Remove fpu lazy mode deadcode from 4.9.y

Remove fpu lazy mode deadcode from 4.9.y

[Daniel Sangorrin]

Hello Greg,

Following up on our discussion during the review of
kernel 4.4.138-stable, I have backported a few
patches that remove the remaining FPU lazy mode deadcode
from 4.4.y and 4.9.y. To avoid confusion I will send the
explanation on separate e-mails:

Patches for 4.9.y:

[PATCH 1/4] x86/fpu: Remove use_eager_fpu()
 -> I only had to solve a small conflict caused by the fact that
 commit  b22cbe404a9c ("x86/fpu: Fix invalid FPU ptrace state after execve()")
 had been applied before (it was supposed to come after)

[PATCH 2/4] x86/fpu: Remove struct fpu::counter
 -> This is just a git cherry-pick of 3913cc350757 ("x86/fpu: Remove struct fpu::counter")
 which applies cleanly on 4.9.y. You can cherry-pick it instead of applying my patch.

[PATCH 3/4] Revert "perf: sync up x86/.../cpufeatures.h"
 -> Sorry to revert your patch ;). This was just for the next patch to apply cleanly.

[PATCH 4/4] x86/fpu: Finish excising 'eagerfpu'
 -> Again you can use a cherry pick of e63650840e8b ("x86/fpu: Finish excising 'eagerfpu'")
 instead of applying my patch.

Tested on x86_64 only with:
  - ./runltp  -f math (all tests pass)
  - IEEE 754 tests (no regressions seen)
    Ref: http://www.math.utah.edu/~beebe/software/ieee/
  [Note] I could not prepare a x86 32-bit machine to test no387
  [Note] If someone knows better about testing the FPU please let me know.

Best regards,
Daniel Sangorrin

PS: Using git send-email --cc-cmd="scripts/get_maintainer.pl" for the first time. Apologies if this is not the right method.

[PATCH 1/4] 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          | 36 ++++--------------------------------
 arch/x86/kernel/fpu/signal.c        |  8 +++-----
 arch/x86/kernel/fpu/xstate.c        |  9 ---------
 arch/x86/kvm/cpuid.c                |  4 +---
 arch/x86/kvm/x86.c                  | 10 ----------
 7 files changed, 13 insertions(+), 105 deletions(-)

diff --git a/arch/x86/crypto/crc32c-intel_glue.c b/arch/x86/crypto/crc32c-intel_glue.c
index dd19584..5773e11 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();
@@ -257,7 +249,6 @@ 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 8852e3a..7801d32 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -60,11 +60,6 @@ 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(X86_FEATURE_XSAVEOPT);
@@ -501,24 +496,6 @@ 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);
@@ -528,7 +505,6 @@ static inline void __fpregs_deactivate(struct fpu *fpu)
 	trace_x86_fpu_regs_deactivated(fpu);
 }
 
-/* Must be paired with a 'clts' (fpregs_activate_hw()) before! */
 static inline void __fpregs_activate(struct fpu *fpu)
 {
 	WARN_ON_FPU(fpu->fpregs_active);
@@ -554,22 +530,17 @@ 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();
 }
 
 /*
@@ -596,8 +567,7 @@ 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))
@@ -615,8 +585,6 @@ switch_fpu_prepare(struct fpu *old_fpu, struct fpu *new_fpu, int cpu)
 			__fpregs_activate(new_fpu);
 			trace_x86_fpu_regs_activated(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 96d80df..2dc1927 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -58,27 +58,9 @@ 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();
 }
 
 /*
@@ -126,7 +108,6 @@ 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);
@@ -137,8 +118,6 @@ void __kernel_fpu_end(void)
 
 	if (fpu->fpregs_active)
 		copy_kernel_to_fpregs(&fpu->state);
-	else
-		__fpregs_deactivate_hw();
 
 	kernel_fpu_enable();
 }
@@ -200,10 +179,7 @@ void fpu__save(struct fpu *fpu)
 	trace_x86_fpu_before_save(fpu);
 	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);
 		}
 	}
 	trace_x86_fpu_after_save(fpu);
@@ -261,8 +237,7 @@ int 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, fpu_kernel_xstate_size);
+	memset(&dst_fpu->state.xsave, 0, fpu_kernel_xstate_size);
 
 	/*
 	 * Save current FPU registers directly into the child
@@ -284,10 +259,7 @@ int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu)
 		memcpy(&src_fpu->state, &dst_fpu->state,
 		       fpu_kernel_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();
 
diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index 3ec0d2d..3a93186 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -344,11 +344,9 @@ 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/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index abfbb61b..e9d7f46 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -890,15 +890,6 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
 	 */
 	if (!boot_cpu_has(X86_FEATURE_OSPKE))
 		return -EINVAL;
-	/*
-	 * For most XSAVE components, this would be an arduous task:
-	 * brining fpstate up to date with fpregs, updating fpstate,
-	 * then re-populating fpregs.  But, for components that are
-	 * never lazily managed, we can just access the fpregs
-	 * directly.  PKRU is never managed lazily, so we can just
-	 * manipulate it directly.  Make sure it stays that way.
-	 */
-	WARN_ON_ONCE(!use_eager_fpu());
 
 	/* Set the bits we need in PKRU:  */
 	if (init_val & PKEY_DISABLE_ACCESS)
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 7e5119c..c17d389 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -16,7 +16,6 @@
 #include <linux/export.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"
@@ -114,8 +113,7 @@ 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 5ca23af..0754dae 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -7513,16 +7513,6 @@ 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);
 }
 
-- 
2.7.4

[PATCH 2/4] x86/fpu: Remove struct fpu::counter

[Daniel Sangorrin]

From: Rik van Riel <riel@redhat.com>

With the lazy FPU code gone, we no longer use the counter field
in struct fpu for anything. Get rid it.

Signed-off-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Andy Lutomirski <luto@kernel.org>
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/1475627678-20788-6-git-send-email-riel@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/include/asm/fpu/internal.h |  3 ---
 arch/x86/include/asm/fpu/types.h    | 11 -----------
 arch/x86/include/asm/trace/fpu.h    |  5 +----
 arch/x86/kernel/fpu/core.c          |  3 ---
 4 files changed, 1 insertion(+), 21 deletions(-)

diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index 7801d32..499d6ed 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -581,16 +581,13 @@ switch_fpu_prepare(struct fpu *old_fpu, struct fpu *new_fpu, int cpu)
 
 		/* Don't change CR0.TS if we just switch! */
 		if (fpu.preload) {
-			new_fpu->counter++;
 			__fpregs_activate(new_fpu);
 			trace_x86_fpu_regs_activated(new_fpu);
 			prefetch(&new_fpu->state);
 		}
 	} else {
-		old_fpu->counter = 0;
 		old_fpu->last_cpu = -1;
 		if (fpu.preload) {
-			new_fpu->counter++;
 			if (fpu_want_lazy_restore(new_fpu, cpu))
 				fpu.preload = 0;
 			else
diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h
index 48df486..e31332d 100644
--- a/arch/x86/include/asm/fpu/types.h
+++ b/arch/x86/include/asm/fpu/types.h
@@ -322,17 +322,6 @@ struct fpu {
 	unsigned char			fpregs_active;
 
