[PATCH 6.12] raid6: add missing vzeroupper to AVX-512 code

[PATCH 6.12] raid6: add missing vzeroupper to AVX-512 code

[Eric Biggers]

commit b82cf9e49c1be7cf1fd8e1bd806b0cdd25ab8127 upstream.

Since the AVX-512 optimized RAID6 code uses ZMM registers, execute
vzeroupper before returning from it.  This is needed to avoid degrading
the performance of any later SSE code that may happen to be executed.

Link: https://lore.kernel.org/20260831212316.213896-1-ebiggers@kernel.org
Fixes: e0a491c12968 ("lib/raid6: Add AVX512 optimized gen_syndrome functions")
Fixes: 13c520b2993c ("lib/raid6: Add AVX512 optimized recovery functions")
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: <stable@vger.kernel.org>
---
 lib/raid6/avx512.c       | 6 ++++++
 lib/raid6/recov_avx512.c | 2 ++
 2 files changed, 8 insertions(+)

diff --git a/lib/raid6/avx512.c b/lib/raid6/avx512.c
index 9c3e822e1adf5..30956989e7d74 100644
--- a/lib/raid6/avx512.c
+++ b/lib/raid6/avx512.c
@@ -95,6 +95,7 @@ static void raid6_avx5121_gen_syndrome(int disks, size_t bytes, void **ptrs)
 	}
 
 	asm volatile("sfence" : : : "memory");
+	asm volatile("vzeroupper");
 	kernel_fpu_end();
 }
 
@@ -154,6 +155,7 @@ static void raid6_avx5121_xor_syndrome(int disks, int start, int stop,
 	}
 
 	asm volatile("sfence" : : : "memory");
+	asm volatile("vzeroupper");
 	kernel_fpu_end();
 }
 
@@ -227,6 +229,7 @@ static void raid6_avx5122_gen_syndrome(int disks, size_t bytes, void **ptrs)
 	}
 
 	asm volatile("sfence" : : : "memory");
+	asm volatile("vzeroupper");
 	kernel_fpu_end();
 }
 
@@ -311,6 +314,7 @@ static void raid6_avx5122_xor_syndrome(int disks, int start, int stop,
 	}
 
 	asm volatile("sfence" : : : "memory");
+	asm volatile("vzeroupper");
 	kernel_fpu_end();
 }
 
@@ -417,6 +421,7 @@ static void raid6_avx5124_gen_syndrome(int disks, size_t bytes, void **ptrs)
 	}
 
 	asm volatile("sfence" : : : "memory");
+	asm volatile("vzeroupper");
 	kernel_fpu_end();
 }
 
@@ -550,6 +555,7 @@ static void raid6_avx5124_xor_syndrome(int disks, int start, int stop,
 			       "m" (q[d+128]), "m" (q[d+192]));
 	}
 	asm volatile("sfence" : : : "memory");
+	asm volatile("vzeroupper");
 	kernel_fpu_end();
 }
 const struct raid6_calls raid6_avx512x4 = {
diff --git a/lib/raid6/recov_avx512.c b/lib/raid6/recov_avx512.c
index fd9e15bf3f30f..c8a152d9ab6da 100644
--- a/lib/raid6/recov_avx512.c
+++ b/lib/raid6/recov_avx512.c
@@ -221,6 +221,7 @@ static void raid6_2data_recov_avx512(int disks, size_t bytes, int faila,
 #endif
 	}
 
+	asm volatile("vzeroupper");
 	kernel_fpu_end();
 }
 
@@ -363,6 +364,7 @@ static void raid6_datap_recov_avx512(int disks, size_t bytes, int faila,
 #endif
 	}
 
+	asm volatile("vzeroupper");
 	kernel_fpu_end();
 }
 

base-commit: 5c40a1750f44dd6c7292d8c8d0b4ffff1734576e
-- 
2.56.0

Re: [PATCH 6.12] raid6: add missing vzeroupper to AVX-512 code

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential
issue to consider:
- [Low] raid6: missing Fixes trailer for AVX-512 xor_syndrome commit
  694dda62d286
--

commit 369a70502fe6ce19affa3189f8d493476e955e10
Author: Eric Biggers <ebiggers@kernel.org>

> raid6: add missing vzeroupper to AVX-512 code
>
> commit b82cf9e49c1be7cf1fd8e1bd806b0cdd25ab8127 upstream.
>
> Since the AVX-512 optimized RAID6 code uses ZMM registers, execute
> vzeroupper before returning from it.  This is needed to avoid degrading
> the performance of any later SSE code that may happen to be executed.
>
> Link: https://lore.kernel.org/20260831212316.213896-1-ebiggers@kernel.org
> Fixes: e0a491c12968 ("lib/raid6: Add AVX512 optimized gen_syndrome functions")
> Fixes: 13c520b2993c ("lib/raid6: Add AVX512 optimized recovery functions")
> Signed-off-by: Eric Biggers <ebiggers@kernel.org>
> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
> Cc: Christoph Hellwig <hch@lst.de>
> Cc: <stable@vger.kernel.org>

[Severity: Low]
In addition to the gen_syndrome and recovery functions, this patch adds
vzeroupper to raid6_avx5121_xor_syndrome(), raid6_avx5122_xor_syndrome(),
and raid6_avx5124_xor_syndrome().  Should this also include:

  Fixes: 694dda62d286 ("lib/raid6: Add AVX512 optimized xor_syndrome functions")

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20261107200913.103158-1-ebiggers@kernel.org?part=1