2019-05-29 01:10:25 +08:00
|
|
|
// SPDX-License-Identifier: GPL-2.0-only
|
vDSO for sparc
Following patch is based on work done by Nick Alcock on 64-bit vDSO for sparc
in Oracle linux. I have extended it to include support for 32-bit vDSO for sparc
on 64-bit kernel.
vDSO for sparc is based on the X86 implementation. This patch
provides vDSO support for both 64-bit and 32-bit programs on 64-bit kernel.
vDSO will be disabled on 32-bit linux kernel on sparc.
*) vclock_gettime.c contains all the vdso functions. Since data page is mapped
before the vdso code page, the pointer to data page is got by subracting offset
from an address in the vdso code page. The return address stored in
%i7 is used for this purpose.
*) During compilation, both 32-bit and 64-bit vdso images are compiled and are
converted into raw bytes by vdso2c program to be ready for mapping into the
process. 32-bit images are compiled only if CONFIG_COMPAT is enabled. vdso2c
generates two files vdso-image-64.c and vdso-image-32.c which contains the
respective vDSO image in C structure.
*) During vdso initialization, required number of vdso pages are allocated and
raw bytes are copied into the pages.
*) During every exec, these pages are mapped into the process through
arch_setup_additional_pages and the location of mapping is passed on to the
process through aux vector AT_SYSINFO_EHDR which is used by glibc.
*) A new update_vsyscall routine for sparc is added to keep the data page in
vdso updated.
*) As vDSO cannot contain dynamically relocatable references, a new version of
cpu_relax is added for the use of vDSO.
This change also requires a putback to glibc to use vDSO. For testing,
programs planning to try vDSO can be compiled against the generated
vdso(64/32).so in the source.
Testing:
========
[root@localhost ~]# cat vdso_test.c
int main() {
struct timespec tv_start, tv_end;
struct timeval tv_tmp;
int i;
int count = 1 * 1000 * 10000;
long long diff;
clock_gettime(0, &tv_start);
for (i = 0; i < count; i++)
gettimeofday(&tv_tmp, NULL);
clock_gettime(0, &tv_end);
diff = (long long)(tv_end.tv_sec -
tv_start.tv_sec)*(1*1000*1000*1000);
diff += (tv_end.tv_nsec - tv_start.tv_nsec);
printf("Start sec: %d\n", tv_start.tv_sec);
printf("End sec : %d\n", tv_end.tv_sec);
printf("%d cycles in %lld ns = %f ns/cycle\n", count, diff,
(double)diff / (double)count);
return 0;
}
[root@localhost ~]# cc vdso_test.c -o t32_without_fix -m32 -lrt
[root@localhost ~]# ./t32_without_fix
Start sec: 1502396130
End sec : 1502396140
10000000 cycles in 9565148528 ns = 956.514853 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t32_with_fix -m32 ./vdso32.so.dbg
[root@localhost ~]# ./t32_with_fix
Start sec: 1502396168
End sec : 1502396169
10000000 cycles in 798141262 ns = 79.814126 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t64_without_fix -m64 -lrt
[root@localhost ~]# ./t64_without_fix
Start sec: 1502396208
End sec : 1502396218
10000000 cycles in 9846091800 ns = 984.609180 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t64_with_fix -m64 ./vdso64.so.dbg
[root@localhost ~]# ./t64_with_fix
Start sec: 1502396257
End sec : 1502396257
10000000 cycles in 380984048 ns = 38.098405 ns/cycle
V1 to V2 Changes:
=================
Added hot patching code to switch the read stick instruction to read
tick instruction based on the hardware.
V2 to V3 Changes:
=================
Merged latest changes from sparc-next and moved the initialization
of clocksource_tick.archdata.vclock_mode to time_init_early. Disabled
queued spinlock and rwlock configuration when simulating 32-bit config
to compile 32-bit VDSO.
V3 to V4 Changes:
=================
Hardcoded the page size as 8192 in linker script for both 64-bit and
32-bit binaries. Removed unused variables in vdso2c.h. Added -mv8plus flag to
Makefile to prevent the generation of relocation entries for __lshrdi3 in 32-bit
vdso binary.
Signed-off-by: Nick Alcock <nick.alcock@oracle.com>
Signed-off-by: Nagarathnam Muthusamy <nagarathnam.muthusamy@oracle.com>
Reviewed-by: Shannon Nelson <shannon.nelson@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-21 23:05:31 +08:00
|
|
|
/*
|
|
|
|
* Copyright 2006 Andi Kleen, SUSE Labs.
|
|
|
|
*
|
|
|
|
* Fast user context implementation of clock_gettime, gettimeofday, and time.
|
|
|
|
*
|
|
|
|
* The code should have no internal unresolved relocations.
|
|
|
|
* Check with readelf after changing.
|
|
|
|
* Also alternative() doesn't work.
|
|
|
|
*/
|
|
|
|
/*
|
|
|
|
* Copyright (c) 2017 Oracle and/or its affiliates. All rights reserved.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include <linux/kernel.h>
|
|
|
|
#include <linux/time.h>
|
|
|
|
#include <linux/string.h>
|
|
|
|
#include <asm/io.h>
|
|
|
|
#include <asm/unistd.h>
|
|
|
|
#include <asm/timex.h>
|
|
|
|
#include <asm/clocksource.h>
|
|
|
|
#include <asm/vvar.h>
|
|
|
|
|
2018-10-18 12:28:01 +08:00
|
|
|
#ifdef CONFIG_SPARC64
|
vDSO for sparc
Following patch is based on work done by Nick Alcock on 64-bit vDSO for sparc
in Oracle linux. I have extended it to include support for 32-bit vDSO for sparc
on 64-bit kernel.
vDSO for sparc is based on the X86 implementation. This patch
provides vDSO support for both 64-bit and 32-bit programs on 64-bit kernel.
vDSO will be disabled on 32-bit linux kernel on sparc.
*) vclock_gettime.c contains all the vdso functions. Since data page is mapped
before the vdso code page, the pointer to data page is got by subracting offset
from an address in the vdso code page. The return address stored in
%i7 is used for this purpose.
*) During compilation, both 32-bit and 64-bit vdso images are compiled and are
converted into raw bytes by vdso2c program to be ready for mapping into the
process. 32-bit images are compiled only if CONFIG_COMPAT is enabled. vdso2c
generates two files vdso-image-64.c and vdso-image-32.c which contains the
respective vDSO image in C structure.
*) During vdso initialization, required number of vdso pages are allocated and
raw bytes are copied into the pages.
*) During every exec, these pages are mapped into the process through
arch_setup_additional_pages and the location of mapping is passed on to the
process through aux vector AT_SYSINFO_EHDR which is used by glibc.
*) A new update_vsyscall routine for sparc is added to keep the data page in
vdso updated.
*) As vDSO cannot contain dynamically relocatable references, a new version of
cpu_relax is added for the use of vDSO.
This change also requires a putback to glibc to use vDSO. For testing,
programs planning to try vDSO can be compiled against the generated
vdso(64/32).so in the source.
Testing:
========
[root@localhost ~]# cat vdso_test.c
int main() {
struct timespec tv_start, tv_end;
struct timeval tv_tmp;
int i;
int count = 1 * 1000 * 10000;
long long diff;
clock_gettime(0, &tv_start);
for (i = 0; i < count; i++)
gettimeofday(&tv_tmp, NULL);
clock_gettime(0, &tv_end);
diff = (long long)(tv_end.tv_sec -
tv_start.tv_sec)*(1*1000*1000*1000);
diff += (tv_end.tv_nsec - tv_start.tv_nsec);
printf("Start sec: %d\n", tv_start.tv_sec);
printf("End sec : %d\n", tv_end.tv_sec);
printf("%d cycles in %lld ns = %f ns/cycle\n", count, diff,
(double)diff / (double)count);
return 0;
}
[root@localhost ~]# cc vdso_test.c -o t32_without_fix -m32 -lrt
[root@localhost ~]# ./t32_without_fix
Start sec: 1502396130
End sec : 1502396140
10000000 cycles in 9565148528 ns = 956.514853 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t32_with_fix -m32 ./vdso32.so.dbg
[root@localhost ~]# ./t32_with_fix
Start sec: 1502396168
End sec : 1502396169
10000000 cycles in 798141262 ns = 79.814126 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t64_without_fix -m64 -lrt
[root@localhost ~]# ./t64_without_fix
Start sec: 1502396208
End sec : 1502396218
10000000 cycles in 9846091800 ns = 984.609180 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t64_with_fix -m64 ./vdso64.so.dbg
[root@localhost ~]# ./t64_with_fix
Start sec: 1502396257
End sec : 1502396257
10000000 cycles in 380984048 ns = 38.098405 ns/cycle
V1 to V2 Changes:
=================
Added hot patching code to switch the read stick instruction to read
tick instruction based on the hardware.
V2 to V3 Changes:
=================
Merged latest changes from sparc-next and moved the initialization
of clocksource_tick.archdata.vclock_mode to time_init_early. Disabled
queued spinlock and rwlock configuration when simulating 32-bit config
to compile 32-bit VDSO.
V3 to V4 Changes:
=================
Hardcoded the page size as 8192 in linker script for both 64-bit and
32-bit binaries. Removed unused variables in vdso2c.h. Added -mv8plus flag to
Makefile to prevent the generation of relocation entries for __lshrdi3 in 32-bit
vdso binary.
Signed-off-by: Nick Alcock <nick.alcock@oracle.com>
Signed-off-by: Nagarathnam Muthusamy <nagarathnam.muthusamy@oracle.com>
Reviewed-by: Shannon Nelson <shannon.nelson@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-21 23:05:31 +08:00
|
|
|
#define SYSCALL_STRING \
|
|
|
|
"ta 0x6d;" \
|
2018-10-18 12:28:01 +08:00
|
|
|
"bcs,a 1f;" \
|
|
|
|
" sub %%g0, %%o0, %%o0;" \
|
|
|
|
"1:"
|
|
|
|
#else
|
|
|
|
#define SYSCALL_STRING \
|
|
|
|
"ta 0x10;" \
|
|
|
|
"bcs,a 1f;" \
|
|
|
|
" sub %%g0, %%o0, %%o0;" \
|
|
|
|
"1:"
|
|
|
|
#endif
|
vDSO for sparc
Following patch is based on work done by Nick Alcock on 64-bit vDSO for sparc
in Oracle linux. I have extended it to include support for 32-bit vDSO for sparc
on 64-bit kernel.
vDSO for sparc is based on the X86 implementation. This patch
provides vDSO support for both 64-bit and 32-bit programs on 64-bit kernel.
vDSO will be disabled on 32-bit linux kernel on sparc.
*) vclock_gettime.c contains all the vdso functions. Since data page is mapped
before the vdso code page, the pointer to data page is got by subracting offset
from an address in the vdso code page. The return address stored in
%i7 is used for this purpose.
*) During compilation, both 32-bit and 64-bit vdso images are compiled and are
converted into raw bytes by vdso2c program to be ready for mapping into the
process. 32-bit images are compiled only if CONFIG_COMPAT is enabled. vdso2c
generates two files vdso-image-64.c and vdso-image-32.c which contains the
respective vDSO image in C structure.
*) During vdso initialization, required number of vdso pages are allocated and
raw bytes are copied into the pages.
*) During every exec, these pages are mapped into the process through
arch_setup_additional_pages and the location of mapping is passed on to the
process through aux vector AT_SYSINFO_EHDR which is used by glibc.
*) A new update_vsyscall routine for sparc is added to keep the data page in
vdso updated.
*) As vDSO cannot contain dynamically relocatable references, a new version of
cpu_relax is added for the use of vDSO.
This change also requires a putback to glibc to use vDSO. For testing,
programs planning to try vDSO can be compiled against the generated
vdso(64/32).so in the source.
Testing:
========
[root@localhost ~]# cat vdso_test.c
int main() {
struct timespec tv_start, tv_end;
struct timeval tv_tmp;
int i;
int count = 1 * 1000 * 10000;
long long diff;
clock_gettime(0, &tv_start);
for (i = 0; i < count; i++)
gettimeofday(&tv_tmp, NULL);
clock_gettime(0, &tv_end);
diff = (long long)(tv_end.tv_sec -
tv_start.tv_sec)*(1*1000*1000*1000);
diff += (tv_end.tv_nsec - tv_start.tv_nsec);
printf("Start sec: %d\n", tv_start.tv_sec);
printf("End sec : %d\n", tv_end.tv_sec);
printf("%d cycles in %lld ns = %f ns/cycle\n", count, diff,
(double)diff / (double)count);
return 0;
}
[root@localhost ~]# cc vdso_test.c -o t32_without_fix -m32 -lrt
[root@localhost ~]# ./t32_without_fix
Start sec: 1502396130
End sec : 1502396140
10000000 cycles in 9565148528 ns = 956.514853 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t32_with_fix -m32 ./vdso32.so.dbg
[root@localhost ~]# ./t32_with_fix
Start sec: 1502396168
End sec : 1502396169
10000000 cycles in 798141262 ns = 79.814126 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t64_without_fix -m64 -lrt
[root@localhost ~]# ./t64_without_fix
Start sec: 1502396208
End sec : 1502396218
10000000 cycles in 9846091800 ns = 984.609180 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t64_with_fix -m64 ./vdso64.so.dbg
[root@localhost ~]# ./t64_with_fix
Start sec: 1502396257
End sec : 1502396257
10000000 cycles in 380984048 ns = 38.098405 ns/cycle
V1 to V2 Changes:
=================
Added hot patching code to switch the read stick instruction to read
tick instruction based on the hardware.
