0, r10, #TI_IWMMXT_STATE       @ get task Concan save area
@@ -179,17 +193,26 @@ ENTRY(iwmmxt_task_disable)
         teqne   r1, r2                          @ or specified one?
         bne     1f                              @ no: quit
 
-        mrc     p15, 0, r4, c15, c1, 0
-        orr     r4, r4, #0x3                    @ enable access to CP0 and CP1
-        mcr     p15, 0, r4, c15, c1, 0
+        @ enable access to CP0 and CP1
+        XSC(mrc p15, 0, r4, c15, c1, 0)
+        XSC(orr r4, r4, #0xf)
+        XSC(mcr p15, 0, r4, c15, c1, 0)
+        PJ4(mrc p15, 0, r4, c1, c0, 2)
+        PJ4(orr r4, r4, #0x3)
+        PJ4(mcr p15, 0, r4, c1, c0, 2)
+
         mov     r0, #0                          @ nothing to load
         str     r0, [r3]                        @ no more current owner
         mrc     p15, 0, r2, c2, c0, 0
         mov     r2, r2                          @ cpwait
         bl      concan_save
 
-        bic     r4, r4, #0x3                    @ disable access to CP0 and CP1
-        mcr     p15, 0, r4, c15, c1, 0
+        @ disable access to CP0 and CP1
+        XSC(bic r4, r4, #0x3)
+        XSC(mcr p15, 0, r4, c15, c1, 0)
+        PJ4(bic r4, r4, #0xf)
+        PJ4(mcr p15, 0, r4, c1, c0, 2)
+
         mrc     p15, 0, r2, c2, c0, 0
         mov     r2, r2                          @ cpwait
 
@@ -277,8 +300,11 @@ ENTRY(iwmmxt_task_restore)
  */
 ENTRY(iwmmxt_task_switch)
 
-        mrc     p15, 0, r1, c15, c1, 0
-        tst     r1, #0x3                        @ CP0 and CP1 accessible?
+        XSC(mrc p15, 0, r1, c15, c1, 0)
+        PJ4(mrc p15, 0, r1, c1, c0, 2)
+        @ CP0 and CP1 accessible?
+        XSC(tst r1, #0x3)
+        PJ4(tst r1, #0xf)
         bne     1f                              @ yes: block them for next task
 
         ldr     r2, =concan_owner
@@ -287,8 +313,11 @@ ENTRY(iwmmxt_task_switch)
         teq     r2, r3                          @ next task owns it?
         movne   pc, lr                          @ no: leave Concan disabled
 
-1:      eor     r1, r1, #3                      @ flip Concan access
-        mcr     p15, 0, r1, c15, c1, 0
+1:      @ flip Conan access
+        XSC(eor r1, r1, #0x3)
+        XSC(mcr p15, 0, r1, c15, c1, 0)
+        PJ4(eor r1, r1, #0xf)
+        PJ4(mcr p15, 0, r1, c1, c0, 2)
 
         mrc     p15, 0, r1, c2, c0, 0
         sub     pc, lr, r1, lsr #32             @ cpwait and return
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index 421a4bb88fe..624e2a5de2b 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -32,7 +32,7 @@ static struct platform_device *pmu_device;
  * Hardware lock to serialize accesses to PMU registers. Needed for the
  * read/modify/write sequences.
  */
-DEFINE_SPINLOCK(pmu_lock);
+static DEFINE_RAW_SPINLOCK(pmu_lock);
 
 /*
  * ARMv6 supports a maximum of 3 events, starting from index 1. If we add
@@ -65,7 +65,7 @@ struct cpu_hw_events {
          */
         unsigned long           active_mask[BITS_TO_LONGS(ARMPMU_MAX_HWEVENTS)];
 };
-DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events);
+static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events);
 
 struct arm_pmu {
         enum arm_perf_pmu_ids id;
@@ -673,17 +673,17 @@ arch_initcall(init_hw_perf_events);
  * This code has been adapted from the ARM OProfile support.
  */
 struct frame_tail {
-        struct frame_tail   *fp;
-        unsigned long       sp;
-        unsigned long       lr;
+        struct frame_tail __user *fp;
+        unsigned long sp;
+        unsigned long lr;
 } __attribute__((packed));
 
