zcommon: Refactor FPU state handling in fletcher4

Currently calls to kfpu_begin() and kfpu_end() are split between
the init() and fini() functions of the particular SIMD
implementation. This was done in #14247 as an optimization measure
for the ABD adapter. Unfortunately the split complicates FPU
handling on platforms that use a local FPU state buffer, like
Windows and macOS.

To ease porting, we introduce a boolean struct member in
fletcher_4_ops_t, indicating use of the FPU, and move the FPU state
handling from the SIMD implementations to the call sites.

Reviewed-by: Tino Reichardt <[email protected]>
Reviewed-by: Richard Yao <[email protected]>
Reviewed-by: Jorgen Lundman <[email protected]>
Signed-off-by: Attila Fülöp <[email protected]>
Closes #14600 

1 files changed, 2 insertions, 2 deletions

diff --git a/module/zcommon/zfs_fletcher_avx512.c b/module/zcommon/zfs_fletcher_avx512.c
index 4a3d5cb24..81182ead2 100644
--- a/module/zcommon/zfs_fletcher_avx512.c
+++ b/module/zcommon/zfs_fletcher_avx512.c
@@ -39,7 +39,6 @@ ZFS_NO_SANITIZE_UNDEFINED
 static void
 fletcher_4_avx512f_init(fletcher_4_ctx_t *ctx)
 {
-	kfpu_begin();
 	memset(ctx->avx512, 0, 4 * sizeof (zfs_fletcher_avx512_t));
 }
 
@@ -73,7 +72,6 @@ fletcher_4_avx512f_fini(fletcher_4_ctx_t *ctx, zio_cksum_t *zcp)
 	}
 
 	ZIO_SET_CHECKSUM(zcp, A, B, C, D);
-	kfpu_end();
 }
 
 #define	FLETCHER_4_AVX512_RESTORE_CTX(ctx)				\
@@ -166,6 +164,7 @@ const fletcher_4_ops_t fletcher_4_avx512f_ops = {
 	.fini_byteswap = fletcher_4_avx512f_fini,
 	.compute_byteswap = fletcher_4_avx512f_byteswap,
 	.valid = fletcher_4_avx512f_valid,
+	.uses_fpu = B_TRUE,
 	.name = "avx512f"
 };
 
@@ -216,6 +215,7 @@ const fletcher_4_ops_t fletcher_4_avx512bw_ops = {
 	.fini_byteswap = fletcher_4_avx512f_fini,
 	.compute_byteswap = fletcher_4_avx512bw_byteswap,
 	.valid = fletcher_4_avx512bw_valid,
+	.uses_fpu = B_TRUE,
 	.name = "avx512bw"
 };
 #endif