block: Range check cpu in blk_cpu_to_group

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 files changed, 6 insertions, 2 deletions

diff --git a/block/blk.h b/block/blk.h
index 6e7dc87141e4..d6b911ac002c 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -142,14 +142,18 @@ static inline int queue_congestion_off_threshold(struct request_queue *q)
 
 static inline int blk_cpu_to_group(int cpu)
 {
+        int group = NR_CPUS;
 #ifdef CONFIG_SCHED_MC
         const struct cpumask *mask = cpu_coregroup_mask(cpu);
-        return cpumask_first(mask);
+        group = cpumask_first(mask);
 #elif defined(CONFIG_SCHED_SMT)
-        return cpumask_first(topology_thread_cpumask(cpu));
+        group = cpumask_first(topology_thread_cpumask(cpu));
 #else
         return cpu;
 #endif
+        if (likely(group < NR_CPUS))
+                return group;
+        return cpu;
 }
 
 /*