select HAVE_FUNCTION_TRACER if (!XIP_KERNEL)
select HAVE_FTRACE_MCOUNT_RECORD if (!XIP_KERNEL)
select HAVE_DYNAMIC_FTRACE if (!XIP_KERNEL)
+ select HAVE_FUNCTION_GRAPH_TRACER if (!THUMB2_KERNEL)
select HAVE_GENERIC_DMA_COHERENT
select HAVE_KERNEL_GZIP
select HAVE_KERNEL_LZO
depends on EXPERIMENTAL
depends on GENERIC_CLOCKEVENTS
depends on REALVIEW_EB_ARM11MP || REALVIEW_EB_A9MP || \
- MACH_REALVIEW_PB11MP || MACH_REALVIEW_PBX || ARCH_OMAP4 ||\
- ARCH_S5PV310 || ARCH_TEGRA || ARCH_U8500 || ARCH_VEXPRESS_CA9X4
+ MACH_REALVIEW_PB11MP || MACH_REALVIEW_PBX || ARCH_OMAP4 || \
+ ARCH_S5PV310 || ARCH_TEGRA || ARCH_U8500 || ARCH_VEXPRESS_CA9X4 || \
+ ARCH_MSM_SCORPIONMP
select USE_GENERIC_SMP_HELPERS
- select HAVE_ARM_SCU
+ select HAVE_ARM_SCU if !ARCH_MSM_SCORPIONMP
help
This enables support for systems with more than one CPU. If you have
a system with only one CPU, like most personal computers, say N. If
config HOTPLUG_CPU
bool "Support for hot-pluggable CPUs (EXPERIMENTAL)"
depends on SMP && HOTPLUG && EXPERIMENTAL
+ depends on !ARCH_MSM
help
Say Y here to experiment with turning CPUs off and on. CPUs
can be controlled through /sys/devices/system/cpu.
bool "Use local timer interrupts"
depends on SMP
default y
- select HAVE_ARM_TWD
+ select HAVE_ARM_TWD if !ARCH_MSM_SCORPIONMP
help
Enable support for local timers on SMP platforms, rather then the
legacy IPI broadcast method. Local timers allows the system
config FRAME_POINTER
bool
depends on !THUMB2_KERNEL
- default y if !ARM_UNWIND
+ default y if !ARM_UNWIND || FUNCTION_GRAPH_TRACER
help
If you say N here, the resulting kernel will be slightly smaller and
faster. However, if neither FRAME_POINTER nor ARM_UNWIND are enabled,
struct arch_hw_breakpoint {
u32 address;
u32 trigger;
- struct perf_event *suspended_wp;
- struct arch_hw_breakpoint_ctrl ctrl;
+ struct arch_hw_breakpoint_ctrl step_ctrl;
+ struct arch_hw_breakpoint_ctrl ctrl;
};
static inline u32 encode_ctrl_reg(struct arch_hw_breakpoint_ctrl ctrl)
#include <asm/outercache.h>
#define __exception __attribute__((section(".exception.text")))
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+#define __exception_irq_entry __irq_entry
+#else
+#define __exception_irq_entry __exception
+#endif
struct thread_info;
struct task_struct;
void register_undef_hook(struct undef_hook *hook);
void unregister_undef_hook(struct undef_hook *hook);
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+static inline int __in_irqentry_text(unsigned long ptr)
+{
+ extern char __irqentry_text_start[];
+ extern char __irqentry_text_end[];
+
+ return ptr >= (unsigned long)&__irqentry_text_start &&
+ ptr < (unsigned long)&__irqentry_text_end;
+}
+#else
+static inline int __in_irqentry_text(unsigned long ptr)
+{
+ return 0;
+}
+#endif
+
static inline int in_exception_text(unsigned long ptr)
{
extern char __exception_text_start[];
extern char __exception_text_end[];
+ int in;
+
+ in = ptr >= (unsigned long)&__exception_text_start &&
+ ptr < (unsigned long)&__exception_text_end;
- return ptr >= (unsigned long)&__exception_text_start &&
- ptr < (unsigned long)&__exception_text_end;
+ return in ? : __in_irqentry_text(ptr);
}
extern void __init early_trap_init(void);
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
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
@
@ set desired IRQ state, then call main handler
@
+ debug_entry r1
msr cpsr_c, r9
mov r2, sp
bl do_DataAbort
#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
@
@ IRQs on, then call the main handler
@
+ debug_entry r1
enable_irq
mov r2, sp
adr lr, BSYM(ret_from_exception)
#else
bl CPU_PABORT_HANDLER
#endif
+ debug_entry r1
enable_irq @ Enable interrupts
mov r2, sp @ regs
bl do_PrefetchAbort @ call abort handler
#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:
.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.
#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)
}
#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;
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
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)
{
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(¤t->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 */
#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>
/* 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. */
/* 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); \
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
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));
/* 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.
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);
}
/*
- * 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)
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;
}
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;
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;
}
if (WARN_ONCE(i == max_slots, "Can't find any breakpoint slot"))
return;
-reset:
/* Reset the control register. */
write_wb_reg(base + i, 0);
}
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? */
{
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);
/* 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;
}
* 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();
}
}
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);
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);
}
}
}
+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. */
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);
#include <linux/list.h>
#include <linux/kallsyms.h>
#include <linux/proc_fs.h>
+#include <linux/ftrace.h>
#include <asm/system.h>
#include <asm/mach/irq.h>
* 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);
* 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
* 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
*/
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;
};
#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)
{
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;
}
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)
/* 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;
.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)
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]. */
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");
}
* 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;
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);
--- /dev/null
+/*
+ * 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 */
--- /dev/null
+/*
+ * 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 */
--- /dev/null
+/*
+ * 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 */
goto out;
if ((gen_type & implied_type) != gen_type) {
- ret = -EINVAL;
- goto out;
+ ret = -EINVAL;
+ goto out;
}
attr.bp_len = gen_len;
#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>
}
#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();
*
* Bit 0 - Inter-processor function call
*/
-asmlinkage void __exception do_IPI(struct pt_regs *regs)
+asmlinkage void __exception_irq_entry do_IPI(struct pt_regs *regs)
{
unsigned int cpu = smp_processor_id();
struct ipi_data *ipi = &per_cpu(ipi_data, cpu);
__exception_text_start = .;
*(.exception.text)
__exception_text_end = .;
+ IRQENTRY_TEXT
TEXT_TEXT
SCHED_TEXT
LOCK_TEXT
Say 'Y' here if you want your kernel to support the
Marvell DB-MV88AP510 Development Board.
