Only allocate the FPU area when the application actually uses FPU, i.e., in the
first lazy FPU trap. This could save memory for non-fpu using apps.
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Cc: Arjan van de Ven <arjan@linux.intel.com>
---
Index: linux-2.6-x86/arch/x86/kernel/i387.c
===================================================================
--- linux-2.6-x86.orig/arch/x86/kernel/i387.c 2008-02-23 18:27:40.000000000 -0800
+++ linux-2.6-x86/arch/x86/kernel/i387.c 2008-02-23 18:27:41.000000000 -0800
@@ -9,7 +9,6 @@
#include <linux/sched.h>
#include <linux/module.h>
#include <linux/regset.h>
-#include <linux/bootmem.h>
#include <asm/processor.h>
#include <asm/i387.h>
#include <asm/math_emu.h>
@@ -67,7 +66,6 @@
else
math_cntxt_size = sizeof(struct i387_fsave_struct);
#endif
- init_task.thread.cntxt = alloc_bootmem(math_cntxt_size);
}
#ifdef CONFIG_X86_64
@@ -105,6 +103,9 @@
return;
}
+ if (!tsk->thread.cntxt)
+ tsk->thread.cntxt = alloc_cntxt_struct();
+
if (cpu_has_fxsr) {
memset(FXSAVE(tsk), 0, math_cntxt_size);
FXSAVE(tsk)->cwd = 0x37f;
Index: linux-2.6-x86/arch/x86/kernel/process.c
===================================================================
--- linux-2.6-x86.orig/arch/x86/kernel/process.c 2008-02-23 18:27:40.000000000 -0800
+++ linux-2.6-x86/arch/x86/kernel/process.c 2008-02-23 18:27:49.000000000 -0800
@@ -8,21 +8,25 @@
static struct kmem_cache *task_struct_cachep;
static struct kmem_cache *task_cntxt_cachep;
-struct task_struct * alloc_task_struct(void)
+union thread_cntxt *alloc_cntxt_struct(void)
+{
+ return kmem_cache_alloc(task_cntxt_cachep, GFP_KERNEL);
+}
+
+struct task_struct * alloc_task_struct(struct task_struct *src)
{
struct task_struct *tsk;
tsk = kmem_cache_alloc(task_struct_cachep, GFP_KERNEL);
- if (!tsk)
- return NULL;
- tsk->thread.cntxt = kmem_cache_alloc(task_cntxt_cachep, GFP_KERNEL);
- if (!tsk->thread.cntxt)
- goto error;
- WARN_ON((unsigned long)tsk->thread.cntxt & 15);
+ if (tsk && src->thread.cntxt) {
+ tsk->thread.cntxt = alloc_cntxt_struct();
+ if (!tsk->thread.cntxt) {
+ kmem_cache_free(task_struct_cachep, tsk);
+ return NULL;
+ }
+ WARN_ON((unsigned long)tsk->thread.cntxt & 15);
+ } else if (tsk)
+ tsk->thread.cntxt = NULL;
return tsk;
-
-error:
- kmem_cache_free(task_struct_cachep, tsk);
- return NULL;
}
void memcpy_task_struct(struct task_struct *dst, struct task_struct *src)
@@ -31,13 +35,21 @@
ptr = dst->thread.cntxt;
*dst = *src;
dst->thread.cntxt = ptr;
- memcpy(dst->thread.cntxt, src->thread.cntxt, math_cntxt_size);
+ if (src->thread.cntxt)
+ memcpy(dst->thread.cntxt, src->thread.cntxt, math_cntxt_size);
+}
+
+void free_cntxt_struct(struct task_struct *tsk)
+{
+ if (tsk->thread.cntxt) {
+ kmem_cache_free(task_cntxt_cachep, tsk->thread.cntxt);
+ tsk->thread.cntxt = NULL;
+ }
}
void free_task_struct(struct task_struct *tsk)
{
- kmem_cache_free(task_cntxt_cachep, tsk->thread.cntxt);
- tsk->thread.cntxt=NULL;
+ free_cntxt_struct(tsk);
kmem_cache_free(task_struct_cachep, tsk);
}
Index: linux-2.6-x86/include/asm-x86/i387.h
===================================================================
--- linux-2.6-x86.orig/include/asm-x86/i387.h 2008-02-23 18:27:40.000000000 -0800
+++ linux-2.6-x86/include/asm-x86/i387.h 2008-02-23 18:27:41.000000000 -0800
@@ -25,6 +25,7 @@
extern asmlinkage void math_state_restore(void);
extern void init_thread_context(void);
extern unsigned int math_cntxt_size;
+extern union thread_cntxt *alloc_cntxt_struct(void);
extern user_regset_active_fn fpregs_active, xfpregs_active;
extern user_regset_get_fn fpregs_get, xfpregs_get, fpregs_soft_get;
Index: linux-2.6-x86/include/asm-x86/processor.h
===================================================================
--- linux-2.6-x86.orig/include/asm-x86/processor.h 2008-02-23 18:27:40.000000000 -0800
+++ linux-2.6-x86/include/asm-x86/processor.h 2008-02-23 18:27:41.000000000 -0800
@@ -743,6 +743,8 @@
.io_bitmap = { [0 ... IO_BITMAP_LONGS] = ~0 }, \
}
+extern void free_cntxt_struct(struct task_struct *);
+
#define start_thread(regs, new_eip, new_esp) do { \
__asm__("movl %0,%%gs": :"r" (0)); \
regs->fs = 0; \
@@ -753,6 +755,7 @@
regs->cs = __USER_CS; \
regs->ip = new_eip; \
regs->sp = new_esp; \
+ free_cntxt_struct(current); \
} while (0)
Index: linux-2.6-x86/include/asm-x86/thread_info.h
===================================================================
--- linux-2.6-x86.orig/include/asm-x86/thread_info.h 2008-02-23 18:27:40.000000000 -0800
+++ linux-2.6-x86/include/asm-x86/thread_info.h 2008-02-23 18:27:41.000000000 -0800
@@ -6,7 +6,7 @@
#ifndef __ASSEMBLY__
#define __HAVE_ARCH_TASK_STRUCT_ALLOCATOR
-extern struct task_struct * alloc_task_struct(void);
+extern struct task_struct * alloc_task_struct(struct task_struct *src);
extern void free_task_struct(struct task_struct *tsk);
extern void memcpy_task_struct(struct task_struct *dst, struct task_struct *src
);
Index: linux-2.6-x86/kernel/fork.c
===================================================================
--- linux-2.6-x86.orig/kernel/fork.c 2008-02-23 18:27:40.000000000 -0800
+++ linux-2.6-x86/kernel/fork.c 2008-02-23 18:27:41.000000000 -0800
@@ -85,7 +85,7 @@
}
#ifndef __HAVE_ARCH_TASK_STRUCT_ALLOCATOR
-# define alloc_task_struct() kmem_cache_alloc(task_struct_cachep, GFP_KERNEL)
+# define alloc_task_struct(src) kmem_cache_alloc(task_struct_cachep, GFP_KERNEL)
# define free_task_struct(tsk) kmem_cache_free(task_struct_cachep, (tsk))
# define memcpy_task_struct(dst, src) do { *dst = *src; } while (0)
static struct kmem_cache *task_struct_cachep;
@@ -174,7 +174,7 @@
prepare_to_copy(orig);
- tsk = alloc_task_struct();
+ tsk = alloc_task_struct(orig);
if (!tsk)
return NULL;
--
--
