[PATCH v3 4.4.y 1/3] x86/fpu: Remove use_eager_fpu()

[PATCH v3 4.4.y 1/3] x86/fpu: Remove use_eager_fpu()

[Daniel Sangorrin]

From: Andy Lutomirski <luto@kernel.org>

commit c592b57347069abfc0dcad3b3a302cf882602597 upstream

This removes all the obvious code paths that depend on lazy FPU mode.
It shouldn't change the generated code at all.

Signed-off-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Rik van Riel <riel@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Quentin Casasnovas <quentin.casasnovas@oracle.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: pbonzini@redhat.com
Link: http://lkml.kernel.org/r/1475627678-20788-5-git-send-email-riel@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Daniel Sangorrin <daniel.sangorrin@toshiba.co.jp>
---
 arch/x86/crypto/crc32c-intel_glue.c | 17 ++++-------------
 arch/x86/include/asm/fpu/internal.h | 34 +--------------------------------
 arch/x86/kernel/fpu/core.c          | 38 +++++--------------------------------
 arch/x86/kernel/fpu/signal.c        |  8 +++-----
 arch/x86/kvm/cpuid.c                |  4 +---
 arch/x86/kvm/x86.c                  | 10 ----------
 6 files changed, 14 insertions(+), 97 deletions(-)

diff --git a/arch/x86/crypto/crc32c-intel_glue.c b/arch/x86/crypto/crc32c-intel_glue.c
index 15f5c76..d610c11 100644
--- a/arch/x86/crypto/crc32c-intel_glue.c
+++ b/arch/x86/crypto/crc32c-intel_glue.c
@@ -48,21 +48,13 @@
 #ifdef CONFIG_X86_64
 /*
  * use carryless multiply version of crc32c when buffer
- * size is >= 512 (when eager fpu is enabled) or
- * >= 1024 (when eager fpu is disabled) to account
+ * size is >= 512 to account
  * for fpu state save/restore overhead.
  */
-#define CRC32C_PCL_BREAKEVEN_EAGERFPU	512
-#define CRC32C_PCL_BREAKEVEN_NOEAGERFPU	1024
+#define CRC32C_PCL_BREAKEVEN	512
 
 asmlinkage unsigned int crc_pcl(const u8 *buffer, int len,
 				unsigned int crc_init);
-static int crc32c_pcl_breakeven = CRC32C_PCL_BREAKEVEN_EAGERFPU;
-#define set_pcl_breakeven_point()					\
-do {									\
-	if (!use_eager_fpu())						\
-		crc32c_pcl_breakeven = CRC32C_PCL_BREAKEVEN_NOEAGERFPU;	\
-} while (0)
 #endif /* CONFIG_X86_64 */
 
 static u32 crc32c_intel_le_hw_byte(u32 crc, unsigned char const *data, size_t length)
@@ -185,7 +177,7 @@ static int crc32c_pcl_intel_update(struct shash_desc *desc, const u8 *data,
 	 * use faster PCL version if datasize is large enough to
 	 * overcome kernel fpu state save/restore overhead
 	 */
-	if (len >= crc32c_pcl_breakeven && irq_fpu_usable()) {
+	if (len >= CRC32C_PCL_BREAKEVEN && irq_fpu_usable()) {
 		kernel_fpu_begin();
 		*crcp = crc_pcl(data, len, *crcp);
 		kernel_fpu_end();
@@ -197,7 +189,7 @@ static int crc32c_pcl_intel_update(struct shash_desc *desc, const u8 *data,
 static int __crc32c_pcl_intel_finup(u32 *crcp, const u8 *data, unsigned int len,
 				u8 *out)
 {
-	if (len >= crc32c_pcl_breakeven && irq_fpu_usable()) {
+	if (len >= CRC32C_PCL_BREAKEVEN && irq_fpu_usable()) {
 		kernel_fpu_begin();
 		*(__le32 *)out = ~cpu_to_le32(crc_pcl(data, len, *crcp));
 		kernel_fpu_end();
@@ -256,7 +248,6 @@ static int __init crc32c_intel_mod_init(void)
 		alg.update = crc32c_pcl_intel_update;
 		alg.finup = crc32c_pcl_intel_finup;
 		alg.digest = crc32c_pcl_intel_digest;
-		set_pcl_breakeven_point();
 	}
 #endif
 	return crypto_register_shash(&alg);
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index 146d838..7796e04 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -56,11 +56,6 @@ extern u64 fpu__get_supported_xfeatures_mask(void);
 /*
  * FPU related CPU feature flag helper routines:
  */
-static __always_inline __pure bool use_eager_fpu(void)
-{
-	return true;
-}
-
 static __always_inline __pure bool use_xsaveopt(void)
 {
 	return static_cpu_has_safe(X86_FEATURE_XSAVEOPT);
@@ -504,24 +499,6 @@ static inline int fpu_want_lazy_restore(struct fpu *fpu, unsigned int cpu)
 }
 