+ config MACH_CM_A510
+ bool "CompuLab CM-A510 Board"
+ help
+ Say 'Y' here if you want your kernel to support the
+ CompuLab CM-A510 Board.
+
endmenu
endif
-obj-y += common.o addr-map.o irq.o pcie.o
+obj-y += common.o addr-map.o irq.o pcie.o mpp.o
obj-$(CONFIG_MACH_DOVE_DB) += dove-db-setup.o
+obj-$(CONFIG_MACH_CM_A510) += cm-a510.o
--- /dev/null
+/*
+ * arch/arm/mach-dove/cm-a510.c
+ *
+ * Copyright (C) 2010 CompuLab, Ltd.
+ * Konstantin Sinyuk <kostyas@compulab.co.il>
+ *
+ * Based on Marvell DB-MV88AP510-BP Development Board Setup
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/platform_device.h>
+#include <linux/ata_platform.h>
+#include <linux/mv643xx_eth.h>
+#include <linux/spi/spi.h>
+#include <linux/spi/flash.h>
+
+#include <asm/mach-types.h>
+#include <asm/mach/arch.h>
+
+#include <mach/dove.h>
+
+#include "common.h"
+
+static struct mv643xx_eth_platform_data cm_a510_ge00_data = {
+ .phy_addr = MV643XX_ETH_PHY_ADDR_DEFAULT,
+};
+
+static struct mv_sata_platform_data cm_a510_sata_data = {
+ .n_ports = 1,
+};
+
+/*
+ * SPI Devices:
+ * SPI0: 1M Flash Winbond w25q32bv
+ */
+static const struct flash_platform_data cm_a510_spi_flash_data = {
+ .type = "w25q32bv",
+};
+
+static struct spi_board_info __initdata cm_a510_spi_flash_info[] = {
+ {
+ .modalias = "m25p80",
+ .platform_data = &cm_a510_spi_flash_data,
+ .irq = -1,
+ .max_speed_hz = 20000000,
+ .bus_num = 0,
+ .chip_select = 0,
+ },
+};
+
+static int __init cm_a510_pci_init(void)
+{
+ if (machine_is_cm_a510())
+ dove_pcie_init(1, 1);
+
+ return 0;
+}
+
+subsys_initcall(cm_a510_pci_init);
+
+/* Board Init */
+static void __init cm_a510_init(void)
+{
+ /*
+ * Basic Dove setup. Needs to be called early.
+ */
+ dove_init();
+
+ dove_ge00_init(&cm_a510_ge00_data);
+ dove_ehci0_init();
+ dove_ehci1_init();
+ dove_sata_init(&cm_a510_sata_data);
+ dove_sdio0_init();
+ dove_sdio1_init();
+ dove_spi0_init();
+ dove_spi1_init();
+ dove_uart0_init();
+ dove_uart1_init();
+ dove_i2c_init();
+ spi_register_board_info(cm_a510_spi_flash_info,
+ ARRAY_SIZE(cm_a510_spi_flash_info));
+}
+
+MACHINE_START(CM_A510, "Compulab CM-A510 Board")
+ .boot_params = 0x00000100,
+ .init_machine = cm_a510_init,
+ .map_io = dove_map_io,
+ .init_irq = dove_init_irq,
+ .timer = &dove_timer,
+MACHINE_END
#define DOVE_RESET_SAMPLE_LO (DOVE_MPP_VIRT_BASE | 0x014)
#define DOVE_RESET_SAMPLE_HI (DOVE_MPP_VIRT_BASE | 0x018)
#define DOVE_GPIO_VIRT_BASE (DOVE_SB_REGS_VIRT_BASE | 0xd0400)
+#define DOVE_GPIO2_VIRT_BASE (DOVE_SB_REGS_VIRT_BASE | 0xe8400)
#define DOVE_MPP_GENERAL_VIRT_BASE (DOVE_SB_REGS_VIRT_BASE | 0xe803c)
#define DOVE_AU1_SPDIFO_GPIO_EN (1 << 1)
#define DOVE_NAND_GPIO_EN (1 << 0)
#define DOVE_MPP_CTRL4_VIRT_BASE (DOVE_GPIO_VIRT_BASE + 0x40)
-
+#define DOVE_SPI_GPIO_SEL (1 << 5)
+#define DOVE_UART1_GPIO_SEL (1 << 4)
+#define DOVE_AU1_GPIO_SEL (1 << 3)
+#define DOVE_CAM_GPIO_SEL (1 << 2)
+#define DOVE_SD1_GPIO_SEL (1 << 1)
+#define DOVE_SD0_GPIO_SEL (1 << 0)
/* Power Management */
#define DOVE_PMU_VIRT_BASE (DOVE_SB_REGS_VIRT_BASE | 0xd0000)
+#define DOVE_PMU_SIG_CTRL (DOVE_PMU_VIRT_BASE + 0x802c)
/* Real Time Clock */
#define DOVE_RTC_PHYS_BASE (DOVE_SB_REGS_PHYS_BASE | 0xd8500)
#include <plat/gpio.h>
#include <asm-generic/gpio.h> /* cansleep wrappers */
-#define GPIO_MAX 64
+#define GPIO_MAX 72
#define GPIO_BASE_LO (DOVE_GPIO_VIRT_BASE + 0x00)
#define GPIO_BASE_HI (DOVE_GPIO_VIRT_BASE + 0x20)
-#define GPIO_BASE(pin) ((pin < 32) ? GPIO_BASE_LO : GPIO_BASE_HI)
+#define GPIO_BASE(pin) ((pin < 32) ? GPIO_BASE_LO : \
+ ((pin < 64) ? GPIO_BASE_HI : \
