Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (123 commits)
  perf: Remove the nmi parameter from the oprofile_perf backend
  x86, perf: Make copy_from_user_nmi() a library function
  perf: Remove perf_event_attr::type check
  x86, perf: P4 PMU - Fix typos in comments and style cleanup
  perf tools: Make test use the preset debugfs path
  perf tools: Add automated tests for events parsing
  perf tools: De-opt the parse_events function
  perf script: Fix display of IP address for non-callchain path
  perf tools: Fix endian conversion reading event attr from file header
  perf tools: Add missing 'node' alias to the hw_cache[] array
  perf probe: Support adding probes on offline kernel modules
  perf probe: Add probed module in front of function
  perf probe: Introduce debuginfo to encapsulate dwarf information
  perf-probe: Move dwarf library routines to dwarf-aux.{c, h}
  perf probe: Remove redundant dwarf functions
  perf probe: Move strtailcmp to string.c
  perf probe: Rename DIE_FIND_CB_FOUND to DIE_FIND_CB_END
  tracing/kprobe: Update symbol reference when loading module
  tracing/kprobes: Support module init function probing
  kprobes: Return -ENOENT if probe point doesn't exist
  ...

Documentation/trace/kprobetrace.txt

@@ -22,14 +22,15 @@ current_tracer. Instead of that, add probe points via
 
 Synopsis of kprobe_events
 -------------------------
-  p[:[GRP/]EVENT] SYMBOL[+offs]|MEMADDR [FETCHARGS]	: Set a probe
-  r[:[GRP/]EVENT] SYMBOL[+0] [FETCHARGS]		: Set a return probe
+  p[:[GRP/]EVENT] [MOD:]SYM[+offs]|MEMADDR [FETCHARGS]	: Set a probe
+  r[:[GRP/]EVENT] [MOD:]SYM[+0] [FETCHARGS]		: Set a return probe
   -:[GRP/]EVENT						: Clear a probe
 
  GRP		: Group name. If omitted, use "kprobes" for it.
  EVENT		: Event name. If omitted, the event name is generated
-		  based on SYMBOL+offs or MEMADDR.
- SYMBOL[+offs]	: Symbol+offset where the probe is inserted.
+		  based on SYM+offs or MEMADDR.
+ MOD		: Module name which has given SYM.
+ SYM[+offs]	: Symbol+offset where the probe is inserted.
  MEMADDR	: Address where the probe is inserted.
 
  FETCHARGS	: Arguments. Each probe can have up to 128 args.

Makefile

@@ -1290,6 +1290,7 @@ help:
 	@echo  '  make O=dir [targets] Locate all output files in "dir", including .config'
 	@echo  '  make C=1   [targets] Check all c source with $$CHECK (sparse by default)'
 	@echo  '  make C=2   [targets] Force check of all c source with $$CHECK'
+	@echo  '  make RECORDMCOUNT_WARN=1 [targets] Warn about ignored mcount sections'
 	@echo  '  make W=n   [targets] Enable extra gcc checks, n=1,2,3 where'
 	@echo  '		1: warnings which may be relevant and do not occur too often'
 	@echo  '		2: warnings which occur quite often but may still be relevant'

arch/alpha/kernel/perf_event.c

@@ -847,7 +847,7 @@ static void alpha_perf_event_irq_handler(unsigned long la_ptr,
 	data.period = event->hw.last_period;
 
 	if (alpha_perf_event_set_period(event, hwc, idx)) {
-		if (perf_event_overflow(event, 1, &data, regs)) {
+		if (perf_event_overflow(event, &data, regs)) {
 			/* Interrupts coming too quickly; "throttle" the
 			 * counter, i.e., disable it for a little while.
 			 */

arch/alpha/kernel/time.c

@@ -91,7 +91,7 @@ DEFINE_PER_CPU(u8, irq_work_pending);
 #define test_irq_work_pending()      __get_cpu_var(irq_work_pending)
 #define clear_irq_work_pending()     __get_cpu_var(irq_work_pending) = 0
 
-void set_irq_work_pending(void)
+void arch_irq_work_raise(void)
 {
 	set_irq_work_pending_flag();
 }

arch/arm/kernel/perf_event_v6.c

@@ -173,6 +173,20 @@ static const unsigned armv6_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
 		},
 	},
+	[C(NODE)] = {
+		[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 {
@@ -310,6 +324,20 @@ static const unsigned armv6mpcore_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
 		},
 	},
+	[C(NODE)] = {
+		[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
@@ -479,7 +507,7 @@ armv6pmu_handle_irq(int irq_num,
 		if (!armpmu_event_set_period(event, hwc, idx))
 			continue;
 
