Merge branch 'x86-fpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 FPU updates from Ingo Molnar:
 "The main changes in this cycle were:

   - do a large round of simplifications after all CPUs do 'eager' FPU
     context switching in v4.9: remove CR0 twiddling, remove leftover
     eager/lazy bts, etc (Andy Lutomirski)

   - more FPU code simplifications: remove struct fpu::counter, clarify
     nomenclature, remove unnecessary arguments/functions and better
     structure the code (Rik van Riel)"

* 'x86-fpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/fpu: Remove clts()
  x86/fpu: Remove stts()
  x86/fpu: Handle #NM without FPU emulation as an error
  x86/fpu, lguest: Remove CR0.TS support
  x86/fpu, kvm: Remove host CR0.TS manipulation
  x86/fpu: Remove irq_ts_save() and irq_ts_restore()
  x86/fpu: Stop saving and restoring CR0.TS in fpu__init_check_bugs()
  x86/fpu: Get rid of two redundant clts() calls
  x86/fpu: Finish excising 'eagerfpu'
  x86/fpu: Split old_fpu & new_fpu handling into separate functions
  x86/fpu: Remove 'cpu' argument from __cpu_invalidate_fpregs_state()
  x86/fpu: Split old & new FPU code paths
  x86/fpu: Remove __fpregs_(de)activate()
  x86/fpu: Rename lazy restore functions to "register state valid"
  x86/fpu, kvm: Remove KVM vcpu->fpu_counter
  x86/fpu: Remove struct fpu::counter
  x86/fpu: Remove use_eager_fpu()
  x86/fpu: Remove the XFEATURE_MASK_EAGER/LAZY distinction
  x86/fpu: Hard-disable lazy FPU mode
  x86/crypto, x86/fpu: Remove X86_FEATURE_EAGER_FPU #ifdef from the crc32c code

29 files changed, 100 insertions, 471 deletions

diff --git a/arch/x86/crypto/crc32c-intel_glue.c b/arch/x86/crypto/crc32c-intel_glue.c
index 0857b1a1de3b..c194d5717ae5 100644
--- a/arch/x86/crypto/crc32c-intel_glue.c
+++ b/arch/x86/crypto/crc32c-intel_glue.c
@@ -48,26 +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;
-#if defined(X86_FEATURE_EAGER_FPU)
-#define set_pcl_breakeven_point()					\
-do {									\
-	if (!use_eager_fpu())						\
-		crc32c_pcl_breakeven = CRC32C_PCL_BREAKEVEN_NOEAGERFPU;	\
-} while (0)
-#else
-#define set_pcl_breakeven_point()					\
-	(crc32c_pcl_breakeven = CRC32C_PCL_BREAKEVEN_NOEAGERFPU)
-#endif
 #endif /* CONFIG_X86_64 */
 
 static u32 crc32c_intel_le_hw_byte(u32 crc, unsigned char const *data, size_t length)
@@ -190,7 +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();
@@ -202,7 +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();
@@ -261,7 +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/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 4dba597c5807..e83f972b0a14 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 */
-#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/api.h b/arch/x86/include/asm/fpu/api.h
index 1429a7c736db..0877ae018fc9 100644
--- a/arch/x86/include/asm/fpu/api.h
+++ b/arch/x86/include/asm/fpu/api.h
@@ -27,16 +27,6 @@ extern void kernel_fpu_end(void);
 extern bool irq_fpu_usable(void);
 
 /*
- * Some instructions like VIA's padlock instructions generate a spurious
- * DNA fault but don't modify SSE registers. And these instructions
- * get used from interrupt context as well. To prevent these kernel instructions
- * in interrupt context interacting wrongly with other user/kernel fpu usage, we
- * should use them only in the context of irq_ts_save/restore()
- */
-extern int  irq_ts_save(void);
-extern void irq_ts_restore(int TS_state);
-
-/*
  * Query the presence of one or more xfeatures. Works on any legacy CPU as well.
  *
  * If 'feature_name' is set then put a human-readable description of
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index 2737366ea583..d4a684997497 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 static_cpu_has(X86_FEATURE_EAGER_FPU);
-}
-
 static __always_inline __pure bool use_xsaveopt(void)
 {
 	return static_cpu_has(X86_FEATURE_XSAVEOPT);
@@ -484,42 +479,42 @@ extern int copy_fpstate_to_sigframe(void __user *buf, void __user *fp, int size)
 DECLARE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx);
 