+ DOVE_GPIO2_VIRT_BASE))
#define GPIO_OUT(pin) (GPIO_BASE(pin) + 0x00)
#define GPIO_IO_CONF(pin) (GPIO_BASE(pin) + 0x04)
--- /dev/null
+/*
+ * arch/arm/mach-dove/mpp.c
+ *
+ * MPP functions for Marvell Dove SoCs
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <linux/kernel.h>
+#include <linux/gpio.h>
+#include <linux/io.h>
+
+#include <mach/dove.h>
+
+#include "mpp.h"
+
+#define MPP_NR_REGS 4
+#define MPP_CTRL(i) ((i) == 3 ? \
+ DOVE_MPP_CTRL4_VIRT_BASE : \
+ DOVE_MPP_VIRT_BASE + (i) * 4)
+#define PMU_SIG_REGS 2
+#define PMU_SIG_CTRL(i) (DOVE_PMU_SIG_CTRL + (i) * 4)
+
+struct dove_mpp_grp {
+ int start;
+ int end;
+};
+
+static struct dove_mpp_grp dove_mpp_grp[] = {
+ [MPP_24_39] = {
+ .start = 24,
+ .end = 39,
+ },
+ [MPP_40_45] = {
+ .start = 40,
+ .end = 45,
+ },
+ [MPP_46_51] = {
+ .start = 40,
+ .end = 45,
+ },
+ [MPP_58_61] = {
+ .start = 58,
+ .end = 61,
+ },
+ [MPP_62_63] = {
+ .start = 62,
+ .end = 63,
+ },
+};
+
+static void dove_mpp_gpio_mode(int start, int end, int gpio_mode)
+{
+ int i;
+
+ for (i = start; i <= end; i++)
+ orion_gpio_set_valid(i, gpio_mode);
+}
+
+static void dove_mpp_dump_regs(void)
+{
+#ifdef DEBUG
+ int i;
+
+ pr_debug("MPP_CTRL regs:");
+ for (i = 0; i < MPP_NR_REGS; i++)
+ printk(" %08x", readl(MPP_CTRL(i)));
+ printk("\n");
+
+ pr_debug("PMU_SIG_CTRL regs:");
+ for (i = 0; i < PMU_SIG_REGS; i++)
+ printk(" %08x", readl(PMU_SIG_CTRL(i)));
+ printk("\n");
+
+ pr_debug("PMU_MPP_GENERAL_CTRL: %08x\n", readl(DOVE_PMU_MPP_GENERAL_CTRL));
+ pr_debug("MPP_GENERAL: %08x\n", readl(DOVE_MPP_GENERAL_VIRT_BASE));
+#endif
+}
+
+static void dove_mpp_cfg_nfc(int sel)
+{
+ u32 mpp_gen_cfg = readl(DOVE_MPP_GENERAL_VIRT_BASE);
+
+ mpp_gen_cfg &= ~0x1;
+ mpp_gen_cfg |= sel;
+ writel(mpp_gen_cfg, DOVE_MPP_GENERAL_VIRT_BASE);
+
+ dove_mpp_gpio_mode(64, 71, GPIO_OUTPUT_OK);
+}
+
+static void dove_mpp_cfg_au1(int sel)
+{
+ u32 mpp_ctrl4 = readl(DOVE_MPP_CTRL4_VIRT_BASE);
+ u32 ssp_ctrl1 = readl(DOVE_SSP_CTRL_STATUS_1);
+ u32 mpp_gen_ctrl = readl(DOVE_MPP_GENERAL_VIRT_BASE);
+ u32 global_cfg_2 = readl(DOVE_GLOBAL_CONFIG_2);
+
+ mpp_ctrl4 &= ~(DOVE_AU1_GPIO_SEL);
+ ssp_ctrl1 &= ~(DOVE_SSP_ON_AU1);
+ mpp_gen_ctrl &= ~(DOVE_AU1_SPDIFO_GPIO_EN);
+ global_cfg_2 &= ~(DOVE_TWSI_OPTION3_GPIO);
+
+ if (!sel || sel == 0x2)
+ dove_mpp_gpio_mode(52, 57, 0);
+ else
+ dove_mpp_gpio_mode(52, 57, GPIO_OUTPUT_OK | GPIO_INPUT_OK);
+
+ if (sel & 0x1) {
+ global_cfg_2 |= DOVE_TWSI_OPTION3_GPIO;
+ dove_mpp_gpio_mode(56, 57, 0);
+ }
+ if (sel & 0x2) {
+ mpp_gen_ctrl |= DOVE_AU1_SPDIFO_GPIO_EN;
+ dove_mpp_gpio_mode(57, 57, GPIO_OUTPUT_OK | GPIO_INPUT_OK);
+ }
+ if (sel & 0x4) {
+ ssp_ctrl1 |= DOVE_SSP_ON_AU1;
+ dove_mpp_gpio_mode(52, 55, 0);
+ }
+ if (sel & 0x8)
+ mpp_ctrl4 |= DOVE_AU1_GPIO_SEL;
+
+ writel(mpp_ctrl4, DOVE_MPP_CTRL4_VIRT_BASE);
+ writel(ssp_ctrl1, DOVE_SSP_CTRL_STATUS_1);
+ writel(mpp_gen_ctrl, DOVE_MPP_GENERAL_VIRT_BASE);
+ writel(global_cfg_2, DOVE_GLOBAL_CONFIG_2);
+}
+
+static void dove_mpp_conf_grp(int num, int sel, u32 *mpp_ctrl)
+{
+ int start = dove_mpp_grp[num].start;
+ int end = dove_mpp_grp[num].end;
+ int gpio_mode = sel ? GPIO_OUTPUT_OK | GPIO_INPUT_OK : 0;
+
+ *mpp_ctrl &= ~(0x1 << num);
+ *mpp_ctrl |= sel << num;
+
+ dove_mpp_gpio_mode(start, end, gpio_mode);
+}
+
+void __init dove_mpp_conf(unsigned int *mpp_list)
+{
+ u32 mpp_ctrl[MPP_NR_REGS];
+ u32 pmu_mpp_ctrl = 0;
+ u32 pmu_sig_ctrl[PMU_SIG_REGS];
+ int i;
+
+ /* Initialize gpiolib. */
+ orion_gpio_init();
+
+ for (i = 0; i < MPP_NR_REGS; i++)
+ mpp_ctrl[i] = readl(MPP_CTRL(i));
+
