x86, fpu: split FPU state from task struct - v5

Split the FPU save area from the task struct. This allows easy migration
of FPU context, and it's generally cleaner. It also allows the following
two optimizations:

1) only allocate when the application actually uses FPU, so in the first
lazy FPU trap. This could save memory for non-fpu using apps. Next patch
does this lazy allocation.

2) allocate the right size for the actual cpu rather than 512 bytes always.
Patches enabling xsave/xrstor support (coming shortly) will take advantage
of this.

Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

5 files changed, 29 insertions, 25 deletions

diff --git a/include/asm-x86/i387.h b/include/asm-x86/i387.h
index 54522b814f1..382a5fa9d49 100644
--- a/include/asm-x86/i387.h
+++ b/include/asm-x86/i387.h
@@ -23,6 +23,7 @@ extern void fpu_init(void);
 extern void mxcsr_feature_mask_init(void);
 extern void init_fpu(struct task_struct *child);
 extern asmlinkage void math_state_restore(void);
+extern void init_thread_xstate(void);
 
 extern user_regset_active_fn fpregs_active, xfpregs_active;
 extern user_regset_get_fn fpregs_get, xfpregs_get, fpregs_soft_get;
@@ -117,24 +118,22 @@ static inline void __save_init_fpu(struct task_struct *tsk)
 	/* Using "fxsaveq %0" would be the ideal choice, but is only supported
 	   starting with gas 2.16. */
 	__asm__ __volatile__("fxsaveq %0"
-			     : "=m" (tsk->thread.i387.fxsave));
+			     : "=m" (tsk->thread.xstate->fxsave));
 #elif 0
 	/* Using, as a workaround, the properly prefixed form below isn't
 	   accepted by any binutils version so far released, complaining that
 	   the same type of prefix is used twice if an extended register is
 	   needed for addressing (fix submitted to mainline 2005-11-21). */
 	__asm__ __volatile__("rex64/fxsave %0"
-			     : "=m" (tsk->thread.i387.fxsave));
+			     : "=m" (tsk->thread.xstate->fxsave));
 #else
 	/* This, however, we can work around by forcing the compiler to select
 	   an addressing mode that doesn't require extended registers. */
-	__asm__ __volatile__("rex64/fxsave %P2(%1)"
-			     : "=m" (tsk->thread.i387.fxsave)
-			     : "cdaSDb" (tsk),
-				"i" (offsetof(__typeof__(*tsk),
-					      thread.i387.fxsave)));
+	__asm__ __volatile__("rex64/fxsave (%1)"
+			     : "=m" (tsk->thread.xstate->fxsave)
+			     : "cdaSDb" (&tsk->thread.xstate->fxsave));
 #endif
-	clear_fpu_state(&tsk->thread.i387.fxsave);
+	clear_fpu_state(&tsk->thread.xstate->fxsave);
 	task_thread_info(tsk)->status &= ~TS_USEDFPU;
 }
 
@@ -148,7 +147,7 @@ static inline int save_i387(struct _fpstate __user *buf)
 	int err = 0;
 
 	BUILD_BUG_ON(sizeof(struct user_i387_struct) !=
-			sizeof(tsk->thread.i387.fxsave));
+			sizeof(tsk->thread.xstate->fxsave));
 
 	if ((unsigned long)buf % 16)
 		printk("save_i387: bad fpstate %p\n", buf);
@@ -164,7 +163,7 @@ static inline int save_i387(struct _fpstate __user *buf)
 		task_thread_info(tsk)->status &= ~TS_USEDFPU;
 		stts();
 	} else {
-		if (__copy_to_user(buf, &tsk->thread.i387.fxsave,
+		if (__copy_to_user(buf, &tsk->thread.xstate->fxsave,
 				   sizeof(struct i387_fxsave_struct)))
 			return -1;
 	}
@@ -201,7 +200,7 @@ static inline void restore_fpu(struct task_struct *tsk)
 		"nop ; frstor %1",
 		"fxrstor %1",
 		X86_FEATURE_FXSR,
-		"m" ((tsk)->thread.i387.fxsave));
+		"m" (tsk->thread.xstate->fxsave));
 }
 
