Merge tag 'arm64-fpsimd-on-stack-for-v6.19' into libcrypto-fpsimd-on-stack

Pull fpsimd-on-stack changes from Ard Biesheuvel:

  "Shared tag/branch for arm64 FP/SIMD changes going through libcrypto"

Signed-off-by: Eric Biggers <ebiggers@kernel.org>

6 files changed, 35 insertions, 62 deletions

diff --git a/lib/crc/arm/crc-t10dif.h b/lib/crc/arm/crc-t10dif.h
index 63441de5e3f1..afc0ebf97f19 100644
--- a/lib/crc/arm/crc-t10dif.h
+++ b/lib/crc/arm/crc-t10dif.h
@@ -5,7 +5,6 @@
  * Copyright (C) 2016 Linaro Ltd <ard.biesheuvel@linaro.org>
  */
 
-#include <asm/neon.h>
 #include <asm/simd.h>
 
 static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);
@@ -19,22 +18,16 @@ asmlinkage void crc_t10dif_pmull8(u16 init_crc, const u8 *buf, size_t len,
 
 static inline u16 crc_t10dif_arch(u16 crc, const u8 *data, size_t length)
 {
-	if (length >= CRC_T10DIF_PMULL_CHUNK_SIZE) {
+	if (length >= CRC_T10DIF_PMULL_CHUNK_SIZE && likely(may_use_simd())) {
 		if (static_branch_likely(&have_pmull)) {
-			if (likely(may_use_simd())) {
-				kernel_neon_begin();
-				crc = crc_t10dif_pmull64(crc, data, length);
-				kernel_neon_end();
-				return crc;
-			}
+			scoped_ksimd()
+				return crc_t10dif_pmull64(crc, data, length);
 		} else if (length > CRC_T10DIF_PMULL_CHUNK_SIZE &&
-			   static_branch_likely(&have_neon) &&
-			   likely(may_use_simd())) {
+			   static_branch_likely(&have_neon)) {
 			u8 buf[16] __aligned(16);
 
-			kernel_neon_begin();
-			crc_t10dif_pmull8(crc, data, length, buf);
-			kernel_neon_end();
+			scoped_ksimd()
+				crc_t10dif_pmull8(crc, data, length, buf);
 
 			return crc_t10dif_generic(0, buf, sizeof(buf));
 		}
diff --git a/lib/crc/arm/crc32.h b/lib/crc/arm/crc32.h
index 7b76f52f6907..f33de6b22cd4 100644
--- a/lib/crc/arm/crc32.h
+++ b/lib/crc/arm/crc32.h
@@ -8,7 +8,6 @@
 #include <linux/cpufeature.h>
 
 #include <asm/hwcap.h>
-#include <asm/neon.h>
 #include <asm/simd.h>
 
 static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_crc32);
@@ -42,9 +41,8 @@ static inline u32 crc32_le_arch(u32 crc, const u8 *p, size_t len)
 			len -= n;
 		}
 		n = round_down(len, 16);
-		kernel_neon_begin();
-		crc = crc32_pmull_le(p, n, crc);
-		kernel_neon_end();
+		scoped_ksimd()
+			crc = crc32_pmull_le(p, n, crc);
 		p += n;
 		len -= n;
 	}
@@ -71,9 +69,8 @@ static inline u32 crc32c_arch(u32 crc, const u8 *p, size_t len)
 			len -= n;
 		}
 		n = round_down(len, 16);
-		kernel_neon_begin();
-		crc = crc32c_pmull_le(p, n, crc);
-		kernel_neon_end();
+		scoped_ksimd()
+			crc = crc32c_pmull_le(p, n, crc);
 		p += n;
 		len -= n;
 	}
diff --git a/lib/crc/arm64/crc-t10dif.h b/lib/crc/arm64/crc-t10dif.h
index f88db2971805..b8338139ed77 100644
--- a/lib/crc/arm64/crc-t10dif.h
+++ b/lib/crc/arm64/crc-t10dif.h
@@ -7,7 +7,6 @@
 
 #include <linux/cpufeature.h>
 
-#include <asm/neon.h>
 #include <asm/simd.h>
 
 static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_asimd);
@@ -21,22 +20,16 @@ asmlinkage u16 crc_t10dif_pmull_p64(u16 init_crc, const u8 *buf, size_t len);
 
 static inline u16 crc_t10dif_arch(u16 crc, const u8 *data, size_t length)
 {
-	if (length >= CRC_T10DIF_PMULL_CHUNK_SIZE) {
+	if (length >= CRC_T10DIF_PMULL_CHUNK_SIZE && likely(may_use_simd())) {
 		if (static_branch_likely(&have_pmull)) {
-			if (likely(may_use_simd())) {
-				kernel_neon_begin();
-				crc = crc_t10dif_pmull_p64(crc, data, length);
-				kernel_neon_end();
-				return crc;
-			}
+			scoped_ksimd()
+				return crc_t10dif_pmull_p64(crc, data, length);
 		} else if (length > CRC_T10DIF_PMULL_CHUNK_SIZE &&
-			   static_branch_likely(&have_asimd) &&
-			   likely(may_use_simd())) {
+			   static_branch_likely(&have_asimd)) {
 			u8 buf[16];
 
-			kernel_neon_begin();
-			crc_t10dif_pmull_p8(crc, data, length, buf);
-			kernel_neon_end();
+			scoped_ksimd()
+				crc_t10dif_pmull_p8(crc, data, length, buf);
 
 			return crc_t10dif_generic(0, buf, sizeof(buf));
 		}
diff --git a/lib/crc/arm64/crc32.h b/lib/crc/arm64/crc32.h
index 31e649cd40a2..1939a5dee477 100644
--- a/lib/crc/arm64/crc32.h
+++ b/lib/crc/arm64/crc32.h
@@ -2,7 +2,6 @@
 
