perf: Remove the nmi parameter from the swevent and overflow interface

The nmi parameter indicated if we could do wakeups from the current
context, if not, we would set some state and self-IPI and let the
resulting interrupt do the wakeup.

For the various event classes:

  - hardware: nmi=0; PMI is in fact an NMI or we run irq_work_run from
    the PMI-tail (ARM etc.)
  - tracepoint: nmi=0; since tracepoint could be from NMI context.
  - software: nmi=[0,1]; some, like the schedule thing cannot
    perform wakeups, and hence need 0.

As one can see, there is very little nmi=1 usage, and the down-side of
not using it is that on some platforms some software events can have a
jiffy delay in wakeup (when arch_irq_work_raise isn't implemented).

The up-side however is that we can remove the nmi parameter and save a
bunch of conditionals in fast paths.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Michael Cree <mcree@orcon.net.nz>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Deng-Cheng Zhu <dengcheng.zhu@gmail.com>
Cc: Anton Blanchard <anton@samba.org>
Cc: Eric B Munson <emunson@mgebm.net>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: David S. Miller <davem@davemloft.net>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jason Wessel <jason.wessel@windriver.com>
Cc: Don Zickus <dzickus@redhat.com>
Link: http://lkml.kernel.org/n/tip-agjev8eu666tvknpb3iaj0fg@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>

46 files changed, 119 insertions, 141 deletions

diff --git a/arch/alpha/kernel/perf_event.c b/arch/alpha/kernel/perf_event.c
index 90561c4..8e47709 100644
--- a/arch/alpha/kernel/perf_event.c
+++ b/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.
 			 */
diff --git a/arch/arm/kernel/perf_event_v6.c b/arch/arm/kernel/perf_event_v6.c
index f1e8dd9..38dc4da 100644
--- a/arch/arm/kernel/perf_event_v6.c
+++ b/arch/arm/kernel/perf_event_v6.c
@@ -479,7 +479,7 @@ 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);
 	}
 
diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index 4960686..6e5f875 100644
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -787,7 +787,7 @@ 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);
 	}
 
diff --git a/arch/arm/kernel/perf_event_xscale.c b/arch/arm/kernel/perf_event_xscale.c
index 39affbe..99b6b85 100644
--- a/arch/arm/kernel/perf_event_xscale.c
+++ b/arch/arm/kernel/perf_event_xscale.c
@@ -251,7 +251,7 @@ 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 +583,7 @@ 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);
 	}
 
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index 9726006..0c9b105 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/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)
 {
diff --git a/arch/arm/kernel/swp_emulate.c b/arch/arm/kernel/swp_emulate.c
index 40ee7e5..5f452f8 100644
--- a/arch/arm/kernel/swp_emulate.c
+++ b/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",
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index bc0e1d8..9ea4f7d 100644
--- a/arch/arm/mm/fault.c
+++ b/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
diff --git a/arch/mips/kernel/perf_event.c b/arch/mips/kernel/perf_event.c
index a824485..d0deaab 100644
--- a/arch/mips/kernel/perf_event.c
+++ b/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);
 }
 
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index e9b3af2..b7517e3 100644
--- a/arch/mips/kernel/traps.c
+++ b/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;
 	}
 
diff --git a/arch/mips/kernel/unaligned.c b/arch/mips/kernel/unaligned.c
index cfea1ad..eb319b5 100644
--- a/arch/mips/kernel/unaligned.c
+++ b/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?
diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c
index d32cb05..dbf2f93 100644
--- a/arch/mips/math-emu/cp1emu.c
+++ b/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:{
diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c
index 137ee76..937cf33 100644
--- a/arch/mips/mm/fault.c
+++ b/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++;
 	}
 
diff --git a/arch/powerpc/include/asm/emulated_ops.h b/arch/powerpc/include/asm/emulated_ops.h
index 4592167..2cc41c7 100644
--- a/arch/powerpc/include/asm/emulated_ops.h
+++ b/arch/powerpc/include/asm/emulated_ops.h
@@ -78,14 +78,14 @@ extern void ppc_warn_emulated_print(const char *type);
 #define PPC_WARN_EMULATED(type, regs)					\
 	do {								\
 		perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS,		\
-			1, 0, regs, 0);					\
+			1, regs, 0);					\
 		__PPC_WARN_EMULATED(type);				\
 	} while (0)
 
 #define PPC_WARN_ALIGNMENT(type, regs)					\
 	do {								\
 		perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS,		\
-			1, 0, regs, regs->dar);				\
+			1, regs, regs->dar);				\
 		__PPC_WARN_EMULATED(type);				\
 	} while (0)
 
diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/kernel/perf_event.c
index 822f630..14967de 100644
--- a/arch/powerpc/kernel/perf_event.c
+++ b/arch/powerpc/kernel/perf_event.c
@@ -1207,7 +1207,7 @@ struct pmu power_pmu = {
  * here so there is no possibility of being interrupted.
  */
 static void record_and_restart(struct perf_event *event, unsigned long val,
-			       struct pt_regs *regs, int nmi)
+			       struct pt_regs *regs)
 {
 	u64 period = event->hw.sample_period;
 	s64 prev, delta, left;
@@ -1258,7 +1258,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 		if (event->attr.sample_type & PERF_SAMPLE_ADDR)
 			perf_get_data_addr(regs, &data.addr);
 