 /*
  * Get the return address for a single stackframe and return a pointer to the
  * next frame tail.
  */
-static struct frame_tail *
-user_backtrace(struct frame_tail *tail,
+static struct frame_tail __user *
+user_backtrace(struct frame_tail __user *tail,
                struct perf_callchain_entry *entry)
 {
         struct frame_tail buftail;
@@ -709,10 +709,10 @@ user_backtrace(struct frame_tail *tail,
 void
 perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 {
-        struct frame_tail *tail;
+        struct frame_tail __user *tail;
 
 
-        tail = (struct frame_tail *)regs->ARM_fp - 1;
+        tail = (struct frame_tail __user *)regs->ARM_fp - 1;
 
         while (tail && !((unsigned long)tail & 0x3))
                 tail = user_backtrace(tail, entry);
diff --git a/arch/arm/kernel/perf_event_v6.c b/arch/arm/kernel/perf_event_v6.c
index 7aeb07da907..c058bfc8532 100644
--- a/arch/arm/kernel/perf_event_v6.c
+++ b/arch/arm/kernel/perf_event_v6.c
@@ -400,7 +400,7 @@ armv6pmu_write_counter(int counter,
                 WARN_ONCE(1, "invalid counter number (%d)\n", counter);
 }
 
-void
+static void
 armv6pmu_enable_event(struct hw_perf_event *hwc,
                       int idx)
 {
@@ -426,12 +426,12 @@ armv6pmu_enable_event(struct hw_perf_event *hwc,
          * Mask out the current event and set the counter to count the event
          * that we're interested in.
          */
-        spin_lock_irqsave(&pmu_lock, flags);
+        raw_spin_lock_irqsave(&pmu_lock, flags);
         val = armv6_pmcr_read();
         val &= ~mask;
         val |= evt;
         armv6_pmcr_write(val);
-        spin_unlock_irqrestore(&pmu_lock, flags);
+        raw_spin_unlock_irqrestore(&pmu_lock, flags);
 }
 
 static irqreturn_t
@@ -500,11 +500,11 @@ armv6pmu_start(void)
 {
         unsigned long flags, val;
 
-        spin_lock_irqsave(&pmu_lock, flags);
+        raw_spin_lock_irqsave(&pmu_lock, flags);
         val = armv6_pmcr_read();
         val |= ARMV6_PMCR_ENABLE;
         armv6_pmcr_write(val);
-        spin_unlock_irqrestore(&pmu_lock, flags);
+        raw_spin_unlock_irqrestore(&pmu_lock, flags);
 }
 
 static void
@@ -512,11 +512,11 @@ armv6pmu_stop(void)
 {
         unsigned long flags, val;
 
-        spin_lock_irqsave(&pmu_lock, flags);
+        raw_spin_lock_irqsave(&pmu_lock, flags);
         val = armv6_pmcr_read();
         val &= ~ARMV6_PMCR_ENABLE;
         armv6_pmcr_write(val);
-        spin_unlock_irqrestore(&pmu_lock, flags);
+        raw_spin_unlock_irqrestore(&pmu_lock, flags);
 }
 
 static int
@@ -570,12 +570,12 @@ armv6pmu_disable_event(struct hw_perf_event *hwc,
          * of ETM bus signal assertion cycles. The external reporting should
          * be disabled and so this should never increment.
          */
-        spin_lock_irqsave(&pmu_lock, flags);
+        raw_spin_lock_irqsave(&pmu_lock, flags);
         val = armv6_pmcr_read();
         val &= ~mask;
         val |= evt;
         armv6_pmcr_write(val);
-        spin_unlock_irqrestore(&pmu_lock, flags);
+        raw_spin_unlock_irqrestore(&pmu_lock, flags);
 }
 
