Allow the left and right 16 bit samples to be shifted out as 1 32 bit sample.

Signed-off-by: Troy Kisky troy.kisky@boundarydevices.com --- arch/arm/mach-davinci/include/mach/asp.h | 6 +++ sound/soc/davinci/davinci-i2s.c | 73 ++++++++++++++++++++++------- 2 files changed, 61 insertions(+), 18 deletions(-)

diff --git a/arch/arm/mach-davinci/include/mach/asp.h b/arch/arm/mach-davinci/include/mach/asp.h index cdf1f44..73b60b6 100644 --- a/arch/arm/mach-davinci/include/mach/asp.h +++ b/arch/arm/mach-davinci/include/mach/asp.h @@ -37,6 +37,12 @@ struct snd_platform_data { u32 rx_dma_offset; enum dma_event_q eventq_no; /* event queue number */ unsigned int codec_fmt; + /* + * Allowing this is more efficient and eliminates left and right swaps + * caused by underruns, but will swap the left and right channels + * when compared to previous behavior. + */ + unsigned disable_channel_combine:1;

/* McASP specific fields */ int tdm_slots; diff --git a/sound/soc/davinci/davinci-i2s.c b/sound/soc/davinci/davinci-i2s.c index 2a56fb7..9587e00 100644 --- a/sound/soc/davinci/davinci-i2s.c +++ b/sound/soc/davinci/davinci-i2s.c @@ -97,6 +97,23 @@ enum { DAVINCI_MCBSP_WORD_32, };

+static const unsigned char data_type[SNDRV_PCM_FORMAT_S32_LE + 1] = { + [SNDRV_PCM_FORMAT_S8] = 1, + [SNDRV_PCM_FORMAT_S16_LE] = 2, + [SNDRV_PCM_FORMAT_S32_LE] = 4, +}; + +static const unsigned char asp_word_length[SNDRV_PCM_FORMAT_S32_LE + 1] = { + [SNDRV_PCM_FORMAT_S8] = DAVINCI_MCBSP_WORD_8, + [SNDRV_PCM_FORMAT_S16_LE] = DAVINCI_MCBSP_WORD_16, + [SNDRV_PCM_FORMAT_S32_LE] = DAVINCI_MCBSP_WORD_32, +}; + +static const unsigned char double_fmt[SNDRV_PCM_FORMAT_S32_LE + 1] = { + [SNDRV_PCM_FORMAT_S8] = SNDRV_PCM_FORMAT_S16_LE, + [SNDRV_PCM_FORMAT_S16_LE] = SNDRV_PCM_FORMAT_S32_LE, +}; + static struct davinci_pcm_dma_params davinci_i2s_pcm_out = { .name = "I2S PCM Stereo out", }; @@ -113,6 +130,27 @@ struct davinci_mcbsp_dev { u32 pcr; struct clk *clk; struct davinci_pcm_dma_params *dma_params[2]; + /* + * Combining both channels into 1 element will at least double the + * amount of time between servicing the dma channel, increase + * effiency, and reduce the chance of overrun/underrun. But, + * it will result in the left & right channels being swapped. + * + * If relabeling the left and right channels is not possible, + * you may want to let the codec know to swap them back. + * + * It may allow x10 the amount of time to service dma requests, + * if the codec is master and is using an unnecessarily fast bit clock + * (ie. tlvaic23b), independent of the sample rate. So, having an + * entire frame at once means it can be serviced at the sample rate + * instead of the bit clock rate. + * + * In the now unlikely case that an underrun still + * occurs, both the left and right samples will be repeated + * so that no pops are heard, and the left and right channels + * won't end up being swapped because of the underrun. + */ + unsigned disable_channel_combine:1; };

static inline void davinci_mcbsp_write_reg(struct davinci_mcbsp_dev *dev, @@ -359,6 +397,8 @@ static int davinci_i2s_hw_params(struct snd_pcm_substream *substream, int mcbsp_word_length; unsigned int rcr, xcr, srgr; u32 spcr; + snd_pcm_format_t fmt; + unsigned element_cnt = 1;