 	/*
-	 * @counter:
-	 *
-	 * This counter contains the number of consecutive context switches
-	 * during which the FPU stays used. If this is over a threshold, the
-	 * lazy FPU restore logic becomes eager, to save the trap overhead.
-	 * This is an unsigned char so that after 256 iterations the counter
-	 * wraps and the context switch behavior turns lazy again; this is to
-	 * deal with bursty apps that only use the FPU for a short time:
-	 */
-	unsigned char			counter;
-	/*
 	 * @state:
 	 *
 	 * In-memory copy of all FPU registers that we save/restore
diff --git a/arch/x86/include/asm/trace/fpu.h b/arch/x86/include/asm/trace/fpu.h
index 9217ab1..342e597 100644
--- a/arch/x86/include/asm/trace/fpu.h
+++ b/arch/x86/include/asm/trace/fpu.h
@@ -14,7 +14,6 @@ DECLARE_EVENT_CLASS(x86_fpu,
 		__field(struct fpu *, fpu)
 		__field(bool, fpregs_active)
 		__field(bool, fpstate_active)
-		__field(int, counter)
 		__field(u64, xfeatures)
 		__field(u64, xcomp_bv)
 		),
@@ -23,17 +22,15 @@ DECLARE_EVENT_CLASS(x86_fpu,
 		__entry->fpu		= fpu;
 		__entry->fpregs_active	= fpu->fpregs_active;
 		__entry->fpstate_active	= fpu->fpstate_active;
-		__entry->counter	= fpu->counter;
 		if (boot_cpu_has(X86_FEATURE_OSXSAVE)) {
 			__entry->xfeatures = fpu->state.xsave.header.xfeatures;
 			__entry->xcomp_bv  = fpu->state.xsave.header.xcomp_bv;
 		}
 	),
-	TP_printk("x86/fpu: %p fpregs_active: %d fpstate_active: %d counter: %d xfeatures: %llx xcomp_bv: %llx",
+	TP_printk("x86/fpu: %p fpregs_active: %d fpstate_active: %d xfeatures: %llx xcomp_bv: %llx",
 			__entry->fpu,
 			__entry->fpregs_active,
 			__entry->fpstate_active,
-			__entry->counter,
 			__entry->xfeatures,
 			__entry->xcomp_bv
 	)
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 2dc1927..76c094c 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -224,7 +224,6 @@ EXPORT_SYMBOL_GPL(fpstate_init);
 
 int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu)
 {
-	dst_fpu->counter = 0;
 	dst_fpu->fpregs_active = 0;
 	dst_fpu->last_cpu = -1;
 
@@ -432,7 +431,6 @@ void fpu__restore(struct fpu *fpu)
 	trace_x86_fpu_before_restore(fpu);
 	fpregs_activate(fpu);
 	copy_kernel_to_fpregs(&fpu->state);
-	fpu->counter++;
 	trace_x86_fpu_after_restore(fpu);
 	kernel_fpu_enable();
 }
@@ -450,7 +448,6 @@ EXPORT_SYMBOL_GPL(fpu__restore);
 void fpu__drop(struct fpu *fpu)
 {
 	preempt_disable();
-	fpu->counter = 0;
 
 	if (fpu->fpregs_active) {
 		/* Ignore delayed exceptions from user space */
-- 
2.7.4

[PATCH 3/4] Revert "perf: sync up x86/.../cpufeatures.h"

[Daniel Sangorrin]

This reverts commit f09a7b0eead737b33d940bf5c2509ca1441e9590.
so that it does not conflict with
e63650840e8b ("x86/fpu: Finish excising 'eagerfpu'")

Signed-off-by: Daniel Sangorrin <daniel.sangorrin@toshiba.co.jp>
---
 tools/arch/x86/include/asm/cpufeatures.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index aea30af..c278f27 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -104,7 +104,7 @@
 #define X86_FEATURE_EXTD_APICID	( 3*32+26) /* has extended APICID (8 bits) */
 #define X86_FEATURE_AMD_DCM     ( 3*32+27) /* multi-node processor */
 #define X86_FEATURE_APERFMPERF	( 3*32+28) /* APERFMPERF */
-/* free, was #define X86_FEATURE_EAGER_FPU	( 3*32+29) * "eagerfpu" Non lazy FPU restore */
+#define X86_FEATURE_EAGER_FPU	( 3*32+29) /* "eagerfpu" Non lazy FPU restore */
 #define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* TSC doesn't stop in S3 state */
 
 /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
-- 
2.7.4

[PATCH 4/4] x86/fpu: Finish excising 'eagerfpu'

[Daniel Sangorrin]

From: Andy Lutomirski <luto@kernel.org>

Now that eagerfpu= is gone, remove it from the docs and some
comments.  Also sync the changes to tools/.

Signed-off-by: Andy Lutomirski <luto@kernel.org>
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: Rik van Riel <riel@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/cf430dd4481d41280e93ac6cf0def1007a67fc8e.1476740397.git.luto@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 Documentation/kernel-parameters.txt      |  6 ------
 arch/x86/include/asm/cpufeatures.h       |  1 -
 arch/x86/include/asm/fpu/types.h         | 23 -----------------------
 arch/x86/mm/pkeys.c                      |  3 +--
 tools/arch/x86/include/asm/cpufeatures.h |  1 -
 5 files changed, 1 insertion(+), 33 deletions(-)

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 52240a6..cb6e169 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1084,12 +1084,6 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	nopku		[X86] Disable Memory Protection Keys CPU feature found
 			in some Intel CPUs.
 
