1ef2a611de
My change had good intentions, but the implementation was incorrect: - printf was returning the number of characters in the format string plus the NUL, but failed in two regards implementation wise: -- the pathological case, printf(""), wasn't being handled properly since the pointer is always incremented, so the value returned would be off-by-one. -- printf(3) reports the number of characters printed post-conversion via vfprintf, etc. - putchar(3) should return the character printed or EOF, not the number of characters output to the screen. My goal in making the change (again) was to increase parity, but as bde pointed out these are freestanding functions, so they don't have to conform to libc/POSIX. I argued that the functions should be named differently since the implementation is different enough to warrant it and to allow boot2 code to be usable when linked against sys/boot and libstand and other libraries in base. I have no interest in pushing this change forward more though, as the original concern I had behind the change with zfsboottest was resolved in r321849 and r321852. The next person that updates the toolchain gets to deal with the inconsistency if it's flagged by a newer compiler. MFC after: 1 month Reported by: ed, markj |
||
---|---|---|
.. | ||
boot0 | ||
boot0iic | ||
boot0spi | ||
boot2 | ||
bootiic | ||
bootspi | ||
libat91 | ||
linker.cfg | ||
Makefile | ||
Makefile.inc |