/* general line settings */ spcr = davinci_mcbsp_read_reg(dev, DAVINCI_MCBSP_SPCR_REG); @@ -388,26 +428,22 @@ static int davinci_i2s_hw_params(struct snd_pcm_substream *substream, xcr |= DAVINCI_MCBSP_XCR_XDATDLY(1); } /* Determine xfer data type */ - switch (params_format(params)) { - case SNDRV_PCM_FORMAT_S8: - dma_params->data_type = 1; - mcbsp_word_length = DAVINCI_MCBSP_WORD_8; - break; - case SNDRV_PCM_FORMAT_S16_LE: - dma_params->data_type = 2; - mcbsp_word_length = DAVINCI_MCBSP_WORD_16; - break; - case SNDRV_PCM_FORMAT_S32_LE: - dma_params->data_type = 4; - mcbsp_word_length = DAVINCI_MCBSP_WORD_32; - break; - default: + fmt = params_format(params); + if ((fmt > SNDRV_PCM_FORMAT_S32_LE) || !data_type[fmt]) { printk(KERN_WARNING "davinci-i2s: unsupported PCM format\n"); return -EINVAL; } - - rcr |= DAVINCI_MCBSP_RCR_RFRLEN1(1); - xcr |= DAVINCI_MCBSP_XCR_XFRLEN1(1); + if (params_channels(params) == 2) { + element_cnt = 2; + if (double_fmt[fmt] && !dev->disable_channel_combine) { + element_cnt = 1; + fmt = double_fmt[fmt]; + } + } + dma_params->data_type = data_type[fmt]; + mcbsp_word_length = asp_word_length[fmt]; + rcr |= DAVINCI_MCBSP_RCR_RFRLEN1(element_cnt - 1); + xcr |= DAVINCI_MCBSP_XCR_XFRLEN1(element_cnt - 1);

rcr |= DAVINCI_MCBSP_RCR_RWDLEN1(mcbsp_word_length) | DAVINCI_MCBSP_RCR_RWDLEN2(mcbsp_word_length); @@ -523,7 +559,8 @@ static int davinci_i2s_probe(struct platform_device *pdev) ret = -ENOMEM; goto err_release_region; } - + if (pdata) + dev->disable_channel_combine = pdata->disable_channel_combine; dev->clk = clk_get(&pdev->dev, NULL); if (IS_ERR(dev->clk)) { ret = -ENODEV;

Fix underruns by using dma to copy 1st to sram in a ping/pong buffer style and then copying from the sram to the ASP. This also has the advantage of tolerating very long interrupt latency on dma completion.

Signed-off-by: Troy Kisky troy.kisky@boundarydevices.com --- arch/arm/mach-davinci/include/mach/asp.h | 2 + sound/soc/davinci/davinci-i2s.c | 5 +- sound/soc/davinci/davinci-pcm.c | 471 +++++++++++++++++++++++++++--- sound/soc/davinci/davinci-pcm.h | 1 + 4 files changed, 435 insertions(+), 44 deletions(-)

diff --git a/arch/arm/mach-davinci/include/mach/asp.h b/arch/arm/mach-davinci/include/mach/asp.h index 73b60b6..0fdbf45 100644 --- a/arch/arm/mach-davinci/include/mach/asp.h +++ b/arch/arm/mach-davinci/include/mach/asp.h @@ -43,6 +43,8 @@ struct snd_platform_data { * when compared to previous behavior. */ unsigned disable_channel_combine:1; + unsigned sram_size_playback; + unsigned sram_size_capture;

/* McASP specific fields */ int tdm_slots; diff --git a/sound/soc/davinci/davinci-i2s.c b/sound/soc/davinci/davinci-i2s.c index 9587e00..129684d 100644 --- a/sound/soc/davinci/davinci-i2s.c +++ b/sound/soc/davinci/davinci-i2s.c @@ -559,8 +559,11 @@ static int davinci_i2s_probe(struct platform_device *pdev) ret = -ENOMEM; goto err_release_region; } - if (pdata) + if (pdata) { dev->disable_channel_combine = pdata->disable_channel_combine; + davinci_i2s_pcm_out.sram_size = pdata->sram_size_playback; + davinci_i2s_pcm_in.sram_size = pdata->sram_size_capture; + } dev->clk = clk_get(&pdev->dev, NULL); if (IS_ERR(dev->clk)) { ret = -ENODEV; diff --git a/sound/soc/davinci/davinci-pcm.c b/sound/soc/davinci/davinci-pcm.c index 3489f18..191cf4f 100644 --- a/sound/soc/davinci/davinci-pcm.c +++ b/sound/soc/davinci/davinci-pcm.c @@ -3,6 +3,7 @@ * * Author: Vladimir Barinov, vbarinov@embeddedalley.com * Copyright: (C) 2007 MontaVista Software, Inc., source@mvista.com + * added SRAM ping/pong (C) 2008 Troy Kisky troy.kisky@boundarydevices.com * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -23,9 +24,28 @@

