From: Eric Biggers <ebiggers@kernel.org>
To: akpm@linux-foundation.org, linux-raid@vger.kernel.org
Cc: linux-crypto@vger.kernel.org, x86@kernel.org,
Christoph Hellwig <hch@lst.de>,
Richard Weinberger <richard@nod.at>,
Anton Ivanov <anton.ivanov@cambridgegreys.com>,
Johannes Berg <johannes@sipsolutions.net>,
Eric Biggers <ebiggers@kernel.org>
Subject: [PATCH 3/3] raid6: opt out of initializing MXCSR and 387 state
Date: Wed, 11 Nov 2026 12:56:04 -0800 [thread overview]
Message-ID: <20261111205604.47547-4-ebiggers@kernel.org> (raw)
In-Reply-To: <20261111205604.47547-1-ebiggers@kernel.org>
The RAID6 code using "kernel-mode FPU" is integer code that does not use
any MMX or x87 instructions. (MMX optimized code previously existed but
was recently removed.) To the extent that float-domain instructions are
used at all, they are only moves, shuffles, and XORs, none of which
raises SIMD floating-point exceptions or depends on MXCSR.
Therefore, there's no need to initialize MXCSR or the 387 FPU state.
Opt out of this initialization by using kernel_fpu_begin_mask(0) instead
of kernel_fpu_begin(). This eliminates an 'ldmxcsr' instruction in
every kernel-mode FPU section, reducing overhead, which matters most for
short input lengths. On 32-bit kernels it also eliminates 'fninit'.
This will make the RAID code consistent with the crypto and CRC code,
which are also switching to kernel_fpu_begin_mask(0)
(https://lore.kernel.org/linux-crypto/20261105005523.84925-1-ebiggers@kernel.org/).
Another precedent for this optimization can be found in
commit a58db7ad80e8 ("netfilter: nft_set_pipapo_avx2: Skip LDMXCSR, we
don't need a valid MXCSR state").
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
---
lib/raid/raid6/x86/avx2.c | 12 ++++++------
lib/raid/raid6/x86/avx512.c | 12 ++++++------
lib/raid/raid6/x86/recov_avx2.c | 4 ++--
lib/raid/raid6/x86/recov_avx512.c | 4 ++--
lib/raid/raid6/x86/recov_ssse3.c | 4 ++--
lib/raid/raid6/x86/sse2.c | 12 ++++++------
6 files changed, 24 insertions(+), 24 deletions(-)
diff --git a/lib/raid/raid6/x86/avx2.c b/lib/raid/raid6/x86/avx2.c
index 3cc2fe7ac42c5..e09d0bd418efc 100644
--- a/lib/raid/raid6/x86/avx2.c
+++ b/lib/raid/raid6/x86/avx2.c
@@ -32,7 +32,7 @@ static void raid6_avx21_gen_syndrome(int disks, size_t bytes, void **ptrs)
p = dptr[z0+1]; /* XOR parity */
q = dptr[z0+2]; /* RS syndrome */
- kernel_fpu_begin();
+ kernel_fpu_begin_mask(0);
asm volatile("vmovdqa %0,%%ymm0" : : "m" (raid6_avx2_constants.x1d[0]));
asm volatile("vpxor %ymm3,%ymm3,%ymm3"); /* Zero temp */
@@ -82,7 +82,7 @@ static void raid6_avx21_xor_syndrome(int disks, int start, int stop,
p = dptr[disks-2]; /* XOR parity */
q = dptr[disks-1]; /* RS syndrome */
- kernel_fpu_begin();
+ kernel_fpu_begin_mask(0);
asm volatile("vmovdqa %0,%%ymm0" : : "m" (raid6_avx2_constants.x1d[0]));
