Use correct macros in raid code, not raw asm
Subsystems (2)
PATCH 1/1 Use correct macros in raid code, not raw asm
This make sure it's paravirtualized correctly when CONFIG_PARAVIRT=y.
drivers/md/raid6x86.h +3 -2
@@ -75,13 +75,14 @@ static inline unsigned long raid6_get_fpunsigned long cr0;preempt_disable (); - asmvolatile ("mov %%cr0,%0 ; clts" :"=r" (cr0)); + cr0 =read_cr0 (); +clts ();return cr0; }static inline void raid6_put_fpu (unsigned long cr0) { - asmvolatile ("mov %0,%%cr0" : :"r" (cr0)); +write_cr0 (cr0);preempt_enable (); }
Quoted 2 lines · Rusty Russell
This make sure it's paravirtualized correctly when
CONFIG_PARAVIRT=y.
Why doesn't this code use "kernel_fpu_begin()" and "kernel_fpu_end()"?
The raid6 code is crap, and slower. It does "fsave/frstor" or movaps or other crud, and the thing is, it shouldn't. It should just do kernel_fpu_begin/end(), which does it all right, and avoids saving any state at all unless it's being used by the user RIGHT NOW.
Linus
Quoted 14 lines · On Fri, 29 Dec 2006 10:34:21 +1100 Rusty Russell <[email protected]> wrote:
This make sure it's paravirtualized correctly when
CONFIG_PARAVIRT=y.Signed-off-by Rusty Russell <[email protected]>diff -r
4ff048622391drivers/md/raid6x86.hdrivers/md/raid6x86.h +2
-1@@ -75,13 +75,14 @@ static inline unsigned long raid6_get_fpunsigned long cr0;preempt_disable (); - asmvolatile ("mov %%cr0,%0 ; clts" :"=r" (cr0)); + cr0 =read_cr0 (); +clts ();
drivers/md/raid6x86.h static inline unsigned long raid6_get_fp · line 88
Quoted 10 lines
drivers/md/raid6x86.h +1
-1return cr0; }static inline void raid6_put_fpu (unsigned long cr0) { - asmvolatile ("mov %0,%%cr0" : :"r" (cr0)); +write_cr0 (cr0);preempt_enable (); }
Perhaps we also need:
drivers/md/raid6x86.h renamed from drivers/md/raid6x86.h~use-correct-macros-in-raid-code-not-raw-asm-include +2 -0
@@ -21,6 +21,8 @@ #if defined(__i386__) || defined(__x86_64__) +#include <asm/system.h> + #ifdef __x86_64__ typedef struct {
_
?
Quoted 33 lines · Andrew Morton
Quoted 14 lines · On Fri, 29 Dec 2006 10:34:21 +1100 Rusty Russell <[email protected]> wrote:
This make sure it's paravirtualized correctly when
CONFIG_PARAVIRT=y.Signed-off-by Rusty Russell <[email protected]>diff -r
4ff048622391drivers/md/raid6x86.hdrivers/md/raid6x86.h +2
-1@@ -75,13 +75,14 @@ static inline unsigned long raid6_get_fpunsigned long cr0;preempt_disable (); - asmvolatile ("mov %%cr0,%0 ; clts" :"=r" (cr0)); + cr0 =read_cr0 (); +clts ();drivers/md/raid6x86.h static inline unsigned long raid6_get_fp · line 88
Quoted 10 lines
drivers/md/raid6x86.h +1
-1return cr0; }static inline void raid6_put_fpu (unsigned long cr0) { - asmvolatile ("mov %0,%%cr0" : :"r" (cr0)); +write_cr0 (cr0);preempt_enable (); }Perhaps we also need:
drivers/md/raid6x86.h line 25
Quoted 5 lines
drivers/md/raid6x86.h renamed from drivers/md/raid6x86.h~use-correct-macros-in-raid-code-not-raw-asm-include +2
-0@@ -21,6 +21,8 @@#if defined(__i386__) || defined(__x86_64__) +#include <asm/system.h> +
The code looks like it's designed to be included from userspace for testing; as it compiles without this include (and has no other includes), I chose not to add it.
Linus makes a good point, but someone who actually knows the code should, y'know, test it and stuff...
Rusty.
Quoted 7 lines
The code looks like it's designed to be included from userspace for testing; as it compiles without this include (and has no other includes), I chose not to add it.
Linus makes a good point, but someone who actually knows the code should, y'know, test it and stuff...
It should use kernel_fpu_begin() imho. If someone wants to test it in user space again they can add dummy definitions of that to their user space header.
-Andi
Quoted 10 lines · Andi Kleen
Quoted 6 lines
The code looks like it's designed to be included from userspace for testing; as it compiles without this include (and has no other includes), I chose not to add it.
Linus makes a good point, but someone who actually knows the code should, y'know, test it and stuff...
It should use
kernel_fpu_begin()imho. If someone wants to test it in user space again they can add dummy definitions of that to their user space header.
I hadn't seen this thread until now, when Neil pointed me to the thread.
Using kernel_fpu_begin() ... kernel_fpu_end() is probably indeed the best option.
-hpa
Quoted 11 lines · On Thursday February 8, [email protected] wrote:
Quoted 4 lines · Andi Kleen
It should use
kernel_fpu_begin()imho. If someone wants to test it in user space again they can add dummy definitions of that to their user space header.I hadn't seen this thread until now, when Neil pointed me to the thread.
Using
kernel_fpu_begin()...kernel_fpu_end()is probably indeed the best option.
