On Fri, 2016-09-23 at 09:06 -0700, Dave Hansen wrote:

On 09/23/2016 06:12 AM, Robert Ho wrote:

quoted

+Note: for both /proc/PID/maps and /proc/PID/smaps readings, it's
+possible in race conditions, that the mappings printed may not be that
+up-to-date, because during each read walking, the task's mappings may have
+changed, this typically happens in multithread cases. But anyway in each single
+read these can be guarunteed: 1) the mapped addresses doesn't go backward; 2) no
+overlaps 3) if there is something at a given vaddr during the entirety of the
+life of the smaps/maps walk, there will be some output for it.

Could we spuce this description up a bit?  Perhaps:

Note: reading /proc/PID/maps or /proc/PID/smaps is inherently racy.
This typically manifests when doing partial reads of these files while
the memory map is being modified.  Despite the races, we do provide the
following guarantees:
1) The mapped addresses never go backwards, which implies no two
   regions will ever overlap.
2) If there is something at a given vaddr during the entirety of the
   life of the smaps/maps walk, there will be some output for it.

Sure. Thanks Dave for helping make it more concise and correct.



--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>