Commit 51fef6b3 authored by Andrew Morton's avatar Andrew Morton Committed by Linus Torvalds

[PATCH] speed up signals

2.5's signal delivery is 20% slower than 2.4.  A signal send/handle
cycle is performing a total of 24 copy_*_user() calls, and
copy_*_user() got optimised for large copies.

The patch reduces that to six copy_*_user() calls, and gets us up to
about 5% slower than 2.4.  We'd have to go back to some additional
inlined copy_user() code to get the last 3% back.  And HZ=100 to get
the 2% back.

It is noteworthy that the benchmark is not using float at all during
the body of the test, yet the kernel is still doing all that floating
point stuff.
parent 622d2a68
...@@ -232,7 +232,7 @@ void set_fpu_mxcsr( struct task_struct *tsk, unsigned short mxcsr ) ...@@ -232,7 +232,7 @@ void set_fpu_mxcsr( struct task_struct *tsk, unsigned short mxcsr )
* FXSR floating point environment conversions. * FXSR floating point environment conversions.
*/ */
static inline int convert_fxsr_to_user( struct _fpstate *buf, static int convert_fxsr_to_user( struct _fpstate *buf,
struct i387_fxsave_struct *fxsave ) struct i387_fxsave_struct *fxsave )
{ {
unsigned long env[7]; unsigned long env[7];
...@@ -254,13 +254,18 @@ static inline int convert_fxsr_to_user( struct _fpstate *buf, ...@@ -254,13 +254,18 @@ static inline int convert_fxsr_to_user( struct _fpstate *buf,
to = &buf->_st[0]; to = &buf->_st[0];
from = (struct _fpxreg *) &fxsave->st_space[0]; from = (struct _fpxreg *) &fxsave->st_space[0];
for ( i = 0 ; i < 8 ; i++, to++, from++ ) { for ( i = 0 ; i < 8 ; i++, to++, from++ ) {
if ( __copy_to_user( to, from, sizeof(*to) ) ) unsigned long *t = (unsigned long *)to;
unsigned long *f = (unsigned long *)from;
if (__put_user(*f, t) ||
__put_user(*(f + 1), t + 1) ||
__put_user(from->exponent, &to->exponent))
return 1; return 1;
} }
return 0; return 0;
} }
static inline int convert_fxsr_from_user( struct i387_fxsave_struct *fxsave, static int convert_fxsr_from_user( struct i387_fxsave_struct *fxsave,
struct _fpstate *buf ) struct _fpstate *buf )
{ {
unsigned long env[7]; unsigned long env[7];
...@@ -283,7 +288,12 @@ static inline int convert_fxsr_from_user( struct i387_fxsave_struct *fxsave, ...@@ -283,7 +288,12 @@ static inline int convert_fxsr_from_user( struct i387_fxsave_struct *fxsave,
to = (struct _fpxreg *) &fxsave->st_space[0]; to = (struct _fpxreg *) &fxsave->st_space[0];
from = &buf->_st[0]; from = &buf->_st[0];
for ( i = 0 ; i < 8 ; i++, to++, from++ ) { for ( i = 0 ; i < 8 ; i++, to++, from++ ) {
if ( __copy_from_user( to, from, sizeof(*from) ) ) unsigned long *t = (unsigned long *)to;
unsigned long *f = (unsigned long *)from;
if (__get_user(*f, t) ||
__get_user(*(f + 1), t + 1) ||
__get_user(from->exponent, &to->exponent))
return 1; return 1;
} }
return 0; return 0;
...@@ -305,7 +315,7 @@ static inline int save_i387_fsave( struct _fpstate *buf ) ...@@ -305,7 +315,7 @@ static inline int save_i387_fsave( struct _fpstate *buf )
return 1; return 1;
} }
static inline int save_i387_fxsave( struct _fpstate *buf ) static int save_i387_fxsave( struct _fpstate *buf )
{ {
struct task_struct *tsk = current; struct task_struct *tsk = current;
int err = 0; int err = 0;
...@@ -355,7 +365,7 @@ static inline int restore_i387_fsave( struct _fpstate *buf ) ...@@ -355,7 +365,7 @@ static inline int restore_i387_fsave( struct _fpstate *buf )
sizeof(struct i387_fsave_struct) ); sizeof(struct i387_fsave_struct) );
} }
static inline int restore_i387_fxsave( struct _fpstate *buf ) static int restore_i387_fxsave( struct _fpstate *buf )
{ {
int err; int err;
struct task_struct *tsk = current; struct task_struct *tsk = current;
...@@ -373,7 +383,7 @@ int restore_i387( struct _fpstate *buf ) ...@@ -373,7 +383,7 @@ int restore_i387( struct _fpstate *buf )
if ( HAVE_HWFP ) { if ( HAVE_HWFP ) {
if ( cpu_has_fxsr ) { if ( cpu_has_fxsr ) {
err = restore_i387_fxsave( buf ); err = restore_i387_fxsave( buf );
} else { } else {
err = restore_i387_fsave( buf ); err = restore_i387_fsave( buf );
} }
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment