Commit f3506b75 authored Jul 22, 2010 by FUJITA Tomonori Committed by James Bottomley Aug 06, 2010

[SCSI] 53c700: remove dma_is_consistent usage



This driver is the only user of dma_is_consistent(). We plan to remove
this API.

The driver uses the API in the following way:

BUG_ON(!dma_is_consistent(hostdata->dev, pScript) && L1_CACHE_BYTES < dma_get_cache_alignment());

The above code tries to see if L1_CACHE_BYTES is greater than
dma_get_cache_alignment() on sysmtes that can not allocate coherent
memory (some old systems can't).

James Bottomley exmplained that this is necesary because the driver
packs the set of mailboxes into a single coherent area and separates
the different usages by a L1 cache stride. So it's fatal if the dma
coherence stride is greater than the L1 cache size.

He also pointed out that we can kill this checking because we don't
hit this BUG_ON on all architectures that actually use the driver.

Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Signed-off-by: James Bottomley <James.Bottomley@suse.de>

parent fc1caf6e

drivers/scsi/53c700.c

+0 −3

Original line number	Diff line number	Diff line
		@@ -309,9 +309,6 @@ NCR_700_detect(struct scsi_host_template *tpnt,
		hostdata->msgin = memory + MSGIN_OFFSET;
		hostdata->msgout = memory + MSGOUT_OFFSET;
		hostdata->status = memory + STATUS_OFFSET;
		/* all of these offsets are L1_CACHE_BYTES separated. It is fatal
		* if this isn't sufficient separation to avoid dma flushing issues */
		BUG_ON(!dma_is_consistent(hostdata->dev, pScript) && L1_CACHE_BYTES < dma_get_cache_alignment());
		hostdata->slots = (struct NCR_700_command_slot *)(memory + SLOTS_OFFSET);
		hostdata->dev = dev;

Admin message