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

Pull x86 FPU state handling updates from Borislav Petkov:
 "This contains work started by Rik van Riel and brought to fruition by
  Sebastian Andrzej Siewior with the main goal to optimize when to load
  FPU registers: only when returning to userspace and not on every
  context switch (while the task remains in the kernel).

  In addition, this optimization makes kernel_fpu_begin() cheaper by
  requiring registers saving only on the first invocation and skipping
  that in following ones.

  What is more, this series cleans up and streamlines many aspects of
  the already complex FPU code, hopefully making it more palatable for
  future improvements and simplifications.

  Finally, there's a __user annotations fix from Jann Horn"

* 'x86-fpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (29 commits)
  x86/fpu: Fault-in user stack if copy_fpstate_to_sigframe() fails
  x86/pkeys: Add PKRU value to init_fpstate
  x86/fpu: Restore regs in copy_fpstate_to_sigframe() in order to use the fastpath
  x86/fpu: Add a fastpath to copy_fpstate_to_sigframe()
  x86/fpu: Add a fastpath to __fpu__restore_sig()
  x86/fpu: Defer FPU state load until return to userspace
  x86/fpu: Merge the two code paths in __fpu__restore_sig()
  x86/fpu: Restore from kernel memory on the 64-bit path too
  x86/fpu: Inline copy_user_to_fpregs_zeroing()
  x86/fpu: Update xstate's PKRU value on write_pkru()
  x86/fpu: Prepare copy_fpstate_to_sigframe() for TIF_NEED_FPU_LOAD
  x86/fpu: Always store the registers in copy_fpstate_to_sigframe()
  x86/entry: Add TIF_NEED_FPU_LOAD
  x86/fpu: Eager switch PKRU state
  x86/pkeys: Don't check if PKRU is zero before writing it
  x86/fpu: Only write PKRU if it is different from current
  x86/pkeys: Provide *pkru() helpers
  x86/fpu: Use a feature number instead of mask in two more helpers
  x86/fpu: Make __raw_xsave_addr() use a feature number instead of mask
  x86/fpu: Add an __fpregs_load_activate() internal helper
  ...

1 files changed, 30 insertions, 18 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index b5edc8e3ce1d..d75bb97b983c 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3681,15 +3681,15 @@ static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu)
 	 */
 	valid = xstate_bv & ~XFEATURE_MASK_FPSSE;
 	while (valid) {
-		u64 feature = valid & -valid;
-		int index = fls64(feature) - 1;
-		void *src = get_xsave_addr(xsave, feature);
+		u64 xfeature_mask = valid & -valid;
+		int xfeature_nr = fls64(xfeature_mask) - 1;
+		void *src = get_xsave_addr(xsave, xfeature_nr);
 
 		if (src) {
 			u32 size, offset, ecx, edx;
-			cpuid_count(XSTATE_CPUID, index,
+			cpuid_count(XSTATE_CPUID, xfeature_nr,
 				    &size, &offset, &ecx, &edx);
-			if (feature == XFEATURE_MASK_PKRU)
+			if (xfeature_nr == XFEATURE_PKRU)
 				memcpy(dest + offset, &vcpu->arch.pkru,
 				       sizeof(vcpu->arch.pkru));
 			else
@@ -3697,7 +3697,7 @@ static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu)
 
 		}
 
-		valid -= feature;
+		valid -= xfeature_mask;
 	}
 }
 
@@ -3724,22 +3724,22 @@ static void load_xsave(struct kvm_vcpu *vcpu, u8 *src)
 	 */
 	valid = xstate_bv & ~XFEATURE_MASK_FPSSE;
 	while (valid) {
-		u64 feature = valid & -valid;
-		int index = fls64(feature) - 1;
-		void *dest = get_xsave_addr(xsave, feature);
+		u64 xfeature_mask = valid & -valid;
+		int xfeature_nr = fls64(xfeature_mask) - 1;
+		void *dest = get_xsave_addr(xsave, xfeature_nr);
 
 		if (dest) {
 			u32 size, offset, ecx, edx;
-			cpuid_count(XSTATE_CPUID, index,
+			cpuid_count(XSTATE_CPUID, xfeature_nr,
 				    &size, &offset, &ecx, &edx);
-			if (feature == XFEATURE_MASK_PKRU)
+			if (xfeature_nr == XFEATURE_PKRU)
 				memcpy(&vcpu->arch.pkru, src + offset,
 				       sizeof(vcpu->arch.pkru));
 			else
 				memcpy(dest, src + offset, size);
 		}
 
-		valid -= feature;
+		valid -= xfeature_mask;
 	}
 }
 
@@ -7899,6 +7899,10 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		wait_lapic_expire(vcpu);
 	guest_enter_irqoff();
 
+	fpregs_assert_state_consistent();
+	if (test_thread_flag(TIF_NEED_FPU_LOAD))
+		switch_fpu_return();
+
 	if (unlikely(vcpu->arch.switch_db_regs)) {
 		set_debugreg(0, 7);
 		set_debugreg(vcpu->arch.eff_db[0], 0);
@@ -8157,22 +8161,30 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu)
 /* Swap (qemu) user FPU context for the guest FPU context. */
 static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
 {
-	preempt_disable();
+	fpregs_lock();
+
 	copy_fpregs_to_fpstate(&current->thread.fpu);
 	/* PKRU is separately restored in kvm_x86_ops->run.  */
 	__copy_kernel_to_fpregs(&vcpu->arch.guest_fpu->state,
 				~XFEATURE_MASK_PKRU);
-	preempt_enable();
+
+	fpregs_mark_activate();
+	fpregs_unlock();
+
 	trace_kvm_fpu(1);
 }
 
 /* When vcpu_run ends, restore user space FPU context. */
 static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
 {
-	preempt_disable();
+	fpregs_lock();
+
 	copy_fpregs_to_fpstate(vcpu->arch.guest_fpu);
 	copy_kernel_to_fpregs(&current->thread.fpu.state);
-	preempt_enable();
+
+	fpregs_mark_activate();
+	fpregs_unlock();
+
 	++vcpu->stat.fpu_reload;
 	trace_kvm_fpu(0);
 }
@@ -8870,11 +8882,11 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 		if (init_event)
 			kvm_put_guest_fpu(vcpu);
 		mpx_state_buffer = get_xsave_addr(&vcpu->arch.guest_fpu->state.xsave,
-					XFEATURE_MASK_BNDREGS);
+					XFEATURE_BNDREGS);
 		if (mpx_state_buffer)
 			memset(mpx_state_buffer, 0, sizeof(struct mpx_bndreg_state));
 		mpx_state_buffer = get_xsave_addr(&vcpu->arch.guest_fpu->state.xsave,
-					XFEATURE_MASK_BNDCSR);
+					XFEATURE_BNDCSR);
 		if (mpx_state_buffer)
 			memset(mpx_state_buffer, 0, sizeof(struct mpx_bndcsr));
 		if (init_event)