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 |
---|---|---|
ChangeLog | -rw-r--r-- | 14.0 KB |
Kconfig | -rw-r--r-- | 948 bytes |
Makefile | -rw-r--r-- | 164 bytes |
TODO | -rw-r--r-- | 385 bytes |
befs.h | -rw-r--r-- | 3.2 KB |
befs_fs_types.h | -rw-r--r-- | 4.9 KB |
btree.c | -rw-r--r-- | 21.9 KB |
btree.h | -rw-r--r-- | 300 bytes |
datastream.c | -rw-r--r-- | 15.5 KB |
datastream.h | -rw-r--r-- | 514 bytes |
debug.c | -rw-r--r-- | 7.6 KB |
endian.h | -rw-r--r-- | 3.1 KB |
inode.c | -rw-r--r-- | 1.1 KB |
inode.h | -rw-r--r-- | 123 bytes |
io.c | -rw-r--r-- | 1.8 KB |
io.h | -rw-r--r-- | 190 bytes |
linuxvfs.c | -rw-r--r-- | 24.0 KB |
super.c | -rw-r--r-- | 3.0 KB |
super.h | -rw-r--r-- | 134 bytes |
Computing file changes ...