Merge branch 'devel' of master.kernel.org:/home/rmk/linux-2.6-arm

* 'devel' of master.kernel.org:/home/rmk/linux-2.6-arm: (416 commits)
  ARM: DMA: add support for DMA debugging
  ARM: PL011: add DMA burst threshold support for ST variants
  ARM: PL011: Add support for transmit DMA
  ARM: PL011: Ensure IRQs are disabled in UART interrupt handler
  ARM: PL011: Separate hardware FIFO size from TTY FIFO size
  ARM: PL011: Allow better handling of vendor data
  ARM: PL011: Ensure error flags are clear at startup
  ARM: PL011: include revision number in boot-time port printk
  ARM: vexpress: add sched_clock() for Versatile Express
  ARM i.MX53: Make MX53 EVK bootable
  ARM i.MX53: Some bug fix about MX53 MSL code
  ARM: 6607/1: sa1100: Update platform device registration
  ARM: 6606/1: sa1100: Fix platform device registration
  ARM i.MX51: rename IPU irqs
  ARM i.MX51: Add ipu clock support
  ARM: imx/mx27_3ds: Add PMIC support
  ARM: DMA: Replace page_to_dma()/dma_to_page() with pfn_to_dma()/dma_to_pfn()
  mx51: fix usb clock support
  MX51: Add support for usb host 2
  arch/arm/plat-mxc/ehci.c: fix errors/typos
  ...

27 files changed, 3989 insertions, 3189 deletions

diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index 5b9b268f4fbb..185ee822c935 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -5,7 +5,7 @@
 CPPFLAGS_vmlinux.lds := -DTEXT_OFFSET=$(TEXT_OFFSET)
 AFLAGS_head.o        := -DTEXT_OFFSET=$(TEXT_OFFSET)
 
-ifdef CONFIG_DYNAMIC_FTRACE
+ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_ftrace.o = -pg
 endif
 
@@ -29,10 +29,12 @@ obj-$(CONFIG_MODULES)		+= armksyms.o module.o
 obj-$(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_SCHED_CLOCK)  += sched_clock.o
+obj-$(CONFIG_SMP)               += smp.o smp_tlb.o
 obj-$(CONFIG_HAVE_ARM_SCU)      += smp_scu.o
 obj-$(CONFIG_HAVE_ARM_TWD)      += smp_twd.o
 obj-$(CONFIG_DYNAMIC_FTRACE)    += ftrace.o
+obj-$(CONFIG_FUNCTION_GRAPH_TRACER)     += ftrace.o
 obj-$(CONFIG_KEXEC)             += machine_kexec.o relocate_kernel.o
 obj-$(CONFIG_KPROBES)           += kprobes.o kprobes-decode.o
 obj-$(CONFIG_ATAGS_PROC)        += atags.o
@@ -42,6 +44,8 @@ obj-$(CONFIG_KGDB)		+= kgdb.o
 obj-$(CONFIG_ARM_UNWIND)        += unwind.o
 obj-$(CONFIG_HAVE_TCM)          += tcm.o
 obj-$(CONFIG_CRASH_DUMP)        += crash_dump.o
+obj-$(CONFIG_SWP_EMULATE)       += swp_emulate.o
+CFLAGS_swp_emulate.o            := -Wa,-march=armv7-a
 obj-$(CONFIG_HAVE_HW_BREAKPOINT)        += hw_breakpoint.o
 
 obj-$(CONFIG_CRUNCH)            += crunch.o crunch-bits.o
@@ -50,6 +54,7 @@ AFLAGS_crunch-bits.o		:= -Wa,-mcpu=ep9312
 obj-$(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 bb96a7d4bbf5..2b46fea36c9f 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -25,42 +25,22 @@
 #include <asm/tls.h>
 
 #include "entry-header.S"
+#include <asm/entry-macro-multi.S>
 
 /*
  * Interrupt handling.  Preserves r7, r8, r9
  */
         .macro  irq_handler
-        get_irqnr_preamble r5, lr
-1:      get_irqnr_and_base r0, r6, r5, lr
-        movne   r1, sp
-        @
-        @ routine called with r0 = irq number, r1 = struct pt_regs *
-        @
-        adrne   lr, BSYM(1b)
-        bne     asm_do_IRQ
-
-#ifdef CONFIG_SMP
-        /*
-         * XXX
-         *
-         * this macro assumes that irqstat (r6) and base (r5) are
-         * preserved from get_irqnr_and_base above
-         */
-        ALT_SMP(test_for_ipi r0, r6, r5, lr)
-        ALT_UP_B(9997f)
-        movne   r0, sp
-        adrne   lr, BSYM(1b)
-        bne     do_IPI
-
-#ifdef CONFIG_LOCAL_TIMERS
-        test_for_ltirq r0, r6, r5, lr
-        movne   r0, sp
-        adrne   lr, BSYM(1b)
-        bne     do_local_timer
+#ifdef CONFIG_MULTI_IRQ_HANDLER
+        ldr     r5, =handle_arch_irq
+        mov     r0, sp
+        ldr     r5, [r5]
+        adr     lr, BSYM(9997f)
+        teq     r5, #0
+        movne   pc, r5
 #endif
+        arch_irq_handler_default
 9997:
-#endif
-
         .endm
 
 #ifdef CONFIG_KPROBES
@@ -198,6 +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
@@ -324,6 +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
@@ -439,6 +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)
@@ -703,6 +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
@@ -735,7 +719,7 @@ ENTRY(__switch_to)
  THUMB( stmia   ip!, {r4 - sl, fp}         )    @ Store most regs on stack
  THUMB( str     sp, [ip], #4               )
  THUMB( str     lr, [ip], #4               )
-#ifdef CONFIG_MMU
+#ifdef CONFIG_CPU_USE_DOMAINS
         ldr     r6, [r2, #TI_CPU_DOMAIN]
 #endif
         set_tls r3, r4, r5
@@ -744,7 +728,7 @@ ENTRY(__switch_to)
         ldr     r8, =__stack_chk_guard
         ldr     r7, [r7, #TSK_STACK_CANARY]
 #endif
-#ifdef CONFIG_MMU
+#ifdef CONFIG_CPU_USE_DOMAINS
         mcr     p15, 0, r6, c3, c0, 0           @ Set domain register
 #endif
         mov     r5, r0
@@ -842,7 +826,7 @@ __kuser_helper_start:
  */
 
 __kuser_memory_barrier:                         @ 0xffff0fa0
-        smp_dmb
+        smp_dmb arm
         usr_ret lr
 
         .align  5
@@ -959,7 +943,7 @@ kuser_cmpxchg_fixup:
 
 #else
 
-        smp_dmb
+        smp_dmb arm
 1:      ldrex   r3, [r2]
         subs    r3, r3, r0
         strexeq r3, r1, [r2]
@@ -1245,3 +1229,9 @@ cr_alignment:
         .space  4
 cr_no_alignment:
         .space  4
+
+#ifdef CONFIG_MULTI_IRQ_HANDLER
+        .globl  handle_arch_irq
+handle_arch_irq:
+        .space  4
+#endif
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 80bf8cd88d7c..1e7b04a40a31 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -147,98 +147,170 @@ ENDPROC(ret_from_fork)
 #endif
 #endif
 
-#ifdef CONFIG_DYNAMIC_FTRACE
-ENTRY(__gnu_mcount_nc)
-        mov     ip, lr
-        ldmia   sp!, {lr}
-        mov     pc, ip
-ENDPROC(__gnu_mcount_nc)
+.macro __mcount suffix
+        mcount_enter
+        ldr     r0, =ftrace_trace_function
+        ldr     r2, [r0]
+        adr     r0, .Lftrace_stub
+        cmp     r0, r2
+        bne     1f
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+        ldr     r1, =ftrace_graph_return
+        ldr     r2, [r1]
+        cmp     r0, r2
+        bne     ftrace_graph_caller\suffix
+
+        ldr     r1, =ftrace_graph_entry
+        ldr     r2, [r1]
+        ldr     r0, =ftrace_graph_entry_stub
+        cmp     r0, r2
+        bne     ftrace_graph_caller\suffix
+#endif
 
-ENTRY(ftrace_caller)
-        stmdb   sp!, {r0-r3, lr}
-        mov     r0, lr
+        mcount_exit
+
+1:      mcount_get_lr   r1                      @ lr of instrumented func
+        mov     r0, lr                          @ instrumented function
+        sub     r0, r0, #MCOUNT_INSN_SIZE
+        adr     lr, BSYM(2f)
+        mov     pc, r2
+2:      mcount_exit
+.endm
+
+.macro __ftrace_caller suffix
+        mcount_enter
+
+        mcount_get_lr   r1                      @ lr of instrumented func
+        mov     r0, lr                          @ instrumented function
         sub     r0, r0, #MCOUNT_INSN_SIZE
-        ldr     r1, [sp, #20]
 
-        .global ftrace_call
-ftrace_call:
+        .globl ftrace_call\suffix
+ftrace_call\suffix:
         bl      ftrace_stub
-        ldmia   sp!, {r0-r3, ip, lr}
-        mov     pc, ip
-ENDPROC(ftrace_caller)
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+        .globl ftrace_graph_call\suffix
+ftrace_graph_call\suffix:
+        mov     r0, r0
+#endif
+
+        mcount_exit
+.endm
+
+.macro __ftrace_graph_caller
+        sub     r0, fp, #4              @ &lr of instrumented routine (&parent)
+#ifdef CONFIG_DYNAMIC_FTRACE
+        @ called from __ftrace_caller, saved in mcount_enter
+        ldr     r1, [sp, #16]           @ instrumented routine (func)
+#else
+        @ called from __mcount, untouched in lr
+        mov     r1, lr                  @ instrumented routine (func)
+#endif
+        sub     r1, r1, #MCOUNT_INSN_SIZE
+        mov     r2, fp                  @ frame pointer
+        bl      prepare_ftrace_return
+        mcount_exit
+.endm
 
 #ifdef CONFIG_OLD_MCOUNT
+/*
+ * mcount
+ */
+
+.macro mcount_enter
+        stmdb   sp!, {r0-r3, lr}
+.endm
+
+.macro mcount_get_lr reg
+        ldr     \reg, [fp, #-4]
+.endm
+
+.macro mcount_exit
+        ldr     lr, [fp, #-4]
+        ldmia   sp!, {r0-r3, pc}
+.endm
+
 ENTRY(mcount)
+#ifdef CONFIG_DYNAMIC_FTRACE
         stmdb   sp!, {lr}
         ldr     lr, [fp, #-4]
         ldmia   sp!, {pc}
+#else
+        __mcount _old
+#endif
 ENDPROC(mcount)
 
+#ifdef CONFIG_DYNAMIC_FTRACE
 ENTRY(ftrace_caller_old)
-        stmdb   sp!, {r0-r3, lr}
-        ldr     r1, [fp, #-4]
-        mov     r0, lr
-        sub     r0, r0, #MCOUNT_INSN_SIZE
-
-        .globl ftrace_call_old
-ftrace_call_old:
-        bl      ftrace_stub
-        ldr     lr, [fp, #-4]                   @ restore lr
-        ldmia   sp!, {r0-r3, pc}
+        __ftrace_caller _old
 ENDPROC(ftrace_caller_old)
 #endif
 
-#else
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ENTRY(ftrace_graph_caller_old)
+        __ftrace_graph_caller
+ENDPROC(ftrace_graph_caller_old)
+#endif
 
-ENTRY(__gnu_mcount_nc)
+.purgem mcount_enter
+.purgem mcount_get_lr
+.purgem mcount_exit
+#endif
+
+/*
+ * __gnu_mcount_nc
+ */
+
+.macro mcount_enter
         stmdb   sp!, {r0-r3, lr}
-        ldr     r0, =ftrace_trace_function
-        ldr     r2, [r0]
-        adr     r0, .Lftrace_stub
-        cmp     r0, r2
-        bne     gnu_trace
+.endm
+
+.macro mcount_get_lr reg
+        ldr     \reg, [sp, #20]
+.endm
+
+.macro mcount_exit
         ldmia   sp!, {r0-r3, ip, lr}
         mov     pc, ip
+.endm
 
-gnu_trace:
-        ldr     r1, [sp, #20]                   @ lr of instrumented routine
-        mov     r0, lr
-        sub     r0, r0, #MCOUNT_INSN_SIZE
-        adr     lr, BSYM(1f)
-        mov     pc, r2
-1:
-        ldmia   sp!, {r0-r3, ip, lr}
+ENTRY(__gnu_mcount_nc)
+#ifdef CONFIG_DYNAMIC_FTRACE
+        mov     ip, lr
+        ldmia   sp!, {lr}
         mov     pc, ip
+#else
+        __mcount
+#endif
 ENDPROC(__gnu_mcount_nc)
 
-#ifdef CONFIG_OLD_MCOUNT
-/*
- * This is under an ifdef in order to force link-time errors for people trying
- * to build with !FRAME_POINTER with a GCC which doesn't use the new-style
- * mcount.
- */
-ENTRY(mcount)
-        stmdb   sp!, {r0-r3, lr}
-        ldr     r0, =ftrace_trace_function
-        ldr     r2, [r0]
-        adr     r0, ftrace_stub
-        cmp     r0, r2
-        bne     trace
-        ldr     lr, [fp, #-4]                   @ restore lr
-        ldmia   sp!, {r0-r3, pc}
+#ifdef CONFIG_DYNAMIC_FTRACE
+ENTRY(ftrace_caller)
+        __ftrace_caller
+ENDPROC(ftrace_caller)
+#endif
 
-trace:
-        ldr     r1, [fp, #-4]                   @ lr of instrumented routine
-        mov     r0, lr
-        sub     r0, r0, #MCOUNT_INSN_SIZE
-        mov     lr, pc
-        mov     pc, r2
-        ldr     lr, [fp, #-4]                   @ restore lr
-        ldmia   sp!, {r0-r3, pc}
-ENDPROC(mcount)
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ENTRY(ftrace_graph_caller)
+        __ftrace_graph_caller
+ENDPROC(ftrace_graph_caller)
 #endif
 
-#endif /* CONFIG_DYNAMIC_FTRACE */
+.purgem mcount_enter
+.purgem mcount_get_lr
+.purgem mcount_exit
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+        .globl return_to_handler
+return_to_handler:
+        stmdb   sp!, {r0-r3}
+        mov     r0, fp                  @ frame pointer
+        bl      ftrace_return_to_handler
+        mov     lr, r0                  @ r0 has real ret addr
+        ldmia   sp!, {r0-r3}
+        mov     pc, lr
+#endif
 
 ENTRY(ftrace_stub)
 .Lftrace_stub:
diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S
index d93f976fb389..ae9464900168 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/fiq.c b/arch/arm/kernel/fiq.c
index 6ff7919613d7..e72dc34eea1c 100644
--- a/arch/arm/kernel/fiq.c
+++ b/arch/arm/kernel/fiq.c
@@ -45,6 +45,7 @@
 #include <asm/fiq.h>
 #include <asm/irq.h>
 #include <asm/system.h>
+#include <asm/traps.h>
 
 static unsigned long no_fiq_insn;
 
@@ -67,17 +68,22 @@ static struct fiq_handler default_owner = {
 
 static struct fiq_handler *current_fiq = &default_owner;
 
-int show_fiq_list(struct seq_file *p, void *v)
+int show_fiq_list(struct seq_file *p, int prec)
 {
         if (current_fiq != &default_owner)
-                seq_printf(p, "FIQ:              %s\n", current_fiq->name);
+                seq_printf(p, "%*s:              %s\n", prec, "FIQ",
+                        current_fiq->name);
 
         return 0;
 }
 
 void set_fiq_handler(void *start, unsigned int length)
 {
+#if defined(CONFIG_CPU_USE_DOMAINS)
         memcpy((void *)0xffff001c, start, length);
+#else
+        memcpy(vectors_page + 0x1c, start, length);
+#endif
         flush_icache_range(0xffff001c, 0xffff001c + length);
         if (!vectors_high())
                 flush_icache_range(0x1c, 0x1c + length);
diff --git a/arch/arm/kernel/ftrace.c b/arch/arm/kernel/ftrace.c
index 971ac8c36ea7..c0062ad1e847 100644
--- a/arch/arm/kernel/ftrace.c
+++ b/arch/arm/kernel/ftrace.c
@@ -24,6 +24,7 @@
 #define NOP             0xe8bd4000      /* pop {lr} */
 #endif
 
+#ifdef CONFIG_DYNAMIC_FTRACE
 #ifdef CONFIG_OLD_MCOUNT
 #define OLD_MCOUNT_ADDR ((unsigned long) mcount)
 #define OLD_FTRACE_ADDR ((unsigned long) ftrace_caller_old)
@@ -59,9 +60,9 @@ static unsigned long adjust_address(struct dyn_ftrace *rec, unsigned long addr)
 }
 #endif
 
-/* construct a branch (BL) instruction to addr */
 #ifdef CONFIG_THUMB2_KERNEL
-static unsigned long ftrace_call_replace(unsigned long pc, unsigned long addr)
+static unsigned long ftrace_gen_branch(unsigned long pc, unsigned long addr,
+                                       bool link)
 {
         unsigned long s, j1, j2, i1, i2, imm10, imm11;
         unsigned long first, second;
@@ -83,15 +84,22 @@ static unsigned long ftrace_call_replace(unsigned long pc, unsigned long addr)
         j2 = (!i2) ^ s;
 
         first = 0xf000 | (s << 10) | imm10;
-        second = 0xd000 | (j1 << 13) | (j2 << 11) | imm11;
+        second = 0x9000 | (j1 << 13) | (j2 << 11) | imm11;
+        if (link)
+                second |= 1 << 14;
 
         return (second << 16) | first;
 }
 #else
-static unsigned long ftrace_call_replace(unsigned long pc, unsigned long addr)
+static unsigned long ftrace_gen_branch(unsigned long pc, unsigned long addr,
+                                       bool link)
 {
+        unsigned long opcode = 0xea000000;
         long offset;
 
+        if (link)
+                opcode |= 1 << 24;
+
         offset = (long)addr - (long)(pc + 8);
         if (unlikely(offset < -33554432 || offset > 33554428)) {
                 /* Can't generate branches that far (from ARM ARM). Ftrace
@@ -103,10 +111,15 @@ static unsigned long ftrace_call_replace(unsigned long pc, unsigned long addr)
 
         offset = (offset >> 2) & 0x00ffffff;
 
-        return 0xeb000000 | offset;
+        return opcode | offset;
 }
 #endif
 
+static unsigned long ftrace_call_replace(unsigned long pc, unsigned long addr)
+{
+        return ftrace_gen_branch(pc, addr, true);
+}
+
 static int ftrace_modify_code(unsigned long pc, unsigned long old,
                               unsigned long new)
 {
@@ -193,3 +206,83 @@ int __init ftrace_dyn_arch_init(void *data)
 
         return 0;
 }
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
+                           unsigned long frame_pointer)
+{
+        unsigned long return_hooker = (unsigned long) &return_to_handler;
+        struct ftrace_graph_ent trace;
+        unsigned long old;
+        int err;
+
+        if (unlikely(atomic_read(&current->tracing_graph_pause)))
+                return;
+
+        old = *parent;
+        *parent = return_hooker;
+
+        err = ftrace_push_return_trace(old, self_addr, &trace.depth,
+                                       frame_pointer);
+        if (err == -EBUSY) {
+                *parent = old;
+                return;
+        }
+
+        trace.func = self_addr;
+
+        /* Only trace if the calling function expects to */
+        if (!ftrace_graph_entry(&trace)) {
+                current->curr_ret_stack--;
+                *parent = old;
+        }
+}
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+extern unsigned long ftrace_graph_call;
+extern unsigned long ftrace_graph_call_old;
+extern void ftrace_graph_caller_old(void);
+
+static int __ftrace_modify_caller(unsigned long *callsite,
+                                  void (*func) (void), bool enable)
+{
+        unsigned long caller_fn = (unsigned long) func;
+        unsigned long pc = (unsigned long) callsite;
+        unsigned long branch = ftrace_gen_branch(pc, caller_fn, false);
+        unsigned long nop = 0xe1a00000; /* mov r0, r0 */
+        unsigned long old = enable ? nop : branch;
+        unsigned long new = enable ? branch : nop;
+
+        return ftrace_modify_code(pc, old, new);
+}
+
+static int ftrace_modify_graph_caller(bool enable)
+{
+        int ret;
+
+        ret = __ftrace_modify_caller(&ftrace_graph_call,
+                                     ftrace_graph_caller,
+                                     enable);
+
+#ifdef CONFIG_OLD_MCOUNT
+        if (!ret)
+                ret = __ftrace_modify_caller(&ftrace_graph_call_old,
+                                             ftrace_graph_caller_old,
+                                             enable);
+#endif
+
+        return ret;
+}
+
+int ftrace_enable_ftrace_graph_caller(void)
+{
+        return ftrace_modify_graph_caller(true);
+}
+
+int ftrace_disable_ftrace_graph_caller(void)
+{
+        return ftrace_modify_graph_caller(false);
+}
+#endif /* CONFIG_DYNAMIC_FTRACE */
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 6bd82d25683c..f17d9a09e8fb 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -91,6 +91,11 @@ ENTRY(stext)
         movs    r8, r5                          @ invalid machine (r5=0)?
  THUMB( it      eq )            @ force fixup-able long branch encoding
         beq     __error_a                       @ yes, error 'a'
+
+        /*
+         * r1 = machine no, r2 = atags,
+         * r8 = machinfo, r9 = cpuid, r10 = procinfo
+         */
         bl      __vet_atags
 #ifdef CONFIG_SMP_ON_UP
         bl      __fixup_smp
@@ -387,19 +392,19 @@ ENDPROC(__turn_mmu_on)
 
 #ifdef CONFIG_SMP_ON_UP
 __fixup_smp:
-        mov     r7, #0x00070000
-        orr     r6, r7, #0xff000000     @ mask 0xff070000
-        orr     r7, r7, #0x41000000     @ val 0x41070000
-        and     r0, r9, r6
-        teq     r0, r7                  @ ARM CPU and ARMv6/v7?
+        mov     r4, #0x00070000
+        orr     r3, r4, #0xff000000     @ mask 0xff070000
+        orr     r4, r4, #0x41000000     @ val 0x41070000
+        and     r0, r9, r3
+        teq     r0, r4                  @ ARM CPU and ARMv6/v7?
         bne     __fixup_smp_on_up       @ no, assume UP
 
-        orr     r6, r6, #0x0000ff00
-        orr     r6, r6, #0x000000f0     @ mask 0xff07fff0
-        orr     r7, r7, #0x0000b000
-        orr     r7, r7, #0x00000020     @ val 0x4107b020
-        and     r0, r9, r6
-        teq     r0, r7                  @ ARM 11MPCore?
+        orr     r3, r3, #0x0000ff00
+        orr     r3, r3, #0x000000f0     @ mask 0xff07fff0
+        orr     r4, r4, #0x0000b000
+        orr     r4, r4, #0x00000020     @ val 0x4107b020
+        and     r0, r9, r3
+        teq     r0, r4                  @ ARM 11MPCore?
         moveq   pc, lr                  @ yes, assume SMP
 
         mrc     p15, 0, r0, c0, c0, 5   @ read MPIDR
@@ -408,15 +413,22 @@ __fixup_smp:
 
 __fixup_smp_on_up:
         adr     r0, 1f
-        ldmia   r0, {r3, r6, r7}
+        ldmia   r0, {r3 - r5}
         sub     r3, r0, r3
-        add     r6, r6, r3
-        add     r7, r7, r3
-2:      cmp     r6, r7
-        ldmia   r6!, {r0, r4}
-        strlo   r4, [r0, r3]
-        blo     2b
-        mov     pc, lr
+        add     r4, r4, r3
+        add     r5, r5, r3
+2:      cmp     r4, r5
+        movhs   pc, lr
+        ldmia   r4!, {r0, r6}
+ ARM(   str     r6, [r0, r3]    )
+ THUMB( add     r0, r0, r3      )
+#ifdef __ARMEB__
+ THUMB( mov     r6, r6, ror #16 )       @ Convert word order for big-endian.
+#endif
+ THUMB( strh    r6, [r0], #2    )       @ For Thumb-2, store as two halfwords
+ THUMB( mov     r6, r6, lsr #16 )       @ to be robust against misaligned r3.
+ THUMB( strh    r6, [r0]        )
+        b       2b
 ENDPROC(__fixup_smp)
 
         .align
diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c
index 21e3a4ab3b8c..c9f3f0467570 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/irq.c b/arch/arm/kernel/irq.c
index 36ad3be4692a..8135438b8818 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -35,8 +35,10 @@
 #include <linux/list.h>
 #include <linux/kallsyms.h>
 #include <linux/proc_fs.h>
+#include <linux/ftrace.h>
 
 #include <asm/system.h>
+#include <asm/mach/arch.h>
 #include <asm/mach/irq.h>
 #include <asm/mach/time.h>
 
@@ -47,8 +49,6 @@
 #define irq_finish(irq) do { } while (0)
 #endif
 
-unsigned int arch_nr_irqs;
-void (*init_arch_irq)(void) __initdata = NULL;
 unsigned long irq_err_count;
 
 int show_interrupts(struct seq_file *p, void *v)
@@ -57,11 +57,20 @@ int show_interrupts(struct seq_file *p, void *v)
         struct irq_desc *desc;
         struct irqaction * action;
         unsigned long flags;
+        int prec, n;
+
+        for (prec = 3, n = 1000; prec < 10 && n <= nr_irqs; prec++)
+                n *= 10;
+
+#ifdef CONFIG_SMP
+        if (prec < 4)
+                prec = 4;
+#endif
 
         if (i == 0) {
                 char cpuname[12];
 
-                seq_printf(p, "    ");
+                seq_printf(p, "%*s ", prec, "");
                 for_each_present_cpu(cpu) {
                         sprintf(cpuname, "CPU%d", cpu);
                         seq_printf(p, " %10s", cpuname);
@@ -76,7 +85,7 @@ int show_interrupts(struct seq_file *p, void *v)
                 if (!action)
                         goto unlock;
 
-                seq_printf(p, "%3d: ", i);
+                seq_printf(p, "%*d: ", prec, i);
                 for_each_present_cpu(cpu)
                         seq_printf(p, "%10u ", kstat_irqs_cpu(i, cpu));
                 seq_printf(p, " %10s", desc->chip->name ? : "-");
@@ -89,13 +98,15 @@ unlock:
                 raw_spin_unlock_irqrestore(&desc->lock, flags);
         } else if (i == nr_irqs) {
 #ifdef CONFIG_FIQ
-                show_fiq_list(p, v);
+                show_fiq_list(p, prec);
 #endif
 #ifdef CONFIG_SMP
-                show_ipi_list(p);
-                show_local_irqs(p);
+                show_ipi_list(p, prec);
+#endif
+#ifdef CONFIG_LOCAL_TIMERS
+                show_local_irqs(p, prec);
 #endif
-                seq_printf(p, "Err: %10lu\n", irq_err_count);
+                seq_printf(p, "%*s: %10lu\n", prec, "Err", irq_err_count);
         }
         return 0;
 }
@@ -105,7 +116,8 @@ unlock:
  * come via this function.  Instead, they should provide their
  * own 'handler'
  */
-asmlinkage void __exception asm_do_IRQ(unsigned int irq, struct pt_regs *regs)
+asmlinkage void __exception_irq_entry
+asm_do_IRQ(unsigned int irq, struct pt_regs *regs)
 {
         struct pt_regs *old_regs = set_irq_regs(regs);
 
@@ -154,13 +166,13 @@ void set_irq_flags(unsigned int irq, unsigned int iflags)
 
 void __init init_IRQ(void)
 {
-        init_arch_irq();
+        machine_desc->init_irq();
 }
 
 #ifdef CONFIG_SPARSE_IRQ
 int __init arch_probe_nr_irqs(void)
 {
-        nr_irqs = arch_nr_irqs ? arch_nr_irqs : NR_IRQS;
+        nr_irqs = machine_desc->nr_irqs ? machine_desc->nr_irqs : NR_IRQS;
         return nr_irqs;
 }
 #endif
diff --git a/arch/arm/kernel/iwmmxt.S b/arch/arm/kernel/iwmmxt.S
index b63b528f22a6..7fa3bb0d2397 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/machine_kexec.c b/arch/arm/kernel/machine_kexec.c
index 3a8fd5140d7a..30ead135ff5f 100644
--- a/arch/arm/kernel/machine_kexec.c
+++ b/arch/arm/kernel/machine_kexec.c
@@ -23,6 +23,8 @@ extern unsigned long kexec_indirection_page;
 extern unsigned long kexec_mach_type;
 extern unsigned long kexec_boot_atags;
 
+static atomic_t waiting_for_crash_ipi;
+
 /*
  * Provide a dummy crash_notes definition while crash dump arrives to arm.
  * This prevents breakage of crash_notes attribute in kernel/ksysfs.c.
@@ -37,9 +39,37 @@ void machine_kexec_cleanup(struct kimage *image)
 {
 }
 
+void machine_crash_nonpanic_core(void *unused)
+{
+        struct pt_regs regs;
+
+        crash_setup_regs(&regs, NULL);
+        printk(KERN_DEBUG "CPU %u will stop doing anything useful since another CPU has crashed\n",
+               smp_processor_id());
+        crash_save_cpu(&regs, smp_processor_id());
+        flush_cache_all();
+
+        atomic_dec(&waiting_for_crash_ipi);
+        while (1)
+                cpu_relax();
+}
+
 void machine_crash_shutdown(struct pt_regs *regs)
 {
+        unsigned long msecs;
+
         local_irq_disable();
+
+        atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1);
+        smp_call_function(machine_crash_nonpanic_core, NULL, false);
+        msecs = 1000; /* Wait at most a second for the other cpus to stop */
+        while ((atomic_read(&waiting_for_crash_ipi) > 0) && msecs) {
+                mdelay(1);
+                msecs--;
+        }
+        if (atomic_read(&waiting_for_crash_ipi) > 0)
+                printk(KERN_WARNING "Non-crashing CPUs did not react to IPI\n");
+
         crash_save_cpu(regs, smp_processor_id());
 
         printk(KERN_INFO "Loading crashdump kernel...\n");
diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c
index d9bd786ce23d..0c1bb68ff4a8 100644
--- a/arch/arm/kernel/module.c
+++ b/arch/arm/kernel/module.c
@@ -67,35 +67,6 @@ int module_frob_arch_sections(Elf_Ehdr *hdr,
                               char *secstrings,
                               struct module *mod)
 {
-#ifdef CONFIG_ARM_UNWIND
-        Elf_Shdr *s, *sechdrs_end = sechdrs + hdr->e_shnum;
-        struct arm_unwind_mapping *maps = mod->arch.map;
-
-        for (s = sechdrs; s < sechdrs_end; s++) {
-                char const *secname = secstrings + s->sh_name;
-
-                if (strcmp(".ARM.exidx.init.text", secname) == 0)
-                        maps[ARM_SEC_INIT].unw_sec = s;
-                else if (strcmp(".ARM.exidx.devinit.text", secname) == 0)
-                        maps[ARM_SEC_DEVINIT].unw_sec = s;
-                else if (strcmp(".ARM.exidx", secname) == 0)
-                        maps[ARM_SEC_CORE].unw_sec = s;
-                else if (strcmp(".ARM.exidx.exit.text", secname) == 0)
-                        maps[ARM_SEC_EXIT].unw_sec = s;
-                else if (strcmp(".ARM.exidx.devexit.text", secname) == 0)
-                        maps[ARM_SEC_DEVEXIT].unw_sec = s;
-                else if (strcmp(".init.text", secname) == 0)
-                        maps[ARM_SEC_INIT].sec_text = s;
-                else if (strcmp(".devinit.text", secname) == 0)
-                        maps[ARM_SEC_DEVINIT].sec_text = s;
-                else if (strcmp(".text", secname) == 0)
-                        maps[ARM_SEC_CORE].sec_text = s;
-                else if (strcmp(".exit.text", secname) == 0)
-                        maps[ARM_SEC_EXIT].sec_text = s;
-                else if (strcmp(".devexit.text", secname) == 0)
-                        maps[ARM_SEC_DEVEXIT].sec_text = s;
-        }
-#endif
         return 0;
 }
 
@@ -300,41 +271,69 @@ apply_relocate_add(Elf32_Shdr *sechdrs, const char *strtab,
         return -ENOEXEC;
 }
 
-#ifdef CONFIG_ARM_UNWIND
-static void register_unwind_tables(struct module *mod)
+struct mod_unwind_map {
+        const Elf_Shdr *unw_sec;
+        const Elf_Shdr *txt_sec;
+};
+
+int module_finalize(const Elf32_Ehdr *hdr, const Elf_Shdr *sechdrs,
+                    struct module *mod)
 {
+#ifdef CONFIG_ARM_UNWIND
+        const char *secstrs = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
+        const Elf_Shdr *s, *sechdrs_end = sechdrs + hdr->e_shnum;
+        struct mod_unwind_map maps[ARM_SEC_MAX];
         int i;
-        for (i = 0; i < ARM_SEC_MAX; ++i) {
-                struct arm_unwind_mapping *map = &mod->arch.map[i];
-                if (map->unw_sec && map->sec_text)
-                        map->unwind = unwind_table_add(map->unw_sec->sh_addr,
-                                                       map->unw_sec->sh_size,
-                                                       map->sec_text->sh_addr,
-                                                       map->sec_text->sh_size);
+
+        memset(maps, 0, sizeof(maps));
+
+        for (s = sechdrs; s < sechdrs_end; s++) {
+                const char *secname = secstrs + s->sh_name;
+
+                if (!(s->sh_flags & SHF_ALLOC))
+                        continue;
+
+                if (strcmp(".ARM.exidx.init.text", secname) == 0)
+                        maps[ARM_SEC_INIT].unw_sec = s;
+                else if (strcmp(".ARM.exidx.devinit.text", secname) == 0)
+                        maps[ARM_SEC_DEVINIT].unw_sec = s;
+                else if (strcmp(".ARM.exidx", secname) == 0)
+                        maps[ARM_SEC_CORE].unw_sec = s;
+                else if (strcmp(".ARM.exidx.exit.text", secname) == 0)
+                        maps[ARM_SEC_EXIT].unw_sec = s;
+                else if (strcmp(".ARM.exidx.devexit.text", secname) == 0)
+                        maps[ARM_SEC_DEVEXIT].unw_sec = s;
+                else if (strcmp(".init.text", secname) == 0)
+                        maps[ARM_SEC_INIT].txt_sec = s;
+                else if (strcmp(".devinit.text", secname) == 0)
+                        maps[ARM_SEC_DEVINIT].txt_sec = s;
+                else if (strcmp(".text", secname) == 0)
+                        maps[ARM_SEC_CORE].txt_sec = s;
+                else if (strcmp(".exit.text", secname) == 0)
+                        maps[ARM_SEC_EXIT].txt_sec = s;
+                else if (strcmp(".devexit.text", secname) == 0)
+                        maps[ARM_SEC_DEVEXIT].txt_sec = s;
         }
-}
 
