mirros/rockchip-kernel
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

x86/tsc: Remodel cyc2ns to use seqcount_latch()

Browse Source 
Replace the custom multi-value scheme with the more regular
seqcount_latch() scheme. Along with scrapping a lot of lines, the latch
scheme is better documented and used in more places.

The immediate benefit however is not being limited on the update side.
The current code has a limit where the writers block which is hit by
future changes.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This commit is contained in:
Peter Zijlstra
2017-05-02 13:22:07 +02:00
committed by Ingo Molnar
parent 8309f86cd4
commit 59eaef78bf
4 changed files with 54 additions and 155 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
arch/x86/events/core.c
View File

@@ -2255,7 +2255,7 @@ static struct pmu pmu = {
void arch_perf_update_userpage(struct perf_event *event,
struct perf_event_mmap_page *userpg, u64 now)
{
struct cyc2ns_data *data;
struct cyc2ns_data data;
u64 offset;
userpg->cap_user_time = 0;
@@ -2267,17 +2267,17 @@ void arch_perf_update_userpage(struct perf_event *event,
if (!using_native_sched_clock() || !sched_clock_stable())
return;
data = cyc2ns_read_begin();
cyc2ns_read_begin(&data);
offset = data->cyc2ns_offset + __sched_clock_offset;
offset = data.cyc2ns_offset + __sched_clock_offset;
/*
* Internal timekeeping for enabled/running/stopped times
* is always in the local_clock domain.
*/
userpg->cap_user_time = 1;
userpg->time_mult = data->cyc2ns_mul;
userpg->time_shift = data->cyc2ns_shift;
userpg->time_mult = data.cyc2ns_mul;
userpg->time_shift = data.cyc2ns_shift;
userpg->time_offset = offset - now;
/*
@@ -2289,7 +2289,7 @@ void arch_perf_update_userpage(struct perf_event *event,
userpg->time_zero = offset;
}
cyc2ns_read_end(data);
cyc2ns_read_end();
}
void