dcache questions, bug in alt_dcache_flush

This does look like a bug in alt_dcache_flush(). I'll get it fixed. The fix should be to# ifdef out the code that limits len when flushda exists. Here's what what a fixed version looks like:

void alt_dcache_flush (void* start, alt_u32 len)

{# if NIOS2_DCACHE_SIZE > 0

char* i;

char* end;

# ifndef NIOS2_FLUSHDA_SUPPORTED

/*

* This is the most we would ever need to flush.

*/

if (len > NIOS2_DCACHE_SIZE)

{

len = NIOS2_DCACHE_SIZE;

}# endif /* NIOS2_FLUSHDA_SUPPORTED */

end = ((char*) start) + len;

for (i = start; i < end; i+= NIOS2_DCACHE_LINE_SIZE)

{

ALT_FLUSH_DATA(i);

}

/*

* For an unaligned flush request, we&#39;ve got one more line left.

* Note that this is dependent on NIOS2_DCACHE_LINE_SIZE to be a

* multiple of 2 (which it always is).

*/

if (((alt_u32) start) & (NIOS2_DCACHE_LINE_SIZE - 1))

{

ALT_FLUSH_DATA(i);

}

# endif /* NIOS2_DCACHE_SIZE > 0 */

}

As for the behavior of the flushd instruction when the line is not dirty, it is invalidated.