V2 to V3 Changes:
=================
Merged latest changes from sparc-next and moved the initialization
of clocksource_tick.archdata.vclock_mode to time_init_early. Disabled
queued spinlock and rwlock configuration when simulating 32-bit config
to compile 32-bit VDSO.
V3 to V4 Changes:
=================
Hardcoded the page size as 8192 in linker script for both 64-bit and
32-bit binaries. Removed unused variables in vdso2c.h. Added -mv8plus flag to
Makefile to prevent the generation of relocation entries for __lshrdi3 in 32-bit
vdso binary.
Signed-off-by: Nick Alcock <nick.alcock@oracle.com>
Signed-off-by: Nagarathnam Muthusamy <nagarathnam.muthusamy@oracle.com>
Reviewed-by: Shannon Nelson <shannon.nelson@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-21 23:05:31 +08:00
|
|
|
|
|
|
|
#define SYSCALL_CLOBBERS \
|
|
|
|
"f0", "f1", "f2", "f3", "f4", "f5", "f6", "f7", \
|
|
|
|
"f8", "f9", "f10", "f11", "f12", "f13", "f14", "f15", \
|
|
|
|
"f16", "f17", "f18", "f19", "f20", "f21", "f22", "f23", \
|
|
|
|
"f24", "f25", "f26", "f27", "f28", "f29", "f30", "f31", \
|
|
|
|
"f32", "f34", "f36", "f38", "f40", "f42", "f44", "f46", \
|
|
|
|
"f48", "f50", "f52", "f54", "f56", "f58", "f60", "f62", \
|
|
|
|
"cc", "memory"
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Compute the vvar page's address in the process address space, and return it
|
|
|
|
* as a pointer to the vvar_data.
|
|
|
|
*/
|
2018-10-22 13:09:40 +08:00
|
|
|
notrace static __always_inline struct vvar_data *get_vvar_data(void)
|
vDSO for sparc
Following patch is based on work done by Nick Alcock on 64-bit vDSO for sparc
in Oracle linux. I have extended it to include support for 32-bit vDSO for sparc
on 64-bit kernel.
vDSO for sparc is based on the X86 implementation. This patch
provides vDSO support for both 64-bit and 32-bit programs on 64-bit kernel.
vDSO will be disabled on 32-bit linux kernel on sparc.
*) vclock_gettime.c contains all the vdso functions. Since data page is mapped
before the vdso code page, the pointer to data page is got by subracting offset
from an address in the vdso code page. The return address stored in
%i7 is used for this purpose.
*) During compilation, both 32-bit and 64-bit vdso images are compiled and are
converted into raw bytes by vdso2c program to be ready for mapping into the
process. 32-bit images are compiled only if CONFIG_COMPAT is enabled. vdso2c
generates two files vdso-image-64.c and vdso-image-32.c which contains the
respective vDSO image in C structure.
*) During vdso initialization, required number of vdso pages are allocated and
raw bytes are copied into the pages.
*) During every exec, these pages are mapped into the process through
arch_setup_additional_pages and the location of mapping is passed on to the
process through aux vector AT_SYSINFO_EHDR which is used by glibc.
*) A new update_vsyscall routine for sparc is added to keep the data page in
vdso updated.
*) As vDSO cannot contain dynamically relocatable references, a new version of
cpu_relax is added for the use of vDSO.
This change also requires a putback to glibc to use vDSO. For testing,
programs planning to try vDSO can be compiled against the generated
vdso(64/32).so in the source.
Testing:
========
[root@localhost ~]# cat vdso_test.c
int main() {
struct timespec tv_start, tv_end;
struct timeval tv_tmp;
int i;
int count = 1 * 1000 * 10000;
long long diff;
clock_gettime(0, &tv_start);
for (i = 0; i < count; i++)
gettimeofday(&tv_tmp, NULL);
clock_gettime(0, &tv_end);
diff = (long long)(tv_end.tv_sec -
tv_start.tv_sec)*(1*1000*1000*1000);
diff += (tv_end.tv_nsec - tv_start.tv_nsec);
printf("Start sec: %d\n", tv_start.tv_sec);
printf("End sec : %d\n", tv_end.tv_sec);
printf("%d cycles in %lld ns = %f ns/cycle\n", count, diff,
(double)diff / (double)count);
return 0;
}
[root@localhost ~]# cc vdso_test.c -o t32_without_fix -m32 -lrt
[root@localhost ~]# ./t32_without_fix
Start sec: 1502396130
End sec : 1502396140
10000000 cycles in 9565148528 ns = 956.514853 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t32_with_fix -m32 ./vdso32.so.dbg
[root@localhost ~]# ./t32_with_fix
Start sec: 1502396168
End sec : 1502396169
10000000 cycles in 798141262 ns = 79.814126 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t64_without_fix -m64 -lrt
[root@localhost ~]# ./t64_without_fix
Start sec: 1502396208
End sec : 1502396218
10000000 cycles in 9846091800 ns = 984.609180 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t64_with_fix -m64 ./vdso64.so.dbg
[root@localhost ~]# ./t64_with_fix
Start sec: 1502396257
End sec : 1502396257
10000000 cycles in 380984048 ns = 38.098405 ns/cycle
V1 to V2 Changes:
=================
Added hot patching code to switch the read stick instruction to read
tick instruction based on the hardware.
V2 to V3 Changes:
=================
Merged latest changes from sparc-next and moved the initialization
of clocksource_tick.archdata.vclock_mode to time_init_early. Disabled
queued spinlock and rwlock configuration when simulating 32-bit config
to compile 32-bit VDSO.
V3 to V4 Changes:
=================
Hardcoded the page size as 8192 in linker script for both 64-bit and
32-bit binaries. Removed unused variables in vdso2c.h. Added -mv8plus flag to
Makefile to prevent the generation of relocation entries for __lshrdi3 in 32-bit
vdso binary.
Signed-off-by: Nick Alcock <nick.alcock@oracle.com>
Signed-off-by: Nagarathnam Muthusamy <nagarathnam.muthusamy@oracle.com>
Reviewed-by: Shannon Nelson <shannon.nelson@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-21 23:05:31 +08:00
|
|
|
{
|
|
|
|
unsigned long ret;
|
|
|
|
|
|
|
|
/*
|
2018-10-22 13:09:40 +08:00
|
|
|
* vdso data page is the first vDSO page so grab the PC
|
vDSO for sparc
Following patch is based on work done by Nick Alcock on 64-bit vDSO for sparc
in Oracle linux. I have extended it to include support for 32-bit vDSO for sparc
on 64-bit kernel.
vDSO for sparc is based on the X86 implementation. This patch
provides vDSO support for both 64-bit and 32-bit programs on 64-bit kernel.
vDSO will be disabled on 32-bit linux kernel on sparc.
*) vclock_gettime.c contains all the vdso functions. Since data page is mapped
before the vdso code page, the pointer to data page is got by subracting offset
from an address in the vdso code page. The return address stored in
%i7 is used for this purpose.
*) During compilation, both 32-bit and 64-bit vdso images are compiled and are
converted into raw bytes by vdso2c program to be ready for mapping into the
process. 32-bit images are compiled only if CONFIG_COMPAT is enabled. vdso2c
generates two files vdso-image-64.c and vdso-image-32.c which contains the
respective vDSO image in C structure.
*) During vdso initialization, required number of vdso pages are allocated and
raw bytes are copied into the pages.
*) During every exec, these pages are mapped into the process through
arch_setup_additional_pages and the location of mapping is passed on to the
process through aux vector AT_SYSINFO_EHDR which is used by glibc.
*) A new update_vsyscall routine for sparc is added to keep the data page in
vdso updated.
*) As vDSO cannot contain dynamically relocatable references, a new version of
cpu_relax is added for the use of vDSO.
This change also requires a putback to glibc to use vDSO. For testing,
programs planning to try vDSO can be compiled against the generated
vdso(64/32).so in the source.
Testing:
========
[root@localhost ~]# cat vdso_test.c
int main() {
struct timespec tv_start, tv_end;
struct timeval tv_tmp;
int i;
int count = 1 * 1000 * 10000;
long long diff;
clock_gettime(0, &tv_start);
for (i = 0; i < count; i++)
gettimeofday(&tv_tmp, NULL);
clock_gettime(0, &tv_end);
diff = (long long)(tv_end.tv_sec -
tv_start.tv_sec)*(1*1000*1000*1000);
diff += (tv_end.tv_nsec - tv_start.tv_nsec);
printf("Start sec: %d\n", tv_start.tv_sec);
printf("End sec : %d\n", tv_end.tv_sec);
printf("%d cycles in %lld ns = %f ns/cycle\n", count, diff,
(double)diff / (double)count);
return 0;
}
[root@localhost ~]# cc vdso_test.c -o t32_without_fix -m32 -lrt
[root@localhost ~]# ./t32_without_fix
Start sec: 1502396130
End sec : 1502396140
10000000 cycles in 9565148528 ns = 956.514853 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t32_with_fix -m32 ./vdso32.so.dbg
[root@localhost ~]# ./t32_with_fix
Start sec: 1502396168
End sec : 1502396169
10000000 cycles in 798141262 ns = 79.814126 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t64_without_fix -m64 -lrt
[root@localhost ~]# ./t64_without_fix
Start sec: 1502396208
End sec : 1502396218
10000000 cycles in 9846091800 ns = 984.609180 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t64_with_fix -m64 ./vdso64.so.dbg
[root@localhost ~]# ./t64_with_fix
Start sec: 1502396257
End sec : 1502396257
10000000 cycles in 380984048 ns = 38.098405 ns/cycle
V1 to V2 Changes:
=================
Added hot patching code to switch the read stick instruction to read
tick instruction based on the hardware.
V2 to V3 Changes:
=================
Merged latest changes from sparc-next and moved the initialization
of clocksource_tick.archdata.vclock_mode to time_init_early. Disabled
queued spinlock and rwlock configuration when simulating 32-bit config
to compile 32-bit VDSO.
V3 to V4 Changes:
=================
Hardcoded the page size as 8192 in linker script for both 64-bit and
32-bit binaries. Removed unused variables in vdso2c.h. Added -mv8plus flag to
Makefile to prevent the generation of relocation entries for __lshrdi3 in 32-bit
vdso binary.
Signed-off-by: Nick Alcock <nick.alcock@oracle.com>
Signed-off-by: Nagarathnam Muthusamy <nagarathnam.muthusamy@oracle.com>
Reviewed-by: Shannon Nelson <shannon.nelson@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-21 23:05:31 +08:00
|
|
|
* and move up a page to get to the data page.
|
|
|
|
*/
|
2018-10-22 13:09:40 +08:00
|
|
|
__asm__("rd %%pc, %0" : "=r" (ret));
|
vDSO for sparc
Following patch is based on work done by Nick Alcock on 64-bit vDSO for sparc
in Oracle linux. I have extended it to include support for 32-bit vDSO for sparc
on 64-bit kernel.
vDSO for sparc is based on the X86 implementation. This patch
provides vDSO support for both 64-bit and 32-bit programs on 64-bit kernel.
vDSO will be disabled on 32-bit linux kernel on sparc.
*) vclock_gettime.c contains all the vdso functions. Since data page is mapped
before the vdso code page, the pointer to data page is got by subracting offset
from an address in the vdso code page. The return address stored in
%i7 is used for this purpose.
*) During compilation, both 32-bit and 64-bit vdso images are compiled and are
converted into raw bytes by vdso2c program to be ready for mapping into the
process. 32-bit images are compiled only if CONFIG_COMPAT is enabled. vdso2c
generates two files vdso-image-64.c and vdso-image-32.c which contains the
respective vDSO image in C structure.
*) During vdso initialization, required number of vdso pages are allocated and
raw bytes are copied into the pages.
*) During every exec, these pages are mapped into the process through
arch_setup_additional_pages and the location of mapping is passed on to the
process through aux vector AT_SYSINFO_EHDR which is used by glibc.
*) A new update_vsyscall routine for sparc is added to keep the data page in
vdso updated.
*) As vDSO cannot contain dynamically relocatable references, a new version of
cpu_relax is added for the use of vDSO.
This change also requires a putback to glibc to use vDSO. For testing,
programs planning to try vDSO can be compiled against the generated
vdso(64/32).so in the source.