-static void unregister_unwind_tables(struct module *mod)
-{
-        int i = ARM_SEC_MAX;
-        while (--i >= 0)
-                unwind_table_del(mod->arch.map[i].unwind);
-}
-#else
-static inline void register_unwind_tables(struct module *mod) { }
-static inline void unregister_unwind_tables(struct module *mod) { }
+        for (i = 0; i < ARM_SEC_MAX; i++)
+                if (maps[i].unw_sec && maps[i].txt_sec)
+                        mod->arch.unwind[i] =
+                                unwind_table_add(maps[i].unw_sec->sh_addr,
+                                                 maps[i].unw_sec->sh_size,
+                                                 maps[i].txt_sec->sh_addr,
+                                                 maps[i].txt_sec->sh_size);
 #endif
-
-int
-module_finalize(const Elf32_Ehdr *hdr, const Elf_Shdr *sechdrs,
-                struct module *module)
-{
-        register_unwind_tables(module);
         return 0;
 }
 
 void
 module_arch_cleanup(struct module *mod)
 {
-        unregister_unwind_tables(mod);
+#ifdef CONFIG_ARM_UNWIND
+        int i;
+
+        for (i = 0; i < ARM_SEC_MAX; i++)
+                if (mod->arch.unwind[i])
+                        unwind_table_del(mod->arch.unwind[i]);
+#endif
 }
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index fdfa4976b0bf..5efa2647a2fb 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -4,9 +4,7 @@
  * ARM performance counter support.
  *
  * Copyright (C) 2009 picoChip Designs, Ltd., Jamie Iles
- *
- * ARMv7 support: Jean Pihet <jpihet@mvista.com>
- * 2010 (c) MontaVista Software, LLC.
+ * Copyright (C) 2010 ARM Ltd., Will Deacon <will.deacon@arm.com>
  *
  * This code is based on the sparc64 perf event code, which is in turn based
  * on the x86 code. Callchain code is based on the ARM OProfile backtrace
@@ -34,7 +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
@@ -67,31 +65,25 @@ struct cpu_hw_events {
          */
         unsigned long           active_mask[BITS_TO_LONGS(ARMPMU_MAX_HWEVENTS)];
 };
-DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events);
-
-/* PMU names. */
-static const char *arm_pmu_names[] = {
-        [ARM_PERF_PMU_ID_XSCALE1] = "xscale1",
-        [ARM_PERF_PMU_ID_XSCALE2] = "xscale2",
-        [ARM_PERF_PMU_ID_V6]      = "v6",
-        [ARM_PERF_PMU_ID_V6MP]    = "v6mpcore",
-        [ARM_PERF_PMU_ID_CA8]     = "ARMv7 Cortex-A8",
-        [ARM_PERF_PMU_ID_CA9]     = "ARMv7 Cortex-A9",
-};
+static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events);
 
 struct arm_pmu {
         enum arm_perf_pmu_ids id;
+        const char      *name;
         irqreturn_t     (*handle_irq)(int irq_num, void *dev);
         void            (*enable)(struct hw_perf_event *evt, int idx);
         void            (*disable)(struct hw_perf_event *evt, int idx);
-        int             (*event_map)(int evt);
-        u64             (*raw_event)(u64);
         int             (*get_event_idx)(struct cpu_hw_events *cpuc,
                                          struct hw_perf_event *hwc);
         u32             (*read_counter)(int idx);
         void            (*write_counter)(int idx, u32 val);
         void            (*start)(void);
         void            (*stop)(void);
+        const unsigned  (*cache_map)[PERF_COUNT_HW_CACHE_MAX]
+                                    [PERF_COUNT_HW_CACHE_OP_MAX]
+                                    [PERF_COUNT_HW_CACHE_RESULT_MAX];
+        const unsigned  (*event_map)[PERF_COUNT_HW_MAX];
+        u32             raw_event_mask;
         int             num_events;
         u64             max_period;
 };
@@ -136,10 +128,6 @@ EXPORT_SYMBOL_GPL(perf_num_counters);
 
 #define CACHE_OP_UNSUPPORTED            0xFFFF
 
-static unsigned armpmu_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
-                                     [PERF_COUNT_HW_CACHE_OP_MAX]
-                                     [PERF_COUNT_HW_CACHE_RESULT_MAX];
-
 static int
 armpmu_map_cache_event(u64 config)
 {
@@ -157,7 +145,7 @@ armpmu_map_cache_event(u64 config)
         if (cache_result >= PERF_COUNT_HW_CACHE_RESULT_MAX)
                 return -EINVAL;
 
-        ret = (int)armpmu_perf_cache_map[cache_type][cache_op][cache_result];
+        ret = (int)(*armpmu->cache_map)[cache_type][cache_op][cache_result];
 
         if (ret == CACHE_OP_UNSUPPORTED)
                 return -ENOENT;
@@ -166,6 +154,19 @@ armpmu_map_cache_event(u64 config)
 }
 
 static int
+armpmu_map_event(u64 config)
+{
+        int mapping = (*armpmu->event_map)[config];
+        return mapping == HW_OP_UNSUPPORTED ? -EOPNOTSUPP : mapping;
+}
+
+static int
+armpmu_map_raw_event(u64 config)
+{
+        return (int)(config & armpmu->raw_event_mask);
+}
+
+static int
 armpmu_event_set_period(struct perf_event *event,
                         struct hw_perf_event *hwc,
                         int idx)
@@ -458,11 +459,11 @@ __hw_perf_event_init(struct perf_event *event)
 
         /* Decode the generic type into an ARM event identifier. */
         if (PERF_TYPE_HARDWARE == event->attr.type) {
-                mapping = armpmu->event_map(event->attr.config);
+                mapping = armpmu_map_event(event->attr.config);
         } else if (PERF_TYPE_HW_CACHE == event->attr.type) {
                 mapping = armpmu_map_cache_event(event->attr.config);
         } else if (PERF_TYPE_RAW == event->attr.type) {
-                mapping = armpmu->raw_event(event->attr.config);
+                mapping = armpmu_map_raw_event(event->attr.config);
         } else {
                 pr_debug("event type %x not supported\n", event->attr.type);
                 return -EOPNOTSUPP;
@@ -603,2366 +604,10 @@ static struct pmu pmu = {
         .read           = armpmu_read,
 };
 
-/*
- * ARMv6 Performance counter handling code.
- *
- * ARMv6 has 2 configurable performance counters and a single cycle counter.
- * They all share a single reset bit but can be written to zero so we can use
- * that for a reset.
- *
- * The counters can't be individually enabled or disabled so when we remove
- * one event and replace it with another we could get spurious counts from the
- * wrong event. However, we can take advantage of the fact that the
- * performance counters can export events to the event bus, and the event bus
- * itself can be monitored. This requires that we *don't* export the events to
- * the event bus. The procedure for disabling a configurable counter is:
- *      - change the counter to count the ETMEXTOUT[0] signal (0x20). This
- *        effectively stops the counter from counting.
- *      - disable the counter's interrupt generation (each counter has it's
- *        own interrupt enable bit).
- * Once stopped, the counter value can be written as 0 to reset.
- *
- * To enable a counter:
- *      - enable the counter's interrupt generation.
- *      - set the new event type.
- *
- * Note: the dedicated cycle counter only counts cycles and can't be
- * enabled/disabled independently of the others. When we want to disable the
- * cycle counter, we have to just disable the interrupt reporting and start
- * ignoring that counter. When re-enabling, we have to reset the value and
- * enable the interrupt.
- */
-
-enum armv6_perf_types {
-        ARMV6_PERFCTR_ICACHE_MISS           = 0x0,
-        ARMV6_PERFCTR_IBUF_STALL            = 0x1,
-        ARMV6_PERFCTR_DDEP_STALL            = 0x2,
-        ARMV6_PERFCTR_ITLB_MISS             = 0x3,
-        ARMV6_PERFCTR_DTLB_MISS             = 0x4,
-        ARMV6_PERFCTR_BR_EXEC               = 0x5,
-        ARMV6_PERFCTR_BR_MISPREDICT         = 0x6,
-        ARMV6_PERFCTR_INSTR_EXEC            = 0x7,
-        ARMV6_PERFCTR_DCACHE_HIT            = 0x9,
-        ARMV6_PERFCTR_DCACHE_ACCESS         = 0xA,
-        ARMV6_PERFCTR_DCACHE_MISS           = 0xB,
-        ARMV6_PERFCTR_DCACHE_WBACK          = 0xC,
-        ARMV6_PERFCTR_SW_PC_CHANGE          = 0xD,
-        ARMV6_PERFCTR_MAIN_TLB_MISS         = 0xF,
-        ARMV6_PERFCTR_EXPL_D_ACCESS         = 0x10,
-        ARMV6_PERFCTR_LSU_FULL_STALL        = 0x11,
-        ARMV6_PERFCTR_WBUF_DRAINED          = 0x12,
-        ARMV6_PERFCTR_CPU_CYCLES            = 0xFF,
-        ARMV6_PERFCTR_NOP                   = 0x20,
-};
-
-enum armv6_counters {
-        ARMV6_CYCLE_COUNTER = 1,
-        ARMV6_COUNTER0,
-        ARMV6_COUNTER1,
-};
-
-/*
- * The hardware events that we support. We do support cache operations but
- * we have harvard caches and no way to combine instruction and data
- * accesses/misses in hardware.
- */
-static const unsigned armv6_perf_map[PERF_COUNT_HW_MAX] = {
-        [PERF_COUNT_HW_CPU_CYCLES]          = ARMV6_PERFCTR_CPU_CYCLES,
-        [PERF_COUNT_HW_INSTRUCTIONS]        = ARMV6_PERFCTR_INSTR_EXEC,
-        [PERF_COUNT_HW_CACHE_REFERENCES]    = HW_OP_UNSUPPORTED,
-        [PERF_COUNT_HW_CACHE_MISSES]        = HW_OP_UNSUPPORTED,
-        [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV6_PERFCTR_BR_EXEC,
-        [PERF_COUNT_HW_BRANCH_MISSES]       = ARMV6_PERFCTR_BR_MISPREDICT,
-        [PERF_COUNT_HW_BUS_CYCLES]          = HW_OP_UNSUPPORTED,
-};
-
-static const unsigned armv6_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
-                                          [PERF_COUNT_HW_CACHE_OP_MAX]
-                                          [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
-        [C(L1D)] = {
-                /*
-                 * The performance counters don't differentiate between read
-                 * and write accesses/misses so this isn't strictly correct,
-                 * but it's the best we can do. Writes and reads get
-                 * combined.
-                 */
-                [C(OP_READ)] = {
-                        [C(RESULT_ACCESS)]      = ARMV6_PERFCTR_DCACHE_ACCESS,
-                        [C(RESULT_MISS)]        = ARMV6_PERFCTR_DCACHE_MISS,
-                },
-                [C(OP_WRITE)] = {
-                        [C(RESULT_ACCESS)]      = ARMV6_PERFCTR_DCACHE_ACCESS,
-                        [C(RESULT_MISS)]        = ARMV6_PERFCTR_DCACHE_MISS,
-                },
-                [C(OP_PREFETCH)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
-                },
-        },
-        [C(L1I)] = {
-                [C(OP_READ)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = ARMV6_PERFCTR_ICACHE_MISS,
-                },
-                [C(OP_WRITE)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = ARMV6_PERFCTR_ICACHE_MISS,
-                },
-                [C(OP_PREFETCH)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
-                },
-        },
-        [C(LL)] = {
-                [C(OP_READ)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
-                },
-                [C(OP_WRITE)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
-                },
-                [C(OP_PREFETCH)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
-                },
-        },
-        [C(DTLB)] = {
-                /*
-                 * The ARM performance counters can count micro DTLB misses,
-                 * micro ITLB misses and main TLB misses. There isn't an event
-                 * for TLB misses, so use the micro misses here and if users
-                 * want the main TLB misses they can use a raw counter.
-                 */
-                [C(OP_READ)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = ARMV6_PERFCTR_DTLB_MISS,
-                },
-                [C(OP_WRITE)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = ARMV6_PERFCTR_DTLB_MISS,
-                },
-                [C(OP_PREFETCH)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
-                },
-        },
-        [C(ITLB)] = {
-                [C(OP_READ)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = ARMV6_PERFCTR_ITLB_MISS,
-                },
-                [C(OP_WRITE)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = ARMV6_PERFCTR_ITLB_MISS,
-                },
-                [C(OP_PREFETCH)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
-                },
-        },
-        [C(BPU)] = {
-                [C(OP_READ)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
-                },
-                [C(OP_WRITE)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
-                },
-                [C(OP_PREFETCH)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
-                },
-        },
-};
-
-enum armv6mpcore_perf_types {
-        ARMV6MPCORE_PERFCTR_ICACHE_MISS     = 0x0,
-        ARMV6MPCORE_PERFCTR_IBUF_STALL      = 0x1,
-        ARMV6MPCORE_PERFCTR_DDEP_STALL      = 0x2,
-        ARMV6MPCORE_PERFCTR_ITLB_MISS       = 0x3,
-        ARMV6MPCORE_PERFCTR_DTLB_MISS       = 0x4,
-        ARMV6MPCORE_PERFCTR_BR_EXEC         = 0x5,
-        ARMV6MPCORE_PERFCTR_BR_NOTPREDICT   = 0x6,
-        ARMV6MPCORE_PERFCTR_BR_MISPREDICT   = 0x7,
-        ARMV6MPCORE_PERFCTR_INSTR_EXEC      = 0x8,
-        ARMV6MPCORE_PERFCTR_DCACHE_RDACCESS = 0xA,
-        ARMV6MPCORE_PERFCTR_DCACHE_RDMISS   = 0xB,
-        ARMV6MPCORE_PERFCTR_DCACHE_WRACCESS = 0xC,
-        ARMV6MPCORE_PERFCTR_DCACHE_WRMISS   = 0xD,
-        ARMV6MPCORE_PERFCTR_DCACHE_EVICTION = 0xE,
-        ARMV6MPCORE_PERFCTR_SW_PC_CHANGE    = 0xF,
-        ARMV6MPCORE_PERFCTR_MAIN_TLB_MISS   = 0x10,
-        ARMV6MPCORE_PERFCTR_EXPL_MEM_ACCESS = 0x11,
-        ARMV6MPCORE_PERFCTR_LSU_FULL_STALL  = 0x12,
-        ARMV6MPCORE_PERFCTR_WBUF_DRAINED    = 0x13,
-        ARMV6MPCORE_PERFCTR_CPU_CYCLES      = 0xFF,
-};
-
-/*
- * The hardware events that we support. We do support cache operations but
- * we have harvard caches and no way to combine instruction and data
- * accesses/misses in hardware.
- */
-static const unsigned armv6mpcore_perf_map[PERF_COUNT_HW_MAX] = {
-        [PERF_COUNT_HW_CPU_CYCLES]          = ARMV6MPCORE_PERFCTR_CPU_CYCLES,
-        [PERF_COUNT_HW_INSTRUCTIONS]        = ARMV6MPCORE_PERFCTR_INSTR_EXEC,
-        [PERF_COUNT_HW_CACHE_REFERENCES]    = HW_OP_UNSUPPORTED,
-        [PERF_COUNT_HW_CACHE_MISSES]        = HW_OP_UNSUPPORTED,
-        [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV6MPCORE_PERFCTR_BR_EXEC,
-        [PERF_COUNT_HW_BRANCH_MISSES]       = ARMV6MPCORE_PERFCTR_BR_MISPREDICT,
-        [PERF_COUNT_HW_BUS_CYCLES]          = HW_OP_UNSUPPORTED,
-};
-
-static const unsigned armv6mpcore_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
-                                        [PERF_COUNT_HW_CACHE_OP_MAX]
-                                        [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
-        [C(L1D)] = {
-                [C(OP_READ)] = {
-                        [C(RESULT_ACCESS)]  =
-                                ARMV6MPCORE_PERFCTR_DCACHE_RDACCESS,
-                        [C(RESULT_MISS)]    =
-                                ARMV6MPCORE_PERFCTR_DCACHE_RDMISS,
-                },
-                [C(OP_WRITE)] = {
-                        [C(RESULT_ACCESS)]  =
-                                ARMV6MPCORE_PERFCTR_DCACHE_WRACCESS,
-                        [C(RESULT_MISS)]    =
-                                ARMV6MPCORE_PERFCTR_DCACHE_WRMISS,
-                },
-                [C(OP_PREFETCH)] = {
-                        [C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
-                },
-        },
-        [C(L1I)] = {
-                [C(OP_READ)] = {
-                        [C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]    = ARMV6MPCORE_PERFCTR_ICACHE_MISS,
-                },
-                [C(OP_WRITE)] = {
-                        [C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]    = ARMV6MPCORE_PERFCTR_ICACHE_MISS,
-                },
-                [C(OP_PREFETCH)] = {
-                        [C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
-                },
-        },
-        [C(LL)] = {
-                [C(OP_READ)] = {
-                        [C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
-                },
-                [C(OP_WRITE)] = {
-                        [C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
-                },
-                [C(OP_PREFETCH)] = {
-                        [C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
-                },
-        },
-        [C(DTLB)] = {
-                /*
-                 * The ARM performance counters can count micro DTLB misses,
-                 * micro ITLB misses and main TLB misses. There isn't an event
-                 * for TLB misses, so use the micro misses here and if users
-                 * want the main TLB misses they can use a raw counter.
-                 */
-                [C(OP_READ)] = {
-                        [C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]    = ARMV6MPCORE_PERFCTR_DTLB_MISS,
-                },
-                [C(OP_WRITE)] = {
-                        [C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]    = ARMV6MPCORE_PERFCTR_DTLB_MISS,
-                },
-                [C(OP_PREFETCH)] = {
-                        [C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
-                },
-        },
-        [C(ITLB)] = {
-                [C(OP_READ)] = {
-                        [C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]    = ARMV6MPCORE_PERFCTR_ITLB_MISS,
-                },
-                [C(OP_WRITE)] = {
-                        [C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]    = ARMV6MPCORE_PERFCTR_ITLB_MISS,
-                },
-                [C(OP_PREFETCH)] = {
-                        [C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
-                },
-        },
-        [C(BPU)] = {
-                [C(OP_READ)] = {
-                        [C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
-                },
-                [C(OP_WRITE)] = {
-                        [C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
-                },
-                [C(OP_PREFETCH)] = {
-                        [C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
-                },
-        },
-};
-
-static inline unsigned long
-armv6_pmcr_read(void)
-{
-        u32 val;
-        asm volatile("mrc   p15, 0, %0, c15, c12, 0" : "=r"(val));
-        return val;
-}
-
-static inline void
-armv6_pmcr_write(unsigned long val)
-{
-        asm volatile("mcr   p15, 0, %0, c15, c12, 0" : : "r"(val));
-}
-
-#define ARMV6_PMCR_ENABLE               (1 << 0)
-#define ARMV6_PMCR_CTR01_RESET          (1 << 1)
-#define ARMV6_PMCR_CCOUNT_RESET         (1 << 2)
-#define ARMV6_PMCR_CCOUNT_DIV           (1 << 3)
-#define ARMV6_PMCR_COUNT0_IEN           (1 << 4)
-#define ARMV6_PMCR_COUNT1_IEN           (1 << 5)
-#define ARMV6_PMCR_CCOUNT_IEN           (1 << 6)
-#define ARMV6_PMCR_COUNT0_OVERFLOW      (1 << 8)
-#define ARMV6_PMCR_COUNT1_OVERFLOW      (1 << 9)
-#define ARMV6_PMCR_CCOUNT_OVERFLOW      (1 << 10)
-#define ARMV6_PMCR_EVT_COUNT0_SHIFT     20
-#define ARMV6_PMCR_EVT_COUNT0_MASK      (0xFF << ARMV6_PMCR_EVT_COUNT0_SHIFT)
-#define ARMV6_PMCR_EVT_COUNT1_SHIFT     12
-#define ARMV6_PMCR_EVT_COUNT1_MASK      (0xFF << ARMV6_PMCR_EVT_COUNT1_SHIFT)
-
-#define ARMV6_PMCR_OVERFLOWED_MASK \
-        (ARMV6_PMCR_COUNT0_OVERFLOW | ARMV6_PMCR_COUNT1_OVERFLOW | \
-         ARMV6_PMCR_CCOUNT_OVERFLOW)
-
-static inline int
-armv6_pmcr_has_overflowed(unsigned long pmcr)
-{
-        return (pmcr & ARMV6_PMCR_OVERFLOWED_MASK);
-}
-
-static inline int
-armv6_pmcr_counter_has_overflowed(unsigned long pmcr,
-                                  enum armv6_counters counter)
-{
-        int ret = 0;
-
-        if (ARMV6_CYCLE_COUNTER == counter)
-                ret = pmcr & ARMV6_PMCR_CCOUNT_OVERFLOW;
-        else if (ARMV6_COUNTER0 == counter)
-                ret = pmcr & ARMV6_PMCR_COUNT0_OVERFLOW;
-        else if (ARMV6_COUNTER1 == counter)
-                ret = pmcr & ARMV6_PMCR_COUNT1_OVERFLOW;
-        else
-                WARN_ONCE(1, "invalid counter number (%d)\n", counter);
-
-        return ret;
-}
-
-static inline u32
-armv6pmu_read_counter(int counter)
-{
-        unsigned long value = 0;
-
-        if (ARMV6_CYCLE_COUNTER == counter)
-                asm volatile("mrc   p15, 0, %0, c15, c12, 1" : "=r"(value));
-        else if (ARMV6_COUNTER0 == counter)
-                asm volatile("mrc   p15, 0, %0, c15, c12, 2" : "=r"(value));
-        else if (ARMV6_COUNTER1 == counter)
-                asm volatile("mrc   p15, 0, %0, c15, c12, 3" : "=r"(value));
-        else
-                WARN_ONCE(1, "invalid counter number (%d)\n", counter);
-
-        return value;
-}
-
-static inline void
-armv6pmu_write_counter(int counter,
-                       u32 value)
-{
-        if (ARMV6_CYCLE_COUNTER == counter)
-                asm volatile("mcr   p15, 0, %0, c15, c12, 1" : : "r"(value));
-        else if (ARMV6_COUNTER0 == counter)
-                asm volatile("mcr   p15, 0, %0, c15, c12, 2" : : "r"(value));
-        else if (ARMV6_COUNTER1 == counter)
-                asm volatile("mcr   p15, 0, %0, c15, c12, 3" : : "r"(value));
-        else
-                WARN_ONCE(1, "invalid counter number (%d)\n", counter);
-}
-
-void
-armv6pmu_enable_event(struct hw_perf_event *hwc,
-                      int idx)
-{
-        unsigned long val, mask, evt, flags;
-
-        if (ARMV6_CYCLE_COUNTER == idx) {
-                mask    = 0;
-                evt     = ARMV6_PMCR_CCOUNT_IEN;
-        } else if (ARMV6_COUNTER0 == idx) {
-                mask    = ARMV6_PMCR_EVT_COUNT0_MASK;
-                evt     = (hwc->config_base << ARMV6_PMCR_EVT_COUNT0_SHIFT) |
-                          ARMV6_PMCR_COUNT0_IEN;
-        } else if (ARMV6_COUNTER1 == idx) {
-                mask    = ARMV6_PMCR_EVT_COUNT1_MASK;
-                evt     = (hwc->config_base << ARMV6_PMCR_EVT_COUNT1_SHIFT) |
-                          ARMV6_PMCR_COUNT1_IEN;
-        } else {
-                WARN_ONCE(1, "invalid counter number (%d)\n", idx);
-                return;
-        }
-
-        /*
-         * Mask out the current event and set the counter to count the event
-         * that we're interested in.
-         */
-        spin_lock_irqsave(&pmu_lock, flags);
-        val = armv6_pmcr_read();
-        val &= ~mask;
-        val |= evt;
-        armv6_pmcr_write(val);
-        spin_unlock_irqrestore(&pmu_lock, flags);
-}
-
-static irqreturn_t
-armv6pmu_handle_irq(int irq_num,
-                    void *dev)
-{
-        unsigned long pmcr = armv6_pmcr_read();
-        struct perf_sample_data data;
-        struct cpu_hw_events *cpuc;
-        struct pt_regs *regs;
-        int idx;
-
-        if (!armv6_pmcr_has_overflowed(pmcr))
-                return IRQ_NONE;
-
-        regs = get_irq_regs();
-
-        /*
-         * The interrupts are cleared by writing the overflow flags back to
-         * the control register. All of the other bits don't have any effect
-         * if they are rewritten, so write the whole value back.
-         */
-        armv6_pmcr_write(pmcr);
-
-        perf_sample_data_init(&data, 0);
-
-        cpuc = &__get_cpu_var(cpu_hw_events);
-        for (idx = 0; idx <= armpmu->num_events; ++idx) {
-                struct perf_event *event = cpuc->events[idx];
-                struct hw_perf_event *hwc;
-
-                if (!test_bit(idx, cpuc->active_mask))
-                        continue;
-
-                /*
-                 * We have a single interrupt for all counters. Check that
-                 * each counter has overflowed before we process it.
-                 */
-                if (!armv6_pmcr_counter_has_overflowed(pmcr, idx))
-                        continue;
-
-                hwc = &event->hw;
-                armpmu_event_update(event, hwc, idx);
-                data.period = event->hw.last_period;
-                if (!armpmu_event_set_period(event, hwc, idx))
-                        continue;
-
-                if (perf_event_overflow(event, 0, &data, regs))
-                        armpmu->disable(hwc, idx);
-        }
-
-        /*
-         * Handle the pending perf events.
-         *
-         * Note: this call *must* be run with interrupts disabled. For
-         * platforms that can have the PMU interrupts raised as an NMI, this
-         * will not work.
-         */
-        irq_work_run();
-
-        return IRQ_HANDLED;
-}
-
-static void
-armv6pmu_start(void)
-{
-        unsigned long flags, val;
-
-        spin_lock_irqsave(&pmu_lock, flags);
-        val = armv6_pmcr_read();
-        val |= ARMV6_PMCR_ENABLE;
-        armv6_pmcr_write(val);
-        spin_unlock_irqrestore(&pmu_lock, flags);
-}
-
-void
-armv6pmu_stop(void)
-{
-        unsigned long flags, val;
-
-        spin_lock_irqsave(&pmu_lock, flags);
-        val = armv6_pmcr_read();
-        val &= ~ARMV6_PMCR_ENABLE;
-        armv6_pmcr_write(val);
-        spin_unlock_irqrestore(&pmu_lock, flags);
-}
-
-static inline int
-armv6pmu_event_map(int config)
-{
-        int mapping = armv6_perf_map[config];
-        if (HW_OP_UNSUPPORTED == mapping)
-                mapping = -EOPNOTSUPP;
-        return mapping;
-}
-
-static inline int
-armv6mpcore_pmu_event_map(int config)
-{
-        int mapping = armv6mpcore_perf_map[config];
-        if (HW_OP_UNSUPPORTED == mapping)
-                mapping = -EOPNOTSUPP;
-        return mapping;
-}
-
-static u64
-armv6pmu_raw_event(u64 config)
-{
-        return config & 0xff;
-}
-
-static int
-armv6pmu_get_event_idx(struct cpu_hw_events *cpuc,
-                       struct hw_perf_event *event)
-{
-        /* Always place a cycle counter into the cycle counter. */
-        if (ARMV6_PERFCTR_CPU_CYCLES == event->config_base) {
-                if (test_and_set_bit(ARMV6_CYCLE_COUNTER, cpuc->used_mask))
-                        return -EAGAIN;
-
-                return ARMV6_CYCLE_COUNTER;
-        } else {
-                /*
-                 * For anything other than a cycle counter, try and use
-                 * counter0 and counter1.
-                 */
-                if (!test_and_set_bit(ARMV6_COUNTER1, cpuc->used_mask)) {
-                        return ARMV6_COUNTER1;
-                }
-
-                if (!test_and_set_bit(ARMV6_COUNTER0, cpuc->used_mask)) {
-                        return ARMV6_COUNTER0;
-                }
-
-                /* The counters are all in use. */
-                return -EAGAIN;
-        }
-}
-
-static void
-armv6pmu_disable_event(struct hw_perf_event *hwc,
-                       int idx)
-{
-        unsigned long val, mask, evt, flags;
-
-        if (ARMV6_CYCLE_COUNTER == idx) {
-                mask    = ARMV6_PMCR_CCOUNT_IEN;
-                evt     = 0;
-        } else if (ARMV6_COUNTER0 == idx) {
-                mask    = ARMV6_PMCR_COUNT0_IEN | ARMV6_PMCR_EVT_COUNT0_MASK;
-                evt     = ARMV6_PERFCTR_NOP << ARMV6_PMCR_EVT_COUNT0_SHIFT;
-        } else if (ARMV6_COUNTER1 == idx) {
-                mask    = ARMV6_PMCR_COUNT1_IEN | ARMV6_PMCR_EVT_COUNT1_MASK;
-                evt     = ARMV6_PERFCTR_NOP << ARMV6_PMCR_EVT_COUNT1_SHIFT;
-        } else {
-                WARN_ONCE(1, "invalid counter number (%d)\n", idx);
-                return;
-        }
-
-        /*
-         * Mask out the current event and set the counter to count the number
-         * of ETM bus signal assertion cycles. The external reporting should
-         * be disabled and so this should never increment.
-         */
-        spin_lock_irqsave(&pmu_lock, flags);
-        val = armv6_pmcr_read();
-        val &= ~mask;
-        val |= evt;
-        armv6_pmcr_write(val);
-        spin_unlock_irqrestore(&pmu_lock, flags);
-}
-
-static void
-armv6mpcore_pmu_disable_event(struct hw_perf_event *hwc,
-                              int idx)
-{
-        unsigned long val, mask, flags, evt = 0;
-
-        if (ARMV6_CYCLE_COUNTER == idx) {
-                mask    = ARMV6_PMCR_CCOUNT_IEN;
-        } else if (ARMV6_COUNTER0 == idx) {
-                mask    = ARMV6_PMCR_COUNT0_IEN;
-        } else if (ARMV6_COUNTER1 == idx) {
-                mask    = ARMV6_PMCR_COUNT1_IEN;
-        } else {
-                WARN_ONCE(1, "invalid counter number (%d)\n", idx);
-                return;
-        }
-
-        /*
-         * 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);
-        val = armv6_pmcr_read();
-        val &= ~mask;
-        val |= evt;
-        armv6_pmcr_write(val);
-        spin_unlock_irqrestore(&pmu_lock, flags);
-}
-
-static const struct arm_pmu armv6pmu = {
-        .id                     = ARM_PERF_PMU_ID_V6,
-        .handle_irq             = armv6pmu_handle_irq,
-        .enable                 = armv6pmu_enable_event,
-        .disable                = armv6pmu_disable_event,
-        .event_map              = armv6pmu_event_map,
-        .raw_event              = armv6pmu_raw_event,
-        .read_counter           = armv6pmu_read_counter,
-        .write_counter          = armv6pmu_write_counter,
-        .get_event_idx          = armv6pmu_get_event_idx,
-        .start                  = armv6pmu_start,
-        .stop                   = armv6pmu_stop,
-        .num_events             = 3,
-        .max_period             = (1LLU << 32) - 1,
-};
-
-/*
- * ARMv6mpcore is almost identical to single core ARMv6 with the exception
- * that some of the events have different enumerations and that there is no
- * *hack* to stop the programmable counters. To stop the counters we simply
- * disable the interrupt reporting and update the event. When unthrottling we
- * reset the period and enable the interrupt reporting.
- */
-static const struct arm_pmu armv6mpcore_pmu = {
-        .id                     = ARM_PERF_PMU_ID_V6MP,
-        .handle_irq             = armv6pmu_handle_irq,
-        .enable                 = armv6pmu_enable_event,
-        .disable                = armv6mpcore_pmu_disable_event,
-        .event_map              = armv6mpcore_pmu_event_map,
-        .raw_event              = armv6pmu_raw_event,
-        .read_counter           = armv6pmu_read_counter,
-        .write_counter          = armv6pmu_write_counter,
-        .get_event_idx          = armv6pmu_get_event_idx,
-        .start                  = armv6pmu_start,
-        .stop                   = armv6pmu_stop,
-        .num_events             = 3,
-        .max_period             = (1LLU << 32) - 1,
-};
-
-/*
- * ARMv7 Cortex-A8 and Cortex-A9 Performance Events handling code.
- *
- * Copied from ARMv6 code, with the low level code inspired
- *  by the ARMv7 Oprofile code.
- *
- * Cortex-A8 has up to 4 configurable performance counters and
- *  a single cycle counter.
- * Cortex-A9 has up to 31 configurable performance counters and
- *  a single cycle counter.
- *
- * All counters can be enabled/disabled and IRQ masked separately. The cycle
- *  counter and all 4 performance counters together can be reset separately.
- */
-
-/* Common ARMv7 event types */
-enum armv7_perf_types {
-        ARMV7_PERFCTR_PMNC_SW_INCR              = 0x00,
-        ARMV7_PERFCTR_IFETCH_MISS               = 0x01,
-        ARMV7_PERFCTR_ITLB_MISS                 = 0x02,
-        ARMV7_PERFCTR_DCACHE_REFILL             = 0x03,
-        ARMV7_PERFCTR_DCACHE_ACCESS             = 0x04,
-        ARMV7_PERFCTR_DTLB_REFILL               = 0x05,
-        ARMV7_PERFCTR_DREAD                     = 0x06,
-        ARMV7_PERFCTR_DWRITE                    = 0x07,
-
-        ARMV7_PERFCTR_EXC_TAKEN                 = 0x09,
-        ARMV7_PERFCTR_EXC_EXECUTED              = 0x0A,
-        ARMV7_PERFCTR_CID_WRITE                 = 0x0B,
-        /* ARMV7_PERFCTR_PC_WRITE is equivalent to HW_BRANCH_INSTRUCTIONS.
-         * It counts:
-         *  - all branch instructions,
-         *  - instructions that explicitly write the PC,
-         *  - exception generating instructions.
-         */
-        ARMV7_PERFCTR_PC_WRITE                  = 0x0C,
-        ARMV7_PERFCTR_PC_IMM_BRANCH             = 0x0D,
-        ARMV7_PERFCTR_UNALIGNED_ACCESS          = 0x0F,
-        ARMV7_PERFCTR_PC_BRANCH_MIS_PRED        = 0x10,
-        ARMV7_PERFCTR_CLOCK_CYCLES              = 0x11,
-
-        ARMV7_PERFCTR_PC_BRANCH_MIS_USED        = 0x12,
-
-        ARMV7_PERFCTR_CPU_CYCLES                = 0xFF
-};
-
-/* ARMv7 Cortex-A8 specific event types */
-enum armv7_a8_perf_types {
-        ARMV7_PERFCTR_INSTR_EXECUTED            = 0x08,
-
-        ARMV7_PERFCTR_PC_PROC_RETURN            = 0x0E,
-
-        ARMV7_PERFCTR_WRITE_BUFFER_FULL         = 0x40,
-        ARMV7_PERFCTR_L2_STORE_MERGED           = 0x41,
-        ARMV7_PERFCTR_L2_STORE_BUFF             = 0x42,
-        ARMV7_PERFCTR_L2_ACCESS                 = 0x43,
-        ARMV7_PERFCTR_L2_CACH_MISS              = 0x44,
-        ARMV7_PERFCTR_AXI_READ_CYCLES           = 0x45,
-        ARMV7_PERFCTR_AXI_WRITE_CYCLES          = 0x46,
-        ARMV7_PERFCTR_MEMORY_REPLAY             = 0x47,
-        ARMV7_PERFCTR_UNALIGNED_ACCESS_REPLAY   = 0x48,
-        ARMV7_PERFCTR_L1_DATA_MISS              = 0x49,
-        ARMV7_PERFCTR_L1_INST_MISS              = 0x4A,
-        ARMV7_PERFCTR_L1_DATA_COLORING          = 0x4B,
-        ARMV7_PERFCTR_L1_NEON_DATA              = 0x4C,
-        ARMV7_PERFCTR_L1_NEON_CACH_DATA         = 0x4D,
-        ARMV7_PERFCTR_L2_NEON                   = 0x4E,
-        ARMV7_PERFCTR_L2_NEON_HIT               = 0x4F,
-        ARMV7_PERFCTR_L1_INST                   = 0x50,
-        ARMV7_PERFCTR_PC_RETURN_MIS_PRED        = 0x51,
-        ARMV7_PERFCTR_PC_BRANCH_FAILED          = 0x52,
-        ARMV7_PERFCTR_PC_BRANCH_TAKEN           = 0x53,
-        ARMV7_PERFCTR_PC_BRANCH_EXECUTED        = 0x54,
-        ARMV7_PERFCTR_OP_EXECUTED               = 0x55,
-        ARMV7_PERFCTR_CYCLES_INST_STALL         = 0x56,
-        ARMV7_PERFCTR_CYCLES_INST               = 0x57,
-        ARMV7_PERFCTR_CYCLES_NEON_DATA_STALL    = 0x58,
-        ARMV7_PERFCTR_CYCLES_NEON_INST_STALL    = 0x59,
-        ARMV7_PERFCTR_NEON_CYCLES               = 0x5A,
-
-        ARMV7_PERFCTR_PMU0_EVENTS               = 0x70,
-        ARMV7_PERFCTR_PMU1_EVENTS               = 0x71,
-        ARMV7_PERFCTR_PMU_EVENTS                = 0x72,
-};
-
-/* ARMv7 Cortex-A9 specific event types */
-enum armv7_a9_perf_types {
-        ARMV7_PERFCTR_JAVA_HW_BYTECODE_EXEC     = 0x40,
-        ARMV7_PERFCTR_JAVA_SW_BYTECODE_EXEC     = 0x41,
-        ARMV7_PERFCTR_JAZELLE_BRANCH_EXEC       = 0x42,
-
-        ARMV7_PERFCTR_COHERENT_LINE_MISS        = 0x50,
-        ARMV7_PERFCTR_COHERENT_LINE_HIT         = 0x51,
-
-        ARMV7_PERFCTR_ICACHE_DEP_STALL_CYCLES   = 0x60,
-        ARMV7_PERFCTR_DCACHE_DEP_STALL_CYCLES   = 0x61,
-        ARMV7_PERFCTR_TLB_MISS_DEP_STALL_CYCLES = 0x62,
-        ARMV7_PERFCTR_STREX_EXECUTED_PASSED     = 0x63,
-        ARMV7_PERFCTR_STREX_EXECUTED_FAILED     = 0x64,
-        ARMV7_PERFCTR_DATA_EVICTION             = 0x65,
-        ARMV7_PERFCTR_ISSUE_STAGE_NO_INST       = 0x66,
-        ARMV7_PERFCTR_ISSUE_STAGE_EMPTY         = 0x67,
-        ARMV7_PERFCTR_INST_OUT_OF_RENAME_STAGE  = 0x68,
-
-        ARMV7_PERFCTR_PREDICTABLE_FUNCT_RETURNS = 0x6E,
-
-        ARMV7_PERFCTR_MAIN_UNIT_EXECUTED_INST   = 0x70,
-        ARMV7_PERFCTR_SECOND_UNIT_EXECUTED_INST = 0x71,
-        ARMV7_PERFCTR_LD_ST_UNIT_EXECUTED_INST  = 0x72,
-        ARMV7_PERFCTR_FP_EXECUTED_INST          = 0x73,
-        ARMV7_PERFCTR_NEON_EXECUTED_INST        = 0x74,
-
-        ARMV7_PERFCTR_PLD_FULL_DEP_STALL_CYCLES = 0x80,
-        ARMV7_PERFCTR_DATA_WR_DEP_STALL_CYCLES  = 0x81,
-        ARMV7_PERFCTR_ITLB_MISS_DEP_STALL_CYCLES        = 0x82,
-        ARMV7_PERFCTR_DTLB_MISS_DEP_STALL_CYCLES        = 0x83,
-        ARMV7_PERFCTR_MICRO_ITLB_MISS_DEP_STALL_CYCLES  = 0x84,
-        ARMV7_PERFCTR_MICRO_DTLB_MISS_DEP_STALL_CYCLES  = 0x85,
-        ARMV7_PERFCTR_DMB_DEP_STALL_CYCLES      = 0x86,
-
-        ARMV7_PERFCTR_INTGR_CLK_ENABLED_CYCLES  = 0x8A,
-        ARMV7_PERFCTR_DATA_ENGINE_CLK_EN_CYCLES = 0x8B,
-
-        ARMV7_PERFCTR_ISB_INST                  = 0x90,
-        ARMV7_PERFCTR_DSB_INST                  = 0x91,
-        ARMV7_PERFCTR_DMB_INST                  = 0x92,
-        ARMV7_PERFCTR_EXT_INTERRUPTS            = 0x93,
-
-        ARMV7_PERFCTR_PLE_CACHE_LINE_RQST_COMPLETED     = 0xA0,
-        ARMV7_PERFCTR_PLE_CACHE_LINE_RQST_SKIPPED       = 0xA1,
-        ARMV7_PERFCTR_PLE_FIFO_FLUSH            = 0xA2,
-        ARMV7_PERFCTR_PLE_RQST_COMPLETED        = 0xA3,
-        ARMV7_PERFCTR_PLE_FIFO_OVERFLOW         = 0xA4,
-        ARMV7_PERFCTR_PLE_RQST_PROG             = 0xA5
-};
-
-/*
- * Cortex-A8 HW events mapping
- *
- * The hardware events that we support. We do support cache operations but
- * we have harvard caches and no way to combine instruction and data
- * accesses/misses in hardware.
- */
-static const unsigned armv7_a8_perf_map[PERF_COUNT_HW_MAX] = {
-        [PERF_COUNT_HW_CPU_CYCLES]          = ARMV7_PERFCTR_CPU_CYCLES,
-        [PERF_COUNT_HW_INSTRUCTIONS]        = ARMV7_PERFCTR_INSTR_EXECUTED,
-        [PERF_COUNT_HW_CACHE_REFERENCES]    = HW_OP_UNSUPPORTED,
-        [PERF_COUNT_HW_CACHE_MISSES]        = HW_OP_UNSUPPORTED,
-        [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV7_PERFCTR_PC_WRITE,
-        [PERF_COUNT_HW_BRANCH_MISSES]       = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
-        [PERF_COUNT_HW_BUS_CYCLES]          = ARMV7_PERFCTR_CLOCK_CYCLES,
-};
-
-static const unsigned armv7_a8_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
-                                          [PERF_COUNT_HW_CACHE_OP_MAX]
-                                          [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
-        [C(L1D)] = {
-                /*
-                 * The performance counters don't differentiate between read
-                 * and write accesses/misses so this isn't strictly correct,
-                 * but it's the best we can do. Writes and reads get
-                 * combined.
-                 */
-                [C(OP_READ)] = {
-                        [C(RESULT_ACCESS)]      = ARMV7_PERFCTR_DCACHE_ACCESS,
-                        [C(RESULT_MISS)]        = ARMV7_PERFCTR_DCACHE_REFILL,
-                },
-                [C(OP_WRITE)] = {
-                        [C(RESULT_ACCESS)]      = ARMV7_PERFCTR_DCACHE_ACCESS,
-                        [C(RESULT_MISS)]        = ARMV7_PERFCTR_DCACHE_REFILL,
-                },
-                [C(OP_PREFETCH)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
-                },
-        },
-        [C(L1I)] = {
-                [C(OP_READ)] = {
-                        [C(RESULT_ACCESS)]      = ARMV7_PERFCTR_L1_INST,
-                        [C(RESULT_MISS)]        = ARMV7_PERFCTR_L1_INST_MISS,
-                },
-                [C(OP_WRITE)] = {
-                        [C(RESULT_ACCESS)]      = ARMV7_PERFCTR_L1_INST,
-                        [C(RESULT_MISS)]        = ARMV7_PERFCTR_L1_INST_MISS,
-                },
-                [C(OP_PREFETCH)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
-                },
-        },
-        [C(LL)] = {
-                [C(OP_READ)] = {
-                        [C(RESULT_ACCESS)]      = ARMV7_PERFCTR_L2_ACCESS,
-                        [C(RESULT_MISS)]        = ARMV7_PERFCTR_L2_CACH_MISS,
-                },
-                [C(OP_WRITE)] = {
-                        [C(RESULT_ACCESS)]      = ARMV7_PERFCTR_L2_ACCESS,
-                        [C(RESULT_MISS)]        = ARMV7_PERFCTR_L2_CACH_MISS,
-                },
-                [C(OP_PREFETCH)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
-                },
-        },
-        [C(DTLB)] = {
-                /*
-                 * Only ITLB misses and DTLB refills are supported.
-                 * If users want the DTLB refills misses a raw counter
-                 * must be used.
-                 */
-                [C(OP_READ)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = ARMV7_PERFCTR_DTLB_REFILL,
-                },
-                [C(OP_WRITE)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = ARMV7_PERFCTR_DTLB_REFILL,
-                },
-                [C(OP_PREFETCH)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
-                },
-        },
-        [C(ITLB)] = {
-                [C(OP_READ)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = ARMV7_PERFCTR_ITLB_MISS,
-                },
-                [C(OP_WRITE)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = ARMV7_PERFCTR_ITLB_MISS,
-                },
-                [C(OP_PREFETCH)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
-                },
-        },
-        [C(BPU)] = {
-                [C(OP_READ)] = {
-                        [C(RESULT_ACCESS)]      = ARMV7_PERFCTR_PC_WRITE,
-                        [C(RESULT_MISS)]
-                                        = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
-                },
-                [C(OP_WRITE)] = {
-                        [C(RESULT_ACCESS)]      = ARMV7_PERFCTR_PC_WRITE,
-                        [C(RESULT_MISS)]
-                                        = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
-                },
-                [C(OP_PREFETCH)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
-                },
-        },
-};
-
-/*
- * Cortex-A9 HW events mapping
- */
-static const unsigned armv7_a9_perf_map[PERF_COUNT_HW_MAX] = {
-        [PERF_COUNT_HW_CPU_CYCLES]          = ARMV7_PERFCTR_CPU_CYCLES,
-        [PERF_COUNT_HW_INSTRUCTIONS]        =
-                                        ARMV7_PERFCTR_INST_OUT_OF_RENAME_STAGE,
-        [PERF_COUNT_HW_CACHE_REFERENCES]    = ARMV7_PERFCTR_COHERENT_LINE_HIT,
-        [PERF_COUNT_HW_CACHE_MISSES]        = ARMV7_PERFCTR_COHERENT_LINE_MISS,
-        [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV7_PERFCTR_PC_WRITE,
-        [PERF_COUNT_HW_BRANCH_MISSES]       = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
-        [PERF_COUNT_HW_BUS_CYCLES]          = ARMV7_PERFCTR_CLOCK_CYCLES,
-};
-
-static const unsigned armv7_a9_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
-                                          [PERF_COUNT_HW_CACHE_OP_MAX]
-                                          [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
-        [C(L1D)] = {
-                /*
-                 * The performance counters don't differentiate between read
-                 * and write accesses/misses so this isn't strictly correct,
-                 * but it's the best we can do. Writes and reads get
-                 * combined.
-                 */
-                [C(OP_READ)] = {
-                        [C(RESULT_ACCESS)]      = ARMV7_PERFCTR_DCACHE_ACCESS,
-                        [C(RESULT_MISS)]        = ARMV7_PERFCTR_DCACHE_REFILL,
-                },
-                [C(OP_WRITE)] = {
-                        [C(RESULT_ACCESS)]      = ARMV7_PERFCTR_DCACHE_ACCESS,
-                        [C(RESULT_MISS)]        = ARMV7_PERFCTR_DCACHE_REFILL,
-                },
-                [C(OP_PREFETCH)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
-                },
-        },
-        [C(L1I)] = {
-                [C(OP_READ)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = ARMV7_PERFCTR_IFETCH_MISS,
-                },
-                [C(OP_WRITE)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = ARMV7_PERFCTR_IFETCH_MISS,
-                },
-                [C(OP_PREFETCH)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
-                },
-        },
-        [C(LL)] = {
-                [C(OP_READ)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
-                },
-                [C(OP_WRITE)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
-                },
-                [C(OP_PREFETCH)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
-                },
-        },
-        [C(DTLB)] = {
-                /*
-                 * Only ITLB misses and DTLB refills are supported.
-                 * If users want the DTLB refills misses a raw counter
-                 * must be used.
-                 */
-                [C(OP_READ)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = ARMV7_PERFCTR_DTLB_REFILL,
-                },
-                [C(OP_WRITE)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = ARMV7_PERFCTR_DTLB_REFILL,
-                },
-                [C(OP_PREFETCH)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
-                },
-        },
-        [C(ITLB)] = {
-                [C(OP_READ)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = ARMV7_PERFCTR_ITLB_MISS,
-                },
-                [C(OP_WRITE)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = ARMV7_PERFCTR_ITLB_MISS,
-                },
-                [C(OP_PREFETCH)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
-                },
-        },
-        [C(BPU)] = {
-                [C(OP_READ)] = {
-                        [C(RESULT_ACCESS)]      = ARMV7_PERFCTR_PC_WRITE,
-                        [C(RESULT_MISS)]
-                                        = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
-                },
-                [C(OP_WRITE)] = {
-                        [C(RESULT_ACCESS)]      = ARMV7_PERFCTR_PC_WRITE,
-                        [C(RESULT_MISS)]
-                                        = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
-                },
-                [C(OP_PREFETCH)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
-                },
-        },
-};
-
-/*
- * Perf Events counters
- */
-enum armv7_counters {
-        ARMV7_CYCLE_COUNTER             = 1,    /* Cycle counter */
-        ARMV7_COUNTER0                  = 2,    /* First event counter */
-};
-
-/*
- * The cycle counter is ARMV7_CYCLE_COUNTER.
- * The first event counter is ARMV7_COUNTER0.
- * The last event counter is (ARMV7_COUNTER0 + armpmu->num_events - 1).
- */
-#define ARMV7_COUNTER_LAST      (ARMV7_COUNTER0 + armpmu->num_events - 1)
-
-/*
- * ARMv7 low level PMNC access
- */
-
-/*
- * Per-CPU PMNC: config reg
- */
-#define ARMV7_PMNC_E            (1 << 0) /* Enable all counters */
-#define ARMV7_PMNC_P            (1 << 1) /* Reset all counters */
-#define ARMV7_PMNC_C            (1 << 2) /* Cycle counter reset */
-#define ARMV7_PMNC_D            (1 << 3) /* CCNT counts every 64th cpu cycle */
-#define ARMV7_PMNC_X            (1 << 4) /* Export to ETM */
-#define ARMV7_PMNC_DP           (1 << 5) /* Disable CCNT if non-invasive debug*/
-#define ARMV7_PMNC_N_SHIFT      11       /* Number of counters supported */
-#define ARMV7_PMNC_N_MASK       0x1f
-#define ARMV7_PMNC_MASK         0x3f     /* Mask for writable bits */
-
-/*
- * Available counters
- */
-#define ARMV7_CNT0              0       /* First event counter */
-#define ARMV7_CCNT              31      /* Cycle counter */
-
-/* Perf Event to low level counters mapping */
-#define ARMV7_EVENT_CNT_TO_CNTx (ARMV7_COUNTER0 - ARMV7_CNT0)
-
-/*
- * CNTENS: counters enable reg
- */
-#define ARMV7_CNTENS_P(idx)     (1 << (idx - ARMV7_EVENT_CNT_TO_CNTx))
-#define ARMV7_CNTENS_C          (1 << ARMV7_CCNT)
-
-/*
- * CNTENC: counters disable reg
- */
-#define ARMV7_CNTENC_P(idx)     (1 << (idx - ARMV7_EVENT_CNT_TO_CNTx))
-#define ARMV7_CNTENC_C          (1 << ARMV7_CCNT)
-
-/*
- * INTENS: counters overflow interrupt enable reg
- */
-#define ARMV7_INTENS_P(idx)     (1 << (idx - ARMV7_EVENT_CNT_TO_CNTx))
-#define ARMV7_INTENS_C          (1 << ARMV7_CCNT)
-
-/*
- * INTENC: counters overflow interrupt disable reg
- */
-#define ARMV7_INTENC_P(idx)     (1 << (idx - ARMV7_EVENT_CNT_TO_CNTx))
-#define ARMV7_INTENC_C          (1 << ARMV7_CCNT)
-
-/*
- * EVTSEL: Event selection reg
- */
-#define ARMV7_EVTSEL_MASK       0xff            /* Mask for writable bits */
-
-/*
- * SELECT: Counter selection reg
- */
-#define ARMV7_SELECT_MASK       0x1f            /* Mask for writable bits */
-
-/*
- * FLAG: counters overflow flag status reg
- */
-#define ARMV7_FLAG_P(idx)       (1 << (idx - ARMV7_EVENT_CNT_TO_CNTx))
-#define ARMV7_FLAG_C            (1 << ARMV7_CCNT)
-#define ARMV7_FLAG_MASK         0xffffffff      /* Mask for writable bits */
-#define ARMV7_OVERFLOWED_MASK   ARMV7_FLAG_MASK
-
-static inline unsigned long armv7_pmnc_read(void)
-{
-        u32 val;
-        asm volatile("mrc p15, 0, %0, c9, c12, 0" : "=r"(val));
-        return val;
-}
-
-static inline void armv7_pmnc_write(unsigned long val)
-{
-        val &= ARMV7_PMNC_MASK;
-        asm volatile("mcr p15, 0, %0, c9, c12, 0" : : "r"(val));
-}
-
-static inline int armv7_pmnc_has_overflowed(unsigned long pmnc)
-{
-        return pmnc & ARMV7_OVERFLOWED_MASK;
-}
-
-static inline int armv7_pmnc_counter_has_overflowed(unsigned long pmnc,
-                                        enum armv7_counters counter)
-{
-        int ret = 0;
-
-        if (counter == ARMV7_CYCLE_COUNTER)
-                ret = pmnc & ARMV7_FLAG_C;
-        else if ((counter >= ARMV7_COUNTER0) && (counter <= ARMV7_COUNTER_LAST))
-                ret = pmnc & ARMV7_FLAG_P(counter);
-        else
-                pr_err("CPU%u checking wrong counter %d overflow status\n",
-                        smp_processor_id(), counter);
-
-        return ret;
-}
-
-static inline int armv7_pmnc_select_counter(unsigned int idx)
-{
-        u32 val;
-
-        if ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST)) {
-                pr_err("CPU%u selecting wrong PMNC counter"
-                        " %d\n", smp_processor_id(), idx);
-                return -1;
-        }
-
-        val = (idx - ARMV7_EVENT_CNT_TO_CNTx) & ARMV7_SELECT_MASK;
-        asm volatile("mcr p15, 0, %0, c9, c12, 5" : : "r" (val));
-
-        return idx;
-}
-
-static inline u32 armv7pmu_read_counter(int idx)
-{
-        unsigned long value = 0;
-
-        if (idx == ARMV7_CYCLE_COUNTER)
-                asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (value));
-        else if ((idx >= ARMV7_COUNTER0) && (idx <= ARMV7_COUNTER_LAST)) {
-                if (armv7_pmnc_select_counter(idx) == idx)
-                        asm volatile("mrc p15, 0, %0, c9, c13, 2"
-                                     : "=r" (value));
-        } else
-                pr_err("CPU%u reading wrong counter %d\n",
-                        smp_processor_id(), idx);
-
-        return value;
-}
-
-static inline void armv7pmu_write_counter(int idx, u32 value)
-{
-        if (idx == ARMV7_CYCLE_COUNTER)
-                asm volatile("mcr p15, 0, %0, c9, c13, 0" : : "r" (value));
-        else if ((idx >= ARMV7_COUNTER0) && (idx <= ARMV7_COUNTER_LAST)) {
-                if (armv7_pmnc_select_counter(idx) == idx)
-                        asm volatile("mcr p15, 0, %0, c9, c13, 2"
-                                     : : "r" (value));
-        } else
-                pr_err("CPU%u writing wrong counter %d\n",
-                        smp_processor_id(), idx);
-}
-
-static inline void armv7_pmnc_write_evtsel(unsigned int idx, u32 val)
-{
-        if (armv7_pmnc_select_counter(idx) == idx) {
-                val &= ARMV7_EVTSEL_MASK;
-                asm volatile("mcr p15, 0, %0, c9, c13, 1" : : "r" (val));
-        }
-}
-
-static inline u32 armv7_pmnc_enable_counter(unsigned int idx)
-{
-        u32 val;
-
-        if ((idx != ARMV7_CYCLE_COUNTER) &&
-            ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST))) {
-                pr_err("CPU%u enabling wrong PMNC counter"
-                        " %d\n", smp_processor_id(), idx);
-                return -1;
-        }
-
-        if (idx == ARMV7_CYCLE_COUNTER)
-                val = ARMV7_CNTENS_C;
-        else
-                val = ARMV7_CNTENS_P(idx);
-
-        asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (val));
-
-        return idx;
-}
-
-static inline u32 armv7_pmnc_disable_counter(unsigned int idx)
-{
-        u32 val;
-
-
-        if ((idx != ARMV7_CYCLE_COUNTER) &&
-            ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST))) {
-                pr_err("CPU%u disabling wrong PMNC counter"
-                        " %d\n", smp_processor_id(), idx);
-                return -1;
-        }
-
-        if (idx == ARMV7_CYCLE_COUNTER)
-                val = ARMV7_CNTENC_C;
-        else
-                val = ARMV7_CNTENC_P(idx);
-
-        asm volatile("mcr p15, 0, %0, c9, c12, 2" : : "r" (val));
-
-        return idx;
-}
-
-static inline u32 armv7_pmnc_enable_intens(unsigned int idx)
-{
-        u32 val;
-
-        if ((idx != ARMV7_CYCLE_COUNTER) &&
-            ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST))) {
-                pr_err("CPU%u enabling wrong PMNC counter"
-                        " interrupt enable %d\n", smp_processor_id(), idx);
-                return -1;
-        }
-
-        if (idx == ARMV7_CYCLE_COUNTER)
-                val = ARMV7_INTENS_C;
-        else
-                val = ARMV7_INTENS_P(idx);
-
-        asm volatile("mcr p15, 0, %0, c9, c14, 1" : : "r" (val));
-
-        return idx;
-}
-
-static inline u32 armv7_pmnc_disable_intens(unsigned int idx)
-{
-        u32 val;
-
-        if ((idx != ARMV7_CYCLE_COUNTER) &&
-            ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST))) {
-                pr_err("CPU%u disabling wrong PMNC counter"
-                        " interrupt enable %d\n", smp_processor_id(), idx);
-                return -1;
-        }
-
-        if (idx == ARMV7_CYCLE_COUNTER)
-                val = ARMV7_INTENC_C;
-        else
-                val = ARMV7_INTENC_P(idx);
-
-        asm volatile("mcr p15, 0, %0, c9, c14, 2" : : "r" (val));
-
-        return idx;
-}
-
-static inline u32 armv7_pmnc_getreset_flags(void)
-{
-        u32 val;
-
-        /* Read */
-        asm volatile("mrc p15, 0, %0, c9, c12, 3" : "=r" (val));
-
-        /* Write to clear flags */
-        val &= ARMV7_FLAG_MASK;
-        asm volatile("mcr p15, 0, %0, c9, c12, 3" : : "r" (val));
-
-        return val;
-}
-
-#ifdef DEBUG
-static void armv7_pmnc_dump_regs(void)
-{
-        u32 val;
-        unsigned int cnt;
-
-        printk(KERN_INFO "PMNC registers dump:\n");
-
-        asm volatile("mrc p15, 0, %0, c9, c12, 0" : "=r" (val));
-        printk(KERN_INFO "PMNC  =0x%08x\n", val);
-
-        asm volatile("mrc p15, 0, %0, c9, c12, 1" : "=r" (val));
-        printk(KERN_INFO "CNTENS=0x%08x\n", val);
-
-        asm volatile("mrc p15, 0, %0, c9, c14, 1" : "=r" (val));
-        printk(KERN_INFO "INTENS=0x%08x\n", val);
-
-        asm volatile("mrc p15, 0, %0, c9, c12, 3" : "=r" (val));
-        printk(KERN_INFO "FLAGS =0x%08x\n", val);
-
-        asm volatile("mrc p15, 0, %0, c9, c12, 5" : "=r" (val));
-        printk(KERN_INFO "SELECT=0x%08x\n", val);
-
-        asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (val));
-        printk(KERN_INFO "CCNT  =0x%08x\n", val);
-
-        for (cnt = ARMV7_COUNTER0; cnt < ARMV7_COUNTER_LAST; cnt++) {
-                armv7_pmnc_select_counter(cnt);
-                asm volatile("mrc p15, 0, %0, c9, c13, 2" : "=r" (val));
-                printk(KERN_INFO "CNT[%d] count =0x%08x\n",
-                        cnt-ARMV7_EVENT_CNT_TO_CNTx, val);
-                asm volatile("mrc p15, 0, %0, c9, c13, 1" : "=r" (val));
-                printk(KERN_INFO "CNT[%d] evtsel=0x%08x\n",
-                        cnt-ARMV7_EVENT_CNT_TO_CNTx, val);
-        }
-}
-#endif
-
-void armv7pmu_enable_event(struct hw_perf_event *hwc, int idx)
-{
-        unsigned long flags;
-
-        /*
-         * Enable counter and interrupt, and set the counter to count
-         * the event that we're interested in.
-         */
-        spin_lock_irqsave(&pmu_lock, flags);
-
-        /*
-         * Disable counter
-         */
-        armv7_pmnc_disable_counter(idx);
-
-        /*
-         * Set event (if destined for PMNx counters)
-         * We don't need to set the event if it's a cycle count
-         */
-        if (idx != ARMV7_CYCLE_COUNTER)
-                armv7_pmnc_write_evtsel(idx, hwc->config_base);
-
-        /*
-         * Enable interrupt for this counter
-         */
-        armv7_pmnc_enable_intens(idx);
-
-        /*
-         * Enable counter
-         */
-        armv7_pmnc_enable_counter(idx);
-
-        spin_unlock_irqrestore(&pmu_lock, flags);
-}
-
-static void armv7pmu_disable_event(struct hw_perf_event *hwc, int idx)
-{
-        unsigned long flags;
-
-        /*
-         * Disable counter and interrupt
-         */
-        spin_lock_irqsave(&pmu_lock, flags);
-
-        /*
-         * Disable counter
-         */
-        armv7_pmnc_disable_counter(idx);
-
-        /*
-         * Disable interrupt for this counter
-         */
-        armv7_pmnc_disable_intens(idx);
-
-        spin_unlock_irqrestore(&pmu_lock, flags);
-}
-
-static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev)
-{
-        unsigned long pmnc;
-        struct perf_sample_data data;
-        struct cpu_hw_events *cpuc;
-        struct pt_regs *regs;
-        int idx;
-
-        /*
-         * Get and reset the IRQ flags
-         */
-        pmnc = armv7_pmnc_getreset_flags();
-
-        /*
-         * Did an overflow occur?
-         */
-        if (!armv7_pmnc_has_overflowed(pmnc))
-                return IRQ_NONE;
-
-        /*
-         * Handle the counter(s) overflow(s)
-         */
-        regs = get_irq_regs();
-
-        perf_sample_data_init(&data, 0);
-
-        cpuc = &__get_cpu_var(cpu_hw_events);
-        for (idx = 0; idx <= armpmu->num_events; ++idx) {
-                struct perf_event *event = cpuc->events[idx];
-                struct hw_perf_event *hwc;
-
-                if (!test_bit(idx, cpuc->active_mask))
-                        continue;
-
-                /*
-                 * We have a single interrupt for all counters. Check that
-                 * each counter has overflowed before we process it.
-                 */
-                if (!armv7_pmnc_counter_has_overflowed(pmnc, idx))
-                        continue;
-
-                hwc = &event->hw;
-                armpmu_event_update(event, hwc, idx);
-                data.period = event->hw.last_period;
-                if (!armpmu_event_set_period(event, hwc, idx))
-                        continue;
-
-                if (perf_event_overflow(event, 0, &data, regs))
-                        armpmu->disable(hwc, idx);
-        }
-
-        /*
-         * Handle the pending perf events.
-         *
-         * Note: this call *must* be run with interrupts disabled. For
-         * platforms that can have the PMU interrupts raised as an NMI, this
-         * will not work.
-         */
-        irq_work_run();
-
-        return IRQ_HANDLED;
-}
-
-static void armv7pmu_start(void)
-{
-        unsigned long flags;
-
-        spin_lock_irqsave(&pmu_lock, flags);
-        /* Enable all counters */
-        armv7_pmnc_write(armv7_pmnc_read() | ARMV7_PMNC_E);
-        spin_unlock_irqrestore(&pmu_lock, flags);
-}
-
-static void armv7pmu_stop(void)
-{
-        unsigned long flags;
-
-        spin_lock_irqsave(&pmu_lock, flags);
-        /* Disable all counters */
-        armv7_pmnc_write(armv7_pmnc_read() & ~ARMV7_PMNC_E);
-        spin_unlock_irqrestore(&pmu_lock, flags);
-}
-
-static inline int armv7_a8_pmu_event_map(int config)
-{
-        int mapping = armv7_a8_perf_map[config];
-        if (HW_OP_UNSUPPORTED == mapping)
-                mapping = -EOPNOTSUPP;
-        return mapping;
-}
-
-static inline int armv7_a9_pmu_event_map(int config)
-{
-        int mapping = armv7_a9_perf_map[config];
-        if (HW_OP_UNSUPPORTED == mapping)
-                mapping = -EOPNOTSUPP;
-        return mapping;
-}
-
-static u64 armv7pmu_raw_event(u64 config)
-{
-        return config & 0xff;
-}
-
-static int armv7pmu_get_event_idx(struct cpu_hw_events *cpuc,
-                                  struct hw_perf_event *event)
-{
-        int idx;
-
-        /* Always place a cycle counter into the cycle counter. */
-        if (event->config_base == ARMV7_PERFCTR_CPU_CYCLES) {
-                if (test_and_set_bit(ARMV7_CYCLE_COUNTER, cpuc->used_mask))
-                        return -EAGAIN;
-
-                return ARMV7_CYCLE_COUNTER;
-        } else {
-                /*
-                 * For anything other than a cycle counter, try and use
-                 * the events counters
-                 */
-                for (idx = ARMV7_COUNTER0; idx <= armpmu->num_events; ++idx) {
-                        if (!test_and_set_bit(idx, cpuc->used_mask))
-                                return idx;
-                }
-
-                /* The counters are all in use. */
-                return -EAGAIN;
-        }
-}
-
-static struct arm_pmu armv7pmu = {
-        .handle_irq             = armv7pmu_handle_irq,
-        .enable                 = armv7pmu_enable_event,
-        .disable                = armv7pmu_disable_event,
-        .raw_event              = armv7pmu_raw_event,
-        .read_counter           = armv7pmu_read_counter,
-        .write_counter          = armv7pmu_write_counter,
-        .get_event_idx          = armv7pmu_get_event_idx,
-        .start                  = armv7pmu_start,
-        .stop                   = armv7pmu_stop,
-        .max_period             = (1LLU << 32) - 1,
-};
-
-static u32 __init armv7_reset_read_pmnc(void)
-{
-        u32 nb_cnt;
-
-        /* Initialize & Reset PMNC: C and P bits */
-        armv7_pmnc_write(ARMV7_PMNC_P | ARMV7_PMNC_C);
-
-        /* Read the nb of CNTx counters supported from PMNC */
-        nb_cnt = (armv7_pmnc_read() >> ARMV7_PMNC_N_SHIFT) & ARMV7_PMNC_N_MASK;
-
-        /* Add the CPU cycles counter and return */
-        return nb_cnt + 1;
-}
-
-/*
- * ARMv5 [xscale] Performance counter handling code.
- *
- * Based on xscale OProfile code.
- *
- * There are two variants of the xscale PMU that we support:
- *      - xscale1pmu: 2 event counters and a cycle counter
- *      - xscale2pmu: 4 event counters and a cycle counter
- * The two variants share event definitions, but have different
- * PMU structures.
- */
-
-enum xscale_perf_types {
-        XSCALE_PERFCTR_ICACHE_MISS              = 0x00,
-        XSCALE_PERFCTR_ICACHE_NO_DELIVER        = 0x01,
-        XSCALE_PERFCTR_DATA_STALL               = 0x02,
-        XSCALE_PERFCTR_ITLB_MISS                = 0x03,
-        XSCALE_PERFCTR_DTLB_MISS                = 0x04,
-        XSCALE_PERFCTR_BRANCH                   = 0x05,
-        XSCALE_PERFCTR_BRANCH_MISS              = 0x06,
-        XSCALE_PERFCTR_INSTRUCTION              = 0x07,
-        XSCALE_PERFCTR_DCACHE_FULL_STALL        = 0x08,
-        XSCALE_PERFCTR_DCACHE_FULL_STALL_CONTIG = 0x09,
-        XSCALE_PERFCTR_DCACHE_ACCESS            = 0x0A,
-        XSCALE_PERFCTR_DCACHE_MISS              = 0x0B,
-        XSCALE_PERFCTR_DCACHE_WRITE_BACK        = 0x0C,
-        XSCALE_PERFCTR_PC_CHANGED               = 0x0D,
-        XSCALE_PERFCTR_BCU_REQUEST              = 0x10,
-        XSCALE_PERFCTR_BCU_FULL                 = 0x11,
-        XSCALE_PERFCTR_BCU_DRAIN                = 0x12,
-        XSCALE_PERFCTR_BCU_ECC_NO_ELOG          = 0x14,
-        XSCALE_PERFCTR_BCU_1_BIT_ERR            = 0x15,
-        XSCALE_PERFCTR_RMW                      = 0x16,
-        /* XSCALE_PERFCTR_CCNT is not hardware defined */
-        XSCALE_PERFCTR_CCNT                     = 0xFE,
-        XSCALE_PERFCTR_UNUSED                   = 0xFF,
-};
-
-enum xscale_counters {
-        XSCALE_CYCLE_COUNTER    = 1,
-        XSCALE_COUNTER0,
-        XSCALE_COUNTER1,
-        XSCALE_COUNTER2,
-        XSCALE_COUNTER3,
-};
-
-static const unsigned xscale_perf_map[PERF_COUNT_HW_MAX] = {
-        [PERF_COUNT_HW_CPU_CYCLES]          = XSCALE_PERFCTR_CCNT,
-        [PERF_COUNT_HW_INSTRUCTIONS]        = XSCALE_PERFCTR_INSTRUCTION,
-        [PERF_COUNT_HW_CACHE_REFERENCES]    = HW_OP_UNSUPPORTED,
-        [PERF_COUNT_HW_CACHE_MISSES]        = HW_OP_UNSUPPORTED,
-        [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = XSCALE_PERFCTR_BRANCH,
-        [PERF_COUNT_HW_BRANCH_MISSES]       = XSCALE_PERFCTR_BRANCH_MISS,
-        [PERF_COUNT_HW_BUS_CYCLES]          = HW_OP_UNSUPPORTED,
-};
-
-static const unsigned xscale_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
-                                           [PERF_COUNT_HW_CACHE_OP_MAX]
-                                           [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
-        [C(L1D)] = {
-                [C(OP_READ)] = {
-                        [C(RESULT_ACCESS)]      = XSCALE_PERFCTR_DCACHE_ACCESS,
-                        [C(RESULT_MISS)]        = XSCALE_PERFCTR_DCACHE_MISS,
-                },
-                [C(OP_WRITE)] = {
-                        [C(RESULT_ACCESS)]      = XSCALE_PERFCTR_DCACHE_ACCESS,
-                        [C(RESULT_MISS)]        = XSCALE_PERFCTR_DCACHE_MISS,
-                },
-                [C(OP_PREFETCH)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
-                },
-        },
-        [C(L1I)] = {
-                [C(OP_READ)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = XSCALE_PERFCTR_ICACHE_MISS,
-                },
-                [C(OP_WRITE)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = XSCALE_PERFCTR_ICACHE_MISS,
-                },
-                [C(OP_PREFETCH)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
-                },
-        },
-        [C(LL)] = {
-                [C(OP_READ)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
-                },
-                [C(OP_WRITE)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
-                },
-                [C(OP_PREFETCH)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
-                },
-        },
-        [C(DTLB)] = {
-                [C(OP_READ)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = XSCALE_PERFCTR_DTLB_MISS,
-                },
-                [C(OP_WRITE)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = XSCALE_PERFCTR_DTLB_MISS,
-                },
-                [C(OP_PREFETCH)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
-                },
-        },
-        [C(ITLB)] = {
-                [C(OP_READ)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = XSCALE_PERFCTR_ITLB_MISS,
-                },
-                [C(OP_WRITE)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = XSCALE_PERFCTR_ITLB_MISS,
-                },
-                [C(OP_PREFETCH)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
-                },
-        },
-        [C(BPU)] = {
-                [C(OP_READ)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
-                },
-                [C(OP_WRITE)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
-                },
-                [C(OP_PREFETCH)] = {
-                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
-                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
-                },
-        },
-};
-
-#define XSCALE_PMU_ENABLE       0x001
-#define XSCALE_PMN_RESET        0x002
-#define XSCALE_CCNT_RESET       0x004
-#define XSCALE_PMU_RESET        (CCNT_RESET | PMN_RESET)
-#define XSCALE_PMU_CNT64        0x008
-
-static inline int
-xscalepmu_event_map(int config)
-{
-        int mapping = xscale_perf_map[config];
-        if (HW_OP_UNSUPPORTED == mapping)
-                mapping = -EOPNOTSUPP;
-        return mapping;
-}
-
-static u64
-xscalepmu_raw_event(u64 config)
-{
-        return config & 0xff;
-}
-
-#define XSCALE1_OVERFLOWED_MASK 0x700
-#define XSCALE1_CCOUNT_OVERFLOW 0x400
-#define XSCALE1_COUNT0_OVERFLOW 0x100
-#define XSCALE1_COUNT1_OVERFLOW 0x200
-#define XSCALE1_CCOUNT_INT_EN   0x040
-#define XSCALE1_COUNT0_INT_EN   0x010
-#define XSCALE1_COUNT1_INT_EN   0x020
-#define XSCALE1_COUNT0_EVT_SHFT 12
-#define XSCALE1_COUNT0_EVT_MASK (0xff << XSCALE1_COUNT0_EVT_SHFT)
-#define XSCALE1_COUNT1_EVT_SHFT 20
-#define XSCALE1_COUNT1_EVT_MASK (0xff << XSCALE1_COUNT1_EVT_SHFT)
-
-static inline u32
-xscale1pmu_read_pmnc(void)
-{
-        u32 val;
-        asm volatile("mrc p14, 0, %0, c0, c0, 0" : "=r" (val));
-        return val;
-}
-
-static inline void
-xscale1pmu_write_pmnc(u32 val)
-{
-        /* upper 4bits and 7, 11 are write-as-0 */
-        val &= 0xffff77f;
-        asm volatile("mcr p14, 0, %0, c0, c0, 0" : : "r" (val));
-}
-
-static inline int
-xscale1_pmnc_counter_has_overflowed(unsigned long pmnc,
-                                        enum xscale_counters counter)
-{
-        int ret = 0;
-
-        switch (counter) {
-        case XSCALE_CYCLE_COUNTER:
-                ret = pmnc & XSCALE1_CCOUNT_OVERFLOW;
-                break;
-        case XSCALE_COUNTER0:
-                ret = pmnc & XSCALE1_COUNT0_OVERFLOW;
-                break;
-        case XSCALE_COUNTER1:
-                ret = pmnc & XSCALE1_COUNT1_OVERFLOW;
-                break;
-        default:
-                WARN_ONCE(1, "invalid counter number (%d)\n", counter);
-        }
-
-        return ret;
-}
-
-static irqreturn_t
-xscale1pmu_handle_irq(int irq_num, void *dev)
-{
-        unsigned long pmnc;
-        struct perf_sample_data data;
-        struct cpu_hw_events *cpuc;
-        struct pt_regs *regs;
-        int idx;
-
-        /*
-         * NOTE: there's an A stepping erratum that states if an overflow
-         *       bit already exists and another occurs, the previous
-         *       Overflow bit gets cleared. There's no workaround.
-         *       Fixed in B stepping or later.
-         */
-        pmnc = xscale1pmu_read_pmnc();
-
-        /*
-         * Write the value back to clear the overflow flags. Overflow
-         * flags remain in pmnc for use below. We also disable the PMU
-         * while we process the interrupt.
-         */
-        xscale1pmu_write_pmnc(pmnc & ~XSCALE_PMU_ENABLE);
-
-        if (!(pmnc & XSCALE1_OVERFLOWED_MASK))
-                return IRQ_NONE;
-
-        regs = get_irq_regs();
-
-        perf_sample_data_init(&data, 0);
-
-        cpuc = &__get_cpu_var(cpu_hw_events);
-        for (idx = 0; idx <= armpmu->num_events; ++idx) {
-                struct perf_event *event = cpuc->events[idx];
-                struct hw_perf_event *hwc;
-
-                if (!test_bit(idx, cpuc->active_mask))
-                        continue;
-
-                if (!xscale1_pmnc_counter_has_overflowed(pmnc, idx))
-                        continue;
-
-                hwc = &event->hw;
-                armpmu_event_update(event, hwc, idx);
-                data.period = event->hw.last_period;
-                if (!armpmu_event_set_period(event, hwc, idx))
-                        continue;
-
-                if (perf_event_overflow(event, 0, &data, regs))
-                        armpmu->disable(hwc, idx);
-        }
-
-        irq_work_run();
-
-        /*
-         * Re-enable the PMU.
-         */
-        pmnc = xscale1pmu_read_pmnc() | XSCALE_PMU_ENABLE;
-        xscale1pmu_write_pmnc(pmnc);
-
-        return IRQ_HANDLED;
-}
-
-static void
-xscale1pmu_enable_event(struct hw_perf_event *hwc, int idx)
-{
-        unsigned long val, mask, evt, flags;
-
-        switch (idx) {
-        case XSCALE_CYCLE_COUNTER:
-                mask = 0;
-                evt = XSCALE1_CCOUNT_INT_EN;
-                break;
-        case XSCALE_COUNTER0:
-                mask = XSCALE1_COUNT0_EVT_MASK;
-                evt = (hwc->config_base << XSCALE1_COUNT0_EVT_SHFT) |
-                        XSCALE1_COUNT0_INT_EN;
-                break;
-        case XSCALE_COUNTER1:
-                mask = XSCALE1_COUNT1_EVT_MASK;
-                evt = (hwc->config_base << XSCALE1_COUNT1_EVT_SHFT) |
-                        XSCALE1_COUNT1_INT_EN;
-                break;
-        default:
-                WARN_ONCE(1, "invalid counter number (%d)\n", idx);
-                return;
-        }
-
-        spin_lock_irqsave(&pmu_lock, flags);
-        val = xscale1pmu_read_pmnc();
-        val &= ~mask;
-        val |= evt;
-        xscale1pmu_write_pmnc(val);
-        spin_unlock_irqrestore(&pmu_lock, flags);
-}
-
-static void
-xscale1pmu_disable_event(struct hw_perf_event *hwc, int idx)
-{
-        unsigned long val, mask, evt, flags;
-
-        switch (idx) {
-        case XSCALE_CYCLE_COUNTER:
-                mask = XSCALE1_CCOUNT_INT_EN;
-                evt = 0;
-                break;
-        case XSCALE_COUNTER0:
-                mask = XSCALE1_COUNT0_INT_EN | XSCALE1_COUNT0_EVT_MASK;
-                evt = XSCALE_PERFCTR_UNUSED << XSCALE1_COUNT0_EVT_SHFT;
-                break;
-        case XSCALE_COUNTER1:
-                mask = XSCALE1_COUNT1_INT_EN | XSCALE1_COUNT1_EVT_MASK;
-                evt = XSCALE_PERFCTR_UNUSED << XSCALE1_COUNT1_EVT_SHFT;
-                break;
-        default:
-                WARN_ONCE(1, "invalid counter number (%d)\n", idx);
-                return;
-        }
-
-        spin_lock_irqsave(&pmu_lock, flags);
-        val = xscale1pmu_read_pmnc();
-        val &= ~mask;
-        val |= evt;
-        xscale1pmu_write_pmnc(val);
-        spin_unlock_irqrestore(&pmu_lock, flags);
-}
-
-static int
-xscale1pmu_get_event_idx(struct cpu_hw_events *cpuc,
-                        struct hw_perf_event *event)
-{
-        if (XSCALE_PERFCTR_CCNT == event->config_base) {
-                if (test_and_set_bit(XSCALE_CYCLE_COUNTER, cpuc->used_mask))
-                        return -EAGAIN;
-
-                return XSCALE_CYCLE_COUNTER;
-        } else {
-                if (!test_and_set_bit(XSCALE_COUNTER1, cpuc->used_mask)) {
-                        return XSCALE_COUNTER1;
-                }
-
-                if (!test_and_set_bit(XSCALE_COUNTER0, cpuc->used_mask)) {
-                        return XSCALE_COUNTER0;
-                }
-
-                return -EAGAIN;
-        }
-}
-
-static void
-xscale1pmu_start(void)
-{
-        unsigned long flags, val;
-
-        spin_lock_irqsave(&pmu_lock, flags);
-        val = xscale1pmu_read_pmnc();
-        val |= XSCALE_PMU_ENABLE;
-        xscale1pmu_write_pmnc(val);
-        spin_unlock_irqrestore(&pmu_lock, flags);
-}
-
-static void
-xscale1pmu_stop(void)
-{
-        unsigned long flags, val;
-
-        spin_lock_irqsave(&pmu_lock, flags);
-        val = xscale1pmu_read_pmnc();
-        val &= ~XSCALE_PMU_ENABLE;
-        xscale1pmu_write_pmnc(val);
-        spin_unlock_irqrestore(&pmu_lock, flags);
-}
-
-static inline u32
-xscale1pmu_read_counter(int counter)
-{
-        u32 val = 0;
-
-        switch (counter) {
-        case XSCALE_CYCLE_COUNTER:
-                asm volatile("mrc p14, 0, %0, c1, c0, 0" : "=r" (val));
-                break;
-        case XSCALE_COUNTER0:
-                asm volatile("mrc p14, 0, %0, c2, c0, 0" : "=r" (val));
-                break;
-        case XSCALE_COUNTER1:
-                asm volatile("mrc p14, 0, %0, c3, c0, 0" : "=r" (val));
-                break;
-        }
-
-        return val;
-}
-
-static inline void
-xscale1pmu_write_counter(int counter, u32 val)
-{
-        switch (counter) {
-        case XSCALE_CYCLE_COUNTER:
-                asm volatile("mcr p14, 0, %0, c1, c0, 0" : : "r" (val));
-                break;
-        case XSCALE_COUNTER0:
-                asm volatile("mcr p14, 0, %0, c2, c0, 0" : : "r" (val));
-                break;
-        case XSCALE_COUNTER1:
-                asm volatile("mcr p14, 0, %0, c3, c0, 0" : : "r" (val));
-                break;
-        }
-}
-
-static const struct arm_pmu xscale1pmu = {
-        .id             = ARM_PERF_PMU_ID_XSCALE1,
-        .handle_irq     = xscale1pmu_handle_irq,
-        .enable         = xscale1pmu_enable_event,
-        .disable        = xscale1pmu_disable_event,
-        .event_map      = xscalepmu_event_map,
-        .raw_event      = xscalepmu_raw_event,
-        .read_counter   = xscale1pmu_read_counter,
-        .write_counter  = xscale1pmu_write_counter,
-        .get_event_idx  = xscale1pmu_get_event_idx,
-        .start          = xscale1pmu_start,
-        .stop           = xscale1pmu_stop,
-        .num_events     = 3,
-        .max_period     = (1LLU << 32) - 1,
-};
-
-#define XSCALE2_OVERFLOWED_MASK 0x01f
-#define XSCALE2_CCOUNT_OVERFLOW 0x001
-#define XSCALE2_COUNT0_OVERFLOW 0x002
-#define XSCALE2_COUNT1_OVERFLOW 0x004
-#define XSCALE2_COUNT2_OVERFLOW 0x008
-#define XSCALE2_COUNT3_OVERFLOW 0x010
-#define XSCALE2_CCOUNT_INT_EN   0x001
-#define XSCALE2_COUNT0_INT_EN   0x002
-#define XSCALE2_COUNT1_INT_EN   0x004
-#define XSCALE2_COUNT2_INT_EN   0x008
-#define XSCALE2_COUNT3_INT_EN   0x010
-#define XSCALE2_COUNT0_EVT_SHFT 0
-#define XSCALE2_COUNT0_EVT_MASK (0xff << XSCALE2_COUNT0_EVT_SHFT)
-#define XSCALE2_COUNT1_EVT_SHFT 8
-#define XSCALE2_COUNT1_EVT_MASK (0xff << XSCALE2_COUNT1_EVT_SHFT)
-#define XSCALE2_COUNT2_EVT_SHFT 16
-#define XSCALE2_COUNT2_EVT_MASK (0xff << XSCALE2_COUNT2_EVT_SHFT)
-#define XSCALE2_COUNT3_EVT_SHFT 24
-#define XSCALE2_COUNT3_EVT_MASK (0xff << XSCALE2_COUNT3_EVT_SHFT)
-
-static inline u32
-xscale2pmu_read_pmnc(void)
-{
-        u32 val;
-        asm volatile("mrc p14, 0, %0, c0, c1, 0" : "=r" (val));
-        /* bits 1-2 and 4-23 are read-unpredictable */
-        return val & 0xff000009;
-}
-
-static inline void
-xscale2pmu_write_pmnc(u32 val)
-{
-        /* bits 4-23 are write-as-0, 24-31 are write ignored */
-        val &= 0xf;
-        asm volatile("mcr p14, 0, %0, c0, c1, 0" : : "r" (val));
-}
-
-static inline u32
-xscale2pmu_read_overflow_flags(void)
-{
-        u32 val;
-        asm volatile("mrc p14, 0, %0, c5, c1, 0" : "=r" (val));
-        return val;
-}
-
-static inline void
-xscale2pmu_write_overflow_flags(u32 val)
-{
-        asm volatile("mcr p14, 0, %0, c5, c1, 0" : : "r" (val));
-}
-
-static inline u32
-xscale2pmu_read_event_select(void)
-{
-        u32 val;
-        asm volatile("mrc p14, 0, %0, c8, c1, 0" : "=r" (val));
-        return val;
-}
-
-static inline void
-xscale2pmu_write_event_select(u32 val)
-{
-        asm volatile("mcr p14, 0, %0, c8, c1, 0" : : "r"(val));
-}
-
-static inline u32
-xscale2pmu_read_int_enable(void)
-{
-        u32 val;
-        asm volatile("mrc p14, 0, %0, c4, c1, 0" : "=r" (val));
-        return val;
-}
-
-static void
-xscale2pmu_write_int_enable(u32 val)
-{
-        asm volatile("mcr p14, 0, %0, c4, c1, 0" : : "r" (val));
-}
-
-static inline int
-xscale2_pmnc_counter_has_overflowed(unsigned long of_flags,
-                                        enum xscale_counters counter)
-{
-        int ret = 0;
-
-        switch (counter) {
-        case XSCALE_CYCLE_COUNTER:
-                ret = of_flags & XSCALE2_CCOUNT_OVERFLOW;
-                break;
-        case XSCALE_COUNTER0:
-                ret = of_flags & XSCALE2_COUNT0_OVERFLOW;
-                break;
-        case XSCALE_COUNTER1:
-                ret = of_flags & XSCALE2_COUNT1_OVERFLOW;
-                break;
-        case XSCALE_COUNTER2:
-                ret = of_flags & XSCALE2_COUNT2_OVERFLOW;
-                break;
-        case XSCALE_COUNTER3:
-                ret = of_flags & XSCALE2_COUNT3_OVERFLOW;
-                break;
-        default:
-                WARN_ONCE(1, "invalid counter number (%d)\n", counter);
-        }
-
-        return ret;
-}
-
-static irqreturn_t
-xscale2pmu_handle_irq(int irq_num, void *dev)
-{
-        unsigned long pmnc, of_flags;
-        struct perf_sample_data data;
-        struct cpu_hw_events *cpuc;
-        struct pt_regs *regs;
-        int idx;
-
-        /* Disable the PMU. */
-        pmnc = xscale2pmu_read_pmnc();
-        xscale2pmu_write_pmnc(pmnc & ~XSCALE_PMU_ENABLE);
-
-        /* Check the overflow flag register. */
-        of_flags = xscale2pmu_read_overflow_flags();
-        if (!(of_flags & XSCALE2_OVERFLOWED_MASK))
-                return IRQ_NONE;
-
-        /* Clear the overflow bits. */
-        xscale2pmu_write_overflow_flags(of_flags);
-
-        regs = get_irq_regs();
-
-        perf_sample_data_init(&data, 0);
-
-        cpuc = &__get_cpu_var(cpu_hw_events);
-        for (idx = 0; idx <= armpmu->num_events; ++idx) {
-                struct perf_event *event = cpuc->events[idx];
-                struct hw_perf_event *hwc;
-
-                if (!test_bit(idx, cpuc->active_mask))
-                        continue;
-
-                if (!xscale2_pmnc_counter_has_overflowed(pmnc, idx))
-                        continue;
-
-                hwc = &event->hw;
-                armpmu_event_update(event, hwc, idx);
-                data.period = event->hw.last_period;
-                if (!armpmu_event_set_period(event, hwc, idx))
-                        continue;
-
-                if (perf_event_overflow(event, 0, &data, regs))
-                        armpmu->disable(hwc, idx);
-        }
-
-        irq_work_run();
-
-        /*
-         * Re-enable the PMU.
-         */
-        pmnc = xscale2pmu_read_pmnc() | XSCALE_PMU_ENABLE;
-        xscale2pmu_write_pmnc(pmnc);
-
-        return IRQ_HANDLED;
-}
-
-static void
-xscale2pmu_enable_event(struct hw_perf_event *hwc, int idx)
-{
-        unsigned long flags, ien, evtsel;
-
-        ien = xscale2pmu_read_int_enable();
-        evtsel = xscale2pmu_read_event_select();
-
-        switch (idx) {
-        case XSCALE_CYCLE_COUNTER:
-                ien |= XSCALE2_CCOUNT_INT_EN;
-                break;
-        case XSCALE_COUNTER0:
-                ien |= XSCALE2_COUNT0_INT_EN;
-                evtsel &= ~XSCALE2_COUNT0_EVT_MASK;
-                evtsel |= hwc->config_base << XSCALE2_COUNT0_EVT_SHFT;
-                break;
-        case XSCALE_COUNTER1:
-                ien |= XSCALE2_COUNT1_INT_EN;
-                evtsel &= ~XSCALE2_COUNT1_EVT_MASK;
-                evtsel |= hwc->config_base << XSCALE2_COUNT1_EVT_SHFT;
-                break;
-        case XSCALE_COUNTER2:
-                ien |= XSCALE2_COUNT2_INT_EN;
-                evtsel &= ~XSCALE2_COUNT2_EVT_MASK;
-                evtsel |= hwc->config_base << XSCALE2_COUNT2_EVT_SHFT;
-                break;
-        case XSCALE_COUNTER3:
-                ien |= XSCALE2_COUNT3_INT_EN;
-                evtsel &= ~XSCALE2_COUNT3_EVT_MASK;
-                evtsel |= hwc->config_base << XSCALE2_COUNT3_EVT_SHFT;
-                break;
-        default:
-                WARN_ONCE(1, "invalid counter number (%d)\n", idx);
-                return;
-        }
-
-        spin_lock_irqsave(&pmu_lock, flags);
-        xscale2pmu_write_event_select(evtsel);
-        xscale2pmu_write_int_enable(ien);
-        spin_unlock_irqrestore(&pmu_lock, flags);
-}
-
-static void
-xscale2pmu_disable_event(struct hw_perf_event *hwc, int idx)
-{
-        unsigned long flags, ien, evtsel;
-
-        ien = xscale2pmu_read_int_enable();
-        evtsel = xscale2pmu_read_event_select();
-
-        switch (idx) {
-        case XSCALE_CYCLE_COUNTER:
-                ien &= ~XSCALE2_CCOUNT_INT_EN;
-                break;
-        case XSCALE_COUNTER0:
-                ien &= ~XSCALE2_COUNT0_INT_EN;
-                evtsel &= ~XSCALE2_COUNT0_EVT_MASK;
-                evtsel |= XSCALE_PERFCTR_UNUSED << XSCALE2_COUNT0_EVT_SHFT;
-                break;
-        case XSCALE_COUNTER1:
-                ien &= ~XSCALE2_COUNT1_INT_EN;
-                evtsel &= ~XSCALE2_COUNT1_EVT_MASK;
-                evtsel |= XSCALE_PERFCTR_UNUSED << XSCALE2_COUNT1_EVT_SHFT;
-                break;
-        case XSCALE_COUNTER2:
-                ien &= ~XSCALE2_COUNT2_INT_EN;
-                evtsel &= ~XSCALE2_COUNT2_EVT_MASK;
-                evtsel |= XSCALE_PERFCTR_UNUSED << XSCALE2_COUNT2_EVT_SHFT;
-                break;
-        case XSCALE_COUNTER3:
-                ien &= ~XSCALE2_COUNT3_INT_EN;
-                evtsel &= ~XSCALE2_COUNT3_EVT_MASK;
-                evtsel |= XSCALE_PERFCTR_UNUSED << XSCALE2_COUNT3_EVT_SHFT;
-                break;
-        default:
-                WARN_ONCE(1, "invalid counter number (%d)\n", idx);
-                return;
-        }
-
-        spin_lock_irqsave(&pmu_lock, flags);
-        xscale2pmu_write_event_select(evtsel);
-        xscale2pmu_write_int_enable(ien);
-        spin_unlock_irqrestore(&pmu_lock, flags);
-}
-
-static int
-xscale2pmu_get_event_idx(struct cpu_hw_events *cpuc,
-                        struct hw_perf_event *event)
-{
-        int idx = xscale1pmu_get_event_idx(cpuc, event);
-        if (idx >= 0)
-                goto out;
-
-        if (!test_and_set_bit(XSCALE_COUNTER3, cpuc->used_mask))
-                idx = XSCALE_COUNTER3;
-        else if (!test_and_set_bit(XSCALE_COUNTER2, cpuc->used_mask))
-                idx = XSCALE_COUNTER2;
-out:
-        return idx;
-}
-
-static void
-xscale2pmu_start(void)
-{
-        unsigned long flags, val;
-
-        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);
-}
-
-static void
-xscale2pmu_stop(void)
-{
-        unsigned long flags, val;
-
-        spin_lock_irqsave(&pmu_lock, flags);
-        val = xscale2pmu_read_pmnc();
-        val &= ~XSCALE_PMU_ENABLE;
-        xscale2pmu_write_pmnc(val);
-        spin_unlock_irqrestore(&pmu_lock, flags);
-}
-
-static inline u32
-xscale2pmu_read_counter(int counter)
-{
-        u32 val = 0;
-
-        switch (counter) {
-        case XSCALE_CYCLE_COUNTER:
-                asm volatile("mrc p14, 0, %0, c1, c1, 0" : "=r" (val));
-                break;
-        case XSCALE_COUNTER0:
-                asm volatile("mrc p14, 0, %0, c0, c2, 0" : "=r" (val));
-                break;
-        case XSCALE_COUNTER1:
-                asm volatile("mrc p14, 0, %0, c1, c2, 0" : "=r" (val));
-                break;
-        case XSCALE_COUNTER2:
-                asm volatile("mrc p14, 0, %0, c2, c2, 0" : "=r" (val));
-                break;
-        case XSCALE_COUNTER3:
-                asm volatile("mrc p14, 0, %0, c3, c2, 0" : "=r" (val));
-                break;
-        }
-
-        return val;
-}
-
-static inline void
-xscale2pmu_write_counter(int counter, u32 val)
-{
-        switch (counter) {
-        case XSCALE_CYCLE_COUNTER:
-                asm volatile("mcr p14, 0, %0, c1, c1, 0" : : "r" (val));
-                break;
-        case XSCALE_COUNTER0:
-                asm volatile("mcr p14, 0, %0, c0, c2, 0" : : "r" (val));
-                break;
-        case XSCALE_COUNTER1:
-                asm volatile("mcr p14, 0, %0, c1, c2, 0" : : "r" (val));
-                break;
-        case XSCALE_COUNTER2:
-                asm volatile("mcr p14, 0, %0, c2, c2, 0" : : "r" (val));
-                break;
-        case XSCALE_COUNTER3:
-                asm volatile("mcr p14, 0, %0, c3, c2, 0" : : "r" (val));
-                break;
-        }
-}
-
-static const struct arm_pmu xscale2pmu = {
-        .id             = ARM_PERF_PMU_ID_XSCALE2,
-        .handle_irq     = xscale2pmu_handle_irq,
-        .enable         = xscale2pmu_enable_event,
-        .disable        = xscale2pmu_disable_event,
-        .event_map      = xscalepmu_event_map,
-        .raw_event      = xscalepmu_raw_event,
-        .read_counter   = xscale2pmu_read_counter,
-        .write_counter  = xscale2pmu_write_counter,
-        .get_event_idx  = xscale2pmu_get_event_idx,
-        .start          = xscale2pmu_start,
-        .stop           = xscale2pmu_stop,
-        .num_events     = 5,
-        .max_period     = (1LLU << 32) - 1,
-};
+/* Include the PMU-specific implementations. */
+#include "perf_event_xscale.c"
+#include "perf_event_v6.c"
+#include "perf_event_v7.c"
 
