diff options
Diffstat (limited to 'drivers/dma/ti')
| -rw-r--r-- | drivers/dma/ti/Kconfig | 24 | ||||
| -rw-r--r-- | drivers/dma/ti/Makefile | 3 | ||||
| -rw-r--r-- | drivers/dma/ti/edma.c | 39 | ||||
| -rw-r--r-- | drivers/dma/ti/k3-psil-am654.c | 175 | ||||
| -rw-r--r-- | drivers/dma/ti/k3-psil-j721e.c | 222 | ||||
| -rw-r--r-- | drivers/dma/ti/k3-psil-priv.h | 43 | ||||
| -rw-r--r-- | drivers/dma/ti/k3-psil.c | 90 | ||||
| -rw-r--r-- | drivers/dma/ti/k3-udma-glue.c | 1207 | ||||
| -rw-r--r-- | drivers/dma/ti/k3-udma-private.c | 133 | ||||
| -rw-r--r-- | drivers/dma/ti/k3-udma.c | 3661 | ||||
| -rw-r--r-- | drivers/dma/ti/k3-udma.h | 151 | ||||
| -rw-r--r-- | drivers/dma/ti/omap-dma.c | 288 |
12 files changed, 6001 insertions, 35 deletions
diff --git a/drivers/dma/ti/Kconfig b/drivers/dma/ti/Kconfig index d507c24fbf31..f76e06651f80 100644 --- a/drivers/dma/ti/Kconfig +++ b/drivers/dma/ti/Kconfig @@ -34,5 +34,29 @@ config DMA_OMAP Enable support for the TI sDMA (System DMA or DMA4) controller. This DMA engine is found on OMAP and DRA7xx parts. +config TI_K3_UDMA + bool "Texas Instruments UDMA support" + depends on ARCH_K3 || COMPILE_TEST + depends on TI_SCI_PROTOCOL + depends on TI_SCI_INTA_IRQCHIP + select DMA_ENGINE + select DMA_VIRTUAL_CHANNELS + select TI_K3_RINGACC + select TI_K3_PSIL + help + Enable support for the TI UDMA (Unified DMA) controller. This + DMA engine is used in AM65x and j721e. + +config TI_K3_UDMA_GLUE_LAYER + bool "Texas Instruments UDMA Glue layer for non DMAengine users" + depends on ARCH_K3 || COMPILE_TEST + depends on TI_K3_UDMA + help + Say y here to support the K3 NAVSS DMA glue interface + If unsure, say N. + +config TI_K3_PSIL + bool + config TI_DMA_CROSSBAR bool diff --git a/drivers/dma/ti/Makefile b/drivers/dma/ti/Makefile index 113e59ec9c32..9a29a107e374 100644 --- a/drivers/dma/ti/Makefile +++ b/drivers/dma/ti/Makefile @@ -2,4 +2,7 @@ obj-$(CONFIG_TI_CPPI41) += cppi41.o obj-$(CONFIG_TI_EDMA) += edma.o obj-$(CONFIG_DMA_OMAP) += omap-dma.o +obj-$(CONFIG_TI_K3_UDMA) += k3-udma.o +obj-$(CONFIG_TI_K3_UDMA_GLUE_LAYER) += k3-udma-glue.o +obj-$(CONFIG_TI_K3_PSIL) += k3-psil.o k3-psil-am654.o k3-psil-j721e.o obj-$(CONFIG_TI_DMA_CROSSBAR) += dma-crossbar.o diff --git a/drivers/dma/ti/edma.c b/drivers/dma/ti/edma.c index 756a3c951dc7..03a7f647f7b2 100644 --- a/drivers/dma/ti/edma.c +++ b/drivers/dma/ti/edma.c @@ -2289,13 +2289,6 @@ static int edma_probe(struct platform_device *pdev) if (!info) return -ENODEV; - pm_runtime_enable(dev); - ret = pm_runtime_get_sync(dev); - if (ret < 0) { - dev_err(dev, "pm_runtime_get_sync() failed\n"); - return ret; - } - ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32)); if (ret) return ret; @@ -2326,27 +2319,33 @@ static int edma_probe(struct platform_device *pdev) platform_set_drvdata(pdev, ecc); + pm_runtime_enable(dev); + ret = pm_runtime_get_sync(dev); + if (ret < 0) { + dev_err(dev, "pm_runtime_get_sync() failed\n"); + pm_runtime_disable(dev); + return ret; + } + /* Get eDMA3 configuration from IP */ ret = edma_setup_from_hw(dev, info, ecc); if (ret) - return ret; + goto err_disable_pm; /* Allocate memory based on the information we got from the IP */ ecc->slave_chans = devm_kcalloc(dev, ecc->num_channels, sizeof(*ecc->slave_chans), GFP_KERNEL); - if (!ecc->slave_chans) - return -ENOMEM; ecc->slot_inuse = devm_kcalloc(dev, BITS_TO_LONGS(ecc->num_slots), sizeof(unsigned long), GFP_KERNEL); - if (!ecc->slot_inuse) - return -ENOMEM; ecc->channels_mask = devm_kcalloc(dev, BITS_TO_LONGS(ecc->num_channels), sizeof(unsigned long), GFP_KERNEL); - if (!ecc->channels_mask) - return -ENOMEM; + if (!ecc->slave_chans || !ecc->slot_inuse || !ecc->channels_mask) { + ret = -ENOMEM; + goto err_disable_pm; + } /* Mark all channels available initially */ bitmap_fill(ecc->channels_mask, ecc->num_channels); @@ -2388,7 +2387,7 @@ static int edma_probe(struct platform_device *pdev) ecc); if (ret) { dev_err(dev, "CCINT (%d) failed --> %d\n", irq, ret); - return ret; + goto err_disable_pm; } ecc->ccint = irq; } @@ -2404,7 +2403,7 @@ static int edma_probe(struct platform_device *pdev) ecc); if (ret) { dev_err(dev, "CCERRINT (%d) failed --> %d\n", irq, ret); - return ret; + goto err_disable_pm; } ecc->ccerrint = irq; } @@ -2412,7 +2411,8 @@ static int edma_probe(struct platform_device *pdev) ecc->dummy_slot = edma_alloc_slot(ecc, EDMA_SLOT_ANY); if (ecc->dummy_slot < 0) { dev_err(dev, "Can't allocate PaRAM dummy slot\n"); - return ecc->dummy_slot; + ret = ecc->dummy_slot; + goto err_disable_pm; } queue_priority_mapping = info->queue_priority_mapping; @@ -2512,6 +2512,9 @@ static int edma_probe(struct platform_device *pdev) err_reg1: edma_free_slot(ecc, ecc->dummy_slot); +err_disable_pm: + pm_runtime_put_sync(dev); + pm_runtime_disable(dev); return ret; } @@ -2542,6 +2545,8 @@ static int edma_remove(struct platform_device *pdev) if (ecc->dma_memcpy) dma_async_device_unregister(ecc->dma_memcpy); edma_free_slot(ecc, ecc->dummy_slot); + pm_runtime_put_sync(dev); + pm_runtime_disable(dev); return 0; } diff --git a/drivers/dma/ti/k3-psil-am654.c b/drivers/dma/ti/k3-psil-am654.c new file mode 100644 index 000000000000..a896a15908cf --- /dev/null +++ b/drivers/dma/ti/k3-psil-am654.c @@ -0,0 +1,175 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com + * Author: Peter Ujfalusi <peter.ujfalusi@ti.com> + */ + +#include <linux/kernel.h> + +#include "k3-psil-priv.h" + +#define PSIL_PDMA_XY_TR(x) \ + { \ + .thread_id = x, \ + .ep_config = { \ + .ep_type = PSIL_EP_PDMA_XY, \ + }, \ + } + +#define PSIL_PDMA_XY_PKT(x) \ + { \ + .thread_id = x, \ + .ep_config = { \ + .ep_type = PSIL_EP_PDMA_XY, \ + .pkt_mode = 1, \ + }, \ + } + +#define PSIL_ETHERNET(x) \ + { \ + .thread_id = x, \ + .ep_config = { \ + .ep_type = PSIL_EP_NATIVE, \ + .pkt_mode = 1, \ + .needs_epib = 1, \ + .psd_size = 16, \ + }, \ + } + +#define PSIL_SA2UL(x, tx) \ + { \ + .thread_id = x, \ + .ep_config = { \ + .ep_type = PSIL_EP_NATIVE, \ + .pkt_mode = 1, \ + .needs_epib = 1, \ + .psd_size = 64, \ + .notdpkt = tx, \ + }, \ + } + +/* PSI-L source thread IDs, used for RX (DMA_DEV_TO_MEM) */ +static struct psil_ep am654_src_ep_map[] = { + /* SA2UL */ + PSIL_SA2UL(0x4000, 0), + PSIL_SA2UL(0x4001, 0), + PSIL_SA2UL(0x4002, 0), + PSIL_SA2UL(0x4003, 0), + /* PRU_ICSSG0 */ + PSIL_ETHERNET(0x4100), + PSIL_ETHERNET(0x4101), + PSIL_ETHERNET(0x4102), + PSIL_ETHERNET(0x4103), + /* PRU_ICSSG1 */ + PSIL_ETHERNET(0x4200), + PSIL_ETHERNET(0x4201), + PSIL_ETHERNET(0x4202), + PSIL_ETHERNET(0x4203), + /* PRU_ICSSG2 */ + PSIL_ETHERNET(0x4300), + PSIL_ETHERNET(0x4301), + PSIL_ETHERNET(0x4302), + PSIL_ETHERNET(0x4303), + /* PDMA0 - McASPs */ + PSIL_PDMA_XY_TR(0x4400), + PSIL_PDMA_XY_TR(0x4401), + PSIL_PDMA_XY_TR(0x4402), + /* PDMA1 - SPI0-4 */ + PSIL_PDMA_XY_PKT(0x4500), + PSIL_PDMA_XY_PKT(0x4501), + PSIL_PDMA_XY_PKT(0x4502), + PSIL_PDMA_XY_PKT(0x4503), + PSIL_PDMA_XY_PKT(0x4504), + PSIL_PDMA_XY_PKT(0x4505), + PSIL_PDMA_XY_PKT(0x4506), + PSIL_PDMA_XY_PKT(0x4507), + PSIL_PDMA_XY_PKT(0x4508), + PSIL_PDMA_XY_PKT(0x4509), + PSIL_PDMA_XY_PKT(0x450a), + PSIL_PDMA_XY_PKT(0x450b), + PSIL_PDMA_XY_PKT(0x450c), + PSIL_PDMA_XY_PKT(0x450d), + PSIL_PDMA_XY_PKT(0x450e), + PSIL_PDMA_XY_PKT(0x450f), + PSIL_PDMA_XY_PKT(0x4510), + PSIL_PDMA_XY_PKT(0x4511), + PSIL_PDMA_XY_PKT(0x4512), + PSIL_PDMA_XY_PKT(0x4513), + /* PDMA1 - USART0-2 */ + PSIL_PDMA_XY_PKT(0x4514), + PSIL_PDMA_XY_PKT(0x4515), + PSIL_PDMA_XY_PKT(0x4516), + /* CPSW0 */ + PSIL_ETHERNET(0x7000), + /* MCU_PDMA0 - ADCs */ + PSIL_PDMA_XY_TR(0x7100), + PSIL_PDMA_XY_TR(0x7101), + PSIL_PDMA_XY_TR(0x7102), + PSIL_PDMA_XY_TR(0x7103), + /* MCU_PDMA1 - MCU_SPI0-2 */ + PSIL_PDMA_XY_PKT(0x7200), + PSIL_PDMA_XY_PKT(0x7201), + PSIL_PDMA_XY_PKT(0x7202), + PSIL_PDMA_XY_PKT(0x7203), + PSIL_PDMA_XY_PKT(0x7204), + PSIL_PDMA_XY_PKT(0x7205), + PSIL_PDMA_XY_PKT(0x7206), + PSIL_PDMA_XY_PKT(0x7207), + PSIL_PDMA_XY_PKT(0x7208), + PSIL_PDMA_XY_PKT(0x7209), + PSIL_PDMA_XY_PKT(0x720a), + PSIL_PDMA_XY_PKT(0x720b), + /* MCU_PDMA1 - MCU_USART0 */ + PSIL_PDMA_XY_PKT(0x7212), +}; + +/* PSI-L destination thread IDs, used for TX (DMA_MEM_TO_DEV) */ +static struct psil_ep am654_dst_ep_map[] = { + /* SA2UL */ + PSIL_SA2UL(0xc000, 1), + PSIL_SA2UL(0xc001, 1), + /* PRU_ICSSG0 */ + PSIL_ETHERNET(0xc100), + PSIL_ETHERNET(0xc101), + PSIL_ETHERNET(0xc102), + PSIL_ETHERNET(0xc103), + PSIL_ETHERNET(0xc104), + PSIL_ETHERNET(0xc105), + PSIL_ETHERNET(0xc106), + PSIL_ETHERNET(0xc107), + /* PRU_ICSSG1 */ + PSIL_ETHERNET(0xc200), + PSIL_ETHERNET(0xc201), + PSIL_ETHERNET(0xc202), + PSIL_ETHERNET(0xc203), + PSIL_ETHERNET(0xc204), + PSIL_ETHERNET(0xc205), + PSIL_ETHERNET(0xc206), + PSIL_ETHERNET(0xc207), + /* PRU_ICSSG2 */ + PSIL_ETHERNET(0xc300), + PSIL_ETHERNET(0xc301), + PSIL_ETHERNET(0xc302), + PSIL_ETHERNET(0xc303), + PSIL_ETHERNET(0xc304), + PSIL_ETHERNET(0xc305), + PSIL_ETHERNET(0xc306), + PSIL_ETHERNET(0xc307), + /* CPSW0 */ + PSIL_ETHERNET(0xf000), + PSIL_ETHERNET(0xf001), + PSIL_ETHERNET(0xf002), + PSIL_ETHERNET(0xf003), + PSIL_ETHERNET(0xf004), + PSIL_ETHERNET(0xf005), + PSIL_ETHERNET(0xf006), + PSIL_ETHERNET(0xf007), +}; + +struct psil_ep_map am654_ep_map = { + .name = "am654", + .src = am654_src_ep_map, + .src_count = ARRAY_SIZE(am654_src_ep_map), + .dst = am654_dst_ep_map, + .dst_count = ARRAY_SIZE(am654_dst_ep_map), +}; diff --git a/drivers/dma/ti/k3-psil-j721e.c b/drivers/dma/ti/k3-psil-j721e.c new file mode 100644 index 000000000000..e3cfd5f66842 --- /dev/null +++ b/drivers/dma/ti/k3-psil-j721e.c @@ -0,0 +1,222 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com + * Author: Peter Ujfalusi <peter.ujfalusi@ti.com> + */ + +#include <linux/kernel.h> + +#include "k3-psil-priv.h" + +#define PSIL_PDMA_XY_TR(x) \ + { \ + .thread_id = x, \ + .ep_config = { \ + .ep_type = PSIL_EP_PDMA_XY, \ + }, \ + } + +#define PSIL_PDMA_XY_PKT(x) \ + { \ + .thread_id = x, \ + .ep_config = { \ + .ep_type = PSIL_EP_PDMA_XY, \ + .pkt_mode = 1, \ + }, \ + } + +#define PSIL_PDMA_MCASP(x) \ + { \ + .thread_id = x, \ + .ep_config = { \ + .ep_type = PSIL_EP_PDMA_XY, \ + .pdma_acc32 = 1, \ + .pdma_burst = 1, \ + }, \ + } + +#define PSIL_ETHERNET(x) \ + { \ + .thread_id = x, \ + .ep_config = { \ + .ep_type = PSIL_EP_NATIVE, \ + .pkt_mode = 1, \ + .needs_epib = 1, \ + .psd_size = 16, \ + }, \ + } + +#define PSIL_SA2UL(x, tx) \ + { \ + .thread_id = x, \ + .ep_config = { \ + .ep_type = PSIL_EP_NATIVE, \ + .pkt_mode = 1, \ + .needs_epib = 1, \ + .psd_size = 64, \ + .notdpkt = tx, \ + }, \ + } + +/* PSI-L source thread IDs, used for RX (DMA_DEV_TO_MEM) */ +static struct psil_ep j721e_src_ep_map[] = { + /* SA2UL */ + PSIL_SA2UL(0x4000, 0), + PSIL_SA2UL(0x4001, 0), + PSIL_SA2UL(0x4002, 0), + PSIL_SA2UL(0x4003, 0), + /* PRU_ICSSG0 */ + PSIL_ETHERNET(0x4100), + PSIL_ETHERNET(0x4101), + PSIL_ETHERNET(0x4102), + PSIL_ETHERNET(0x4103), + /* PRU_ICSSG1 */ + PSIL_ETHERNET(0x4200), + PSIL_ETHERNET(0x4201), + PSIL_ETHERNET(0x4202), + PSIL_ETHERNET(0x4203), + /* PDMA6 (PSIL_PDMA_MCASP_G0) - McASP0-2 */ + PSIL_PDMA_MCASP(0x4400), + PSIL_PDMA_MCASP(0x4401), + PSIL_PDMA_MCASP(0x4402), + /* PDMA7 (PSIL_PDMA_MCASP_G1) - McASP3-11 */ + PSIL_PDMA_MCASP(0x4500), + PSIL_PDMA_MCASP(0x4501), + PSIL_PDMA_MCASP(0x4502), + PSIL_PDMA_MCASP(0x4503), + PSIL_PDMA_MCASP(0x4504), + PSIL_PDMA_MCASP(0x4505), + PSIL_PDMA_MCASP(0x4506), + PSIL_PDMA_MCASP(0x4507), + PSIL_PDMA_MCASP(0x4508), + /* PDMA8 (PDMA_MISC_G0) - SPI0-1 */ + PSIL_PDMA_XY_PKT(0x4600), + PSIL_PDMA_XY_PKT(0x4601), + PSIL_PDMA_XY_PKT(0x4602), + PSIL_PDMA_XY_PKT(0x4603), + PSIL_PDMA_XY_PKT(0x4604), + PSIL_PDMA_XY_PKT(0x4605), + PSIL_PDMA_XY_PKT(0x4606), + PSIL_PDMA_XY_PKT(0x4607), + /* PDMA9 (PDMA_MISC_G1) - SPI2-3 */ + PSIL_PDMA_XY_PKT(0x460c), + PSIL_PDMA_XY_PKT(0x460d), + PSIL_PDMA_XY_PKT(0x460e), + PSIL_PDMA_XY_PKT(0x460f), + PSIL_PDMA_XY_PKT(0x4610), + PSIL_PDMA_XY_PKT(0x4611), + PSIL_PDMA_XY_PKT(0x4612), + PSIL_PDMA_XY_PKT(0x4613), + /* PDMA10 (PDMA_MISC_G2) - SPI4-5 */ + PSIL_PDMA_XY_PKT(0x4618), + PSIL_PDMA_XY_PKT(0x4619), + PSIL_PDMA_XY_PKT(0x461a), + PSIL_PDMA_XY_PKT(0x461b), + PSIL_PDMA_XY_PKT(0x461c), + PSIL_PDMA_XY_PKT(0x461d), + PSIL_PDMA_XY_PKT(0x461e), + PSIL_PDMA_XY_PKT(0x461f), + /* PDMA11 (PDMA_MISC_G3) */ + PSIL_PDMA_XY_PKT(0x4624), + PSIL_PDMA_XY_PKT(0x4625), + PSIL_PDMA_XY_PKT(0x4626), + PSIL_PDMA_XY_PKT(0x4627), + PSIL_PDMA_XY_PKT(0x4628), + PSIL_PDMA_XY_PKT(0x4629), + PSIL_PDMA_XY_PKT(0x4630), + PSIL_PDMA_XY_PKT(0x463a), + /* PDMA13 (PDMA_USART_G0) - UART0-1 */ + PSIL_PDMA_XY_PKT(0x4700), + PSIL_PDMA_XY_PKT(0x4701), + /* PDMA14 (PDMA_USART_G1) - UART2-3 */ + PSIL_PDMA_XY_PKT(0x4702), + PSIL_PDMA_XY_PKT(0x4703), + /* PDMA15 (PDMA_USART_G2) - UART4-9 */ + PSIL_PDMA_XY_PKT(0x4704), + PSIL_PDMA_XY_PKT(0x4705), + PSIL_PDMA_XY_PKT(0x4706), + PSIL_PDMA_XY_PKT(0x4707), + PSIL_PDMA_XY_PKT(0x4708), + PSIL_PDMA_XY_PKT(0x4709), + /* CPSW9 */ + PSIL_ETHERNET(0x4a00), + /* CPSW0 */ + PSIL_ETHERNET(0x7000), + /* MCU_PDMA0 (MCU_PDMA_MISC_G0) - SPI0 */ + PSIL_PDMA_XY_PKT(0x7100), + PSIL_PDMA_XY_PKT(0x7101), + PSIL_PDMA_XY_PKT(0x7102), + PSIL_PDMA_XY_PKT(0x7103), + /* MCU_PDMA1 (MCU_PDMA_MISC_G1) - SPI1-2 */ + PSIL_PDMA_XY_PKT(0x7200), + PSIL_PDMA_XY_PKT(0x7201), + PSIL_PDMA_XY_PKT(0x7202), + PSIL_PDMA_XY_PKT(0x7203), + PSIL_PDMA_XY_PKT(0x7204), + PSIL_PDMA_XY_PKT(0x7205), + PSIL_PDMA_XY_PKT(0x7206), + PSIL_PDMA_XY_PKT(0x7207), + /* MCU_PDMA2 (MCU_PDMA_MISC_G2) - UART0 */ + PSIL_PDMA_XY_PKT(0x7300), + /* MCU_PDMA_ADC - ADC0-1 */ + PSIL_PDMA_XY_TR(0x7400), + PSIL_PDMA_XY_TR(0x7401), + PSIL_PDMA_XY_TR(0x7402), + PSIL_PDMA_XY_TR(0x7403), + /* SA2UL */ + PSIL_SA2UL(0x7500, 0), + PSIL_SA2UL(0x7501, 0), +}; + +/* PSI-L destination thread IDs, used for TX (DMA_MEM_TO_DEV) */ +static struct psil_ep j721e_dst_ep_map[] = { + /* SA2UL */ + PSIL_SA2UL(0xc000, 1), + PSIL_SA2UL(0xc001, 1), + /* PRU_ICSSG0 */ + PSIL_ETHERNET(0xc100), + PSIL_ETHERNET(0xc101), + PSIL_ETHERNET(0xc102), + PSIL_ETHERNET(0xc103), + PSIL_ETHERNET(0xc104), + PSIL_ETHERNET(0xc105), + PSIL_ETHERNET(0xc106), + PSIL_ETHERNET(0xc107), + /* PRU_ICSSG1 */ + PSIL_ETHERNET(0xc200), + PSIL_ETHERNET(0xc201), + PSIL_ETHERNET(0xc202), + PSIL_ETHERNET(0xc203), + PSIL_ETHERNET(0xc204), + PSIL_ETHERNET(0xc205), + PSIL_ETHERNET(0xc206), + PSIL_ETHERNET(0xc207), + /* CPSW9 */ + PSIL_ETHERNET(0xca00), + PSIL_ETHERNET(0xca01), + PSIL_ETHERNET(0xca02), + PSIL_ETHERNET(0xca03), + PSIL_ETHERNET(0xca04), + PSIL_ETHERNET(0xca05), + PSIL_ETHERNET(0xca06), + PSIL_ETHERNET(0xca07), + /* CPSW0 */ + PSIL_ETHERNET(0xf000), + PSIL_ETHERNET(0xf001), + PSIL_ETHERNET(0xf002), + PSIL_ETHERNET(0xf003), + PSIL_ETHERNET(0xf004), + PSIL_ETHERNET(0xf005), + PSIL_ETHERNET(0xf006), + PSIL_ETHERNET(0xf007), + /* SA2UL */ + PSIL_SA2UL(0xf500, 1), +}; + +struct psil_ep_map j721e_ep_map = { + .name = "j721e", + .src = j721e_src_ep_map, + .src_count = ARRAY_SIZE(j721e_src_ep_map), + .dst = j721e_dst_ep_map, + .dst_count = ARRAY_SIZE(j721e_dst_ep_map), +}; diff --git a/drivers/dma/ti/k3-psil-priv.h b/drivers/dma/ti/k3-psil-priv.h new file mode 100644 index 000000000000..a1f389ca371e --- /dev/null +++ b/drivers/dma/ti/k3-psil-priv.h @@ -0,0 +1,43 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com + */ + +#ifndef K3_PSIL_PRIV_H_ +#define K3_PSIL_PRIV_H_ + +#include <linux/dma/k3-psil.h> + +struct psil_ep { + u32 thread_id; + struct psil_endpoint_config ep_config; +}; + +/** + * struct psil_ep_map - PSI-L thread ID configuration maps + * @name: Name of the map, set it to the name of the SoC + * @src: Array of source PSI-L thread configurations + * @src_count: Number of entries in the src array + * @dst: Array of destination PSI-L thread configurations + * @dst_count: Number of entries in the dst array + * + * In case of symmetric configuration for a matching src/dst thread (for example + * 0x4400 and 0xc400) only