perf tools: Add get_unaligned_leNN()

Add get_unaligned_le16(), get_unaligned_le32 and get_unaligned_le64, same
as include/asm-generic/unaligned.h. And add include/asm-generic/unaligned.h
to check-headers.sh bringing tools/include/asm-generic/unaligned.h up to
date so that the kernel and tools versions match.

Use diagnostic pragmas to ignore -Wpacked used by perf build.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Reviewed-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20231005190451.175568-2-adrian.hunter@intel.com
Link: https://lore.kernel.org/r/20231010142234.20061-1-adrian.hunter@intel.com
[ squashed check-header.sh addition ]
Signed-off-by: Namhyung Kim <namhyung@kernel.org>

2 files changed, 140 insertions, 6 deletions

diff --git a/tools/include/asm-generic/unaligned.h b/tools/include/asm-generic/unaligned.h
index 47387c607035..156743d399ae 100644
--- a/tools/include/asm-generic/unaligned.h
+++ b/tools/include/asm-generic/unaligned.h
@@ -1,10 +1,13 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_GENERIC_UNALIGNED_H
+#define __ASM_GENERIC_UNALIGNED_H
+
 /*
- * Copied from the kernel sources to tools/perf/:
+ * This is the most generic implementation of unaligned accesses
+ * and should work almost anywhere.
  */
-
-#ifndef __TOOLS_LINUX_ASM_GENERIC_UNALIGNED_H
-#define __TOOLS_LINUX_ASM_GENERIC_UNALIGNED_H
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wpacked"
 
 #define __get_unaligned_t(type, ptr) ({						\
 	const struct { type x; } __packed *__pptr = (typeof(__pptr))(ptr);	\
@@ -19,5 +22,135 @@
 #define get_unaligned(ptr)	__get_unaligned_t(typeof(*(ptr)), (ptr))
 #define put_unaligned(val, ptr) __put_unaligned_t(typeof(*(ptr)), (val), (ptr))
 
-#endif /* __TOOLS_LINUX_ASM_GENERIC_UNALIGNED_H */
+static inline u16 get_unaligned_le16(const void *p)
+{
+	return le16_to_cpu(__get_unaligned_t(__le16, p));
+}
+
+static inline u32 get_unaligned_le32(const void *p)
+{
+	return le32_to_cpu(__get_unaligned_t(__le32, p));
+}
+
+static inline u64 get_unaligned_le64(const void *p)
+{
+	return le64_to_cpu(__get_unaligned_t(__le64, p));
+}
+
+static inline void put_unaligned_le16(u16 val, void *p)
+{
+	__put_unaligned_t(__le16, cpu_to_le16(val), p);
+}
+
+static inline void put_unaligned_le32(u32 val, void *p)
+{
+	__put_unaligned_t(__le32, cpu_to_le32(val), p);
+}
+
+static inline void put_unaligned_le64(u64 val, void *p)
+{
+	__put_unaligned_t(__le64, cpu_to_le64(val), p);
+}
+
+static inline u16 get_unaligned_be16(const void *p)
+{
+	return be16_to_cpu(__get_unaligned_t(__be16, p));
+}
+
+static inline u32 get_unaligned_be32(const void *p)
+{
+	return be32_to_cpu(__get_unaligned_t(__be32, p));
+}
+
+static inline u64 get_unaligned_be64(const void *p)
+{
+	return be64_to_cpu(__get_unaligned_t(__be64, p));
+}
+
+static inline void put_unaligned_be16(u16 val, void *p)
+{
+	__put_unaligned_t(__be16, cpu_to_be16(val), p);
+}
+
+static inline void put_unaligned_be32(u32 val, void *p)
+{
+	__put_unaligned_t(__be32, cpu_to_be32(val), p);
+}
+
+static inline void put_unaligned_be64(u64 val, void *p)
+{
+	__put_unaligned_t(__be64, cpu_to_be64(val), p);
+}
+
+static inline u32 __get_unaligned_be24(const u8 *p)
+{
+	return p[0] << 16 | p[1] << 8 | p[2];
+}
+
+static inline u32 get_unaligned_be24(const void *p)
+{
+	return __get_unaligned_be24(p);
+}
+
+static inline u32 __get_unaligned_le24(const u8 *p)
+{
+	return p[0] | p[1] << 8 | p[2] << 16;
+}
+
+static inline u32 get_unaligned_le24(const void *p)
+{
+	return __get_unaligned_le24(p);
+}
+
+static inline void __put_unaligned_be24(const u32 val, u8 *p)
+{
+	*p++ = val >> 16;
+	*p++ = val >> 8;
+	*p++ = val;
+}
+
+static inline void put_unaligned_be24(const u32 val, void *p)
+{
+	__put_unaligned_be24(val, p);
+}
+
+static inline void __put_unaligned_le24(const u32 val, u8 *p)
+{
+	*p++ = val;
+	*p++ = val >> 8;
+	*p++ = val >> 16;
+}
+
+static inline void put_unaligned_le24(const u32 val, void *p)
+{
+	__put_unaligned_le24(val, p);
+}
+
+static inline void __put_unaligned_be48(const u64 val, u8 *p)
+{
+	*p++ = val >> 40;
+	*p++ = val >> 32;
+	*p++ = val >> 24;
+	*p++ = val >> 16;
+	*p++ = val >> 8;
+	*p++ = val;
+}
+
+static inline void put_unaligned_be48(const u64 val, void *p)
+{
+	__put_unaligned_be48(val, p);
+}
+
+static inline u64 __get_unaligned_be48(const u8 *p)
+{
+	return (u64)p[0] << 40 | (u64)p[1] << 32 | (u64)p[2] << 24 |
+		p[3] << 16 | p[4] << 8 | p[5];
+}
+
+static inline u64 get_unaligned_be48(const void *p)
+{
+	return __get_unaligned_be48(p);
+}
+#pragma GCC diagnostic pop
 
+#endif /* __ASM_GENERIC_UNALIGNED_H */
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index e21caadda7c1..66ba33dbcef2 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -162,6 +162,7 @@ check arch/x86/lib/memcpy_64.S        '-I "^EXPORT_SYMBOL" -I "^#include <asm/ex
 check arch/x86/lib/memset_64.S        '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" -I"^SYM_FUNC_START\(_LOCAL\)*(memset_\(erms\|orig\))"'
 check arch/x86/include/asm/amd-ibs.h  '-I "^#include [<\"]\(asm/\)*msr-index.h"'
 check arch/arm64/include/asm/cputype.h '-I "^#include [<\"]\(asm/\)*sysreg.h"'
+check include/asm-generic/unaligned.h '-I "^#include <linux/unaligned/packed_struct.h>" -I "^#include <asm/byteorder.h>" -I "^#pragma GCC diagnostic"'
 check include/uapi/asm-generic/mman.h '-I "^#include <\(uapi/\)*asm-generic/mman-common\(-tools\)*.h>"'
 check include/uapi/linux/mman.h       '-I "^#include <\(uapi/\)*asm/mman.h>"'
 check include/linux/build_bug.h       '-I "^#\(ifndef\|endif\)\( \/\/\)* static_assert$"'