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>

8 files changed, 18 insertions, 22 deletions

diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index 2cb0e1c001e2..0b32f2e9e08d 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 4491f4cb2695..7efbb2f9e77f 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 b2b019ea8caa..35cff1673aa4 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 36357717d691..32b626c9d815 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 a3fccde894ec..aa4d55b0bdf0 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 56d2c44747b8..e575bd2fe381 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 7543ddbdadb2..aa1c1b1ce5cc 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 f92ce56a8b22..504c0622f729 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);