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

3 files changed, 11 insertions, 21 deletions

diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index 70ecb7c032cb..04042eacc852 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -494,11 +494,14 @@ static inline void fpregs_activate(struct fpu *fpu)
  *
  *  - switch_fpu_finish() restores the new state as
  *    necessary.
+ *
+ * The FPU context is only stored/restored for a user task and
+ * ->mm is used to distinguish between kernel and user threads.
  */
 static inline void
 switch_fpu_prepare(struct fpu *old_fpu, int cpu)
 {
-	if (static_cpu_has(X86_FEATURE_FPU) && old_fpu->initialized) {
+	if (static_cpu_has(X86_FEATURE_FPU) && current->mm) {
 		if (!copy_fpregs_to_fpstate(old_fpu))
 			old_fpu->last_cpu = -1;
 		else
@@ -506,8 +509,7 @@ switch_fpu_prepare(struct fpu *old_fpu, int cpu)
 
 		/* But leave fpu_fpregs_owner_ctx! */
 		trace_x86_fpu_regs_deactivated(old_fpu);
-	} else
-		old_fpu->last_cpu = -1;
+	}
 }
 
 /*
@@ -520,12 +522,12 @@ switch_fpu_prepare(struct fpu *old_fpu, int cpu)
  */
 static inline void switch_fpu_finish(struct fpu *new_fpu, int cpu)
 {
-	bool preload = static_cpu_has(X86_FEATURE_FPU) &&
-		       new_fpu->initialized;
+	if (static_cpu_has(X86_FEATURE_FPU)) {
+		if (!fpregs_state_valid(new_fpu, cpu)) {
+			if (current->mm)
+				copy_kernel_to_fpregs(&new_fpu->state);
+		}
 
-	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 2e32e178e064..f098f6cab94b 100644
--- a/arch/x86/include/asm/fpu/types.h
+++ b/arch/x86/include/asm/fpu/types.h
@@ -294,15 +294,6 @@ struct fpu {
 	unsigned int			last_cpu;
 
 	/*
-	 * @initialized:
-	 *
-	 * This flag indicates whether this context is initialized: if the task
-	 * is not running then we can restore from this context, if the task
-	 * is running then we should save into this context.
-	 */
-	unsigned char			initialized;
-
-	/*
 	 * @avx512_timestamp:
 	 *
 	 * Records the timestamp of AVX512 use during last context switch.
diff --git a/arch/x86/include/asm/trace/fpu.h b/arch/x86/include/asm/trace/fpu.h
index 069c04be1507..bd65f6ba950f 100644
--- a/arch/x86/include/asm/trace/fpu.h
+++ b/arch/x86/include/asm/trace/fpu.h
@@ -13,22 +13,19 @@ DECLARE_EVENT_CLASS(x86_fpu,
 
 	TP_STRUCT__entry(
 		__field(struct fpu *, fpu)
-		__field(bool, initialized)
 		__field(u64, xfeatures)
 		__field(u64, xcomp_bv)
 		),
 
 	TP_fast_assign(
 		__entry->fpu		= fpu;
-		__entry->initialized	= fpu->initialized;
 		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 initialized: %d xfeatures: %llx xcomp_bv: %llx",
+	TP_printk("x86/fpu: %p xfeatures: %llx xcomp_bv: %llx",
 			__entry->fpu,
-			__entry->initialized,
 			__entry->xfeatures,
 			__entry->xcomp_bv
 	)