 /*
- * Must be run with preemption disabled: this clears the fpu_fpregs_owner_ctx,
- * on this CPU.
+ * The in-register FPU state for an FPU context on a CPU is assumed to be
+ * valid if the fpu->last_cpu matches the CPU, and the fpu_fpregs_owner_ctx
+ * matches the FPU.
  *
- * This will disable any lazy FPU state restore of the current FPU state,
- * but if the current thread owns the FPU, it will still be saved by.
+ * If the FPU register state is valid, the kernel can skip restoring the
+ * FPU state from memory.
+ *
+ * Any code that clobbers the FPU registers or updates the in-memory
+ * FPU state for a task MUST let the rest of the kernel know that the
+ * FPU registers are no longer valid for this task.
+ *
+ * Either one of these invalidation functions is enough. Invalidate
+ * a resource you control: CPU if using the CPU for something else
+ * (with preemption disabled), FPU for the current task, or a task that
+ * is prevented from running by the current task.
  */
-static inline void __cpu_disable_lazy_restore(unsigned int cpu)
+static inline void __cpu_invalidate_fpregs_state(void)
 {
-	per_cpu(fpu_fpregs_owner_ctx, cpu) = NULL;
+	__this_cpu_write(fpu_fpregs_owner_ctx, NULL);
 }
 
-static inline int fpu_want_lazy_restore(struct fpu *fpu, unsigned int cpu)
-{
-	return fpu == this_cpu_read_stable(fpu_fpregs_owner_ctx) && cpu == fpu->last_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)
+static inline void __fpu_invalidate_fpregs_state(struct fpu *fpu)
 {
-	if (!use_eager_fpu())
-		clts();
+	fpu->last_cpu = -1;
 }
 
-static inline void __fpregs_deactivate_hw(void)
+static inline int fpregs_state_valid(struct fpu *fpu, unsigned int cpu)
 {
-	if (!use_eager_fpu())
-		stts();
+	return fpu == this_cpu_read_stable(fpu_fpregs_owner_ctx) && cpu == fpu->last_cpu;
 }
 
-/* Must be paired with an 'stts' (fpregs_deactivate_hw()) after! */
-static inline void __fpregs_deactivate(struct fpu *fpu)
+/*
+ * These generally need preemption protection to work,
+ * do try to avoid using these on their own:
+ */
+static inline void fpregs_deactivate(struct fpu *fpu)
 {
 	WARN_ON_FPU(!fpu->fpregs_active);
 
@@ -528,8 +523,7 @@ 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)
+static inline void fpregs_activate(struct fpu *fpu)
 {
 	WARN_ON_FPU(fpu->fpregs_active);
 
@@ -554,51 +548,19 @@ 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();
-}
-
-/*
  * FPU state switching for scheduling.
  *
  * This is a two-stage process:
  *
- *  - switch_fpu_prepare() saves the old state and
- *    sets the new state of the CR0.TS bit. This is
- *    done within the context of the old process.
+ *  - switch_fpu_prepare() saves the old state.
+ *    This is done within the context of the old process.
  *
  *  - switch_fpu_finish() restores the new state as
  *    necessary.
  */
-typedef struct { int preload; } fpu_switch_t;
-
-static inline fpu_switch_t
-switch_fpu_prepare(struct fpu *old_fpu, struct fpu *new_fpu, int cpu)
+static inline void
+switch_fpu_prepare(struct fpu *old_fpu, int cpu)
 {
-	fpu_switch_t fpu;
-
-	/*
-	 * If the task has used the math, pre-load the FPU on xsave processors
-	 * 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);
-
 	if (old_fpu->fpregs_active) {
 		if (!copy_fpregs_to_fpstate(old_fpu))
 			old_fpu->last_cpu = -1;
@@ -608,29 +570,8 @@ switch_fpu_prepare(struct fpu *old_fpu, struct fpu *new_fpu, int cpu)
 		/* But leave fpu_fpregs_owner_ctx! */
 		old_fpu->fpregs_active = 0;
 		trace_x86_fpu_regs_deactivated(old_fpu);
-
-		/* 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 {
-			__fpregs_deactivate_hw();
-		}
-	} else {
-		old_fpu->counter = 0;
+	} else
 		old_fpu->last_cpu = -1;
-		if (fpu.preload) {
-			new_fpu->counter++;
-			if (fpu_want_lazy_restore(new_fpu, cpu))
-				fpu.preload = 0;
-			else
-				prefetch(&new_fpu->state);
-			fpregs_activate(new_fpu);
-		}
-	}
-	return fpu;
 }
 
 /*
@@ -638,15 +579,19 @@ switch_fpu_prepare(struct fpu *old_fpu, struct fpu *new_fpu, int cpu)
  */
 