+ for (i = 0; i < PMU_SIG_REGS; i++)
+ pmu_sig_ctrl[i] = readl(PMU_SIG_CTRL(i));
+
+ pmu_mpp_ctrl = readl(DOVE_PMU_MPP_GENERAL_CTRL);
+
+ dove_mpp_dump_regs();
+
+ for ( ; *mpp_list != MPP_END; mpp_list++) {
+ unsigned int num = MPP_NUM(*mpp_list);
+ unsigned int sel = MPP_SEL(*mpp_list);
+ int shift, gpio_mode;
+
+ if (num > MPP_MAX) {
+ pr_err("dove: invalid MPP number (%u)\n", num);
+ continue;
+ }
+
+ if (*mpp_list & MPP_NFC_MASK) {
+ dove_mpp_cfg_nfc(sel);
+ continue;
+ }
+
+ if (*mpp_list & MPP_AU1_MASK) {
+ dove_mpp_cfg_au1(sel);
+ continue;
+ }
+
+ if (*mpp_list & MPP_GRP_MASK) {
+ dove_mpp_conf_grp(num, sel, &mpp_ctrl[3]);
+ continue;
+ }
+
+ shift = (num & 7) << 2;
+ if (*mpp_list & MPP_PMU_MASK) {
+ pmu_mpp_ctrl |= (0x1 << num);
+ pmu_sig_ctrl[num / 8] &= ~(0xf << shift);
+ pmu_sig_ctrl[num / 8] |= 0xf << shift;
+ gpio_mode = 0;
+ } else {
+ mpp_ctrl[num / 8] &= ~(0xf << shift);
+ mpp_ctrl[num / 8] |= sel << shift;
+ gpio_mode = GPIO_OUTPUT_OK | GPIO_INPUT_OK;
+ }
+
+ orion_gpio_set_valid(num, gpio_mode);
+ }
+
+ for (i = 0; i < MPP_NR_REGS; i++)
+ writel(mpp_ctrl[i], MPP_CTRL(i));
+
+ for (i = 0; i < PMU_SIG_REGS; i++)
+ writel(pmu_sig_ctrl[i], PMU_SIG_CTRL(i));
+
+ writel(pmu_mpp_ctrl, DOVE_PMU_MPP_GENERAL_CTRL);
+
+ dove_mpp_dump_regs();
+}
--- /dev/null
+#ifndef __ARCH_DOVE_MPP_CODED_H
+#define __ARCH_DOVE_MPP_CODED_H
+
+#define MPP(_num, _mode, _pmu, _grp, _au1, _nfc) ( \
+/* MPP/group number */ ((_num) & 0xff) | \
+/* MPP select value */ (((_mode) & 0xf) << 8) | \
+/* MPP PMU */ ((!!(_pmu)) << 12) | \
+/* group flag */ ((!!(_grp)) << 13) | \
+/* AU1 flag */ ((!!(_au1)) << 14) | \
+/* NFCE flag */ ((!!(_nfc)) << 15))
+
+#define MPP_MAX 71
+
+#define MPP_NUM(x) ((x) & 0xff)
+#define MPP_SEL(x) (((x) >> 8) & 0xf)
+
+#define MPP_PMU_MASK MPP(0, 0x0, 1, 0, 0, 0)
+#define MPP_GRP_MASK MPP(0, 0x0, 0, 1, 0, 0)
+#define MPP_AU1_MASK MPP(0, 0x0, 0, 0, 1, 0)
+#define MPP_NFC_MASK MPP(0, 0x0, 0, 0, 0, 1)
+
+#define MPP_END MPP(0xff, 0xf, 1, 1, 1, 1)
+
+#define MPP_PMU_DRIVE_0 0x1
+#define MPP_PMU_DRIVE_1 0x2
+#define MPP_PMU_SDI 0x3
+#define MPP_PMU_CPU_PWRDWN 0x4
+#define MPP_PMU_STBY_PWRDWN 0x5
+#define MPP_PMU_CORE_PWR_GOOD 0x8
+#define MPP_PMU_BAT_FAULT 0xa
+#define MPP_PMU_EXT0_WU 0xb
+#define MPP_PMU_EXT1_WU 0xc
+#define MPP_PMU_EXT2_WU 0xd
+#define MPP_PMU_BLINK 0xe
+#define MPP_PMU(_num, _mode) MPP((_num), MPP_PMU_##_mode, 1, 0, 0, 0)
+
+#define MPP_PIN(_num, _mode) MPP((_num), (_mode), 0, 0, 0, 0)
+#define MPP_GRP(_grp, _mode) MPP((_grp), (_mode), 0, 1, 0, 0)
+#define MPP_GRP_AU1(_mode) MPP(0, (_mode), 0, 0, 1, 0)
+#define MPP_GRP_NFC(_mode) MPP(0, (_mode), 0, 0, 0, 1)
+
+#define MPP0_GPIO0 MPP_PIN(0, 0x0)
+#define MPP0_UA2_RTSn MPP_PIN(0, 0x2)
+#define MPP0_SDIO0_CD MPP_PIN(0, 0x3)
+#define MPP0_LCD0_PWM MPP_PIN(0, 0xf)
+
+#define MPP1_GPIO1 MPP_PIN(1, 0x0)
+#define MPP1_UA2_CTSn MPP_PIN(1, 0x2)
+#define MPP1_SDIO0_WP MPP_PIN(1, 0x3)
+#define MPP1_LCD1_PWM MPP_PIN(1, 0xf)
+
+#define MPP2_GPIO2 MPP_PIN(2, 0x0)
+#define MPP2_SATA_PRESENT MPP_PIN(2, 0x1)
+#define MPP2_UA2_TXD MPP_PIN(2, 0x2)
+#define MPP2_SDIO0_BUS_POWER MPP_PIN(2, 0x3)
+#define MPP2_UA_RTSn1 MPP_PIN(2, 0x4)
+
+#define MPP3_GPIO3 MPP_PIN(3, 0x0)
+#define MPP3_SATA_ACT MPP_PIN(3, 0x1)
+#define MPP3_UA2_RXD MPP_PIN(3, 0x2)
+#define MPP3_SDIO0_LED_CTRL MPP_PIN(3, 0x3)
+#define MPP3_UA_CTSn1 MPP_PIN(3, 0x4)
+#define MPP3_SPI_LCD_CS1 MPP_PIN(3, 0xf)
+
+#define MPP4_GPIO4 MPP_PIN(4, 0x0)
+#define MPP4_UA3_RTSn MPP_PIN(4, 0x2)
+#define MPP4_SDIO1_CD MPP_PIN(4, 0x3)
+#define MPP4_SPI_1_MISO MPP_PIN(4, 0x4)
+
