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 |
---|---|---|
Kconfig | -rw-r--r-- | 2.2 KB |
Makefile | -rw-r--r-- | 486 bytes |
cache.c | -rw-r--r-- | 4.6 KB |
dir.c | -rw-r--r-- | 15.8 KB |
file.c | -rw-r--r-- | 10.9 KB |
getopt.c | -rw-r--r-- | 1.6 KB |
getopt.h | -rw-r--r-- | 312 bytes |
inode.c | -rw-r--r-- | 19.9 KB |
ioctl.c | -rw-r--r-- | 1.5 KB |
proc.c | -rw-r--r-- | 83.8 KB |
proto.h | -rw-r--r-- | 4.8 KB |
request.c | -rw-r--r-- | 20.1 KB |
request.h | -rw-r--r-- | 1.6 KB |
smb_debug.h | -rw-r--r-- | 878 bytes |
smbiod.c | -rw-r--r-- | 7.5 KB |
sock.c | -rw-r--r-- | 7.8 KB |
symlink.c | -rw-r--r-- | 1.4 KB |
Computing file changes ...