 /*
- * By the time this gets called, we've already cleared CR0.TS and
- * given the process the FPU if we are going to preload the FPU
- * state - all we need to do is to conditionally restore the register
- * state itself.
+ * Set up the userspace FPU context for the new task, if the task
+ * has used the FPU.
  */
-static inline void switch_fpu_finish(struct fpu *new_fpu, fpu_switch_t fpu_switch)
+static inline void switch_fpu_finish(struct fpu *new_fpu, int cpu)
 {
-	if (fpu_switch.preload)
-		copy_kernel_to_fpregs(&new_fpu->state);
+	bool preload = static_cpu_has(X86_FEATURE_FPU) &&
+		       new_fpu->fpstate_active;
+
+	if (preload) {
+		if (!fpregs_state_valid(new_fpu, cpu))
+			copy_kernel_to_fpregs(&new_fpu->state);
+		fpregs_activate(new_fpu);
+	}
 }
 
 /*
diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h
index 48df486b02f9..3c80f5b9c09d 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
@@ -340,29 +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/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
index 430bacf73074..1b2799e0699a 100644
--- a/arch/x86/include/asm/fpu/xstate.h
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -21,21 +21,16 @@
 /* Supervisor features */
 #define XFEATURE_MASK_SUPERVISOR (XFEATURE_MASK_PT)
 
-/* Supported features which support lazy state saving */
-#define XFEATURE_MASK_LAZY	(XFEATURE_MASK_FP | \
+/* All currently supported features */
+#define XCNTXT_MASK		(XFEATURE_MASK_FP | \
 				 XFEATURE_MASK_SSE | \
 				 XFEATURE_MASK_YMM | \
 				 XFEATURE_MASK_OPMASK | \
 				 XFEATURE_MASK_ZMM_Hi256 | \
-				 XFEATURE_MASK_Hi16_ZMM)
-
-/* Supported features which require eager state saving */
-#define XFEATURE_MASK_EAGER	(XFEATURE_MASK_BNDREGS | \
-				 XFEATURE_MASK_BNDCSR | \
-				 XFEATURE_MASK_PKRU)
-
-/* All currently supported features */
-#define XCNTXT_MASK	(XFEATURE_MASK_LAZY | XFEATURE_MASK_EAGER)
+				 XFEATURE_MASK_Hi16_ZMM	 | \
+				 XFEATURE_MASK_PKRU | \
+				 XFEATURE_MASK_BNDREGS | \
+				 XFEATURE_MASK_BNDCSR)
 
 #ifdef CONFIG_X86_64
 #define REX_PREFIX	"0x48, "
diff --git a/arch/x86/include/asm/lguest_hcall.h b/arch/x86/include/asm/lguest_hcall.h
index ef01fef3eebc..6c119cfae218 100644
--- a/arch/x86/include/asm/lguest_hcall.h
+++ b/arch/x86/include/asm/lguest_hcall.h
@@ -9,7 +9,6 @@
 #define LHCALL_FLUSH_TLB	5
 #define LHCALL_LOAD_IDT_ENTRY	6
 #define LHCALL_SET_STACK	7
-#define LHCALL_TS		8
 #define LHCALL_SET_CLOCKEVENT	9
 #define LHCALL_HALT		10
 #define LHCALL_SET_PMD		13
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 6108b1fada2b..1eea6ca40694 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -41,11 +41,6 @@ static inline void set_debugreg(unsigned long val, int reg)
 	PVOP_VCALL2(pv_cpu_ops.set_debugreg, reg, val);
 }
 
-static inline void clts(void)
-{
-	PVOP_VCALL0(pv_cpu_ops.clts);
-}
-
 static inline unsigned long read_cr0(void)
 {
 	return PVOP_CALL0(unsigned long, pv_cpu_ops.read_cr0);
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 3f2bc0f0d3e8..bb2de45a60f2 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -103,8 +103,6 @@ struct pv_cpu_ops {
 	unsigned long (*get_debugreg)(int regno);
 	void (*set_debugreg)(int regno, unsigned long value);
 
-	void (*clts)(void);
-
 	unsigned long (*read_cr0)(void);
 	void (*write_cr0)(unsigned long);
 
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index 19a2224f9e16..12af3e35edfa 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -6,11 +6,6 @@
 
 #include <asm/nops.h>
 
-static inline void native_clts(void)
-{
-	asm volatile("clts");
-}
-
 /*
  * Volatile isn't enough to prevent the compiler from reordering the
  * read/write functions for the control registers and messing everything up.
@@ -208,16 +203,8 @@ static inline void load_gs_index(unsigned selector)
 
 #endif
 
-/* Clear the 'TS' bit */
-static inline void clts(void)
-{
-	native_clts();
-}
-
 #endif/* CONFIG_PARAVIRT */
 