#include <asm/dma.h> #include <mach/edma.h> +#include <mach/sram.h>

#include "davinci-pcm.h"

+#ifdef DEBUG +static void print_buf_info(int lch, char *name) +{ + struct edmacc_param p; + if (lch < 0) + return; + edma_read_slot(lch, &p); + printk(KERN_DEBUG "%s: 0x%x, opt=%x, src=%x, a_b_cnt=%x dst=%x\n", + name, lch, p.opt, p.src, p.a_b_cnt, p.dst); + printk(KERN_DEBUG " src_dst_bidx=%x link_bcntrld=%x src_dst_cidx=%x ccnt=%x\n", + p.src_dst_bidx, p.link_bcntrld, p.src_dst_cidx, p.ccnt); +} +#else +static void print_buf_info(int lch, char *name) +{ +} +#endif + static struct snd_pcm_hardware davinci_pcm_hardware = { .info = (SNDRV_PCM_INFO_INTERLEAVED | SNDRV_PCM_INFO_BLOCK_TRANSFER | SNDRV_PCM_INFO_MMAP | SNDRV_PCM_INFO_MMAP_VALID | @@ -48,14 +68,58 @@ static struct snd_pcm_hardware davinci_pcm_hardware = { .fifo_size = 0, };

+/* + * How ping/pong works.... + * + * Playback: + * ram_params - copys 2*ping_size from start of SDRAM to iram, + * links to ram_link_lch2 + * ram_link_lch2 - copys rest of SDRAM to iram in ping_size units, + * links to ram_link_lch + * ram_link_lch - copys entire SDRAM to iram in ping_size uints, + * links to self + * + * asp_params - same as asp_link_lch[0] + * asp_link_lch[0] - copys from lower half of iram to asp port + * links to asp_link_lch[1], triggers iram copy event on completion + * asp_link_lch[1] - copys from upper half of iram to asp port + * links to asp_link_lch[0], triggers iram copy event on completion + * triggers interrupt only needed to let upper SOC levels update position + * in stream on completion + * + * When playback is started: + * ram_params started + * asp_params started + * + * Capture: + * ram_params - same as ram_link_lch, + * links to ram_link_lch + * ram_link_lch - same as playback + * links to self + * + * asp_params - same as playback + * asp_link_lch[0] - same as playback + * asp_link_lch[1] - same as playback + * + * When capture is started: + * asp_params started + */ struct davinci_runtime_data { spinlock_t lock; int period; /* current DMA period */ int asp_master_lch; /* Master DMA channel */ int asp_link_lch[2]; /* asp parameter link channel, ping/pong */ struct davinci_pcm_dma_params *params; /* DMA params */ + int ram_master_lch; + int ram_link_lch; + int ram_link_lch2; + struct edmacc_param asp_params; + struct edmacc_param ram_params; };

+/* + * Not used with ping/pong + */ static void davinci_pcm_enqueue_dma(struct snd_pcm_substream *substream) { struct davinci_runtime_data *prtd = substream->runtime->private_data; @@ -107,48 +171,280 @@ static void davinci_pcm_dma_irq(unsigned lch, u16 ch_status, void *data) struct snd_pcm_substream *substream = data; struct davinci_runtime_data *prtd = substream->runtime->private_data;

