From f8f022e5bc574088ae80327ea5f88a8fe09b48c8 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers3@gmail.com>
Date: Sun, 25 Dec 2022 15:05:52 -0800
Subject: [PATCH] lib/arm/crc32: use crypto target when required due to gcc bug

Fixes https://github.com/ebiggers/libdeflate/issues/280
Fixes: 6db64ab7afd2 ("lib/crc32: CRC-32 optimizations and other improvements")
[Retrieved from:
https://github.com/ebiggers/libdeflate/commit/f8f022e5bc574088ae80327ea5f88a8fe09b48c8]
Signed-off-by: Fabrice Fontaine <fontaine.fabrice@gmail.com>
---
 lib/arm/cpu_features.h | 23 +++++++++++++++++++++++
 lib/arm/crc32_impl.h   |  9 +++++----
 2 files changed, 28 insertions(+), 4 deletions(-)

diff --git a/lib/arm/cpu_features.h b/lib/arm/cpu_features.h
index 204c0cd5..4092eba8 100644
--- a/lib/arm/cpu_features.h
+++ b/lib/arm/cpu_features.h
@@ -116,6 +116,29 @@ static inline u32 get_arm_cpu_features(void) { return 0; }
 #else
 #  define HAVE_PMULL_INTRIN	0
 #endif
+/*
+ * Set USE_PMULL_TARGET_EVEN_IF_NATIVE if a workaround for a gcc bug that was
+ * fixed by commit 11a113d501ff ("aarch64: Simplify feature definitions") in gcc
+ * 13 is needed.  A minimal program that fails to build due to this bug when
+ * compiled with -mcpu=emag, at least with gcc 10 through 12, is:
+ *
+ *    static inline __attribute__((always_inline,target("+crypto"))) void f() {}
+ *    void g() { f(); }
+ *
+ * The error is:
+ *
+ *    error: inlining failed in call to ‘always_inline’ ‘f’: target specific option mismatch
+ *
+ * The workaround is to explicitly add the crypto target to the non-inline
+ * function g(), even though this should not be required due to -mcpu=emag
+ * enabling 'crypto' natively and causing __ARM_FEATURE_CRYPTO to be defined.
+ */
+#if HAVE_PMULL_NATIVE && defined(ARCH_ARM64) && \
+		GCC_PREREQ(6, 1) && !GCC_PREREQ(13, 1)
+#  define USE_PMULL_TARGET_EVEN_IF_NATIVE	1
+#else
+#  define USE_PMULL_TARGET_EVEN_IF_NATIVE	0
+#endif
 
 /* CRC32 */
 #ifdef __ARM_FEATURE_CRC32
diff --git a/lib/arm/crc32_impl.h b/lib/arm/crc32_impl.h
index e426a63d..b9300e4b 100644
--- a/lib/arm/crc32_impl.h
+++ b/lib/arm/crc32_impl.h
@@ -236,7 +236,7 @@ crc32_arm_crc(u32 crc, const u8 *p, size_t len)
  * for implementations that use pmull for folding the data itself.
  */
 #if HAVE_CRC32_INTRIN && HAVE_PMULL_INTRIN
-#  if HAVE_CRC32_NATIVE && HAVE_PMULL_NATIVE
+#  if HAVE_CRC32_NATIVE && HAVE_PMULL_NATIVE && !USE_PMULL_TARGET_EVEN_IF_NATIVE
 #    define ATTRIBUTES
 #  else
 #    ifdef ARCH_ARM32
@@ -438,7 +438,7 @@ crc32_arm_crc_pmullcombine(u32 crc, const u8 *p, size_t len)
 #if HAVE_PMULL_INTRIN
 #  define crc32_arm_pmullx4	crc32_arm_pmullx4
 #  define SUFFIX			 _pmullx4
-#  if HAVE_PMULL_NATIVE
+#  if HAVE_PMULL_NATIVE && !USE_PMULL_TARGET_EVEN_IF_NATIVE
 #    define ATTRIBUTES
 #  else
 #    ifdef ARCH_ARM32
@@ -558,7 +558,7 @@ crc32_arm_pmullx4(u32 crc, const u8 *p, size_t len)
 #if defined(ARCH_ARM64) && HAVE_PMULL_INTRIN && HAVE_CRC32_INTRIN
 #  define crc32_arm_pmullx12_crc	crc32_arm_pmullx12_crc
 #  define SUFFIX				 _pmullx12_crc
-#  if HAVE_PMULL_NATIVE && HAVE_CRC32_NATIVE
+#  if HAVE_PMULL_NATIVE && HAVE_CRC32_NATIVE && !USE_PMULL_TARGET_EVEN_IF_NATIVE
 #    define ATTRIBUTES
 #  else
 #    ifdef __clang__
@@ -584,7 +584,8 @@ crc32_arm_pmullx4(u32 crc, const u8 *p, size_t len)
 	(HAVE_SHA3_TARGET || HAVE_SHA3_NATIVE)
 #  define crc32_arm_pmullx12_crc_eor3	crc32_arm_pmullx12_crc_eor3
 #  define SUFFIX				 _pmullx12_crc_eor3
-#  if HAVE_PMULL_NATIVE && HAVE_CRC32_NATIVE && HAVE_SHA3_NATIVE
+#  if HAVE_PMULL_NATIVE && HAVE_CRC32_NATIVE && HAVE_SHA3_NATIVE && \
+	!USE_PMULL_TARGET_EVEN_IF_NATIVE
 #    define ATTRIBUTES
 #  else
 #    ifdef __clang__