-		if (perf_event_overflow(event, nmi, &data, regs))
+		if (perf_event_overflow(event, &data, regs))
 			power_pmu_stop(event, 0);
 	}
 }
@@ -1346,7 +1346,7 @@ static void perf_event_interrupt(struct pt_regs *regs)
 		if ((int)val < 0) {
 			/* event has overflowed */
 			found = 1;
-			record_and_restart(event, val, regs, nmi);
+			record_and_restart(event, val, regs);
 		}
 	}
 
diff --git a/arch/powerpc/kernel/perf_event_fsl_emb.c b/arch/powerpc/kernel/perf_event_fsl_emb.c
index b0dc8f7..0a6d2a9 100644
--- a/arch/powerpc/kernel/perf_event_fsl_emb.c
+++ b/arch/powerpc/kernel/perf_event_fsl_emb.c
@@ -568,7 +568,7 @@ static struct pmu fsl_emb_pmu = {
  * here so there is no possibility of being interrupted.
  */
 static void record_and_restart(struct perf_event *event, unsigned long val,
-			       struct pt_regs *regs, int nmi)
+			       struct pt_regs *regs)
 {
 	u64 period = event->hw.sample_period;
 	s64 prev, delta, left;
@@ -616,7 +616,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 		perf_sample_data_init(&data, 0);
 		data.period = event->hw.last_period;
 
-		if (perf_event_overflow(event, nmi, &data, regs))
+		if (perf_event_overflow(event, &data, regs))
 			fsl_emb_pmu_stop(event, 0);
 	}
 }
@@ -644,7 +644,7 @@ static void perf_event_interrupt(struct pt_regs *regs)
 			if (event) {
 				/* event has overflowed */
 				found = 1;
-				record_and_restart(event, val, regs, nmi);
+				record_and_restart(event, val, regs);
 			} else {
 				/*
 				 * Disabled counter is negative,
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index cb22024..3177617 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -882,7 +882,7 @@ void user_disable_single_step(struct task_struct *task)
 }
 
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
-void ptrace_triggered(struct perf_event *bp, int nmi,
+void ptrace_triggered(struct perf_event *bp,
 		      struct perf_sample_data *data, struct pt_regs *regs)
 {
 	struct perf_event_attr attr;
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 54f4fb9..dbc4825 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -173,7 +173,7 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
 		die("Weird page fault", regs, SIGSEGV);
 	}
 
-	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, 0, regs, address);
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
 
 	/* When running in the kernel we expect faults to occur only to
 	 * addresses in user space.  All other faults represent errors in the
@@ -319,7 +319,7 @@ good_area:
 	}
 	if (ret & VM_FAULT_MAJOR) {
 		current->maj_flt++;
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, 0,
+		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1,
 				     regs, address);
 #ifdef CONFIG_PPC_SMLPAR
 		if (firmware_has_feature(FW_FEATURE_CMO)) {
@@ -330,7 +330,7 @@ good_area:
 #endif
 	} else {
 		current->min_flt++;
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, 0,
+		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1,
 				     regs, address);
 	}
 	up_read(&mm->mmap_sem);
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index fe103e8..095f782 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -299,7 +299,7 @@ static inline int do_exception(struct pt_regs *regs, int access,
 		goto out;
 
 	address = trans_exc_code & __FAIL_ADDR_MASK;
-	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, 0, regs, address);
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
 	flags = FAULT_FLAG_ALLOW_RETRY;
 	if (access == VM_WRITE || (trans_exc_code & store_indication) == 0x400)
 		flags |= FAULT_FLAG_WRITE;
@@ -345,11 +345,11 @@ retry:
 	if (flags & FAULT_FLAG_ALLOW_RETRY) {
 		if (fault & VM_FAULT_MAJOR) {
 			tsk->maj_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, 0,
+			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1,
 				      regs, address);
 		} else {
 			tsk->min_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, 0,
+			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1,
 				      regs, address);
 		}
 		if (fault & VM_FAULT_RETRY) {
diff --git a/arch/sh/kernel/ptrace_32.c b/arch/sh/kernel/ptrace_32.c
index 3d7b209..8051976 100644
--- a/arch/sh/kernel/ptrace_32.c
+++ b/arch/sh/kernel/ptrace_32.c
@@ -63,7 +63,7 @@ static inline int put_stack_long(struct task_struct *task, int offset,
 	return 0;
 }
 
