While researching the race in rx configuration, I came across the following
code in e1000.h
#define E1000_DESC_UNUSED(R) \
({ \
unsigned int clean = smp_load_acquire(&(R)->next_to_clean); \
unsigned int use = READ_ONCE((R)->next_to_use); \
(clean > use ? 0 : (R)->count) + clean - use - 1; \
})
This looks rather odd in the context of a ring-buffer, in that if
next_to_use has wrapped around, the macro will return zero until
next_to_clean also wraps around. The latter will presumably occur
eventually, so nothing breaks, but it seems to me the macro is
miscalculating the number of unused buffers for part of the time, with
whatever consequence that has.
Sylvia.
------------------------------------------------------------------------------
Check out the vibrant tech community on one of the world's most
engaging tech sites, Slashdot.org! http://sdm.link/slashdot
_______________________________________________
E1000-devel mailing list
E1000-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/e1000-devel
To learn more about Intel® Ethernet, visit
http://communities.intel.com/community/wired