 static int __init
 init_hw_perf_events(void)
@@ -2977,37 +622,16 @@ init_hw_perf_events(void)
                 case 0xB360:    /* ARM1136 */
                 case 0xB560:    /* ARM1156 */
                 case 0xB760:    /* ARM1176 */
-                        armpmu = &armv6pmu;
-                        memcpy(armpmu_perf_cache_map, armv6_perf_cache_map,
-                                        sizeof(armv6_perf_cache_map));
+                        armpmu = armv6pmu_init();
                         break;
                 case 0xB020:    /* ARM11mpcore */
-                        armpmu = &armv6mpcore_pmu;
-                        memcpy(armpmu_perf_cache_map,
-                               armv6mpcore_perf_cache_map,
-                               sizeof(armv6mpcore_perf_cache_map));
+                        armpmu = armv6mpcore_pmu_init();
                         break;
                 case 0xC080:    /* Cortex-A8 */
-                        armv7pmu.id = ARM_PERF_PMU_ID_CA8;
-                        memcpy(armpmu_perf_cache_map, armv7_a8_perf_cache_map,
-                                sizeof(armv7_a8_perf_cache_map));
-                        armv7pmu.event_map = armv7_a8_pmu_event_map;
-                        armpmu = &armv7pmu;
-
-                        /* Reset PMNC and read the nb of CNTx counters
-                            supported */
-                        armv7pmu.num_events = armv7_reset_read_pmnc();
+                        armpmu = armv7_a8_pmu_init();
                         break;
                 case 0xC090:    /* Cortex-A9 */
-                        armv7pmu.id = ARM_PERF_PMU_ID_CA9;
-                        memcpy(armpmu_perf_cache_map, armv7_a9_perf_cache_map,
-                                sizeof(armv7_a9_perf_cache_map));
-                        armv7pmu.event_map = armv7_a9_pmu_event_map;
-                        armpmu = &armv7pmu;
-
-                        /* Reset PMNC and read the nb of CNTx counters
-                            supported */
-                        armv7pmu.num_events = armv7_reset_read_pmnc();
+                        armpmu = armv7_a9_pmu_init();
                         break;
                 }
         /* Intel CPUs [xscale]. */
@@ -3015,21 +639,17 @@ init_hw_perf_events(void)
                 part_number = (cpuid >> 13) & 0x7;
                 switch (part_number) {
                 case 1:
-                        armpmu = &xscale1pmu;
-                        memcpy(armpmu_perf_cache_map, xscale_perf_cache_map,
-                                        sizeof(xscale_perf_cache_map));
+                        armpmu = xscale1pmu_init();
                         break;
                 case 2:
-                        armpmu = &xscale2pmu;
-                        memcpy(armpmu_perf_cache_map, xscale_perf_cache_map,
-                                        sizeof(xscale_perf_cache_map));
+                        armpmu = xscale2pmu_init();
                         break;
                 }
         }
 