the src configuration can be present. If no dst + * configuration found the code will look for (dst_thread_id & ~0x8000) to find + * the symmetric match. + */ +struct psil_ep_map { + char *name; + struct psil_ep *src; + int src_count; + struct psil_ep *dst; + int dst_count; +}; + +struct psil_endpoint_config *psil_get_ep_config(u32 thread_id); + +/* SoC PSI-L endpoint maps */ +extern struct psil_ep_map am654_ep_map; +extern struct psil_ep_map j721e_ep_map; + +#endif /* K3_PSIL_PRIV_H_ */ diff --git a/drivers/dma/ti/k3-psil.c b/drivers/dma/ti/k3-psil.c new file mode 100644 index 000000000000..d7b965049ccb --- /dev/null +++ b/drivers/dma/ti/k3-psil.c @@ -0,0 +1,90 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com + * Author: Peter Ujfalusi <peter.ujfalusi@ti.com> + */ + +#include <linux/kernel.h> +#include <linux/device.h> +#include <linux/init.h> +#include <linux/mutex.h> +#include <linux/of.h> + +#include "k3-psil-priv.h" + +static DEFINE_MUTEX(ep_map_mutex); +static struct psil_ep_map *soc_ep_map; + +struct psil_endpoint_config *psil_get_ep_config(u32 thread_id) +{ + int i; + + mutex_lock(&ep_map_mutex); + if (!soc_ep_map) { + if (of_machine_is_compatible("ti,am654")) { + soc_ep_map = &am654_ep_map; + } else if (of_machine_is_compatible("ti,j721e")) { + soc_ep_map = &j721e_ep_map; + } else { + pr_err("PSIL: No compatible machine found for map\n"); + return ERR_PTR(-ENOTSUPP); + } + pr_debug("%s: Using map for %s\n", __func__, soc_ep_map->name); + } + mutex_unlock(&ep_map_mutex); + + if (thread_id & K3_PSIL_DST_THREAD_ID_OFFSET && soc_ep_map->dst) { + /* check in destination thread map */ + for (i = 0; i < soc_ep_map->dst_count; i++) { + if (soc_ep_map->dst[i].thread_id == thread_id) + return &soc_ep_map->dst[i].ep_config; + } + } + + thread_id &= ~K3_PSIL_DST_THREAD_ID_OFFSET; + if (soc_ep_map->src) { + for (i = 0; i < soc_ep_map->src_count; i++) { + if (soc_ep_map->src[i].thread_id == thread_id) + return &soc_ep_map->src[i].ep_config; + } + } + + return ERR_PTR(-ENOENT); +} +EXPORT_SYMBOL_GPL(psil_get_ep_config); + +int psil_set_new_ep_config(struct device *dev, const char *name, + struct psil_endpoint_config *ep_config) +{ + struct psil_endpoint_config *dst_ep_config; + struct of_phandle_args dma_spec; + u32 thread_id; + int index; + + if (!dev || !dev->of_node) + return -EINVAL; + + index = of_property_match_string(dev->of_node, "dma-names", name); + if (index < 0) + return index; + + if (of_parse_phandle_with_args(dev->of_node, "dmas", "#dma-cells", + index, &dma_spec)) + return -ENOENT; + + thread_id = dma_spec.args[0]; + + dst_ep_config = psil_get_ep_config(thread_id); + if (IS_ERR(dst_ep_config)) { + pr_err("PSIL: thread ID 0x%04x not defined in map\n", + thread_id); + of_node_put(dma_spec.np); + return PTR_ERR(dst_ep_config); + } + + memcpy(dst_ep_config, ep_config, sizeof(*dst_ep_config)); + + of_node_put(dma_spec.np); + return 0; +} +EXPORT_SYMBOL_GPL(psil_set_new_ep_config); diff --git a/drivers/dma/ti/k3-udma-glue.c b/drivers/dma/ti/k3-udma-glue.c new file mode 100644 index 000000000000..4d7561a1b3e3 --- /dev/null +++ b/drivers/dma/ti/k3-udma-glue.c @@ -0,0 +1,1207 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * K3 NAVSS DMA glue interface + * + * Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com + * + */ + +#include <linux/atomic.h> +#include <linux/delay.h> +#include <linux/dma-mapping.h> +#include <linux/io.h> +#include <linux/init.h> +#include <linux/of.h> +#include <linux/platform_device.h> +#include <linux/soc/ti/k3-ringacc.h> +#include <linux/dma/ti-cppi5.h> +#include <linux/dma/k3-udma-glue.h> + +#include "k3-udma.h" +#include "k3-psil-priv.h" + +struct k3_udma_glue_common { + struct device *dev; + struct udma_dev *udmax; + const struct udma_tisci_rm *tisci_rm; + struct k3_ringacc *ringacc; + u32 src_thread; + u32 dst_thread; + + u32 hdesc_size; + bool epib; + u32 psdata_size; + u32 swdata_size; +}; + +struct