Re: Help with implementing some form of barriers in 3.0 kernels.

[Jan Beulich]

>>> On 14.09.11 at 10:59, Konrad Rzeszutek Wilk <konrad.wilk@xxxxxxxxxx> wrote:
> On Tue, Sep 13, 2011 at 11:44:07AM +0100, Jan Beulich wrote:
>> >>> On 07.09.11 at 19:48, Konrad Rzeszutek Wilk <konrad.wilk@xxxxxxxxxx> wrote:
>> > Hey Christoph,
>> > 
>> > I was wondering what you think is the proper way of implementing a
>> > backend to support the 'barrier' type requests? We have this issue were
>> > there are 2.6.36 type guests that still use barriers and we would like
>> > to support them properly. But in 3.0 there are no barriers - hence
>> > the question whether WRITE_fLUSH_FUA would be equal to WRITE_BARRIER?
>> > 
>> > Or is there some other things that we should take in consideration?
>> > 
>> > Thanks!
>> 
>> Below is what Jan Kara came up with for addressing this - what do
>> you think?
> 
> It looks like it would do it. I modified it a bit, testing it now.
> 
> 
> commit 315c0cf1a5174b9aed494d7903133ce9ac76d6f1
> Author: Jan Kara <jack@xxxxxxx>
> Date:   Tue Sep 13 11:44:07 2011 +0100
> 
>     xen: Add support for old BARRIER requests to xenblk driver
>     
>     Recent kernels do not support BARRIER operation but only FLUSH 
> operation. But
>     older xenblk frontends still use the BARRIER operation to achieve data
>     integrity requirements. So add support for BARRIER operation into xenblk
>     backend so that all guests do not corrupt their filesystem on host 
> crash.
>     
>     Signed-off-by: Jan Kara <jack@xxxxxxx>
>     Signed-off-by: Jan Beulich <JBeulich@xxxxxxxx>
>     [v1: Added some extra functions, and other cases]

Ah, yes, of course - Jan probably didn't pay attention because in our
variant of the driver these functions never got removed.

>     Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@xxxxxxxxxx>
> 
> diff --git a/block/elevator.c b/block/elevator.c
> index a3b64bc..b2143a8 100644
> --- a/block/elevator.c
> +++ b/block/elevator.c
> @@ -616,6 +616,7 @@ void elv_drain_elevator(struct request_queue *q)
>  		       q->elevator->elevator_type->elevator_name, q->nr_sorted);
>  	}
>  }
> +EXPORT_SYMBOL(elv_drain_elevator);

Now, if you modify it anyway, how about making this an
EXPORT_SYMBOL_GPL()?