         if (armpmu) {
                 pr_info("enabled with %s PMU driver, %d counters available\n",
-                                arm_pmu_names[armpmu->id], armpmu->num_events);
+                        armpmu->name, armpmu->num_events);
         } else {
                 pr_info("no hardware support available\n");
         }
@@ -3053,17 +673,17 @@ early_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;
@@ -3089,10 +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
new file mode 100644
index 000000000000..c058bfc8532b
--- /dev/null
+++ b/arch/arm/kernel/perf_event_v6.c
@@ -0,0 +1,672 @@
+/*
+ * ARMv6 Performance counter handling code.
+ *
+ * Copyright (C) 2009 picoChip Designs, Ltd., Jamie Iles
+ *
+ * ARMv6 has 2 configurable performance counters and a single cycle counter.
+ * They all share a single reset bit but can be written to zero so we can use
+ * that for a reset.
+ *
+ * The counters can't be individually enabled or disabled so when we remove
+ * one event and replace it with another we could get spurious counts from the
+ * wrong event. However, we can take advantage of the fact that the
+ * performance counters can export events to the event bus, and the event bus
+ * itself can be monitored. This requires that we *don't* export the events to
+ * the event bus. The procedure for disabling a configurable counter is:
+ *      - change the counter to count the ETMEXTOUT[0] signal (0x20). This
+ *        effectively stops the counter from counting.
+ *      - disable the counter's interrupt generation (each counter has it's
+ *        own interrupt enable bit).
+ * Once stopped, the counter value can be written as 0 to reset.
+ *
+ * To enable a counter:
+ *      - enable the counter's interrupt generation.
+ *      - set the new event type.
+ *
+ * Note: the dedicated cycle counter only counts cycles and can't be
+ * enabled/disabled independently of the others. When we want to disable the
+ * cycle counter, we have to just disable the interrupt reporting and start
+ * ignoring that counter. When re-enabling, we have to reset the value and
+ * enable the interrupt.
+ */
+
+#ifdef CONFIG_CPU_V6
+enum armv6_perf_types {
+        ARMV6_PERFCTR_ICACHE_MISS           = 0x0,
+        ARMV6_PERFCTR_IBUF_STALL            = 0x1,
+        ARMV6_PERFCTR_DDEP_STALL            = 0x2,
+        ARMV6_PERFCTR_ITLB_MISS             = 0x3,
+        ARMV6_PERFCTR_DTLB_MISS             = 0x4,
+        ARMV6_PERFCTR_BR_EXEC               = 0x5,
+        ARMV6_PERFCTR_BR_MISPREDICT         = 0x6,
+        ARMV6_PERFCTR_INSTR_EXEC            = 0x7,
+        ARMV6_PERFCTR_DCACHE_HIT            = 0x9,
+        ARMV6_PERFCTR_DCACHE_ACCESS         = 0xA,
+        ARMV6_PERFCTR_DCACHE_MISS           = 0xB,
+        ARMV6_PERFCTR_DCACHE_WBACK          = 0xC,
+        ARMV6_PERFCTR_SW_PC_CHANGE          = 0xD,
+        ARMV6_PERFCTR_MAIN_TLB_MISS         = 0xF,
+        ARMV6_PERFCTR_EXPL_D_ACCESS         = 0x10,
+        ARMV6_PERFCTR_LSU_FULL_STALL        = 0x11,
+        ARMV6_PERFCTR_WBUF_DRAINED          = 0x12,
+        ARMV6_PERFCTR_CPU_CYCLES            = 0xFF,
+        ARMV6_PERFCTR_NOP                   = 0x20,
+};
+
+enum armv6_counters {
+        ARMV6_CYCLE_COUNTER = 1,
+        ARMV6_COUNTER0,
+        ARMV6_COUNTER1,
+};
+
+/*
+ * The hardware events that we support. We do support cache operations but
+ * we have harvard caches and no way to combine instruction and data
+ * accesses/misses in hardware.
+ */
+static const unsigned armv6_perf_map[PERF_COUNT_HW_MAX] = {
+        [PERF_COUNT_HW_CPU_CYCLES]          = ARMV6_PERFCTR_CPU_CYCLES,
+        [PERF_COUNT_HW_INSTRUCTIONS]        = ARMV6_PERFCTR_INSTR_EXEC,
+        [PERF_COUNT_HW_CACHE_REFERENCES]    = HW_OP_UNSUPPORTED,
+        [PERF_COUNT_HW_CACHE_MISSES]        = HW_OP_UNSUPPORTED,
+        [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV6_PERFCTR_BR_EXEC,
+        [PERF_COUNT_HW_BRANCH_MISSES]       = ARMV6_PERFCTR_BR_MISPREDICT,
+        [PERF_COUNT_HW_BUS_CYCLES]          = HW_OP_UNSUPPORTED,
+};
+
+static const unsigned armv6_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
+                                          [PERF_COUNT_HW_CACHE_OP_MAX]
+                                          [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+        [C(L1D)] = {
+                /*
+                 * The performance counters don't differentiate between read
+                 * and write accesses/misses so this isn't strictly correct,
+                 * but it's the best we can do. Writes and reads get
+                 * combined.
+                 */
+                [C(OP_READ)] = {
+                        [C(RESULT_ACCESS)]      = ARMV6_PERFCTR_DCACHE_ACCESS,
+                        [C(RESULT_MISS)]        = ARMV6_PERFCTR_DCACHE_MISS,
+                },
+                [C(OP_WRITE)] = {
+                        [C(RESULT_ACCESS)]      = ARMV6_PERFCTR_DCACHE_ACCESS,
+                        [C(RESULT_MISS)]        = ARMV6_PERFCTR_DCACHE_MISS,
+                },
+                [C(OP_PREFETCH)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
+                },
+        },
+        [C(L1I)] = {
+                [C(OP_READ)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = ARMV6_PERFCTR_ICACHE_MISS,
+                },
+                [C(OP_WRITE)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = ARMV6_PERFCTR_ICACHE_MISS,
+                },
+                [C(OP_PREFETCH)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
+                },
+        },
+        [C(LL)] = {
+                [C(OP_READ)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
+                },
+                [C(OP_WRITE)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
+                },
+                [C(OP_PREFETCH)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
+                },
+        },
+        [C(DTLB)] = {
+                /*
+                 * The ARM performance counters can count micro DTLB misses,
+                 * micro ITLB misses and main TLB misses. There isn't an event
+                 * for TLB misses, so use the micro misses here and if users
+                 * want the main TLB misses they can use a raw counter.
+                 */
+                [C(OP_READ)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = ARMV6_PERFCTR_DTLB_MISS,
+                },
+                [C(OP_WRITE)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = ARMV6_PERFCTR_DTLB_MISS,
+                },
+                [C(OP_PREFETCH)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
+                },
+        },
+        [C(ITLB)] = {
+                [C(OP_READ)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = ARMV6_PERFCTR_ITLB_MISS,
+                },
+                [C(OP_WRITE)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = ARMV6_PERFCTR_ITLB_MISS,
+                },
+                [C(OP_PREFETCH)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
+                },
+        },
+        [C(BPU)] = {
+                [C(OP_READ)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
+                },
+                [C(OP_WRITE)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
+                },
+                [C(OP_PREFETCH)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
+                },
+        },
+};
+
+enum armv6mpcore_perf_types {
+        ARMV6MPCORE_PERFCTR_ICACHE_MISS     = 0x0,
+        ARMV6MPCORE_PERFCTR_IBUF_STALL      = 0x1,
+        ARMV6MPCORE_PERFCTR_DDEP_STALL      = 0x2,
+        ARMV6MPCORE_PERFCTR_ITLB_MISS       = 0x3,
+        ARMV6MPCORE_PERFCTR_DTLB_MISS       = 0x4,
+        ARMV6MPCORE_PERFCTR_BR_EXEC         = 0x5,
+        ARMV6MPCORE_PERFCTR_BR_NOTPREDICT   = 0x6,
+        ARMV6MPCORE_PERFCTR_BR_MISPREDICT   = 0x7,
+        ARMV6MPCORE_PERFCTR_INSTR_EXEC      = 0x8,
+        ARMV6MPCORE_PERFCTR_DCACHE_RDACCESS = 0xA,
+        ARMV6MPCORE_PERFCTR_DCACHE_RDMISS   = 0xB,
+        ARMV6MPCORE_PERFCTR_DCACHE_WRACCESS = 0xC,
+        ARMV6MPCORE_PERFCTR_DCACHE_WRMISS   = 0xD,
+        ARMV6MPCORE_PERFCTR_DCACHE_EVICTION = 0xE,
+        ARMV6MPCORE_PERFCTR_SW_PC_CHANGE    = 0xF,
+        ARMV6MPCORE_PERFCTR_MAIN_TLB_MISS   = 0x10,
+        ARMV6MPCORE_PERFCTR_EXPL_MEM_ACCESS = 0x11,
+        ARMV6MPCORE_PERFCTR_LSU_FULL_STALL  = 0x12,
+        ARMV6MPCORE_PERFCTR_WBUF_DRAINED    = 0x13,
+        ARMV6MPCORE_PERFCTR_CPU_CYCLES      = 0xFF,
+};
+
+/*
+ * The hardware events that we support. We do support cache operations but
+ * we have harvard caches and no way to combine instruction and data
+ * accesses/misses in hardware.
+ */
+static const unsigned armv6mpcore_perf_map[PERF_COUNT_HW_MAX] = {
+        [PERF_COUNT_HW_CPU_CYCLES]          = ARMV6MPCORE_PERFCTR_CPU_CYCLES,
+        [PERF_COUNT_HW_INSTRUCTIONS]        = ARMV6MPCORE_PERFCTR_INSTR_EXEC,
+        [PERF_COUNT_HW_CACHE_REFERENCES]    = HW_OP_UNSUPPORTED,
+        [PERF_COUNT_HW_CACHE_MISSES]        = HW_OP_UNSUPPORTED,
+        [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV6MPCORE_PERFCTR_BR_EXEC,
+        [PERF_COUNT_HW_BRANCH_MISSES]       = ARMV6MPCORE_PERFCTR_BR_MISPREDICT,
+        [PERF_COUNT_HW_BUS_CYCLES]          = HW_OP_UNSUPPORTED,
+};
+
+static const unsigned armv6mpcore_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
+                                        [PERF_COUNT_HW_CACHE_OP_MAX]
+                                        [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+        [C(L1D)] = {
+                [C(OP_READ)] = {
+                        [C(RESULT_ACCESS)]  =
+                                ARMV6MPCORE_PERFCTR_DCACHE_RDACCESS,
+                        [C(RESULT_MISS)]    =
+                                ARMV6MPCORE_PERFCTR_DCACHE_RDMISS,
+                },
+                [C(OP_WRITE)] = {
+                        [C(RESULT_ACCESS)]  =
+                                ARMV6MPCORE_PERFCTR_DCACHE_WRACCESS,
+                        [C(RESULT_MISS)]    =
+                                ARMV6MPCORE_PERFCTR_DCACHE_WRMISS,
+                },
+                [C(OP_PREFETCH)] = {
+                        [C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
+                },
+        },
+        [C(L1I)] = {
+                [C(OP_READ)] = {
+                        [C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]    = ARMV6MPCORE_PERFCTR_ICACHE_MISS,
+                },
+                [C(OP_WRITE)] = {
+                        [C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]    = ARMV6MPCORE_PERFCTR_ICACHE_MISS,
+                },
+                [C(OP_PREFETCH)] = {
+                        [C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
+                },
+        },
+        [C(LL)] = {
+                [C(OP_READ)] = {
+                        [C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
+                },
+                [C(OP_WRITE)] = {
+                        [C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
+                },
+                [C(OP_PREFETCH)] = {
+                        [C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
+                },
+        },
+        [C(DTLB)] = {
+                /*
+                 * The ARM performance counters can count micro DTLB misses,
+                 * micro ITLB misses and main TLB misses. There isn't an event
+                 * for TLB misses, so use the micro misses here and if users
+                 * want the main TLB misses they can use a raw counter.
+                 */
+                [C(OP_READ)] = {
+                        [C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]    = ARMV6MPCORE_PERFCTR_DTLB_MISS,
+                },
+                [C(OP_WRITE)] = {
+                        [C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]    = ARMV6MPCORE_PERFCTR_DTLB_MISS,
+                },
+                [C(OP_PREFETCH)] = {
+                        [C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
+                },
+        },
+        [C(ITLB)] = {
+                [C(OP_READ)] = {
+                        [C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]    = ARMV6MPCORE_PERFCTR_ITLB_MISS,
+                },
+                [C(OP_WRITE)] = {
+                        [C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]    = ARMV6MPCORE_PERFCTR_ITLB_MISS,
+                },
+                [C(OP_PREFETCH)] = {
+                        [C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
+                },
+        },
+        [C(BPU)] = {
+                [C(OP_READ)] = {
+                        [C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
+                },
+                [C(OP_WRITE)] = {
+                        [C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
+                },
+                [C(OP_PREFETCH)] = {
+                        [C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
+                },
+        },
+};
+
+static inline unsigned long
+armv6_pmcr_read(void)
+{
+        u32 val;
+        asm volatile("mrc   p15, 0, %0, c15, c12, 0" : "=r"(val));
+        return val;
+}
+
+static inline void
+armv6_pmcr_write(unsigned long val)
+{
+        asm volatile("mcr   p15, 0, %0, c15, c12, 0" : : "r"(val));
+}
+
+#define ARMV6_PMCR_ENABLE               (1 << 0)
+#define ARMV6_PMCR_CTR01_RESET          (1 << 1)
+#define ARMV6_PMCR_CCOUNT_RESET         (1 << 2)
+#define ARMV6_PMCR_CCOUNT_DIV           (1 << 3)
+#define ARMV6_PMCR_COUNT0_IEN           (1 << 4)
+#define ARMV6_PMCR_COUNT1_IEN           (1 << 5)
+#define ARMV6_PMCR_CCOUNT_IEN           (1 << 6)
+#define ARMV6_PMCR_COUNT0_OVERFLOW      (1 << 8)
+#define ARMV6_PMCR_COUNT1_OVERFLOW      (1 << 9)
+#define ARMV6_PMCR_CCOUNT_OVERFLOW      (1 << 10)
+#define ARMV6_PMCR_EVT_COUNT0_SHIFT     20
+#define ARMV6_PMCR_EVT_COUNT0_MASK      (0xFF << ARMV6_PMCR_EVT_COUNT0_SHIFT)
+#define ARMV6_PMCR_EVT_COUNT1_SHIFT     12
+#define ARMV6_PMCR_EVT_COUNT1_MASK      (0xFF << ARMV6_PMCR_EVT_COUNT1_SHIFT)
+
+#define ARMV6_PMCR_OVERFLOWED_MASK \
+        (ARMV6_PMCR_COUNT0_OVERFLOW | ARMV6_PMCR_COUNT1_OVERFLOW | \
+         ARMV6_PMCR_CCOUNT_OVERFLOW)
+
+static inline int
+armv6_pmcr_has_overflowed(unsigned long pmcr)
+{
+        return pmcr & ARMV6_PMCR_OVERFLOWED_MASK;
+}
+
+static inline int
+armv6_pmcr_counter_has_overflowed(unsigned long pmcr,
+                                  enum armv6_counters counter)
+{
+        int ret = 0;
+
+        if (ARMV6_CYCLE_COUNTER == counter)
+                ret = pmcr & ARMV6_PMCR_CCOUNT_OVERFLOW;
+        else if (ARMV6_COUNTER0 == counter)
+                ret = pmcr & ARMV6_PMCR_COUNT0_OVERFLOW;
+        else if (ARMV6_COUNTER1 == counter)
+                ret = pmcr & ARMV6_PMCR_COUNT1_OVERFLOW;
+        else
+                WARN_ONCE(1, "invalid counter number (%d)\n", counter);
+
+        return ret;
+}
+
+static inline u32
+armv6pmu_read_counter(int counter)
+{
+        unsigned long value = 0;
+
+        if (ARMV6_CYCLE_COUNTER == counter)
+                asm volatile("mrc   p15, 0, %0, c15, c12, 1" : "=r"(value));
+        else if (ARMV6_COUNTER0 == counter)
+                asm volatile("mrc   p15, 0, %0, c15, c12, 2" : "=r"(value));
+        else if (ARMV6_COUNTER1 == counter)
+                asm volatile("mrc   p15, 0, %0, c15, c12, 3" : "=r"(value));
+        else
+                WARN_ONCE(1, "invalid counter number (%d)\n", counter);
+
+        return value;
+}
+
+static inline void
+armv6pmu_write_counter(int counter,
+                       u32 value)
+{
+        if (ARMV6_CYCLE_COUNTER == counter)
+                asm volatile("mcr   p15, 0, %0, c15, c12, 1" : : "r"(value));
+        else if (ARMV6_COUNTER0 == counter)
+                asm volatile("mcr   p15, 0, %0, c15, c12, 2" : : "r"(value));
+        else if (ARMV6_COUNTER1 == counter)
+                asm volatile("mcr   p15, 0, %0, c15, c12, 3" : : "r"(value));
+        else
+                WARN_ONCE(1, "invalid counter number (%d)\n", counter);
+}
+
+static void
+armv6pmu_enable_event(struct hw_perf_event *hwc,
+                      int idx)
+{
+        unsigned long val, mask, evt, flags;
+
+        if (ARMV6_CYCLE_COUNTER == idx) {
+                mask    = 0;
+                evt     = ARMV6_PMCR_CCOUNT_IEN;
+        } else if (ARMV6_COUNTER0 == idx) {
+                mask    = ARMV6_PMCR_EVT_COUNT0_MASK;
+                evt     = (hwc->config_base << ARMV6_PMCR_EVT_COUNT0_SHIFT) |
+                          ARMV6_PMCR_COUNT0_IEN;
+        } else if (ARMV6_COUNTER1 == idx) {
+                mask    = ARMV6_PMCR_EVT_COUNT1_MASK;
+                evt     = (hwc->config_base << ARMV6_PMCR_EVT_COUNT1_SHIFT) |
+                          ARMV6_PMCR_COUNT1_IEN;
+        } else {
+                WARN_ONCE(1, "invalid counter number (%d)\n", idx);
+                return;
+        }
+
+        /*
+         * Mask out the current event and set the counter to count the event
+         * that we're interested in.
+         */
+        raw_spin_lock_irqsave(&pmu_lock, flags);
+        val = armv6_pmcr_read();
+        val &= ~mask;
+        val |= evt;
+        armv6_pmcr_write(val);
+        raw_spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static irqreturn_t
+armv6pmu_handle_irq(int irq_num,
+                    void *dev)
+{
+        unsigned long pmcr = armv6_pmcr_read();
+        struct perf_sample_data data;
+        struct cpu_hw_events *cpuc;
+        struct pt_regs *regs;
+        int idx;
+
+        if (!armv6_pmcr_has_overflowed(pmcr))
+                return IRQ_NONE;
+
+        regs = get_irq_regs();
+
+        /*
+         * The interrupts are cleared by writing the overflow flags back to
+         * the control register. All of the other bits don't have any effect
+         * if they are rewritten, so write the whole value back.
+         */
+        armv6_pmcr_write(pmcr);
+
+        perf_sample_data_init(&data, 0);
+
+        cpuc = &__get_cpu_var(cpu_hw_events);
+        for (idx = 0; idx <= armpmu->num_events; ++idx) {
+                struct perf_event *event = cpuc->events[idx];
+                struct hw_perf_event *hwc;
+
+                if (!test_bit(idx, cpuc->active_mask))
+                        continue;
+
+                /*
+                 * We have a single interrupt for all counters. Check that
+                 * each counter has overflowed before we process it.
+                 */
+                if (!armv6_pmcr_counter_has_overflowed(pmcr, idx))
+                        continue;
+
+                hwc = &event->hw;
+                armpmu_event_update(event, hwc, idx);
+                data.period = event->hw.last_period;
+                if (!armpmu_event_set_period(event, hwc, idx))
+                        continue;
+
+                if (perf_event_overflow(event, 0, &data, regs))
+                        armpmu->disable(hwc, idx);
+        }
+
+        /*
+         * Handle the pending perf events.
+         *
+         * Note: this call *must* be run with interrupts disabled. For
+         * platforms that can have the PMU interrupts raised as an NMI, this
+         * will not work.
+         */
+        irq_work_run();
+
+        return IRQ_HANDLED;
+}
+
+static void
+armv6pmu_start(void)
+{
+        unsigned long flags, val;
+
+        raw_spin_lock_irqsave(&pmu_lock, flags);
+        val = armv6_pmcr_read();
+        val |= ARMV6_PMCR_ENABLE;
+        armv6_pmcr_write(val);
+        raw_spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static void
+armv6pmu_stop(void)
+{
+        unsigned long flags, val;
+
+        raw_spin_lock_irqsave(&pmu_lock, flags);
+        val = armv6_pmcr_read();
+        val &= ~ARMV6_PMCR_ENABLE;
+        armv6_pmcr_write(val);
+        raw_spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static int
+armv6pmu_get_event_idx(struct cpu_hw_events *cpuc,
+                       struct hw_perf_event *event)
+{
+        /* Always place a cycle counter into the cycle counter. */
+        if (ARMV6_PERFCTR_CPU_CYCLES == event->config_base) {
+                if (test_and_set_bit(ARMV6_CYCLE_COUNTER, cpuc->used_mask))
+                        return -EAGAIN;
+
+                return ARMV6_CYCLE_COUNTER;
+        } else {
+                /*
+                 * For anything other than a cycle counter, try and use
+                 * counter0 and counter1.
+                 */
+                if (!test_and_set_bit(ARMV6_COUNTER1, cpuc->used_mask))
+                        return ARMV6_COUNTER1;
+
+                if (!test_and_set_bit(ARMV6_COUNTER0, cpuc->used_mask))
+                        return ARMV6_COUNTER0;
+
+                /* The counters are all in use. */
+                return -EAGAIN;
+        }
+}
+
+static void
+armv6pmu_disable_event(struct hw_perf_event *hwc,
+                       int idx)
+{
+        unsigned long val, mask, evt, flags;
+
+        if (ARMV6_CYCLE_COUNTER == idx) {
+                mask    = ARMV6_PMCR_CCOUNT_IEN;
+                evt     = 0;
+        } else if (ARMV6_COUNTER0 == idx) {
+                mask    = ARMV6_PMCR_COUNT0_IEN | ARMV6_PMCR_EVT_COUNT0_MASK;
+                evt     = ARMV6_PERFCTR_NOP << ARMV6_PMCR_EVT_COUNT0_SHIFT;
+        } else if (ARMV6_COUNTER1 == idx) {
+                mask    = ARMV6_PMCR_COUNT1_IEN | ARMV6_PMCR_EVT_COUNT1_MASK;
+                evt     = ARMV6_PERFCTR_NOP << ARMV6_PMCR_EVT_COUNT1_SHIFT;
+        } else {
+                WARN_ONCE(1, "invalid counter number (%d)\n", idx);
+                return;
+        }
+
+        /*
+         * Mask out the current event and set the counter to count the number
+         * of ETM bus signal assertion cycles. The external reporting should
+         * be disabled and so this should never increment.
+         */
+        raw_spin_lock_irqsave(&pmu_lock, flags);
+        val = armv6_pmcr_read();
+        val &= ~mask;
+        val |= evt;
+        armv6_pmcr_write(val);
+        raw_spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static void
+armv6mpcore_pmu_disable_event(struct hw_perf_event *hwc,
+                              int idx)
+{
+        unsigned long val, mask, flags, evt = 0;
+
+        if (ARMV6_CYCLE_COUNTER == idx) {
+                mask    = ARMV6_PMCR_CCOUNT_IEN;
+        } else if (ARMV6_COUNTER0 == idx) {
+                mask    = ARMV6_PMCR_COUNT0_IEN;
+        } else if (ARMV6_COUNTER1 == idx) {
+                mask    = ARMV6_PMCR_COUNT1_IEN;
+        } else {
+                WARN_ONCE(1, "invalid counter number (%d)\n", idx);
+                return;
+        }
+
+        /*
+         * Unlike UP ARMv6, we don't have a way of stopping the counters. We
+         * simply disable the interrupt reporting.
+         */
+        raw_spin_lock_irqsave(&pmu_lock, flags);
+        val = armv6_pmcr_read();
+        val &= ~mask;
+        val |= evt;
+        armv6_pmcr_write(val);
+        raw_spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static const struct arm_pmu armv6pmu = {
+        .id                     = ARM_PERF_PMU_ID_V6,
+        .name                   = "v6",
+        .handle_irq             = armv6pmu_handle_irq,
+        .enable                 = armv6pmu_enable_event,
+        .disable                = armv6pmu_disable_event,
+        .read_counter           = armv6pmu_read_counter,
+        .write_counter          = armv6pmu_write_counter,
+        .get_event_idx          = armv6pmu_get_event_idx,
+        .start                  = armv6pmu_start,
+        .stop                   = armv6pmu_stop,
+        .cache_map              = &armv6_perf_cache_map,
+        .event_map              = &armv6_perf_map,
+        .raw_event_mask         = 0xFF,
+        .num_events             = 3,
+        .max_period             = (1LLU << 32) - 1,
+};
+
+static const struct arm_pmu *__init armv6pmu_init(void)
+{
+        return &armv6pmu;
+}
+
+/*
+ * ARMv6mpcore is almost identical to single core ARMv6 with the exception
+ * that some of the events have different enumerations and that there is no
+ * *hack* to stop the programmable counters. To stop the counters we simply
+ * disable the interrupt reporting and update the event. When unthrottling we
+ * reset the period and enable the interrupt reporting.
+ */
+static const struct arm_pmu armv6mpcore_pmu = {
+        .id                     = ARM_PERF_PMU_ID_V6MP,
+        .name                   = "v6mpcore",
+        .handle_irq             = armv6pmu_handle_irq,
+        .enable                 = armv6pmu_enable_event,
+        .disable                = armv6mpcore_pmu_disable_event,
+        .read_counter           = armv6pmu_read_counter,
+        .write_counter          = armv6pmu_write_counter,
+        .get_event_idx          = armv6pmu_get_event_idx,
+        .start                  = armv6pmu_start,
+        .stop                   = armv6pmu_stop,
+        .cache_map              = &armv6mpcore_perf_cache_map,
+        .event_map              = &armv6mpcore_perf_map,
+        .raw_event_mask         = 0xFF,
+        .num_events             = 3,
+        .max_period             = (1LLU << 32) - 1,
+};
+
+static const struct arm_pmu *__init armv6mpcore_pmu_init(void)
+{
+        return &armv6mpcore_pmu;
+}
+#else
+static const struct arm_pmu *__init armv6pmu_init(void)
+{
+        return NULL;
+}
+
+static const struct arm_pmu *__init armv6mpcore_pmu_init(void)
+{
+        return NULL;
+}
+#endif  /* CONFIG_CPU_V6 */
diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
new file mode 100644
index 000000000000..2e1402556fa0
--- /dev/null
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -0,0 +1,906 @@
+/*
+ * ARMv7 Cortex-A8 and Cortex-A9 Performance Events handling code.
+ *
+ * ARMv7 support: Jean Pihet <jpihet@mvista.com>
+ * 2010 (c) MontaVista Software, LLC.
+ *
+ * Copied from ARMv6 code, with the low level code inspired
+ *  by the ARMv7 Oprofile code.
+ *
+ * Cortex-A8 has up to 4 configurable performance counters and
+ *  a single cycle counter.
+ * Cortex-A9 has up to 31 configurable performance counters and
+ *  a single cycle counter.
+ *
+ * All counters can be enabled/disabled and IRQ masked separately. The cycle
+ *  counter and all 4 performance counters together can be reset separately.
+ */
+
+#ifdef CONFIG_CPU_V7
+/* Common ARMv7 event types */
+enum armv7_perf_types {
+        ARMV7_PERFCTR_PMNC_SW_INCR              = 0x00,
+        ARMV7_PERFCTR_IFETCH_MISS               = 0x01,
+        ARMV7_PERFCTR_ITLB_MISS                 = 0x02,
+        ARMV7_PERFCTR_DCACHE_REFILL             = 0x03,
+        ARMV7_PERFCTR_DCACHE_ACCESS             = 0x04,
+        ARMV7_PERFCTR_DTLB_REFILL               = 0x05,
+        ARMV7_PERFCTR_DREAD                     = 0x06,
+        ARMV7_PERFCTR_DWRITE                    = 0x07,
+
+        ARMV7_PERFCTR_EXC_TAKEN                 = 0x09,
+        ARMV7_PERFCTR_EXC_EXECUTED              = 0x0A,
+        ARMV7_PERFCTR_CID_WRITE                 = 0x0B,
+        /* ARMV7_PERFCTR_PC_WRITE is equivalent to HW_BRANCH_INSTRUCTIONS.
+         * It counts:
+         *  - all branch instructions,
+         *  - instructions that explicitly write the PC,
+         *  - exception generating instructions.
+         */
+        ARMV7_PERFCTR_PC_WRITE                  = 0x0C,
+        ARMV7_PERFCTR_PC_IMM_BRANCH             = 0x0D,
+        ARMV7_PERFCTR_UNALIGNED_ACCESS          = 0x0F,
+        ARMV7_PERFCTR_PC_BRANCH_MIS_PRED        = 0x10,
+        ARMV7_PERFCTR_CLOCK_CYCLES              = 0x11,
+
+        ARMV7_PERFCTR_PC_BRANCH_MIS_USED        = 0x12,
+
+        ARMV7_PERFCTR_CPU_CYCLES                = 0xFF
+};
+
+/* ARMv7 Cortex-A8 specific event types */
+enum armv7_a8_perf_types {
+        ARMV7_PERFCTR_INSTR_EXECUTED            = 0x08,
+
+        ARMV7_PERFCTR_PC_PROC_RETURN            = 0x0E,
+
+        ARMV7_PERFCTR_WRITE_BUFFER_FULL         = 0x40,
+        ARMV7_PERFCTR_L2_STORE_MERGED           = 0x41,
+        ARMV7_PERFCTR_L2_STORE_BUFF             = 0x42,
+        ARMV7_PERFCTR_L2_ACCESS                 = 0x43,
+        ARMV7_PERFCTR_L2_CACH_MISS              = 0x44,
+        ARMV7_PERFCTR_AXI_READ_CYCLES           = 0x45,
+        ARMV7_PERFCTR_AXI_WRITE_CYCLES          = 0x46,
+        ARMV7_PERFCTR_MEMORY_REPLAY             = 0x47,
+        ARMV7_PERFCTR_UNALIGNED_ACCESS_REPLAY   = 0x48,
+        ARMV7_PERFCTR_L1_DATA_MISS              = 0x49,
+        ARMV7_PERFCTR_L1_INST_MISS              = 0x4A,
+        ARMV7_PERFCTR_L1_DATA_COLORING          = 0x4B,
+        ARMV7_PERFCTR_L1_NEON_DATA              = 0x4C,
+        ARMV7_PERFCTR_L1_NEON_CACH_DATA         = 0x4D,
+        ARMV7_PERFCTR_L2_NEON                   = 0x4E,
+        ARMV7_PERFCTR_L2_NEON_HIT               = 0x4F,
+        ARMV7_PERFCTR_L1_INST                   = 0x50,
+        ARMV7_PERFCTR_PC_RETURN_MIS_PRED        = 0x51,
+        ARMV7_PERFCTR_PC_BRANCH_FAILED          = 0x52,
+        ARMV7_PERFCTR_PC_BRANCH_TAKEN           = 0x53,
+        ARMV7_PERFCTR_PC_BRANCH_EXECUTED        = 0x54,
+        ARMV7_PERFCTR_OP_EXECUTED               = 0x55,
+        ARMV7_PERFCTR_CYCLES_INST_STALL         = 0x56,
+        ARMV7_PERFCTR_CYCLES_INST               = 0x57,
+        ARMV7_PERFCTR_CYCLES_NEON_DATA_STALL    = 0x58,
+        ARMV7_PERFCTR_CYCLES_NEON_INST_STALL    = 0x59,
+        ARMV7_PERFCTR_NEON_CYCLES               = 0x5A,
+
+        ARMV7_PERFCTR_PMU0_EVENTS               = 0x70,
+        ARMV7_PERFCTR_PMU1_EVENTS               = 0x71,
+        ARMV7_PERFCTR_PMU_EVENTS                = 0x72,
+};
+
+/* ARMv7 Cortex-A9 specific event types */
+enum armv7_a9_perf_types {
+        ARMV7_PERFCTR_JAVA_HW_BYTECODE_EXEC     = 0x40,
+        ARMV7_PERFCTR_JAVA_SW_BYTECODE_EXEC     = 0x41,
+        ARMV7_PERFCTR_JAZELLE_BRANCH_EXEC       = 0x42,
+
+        ARMV7_PERFCTR_COHERENT_LINE_MISS        = 0x50,
+        ARMV7_PERFCTR_COHERENT_LINE_HIT         = 0x51,
+
+        ARMV7_PERFCTR_ICACHE_DEP_STALL_CYCLES   = 0x60,
+        ARMV7_PERFCTR_DCACHE_DEP_STALL_CYCLES   = 0x61,
+        ARMV7_PERFCTR_TLB_MISS_DEP_STALL_CYCLES = 0x62,
+        ARMV7_PERFCTR_STREX_EXECUTED_PASSED     = 0x63,
+        ARMV7_PERFCTR_STREX_EXECUTED_FAILED     = 0x64,
+        ARMV7_PERFCTR_DATA_EVICTION             = 0x65,
+        ARMV7_PERFCTR_ISSUE_STAGE_NO_INST       = 0x66,
+        ARMV7_PERFCTR_ISSUE_STAGE_EMPTY         = 0x67,
+        ARMV7_PERFCTR_INST_OUT_OF_RENAME_STAGE  = 0x68,
+
+        ARMV7_PERFCTR_PREDICTABLE_FUNCT_RETURNS = 0x6E,
+
+        ARMV7_PERFCTR_MAIN_UNIT_EXECUTED_INST   = 0x70,
+        ARMV7_PERFCTR_SECOND_UNIT_EXECUTED_INST = 0x71,
+        ARMV7_PERFCTR_LD_ST_UNIT_EXECUTED_INST  = 0x72,
+        ARMV7_PERFCTR_FP_EXECUTED_INST          = 0x73,
+        ARMV7_PERFCTR_NEON_EXECUTED_INST        = 0x74,
+
+        ARMV7_PERFCTR_PLD_FULL_DEP_STALL_CYCLES = 0x80,
+        ARMV7_PERFCTR_DATA_WR_DEP_STALL_CYCLES  = 0x81,
+        ARMV7_PERFCTR_ITLB_MISS_DEP_STALL_CYCLES        = 0x82,
+        ARMV7_PERFCTR_DTLB_MISS_DEP_STALL_CYCLES        = 0x83,
+        ARMV7_PERFCTR_MICRO_ITLB_MISS_DEP_STALL_CYCLES  = 0x84,
+        ARMV7_PERFCTR_MICRO_DTLB_MISS_DEP_STALL_CYCLES  = 0x85,
+        ARMV7_PERFCTR_DMB_DEP_STALL_CYCLES      = 0x86,
+
+        ARMV7_PERFCTR_INTGR_CLK_ENABLED_CYCLES  = 0x8A,
+        ARMV7_PERFCTR_DATA_ENGINE_CLK_EN_CYCLES = 0x8B,
+
+        ARMV7_PERFCTR_ISB_INST                  = 0x90,
+        ARMV7_PERFCTR_DSB_INST                  = 0x91,
+        ARMV7_PERFCTR_DMB_INST                  = 0x92,
+        ARMV7_PERFCTR_EXT_INTERRUPTS            = 0x93,
+
+        ARMV7_PERFCTR_PLE_CACHE_LINE_RQST_COMPLETED     = 0xA0,
+        ARMV7_PERFCTR_PLE_CACHE_LINE_RQST_SKIPPED       = 0xA1,
+        ARMV7_PERFCTR_PLE_FIFO_FLUSH            = 0xA2,
+        ARMV7_PERFCTR_PLE_RQST_COMPLETED        = 0xA3,
+        ARMV7_PERFCTR_PLE_FIFO_OVERFLOW         = 0xA4,
+        ARMV7_PERFCTR_PLE_RQST_PROG             = 0xA5
+};
+
+/*
+ * Cortex-A8 HW events mapping
+ *
+ * The hardware events that we support. We do support cache operations but
+ * we have harvard caches and no way to combine instruction and data
+ * accesses/misses in hardware.
+ */
+static const unsigned armv7_a8_perf_map[PERF_COUNT_HW_MAX] = {
+        [PERF_COUNT_HW_CPU_CYCLES]          = ARMV7_PERFCTR_CPU_CYCLES,
+        [PERF_COUNT_HW_INSTRUCTIONS]        = ARMV7_PERFCTR_INSTR_EXECUTED,
+        [PERF_COUNT_HW_CACHE_REFERENCES]    = HW_OP_UNSUPPORTED,
+        [PERF_COUNT_HW_CACHE_MISSES]        = HW_OP_UNSUPPORTED,
+        [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV7_PERFCTR_PC_WRITE,
+        [PERF_COUNT_HW_BRANCH_MISSES]       = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+        [PERF_COUNT_HW_BUS_CYCLES]          = ARMV7_PERFCTR_CLOCK_CYCLES,
+};
+
+static const unsigned armv7_a8_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
+                                          [PERF_COUNT_HW_CACHE_OP_MAX]
+                                          [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+        [C(L1D)] = {
+                /*
+                 * The performance counters don't differentiate between read
+                 * and write accesses/misses so this isn't strictly correct,
+                 * but it's the best we can do. Writes and reads get
+                 * combined.
+                 */
+                [C(OP_READ)] = {
+                        [C(RESULT_ACCESS)]      = ARMV7_PERFCTR_DCACHE_ACCESS,
+                        [C(RESULT_MISS)]        = ARMV7_PERFCTR_DCACHE_REFILL,
+                },
+                [C(OP_WRITE)] = {
+                        [C(RESULT_ACCESS)]      = ARMV7_PERFCTR_DCACHE_ACCESS,
+                        [C(RESULT_MISS)]        = ARMV7_PERFCTR_DCACHE_REFILL,
+                },
+                [C(OP_PREFETCH)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
+                },
+        },
+        [C(L1I)] = {
+                [C(OP_READ)] = {
+                        [C(RESULT_ACCESS)]      = ARMV7_PERFCTR_L1_INST,
+                        [C(RESULT_MISS)]        = ARMV7_PERFCTR_L1_INST_MISS,
+                },
+                [C(OP_WRITE)] = {
+                        [C(RESULT_ACCESS)]      = ARMV7_PERFCTR_L1_INST,
+                        [C(RESULT_MISS)]        = ARMV7_PERFCTR_L1_INST_MISS,
+                },
+                [C(OP_PREFETCH)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
+                },
+        },
+        [C(LL)] = {
+                [C(OP_READ)] = {
+                        [C(RESULT_ACCESS)]      = ARMV7_PERFCTR_L2_ACCESS,
+                        [C(RESULT_MISS)]        = ARMV7_PERFCTR_L2_CACH_MISS,
+                },
+                [C(OP_WRITE)] = {
+                        [C(RESULT_ACCESS)]      = ARMV7_PERFCTR_L2_ACCESS,
+                        [C(RESULT_MISS)]        = ARMV7_PERFCTR_L2_CACH_MISS,
+                },
+                [C(OP_PREFETCH)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
+                },
+        },
+        [C(DTLB)] = {
+                /*
+                 * Only ITLB misses and DTLB refills are supported.
+                 * If users want the DTLB refills misses a raw counter
+                 * must be used.
+                 */
+                [C(OP_READ)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = ARMV7_PERFCTR_DTLB_REFILL,
+                },
+                [C(OP_WRITE)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = ARMV7_PERFCTR_DTLB_REFILL,
+                },
+                [C(OP_PREFETCH)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
+                },
+        },
+        [C(ITLB)] = {
+                [C(OP_READ)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = ARMV7_PERFCTR_ITLB_MISS,
+                },
+                [C(OP_WRITE)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = ARMV7_PERFCTR_ITLB_MISS,
+                },
+                [C(OP_PREFETCH)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
+                },
+        },
+        [C(BPU)] = {
+                [C(OP_READ)] = {
+                        [C(RESULT_ACCESS)]      = ARMV7_PERFCTR_PC_WRITE,
+                        [C(RESULT_MISS)]
+                                        = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+                },
+                [C(OP_WRITE)] = {
+                        [C(RESULT_ACCESS)]      = ARMV7_PERFCTR_PC_WRITE,
+                        [C(RESULT_MISS)]
+                                        = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+                },
+                [C(OP_PREFETCH)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
+                },
+        },
+};
+
+/*
+ * Cortex-A9 HW events mapping
+ */
+static const unsigned armv7_a9_perf_map[PERF_COUNT_HW_MAX] = {
+        [PERF_COUNT_HW_CPU_CYCLES]          = ARMV7_PERFCTR_CPU_CYCLES,
+        [PERF_COUNT_HW_INSTRUCTIONS]        =
+                                        ARMV7_PERFCTR_INST_OUT_OF_RENAME_STAGE,
+        [PERF_COUNT_HW_CACHE_REFERENCES]    = ARMV7_PERFCTR_COHERENT_LINE_HIT,
+        [PERF_COUNT_HW_CACHE_MISSES]        = ARMV7_PERFCTR_COHERENT_LINE_MISS,
+        [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV7_PERFCTR_PC_WRITE,
+        [PERF_COUNT_HW_BRANCH_MISSES]       = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+        [PERF_COUNT_HW_BUS_CYCLES]          = ARMV7_PERFCTR_CLOCK_CYCLES,
+};
+
+static const unsigned armv7_a9_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
+                                          [PERF_COUNT_HW_CACHE_OP_MAX]
+                                          [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+        [C(L1D)] = {
+                /*
+                 * The performance counters don't differentiate between read
+                 * and write accesses/misses so this isn't strictly correct,
+                 * but it's the best we can do. Writes and reads get
+                 * combined.
+                 */
+                [C(OP_READ)] = {
+                        [C(RESULT_ACCESS)]      = ARMV7_PERFCTR_DCACHE_ACCESS,
+                        [C(RESULT_MISS)]        = ARMV7_PERFCTR_DCACHE_REFILL,
+                },
+                [C(OP_WRITE)] = {
+                        [C(RESULT_ACCESS)]      = ARMV7_PERFCTR_DCACHE_ACCESS,
+                        [C(RESULT_MISS)]        = ARMV7_PERFCTR_DCACHE_REFILL,
+                },
+                [C(OP_PREFETCH)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
+                },
+        },
+        [C(L1I)] = {
+                [C(OP_READ)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = ARMV7_PERFCTR_IFETCH_MISS,
+                },
+                [C(OP_WRITE)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = ARMV7_PERFCTR_IFETCH_MISS,
+                },
+                [C(OP_PREFETCH)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
+                },
+        },
+        [C(LL)] = {
+                [C(OP_READ)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
+                },
+                [C(OP_WRITE)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
+                },
+                [C(OP_PREFETCH)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
+                },
+        },
+        [C(DTLB)] = {
+                /*
+                 * Only ITLB misses and DTLB refills are supported.
+                 * If users want the DTLB refills misses a raw counter
+                 * must be used.
+                 */
+                [C(OP_READ)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = ARMV7_PERFCTR_DTLB_REFILL,
+                },
+                [C(OP_WRITE)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = ARMV7_PERFCTR_DTLB_REFILL,
+                },
+                [C(OP_PREFETCH)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
+                },
+        },
+        [C(ITLB)] = {
+                [C(OP_READ)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = ARMV7_PERFCTR_ITLB_MISS,
+                },
+                [C(OP_WRITE)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = ARMV7_PERFCTR_ITLB_MISS,
+                },
+                [C(OP_PREFETCH)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
+                },
+        },
+        [C(BPU)] = {
+                [C(OP_READ)] = {
+                        [C(RESULT_ACCESS)]      = ARMV7_PERFCTR_PC_WRITE,
+                        [C(RESULT_MISS)]
+                                        = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+                },
+                [C(OP_WRITE)] = {
+                        [C(RESULT_ACCESS)]      = ARMV7_PERFCTR_PC_WRITE,
+                        [C(RESULT_MISS)]
+                                        = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+                },
+                [C(OP_PREFETCH)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
+                },
+        },
+};
+
+/*
+ * Perf Events counters
+ */
+enum armv7_counters {
+        ARMV7_CYCLE_COUNTER             = 1,    /* Cycle counter */
+        ARMV7_COUNTER0                  = 2,    /* First event counter */
+};
+
+/*
+ * The cycle counter is ARMV7_CYCLE_COUNTER.
+ * The first event counter is ARMV7_COUNTER0.
+ * The last event counter is (ARMV7_COUNTER0 + armpmu->num_events - 1).
+ */
+#define ARMV7_COUNTER_LAST      (ARMV7_COUNTER0 + armpmu->num_events - 1)
+
+/*
+ * ARMv7 low level PMNC access
+ */
+
+/*
+ * Per-CPU PMNC: config reg
+ */
+#define ARMV7_PMNC_E            (1 << 0) /* Enable all counters */
+#define ARMV7_PMNC_P            (1 << 1) /* Reset all counters */
+#define ARMV7_PMNC_C            (1 << 2) /* Cycle counter reset */
+#define ARMV7_PMNC_D            (1 << 3) /* CCNT counts every 64th cpu cycle */
+#define ARMV7_PMNC_X            (1 << 4) /* Export to ETM */
+#define ARMV7_PMNC_DP           (1 << 5) /* Disable CCNT if non-invasive debug*/
+#define ARMV7_PMNC_N_SHIFT      11       /* Number of counters supported */
+#define ARMV7_PMNC_N_MASK       0x1f
+#define ARMV7_PMNC_MASK         0x3f     /* Mask for writable bits */
+
+/*
+ * Available counters
+ */
+#define ARMV7_CNT0              0       /* First event counter */
+#define ARMV7_CCNT              31      /* Cycle counter */
+
+/* Perf Event to low level counters mapping */
+#define ARMV7_EVENT_CNT_TO_CNTx (ARMV7_COUNTER0 - ARMV7_CNT0)
+
+/*
+ * CNTENS: counters enable reg
+ */
+#define ARMV7_CNTENS_P(idx)     (1 << (idx - ARMV7_EVENT_CNT_TO_CNTx))
+#define ARMV7_CNTENS_C          (1 << ARMV7_CCNT)
+
+/*
+ * CNTENC: counters disable reg
+ */
+#define ARMV7_CNTENC_P(idx)     (1 << (idx - ARMV7_EVENT_CNT_TO_CNTx))
+#define ARMV7_CNTENC_C          (1 << ARMV7_CCNT)
+
+/*
+ * INTENS: counters overflow interrupt enable reg
+ */
+#define ARMV7_INTENS_P(idx)     (1 << (idx - ARMV7_EVENT_CNT_TO_CNTx))
+#define ARMV7_INTENS_C          (1 << ARMV7_CCNT)
+
+/*
+ * INTENC: counters overflow interrupt disable reg
+ */
+#define ARMV7_INTENC_P(idx)     (1 << (idx - ARMV7_EVENT_CNT_TO_CNTx))
+#define ARMV7_INTENC_C          (1 << ARMV7_CCNT)
+
+/*
+ * EVTSEL: Event selection reg
+ */
+#define ARMV7_EVTSEL_MASK       0xff            /* Mask for writable bits */
+
+/*
+ * SELECT: Counter selection reg
+ */