-		if (perf_event_overflow(event, 0, &data, regs))
+		if (perf_event_overflow(event, &data, regs))
 			armpmu->disable(hwc, idx);
 	}
 

arch/arm/kernel/perf_event_v7.c

@@ -255,6 +255,20 @@ static const unsigned armv7_a8_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
 		},
 	},
+	[C(NODE)] = {
+		[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,
+		},
+	},
 };
 
 /*
@@ -371,6 +385,20 @@ static const unsigned armv7_a9_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
 		},
 	},
+	[C(NODE)] = {
+		[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,
+		},
+	},
 };
 
 /*
@@ -787,7 +815,7 @@ static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev)
 		if (!armpmu_event_set_period(event, hwc, idx))
 			continue;
 
-		if (perf_event_overflow(event, 0, &data, regs))
+		if (perf_event_overflow(event, &data, regs))
 			armpmu->disable(hwc, idx);
 	}
 

arch/arm/kernel/perf_event_xscale.c

@@ -144,6 +144,20 @@ static const unsigned xscale_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
 		},
 	},
+	[C(NODE)] = {
+		[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
@@ -251,7 +265,7 @@ xscale1pmu_handle_irq(int irq_num, void *dev)
 		if (!armpmu_event_set_period(event, hwc, idx))
 			continue;
 
-		if (perf_event_overflow(event, 0, &data, regs))
+		if (perf_event_overflow(event, &data, regs))
 			armpmu->disable(hwc, idx);
 	}
 
@@ -583,7 +597,7 @@ xscale2pmu_handle_irq(int irq_num, void *dev)
 		if (!armpmu_event_set_period(event, hwc, idx))
 			continue;
 
-		if (perf_event_overflow(event, 0, &data, regs))
+		if (perf_event_overflow(event, &data, regs))
 			armpmu->disable(hwc, idx);
 	}
 

arch/arm/kernel/ptrace.c

@@ -396,7 +396,7 @@ static long ptrace_hbp_idx_to_num(int idx)
 /*
  * Handle hitting a HW-breakpoint.
  */
-static void ptrace_hbptriggered(struct perf_event *bp, int unused,
+static void ptrace_hbptriggered(struct perf_event *bp,
 				     struct perf_sample_data *data,
 				     struct pt_regs *regs)
 {
@@ -479,7 +479,8 @@ static struct perf_event *ptrace_hbp_create(struct task_struct *tsk, int type)
 	attr.bp_type	= type;
 	attr.disabled	= 1;
 
-	return register_user_hw_breakpoint(&attr, ptrace_hbptriggered, tsk);
+	return register_user_hw_breakpoint(&attr, ptrace_hbptriggered, NULL,
+					   tsk);
 }
 
 static int ptrace_gethbpregs(struct task_struct *tsk, long num,

arch/arm/kernel/swp_emulate.c

@@ -183,7 +183,7 @@ static int swp_handler(struct pt_regs *regs, unsigned int instr)
 	unsigned int address, destreg, data, type;
 	unsigned int res = 0;
 
-	perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, 0, regs, regs->ARM_pc);
+	perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, regs, regs->ARM_pc);
 
 	if (current->pid != previous_pid) {
 		pr_debug("\"%s\" (%ld) uses deprecated SWP{B} instruction\n",

arch/arm/mm/fault.c

@@ -318,11 +318,11 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	fault = __do_page_fault(mm, addr, fsr, tsk);
 	up_read(&mm->mmap_sem);
 
-	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, 0, regs, addr);
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);
 	if (fault & VM_FAULT_MAJOR)
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, 0, regs, addr);
+		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, addr);
 	else if (fault & VM_FAULT_MINOR)
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, 0, regs, addr);
+		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, addr);
 
 	/*
 	 * Handle the "normal" case first - VM_FAULT_MAJOR / VM_FAULT_MINOR

arch/mips/include/asm/stacktrace.h

@@ -7,6 +7,10 @@
 extern int raw_show_trace;
 extern unsigned long unwind_stack(struct task_struct *task, unsigned long *sp,
 				  unsigned long pc, unsigned long *ra);
+extern unsigned long unwind_stack_by_address(unsigned long stack_page,
+					     unsigned long *sp,
+					     unsigned long pc,
+					     unsigned long *ra);
 #else
 #define raw_show_trace 1
 static inline unsigned long unwind_stack(struct task_struct *task,

arch/mips/kernel/perf_event.c

@@ -527,7 +527,7 @@ handle_associated_event(struct cpu_hw_events *cpuc,
 	if (!mipspmu_event_set_period(event, hwc, idx))
 		return;
 
