[PATCH][SRU Xenial] UBUNTU: SAUCE: Revert "crypto: arm64/sha - avoid non-standard inline asm tricks"

[dann frazier]

BugLink: https://bugs.launchpad.net/bugs/1905336

This commit from stable-4.4.y appears to be an upstream regression. It
caused the build to emit ADR_PREL_PG_HI21 relocations in the sha{1,2}_ce
modules. This relocation type is not supported by the stable-4.4.y kernel
module loader when CONFIG_ARM64_ERRATUM_843419=y, which we have enabled, so
these modules now fail to load:

[   37.866250] module sha1_ce: unsupported RELA relocation: 275

Support for these relocations was later introduced upstream in
v4.17 (and backported to bionic) but that's too large of a change to
consider backporting to xenial to address this issue.

Since the purpose of this commit was to better support Clang, and we don't
build Ubuntu kernels with Clang, it should be safe for us to revert - at
least until there's a proper stable-4.4.y fix.

This reverts commit 2675530a1d1671ca0d05c2375e4227eccad3f3c0.

Signed-off-by: dann frazier <dann.frazier at canonical.com>
---
 arch/arm64/crypto/sha1-ce-core.S |  6 ++----
 arch/arm64/crypto/sha1-ce-glue.c | 11 ++++++++---
 arch/arm64/crypto/sha2-ce-core.S |  6 ++----
 arch/arm64/crypto/sha2-ce-glue.c | 13 ++++++++-----
 4 files changed, 20 insertions(+), 16 deletions(-)

diff --git a/arch/arm64/crypto/sha1-ce-core.S b/arch/arm64/crypto/sha1-ce-core.S
index 8550408..c98e7e8 100644
--- a/arch/arm64/crypto/sha1-ce-core.S
+++ b/arch/arm64/crypto/sha1-ce-core.S
@@ -82,8 +82,7 @@ ENTRY(sha1_ce_transform)
 	ldr		dgb, [x0, #16]
 
 	/* load sha1_ce_state::finalize */
-	ldr_l		w4, sha1_ce_offsetof_finalize, x4
-	ldr		w4, [x0, x4]
+	ldr		w4, [x0, #:lo12:sha1_ce_offsetof_finalize]
 
 	/* load input */
 0:	ld1		{v8.4s-v11.4s}, [x1], #64
@@ -133,8 +132,7 @@ CPU_LE(	rev32		v11.16b, v11.16b	)
 	 * the padding is handled by the C code in that case.
 	 */
 	cbz		x4, 3f
-	ldr_l		w4, sha1_ce_offsetof_count, x4
-	ldr		x4, [x0, x4]
+	ldr		x4, [x0, #:lo12:sha1_ce_offsetof_count]
 	movi		v9.2d, #0
 	mov		x8, #0x80000000
 	movi		v10.2d, #0
diff --git a/arch/arm64/crypto/sha1-ce-glue.c b/arch/arm64/crypto/sha1-ce-glue.c
index 1b7b468..01e48b8 100644
--- a/arch/arm64/crypto/sha1-ce-glue.c
+++ b/arch/arm64/crypto/sha1-ce-glue.c
@@ -17,6 +17,9 @@
 #include <linux/crypto.h>
 #include <linux/module.h>
 
+#define ASM_EXPORT(sym, val) \
+	asm(".globl " #sym "; .set " #sym ", %0" :: "I"(val));
+
 MODULE_DESCRIPTION("SHA1 secure hash using ARMv8 Crypto Extensions");
 MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel at linaro.org>");
 MODULE_LICENSE("GPL v2");
@@ -29,9 +32,6 @@ struct sha1_ce_state {
 asmlinkage void sha1_ce_transform(struct sha1_ce_state *sst, u8 const *src,
 				  int blocks);
 
