mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-08 04:26:40 +07:00
5a0e3ad6af
percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
193 lines
4.9 KiB
C
193 lines
4.9 KiB
C
/*
|
|
* Copyright (C) 2009 Intel Corporation.
|
|
* Author: Patrick Ohly <patrick.ohly@intel.com>
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify
|
|
* it under the terms of the GNU General Public License as published by
|
|
* the Free Software Foundation; either version 2 of the License, or
|
|
* (at your option) any later version.
|
|
*
|
|
* This program is distributed in the hope that it will be useful,
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
* GNU General Public License for more details.
|
|
*
|
|
* You should have received a copy of the GNU General Public License
|
|
* along with this program; if not, write to the Free Software
|
|
* Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
|
*/
|
|
|
|
#include <linux/timecompare.h>
|
|
#include <linux/module.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/math64.h>
|
|
|
|
/*
|
|
* fixed point arithmetic scale factor for skew
|
|
*
|
|
* Usually one would measure skew in ppb (parts per billion, 1e9), but
|
|
* using a factor of 2 simplifies the math.
|
|
*/
|
|
#define TIMECOMPARE_SKEW_RESOLUTION (((s64)1)<<30)
|
|
|
|
ktime_t timecompare_transform(struct timecompare *sync,
|
|
u64 source_tstamp)
|
|
{
|
|
u64 nsec;
|
|
|
|
nsec = source_tstamp + sync->offset;
|
|
nsec += (s64)(source_tstamp - sync->last_update) * sync->skew /
|
|
TIMECOMPARE_SKEW_RESOLUTION;
|
|
|
|
return ns_to_ktime(nsec);
|
|
}
|
|
EXPORT_SYMBOL_GPL(timecompare_transform);
|
|
|
|
int timecompare_offset(struct timecompare *sync,
|
|
s64 *offset,
|
|
u64 *source_tstamp)
|
|
{
|
|
u64 start_source = 0, end_source = 0;
|
|
struct {
|
|
s64 offset;
|
|
s64 duration_target;
|
|
} buffer[10], sample, *samples;
|
|
int counter = 0, i;
|
|
int used;
|
|
int index;
|
|
int num_samples = sync->num_samples;
|
|
|
|
if (num_samples > sizeof(buffer)/sizeof(buffer[0])) {
|
|
samples = kmalloc(sizeof(*samples) * num_samples, GFP_ATOMIC);
|
|
if (!samples) {
|
|
samples = buffer;
|
|
num_samples = sizeof(buffer)/sizeof(buffer[0]);
|
|
}
|
|
} else {
|
|
samples = buffer;
|
|
}
|
|
|
|
/* run until we have enough valid samples, but do not try forever */
|
|
i = 0;
|
|
counter = 0;
|
|
while (1) {
|
|
u64 ts;
|
|
ktime_t start, end;
|
|
|
|
start = sync->target();
|
|
ts = timecounter_read(sync->source);
|
|
end = sync->target();
|
|
|
|
if (!i)
|
|
start_source = ts;
|
|
|
|
/* ignore negative durations */
|
|
sample.duration_target = ktime_to_ns(ktime_sub(end, start));
|
|
if (sample.duration_target >= 0) {
|
|
/*
|
|
* assume symetric delay to and from source:
|
|
* average target time corresponds to measured
|
|
* source time
|
|
*/
|
|
sample.offset =
|
|
(ktime_to_ns(end) + ktime_to_ns(start)) / 2 -
|
|
ts;
|
|
|
|
/* simple insertion sort based on duration */
|
|
index = counter - 1;
|
|
while (index >= 0) {
|
|
if (samples[index].duration_target <
|
|
sample.duration_target)
|
|
break;
|
|
samples[index + 1] = samples[index];
|
|
index--;
|
|
}
|
|
samples[index + 1] = sample;
|
|
counter++;
|
|
}
|
|
|
|
i++;
|
|
if (counter >= num_samples || i >= 100000) {
|
|
end_source = ts;
|
|
break;
|
|
}
|
|
}
|
|
|
|
*source_tstamp = (end_source + start_source) / 2;
|
|
|
|
/* remove outliers by only using 75% of the samples */
|
|
used = counter * 3 / 4;
|
|
if (!used)
|
|
used = counter;
|
|
if (used) {
|
|
/* calculate average */
|
|
s64 off = 0;
|
|
for (index = 0; index < used; index++)
|
|
off += samples[index].offset;
|
|
*offset = div_s64(off, used);
|
|
}
|
|
|
|
if (samples && samples != buffer)
|
|
kfree(samples);
|
|
|
|
return used;
|
|
}
|
|
EXPORT_SYMBOL_GPL(timecompare_offset);
|
|
|
|
void __timecompare_update(struct timecompare *sync,
|
|
u64 source_tstamp)
|
|
{
|
|
s64 offset;
|
|
u64 average_time;
|
|
|
|
if (!timecompare_offset(sync, &offset, &average_time))
|
|
return;
|
|
|
|
if (!sync->last_update) {
|
|
sync->last_update = average_time;
|
|
sync->offset = offset;
|
|
sync->skew = 0;
|
|
} else {
|
|
s64 delta_nsec = average_time - sync->last_update;
|
|
|
|
/* avoid division by negative or small deltas */
|
|
if (delta_nsec >= 10000) {
|
|
s64 delta_offset_nsec = offset - sync->offset;
|
|
s64 skew; /* delta_offset_nsec *
|
|
TIMECOMPARE_SKEW_RESOLUTION /
|
|
delta_nsec */
|
|
u64 divisor;
|
|
|
|
/* div_s64() is limited to 32 bit divisor */
|
|
skew = delta_offset_nsec * TIMECOMPARE_SKEW_RESOLUTION;
|
|
divisor = delta_nsec;
|
|
while (unlikely(divisor >= ((s64)1) << 32)) {
|
|
/* divide both by 2; beware, right shift
|
|
of negative value has undefined
|
|
behavior and can only be used for
|
|
the positive divisor */
|
|
skew = div_s64(skew, 2);
|
|
divisor >>= 1;
|
|
}
|
|
skew = div_s64(skew, divisor);
|
|
|
|
/*
|
|
* Calculate new overall skew as 4/16 the
|
|
* old value and 12/16 the new one. This is
|
|
* a rather arbitrary tradeoff between
|
|
* only using the latest measurement (0/16 and
|
|
* 16/16) and even more weight on past measurements.
|
|
*/
|
|
#define TIMECOMPARE_NEW_SKEW_PER_16 12
|
|
sync->skew =
|
|
div_s64((16 - TIMECOMPARE_NEW_SKEW_PER_16) *
|
|
sync->skew +
|
|
TIMECOMPARE_NEW_SKEW_PER_16 * skew,
|
|
16);
|
|
sync->last_update = average_time;
|
|
sync->offset = offset;
|
|
}
|
|
}
|
|
}
|
|
EXPORT_SYMBOL_GPL(__timecompare_update);
|