arm64/sve: Skip flushing Z registers with 128 bit vectors
When the SVE vector length is 128 bits then there are no bits in the Z
registers which are not shared with the V registers so we can skip them
when zeroing state not shared with FPSIMD, this results in a minor
performance improvement.
Signed-off-by: Mark Brown <broonie@kernel.org>
diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index 2599504..c072161 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -69,7 +69,7 @@
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/kernel/entry-fpsimd.S b/arch/arm64/kernel/entry-fpsimd.S
index dd8382e..87ef2583 100644
--- a/arch/arm64/kernel/entry-fpsimd.S
+++ b/arch/arm64/kernel/entry-fpsimd.S
@@ -69,10 +69,15 @@
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
+ *
+ * x0 = VQ - 1
+ */
SYM_FUNC_START(sve_flush_live)
+ cbz x0, 1f // A VQ-1 of 0 is 128 bits so no extra Z state
sve_flush_z
- sve_flush_p_ffr
+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 ad3dd34..e57b23f 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -957,8 +957,10 @@
* 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);