 static void
@@ -599,12 +599,12 @@ armv6mpcore_pmu_disable_event(struct hw_perf_event *hwc,
          * Unlike UP ARMv6, we don't have a way of stopping the counters. We
          * simply disable the interrupt reporting.
          */
-        spin_lock_irqsave(&pmu_lock, flags);
+        raw_spin_lock_irqsave(&pmu_lock, flags);
         val = armv6_pmcr_read();
         val &= ~mask;
         val |= evt;
         armv6_pmcr_write(val);
-        spin_unlock_irqrestore(&pmu_lock, flags);
+        raw_spin_unlock_irqrestore(&pmu_lock, flags);
 }
 
 static const struct arm_pmu armv6pmu = {
@@ -625,7 +625,7 @@ static const struct arm_pmu armv6pmu = {
         .max_period             = (1LLU << 32) - 1,
 };
 
-const struct arm_pmu *__init armv6pmu_init(void)
+static const struct arm_pmu *__init armv6pmu_init(void)
 {
         return &armv6pmu;
 }
@@ -655,17 +655,17 @@ static const struct arm_pmu armv6mpcore_pmu = {
         .max_period             = (1LLU << 32) - 1,
 };
 
-const struct arm_pmu *__init armv6mpcore_pmu_init(void)
+static const struct arm_pmu *__init armv6mpcore_pmu_init(void)
 {
         return &armv6mpcore_pmu;
 }
 #else
-const struct arm_pmu *__init armv6pmu_init(void)
+static const struct arm_pmu *__init armv6pmu_init(void)
 {
         return NULL;
 }
 
-const struct arm_pmu *__init armv6mpcore_pmu_init(void)
+static const struct arm_pmu *__init armv6mpcore_pmu_init(void)
 {
         return NULL;
 }
diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index 4d0423969df..2e1402556fa 100644
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -681,7 +681,7 @@ static void armv7_pmnc_dump_regs(void)
 }
 #endif
 
-void armv7pmu_enable_event(struct hw_perf_event *hwc, int idx)
+static void armv7pmu_enable_event(struct hw_perf_event *hwc, int idx)
 {
         unsigned long flags;
 
@@ -689,7 +689,7 @@ void armv7pmu_enable_event(struct hw_perf_event *hwc, int idx)
          * Enable counter and interrupt, and set the counter to count
          * the event that we're interested in.
          */
-        spin_lock_irqsave(&pmu_lock, flags);
+        raw_spin_lock_irqsave(&pmu_lock, flags);
 
         /*
          * Disable counter
@@ -713,7 +713,7 @@ void armv7pmu_enable_event(struct hw_perf_event *hwc, int idx)
          */
         armv7_pmnc_enable_counter(idx);
 
-        spin_unlock_irqrestore(&pmu_lock, flags);
+        raw_spin_unlock_irqrestore(&pmu_lock, flags);
 }
 
 static void armv7pmu_disable_event(struct hw_perf_event *hwc, int idx)
@@ -723,7 +723,7 @@ static void armv7pmu_disable_event(struct hw_perf_event *hwc, int idx)
         /*
          * Disable counter and interrupt
          */
-        spin_lock_irqsave(&pmu_lock, flags);
+        raw_spin_lock_irqsave(&pmu_lock, flags);
 
         /*
          * Disable counter
@@ -735,7 +735,7 @@ static void armv7pmu_disable_event(struct hw_perf_event *hwc, int idx)
          */
         armv7_pmnc_disable_intens(idx);
 
-        spin_unlock_irqrestore(&pmu_lock, flags);
+        raw_spin_unlock_irqrestore(&pmu_lock, flags);
 }
 
 static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev)
@@ -805,20 +805,20 @@ static void armv7pmu_start(void)
 {
         unsigned long flags;
 