-void ptrace_triggered(struct perf_event *bp, int nmi,
+void ptrace_triggered(struct perf_event *bp,
 		      struct perf_sample_data *data, struct pt_regs *regs)
 {
 	struct perf_event_attr attr;
diff --git a/arch/sh/kernel/traps_32.c b/arch/sh/kernel/traps_32.c
index b51a171..d9006f8 100644
--- a/arch/sh/kernel/traps_32.c
+++ b/arch/sh/kernel/traps_32.c
@@ -393,7 +393,7 @@ int handle_unaligned_access(insn_size_t instruction, struct pt_regs *regs,
 	 */
 	if (!expected) {
 		unaligned_fixups_notify(current, instruction, regs);
-		perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, 0,
+		perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1,
 			      regs, address);
 	}
 
diff --git a/arch/sh/kernel/traps_64.c b/arch/sh/kernel/traps_64.c
index 6713ca9..67110be 100644
--- a/arch/sh/kernel/traps_64.c
+++ b/arch/sh/kernel/traps_64.c
@@ -434,7 +434,7 @@ static int misaligned_load(struct pt_regs *regs,
 		return error;
 	}
 
-	perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, 0, regs, address);
+	perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, address);
 
 	destreg = (opcode >> 4) & 0x3f;
 	if (user_mode(regs)) {
@@ -512,7 +512,7 @@ static int misaligned_store(struct pt_regs *regs,
 		return error;
 	}
 
-	perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, 0, regs, address);
+	perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, address);
 
 	srcreg = (opcode >> 4) & 0x3f;
 	if (user_mode(regs)) {
@@ -588,7 +588,7 @@ static int misaligned_fpu_load(struct pt_regs *regs,
 		return error;
 	}
 
-	perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, 0, regs, address);
+	perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, regs, address);
 
 	destreg = (opcode >> 4) & 0x3f;
 	if (user_mode(regs)) {
@@ -665,7 +665,7 @@ static int misaligned_fpu_store(struct pt_regs *regs,
 		return error;
 	}
 
-	perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, 0, regs, address);
+	perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, regs, address);
 
 	srcreg = (opcode >> 4) & 0x3f;
 	if (user_mode(regs)) {
diff --git a/arch/sh/math-emu/math.c b/arch/sh/math-emu/math.c
index f76a509..9771952 100644
--- a/arch/sh/math-emu/math.c
+++ b/arch/sh/math-emu/math.c
@@ -620,7 +620,7 @@ int do_fpu_inst(unsigned short inst, struct pt_regs *regs)
 	struct task_struct *tsk = current;
 	struct sh_fpu_soft_struct *fpu = &(tsk->thread.xstate->softfpu);
 
-	perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, 0, regs, 0);
+	perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, regs, 0);
 
 	if (!(task_thread_info(tsk)->status & TS_USEDFPU)) {
 		/* initialize once. */
diff --git a/arch/sh/mm/fault_32.c b/arch/sh/mm/fault_32.c
index d4c34d7..7bebd04 100644
--- a/arch/sh/mm/fault_32.c
+++ b/arch/sh/mm/fault_32.c
@@ -160,7 +160,7 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
 	if ((regs->sr & SR_IMASK) != SR_IMASK)
 		local_irq_enable();
 
-	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, 0, regs, address);
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
 
 	/*
 	 * If we're in an interrupt, have no user context or are running
@@ -210,11 +210,11 @@ good_area:
 	}
 	if (fault & VM_FAULT_MAJOR) {
 		tsk->maj_flt++;
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, 0,
+		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1,
 				     regs, address);
 	} else {
 		tsk->min_flt++;
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, 0,
+		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1,
 				     regs, address);
 	}
 
diff --git a/arch/sh/mm/tlbflush_64.c b/arch/sh/mm/tlbflush_64.c
index 7f5810f..e3430e0 100644
--- a/arch/sh/mm/tlbflush_64.c
+++ b/arch/sh/mm/tlbflush_64.c
@@ -116,7 +116,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long writeaccess,
 	/* Not an IO address, so reenable interrupts */
 	local_irq_enable();
 
-	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, 0, regs, address);
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
 
 	/*
 	 * If we're in an interrupt or have no user
@@ -200,11 +200,11 @@ good_area:
 
 	if (fault & VM_FAULT_MAJOR) {
 		tsk->maj_flt++;
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, 0,
+		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1,
 				     regs, address);
 	} else {
 		tsk->min_flt++;
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, 0,
+		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1,
 				     regs, address);
 	}
 
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index 2cb0e1c..0b32f2e 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -1277,7 +1277,7 @@ static int __kprobes perf_event_nmi_handler(struct notifier_block *self,
 		if (!sparc_perf_event_set_period(event, hwc, idx))
 			continue;
 
-		if (perf_event_overflow(event, 1, &data, regs))
+		if (perf_event_overflow(event, &data, regs))
 			sparc_pmu_stop(event, 0);
 	}
 
diff --git a/arch/sparc/kernel/unaligned_32.c b/arch/sparc/kernel/unaligned_32.c
index 4491f4c..7efbb2f 100644
--- a/arch/sparc/kernel/unaligned_32.c
+++ b/arch/sparc/kernel/unaligned_32.c
@@ -247,7 +247,7 @@ asmlinkage void kernel_unaligned_trap(struct pt_regs *regs, unsigned int insn)
 		unsigned long addr = compute_effective_address(regs, insn);
 		int err;
 
