linux-kernel - Re: [PATCH v2 4/8] powerpc/vdso32: inline __get

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <87h864iiq9.fsf@santosiv.in.ibm.com>
Date:   Mon, 26 Aug 2019 11:14:14 +0530
From:   Santosh Sivaraj <santosh@...six.org>
To:     Christophe Leroy <christophe.leroy@....fr>,
        Benjamin Herrenschmidt <benh@...nel.crashing.org>,
        Paul Mackerras <paulus@...ba.org>,
        Michael Ellerman <mpe@...erman.id.au>
Cc:     linuxppc-dev@...ts.ozlabs.org, linux-kernel@...r.kernel.org
Subject: Re: [PATCH v2 4/8] powerpc/vdso32: inline __get_datapage()

Hi Christophe,

Christophe Leroy <christophe.leroy@....fr> writes:

> __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@....fr>
> ---
>  arch/powerpc/kernel/vdso32/cacheflush.S   | 10 +++++-----
>  arch/powerpc/kernel/vdso32/datapage.S     | 29 ++++-------------------------
>  arch/powerpc/kernel/vdso32/datapage.h     | 11 +++++++++++
>  arch/powerpc/kernel/vdso32/gettimeofday.S | 13 ++++++-------
>  4 files changed, 26 insertions(+), 37 deletions(-)
>  create mode 100644 arch/powerpc/kernel/vdso32/datapage.h

The datapage.h file should ideally be moved under include/asm, then we can use
the same for powerpc64 too.

Santosh

>
> diff --git a/arch/powerpc/kernel/vdso32/cacheflush.S b/arch/powerpc/kernel/vdso32/cacheflush.S
> index 7f882e7b9f43..e9453837e4ee 100644
> --- a/arch/powerpc/kernel/vdso32/cacheflush.S
> +++ b/arch/powerpc/kernel/vdso32/cacheflush.S
> @@ -10,6 +10,8 @@
>  #include <asm/vdso.h>
>  #include <asm/asm-offsets.h>
>  
> +#include "datapage.h"
> +
>  	.text
>  
>  /*
> @@ -24,14 +26,12 @@ V_FUNCTION_BEGIN(__kernel_sync_dicache)
>    .cfi_startproc
>  	mflr	r12
>    .cfi_register lr,r12
> -	mr	r11,r3
> -	bl	__get_datapage@...al
> +	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 +48,7 @@ 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 6984125b9fc0..d480d2d4a3fe 100644
> --- a/arch/powerpc/kernel/vdso32/datapage.S
> +++ b/arch/powerpc/kernel/vdso32/datapage.S
> @@ -11,34 +11,13 @@
>  #include <asm/unistd.h>
>  #include <asm/vdso.h>
>  
> +#include "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 +32,7 @@ V_FUNCTION_BEGIN(__kernel_get_syscall_map)
>  	mflr	r12
>    .cfi_register lr,r12
>  	mr	r4,r3
> -	bl	__get_datapage@...al
> +	get_datapage	r3, r0
>  	mtlr	r12
>  	addi	r3,r3,CFG_SYSCALL_MAP32
>  	cmpli	cr0,r4,0
> @@ -74,7 +53,7 @@ V_FUNCTION_BEGIN(__kernel_get_tbfreq)
>    .cfi_startproc
>  	mflr	r12
>    .cfi_register lr,r12
> -	bl	__get_datapage@...al
> +	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/datapage.h b/arch/powerpc/kernel/vdso32/datapage.h
> new file mode 100644
> index 000000000000..74f4f57c2da8
> --- /dev/null
> +++ b/arch/powerpc/kernel/vdso32/datapage.h
> @@ -0,0 +1,11 @@
> +/* SPDX-License-Identifier: GPL-2.0-or-later */
> +
> +.macro get_datapage ptr, tmp
> +	bcl	20,31,.+4
> +	mflr	\ptr
> +	addi	\ptr, \ptr, __kernel_datapage_offset - (.-4)
> +	lwz	\tmp, 0(\ptr)
> +	add	\ptr, \tmp, \ptr
> +.endm
> +
> +
> diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S
> index 355b537d327a..3e55cba19f44 100644
> --- a/arch/powerpc/kernel/vdso32/gettimeofday.S
> +++ b/arch/powerpc/kernel/vdso32/gettimeofday.S
> @@ -12,6 +12,8 @@
>  #include <asm/asm-offsets.h>
>  #include <asm/unistd.h>
>  
> +#include "datapage.h"
> +
>  /* Offset for the low 32-bit part of a field of long type */
>  #ifdef CONFIG_PPC64
>  #define LOPART	4
> @@ -35,8 +37,7 @@ V_FUNCTION_BEGIN(__kernel_gettimeofday)
>  
>  	mr	r10,r3			/* r10 saves tv */
>  	mr	r11,r4			/* r11 saves tz */
> -	bl	__get_datapage@...al	/* 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 */
> @@ -82,8 +83,7 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
>  	mflr	r12			/* r12 saves lr */
>    .cfi_register lr,r12
>  	mr	r11,r4			/* r11 saves tp */
> -	bl	__get_datapage@...al	/* 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
>  	beq	cr5, .Lcoarse_clocks
> @@ -208,7 +208,7 @@ V_FUNCTION_BEGIN(__kernel_clock_getres)
>  
>  	mflr	r12
>    .cfi_register lr,r12
> -	bl	__get_datapage@...al	/* get data page */
> +	get_datapage	r3, r0
>  	lwz	r5, CLOCK_HRTIMER_RES(r3)
>  	mtlr	r12
>  	li	r3,0
> @@ -242,8 +242,7 @@ V_FUNCTION_BEGIN(__kernel_time)
>    .cfi_register lr,r12
>  
>  	mr	r11,r3			/* r11 holds t */
> -	bl	__get_datapage@...al
> -	mr	r9, r3			/* datapage ptr in r9 */
> +	get_datapage	r9, r0
>  
>  	lwz	r3,STAMP_XTIME+TSPEC_TV_SEC(r9)
>  
> -- 
> 2.13.3