[PATCH 2/2] Use alignment properties of vcpu to simplify FPU ops

[Rusty Russell <rusty-8n+1lVoiYb80n/F98K4Iww@public.gmane.org>]

Now we use a kmem cache for allocating vcpus, we can get the 16-byte
alignment required by fxsave & fxrstor instructions, and avoid
manually aligning the buffer.

Signed-off-by: Rusty Russell <rusty-8n+1lVoiYb80n/F98K4Iww@public.gmane.org>

diff -r 39421cbc0486 drivers/kvm/kvm.h
--- a/drivers/kvm/kvm.h	Mon Jul 30 15:01:44 2007 +1000
+++ b/drivers/kvm/kvm.h	Mon Jul 30 15:09:54 2007 +1000
@@ -43,10 +43,6 @@
 #define KVM_MIN_FREE_MMU_PAGES 5
 #define KVM_REFILL_PAGES 25
 #define KVM_MAX_CPUID_ENTRIES 40
-
-#define FX_IMAGE_SIZE 512
-#define FX_IMAGE_ALIGN 16
-#define FX_BUF_SIZE (2 * FX_IMAGE_SIZE + FX_IMAGE_ALIGN)
 
 #define DE_VECTOR 0
 #define NM_VECTOR 7
@@ -339,9 +335,8 @@ struct kvm_vcpu {
 
 	struct kvm_guest_debug guest_debug;
 
-	char fx_buf[FX_BUF_SIZE];
-	char *host_fx_image;
-	char *guest_fx_image;
+	struct i387_fxsave_struct host_fx_image;
+	struct i387_fxsave_struct guest_fx_image;
 	int fpu_active;
 	int guest_fpu_loaded;
 
@@ -697,12 +692,12 @@ static inline unsigned long read_msr(uns
 }
 #endif
 
-static inline void fx_save(void *image)
+static inline void fx_save(struct i387_fxsave_struct *image)
 {
 	asm ("fxsave (%0)":: "r" (image));
 }
 
-static inline void fx_restore(void *image)
+static inline void fx_restore(struct i387_fxsave_struct *image)
 {
 	asm ("fxrstor (%0)":: "r" (image));
 }
diff -r 39421cbc0486 drivers/kvm/kvm_main.c
--- a/drivers/kvm/kvm_main.c	Mon Jul 30 15:01:44 2007 +1000
+++ b/drivers/kvm/kvm_main.c	Mon Jul 30 15:10:09 2007 +1000
@@ -218,8 +218,8 @@ void kvm_load_guest_fpu(struct kvm_vcpu 
 		return;
 
 	vcpu->guest_fpu_loaded = 1;
-	fx_save(vcpu->host_fx_image);
-	fx_restore(vcpu->guest_fx_image);
+	fx_save(&vcpu->host_fx_image);
+	fx_restore(&vcpu->guest_fx_image);
 }
 EXPORT_SYMBOL_GPL(kvm_load_guest_fpu);
 
@@ -229,8 +229,8 @@ void kvm_put_guest_fpu(struct kvm_vcpu *
 		return;
 
 	vcpu->guest_fpu_loaded = 0;
-	fx_save(vcpu->guest_fx_image);
-	fx_restore(vcpu->host_fx_image);
+	fx_save(&vcpu->guest_fx_image);
+	fx_restore(&vcpu->host_fx_image);
 }
 EXPORT_SYMBOL_GPL(kvm_put_guest_fpu);
 
@@ -317,10 +317,6 @@ int kvm_vcpu_init(struct kvm_vcpu *vcpu,
 		goto fail_free_run;
 	}
 	vcpu->pio_data = page_address(page);
-
-	vcpu->host_fx_image = (char*)ALIGN((hva_t)vcpu->fx_buf,
-					   FX_IMAGE_ALIGN);
-	vcpu->guest_fx_image = vcpu->host_fx_image + FX_IMAGE_SIZE;
 
 	r = kvm_mmu_create(vcpu);
 	if (r < 0)
@@ -672,30 +668,20 @@ EXPORT_SYMBOL_GPL(set_cr8);
 
 void fx_init(struct kvm_vcpu *vcpu)
 {
-	struct __attribute__ ((__packed__)) fx_image_s {
-		u16 control; //fcw
-		u16 status; //fsw
-		u16 tag; // ftw
-		u16 opcode; //fop
-		u64 ip; // fpu ip
-		u64 operand;// fpu dp
-		u32 mxcsr;
-		u32 mxcsr_mask;
-
-	} *fx_image;
+	unsigned after_mxcsr_mask;
 