-		perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, 0, regs, addr);
+		perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, addr);
 		switch (dir) {
 		case load:
 			err = do_int_load(fetch_reg_addr(((insn>>25)&0x1f),
@@ -338,7 +338,7 @@ asmlinkage void user_unaligned_trap(struct pt_regs *regs, unsigned int insn)
 		}
 
 		addr = compute_effective_address(regs, insn);
-		perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, 0, regs, addr);
+		perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, addr);
 		switch(dir) {
 		case load:
 			err = do_int_load(fetch_reg_addr(((insn>>25)&0x1f),
diff --git a/arch/sparc/kernel/unaligned_64.c b/arch/sparc/kernel/unaligned_64.c
index b2b019e..35cff16 100644
--- a/arch/sparc/kernel/unaligned_64.c
+++ b/arch/sparc/kernel/unaligned_64.c
@@ -317,7 +317,7 @@ asmlinkage void kernel_unaligned_trap(struct pt_regs *regs, unsigned int insn)
 
 		addr = compute_effective_address(regs, insn,
 						 ((insn >> 25) & 0x1f));
-		perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, 0, regs, addr);
+		perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, addr);
 		switch (asi) {
 		case ASI_NL:
 		case ASI_AIUPL:
@@ -384,7 +384,7 @@ int handle_popc(u32 insn, struct pt_regs *regs)
 	int ret, i, rd = ((insn >> 25) & 0x1f);
 	int from_kernel = (regs->tstate & TSTATE_PRIV) != 0;
 	                        
-	perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, 0, regs, 0);
+	perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, regs, 0);
 	if (insn & 0x2000) {
 		maybe_flush_windows(0, 0, rd, from_kernel);
 		value = sign_extend_imm13(insn);
@@ -431,7 +431,7 @@ int handle_ldf_stq(u32 insn, struct pt_regs *regs)
 	int asi = decode_asi(insn, regs);
 	int flag = (freg < 32) ? FPRS_DL : FPRS_DU;
 
-	perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, 0, regs, 0);
+	perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, regs, 0);
 
 	save_and_clear_fpu();
 	current_thread_info()->xfsr[0] &= ~0x1c000;
@@ -554,7 +554,7 @@ void handle_ld_nf(u32 insn, struct pt_regs *regs)
 	int from_kernel = (regs->tstate & TSTATE_PRIV) != 0;
 	unsigned long *reg;
 	                        
-	perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, 0, regs, 0);
+	perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, regs, 0);
 
 	maybe_flush_windows(0, 0, rd, from_kernel);
 	reg = fetch_reg_addr(rd, regs);
@@ -586,7 +586,7 @@ void handle_lddfmna(struct pt_regs *regs, unsigned long sfar, unsigned long sfsr
 
 	if (tstate & TSTATE_PRIV)
 		die_if_kernel("lddfmna from kernel", regs);
-	perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, 0, regs, sfar);
+	perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, sfar);
 	if (test_thread_flag(TIF_32BIT))
 		pc = (u32)pc;
 	if (get_user(insn, (u32 __user *) pc) != -EFAULT) {
@@ -647,7 +647,7 @@ void handle_stdfmna(struct pt_regs *regs, unsigned long sfar, unsigned long sfsr
 
 	if (tstate & TSTATE_PRIV)
 		die_if_kernel("stdfmna from kernel", regs);
-	perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, 0, regs, sfar);
+	perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, sfar);
 	if (test_thread_flag(TIF_32BIT))
 		pc = (u32)pc;
 	if (get_user(insn, (u32 __user *) pc) != -EFAULT) {
diff --git a/arch/sparc/kernel/visemul.c b/arch/sparc/kernel/visemul.c
index 3635771..32b626c 100644
--- a/arch/sparc/kernel/visemul.c
+++ b/arch/sparc/kernel/visemul.c
@@ -802,7 +802,7 @@ int vis_emul(struct pt_regs *regs, unsigned int insn)
 
 	BUG_ON(regs->tstate & TSTATE_PRIV);
 
-	perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, 0, regs, 0);
+	perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, regs, 0);
 
 	if (test_thread_flag(TIF_32BIT))
 		pc = (u32)pc;
diff --git a/arch/sparc/math-emu/math_32.c b/arch/sparc/math-emu/math_32.c
index a3fccde..aa4d55b 100644
--- a/arch/sparc/math-emu/math_32.c
+++ b/arch/sparc/math-emu/math_32.c
@@ -164,7 +164,7 @@ int do_mathemu(struct pt_regs *regs, struct task_struct *fpt)
 	int retcode = 0;                               /* assume all succeed */
 	unsigned long insn;
 
-	perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, 0, regs, 0);
+	perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, regs, 0);
 
 #ifdef DEBUG_MATHEMU
 	printk("In do_mathemu()... pc is %08lx\n", regs->pc);
diff --git a/arch/sparc/math-emu/math_64.c b/arch/sparc/math-emu/math_64.c
index 56d2c44..e575bd2 100644
--- a/arch/sparc/math-emu/math_64.c
+++ b/arch/sparc/math-emu/math_64.c
@@ -184,7 +184,7 @@ int do_mathemu(struct pt_regs *regs, struct fpustate *f)
 
 	if (tstate & TSTATE_PRIV)
 		die_if_kernel("unfinished/unimplemented FPop from kernel", regs);
-	perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, 0, regs, 0);
+	perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, regs, 0);
 	if (test_thread_flag(TIF_32BIT))
 		pc = (u32)pc;
 	if (get_user(insn, (u32 __user *) pc) != -EFAULT) {
diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c
index 7543ddb..aa1c1b1 100644
--- a/arch/sparc/mm/fault_32.c
+++ b/arch/sparc/mm/fault_32.c
@@ -251,7 +251,7 @@ asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write,
         if (in_atomic() || !mm)
                 goto no_context;
 