 #include <asm/alternative.h>
 #include <asm/cpufeature.h>
-#include <asm/neon.h>
 #include <asm/simd.h>
 
 // The minimum input length to consider the 4-way interleaved code path
@@ -23,9 +22,8 @@ static inline u32 crc32_le_arch(u32 crc, const u8 *p, size_t len)
 
 	if (len >= min_len && cpu_have_named_feature(PMULL) &&
 	    likely(may_use_simd())) {
-		kernel_neon_begin();
-		crc = crc32_le_arm64_4way(crc, p, len);
-		kernel_neon_end();
+		scoped_ksimd()
+			crc = crc32_le_arm64_4way(crc, p, len);
 
 		p += round_down(len, 64);
 		len %= 64;
@@ -44,9 +42,8 @@ static inline u32 crc32c_arch(u32 crc, const u8 *p, size_t len)
 
 	if (len >= min_len && cpu_have_named_feature(PMULL) &&
 	    likely(may_use_simd())) {
-		kernel_neon_begin();
-		crc = crc32c_le_arm64_4way(crc, p, len);
-		kernel_neon_end();
+		scoped_ksimd()
+			crc = crc32c_le_arm64_4way(crc, p, len);
 
 		p += round_down(len, 64);
 		len %= 64;
@@ -65,9 +62,8 @@ static inline u32 crc32_be_arch(u32 crc, const u8 *p, size_t len)
 
 	if (len >= min_len && cpu_have_named_feature(PMULL) &&
 	    likely(may_use_simd())) {
-		kernel_neon_begin();
-		crc = crc32_be_arm64_4way(crc, p, len);
-		kernel_neon_end();
+		scoped_ksimd()
+			crc = crc32_be_arm64_4way(crc, p, len);
 
 		p += round_down(len, 64);
 		len %= 64;
diff --git a/lib/raid6/neon.c b/lib/raid6/neon.c
index 0a2e76035ea9..6d9474ce6da9 100644
--- a/lib/raid6/neon.c
+++ b/lib/raid6/neon.c
@@ -8,10 +8,9 @@
 #include <linux/raid/pq.h>
 
 #ifdef __KERNEL__
-#include <asm/neon.h>
+#include <asm/simd.h>
 #else
-#define kernel_neon_begin()
-#define kernel_neon_end()
+#define scoped_ksimd()
 #define cpu_has_neon()		(1)
 #endif
 
@@ -32,10 +31,9 @@
 	{								\
 		void raid6_neon ## _n  ## _gen_syndrome_real(int,	\
 						unsigned long, void**);	\
-		kernel_neon_begin();					\
-		raid6_neon ## _n ## _gen_syndrome_real(disks,		\
+		scoped_ksimd()						\
+			raid6_neon ## _n ## _gen_syndrome_real(disks,	\
 					(unsigned long)bytes, ptrs);	\
-		kernel_neon_end();					\
 	}								\
 	static void raid6_neon ## _n ## _xor_syndrome(int disks,	\
 					int start, int stop, 		\
@@ -43,10 +41,9 @@
 	{								\
 		void raid6_neon ## _n  ## _xor_syndrome_real(int,	\
 				int, int, unsigned long, void**);	\
-		kernel_neon_begin();					\
-		raid6_neon ## _n ## _xor_syndrome_real(disks,		\
-			start, stop, (unsigned long)bytes, ptrs);	\
-		kernel_neon_end();					\
+		scoped_ksimd()						\
+			raid6_neon ## _n ## _xor_syndrome_real(disks,	\
+				start, stop, (unsigned long)bytes, ptrs);\
 	}								\
 	struct raid6_calls const raid6_neonx ## _n = {			\
 		raid6_neon ## _n ## _gen_syndrome,			\
diff --git a/lib/raid6/recov_neon.c b/lib/raid6/recov_neon.c
index 70e1404c1512..9d99aeabd31a 100644
--- a/lib/raid6/recov_neon.c
+++ b/lib/raid6/recov_neon.c
@@ -7,11 +7,10 @@
 #include <linux/raid/pq.h>
 
 #ifdef __KERNEL__
-#include <asm/neon.h>
+#include <asm/simd.h>
 #include "neon.h"
 #else
-#define kernel_neon_begin()
-#define kernel_neon_end()
+#define scoped_ksimd()
 #define cpu_has_neon()		(1)
 #endif
 
@@ -55,9 +54,8 @@ static void raid6_2data_recov_neon(int disks, size_t bytes, int faila,
 	qmul  = raid6_vgfmul[raid6_gfinv[raid6_gfexp[faila] ^
 					 raid6_gfexp[failb]]];
 
-	kernel_neon_begin();
-	__raid6_2data_recov_neon(bytes, p, q, dp, dq, pbmul, qmul);
-	kernel_neon_end();
+	scoped_ksimd()
+		__raid6_2data_recov_neon(bytes, p, q, dp, dq, pbmul, qmul);
 }
 
 static void raid6_datap_recov_neon(int disks, size_t bytes, int faila,
@@ -86,9 +84,8 @@ static void raid6_datap_recov_neon(int disks, size_t bytes, int faila,
 	/* Now, pick the proper data tables */
 	qmul = raid6_vgfmul[raid6_gfinv[raid6_gfexp[faila]]];
 
-	kernel_neon_begin();
-	__raid6_datap_recov_neon(bytes, p, q, dq, qmul);
-	kernel_neon_end();
+	scoped_ksimd()
+		__raid6_datap_recov_neon(bytes, p, q, dq, qmul);
 }
 
 const struct raid6_recov_calls raid6_recov_neon = {