-#define stts() write_cr0(read_cr0() | X86_CR0_TS)
-
 static inline void clflush(volatile void *__p)
 {
 	asm volatile("clflush %0" : "+m" (*(volatile char __force *)__p));
diff --git a/arch/x86/include/asm/trace/fpu.h b/arch/x86/include/asm/trace/fpu.h
index 9217ab1f5bf6..342e59789fcd 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/bugs.c b/arch/x86/kernel/fpu/bugs.c
index aad34aafc0e0..d913047f832c 100644
--- a/arch/x86/kernel/fpu/bugs.c
+++ b/arch/x86/kernel/fpu/bugs.c
@@ -23,17 +23,12 @@ static double __initdata y = 3145727.0;
  */
 void __init fpu__init_check_bugs(void)
 {
-	u32 cr0_saved;
 	s32 fdiv_bug;
 
 	/* kernel_fpu_begin/end() relies on patched alternative instructions. */
 	if (!boot_cpu_has(X86_FEATURE_FPU))
 		return;
 
-	/* We might have CR0::TS set already, clear it: */
-	cr0_saved = read_cr0();
-	write_cr0(cr0_saved & ~X86_CR0_TS);
-
 	kernel_fpu_begin();
 
 	/*
@@ -56,8 +51,6 @@ void __init fpu__init_check_bugs(void)
 
 	kernel_fpu_end();
 
-	write_cr0(cr0_saved);
-
 	if (fdiv_bug) {
 		set_cpu_bug(&boot_cpu_data, X86_BUG_FDIV);
 		pr_warn("Hmm, FPU with FDIV bug\n");
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index ebb4e95fbd74..e4e97a5355ce 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();
 }
 
 /*
@@ -125,8 +107,7 @@ void __kernel_fpu_begin(void)
 		 */
 		copy_fpregs_to_fpstate(fpu);
 	} else {
-		this_cpu_write(fpu_fpregs_owner_ctx, NULL);
-		__fpregs_activate_hw();
+		__cpu_invalidate_fpregs_state();
 	}
 }
 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();
 }
@@ -159,35 +138,6 @@ void kernel_fpu_end(void)
 EXPORT_SYMBOL_GPL(kernel_fpu_end);
 
 /*
- * CR0::TS save/restore functions:
- */
-int irq_ts_save(void)
-{
-	/*
-	 * If in process context and not atomic, we can take a spurious DNA fault.
-	 * Otherwise, doing clts() in process context requires disabling preemption
-	 * or some heavy lifting like kernel_fpu_begin()
-	 */
-	if (!in_atomic())
-		return 0;
-
-	if (read_cr0() & X86_CR0_TS) {
-		clts();
-		return 1;
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(irq_ts_save);
-
-void irq_ts_restore(int TS_state)
-{
-	if (TS_state)
-		stts();
-}
-EXPORT_SYMBOL_GPL(irq_ts_restore);
-
-/*
  * Save the FPU state (mark it for reload if necessary):
  *
  * This only ever gets called for the current task.
@@ -200,10 +150,7 @@ 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);
@@ -247,7 +194,6 @@ 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;
 
@@ -260,8 +206,7 @@ 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
@@ -283,10 +228,7 @@ 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();
 
@@ -366,7 +308,7 @@ void fpu__activate_fpstate_write(struct fpu *fpu)
 
 	if (fpu->fpstate_active) {
 		/* Invalidate any lazy state: */
-		fpu->last_cpu = -1;
+		__fpu_invalidate_fpregs_state(fpu);
 	} else {
 		fpstate_init(&fpu->state);
 		trace_x86_fpu_init_state(fpu);
@@ -409,7 +351,7 @@ void fpu__current_fpstate_write_begin(void)
 	 * ensures we will not be lazy and skip a XRSTOR in the
 	 * future.
 	 */
-	fpu->last_cpu = -1;
+	__fpu_invalidate_fpregs_state(fpu);
 }
 
 /*
@@ -459,7 +401,6 @@ 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();
 }
@@ -477,7 +418,6 @@ 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 */
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index 2f2b8c7ccb85..60dece392b3a 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -10,18 +10,6 @@
 #include <linux/init.h>
 
 /*
- * Initialize the TS bit in CR0 according to the style of context-switches
- * we are using:
- */
-static void fpu__init_cpu_ctx_switch(void)
-{
-	if (!boot_cpu_has(X86_FEATURE_EAGER_FPU))
-		stts();
-	else
-		clts();
-}
-
-/*
  * Initialize the registers found in all CPUs, CR0 and CR4:
  */
 static void fpu__init_cpu_generic(void)
@@ -58,7 +46,6 @@ void fpu__init_cpu(void)
 {
 	fpu__init_cpu_generic();
 	fpu__init_cpu_xstate();
-	fpu__init_cpu_ctx_switch();
 }
 