-	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, 0, regs, address);
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
 
 	down_read(&mm->mmap_sem);
 
@@ -301,12 +301,10 @@ good_area:
 	}
 	if (fault & VM_FAULT_MAJOR) {
 		current->maj_flt++;
-		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);
 	} else {
 		current->min_flt++;
-		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);
 	}
 	up_read(&mm->mmap_sem);
 	return;
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index f92ce56..504c062 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -325,7 +325,7 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs)
 	if (in_atomic() || !mm)
 		goto intr_or_no_mm;
 
-	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, 0, regs, address);
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
 
 	if (!down_read_trylock(&mm->mmap_sem)) {
 		if ((regs->tstate & TSTATE_PRIV) &&
@@ -433,12 +433,10 @@ good_area:
 	}
 	if (fault & VM_FAULT_MAJOR) {
 		current->maj_flt++;
-		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);
 	} else {
 		current->min_flt++;
-		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);
 	}
 	up_read(&mm->mmap_sem);
 
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 8a57f9a..5b86ec5 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1339,7 +1339,7 @@ static int x86_pmu_handle_irq(struct pt_regs *regs)
 		if (!x86_perf_event_set_period(event))
 			continue;
 
-		if (perf_event_overflow(event, 1, &data, regs))
+		if (perf_event_overflow(event, &data, regs))
 			x86_pmu_stop(event, 0);
 	}
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 41178c8..d38b002 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1003,7 +1003,7 @@ again:
 
 		data.period = event->hw.last_period;
 
-		if (perf_event_overflow(event, 1, &data, regs))
+		if (perf_event_overflow(event, &data, regs))
 			x86_pmu_stop(event, 0);
 	}
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index bab491b..0941f93 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -340,7 +340,7 @@ static int intel_pmu_drain_bts_buffer(void)
 	 */
 	perf_prepare_sample(&header, &data, event, &regs);
 
-	if (perf_output_begin(&handle, event, header.size * (top - at), 1, 1))
+	if (perf_output_begin(&handle, event, header.size * (top - at), 1))
 		return 1;
 
 	for (; at < top; at++) {
@@ -616,7 +616,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 	else
 		regs.flags &= ~PERF_EFLAGS_EXACT;
 
-	if (perf_event_overflow(event, 1, &data, &regs))
+	if (perf_event_overflow(event, &data, &regs))
 		x86_pmu_stop(event, 0);
 }
 
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index f76fddf..d6e6a67 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -970,7 +970,7 @@ static int p4_pmu_handle_irq(struct pt_regs *regs)
 
 		if (!x86_perf_event_set_period(event))
 			continue;
-		if (perf_event_overflow(event, 1, &data, regs))
+		if (perf_event_overflow(event, &data, regs))
 			x86_pmu_stop(event, 0);
 	}
 
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index 5f9ecff..98da6a7 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -608,7 +608,7 @@ int kgdb_arch_init(void)
 	return register_die_notifier(&kgdb_notifier);
 }
 
-static void kgdb_hw_overflow_handler(struct perf_event *event, int nmi,
+static void kgdb_hw_overflow_handler(struct perf_event *event,
 		struct perf_sample_data *data, struct pt_regs *regs)
 {
 	struct task_struct *tsk = current;
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 807c2a2..11db2e9 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -528,7 +528,7 @@ static int genregs_set(struct task_struct *target,
 	return ret;
 }
 
-static void ptrace_triggered(struct perf_event *bp, int nmi,
+static void ptrace_triggered(struct perf_event *bp,
 			     struct perf_sample_data *data,
 			     struct pt_regs *regs)
 {
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 2dbf6bf..4d09df0 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -1059,7 +1059,7 @@ do_page_fault(struct pt_regs *regs, unsigned long error_code)
 	if (unlikely(error_code & PF_RSVD))
 		pgtable_bad(regs, error_code, address);
 
-	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, 0, regs, address);
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
 
 	/*
 	 * If we're in an interrupt, have no user context or are running
@@ -1161,11 +1161,11 @@ good_area:
 	if (flags & FAULT_FLAG_ALLOW_RETRY) {
 		if (fault & VM_FAULT_MAJOR) {
 			tsk->maj_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, 0,
+			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1,
 				      regs, address);
 		} else {
 			tsk->min_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, 0,
+			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1,
 				      regs, address);
 		}
 		if (fault & VM_FAULT_RETRY) {
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 2f7b5d4..0946a8b 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -682,7 +682,7 @@ enum perf_event_active_state {
 struct file;
 struct perf_sample_data;
 
