Skip to content
Permalink
Browse files
dmaengine: ti: k3-udma: Add support for burst_size configuration for … 
…mem2mem

The UDMA and BCDMA can provide higher throughput if the burst_size of the
channel is changed from it's default (which is 64 bytes) for Ultra-high
and high capacity channels.

This performance benefit is even more visible when the buffers are aligned
with the burst_size configuration.

The am654 does not have a way to change the burst size, but it is using
64 bytes burst, so increasing the copy_align from 8 bytes to 64 (and
clients taking that into account) can increase the througput as well.

Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
  • Loading branch information
Peter Ujfalusi committed Nov 18, 2020
1 parent 63b8fda commit 7e4a26181ab91aeb561a52a2ea28b62f1078a261
Showing 1 changed file with 112 additions and 5 deletions.
117 drivers/dma/ti/k3-udma.c
View file
@@ -121,13 +121,19 @@ struct udma_oes_offsets {
#define UDMA_FLAG_PDMA_ACC32 BIT(0)
#define UDMA_FLAG_PDMA_BURST BIT(1)
#define UDMA_FLAG_TDTYPE BIT(2)
#define UDMA_FLAG_BURST_SIZE BIT(3)
#define UDMA_FLAGS_J7_CLASS (UDMA_FLAG_PDMA_ACC32 | \
UDMA_FLAG_PDMA_BURST | \
UDMA_FLAG_TDTYPE | \
UDMA_FLAG_BURST_SIZE)

struct udma_match_data {
enum k3_dma_type type;
u32 psil_base;
bool enable_memcpy_support;
u32 flags;
u32 statictr_z_mask;
u8 burst_size[3];
};

struct udma_soc_data {
@@ -436,6 +442,18 @@ static void k3_configure_chan_coherency(struct dma_chan *chan, u32 asel)
}
}

static u8 udma_get_chan_tpl_index(struct udma_tpl *tpl_map, int chan_id)
{
int i;

for (i = 0; i < tpl_map->levels; i++) {
if (chan_id >= tpl_map->start_idx[i])
return i;
}

return 0;
}

static void udma_reset_uchan(struct udma_chan *uc)
{
memset(&uc->config, 0, sizeof(uc->config));
@@ -1811,20 +1829,31 @@ static int udma_tisci_m2m_channel_config(struct udma_chan *uc)
const struct ti_sci_rm_udmap_ops *tisci_ops = tisci_rm->tisci_udmap_ops;
struct udma_tchan *tchan = uc->tchan;
struct udma_rchan *rchan = uc->rchan;
u8 burst_size = 0;
int ret = 0;

/* Non synchronized - mem to mem type of transfer */
int tc_ring = k3_ringacc_get_ring_id(tchan->tc_ring);
struct ti_sci_msg_rm_udmap_tx_ch_cfg req_tx = { 0 };
struct ti_sci_msg_rm_udmap_rx_ch_cfg req_rx = { 0 };

if (ud->match_data->flags & UDMA_FLAG_BURST_SIZE) {
u8 tpl = udma_get_chan_tpl_index(&ud->tchan_tpl, tchan->id);

burst_size = ud->match_data->burst_size[tpl];
}

req_tx.valid_params = TISCI_UDMA_TCHAN_VALID_PARAMS;
req_tx.nav_id = tisci_rm->tisci_dev_id;
req_tx.index = tchan->id;
req_tx.tx_chan_type = TI_SCI_RM_UDMAP_CHAN_TYPE_3RDP_BCOPY_PBRR;
req_tx.tx_fetch_size = sizeof(struct cppi5_desc_hdr_t) >> 2;
req_tx.txcq_qnum = tc_ring;
req_tx.tx_atype = ud->atype;
if (burst_size) {
req_tx.valid_params |= TI_SCI_MSG_VALUE_RM_UDMAP_CH_BURST_SIZE_VALID;
req_tx.tx_burst_size = burst_size;
}