 /*
@@ -233,82 +220,16 @@ static void __init fpu__init_system_xstate_size_legacy(void)
 }
 
 /*
- * FPU context switching strategies:
- *
- * Against popular belief, we don't do lazy FPU saves, due to the
- * task migration complications it brings on SMP - we only do
- * lazy FPU restores.
- *
- * 'lazy' is the traditional strategy, which is based on setting
- * CR0::TS to 1 during context-switch (instead of doing a full
- * restore of the FPU state), which causes the first FPU instruction
- * after the context switch (whenever it is executed) to fault - at
- * which point we lazily restore the FPU state into FPU registers.
- *
- * Tasks are of course under no obligation to execute FPU instructions,
- * so it can easily happen that another context-switch occurs without
- * a single FPU instruction being executed. If we eventually switch
- * back to the original task (that still owns the FPU) then we have
- * not only saved the restores along the way, but we also have the
- * FPU ready to be used for the original task.
- *
- * 'lazy' is deprecated because it's almost never a performance win
- * and it's much more complicated than 'eager'.
- *
- * 'eager' switching is by default on all CPUs, there we switch the FPU
- * state during every context switch, regardless of whether the task
- * has used FPU instructions in that time slice or not. This is done
- * because modern FPU context saving instructions are able to optimize
- * state saving and restoration in hardware: they can detect both
- * unused and untouched FPU state and optimize accordingly.
- *
- * [ Note that even in 'lazy' mode we might optimize context switches
- *   to use 'eager' restores, if we detect that a task is using the FPU
- *   frequently. See the fpu->counter logic in fpu/internal.h for that. ]
- */
-static enum { ENABLE, DISABLE } eagerfpu = ENABLE;
-
-/*
  * Find supported xfeatures based on cpu features and command-line input.
  * This must be called after fpu__init_parse_early_param() is called and
  * xfeatures_mask is enumerated.
  */
 u64 __init fpu__get_supported_xfeatures_mask(void)
 {
-	/* Support all xfeatures known to us */
-	if (eagerfpu != DISABLE)
-		return XCNTXT_MASK;
-
-	/* Warning of xfeatures being disabled for no eagerfpu mode */
-	if (xfeatures_mask & XFEATURE_MASK_EAGER) {
-		pr_err("x86/fpu: eagerfpu switching disabled, disabling the following xstate features: 0x%llx.\n",
-			xfeatures_mask & XFEATURE_MASK_EAGER);
-	}
-
-	/* Return a mask that masks out all features requiring eagerfpu mode */
-	return ~XFEATURE_MASK_EAGER;
+	return XCNTXT_MASK;
 }
 
-/*
- * Disable features dependent on eagerfpu.
- */
-static void __init fpu__clear_eager_fpu_features(void)
-{
-	setup_clear_cpu_cap(X86_FEATURE_MPX);
-}
-
-/*
- * Pick the FPU context switching strategy:
- *
- * When eagerfpu is AUTO or ENABLE, we ensure it is ENABLE if either of
- * the following is true:
- *
- * (1) the cpu has xsaveopt, as it has the optimization and doing eager
- *     FPU switching has a relatively low cost compared to a plain xsave;
- * (2) the cpu has xsave features (e.g. MPX) that depend on eager FPU
- *     switching. Should the kernel boot with noxsaveopt, we support MPX
- *     with eager FPU switching at a higher cost.
- */
+/* Legacy code to initialize eager fpu mode. */
 static void __init fpu__init_system_ctx_switch(void)
 {
 	static bool on_boot_cpu __initdata = 1;
@@ -317,17 +238,6 @@ static void __init fpu__init_system_ctx_switch(void)
 	on_boot_cpu = 0;
 
 	WARN_ON_FPU(current->thread.fpu.fpstate_active);
-
-	if (boot_cpu_has(X86_FEATURE_XSAVEOPT) && eagerfpu != DISABLE)
-		eagerfpu = ENABLE;
-
-	if (xfeatures_mask & XFEATURE_MASK_EAGER)
-		eagerfpu = ENABLE;
-
-	if (eagerfpu == ENABLE)
-		setup_force_cpu_cap(X86_FEATURE_EAGER_FPU);
-
-	printk(KERN_INFO "x86/fpu: Using '%s' FPU context switches.\n", eagerfpu == ENABLE ? "eager" : "lazy");
 }
 
