| To: | David Daney <ddaney@caviumnetworks.com> |
|---|---|
| Subject: | Re: [PATCH] Don't unmap the memory for dma_sync*. |
| From: | Ralf Baechle <ralf@linux-mips.org> |
| Date: | Sat, 18 Oct 2008 12:02:11 +0100 |
| Cc: | linux-mips@linux-mips.org, "Paoletti, Tomaso" <Tomaso.Paoletti@caviumnetworks.com>, Thomas Bogendoerfer <tsbogend@alpha.franken.de> |
| In-reply-to: | <48F93275.8010305@caviumnetworks.com> |
| Original-recipient: | rfc822;linux-mips@linux-mips.org |
| References: | <48F93275.8010305@caviumnetworks.com> |
| Sender: | linux-mips-bounce@linux-mips.org |
| User-agent: | Mutt/1.5.18 (2008-05-17) |
On Fri, Oct 17, 2008 at 05:48:53PM -0700, David Daney wrote: > Don't unmap the memory for dma_sync*. > > This must have been typo, it cannot have been correct. Interesting ... We were getting away with this for so long only because the only platform (Jazz) with a non-empty plat_unmap_dma_mem() doesn't call dma_sync_sg_for_cpu() and dma_sync_sg_for_device() from its commonly used drivers. Ralf |
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | stop_this_cpu - redundant code?, Anirban Sinha |
|---|---|
| Next by Date: | Re: [PATCH] ide: Add tx4939ide driver (v4), Ralf Baechle |
| Previous by Thread: | [PATCH] Don't unmap the memory for dma_sync*., David Daney |
| Next by Thread: | stop_this_cpu - redundant code?, Anirban Sinha |
| Indexes: | [Date] [Thread] [Top] [All Lists] |