[PATCH v3 5/8] arm64/sve: Implement a helper to flush SVE registers

Mark Brown broonie at kernel.org
Mon Jun 29 09:35:53 EDT 2020


From: Julien Grall <julien.grall at arm.com>

Introduce a new helper that will zero all SVE registers but the first
128-bits of each vector. This will be used by subsequent patches to
avoid costly store/maipulate/reload sequences in places like do_sve_acc().

Signed-off-by: Julien Grall <julien.grall at arm.com>
Reviewed-by: Dave Martin <Dave.Martin at arm.com>
Signed-off-by: Mark Brown <broonie at kernel.org>
---
 arch/arm64/include/asm/fpsimd.h       |  1 +
 arch/arm64/include/asm/fpsimdmacros.h | 19 +++++++++++++++++++
 arch/arm64/kernel/entry-fpsimd.S      |  8 ++++++++
 3 files changed, 28 insertions(+)

diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index 59f10dd13f12..958f642e930d 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -69,6 +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 unsigned int sve_get_vl(void);
 
 struct arm64_cpu_capabilities;
diff --git a/arch/arm64/include/asm/fpsimdmacros.h b/arch/arm64/include/asm/fpsimdmacros.h
index feef5b371fba..af43367534c7 100644
--- a/arch/arm64/include/asm/fpsimdmacros.h
+++ b/arch/arm64/include/asm/fpsimdmacros.h
@@ -164,6 +164,13 @@
 		| ((\np) << 5)
 .endm
 
+/* PFALSE P\np.B */
+.macro _sve_pfalse np
+	_sve_check_preg \np
+	.inst	0x2518e400			\
+		| (\np)
+.endm
+
 .macro __for from:req, to:req
 	.if (\from) == (\to)
 		_for__body %\from
@@ -198,6 +205,18 @@
 921:
 .endm
 
+/* Preserve the first 128-bits of Znz and zero the rest. */
+.macro _sve_flush_z nz
+	_sve_check_zreg \nz
+	mov	v\nz\().16b, v\nz\().16b
+.endm
+
+.macro sve_flush
+ _for n, 0, 31, _sve_flush_z	\n
+ _for n, 0, 15, _sve_pfalse	\n
+		_sve_wrffr	0
+.endm
+
 .macro sve_save nxbase, xpfpsr, nxtmp
  _for n, 0, 31,	_sve_str_v	\n, \nxbase, \n - 34
  _for n, 0, 15,	_sve_str_p	\n, \nxbase, \n - 16
diff --git a/arch/arm64/kernel/entry-fpsimd.S b/arch/arm64/kernel/entry-fpsimd.S
index f880dd63ddc3..fdf7a5a35c63 100644
--- a/arch/arm64/kernel/entry-fpsimd.S
+++ b/arch/arm64/kernel/entry-fpsimd.S
@@ -32,6 +32,7 @@ SYM_FUNC_START(fpsimd_load_state)
 SYM_FUNC_END(fpsimd_load_state)
 
 #ifdef CONFIG_ARM64_SVE
+
 SYM_FUNC_START(sve_save_state)
 	sve_save 0, x1, 2
 	ret
@@ -46,4 +47,11 @@ SYM_FUNC_START(sve_get_vl)
 	_sve_rdvl	0, 1
 	ret
 SYM_FUNC_END(sve_get_vl)
+
+/* Zero all SVE registers but the first 128-bits of each vector */
+SYM_FUNC_START(sve_flush_live)
+	sve_flush
+	ret
+SYM_FUNC_END(sve_flush_live)
+
 #endif /* CONFIG_ARM64_SVE */
-- 
2.20.1




More information about the linux-arm-kernel mailing list