+ print_buf_info(prtd->ram_master_lch, "i ram_master_lch"); pr_debug("davinci_pcm: lch=%d, status=0x%x\n", lch, ch_status);

if (unlikely(ch_status != DMA_COMPLETE)) return;

if (snd_pcm_running(substream)) { + if (prtd->ram_master_lch < 0) { + /* No ping/pong must fix up link dma data*/ + spin_lock(&prtd->lock); + davinci_pcm_enqueue_dma(substream); + spin_unlock(&prtd->lock); + } snd_pcm_period_elapsed(substream); + } +} + +static int allocate_sram(struct snd_pcm_substream *substream, unsigned size) +{ + struct snd_dma_buffer *buf = &substream->dma_buffer; + struct snd_dma_buffer *iram_dma = NULL; + dma_addr_t iram_phys = 0; + void *iram_virt = NULL; + + if (buf->private_data || !size) + return 0; + + davinci_pcm_hardware.period_bytes_max = size; + iram_virt = sram_alloc(size, &iram_phys); + if (!iram_virt) + goto exit1; + iram_dma = kzalloc(sizeof(*iram_dma), GFP_KERNEL); + if (!iram_dma) + goto exit2; + iram_dma->area = iram_virt; + iram_dma->addr = iram_phys; + memset(iram_dma->area, 0, size); + iram_dma->bytes = size; + buf->private_data = iram_dma; + return 0; +exit2: + if (iram_virt) + sram_free(iram_virt, size); +exit1: + return -ENOMEM; +} + +/* + * Only used with ping/pong. + * This is called after runtime->dma_addr, period_bytes and data_type are valid + */ +static int ping_pong_dma_setup(struct snd_pcm_substream *substream) +{ + unsigned short ram_src_cidx, ram_dst_cidx; + struct snd_pcm_runtime *runtime = substream->runtime; + struct davinci_runtime_data *prtd = runtime->private_data; + struct snd_dma_buffer *iram_dma = + (struct snd_dma_buffer *)substream->dma_buffer.private_data; + struct snd_soc_pcm_runtime *rtd = substream->private_data; + struct davinci_pcm_dma_params *dma_data = rtd->dai->cpu_dai->dma_data; + unsigned int data_type = dma_data->data_type; + /* divide by 2 for ping/pong */ + unsigned int ping_size = snd_pcm_lib_period_bytes(substream) >> 1; + int lch = prtd->asp_link_lch[1]; + if ((data_type == 0) || (data_type > 4)) { + printk(KERN_ERR "%s: data_type=%i\n", __func__, data_type); + return -EINVAL; + } + if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { + dma_addr_t asp_src_pong = iram_dma->addr + ping_size; + ram_src_cidx = ping_size; + ram_dst_cidx = -ping_size; + edma_set_src(lch, asp_src_pong, INCR, W8BIT); + + lch = prtd->asp_link_lch[0]; + edma_set_src_index(lch, data_type, 0); + lch = prtd->asp_link_lch[1]; + edma_set_src_index(lch, data_type, 0); + + lch = prtd->ram_link_lch; + edma_set_src(lch, runtime->dma_addr, INCR, W32BIT); + } else { + dma_addr_t asp_dst_pong = iram_dma->addr + ping_size; + ram_src_cidx = -ping_size; + ram_dst_cidx = ping_size; + edma_set_dest(lch, asp_dst_pong, INCR, W8BIT); + + lch = prtd->asp_link_lch[0]; + edma_set_dest_index(lch, data_type, 0); + lch = prtd->asp_link_lch[1]; + edma_set_dest_index(lch, data_type, 0); + + lch = prtd->ram_link_lch; + edma_set_dest(lch, runtime->dma_addr, INCR, W32BIT); + }