-        spin_lock_irqsave(&pmu_lock, flags);
+        raw_spin_lock_irqsave(&pmu_lock, flags);
         /* Enable all counters */
         armv7_pmnc_write(armv7_pmnc_read() | ARMV7_PMNC_E);
-        spin_unlock_irqrestore(&pmu_lock, flags);
+        raw_spin_unlock_irqrestore(&pmu_lock, flags);
 }
 
 static void armv7pmu_stop(void)
 {
         unsigned long flags;
 
-        spin_lock_irqsave(&pmu_lock, flags);
+        raw_spin_lock_irqsave(&pmu_lock, flags);
         /* Disable all counters */
         armv7_pmnc_write(armv7_pmnc_read() & ~ARMV7_PMNC_E);
-        spin_unlock_irqrestore(&pmu_lock, flags);
+        raw_spin_unlock_irqrestore(&pmu_lock, flags);
 }
 
 static int armv7pmu_get_event_idx(struct cpu_hw_events *cpuc,
@@ -874,7 +874,7 @@ static u32 __init armv7_reset_read_pmnc(void)
         return nb_cnt + 1;
 }
 
-const struct arm_pmu *__init armv7_a8_pmu_init(void)
+static const struct arm_pmu *__init armv7_a8_pmu_init(void)
 {
         armv7pmu.id             = ARM_PERF_PMU_ID_CA8;
         armv7pmu.name           = "ARMv7 Cortex-A8";
@@ -884,7 +884,7 @@ const struct arm_pmu *__init armv7_a8_pmu_init(void)
         return &armv7pmu;
 }
 
-const struct arm_pmu *__init armv7_a9_pmu_init(void)
+static const struct arm_pmu *__init armv7_a9_pmu_init(void)
 {
         armv7pmu.id             = ARM_PERF_PMU_ID_CA9;
         armv7pmu.name           = "ARMv7 Cortex-A9";
@@ -894,12 +894,12 @@ const struct arm_pmu *__init armv7_a9_pmu_init(void)
         return &armv7pmu;
 }
 #else
-const struct arm_pmu *__init armv7_a8_pmu_init(void)
+static const struct arm_pmu *__init armv7_a8_pmu_init(void)
 {
         return NULL;
 }
 
-const struct arm_pmu *__init armv7_a9_pmu_init(void)
+static const struct arm_pmu *__init armv7_a9_pmu_init(void)
 {
         return NULL;
 }
diff --git a/arch/arm/kernel/perf_event_xscale.c b/arch/arm/kernel/perf_event_xscale.c
index 4e9592789d4..28cd3b025bc 100644
--- a/arch/arm/kernel/perf_event_xscale.c
+++ b/arch/arm/kernel/perf_event_xscale.c
@@ -291,12 +291,12 @@ xscale1pmu_enable_event(struct hw_perf_event *hwc, int idx)
                 return;
         }
 
-        spin_lock_irqsave(&pmu_lock, flags);
+        raw_spin_lock_irqsave(&pmu_lock, flags);
         val = xscale1pmu_read_pmnc();
         val &= ~mask;
         val |= evt;
         xscale1pmu_write_pmnc(val);
-        spin_unlock_irqrestore(&pmu_lock, flags);
+        raw_spin_unlock_irqrestore(&pmu_lock, flags);
 }
 
 static void
@@ -322,12 +322,12 @@ xscale1pmu_disable_event(struct hw_perf_event *hwc, int idx)
                 return;
         }
 
-        spin_lock_irqsave(&pmu_lock, flags);
+        raw_spin_lock_irqsave(&pmu_lock, flags);
         val = xscale1pmu_read_pmnc();
         val &= ~mask;
         val |= evt;
         xscale1pmu_write_pmnc(val);
-        spin_unlock_irqrestore(&pmu_lock, flags);
+        raw_spin_unlock_irqrestore(&pmu_lock, flags);
 }
 
 static int
@@ -355,11 +355,11 @@ xscale1pmu_start(void)
 {
         unsigned long flags, val;
 
