Merge branch 'for-next/sve' into for-next/core

Optimise SVE switching for CPUs with 128-bit implementations.

* for-next/sve:
  arm64/sve: Skip flushing Z registers with 128 bit vectors
  arm64/sve: Use the sve_flush macros in sve_load_from_fpsimd_state()
  arm64/sve: Split _sve_flush macro into separate Z and predicate flushes

4 files changed, 23 insertions, 11 deletions

diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index 2599504674b5..c072161d5c65 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -69,7 +69,7 @@ static inline void *sve_pffr(struct thread_struct *thread)
 extern void sve_save_state(void *state, u32 *pfpsr);
 extern void sve_load_state(void const *state, u32 const *pfpsr,
 			   unsigned long vq_minus_1);
-extern void sve_flush_live(void);
+extern void sve_flush_live(unsigned long vq_minus_1);
 extern void sve_load_from_fpsimd_state(struct user_fpsimd_state const *state,
 				       unsigned long vq_minus_1);
 extern unsigned int sve_get_vl(void);
diff --git a/arch/arm64/include/asm/fpsimdmacros.h b/arch/arm64/include/asm/fpsimdmacros.h
index a2563992d2dc..059204477ce6 100644
--- a/arch/arm64/include/asm/fpsimdmacros.h
+++ b/arch/arm64/include/asm/fpsimdmacros.h
@@ -213,8 +213,10 @@
 	mov	v\nz\().16b, v\nz\().16b
 .endm
 
-.macro sve_flush
+.macro sve_flush_z
  _for n, 0, 31, _sve_flush_z	\n
+.endm
+.macro sve_flush_p_ffr
  _for n, 0, 15, _sve_pfalse	\n
 		_sve_wrffr	0
 .endm
diff --git a/arch/arm64/kernel/entry-fpsimd.S b/arch/arm64/kernel/entry-fpsimd.S
index 3ecec60d3295..0a7a64753878 100644
--- a/arch/arm64/kernel/entry-fpsimd.S
+++ b/arch/arm64/kernel/entry-fpsimd.S
@@ -63,16 +63,24 @@ SYM_FUNC_END(sve_set_vq)
  * and the rest zeroed. All the other SVE registers will be zeroed.
  */
 SYM_FUNC_START(sve_load_from_fpsimd_state)
-		sve_load_vq	x1, x2, x3
-		fpsimd_restore	x0, 8
- _for n, 0, 15, _sve_pfalse	\n
-		_sve_wrffr	0
-		ret
+	sve_load_vq	x1, x2, x3
+	fpsimd_restore	x0, 8
+	sve_flush_p_ffr
+	ret
 SYM_FUNC_END(sve_load_from_fpsimd_state)
 
-/* Zero all SVE registers but the first 128-bits of each vector */
+/*
+ * Zero all SVE registers but the first 128-bits of each vector
+ *
+ * VQ must already be configured by caller, any further updates of VQ
+ * will need to ensure that the register state remains valid.
+ *
+ * x0 = VQ - 1
+ */
 SYM_FUNC_START(sve_flush_live)
-	sve_flush
+	cbz		x0, 1f	// A VQ-1 of 0 is 128 bits so no extra Z state
+	sve_flush_z
+1:	sve_flush_p_ffr
 	ret
 SYM_FUNC_END(sve_flush_live)
 
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index ad3dd34a83cf..e57b23f95284 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -957,8 +957,10 @@ void do_sve_acc(unsigned int esr, struct pt_regs *regs)
 	 * disabling the trap, otherwise update our in-memory copy.
 	 */
 	if (!test_thread_flag(TIF_FOREIGN_FPSTATE)) {
-		sve_set_vq(sve_vq_from_vl(current->thread.sve_vl) - 1);
-		sve_flush_live();
+		unsigned long vq_minus_one =
+			sve_vq_from_vl(current->thread.sve_vl) - 1;
+		sve_set_vq(vq_minus_one);
+		sve_flush_live(vq_minus_one);
 		fpsimd_bind_task_to_cpu();
 	} else {
 		fpsimd_to_sve(current);