 /*
@@ -336,11 +246,6 @@ static void __init fpu__init_system_ctx_switch(void)
  */
 static void __init fpu__init_parse_early_param(void)
 {
-	if (cmdline_find_option_bool(boot_command_line, "eagerfpu=off")) {
-		eagerfpu = DISABLE;
-		fpu__clear_eager_fpu_features();
-	}
-
 	if (cmdline_find_option_bool(boot_command_line, "no387"))
 		setup_clear_cpu_cap(X86_FEATURE_FPU);
 
@@ -375,14 +280,6 @@ void __init fpu__init_system(struct cpuinfo_x86 *c)
 	 */
 	fpu__init_cpu();
 
-	/*
-	 * But don't leave CR0::TS set yet, as some of the FPU setup
-	 * methods depend on being able to execute FPU instructions
-	 * that will fault on a set TS, such as the FXSAVE in
-	 * fpu__init_system_mxcsr().
-	 */
-	clts();
-
 	fpu__init_system_generic();
 	fpu__init_system_xstate_size_legacy();
 	fpu__init_system_xstate();
diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index a184c210efba..83c23c230b4c 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -340,11 +340,9 @@ 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 ce47452879fd..1d7770447b3e 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -892,15 +892,6 @@ 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/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index bbf3d5933eaa..a1bfba0f7234 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -328,7 +328,6 @@ __visible struct pv_cpu_ops pv_cpu_ops = {
 	.cpuid = native_cpuid,
 	.get_debugreg = native_get_debugreg,
 	.set_debugreg = native_set_debugreg,
-	.clts = native_clts,
 	.read_cr0 = native_read_cr0,
 	.write_cr0 = native_write_cr0,
 	.read_cr4 = native_read_cr4,
diff --git a/arch/x86/kernel/paravirt_patch_32.c b/arch/x86/kernel/paravirt_patch_32.c
index 33cdec221f3d..d33ef165b1f8 100644
--- a/arch/x86/kernel/paravirt_patch_32.c
+++ b/arch/x86/kernel/paravirt_patch_32.c
@@ -8,7 +8,6 @@ DEF_NATIVE(pv_cpu_ops, iret, "iret");
 DEF_NATIVE(pv_mmu_ops, read_cr2, "mov %cr2, %eax");
 DEF_NATIVE(pv_mmu_ops, write_cr3, "mov %eax, %cr3");
 DEF_NATIVE(pv_mmu_ops, read_cr3, "mov %cr3, %eax");
-DEF_NATIVE(pv_cpu_ops, clts, "clts");
 
 #if defined(CONFIG_PARAVIRT_SPINLOCKS)
 DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%eax)");
@@ -50,7 +49,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
 		PATCH_SITE(pv_mmu_ops, read_cr2);
 		PATCH_SITE(pv_mmu_ops, read_cr3);
 		PATCH_SITE(pv_mmu_ops, write_cr3);
-		PATCH_SITE(pv_cpu_ops, clts);
 #if defined(CONFIG_PARAVIRT_SPINLOCKS)
 		case PARAVIRT_PATCH(pv_lock_ops.queued_spin_unlock):
 			if (pv_is_native_spin_unlock()) {
diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c
index b0fceff502b3..f4fcf26c9fce 100644
--- a/arch/x86/kernel/paravirt_patch_64.c
+++ b/arch/x86/kernel/paravirt_patch_64.c
@@ -10,7 +10,6 @@ DEF_NATIVE(pv_mmu_ops, read_cr2, "movq %cr2, %rax");
 DEF_NATIVE(pv_mmu_ops, read_cr3, "movq %cr3, %rax");
 DEF_NATIVE(pv_mmu_ops, write_cr3, "movq %rdi, %cr3");
 DEF_NATIVE(pv_mmu_ops, flush_tlb_single, "invlpg (%rdi)");
-DEF_NATIVE(pv_cpu_ops, clts, "clts");
 DEF_NATIVE(pv_cpu_ops, wbinvd, "wbinvd");
 
 DEF_NATIVE(pv_cpu_ops, usergs_sysret64, "swapgs; sysretq");
@@ -60,7 +59,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
 		PATCH_SITE(pv_mmu_ops, read_cr2);
 		PATCH_SITE(pv_mmu_ops, read_cr3);
 		PATCH_SITE(pv_mmu_ops, write_cr3);
-		PATCH_SITE(pv_cpu_ops, clts);
 		PATCH_SITE(pv_mmu_ops, flush_tlb_single);
 		PATCH_SITE(pv_cpu_ops, wbinvd);
 #if defined(CONFIG_PARAVIRT_SPINLOCKS)
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index e3223bc78cb6..f854404be1c6 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -231,11 +231,10 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	struct fpu *next_fpu = &next->fpu;
 	int cpu = smp_processor_id();
 	struct tss_struct *tss = &per_cpu(cpu_tss, cpu);
-	fpu_switch_t fpu_switch;
 