+#define ARMV7_SELECT_MASK       0x1f            /* Mask for writable bits */
+
+/*
+ * FLAG: counters overflow flag status reg
+ */
+#define ARMV7_FLAG_P(idx)       (1 << (idx - ARMV7_EVENT_CNT_TO_CNTx))
+#define ARMV7_FLAG_C            (1 << ARMV7_CCNT)
+#define ARMV7_FLAG_MASK         0xffffffff      /* Mask for writable bits */
+#define ARMV7_OVERFLOWED_MASK   ARMV7_FLAG_MASK
+
+static inline unsigned long armv7_pmnc_read(void)
+{
+        u32 val;
+        asm volatile("mrc p15, 0, %0, c9, c12, 0" : "=r"(val));
+        return val;
+}
+
+static inline void armv7_pmnc_write(unsigned long val)
+{
+        val &= ARMV7_PMNC_MASK;
+        asm volatile("mcr p15, 0, %0, c9, c12, 0" : : "r"(val));
+}
+
+static inline int armv7_pmnc_has_overflowed(unsigned long pmnc)
+{
+        return pmnc & ARMV7_OVERFLOWED_MASK;
+}
+
+static inline int armv7_pmnc_counter_has_overflowed(unsigned long pmnc,
+                                        enum armv7_counters counter)
+{
+        int ret = 0;
+
+        if (counter == ARMV7_CYCLE_COUNTER)
+                ret = pmnc & ARMV7_FLAG_C;
+        else if ((counter >= ARMV7_COUNTER0) && (counter <= ARMV7_COUNTER_LAST))
+                ret = pmnc & ARMV7_FLAG_P(counter);
+        else
+                pr_err("CPU%u checking wrong counter %d overflow status\n",
+                        smp_processor_id(), counter);
+
+        return ret;
+}
+
+static inline int armv7_pmnc_select_counter(unsigned int idx)
+{
+        u32 val;
+
+        if ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST)) {
+                pr_err("CPU%u selecting wrong PMNC counter"
+                        " %d\n", smp_processor_id(), idx);
+                return -1;
+        }
+
+        val = (idx - ARMV7_EVENT_CNT_TO_CNTx) & ARMV7_SELECT_MASK;
+        asm volatile("mcr p15, 0, %0, c9, c12, 5" : : "r" (val));
+
+        return idx;
+}
+
+static inline u32 armv7pmu_read_counter(int idx)
+{
+        unsigned long value = 0;
+
+        if (idx == ARMV7_CYCLE_COUNTER)
+                asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (value));
+        else if ((idx >= ARMV7_COUNTER0) && (idx <= ARMV7_COUNTER_LAST)) {
+                if (armv7_pmnc_select_counter(idx) == idx)
+                        asm volatile("mrc p15, 0, %0, c9, c13, 2"
+                                     : "=r" (value));
+        } else
+                pr_err("CPU%u reading wrong counter %d\n",
+                        smp_processor_id(), idx);
+
+        return value;
+}
+
+static inline void armv7pmu_write_counter(int idx, u32 value)
+{
+        if (idx == ARMV7_CYCLE_COUNTER)
+                asm volatile("mcr p15, 0, %0, c9, c13, 0" : : "r" (value));
+        else if ((idx >= ARMV7_COUNTER0) && (idx <= ARMV7_COUNTER_LAST)) {
+                if (armv7_pmnc_select_counter(idx) == idx)
+                        asm volatile("mcr p15, 0, %0, c9, c13, 2"
+                                     : : "r" (value));
+        } else
+                pr_err("CPU%u writing wrong counter %d\n",
+                        smp_processor_id(), idx);
+}
+
+static inline void armv7_pmnc_write_evtsel(unsigned int idx, u32 val)
+{
+        if (armv7_pmnc_select_counter(idx) == idx) {
+                val &= ARMV7_EVTSEL_MASK;
+                asm volatile("mcr p15, 0, %0, c9, c13, 1" : : "r" (val));
+        }
+}
+
+static inline u32 armv7_pmnc_enable_counter(unsigned int idx)
+{
+        u32 val;
+
+        if ((idx != ARMV7_CYCLE_COUNTER) &&
+            ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST))) {
+                pr_err("CPU%u enabling wrong PMNC counter"
+                        " %d\n", smp_processor_id(), idx);
+                return -1;
+        }
+
+        if (idx == ARMV7_CYCLE_COUNTER)
+                val = ARMV7_CNTENS_C;
+        else
+                val = ARMV7_CNTENS_P(idx);
+
+        asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (val));
+
+        return idx;
+}
+
+static inline u32 armv7_pmnc_disable_counter(unsigned int idx)
+{
+        u32 val;
+
+
+        if ((idx != ARMV7_CYCLE_COUNTER) &&
+            ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST))) {
+                pr_err("CPU%u disabling wrong PMNC counter"
+                        " %d\n", smp_processor_id(), idx);
+                return -1;
+        }
+
+        if (idx == ARMV7_CYCLE_COUNTER)
+                val = ARMV7_CNTENC_C;
+        else
+                val = ARMV7_CNTENC_P(idx);
+
+        asm volatile("mcr p15, 0, %0, c9, c12, 2" : : "r" (val));
+
+        return idx;
+}
+
+static inline u32 armv7_pmnc_enable_intens(unsigned int idx)
+{
+        u32 val;
+
+        if ((idx != ARMV7_CYCLE_COUNTER) &&
+            ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST))) {
+                pr_err("CPU%u enabling wrong PMNC counter"
+                        " interrupt enable %d\n", smp_processor_id(), idx);
+                return -1;
+        }
+
+        if (idx == ARMV7_CYCLE_COUNTER)
+                val = ARMV7_INTENS_C;
+        else
+                val = ARMV7_INTENS_P(idx);
+
+        asm volatile("mcr p15, 0, %0, c9, c14, 1" : : "r" (val));
+
+        return idx;
+}
+
+static inline u32 armv7_pmnc_disable_intens(unsigned int idx)
+{
+        u32 val;
+
+        if ((idx != ARMV7_CYCLE_COUNTER) &&
+            ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST))) {
+                pr_err("CPU%u disabling wrong PMNC counter"
+                        " interrupt enable %d\n", smp_processor_id(), idx);
+                return -1;
+        }
+
+        if (idx == ARMV7_CYCLE_COUNTER)
+                val = ARMV7_INTENC_C;
+        else
+                val = ARMV7_INTENC_P(idx);
+
+        asm volatile("mcr p15, 0, %0, c9, c14, 2" : : "r" (val));
+
+        return idx;
+}
+
+static inline u32 armv7_pmnc_getreset_flags(void)
+{
+        u32 val;
+
+        /* Read */
+        asm volatile("mrc p15, 0, %0, c9, c12, 3" : "=r" (val));
+
+        /* Write to clear flags */
+        val &= ARMV7_FLAG_MASK;
+        asm volatile("mcr p15, 0, %0, c9, c12, 3" : : "r" (val));
+
+        return val;
+}
+
+#ifdef DEBUG
+static void armv7_pmnc_dump_regs(void)
+{
+        u32 val;
+        unsigned int cnt;
+
+        printk(KERN_INFO "PMNC registers dump:\n");
+
+        asm volatile("mrc p15, 0, %0, c9, c12, 0" : "=r" (val));
+        printk(KERN_INFO "PMNC  =0x%08x\n", val);
+
+        asm volatile("mrc p15, 0, %0, c9, c12, 1" : "=r" (val));
+        printk(KERN_INFO "CNTENS=0x%08x\n", val);
+
+        asm volatile("mrc p15, 0, %0, c9, c14, 1" : "=r" (val));
+        printk(KERN_INFO "INTENS=0x%08x\n", val);
+
+        asm volatile("mrc p15, 0, %0, c9, c12, 3" : "=r" (val));
+        printk(KERN_INFO "FLAGS =0x%08x\n", val);
+
+        asm volatile("mrc p15, 0, %0, c9, c12, 5" : "=r" (val));
+        printk(KERN_INFO "SELECT=0x%08x\n", val);
+
+        asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (val));
+        printk(KERN_INFO "CCNT  =0x%08x\n", val);
+
+        for (cnt = ARMV7_COUNTER0; cnt < ARMV7_COUNTER_LAST; cnt++) {
+                armv7_pmnc_select_counter(cnt);
+                asm volatile("mrc p15, 0, %0, c9, c13, 2" : "=r" (val));
+                printk(KERN_INFO "CNT[%d] count =0x%08x\n",
+                        cnt-ARMV7_EVENT_CNT_TO_CNTx, val);
+                asm volatile("mrc p15, 0, %0, c9, c13, 1" : "=r" (val));
+                printk(KERN_INFO "CNT[%d] evtsel=0x%08x\n",
+                        cnt-ARMV7_EVENT_CNT_TO_CNTx, val);
+        }
+}
+#endif
+
+static void armv7pmu_enable_event(struct hw_perf_event *hwc, int idx)
+{
+        unsigned long flags;
+
+        /*
+         * Enable counter and interrupt, and set the counter to count
+         * the event that we're interested in.
+         */
+        raw_spin_lock_irqsave(&pmu_lock, flags);
+
+        /*
+         * Disable counter
+         */
+        armv7_pmnc_disable_counter(idx);
+
+        /*
+         * Set event (if destined for PMNx counters)
+         * We don't need to set the event if it's a cycle count
+         */
+        if (idx != ARMV7_CYCLE_COUNTER)
+                armv7_pmnc_write_evtsel(idx, hwc->config_base);
+
+        /*
+         * Enable interrupt for this counter
+         */
+        armv7_pmnc_enable_intens(idx);
+
+        /*
+         * Enable counter
+         */
+        armv7_pmnc_enable_counter(idx);
+
+        raw_spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static void armv7pmu_disable_event(struct hw_perf_event *hwc, int idx)
+{
+        unsigned long flags;
+
+        /*
+         * Disable counter and interrupt
+         */
+        raw_spin_lock_irqsave(&pmu_lock, flags);
+
+        /*
+         * Disable counter
+         */
+        armv7_pmnc_disable_counter(idx);
+
+        /*
+         * Disable interrupt for this counter
+         */
+        armv7_pmnc_disable_intens(idx);
+
+        raw_spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev)
+{
+        unsigned long pmnc;
+        struct perf_sample_data data;
+        struct cpu_hw_events *cpuc;
+        struct pt_regs *regs;
+        int idx;
+
+        /*
+         * Get and reset the IRQ flags
+         */
+        pmnc = armv7_pmnc_getreset_flags();
+
+        /*
+         * Did an overflow occur?
+         */
+        if (!armv7_pmnc_has_overflowed(pmnc))
+                return IRQ_NONE;
+
+        /*
+         * Handle the counter(s) overflow(s)
+         */
+        regs = get_irq_regs();
+
+        perf_sample_data_init(&data, 0);
+
+        cpuc = &__get_cpu_var(cpu_hw_events);
+        for (idx = 0; idx <= armpmu->num_events; ++idx) {
+                struct perf_event *event = cpuc->events[idx];
+                struct hw_perf_event *hwc;
+
+                if (!test_bit(idx, cpuc->active_mask))
+                        continue;
+
+                /*
+                 * We have a single interrupt for all counters. Check that
+                 * each counter has overflowed before we process it.
+                 */
+                if (!armv7_pmnc_counter_has_overflowed(pmnc, idx))
+                        continue;
+
+                hwc = &event->hw;
+                armpmu_event_update(event, hwc, idx);
+                data.period = event->hw.last_period;
+                if (!armpmu_event_set_period(event, hwc, idx))
+                        continue;
+
+                if (perf_event_overflow(event, 0, &data, regs))
+                        armpmu->disable(hwc, idx);
+        }
+
+        /*
+         * Handle the pending perf events.
+         *
+         * Note: this call *must* be run with interrupts disabled. For
+         * platforms that can have the PMU interrupts raised as an NMI, this
+         * will not work.
+         */
+        irq_work_run();
+
+        return IRQ_HANDLED;
+}
+
+static void armv7pmu_start(void)
+{
+        unsigned long flags;
+
+        raw_spin_lock_irqsave(&pmu_lock, flags);
+        /* Enable all counters */
+        armv7_pmnc_write(armv7_pmnc_read() | ARMV7_PMNC_E);
+        raw_spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static void armv7pmu_stop(void)
+{
+        unsigned long flags;
+
+        raw_spin_lock_irqsave(&pmu_lock, flags);
+        /* Disable all counters */
+        armv7_pmnc_write(armv7_pmnc_read() & ~ARMV7_PMNC_E);
+        raw_spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static int armv7pmu_get_event_idx(struct cpu_hw_events *cpuc,
+                                  struct hw_perf_event *event)
+{
+        int idx;
+
+        /* Always place a cycle counter into the cycle counter. */
+        if (event->config_base == ARMV7_PERFCTR_CPU_CYCLES) {
+                if (test_and_set_bit(ARMV7_CYCLE_COUNTER, cpuc->used_mask))
+                        return -EAGAIN;
+
+                return ARMV7_CYCLE_COUNTER;
+        } else {
+                /*
+                 * For anything other than a cycle counter, try and use
+                 * the events counters
+                 */
+                for (idx = ARMV7_COUNTER0; idx <= armpmu->num_events; ++idx) {
+                        if (!test_and_set_bit(idx, cpuc->used_mask))
+                                return idx;
+                }
+
+                /* The counters are all in use. */
+                return -EAGAIN;
+        }
+}
+
+static struct arm_pmu armv7pmu = {
+        .handle_irq             = armv7pmu_handle_irq,
+        .enable                 = armv7pmu_enable_event,
+        .disable                = armv7pmu_disable_event,
+        .read_counter           = armv7pmu_read_counter,
+        .write_counter          = armv7pmu_write_counter,
+        .get_event_idx          = armv7pmu_get_event_idx,
+        .start                  = armv7pmu_start,
+        .stop                   = armv7pmu_stop,
+        .raw_event_mask         = 0xFF,
+        .max_period             = (1LLU << 32) - 1,
+};
+
+static u32 __init armv7_reset_read_pmnc(void)
+{
+        u32 nb_cnt;
+
+        /* Initialize & Reset PMNC: C and P bits */
+        armv7_pmnc_write(ARMV7_PMNC_P | ARMV7_PMNC_C);
+
+        /* Read the nb of CNTx counters supported from PMNC */
+        nb_cnt = (armv7_pmnc_read() >> ARMV7_PMNC_N_SHIFT) & ARMV7_PMNC_N_MASK;
+
+        /* Add the CPU cycles counter and return */
+        return nb_cnt + 1;
+}
+
+static const struct arm_pmu *__init armv7_a8_pmu_init(void)
+{
+        armv7pmu.id             = ARM_PERF_PMU_ID_CA8;
+        armv7pmu.name           = "ARMv7 Cortex-A8";
+        armv7pmu.cache_map      = &armv7_a8_perf_cache_map;
+        armv7pmu.event_map      = &armv7_a8_perf_map;
+        armv7pmu.num_events     = armv7_reset_read_pmnc();
+        return &armv7pmu;
+}
+
+static const struct arm_pmu *__init armv7_a9_pmu_init(void)
+{
+        armv7pmu.id             = ARM_PERF_PMU_ID_CA9;
+        armv7pmu.name           = "ARMv7 Cortex-A9";
+        armv7pmu.cache_map      = &armv7_a9_perf_cache_map;
+        armv7pmu.event_map      = &armv7_a9_perf_map;
+        armv7pmu.num_events     = armv7_reset_read_pmnc();
+        return &armv7pmu;
+}
+#else
+static const struct arm_pmu *__init armv7_a8_pmu_init(void)
+{
+        return NULL;
+}
+
+static const struct arm_pmu *__init armv7_a9_pmu_init(void)
+{
+        return NULL;
+}
+#endif  /* CONFIG_CPU_V7 */
diff --git a/arch/arm/kernel/perf_event_xscale.c b/arch/arm/kernel/perf_event_xscale.c
new file mode 100644
index 000000000000..28cd3b025bc3
--- /dev/null
+++ b/arch/arm/kernel/perf_event_xscale.c
@@ -0,0 +1,807 @@
+/*
+ * ARMv5 [xscale] Performance counter handling code.
+ *
+ * Copyright (C) 2010, ARM Ltd., Will Deacon <will.deacon@arm.com>
+ *
+ * Based on the previous xscale OProfile code.
+ *
+ * There are two variants of the xscale PMU that we support:
+ *      - xscale1pmu: 2 event counters and a cycle counter
+ *      - xscale2pmu: 4 event counters and a cycle counter
+ * The two variants share event definitions, but have different
+ * PMU structures.
+ */
+
+#ifdef CONFIG_CPU_XSCALE
+enum xscale_perf_types {
+        XSCALE_PERFCTR_ICACHE_MISS              = 0x00,
+        XSCALE_PERFCTR_ICACHE_NO_DELIVER        = 0x01,
+        XSCALE_PERFCTR_DATA_STALL               = 0x02,
+        XSCALE_PERFCTR_ITLB_MISS                = 0x03,
+        XSCALE_PERFCTR_DTLB_MISS                = 0x04,
+        XSCALE_PERFCTR_BRANCH                   = 0x05,
+        XSCALE_PERFCTR_BRANCH_MISS              = 0x06,
+        XSCALE_PERFCTR_INSTRUCTION              = 0x07,
+        XSCALE_PERFCTR_DCACHE_FULL_STALL        = 0x08,
+        XSCALE_PERFCTR_DCACHE_FULL_STALL_CONTIG = 0x09,
+        XSCALE_PERFCTR_DCACHE_ACCESS            = 0x0A,
+        XSCALE_PERFCTR_DCACHE_MISS              = 0x0B,
+        XSCALE_PERFCTR_DCACHE_WRITE_BACK        = 0x0C,
+        XSCALE_PERFCTR_PC_CHANGED               = 0x0D,
+        XSCALE_PERFCTR_BCU_REQUEST              = 0x10,
+        XSCALE_PERFCTR_BCU_FULL                 = 0x11,
+        XSCALE_PERFCTR_BCU_DRAIN                = 0x12,
+        XSCALE_PERFCTR_BCU_ECC_NO_ELOG          = 0x14,
+        XSCALE_PERFCTR_BCU_1_BIT_ERR            = 0x15,
+        XSCALE_PERFCTR_RMW                      = 0x16,
+        /* XSCALE_PERFCTR_CCNT is not hardware defined */
+        XSCALE_PERFCTR_CCNT                     = 0xFE,
+        XSCALE_PERFCTR_UNUSED                   = 0xFF,
+};
+
+enum xscale_counters {
+        XSCALE_CYCLE_COUNTER    = 1,
+        XSCALE_COUNTER0,
+        XSCALE_COUNTER1,
+        XSCALE_COUNTER2,
+        XSCALE_COUNTER3,
+};
+
+static const unsigned xscale_perf_map[PERF_COUNT_HW_MAX] = {
+        [PERF_COUNT_HW_CPU_CYCLES]          = XSCALE_PERFCTR_CCNT,
+        [PERF_COUNT_HW_INSTRUCTIONS]        = XSCALE_PERFCTR_INSTRUCTION,
+        [PERF_COUNT_HW_CACHE_REFERENCES]    = HW_OP_UNSUPPORTED,
+        [PERF_COUNT_HW_CACHE_MISSES]        = HW_OP_UNSUPPORTED,
+        [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = XSCALE_PERFCTR_BRANCH,
+        [PERF_COUNT_HW_BRANCH_MISSES]       = XSCALE_PERFCTR_BRANCH_MISS,
+        [PERF_COUNT_HW_BUS_CYCLES]          = HW_OP_UNSUPPORTED,
+};
+
+static const unsigned xscale_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
+                                           [PERF_COUNT_HW_CACHE_OP_MAX]
+                                           [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+        [C(L1D)] = {
+                [C(OP_READ)] = {
+                        [C(RESULT_ACCESS)]      = XSCALE_PERFCTR_DCACHE_ACCESS,
+                        [C(RESULT_MISS)]        = XSCALE_PERFCTR_DCACHE_MISS,
+                },
+                [C(OP_WRITE)] = {
+                        [C(RESULT_ACCESS)]      = XSCALE_PERFCTR_DCACHE_ACCESS,
+                        [C(RESULT_MISS)]        = XSCALE_PERFCTR_DCACHE_MISS,
+                },
+                [C(OP_PREFETCH)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
+                },
+        },
+        [C(L1I)] = {
+                [C(OP_READ)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = XSCALE_PERFCTR_ICACHE_MISS,
+                },
+                [C(OP_WRITE)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = XSCALE_PERFCTR_ICACHE_MISS,
+                },
+                [C(OP_PREFETCH)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
+                },
+        },
+        [C(LL)] = {
+                [C(OP_READ)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
+                },
+                [C(OP_WRITE)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
+                },
+                [C(OP_PREFETCH)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
+                },
+        },
+        [C(DTLB)] = {
+                [C(OP_READ)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = XSCALE_PERFCTR_DTLB_MISS,
+                },
+                [C(OP_WRITE)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = XSCALE_PERFCTR_DTLB_MISS,
+                },
+                [C(OP_PREFETCH)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
+                },
+        },
+        [C(ITLB)] = {
+                [C(OP_READ)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = XSCALE_PERFCTR_ITLB_MISS,
+                },
+                [C(OP_WRITE)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = XSCALE_PERFCTR_ITLB_MISS,
+                },
+                [C(OP_PREFETCH)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
+                },
+        },
+        [C(BPU)] = {
+                [C(OP_READ)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
+                },
+                [C(OP_WRITE)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
+                },
+                [C(OP_PREFETCH)] = {
+                        [C(RESULT_ACCESS)]      = CACHE_OP_UNSUPPORTED,
+                        [C(RESULT_MISS)]        = CACHE_OP_UNSUPPORTED,
+                },
+        },
+};
+
+#define XSCALE_PMU_ENABLE       0x001
+#define XSCALE_PMN_RESET        0x002
+#define XSCALE_CCNT_RESET       0x004
+#define XSCALE_PMU_RESET        (CCNT_RESET | PMN_RESET)
+#define XSCALE_PMU_CNT64        0x008
+
+#define XSCALE1_OVERFLOWED_MASK 0x700
+#define XSCALE1_CCOUNT_OVERFLOW 0x400
+#define XSCALE1_COUNT0_OVERFLOW 0x100
+#define XSCALE1_COUNT1_OVERFLOW 0x200
+#define XSCALE1_CCOUNT_INT_EN   0x040
+#define XSCALE1_COUNT0_INT_EN   0x010
+#define XSCALE1_COUNT1_INT_EN   0x020
+#define XSCALE1_COUNT0_EVT_SHFT 12
+#define XSCALE1_COUNT0_EVT_MASK (0xff << XSCALE1_COUNT0_EVT_SHFT)
+#define XSCALE1_COUNT1_EVT_SHFT 20
+#define XSCALE1_COUNT1_EVT_MASK (0xff << XSCALE1_COUNT1_EVT_SHFT)
+
+static inline u32
+xscale1pmu_read_pmnc(void)
+{
+        u32 val;
+        asm volatile("mrc p14, 0, %0, c0, c0, 0" : "=r" (val));
+        return val;
+}
+
+static inline void
+xscale1pmu_write_pmnc(u32 val)
+{
+        /* upper 4bits and 7, 11 are write-as-0 */
+        val &= 0xffff77f;
+        asm volatile("mcr p14, 0, %0, c0, c0, 0" : : "r" (val));
+}
+
+static inline int
+xscale1_pmnc_counter_has_overflowed(unsigned long pmnc,
+                                        enum xscale_counters counter)
+{
+        int ret = 0;
+
+        switch (counter) {
+        case XSCALE_CYCLE_COUNTER:
+                ret = pmnc & XSCALE1_CCOUNT_OVERFLOW;
+                break;
+        case XSCALE_COUNTER0:
+                ret = pmnc & XSCALE1_COUNT0_OVERFLOW;
+                break;
+        case XSCALE_COUNTER1:
+                ret = pmnc & XSCALE1_COUNT1_OVERFLOW;
+                break;
+        default:
+                WARN_ONCE(1, "invalid counter number (%d)\n", counter);
+        }
+
+        return ret;
+}
+
+static irqreturn_t
+xscale1pmu_handle_irq(int irq_num, void *dev)
+{
+        unsigned long pmnc;
+        struct perf_sample_data data;
+        struct cpu_hw_events *cpuc;
+        struct pt_regs *regs;
+        int idx;
+
+        /*
+         * NOTE: there's an A stepping erratum that states if an overflow
+         *       bit already exists and another occurs, the previous
+         *       Overflow bit gets cleared. There's no workaround.
+         *       Fixed in B stepping or later.
+         */
+        pmnc = xscale1pmu_read_pmnc();
+
+        /*
+         * Write the value back to clear the overflow flags. Overflow
+         * flags remain in pmnc for use below. We also disable the PMU
+         * while we process the interrupt.
+         */
+        xscale1pmu_write_pmnc(pmnc & ~XSCALE_PMU_ENABLE);
+
+        if (!(pmnc & XSCALE1_OVERFLOWED_MASK))
+                return IRQ_NONE;
+
+        regs = get_irq_regs();
+
+        perf_sample_data_init(&data, 0);
+
+        cpuc = &__get_cpu_var(cpu_hw_events);
+        for (idx = 0; idx <= armpmu->num_events; ++idx) {
+                struct perf_event *event = cpuc->events[idx];
+                struct hw_perf_event *hwc;
+
+                if (!test_bit(idx, cpuc->active_mask))
+                        continue;
+
+                if (!xscale1_pmnc_counter_has_overflowed(pmnc, idx))
+                        continue;
+
+                hwc = &event->hw;
+                armpmu_event_update(event, hwc, idx);
+                data.period = event->hw.last_period;
+                if (!armpmu_event_set_period(event, hwc, idx))
+                        continue;
+
+                if (perf_event_overflow(event, 0, &data, regs))
+                        armpmu->disable(hwc, idx);
+        }
+
+        irq_work_run();
+
+        /*
+         * Re-enable the PMU.
+         */
+        pmnc = xscale1pmu_read_pmnc() | XSCALE_PMU_ENABLE;
+        xscale1pmu_write_pmnc(pmnc);
+
+        return IRQ_HANDLED;
+}
+
+static void
+xscale1pmu_enable_event(struct hw_perf_event *hwc, int idx)
+{
+        unsigned long val, mask, evt, flags;
+
+        switch (idx) {
+        case XSCALE_CYCLE_COUNTER:
+                mask = 0;
+                evt = XSCALE1_CCOUNT_INT_EN;
+                break;
+        case XSCALE_COUNTER0:
+                mask = XSCALE1_COUNT0_EVT_MASK;
+                evt = (hwc->config_base << XSCALE1_COUNT0_EVT_SHFT) |
+                        XSCALE1_COUNT0_INT_EN;
+                break;
+        case XSCALE_COUNTER1:
+                mask = XSCALE1_COUNT1_EVT_MASK;
+                evt = (hwc->config_base << XSCALE1_COUNT1_EVT_SHFT) |
+                        XSCALE1_COUNT1_INT_EN;
+                break;
+        default:
+                WARN_ONCE(1, "invalid counter number (%d)\n", idx);
+                return;
+        }
+
+        raw_spin_lock_irqsave(&pmu_lock, flags);
+        val = xscale1pmu_read_pmnc();
+        val &= ~mask;
+        val |= evt;
+        xscale1pmu_write_pmnc(val);
+        raw_spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static void
+xscale1pmu_disable_event(struct hw_perf_event *hwc, int idx)
+{
+        unsigned long val, mask, evt, flags;
+
+        switch (idx) {
+        case XSCALE_CYCLE_COUNTER:
+                mask = XSCALE1_CCOUNT_INT_EN;
+                evt = 0;
+                break;
+        case XSCALE_COUNTER0:
+                mask = XSCALE1_COUNT0_INT_EN | XSCALE1_COUNT0_EVT_MASK;
+                evt = XSCALE_PERFCTR_UNUSED << XSCALE1_COUNT0_EVT_SHFT;
+                break;
+        case XSCALE_COUNTER1:
+                mask = XSCALE1_COUNT1_INT_EN | XSCALE1_COUNT1_EVT_MASK;
+                evt = XSCALE_PERFCTR_UNUSED << XSCALE1_COUNT1_EVT_SHFT;
+                break;
+        default:
+                WARN_ONCE(1, "invalid counter number (%d)\n", idx);
+                return;
+        }
+
+        raw_spin_lock_irqsave(&pmu_lock, flags);
+        val = xscale1pmu_read_pmnc();
+        val &= ~mask;
+        val |= evt;
+        xscale1pmu_write_pmnc(val);
+        raw_spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static int
+xscale1pmu_get_event_idx(struct cpu_hw_events *cpuc,
+                        struct hw_perf_event *event)
+{
+        if (XSCALE_PERFCTR_CCNT == event->config_base) {
+                if (test_and_set_bit(XSCALE_CYCLE_COUNTER, cpuc->used_mask))
+                        return -EAGAIN;
+
+                return XSCALE_CYCLE_COUNTER;
+        } else {
+                if (!test_and_set_bit(XSCALE_COUNTER1, cpuc->used_mask))
+                        return XSCALE_COUNTER1;
+
+                if (!test_and_set_bit(XSCALE_COUNTER0, cpuc->used_mask))
+                        return XSCALE_COUNTER0;
+
+                return -EAGAIN;
+        }
+}
+
+static void
+xscale1pmu_start(void)
+{
+        unsigned long flags, val;
+
+        raw_spin_lock_irqsave(&pmu_lock, flags);
+        val = xscale1pmu_read_pmnc();
+        val |= XSCALE_PMU_ENABLE;
+        xscale1pmu_write_pmnc(val);
+        raw_spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static void
+xscale1pmu_stop(void)
+{
+        unsigned long flags, val;
+
+        raw_spin_lock_irqsave(&pmu_lock, flags);
+        val = xscale1pmu_read_pmnc();
+        val &= ~XSCALE_PMU_ENABLE;
+        xscale1pmu_write_pmnc(val);
+        raw_spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static inline u32
+xscale1pmu_read_counter(int counter)
+{
+        u32 val = 0;
+
+        switch (counter) {
+        case XSCALE_CYCLE_COUNTER:
+                asm volatile("mrc p14, 0, %0, c1, c0, 0" : "=r" (val));
+                break;
+        case XSCALE_COUNTER0:
+                asm volatile("mrc p14, 0, %0, c2, c0, 0" : "=r" (val));
+                break;
+        case XSCALE_COUNTER1:
+                asm volatile("mrc p14, 0, %0, c3, c0, 0" : "=r" (val));
+                break;
+        }
+
+        return val;
+}
+
+static inline void
+xscale1pmu_write_counter(int counter, u32 val)
+{
+        switch (counter) {
+        case XSCALE_CYCLE_COUNTER:
+                asm volatile("mcr p14, 0, %0, c1, c0, 0" : : "r" (val));
+                break;
+        case XSCALE_COUNTER0:
+                asm volatile("mcr p14, 0, %0, c2, c0, 0" : : "r" (val));
+                break;
+        case XSCALE_COUNTER1:
+                asm volatile("mcr p14, 0, %0, c3, c0, 0" : : "r" (val));
+                break;
+        }
+}
+
+static const struct arm_pmu xscale1pmu = {
+        .id             = ARM_PERF_PMU_ID_XSCALE1,
+        .name           = "xscale1",
+        .handle_irq     = xscale1pmu_handle_irq,
+        .enable         = xscale1pmu_enable_event,
+        .disable        = xscale1pmu_disable_event,
+        .read_counter   = xscale1pmu_read_counter,
+        .write_counter  = xscale1pmu_write_counter,
+        .get_event_idx  = xscale1pmu_get_event_idx,
+        .start          = xscale1pmu_start,
+        .stop           = xscale1pmu_stop,
+        .cache_map      = &xscale_perf_cache_map,
+        .event_map      = &xscale_perf_map,
+        .raw_event_mask = 0xFF,
+        .num_events     = 3,
+        .max_period     = (1LLU << 32) - 1,
+};
+
+static const struct arm_pmu *__init xscale1pmu_init(void)
+{
+        return &xscale1pmu;
+}
+
+#define XSCALE2_OVERFLOWED_MASK 0x01f
+#define XSCALE2_CCOUNT_OVERFLOW 0x001
+#define XSCALE2_COUNT0_OVERFLOW 0x002
+#define XSCALE2_COUNT1_OVERFLOW 0x004
+#define XSCALE2_COUNT2_OVERFLOW 0x008
+#define XSCALE2_COUNT3_OVERFLOW 0x010
+#define XSCALE2_CCOUNT_INT_EN   0x001
+#define XSCALE2_COUNT0_INT_EN   0x002
+#define XSCALE2_COUNT1_INT_EN   0x004
+#define XSCALE2_COUNT2_INT_EN   0x008
+#define XSCALE2_COUNT3_INT_EN   0x010
+#define XSCALE2_COUNT0_EVT_SHFT 0
+#define XSCALE2_COUNT0_EVT_MASK (0xff << XSCALE2_COUNT0_EVT_SHFT)
+#define XSCALE2_COUNT1_EVT_SHFT 8
+#define XSCALE2_COUNT1_EVT_MASK (0xff << XSCALE2_COUNT1_EVT_SHFT)
+#define XSCALE2_COUNT2_EVT_SHFT 16
+#define XSCALE2_COUNT2_EVT_MASK (0xff << XSCALE2_COUNT2_EVT_SHFT)
+#define XSCALE2_COUNT3_EVT_SHFT 24
+#define XSCALE2_COUNT3_EVT_MASK (0xff << XSCALE2_COUNT3_EVT_SHFT)
+
+static inline u32
+xscale2pmu_read_pmnc(void)
+{
+        u32 val;
+        asm volatile("mrc p14, 0, %0, c0, c1, 0" : "=r" (val));
+        /* bits 1-2 and 4-23 are read-unpredictable */
+        return val & 0xff000009;
+}
+
+static inline void
+xscale2pmu_write_pmnc(u32 val)
+{
+        /* bits 4-23 are write-as-0, 24-31 are write ignored */
+        val &= 0xf;
+        asm volatile("mcr p14, 0, %0, c0, c1, 0" : : "r" (val));
+}
+
+static inline u32
+xscale2pmu_read_overflow_flags(void)
+{
+        u32 val;
+        asm volatile("mrc p14, 0, %0, c5, c1, 0" : "=r" (val));
+        return val;
+}
+
+static inline void
+xscale2pmu_write_overflow_flags(u32 val)
+{
+        asm volatile("mcr p14, 0, %0, c5, c1, 0" : : "r" (val));
+}
+
+static inline u32
+xscale2pmu_read_event_select(void)
+{
+        u32 val;
+        asm volatile("mrc p14, 0, %0, c8, c1, 0" : "=r" (val));
+        return val;
+}
+
+static inline void
+xscale2pmu_write_event_select(u32 val)
+{
+        asm volatile("mcr p14, 0, %0, c8, c1, 0" : : "r"(val));
+}
+
+static inline u32
+xscale2pmu_read_int_enable(void)
+{
+        u32 val;
+        asm volatile("mrc p14, 0, %0, c4, c1, 0" : "=r" (val));
+        return val;
+}
+
+static void
+xscale2pmu_write_int_enable(u32 val)
+{
+        asm volatile("mcr p14, 0, %0, c4, c1, 0" : : "r" (val));
+}
+
+static inline int
+xscale2_pmnc_counter_has_overflowed(unsigned long of_flags,
+                                        enum xscale_counters counter)
+{
+        int ret = 0;
+
+        switch (counter) {
+        case XSCALE_CYCLE_COUNTER:
+                ret = of_flags & XSCALE2_CCOUNT_OVERFLOW;
+                break;
+        case XSCALE_COUNTER0:
+                ret = of_flags & XSCALE2_COUNT0_OVERFLOW;
+                break;
+        case XSCALE_COUNTER1:
+                ret = of_flags & XSCALE2_COUNT1_OVERFLOW;
+                break;
+        case XSCALE_COUNTER2:
+                ret = of_flags & XSCALE2_COUNT2_OVERFLOW;
+                break;
+        case XSCALE_COUNTER3:
+                ret = of_flags & XSCALE2_COUNT3_OVERFLOW;
+                break;
+        default:
+                WARN_ONCE(1, "invalid counter number (%d)\n", counter);
+        }
+
+        return ret;
+}
+
+static irqreturn_t
+xscale2pmu_handle_irq(int irq_num, void *dev)
+{
+        unsigned long pmnc, of_flags;
+        struct perf_sample_data data;
+        struct cpu_hw_events *cpuc;
+        struct pt_regs *regs;
+        int idx;
+
+        /* Disable the PMU. */
+        pmnc = xscale2pmu_read_pmnc();
+        xscale2pmu_write_pmnc(pmnc & ~XSCALE_PMU_ENABLE);
+
+        /* Check the overflow flag register. */
+        of_flags = xscale2pmu_read_overflow_flags();
+        if (!(of_flags & XSCALE2_OVERFLOWED_MASK))
+                return IRQ_NONE;
+
+        /* Clear the overflow bits. */
+        xscale2pmu_write_overflow_flags(of_flags);
+
+        regs = get_irq_regs();
+
+        perf_sample_data_init(&data, 0);
+
+        cpuc = &__get_cpu_var(cpu_hw_events);
+        for (idx = 0; idx <= armpmu->num_events; ++idx) {
+                struct perf_event *event = cpuc->events[idx];
+                struct hw_perf_event *hwc;
+
+                if (!test_bit(idx, cpuc->active_mask))
+                        continue;
+
+                if (!xscale2_pmnc_counter_has_overflowed(pmnc, idx))
+                        continue;
+
+                hwc = &event->hw;
+                armpmu_event_update(event, hwc, idx);
+                data.period = event->hw.last_period;
+                if (!armpmu_event_set_period(event, hwc, idx))
+                        continue;
+
+                if (perf_event_overflow(event, 0, &data, regs))
+                        armpmu->disable(hwc, idx);
+        }
+
+        irq_work_run();
+
+        /*
+         * Re-enable the PMU.
+         */
+        pmnc = xscale2pmu_read_pmnc() | XSCALE_PMU_ENABLE;
+        xscale2pmu_write_pmnc(pmnc);
+
+        return IRQ_HANDLED;
+}
+
+static void
+xscale2pmu_enable_event(struct hw_perf_event *hwc, int idx)
+{
+        unsigned long flags, ien, evtsel;
+
+        ien = xscale2pmu_read_int_enable();
+        evtsel = xscale2pmu_read_event_select();
+
+        switch (idx) {
+        case XSCALE_CYCLE_COUNTER:
+                ien |= XSCALE2_CCOUNT_INT_EN;
+                break;
+        case XSCALE_COUNTER0:
+                ien |= XSCALE2_COUNT0_INT_EN;
+                evtsel &= ~XSCALE2_COUNT0_EVT_MASK;
+                evtsel |= hwc->config_base << XSCALE2_COUNT0_EVT_SHFT;
+                break;
+        case XSCALE_COUNTER1:
+                ien |= XSCALE2_COUNT1_INT_EN;
+                evtsel &= ~XSCALE2_COUNT1_EVT_MASK;
+                evtsel |= hwc->config_base << XSCALE2_COUNT1_EVT_SHFT;
+                break;
+        case XSCALE_COUNTER2:
+                ien |= XSCALE2_COUNT2_INT_EN;
+                evtsel &= ~XSCALE2_COUNT2_EVT_MASK;
+                evtsel |= hwc->config_base << XSCALE2_COUNT2_EVT_SHFT;
+                break;
+        case XSCALE_COUNTER3:
+                ien |= XSCALE2_COUNT3_INT_EN;
+                evtsel &= ~XSCALE2_COUNT3_EVT_MASK;
+                evtsel |= hwc->config_base << XSCALE2_COUNT3_EVT_SHFT;
+                break;
+        default:
+                WARN_ONCE(1, "invalid counter number (%d)\n", idx);
+                return;
+        }
+
+        raw_spin_lock_irqsave(&pmu_lock, flags);
+        xscale2pmu_write_event_select(evtsel);
+        xscale2pmu_write_int_enable(ien);
+        raw_spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static void
+xscale2pmu_disable_event(struct hw_perf_event *hwc, int idx)
+{
+        unsigned long flags, ien, evtsel;
+
+        ien = xscale2pmu_read_int_enable();
+        evtsel = xscale2pmu_read_event_select();
+
+        switch (idx) {
+        case XSCALE_CYCLE_COUNTER:
+                ien &= ~XSCALE2_CCOUNT_INT_EN;
+                break;
+        case XSCALE_COUNTER0:
+                ien &= ~XSCALE2_COUNT0_INT_EN;
+                evtsel &= ~XSCALE2_COUNT0_EVT_MASK;
+                evtsel |= XSCALE_PERFCTR_UNUSED << XSCALE2_COUNT0_EVT_SHFT;
+                break;
+        case XSCALE_COUNTER1:
+                ien &= ~XSCALE2_COUNT1_INT_EN;
+                evtsel &= ~XSCALE2_COUNT1_EVT_MASK;
+                evtsel |= XSCALE_PERFCTR_UNUSED << XSCALE2_COUNT1_EVT_SHFT;
+                break;
+        case XSCALE_COUNTER2:
+                ien &= ~XSCALE2_COUNT2_INT_EN;
+                evtsel &= ~XSCALE2_COUNT2_EVT_MASK;
+                evtsel |= XSCALE_PERFCTR_UNUSED << XSCALE2_COUNT2_EVT_SHFT;
+                break;
+        case XSCALE_COUNTER3:
+                ien &= ~XSCALE2_COUNT3_INT_EN;
+                evtsel &= ~XSCALE2_COUNT3_EVT_MASK;
+                evtsel |= XSCALE_PERFCTR_UNUSED << XSCALE2_COUNT3_EVT_SHFT;
+                break;
+        default:
+                WARN_ONCE(1, "invalid counter number (%d)\n", idx);
+                return;
+        }
+
+        raw_spin_lock_irqsave(&pmu_lock, flags);
+        xscale2pmu_write_event_select(evtsel);
+        xscale2pmu_write_int_enable(ien);
+        raw_spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static int
+xscale2pmu_get_event_idx(struct cpu_hw_events *cpuc,
+                        struct hw_perf_event *event)
+{
+        int idx = xscale1pmu_get_event_idx(cpuc, event);
+        if (idx >= 0)
+                goto out;
+
+        if (!test_and_set_bit(XSCALE_COUNTER3, cpuc->used_mask))
+                idx = XSCALE_COUNTER3;
+        else if (!test_and_set_bit(XSCALE_COUNTER2, cpuc->used_mask))
+                idx = XSCALE_COUNTER2;
+out:
+        return idx;
+}
+
+static void
+xscale2pmu_start(void)
+{
+        unsigned long flags, val;
+
+        raw_spin_lock_irqsave(&pmu_lock, flags);
+        val = xscale2pmu_read_pmnc() & ~XSCALE_PMU_CNT64;
+        val |= XSCALE_PMU_ENABLE;
+        xscale2pmu_write_pmnc(val);
+        raw_spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static void
+xscale2pmu_stop(void)
+{
+        unsigned long flags, val;
+
+        raw_spin_lock_irqsave(&pmu_lock, flags);
+        val = xscale2pmu_read_pmnc();
+        val &= ~XSCALE_PMU_ENABLE;
+        xscale2pmu_write_pmnc(val);
+        raw_spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static inline u32
+xscale2pmu_read_counter(int counter)
+{
+        u32 val = 0;
+
+        switch (counter) {
+        case XSCALE_CYCLE_COUNTER:
+                asm volatile("mrc p14, 0, %0, c1, c1, 0" : "=r" (val));
+                break;
+        case XSCALE_COUNTER0:
+                asm volatile("mrc p14, 0, %0, c0, c2, 0" : "=r" (val));
+                break;
+        case XSCALE_COUNTER1:
+                asm volatile("mrc p14, 0, %0, c1, c2, 0" : "=r" (val));
+                break;
+        case XSCALE_COUNTER2:
+                asm volatile("mrc p14, 0, %0, c2, c2, 0" : "=r" (val));
+                break;
+        case XSCALE_COUNTER3:
+                asm volatile("mrc p14, 0, %0, c3, c2, 0" : "=r" (val));
+                break;
+        }
+
+        return val;
+}
+
+static inline void
+xscale2pmu_write_counter(int counter, u32 val)
+{
+        switch (counter) {
+        case XSCALE_CYCLE_COUNTER:
+                asm volatile("mcr p14, 0, %0, c1, c1, 0" : : "r" (val));
+                break;
+        case XSCALE_COUNTER0:
+                asm volatile("mcr p14, 0, %0, c0, c2, 0" : : "r" (val));
+                break;
+        case XSCALE_COUNTER1:
+                asm volatile("mcr p14, 0, %0, c1, c2, 0" : : "r" (val));
+                break;
+        case XSCALE_COUNTER2:
+                asm volatile("mcr p14, 0, %0, c2, c2, 0" : : "r" (val));
+                break;
+        case XSCALE_COUNTER3:
+                asm volatile("mcr p14, 0, %0, c3, c2, 0" : : "r" (val));
+                break;
+        }
+}
+
+static const struct arm_pmu xscale2pmu = {
+        .id             = ARM_PERF_PMU_ID_XSCALE2,
+        .name           = "xscale2",
+        .handle_irq     = xscale2pmu_handle_irq,
+        .enable         = xscale2pmu_enable_event,
+        .disable        = xscale2pmu_disable_event,
+        .read_counter   = xscale2pmu_read_counter,
+        .write_counter  = xscale2pmu_write_counter,
+        .get_event_idx  = xscale2pmu_get_event_idx,
+        .start          = xscale2pmu_start,
+        .stop           = xscale2pmu_stop,
+        .cache_map      = &xscale_perf_cache_map,
+        .event_map      = &xscale_perf_map,
+        .raw_event_mask = 0xFF,
+        .num_events     = 5,
+        .max_period     = (1LLU << 32) - 1,
+};
+
+static const struct arm_pmu *__init xscale2pmu_init(void)
+{
+        return &xscale2pmu;
+}
+#else
+static const struct arm_pmu *__init xscale1pmu_init(void)
+{
+        return NULL;
+}
+
+static const struct arm_pmu *__init xscale2pmu_init(void)
+{
+        return NULL;
+}
+#endif  /* CONFIG_CPU_XSCALE */
diff --git a/arch/arm/kernel/pj4-cp0.c b/arch/arm/kernel/pj4-cp0.c
new file mode 100644
index 000000000000..a4b1b0748fd3
--- /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 3e97483abcf0..19c6816db61e 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;
diff --git a/arch/arm/kernel/sched_clock.c b/arch/arm/kernel/sched_clock.c
new file mode 100644
index 000000000000..2cdcc9287c74
--- /dev/null
+++ b/arch/arm/kernel/sched_clock.c
@@ -0,0 +1,69 @@
+/*
+ * sched_clock.c: support for extending counters to full 64-bit ns counter
+ *
+ * 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/clocksource.h>
+#include <linux/init.h>
+#include <linux/jiffies.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/timer.h>
+
+#include <asm/sched_clock.h>
+
+static void sched_clock_poll(unsigned long wrap_ticks);
+static DEFINE_TIMER(sched_clock_timer, sched_clock_poll, 0, 0);
+static void (*sched_clock_update_fn)(void);
+
+static void sched_clock_poll(unsigned long wrap_ticks)
+{
+        mod_timer(&sched_clock_timer, round_jiffies(jiffies + wrap_ticks));
+        sched_clock_update_fn();
+}
+
+void __init init_sched_clock(struct clock_data *cd, void (*update)(void),
+        unsigned int clock_bits, unsigned long rate)
+{
+        unsigned long r, w;
+        u64 res, wrap;
+        char r_unit;
+
+        sched_clock_update_fn = update;
+
+        /* calculate the mult/shift to convert counter ticks to ns. */
+        clocks_calc_mult_shift(&cd->mult, &cd->shift, rate, NSEC_PER_SEC, 60);
+
+        r = rate;
+        if (r >= 4000000) {
+                r /= 1000000;
+                r_unit = 'M';
+        } else {
+                r /= 1000;
+                r_unit = 'k';
+        }
+
+        /* calculate how many ns until we wrap */
+        wrap = cyc_to_ns((1ULL << clock_bits) - 1, cd->mult, cd->shift);
+        do_div(wrap, NSEC_PER_MSEC);
+        w = wrap;
+
+        /* calculate the ns resolution of this counter */
+        res = cyc_to_ns(1ULL, cd->mult, cd->shift);
+        pr_info("sched_clock: %u bits at %lu%cHz, resolution %lluns, wraps every %lums\n",
+                clock_bits, r, r_unit, res, w);
+
+        /*
+         * Start the timer to keep sched_clock() properly updated and
+         * sets the initial epoch.
+         */
+        sched_clock_timer.data = msecs_to_jiffies(w - (w / 10));
+        sched_clock_poll(sched_clock_timer.data);
+
+        /*
+         * Ensure that sched_clock() starts off at 0ns
+         */
+        cd->epoch_ns = 0;
+}
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 336f14e0e5c2..3455ad33de4c 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -75,9 +75,9 @@ extern void reboot_setup(char *str);
 
 unsigned int processor_id;
 EXPORT_SYMBOL(processor_id);
-unsigned int __machine_arch_type;
+unsigned int __machine_arch_type __read_mostly;
 EXPORT_SYMBOL(__machine_arch_type);
-unsigned int cacheid;
+unsigned int cacheid __read_mostly;
 EXPORT_SYMBOL(cacheid);
 
 unsigned int __atags_pointer __initdata;
@@ -91,24 +91,24 @@ EXPORT_SYMBOL(system_serial_low);
 unsigned int system_serial_high;
 EXPORT_SYMBOL(system_serial_high);
 
-unsigned int elf_hwcap;
+unsigned int elf_hwcap __read_mostly;
 EXPORT_SYMBOL(elf_hwcap);
 
 
 #ifdef MULTI_CPU
-struct processor processor;
+struct processor processor __read_mostly;
 #endif
 #ifdef MULTI_TLB
-struct cpu_tlb_fns cpu_tlb;
+struct cpu_tlb_fns cpu_tlb __read_mostly;
 #endif
 #ifdef MULTI_USER
-struct cpu_user_fns cpu_user;
+struct cpu_user_fns cpu_user __read_mostly;
 #endif
 #ifdef MULTI_CACHE
-struct cpu_cache_fns cpu_cache;
+struct cpu_cache_fns cpu_cache __read_mostly;
 #endif
 #ifdef CONFIG_OUTER_CACHE
-struct outer_cache_fns outer_cache;
+struct outer_cache_fns outer_cache __read_mostly;
 EXPORT_SYMBOL(outer_cache);
 #endif
 
@@ -126,6 +126,7 @@ EXPORT_SYMBOL(elf_platform);
 static const char *cpu_name;
 static const char *machine_name;
 static char __initdata cmd_line[COMMAND_LINE_SIZE];
+struct machine_desc *machine_desc __initdata;
 
 static char default_command_line[COMMAND_LINE_SIZE] __initdata = CONFIG_CMDLINE;
 static union { char c[4]; unsigned long l; } endian_test __initdata = { { 'l', '?', '?', 'b' } };
@@ -708,13 +709,11 @@ static struct init_tags {
         { 0, ATAG_NONE }
 };
 
-static void (*init_machine)(void) __initdata;
-
 static int __init customize_machine(void)
 {
         /* customizes platform devices, or adds new ones */
-        if (init_machine)
-                init_machine();
+        if (machine_desc->init_machine)
+                machine_desc->init_machine();
         return 0;
 }
 arch_initcall(customize_machine);
@@ -809,6 +808,7 @@ void __init setup_arch(char **cmdline_p)
 
         setup_processor();
         mdesc = setup_machine(machine_arch_type);
+        machine_desc = mdesc;
         machine_name = mdesc->name;
 
         if (mdesc->soft_reboot)
@@ -868,13 +868,9 @@ void __init setup_arch(char **cmdline_p)
         cpu_init();
         tcm_init();
 
-        /*
-         * Set up various architecture-specific pointers
-         */
-        arch_nr_irqs = mdesc->nr_irqs;
-        init_arch_irq = mdesc->init_irq;
-        system_timer = mdesc->timer;
-        init_machine = mdesc->init_machine;
+#ifdef CONFIG_MULTI_IRQ_HANDLER
+        handle_arch_irq = mdesc->handle_irq;
+#endif
 
 #ifdef CONFIG_VT
 #if defined(CONFIG_VGA_CONSOLE)
@@ -884,6 +880,9 @@ void __init setup_arch(char **cmdline_p)
 #endif
 #endif
         early_trap_init();
+
+        if (mdesc->init_early)
+                mdesc->init_early();
 }
 
 
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 9066473c0ebc..4539ebcb089f 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -16,6 +16,7 @@
 #include <linux/cache.h>
 #include <linux/profile.h>
 #include <linux/errno.h>
+#include <linux/ftrace.h>
 #include <linux/mm.h>
 #include <linux/err.h>
 #include <linux/cpu.h>
@@ -24,6 +25,7 @@
 #include <linux/irq.h>
 #include <linux/percpu.h>
 #include <linux/clockchips.h>
+#include <linux/completion.h>
 
 #include <asm/atomic.h>
 #include <asm/cacheflush.h>
@@ -37,7 +39,6 @@
 #include <asm/tlbflush.h>
 #include <asm/ptrace.h>
 #include <asm/localtimer.h>
-#include <asm/smp_plat.h>
 
 /*
  * as from 2.5, kernels no longer have an init_tasks structure
@@ -46,64 +47,14 @@
  */
 struct secondary_data secondary_data;
 
-/*
- * structures for inter-processor calls
- * - A collection of single bit ipi messages.
- */
-struct ipi_data {
-        spinlock_t lock;
-        unsigned long ipi_count;
-        unsigned long bits;
-};
-
-static DEFINE_PER_CPU(struct ipi_data, ipi_data) = {
-        .lock   = SPIN_LOCK_UNLOCKED,
-};
-
 enum ipi_msg_type {
-        IPI_TIMER,
+        IPI_TIMER = 2,
         IPI_RESCHEDULE,
         IPI_CALL_FUNC,
         IPI_CALL_FUNC_SINGLE,
         IPI_CPU_STOP,
 };
 
-static inline void identity_mapping_add(pgd_t *pgd, unsigned long start,
-        unsigned long end)
-{
-        unsigned long addr, prot;
-        pmd_t *pmd;
-
-        prot = PMD_TYPE_SECT | PMD_SECT_AP_WRITE;
-        if (cpu_architecture() <= CPU_ARCH_ARMv5TEJ && !cpu_is_xscale())
-                prot |= PMD_BIT4;
-
-        for (addr = start & PGDIR_MASK; addr < end;) {
-                pmd = pmd_offset(pgd + pgd_index(addr), addr);
-                pmd[0] = __pmd(addr | prot);
-                addr += SECTION_SIZE;
-                pmd[1] = __pmd(addr | prot);
-                addr += SECTION_SIZE;
-                flush_pmd_entry(pmd);
-                outer_clean_range(__pa(pmd), __pa(pmd + 1));
-        }
-}
-
-static inline void identity_mapping_del(pgd_t *pgd, unsigned long start,
-        unsigned long end)
-{
-        unsigned long addr;
-        pmd_t *pmd;
-
-        for (addr = start & PGDIR_MASK; addr < end; addr += PGDIR_SIZE) {
-                pmd = pmd_offset(pgd + pgd_index(addr), addr);
-                pmd[0] = __pmd(0);
-                pmd[1] = __pmd(0);
-                clean_pmd_entry(pmd);
-                outer_clean_range(__pa(pmd), __pa(pmd + 1));
-        }
-}
-
 int __cpuinit __cpu_up(unsigned int cpu)
 {
         struct cpuinfo_arm *ci = &per_cpu(cpu_data, cpu);
@@ -177,8 +128,12 @@ int __cpuinit __cpu_up(unsigned int cpu)
                         barrier();
                 }
 
-                if (!cpu_online(cpu))
+                if (!cpu_online(cpu)) {
+                        pr_crit("CPU%u: failed to come online\n", cpu);
                         ret = -EIO;
+                }
+        } else {
+                pr_err("CPU%u: failed to boot: %d\n", cpu, ret);
         }
 
         secondary_data.stack = NULL;
@@ -194,18 +149,12 @@ int __cpuinit __cpu_up(unsigned int cpu)
 
         pgd_free(&init_mm, pgd);
 