+#define MPP5_GPIO5 MPP_PIN(5, 0x0)
+#define MPP5_UA3_CTSn MPP_PIN(5, 0x2)
+#define MPP5_SDIO1_WP MPP_PIN(5, 0x3)
+#define MPP5_SPI_1_CS MPP_PIN(5, 0x4)
+
+#define MPP6_GPIO6 MPP_PIN(6, 0x0)
+#define MPP6_UA3_TXD MPP_PIN(6, 0x2)
+#define MPP6_SDIO1_BUS_POWER MPP_PIN(6, 0x3)
+#define MPP6_SPI_1_MOSI MPP_PIN(6, 0x4)
+
+#define MPP7_GPIO7 MPP_PIN(7, 0x0)
+#define MPP7_UA3_RXD MPP_PIN(7, 0x2)
+#define MPP7_SDIO1_LED_CTRL MPP_PIN(7, 0x3)
+#define MPP7_SPI_1_SCK MPP_PIN(7, 0x4)
+
+#define MPP8_GPIO8 MPP_PIN(8, 0x0)
+#define MPP8_WD_RST_OUT MPP_PIN(8, 0x1)
+
+#define MPP9_GPIO9 MPP_PIN(9, 0x0)
+#define MPP9_PEX1_CLKREQn MPP_PIN(9, 0x5)
+
+#define MPP10_GPIO10 MPP_PIN(10, 0x0)
+#define MPP10_SSP_SCLK MPP_PIN(10, 0x5)
+
+#define MPP11_GPIO11 MPP_PIN(11, 0x0)
+#define MPP11_SATA_PRESENT MPP_PIN(11, 0x1)
+#define MPP11_SATA_ACT MPP_PIN(11, 0x2)
+#define MPP11_SDIO0_LED_CTRL MPP_PIN(11, 0x3)
+#define MPP11_SDIO1_LED_CTRL MPP_PIN(11, 0x4)
+#define MPP11_PEX0_CLKREQn MPP_PIN(11, 0x5)
+
+#define MPP12_GPIO12 MPP_PIN(12, 0x0)
+#define MPP12_SATA_ACT MPP_PIN(12, 0x1)
+#define MPP12_UA2_RTSn MPP_PIN(12, 0x2)
+#define MPP12_AD0_I2S_EXT_MCLK MPP_PIN(12, 0x3)
+#define MPP12_SDIO1_CD MPP_PIN(12, 0x4)
+
+#define MPP13_GPIO13 MPP_PIN(13, 0x0)
+#define MPP13_UA2_CTSn MPP_PIN(13, 0x2)
+#define MPP13_AD1_I2S_EXT_MCLK MPP_PIN(13, 0x3)
+#define MPP13_SDIO1WP MPP_PIN(13, 0x4)
+#define MPP13_SSP_EXTCLK MPP_PIN(13, 0x5)
+
+#define MPP14_GPIO14 MPP_PIN(14, 0x0)
+#define MPP14_UA2_TXD MPP_PIN(14, 0x2)
+#define MPP14_SDIO1_BUS_POWER MPP_PIN(14, 0x4)
+#define MPP14_SSP_RXD MPP_PIN(14, 0x5)
+
+#define MPP15_GPIO15 MPP_PIN(15, 0x0)
+#define MPP15_UA2_RXD MPP_PIN(15, 0x2)
+#define MPP15_SDIO1_LED_CTRL MPP_PIN(15, 0x4)
+#define MPP15_SSP_SFRM MPP_PIN(15, 0x5)
+
+#define MPP16_GPIO16 MPP_PIN(16, 0x0)
+#define MPP16_UA3_RTSn MPP_PIN(16, 0x2)
+#define MPP16_SDIO0_CD MPP_PIN(16, 0x3)
+#define MPP16_SPI_LCD_CS1 MPP_PIN(16, 0x4)
+#define MPP16_AC97_SDATA_IN1 MPP_PIN(16, 0x5)
+
+#define MPP17_GPIO17 MPP_PIN(17, 0x0)
+#define MPP17_AC97_SYSCLK_OUT MPP_PIN(17, 0x1)
+#define MPP17_UA3_CTSn MPP_PIN(17, 0x2)
+#define MPP17_SDIO0_WP MPP_PIN(17, 0x3)
+#define MPP17_TW_SDA2 MPP_PIN(17, 0x4)
+#define MPP17_AC97_SDATA_IN2 MPP_PIN(17, 0x5)
+
+#define MPP18_GPIO18 MPP_PIN(18, 0x0)
+#define MPP18_UA3_TXD MPP_PIN(18, 0x2)
+#define MPP18_SDIO0_BUS_POWER MPP_PIN(18, 0x3)
+#define MPP18_LCD0_PWM MPP_PIN(18, 0x4)
+#define MPP18_AC_SDATA_IN3 MPP_PIN(18, 0x5)
+
+#define MPP19_GPIO19 MPP_PIN(19, 0x0)
+#define MPP19_UA3_RXD MPP_PIN(19, 0x2)
+#define MPP19_SDIO0_LED_CTRL MPP_PIN(19, 0x3)
+#define MPP19_TW_SCK2 MPP_PIN(19, 0x4)
+
+#define MPP20_GPIO20 MPP_PIN(20, 0x0)
+#define MPP20_AC97_SYSCLK_OUT MPP_PIN(20, 0x1)
+#define MPP20_SPI_LCD_MISO MPP_PIN(20, 0x2)
+#define MPP20_SDIO1_CD MPP_PIN(20, 0x3)
+#define MPP20_SDIO0_CD MPP_PIN(20, 0x5)
+#define MPP20_SPI_1_MISO MPP_PIN(20, 0x6)
+
+#define MPP21_GPIO21 MPP_PIN(21, 0x0)
+#define MPP21_UA1_RTSn MPP_PIN(21, 0x1)
+#define MPP21_SPI_LCD_CS0 MPP_PIN(21, 0x2)
+#define MPP21_SDIO1_WP MPP_PIN(21, 0x3)
+#define MPP21_SSP_SFRM MPP_PIN(21, 0x4)
+#define MPP21_SDIO0_WP MPP_PIN(21, 0x5)
+#define MPP21_SPI_1_CS MPP_PIN(21, 0x6)
+
+#define MPP22_GPIO22 MPP_PIN(22, 0x0)
+#define MPP22_UA1_CTSn MPP_PIN(22, 0x1)
+#define MPP22_SPI_LCD_MOSI MPP_PIN(22, 0x2)
+#define MPP22_SDIO1_BUS_POWER MPP_PIN(22, 0x3)
+#define MPP22_SSP_TXD MPP_PIN(22, 0x4)
+#define MPP22_SDIO0_BUS_POWER MPP_PIN(22, 0x5)
+#define MPP22_SPI_1_MOSI MPP_PIN(22, 0x6)
+
+#define MPP23_GPIO23 MPP_PIN(23, 0x0)
+#define MPP23_SPI_LCD_SCK MPP_PIN(23, 0x2)