@@ -139,7 +139,7 @@ static void raid6_avx22_gen_syndrome(int disks, size_t bytes, void **ptrs)
p = dptr[z0+1]; /* XOR parity */
q = dptr[z0+2]; /* RS syndrome */
- kernel_fpu_begin();
+ kernel_fpu_begin_mask(0);
asm volatile("vmovdqa %0,%%ymm0" : : "m" (raid6_avx2_constants.x1d[0]));
asm volatile("vpxor %ymm1,%ymm1,%ymm1"); /* Zero temp */
@@ -192,7 +192,7 @@ static void raid6_avx22_xor_syndrome(int disks, int start, int stop,
p = dptr[disks-2]; /* XOR parity */
q = dptr[disks-1]; /* RS syndrome */
- kernel_fpu_begin();
+ kernel_fpu_begin_mask(0);
asm volatile("vmovdqa %0,%%ymm0" : : "m" (raid6_avx2_constants.x1d[0]));
@@ -271,7 +271,7 @@ static void raid6_avx24_gen_syndrome(int disks, size_t bytes, void **ptrs)
p = dptr[z0+1]; /* XOR parity */
q = dptr[z0+2]; /* RS syndrome */
- kernel_fpu_begin();
+ kernel_fpu_begin_mask(0);
asm volatile("vmovdqa %0,%%ymm0" : : "m" (raid6_avx2_constants.x1d[0]));
asm volatile("vpxor %ymm1,%ymm1,%ymm1"); /* Zero temp */
@@ -353,7 +353,7 @@ static void raid6_avx24_xor_syndrome(int disks, int start, int stop,
p = dptr[disks-2]; /* XOR parity */
q = dptr[disks-1]; /* RS syndrome */
- kernel_fpu_begin();
+ kernel_fpu_begin_mask(0);
asm volatile("vmovdqa %0,%%ymm0" :: "m" (raid6_avx2_constants.x1d[0]));
diff --git a/lib/raid/raid6/x86/avx512.c b/lib/raid/raid6/x86/avx512.c
index 772bfc4af6dfd..6ba5ca7df29d5 100644
--- a/lib/raid/raid6/x86/avx512.c
+++ b/lib/raid/raid6/x86/avx512.c
@@ -34,7 +34,7 @@ static void raid6_avx5121_gen_syndrome(int disks, size_t bytes, void **ptrs)
p = dptr[z0+1]; /* XOR parity */
q = dptr[z0+2]; /* RS syndrome */
- kernel_fpu_begin();
+ kernel_fpu_begin_mask(0);
asm volatile("vmovdqa64 %0,%%zmm0\n\t"
"vpxorq %%zmm1,%%zmm1,%%zmm1" /* Zero temp */
@@ -93,7 +93,7 @@ static void raid6_avx5121_xor_syndrome(int disks, int start, int stop,
p = dptr[disks-2]; /* XOR parity */
q = dptr[disks-1]; /* RS syndrome */
- kernel_fpu_begin();
+ kernel_fpu_begin_mask(0);
asm volatile("vmovdqa64 %0,%%zmm0"
: : "m" (raid6_avx512_constants.x1d[0]));
@@ -161,7 +161,7 @@ static void raid6_avx5122_gen_syndrome(int disks, size_t bytes, void **ptrs)
p = dptr[z0+1]; /* XOR parity */
q = dptr[z0+2]; /* RS syndrome */
- kernel_fpu_begin();
+ kernel_fpu_begin_mask(0);
asm volatile("vmovdqa64 %0,%%zmm0\n\t"
"vpxorq %%zmm1,%%zmm1,%%zmm1" /* Zero temp */
@@ -225,7 +225,7 @@ static void raid6_avx5122_xor_syndrome(int disks, int start, int stop,
p = dptr[disks-2]; /* XOR parity */
q = dptr[disks-1]; /* RS syndrome */
- kernel_fpu_begin();
+ kernel_fpu_begin_mask(0);
asm volatile("vmovdqa64 %0,%%zmm0"
: : "m" (raid6_avx512_constants.x1d[0]));
@@ -320,7 +320,7 @@ static void raid6_avx5124_gen_syndrome(int disks, size_t bytes, void **ptrs)
p = dptr[z0+1]; /* XOR parity */
q = dptr[z0+2]; /* RS syndrome */
- kernel_fpu_begin();
