x86/fpu: Remove fpu->initialized

The struct fpu.initialized member is always set to one for user tasks
and zero for kernel tasks. This avoids saving/restoring the FPU
registers for kernel threads.

The ->initialized = 0 case for user tasks has been removed in previous
changes, for instance, by doing an explicit unconditional init at fork()
time for FPU-less systems which was otherwise delayed until the emulated
opcode.

The context switch code (switch_fpu_prepare() + switch_fpu_finish())
can't unconditionally save/restore registers for kernel threads. Not
only would it slow down the switch but also load a zeroed xcomp_bv for
XSAVES.

For kernel_fpu_begin() (+end) the situation is similar: EFI with runtime
services uses this before alternatives_patched is true. Which means that
this function is used too early and it wasn't the case before.

For those two cases, use current->mm to distinguish between user and
kernel thread. For kernel_fpu_begin() skip save/restore of the FPU
registers.

During the context switch into a kernel thread don't do anything. There
is no reason to save the FPU state of a kernel thread.

The reordering in __switch_to() is important because the current()
pointer needs to be valid before switch_fpu_finish() is invoked so ->mm
is seen of the new task instead the old one.

N.B.: fpu__save() doesn't need to check ->mm because it is called by
user tasks only.

 [ bp: Massage. ]

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Dave Hansen <dave.hansen@intel.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Aubrey Li <aubrey.li@intel.com>
Cc: Babu Moger <Babu.Moger@amd.com>
Cc: "Chang S. Bae" <chang.seok.bae@intel.com>
Cc: Dmitry Safonov <dima@arista.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jann Horn <jannh@google.com>
Cc: "Jason A. Donenfeld" <Jason@zx2c4.com>
Cc: Joerg Roedel <jroedel@suse.de>
Cc: kvm ML <kvm@vger.kernel.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Nicolai Stange <nstange@suse.de>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: x86-ml <x86@kernel.org>
Link: https://lkml.kernel.org/r/20190403164156.19645-8-bigeasy@linutronix.de

arch/x86/kernel/fpu/core.c

@@ -101,7 +101,7 @@ static void __kernel_fpu_begin(void)
 
 	kernel_fpu_disable();
 
-	if (fpu->initialized) {
+	if (current->mm) {
 		/*
 		 * Ignore return value -- we don't care if reg state
 		 * is clobbered.
@@ -116,7 +116,7 @@ static void __kernel_fpu_end(void)
 {
 	struct fpu *fpu = &current->thread.fpu;
 
-	if (fpu->initialized)
+	if (current->mm)
 		copy_kernel_to_fpregs(&fpu->state);
 
 	kernel_fpu_enable();
@@ -147,11 +147,10 @@ void fpu__save(struct fpu *fpu)
 
 	preempt_disable();
 	trace_x86_fpu_before_save(fpu);
-	if (fpu->initialized) {
-		if (!copy_fpregs_to_fpstate(fpu)) {
-			copy_kernel_to_fpregs(&fpu->state);
-		}
-	}
+
+	if (!copy_fpregs_to_fpstate(fpu))
+		copy_kernel_to_fpregs(&fpu->state);
+
 	trace_x86_fpu_after_save(fpu);
 	preempt_enable();
 }
@@ -190,7 +189,7 @@ int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu)
 {
 	dst_fpu->last_cpu = -1;
 
-	if (!src_fpu->initialized || !static_cpu_has(X86_FEATURE_FPU))
+	if (!static_cpu_has(X86_FEATURE_FPU))
 		return 0;
 
 	WARN_ON_FPU(src_fpu != &current->thread.fpu);
@@ -227,14 +226,10 @@ static void fpu__initialize(struct fpu *fpu)
 {
 	WARN_ON_FPU(fpu != &current->thread.fpu);
 
-	if (!fpu->initialized) {
-		fpstate_init(&fpu->state);
-		trace_x86_fpu_init_state(fpu);
+	fpstate_init(&fpu->state);
+	trace_x86_fpu_init_state(fpu);
 
-		trace_x86_fpu_activate_state(fpu);
-		/* Safe to do for the current task: */
-		fpu->initialized = 1;
-	}
+	trace_x86_fpu_activate_state(fpu);
 }
 