+#define MPP23_SDIO1_LED_CTRL MPP_PIN(23, 0x3)
+#define MPP23_SSP_SCLK MPP_PIN(23, 0x4)
+#define MPP23_SDIO0_LED_CTRL MPP_PIN(23, 0x5)
+#define MPP23_SPI_1_SCK MPP_PIN(23, 0x6)
+
+/* for MPP groups _num is a group index */
+enum dove_mpp_grp_idx {
+ MPP_24_39 = 2,
+ MPP_40_45 = 0,
+ MPP_46_51 = 1,
+ MPP_58_61 = 5,
+ MPP_62_63 = 4,
+};
+
+#define MPP24_39_GPIO MPP_GRP(MPP_24_39, 0x1)
+#define MPP24_39_CAM MPP_GRP(MPP_24_39, 0x0)
+
+#define MPP40_45_GPIO MPP_GRP(MPP_40_45, 0x1)
+#define MPP40_45_SD0 MPP_GRP(MPP_40_45, 0x0)
+
+#define MPP46_51_GPIO MPP_GRP(MPP_46_51, 0x1)
+#define MPP46_51_SD1 MPP_GRP(MPP_46_51, 0x0)
+
+#define MPP58_61_GPIO MPP_GRP(MPP_58_61, 0x1)
+#define MPP58_61_SPI MPP_GRP(MPP_58_61, 0x0)
+
+#define MPP62_63_GPIO MPP_GRP(MPP_62_63, 0x1)
+#define MPP62_63_UA1 MPP_GRP(MPP_62_63, 0x0)
+
+/* The MPP[64:71] control differs from other groups */
+#define MPP64_71_GPO MPP_GRP_NFC(0x1)
+#define MPP64_71_NFC MPP_GRP_NFC(0x0)
+
+/*
+ * The MPP[52:57] functionality is encoded by 4 bits in different
+ * registers. The _num field in this case encodes those bits in
+ * correspodence with Table 135 of 88AP510 Functional specification
+ */
+#define MPP52_57_AU1 MPP_GRP_AU1(0x0)
+#define MPP52_57_AU1_GPIO57 MPP_GRP_AU1(0x2)
+#define MPP52_57_GPIO MPP_GRP_AU1(0xa)
+#define MPP52_57_TW_GPIO MPP_GRP_AU1(0xb)
+#define MPP52_57_AU1_SSP MPP_GRP_AU1(0xc)
+#define MPP52_57_SSP_GPIO MPP_GRP_AU1(0xe)
+#define MPP52_57_SSP_TW MPP_GRP_AU1(0xf)
+
+void dove_mpp_conf(unsigned int *mpp_list);
+
+#endif /* __ARCH_DOVE_MPP_CODED_H */
Marvell GuruPlug Reference Board.
config MACH_TS219
- bool "QNAP TS-110, TS-119, TS-210, TS-219 and TS-219P Turbo NAS"
+ bool "QNAP TS-110, TS-119, TS-119P+, TS-210, TS-219, TS-219P and TS-219P+ Turbo NAS"
help
Say 'Y' here if you want your kernel to support the
- QNAP TS-110, TS-119, TS-210, TS-219 and TS-219P Turbo NAS
- devices.
+ QNAP TS-110, TS-119, TS-119P+, TS-210, TS-219, TS-219P and
+ TS-219P+ Turbo NAS devices.
config MACH_TS41X
- bool "QNAP TS-410, TS-410U, TS-419P and TS-419U Turbo NAS"
+ bool "QNAP TS-410, TS-410U, TS-419P, TS-419P+ and TS-419U Turbo NAS"
help
Say 'Y' here if you want your kernel to support the
- QNAP TS-410, TS-410U, TS-419P and TS-419U Turbo NAS
- devices.
+ QNAP TS-410, TS-410U, TS-419P, TS-419P+ and TS-419U Turbo
+ NAS devices.
config MACH_DOCKSTAR
bool "Seagate FreeAgent DockStar"
MPP11_UART0_RXD,
MPP13_UART1_TXD, /* PIC controller */
MPP14_UART1_RXD, /* PIC controller */
- MPP15_GPIO, /* USB Copy button */
- MPP16_GPIO, /* Reset button */
+ MPP15_GPIO, /* USB Copy button (on devices with 88F6281) */
+ MPP16_GPIO, /* Reset button (on devices with 88F6281) */
MPP36_GPIO, /* RAM: 0: 256 MB, 1: 512 MB */
+ MPP37_GPIO, /* Reset button (on devices with 88F6282) */
+ MPP43_GPIO, /* USB Copy button (on devices with 88F6282) */
MPP44_GPIO, /* Board ID: 0: TS-11x, 1: TS-21x */
0
};
static void __init qnap_ts219_init(void)
{
+ u32 dev, rev;
+
/*
* Basic setup. Needs to be called early.
*/
qnap_tsx1x_register_flash();
kirkwood_i2c_init();
i2c_register_board_info(0, &qnap_ts219_i2c_rtc, 1);
+
+ kirkwood_pcie_id(&dev, &rev);
+ if (dev == MV88F6282_DEV_ID) {
+ qnap_ts219_buttons[0].gpio = 43; /* USB Copy button */
+ qnap_ts219_buttons[1].gpio = 37; /* Reset button */
+ qnap_ts219_ge00_data.phy_addr = MV643XX_ETH_PHY_ADDR(0);
+ }
+
kirkwood_ge00_init(&qnap_ts219_ge00_data);
kirkwood_sata_init(&qnap_ts219_sata_data);
kirkwood_ehci_init();
static void __init qnap_ts41x_init(void)
{
+ u32 dev, rev;
+
/*
* Basic setup. Needs to be called early.