Testing:
========
[root@localhost ~]# cat vdso_test.c
int main() {
struct timespec tv_start, tv_end;
struct timeval tv_tmp;
int i;
int count = 1 * 1000 * 10000;
long long diff;
clock_gettime(0, &tv_start);
for (i = 0; i < count; i++)
gettimeofday(&tv_tmp, NULL);
clock_gettime(0, &tv_end);
diff = (long long)(tv_end.tv_sec -
tv_start.tv_sec)*(1*1000*1000*1000);
diff += (tv_end.tv_nsec - tv_start.tv_nsec);
printf("Start sec: %d\n", tv_start.tv_sec);
printf("End sec : %d\n", tv_end.tv_sec);
printf("%d cycles in %lld ns = %f ns/cycle\n", count, diff,
(double)diff / (double)count);
return 0;
}
[root@localhost ~]# cc vdso_test.c -o t32_without_fix -m32 -lrt
[root@localhost ~]# ./t32_without_fix
Start sec: 1502396130
End sec : 1502396140
10000000 cycles in 9565148528 ns = 956.514853 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t32_with_fix -m32 ./vdso32.so.dbg
[root@localhost ~]# ./t32_with_fix
Start sec: 1502396168
End sec : 1502396169
10000000 cycles in 798141262 ns = 79.814126 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t64_without_fix -m64 -lrt
[root@localhost ~]# ./t64_without_fix
Start sec: 1502396208
End sec : 1502396218
10000000 cycles in 9846091800 ns = 984.609180 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t64_with_fix -m64 ./vdso64.so.dbg
[root@localhost ~]# ./t64_with_fix
Start sec: 1502396257
End sec : 1502396257
10000000 cycles in 380984048 ns = 38.098405 ns/cycle
V1 to V2 Changes:
=================
Added hot patching code to switch the read stick instruction to read
tick instruction based on the hardware.
V2 to V3 Changes:
=================
Merged latest changes from sparc-next and moved the initialization
of clocksource_tick.archdata.vclock_mode to time_init_early. Disabled
queued spinlock and rwlock configuration when simulating 32-bit config
to compile 32-bit VDSO.
V3 to V4 Changes:
=================
Hardcoded the page size as 8192 in linker script for both 64-bit and
32-bit binaries. Removed unused variables in vdso2c.h. Added -mv8plus flag to
Makefile to prevent the generation of relocation entries for __lshrdi3 in 32-bit
vdso binary.
Signed-off-by: Nick Alcock <nick.alcock@oracle.com>
Signed-off-by: Nagarathnam Muthusamy <nagarathnam.muthusamy@oracle.com>
Reviewed-by: Shannon Nelson <shannon.nelson@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-21 23:05:31 +08:00
|
|
|
ret &= ~(8192 - 1);
|
|
|
|
ret -= 8192;
|
|
|
|
|
|
|
|
return (struct vvar_data *) ret;
|
|
|
|
}
|
|
|
|
|
2018-10-22 13:09:40 +08:00
|
|
|
notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
|
vDSO for sparc
Following patch is based on work done by Nick Alcock on 64-bit vDSO for sparc
in Oracle linux. I have extended it to include support for 32-bit vDSO for sparc
on 64-bit kernel.
vDSO for sparc is based on the X86 implementation. This patch
provides vDSO support for both 64-bit and 32-bit programs on 64-bit kernel.
vDSO will be disabled on 32-bit linux kernel on sparc.
*) vclock_gettime.c contains all the vdso functions. Since data page is mapped
before the vdso code page, the pointer to data page is got by subracting offset
from an address in the vdso code page. The return address stored in
%i7 is used for this purpose.
*) During compilation, both 32-bit and 64-bit vdso images are compiled and are
converted into raw bytes by vdso2c program to be ready for mapping into the
process. 32-bit images are compiled only if CONFIG_COMPAT is enabled. vdso2c
generates two files vdso-image-64.c and vdso-image-32.c which contains the
respective vDSO image in C structure.
*) During vdso initialization, required number of vdso pages are allocated and
raw bytes are copied into the pages.
*) During every exec, these pages are mapped into the process through
arch_setup_additional_pages and the location of mapping is passed on to the
process through aux vector AT_SYSINFO_EHDR which is used by glibc.
*) A new update_vsyscall routine for sparc is added to keep the data page in
vdso updated.
*) As vDSO cannot contain dynamically relocatable references, a new version of
cpu_relax is added for the use of vDSO.
This change also requires a putback to glibc to use vDSO. For testing,
programs planning to try vDSO can be compiled against the generated
vdso(64/32).so in the source.
Testing:
========
[root@localhost ~]# cat vdso_test.c
int main() {
struct timespec tv_start, tv_end;
struct timeval tv_tmp;
int i;
int count = 1 * 1000 * 10000;
long long diff;
clock_gettime(0, &tv_start);
for (i = 0; i < count; i++)
gettimeofday(&tv_tmp, NULL);
clock_gettime(0, &tv_end);
diff = (long long)(tv_end.tv_sec -
tv_start.tv_sec)*(1*1000*1000*1000);
diff += (tv_end.tv_nsec - tv_start.tv_nsec);
printf("Start sec: %d\n", tv_start.tv_sec);
printf("End sec : %d\n", tv_end.tv_sec);
printf("%d cycles in %lld ns = %f ns/cycle\n", count, diff,
(double)diff / (double)count);
return 0;
}
[root@localhost ~]# cc vdso_test.c -o t32_without_fix -m32 -lrt
[root@localhost ~]# ./t32_without_fix
Start sec: 1502396130
End sec : 1502396140
10000000 cycles in 9565148528 ns = 956.514853 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t32_with_fix -m32 ./vdso32.so.dbg
[root@localhost ~]# ./t32_with_fix
Start sec: 1502396168
End sec : 1502396169
10000000 cycles in 798141262 ns = 79.814126 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t64_without_fix -m64 -lrt
[root@localhost ~]# ./t64_without_fix
Start sec: 1502396208
End sec : 1502396218
10000000 cycles in 9846091800 ns = 984.609180 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t64_with_fix -m64 ./vdso64.so.dbg
[root@localhost ~]# ./t64_with_fix
Start sec: 1502396257
End sec : 1502396257
10000000 cycles in 380984048 ns = 38.098405 ns/cycle
V1 to V2 Changes:
=================
Added hot patching code to switch the read stick instruction to read
tick instruction based on the hardware.
V2 to V3 Changes:
=================
Merged latest changes from sparc-next and moved the initialization
of clocksource_tick.archdata.vclock_mode to time_init_early. Disabled
queued spinlock and rwlock configuration when simulating 32-bit config
to compile 32-bit VDSO.
V3 to V4 Changes:
=================
Hardcoded the page size as 8192 in linker script for both 64-bit and
32-bit binaries. Removed unused variables in vdso2c.h. Added -mv8plus flag to
Makefile to prevent the generation of relocation entries for __lshrdi3 in 32-bit
vdso binary.
Signed-off-by: Nick Alcock <nick.alcock@oracle.com>
Signed-off-by: Nagarathnam Muthusamy <nagarathnam.muthusamy@oracle.com>
Reviewed-by: Shannon Nelson <shannon.nelson@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-21 23:05:31 +08:00
|
|
|
{
|
|
|
|
register long num __asm__("g1") = __NR_clock_gettime;
|
|
|
|
register long o0 __asm__("o0") = clock;
|
|
|
|
register long o1 __asm__("o1") = (long) ts;
|
|
|
|
|
|
|
|
__asm__ __volatile__(SYSCALL_STRING : "=r" (o0) : "r" (num),
|
|
|
|
"0" (o0), "r" (o1) : SYSCALL_CLOBBERS);
|
|
|
|
return o0;
|
|
|
|
}
|
|
|
|
|
2018-10-22 13:09:40 +08:00
|
|
|
notrace static long vdso_fallback_gettimeofday(struct timeval *tv, struct timezone *tz)
|
vDSO for sparc
Following patch is based on work done by Nick Alcock on 64-bit vDSO for sparc
in Oracle linux. I have extended it to include support for 32-bit vDSO for sparc
on 64-bit kernel.
vDSO for sparc is based on the X86 implementation. This patch
provides vDSO support for both 64-bit and 32-bit programs on 64-bit kernel.
vDSO will be disabled on 32-bit linux kernel on sparc.
*) vclock_gettime.c contains all the vdso functions. Since data page is mapped
before the vdso code page, the pointer to data page is got by subracting offset
from an address in the vdso code page. The return address stored in
%i7 is used for this purpose.
*) During compilation, both 32-bit and 64-bit vdso images are compiled and are
converted into raw bytes by vdso2c program to be ready for mapping into the
process. 32-bit images are compiled only if CONFIG_COMPAT is enabled. vdso2c
generates two files vdso-image-64.c and vdso-image-32.c which contains the
respective vDSO image in C structure.
*) During vdso initialization, required number of vdso pages are allocated and
raw bytes are copied into the pages.
*) During every exec, these pages are mapped into the process through
arch_setup_additional_pages and the location of mapping is passed on to the
process through aux vector AT_SYSINFO_EHDR which is used by glibc.
*) A new update_vsyscall routine for sparc is added to keep the data page in
vdso updated.
*) As vDSO cannot contain dynamically relocatable references, a new version of
cpu_relax is added for the use of vDSO.
This change also requires a putback to glibc to use vDSO. For testing,
programs planning to try vDSO can be compiled against the generated
vdso(64/32).so in the source.
Testing:
========
[root@localhost ~]# cat vdso_test.c
int main() {
struct timespec tv_start, tv_end;
struct timeval tv_tmp;
int i;
int count = 1 * 1000 * 10000;
long long diff;
clock_gettime(0, &tv_start);
for (i = 0; i < count; i++)
gettimeofday(&tv_tmp, NULL);
clock_gettime(0, &tv_end);
diff = (long long)(tv_end.tv_sec -
tv_start.tv_sec)*(1*1000*1000*1000);
diff += (tv_end.tv_nsec - tv_start.tv_nsec);
printf("Start sec: %d\n", tv_start.tv_sec);
printf("End sec : %d\n", tv_end.tv_sec);
printf("%d cycles in %lld ns = %f ns/cycle\n", count, diff,
(double)diff / (double)count);
return 0;
}
[root@localhost ~]# cc vdso_test.c -o t32_without_fix -m32 -lrt
[root@localhost ~]# ./t32_without_fix
Start sec: 1502396130
End sec : 1502396140
10000000 cycles in 9565148528 ns = 956.514853 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t32_with_fix -m32 ./vdso32.so.dbg
[root@localhost ~]# ./t32_with_fix
Start sec: 1502396168
End sec : 1502396169
10000000 cycles in 798141262 ns = 79.814126 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t64_without_fix -m64 -lrt
[root@localhost ~]# ./t64_without_fix
Start sec: 1502396208
End sec : 1502396218
10000000 cycles in 9846091800 ns = 984.609180 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t64_with_fix -m64 ./vdso64.so.dbg
[root@localhost ~]# ./t64_with_fix
Start sec: 1502396257
End sec : 1502396257
10000000 cycles in 380984048 ns = 38.098405 ns/cycle
V1 to V2 Changes:
=================
Added hot patching code to switch the read stick instruction to read
tick instruction based on the hardware.
V2 to V3 Changes:
=================
Merged latest changes from sparc-next and moved the initialization
of clocksource_tick.archdata.vclock_mode to time_init_early. Disabled
queued spinlock and rwlock configuration when simulating 32-bit config
to compile 32-bit VDSO.
V3 to V4 Changes:
=================
Hardcoded the page size as 8192 in linker script for both 64-bit and
32-bit binaries. Removed unused variables in vdso2c.h. Added -mv8plus flag to
Makefile to prevent the generation of relocation entries for __lshrdi3 in 32-bit
vdso binary.
Signed-off-by: Nick Alcock <nick.alcock@oracle.com>
Signed-off-by: Nagarathnam Muthusamy <nagarathnam.muthusamy@oracle.com>
Reviewed-by: Shannon Nelson <shannon.nelson@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-21 23:05:31 +08:00
|
|
|
{
|
|
|
|
register long num __asm__("g1") = __NR_gettimeofday;
|
|
|
|
register long o0 __asm__("o0") = (long) tv;
|
|
|
|
register long o1 __asm__("o1") = (long) tz;
|
|
|
|
|
|
|
|
__asm__ __volatile__(SYSCALL_STRING : "=r" (o0) : "r" (num),
|
|
|
|
"0" (o0), "r" (o1) : SYSCALL_CLOBBERS);
|
|
|
|
return o0;
|
|
|
|
}
|
|
|
|
|
|
|
|
#ifdef CONFIG_SPARC64
|
2018-10-22 13:09:40 +08:00
|
|
|
notrace static __always_inline u64 vread_tick(void)
|
|
|
|
{
|
vDSO for sparc
Following patch is based on work done by Nick Alcock on 64-bit vDSO for sparc
in Oracle linux. I have extended it to include support for 32-bit vDSO for sparc
on 64-bit kernel.
vDSO for sparc is based on the X86 implementation. This patch
provides vDSO support for both 64-bit and 32-bit programs on 64-bit kernel.
vDSO will be disabled on 32-bit linux kernel on sparc.
*) vclock_gettime.c contains all the vdso functions. Since data page is mapped
before the vdso code page, the pointer to data page is got by subracting offset
from an address in the vdso code page. The return address stored in
%i7 is used for this purpose.
*) During compilation, both 32-bit and 64-bit vdso images are compiled and are
converted into raw bytes by vdso2c program to be ready for mapping into the
process. 32-bit images are compiled only if CONFIG_COMPAT is enabled. vdso2c
generates two files vdso-image-64.c and vdso-image-32.c which contains the
respective vDSO image in C structure.
*) During vdso initialization, required number of vdso pages are allocated and
raw bytes are copied into the pages.
*) During every exec, these pages are mapped into the process through
arch_setup_additional_pages and the location of mapping is passed on to the
process through aux vector AT_SYSINFO_EHDR which is used by glibc.