-const u32 sha1_ce_offsetof_count = offsetof(struct sha1_ce_state, sst.count);
-const u32 sha1_ce_offsetof_finalize = offsetof(struct sha1_ce_state, finalize);
-
 static int sha1_ce_update(struct shash_desc *desc, const u8 *data,
 			  unsigned int len)
 {
@@ -52,6 +52,11 @@ static int sha1_ce_finup(struct shash_desc *desc, const u8 *data,
 	struct sha1_ce_state *sctx = shash_desc_ctx(desc);
 	bool finalize = !sctx->sst.count && !(len % SHA1_BLOCK_SIZE) && len;
 
+	ASM_EXPORT(sha1_ce_offsetof_count,
+		   offsetof(struct sha1_ce_state, sst.count));
+	ASM_EXPORT(sha1_ce_offsetof_finalize,
+		   offsetof(struct sha1_ce_state, finalize));
+
 	/*
 	 * Allow the asm code to perform the finalization if there is no
 	 * partial data and the input is a round multiple of the block size.
diff --git a/arch/arm64/crypto/sha2-ce-core.S b/arch/arm64/crypto/sha2-ce-core.S
index 679c6c0..01cfee0 100644
--- a/arch/arm64/crypto/sha2-ce-core.S
+++ b/arch/arm64/crypto/sha2-ce-core.S
@@ -88,8 +88,7 @@ ENTRY(sha2_ce_transform)
 	ld1		{dgav.4s, dgbv.4s}, [x0]
 
 	/* load sha256_ce_state::finalize */
-	ldr_l		w4, sha256_ce_offsetof_finalize, x4
-	ldr		w4, [x0, x4]
+	ldr		w4, [x0, #:lo12:sha256_ce_offsetof_finalize]
 
 	/* load input */
 0:	ld1		{v16.4s-v19.4s}, [x1], #64
@@ -137,8 +136,7 @@ CPU_LE(	rev32		v19.16b, v19.16b	)
 	 * the padding is handled by the C code in that case.
 	 */
 	cbz		x4, 3f
-	ldr_l		w4, sha256_ce_offsetof_count, x4
-	ldr		x4, [x0, x4]
+	ldr		x4, [x0, #:lo12:sha256_ce_offsetof_count]
 	movi		v17.2d, #0
 	mov		x8, #0x80000000
 	movi		v18.2d, #0
diff --git a/arch/arm64/crypto/sha2-ce-glue.c b/arch/arm64/crypto/sha2-ce-glue.c
index 356ca93..7a7f95b 100644
--- a/arch/arm64/crypto/sha2-ce-glue.c
+++ b/arch/arm64/crypto/sha2-ce-glue.c
@@ -17,6 +17,9 @@
 #include <linux/crypto.h>
 #include <linux/module.h>
 
+#define ASM_EXPORT(sym, val) \
+	asm(".globl " #sym "; .set " #sym ", %0" :: "I"(val));
+
 MODULE_DESCRIPTION("SHA-224/SHA-256 secure hash using ARMv8 Crypto Extensions");
 MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel at linaro.org>");
 MODULE_LICENSE("GPL v2");
@@ -29,11 +32,6 @@ struct sha256_ce_state {
 asmlinkage void sha2_ce_transform(struct sha256_ce_state *sst, u8 const *src,
 				  int blocks);
 
-const u32 sha256_ce_offsetof_count = offsetof(struct sha256_ce_state,
-					      sst.count);
-const u32 sha256_ce_offsetof_finalize = offsetof(struct sha256_ce_state,
-						 finalize);
-
 static int sha256_ce_update(struct shash_desc *desc, const u8 *data,
 			    unsigned int len)
 {
@@ -54,6 +52,11 @@ static int sha256_ce_finup(struct shash_desc *desc, const u8 *data,
 	struct sha256_ce_state *sctx = shash_desc_ctx(desc);
 	bool finalize = !sctx->sst.count && !(len % SHA256_BLOCK_SIZE) && len;
 
+	ASM_EXPORT(sha256_ce_offsetof_count,
+		   offsetof(struct sha256_ce_state, sst.count));
+	ASM_EXPORT(sha256_ce_offsetof_finalize,
+		   offsetof(struct sha256_ce_state, finalize));
+
 	/*
 	 * Allow the asm code to perform the finalization if there is no
 	 * partial data and the input is a round multiple of the block size.
-- 
2.7.4