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>
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 @@
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 @@
unsigned long size;
void *addr;
int page;
- int nmi;
int sample;
};
@@ -993,7 +992,7 @@
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 @@
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 __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_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_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 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_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) { }