 	/* Initialize guest FPU by resetting ours and saving into guest's */
 	preempt_disable();
-	fx_save(vcpu->host_fx_image);
+	fx_save(&vcpu->host_fx_image);
 	fpu_init();
-	fx_save(vcpu->guest_fx_image);
-	fx_restore(vcpu->host_fx_image);
+	fx_save(&vcpu->guest_fx_image);
+	fx_restore(&vcpu->host_fx_image);
 	preempt_enable();
 
-	fx_image = (struct fx_image_s *)vcpu->guest_fx_image;
-	fx_image->mxcsr = 0x1f80;
-	memset(vcpu->guest_fx_image + sizeof(struct fx_image_s),
-	       0, FX_IMAGE_SIZE - sizeof(struct fx_image_s));
+	after_mxcsr_mask = offsetof(struct i387_fxsave_struct, st_space);
+	vcpu->guest_fx_image.mxcsr = 0x1f80;
+	memset((void *)&vcpu->guest_fx_image + after_mxcsr_mask,
+	       0, sizeof(struct i387_fxsave_struct) - after_mxcsr_mask);
 }
 EXPORT_SYMBOL_GPL(fx_init);
 
@@ -2414,6 +2400,9 @@ static int kvm_vm_ioctl_create_vcpu(stru
 	if (IS_ERR(vcpu))
 		return PTR_ERR(vcpu);
 
+	/* We do fxsave: this must be aligned. */
+	BUG_ON((unsigned long)&vcpu->host_fx_image & 0xF);
+
 	vcpu_load(vcpu);
 	r = kvm_mmu_setup(vcpu);
 	vcpu_put(vcpu);
@@ -2526,7 +2515,7 @@ struct fxsave {
 
 static int kvm_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 {
-	struct fxsave *fxsave = (struct fxsave *)vcpu->guest_fx_image;
+	struct fxsave *fxsave = (struct fxsave *)&vcpu->guest_fx_image;
 
 	vcpu_load(vcpu);
 
@@ -2546,7 +2535,7 @@ static int kvm_vcpu_ioctl_get_fpu(struct
 
 static int kvm_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 {
-	struct fxsave *fxsave = (struct fxsave *)vcpu->guest_fx_image;
+	struct fxsave *fxsave = (struct fxsave *)&vcpu->guest_fx_image;
 
 	vcpu_load(vcpu);
 
diff -r 39421cbc0486 drivers/kvm/svm.c
--- a/drivers/kvm/svm.c	Mon Jul 30 15:01:44 2007 +1000
+++ b/drivers/kvm/svm.c	Mon Jul 30 15:09:54 2007 +1000
@@ -1540,8 +1541,8 @@ again:
 	}
 
 	if (vcpu->fpu_active) {
-		fx_save(vcpu->host_fx_image);
-		fx_restore(vcpu->guest_fx_image);
+		fx_save(&vcpu->host_fx_image);
+		fx_restore(&vcpu->guest_fx_image);
 	}
 
 	asm volatile (
@@ -1653,8 +1654,8 @@ again:
 	vcpu->guest_mode = 0;
 
 	if (vcpu->fpu_active) {
-		fx_save(vcpu->guest_fx_image);
-		fx_restore(vcpu->host_fx_image);
+		fx_save(&vcpu->guest_fx_image);
+		fx_restore(&vcpu->host_fx_image);
 	}
 
 	if ((svm->vmcb->save.dr7 & 0xff))



-------------------------------------------------------------------------
This SF.net email is sponsored by: Splunk Inc.
Still grepping through log files to find problems?  Stop.
Now Search log events and configuration files using AJAX and a browser.
Download your FREE copy of Splunk now >>  http://get.splunk.com/