ret = tisci_ops->tx_ch_cfg(tisci_rm->tisci, &req_tx);
if (ret) {
@@ -1839,6 +1868,10 @@ static int udma_tisci_m2m_channel_config(struct udma_chan *uc)
req_rx.rxcq_qnum = tc_ring;
req_rx.rx_chan_type = TI_SCI_RM_UDMAP_CHAN_TYPE_3RDP_BCOPY_PBRR;
req_rx.rx_atype = ud->atype;
if (burst_size) {
req_rx.valid_params |= TI_SCI_MSG_VALUE_RM_UDMAP_CH_BURST_SIZE_VALID;
req_rx.rx_burst_size = burst_size;
}

ret = tisci_ops->rx_ch_cfg(tisci_rm->tisci, &req_rx);
if (ret)
@@ -1854,12 +1887,23 @@ static int bcdma_tisci_m2m_channel_config(struct udma_chan *uc)
const struct ti_sci_rm_udmap_ops *tisci_ops = tisci_rm->tisci_udmap_ops;
struct ti_sci_msg_rm_udmap_tx_ch_cfg req_tx = { 0 };
struct udma_bchan *bchan = uc->bchan;
u8 burst_size = 0;
int ret = 0;

if (ud->match_data->flags & UDMA_FLAG_BURST_SIZE) {
u8 tpl = udma_get_chan_tpl_index(&ud->bchan_tpl, bchan->id);

burst_size = ud->match_data->burst_size[tpl];
}

req_tx.valid_params = TISCI_BCDMA_BCHAN_VALID_PARAMS;
req_tx.nav_id = tisci_rm->tisci_dev_id;
req_tx.extended_ch_type = TI_SCI_RM_BCDMA_EXTENDED_CH_TYPE_BCHAN;
req_tx.index = bchan->id;
if (burst_size) {
req_tx.valid_params |= TI_SCI_MSG_VALUE_RM_UDMAP_CH_BURST_SIZE_VALID;
req_tx.tx_burst_size = burst_size;
}

ret = tisci_ops->tx_ch_cfg(tisci_rm->tisci, &req_tx);
if (ret)
@@ -4167,45 +4211,75 @@ static struct udma_match_data am654_main_data = {
.psil_base = 0x1000,
.enable_memcpy_support = true,
.statictr_z_mask = GENMASK(11, 0),
.burst_size = {
TI_SCI_RM_UDMAP_CHAN_BURST_SIZE_64_BYTES, /* Normal Channels */
TI_SCI_RM_UDMAP_CHAN_BURST_SIZE_64_BYTES, /* H Channels */
0, /* No UH Channels */
},
};

static struct udma_match_data am654_mcu_data = {
.type = DMA_TYPE_UDMA,
.psil_base = 0x6000,
.enable_memcpy_support = false,
.statictr_z_mask = GENMASK(11, 0),
.burst_size = {
TI_SCI_RM_UDMAP_CHAN_BURST_SIZE_64_BYTES, /* Normal Channels */
TI_SCI_RM_UDMAP_CHAN_BURST_SIZE_64_BYTES, /* H Channels */
0, /* No UH Channels */
},
};

static struct udma_match_data j721e_main_data = {
.type = DMA_TYPE_UDMA,
.psil_base = 0x1000,
.enable_memcpy_support = true,
.flags = UDMA_FLAG_PDMA_ACC32 | UDMA_FLAG_PDMA_BURST | UDMA_FLAG_TDTYPE,
.flags = UDMA_FLAGS_J7_CLASS,
.statictr_z_mask = GENMASK(23, 0),
.burst_size = {
TI_SCI_RM_UDMAP_CHAN_BURST_SIZE_64_BYTES, /* Normal Channels */
TI_SCI_RM_UDMAP_CHAN_BURST_SIZE_256_BYTES, /* H Channels */
TI_SCI_RM_UDMAP_CHAN_BURST_SIZE_256_BYTES, /* UH Channels */
},
};

static struct udma_match_data j721e_mcu_data = {
.type = DMA_TYPE_UDMA,
.psil_base = 0x6000,
.enable_memcpy_support = false, /* MEM_TO_MEM is slow via MCU UDMA */
.flags = UDMA_FLAG_PDMA_ACC32 | UDMA_FLAG_PDMA_BURST | UDMA_FLAG_TDTYPE,
.flags = UDMA_FLAGS_J7_CLASS,
.statictr_z_mask = GENMASK(23, 0),
.burst_size = {
TI_SCI_RM_UDMAP_CHAN_BURST_SIZE_64_BYTES, /* Normal Channels */
TI_SCI_RM_UDMAP_CHAN_BURST_SIZE_128_BYTES, /* H Channels */
0, /* No UH Channels */
},
};

