s390/kernel: lazy restore fpu registers

Improve the save and restore behavior of FPU register contents to use the
vector extension within the kernel.

The kernel does not use floating-point or vector registers and, therefore,
saving and restoring the FPU register contents are performed for handling
signals or switching processes only.  To prepare for using vector
instructions and vector registers within the kernel, enhance the save
behavior and implement a lazy restore at return to user space from a
system call or interrupt.

To implement the lazy restore, the save_fpu_regs() sets a CPU information
flag, CIF_FPU, to indicate that the FPU registers must be restored.
Saving and setting CIF_FPU is performed in an atomic fashion to be
interrupt-safe.  When the kernel wants to use the vector extension or
wants to change the FPU register state for a task during signal handling,
the save_fpu_regs() must be called first.  The CIF_FPU flag is also set at
process switch.  At return to user space, the FPU state is restored.  In
particular, the FPU state includes the floating-point or vector register
contents, as well as, vector-enablement and floating-point control.  The
FPU state restore and clearing CIF_FPU is also performed in an atomic
fashion.

For KVM, the restore of the FPU register state is performed when restoring
the general-purpose guest registers before the SIE instructions is started.
Because the path towards the SIE instruction is interruptible, the CIF_FPU
flag must be checked again right before going into SIE.  If set, the guest
registers must be reloaded again by re-entering the outer SIE loop.  This
is the same behavior as if the SIE critical section is interrupted.

Signed-off-by: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

1 files changed, 16 insertions, 37 deletions

diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index 52e2e1dd919d..8c525880a3ff 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -45,39 +45,27 @@ void update_cr_regs(struct task_struct *task)
 	struct per_regs old, new;
 
 	/* Take care of the enable/disable of transactional execution. */
-	if (MACHINE_HAS_TE || MACHINE_HAS_VX) {
+	if (MACHINE_HAS_TE) {
 		unsigned long cr, cr_new;
 
 		__ctl_store(cr, 0, 0);
-		cr_new = cr;
-		if (MACHINE_HAS_TE) {
-			/* Set or clear transaction execution TXC bit 8. */
-			cr_new |= (1UL << 55);
-			if (task->thread.per_flags & PER_FLAG_NO_TE)
-				cr_new &= ~(1UL << 55);
-		}
-		if (MACHINE_HAS_VX) {
-			/* Enable/disable of vector extension */
-			cr_new &= ~(1UL << 17);
-			if (task->thread.fpu.vxrs)
-				cr_new |= (1UL << 17);
-		}
+		/* Set or clear transaction execution TXC bit 8. */
+		cr_new = cr | (1UL << 55);
+		if (task->thread.per_flags & PER_FLAG_NO_TE)
+			cr_new &= ~(1UL << 55);
 		if (cr_new != cr)
 			__ctl_load(cr_new, 0, 0);
-		if (MACHINE_HAS_TE) {
-			/* Set/clear transaction execution TDC bits 62/63. */
-			__ctl_store(cr, 2, 2);
-			cr_new = cr & ~3UL;
-			if (task->thread.per_flags & PER_FLAG_TE_ABORT_RAND) {
-				if (task->thread.per_flags &
-				    PER_FLAG_TE_ABORT_RAND_TEND)
-					cr_new |= 1UL;
-				else
-					cr_new |= 2UL;
-			}
-			if (cr_new != cr)
-				__ctl_load(cr_new, 2, 2);
+		/* Set or clear transaction execution TDC bits 62 and 63. */
+		__ctl_store(cr, 2, 2);
+		cr_new = cr & ~3UL;
+		if (task->thread.per_flags & PER_FLAG_TE_ABORT_RAND) {
+			if (task->thread.per_flags & PER_FLAG_TE_ABORT_RAND_TEND)
+				cr_new |= 1UL;
+			else
+				cr_new |= 2UL;
 		}
+		if (cr_new != cr)
+			__ctl_load(cr_new, 2, 2);
 	}
 	/* Copy user specified PER registers */
 	new.control = thread->per_user.control;
@@ -998,9 +986,6 @@ static int s390_fpregs_set(struct task_struct *target,
 	else
 		memcpy(target->thread.fpu.fprs, &fprs, sizeof(fprs));
 
-	if (target == current)
-		restore_fpu_regs(&target->thread.fpu);
-
 	return rc;
 }
 
@@ -1090,12 +1075,9 @@ static int s390_vxrs_low_set(struct task_struct *target,
 		save_fpu_regs(&target->thread.fpu);
 
 	rc = user_regset_copyin(&pos, &count, &kbuf, &ubuf, vxrs, 0, -1);
-	if (rc == 0) {
+	if (rc == 0)
 		for (i = 0; i < __NUM_VXRS_LOW; i++)
 			*((__u64 *)(target->thread.fpu.vxrs + i) + 1) = vxrs[i];
-		if (target == current)
-			restore_fpu_regs(&target->thread.fpu);
-	}
 
 	return rc;
 }
@@ -1137,9 +1119,6 @@ static int s390_vxrs_high_set(struct task_struct *target,
 
 	rc = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
 				target->thread.fpu.vxrs + __NUM_VXRS_LOW, 0, -1);
-	if (rc == 0 && target == current)
-		restore_vx_regs(target->thread.fpu.vxrs);
-
 	return rc;
 }