-	eagerfpu=	[X86]
-			on	enable eager fpu restore
-			off	disable eager fpu restore
-			auto	selects the default scheme, which automatically
-				enables eagerfpu restore for xsaveopt.
-
 	module.async_probe [KNL]
 			Enable asynchronous probe on this module.
 
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index aea30af..3d5df1c1 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -104,7 +104,6 @@
 #define X86_FEATURE_EXTD_APICID	( 3*32+26) /* has extended APICID (8 bits) */
 #define X86_FEATURE_AMD_DCM     ( 3*32+27) /* multi-node processor */
 #define X86_FEATURE_APERFMPERF	( 3*32+28) /* APERFMPERF */
-/* free, was #define X86_FEATURE_EAGER_FPU	( 3*32+29) * "eagerfpu" Non lazy FPU restore */
 #define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* TSC doesn't stop in S3 state */
 
 /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h
index e31332d..3c80f5b 100644
--- a/arch/x86/include/asm/fpu/types.h
+++ b/arch/x86/include/asm/fpu/types.h
@@ -329,29 +329,6 @@ struct fpu {
 	 * the registers in the FPU are more recent than this state
 	 * copy. If the task context-switches away then they get
 	 * saved here and represent the FPU state.
-	 *
-	 * After context switches there may be a (short) time period
-	 * during which the in-FPU hardware registers are unchanged
-	 * and still perfectly match this state, if the tasks
-	 * scheduled afterwards are not using the FPU.
-	 *
-	 * This is the 'lazy restore' window of optimization, which
-	 * we track though 'fpu_fpregs_owner_ctx' and 'fpu->last_cpu'.
-	 *
-	 * We detect whether a subsequent task uses the FPU via setting
-	 * CR0::TS to 1, which causes any FPU use to raise a #NM fault.
-	 *
-	 * During this window, if the task gets scheduled again, we
-	 * might be able to skip having to do a restore from this
-	 * memory buffer to the hardware registers - at the cost of
-	 * incurring the overhead of #NM fault traps.
-	 *
-	 * Note that on modern CPUs that support the XSAVEOPT (or other
-	 * optimized XSAVE instructions), we don't use #NM traps anymore,
-	 * as the hardware can track whether FPU registers need saving
-	 * or not. On such CPUs we activate the non-lazy ('eagerfpu')
-	 * logic, which unconditionally saves/restores all FPU state
-	 * across context switches. (if FPU state exists.)
 	 */
 	union fpregs_state		state;
 	/*
diff --git a/arch/x86/mm/pkeys.c b/arch/x86/mm/pkeys.c
index 0bbec04..e2d2b3c 100644
--- a/arch/x86/mm/pkeys.c
+++ b/arch/x86/mm/pkeys.c
@@ -142,8 +142,7 @@ u32 init_pkru_value = PKRU_AD_KEY( 1) | PKRU_AD_KEY( 2) | PKRU_AD_KEY( 3) |
  * Called from the FPU code when creating a fresh set of FPU
  * registers.  This is called from a very specific context where
  * we know the FPU regstiers are safe for use and we can use PKRU
- * directly.  The fact that PKRU is only available when we are
- * using eagerfpu mode makes this possible.
+ * directly.
  */
 void copy_init_pkru_to_fpregs(void)
 {
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index c278f27..3d5df1c1 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -104,7 +104,6 @@
 #define X86_FEATURE_EXTD_APICID	( 3*32+26) /* has extended APICID (8 bits) */
 #define X86_FEATURE_AMD_DCM     ( 3*32+27) /* multi-node processor */
 #define X86_FEATURE_APERFMPERF	( 3*32+28) /* APERFMPERF */
-#define X86_FEATURE_EAGER_FPU	( 3*32+29) /* "eagerfpu" Non lazy FPU restore */
 #define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* TSC doesn't stop in S3 state */
 
 /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
-- 
2.7.4