 	/* never put a printk in __switch_to... printk() calls wake_up*() indirectly */
 
-	fpu_switch = switch_fpu_prepare(prev_fpu, next_fpu, cpu);
+	switch_fpu_prepare(prev_fpu, cpu);
 
 	/*
 	 * Save away %gs. No need to save %fs, as it was saved on the
@@ -294,7 +293,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	if (prev->gs | next->gs)
 		lazy_load_gs(next->gs);
 
-	switch_fpu_finish(next_fpu, fpu_switch);
+	switch_fpu_finish(next_fpu, cpu);
 
 	this_cpu_write(current_task, next_p);
 
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index c99f1ca35eb5..6c1b43eab80c 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -270,9 +270,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	int cpu = smp_processor_id();
 	struct tss_struct *tss = &per_cpu(cpu_tss, cpu);
 	unsigned prev_fsindex, prev_gsindex;
-	fpu_switch_t fpu_switch;
 
-	fpu_switch = switch_fpu_prepare(prev_fpu, next_fpu, cpu);
+	switch_fpu_prepare(prev_fpu, cpu);
 
 	/* We must save %fs and %gs before load_TLS() because
 	 * %fs and %gs may be cleared by load_TLS().
@@ -422,7 +421,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 		prev->gsbase = 0;
 	prev->gsindex = prev_gsindex;
 
-	switch_fpu_finish(next_fpu, fpu_switch);
+	switch_fpu_finish(next_fpu, cpu);
 
 	/*
 	 * Switch the PDA and FPU contexts.
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index f084a24c2c0f..2a501abe5000 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1132,7 +1132,7 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle)
 		return err;
 
 	/* the FPU context is blank, nobody can own it */
-	__cpu_disable_lazy_restore(cpu);
+	per_cpu(fpu_fpregs_owner_ctx, cpu) = NULL;
 
 	common_cpu_up(cpu, tidle);
 
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index bd4e3d4d3625..bf0c6d049080 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -853,6 +853,8 @@ do_spurious_interrupt_bug(struct pt_regs *regs, long error_code)
 dotraplinkage void
 do_device_not_available(struct pt_regs *regs, long error_code)
 {
+	unsigned long cr0;
+
 	RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
 
 #ifdef CONFIG_MATH_EMULATION
@@ -866,10 +868,20 @@ do_device_not_available(struct pt_regs *regs, long error_code)
 		return;
 	}
 #endif
-	fpu__restore(&current->thread.fpu); /* interrupts still off */
-#ifdef CONFIG_X86_32
-	cond_local_irq_enable(regs);
-#endif
+
+	/* This should not happen. */
+	cr0 = read_cr0();
+	if (WARN(cr0 & X86_CR0_TS, "CR0.TS was set")) {
+		/* Try to fix it up and carry on. */
+		write_cr0(cr0 & ~X86_CR0_TS);
+	} else {
+		/*
+		 * Something terrible happened, and we're better off trying
+		 * to kill the task than getting stuck in a never-ending
+		 * loop of #NM faults.
+		 */
+		die("unexpected #NM exception", regs, error_code);
+	}
 }
 NOKPROBE_SYMBOL(do_device_not_available);
 
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index afa7bbb596cd..0aefb626fa8f 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/vmx.c b/arch/x86/kvm/vmx.c
index 5382b82462fc..3980da515fd0 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2145,12 +2145,6 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx)
 #endif
 	if (vmx->host_state.msr_host_bndcfgs)
 		wrmsrl(MSR_IA32_BNDCFGS, vmx->host_state.msr_host_bndcfgs);
-	/*
-	 * If the FPU is not active (through the host task or
-	 * the guest vcpu), then restore the cr0.TS bit.
-	 */
-	if (!fpregs_active() && !vmx->vcpu.guest_fpu_loaded)
-		stts();
 	load_gdt(this_cpu_ptr(&host_gdt));
 }
 
@@ -4845,9 +4839,11 @@ static void vmx_set_constant_host_state(struct vcpu_vmx *vmx)
 	u32 low32, high32;
 	unsigned long tmpl;
 	struct desc_ptr dt;
-	unsigned long cr4;
+	unsigned long cr0, cr4;
 
-	vmcs_writel(HOST_CR0, read_cr0() & ~X86_CR0_TS);  /* 22.2.3 */
+	cr0 = read_cr0();
+	WARN_ON(cr0 & X86_CR0_TS);
+	vmcs_writel(HOST_CR0, cr0);  /* 22.2.3 */
 	vmcs_writel(HOST_CR3, read_cr3());  /* 22.2.3  FIXME: shadow tables */
 
