On 01/23/2014 01:38 PM, Guillaume Morin wrote:
Khalid,
On 23 Jan 12:58, Khalid Aziz wrote:
This does look like the same issue that is fixed with commit
27c73ae759774e63313c1fbfeb17ba076cea64c5. I will build a 3.4.69
kernel and try to reproduce this problem.
Thanks. You should be able to reproduce the issue with any stable 3.4
kernels that is >= 3.4.69. I've personally tried to reproduce it only
with 3.4.7[67] and 3.12.8
Let me know if you need any help. I might give it a shot and backport
27c73ae759774e63313c1fbfeb17ba076cea64c5 to 3.4 but I am pretty busy
with other things atm.
So far I am not having any luck reproducing this. I have built a 3.4.69
kernel with:
# CONFIG_TRANSPARENT_HUGEPAGE is not set
CONFIG_HUGETLBFS=y
CONFIG_HUGETLB_PAGE=y
I boot this kernel up with "hugepages=512" and run the test program
included in the bug report. It completes with no error whether I run it
with "LD_PRELOAD=libhugetlbfs.so" or not and dmesg is clean.
I built a 3.4.77 kernel and that one works as well. If you can mail me
your kernel config, I can try with that. Maybe you have something
configured that I don't.
--
Khalid
--
To unsubscribe from this list: send the line "unsubscribe stable" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html