-typedef void (*perf_overflow_handler_t)(struct perf_event *, int,
+typedef void (*perf_overflow_handler_t)(struct perf_event *,
 					struct perf_sample_data *,
 					struct pt_regs *regs);
 
@@ -925,7 +925,6 @@ struct perf_output_handle {
 	unsigned long			size;
 	void				*addr;
 	int				page;
-	int				nmi;
 	int				sample;
 };
 
@@ -993,7 +992,7 @@ extern void perf_prepare_sample(struct perf_event_header *header,
 				struct perf_event *event,
 				struct pt_regs *regs);
 
-extern int perf_event_overflow(struct perf_event *event, int nmi,
+extern int perf_event_overflow(struct perf_event *event,
 				 struct perf_sample_data *data,
 				 struct pt_regs *regs);
 
@@ -1012,7 +1011,7 @@ static inline int is_software_event(struct perf_event *event)
 
 extern struct jump_label_key perf_swevent_enabled[PERF_COUNT_SW_MAX];
 
-extern void __perf_sw_event(u32, u64, int, struct pt_regs *, u64);
+extern void __perf_sw_event(u32, u64, struct pt_regs *, u64);
 
 #ifndef perf_arch_fetch_caller_regs
 static inline void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip) { }
@@ -1034,7 +1033,7 @@ static inline void perf_fetch_caller_regs(struct pt_regs *regs)
 }
 
 static __always_inline void
-perf_sw_event(u32 event_id, u64 nr, int nmi, struct pt_regs *regs, u64 addr)
+perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr)
 {
 	struct pt_regs hot_regs;
 
@@ -1043,7 +1042,7 @@ perf_sw_event(u32 event_id, u64 nr, int nmi, struct pt_regs *regs, u64 addr)
 			perf_fetch_caller_regs(&hot_regs);
 			regs = &hot_regs;
 		}
-		__perf_sw_event(event_id, nr, nmi, regs, addr);
+		__perf_sw_event(event_id, nr, regs, addr);
 	}
 }
 
@@ -1057,7 +1056,7 @@ static inline void perf_event_task_sched_in(struct task_struct *task)
 
 static inline void perf_event_task_sched_out(struct task_struct *task, struct task_struct *next)
 {
-	perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 1, NULL, 0);
+	perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, NULL, 0);
 
 	__perf_event_task_sched_out(task, next);
 }
@@ -1119,7 +1118,7 @@ extern void perf_bp_event(struct perf_event *event, void *data);
 
 extern int perf_output_begin(struct perf_output_handle *handle,
 			     struct perf_event *event, unsigned int size,
-			     int nmi, int sample);
+			     int sample);
 extern void perf_output_end(struct perf_output_handle *handle);
 extern void perf_output_copy(struct perf_output_handle *handle,
 			     const void *buf, unsigned int len);
@@ -1143,8 +1142,7 @@ static inline int perf_event_task_disable(void)				{ return -EINVAL; }
 static inline int perf_event_task_enable(void)				{ return -EINVAL; }
 
 static inline void
-perf_sw_event(u32 event_id, u64 nr, int nmi,
-		     struct pt_regs *regs, u64 addr)			{ }
+perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr)	{ }
 static inline void
 perf_bp_event(struct perf_event *event, void *data)			{ }
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 270e32f..dbd1ca7 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3972,7 +3972,7 @@ void perf_prepare_sample(struct perf_event_header *header,
 	}
 }
 
-static void perf_event_output(struct perf_event *event, int nmi,
+static void perf_event_output(struct perf_event *event,
 				struct perf_sample_data *data,
 				struct pt_regs *regs)
 {
@@ -3984,7 +3984,7 @@ static void perf_event_output(struct perf_event *event, int nmi,
 
 	perf_prepare_sample(&header, data, event, regs);
 
-	if (perf_output_begin(&handle, event, header.size, nmi, 1))
+	if (perf_output_begin(&handle, event, header.size, 1))
 		goto exit;
 
 	perf_output_sample(&handle, &header, data, event);
@@ -4024,7 +4024,7 @@ perf_event_read_event(struct perf_event *event,
 	int ret;
 
 	perf_event_header__init_id(&read_event.header, &sample, event);
-	ret = perf_output_begin(&handle, event, read_event.header.size, 0, 0);
+	ret = perf_output_begin(&handle, event, read_event.header.size, 0);
 	if (ret)
 		return;
 
@@ -4067,7 +4067,7 @@ static void perf_event_task_output(struct perf_event *event,
 	perf_event_header__init_id(&task_event->event_id.header, &sample, event);
 
 	ret = perf_output_begin(&handle, event,
-				task_event->event_id.header.size, 0, 0);
+				task_event->event_id.header.size, 0);
 	if (ret)
 		goto out;
 