-	if (perf_event_overflow(event, 0, data, regs))
+	if (perf_event_overflow(event, data, regs))
 		mipspmu->disable_event(idx);
 }
 

arch/mips/kernel/perf_event_mipsxx.c

@@ -377,6 +377,20 @@ static const struct mips_perf_event mipsxxcore_cache_map
 		[C(RESULT_MISS)]	= { UNSUPPORTED_PERF_EVENT_ID },
 	},
 },
+[C(NODE)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)]	= { UNSUPPORTED_PERF_EVENT_ID },
+		[C(RESULT_MISS)]	= { UNSUPPORTED_PERF_EVENT_ID },
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)]	= { UNSUPPORTED_PERF_EVENT_ID },
+		[C(RESULT_MISS)]	= { UNSUPPORTED_PERF_EVENT_ID },
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)]	= { UNSUPPORTED_PERF_EVENT_ID },
+		[C(RESULT_MISS)]	= { UNSUPPORTED_PERF_EVENT_ID },
+	},
+},
 };
 
 /* 74K core has completely different cache event map. */
@@ -480,6 +494,20 @@ static const struct mips_perf_event mipsxx74Kcore_cache_map
 		[C(RESULT_MISS)]	= { UNSUPPORTED_PERF_EVENT_ID },
 	},
 },
+[C(NODE)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)]	= { UNSUPPORTED_PERF_EVENT_ID },
+		[C(RESULT_MISS)]	= { UNSUPPORTED_PERF_EVENT_ID },
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)]	= { UNSUPPORTED_PERF_EVENT_ID },
+		[C(RESULT_MISS)]	= { UNSUPPORTED_PERF_EVENT_ID },
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)]	= { UNSUPPORTED_PERF_EVENT_ID },
+		[C(RESULT_MISS)]	= { UNSUPPORTED_PERF_EVENT_ID },
+	},
+},
 };
 
 #ifdef CONFIG_MIPS_MT_SMP

arch/mips/kernel/process.c

@@ -373,18 +373,18 @@ unsigned long thread_saved_pc(struct task_struct *tsk)
 
 
 #ifdef CONFIG_KALLSYMS
-/* used by show_backtrace() */
-unsigned long unwind_stack(struct task_struct *task, unsigned long *sp,
-			   unsigned long pc, unsigned long *ra)
+/* generic stack unwinding function */
+unsigned long notrace unwind_stack_by_address(unsigned long stack_page,
+					      unsigned long *sp,
+					      unsigned long pc,
+					      unsigned long *ra)
 {
-	unsigned long stack_page;
 	struct mips_frame_info info;
 	unsigned long size, ofs;
 	int leaf;
 	extern void ret_from_irq(void);
 	extern void ret_from_exception(void);
 
-	stack_page = (unsigned long)task_stack_page(task);
 	if (!stack_page)
 		return 0;
 
@@ -443,6 +443,15 @@ unsigned long unwind_stack(struct task_struct *task, unsigned long *sp,
 	*ra = 0;
 	return __kernel_text_address(pc) ? pc : 0;
 }
+EXPORT_SYMBOL(unwind_stack_by_address);
+
+/* used by show_backtrace() */
+unsigned long unwind_stack(struct task_struct *task, unsigned long *sp,
+			   unsigned long pc, unsigned long *ra)
+{
+	unsigned long stack_page = (unsigned long)task_stack_page(task);
+	return unwind_stack_by_address(stack_page, sp, pc, ra);
+}
 #endif
 
 /*

arch/mips/kernel/traps.c

@@ -578,12 +578,12 @@ static int simulate_llsc(struct pt_regs *regs, unsigned int opcode)
 {
 	if ((opcode & OPCODE) == LL) {
 		perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS,
-				1, 0, regs, 0);
+				1, regs, 0);
 		return simulate_ll(regs, opcode);
 	}
 	if ((opcode & OPCODE) == SC) {
 		perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS,
-				1, 0, regs, 0);
+				1, regs, 0);
 		return simulate_sc(regs, opcode);
 	}
 
@@ -602,7 +602,7 @@ static int simulate_rdhwr(struct pt_regs *regs, unsigned int opcode)
 		int rd = (opcode & RD) >> 11;
 		int rt = (opcode & RT) >> 16;
 		perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS,
-				1, 0, regs, 0);
+				1, regs, 0);
 		switch (rd) {
 		case 0:		/* CPU number */
 			regs->regs[rt] = smp_processor_id();
@@ -640,7 +640,7 @@ static int simulate_sync(struct pt_regs *regs, unsigned int opcode)
 {
 	if ((opcode & OPCODE) == SPEC0 && (opcode & FUNC) == SYNC) {
 		perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS,
-				1, 0, regs, 0);
+				1, regs, 0);
 		return 0;
 	}
 

arch/mips/kernel/unaligned.c

@@ -111,8 +111,7 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 	unsigned long value;
 	unsigned int res;
 
-	perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS,
-		      1, 0, regs, 0);
+	perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, regs, 0);
 
 	/*
 	 * This load never faults.
@@ -517,7 +516,7 @@ asmlinkage void do_ade(struct pt_regs *regs)
 	mm_segment_t seg;
 
 	perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS,
-			1, 0, regs, regs->cp0_badvaddr);
+			1, regs, regs->cp0_badvaddr);
 	/*
 	 * Did we catch a fault trying to load an instruction?
 	 * Or are we running in MIPS16 mode?

arch/mips/math-emu/cp1emu.c

@@ -272,8 +272,7 @@ static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 	}
 
       emul:
-	perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS,
-			1, 0, xcp, 0);
+	perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, xcp, 0);
 	MIPS_FPU_EMU_INC_STATS(emulated);
 	switch (MIPSInst_OPCODE(ir)) {
 	case ldc1_op:{

arch/mips/mm/fault.c

@@ -145,7 +145,7 @@ good_area:
 	 * the fault.
 	 */
 	fault = handle_mm_fault(mm, vma, address, write ? FAULT_FLAG_WRITE : 0);
-	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, 0, regs, address);
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
@@ -154,12 +154,10 @@ good_area:
 		BUG();
 	}
 	if (fault & VM_FAULT_MAJOR) {
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ,
-				1, 0, regs, address);
+		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address);
 		tsk->maj_flt++;
 	} else {
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN,
-				1, 0, regs, address);
+		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address);
 		tsk->min_flt++;
 	}
 

arch/mips/oprofile/Makefile

@@ -8,7 +8,7 @@ DRIVER_OBJS = $(addprefix ../../../drivers/oprofile/, \
 		oprofilefs.o oprofile_stats.o \
 		timer_int.o )
 
-oprofile-y				:= $(DRIVER_OBJS) common.o
+oprofile-y				:= $(DRIVER_OBJS) common.o backtrace.o
 
 oprofile-$(CONFIG_CPU_MIPS32)		+= op_model_mipsxx.o
 oprofile-$(CONFIG_CPU_MIPS64)		+= op_model_mipsxx.o

