lkml.org 
[lkml]   [2015]   [May]   [22]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
From
Subject[PATCH v1 0/7] perf/x86/intel/pt: Fixes and cleanups
Date
Hi Peter and Ingo,

I'm resending the previously posted PT fixes along with two more that I
produced since. One new fix (1/7) is for the perf ring buffer code to make
sure user only gets a single chunk high-order allocation for overwrite mode
on PMUs that don't support hardware scatter lists, such as some versions
of Intel PT.

Another not-entirely-trivial patch (3/7) fixes an issue with multientry
ToPA PT implementations that causes bigger data loss than it actually has
to be, which was due to stop and interrupt markers being misplaced in the
buffer, preventing a timely consumer wakeup.

The rest of the patches are trivial fixes or documentation updates.

These are against tip/perf/urgent.

Alexander Shishkin (7):
perf: Disallow sparse AUX allocations for non-SG PMUs in overwrite
mode
perf/x86/intel/pt: Kill an unused variable
perf/x86/intel/pt: Untangle pt_buffer_reset_markers()
perf/x86/intel/pt: Document pt_buffer_reset_markers()
perf/x86/intel/pt: Document pt_buffer_reset_offsets()
perf/x86/intel/pt: Kill pt_is_running()
perf/x86/intel/pt: Remove an extra variable declaration

arch/x86/kernel/cpu/perf_event_intel_pt.c | 72 ++++++++++++++++++-------------
kernel/events/ring_buffer.c | 14 ++++++
2 files changed, 55 insertions(+), 31 deletions(-)

--
2.1.4



\
 
 \ /
  Last update: 2015-05-22 17:41    [W:0.046 / U:0.280 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site