 /* We need a safe address that is cheap to find and that is already
@@ -225,8 +224,8 @@ static inline void __save_init_fpu(struct task_struct *tsk)
 		"fxsave %[fx]\n"
 		"bt $7,%[fsw] ; jnc 1f ; fnclex\n1:",
 		X86_FEATURE_FXSR,
-		[fx] "m" (tsk->thread.i387.fxsave),
-		[fsw] "m" (tsk->thread.i387.fxsave.swd) : "memory");
+		[fx] "m" (tsk->thread.xstate->fxsave),
+		[fsw] "m" (tsk->thread.xstate->fxsave.swd) : "memory");
 	/* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception
 	   is pending.  Clear the x87 state here by setting it to fixed
 	   values. safe_address is a random variable that should be in L1 */
@@ -327,25 +326,25 @@ static inline void clear_fpu(struct task_struct *tsk)
 static inline unsigned short get_fpu_cwd(struct task_struct *tsk)
 {
 	if (cpu_has_fxsr) {
-		return tsk->thread.i387.fxsave.cwd;
+		return tsk->thread.xstate->fxsave.cwd;
 	} else {
-		return (unsigned short)tsk->thread.i387.fsave.cwd;
+		return (unsigned short) tsk->thread.xstate->fsave.cwd;
 	}
 }
 
 static inline unsigned short get_fpu_swd(struct task_struct *tsk)
 {
 	if (cpu_has_fxsr) {
-		return tsk->thread.i387.fxsave.swd;
+		return tsk->thread.xstate->fxsave.swd;
 	} else {
-		return (unsigned short)tsk->thread.i387.fsave.swd;
+		return (unsigned short) tsk->thread.xstate->fsave.swd;
 	}
 }
 
 static inline unsigned short get_fpu_mxcsr(struct task_struct *tsk)
 {
 	if (cpu_has_xmm) {
-		return tsk->thread.i387.fxsave.mxcsr;
+		return tsk->thread.xstate->fxsave.mxcsr;
 	} else {
 		return MXCSR_DEFAULT;
 	}
diff --git a/include/asm-x86/processor.h b/include/asm-x86/processor.h
index eaf4548a23d..99d29788578 100644
--- a/include/asm-x86/processor.h
+++ b/include/asm-x86/processor.h
@@ -354,7 +354,7 @@ struct i387_soft_struct {
 	u32			entry_eip;
 };
 
-union i387_union {
+union thread_xstate {
 	struct i387_fsave_struct	fsave;
 	struct i387_fxsave_struct	fxsave;
 	struct i387_soft_struct		soft;
@@ -365,6 +365,7 @@ DECLARE_PER_CPU(struct orig_ist, orig_ist);
 #endif
 
 extern void print_cpu_info(struct cpuinfo_x86 *);
+extern unsigned int xstate_size;
 extern void init_scattered_cpuid_features(struct cpuinfo_x86 *c);
 extern unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c);
 extern unsigned short num_cache_leaves;
@@ -397,8 +398,8 @@ struct thread_struct {
 	unsigned long		cr2;
 	unsigned long		trap_no;
 	unsigned long		error_code;
-	/* Floating point info: */
-	union i387_union	i387 __attribute__((aligned(16)));;
+	/* floating point and extended processor state */
+	union thread_xstate	*xstate;
 #ifdef CONFIG_X86_32
 	/* Virtual 86 mode info */
 	struct vm86_struct __user *vm86_info;
diff --git a/include/asm-x86/thread_info.h b/include/asm-x86/thread_info.h
index d5fd12f2abd..407b88c170d 100644
--- a/include/asm-x86/thread_info.h
+++ b/include/asm-x86/thread_info.h
@@ -1,5 +1,13 @@
+#ifndef _ASM_X86_THREAD_INFO_H
 #ifdef CONFIG_X86_32
 # include "thread_info_32.h"
 #else
 # include "thread_info_64.h"
 #endif
+
+#ifndef __ASSEMBLY__
+extern void arch_task_cache_init(void);
+extern void free_thread_info(struct thread_info *ti);
+extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
+#endif
+#endif /* _ASM_X86_THREAD_INFO_H */
diff --git a/include/asm-x86/thread_info_32.h b/include/asm-x86/thread_info_32.h
index 4e053fa561a..53185996209 100644
--- a/include/asm-x86/thread_info_32.h
+++ b/include/asm-x86/thread_info_32.h
@@ -102,8 +102,6 @@ static inline struct thread_info *current_thread_info(void)
 	__get_free_pages(GFP_KERNEL, get_order(THREAD_SIZE)))
 #endif
 
-#define free_thread_info(info)	free_pages((unsigned long)(info), get_order(THREAD_SIZE))
-
 #else /* !__ASSEMBLY__ */
 
 /* how to get the thread information struct from ASM */
diff --git a/include/asm-x86/thread_info_64.h b/include/asm-x86/thread_info_64.h
index b17f5f6c2c5..ed664e874de 100644
--- a/include/asm-x86/thread_info_64.h
+++ b/include/asm-x86/thread_info_64.h
@@ -85,8 +85,6 @@ static inline struct thread_info *stack_thread_info(void)
 #define alloc_thread_info(tsk)						\
 	((struct thread_info *)__get_free_pages(THREAD_FLAGS, THREAD_ORDER))
 
-#define free_thread_info(ti) free_pages((unsigned long) (ti), THREAD_ORDER)
-
 #else /* !__ASSEMBLY__ */
 
 /* how to get the thread information struct from ASM */