[Tarantool-patches] [PATCH v2 04/10] crc32: align memory access

[Timur Safin]

: -----Original Message-----
: From: Vladislav Shpilevoy <v.shpilevoy at tarantool.org>
: Subject: [PATCH v2 04/10] crc32: align memory access
: 
: 
: diff --git a/src/cpu_feature.c b/src/cpu_feature.c
: index 98567ccb3..9bf6223de 100644
: --- a/src/cpu_feature.c
: +++ b/src/cpu_feature.c
: @@ -50,7 +51,7 @@
: 
: 
:  static uint32_t
: -crc32c_hw_byte(uint32_t crc, unsigned char const *data, unsigned int
: length)
: +crc32c_hw_byte(uint32_t crc, char const *data, unsigned int length)
:  {
:  	while (length--) {
:  		__asm__ __volatile__(
: @@ -68,6 +69,26 @@ crc32c_hw_byte(uint32_t crc, unsigned char const *data,
: unsigned int length)
:  uint32_t
:  crc32c_hw(uint32_t crc, const char *buf, unsigned int len)
:  {
: +	const int align = alignof(unsigned long);
: +	unsigned long addr = (unsigned long)buf;
: +	unsigned int not_aligned_prefix =
: +		((addr - 1 + align) & ~(align - 1)) - addr;

Hmm, hmm...

Isn't it simple `addr % align`? Or even `addr & (align - 1)` ?


: +	/*
: +	 * Calculate CRC32 for the prefix byte-by-byte so as to
: +	 * then use aligned words to calculate the rest. This is
: +	 * twice less loads, because every load takes exactly one
: +	 * word from memory. Not 2 words, which would need to be
: +	 * partially merged then.
: +	 * But the main reason is that unaligned loads are just
: +	 * unsafe, because this is an undefined behaviour.
: +	 */
: +	if (not_aligned_prefix < len) {
: +		crc = crc32c_hw_byte(crc, buf, not_aligned_prefix);
: +		buf += not_aligned_prefix;
: +		len -= not_aligned_prefix;
: +	} else {
: +		return crc32c_hw_byte(crc, buf, len);
: +	}
:  	unsigned int iquotient = len / SCALE_F;
:  	unsigned int iremainder = len % SCALE_F;
:  	unsigned long *ptmp = (unsigned long *)buf;