From: Christophe Leroy <christophe.leroy@c-s.fr>
To: Benjamin Herrenschmidt <benh@kernel.crashing.org>,
Paul Mackerras <paulus@samba.org>,
Michael Ellerman <mpe@ellerman.id.au>,
arnd@arndb.de, tglx@linutronix.de, vincenzo.frascino@arm.com,
luto@kernel.org
Cc: linux-kernel@vger.kernel.org, linuxppc-dev@lists.ozlabs.org,
linux-arm-kernel@lists.infradead.org, linux-mips@vger.kernel.org,
x86@kernel.org
Subject: [RFC PATCH v2 09/10] powerpc/vdso32: inline __get_datapage()
Date: Mon, 23 Dec 2019 14:31:10 +0000 (UTC) [thread overview]
Message-ID: <4e44aca7d8c3b5ebb1453d499354ca5233d6defb.1577111367.git.christophe.leroy@c-s.fr> (raw)
In-Reply-To: <cover.1577111363.git.christophe.leroy@c-s.fr>
__get_datapage() is only a few instructions to retrieve the
address of the page where the kernel stores data to the VDSO.
By inlining this function into its users, a bl/blr pair and
a mflr/mtlr pair is avoided, plus a few reg moves.
The improvement is noticeable (about 55 nsec/call on an 8xx)
vdsotest before the patch:
gettimeofday: vdso: 731 nsec/call
clock-gettime-realtime-coarse: vdso: 668 nsec/call
clock-gettime-monotonic-coarse: vdso: 745 nsec/call
vdsotest after the patch:
gettimeofday: vdso: 677 nsec/call
clock-gettime-realtime-coarse: vdso: 613 nsec/call
clock-gettime-monotonic-coarse: vdso: 690 nsec/call
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
v3: define get_datapage macro in asm/vdso_datapage.h
v4: fixed build failure with old binutils
---
arch/powerpc/include/asm/vdso_datapage.h | 10 ++++++++++
arch/powerpc/kernel/vdso32/cacheflush.S | 9 ++++-----
arch/powerpc/kernel/vdso32/datapage.S | 28 +++-------------------------
arch/powerpc/kernel/vdso32/gettimeofday.S | 12 +++++-------
4 files changed, 22 insertions(+), 37 deletions(-)
diff --git a/arch/powerpc/include/asm/vdso_datapage.h b/arch/powerpc/include/asm/vdso_datapage.h
index 40f13f3626d3..ee5319a6f4e3 100644
--- a/arch/powerpc/include/asm/vdso_datapage.h
+++ b/arch/powerpc/include/asm/vdso_datapage.h
@@ -118,6 +118,16 @@ struct vdso_data {
extern struct vdso_data *vdso_data;
+#else /* __ASSEMBLY__ */
+
+.macro get_datapage ptr, tmp
+ bcl 20, 31, .+4
+ mflr \ptr
+ addi \ptr, \ptr, (__kernel_datapage_offset - (.-4))@l
+ lwz \tmp, 0(\ptr)
+ add \ptr, \tmp, \ptr
+.endm
+
#endif /* __ASSEMBLY__ */
#endif /* __KERNEL__ */
diff --git a/arch/powerpc/kernel/vdso32/cacheflush.S b/arch/powerpc/kernel/vdso32/cacheflush.S
index 7f882e7b9f43..d178ec8c279d 100644
--- a/arch/powerpc/kernel/vdso32/cacheflush.S
+++ b/arch/powerpc/kernel/vdso32/cacheflush.S
@@ -8,6 +8,7 @@
#include <asm/processor.h>
#include <asm/ppc_asm.h>
#include <asm/vdso.h>
+#include <asm/vdso_datapage.h>
#include <asm/asm-offsets.h>
.text
@@ -24,14 +25,12 @@ V_FUNCTION_BEGIN(__kernel_sync_dicache)
.cfi_startproc
mflr r12
.cfi_register lr,r12
- mr r11,r3
- bl __get_datapage@local
+ get_datapage r10, r0
mtlr r12
- mr r10,r3
lwz r7,CFG_DCACHE_BLOCKSZ(r10)
addi r5,r7,-1
- andc r6,r11,r5 /* round low to line bdy */
+ andc r6,r3,r5 /* round low to line bdy */
subf r8,r6,r4 /* compute length */
add r8,r8,r5 /* ensure we get enough */