- spin_lock(&prtd->lock); - davinci_pcm_enqueue_dma(substream); - spin_unlock(&prtd->lock); + lch = prtd->asp_link_lch[0]; + edma_set_transfer_params(lch, data_type, + ping_size/data_type, 1, 0, ASYNC); + lch = prtd->asp_link_lch[1]; + edma_set_transfer_params(lch, data_type, + ping_size/data_type, 1, 0, ASYNC); + + lch = prtd->ram_link_lch; + edma_set_src_index(lch, ping_size, ram_src_cidx); + edma_set_dest_index(lch, ping_size, ram_dst_cidx); + edma_set_transfer_params(lch, ping_size, 2, + runtime->periods, 2, ASYNC); + + /* init master params */ + edma_read_slot(prtd->asp_link_lch[0], &prtd->asp_params); + edma_read_slot(prtd->ram_link_lch, &prtd->ram_params); + if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { + struct edmacc_param p_ram; + /* Copy entire iram buffer before playback started */ + prtd->ram_params.a_b_cnt = (1 << 16) | (ping_size << 1); + /* 0 dst_bidx */ + prtd->ram_params.src_dst_bidx = (ping_size << 1); + /* 0 dst_cidx */ + prtd->ram_params.src_dst_cidx = (ping_size << 1); + prtd->ram_params.ccnt = 1; + + /* Skip 1st period */ + edma_read_slot(prtd->ram_link_lch, &p_ram); + p_ram.src += (ping_size << 1); + p_ram.ccnt -= 1; + edma_write_slot(prtd->ram_link_lch2, &p_ram); + /* + * When 1st started, ram -> iram dma channel will fill the + * entire iram. Then, whenever a ping/pong asp buffer finishes, + * 1/2 iram will be filled. + */ + prtd->ram_params.link_bcntrld = + EDMA_CHAN_SLOT(prtd->ram_link_lch2) << 5; } + return 0; +} + +/* 1 asp tx or rx channel using 2 parameter channels + * 1 ram to/from iram channel using 1 parameter channel + * + * Playback + * ram copy channel kicks off first, + * 1st ram copy of entire iram buffer completion kicks off asp channel + * asp tcc always kicks off ram copy of 1/2 iram buffer + * + * Record + * asp channel starts, tcc kicks off ram copy + */ +static int request_ping_pong(struct snd_pcm_substream *substream, + struct davinci_runtime_data *prtd, + struct snd_dma_buffer *iram_dma) +{ + dma_addr_t asp_src_ping; + dma_addr_t asp_dst_ping; + int lch; + struct davinci_pcm_dma_params *dma_data = prtd->params; + + /* Request ram master channel */ + lch = prtd->ram_master_lch = edma_alloc_channel(EDMA_CHANNEL_ANY, + davinci_pcm_dma_irq, substream, + EVENTQ_1); + if (lch < 0) + goto exit1; + + /* Request ram link channel */ + lch = prtd->ram_link_lch = edma_alloc_slot( + EDMA_CTLR(prtd->ram_master_lch), EDMA_SLOT_ANY); + if (lch < 0) + goto exit2; + + lch = prtd->asp_link_lch[1] = edma_alloc_slot( + EDMA_CTLR(prtd->asp_master_lch), EDMA_SLOT_ANY); + if (lch < 0) + goto exit3; + + prtd->ram_link_lch2 = -1; + if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { + lch = prtd->ram_link_lch2 = edma_alloc_slot( + EDMA_CTLR(prtd->ram_master_lch), EDMA_SLOT_ANY); + if (lch < 0) + goto exit4; + } + /* circle ping-pong buffers */ + edma_link(prtd->asp_link_lch[0], prtd->asp_link_lch[1]); + edma_link(prtd->asp_link_lch[1], prtd->asp_link_lch[0]); + /* circle ram buffers */ + edma_link(prtd->ram_link_lch, prtd->ram_link_lch); + + if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { + asp_src_ping = iram_dma->addr; + asp_dst_ping = dma_data->dma_addr; /* fifo */ + } else { + asp_src_ping = dma_data->dma_addr; /* fifo */ + asp_dst_ping = iram_dma->addr; + } + /* ping */ + lch = prtd->asp_link_lch[0]; + edma_set_src(lch, asp_src_ping, INCR, W16BIT); + edma_set_dest(lch, asp_dst_ping, INCR, W16BIT); + edma_set_src_index(lch, 0, 0); + edma_set_dest_index(lch, 0, 0); + + edma_read_slot(lch, &prtd->asp_params); + prtd->asp_params.opt &= ~(TCCMODE | EDMA_TCC(0x3f) | TCINTEN); + prtd->asp_params.opt |= TCCHEN | EDMA_TCC(prtd->ram_master_lch & 0x3f); + edma_write_slot(lch, &prtd->asp_params); + + /* pong */ + lch = prtd->asp_link_lch[1]; + edma_set_src(lch, asp_src_ping, INCR, W16BIT); + edma_set_dest(lch, asp_dst_ping, INCR, W16BIT); + edma_set_src_index(lch, 0, 0); + edma_set_dest_index(lch, 0, 0); + + edma_read_slot(lch, &prtd->asp_params); + prtd->asp_params.opt &= ~(TCCMODE | EDMA_TCC(0x3f)); + /* interrupt after every pong completion */ + prtd->asp_params.opt |= TCINTEN | TCCHEN | + EDMA_TCC(EDMA_CHAN_SLOT(prtd->ram_master_lch)); + edma_write_slot(lch, &prtd->asp_params); + + /* ram */ + lch = prtd->ram_link_lch; + edma_set_src(lch, iram_dma->addr, INCR, W32BIT); + edma_set_dest(lch, iram_dma->addr, INCR, W32BIT); + pr_debug("%s: audio dma channels/slots in use for ram:%u %u %u," + "for asp:%u %u %u\n", __func__, + prtd->ram_master_lch, prtd->ram_link_lch, prtd->ram_link_lch2, + prtd->asp_master_lch, prtd->asp_link_lch[0], + prtd->asp_link_lch[1]); + return 0; +exit4: + edma_free_channel(prtd->asp_link_lch[1]); + prtd->asp_link_lch[1] = -1; +exit3: + edma_free_channel(prtd->ram_link_lch); + prtd->ram_link_lch = -1; +exit2: + edma_free_channel(prtd->ram_master_lch); + prtd->ram_master_lch = -1; +exit1: + return lch; }