*) A new update_vsyscall routine for sparc is added to keep the data page in
vdso updated.
*) As vDSO cannot contain dynamically relocatable references, a new version of
cpu_relax is added for the use of vDSO.
This change also requires a putback to glibc to use vDSO. For testing,
programs planning to try vDSO can be compiled against the generated
vdso(64/32).so in the source.
Testing:
========
[root@localhost ~]# cat vdso_test.c
int main() {
struct timespec tv_start, tv_end;
struct timeval tv_tmp;
int i;
int count = 1 * 1000 * 10000;
long long diff;
clock_gettime(0, &tv_start);
for (i = 0; i < count; i++)
gettimeofday(&tv_tmp, NULL);
clock_gettime(0, &tv_end);
diff = (long long)(tv_end.tv_sec -
tv_start.tv_sec)*(1*1000*1000*1000);
diff += (tv_end.tv_nsec - tv_start.tv_nsec);
printf("Start sec: %d\n", tv_start.tv_sec);
printf("End sec : %d\n", tv_end.tv_sec);
printf("%d cycles in %lld ns = %f ns/cycle\n", count, diff,
(double)diff / (double)count);
return 0;
}
[root@localhost ~]# cc vdso_test.c -o t32_without_fix -m32 -lrt
[root@localhost ~]# ./t32_without_fix
Start sec: 1502396130
End sec : 1502396140
10000000 cycles in 9565148528 ns = 956.514853 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t32_with_fix -m32 ./vdso32.so.dbg
[root@localhost ~]# ./t32_with_fix
Start sec: 1502396168
End sec : 1502396169
10000000 cycles in 798141262 ns = 79.814126 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t64_without_fix -m64 -lrt
[root@localhost ~]# ./t64_without_fix
Start sec: 1502396208
End sec : 1502396218
10000000 cycles in 9846091800 ns = 984.609180 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t64_with_fix -m64 ./vdso64.so.dbg
[root@localhost ~]# ./t64_with_fix
Start sec: 1502396257
End sec : 1502396257
10000000 cycles in 380984048 ns = 38.098405 ns/cycle
V1 to V2 Changes:
=================
Added hot patching code to switch the read stick instruction to read
tick instruction based on the hardware.
V2 to V3 Changes:
=================
Merged latest changes from sparc-next and moved the initialization
of clocksource_tick.archdata.vclock_mode to time_init_early. Disabled
queued spinlock and rwlock configuration when simulating 32-bit config
to compile 32-bit VDSO.
V3 to V4 Changes:
=================
Hardcoded the page size as 8192 in linker script for both 64-bit and
32-bit binaries. Removed unused variables in vdso2c.h. Added -mv8plus flag to
Makefile to prevent the generation of relocation entries for __lshrdi3 in 32-bit
vdso binary.
Signed-off-by: Nick Alcock <nick.alcock@oracle.com>
Signed-off-by: Nagarathnam Muthusamy <nagarathnam.muthusamy@oracle.com>
Reviewed-by: Shannon Nelson <shannon.nelson@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-21 23:05:31 +08:00
|
|
|
u64 ret;
|
|
|
|
|
2018-10-26 01:36:19 +08:00
|
|
|
__asm__ __volatile__("rd %%tick, %0" : "=r" (ret));
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
notrace static __always_inline u64 vread_tick_stick(void)
|
|
|
|
{
|
|
|
|
u64 ret;
|
|
|
|
|
|
|
|
__asm__ __volatile__("rd %%asr24, %0" : "=r" (ret));
|
2018-10-22 13:10:51 +08:00
|
|
|
return ret;
|
vDSO for sparc
Following patch is based on work done by Nick Alcock on 64-bit vDSO for sparc
in Oracle linux. I have extended it to include support for 32-bit vDSO for sparc
on 64-bit kernel.
vDSO for sparc is based on the X86 implementation. This patch
provides vDSO support for both 64-bit and 32-bit programs on 64-bit kernel.
vDSO will be disabled on 32-bit linux kernel on sparc.
*) vclock_gettime.c contains all the vdso functions. Since data page is mapped
before the vdso code page, the pointer to data page is got by subracting offset
from an address in the vdso code page. The return address stored in
%i7 is used for this purpose.
*) During compilation, both 32-bit and 64-bit vdso images are compiled and are
converted into raw bytes by vdso2c program to be ready for mapping into the
process. 32-bit images are compiled only if CONFIG_COMPAT is enabled. vdso2c
generates two files vdso-image-64.c and vdso-image-32.c which contains the
respective vDSO image in C structure.
*) During vdso initialization, required number of vdso pages are allocated and
raw bytes are copied into the pages.
*) During every exec, these pages are mapped into the process through
arch_setup_additional_pages and the location of mapping is passed on to the
process through aux vector AT_SYSINFO_EHDR which is used by glibc.
*) A new update_vsyscall routine for sparc is added to keep the data page in
vdso updated.
*) As vDSO cannot contain dynamically relocatable references, a new version of
cpu_relax is added for the use of vDSO.
This change also requires a putback to glibc to use vDSO. For testing,
programs planning to try vDSO can be compiled against the generated
vdso(64/32).so in the source.
Testing:
========
[root@localhost ~]# cat vdso_test.c
int main() {
struct timespec tv_start, tv_end;
struct timeval tv_tmp;
int i;
int count = 1 * 1000 * 10000;
long long diff;
clock_gettime(0, &tv_start);
for (i = 0; i < count; i++)
gettimeofday(&tv_tmp, NULL);
clock_gettime(0, &tv_end);
diff = (long long)(tv_end.tv_sec -
tv_start.tv_sec)*(1*1000*1000*1000);
diff += (tv_end.tv_nsec - tv_start.tv_nsec);
printf("Start sec: %d\n", tv_start.tv_sec);
printf("End sec : %d\n", tv_end.tv_sec);
printf("%d cycles in %lld ns = %f ns/cycle\n", count, diff,
(double)diff / (double)count);
return 0;
}
[root@localhost ~]# cc vdso_test.c -o t32_without_fix -m32 -lrt
[root@localhost ~]# ./t32_without_fix
Start sec: 1502396130
End sec : 1502396140
10000000 cycles in 9565148528 ns = 956.514853 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t32_with_fix -m32 ./vdso32.so.dbg
[root@localhost ~]# ./t32_with_fix
Start sec: 1502396168
End sec : 1502396169
10000000 cycles in 798141262 ns = 79.814126 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t64_without_fix -m64 -lrt
[root@localhost ~]# ./t64_without_fix
Start sec: 1502396208
End sec : 1502396218
10000000 cycles in 9846091800 ns = 984.609180 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t64_with_fix -m64 ./vdso64.so.dbg
[root@localhost ~]# ./t64_with_fix
Start sec: 1502396257
End sec : 1502396257
10000000 cycles in 380984048 ns = 38.098405 ns/cycle
V1 to V2 Changes:
=================
Added hot patching code to switch the read stick instruction to read
tick instruction based on the hardware.
V2 to V3 Changes:
=================
Merged latest changes from sparc-next and moved the initialization
of clocksource_tick.archdata.vclock_mode to time_init_early. Disabled
queued spinlock and rwlock configuration when simulating 32-bit config
to compile 32-bit VDSO.
V3 to V4 Changes:
=================
Hardcoded the page size as 8192 in linker script for both 64-bit and
32-bit binaries. Removed unused variables in vdso2c.h. Added -mv8plus flag to
Makefile to prevent the generation of relocation entries for __lshrdi3 in 32-bit
vdso binary.
Signed-off-by: Nick Alcock <nick.alcock@oracle.com>
Signed-off-by: Nagarathnam Muthusamy <nagarathnam.muthusamy@oracle.com>
Reviewed-by: Shannon Nelson <shannon.nelson@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-21 23:05:31 +08:00
|
|
|
}
|
|
|
|
#else
|
2018-10-22 13:09:40 +08:00
|
|
|
notrace static __always_inline u64 vread_tick(void)
|
vDSO for sparc
Following patch is based on work done by Nick Alcock on 64-bit vDSO for sparc
in Oracle linux. I have extended it to include support for 32-bit vDSO for sparc
on 64-bit kernel.
vDSO for sparc is based on the X86 implementation. This patch
provides vDSO support for both 64-bit and 32-bit programs on 64-bit kernel.
vDSO will be disabled on 32-bit linux kernel on sparc.
*) vclock_gettime.c contains all the vdso functions. Since data page is mapped
before the vdso code page, the pointer to data page is got by subracting offset
from an address in the vdso code page. The return address stored in
%i7 is used for this purpose.
*) During compilation, both 32-bit and 64-bit vdso images are compiled and are
converted into raw bytes by vdso2c program to be ready for mapping into the
process. 32-bit images are compiled only if CONFIG_COMPAT is enabled. vdso2c
generates two files vdso-image-64.c and vdso-image-32.c which contains the
respective vDSO image in C structure.
*) During vdso initialization, required number of vdso pages are allocated and
raw bytes are copied into the pages.
*) During every exec, these pages are mapped into the process through
arch_setup_additional_pages and the location of mapping is passed on to the
process through aux vector AT_SYSINFO_EHDR which is used by glibc.
*) A new update_vsyscall routine for sparc is added to keep the data page in
vdso updated.
*) As vDSO cannot contain dynamically relocatable references, a new version of
cpu_relax is added for the use of vDSO.
This change also requires a putback to glibc to use vDSO. For testing,
programs planning to try vDSO can be compiled against the generated
vdso(64/32).so in the source.
Testing:
========
[root@localhost ~]# cat vdso_test.c
int main() {
struct timespec tv_start, tv_end;
struct timeval tv_tmp;
int i;
int count = 1 * 1000 * 10000;
long long diff;
clock_gettime(0, &tv_start);
for (i = 0; i < count; i++)
gettimeofday(&tv_tmp, NULL);
clock_gettime(0, &tv_end);
diff = (long long)(tv_end.tv_sec -
tv_start.tv_sec)*(1*1000*1000*1000);
diff += (tv_end.tv_nsec - tv_start.tv_nsec);
printf("Start sec: %d\n", tv_start.tv_sec);
printf("End sec : %d\n", tv_end.tv_sec);
printf("%d cycles in %lld ns = %f ns/cycle\n", count, diff,
(double)diff / (double)count);
return 0;
}
[root@localhost ~]# cc vdso_test.c -o t32_without_fix -m32 -lrt
[root@localhost ~]# ./t32_without_fix
Start sec: 1502396130
End sec : 1502396140
10000000 cycles in 9565148528 ns = 956.514853 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t32_with_fix -m32 ./vdso32.so.dbg
[root@localhost ~]# ./t32_with_fix
Start sec: 1502396168
End sec : 1502396169
10000000 cycles in 798141262 ns = 79.814126 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t64_without_fix -m64 -lrt
[root@localhost ~]# ./t64_without_fix
Start sec: 1502396208
End sec : 1502396218
10000000 cycles in 9846091800 ns = 984.609180 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t64_with_fix -m64 ./vdso64.so.dbg
[root@localhost ~]# ./t64_with_fix
Start sec: 1502396257
End sec : 1502396257
10000000 cycles in 380984048 ns = 38.098405 ns/cycle
V1 to V2 Changes:
=================
Added hot patching code to switch the read stick instruction to read
tick instruction based on the hardware.
V2 to V3 Changes:
=================
Merged latest changes from sparc-next and moved the initialization
of clocksource_tick.archdata.vclock_mode to time_init_early. Disabled
queued spinlock and rwlock configuration when simulating 32-bit config
to compile 32-bit VDSO.
V3 to V4 Changes:
=================
Hardcoded the page size as 8192 in linker script for both 64-bit and
32-bit binaries. Removed unused variables in vdso2c.h. Added -mv8plus flag to
Makefile to prevent the generation of relocation entries for __lshrdi3 in 32-bit
vdso binary.
Signed-off-by: Nick Alcock <nick.alcock@oracle.com>
Signed-off-by: Nagarathnam Muthusamy <nagarathnam.muthusamy@oracle.com>
Reviewed-by: Shannon Nelson <shannon.nelson@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-21 23:05:31 +08:00
|
|
|
{
|
sparc: Improve VDSO instruction patching.
The current VDSO patch mechanism has several problems:
1) It assumes how gcc will emit a function, with a register
window, an initial save instruction and then immediately
the %tick read when compiling vread_tick().
There is no such guarantees, code generation could change
at any time, gcc could put a nop between the save and
the %tick read, etc.
So this is extremely fragile and would fail some day.
2) It disallows us to properly inline vread_tick() into the callers
and thus get the best possible code sequences.
So fix this to patch properly, with location based annotations.
We have to be careful because we cannot do it the way we do
patches elsewhere in the kernel. Those use a sequence like:
1:
insn
.section .whatever_patch, "ax"
.word 1b
replacement_insn
.previous
This is a dynamic shared object, so that .word cannot be resolved at
build time, and thus cannot be used to execute the patches when the
kernel initializes the images.
Even trying to use label difference equations doesn't work in the
above kind of scheme:
1:
insn
.section .whatever_patch, "ax"
.word . - 1b
replacement_insn
.previous
The assembler complains that it cannot resolve that computation.
The issue is that this is contained in an executable section.