Jan

>  
>  /*
>   * Call with queue lock held, interrupts disabled
> diff --git a/drivers/block/xen-blkback/blkback.c 
> b/drivers/block/xen-blkback/blkback.c
> index 9713d5a..1df773c 100644
> --- a/drivers/block/xen-blkback/blkback.c
> +++ b/drivers/block/xen-blkback/blkback.c
> @@ -464,6 +464,11 @@ static void __end_block_io_op(struct pending_req 
> *pending_req, int error)
>  		pr_debug(DRV_PFX "flush diskcache op failed, not supported\n");
>  		xen_blkbk_flush_diskcache(XBT_NIL, pending_req->blkif->be, 0);
>  		pending_req->status = BLKIF_RSP_EOPNOTSUPP;
> +	} else if ((pending_req->operation == BLKIF_OP_WRITE_BARRIER) &&
> +		 (error == -EOPNOTSUPP)) {
> +		pr_debug(DRV_PFX "write barrier op failed, not supported\n");
> +		xen_blkbk_barrier(XBT_NIL, pending_req->blkif->be, 0);
> +		pending_req->status = BLKIF_RSP_EOPNOTSUPP;
>  	} else if (error) {
>  		pr_debug(DRV_PFX "Buffer not up-to-date at end of operation,"
>  			 " error=%d\n", error);
> @@ -590,6 +595,7 @@ static int dispatch_rw_block_io(struct xen_blkif *blkif,
>  	struct bio *biolist[BLKIF_MAX_SEGMENTS_PER_REQUEST];
>  	int i, nbio = 0;
>  	int operation;
> +	bool drain = false;
>  	struct blk_plug plug;
>  
>  	switch (req->operation) {
> @@ -601,6 +607,8 @@ static int dispatch_rw_block_io(struct xen_blkif *blkif,
>  		blkif->st_wr_req++;
>  		operation = WRITE_ODIRECT;
>  		break;
> +	case BLKIF_OP_WRITE_BARRIER:
> +		drain = true;
>  	case BLKIF_OP_FLUSH_DISKCACHE:
>  		blkif->st_f_req++;
>  		operation = WRITE_FLUSH;
> @@ -609,7 +617,6 @@ static int dispatch_rw_block_io(struct xen_blkif *blkif,
>  		blkif->st_ds_req++;
>  		operation = REQ_DISCARD;
>  		break;
> -	case BLKIF_OP_WRITE_BARRIER:
>  	default:
>  		operation = 0; /* make gcc happy */
>  		goto fail_response;
> @@ -668,6 +675,17 @@ static int dispatch_rw_block_io(struct xen_blkif *blkif,
>  		}
>  	}
>  
> +	if (drain) {
> +		struct request_queue *q = bdev_get_queue(preq.bdev);
> +		unsigned long flags;
> +
> +		/* Emulate the original behavior of write barriers */
> +		spin_lock_irqsave(q->queue_lock, flags);
> +		elv_drain_elevator(q);
> +		__blk_run_queue(q);
> +		spin_unlock_irqrestore(q->queue_lock, flags);
> +	}
> +
>  	/*
>  	 * If we have failed at this point, we need to undo the M2P override,
>  	 * set gnttab_set_unmap_op on all of the grant references and perform
> diff --git a/drivers/block/xen-blkback/common.h 
> b/drivers/block/xen-blkback/common.h
> index bfb532e..42b0e46 100644
> --- a/drivers/block/xen-blkback/common.h
> +++ b/drivers/block/xen-blkback/common.h
> @@ -228,6 +228,8 @@ int xen_blkif_schedule(void *arg);
>  
>  int xen_blkbk_flush_diskcache(struct xenbus_transaction xbt,
>  			      struct backend_info *be, int state);
> +int xen_blkbk_barrier(struct xenbus_transaction xbt,
> +		      struct backend_info *be, int state);
>  
>  struct xenbus_device *xen_blkbk_xenbus(struct backend_info *be);
>  
> diff --git a/drivers/block/xen-blkback/xenbus.c 
> b/drivers/block/xen-blkback/xenbus.c
> index 2b3aef0..b477aee 100644
> --- a/drivers/block/xen-blkback/xenbus.c
> +++ b/drivers/block/xen-blkback/xenbus.c
> @@ -421,6 +421,20 @@ int xen_blkbk_flush_diskcache(struct xenbus_transaction 
> xbt,
>  	return err;
>  }
>  
> +int xen_blkbk_barrier(struct xenbus_transaction xbt,
> +		      struct backend_info *be, int state)
> +{
> +	struct xenbus_device *dev = be->dev;
> +	int err;
> +
> +	err = xenbus_printf(xbt, dev->nodename, "feature-barrier",
> +			    "%d", state);
> +	if (err)
> +		xenbus_dev_fatal(dev, err, "writing feature-barrier");
> +
> +	return err;
> +}
> +
>  int xen_blkbk_discard(struct xenbus_transaction xbt, struct backend_info 
> *be)
>  {
>  	struct xenbus_device *dev = be->dev;
> @@ -706,6 +720,8 @@ again:
>  	if (err)
>  		goto abort;
>  
> +	err = xen_blkbk_barrier(xbt, be, be->blkif->vbd.flush_support);
> +
>  	err = xen_blkbk_discard(xbt, be);
>  
>  	err = xenbus_printf(xbt, dev->nodename, "sectors", "%llu",


--
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/