static int davinci_pcm_dma_request(struct snd_pcm_substream *substream) { + struct snd_dma_buffer *iram_dma; struct davinci_runtime_data *prtd = substream->runtime->private_data; struct snd_soc_pcm_runtime *rtd = substream->private_data; struct davinci_pcm_dma_params *dma_data = rtd->dai->cpu_dai->dma_data; - struct edmacc_param p_ram; - int ret; + int lch;

if (!dma_data) return -ENODEV;

prtd->params = dma_data;

- /* Request master DMA channel */ - ret = edma_alloc_channel(prtd->params->channel, - davinci_pcm_dma_irq, substream, - EVENTQ_0); - if (ret < 0) - return ret; - prtd->asp_master_lch = ret; + /* Request asp master DMA channel */ + lch = prtd->asp_master_lch = edma_alloc_channel(dma_data->channel, + davinci_pcm_dma_irq, substream, EVENTQ_0); + if (lch < 0) + goto exit1;

- /* Request parameter RAM reload slot */ - ret = edma_alloc_slot(EDMA_CTLR(prtd->asp_master_lch), EDMA_SLOT_ANY); - if (ret < 0) { - edma_free_channel(prtd->asp_master_lch); - return ret; - } - prtd->asp_link_lch[0] = ret; + /* Request asp link channels */ + lch = prtd->asp_link_lch[0] = edma_alloc_slot( + EDMA_CTLR(prtd->asp_master_lch), EDMA_SLOT_ANY); + if (lch < 0) + goto exit2; + + allocate_sram(substream, dma_data->sram_size); + iram_dma = (struct snd_dma_buffer *)substream->dma_buffer.private_data; + if (iram_dma) + return request_ping_pong(substream, prtd, iram_dma);

/* Issue transfer completion IRQ when the channel completes a * transfer, then always reload from the same slot (by a kind @@ -159,12 +455,17 @@ static int davinci_pcm_dma_request(struct snd_pcm_substream *substream) * the buffer and its length (ccnt) ... use it as a template * so davinci_pcm_enqueue_dma() takes less time in IRQ. */ - edma_read_slot(prtd->asp_link_lch[0], &p_ram); - p_ram.opt |= TCINTEN | EDMA_TCC(EDMA_CHAN_SLOT(prtd->asp_master_lch)); - p_ram.link_bcntrld = EDMA_CHAN_SLOT(prtd->asp_link_lch[0]) << 5; - edma_write_slot(prtd->asp_link_lch[0], &p_ram); - + edma_read_slot(lch, &prtd->asp_params); + prtd->asp_params.opt |= TCINTEN | + EDMA_TCC(EDMA_CHAN_SLOT(prtd->asp_master_lch)); + prtd->asp_params.link_bcntrld = EDMA_CHAN_SLOT(lch) << 5; + edma_write_slot(lch, &prtd->asp_params); return 0; +exit2: + edma_free_channel(prtd->asp_master_lch); + prtd->asp_master_lch = -1; +exit1: + return lch; }

