linuxppc-dev.lists.ozlabs.org archive mirror
 help / color / mirror / Atom feed
From: Boqun Feng <boqun.feng@gmail.com>
To: Pan Xinhui <xinhui@linux.vnet.ibm.com>
Cc: linux-kernel@vger.kernel.org, linuxppc-dev@lists.ozlabs.org,
	benh@kernel.crashing.org, paulus@samba.org, mpe@ellerman.id.au,
	peterz@infradead.org, paulmck@linux.vnet.ibm.com,
	tglx@linutronix.de
Subject: Re: [PATCH V4] powerpc: Implement {cmp}xchg for u8 and u16
Date: Wed, 27 Apr 2016 21:58:17 +0800	[thread overview]
Message-ID: <20160427135817.GJ3369@insomnia> (raw)
In-Reply-To: <5720837D.6050807@linux.vnet.ibm.com>

[-- Attachment #1: Type: text/plain, Size: 7814 bytes --]

On Wed, Apr 27, 2016 at 05:16:45PM +0800, Pan Xinhui wrote:
> From: Pan Xinhui <xinhui.pan@linux.vnet.ibm.com>
> 
> Implement xchg{u8,u16}{local,relaxed}, and
> cmpxchg{u8,u16}{,local,acquire,relaxed}.
> 
> It works on all ppc.
> 
> remove volatile of first parameter in __cmpxchg_local and __cmpxchg
> 
> Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
> Signed-off-by: Pan Xinhui <xinhui.pan@linux.vnet.ibm.com>
> ---
> change from v3:
> 	rewrite in asm for the LL/SC.
> 	remove volatile in __cmpxchg_local and __cmpxchg.
> change from v2:
> 	in the do{}while(), we save one load and use corresponding cmpxchg suffix.
> 	Also add corresponding __cmpxchg_u32 function declaration in the __XCHG_GEN 
> change from V1:
> 	rework totally.
> ---
>  arch/powerpc/include/asm/cmpxchg.h | 109 ++++++++++++++++++++++++++++++++++++-
>  1 file changed, 106 insertions(+), 3 deletions(-)
> 
> diff --git a/arch/powerpc/include/asm/cmpxchg.h b/arch/powerpc/include/asm/cmpxchg.h
> index 44efe73..8a3735f 100644
> --- a/arch/powerpc/include/asm/cmpxchg.h
> +++ b/arch/powerpc/include/asm/cmpxchg.h
> @@ -7,6 +7,71 @@
>  #include <asm/asm-compat.h>
>  #include <linux/bug.h>
>  
> +#ifdef __BIG_ENDIAN
> +#define BITOFF_CAL(size, off)	((sizeof(u32) - size - off) * BITS_PER_BYTE)
> +#else
> +#define BITOFF_CAL(size, off)	(off * BITS_PER_BYTE)
> +#endif
> +
> +#define XCHG_GEN(type, sfx, cl)				\
> +static inline u32 __xchg_##type##sfx(void *p, u32 val)		\
> +{								\
> +	unsigned int prev, prev_mask, tmp, bitoff, off;		\
> +								\
> +	off = (unsigned long)p % sizeof(u32);			\
> +	bitoff = BITOFF_CAL(sizeof(type), off);			\
> +	p -= off;						\
> +	val <<= bitoff;						\
> +	prev_mask = (u32)(type)-1 << bitoff;			\
> +								\
> +	__asm__ __volatile__(					\
> +"1:	lwarx   %0,0,%3\n"					\
> +"	andc	%1,%0,%5\n"					\
> +"	or	%1,%1,%4\n"					\
> +	PPC405_ERR77(0,%3)					\
> +"	stwcx.	%1,0,%3\n"					\
> +"	bne-	1b\n"						\
> +	: "=&r" (prev), "=&r" (tmp), "+m" (*(u32*)p)		\

I think we can save the "tmp" here by:

	__asm__ volatile__(
"1:	lwarx	%0,0,%2\n"
"	andc	%0,%0,%4\n"
"	or	%0,%0,%3\n"
	PPC405_ERR77(0,%2)
"	stwcx.	%0,0,%2\n"
"	bne-	1b\n"
	: "=&r" (prev), "+m" (*(u32*)p)
	: "r" (p), "r" (val), "r" (prev_mask)
	: "cc", cl);

right?