@@ -4204,7 +4204,7 @@ static void perf_event_comm_output(struct perf_event *event,
 
 	perf_event_header__init_id(&comm_event->event_id.header, &sample, event);
 	ret = perf_output_begin(&handle, event,
-				comm_event->event_id.header.size, 0, 0);
+				comm_event->event_id.header.size, 0);
 
 	if (ret)
 		goto out;
@@ -4351,7 +4351,7 @@ static void perf_event_mmap_output(struct perf_event *event,
 
 	perf_event_header__init_id(&mmap_event->event_id.header, &sample, event);
 	ret = perf_output_begin(&handle, event,
-				mmap_event->event_id.header.size, 0, 0);
+				mmap_event->event_id.header.size, 0);
 	if (ret)
 		goto out;
 
@@ -4546,7 +4546,7 @@ static void perf_log_throttle(struct perf_event *event, int enable)
 	perf_event_header__init_id(&throttle_event.header, &sample, event);
 
 	ret = perf_output_begin(&handle, event,
-				throttle_event.header.size, 1, 0);
+				throttle_event.header.size, 0);
 	if (ret)
 		return;
 
@@ -4559,7 +4559,7 @@ static void perf_log_throttle(struct perf_event *event, int enable)
  * Generic event overflow handling, sampling.
  */
 
-static int __perf_event_overflow(struct perf_event *event, int nmi,
+static int __perf_event_overflow(struct perf_event *event,
 				   int throttle, struct perf_sample_data *data,
 				   struct pt_regs *regs)
 {
@@ -4602,34 +4602,28 @@ static int __perf_event_overflow(struct perf_event *event, int nmi,
 	if (events && atomic_dec_and_test(&event->event_limit)) {
 		ret = 1;
 		event->pending_kill = POLL_HUP;
-		if (nmi) {
-			event->pending_disable = 1;
-			irq_work_queue(&event->pending);
-		} else
-			perf_event_disable(event);
+		event->pending_disable = 1;
+		irq_work_queue(&event->pending);
 	}
 
 	if (event->overflow_handler)
-		event->overflow_handler(event, nmi, data, regs);
+		event->overflow_handler(event, data, regs);
 	else
-		perf_event_output(event, nmi, data, regs);
+		perf_event_output(event, data, regs);
 
 	if (event->fasync && event->pending_kill) {
-		if (nmi) {
-			event->pending_wakeup = 1;
-			irq_work_queue(&event->pending);
-		} else
-			perf_event_wakeup(event);
+		event->pending_wakeup = 1;
+		irq_work_queue(&event->pending);
 	}
 
 	return ret;
 }
 
-int perf_event_overflow(struct perf_event *event, int nmi,
+int perf_event_overflow(struct perf_event *event,
 			  struct perf_sample_data *data,
 			  struct pt_regs *regs)
 {
-	return __perf_event_overflow(event, nmi, 1, data, regs);
+	return __perf_event_overflow(event, 1, data, regs);
 }
 
 /*
@@ -4678,7 +4672,7 @@ again:
 }
 
 static void perf_swevent_overflow(struct perf_event *event, u64 overflow,
-				    int nmi, struct perf_sample_data *data,
+				    struct perf_sample_data *data,
 				    struct pt_regs *regs)
 {
 	struct hw_perf_event *hwc = &event->hw;
@@ -4692,7 +4686,7 @@ static void perf_swevent_overflow(struct perf_event *event, u64 overflow,
 		return;
 
 	for (; overflow; overflow--) {
-		if (__perf_event_overflow(event, nmi, throttle,
+		if (__perf_event_overflow(event, throttle,
 					    data, regs)) {
 			/*
 			 * We inhibit the overflow from happening when
@@ -4705,7 +4699,7 @@ static void perf_swevent_overflow(struct perf_event *event, u64 overflow,
 }
 
 static void perf_swevent_event(struct perf_event *event, u64 nr,
-			       int nmi, struct perf_sample_data *data,
+			       struct perf_sample_data *data,
 			       struct pt_regs *regs)
 {
 	struct hw_perf_event *hwc = &event->hw;
@@ -4719,12 +4713,12 @@ static void perf_swevent_event(struct perf_event *event, u64 nr,
 		return;
 
 	if (nr == 1 && hwc->sample_period == 1 && !event->attr.freq)
-		return perf_swevent_overflow(event, 1, nmi, data, regs);
+		return perf_swevent_overflow(event, 1, data, regs);
 
 	if (local64_add_negative(nr, &hwc->period_left))
 		return;
 
-	perf_swevent_overflow(event, 0, nmi, data, regs);
+	perf_swevent_overflow(event, 0, data, regs);
 }
 
 static int perf_exclude_event(struct perf_event *event,
@@ -4812,7 +4806,7 @@ find_swevent_head(struct swevent_htable *swhash, struct perf_event *event)
 }
 
 static void do_perf_sw_event(enum perf_type_id type, u32 event_id,
-				    u64 nr, int nmi,
+				    u64 nr,
 				    struct perf_sample_data *data,
 				    struct pt_regs *regs)
 {
@@ -4828,7 +4822,7 @@ static void do_perf_sw_event(enum perf_type_id type, u32 event_id,
 
 	hlist_for_each_entry_rcu(event, node, head, hlist_entry) {
 		if (perf_swevent_match(event, type, event_id, data, regs))
-			perf_swevent_event(event, nr, nmi, data, regs);
+			perf_swevent_event(event, nr, data, regs);
 	}
 end:
 	rcu_read_unlock();
@@ -4849,8 +4843,7 @@ inline void perf_swevent_put_recursion_context(int rctx)
 	put_recursion_context(swhash->recursion, rctx);
 }
 