*/
qnap_tsx1x_register_flash();
kirkwood_i2c_init();
i2c_register_board_info(0, &qnap_ts41x_i2c_rtc, 1);
+
+ kirkwood_pcie_id(&dev, &rev);
+ if (dev == MV88F6282_DEV_ID) {
+ qnap_ts41x_ge00_data.phy_addr = MV643XX_ETH_PHY_ADDR(0);
+ qnap_ts41x_ge01_data.phy_addr = MV643XX_ETH_PHY_ADDR(1);
+ }
kirkwood_ge00_init(&qnap_ts41x_ge00_data);
kirkwood_ge01_init(&qnap_ts41x_ge01_data);
+
kirkwood_sata_init(&qnap_ts41x_sata_data);
kirkwood_ehci_init();
platform_device_register(&qnap_ts41x_button_device);
config MSM_SOC_REV_A
bool
+config ARCH_MSM_SCORPIONMP
+ bool
config ARCH_MSM_ARM11
bool
*/
#define DDR_VIRT_BASE (MV78XX0_REGS_VIRT_BASE | 0x00000)
#define DDR_WINDOW_CPU0_BASE (DDR_VIRT_BASE | 0x1500)
-#define DDR_WINDOW_CPU1_BASE (DDR_VIRT_BASE | 0x1700)
+#define DDR_WINDOW_CPU1_BASE (DDR_VIRT_BASE | 0x1570)
#define DEV_BUS_PHYS_BASE (MV78XX0_REGS_PHYS_BASE | 0x10000)
#define DEV_BUS_VIRT_BASE (MV78XX0_REGS_VIRT_BASE | 0x10000)
Buffalo Linkstation Pro/Live platform. Both v1 and
v2 devices are supported.
+config MACH_LINKSTATION_LSCHL
+ bool "Buffalo Linkstation Live v3 (LS-CHL)"
+ select I2C_BOARDINFO
+ help
+ Say 'Y' here if you want your kernel to support the
+ Buffalo Linkstation Live v3 (LS-CHL) platform.
+
config MACH_LINKSTATION_MINI
bool "Buffalo Linkstation Mini"
select I2C_BOARDINFO
obj-$(CONFIG_MACH_RD88F5181L_GE) += rd88f5181l-ge-setup.o
obj-$(CONFIG_MACH_RD88F5181L_FXO) += rd88f5181l-fxo-setup.o
obj-$(CONFIG_MACH_RD88F6183AP_GE) += rd88f6183ap-ge-setup.o
+obj-$(CONFIG_MACH_LINKSTATION_LSCHL) += ls-chl-setup.o
--- /dev/null
+/*
+ * arch/arm/mach-orion5x/ls-chl-setup.c
+ *
+ * Maintainer: Ash Hughes <ashley.hughes@blueyonder.co.uk>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/platform_device.h>
+#include <linux/mtd/physmap.h>
+#include <linux/mv643xx_eth.h>
+#include <linux/leds.h>
+#include <linux/gpio_keys.h>
+#include <linux/gpio-fan.h>
+#include <linux/input.h>
+#include <linux/i2c.h>
+#include <linux/ata_platform.h>
+#include <linux/gpio.h>
+#include <asm/mach-types.h>
+#include <asm/mach/arch.h>
+#include <asm/system.h>
+#include <mach/orion5x.h>
+#include "common.h"
+#include "mpp.h"
+
+/*****************************************************************************
+ * Linkstation LS-CHL Info
+ ****************************************************************************/
+
+/*
+ * 256K NOR flash Device bus boot chip select
+ */
+
+#define LSCHL_NOR_BOOT_BASE 0xf4000000
+#define LSCHL_NOR_BOOT_SIZE SZ_256K
+
+/*****************************************************************************
+ * 256KB NOR Flash on BOOT Device
+ ****************************************************************************/
+
+static struct physmap_flash_data lschl_nor_flash_data = {
+ .width = 1,
+};
+
+static struct resource lschl_nor_flash_resource = {
+ .flags = IORESOURCE_MEM,
+ .start = LSCHL_NOR_BOOT_BASE,
+ .end = LSCHL_NOR_BOOT_BASE + LSCHL_NOR_BOOT_SIZE - 1,
+};
+
+static struct platform_device lschl_nor_flash = {
+ .name = "physmap-flash",
+ .id = 0,
+ .dev = {
+ .platform_data = &lschl_nor_flash_data,
+ },
+ .num_resources = 1,
+ .resource = &lschl_nor_flash_resource,
+};
+
+/*****************************************************************************
+ * Ethernet
+ ****************************************************************************/
+
+static struct mv643xx_eth_platform_data lschl_eth_data = {
+ .phy_addr = MV643XX_ETH_PHY_ADDR(8),
+};
+
+/*****************************************************************************
+ * RTC 5C372a on I2C bus
+ ****************************************************************************/
+
+static struct i2c_board_info __initdata lschl_i2c_rtc = {
+ I2C_BOARD_INFO("rs5c372a", 0x32),
+};
+
+/*****************************************************************************
+ * LEDs attached to GPIO
+ ****************************************************************************/
+
+#define LSCHL_GPIO_LED_ALARM 2
+#define LSCHL_GPIO_LED_INFO 3
+#define LSCHL_GPIO_LED_FUNC 17
+#define LSCHL_GPIO_LED_PWR 0
+
+static struct gpio_led lschl_led_pins[] = {
+ {
+ .name = "alarm:red",
+ .gpio = LSCHL_GPIO_LED_ALARM,
+ .active_low = 1,
+ }, {
+ .name = "info:amber",
+ .gpio = LSCHL_GPIO_LED_INFO,
+ .active_low = 1,
+ }, {
+ .name = "func:blue:top",
+ .gpio = LSCHL_GPIO_LED_FUNC,
+ .active_low = 1,
+ }, {
+ .name = "power:blue:bottom",
+ .gpio = LSCHL_GPIO_LED_PWR,
+ },
+};
+
+static struct gpio_led_platform_data lschl_led_data = {
+ .leds = lschl_led_pins,
+ .num_leds = ARRAY_SIZE(lschl_led_pins),
+};
+
+static struct platform_device lschl_leds = {
+ .name = "leds-gpio",
+ .id = -1,
+ .dev = {
+ .platform_data = &lschl_led_data,
+ },
+};
+
+/*****************************************************************************
+ * SATA
+ ****************************************************************************/
+static struct mv_sata_platform_data lschl_sata_data = {
+ .n_ports = 2,
+};
+
+/*****************************************************************************
+ * LS-CHL specific power off method: reboot
+ ****************************************************************************/
