| Message ID | 1407155216-20267-1-git-send-email-peter.ujfalusi@ti.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
On Mon, Aug 04, 2014 at 03:26:56PM +0300, Peter Ujfalusi wrote: > The edma_setup_from_hw() should know about the CC number when parsing the > CCCFG register - when it reads the register to be precise. The base > addresses for CCs stored in an array and we need to provide the correct id > to edma_read() in order to read the correct register. Just an othognal question: I still see lot of code for edma in arm/. What is the plan to re/move that to dma/
On 08/05/2014 07:32 PM, Vinod Koul wrote: > On Mon, Aug 04, 2014 at 03:26:56PM +0300, Peter Ujfalusi wrote: >> The edma_setup_from_hw() should know about the CC number when parsing the >> CCCFG register - when it reads the register to be precise. The base >> addresses for CCs stored in an array and we need to provide the correct id >> to edma_read() in order to read the correct register. > > Just an othognal question: > > I still see lot of code for edma in arm/. What is the plan to re/move that > to dma/ Yes, there's still a big split. The code under arch/arm/common/ provides still the 'legacy' edma API. This is still used by audio sound/soc/davinci/davinci-pcm for older daVinci devices (AM335x. AM43xx uses the edma-pcm). And it is not that simple to deprecate davinci-pcm: it can use so called ping-pong mode for audio data transfer. This mode is not possible via dmaengine AFAIK. I'm going to check if edma-pcm would work fine instead of the ping-pong mode. If it does I can remove davinci-pcm and we can start cleaning up the edma code.
On Monday 04 August 2014 05:56 PM, Peter Ujfalusi wrote: > The edma_setup_from_hw() should know about the CC number when parsing the > CCCFG register - when it reads the register to be precise. The base > addresses for CCs stored in an array and we need to provide the correct id > to edma_read() in order to read the correct register. > > Cc: <stable@vger.kernel.org> # 3.16 > Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> Applied and will queue for v3.17-rc Thanks, Sekhar
diff --git a/arch/arm/common/edma.c b/arch/arm/common/edma.c index 88099175fc56..d86771abbf57 100644 --- a/arch/arm/common/edma.c +++ b/arch/arm/common/edma.c @@ -1443,14 +1443,14 @@ void edma_assign_channel_eventq(unsigned channel, enum dma_event_q eventq_no) EXPORT_SYMBOL(edma_assign_channel_eventq); static int edma_setup_from_hw(struct device *dev, struct edma_soc_info *pdata, - struct edma *edma_cc) + struct edma *edma_cc, int cc_id) { int i; u32 value, cccfg; s8 (*queue_priority_map)[2]; /* Decode the eDMA3 configuration from CCCFG register */ - cccfg = edma_read(0, EDMA_CCCFG); + cccfg = edma_read(cc_id, EDMA_CCCFG); value = GET_NUM_REGN(cccfg); edma_cc->num_region = BIT(value); @@ -1464,7 +1464,8 @@ static int edma_setup_from_hw(struct device *dev, struct edma_soc_info *pdata, value = GET_NUM_EVQUE(cccfg); edma_cc->num_tc = value + 1; - dev_dbg(dev, "eDMA3 HW configuration (cccfg: 0x%08x):\n", cccfg); + dev_dbg(dev, "eDMA3 CC%d HW configuration (cccfg: 0x%08x):\n", cc_id, + cccfg); dev_dbg(dev, "num_region: %u\n", edma_cc->num_region); dev_dbg(dev, "num_channel: %u\n", edma_cc->num_channels); dev_dbg(dev, "num_slot: %u\n", edma_cc->num_slots); @@ -1684,7 +1685,7 @@ static int edma_probe(struct platform_device *pdev) return -ENOMEM; /* Get eDMA3 configuration from IP */ - ret = edma_setup_from_hw(dev, info[j], edma_cc[j]); + ret = edma_setup_from_hw(dev, info[j], edma_cc[j], j); if (ret) return ret;
The edma_setup_from_hw() should know about the CC number when parsing the CCCFG register - when it reads the register to be precise. The base addresses for CCs stored in an array and we need to provide the correct id to edma_read() in order to read the correct register. Cc: <stable@vger.kernel.org> # 3.16 Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com> --- arch/arm/common/edma.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-)