Borrow the sequence used by x86 alternatives, which is:
1:
insn
.pushsection .whatever_patch, "a"
.word . - 1b, . - 1f
.popsection
.pushsection .whatever_patch_replacements, "ax"
1:
replacement_insn
.previous
This works, allows us to inline vread_tick() as much as we like, and
can be used for arbitrary kinds of VDSO patching in the future.
Also, reverse the condition for patching. Most systems are %stick
based, so if we only patch on %tick systems the patching code will
get little or no testing.
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-10-22 12:44:33 +08:00
|
|
|
register unsigned long long ret asm("o4");
|
|
|
|
|
2018-10-26 01:36:19 +08:00
|
|
|
__asm__ __volatile__("rd %%tick, %L0\n\t"
|
|
|
|
"srlx %L0, 32, %H0"
|
|
|
|
: "=r" (ret));
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
notrace static __always_inline u64 vread_tick_stick(void)
|
|
|
|
{
|
|
|
|
register unsigned long long ret asm("o4");
|
|
|
|
|
|
|
|
__asm__ __volatile__("rd %%asr24, %L0\n\t"
|
|
|
|
"srlx %L0, 32, %H0"
|
sparc: Improve VDSO instruction patching.
The current VDSO patch mechanism has several problems:
1) It assumes how gcc will emit a function, with a register
window, an initial save instruction and then immediately
the %tick read when compiling vread_tick().
There is no such guarantees, code generation could change
at any time, gcc could put a nop between the save and
the %tick read, etc.
So this is extremely fragile and would fail some day.
2) It disallows us to properly inline vread_tick() into the callers
and thus get the best possible code sequences.
So fix this to patch properly, with location based annotations.
We have to be careful because we cannot do it the way we do
patches elsewhere in the kernel. Those use a sequence like:
1:
insn
.section .whatever_patch, "ax"
.word 1b
replacement_insn
.previous
This is a dynamic shared object, so that .word cannot be resolved at
build time, and thus cannot be used to execute the patches when the
kernel initializes the images.
Even trying to use label difference equations doesn't work in the
above kind of scheme:
1:
insn
.section .whatever_patch, "ax"
.word . - 1b
replacement_insn
.previous
The assembler complains that it cannot resolve that computation.
The issue is that this is contained in an executable section.
Borrow the sequence used by x86 alternatives, which is:
1:
insn
.pushsection .whatever_patch, "a"
.word . - 1b, . - 1f
.popsection
.pushsection .whatever_patch_replacements, "ax"
1:
replacement_insn
.previous
This works, allows us to inline vread_tick() as much as we like, and
can be used for arbitrary kinds of VDSO patching in the future.
Also, reverse the condition for patching. Most systems are %stick
based, so if we only patch on %tick systems the patching code will
get little or no testing.
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-10-22 12:44:33 +08:00
|
|
|
: "=r" (ret));
|
|
|
|
return ret;
|
vDSO for sparc
Following patch is based on work done by Nick Alcock on 64-bit vDSO for sparc
in Oracle linux. I have extended it to include support for 32-bit vDSO for sparc
on 64-bit kernel.
vDSO for sparc is based on the X86 implementation. This patch
provides vDSO support for both 64-bit and 32-bit programs on 64-bit kernel.
vDSO will be disabled on 32-bit linux kernel on sparc.
*) vclock_gettime.c contains all the vdso functions. Since data page is mapped
before the vdso code page, the pointer to data page is got by subracting offset
from an address in the vdso code page. The return address stored in
%i7 is used for this purpose.
*) During compilation, both 32-bit and 64-bit vdso images are compiled and are
converted into raw bytes by vdso2c program to be ready for mapping into the
process. 32-bit images are compiled only if CONFIG_COMPAT is enabled. vdso2c
generates two files vdso-image-64.c and vdso-image-32.c which contains the
respective vDSO image in C structure.
*) During vdso initialization, required number of vdso pages are allocated and
raw bytes are copied into the pages.
*) During every exec, these pages are mapped into the process through
arch_setup_additional_pages and the location of mapping is passed on to the
process through aux vector AT_SYSINFO_EHDR which is used by glibc.
*) A new update_vsyscall routine for sparc is added to keep the data page in
vdso updated.
*) As vDSO cannot contain dynamically relocatable references, a new version of
cpu_relax is added for the use of vDSO.
This change also requires a putback to glibc to use vDSO. For testing,
programs planning to try vDSO can be compiled against the generated
vdso(64/32).so in the source.
Testing:
========
[root@localhost ~]# cat vdso_test.c
int main() {
struct timespec tv_start, tv_end;
struct timeval tv_tmp;
int i;
int count = 1 * 1000 * 10000;
long long diff;
clock_gettime(0, &tv_start);
for (i = 0; i < count; i++)
gettimeofday(&tv_tmp, NULL);
clock_gettime(0, &tv_end);
diff = (long long)(tv_end.tv_sec -
tv_start.tv_sec)*(1*1000*1000*1000);
diff += (tv_end.tv_nsec - tv_start.tv_nsec);
printf("Start sec: %d\n", tv_start.tv_sec);
printf("End sec : %d\n", tv_end.tv_sec);
printf("%d cycles in %lld ns = %f ns/cycle\n", count, diff,
(double)diff / (double)count);
return 0;
}
[root@localhost ~]# cc vdso_test.c -o t32_without_fix -m32 -lrt
[root@localhost ~]# ./t32_without_fix
Start sec: 1502396130
End sec : 1502396140
10000000 cycles in 9565148528 ns = 956.514853 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t32_with_fix -m32 ./vdso32.so.dbg
[root@localhost ~]# ./t32_with_fix
Start sec: 1502396168
End sec : 1502396169
10000000 cycles in 798141262 ns = 79.814126 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t64_without_fix -m64 -lrt
[root@localhost ~]# ./t64_without_fix
Start sec: 1502396208
End sec : 1502396218
10000000 cycles in 9846091800 ns = 984.609180 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t64_with_fix -m64 ./vdso64.so.dbg
[root@localhost ~]# ./t64_with_fix
Start sec: 1502396257
End sec : 1502396257
10000000 cycles in 380984048 ns = 38.098405 ns/cycle
V1 to V2 Changes:
=================
Added hot patching code to switch the read stick instruction to read
tick instruction based on the hardware.
V2 to V3 Changes:
=================
Merged latest changes from sparc-next and moved the initialization
of clocksource_tick.archdata.vclock_mode to time_init_early. Disabled
queued spinlock and rwlock configuration when simulating 32-bit config
to compile 32-bit VDSO.
V3 to V4 Changes:
=================
Hardcoded the page size as 8192 in linker script for both 64-bit and
32-bit binaries. Removed unused variables in vdso2c.h. Added -mv8plus flag to
Makefile to prevent the generation of relocation entries for __lshrdi3 in 32-bit
vdso binary.
Signed-off-by: Nick Alcock <nick.alcock@oracle.com>
Signed-off-by: Nagarathnam Muthusamy <nagarathnam.muthusamy@oracle.com>
Reviewed-by: Shannon Nelson <shannon.nelson@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-21 23:05:31 +08:00
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
2018-10-22 13:09:40 +08:00
|
|
|
notrace static __always_inline u64 vgetsns(struct vvar_data *vvar)
|
vDSO for sparc
Following patch is based on work done by Nick Alcock on 64-bit vDSO for sparc
in Oracle linux. I have extended it to include support for 32-bit vDSO for sparc
on 64-bit kernel.
vDSO for sparc is based on the X86 implementation. This patch
provides vDSO support for both 64-bit and 32-bit programs on 64-bit kernel.
vDSO will be disabled on 32-bit linux kernel on sparc.
*) vclock_gettime.c contains all the vdso functions. Since data page is mapped
before the vdso code page, the pointer to data page is got by subracting offset
from an address in the vdso code page. The return address stored in
%i7 is used for this purpose.
*) During compilation, both 32-bit and 64-bit vdso images are compiled and are
converted into raw bytes by vdso2c program to be ready for mapping into the
process. 32-bit images are compiled only if CONFIG_COMPAT is enabled. vdso2c
generates two files vdso-image-64.c and vdso-image-32.c which contains the
respective vDSO image in C structure.
*) During vdso initialization, required number of vdso pages are allocated and
raw bytes are copied into the pages.
*) During every exec, these pages are mapped into the process through
arch_setup_additional_pages and the location of mapping is passed on to the
process through aux vector AT_SYSINFO_EHDR which is used by glibc.
*) A new update_vsyscall routine for sparc is added to keep the data page in
vdso updated.
*) As vDSO cannot contain dynamically relocatable references, a new version of
cpu_relax is added for the use of vDSO.
This change also requires a putback to glibc to use vDSO. For testing,
programs planning to try vDSO can be compiled against the generated
vdso(64/32).so in the source.
Testing:
========
[root@localhost ~]# cat vdso_test.c
int main() {
struct timespec tv_start, tv_end;
struct timeval tv_tmp;
int i;
int count = 1 * 1000 * 10000;
long long diff;
clock_gettime(0, &tv_start);
for (i = 0; i < count; i++)
gettimeofday(&tv_tmp, NULL);
clock_gettime(0, &tv_end);
diff = (long long)(tv_end.tv_sec -
tv_start.tv_sec)*(1*1000*1000*1000);
diff += (tv_end.tv_nsec - tv_start.tv_nsec);
printf("Start sec: %d\n", tv_start.tv_sec);
printf("End sec : %d\n", tv_end.tv_sec);
printf("%d cycles in %lld ns = %f ns/cycle\n", count, diff,
(double)diff / (double)count);
return 0;
}
[root@localhost ~]# cc vdso_test.c -o t32_without_fix -m32 -lrt
[root@localhost ~]# ./t32_without_fix
Start sec: 1502396130
End sec : 1502396140
10000000 cycles in 9565148528 ns = 956.514853 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t32_with_fix -m32 ./vdso32.so.dbg
[root@localhost ~]# ./t32_with_fix
Start sec: 1502396168
End sec : 1502396169
10000000 cycles in 798141262 ns = 79.814126 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t64_without_fix -m64 -lrt
[root@localhost ~]# ./t64_without_fix
Start sec: 1502396208
End sec : 1502396218
10000000 cycles in 9846091800 ns = 984.609180 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t64_with_fix -m64 ./vdso64.so.dbg
[root@localhost ~]# ./t64_with_fix
Start sec: 1502396257
End sec : 1502396257
10000000 cycles in 380984048 ns = 38.098405 ns/cycle
V1 to V2 Changes:
=================
Added hot patching code to switch the read stick instruction to read
tick instruction based on the hardware.
V2 to V3 Changes:
=================
Merged latest changes from sparc-next and moved the initialization
of clocksource_tick.archdata.vclock_mode to time_init_early. Disabled
queued spinlock and rwlock configuration when simulating 32-bit config
to compile 32-bit VDSO.
V3 to V4 Changes:
=================
Hardcoded the page size as 8192 in linker script for both 64-bit and
32-bit binaries. Removed unused variables in vdso2c.h. Added -mv8plus flag to
Makefile to prevent the generation of relocation entries for __lshrdi3 in 32-bit
vdso binary.
Signed-off-by: Nick Alcock <nick.alcock@oracle.com>
Signed-off-by: Nagarathnam Muthusamy <nagarathnam.muthusamy@oracle.com>
Reviewed-by: Shannon Nelson <shannon.nelson@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-21 23:05:31 +08:00
|
|
|
{
|
|
|
|
u64 v;
|
|
|
|
u64 cycles;
|
|
|
|
|
|
|
|
cycles = vread_tick();
|
|
|
|
v = (cycles - vvar->clock.cycle_last) & vvar->clock.mask;
|
|
|
|
return v * vvar->clock.mult;
|
|
|
|
}
|
|
|
|
|
2018-10-26 01:36:19 +08:00
|
|
|
notrace static __always_inline u64 vgetsns_stick(struct vvar_data *vvar)
|
|
|
|
{
|
|
|
|
u64 v;
|
|
|
|
u64 cycles;
|
|
|
|
|
|
|
|
cycles = vread_tick_stick();
|
|
|
|
v = (cycles - vvar->clock.cycle_last) & vvar->clock.mask;
|
|
|
|
return v * vvar->clock.mult;
|
|
|
|
}
|
|
|
|
|
2018-10-22 13:09:40 +08:00
|
|
|
notrace static __always_inline int do_realtime(struct vvar_data *vvar,
|
|
|
|
struct timespec *ts)
|
vDSO for sparc
Following patch is based on work done by Nick Alcock on 64-bit vDSO for sparc
in Oracle linux. I have extended it to include support for 32-bit vDSO for sparc
on 64-bit kernel.
vDSO for sparc is based on the X86 implementation. This patch
provides vDSO support for both 64-bit and 32-bit programs on 64-bit kernel.
vDSO will be disabled on 32-bit linux kernel on sparc.
*) vclock_gettime.c contains all the vdso functions. Since data page is mapped
before the vdso code page, the pointer to data page is got by subracting offset
from an address in the vdso code page. The return address stored in
%i7 is used for this purpose.
*) During compilation, both 32-bit and 64-bit vdso images are compiled and are
converted into raw bytes by vdso2c program to be ready for mapping into the
process. 32-bit images are compiled only if CONFIG_COMPAT is enabled. vdso2c
generates two files vdso-image-64.c and vdso-image-32.c which contains the
respective vDSO image in C structure.