static struct udma_match_data am64_bcdma_data = {
.type = DMA_TYPE_BCDMA,
.psil_base = 0x2000, /* for tchan and rchan, not applicable to bchan */
.enable_memcpy_support = true, /* Supported via bchan */
.flags = UDMA_FLAG_PDMA_ACC32 | UDMA_FLAG_PDMA_BURST | UDMA_FLAG_TDTYPE,
.flags = UDMA_FLAGS_J7_CLASS,
.statictr_z_mask = GENMASK(23, 0),
.burst_size = {
TI_SCI_RM_UDMAP_CHAN_BURST_SIZE_64_BYTES, /* Normal Channels */
0, /* No H Channels */
0, /* No UH Channels */
},
};

static struct udma_match_data am64_pktdma_data = {
.type = DMA_TYPE_PKTDMA,
.psil_base = 0x1000,
.enable_memcpy_support = false, /* PKTDMA does not support MEM_TO_MEM */
.flags = UDMA_FLAG_PDMA_ACC32 | UDMA_FLAG_PDMA_BURST | UDMA_FLAG_TDTYPE,
.flags = UDMA_FLAGS_J7_CLASS,
.statictr_z_mask = GENMASK(23, 0),
.burst_size = {
TI_SCI_RM_UDMAP_CHAN_BURST_SIZE_64_BYTES, /* Normal Channels */
0, /* No H Channels */
0, /* No UH Channels */
},
};

static const struct of_device_id udma_of_match[] = {
@@ -5045,6 +5119,37 @@ static void udma_dbg_summary_show(struct seq_file *s,
}
#endif /* CONFIG_DEBUG_FS */

static enum dmaengine_alignment udma_get_copy_align(struct udma_dev *ud)
{
const struct udma_match_data *match_data = ud->match_data;
u8 tpl, burst_size;

if (!match_data->enable_memcpy_support)
return DMAENGINE_ALIGN_8_BYTES;

/* Get the highest TPL level the device supports for memcpy */
if (ud->bchan_cnt) {
tpl = udma_get_chan_tpl_index(&ud->bchan_tpl, 0);
} else if (ud->tchan_cnt) {
tpl = udma_get_chan_tpl_index(&ud->tchan_tpl, 0);
} else {
return DMAENGINE_ALIGN_8_BYTES;
}

burst_size = match_data->burst_size[tpl];

switch (match_data->burst_size[tpl]) {
case TI_SCI_RM_UDMAP_CHAN_BURST_SIZE_256_BYTES:
return DMAENGINE_ALIGN_256_BYTES;
case TI_SCI_RM_UDMAP_CHAN_BURST_SIZE_128_BYTES:
return DMAENGINE_ALIGN_128_BYTES;
case TI_SCI_RM_UDMAP_CHAN_BURST_SIZE_64_BYTES:
fallthrough;
default:
return DMAENGINE_ALIGN_64_BYTES;
}
}

#define TI_UDMAC_BUSWIDTHS (BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) | \
BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) | \
BIT(DMA_SLAVE_BUSWIDTH_3_BYTES) | \
@@ -5201,7 +5306,6 @@ static int udma_probe(struct platform_device *pdev)
ud->ddev.dst_addr_widths = TI_UDMAC_BUSWIDTHS;
ud->ddev.directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
ud->ddev.residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;
ud->ddev.copy_align = DMAENGINE_ALIGN_8_BYTES;
ud->ddev.desc_metadata_modes = DESC_METADATA_CLIENT |
DESC_METADATA_ENGINE;
if (ud->match_data->enable_memcpy_support &&
@@ -5283,6 +5387,9 @@ static int udma_probe(struct platform_device *pdev)
INIT_DELAYED_WORK(&uc->tx_drain.work, udma_check_tx_completion);
}

/* Configure the copy_align to the maximum burst size the device supports */
ud->ddev.copy_align = udma_get_copy_align(ud);

ret = dma_async_device_register(&ud->ddev);
if (ret) {
dev_err(dev, "failed to register slave DMA engine: %d\n", ret);

0 comments on commit 7e4a261

Please sign in to comment.