arch/mips/oprofile/backtrace.c

@@ -0,0 +1,175 @@
+#include <linux/oprofile.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/uaccess.h>
+#include <asm/ptrace.h>
+#include <asm/stacktrace.h>
+#include <linux/stacktrace.h>
+#include <linux/kernel.h>
+#include <asm/sections.h>
+#include <asm/inst.h>
+
+struct stackframe {
+	unsigned long sp;
+	unsigned long pc;
+	unsigned long ra;
+};
+
+static inline int get_mem(unsigned long addr, unsigned long *result)
+{
+	unsigned long *address = (unsigned long *) addr;
+	if (!access_ok(VERIFY_READ, addr, sizeof(unsigned long)))
+		return -1;
+	if (__copy_from_user_inatomic(result, address, sizeof(unsigned long)))
+		return -3;
+	return 0;
+}
+
+/*
+ * These two instruction helpers were taken from process.c
+ */
+static inline int is_ra_save_ins(union mips_instruction *ip)
+{
+	/* sw / sd $ra, offset($sp) */
+	return (ip->i_format.opcode == sw_op || ip->i_format.opcode == sd_op)
+		&& ip->i_format.rs == 29 && ip->i_format.rt == 31;
+}
+
+static inline int is_sp_move_ins(union mips_instruction *ip)
+{
+	/* addiu/daddiu sp,sp,-imm */
+	if (ip->i_format.rs != 29 || ip->i_format.rt != 29)
+		return 0;
+	if (ip->i_format.opcode == addiu_op || ip->i_format.opcode == daddiu_op)
+		return 1;
+	return 0;
+}
+
+/*
+ * Looks for specific instructions that mark the end of a function.
+ * This usually means we ran into the code area of the previous function.
+ */
+static inline int is_end_of_function_marker(union mips_instruction *ip)
+{
+	/* jr ra */
+	if (ip->r_format.func == jr_op && ip->r_format.rs == 31)
+		return 1;
+	/* lui gp */
+	if (ip->i_format.opcode == lui_op && ip->i_format.rt == 28)
+		return 1;
+	return 0;
+}
+
+/*
+ * TODO for userspace stack unwinding:
+ * - handle cases where the stack is adjusted inside a function
+ *     (generally doesn't happen)
+ * - find optimal value for max_instr_check
+ * - try to find a way to handle leaf functions
+ */
+
+static inline int unwind_user_frame(struct stackframe *old_frame,
+				    const unsigned int max_instr_check)
+{
+	struct stackframe new_frame = *old_frame;
+	off_t ra_offset = 0;
+	size_t stack_size = 0;
+	unsigned long addr;
+
+	if (old_frame->pc == 0 || old_frame->sp == 0 || old_frame->ra == 0)
+		return -9;
+
+	for (addr = new_frame.pc; (addr + max_instr_check > new_frame.pc)
+		&& (!ra_offset || !stack_size); --addr) {
+		union mips_instruction ip;
+
+		if (get_mem(addr, (unsigned long *) &ip))
+			return -11;
+
+		if (is_sp_move_ins(&ip)) {
+			int stack_adjustment = ip.i_format.simmediate;
+			if (stack_adjustment > 0)
+				/* This marks the end of the previous function,
+				   which means we overran. */
+				break;
+			stack_size = (unsigned) stack_adjustment;
+		} else if (is_ra_save_ins(&ip)) {
+			int ra_slot = ip.i_format.simmediate;
+			if (ra_slot < 0)
+				/* This shouldn't happen. */
+				break;
+			ra_offset = ra_slot;
+		} else if (is_end_of_function_marker(&ip))
+			break;
+	}
+
+	if (!ra_offset || !stack_size)
+		return -1;
+
+	if (ra_offset) {
+		new_frame.ra = old_frame->sp + ra_offset;
+		if (get_mem(new_frame.ra, &(new_frame.ra)))
+			return -13;
+	}
+
+	if (stack_size) {
+		new_frame.sp = old_frame->sp + stack_size;
+		if (get_mem(new_frame.sp, &(new_frame.sp)))
+			return -14;
+	}
+
+	if (new_frame.sp > old_frame->sp)
+		return -2;
+
+	new_frame.pc = old_frame->ra;
+	*old_frame = new_frame;
+
+	return 0;
+}
+
+static inline void do_user_backtrace(unsigned long low_addr,
+				     struct stackframe *frame,
+				     unsigned int depth)
+{
+	const unsigned int max_instr_check = 512;
+	const unsigned long high_addr = low_addr + THREAD_SIZE;
+
+	while (depth-- && !unwind_user_frame(frame, max_instr_check)) {
+		oprofile_add_trace(frame->ra);
+		if (frame->sp < low_addr || frame->sp > high_addr)
+			break;
+	}
+}
+
+#ifndef CONFIG_KALLSYMS
+static inline void do_kernel_backtrace(unsigned long low_addr,
+				       struct stackframe *frame,
+				       unsigned int depth) { }
+#else
+static inline void do_kernel_backtrace(unsigned long low_addr,
+				       struct stackframe *frame,
+				       unsigned int depth)
+{
+	while (depth-- && frame->pc) {
+		frame->pc = unwind_stack_by_address(low_addr,
+						    &(frame->sp),
+						    frame->pc,
+						    &(frame->ra));
+		oprofile_add_trace(frame->ra);
+	}
+}
+#endif
+
+void notrace op_mips_backtrace(struct pt_regs *const regs, unsigned int depth)
+{
+	struct stackframe frame = { .sp = regs->regs[29],
+				    .pc = regs->cp0_epc,
+				    .ra = regs->regs[31] };
+	const int userspace = user_mode(regs);
+	const unsigned long low_addr = ALIGN(frame.sp, THREAD_SIZE);
+
+	if (userspace)
+		do_user_backtrace(low_addr, &frame, depth);
+	else
+		do_kernel_backtrace(low_addr, &frame, depth);
+}