*) During vdso initialization, required number of vdso pages are allocated and
raw bytes are copied into the pages.
*) During every exec, these pages are mapped into the process through
arch_setup_additional_pages and the location of mapping is passed on to the
process through aux vector AT_SYSINFO_EHDR which is used by glibc.
*) A new update_vsyscall routine for sparc is added to keep the data page in
vdso updated.
*) As vDSO cannot contain dynamically relocatable references, a new version of
cpu_relax is added for the use of vDSO.
This change also requires a putback to glibc to use vDSO. For testing,
programs planning to try vDSO can be compiled against the generated
vdso(64/32).so in the source.
Testing:
========
[root@localhost ~]# cat vdso_test.c
int main() {
struct timespec tv_start, tv_end;
struct timeval tv_tmp;
int i;
int count = 1 * 1000 * 10000;
long long diff;
clock_gettime(0, &tv_start);
for (i = 0; i < count; i++)
gettimeofday(&tv_tmp, NULL);
clock_gettime(0, &tv_end);
diff = (long long)(tv_end.tv_sec -
tv_start.tv_sec)*(1*1000*1000*1000);
diff += (tv_end.tv_nsec - tv_start.tv_nsec);
printf("Start sec: %d\n", tv_start.tv_sec);
printf("End sec : %d\n", tv_end.tv_sec);
printf("%d cycles in %lld ns = %f ns/cycle\n", count, diff,
(double)diff / (double)count);
return 0;
}
[root@localhost ~]# cc vdso_test.c -o t32_without_fix -m32 -lrt
[root@localhost ~]# ./t32_without_fix
Start sec: 1502396130
End sec : 1502396140
10000000 cycles in 9565148528 ns = 956.514853 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t32_with_fix -m32 ./vdso32.so.dbg
[root@localhost ~]# ./t32_with_fix
Start sec: 1502396168
End sec : 1502396169
10000000 cycles in 798141262 ns = 79.814126 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t64_without_fix -m64 -lrt
[root@localhost ~]# ./t64_without_fix
Start sec: 1502396208
End sec : 1502396218
10000000 cycles in 9846091800 ns = 984.609180 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t64_with_fix -m64 ./vdso64.so.dbg
[root@localhost ~]# ./t64_with_fix
Start sec: 1502396257
End sec : 1502396257
10000000 cycles in 380984048 ns = 38.098405 ns/cycle
V1 to V2 Changes:
=================
Added hot patching code to switch the read stick instruction to read
tick instruction based on the hardware.
V2 to V3 Changes:
=================
Merged latest changes from sparc-next and moved the initialization
of clocksource_tick.archdata.vclock_mode to time_init_early. Disabled
queued spinlock and rwlock configuration when simulating 32-bit config
to compile 32-bit VDSO.
V3 to V4 Changes:
=================
Hardcoded the page size as 8192 in linker script for both 64-bit and
32-bit binaries. Removed unused variables in vdso2c.h. Added -mv8plus flag to
Makefile to prevent the generation of relocation entries for __lshrdi3 in 32-bit
vdso binary.
Signed-off-by: Nick Alcock <nick.alcock@oracle.com>
Signed-off-by: Nagarathnam Muthusamy <nagarathnam.muthusamy@oracle.com>
Reviewed-by: Shannon Nelson <shannon.nelson@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-21 23:05:31 +08:00
|
|
|
{
|
|
|
|
unsigned long seq;
|
|
|
|
u64 ns;
|
|
|
|
|
|
|
|
do {
|
|
|
|
seq = vvar_read_begin(vvar);
|
|
|
|
ts->tv_sec = vvar->wall_time_sec;
|
|
|
|
ns = vvar->wall_time_snsec;
|
|
|
|
ns += vgetsns(vvar);
|
|
|
|
ns >>= vvar->clock.shift;
|
|
|
|
} while (unlikely(vvar_read_retry(vvar, seq)));
|
|
|
|
|
2018-10-22 13:38:56 +08:00
|
|
|
ts->tv_sec += __iter_div_u64_rem(ns, NSEC_PER_SEC, &ns);
|
|
|
|
ts->tv_nsec = ns;
|
vDSO for sparc
Following patch is based on work done by Nick Alcock on 64-bit vDSO for sparc
in Oracle linux. I have extended it to include support for 32-bit vDSO for sparc
on 64-bit kernel.
vDSO for sparc is based on the X86 implementation. This patch
provides vDSO support for both 64-bit and 32-bit programs on 64-bit kernel.
vDSO will be disabled on 32-bit linux kernel on sparc.
*) vclock_gettime.c contains all the vdso functions. Since data page is mapped
before the vdso code page, the pointer to data page is got by subracting offset
from an address in the vdso code page. The return address stored in
%i7 is used for this purpose.
*) During compilation, both 32-bit and 64-bit vdso images are compiled and are
converted into raw bytes by vdso2c program to be ready for mapping into the
process. 32-bit images are compiled only if CONFIG_COMPAT is enabled. vdso2c
generates two files vdso-image-64.c and vdso-image-32.c which contains the
respective vDSO image in C structure.
*) During vdso initialization, required number of vdso pages are allocated and
raw bytes are copied into the pages.
*) During every exec, these pages are mapped into the process through
arch_setup_additional_pages and the location of mapping is passed on to the
process through aux vector AT_SYSINFO_EHDR which is used by glibc.
*) A new update_vsyscall routine for sparc is added to keep the data page in
vdso updated.
*) As vDSO cannot contain dynamically relocatable references, a new version of
cpu_relax is added for the use of vDSO.
This change also requires a putback to glibc to use vDSO. For testing,
programs planning to try vDSO can be compiled against the generated
vdso(64/32).so in the source.
Testing:
========
[root@localhost ~]# cat vdso_test.c
int main() {
struct timespec tv_start, tv_end;
struct timeval tv_tmp;
int i;
int count = 1 * 1000 * 10000;
long long diff;
clock_gettime(0, &tv_start);
for (i = 0; i < count; i++)
gettimeofday(&tv_tmp, NULL);
clock_gettime(0, &tv_end);
diff = (long long)(tv_end.tv_sec -
tv_start.tv_sec)*(1*1000*1000*1000);
diff += (tv_end.tv_nsec - tv_start.tv_nsec);
printf("Start sec: %d\n", tv_start.tv_sec);
printf("End sec : %d\n", tv_end.tv_sec);
printf("%d cycles in %lld ns = %f ns/cycle\n", count, diff,
(double)diff / (double)count);
return 0;
}
[root@localhost ~]# cc vdso_test.c -o t32_without_fix -m32 -lrt
[root@localhost ~]# ./t32_without_fix
Start sec: 1502396130
End sec : 1502396140
10000000 cycles in 9565148528 ns = 956.514853 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t32_with_fix -m32 ./vdso32.so.dbg
[root@localhost ~]# ./t32_with_fix
Start sec: 1502396168
End sec : 1502396169
10000000 cycles in 798141262 ns = 79.814126 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t64_without_fix -m64 -lrt
[root@localhost ~]# ./t64_without_fix
Start sec: 1502396208
End sec : 1502396218
10000000 cycles in 9846091800 ns = 984.609180 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t64_with_fix -m64 ./vdso64.so.dbg
[root@localhost ~]# ./t64_with_fix
Start sec: 1502396257
End sec : 1502396257
10000000 cycles in 380984048 ns = 38.098405 ns/cycle
V1 to V2 Changes:
=================
Added hot patching code to switch the read stick instruction to read
tick instruction based on the hardware.
V2 to V3 Changes:
=================
Merged latest changes from sparc-next and moved the initialization
of clocksource_tick.archdata.vclock_mode to time_init_early. Disabled
queued spinlock and rwlock configuration when simulating 32-bit config
to compile 32-bit VDSO.
V3 to V4 Changes:
=================
Hardcoded the page size as 8192 in linker script for both 64-bit and
32-bit binaries. Removed unused variables in vdso2c.h. Added -mv8plus flag to
Makefile to prevent the generation of relocation entries for __lshrdi3 in 32-bit
vdso binary.
Signed-off-by: Nick Alcock <nick.alcock@oracle.com>
Signed-off-by: Nagarathnam Muthusamy <nagarathnam.muthusamy@oracle.com>
Reviewed-by: Shannon Nelson <shannon.nelson@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-21 23:05:31 +08:00
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2018-10-26 01:36:19 +08:00
|
|
|
notrace static __always_inline int do_realtime_stick(struct vvar_data *vvar,
|
|
|
|
struct timespec *ts)
|
|
|
|
{
|
|
|
|
unsigned long seq;
|
|
|
|
u64 ns;
|
|
|
|
|
|
|
|
do {
|
|
|
|
seq = vvar_read_begin(vvar);
|
|
|
|
ts->tv_sec = vvar->wall_time_sec;
|
|
|
|
ns = vvar->wall_time_snsec;
|
|
|
|
ns += vgetsns_stick(vvar);
|
|
|
|
ns >>= vvar->clock.shift;
|
|
|
|
} while (unlikely(vvar_read_retry(vvar, seq)));
|
|
|
|
|
|
|
|
ts->tv_sec += __iter_div_u64_rem(ns, NSEC_PER_SEC, &ns);
|
|
|
|
ts->tv_nsec = ns;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2018-10-22 13:09:40 +08:00
|
|
|
notrace static __always_inline int do_monotonic(struct vvar_data *vvar,
|
|
|
|
struct timespec *ts)
|
vDSO for sparc
Following patch is based on work done by Nick Alcock on 64-bit vDSO for sparc
in Oracle linux. I have extended it to include support for 32-bit vDSO for sparc
on 64-bit kernel.
vDSO for sparc is based on the X86 implementation. This patch
provides vDSO support for both 64-bit and 32-bit programs on 64-bit kernel.
vDSO will be disabled on 32-bit linux kernel on sparc.
*) vclock_gettime.c contains all the vdso functions. Since data page is mapped
before the vdso code page, the pointer to data page is got by subracting offset
from an address in the vdso code page. The return address stored in
%i7 is used for this purpose.
*) During compilation, both 32-bit and 64-bit vdso images are compiled and are
converted into raw bytes by vdso2c program to be ready for mapping into the
process. 32-bit images are compiled only if CONFIG_COMPAT is enabled. vdso2c
generates two files vdso-image-64.c and vdso-image-32.c which contains the
respective vDSO image in C structure.
*) During vdso initialization, required number of vdso pages are allocated and
raw bytes are copied into the pages.
*) During every exec, these pages are mapped into the process through
arch_setup_additional_pages and the location of mapping is passed on to the
process through aux vector AT_SYSINFO_EHDR which is used by glibc.
*) A new update_vsyscall routine for sparc is added to keep the data page in
vdso updated.
*) As vDSO cannot contain dynamically relocatable references, a new version of
cpu_relax is added for the use of vDSO.
This change also requires a putback to glibc to use vDSO. For testing,
programs planning to try vDSO can be compiled against the generated
vdso(64/32).so in the source.
Testing:
========
[root@localhost ~]# cat vdso_test.c
int main() {
struct timespec tv_start, tv_end;
struct timeval tv_tmp;
int i;
int count = 1 * 1000 * 10000;
long long diff;
clock_gettime(0, &tv_start);
for (i = 0; i < count; i++)
gettimeofday(&tv_tmp, NULL);
clock_gettime(0, &tv_end);
diff = (long long)(tv_end.tv_sec -
tv_start.tv_sec)*(1*1000*1000*1000);
diff += (tv_end.tv_nsec - tv_start.tv_nsec);
printf("Start sec: %d\n", tv_start.tv_sec);
printf("End sec : %d\n", tv_end.tv_sec);
printf("%d cycles in %lld ns = %f ns/cycle\n", count, diff,
(double)diff / (double)count);
return 0;
}
[root@localhost ~]# cc vdso_test.c -o t32_without_fix -m32 -lrt
[root@localhost ~]# ./t32_without_fix
Start sec: 1502396130
End sec : 1502396140
10000000 cycles in 9565148528 ns = 956.514853 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t32_with_fix -m32 ./vdso32.so.dbg
[root@localhost ~]# ./t32_with_fix
Start sec: 1502396168
End sec : 1502396169
10000000 cycles in 798141262 ns = 79.814126 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t64_without_fix -m64 -lrt
[root@localhost ~]# ./t64_without_fix
Start sec: 1502396208
End sec : 1502396218
10000000 cycles in 9846091800 ns = 984.609180 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t64_with_fix -m64 ./vdso64.so.dbg
[root@localhost ~]# ./t64_with_fix
Start sec: 1502396257
End sec : 1502396257
10000000 cycles in 380984048 ns = 38.098405 ns/cycle
V1 to V2 Changes:
=================
Added hot patching code to switch the read stick instruction to read
tick instruction based on the hardware.
V2 to V3 Changes:
=================
Merged latest changes from sparc-next and moved the initialization
of clocksource_tick.archdata.vclock_mode to time_init_early. Disabled
queued spinlock and rwlock configuration when simulating 32-bit config
to compile 32-bit VDSO.
V3 to V4 Changes:
=================
Hardcoded the page size as 8192 in linker script for both 64-bit and
32-bit binaries. Removed unused variables in vdso2c.h. Added -mv8plus flag to
Makefile to prevent the generation of relocation entries for __lshrdi3 in 32-bit
vdso binary.