lwz r9,CFG_DCACHE_LOGBLOCKSZ(r10)
@@ -48,7 +47,7 @@ V_FUNCTION_BEGIN(__kernel_sync_dicache)
lwz r7,CFG_ICACHE_BLOCKSZ(r10)
addi r5,r7,-1
- andc r6,r11,r5 /* round low to line bdy */
+ andc r6,r3,r5 /* round low to line bdy */
subf r8,r6,r4 /* compute length */
add r8,r8,r5
lwz r9,CFG_ICACHE_LOGBLOCKSZ(r10)
diff --git a/arch/powerpc/kernel/vdso32/datapage.S b/arch/powerpc/kernel/vdso32/datapage.S
index 6c7401bd284e..1095d818f94a 100644
--- a/arch/powerpc/kernel/vdso32/datapage.S
+++ b/arch/powerpc/kernel/vdso32/datapage.S
@@ -10,35 +10,13 @@
#include <asm/asm-offsets.h>
#include <asm/unistd.h>
#include <asm/vdso.h>
+#include <asm/vdso_datapage.h>
.text
.global __kernel_datapage_offset;
__kernel_datapage_offset:
.long 0
-V_FUNCTION_BEGIN(__get_datapage)
- .cfi_startproc
- /* We don't want that exposed or overridable as we want other objects
- * to be able to bl directly to here
- */
- .protected __get_datapage
- .hidden __get_datapage
-
- mflr r0
- .cfi_register lr,r0
-
- bcl 20,31,data_page_branch
-data_page_branch:
- mflr r3
- mtlr r0
- addi r3, r3, __kernel_datapage_offset-data_page_branch
- lwz r0,0(r3)
- .cfi_restore lr
- add r3,r0,r3
- blr
- .cfi_endproc
-V_FUNCTION_END(__get_datapage)
-
/*
* void *__kernel_get_syscall_map(unsigned int *syscall_count) ;
*
@@ -53,7 +31,7 @@ V_FUNCTION_BEGIN(__kernel_get_syscall_map)
mflr r12
.cfi_register lr,r12
mr r4,r3
- bl __get_datapage@local
+ get_datapage r3, r0
mtlr r12
addi r3,r3,CFG_SYSCALL_MAP32
cmpli cr0,r4,0
@@ -75,7 +53,7 @@ V_FUNCTION_BEGIN(__kernel_get_tbfreq)
.cfi_startproc
mflr r12
.cfi_register lr,r12
- bl __get_datapage@local
+ get_datapage r3, r0
lwz r4,(CFG_TB_TICKS_PER_SEC + 4)(r3)
lwz r3,CFG_TB_TICKS_PER_SEC(r3)
mtlr r12
diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S
index 3306672f57a9..d6c1d331e8cb 100644
--- a/arch/powerpc/kernel/vdso32/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso32/gettimeofday.S
@@ -9,6 +9,7 @@
#include <asm/processor.h>
#include <asm/ppc_asm.h>
#include <asm/vdso.h>
+#include <asm/vdso_datapage.h>
#include <asm/asm-offsets.h>
#include <asm/unistd.h>
@@ -33,8 +34,7 @@ V_FUNCTION_BEGIN(__kernel_gettimeofday)
mr r10,r3 /* r10 saves tv */
mr r11,r4 /* r11 saves tz */
- bl __get_datapage@local /* get data page */
- mr r9, r3 /* datapage ptr in r9 */
+ get_datapage r9, r0
cmplwi r10,0 /* check if tv is NULL */
beq 3f
lis r7,1000000@ha /* load up USEC_PER_SEC */
@@ -74,8 +74,7 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
mflr r12 /* r12 saves lr */
.cfi_register lr,r12
mr r11,r4 /* r11 saves tp */
- bl __get_datapage@local /* get data page */
- mr r9,r3 /* datapage ptr in r9 */
+ get_datapage r9, r0
lis r7,NSEC_PER_SEC@h /* want nanoseconds */
ori r7,r7,NSEC_PER_SEC@l
50: bl __do_get_tspec@local /* get sec/nsec from tb & kernel */
@@ -156,7 +155,7 @@ V_FUNCTION_BEGIN(__kernel_clock_getres)
mflr r12
.cfi_register lr,r12
- bl __get_datapage@local /* get data page */
+ get_datapage r3, r0
lwz r5, CLOCK_HRTIMER_RES(r3)
mtlr r12
li r3,0
@@ -190,8 +189,7 @@ V_FUNCTION_BEGIN(__kernel_time)
.cfi_register lr,r12
mr r11,r3 /* r11 holds t */
- bl __get_datapage@local