+ kernel_fpu_begin_mask(0);
asm volatile("vmovdqa64 %0,%%zmm0\n\t"
"vpxorq %%zmm1,%%zmm1,%%zmm1\n\t" /* Zero temp */
@@ -415,7 +415,7 @@ static void raid6_avx5124_xor_syndrome(int disks, int start, int stop,
p = dptr[disks-2]; /* XOR parity */
q = dptr[disks-1]; /* RS syndrome */
- kernel_fpu_begin();
+ kernel_fpu_begin_mask(0);
asm volatile("vmovdqa64 %0,%%zmm0"
:: "m" (raid6_avx512_constants.x1d[0]));
diff --git a/lib/raid/raid6/x86/recov_avx2.c b/lib/raid/raid6/x86/recov_avx2.c
index 820871046e305..41c050746b3dd 100644
--- a/lib/raid/raid6/x86/recov_avx2.c
+++ b/lib/raid/raid6/x86/recov_avx2.c
@@ -43,7 +43,7 @@ static void raid6_2data_recov_avx2(int disks, size_t bytes, int faila,
qmul = raid6_vgfmul[raid6_gfinv[raid6_gfexp[faila] ^
raid6_gfexp[failb]]];
- kernel_fpu_begin();
+ kernel_fpu_begin_mask(0);
/* ymm0 = x0f[16] */
asm volatile("vpbroadcastb %0, %%ymm7" : : "m" (x0f));
@@ -205,7 +205,7 @@ static void raid6_datap_recov_avx2(int disks, size_t bytes, int faila,
/* Now, pick the proper data tables */
qmul = raid6_vgfmul[raid6_gfinv[raid6_gfexp[faila]]];
- kernel_fpu_begin();
+ kernel_fpu_begin_mask(0);
asm volatile("vpbroadcastb %0, %%ymm7" : : "m" (x0f));
diff --git a/lib/raid/raid6/x86/recov_avx512.c b/lib/raid/raid6/x86/recov_avx512.c
index 299a3f044d616..3b48822b61ac3 100644
--- a/lib/raid/raid6/x86/recov_avx512.c
+++ b/lib/raid/raid6/x86/recov_avx512.c
@@ -48,7 +48,7 @@ static void raid6_2data_recov_avx512(int disks, size_t bytes, int faila,
qmul = raid6_vgfmul[raid6_gfinv[raid6_gfexp[faila] ^
raid6_gfexp[failb]]];
- kernel_fpu_begin();
+ kernel_fpu_begin_mask(0);
/* zmm0 = x0f[16] */
asm volatile("vpbroadcastb %0, %%zmm7" : : "m" (x0f));
@@ -243,7 +243,7 @@ static void raid6_datap_recov_avx512(int disks, size_t bytes, int faila,
/* Now, pick the proper data tables */
qmul = raid6_vgfmul[raid6_gfinv[raid6_gfexp[faila]]];
- kernel_fpu_begin();
+ kernel_fpu_begin_mask(0);
asm volatile("vpbroadcastb %0, %%zmm7" : : "m" (x0f));
diff --git a/lib/raid/raid6/x86/recov_ssse3.c b/lib/raid/raid6/x86/recov_ssse3.c
index 700bd2c865ece..5540944945d57 100644
--- a/lib/raid/raid6/x86/recov_ssse3.c
+++ b/lib/raid/raid6/x86/recov_ssse3.c
@@ -44,7 +44,7 @@ static void raid6_2data_recov_ssse3(int disks, size_t bytes, int faila,
qmul = raid6_vgfmul[raid6_gfinv[raid6_gfexp[faila] ^
raid6_gfexp[failb]]];
- kernel_fpu_begin();
+ kernel_fpu_begin_mask(0);
asm volatile("movdqa %0,%%xmm7" : : "m" (x0f[0]));
@@ -210,7 +210,7 @@ static void raid6_datap_recov_ssse3(int disks, size_t bytes, int faila,
/* Now, pick the proper data tables */
qmul = raid6_vgfmul[raid6_gfinv[raid6_gfexp[faila]]];
- kernel_fpu_begin();
+ kernel_fpu_begin_mask(0);
asm volatile("movdqa %0, %%xmm7" : : "m" (x0f[0]));
diff --git a/lib/raid/raid6/x86/sse2.c b/lib/raid/raid6/x86/sse2.c