 
-/*
- * Wrap lazy FPU TS handling in a 'hw fpregs activation/deactivation'
- * idiom, which is then paired with the sw-flag (fpregs_active) later on:
- */
-
-static inline void __fpregs_activate_hw(void)
-{
-	if (!use_eager_fpu())
-		clts();
-}
-
-static inline void __fpregs_deactivate_hw(void)
-{
-	if (!use_eager_fpu())
-		stts();
-}
-
-/* Must be paired with an 'stts' (fpregs_deactivate_hw()) after! */
 static inline void __fpregs_deactivate(struct fpu *fpu)
 {
 	WARN_ON_FPU(!fpu->fpregs_active);
@@ -530,7 +507,6 @@ static inline void __fpregs_deactivate(struct fpu *fpu)
 	this_cpu_write(fpu_fpregs_owner_ctx, NULL);
 }
 
-/* Must be paired with a 'clts' (fpregs_activate_hw()) before! */
 static inline void __fpregs_activate(struct fpu *fpu)
 {
 	WARN_ON_FPU(fpu->fpregs_active);
@@ -555,22 +531,17 @@ static inline int fpregs_active(void)
 }
 
 /*
- * Encapsulate the CR0.TS handling together with the
- * software flag.
- *
  * These generally need preemption protection to work,
  * do try to avoid using these on their own.
  */
 static inline void fpregs_activate(struct fpu *fpu)
 {
-	__fpregs_activate_hw();
 	__fpregs_activate(fpu);
 }
 
 static inline void fpregs_deactivate(struct fpu *fpu)
 {
 	__fpregs_deactivate(fpu);
-	__fpregs_deactivate_hw();
 }
 
 /*
@@ -597,8 +568,7 @@ switch_fpu_prepare(struct fpu *old_fpu, struct fpu *new_fpu, int cpu)
 	 * or if the past 5 consecutive context-switches used math.
 	 */
 	fpu.preload = static_cpu_has(X86_FEATURE_FPU) &&
-		      new_fpu->fpstate_active &&
-		      (use_eager_fpu() || new_fpu->counter > 5);
+		      new_fpu->fpstate_active;
 
 	if (old_fpu->fpregs_active) {
 		if (!copy_fpregs_to_fpstate(old_fpu))
@@ -614,8 +584,6 @@ switch_fpu_prepare(struct fpu *old_fpu, struct fpu *new_fpu, int cpu)
 			new_fpu->counter++;
 			__fpregs_activate(new_fpu);
 			prefetch(&new_fpu->state);
-		} else {
-			__fpregs_deactivate_hw();
 		}
 	} else {
 		old_fpu->counter = 0;
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 6aa0b51..b282364 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -53,27 +53,9 @@ static bool kernel_fpu_disabled(void)
 	return this_cpu_read(in_kernel_fpu);
 }
 
-/*
- * Were we in an interrupt that interrupted kernel mode?
- *
- * On others, we can do a kernel_fpu_begin/end() pair *ONLY* if that
- * pair does nothing at all: the thread must not have fpu (so
- * that we don't try to save the FPU state), and TS must
- * be set (so that the clts/stts pair does nothing that is
- * visible in the interrupted kernel thread).
- *
- * Except for the eagerfpu case when we return true; in the likely case
- * the thread has FPU but we are not going to set/clear TS.
- */
 static bool interrupted_kernel_fpu_idle(void)
 {
-	if (kernel_fpu_disabled())
-		return false;
-
-	if (use_eager_fpu())
-		return true;
-
-	return !current->thread.fpu.fpregs_active && (read_cr0() & X86_CR0_TS);
+	return !kernel_fpu_disabled();
 }
 
 /*
@@ -121,7 +103,6 @@ void __kernel_fpu_begin(void)
 		copy_fpregs_to_fpstate(fpu);
 	} else {
 		this_cpu_write(fpu_fpregs_owner_ctx, NULL);
-		__fpregs_activate_hw();
 	}
 }
 EXPORT_SYMBOL(__kernel_fpu_begin);
@@ -132,8 +113,6 @@ void __kernel_fpu_end(void)
 
 	if (fpu->fpregs_active)
 		copy_kernel_to_fpregs(&fpu->state);
-	else
-		__fpregs_deactivate_hw();
 
 	kernel_fpu_enable();
 }
@@ -194,10 +173,7 @@ void fpu__save(struct fpu *fpu)
 	preempt_disable();
 	if (fpu->fpregs_active) {
 		if (!copy_fpregs_to_fpstate(fpu)) {
-			if (use_eager_fpu())
-				copy_kernel_to_fpregs(&fpu->state);
-			else
-				fpregs_deactivate(fpu);
+			copy_kernel_to_fpregs(&fpu->state);
 		}
 	}
 	preempt_enable();
@@ -245,8 +221,7 @@ static void fpu_copy(struct fpu *dst_fpu, struct fpu *src_fpu)
 	 * Don't let 'init optimized' areas of the XSAVE area
 	 * leak into the child task:
 	 */
-	if (use_eager_fpu())
-		memset(&dst_fpu->state.xsave, 0, xstate_size);
+	memset(&dst_fpu->state.xsave, 0, xstate_size);
 
 	/*
 	 * Save current FPU registers directly into the child
@@ -268,10 +243,7 @@ static void fpu_copy(struct fpu *dst_fpu, struct fpu *src_fpu)
 	if (!copy_fpregs_to_fpstate(dst_fpu)) {
 		memcpy(&src_fpu->state, &dst_fpu->state, xstate_size);
 
-		if (use_eager_fpu())
-			copy_kernel_to_fpregs(&src_fpu->state);
-		else
-			fpregs_deactivate(src_fpu);
+		copy_kernel_to_fpregs(&src_fpu->state);
 	}
 	preempt_enable();
 }
@@ -437,7 +409,7 @@ void fpu__clear(struct fpu *fpu)
 {
 	WARN_ON_FPU(fpu != &current->thread.fpu); /* Almost certainly an anomaly */
 
-	if (!use_eager_fpu() || !static_cpu_has(X86_FEATURE_FPU)) {
+	if (!static_cpu_has(X86_FEATURE_FPU)) {
 		/* FPU state will be reallocated lazily at the first use. */
 		fpu__drop(fpu);
 	} else {
diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index 3de0771..9be3e79 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -319,11 +319,9 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
 		}
 
 		fpu->fpstate_active = 1;
-		if (use_eager_fpu()) {
-			preempt_disable();
-			fpu__restore(fpu);
-			preempt_enable();
-		}
+		preempt_disable();
+		fpu__restore(fpu);
+		preempt_enable();
 
 		return err;
 	} else {
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 7b4ea5e..338d13d 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -16,7 +16,6 @@
 #include <linux/module.h>
 #include <linux/vmalloc.h>
 #include <linux/uaccess.h>
-#include <asm/fpu/internal.h> /* For use_eager_fpu.  Ugh! */
 #include <asm/user.h>
 #include <asm/fpu/xstate.h>
 #include "cpuid.h"
@@ -104,8 +103,7 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu)
 	if (best && (best->eax & (F(XSAVES) | F(XSAVEC))))
 		best->ebx = xstate_required_size(vcpu->arch.xcr0, true);
 