- mr r9, r3 /* datapage ptr in r9 */
+ get_datapage r9, r0
lwz r3,STAMP_XTIME_SEC+LOPART(r9)
--
2.13.3
next prev parent reply other threads:[~2019-12-23 14:31 UTC|newest]
Thread overview: 45+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-12-23 14:31 [RFC PATCH v2 00/10] powerpc/32: switch VDSO to C implementation Christophe Leroy
2019-12-23 14:31 ` [RFC PATCH v2 01/10] lib: vdso: ensure all arches have 32bit fallback Christophe Leroy
2019-12-24 2:07 ` Andy Lutomirski
2020-01-10 20:56 ` Thomas Gleixner
2020-01-10 21:02 ` Andy Lutomirski
2019-12-30 12:27 ` Arnd Bergmann
2020-01-02 11:29 ` Arnd Bergmann
2020-01-09 15:43 ` Christophe Leroy
2019-12-23 14:31 ` [RFC PATCH v2 02/10] lib: vdso: move call to fallback out of common code Christophe Leroy
2019-12-24 2:24 ` Andy Lutomirski
2019-12-24 11:41 ` christophe leroy
2019-12-24 12:09 ` Andy Lutomirski
2019-12-23 14:31 ` [RFC PATCH v2 03/10] lib: vdso: Change __cvdso_clock_gettime/getres_common() to __cvdso_clock_gettime/getres() Christophe Leroy
2019-12-23 14:31 ` [RFC PATCH v2 04/10] lib: vdso: get pointer to vdso data from the arch Christophe Leroy
2019-12-24 2:27 ` Andy Lutomirski
2019-12-24 11:53 ` christophe leroy
2019-12-24 12:15 ` Andy Lutomirski
2019-12-24 12:41 ` Andy Lutomirski
2019-12-24 14:46 ` Segher Boessenkool
2019-12-23 14:31 ` [RFC PATCH v2 05/10] lib: vdso: inline do_hres() Christophe Leroy
2019-12-24 2:29 ` Andy Lutomirski
2019-12-30 12:07 ` Arnd Bergmann
2020-01-10 21:07 ` Thomas Gleixner
2020-01-11 9:06 ` Christophe Leroy
2019-12-23 14:31 ` [RFC PATCH v2 06/10] lib: vdso: make do_coarse() return 0 Christophe Leroy
2019-12-23 14:31 ` [RFC PATCH v2 07/10] lib: vdso: don't use READ_ONCE() in __c_kernel_time() Christophe Leroy
2019-12-24 1:58 ` Andy Lutomirski
2019-12-24 11:12 ` christophe leroy
2019-12-24 12:04 ` Andy Lutomirski
2020-01-10 21:12 ` Thomas Gleixner
2020-01-11 8:05 ` Christophe Leroy
2020-01-11 11:07 ` Thomas Gleixner
2020-01-13 6:52 ` Christophe Leroy
2019-12-23 14:31 ` [RFC PATCH v2 08/10] lib: vdso: Avoid duplication in __cvdso_clock_getres() Christophe Leroy
2019-12-24 1:59 ` Andy Lutomirski
2019-12-23 14:31 ` Christophe Leroy [this message]
2019-12-23 14:31 ` [RFC PATCH v2 10/10] powerpc/32: Switch VDSO to C implementation Christophe Leroy
2020-01-09 17:52 ` Surprising code generated for vdso_read_begin() Christophe Leroy
2020-01-09 20:07 ` Segher Boessenkool
2020-01-10 6:45 ` Christophe Leroy
2020-01-11 11:33 ` Segher Boessenkool
2020-02-16 18:10 ` Arnd Bergmann
2020-02-19 8:45 ` Christophe Leroy
2020-02-19 9:52 ` Arnd Bergmann
2020-02-19 13:08 ` Segher Boessenkool
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=4e44aca7d8c3b5ebb1453d499354ca5233d6defb.1577111367.git.christophe.leroy@c-s.fr \
--to=christophe.leroy@c-s.fr \
--cc=arnd@arndb.de \
--cc=benh@kernel.crashing.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mips@vger.kernel.org \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=luto@kernel.org \
--cc=mpe@ellerman.id.au \
--cc=paulus@samba.org \
--cc=tglx@linutronix.de \
--cc=vincenzo.frascino@arm.com \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).