-        spin_lock_irqsave(&pmu_lock, flags);
+        raw_spin_lock_irqsave(&pmu_lock, flags);
         val = xscale1pmu_read_pmnc();
         val |= XSCALE_PMU_ENABLE;
         xscale1pmu_write_pmnc(val);
-        spin_unlock_irqrestore(&pmu_lock, flags);
+        raw_spin_unlock_irqrestore(&pmu_lock, flags);
 }
 
 static void
@@ -367,11 +367,11 @@ xscale1pmu_stop(void)
 {
         unsigned long flags, val;
 
-        spin_lock_irqsave(&pmu_lock, flags);
+        raw_spin_lock_irqsave(&pmu_lock, flags);
         val = xscale1pmu_read_pmnc();
         val &= ~XSCALE_PMU_ENABLE;
         xscale1pmu_write_pmnc(val);
-        spin_unlock_irqrestore(&pmu_lock, flags);
+        raw_spin_unlock_irqrestore(&pmu_lock, flags);
 }
 
 static inline u32
@@ -428,7 +428,7 @@ static const struct arm_pmu xscale1pmu = {
         .max_period     = (1LLU << 32) - 1,
 };
 
-const struct arm_pmu *__init xscale1pmu_init(void)
+static const struct arm_pmu *__init xscale1pmu_init(void)
 {
         return &xscale1pmu;
 }
@@ -635,10 +635,10 @@ xscale2pmu_enable_event(struct hw_perf_event *hwc, int idx)
                 return;
         }
 
-        spin_lock_irqsave(&pmu_lock, flags);
+        raw_spin_lock_irqsave(&pmu_lock, flags);
         xscale2pmu_write_event_select(evtsel);
         xscale2pmu_write_int_enable(ien);
-        spin_unlock_irqrestore(&pmu_lock, flags);
+        raw_spin_unlock_irqrestore(&pmu_lock, flags);
 }
 
 static void
@@ -678,10 +678,10 @@ xscale2pmu_disable_event(struct hw_perf_event *hwc, int idx)
                 return;
         }
 
-        spin_lock_irqsave(&pmu_lock, flags);
+        raw_spin_lock_irqsave(&pmu_lock, flags);
         xscale2pmu_write_event_select(evtsel);
         xscale2pmu_write_int_enable(ien);
-        spin_unlock_irqrestore(&pmu_lock, flags);
+        raw_spin_unlock_irqrestore(&pmu_lock, flags);
 }
 
 static int
@@ -705,11 +705,11 @@ xscale2pmu_start(void)
 {
         unsigned long flags, val;
 
-        spin_lock_irqsave(&pmu_lock, flags);
+        raw_spin_lock_irqsave(&pmu_lock, flags);
         val = xscale2pmu_read_pmnc() & ~XSCALE_PMU_CNT64;
         val |= XSCALE_PMU_ENABLE;
         xscale2pmu_write_pmnc(val);
-        spin_unlock_irqrestore(&pmu_lock, flags);
+        raw_spin_unlock_irqrestore(&pmu_lock, flags);
 }
 
 static void
@@ -717,11 +717,11 @@ xscale2pmu_stop(void)
 {
         unsigned long flags, val;
 
-        spin_lock_irqsave(&pmu_lock, flags);
+        raw_spin_lock_irqsave(&pmu_lock, flags);
         val = xscale2pmu_read_pmnc();
         val &= ~XSCALE_PMU_ENABLE;
         xscale2pmu_write_pmnc(val);
-        spin_unlock_irqrestore(&pmu_lock, flags);
+        raw_spin_unlock_irqrestore(&pmu_lock, flags);
 }
 
 static inline u32
@@ -790,17 +790,17 @@ static const struct arm_pmu xscale2pmu = {
         .max_period     = (1LLU << 32) - 1,
 };
 