-void __perf_sw_event(u32 event_id, u64 nr, int nmi,
-			    struct pt_regs *regs, u64 addr)
+void __perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr)
 {
 	struct perf_sample_data data;
 	int rctx;
@@ -4862,7 +4855,7 @@ void __perf_sw_event(u32 event_id, u64 nr, int nmi,
 
 	perf_sample_data_init(&data, addr);
 
-	do_perf_sw_event(PERF_TYPE_SOFTWARE, event_id, nr, nmi, &data, regs);
+	do_perf_sw_event(PERF_TYPE_SOFTWARE, event_id, nr, &data, regs);
 
 	perf_swevent_put_recursion_context(rctx);
 	preempt_enable_notrace();
@@ -5110,7 +5103,7 @@ void perf_tp_event(u64 addr, u64 count, void *record, int entry_size,
 
 	hlist_for_each_entry_rcu(event, node, head, hlist_entry) {
 		if (perf_tp_event_match(event, &data, regs))
-			perf_swevent_event(event, count, 1, &data, regs);
+			perf_swevent_event(event, count, &data, regs);
 	}
 
 	perf_swevent_put_recursion_context(rctx);
@@ -5203,7 +5196,7 @@ void perf_bp_event(struct perf_event *bp, void *data)
 	perf_sample_data_init(&sample, bp->attr.bp_addr);
 
 	if (!bp->hw.state && !perf_exclude_event(bp, regs))
-		perf_swevent_event(bp, 1, 1, &sample, regs);
+		perf_swevent_event(bp, 1, &sample, regs);
 }
 #endif
 
@@ -5232,7 +5225,7 @@ static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer)
 
 	if (regs && !perf_exclude_event(event, regs)) {
 		if (!(event->attr.exclude_idle && current->pid == 0))
-			if (perf_event_overflow(event, 0, &data, regs))
+			if (perf_event_overflow(event, &data, regs))
 				ret = HRTIMER_NORESTART;
 	}
 
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index 114f27f..09097dd 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -27,7 +27,6 @@ struct ring_buffer {
 	void				*data_pages[0];
 };
 
-
 extern void rb_free(struct ring_buffer *rb);
 extern struct ring_buffer *
 rb_alloc(int nr_pages, long watermark, int cpu, int flags);
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index fc2701c..8b3b736 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -38,11 +38,8 @@ static void perf_output_wakeup(struct perf_output_handle *handle)
 {
 	atomic_set(&handle->rb->poll, POLL_IN);
 
-	if (handle->nmi) {
-		handle->event->pending_wakeup = 1;
-		irq_work_queue(&handle->event->pending);
-	} else
-		perf_event_wakeup(handle->event);
+	handle->event->pending_wakeup = 1;
+	irq_work_queue(&handle->event->pending);
 }
 
 /*
@@ -102,7 +99,7 @@ out:
 
 int perf_output_begin(struct perf_output_handle *handle,
 		      struct perf_event *event, unsigned int size,
-		      int nmi, int sample)
+		      int sample)
 {
 	struct ring_buffer *rb;
 	unsigned long tail, offset, head;
@@ -127,7 +124,6 @@ int perf_output_begin(struct perf_output_handle *handle,
 
 	handle->rb	= rb;
 	handle->event	= event;
-	handle->nmi	= nmi;
 	handle->sample	= sample;
 
 	if (!rb->nr_pages)
diff --git a/kernel/sched.c b/kernel/sched.c
index 3f2e502..d08d110 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -2220,7 +2220,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 
 	if (task_cpu(p) != new_cpu) {
 		p->se.nr_migrations++;
-		perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 1, NULL, 0);
+		perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS, 1, NULL, 0);
 	}
 
 	__set_task_cpu(p, new_cpu);
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 752b75b..a6708e67 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -211,7 +211,7 @@ static struct perf_event_attr wd_hw_attr = {
 };
 
 /* Callback function for perf event subsystem */
-static void watchdog_overflow_callback(struct perf_event *event, int nmi,
+static void watchdog_overflow_callback(struct perf_event *event,
 		 struct perf_sample_data *data,
 		 struct pt_regs *regs)
 {
diff --git a/samples/hw_breakpoint/data_breakpoint.c b/samples/hw_breakpoint/data_breakpoint.c
index 0636539..7b164d3 100644
--- a/samples/hw_breakpoint/data_breakpoint.c
+++ b/samples/hw_breakpoint/data_breakpoint.c
@@ -41,7 +41,7 @@ module_param_string(ksym, ksym_name, KSYM_NAME_LEN, S_IRUGO);
 MODULE_PARM_DESC(ksym, "Kernel symbol to monitor; this module will report any"
 			" write operations on the kernel symbol");
 
-static void sample_hbp_handler(struct perf_event *bp, int nmi,
+static void sample_hbp_handler(struct perf_event *bp,
 			       struct perf_sample_data *data,
 			       struct pt_regs *regs)
 {