Signed-off-by: Nick Alcock <nick.alcock@oracle.com>
Signed-off-by: Nagarathnam Muthusamy <nagarathnam.muthusamy@oracle.com>
Reviewed-by: Shannon Nelson <shannon.nelson@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-21 23:05:31 +08:00
|
|
|
{
|
|
|
|
unsigned long seq;
|
|
|
|
u64 ns;
|
|
|
|
|
|
|
|
do {
|
|
|
|
seq = vvar_read_begin(vvar);
|
|
|
|
ts->tv_sec = vvar->monotonic_time_sec;
|
|
|
|
ns = vvar->monotonic_time_snsec;
|
|
|
|
ns += vgetsns(vvar);
|
|
|
|
ns >>= vvar->clock.shift;
|
|
|
|
} while (unlikely(vvar_read_retry(vvar, seq)));
|
|
|
|
|
2018-10-22 13:38:56 +08:00
|
|
|
ts->tv_sec += __iter_div_u64_rem(ns, NSEC_PER_SEC, &ns);
|
|
|
|
ts->tv_nsec = ns;
|
vDSO for sparc
Following patch is based on work done by Nick Alcock on 64-bit vDSO for sparc
in Oracle linux. I have extended it to include support for 32-bit vDSO for sparc
on 64-bit kernel.
vDSO for sparc is based on the X86 implementation. This patch
provides vDSO support for both 64-bit and 32-bit programs on 64-bit kernel.
vDSO will be disabled on 32-bit linux kernel on sparc.
*) vclock_gettime.c contains all the vdso functions. Since data page is mapped
before the vdso code page, the pointer to data page is got by subracting offset
from an address in the vdso code page. The return address stored in
%i7 is used for this purpose.
*) During compilation, both 32-bit and 64-bit vdso images are compiled and are
converted into raw bytes by vdso2c program to be ready for mapping into the
process. 32-bit images are compiled only if CONFIG_COMPAT is enabled. vdso2c
generates two files vdso-image-64.c and vdso-image-32.c which contains the
respective vDSO image in C structure.
*) During vdso initialization, required number of vdso pages are allocated and
raw bytes are copied into the pages.
*) During every exec, these pages are mapped into the process through
arch_setup_additional_pages and the location of mapping is passed on to the
process through aux vector AT_SYSINFO_EHDR which is used by glibc.
*) A new update_vsyscall routine for sparc is added to keep the data page in
vdso updated.
*) As vDSO cannot contain dynamically relocatable references, a new version of
cpu_relax is added for the use of vDSO.
This change also requires a putback to glibc to use vDSO. For testing,
programs planning to try vDSO can be compiled against the generated
vdso(64/32).so in the source.
Testing:
========
[root@localhost ~]# cat vdso_test.c
int main() {
struct timespec tv_start, tv_end;
struct timeval tv_tmp;
int i;
int count = 1 * 1000 * 10000;
long long diff;
clock_gettime(0, &tv_start);
for (i = 0; i < count; i++)
gettimeofday(&tv_tmp, NULL);
clock_gettime(0, &tv_end);
diff = (long long)(tv_end.tv_sec -
tv_start.tv_sec)*(1*1000*1000*1000);
diff += (tv_end.tv_nsec - tv_start.tv_nsec);
printf("Start sec: %d\n", tv_start.tv_sec);
printf("End sec : %d\n", tv_end.tv_sec);
printf("%d cycles in %lld ns = %f ns/cycle\n", count, diff,
(double)diff / (double)count);
return 0;
}
[root@localhost ~]# cc vdso_test.c -o t32_without_fix -m32 -lrt
[root@localhost ~]# ./t32_without_fix
Start sec: 1502396130
End sec : 1502396140
10000000 cycles in 9565148528 ns = 956.514853 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t32_with_fix -m32 ./vdso32.so.dbg
[root@localhost ~]# ./t32_with_fix
Start sec: 1502396168
End sec : 1502396169
10000000 cycles in 798141262 ns = 79.814126 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t64_without_fix -m64 -lrt
[root@localhost ~]# ./t64_without_fix
Start sec: 1502396208
End sec : 1502396218
10000000 cycles in 9846091800 ns = 984.609180 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t64_with_fix -m64 ./vdso64.so.dbg
[root@localhost ~]# ./t64_with_fix
Start sec: 1502396257
End sec : 1502396257
10000000 cycles in 380984048 ns = 38.098405 ns/cycle
V1 to V2 Changes:
=================
Added hot patching code to switch the read stick instruction to read
tick instruction based on the hardware.
V2 to V3 Changes:
=================
Merged latest changes from sparc-next and moved the initialization
of clocksource_tick.archdata.vclock_mode to time_init_early. Disabled
queued spinlock and rwlock configuration when simulating 32-bit config
to compile 32-bit VDSO.
V3 to V4 Changes:
=================
Hardcoded the page size as 8192 in linker script for both 64-bit and
32-bit binaries. Removed unused variables in vdso2c.h. Added -mv8plus flag to
Makefile to prevent the generation of relocation entries for __lshrdi3 in 32-bit
vdso binary.
Signed-off-by: Nick Alcock <nick.alcock@oracle.com>
Signed-off-by: Nagarathnam Muthusamy <nagarathnam.muthusamy@oracle.com>
Reviewed-by: Shannon Nelson <shannon.nelson@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-21 23:05:31 +08:00
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2018-10-26 01:36:19 +08:00
|
|
|
notrace static __always_inline int do_monotonic_stick(struct vvar_data *vvar,
|
|
|
|
struct timespec *ts)
|
|
|
|
{
|
|
|
|
unsigned long seq;
|
|
|
|
u64 ns;
|
|
|
|
|
|
|
|
do {
|
|
|
|
seq = vvar_read_begin(vvar);
|
|
|
|
ts->tv_sec = vvar->monotonic_time_sec;
|
|
|
|
ns = vvar->monotonic_time_snsec;
|
|
|
|
ns += vgetsns_stick(vvar);
|
|
|
|
ns >>= vvar->clock.shift;
|
|
|
|
} while (unlikely(vvar_read_retry(vvar, seq)));
|
|
|
|
|
|
|
|
ts->tv_sec += __iter_div_u64_rem(ns, NSEC_PER_SEC, &ns);
|
|
|
|
ts->tv_nsec = ns;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2018-10-22 13:09:40 +08:00
|
|
|
notrace static int do_realtime_coarse(struct vvar_data *vvar,
|
|
|
|
struct timespec *ts)
|
vDSO for sparc
Following patch is based on work done by Nick Alcock on 64-bit vDSO for sparc
in Oracle linux. I have extended it to include support for 32-bit vDSO for sparc
on 64-bit kernel.
vDSO for sparc is based on the X86 implementation. This patch
provides vDSO support for both 64-bit and 32-bit programs on 64-bit kernel.
vDSO will be disabled on 32-bit linux kernel on sparc.
*) vclock_gettime.c contains all the vdso functions. Since data page is mapped
before the vdso code page, the pointer to data page is got by subracting offset
from an address in the vdso code page. The return address stored in
%i7 is used for this purpose.
*) During compilation, both 32-bit and 64-bit vdso images are compiled and are
converted into raw bytes by vdso2c program to be ready for mapping into the
process. 32-bit images are compiled only if CONFIG_COMPAT is enabled. vdso2c
generates two files vdso-image-64.c and vdso-image-32.c which contains the
respective vDSO image in C structure.
*) During vdso initialization, required number of vdso pages are allocated and
raw bytes are copied into the pages.
*) During every exec, these pages are mapped into the process through
arch_setup_additional_pages and the location of mapping is passed on to the
process through aux vector AT_SYSINFO_EHDR which is used by glibc.
*) A new update_vsyscall routine for sparc is added to keep the data page in
vdso updated.
*) As vDSO cannot contain dynamically relocatable references, a new version of
cpu_relax is added for the use of vDSO.
This change also requires a putback to glibc to use vDSO. For testing,
programs planning to try vDSO can be compiled against the generated
vdso(64/32).so in the source.
Testing:
========
[root@localhost ~]# cat vdso_test.c
int main() {
struct timespec tv_start, tv_end;
struct timeval tv_tmp;
int i;
int count = 1 * 1000 * 10000;
long long diff;
clock_gettime(0, &tv_start);
for (i = 0; i < count; i++)
gettimeofday(&tv_tmp, NULL);
clock_gettime(0, &tv_end);
diff = (long long)(tv_end.tv_sec -
tv_start.tv_sec)*(1*1000*1000*1000);
diff += (tv_end.tv_nsec - tv_start.tv_nsec);
printf("Start sec: %d\n", tv_start.tv_sec);
printf("End sec : %d\n", tv_end.tv_sec);
printf("%d cycles in %lld ns = %f ns/cycle\n", count, diff,
(double)diff / (double)count);
return 0;
}
[root@localhost ~]# cc vdso_test.c -o t32_without_fix -m32 -lrt
[root@localhost ~]# ./t32_without_fix
Start sec: 1502396130
End sec : 1502396140
10000000 cycles in 9565148528 ns = 956.514853 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t32_with_fix -m32 ./vdso32.so.dbg
[root@localhost ~]# ./t32_with_fix
Start sec: 1502396168
End sec : 1502396169
10000000 cycles in 798141262 ns = 79.814126 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t64_without_fix -m64 -lrt
[root@localhost ~]# ./t64_without_fix
Start sec: 1502396208
End sec : 1502396218
10000000 cycles in 9846091800 ns = 984.609180 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t64_with_fix -m64 ./vdso64.so.dbg
[root@localhost ~]# ./t64_with_fix
Start sec: 1502396257
End sec : 1502396257
10000000 cycles in 380984048 ns = 38.098405 ns/cycle
V1 to V2 Changes:
=================
Added hot patching code to switch the read stick instruction to read
tick instruction based on the hardware.
V2 to V3 Changes:
=================
Merged latest changes from sparc-next and moved the initialization
of clocksource_tick.archdata.vclock_mode to time_init_early. Disabled
queued spinlock and rwlock configuration when simulating 32-bit config
to compile 32-bit VDSO.
V3 to V4 Changes:
=================
Hardcoded the page size as 8192 in linker script for both 64-bit and
32-bit binaries. Removed unused variables in vdso2c.h. Added -mv8plus flag to
Makefile to prevent the generation of relocation entries for __lshrdi3 in 32-bit
vdso binary.
Signed-off-by: Nick Alcock <nick.alcock@oracle.com>
Signed-off-by: Nagarathnam Muthusamy <nagarathnam.muthusamy@oracle.com>
Reviewed-by: Shannon Nelson <shannon.nelson@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-21 23:05:31 +08:00
|
|
|
{
|
|
|
|
unsigned long seq;
|
|
|
|
|
|
|
|
do {
|
|
|
|
seq = vvar_read_begin(vvar);
|
|
|
|
ts->tv_sec = vvar->wall_time_coarse_sec;
|
|
|
|
ts->tv_nsec = vvar->wall_time_coarse_nsec;
|
|
|
|
} while (unlikely(vvar_read_retry(vvar, seq)));
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2018-10-22 13:09:40 +08:00
|
|
|
notrace static int do_monotonic_coarse(struct vvar_data *vvar,
|
|
|
|
struct timespec *ts)
|
vDSO for sparc
Following patch is based on work done by Nick Alcock on 64-bit vDSO for sparc
in Oracle linux. I have extended it to include support for 32-bit vDSO for sparc
on 64-bit kernel.
vDSO for sparc is based on the X86 implementation. This patch
provides vDSO support for both 64-bit and 32-bit programs on 64-bit kernel.
vDSO will be disabled on 32-bit linux kernel on sparc.
*) vclock_gettime.c contains all the vdso functions. Since data page is mapped
before the vdso code page, the pointer to data page is got by subracting offset
from an address in the vdso code page. The return address stored in
%i7 is used for this purpose.
*) During compilation, both 32-bit and 64-bit vdso images are compiled and are
converted into raw bytes by vdso2c program to be ready for mapping into the
process. 32-bit images are compiled only if CONFIG_COMPAT is enabled. vdso2c
generates two files vdso-image-64.c and vdso-image-32.c which contains the
respective vDSO image in C structure.
*) During vdso initialization, required number of vdso pages are allocated and
raw bytes are copied into the pages.
*) During every exec, these pages are mapped into the process through
arch_setup_additional_pages and the location of mapping is passed on to the
process through aux vector AT_SYSINFO_EHDR which is used by glibc.
*) A new update_vsyscall routine for sparc is added to keep the data page in
vdso updated.
*) As vDSO cannot contain dynamically relocatable references, a new version of
cpu_relax is added for the use of vDSO.
This change also requires a putback to glibc to use vDSO. For testing,
programs planning to try vDSO can be compiled against the generated
vdso(64/32).so in the source.