static int davinci_pcm_trigger(struct snd_pcm_substream *substream, int cmd) @@ -178,12 +479,12 @@ static int davinci_pcm_trigger(struct snd_pcm_substream *substream, int cmd) case SNDRV_PCM_TRIGGER_START: case SNDRV_PCM_TRIGGER_RESUME: case SNDRV_PCM_TRIGGER_PAUSE_RELEASE: - edma_start(prtd->asp_master_lch); + edma_resume(prtd->asp_master_lch); break; case SNDRV_PCM_TRIGGER_STOP: case SNDRV_PCM_TRIGGER_SUSPEND: case SNDRV_PCM_TRIGGER_PAUSE_PUSH: - edma_stop(prtd->asp_master_lch); + edma_pause(prtd->asp_master_lch); break; default: ret = -EINVAL; @@ -198,14 +499,35 @@ static int davinci_pcm_trigger(struct snd_pcm_substream *substream, int cmd) static int davinci_pcm_prepare(struct snd_pcm_substream *substream) { struct davinci_runtime_data *prtd = substream->runtime->private_data; - struct edmacc_param temp;

+ if (prtd->ram_master_lch >= 0) { + int ret = ping_pong_dma_setup(substream); + if (ret < 0) + return ret; + + edma_write_slot(prtd->ram_master_lch, &prtd->ram_params); + edma_write_slot(prtd->asp_master_lch, &prtd->asp_params); + + print_buf_info(prtd->ram_master_lch, "ram_master_lch"); + print_buf_info(prtd->ram_link_lch, "ram_link_lch"); + print_buf_info(prtd->ram_link_lch2, "ram_link_lch2"); + print_buf_info(prtd->asp_master_lch, "asp_master_lch"); + print_buf_info(prtd->asp_link_lch[0], "asp_link_lch[0]"); + print_buf_info(prtd->asp_link_lch[1], "asp_link_lch[1]"); + + if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { + /* copy 1st iram buffer */ + edma_start(prtd->ram_master_lch); + } + edma_start(prtd->asp_master_lch); + return 0; + } prtd->period = 0; davinci_pcm_enqueue_dma(substream);

/* Copy self-linked parameter RAM entry into master channel */ - edma_read_slot(prtd->asp_link_lch[0], &temp); - edma_write_slot(prtd->asp_master_lch, &temp); + edma_read_slot(prtd->asp_link_lch[0], &prtd->asp_params); + edma_write_slot(prtd->asp_master_lch, &prtd->asp_params); davinci_pcm_enqueue_dma(substream);

return 0; @@ -217,20 +539,53 @@ davinci_pcm_pointer(struct snd_pcm_substream *substream) struct snd_pcm_runtime *runtime = substream->runtime; struct davinci_runtime_data *prtd = runtime->private_data; unsigned int offset; - dma_addr_t count; - dma_addr_t src, dst; + int asp_count; + dma_addr_t asp_src, asp_dst;

spin_lock(&prtd->lock); - - edma_get_position(prtd->asp_master_lch, &src, &dst); - if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) - count = src - runtime->dma_addr; - else - count = dst - runtime->dma_addr; - + if (prtd->ram_master_lch >= 0) { + int ram_count; + int mod_ram; + dma_addr_t ram_src, ram_dst; + unsigned int period_size = snd_pcm_lib_period_bytes(substream); + if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { + /* reading ram before asp should be safe + * as long as the asp transfers less than a ping size + * of bytes between the 2 reads + */ + edma_get_position(prtd->ram_master_lch, + &ram_src, &ram_dst); + edma_get_position(prtd->asp_master_lch, + &asp_src, &asp_dst); + asp_count = asp_src - prtd->asp_params.src; + ram_count = ram_src - prtd->ram_params.src; + mod_ram = ram_count % period_size; + mod_ram -= asp_count; + if (mod_ram < 0) + mod_ram += period_size; + else if (mod_ram == 0) { + if (snd_pcm_running(substream)) + mod_ram += period_size; + } + ram_count -= mod_ram; + if (ram_count < 0) + ram_count += period_size * runtime->periods; + } else { + edma_get_position(prtd->ram_master_lch, + &ram_src, &ram_dst); + ram_count = ram_dst - prtd->ram_params.dst; + } + asp_count = ram_count; + } else { + edma_get_position(prtd->asp_master_lch, &asp_src, &asp_dst); + if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) + asp_count = asp_src - runtime->dma_addr; + else + asp_count = asp_dst - runtime->dma_addr; + } spin_unlock(&prtd->lock);