index 43b09ce58270a..2bbb288c244fc 100644
--- a/lib/raid/raid6/x86/sse2.c
+++ b/lib/raid/raid6/x86/sse2.c
@@ -28,7 +28,7 @@ static void raid6_sse21_gen_syndrome(int disks, size_t bytes, void **ptrs)
p = dptr[z0+1]; /* XOR parity */
q = dptr[z0+2]; /* RS syndrome */
- kernel_fpu_begin();
+ kernel_fpu_begin_mask(0);
asm volatile("movdqa %0,%%xmm0" : : "m" (raid6_sse_constants.x1d[0]));
asm volatile("pxor %xmm5,%xmm5"); /* Zero temp */
@@ -80,7 +80,7 @@ static void raid6_sse21_xor_syndrome(int disks, int start, int stop,
p = dptr[disks-2]; /* XOR parity */
q = dptr[disks-1]; /* RS syndrome */
- kernel_fpu_begin();
+ kernel_fpu_begin_mask(0);
asm volatile("movdqa %0,%%xmm0" : : "m" (raid6_sse_constants.x1d[0]));
@@ -136,7 +136,7 @@ static void raid6_sse22_gen_syndrome(int disks, size_t bytes, void **ptrs)
p = dptr[z0+1]; /* XOR parity */
q = dptr[z0+2]; /* RS syndrome */
- kernel_fpu_begin();
+ kernel_fpu_begin_mask(0);
asm volatile("movdqa %0,%%xmm0" : : "m" (raid6_sse_constants.x1d[0]));
asm volatile("pxor %xmm5,%xmm5"); /* Zero temp */
@@ -189,7 +189,7 @@ static void raid6_sse22_xor_syndrome(int disks, int start, int stop,
p = dptr[disks-2]; /* XOR parity */
q = dptr[disks-1]; /* RS syndrome */
- kernel_fpu_begin();
+ kernel_fpu_begin_mask(0);
asm volatile("movdqa %0,%%xmm0" : : "m" (raid6_sse_constants.x1d[0]));
@@ -266,7 +266,7 @@ static void raid6_sse24_gen_syndrome(int disks, size_t bytes, void **ptrs)
p = dptr[z0+1]; /* XOR parity */
q = dptr[z0+2]; /* RS syndrome */
- kernel_fpu_begin();
+ kernel_fpu_begin_mask(0);
asm volatile("movdqa %0,%%xmm0" :: "m" (raid6_sse_constants.x1d[0]));
asm volatile("pxor %xmm2,%xmm2"); /* P[0] */
@@ -353,7 +353,7 @@ static void raid6_sse24_xor_syndrome(int disks, int start, int stop,
p = dptr[disks-2]; /* XOR parity */
q = dptr[disks-1]; /* RS syndrome */
- kernel_fpu_begin();
+ kernel_fpu_begin_mask(0);
asm volatile("movdqa %0,%%xmm0" :: "m" (raid6_sse_constants.x1d[0]));
--
2.56.1
prev parent reply other threads:[~2026-11-11 20:56 UTC|newest]
Thread overview: 5+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-11-11 20:56 [PATCH 0/3] lib/raid: opt out of initializing MXCSR and 387 state Eric Biggers
2026-11-11 20:56 ` [PATCH 1/3] um: Define kernel_fpu_begin_mask() Eric Biggers
2026-11-12 7:28 ` Johannes Berg
2026-11-11 20:56 ` [PATCH 2/3] xor: opt out of initializing MXCSR and 387 state Eric Biggers
2026-11-11 20:56 ` Eric Biggers [this message]
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20261111205604.47547-4-ebiggers@kernel.org \
--to=ebiggers@kernel.org \
--cc=akpm@linux-foundation.org \
--cc=anton.ivanov@cambridgegreys.com \
--cc=hch@lst.de \
--cc=johannes@sipsolutions.net \
--cc=linux-crypto@vger.kernel.org \
--cc=linux-raid@vger.kernel.org \
--cc=richard@nod.at \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox