Revision be14eb619108fa8b7120eb2c42d66d5f623ae10e authored by Brian King on 10 September 2010, 07:03:21 UTC, committed by Jens Axboe on 10 September 2010, 07:03:21 UTC
While testing CPU DLPAR, the following problem was discovered. We were DLPAR removing the first CPU, which in this case was logical CPUs 0-3. CPUs 0-2 were already marked offline and we were in the process of offlining CPU 3. After marking the CPU inactive and offline in cpu_disable, but before the cpu was completely idle (cpu_die), we ended up in __make_request on CPU 3. There we looked at the topology map to see which CPU to complete the I/O on and found no CPUs in the cpu_sibling_map. This resulted in the block layer setting the completion cpu to be NR_CPUS, which then caused an oops when we tried to complete the I/O. Fix this by sanity checking the value we return from blk_cpu_to_group to be a valid cpu value. Signed-off-by: Brian King <brking@linux.vnet.ibm.com> Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
1 parent edce682
File | Mode | Size |
---|---|---|
Makefile | -rw-r--r-- | 292 bytes |
clntlock.c | -rw-r--r-- | 6.7 KB |
clntproc.c | -rw-r--r-- | 20.8 KB |
grace.c | -rw-r--r-- | 1.6 KB |
host.c | -rw-r--r-- | 14.9 KB |
mon.c | -rw-r--r-- | 14.0 KB |
svc.c | -rw-r--r-- | 13.4 KB |
svc4proc.c | -rw-r--r-- | 13.9 KB |
svclock.c | -rw-r--r-- | 24.5 KB |
svcproc.c | -rw-r--r-- | 14.5 KB |
svcshare.c | -rw-r--r-- | 2.4 KB |
svcsubs.c | -rw-r--r-- | 9.8 KB |
xdr.c | -rw-r--r-- | 14.0 KB |
xdr4.c | -rw-r--r-- | 13.7 KB |
Computing file changes ...