 /*
@@ -247,32 +242,20 @@ static void fpu__initialize(struct fpu *fpu)
  *
  * - or it's called for stopped tasks (ptrace), in which case the
  *   registers were already saved by the context-switch code when
- *   the task scheduled out - we only have to initialize the registers
- *   if they've never been initialized.
+ *   the task scheduled out.
  *
  * If the task has used the FPU before then save it.
  */
 void fpu__prepare_read(struct fpu *fpu)
 {
-	if (fpu == &current->thread.fpu) {
+	if (fpu == &current->thread.fpu)
 		fpu__save(fpu);
-	} else {
-		if (!fpu->initialized) {
-			fpstate_init(&fpu->state);
-			trace_x86_fpu_init_state(fpu);
-
-			trace_x86_fpu_activate_state(fpu);
-			/* Safe to do for current and for stopped child tasks: */
-			fpu->initialized = 1;
-		}
-	}
 }
 
 /*
  * This function must be called before we write a task's fpstate.
  *
- * If the task has used the FPU before then invalidate any cached FPU registers.
- * If the task has not used the FPU before then initialize its fpstate.
+ * Invalidate any cached FPU registers.
  *
  * After this function call, after registers in the fpstate are
  * modified and the child task has woken up, the child task will
@@ -289,17 +272,8 @@ void fpu__prepare_write(struct fpu *fpu)
 	 */
 	WARN_ON_FPU(fpu == &current->thread.fpu);
 
-	if (fpu->initialized) {
-		/* Invalidate any cached state: */
-		__fpu_invalidate_fpregs_state(fpu);
-	} else {
-		fpstate_init(&fpu->state);
-		trace_x86_fpu_init_state(fpu);
-
-		trace_x86_fpu_activate_state(fpu);
-		/* Safe to do for stopped child tasks: */
-		fpu->initialized = 1;
-	}
+	/* Invalidate any cached state: */
+	__fpu_invalidate_fpregs_state(fpu);
 }
 
 /*
@@ -316,17 +290,13 @@ void fpu__drop(struct fpu *fpu)
 	preempt_disable();
 
 	if (fpu == &current->thread.fpu) {
-		if (fpu->initialized) {
-			/* Ignore delayed exceptions from user space */
-			asm volatile("1: fwait\n"
-				     "2:\n"
-				     _ASM_EXTABLE(1b, 2b));
-			fpregs_deactivate(fpu);
-		}
+		/* Ignore delayed exceptions from user space */
+		asm volatile("1: fwait\n"
+			     "2:\n"
+			     _ASM_EXTABLE(1b, 2b));
+		fpregs_deactivate(fpu);
 	}
 
-	fpu->initialized = 0;
-
 	trace_x86_fpu_dropped(fpu);
 
 	preempt_enable();

arch/x86/kernel/fpu/init.c

@@ -239,8 +239,6 @@ static void __init fpu__init_system_ctx_switch(void)
 
 	WARN_ON_FPU(!on_boot_cpu);
 	on_boot_cpu = 0;
-
-	WARN_ON_FPU(current->thread.fpu.initialized);
 }
 
 /*

arch/x86/kernel/fpu/regset.c

@@ -15,16 +15,12 @@
  */
 int regset_fpregs_active(struct task_struct *target, const struct user_regset *regset)
 {
-	struct fpu *target_fpu = &target->thread.fpu;
-
-	return target_fpu->initialized ? regset->n : 0;
+	return regset->n;
 }
 
 int regset_xregset_fpregs_active(struct task_struct *target, const struct user_regset *regset)
 {
-	struct fpu *target_fpu = &target->thread.fpu;
-
-	if (boot_cpu_has(X86_FEATURE_FXSR) && target_fpu->initialized)
+	if (boot_cpu_has(X86_FEATURE_FXSR))
 		return regset->n;
 	else
 		return 0;
@@ -370,16 +366,9 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset,
 int dump_fpu(struct pt_regs *regs, struct user_i387_struct *ufpu)
 {
 	struct task_struct *tsk = current;
-	struct fpu *fpu = &tsk->thread.fpu;
-	int fpvalid;
 
-	fpvalid = fpu->initialized;
-	if (fpvalid)
-		fpvalid = !fpregs_get(tsk, NULL,
-				      0, sizeof(struct user_i387_ia32_struct),
-				      ufpu, NULL);
-
-	return fpvalid;
+	return !fpregs_get(tsk, NULL, 0, sizeof(struct user_i387_ia32_struct),
+			   ufpu, NULL);
 }
 EXPORT_SYMBOL(dump_fpu);
 

arch/x86/kernel/fpu/xstate.c

@@ -892,8 +892,6 @@ const void *get_xsave_field_ptr(int xsave_state)
 {
 	struct fpu *fpu = &current->thread.fpu;
 
-	if (!fpu->initialized)
-		return NULL;
 	/*
 	 * fpu__save() takes the CPU's xstate registers
 	 * and saves them off to the 'fpu memory buffer.