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>

5 files changed, 11 insertions, 15 deletions

diff --git a/arch/mips/kernel/perf_event.c b/arch/mips/kernel/perf_event.c
index a8244854d3dc..d0deaab9ace2 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 e9b3af27d844..b7517e3abc85 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 cfea1adfa153..eb319b580353 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 d32cb0503110..dbf2f93a5091 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 137ee76a0045..937cf3368164 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++;
         }