 	/* Save the most likely value for this task's CR4 in the VMCS. */
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 59c2d6f1b131..6f5f465fdb6b 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5097,11 +5097,6 @@ static void emulator_get_fpu(struct x86_emulate_ctxt *ctxt)
 {
 	preempt_disable();
 	kvm_load_guest_fpu(emul_to_vcpu(ctxt));
-	/*
-	 * CR0.TS may reference the host fpu state, not the guest fpu state,
-	 * so it may be clear at this point.
-	 */
-	clts();
 }
 
 static void emulator_put_fpu(struct x86_emulate_ctxt *ctxt)
@@ -7423,25 +7418,13 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
 
 void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
 {
-	if (!vcpu->guest_fpu_loaded) {
-		vcpu->fpu_counter = 0;
+	if (!vcpu->guest_fpu_loaded)
 		return;
-	}
 
 	vcpu->guest_fpu_loaded = 0;
 	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);
 }
 
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index 25da5bc8d83d..4ca0d78adcf0 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -497,38 +497,24 @@ static void lguest_cpuid(unsigned int *ax, unsigned int *bx,
  * a whole series of functions like read_cr0() and write_cr0().
  *
  * We start with cr0.  cr0 allows you to turn on and off all kinds of basic
- * features, but Linux only really cares about one: the horrifically-named Task
- * Switched (TS) bit at bit 3 (ie. 8)
+ * features, but the only cr0 bit that Linux ever used at runtime was the
+ * horrifically-named Task Switched (TS) bit at bit 3 (ie. 8)
  *
  * What does the TS bit do?  Well, it causes the CPU to trap (interrupt 7) if
  * the floating point unit is used.  Which allows us to restore FPU state
- * lazily after a task switch, and Linux uses that gratefully, but wouldn't a
- * name like "FPUTRAP bit" be a little less cryptic?
+ * lazily after a task switch if we wanted to, but wouldn't a name like
+ * "FPUTRAP bit" be a little less cryptic?
  *
- * We store cr0 locally because the Host never changes it.  The Guest sometimes
- * wants to read it and we'd prefer not to bother the Host unnecessarily.
+ * Fortunately, Linux keeps it simple and doesn't use TS, so we can ignore
+ * cr0.
  */
-static unsigned long current_cr0;
 static void lguest_write_cr0(unsigned long val)
 {
-	lazy_hcall1(LHCALL_TS, val & X86_CR0_TS);
-	current_cr0 = val;
 }
 
 static unsigned long lguest_read_cr0(void)
 {
-	return current_cr0;
-}
-
-/*
- * Intel provided a special instruction to clear the TS bit for people too cool
- * to use write_cr0() to do it.  This "clts" instruction is faster, because all
- * the vowels have been optimized out.
- */
-static void lguest_clts(void)
-{
-	lazy_hcall1(LHCALL_TS, 0);
-	current_cr0 &= ~X86_CR0_TS;
+	return 0;
 }
 
 /*
@@ -1432,7 +1418,6 @@ __init void lguest_init(void)
 	pv_cpu_ops.load_tls = lguest_load_tls;
 	pv_cpu_ops.get_debugreg = lguest_get_debugreg;
 	pv_cpu_ops.set_debugreg = lguest_set_debugreg;
-	pv_cpu_ops.clts = lguest_clts;
 	pv_cpu_ops.read_cr0 = lguest_read_cr0;
 	pv_cpu_ops.write_cr0 = lguest_write_cr0;
 	pv_cpu_ops.read_cr4 = lguest_read_cr4;
diff --git a/arch/x86/mm/pkeys.c b/arch/x86/mm/pkeys.c
index f88ce0e5efd9..2dab69a706ec 100644
--- a/arch/x86/mm/pkeys.c
+++ b/arch/x86/mm/pkeys.c
@@ -141,8 +141,7 @@ 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/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index bdd855685403..ced7027b3fbc 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -980,17 +980,6 @@ static void xen_io_delay(void)
 {
 }
 
-static void xen_clts(void)
-{
-	struct multicall_space mcs;
-
-	mcs = xen_mc_entry(0);
-
-	MULTI_fpu_taskswitch(mcs.mc, 0);
-
-	xen_mc_issue(PARAVIRT_LAZY_CPU);
-}
-
 static DEFINE_PER_CPU(unsigned long, xen_cr0_value);
 
 static unsigned long xen_read_cr0(void)
@@ -1233,8 +1222,6 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = {
 	.set_debugreg = xen_set_debugreg,
 	.get_debugreg = xen_get_debugreg,
 
-	.clts = xen_clts,
-
 	.read_cr0 = xen_read_cr0,
 	.write_cr0 = xen_write_cr0,