+/*
+ * On the LS-CHL, the shutdown process is following:
+ * - Userland monitors key events until the power switch goes to off position
+ * - The board reboots
+ * - U-boot starts and goes into an idle mode waiting for the user
+ * to move the switch to ON position
+ *
+ */
+
+static void lschl_power_off(void)
+{
+ arm_machine_restart('h', NULL);
+}
+
+/*****************************************************************************
+ * General Setup
+ ****************************************************************************/
+#define LSCHL_GPIO_USB_POWER 9
+#define LSCHL_GPIO_AUTO_POWER 17
+#define LSCHL_GPIO_POWER 18
+
+/****************************************************************************
+ * GPIO Attached Keys
+ ****************************************************************************/
+#define LSCHL_GPIO_KEY_FUNC 15
+#define LSCHL_GPIO_KEY_POWER 8
+#define LSCHL_GPIO_KEY_AUTOPOWER 10
+#define LSCHL_SW_POWER 0x00
+#define LSCHL_SW_AUTOPOWER 0x01
+#define LSCHL_SW_FUNC 0x02
+
+static struct gpio_keys_button lschl_buttons[] = {
+ {
+ .type = EV_SW,
+ .code = LSCHL_SW_POWER,
+ .gpio = LSCHL_GPIO_KEY_POWER,
+ .desc = "Power-on Switch",
+ .active_low = 1,
+ }, {
+ .type = EV_SW,
+ .code = LSCHL_SW_AUTOPOWER,
+ .gpio = LSCHL_GPIO_KEY_AUTOPOWER,
+ .desc = "Power-auto Switch",
+ .active_low = 1,
+ }, {
+ .type = EV_SW,
+ .code = LSCHL_SW_FUNC,
+ .gpio = LSCHL_GPIO_KEY_FUNC,
+ .desc = "Function Switch",
+ .active_low = 1,
+ },
+};
+
+static struct gpio_keys_platform_data lschl_button_data = {
+ .buttons = lschl_buttons,
+ .nbuttons = ARRAY_SIZE(lschl_buttons),
+};
+
+static struct platform_device lschl_button_device = {
+ .name = "gpio-keys",
+ .id = -1,
+ .num_resources = 0,
+ .dev = {
+ .platform_data = &lschl_button_data,
+ },
+};
+
+#define LSCHL_GPIO_HDD_POWER 1
+
+/****************************************************************************
+ * GPIO Fan
+ ****************************************************************************/
+
+#define LSCHL_GPIO_FAN_LOW 16
+#define LSCHL_GPIO_FAN_HIGH 14
+#define LSCHL_GPIO_FAN_LOCK 6
+
+static struct gpio_fan_alarm lschl_alarm = {
+ .gpio = LSCHL_GPIO_FAN_LOCK,
+};
+
+static struct gpio_fan_speed lschl_speeds[] = {
+ {
+ .rpm = 0,
+ .ctrl_val = 3,
+ }, {
+ .rpm = 1500,
+ .ctrl_val = 2,
+ }, {
+ .rpm = 3250,
+ .ctrl_val = 1,
+ }, {
+ .rpm = 5000,
+ .ctrl_val = 0,
+ },
+};
+
+static int lschl_gpio_list[] = {
+ LSCHL_GPIO_FAN_HIGH, LSCHL_GPIO_FAN_LOW,
+};
+
+static struct gpio_fan_platform_data lschl_fan_data = {
+ .num_ctrl = ARRAY_SIZE(lschl_gpio_list),
+ .ctrl = lschl_gpio_list,
+ .alarm = &lschl_alarm,
+ .num_speed = ARRAY_SIZE(lschl_speeds),
+ .speed = lschl_speeds,
+};
+
+static struct platform_device lschl_fan_device = {
+ .name = "gpio-fan",
+ .id = -1,
+ .num_resources = 0,
+ .dev = {
+ .platform_data = &lschl_fan_data,
+ },
+};
+
+/****************************************************************************
+ * GPIO Data
+ ****************************************************************************/
+
+static struct orion5x_mpp_mode lschl_mpp_modes[] __initdata = {
+ { 0, MPP_GPIO }, /* LED POWER */
+ { 1, MPP_GPIO }, /* HDD POWER */
+ { 2, MPP_GPIO }, /* LED ALARM */
+ { 3, MPP_GPIO }, /* LED INFO */
+ { 4, MPP_UNUSED },
+ { 5, MPP_UNUSED },
+ { 6, MPP_GPIO }, /* FAN LOCK */
+ { 7, MPP_GPIO }, /* SW INIT */
+ { 8, MPP_GPIO }, /* SW POWER */
+ { 9, MPP_GPIO }, /* USB POWER */
+ { 10, MPP_GPIO }, /* SW AUTO POWER */
+ { 11, MPP_UNUSED },
+ { 12, MPP_UNUSED },
+ { 13, MPP_UNUSED },
+ { 14, MPP_GPIO }, /* FAN HIGH */
+ { 15, MPP_GPIO }, /* SW FUNC */
+ { 16, MPP_GPIO }, /* FAN LOW */
+ { 17, MPP_GPIO }, /* LED FUNC */
+ { 18, MPP_UNUSED },
+ { 19, MPP_UNUSED },
+ { -1 },
+};
+
+static void __init lschl_init(void)
+{
+ /*
+ * Setup basic Orion functions. Needs to be called early.
+ */
+ orion5x_init();
+
+ orion5x_mpp_conf(lschl_mpp_modes);
+
+ /*
+ * Configure peripherals.
+ */
+ orion5x_ehci0_init();
+ orion5x_ehci1_init();
+ orion5x_eth_init(&lschl_eth_data);
+ orion5x_i2c_init();
+ orion5x_sata_init(&lschl_sata_data);
+ orion5x_uart0_init();
+ orion5x_xor_init();
+
+ orion5x_setup_dev_boot_win(LSCHL_NOR_BOOT_BASE,
+ LSCHL_NOR_BOOT_SIZE);
+ platform_device_register(&lschl_nor_flash);
+
+ platform_device_register(&lschl_leds);
+
+ platform_device_register(&lschl_button_device);
+
+ platform_device_register(&lschl_fan_device);
+
+ i2c_register_board_info(0, &lschl_i2c_rtc, 1);
+
+ /* usb power on */
+ gpio_set_value(LSCHL_GPIO_USB_POWER, 1);
+
+ /* register power-off method */
+ pm_power_off = lschl_power_off;
+
+ pr_info("%s: finished\n", __func__);
+}
+
+MACHINE_START(LINKSTATION_LSCHL, "Buffalo Linkstation LiveV3 (LS-CHL)")
+ /* Maintainer: Ash Hughes <ashley.hughes@blueyonder.co.uk> */
+ .boot_params = 0x00000100,
+ .init_machine = lschl_init,
+ .map_io = orion5x_map_io,
+ .init_irq = orion5x_init_irq,
+ .timer = &orion5x_timer,
+ .fixup = tag_fixup_mem32,
+MACHINE_END
*/
#include <linux/cnt32_to_63.h>
#include <linux/io.h>
+#include <linux/sched.h>
#include <asm/div64.h>
#include <mach/hardware.h>