So does this look right (no, I haven't compiled it yet)
NeilBrown
### Diffstat output
./drivers/md/raid6x86.h | 56 ++++++++++-------------------------------------- 1 file changed, 12 insertions(+), 44 deletions(-)
drivers/md/raid6x86.h +12 -44
@@ -25,20 +25,17 @@typedef struct {unsigned int fsave[27 ]; -unsigned long cr0; }raid6_mmx_save_t __attribute__((aligned (16 )));/* N.B.: For SSE we only save %xmm0-%xmm7 even for x86-64, since the code doesn't know about the additional x86-64 registers */ typedef struct {unsigned int sarea[8 *4 +2 ]; -unsigned long cr0; }raid6_sse_save_t __attribute__((aligned (16 )));/* This is for x86-64-specific code which uses all 16 XMM registers */ typedef struct {unsigned int sarea[16 *4 +2 ]; -unsigned long cr0; }raid6_sse16_save_t __attribute__((aligned (16 )));/* On x86-64 the stack *SHOULD* be 16-byte aligned, but currently this
@@ -50,7 +47,6 @@ typedef struct {typedef struct {unsigned int fsave[27 ]; -unsigned long cr0; }raid6_mmx_save_t ;/* On i386, the stack is only 8-byte aligned, but SSE requires 16-byte
@@ -58,7 +54,6 @@ typedef struct {a properly-sized area correctly. */ typedef struct {unsigned int sarea[8 *4 +3 ]; -unsigned long cr0; }raid6_sse_save_t ;/* Find the 16-byte aligned save area */
@@ -66,56 +61,29 @@ typedef struct {#endif -#ifdef __KERNEL__/* Real code */ - -/* Note: %cr0 is 32 bits on i386 and 64 bits on x86-64 */ - -static inline unsigned long raid6_get_fpu (void ) -{ -unsigned long cr0; - -preempt_disable (); - asmvolatile ("mov %%cr0,%0 ; clts" :"=r" (cr0)); -return cr0; -} - -static inline void raid6_put_fpu (unsigned long cr0) -{ - asmvolatile ("mov %0,%%cr0" : :"r" (cr0)); -preempt_enable (); -} - -#else /* Dummy code for user space testing */ - -static inline unsigned long raid6_get_fpu (void ) -{ -return 0xf00ba6 ; -} - -static inline void raid6_put_fpu (unsigned long cr0) -{ - (void )cr0; -} - +#ifndef __KERNEL__ +/* for user-space testing */ +#define kernel_fpu_begin () +#define kernel_fpu_end ();#endif static inline void raid6_before_mmx (raid6_mmx_save_t *s) { - s->cr0 =raid6_get_fpu (); +kernel_fpu_begin (); asmvolatile ("fsave %0 ; fwait" :"=m" (s->fsave[0 ])); }static inline void raid6_after_mmx (raid6_mmx_save_t *s) { asmvolatile ("frstor %0" : :"m" (s->fsave[0 ])); -raid6_put_fpu (s->cr0); +kernel_fpu_end (); }static inline void raid6_before_sse (raid6_sse_save_t *s) {unsigned int *rsa =SAREA (s); - s->cr0 =raid6_get_fpu (); +kernel_fpu_begin (); asmvolatile ("movaps %%xmm0,%0" :"=m" (rsa[0 ])); asmvolatile ("movaps %%xmm1,%0" :"=m" (rsa[4 ]));
@@ -140,14 +108,14 @@ static inline void raid6_after_sse(raid6 asmvolatile ("movaps %0,%%xmm6" : :"m" (rsa[24 ])); asmvolatile ("movaps %0,%%xmm7" : :"m" (rsa[28 ])); -raid6_put_fpu (s->cr0); +kernel_fpu_end (); }static inline void raid6_before_sse2 (raid6_sse_save_t *s) {unsigned int *rsa =SAREA (s); - s->cr0 =raid6_get_fpu (); +kernel_fpu_begin (); asmvolatile ("movdqa %%xmm0,%0" :"=m" (rsa[0 ])); asmvolatile ("movdqa %%xmm1,%0" :"=m" (rsa[4 ]));
@@ -172,7 +140,7 @@ static inline void raid6_after_sse2(raid asmvolatile ("movdqa %0,%%xmm6" : :"m" (rsa[24 ])); asmvolatile ("movdqa %0,%%xmm7" : :"m" (rsa[28 ])); -raid6_put_fpu (s->cr0); +kernel_fpu_end (); }#ifdef __x86_64__
@@ -181,7 +149,7 @@ static inline void raid6_before_sse16(ra {unsigned int *rsa =SAREA (s); - s->cr0 =raid6_get_fpu (); +kernel_fpu_begin (); asmvolatile ("movdqa %%xmm0,%0" :"=m" (rsa[0 ])); asmvolatile ("movdqa %%xmm1,%0" :"=m" (rsa[4 ]));
@@ -222,7 +190,7 @@ static inline void raid6_after_sse16(rai asmvolatile ("movdqa %0,%%xmm14" : :"m" (rsa[56 ])); asmvolatile ("movdqa %0,%%xmm15" : :"m" (rsa[60 ])); - raid6_put_fpu(s->cr0); + kernel_fpu_end(); }#endif /* __x86_64__ */
Quoted 3 lines · Neil Brown
So does this look right (no, I haven't compiled it yet)
No, the whole raid6_*_save_t should be removed. I'll try to have a patch for you later.
-hpa