Testing:
========
[root@localhost ~]# cat vdso_test.c
int main() {
struct timespec tv_start, tv_end;
struct timeval tv_tmp;
int i;
int count = 1 * 1000 * 10000;
long long diff;
clock_gettime(0, &tv_start);
for (i = 0; i < count; i++)
gettimeofday(&tv_tmp, NULL);
clock_gettime(0, &tv_end);
diff = (long long)(tv_end.tv_sec -
tv_start.tv_sec)*(1*1000*1000*1000);
diff += (tv_end.tv_nsec - tv_start.tv_nsec);
printf("Start sec: %d\n", tv_start.tv_sec);
printf("End sec : %d\n", tv_end.tv_sec);
printf("%d cycles in %lld ns = %f ns/cycle\n", count, diff,
(double)diff / (double)count);
return 0;
}
[root@localhost ~]# cc vdso_test.c -o t32_without_fix -m32 -lrt
[root@localhost ~]# ./t32_without_fix
Start sec: 1502396130
End sec : 1502396140
10000000 cycles in 9565148528 ns = 956.514853 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t32_with_fix -m32 ./vdso32.so.dbg
[root@localhost ~]# ./t32_with_fix
Start sec: 1502396168
End sec : 1502396169
10000000 cycles in 798141262 ns = 79.814126 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t64_without_fix -m64 -lrt
[root@localhost ~]# ./t64_without_fix
Start sec: 1502396208
End sec : 1502396218
10000000 cycles in 9846091800 ns = 984.609180 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t64_with_fix -m64 ./vdso64.so.dbg
[root@localhost ~]# ./t64_with_fix
Start sec: 1502396257
End sec : 1502396257
10000000 cycles in 380984048 ns = 38.098405 ns/cycle
V1 to V2 Changes:
=================
Added hot patching code to switch the read stick instruction to read
tick instruction based on the hardware.
V2 to V3 Changes:
=================
Merged latest changes from sparc-next and moved the initialization
of clocksource_tick.archdata.vclock_mode to time_init_early. Disabled
queued spinlock and rwlock configuration when simulating 32-bit config
to compile 32-bit VDSO.
V3 to V4 Changes:
=================
Hardcoded the page size as 8192 in linker script for both 64-bit and
32-bit binaries. Removed unused variables in vdso2c.h. Added -mv8plus flag to
Makefile to prevent the generation of relocation entries for __lshrdi3 in 32-bit
vdso binary.
Signed-off-by: Nick Alcock <nick.alcock@oracle.com>
Signed-off-by: Nagarathnam Muthusamy <nagarathnam.muthusamy@oracle.com>
Reviewed-by: Shannon Nelson <shannon.nelson@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-21 23:05:31 +08:00
|
|
|
{
|
|
|
|
unsigned long seq;
|
|
|
|
|
|
|
|
do {
|
|
|
|
seq = vvar_read_begin(vvar);
|
|
|
|
ts->tv_sec = vvar->monotonic_time_coarse_sec;
|
|
|
|
ts->tv_nsec = vvar->monotonic_time_coarse_nsec;
|
|
|
|
} while (unlikely(vvar_read_retry(vvar, seq)));
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
notrace int
|
|
|
|
__vdso_clock_gettime(clockid_t clock, struct timespec *ts)
|
|
|
|
{
|
|
|
|
struct vvar_data *vvd = get_vvar_data();
|
|
|
|
|
|
|
|
switch (clock) {
|
|
|
|
case CLOCK_REALTIME:
|
|
|
|
if (unlikely(vvd->vclock_mode == VCLOCK_NONE))
|
|
|
|
break;
|
|
|
|
return do_realtime(vvd, ts);
|
|
|
|
case CLOCK_MONOTONIC:
|
|
|
|
if (unlikely(vvd->vclock_mode == VCLOCK_NONE))
|
|
|
|
break;
|
|
|
|
return do_monotonic(vvd, ts);
|
|
|
|
case CLOCK_REALTIME_COARSE:
|
|
|
|
return do_realtime_coarse(vvd, ts);
|
|
|
|
case CLOCK_MONOTONIC_COARSE:
|
|
|
|
return do_monotonic_coarse(vvd, ts);
|
|
|
|
}
|
|
|
|
/*
|
|
|
|
* Unknown clock ID ? Fall back to the syscall.
|
|
|
|
*/
|
|
|
|
return vdso_fallback_gettime(clock, ts);
|
|
|
|
}
|
|
|
|
int
|
|
|
|
clock_gettime(clockid_t, struct timespec *)
|
|
|
|
__attribute__((weak, alias("__vdso_clock_gettime")));
|
|
|
|
|
2018-10-26 01:36:19 +08:00
|
|
|
notrace int
|
|
|
|
__vdso_clock_gettime_stick(clockid_t clock, struct timespec *ts)
|
|
|
|
{
|
|
|
|
struct vvar_data *vvd = get_vvar_data();
|
|
|
|
|
|
|
|
switch (clock) {
|
|
|
|
case CLOCK_REALTIME:
|
|
|
|
if (unlikely(vvd->vclock_mode == VCLOCK_NONE))
|
|
|
|
break;
|
|
|
|
return do_realtime_stick(vvd, ts);
|
|
|
|
case CLOCK_MONOTONIC:
|
|
|
|
if (unlikely(vvd->vclock_mode == VCLOCK_NONE))
|
|
|
|
break;
|
|
|
|
return do_monotonic_stick(vvd, ts);
|
|
|
|
case CLOCK_REALTIME_COARSE:
|
|
|
|
return do_realtime_coarse(vvd, ts);
|
|
|
|
case CLOCK_MONOTONIC_COARSE:
|
|
|
|
return do_monotonic_coarse(vvd, ts);
|
|
|
|
}
|
|
|
|
/*
|
|
|
|
* Unknown clock ID ? Fall back to the syscall.
|
|
|
|
*/
|
|
|
|
return vdso_fallback_gettime(clock, ts);
|
|
|
|
}
|
|
|
|
|
vDSO for sparc
Following patch is based on work done by Nick Alcock on 64-bit vDSO for sparc
in Oracle linux. I have extended it to include support for 32-bit vDSO for sparc
on 64-bit kernel.
vDSO for sparc is based on the X86 implementation. This patch
provides vDSO support for both 64-bit and 32-bit programs on 64-bit kernel.
vDSO will be disabled on 32-bit linux kernel on sparc.
*) vclock_gettime.c contains all the vdso functions. Since data page is mapped
before the vdso code page, the pointer to data page is got by subracting offset
from an address in the vdso code page. The return address stored in
%i7 is used for this purpose.
*) During compilation, both 32-bit and 64-bit vdso images are compiled and are
converted into raw bytes by vdso2c program to be ready for mapping into the
process. 32-bit images are compiled only if CONFIG_COMPAT is enabled. vdso2c
generates two files vdso-image-64.c and vdso-image-32.c which contains the
respective vDSO image in C structure.
*) During vdso initialization, required number of vdso pages are allocated and
raw bytes are copied into the pages.
*) During every exec, these pages are mapped into the process through
arch_setup_additional_pages and the location of mapping is passed on to the
process through aux vector AT_SYSINFO_EHDR which is used by glibc.
*) A new update_vsyscall routine for sparc is added to keep the data page in
vdso updated.
*) As vDSO cannot contain dynamically relocatable references, a new version of
cpu_relax is added for the use of vDSO.
This change also requires a putback to glibc to use vDSO. For testing,
programs planning to try vDSO can be compiled against the generated
vdso(64/32).so in the source.
Testing:
========
[root@localhost ~]# cat vdso_test.c
int main() {
struct timespec tv_start, tv_end;
struct timeval tv_tmp;
int i;
int count = 1 * 1000 * 10000;
long long diff;
clock_gettime(0, &tv_start);
for (i = 0; i < count; i++)
gettimeofday(&tv_tmp, NULL);
clock_gettime(0, &tv_end);
diff = (long long)(tv_end.tv_sec -
tv_start.tv_sec)*(1*1000*1000*1000);
diff += (tv_end.tv_nsec - tv_start.tv_nsec);
printf("Start sec: %d\n", tv_start.tv_sec);
printf("End sec : %d\n", tv_end.tv_sec);
printf("%d cycles in %lld ns = %f ns/cycle\n", count, diff,
(double)diff / (double)count);
return 0;
}
[root@localhost ~]# cc vdso_test.c -o t32_without_fix -m32 -lrt
[root@localhost ~]# ./t32_without_fix
Start sec: 1502396130
End sec : 1502396140
10000000 cycles in 9565148528 ns = 956.514853 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t32_with_fix -m32 ./vdso32.so.dbg
[root@localhost ~]# ./t32_with_fix
Start sec: 1502396168
End sec : 1502396169
10000000 cycles in 798141262 ns = 79.814126 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t64_without_fix -m64 -lrt
[root@localhost ~]# ./t64_without_fix
Start sec: 1502396208
End sec : 1502396218
10000000 cycles in 9846091800 ns = 984.609180 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t64_with_fix -m64 ./vdso64.so.dbg
[root@localhost ~]# ./t64_with_fix
Start sec: 1502396257
End sec : 1502396257
10000000 cycles in 380984048 ns = 38.098405 ns/cycle
V1 to V2 Changes:
=================
Added hot patching code to switch the read stick instruction to read
tick instruction based on the hardware.
V2 to V3 Changes:
=================
Merged latest changes from sparc-next and moved the initialization
of clocksource_tick.archdata.vclock_mode to time_init_early. Disabled
queued spinlock and rwlock configuration when simulating 32-bit config
to compile 32-bit VDSO.
V3 to V4 Changes:
=================
Hardcoded the page size as 8192 in linker script for both 64-bit and
32-bit binaries. Removed unused variables in vdso2c.h. Added -mv8plus flag to
Makefile to prevent the generation of relocation entries for __lshrdi3 in 32-bit
vdso binary.
Signed-off-by: Nick Alcock <nick.alcock@oracle.com>
Signed-off-by: Nagarathnam Muthusamy <nagarathnam.muthusamy@oracle.com>
Reviewed-by: Shannon Nelson <shannon.nelson@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-21 23:05:31 +08:00
|
|
|
notrace int
|
|
|
|
__vdso_gettimeofday(struct timeval *tv, struct timezone *tz)
|
|
|
|
{
|
|
|
|
struct vvar_data *vvd = get_vvar_data();
|
|
|
|
|
|
|
|
if (likely(vvd->vclock_mode != VCLOCK_NONE)) {
|
|
|
|
if (likely(tv != NULL)) {
|
|
|
|
union tstv_t {
|
|
|
|
struct timespec ts;
|
|
|
|
struct timeval tv;
|
|
|
|
} *tstv = (union tstv_t *) tv;
|
|
|
|
do_realtime(vvd, &tstv->ts);
|
|
|
|
/*
|
|
|
|
* Assign before dividing to ensure that the division is
|
|
|
|
* done in the type of tv_usec, not tv_nsec.
|
|
|
|
*
|
|
|
|
* There cannot be > 1 billion usec in a second:
|
|
|
|
* do_realtime() has already distributed such overflow
|
|
|
|
* into tv_sec. So we can assign it to an int safely.
|
|
|
|
*/
|
|
|
|
tstv->tv.tv_usec = tstv->ts.tv_nsec;
|
|
|
|
tstv->tv.tv_usec /= 1000;
|
|
|
|
}
|
|
|
|
if (unlikely(tz != NULL)) {
|
|
|
|
/* Avoid memcpy. Some old compilers fail to inline it */
|
|
|
|
tz->tz_minuteswest = vvd->tz_minuteswest;
|
|
|
|
tz->tz_dsttime = vvd->tz_dsttime;
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
return vdso_fallback_gettimeofday(tv, tz);
|
|
|
|
}
|
|
|
|
int
|
|
|
|
gettimeofday(struct timeval *, struct timezone *)
|
|
|
|
__attribute__((weak, alias("__vdso_gettimeofday")));
|
2018-10-26 01:36:19 +08:00
|
|
|
|
|
|
|
notrace int
|
|
|
|
__vdso_gettimeofday_stick(struct timeval *tv, struct timezone *tz)
|
|
|
|
{
|
|
|
|
struct vvar_data *vvd = get_vvar_data();
|
|
|
|
|
|
|
|
if (likely(vvd->vclock_mode != VCLOCK_NONE)) {
|
|
|
|
if (likely(tv != NULL)) {
|
|
|
|
union tstv_t {
|
|
|
|
struct timespec ts;
|
|
|
|
struct timeval tv;
|
|
|
|
} *tstv = (union tstv_t *) tv;
|
|
|
|
do_realtime_stick(vvd, &tstv->ts);
|
|
|
|
/*
|
|
|
|
* Assign before dividing to ensure that the division is
|
|
|
|
* done in the type of tv_usec, not tv_nsec.
|
|
|
|
*
|
|
|
|
* There cannot be > 1 billion usec in a second:
|
|
|
|
* do_realtime() has already distributed such overflow
|
|
|
|
* into tv_sec. So we can assign it to an int safely.
|
|
|
|
*/
|
|
|
|
tstv->tv.tv_usec = tstv->ts.tv_nsec;
|
|
|
|
tstv->tv.tv_usec /= 1000;
|
|
|
|
}
|
|
|
|
if (unlikely(tz != NULL)) {
|
|
|
|
/* Avoid memcpy. Some old compilers fail to inline it */
|
|
|
|
tz->tz_minuteswest = vvd->tz_minuteswest;
|
|
|
|
tz->tz_dsttime = vvd->tz_dsttime;
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
return vdso_fallback_gettimeofday(tv, tz);
|
|
|
|
}
|