x86/fpu: eagerfpu fixes, speedups, and default enablement

index 0fd440df63f1..a1f78a9fbf41 100644
@@ -589,7 +589,8 @@ switch_fpu_prepare(struct fpu *old_fpu, struct fpu *new_fpu, int cpu)
 	 * 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 = new_fpu->fpstate_active &&
+	fpu.preload = static_cpu_has(X86_FEATURE_FPU) &&
+		      new_fpu->fpstate_active &&
 		      (use_eager_fpu() || new_fpu->counter > 5);
 
 	if (old_fpu->fpregs_active) {

index d25097c3fc1d..08e1e11a05ca 100644
@@ -423,7 +423,7 @@ void fpu__clear(struct fpu *fpu)
 {
 	WARN_ON_FPU(fpu != &current->thread.fpu); /* Almost certainly an anomaly */
 
-	if (!use_eager_fpu()) {
+	if (!use_eager_fpu() || !static_cpu_has(X86_FEATURE_FPU)) {
 		/* FPU state will be reallocated lazily at the first use. */
 		fpu__drop(fpu);
 	} else {

index ade185a46b1d..87f80febf477 100644
@@ -750,7 +750,6 @@ dotraplinkage void
 do_device_not_available(struct pt_regs *regs, long error_code)
 {
 	RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
-	BUG_ON(use_eager_fpu());
 
 #ifdef CONFIG_MATH_EMULATION
 	if (read_cr0() & X86_CR0_EM) {

index 08e1e11a05ca..7a9244df33e2 100644
@@ -114,6 +114,10 @@ void __kernel_fpu_begin(void)
 	kernel_fpu_disable();
 
 	if (fpu->fpregs_active) {
+		/*
+		 * Ignore return value -- we don't care if reg state
+		 * is clobbered.
+		 */
 		copy_fpregs_to_fpstate(fpu);
 	} else {
 		this_cpu_write(fpu_fpregs_owner_ctx, NULL);

@@ -189,8 +193,12 @@ void fpu__save(struct fpu *fpu)
 
 	preempt_disable();
 	if (fpu->fpregs_active) {
-		if (!copy_fpregs_to_fpstate(fpu))
-			fpregs_deactivate(fpu);
+		if (!copy_fpregs_to_fpstate(fpu)) {
+			if (use_eager_fpu())
+				copy_kernel_to_fpregs(&fpu->state);
+			else
+				fpregs_deactivate(fpu);
+		}
 	}
 	preempt_enable();
 }

@@ -259,7 +267,11 @@ static void fpu_copy(struct fpu *dst_fpu, struct fpu *src_fpu)
 	preempt_disable();
 	if (!copy_fpregs_to_fpstate(dst_fpu)) {
 		memcpy(&src_fpu->state, &dst_fpu->state, xstate_size);
-		fpregs_deactivate(src_fpu);
+
+		if (use_eager_fpu())
+			copy_kernel_to_fpregs(&src_fpu->state);
+		else
+			fpregs_deactivate(src_fpu);
 	}
 	preempt_enable();
 }

index 7a9244df33e2..299b58bb975b 100644
@@ -231,14 +231,15 @@ void fpstate_init(union fpregs_state *state)
 }
 EXPORT_SYMBOL_GPL(fpstate_init);
 
-/*
- * Copy the current task's FPU state to a new task's FPU context.
- *
- * In both the 'eager' and the 'lazy' case we save hardware registers
- * directly to the destination buffer.
- */
-static void fpu_copy(struct fpu *dst_fpu, struct fpu *src_fpu)
+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;
+
+	if (!src_fpu->fpstate_active || !cpu_has_fpu)
+		return 0;
+
 	WARN_ON_FPU(src_fpu != &current->thread.fpu);
 
 	/*

@@ -251,10 +252,9 @@ static void fpu_copy(struct fpu *dst_fpu, struct fpu *src_fpu)
 	/*
 	 * Save current FPU registers directly into the child
 	 * FPU context, without any memory-to-memory copying.
-	 *
-	 * If the FPU context got destroyed in the process (FNSAVE
-	 * done on old CPUs) then copy it back into the source
-	 * context and mark the current task for lazy restore.
+	 * In lazy mode, if the FPU context isn't loaded into
+	 * fpregs, CR0.TS will be set and do_device_not_available
+	 * will load the FPU context.
 	 *
 	 * We have to do all this with preemption disabled,
 	 * mostly because of the FNSAVE case, because in that

@@ -274,16 +274,6 @@ static void fpu_copy(struct fpu *dst_fpu, struct fpu *src_fpu)
 			fpregs_deactivate(src_fpu);
 	}
 	preempt_enable();
-}
-
-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;
-
-	if (src_fpu->fpstate_active && cpu_has_fpu)
-		fpu_copy(dst_fpu, src_fpu);
 
 	return 0;
 }

index 87f80febf477..36a9c017540e 100644
@@ -752,7 +752,7 @@ do_device_not_available(struct pt_regs *regs, long error_code)
 	RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
 
 #ifdef CONFIG_MATH_EMULATION
-	if (read_cr0() & X86_CR0_EM) {
+	if (!boot_cpu_has(X86_FEATURE_FPU) && (read_cr0() & X86_CR0_EM)) {
 		struct math_emu_info info = { };
 
 		conditional_sti(regs);

index d53ab3d3b8e8..e12cc0ad368e 100644
@@ -262,7 +262,10 @@ static void __init fpu__init_system_xstate_size_legacy(void)
  * not only saved the restores along the way, but we also have the
  * FPU ready to be used for the original task.
  *
- * 'eager' switching is used on modern CPUs, there we switch the FPU
+ * '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

@@ -273,7 +276,7 @@ static void __init fpu__init_system_xstate_size_legacy(void)
  *   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 { AUTO, ENABLE, DISABLE } eagerfpu = AUTO;
+static enum { ENABLE, DISABLE } eagerfpu = ENABLE;
 
 /*
  * Find supported xfeatures based on cpu features and command-line input.

@@ -350,15 +353,9 @@ static void __init fpu__init_system_ctx_switch(void)
  */
 static void __init fpu__init_parse_early_param(void)
 {
-	/*
-	 * No need to check "eagerfpu=auto" again, since it is the
-	 * initial default.
-	 */
 	if (cmdline_find_option_bool(boot_command_line, "eagerfpu=off")) {
 		eagerfpu = DISABLE;
 		fpu__clear_eager_fpu_features();
-	} else if (cmdline_find_option_bool(boot_command_line, "eagerfpu=on")) {
-		eagerfpu = ENABLE;
 	}
 
 	if (cmdline_find_option_bool(boot_command_line, "no387"))