Re: [patch v2 for-3.2] block: initialize request_queue's numa nodeduring allocation

[Dave Young]

On 11/23/2011 09:14 AM, David Rientjes wrote:

> From: Mike Snitzer <snitzer@xxxxxxxxxx>
> 
> struct request_queue is allocated with __GFP_ZERO so its "node" field is 
> zero before initialization.  This causes an oops if node 0 is offline in 
> the page allocator because its zonelists are not initialized.  From Dave 
> Young's dmesg:
> 
> 	SRAT: Node 1 PXM 2 0-d0000000
> 	SRAT: Node 1 PXM 2 100000000-330000000
> 	SRAT: Node 0 PXM 1 330000000-630000000
> 	Initmem setup node 1 0000000000000000-000000000affb000
> 	...
> 	Built 1 zonelists in Node order, mobility grouping on.
> 	...
> 	BUG: unable to handle kernel paging request at 0000000000001c08
> 	IP: [<ffffffff8111c355>] __alloc_pages_nodemask+0xb5/0x870
> 
> and __alloc_pages_nodemask+0xb5 translates to a NULL pointer on 
> zonelist->_zonerefs.
> 
> The fix is to initialize q->node at the time of allocation so the correct 
> node is passed to the slab allocator later.
> 
> Since blk_init_allocated_queue_node() is no longer needed, merge it with 
> blk_init_allocated_queue().
> 
> [rientjes@xxxxxxxxxx: changelog, initializing q->node]
> Cc: stable@xxxxxxxxxxxxxxx [2.6.37+]
> Reported-by: Dave Young <dyoung@xxxxxxxxxx>
> Signed-off-by: Mike Snitzer <snitzer@xxxxxxxxxx>
> Signed-off-by: David Rientjes <rientjes@xxxxxxxxxx>


Tested-by: Dave Young <dyoung@xxxxxxxxxx>

> ---
>  block/blk-core.c       |   14 +++-----------
>  include/linux/blkdev.h |    3 ---
>  2 files changed, 3 insertions(+), 14 deletions(-)
> 
> diff --git a/block/blk-core.c b/block/blk-core.c
> --- a/block/blk-core.c
> +++ b/block/blk-core.c
> @@ -467,6 +467,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
>  	q->backing_dev_info.state = 0;
>  	q->backing_dev_info.capabilities = BDI_CAP_MAP_COPY;
>  	q->backing_dev_info.name = "block";
> +	q->node = node_id;
>  
>  	err = bdi_init(&q->backing_dev_info);
>  	if (err) {
> @@ -551,7 +552,7 @@ blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id)
>  	if (!uninit_q)
>  		return NULL;
>  
> -	q = blk_init_allocated_queue_node(uninit_q, rfn, lock, node_id);
> +	q = blk_init_allocated_queue(uninit_q, rfn, lock);
>  	if (!q)
>  		blk_cleanup_queue(uninit_q);
>  
> @@ -563,18 +564,9 @@ struct request_queue *
>  blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn,
>  			 spinlock_t *lock)
>  {
> -	return blk_init_allocated_queue_node(q, rfn, lock, -1);
> -}
> -EXPORT_SYMBOL(blk_init_allocated_queue);
> -
> -struct request_queue *
> -blk_init_allocated_queue_node(struct request_queue *q, request_fn_proc *rfn,
> -			      spinlock_t *lock, int node_id)
> -{
>  	if (!q)
>  		return NULL;
>  
> -	q->node = node_id;
>  	if (blk_init_free_list(q))
>  		return NULL;
>  
> @@ -604,7 +596,7 @@ blk_init_allocated_queue_node(struct request_queue *q, request_fn_proc *rfn,
>  
>  	return NULL;
>  }
> -EXPORT_SYMBOL(blk_init_allocated_queue_node);
> +EXPORT_SYMBOL(blk_init_allocated_queue);
>  
>  int blk_get_queue(struct request_queue *q)
>  {
> diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
> --- a/include/linux/blkdev.h
> +++ b/include/linux/blkdev.h
> @@ -805,9 +805,6 @@ extern void blk_unprep_request(struct request *);
>   */
>  extern struct request_queue *blk_init_queue_node(request_fn_proc *rfn,
>  					spinlock_t *lock, int node_id);
> -extern struct request_queue *blk_init_allocated_queue_node(struct request_queue *,
> -							   request_fn_proc *,
> -							   spinlock_t *, int node_id);
>  extern struct request_queue *blk_init_queue(request_fn_proc *, spinlock_t *);
>  extern struct request_queue *blk_init_allocated_queue(struct request_queue *,
>  						      request_fn_proc *, spinlock_t *);
> 
> _______________________________________________
> kexec mailing list
> kexec@xxxxxxxxxxxxxxxxxxx
> http://lists.infradead.org/mailman/listinfo/kexec



-- 
Thanks
Dave
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/