> +	: "r" (p), "r" (val), "r" (prev_mask)			\
> +	: "cc", cl);						\
> +								\
> +	return prev >> bitoff;					\
> +}
> +
> +#define CMPXCHG_GEN(type, sfx, br, br2, cl)			\
> +static inline							\
> +u32 __cmpxchg_##type##sfx(void *p, u32 old, u32 new)		\
> +{								\
> +	unsigned int prev, prev_mask, tmp, bitoff, off;		\
> +								\
> +	off = (unsigned long)p % sizeof(u32);			\
> +	bitoff = BITOFF_CAL(sizeof(type), off);			\
> +	p -= off;						\
> +	old <<= bitoff;						\
> +	new <<= bitoff;						\
> +	prev_mask = (u32)(type)-1 << bitoff;			\
> +								\
> +	__asm__ __volatile__(					\
> +	br							\
> +"1:	lwarx   %0,0,%3\n"					\
> +"	and	%1,%0,%6\n"					\
> +"	cmpw	0,%1,%4\n"					\
> +"	bne-	2f\n"						\
> +"	andc	%1,%0,%6\n"					\
> +"	or	%1,%1,%5\n"					\
> +	PPC405_ERR77(0,%3)					\
> +"	stwcx.  %1,0,%3\n"					\
> +"	bne-    1b\n"						\
> +	br2							\
> +	"\n"							\
> +"2:"								\
> +	: "=&r" (prev), "=&r" (tmp), "+m" (*(u32*)p)		\

And "tmp" here could also be saved by:

"1:	lwarx   %0,0,%2\n"					\
"	xor	%3,%0,%3\n"					\
"	and.	%3,%3,%5\n"					\
"	bne-	2f\n"						\
"	andc	%0,%0,%5\n"					\
"	or	%0,%0,%4\n"					\
	PPC405_ERR77(0,%2)					\
"	stwcx.  %0,0,%2\n"					\
"	bne-    1b\n"						\
	br2							\
	"\n"							\
"2:"								\
	: "=&r" (prev), "+m" (*(u32*)p)		\
	: "r" (p), "r" (old), "r" (new), "r" (prev_mask)	\
	: "cc", cl);						\

right?

IIUC, saving the local variable "tmp" will result in saving a general
register for the compilers to use for other variables.

So thoughts?