-        if (ret) {
-                printk(KERN_CRIT "CPU%u: processor failed to boot\n", cpu);
-
-                /*
-                 * FIXME: We need to clean up the new idle thread. --rmk
-                 */
-        }
-
         return ret;
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
+static void percpu_timer_stop(void);
+
 /*
  * __cpu_disable runs on the processor to be shutdown.
  */
@@ -233,7 +182,7 @@ int __cpu_disable(void)
         /*
          * Stop the local timer for this CPU.
          */
-        local_timer_stop();
+        percpu_timer_stop();
 
         /*
          * Flush user cache and TLB mappings, and then remove this CPU
@@ -252,12 +201,20 @@ int __cpu_disable(void)
         return 0;
 }
 
+static DECLARE_COMPLETION(cpu_died);
+
 /*
  * called on the thread which is asking for a CPU to be shutdown -
  * waits until shutdown has completed, or it is timed out.
  */
 void __cpu_die(unsigned int cpu)
 {
+        if (!wait_for_completion_timeout(&cpu_died, msecs_to_jiffies(5000))) {
+                pr_err("CPU%u: cpu didn't die\n", cpu);
+                return;
+        }
+        printk(KERN_NOTICE "CPU%u: shutdown\n", cpu);
+
         if (!platform_cpu_kill(cpu))
                 printk("CPU%u: unable to kill\n", cpu);
 }
@@ -274,12 +231,17 @@ void __ref cpu_die(void)
 {
         unsigned int cpu = smp_processor_id();
 
-        local_irq_disable();
         idle_task_exit();
 
+        local_irq_disable();
+        mb();
+
+        /* Tell __cpu_die() that this CPU is now safe to dispose of */
+        complete(&cpu_died);
+
         /*
          * actual CPU shutdown procedure is at least platform (if not
-         * CPU) specific
+         * CPU) specific.
          */
         platform_cpu_die(cpu);
 
@@ -289,6 +251,7 @@ void __ref cpu_die(void)
          * to be repeated to undo the effects of taking the CPU offline.
          */
         __asm__("mov    sp, %0\n"
+        "       mov     fp, #0\n"
         "       b       secondary_start_kernel"
                 :
                 : "r" (task_stack_page(current) + THREAD_SIZE - 8));
@@ -296,6 +259,17 @@ void __ref cpu_die(void)
 #endif /* CONFIG_HOTPLUG_CPU */
 
 /*
+ * Called by both boot and secondaries to move global data into
+ * per-processor storage.
+ */
+static void __cpuinit smp_store_cpu_info(unsigned int cpuid)
+{
+        struct cpuinfo_arm *cpu_info = &per_cpu(cpu_data, cpuid);
+
+        cpu_info->loops_per_jiffy = loops_per_jiffy;
+}
+
+/*
  * This is the secondary CPU boot entry.  We're using this CPUs
  * idle thread stack, but a set of temporary page tables.
  */
@@ -319,6 +293,7 @@ asmlinkage void __cpuinit secondary_start_kernel(void)
 
         cpu_init();
         preempt_disable();
+        trace_hardirqs_off();
 
         /*
          * Give the platform a chance to do its own initialisation.
@@ -352,17 +327,6 @@ asmlinkage void __cpuinit secondary_start_kernel(void)
         cpu_idle();
 }
 
-/*
- * Called by both boot and secondaries to move global data into
- * per-processor storage.
- */
-void __cpuinit smp_store_cpu_info(unsigned int cpuid)
-{
-        struct cpuinfo_arm *cpu_info = &per_cpu(cpu_data, cpuid);
-
-        cpu_info->loops_per_jiffy = loops_per_jiffy;
-}
-
 void __init smp_cpus_done(unsigned int max_cpus)
 {
         int cpu;
@@ -385,61 +349,80 @@ void __init smp_prepare_boot_cpu(void)
         per_cpu(cpu_data, cpu).idle = current;
 }
 
-static void send_ipi_message(const struct cpumask *mask, enum ipi_msg_type msg)
+void __init smp_prepare_cpus(unsigned int max_cpus)
 {
-        unsigned long flags;
-        unsigned int cpu;
+        unsigned int ncores = num_possible_cpus();
 
-        local_irq_save(flags);
-
-        for_each_cpu(cpu, mask) {
-                struct ipi_data *ipi = &per_cpu(ipi_data, cpu);
-
-                spin_lock(&ipi->lock);
-                ipi->bits |= 1 << msg;
-                spin_unlock(&ipi->lock);
-        }
+        smp_store_cpu_info(smp_processor_id());
 
         /*
-         * Call the platform specific cross-CPU call function.
+         * are we trying to boot more cores than exist?
          */
-        smp_cross_call(mask);
+        if (max_cpus > ncores)
+                max_cpus = ncores;
+
+        if (max_cpus > 1) {
+                /*
+                 * Enable the local timer or broadcast device for the
+                 * boot CPU, but only if we have more than one CPU.
+                 */
+                percpu_timer_setup();
 
-        local_irq_restore(flags);
+                /*
+                 * Initialise the SCU if there are more than one CPU
+                 * and let them know where to start.
+                 */
+                platform_smp_prepare_cpus(max_cpus);
+        }
 }
 
 void arch_send_call_function_ipi_mask(const struct cpumask *mask)
 {
-        send_ipi_message(mask, IPI_CALL_FUNC);
+        smp_cross_call(mask, IPI_CALL_FUNC);
 }
 
 void arch_send_call_function_single_ipi(int cpu)
 {
-        send_ipi_message(cpumask_of(cpu), IPI_CALL_FUNC_SINGLE);
+        smp_cross_call(cpumask_of(cpu), IPI_CALL_FUNC_SINGLE);
 }
 
-void show_ipi_list(struct seq_file *p)
+static const char *ipi_types[NR_IPI] = {
+#define S(x,s)  [x - IPI_TIMER] = s
+        S(IPI_TIMER, "Timer broadcast interrupts"),
+        S(IPI_RESCHEDULE, "Rescheduling interrupts"),
+        S(IPI_CALL_FUNC, "Function call interrupts"),
+        S(IPI_CALL_FUNC_SINGLE, "Single function call interrupts"),
+        S(IPI_CPU_STOP, "CPU stop interrupts"),
+};
+
+void show_ipi_list(struct seq_file *p, int prec)
 {
-        unsigned int cpu;
+        unsigned int cpu, i;
 
-        seq_puts(p, "IPI:");
+        for (i = 0; i < NR_IPI; i++) {
+                seq_printf(p, "%*s%u: ", prec - 1, "IPI", i);
 
-        for_each_present_cpu(cpu)
-                seq_printf(p, " %10lu", per_cpu(ipi_data, cpu).ipi_count);
+                for_each_present_cpu(cpu)
+                        seq_printf(p, "%10u ",
+                                   __get_irq_stat(cpu, ipi_irqs[i]));
 
-        seq_putc(p, '\n');
+                seq_printf(p, " %s\n", ipi_types[i]);
+        }
 }
 
-void show_local_irqs(struct seq_file *p)
+u64 smp_irq_stat_cpu(unsigned int cpu)
 {
-        unsigned int cpu;
+        u64 sum = 0;
+        int i;
 
-        seq_printf(p, "LOC: ");
+        for (i = 0; i < NR_IPI; i++)
+                sum += __get_irq_stat(cpu, ipi_irqs[i]);
 
-        for_each_present_cpu(cpu)
-                seq_printf(p, "%10u ", irq_stat[cpu].local_timer_irqs);
+#ifdef CONFIG_LOCAL_TIMERS
+        sum += __get_irq_stat(cpu, local_timer_irqs);
+#endif
 
-        seq_putc(p, '\n');
+        return sum;
 }
 
 /*
@@ -456,24 +439,36 @@ static void ipi_timer(void)
 }
 
 #ifdef CONFIG_LOCAL_TIMERS
-asmlinkage void __exception do_local_timer(struct pt_regs *regs)
+asmlinkage void __exception_irq_entry do_local_timer(struct pt_regs *regs)
 {
         struct pt_regs *old_regs = set_irq_regs(regs);
         int cpu = smp_processor_id();
 
         if (local_timer_ack()) {
-                irq_stat[cpu].local_timer_irqs++;
+                __inc_irq_stat(cpu, local_timer_irqs);
                 ipi_timer();
         }
 
         set_irq_regs(old_regs);
 }
+
+void show_local_irqs(struct seq_file *p, int prec)
+{
+        unsigned int cpu;
+
+        seq_printf(p, "%*s: ", prec, "LOC");
+
+        for_each_present_cpu(cpu)
+                seq_printf(p, "%10u ", __get_irq_stat(cpu, local_timer_irqs));
+
+        seq_printf(p, " Local timer interrupts\n");
+}
 #endif
 
 #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
 static void smp_timer_broadcast(const struct cpumask *mask)
 {
-        send_ipi_message(mask, IPI_TIMER);
+        smp_cross_call(mask, IPI_TIMER);
 }
 #else
 #define smp_timer_broadcast     NULL
@@ -510,6 +505,21 @@ void __cpuinit percpu_timer_setup(void)
         local_timer_setup(evt);
 }
 
+#ifdef CONFIG_HOTPLUG_CPU
+/*
+ * The generic clock events code purposely does not stop the local timer
+ * on CPU_DEAD/CPU_DEAD_FROZEN hotplug events, so we have to do it
+ * manually here.
+ */
+static void percpu_timer_stop(void)
+{
+        unsigned int cpu = smp_processor_id();
+        struct clock_event_device *evt = &per_cpu(percpu_clockevent, cpu);
+
+        evt->set_mode(CLOCK_EVT_MODE_UNUSED, evt);
+}
+#endif
+
 static DEFINE_SPINLOCK(stop_lock);
 
 /*
@@ -536,216 +546,76 @@ static void ipi_cpu_stop(unsigned int cpu)
 
 /*
  * Main handler for inter-processor interrupts
- *
- * For ARM, the ipimask now only identifies a single
- * category of IPI (Bit 1 IPIs have been replaced by a
- * different mechanism):
- *
- *  Bit 0 - Inter-processor function call
  */
-asmlinkage void __exception do_IPI(struct pt_regs *regs)
+asmlinkage void __exception_irq_entry do_IPI(int ipinr, struct pt_regs *regs)
 {
         unsigned int cpu = smp_processor_id();
-        struct ipi_data *ipi = &per_cpu(ipi_data, cpu);
         struct pt_regs *old_regs = set_irq_regs(regs);
 
-        ipi->ipi_count++;
-
-        for (;;) {
-                unsigned long msgs;
-
-                spin_lock(&ipi->lock);
-                msgs = ipi->bits;
-                ipi->bits = 0;
-                spin_unlock(&ipi->lock);
+        if (ipinr >= IPI_TIMER && ipinr < IPI_TIMER + NR_IPI)
+                __inc_irq_stat(cpu, ipi_irqs[ipinr - IPI_TIMER]);
 
-                if (!msgs)
-                        break;
-
-                do {
-                        unsigned nextmsg;
-
-                        nextmsg = msgs & -msgs;
-                        msgs &= ~nextmsg;
-                        nextmsg = ffz(~nextmsg);
-
-                        switch (nextmsg) {
-                        case IPI_TIMER:
-                                ipi_timer();
-                                break;
+        switch (ipinr) {
+        case IPI_TIMER:
+                ipi_timer();
+                break;
 
-                        case IPI_RESCHEDULE:
-                                /*
-                                 * nothing more to do - eveything is
-                                 * done on the interrupt return path
-                                 */
-                                break;
+        case IPI_RESCHEDULE:
+                /*
+                 * nothing more to do - eveything is
+                 * done on the interrupt return path
+                 */
+                break;
 
-                        case IPI_CALL_FUNC:
-                                generic_smp_call_function_interrupt();
-                                break;
+        case IPI_CALL_FUNC:
+                generic_smp_call_function_interrupt();
+                break;
 
-                        case IPI_CALL_FUNC_SINGLE:
-                                generic_smp_call_function_single_interrupt();
-                                break;
+        case IPI_CALL_FUNC_SINGLE:
+                generic_smp_call_function_single_interrupt();
+                break;
 
-                        case IPI_CPU_STOP:
-                                ipi_cpu_stop(cpu);
-                                break;
+        case IPI_CPU_STOP:
+                ipi_cpu_stop(cpu);
+                break;
 
-                        default:
-                                printk(KERN_CRIT "CPU%u: Unknown IPI message 0x%x\n",
-                                       cpu, nextmsg);
-                                break;
-                        }
-                } while (msgs);
+        default:
+                printk(KERN_CRIT "CPU%u: Unknown IPI message 0x%x\n",
+                       cpu, ipinr);
+                break;
         }
-
         set_irq_regs(old_regs);
 }
 
 void smp_send_reschedule(int cpu)
 {
-        send_ipi_message(cpumask_of(cpu), IPI_RESCHEDULE);
+        smp_cross_call(cpumask_of(cpu), IPI_RESCHEDULE);
 }
 
 void smp_send_stop(void)
 {
-        cpumask_t mask = cpu_online_map;
-        cpu_clear(smp_processor_id(), mask);
-        if (!cpus_empty(mask))
-                send_ipi_message(&mask, IPI_CPU_STOP);
-}
+        unsigned long timeout;
 
-/*
- * not supported here
- */
-int setup_profiling_timer(unsigned int multiplier)
-{
-        return -EINVAL;
-}
+        if (num_online_cpus() > 1) {
+                cpumask_t mask = cpu_online_map;
+                cpu_clear(smp_processor_id(), mask);
 
-static void
-on_each_cpu_mask(void (*func)(void *), void *info, int wait,
-                const struct cpumask *mask)
-{
-        preempt_disable();
+                smp_cross_call(&mask, IPI_CPU_STOP);
+        }
 
-        smp_call_function_many(mask, func, info, wait);
-        if (cpumask_test_cpu(smp_processor_id(), mask))
-                func(info);
+        /* Wait up to one second for other CPUs to stop */
+        timeout = USEC_PER_SEC;
+        while (num_online_cpus() > 1 && timeout--)
+                udelay(1);
 
-        preempt_enable();
+        if (num_online_cpus() > 1)
+                pr_warning("SMP: failed to stop secondary CPUs\n");
 }
 
-/**********************************************************************/
-
 /*
- * TLB operations
+ * not supported here
  */
-struct tlb_args {
-        struct vm_area_struct *ta_vma;
-        unsigned long ta_start;
-        unsigned long ta_end;
-};
-
-static inline void ipi_flush_tlb_all(void *ignored)
-{
-        local_flush_tlb_all();
-}
-
-static inline void ipi_flush_tlb_mm(void *arg)
-{
-        struct mm_struct *mm = (struct mm_struct *)arg;
-
-        local_flush_tlb_mm(mm);
-}
-
-static inline void ipi_flush_tlb_page(void *arg)
-{
-        struct tlb_args *ta = (struct tlb_args *)arg;
-
-        local_flush_tlb_page(ta->ta_vma, ta->ta_start);
-}
-
-static inline void ipi_flush_tlb_kernel_page(void *arg)
-{
-        struct tlb_args *ta = (struct tlb_args *)arg;
-
-        local_flush_tlb_kernel_page(ta->ta_start);
-}
-
-static inline void ipi_flush_tlb_range(void *arg)
-{
-        struct tlb_args *ta = (struct tlb_args *)arg;
-
-        local_flush_tlb_range(ta->ta_vma, ta->ta_start, ta->ta_end);
-}
-
-static inline void ipi_flush_tlb_kernel_range(void *arg)
-{
-        struct tlb_args *ta = (struct tlb_args *)arg;
-
-        local_flush_tlb_kernel_range(ta->ta_start, ta->ta_end);
-}
-
-void flush_tlb_all(void)
-{
-        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)
-{
-        if (tlb_ops_need_broadcast())
-                on_each_cpu_mask(ipi_flush_tlb_mm, mm, 1, mm_cpumask(mm));
-        else
-                local_flush_tlb_mm(mm);
-}
-
-void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
-{
-        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, mm_cpumask(vma->vm_mm));
-        } else
-                local_flush_tlb_page(vma, uaddr);
-}
-
-void flush_tlb_kernel_page(unsigned long kaddr)
-{
-        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)
-{
-        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, mm_cpumask(vma->vm_mm));
-        } else
-                local_flush_tlb_range(vma, start, end);
-}
-
-void flush_tlb_kernel_range(unsigned long start, unsigned long end)
+int setup_profiling_timer(unsigned int multiplier)
 {
-        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);
+        return -EINVAL;
 }
diff --git a/arch/arm/kernel/smp_tlb.c b/arch/arm/kernel/smp_tlb.c
new file mode 100644
index 000000000000..7dcb35285be7
--- /dev/null
+++ b/arch/arm/kernel/smp_tlb.c
@@ -0,0 +1,139 @@
+/*
+ *  linux/arch/arm/kernel/smp_tlb.c
+ *
+ *  Copyright (C) 2002 ARM Limited, 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/preempt.h>
+#include <linux/smp.h>
+
+#include <asm/smp_plat.h>
+#include <asm/tlbflush.h>
+
+static void on_each_cpu_mask(void (*func)(void *), void *info, int wait,
+        const struct cpumask *mask)
+{
+        preempt_disable();
+
+        smp_call_function_many(mask, func, info, wait);
+        if (cpumask_test_cpu(smp_processor_id(), mask))
+                func(info);
+
+        preempt_enable();
+}
+
+/**********************************************************************/
+
+/*
+ * TLB operations
+ */
+struct tlb_args {
+        struct vm_area_struct *ta_vma;
+        unsigned long ta_start;
+        unsigned long ta_end;
+};
+
+static inline void ipi_flush_tlb_all(void *ignored)
+{
+        local_flush_tlb_all();
+}
+
+static inline void ipi_flush_tlb_mm(void *arg)
+{
+        struct mm_struct *mm = (struct mm_struct *)arg;
+
+        local_flush_tlb_mm(mm);
+}
+
+static inline void ipi_flush_tlb_page(void *arg)
+{
+        struct tlb_args *ta = (struct tlb_args *)arg;
+
+        local_flush_tlb_page(ta->ta_vma, ta->ta_start);
+}
+
+static inline void ipi_flush_tlb_kernel_page(void *arg)
+{
+        struct tlb_args *ta = (struct tlb_args *)arg;
+
+        local_flush_tlb_kernel_page(ta->ta_start);
+}
+
+static inline void ipi_flush_tlb_range(void *arg)
+{
+        struct tlb_args *ta = (struct tlb_args *)arg;
+
+        local_flush_tlb_range(ta->ta_vma, ta->ta_start, ta->ta_end);
+}
+
+static inline void ipi_flush_tlb_kernel_range(void *arg)
+{
+        struct tlb_args *ta = (struct tlb_args *)arg;
+
+        local_flush_tlb_kernel_range(ta->ta_start, ta->ta_end);
+}
+
+void flush_tlb_all(void)
+{
+        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)
+{
+        if (tlb_ops_need_broadcast())
+                on_each_cpu_mask(ipi_flush_tlb_mm, mm, 1, mm_cpumask(mm));
+        else
+                local_flush_tlb_mm(mm);
+}
+
+void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
+{
+        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, mm_cpumask(vma->vm_mm));
+        } else
+                local_flush_tlb_page(vma, uaddr);
+}
+
+void flush_tlb_kernel_page(unsigned long kaddr)
+{
+        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)
+{
+        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, mm_cpumask(vma->vm_mm));
+        } else
+                local_flush_tlb_range(vma, start, end);
+}
+
+void flush_tlb_kernel_range(unsigned long start, unsigned long end)
+{
+        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_twd.c b/arch/arm/kernel/smp_twd.c
index 35882fbf37f9..dd790745b3ef 100644
--- a/arch/arm/kernel/smp_twd.c
+++ b/arch/arm/kernel/smp_twd.c
@@ -127,8 +127,6 @@ static void __cpuinit twd_calibrate_rate(void)
  */
 void __cpuinit twd_timer_setup(struct clock_event_device *clk)
 {
-        unsigned long flags;
-
         twd_calibrate_rate();
 
         clk->name = "local_timer";
@@ -143,20 +141,7 @@ void __cpuinit twd_timer_setup(struct clock_event_device *clk)
         clk->min_delta_ns = clockevent_delta2ns(0xf, clk);
 
         /* Make sure our local interrupt controller has this enabled */
-        local_irq_save(flags);
-        irq_to_desc(clk->irq)->status |= IRQ_NOPROBE;
-        get_irq_chip(clk->irq)->unmask(clk->irq);
-        local_irq_restore(flags);
+        gic_enable_ppi(clk->irq);
 
         clockevents_register_device(clk);
 }
-
-#ifdef CONFIG_HOTPLUG_CPU
-/*
- * take a local timer down
- */
-void twd_timer_stop(void)
-{
-        __raw_writel(0, twd_base + TWD_TIMER_CONTROL);
-}
-#endif
diff --git a/arch/arm/kernel/swp_emulate.c b/arch/arm/kernel/swp_emulate.c
new file mode 100644
index 000000000000..7a5760922914
--- /dev/null
+++ b/arch/arm/kernel/swp_emulate.c
@@ -0,0 +1,267 @@
+/*
+ *  linux/arch/arm/kernel/swp_emulate.c
+ *
+ *  Copyright (C) 2009 ARM Limited
+ *  __user_* functions adapted from include/asm/uaccess.h
+ *
+ * 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.
+ *
+ *  Implements emulation of the SWP/SWPB instructions using load-exclusive and
+ *  store-exclusive for processors that have them disabled (or future ones that
+ *  might not implement them).
+ *
+ *  Syntax of SWP{B} instruction: SWP{B}<c> <Rt>, <Rt2>, [<Rn>]
+ *  Where: Rt  = destination
+ *         Rt2 = source
+ *         Rn  = address
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/proc_fs.h>
+#include <linux/sched.h>
+#include <linux/syscalls.h>
+#include <linux/perf_event.h>
+
+#include <asm/traps.h>
+#include <asm/uaccess.h>
+
+/*
+ * Error-checking SWP macros implemented using ldrex{b}/strex{b}
+ */
+#define __user_swpX_asm(data, addr, res, temp, B)               \
+        __asm__ __volatile__(                                   \
+        "       mov             %2, %1\n"                       \
+        "0:     ldrex"B"        %1, [%3]\n"                     \
+        "1:     strex"B"        %0, %2, [%3]\n"                 \
+        "       cmp             %0, #0\n"                       \
+        "       movne           %0, %4\n"                       \
+        "2:\n"                                                  \
+        "       .section         .fixup,\"ax\"\n"               \
+        "       .align          2\n"                            \
+        "3:     mov             %0, %5\n"                       \
+        "       b               2b\n"                           \
+        "       .previous\n"                                    \
+        "       .section         __ex_table,\"a\"\n"            \
+        "       .align          3\n"                            \
+        "       .long           0b, 3b\n"                       \
+        "       .long           1b, 3b\n"                       \
+        "       .previous"                                      \
+        : "=&r" (res), "+r" (data), "=&r" (temp)                \
+        : "r" (addr), "i" (-EAGAIN), "i" (-EFAULT)              \
+        : "cc", "memory")
+
+#define __user_swp_asm(data, addr, res, temp) \
+        __user_swpX_asm(data, addr, res, temp, "")
+#define __user_swpb_asm(data, addr, res, temp) \
+        __user_swpX_asm(data, addr, res, temp, "b")
+
+/*
+ * Macros/defines for extracting register numbers from instruction.
+ */
+#define EXTRACT_REG_NUM(instruction, offset) \
+        (((instruction) & (0xf << (offset))) >> (offset))
+#define RN_OFFSET  16
+#define RT_OFFSET  12
+#define RT2_OFFSET  0
+/*
+ * Bit 22 of the instruction encoding distinguishes between
+ * the SWP and SWPB variants (bit set means SWPB).
+ */
+#define TYPE_SWPB (1 << 22)
+
+static unsigned long swpcounter;
+static unsigned long swpbcounter;
+static unsigned long abtcounter;
+static pid_t         previous_pid;
+
+#ifdef CONFIG_PROC_FS
+static int proc_read_status(char *page, char **start, off_t off, int count,
+                            int *eof, void *data)
+{
+        char *p = page;
+        int len;
+
+        p += sprintf(p, "Emulated SWP:\t\t%lu\n", swpcounter);
+        p += sprintf(p, "Emulated SWPB:\t\t%lu\n", swpbcounter);
+        p += sprintf(p, "Aborted SWP{B}:\t\t%lu\n", abtcounter);
+        if (previous_pid != 0)
+                p += sprintf(p, "Last process:\t\t%d\n", previous_pid);
+
+        len = (p - page) - off;
+        if (len < 0)
+                len = 0;
+
+        *eof = (len <= count) ? 1 : 0;
+        *start = page + off;
+
+        return len;
+}
+#endif
+
+/*
+ * Set up process info to signal segmentation fault - called on access error.
+ */
+static void set_segfault(struct pt_regs *regs, unsigned long addr)
+{
+        siginfo_t info;
+
+        if (find_vma(current->mm, addr) == NULL)
+                info.si_code = SEGV_MAPERR;
+        else
+                info.si_code = SEGV_ACCERR;
+
+        info.si_signo = SIGSEGV;
+        info.si_errno = 0;
+        info.si_addr  = (void *) instruction_pointer(regs);
+
+        pr_debug("SWP{B} emulation: access caused memory abort!\n");
+        arm_notify_die("Illegal memory access", regs, &info, 0, 0);
+
+        abtcounter++;
+}
+
+static int emulate_swpX(unsigned int address, unsigned int *data,
+                        unsigned int type)
+{
+        unsigned int res = 0;
+
+        if ((type != TYPE_SWPB) && (address & 0x3)) {
+                /* SWP to unaligned address not permitted */
+                pr_debug("SWP instruction on unaligned pointer!\n");
+                return -EFAULT;
+        }
+
+        while (1) {
+                unsigned long temp;
+
+                /*
+                 * Barrier required between accessing protected resource and
+                 * releasing a lock for it. Legacy code might not have done
+                 * this, and we cannot determine that this is not the case
+                 * being emulated, so insert always.
+                 */
+                smp_mb();
+
+                if (type == TYPE_SWPB)
+                        __user_swpb_asm(*data, address, res, temp);
+                else
+                        __user_swp_asm(*data, address, res, temp);
+
+                if (likely(res != -EAGAIN) || signal_pending(current))
+                        break;
+
+                cond_resched();
+        }
+
+        if (res == 0) {
+                /*
+                 * Barrier also required between aquiring a lock for a
+                 * protected resource and accessing the resource. Inserted for
+                 * same reason as above.
+                 */
+                smp_mb();
+
+                if (type == TYPE_SWPB)
+                        swpbcounter++;
+                else
+                        swpcounter++;
+        }
+
+        return res;
+}
+
+/*
+ * swp_handler logs the id of calling process, dissects the instruction, sanity
+ * checks the memory location, calls emulate_swpX for the actual operation and
+ * deals with fixup/error handling before returning
+ */
+static int swp_handler(struct pt_regs *regs, unsigned int instr)
+{
+        unsigned int address, destreg, data, type;
+        unsigned int res = 0;
+
+        perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, 0, regs, regs->ARM_pc);
+
+        if (current->pid != previous_pid) {
+                pr_debug("\"%s\" (%ld) uses deprecated SWP{B} instruction\n",
+                         current->comm, (unsigned long)current->pid);
+                previous_pid = current->pid;
+        }
+
+        address = regs->uregs[EXTRACT_REG_NUM(instr, RN_OFFSET)];
+        data    = regs->uregs[EXTRACT_REG_NUM(instr, RT2_OFFSET)];
+        destreg = EXTRACT_REG_NUM(instr, RT_OFFSET);
+
+        type = instr & TYPE_SWPB;
+
+        pr_debug("addr in r%d->0x%08x, dest is r%d, source in r%d->0x%08x)\n",
+                 EXTRACT_REG_NUM(instr, RN_OFFSET), address,
+                 destreg, EXTRACT_REG_NUM(instr, RT2_OFFSET), data);
+
+        /* Check access in reasonable access range for both SWP and SWPB */
+        if (!access_ok(VERIFY_WRITE, (address & ~3), 4)) {
+                pr_debug("SWP{B} emulation: access to %p not allowed!\n",
+                         (void *)address);
+                res = -EFAULT;
+        } else {
+                res = emulate_swpX(address, &data, type);
+        }
+
+        if (res == 0) {
+                /*
+                 * On successful emulation, revert the adjustment to the PC
+                 * made in kernel/traps.c in order to resume execution at the
+                 * instruction following the SWP{B}.
+                 */
+                regs->ARM_pc += 4;
+                regs->uregs[destreg] = data;
+        } else if (res == -EFAULT) {
+                /*
+                 * Memory errors do not mean emulation failed.
+                 * Set up signal info to return SEGV, then return OK
+                 */
+                set_segfault(regs, address);
+        }
+
+        return 0;
+}
+
+/*
+ * Only emulate SWP/SWPB executed in ARM state/User mode.
+ * The kernel must be SWP free and SWP{B} does not exist in Thumb/ThumbEE.
+ */
+static struct undef_hook swp_hook = {
+        .instr_mask = 0x0fb00ff0,
+        .instr_val  = 0x01000090,
+        .cpsr_mask  = MODE_MASK | PSR_T_BIT | PSR_J_BIT,
+        .cpsr_val   = USR_MODE,
+        .fn         = swp_handler
+};
+
+/*
+ * Register handler and create status file in /proc/cpu
+ * Invoked as late_initcall, since not needed before init spawned.
+ */
+static int __init swp_emulation_init(void)
+{
+#ifdef CONFIG_PROC_FS
+        struct proc_dir_entry *res;
+
+        res = create_proc_entry("cpu/swp_emulation", S_IRUGO, NULL);
+
+        if (!res)
+                return -ENOMEM;
+
+        res->read_proc = proc_read_status;
+#endif /* CONFIG_PROC_FS */
+
+        printk(KERN_NOTICE "Registering SWP/SWPB emulation handler\n");
+        register_undef_hook(&swp_hook);
+
+        return 0;
+}
+
+late_initcall(swp_emulation_init);
diff --git a/arch/arm/kernel/time.c b/arch/arm/kernel/time.c
index 38c261f9951c..f1e2eb19a67d 100644
--- a/arch/arm/kernel/time.c
+++ b/arch/arm/kernel/time.c
@@ -30,12 +30,13 @@
 #include <asm/leds.h>
 #include <asm/thread_info.h>
 #include <asm/stacktrace.h>
+#include <asm/mach/arch.h>
 #include <asm/mach/time.h>
 
 /*
  * Our system timer.
  */
-struct sys_timer *system_timer;
+static struct sys_timer *system_timer;
 
 #if defined(CONFIG_RTC_DRV_CMOS) || defined(CONFIG_RTC_DRV_CMOS_MODULE)
 /* this needs a better home */
@@ -160,6 +161,7 @@ device_initcall(timer_init_sysfs);
 
 void __init time_init(void)
 {
+        system_timer = machine_desc->timer;
         system_timer->init();
 }
 
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index 446aee97436f..ee57640ba2bb 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -37,6 +37,8 @@
 
 static const char *handler[]= { "prefetch abort", "data abort", "address exception", "interrupt" };
 
+void *vectors_page;
+
 #ifdef CONFIG_DEBUG_USER
 unsigned int user_debug;
 
@@ -708,19 +710,19 @@ void __readwrite_bug(const char *fn)
 }
 EXPORT_SYMBOL(__readwrite_bug);
 
-void __pte_error(const char *file, int line, unsigned long val)
+void __pte_error(const char *file, int line, pte_t pte)
 {
-        printk("%s:%d: bad pte %08lx.\n", file, line, val);
+        printk("%s:%d: bad pte %08lx.\n", file, line, pte_val(pte));
 }
 
-void __pmd_error(const char *file, int line, unsigned long val)
+void __pmd_error(const char *file, int line, pmd_t pmd)
 {
-        printk("%s:%d: bad pmd %08lx.\n", file, line, val);
+        printk("%s:%d: bad pmd %08lx.\n", file, line, pmd_val(pmd));
 }
 
-void __pgd_error(const char *file, int line, unsigned long val)
+void __pgd_error(const char *file, int line, pgd_t pgd)
 {
-        printk("%s:%d: bad pgd %08lx.\n", file, line, val);
+        printk("%s:%d: bad pgd %08lx.\n", file, line, pgd_val(pgd));
 }
 
 asmlinkage void __div0(void)
@@ -756,7 +758,11 @@ static void __init kuser_get_tls_init(unsigned long vectors)
 
 void __init early_trap_init(void)
 {
+#if defined(CONFIG_CPU_USE_DOMAINS)
         unsigned long vectors = CONFIG_VECTORS_BASE;
+#else
+        unsigned long vectors = (unsigned long)vectors_page;
+#endif
         extern char __stubs_start[], __stubs_end[];
         extern char __vectors_start[], __vectors_end[];
         extern char __kuser_helper_start[], __kuser_helper_end[];
@@ -780,10 +786,10 @@ void __init early_trap_init(void)
          * Copy signal return handlers into the vector page, and
          * set sigreturn to be a pointer to these.
          */
-        memcpy((void *)KERN_SIGRETURN_CODE, sigreturn_codes,
-               sizeof(sigreturn_codes));
-        memcpy((void *)KERN_RESTART_CODE, syscall_restart_code,
-               sizeof(syscall_restart_code));
+        memcpy((void *)(vectors + KERN_SIGRETURN_CODE - CONFIG_VECTORS_BASE),
+               sigreturn_codes, sizeof(sigreturn_codes));
+        memcpy((void *)(vectors + KERN_RESTART_CODE - CONFIG_VECTORS_BASE),
+               syscall_restart_code, sizeof(syscall_restart_code));
 
         flush_icache_range(vectors, vectors + PAGE_SIZE);
         modify_domain(DOMAIN_USER, DOMAIN_CLIENT);
diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index cead8893b46b..86b66f3f2031 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -101,6 +101,7 @@ SECTIONS
                         __exception_text_start = .;
                         *(.exception.text)
                         __exception_text_end = .;
+                        IRQENTRY_TEXT
                         TEXT_TEXT
                         SCHED_TEXT
                         LOCK_TEXT
@@ -167,6 +168,7 @@ SECTIONS
 
                 NOSAVE_DATA
                 CACHELINE_ALIGNED_DATA(32)
+                READ_MOSTLY_DATA(32)
 
                 /*
                  * The exception fixup table (might need resorting at runtime)