- offset = bytes_to_frames(runtime, count); + offset = bytes_to_frames(runtime, asp_count); if (offset >= runtime->buffer_size) offset = 0;

@@ -255,6 +610,11 @@ static int davinci_pcm_open(struct snd_pcm_substream *substream) return -ENOMEM;

spin_lock_init(&prtd->lock); + prtd->asp_master_lch = -1; + prtd->asp_link_lch[0] = prtd->asp_link_lch[1] = -1; + prtd->ram_master_lch = -1; + prtd->ram_link_lch = -1; + prtd->ram_link_lch2 = -1;

runtime->private_data = prtd;

@@ -272,10 +632,29 @@ static int davinci_pcm_close(struct snd_pcm_substream *substream) struct snd_pcm_runtime *runtime = substream->runtime; struct davinci_runtime_data *prtd = runtime->private_data;

- edma_unlink(prtd->asp_link_lch[0]); - - edma_free_slot(prtd->asp_link_lch[0]); - edma_free_channel(prtd->asp_master_lch); + if (prtd->ram_master_lch >= 0) + edma_stop(prtd->ram_master_lch); + if (prtd->asp_master_lch >= 0) + edma_stop(prtd->asp_master_lch); + if (prtd->asp_link_lch[0] >= 0) + edma_unlink(prtd->asp_link_lch[0]); + if (prtd->asp_link_lch[1] >= 0) + edma_unlink(prtd->asp_link_lch[1]); + if (prtd->ram_link_lch >= 0) + edma_unlink(prtd->ram_link_lch); + + if (prtd->asp_link_lch[0] >= 0) + edma_free_slot(prtd->asp_link_lch[0]); + if (prtd->asp_link_lch[1] >= 0) + edma_free_slot(prtd->asp_link_lch[1]); + if (prtd->asp_master_lch >= 0) + edma_free_channel(prtd->asp_master_lch); + if (prtd->ram_link_lch >= 0) + edma_free_slot(prtd->ram_link_lch); + if (prtd->ram_link_lch2 >= 0) + edma_free_slot(prtd->ram_link_lch2); + if (prtd->ram_master_lch >= 0) + edma_free_channel(prtd->ram_master_lch);

kfree(prtd);

@@ -346,6 +725,7 @@ static void davinci_pcm_free(struct snd_pcm *pcm) int stream;

for (stream = 0; stream < 2; stream++) { + struct snd_dma_buffer *iram_dma; substream = pcm->streams[stream].substream; if (!substream) continue; @@ -357,6 +737,11 @@ static void davinci_pcm_free(struct snd_pcm *pcm) dma_free_writecombine(pcm->card->dev, buf->bytes, buf->area, buf->addr); buf->area = NULL; + iram_dma = (struct snd_dma_buffer *)buf->private_data; + if (iram_dma) { + sram_free(iram_dma->area, iram_dma->bytes); + kfree(iram_dma); + } } }

diff --git a/sound/soc/davinci/davinci-pcm.h b/sound/soc/davinci/davinci-pcm.h index eb4287f..8d66b35 100644 --- a/sound/soc/davinci/davinci-pcm.h +++ b/sound/soc/davinci/davinci-pcm.h @@ -20,6 +20,7 @@ struct davinci_pcm_dma_params { char *name; /* stream identifier */ int channel; /* sync dma channel ID */ dma_addr_t dma_addr; /* device physical address for DMA */ + unsigned sram_size; enum dma_event_q eventq_no; /* event queue number */ unsigned char data_type; /* xfer data type */ unsigned char convert_mono_stereo;