-const struct arm_pmu *__init xscale2pmu_init(void)
+static const struct arm_pmu *__init xscale2pmu_init(void)
 {
         return &xscale2pmu;
 }
 #else
-const struct arm_pmu *__init xscale1pmu_init(void)
+static const struct arm_pmu *__init xscale1pmu_init(void)
 {
         return NULL;
 }
 
-const struct arm_pmu *__init xscale2pmu_init(void)
+static const struct arm_pmu *__init xscale2pmu_init(void)
 {
         return NULL;
 }
diff --git a/arch/arm/kernel/pj4-cp0.c b/arch/arm/kernel/pj4-cp0.c
new file mode 100644
index 00000000000..a4b1b0748fd
--- /dev/null
+++ b/arch/arm/kernel/pj4-cp0.c
@@ -0,0 +1,94 @@
+/*
+ * linux/arch/arm/kernel/pj4-cp0.c
+ *
+ * PJ4 iWMMXt coprocessor context switching and handling
+ *
+ * Copyright (c) 2010 Marvell International Inc.
+ *
+ * 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/module.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <asm/thread_notify.h>
+
+static int iwmmxt_do(struct notifier_block *self, unsigned long cmd, void *t)
+{
+        struct thread_info *thread = t;
+
+        switch (cmd) {
+        case THREAD_NOTIFY_FLUSH:
+                /*
+                 * flush_thread() zeroes thread->fpstate, so no need
+                 * to do anything here.
+                 *
+                 * FALLTHROUGH: Ensure we don't try to overwrite our newly
+                 * initialised state information on the first fault.
+                 */
+
+        case THREAD_NOTIFY_EXIT:
+                iwmmxt_task_release(thread);
+                break;
+
+        case THREAD_NOTIFY_SWITCH:
+                iwmmxt_task_switch(thread);
+                break;
+        }
+
+        return NOTIFY_DONE;
+}
+
+static struct notifier_block iwmmxt_notifier_block = {
+        .notifier_call  = iwmmxt_do,
+};
+
+
+static u32 __init pj4_cp_access_read(void)
+{
+        u32 value;
+
+        __asm__ __volatile__ (
+                "mrc    p15, 0, %0, c1, c0, 2\n\t"
+                : "=r" (value));
+        return value;
+}
+
+static void __init pj4_cp_access_write(u32 value)
+{
+        u32 temp;
+
+        __asm__ __volatile__ (
+                "mcr    p15, 0, %1, c1, c0, 2\n\t"
+                "mrc    p15, 0, %0, c1, c0, 2\n\t"
+                "mov    %0, %0\n\t"
+                "sub    pc, pc, #4\n\t"
+                : "=r" (temp) : "r" (value));
+}
+
+
+/*
+ * Disable CP0/CP1 on boot, and let call_fpe() and the iWMMXt lazy
+ * switch code handle iWMMXt context switching.
+ */
+static int __init pj4_cp0_init(void)
+{
+        u32 cp_access;
+
+        cp_access = pj4_cp_access_read() & ~0xf;
+        pj4_cp_access_write(cp_access);
+
+        printk(KERN_INFO "PJ4 iWMMXt coprocessor enabled.\n");
+        elf_hwcap |= HWCAP_IWMMXT;
+        thread_register_notifier(&iwmmxt_notifier_block);
+
+        return 0;
+}
+
+late_initcall(pj4_cp0_init);
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index 3e97483abcf..19c6816db61 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -1060,8 +1060,8 @@ static int ptrace_sethbpregs(struct task_struct *tsk, long num,
                         goto out;
 
                 if ((gen_type & implied_type) != gen_type) {
-                                ret = -EINVAL;
-                                goto out;
+                        ret = -EINVAL;
+                        goto out;
                 }
 
                 attr.bp_len     = gen_len;