-	if (use_eager_fpu())
-		kvm_x86_ops->fpu_activate(vcpu);
+	kvm_x86_ops->fpu_activate(vcpu);
 
 	/*
 	 * The existing code assumes virtual address is 48-bit in the canonical
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 660d8a0..e6ab034 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -7319,16 +7319,6 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
 	copy_fpregs_to_fpstate(&vcpu->arch.guest_fpu);
 	__kernel_fpu_end();
 	++vcpu->stat.fpu_reload;
-	/*
-	 * If using eager FPU mode, or if the guest is a frequent user
-	 * of the FPU, just leave the FPU active for next time.
-	 * Every 255 times fpu_counter rolls over to 0; a guest that uses
-	 * the FPU in bursts will revert to loading it on demand.
-	 */
-	if (!use_eager_fpu()) {
-		if (++vcpu->fpu_counter < 5)
-			kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu);
-	}
 	trace_kvm_fpu(0);
 }
 
-- 
2.1.4

Re: [PATCH v3 4.4.y 1/3] x86/fpu: Remove use_eager_fpu()

[Greg Kroah-Hartman]

On Wed, Jul 11, 2018 at 09:48:38AM +0900, Daniel Sangorrin wrote:
> From: Andy Lutomirski <luto@kernel.org>
> 
> commit c592b57347069abfc0dcad3b3a302cf882602597 upstream
> 
> This removes all the obvious code paths that depend on lazy FPU mode.
> It shouldn't change the generated code at all.
> 
> Signed-off-by: Andy Lutomirski <luto@kernel.org>
> Signed-off-by: Rik van Riel <riel@redhat.com>
> Cc: Borislav Petkov <bp@alien8.de>
> Cc: Brian Gerst <brgerst@gmail.com>
> Cc: Dave Hansen <dave.hansen@linux.intel.com>
> Cc: Denys Vlasenko <dvlasenk@redhat.com>
> Cc: Fenghua Yu <fenghua.yu@intel.com>
> Cc: H. Peter Anvin <hpa@zytor.com>
> Cc: Josh Poimboeuf <jpoimboe@redhat.com>
> Cc: Linus Torvalds <torvalds@linux-foundation.org>
> Cc: Oleg Nesterov <oleg@redhat.com>
> Cc: Peter Zijlstra <peterz@infradead.org>
> Cc: Quentin Casasnovas <quentin.casasnovas@oracle.com>
> Cc: Thomas Gleixner <tglx@linutronix.de>
> Cc: pbonzini@redhat.com
> Link: http://lkml.kernel.org/r/1475627678-20788-5-git-send-email-riel@redhat.com
> Signed-off-by: Ingo Molnar <mingo@kernel.org>
> Signed-off-by: Daniel Sangorrin <daniel.sangorrin@toshiba.co.jp>
> ---
>  arch/x86/crypto/crc32c-intel_glue.c | 17 ++++-------------
>  arch/x86/include/asm/fpu/internal.h | 34 +--------------------------------
>  arch/x86/kernel/fpu/core.c          | 38 +++++--------------------------------
>  arch/x86/kernel/fpu/signal.c        |  8 +++-----
>  arch/x86/kvm/cpuid.c                |  4 +---
>  arch/x86/kvm/x86.c                  | 10 ----------
>  6 files changed, 14 insertions(+), 97 deletions(-)

This does not apply to the current 4.4.y tree.  Can you rebase this
series and resend it?

thanks,

greg k-h