Regards,
Boqun

> +	: "r" (p), "r" (old), "r" (new), "r" (prev_mask)	\
> +	: "cc", cl);						\
> +								\
> +	return prev >> bitoff;					\
> +}
> +
>  /*
>   * Atomic exchange
>   *
> @@ -14,6 +79,11 @@
>   * the previous value stored there.
>   */
>  
> +XCHG_GEN(u8, _local, "memory");
> +XCHG_GEN(u8, _relaxed, "cc");
> +XCHG_GEN(u16, _local, "memory");
> +XCHG_GEN(u16, _relaxed, "cc");
> +
>  static __always_inline unsigned long
>  __xchg_u32_local(volatile void *p, unsigned long val)
>  {
> @@ -85,9 +155,13 @@ __xchg_u64_relaxed(u64 *p, unsigned long val)
>  #endif
>  
>  static __always_inline unsigned long
> -__xchg_local(volatile void *ptr, unsigned long x, unsigned int size)
> +__xchg_local(void *ptr, unsigned long x, unsigned int size)
>  {
>  	switch (size) {
> +	case 1:
> +		return __xchg_u8_local(ptr, x);
> +	case 2:
> +		return __xchg_u16_local(ptr, x);
>  	case 4:
>  		return __xchg_u32_local(ptr, x);
>  #ifdef CONFIG_PPC64
> @@ -103,6 +177,10 @@ static __always_inline unsigned long
>  __xchg_relaxed(void *ptr, unsigned long x, unsigned int size)
>  {
>  	switch (size) {
> +	case 1:
> +		return __xchg_u8_relaxed(ptr, x);
> +	case 2:
> +		return __xchg_u16_relaxed(ptr, x);
>  	case 4:
>  		return __xchg_u32_relaxed(ptr, x);
>  #ifdef CONFIG_PPC64
> @@ -131,6 +209,15 @@ __xchg_relaxed(void *ptr, unsigned long x, unsigned int size)
>   * and return the old value of *p.
>   */
>  
> +CMPXCHG_GEN(u8, , PPC_ATOMIC_ENTRY_BARRIER, PPC_ATOMIC_EXIT_BARRIER, "memory");
> +CMPXCHG_GEN(u8, _local, , , "memory");
> +CMPXCHG_GEN(u8, _acquire, , PPC_ACQUIRE_BARRIER, "memory");
> +CMPXCHG_GEN(u8, _relaxed, , , "cc");
> +CMPXCHG_GEN(u16, , PPC_ATOMIC_ENTRY_BARRIER, PPC_ATOMIC_EXIT_BARRIER, "memory");
> +CMPXCHG_GEN(u16, _local, , , "memory");
> +CMPXCHG_GEN(u16, _acquire, , PPC_ACQUIRE_BARRIER, "memory");
> +CMPXCHG_GEN(u16, _relaxed, , , "cc");
> +
>  static __always_inline unsigned long
>  __cmpxchg_u32(volatile unsigned int *p, unsigned long old, unsigned long new)
>  {
> @@ -312,10 +399,14 @@ __cmpxchg_u64_acquire(u64 *p, unsigned long old, unsigned long new)
>  #endif
>  
>  static __always_inline unsigned long
> -__cmpxchg(volatile void *ptr, unsigned long old, unsigned long new,
> +__cmpxchg(void *ptr, unsigned long old, unsigned long new,
>  	  unsigned int size)
>  {
>  	switch (size) {
> +	case 1:
> +		return __cmpxchg_u8(ptr, old, new);
> +	case 2:
> +		return __cmpxchg_u16(ptr, old, new);
>  	case 4:
>  		return __cmpxchg_u32(ptr, old, new);
>  #ifdef CONFIG_PPC64
> @@ -328,10 +419,14 @@ __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new,
>  }
>  
>  static __always_inline unsigned long
> -__cmpxchg_local(volatile void *ptr, unsigned long old, unsigned long new,
> +__cmpxchg_local(void *ptr, unsigned long old, unsigned long new,
>  	  unsigned int size)
>  {
>  	switch (size) {
> +	case 1:
> +		return __cmpxchg_u8_local(ptr, old, new);
> +	case 2:
> +		return __cmpxchg_u16_local(ptr, old, new);
>  	case 4:
>  		return __cmpxchg_u32_local(ptr, old, new);
>  #ifdef CONFIG_PPC64
> @@ -348,6 +443,10 @@ __cmpxchg_relaxed(void *ptr, unsigned long old, unsigned long new,
>  		  unsigned int size)
>  {
>  	switch (size) {
> +	case 1:
> +		return __cmpxchg_u8_relaxed(ptr, old, new);
> +	case 2:
> +		return __cmpxchg_u16_relaxed(ptr, old, new);
>  	case 4:
>  		return __cmpxchg_u32_relaxed(ptr, old, new);
>  #ifdef CONFIG_PPC64
> @@ -364,6 +463,10 @@ __cmpxchg_acquire(void *ptr, unsigned long old, unsigned long new,
>  		  unsigned int size)
>  {
>  	switch (size) {
> +	case 1:
> +		return __cmpxchg_u8_acquire(ptr, old, new);
> +	case 2:
> +		return __cmpxchg_u16_acquire(ptr, old, new);
>  	case 4:
>  		return __cmpxchg_u32_acquire(ptr, old, new);
>  #ifdef CONFIG_PPC64
> -- 
> 2.4.3
> 

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 473 bytes --]

  reply	other threads:[~2016-04-27 13:55 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-04-19  6:29 [PATCH V2] powerpc: Implement {cmp}xchg for u8 and u16 Pan Xinhui
2016-04-19  9:18 ` Boqun Feng
2016-04-20  3:39   ` Pan Xinhui
2016-04-20 13:24 ` [PATCH V3] " Pan Xinhui
2016-04-20 14:24   ` Peter Zijlstra
2016-04-21 15:35     ` Pan Xinhui
2016-04-21 15:52       ` Boqun Feng
2016-04-22  1:59         ` Pan Xinhui
2016-04-22  3:16           ` Boqun Feng
2016-04-21 16:13       ` Peter Zijlstra
2016-04-25 10:10         ` Pan Xinhui
2016-04-25 15:37           ` Peter Zijlstra
2016-04-26 11:35             ` Pan Xinhui
2016-04-27  9:16   ` [PATCH V4] " Pan Xinhui
2016-04-27 13:58     ` Boqun Feng [this message]
2016-04-27 14:16       ` Boqun Feng
2016-04-27 14:50       ` Boqun Feng
2016-04-27 14:59         ` Boqun Feng
2016-04-28 10:21           ` Pan Xinhui
2016-04-28  7:59     ` Peter Zijlstra
2016-04-28 10:21       ` Pan Xinhui
2016-11-25  0:04     ` [V4] " Michael Ellerman

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=20160427135817.GJ3369@insomnia \
    --to=boqun.feng@gmail.com \
    --cc=benh@kernel.crashing.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linuxppc-dev@lists.ozlabs.org \
    --cc=mpe@ellerman.id.au \
    --cc=paulmck@linux.vnet.ibm.com \
    --cc=paulus@samba.org \
    --cc=peterz@infradead.org \
    --cc=tglx@linutronix.de \
    --cc=xinhui@linux.vnet.ibm.com \
    /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).