k3_udma_glue_tx_channel { + struct k3_udma_glue_common common; + + struct udma_tchan *udma_tchanx; + int udma_tchan_id; + + struct k3_ring *ringtx; + struct k3_ring *ringtxcq; + + bool psil_paired; + + int virq; + + atomic_t free_pkts; + bool tx_pause_on_err; + bool tx_filt_einfo; + bool tx_filt_pswords; + bool tx_supr_tdpkt; +}; + +struct k3_udma_glue_rx_flow { + struct udma_rflow *udma_rflow; + int udma_rflow_id; + struct k3_ring *ringrx; + struct k3_ring *ringrxfdq; + + int virq; +}; + +struct k3_udma_glue_rx_channel { + struct k3_udma_glue_common common; + + struct udma_rchan *udma_rchanx; + int udma_rchan_id; + bool remote; + + bool psil_paired; + + u32 swdata_size; + int flow_id_base; + + struct k3_udma_glue_rx_flow *flows; + u32 flow_num; + u32 flows_ready; +}; + +#define K3_UDMAX_TDOWN_TIMEOUT_US 1000 + +static int of_k3_udma_glue_parse(struct device_node *udmax_np, + struct k3_udma_glue_common *common) +{ + common->ringacc = of_k3_ringacc_get_by_phandle(udmax_np, + "ti,ringacc"); + if (IS_ERR(common->ringacc)) + return PTR_ERR(common->ringacc); + + common->udmax = of_xudma_dev_get(udmax_np, NULL); + if (IS_ERR(common->udmax)) + return PTR_ERR(common->udmax); + + common->tisci_rm = xudma_dev_get_tisci_rm(common->udmax); + + return 0; +} + +static int of_k3_udma_glue_parse_chn(struct device_node *chn_np, + const char *name, struct k3_udma_glue_common *common, + bool tx_chn) +{ + struct psil_endpoint_config *ep_config; + struct of_phandle_args dma_spec; + u32 thread_id; + int ret = 0; + int index; + + if (unlikely(!name)) + return -EINVAL; + + index = of_property_match_string(chn_np, "dma-names", name); + if (index < 0) + return index; + + if (of_parse_phandle_with_args(chn_np, "dmas", "#dma-cells", index, + &dma_spec)) + return -ENOENT; + + thread_id = dma_spec.args[0]; + + if (tx_chn && !(thread_id & K3_PSIL_DST_THREAD_ID_OFFSET)) { + ret = -EINVAL; + goto out_put_spec; + } + + if (!tx_chn && (thread_id & K3_PSIL_DST_THREAD_ID_OFFSET)) { + ret = -EINVAL; + goto out_put_spec; + } + + /* get psil endpoint config */ + ep_config = psil_get_ep_config(thread_id); + if (IS_ERR(ep_config)) { + dev_err(common->dev, + "No configuration for psi-l thread 0x%04x\n", + thread_id); + ret = PTR_ERR(ep_config); + goto out_put_spec; + } + + common->epib = ep_config->needs_epib; + common->psdata_size = ep_config->psd_size; + + if (tx_chn) + common->dst_thread = thread_id; + else + common->src_thread = thread_id; + + ret = of_k3_udma_glue_parse(dma_spec.np, common); + +out_put_spec: + of_node_put(dma_spec.np); + return ret; +}; + +static void k3_udma_glue_dump_tx_chn(struct k3_udma_glue_tx_channel *tx_chn) +{ + struct device *dev = tx_chn->common.dev; + + dev_dbg(dev, "dump_tx_chn:\n" + "udma_tchan_id: %d\n" + "src_thread: %08x\n" + "dst_thread: %08x\n", + tx_chn->udma_tchan_id, + tx_chn->common.src_thread, + tx_chn->common.dst_thread); +} + +static void k3_udma_glue_dump_tx_rt_chn(struct k3_udma_glue_tx_channel *chn, + char *mark) +{ + struct device *dev = chn->common.dev; + + dev_dbg(dev, "=== dump ===> %s\n", mark); + dev_dbg(dev, "0x%08X: %08X\n", UDMA_TCHAN_RT_CTL_REG, + xudma_tchanrt_read(chn->udma_tchanx, UDMA_TCHAN_RT_CTL_REG)); + dev_dbg(dev, "0x%08X: %08X\n", UDMA_TCHAN_RT_PEER_RT_EN_REG, + xudma_tchanrt_read(chn->udma_tchanx, + UDMA_TCHAN_RT_PEER_RT_EN_REG)); + dev_dbg(dev, "0x%08X: %08X\n", UDMA_TCHAN_RT_PCNT_REG, + xudma_tchanrt_read(chn->udma_tchanx, UDMA_TCHAN_RT_PCNT_REG)); + dev_dbg(dev, "0x%08X: %08X\n", UDMA_TCHAN_RT_BCNT_REG, + xudma_tchanrt_read(chn->udma_tchanx, UDMA_TCHAN_RT_BCNT_REG)); + dev_dbg(dev, "0x%08X: %08X\n", UDMA_TCHAN_RT_SBCNT_REG, + xudma_tchanrt_read(chn->udma_tchanx, UDMA_TCHAN_RT_SBCNT_REG)); +} + +static int k3_udma_glue_cfg_tx_chn(struct k3_udma_glue_tx_channel *tx_chn) +{ + const struct udma_tisci_rm *tisci_rm = tx_chn->common.tisci_rm; + struct ti_sci_msg_rm_udmap_tx_ch_cfg req; + + memset(&req, 0, sizeof(req)); + + req.valid_params = TI_SCI_MSG_VALUE_RM_UDMAP_CH_PAUSE_ON_ERR_VALID | + TI_SCI_MSG_VALUE_RM_UDMAP_CH_TX_FILT_EINFO_VALID | + TI_SCI_MSG_VALUE_RM_UDMAP_CH_TX_FILT_PSWORDS_VALID | + TI_SCI_MSG_VALUE_RM_UDMAP_CH_CHAN_TYPE_VALID | + TI_SCI_MSG_VALUE_RM_UDMAP_CH_TX_SUPR_TDPKT_VALID | + TI_SCI_MSG_VALUE_RM_UDMAP_CH_FETCH_SIZE_VALID | + TI_SCI_MSG_VALUE_RM_UDMAP_CH_CQ_QNUM_VALID; + req.nav_id = tisci_rm->tisci_dev_id; + req.index = tx_chn->udma_tchan_id; + if (tx_chn->tx_pause_on_err) + req.tx_pause_on_err = 1; + if (tx_chn->tx_filt_einfo) + req.tx_filt_einfo = 1; + if (tx_chn->tx_filt_pswords) + req.tx_filt_pswords = 1; + req.tx_chan_type = TI_SCI_RM_UDMAP_CHAN_TYPE_PKT_PBRR; + if (tx_chn->tx_supr_tdpkt) + req.tx_supr_tdpkt = 1; + req.tx_fetch_size = tx_chn->common.hdesc_size >> 2; + req.txcq_qnum = k3_ringacc_get_ring_id(tx_chn->ringtxcq); + + return tisci_rm->tisci_udmap_ops->tx_ch_cfg(tisci_rm->tisci, &req); +} + +struct k3_udma_glue_tx_channel *k3_udma_glue_request_tx_chn(struct device *dev, + const char *name, struct k3_udma_glue_tx_channel_cfg *cfg) +{ + struct k3_udma_glue_tx_channel *tx_chn; + int ret; + + tx_chn = devm_kzalloc(dev, sizeof(*tx_chn), GFP_KERNEL); + if (!tx_chn) + return ERR_PTR(-ENOMEM); + + tx_chn->common.dev = dev; + tx_chn->common.swdata_size = cfg->swdata_size; + tx_chn->tx_pause_on_err = cfg->tx_pause_on_err; + tx_chn->tx_filt_einfo = cfg->tx_filt_einfo; + tx_chn->tx_filt_pswords = cfg->tx_filt_pswords; + tx_chn->tx_supr_tdpkt = cfg->tx_supr_tdpkt; + + /* parse of udmap channel */ + ret = of_k3_udma_glue_parse_chn(dev->of_node, name, + &tx_chn->common, true); + if (ret) + goto err; + + tx_chn->common.hdesc_size = cppi5_hdesc_calc_size(tx_chn->common.epib, + tx_chn->common.psdata_size, + tx_chn->common.swdata_size); + + /* request and cfg UDMAP TX channel */ + tx_chn->udma_tchanx = xudma_tchan_get(tx_chn->common.udmax, -1); + if (IS_ERR(tx_chn->udma_tchanx)) { + ret = PTR_ERR(tx_chn->udma_tchanx); + dev_err(dev, "UDMAX tchanx get err %d\n", ret); + goto err; + } + tx_chn->udma_tchan_id = xudma_tchan_get_id(tx_chn->udma_tchanx); + + atomic_set(&tx_chn->free_pkts, cfg->txcq_cfg.size); + + /* request and cfg rings */ + tx_chn->ringtx = k3_ringacc_request_ring(tx_chn->common.ringacc, + tx_chn->udma_tchan_id, 0); + if (!tx_chn->ringtx) { + ret = -ENODEV; + dev_err(dev, "Failed to get TX ring %u\n", + tx_chn->udma_tchan_id); + goto err; + } + + tx_chn->ringtxcq = k3_ringacc_request_ring(tx_chn->common.ringacc, + -1, 0); + if (!tx_chn->ringtxcq) { + ret = -ENODEV; + dev_err(dev, "Failed to get TXCQ ring\n"); + goto err; + } + + ret = k3_ringacc_ring_cfg(tx_chn->ringtx, &cfg->tx_cfg); + if (ret) { + dev_err(dev, "Failed to cfg ringtx %d\n", ret); + goto err; + } + + ret = k3_ringacc_ring_cfg(tx_chn->ringtxcq, &cfg->txcq_cfg); + if (ret) { + dev_err(dev, "Failed to cfg ringtx %d\n", ret); + goto err; + } + + /* request and cfg psi-l */ + tx_chn->common.src_thread = + xudma_dev_get_psil_base(tx_chn->common.udmax) + + tx_chn->udma_tchan_id; + + ret = k3_udma_glue_cfg_tx_chn(tx_chn); + if (ret) { + dev_err(dev, "Failed to cfg tchan %d\n", ret); + goto err; + } + + ret = xudma_navss_psil_pair(tx_chn->common.udmax, + tx_chn->common.src_thread, + tx_chn->common.dst_thread); + if (ret) { + dev_err(dev, "PSI-L request err %d\n", ret); + goto err; + } + + tx_chn->psil_paired = true; + + /* reset TX RT registers */ + k3_udma_glue_disable_tx_chn(tx_chn); + + k3_udma_glue_dump_tx_chn(tx_chn); + + return tx_chn; + +err: + k3_udma_glue_release_tx_chn(tx_chn); + return ERR_PTR(ret); +} +EXPORT_SYMBOL_GPL(k3_udma_glue_request_tx_chn); + +void k3_udma_glue_release_tx_chn(struct k3_udma_glue_tx_channel *tx_chn) +{ + if (tx_chn->psil_paired) { + xudma_navss_psil_unpair(tx_chn->common.udmax, + tx_chn->common.src_thread, + tx_chn->common.dst_thread); + tx_chn->psil_paired = false; + } + + if (!IS_ERR_OR_NULL(tx_chn->udma_tchanx)) + xudma_tchan_put(tx_chn->common.udmax, + tx_chn->udma_tchanx); + + if (tx_chn->ringtxcq) + k3_ringacc_ring_free(tx_chn->ringtxcq); + + if (tx_chn->ringtx) + k3_ringacc_ring_free(tx_chn->ringtx); +} +EXPORT_SYMBOL_GPL(k3_udma_glue_release_tx_chn); + +int k3_udma_glue_push_tx_chn(struct k3_udma_glue_tx_channel *tx_chn, + struct cppi5_host_desc_t *desc_tx, + dma_addr_t desc_dma) +{ + u32 ringtxcq_id; + + if (!atomic_add_unless(&tx_chn->free_pkts, -1, 0)) + return -ENOMEM; + + ringtxcq_id = k3_ringacc_get_ring_id(tx_chn->ringtxcq); + cppi5_desc_set_retpolicy(&desc_tx->hdr, 0, ringtxcq_id); + + return k3_ringacc_ring_push(tx_chn->ringtx, &desc_dma); +} +EXPORT_SYMBOL_GPL(k3_udma_glue_push_tx_chn); + +int k3_udma_glue_pop_tx_chn(struct k3_udma_glue_tx_channel *tx_chn, + dma_addr_t *desc_dma) +{ + int ret; + + ret = k3_ringacc_ring_pop(tx_chn->ringtxcq, desc_dma); + if (!ret) + atomic_inc(&tx_chn->free_pkts); + + return ret; +} +EXPORT_SYMBOL_GPL(k3_udma_glue_pop_tx_chn); + +int k3_udma_glue_enable_tx_chn(struct k3_udma_glue_tx_channel *tx_chn) +{ + u32 txrt_ctl; + + txrt_ctl = UDMA_PEER_RT_EN_ENABLE; + xudma_tchanrt_write(tx_chn->udma_tchanx, + UDMA_TCHAN_RT_PEER_RT_EN_REG, + txrt_ctl); + + txrt_ctl = xudma_tchanrt_read(tx_chn->udma_tchanx, + UDMA_TCHAN_RT_CTL_REG); + txrt_ctl |= UDMA_CHAN_RT_CTL_EN; + xudma_tchanrt_write(tx_chn->udma_tchanx, UDMA_TCHAN_RT_CTL_REG, + txrt_ctl); + + k3_udma_glue_dump_tx_rt_chn(tx_chn, "txchn en"); + return 0; +} +EXPORT_SYMBOL_GPL(k3_udma_glue_enable_tx_chn); + +void k3_udma_glue_disable_tx_chn(struct k3_udma_glue_tx_channel *tx_chn) +{ + k3_udma_glue_dump_tx_rt_chn(tx_chn, "txchn dis1"); + + xudma_tchanrt_write(tx_chn->udma_tchanx, UDMA_TCHAN_RT_CTL_REG, 0); + + xudma_tchanrt_write(tx_chn->udma_tchanx, + UDMA_TCHAN_RT_PEER_RT_EN_REG, 0); + k3_udma_glue_dump_tx_rt_chn(tx_chn, "txchn dis2"); +} +EXPORT_SYMBOL_GPL(k3_udma_glue_disable_tx_chn); + +void k3_udma_glue_tdown_tx_chn(struct k3_udma_glue_tx_channel *tx_chn, + bool sync) +{ + int i = 0; + u32 val; + + k3_udma_glue_dump_tx_rt_chn(tx_chn, "txchn tdown1"); + + xudma_tchanrt_write(tx_chn->udma_tchanx, UDMA_TCHAN_RT_CTL_REG, + UDMA_CHAN_RT_CTL_EN | UDMA_CHAN_RT_CTL_TDOWN); + + val = xudma_tchanrt_read(tx_chn->udma_tchanx, UDMA_TCHAN_RT_CTL_REG); + + while (sync && (val & UDMA_CHAN_RT_CTL_EN)) { + val = xudma_tchanrt_read(tx_chn->udma_tchanx, + UDMA_TCHAN_RT_CTL_REG); + udelay(1); + if (i > K3_UDMAX_TDOWN_TIMEOUT_US) { + dev_err(tx_chn->common.dev, "TX tdown timeout\n"); + break; + } + i++; + } + + val = xudma_tchanrt_read(tx_chn->udma_tchanx, + UDMA_TCHAN_RT_PEER_RT_EN_REG); + if (sync && (val & UDMA_PEER_RT_EN_ENABLE)) + dev_err(tx_chn->common.dev, "TX tdown peer not stopped\n"); + k3_udma_glue_dump_tx_rt_chn(tx_chn, "txchn tdown2"); +} +EXPORT_SYMBOL_GPL(k3_udma_glue_tdown_tx_chn); + +void k3_udma_glue_reset_tx_chn(struct k3_udma_glue_tx_channel *tx_chn, + void *data, + void (*cleanup)(void *data, dma_addr_t desc_dma)) +{ + dma_addr_t desc_dma; + int occ_tx, i, ret; + + /* reset TXCQ as it is not input for udma - expected to be empty */ + if (tx_chn->ringtxcq) + k3_ringacc_ring_reset(tx_chn->ringtxcq); + + /* + * TXQ reset need to be special way as it is input for udma and its + * state cached by udma, so: + * 1) save TXQ occ + * 2) clean up TXQ and call callback .cleanup() for each desc + * 3) reset TXQ in a special way + */ + occ_tx = k3_ringacc_ring_get_occ(tx_chn->ringtx); + dev_dbg(tx_chn->common.dev, "TX reset occ_tx %u\n", occ_tx); + + for (i = 0; i < occ_tx; i++) { + ret = k3_ringacc_ring_pop(tx_chn->ringtx, &desc_dma); + if (ret) { + dev_err(tx_chn->common.dev, "TX reset pop %d\n", ret); + break; + } + cleanup(data, desc_dma); + } + + k3_ringacc_ring_reset_dma(tx_chn->ringtx, occ_tx); +} +EXPORT_SYMBOL_GPL(k3_udma_glue_reset_tx_chn); + +u32 k3_udma_glue_tx_get_hdesc_size(struct k3_udma_glue_tx_channel *tx_chn) +{ + return tx_chn->common.hdesc_size; +} +EXPORT_SYMBOL_GPL(k3_udma_glue_tx_get_hdesc_size); + +u32 k3_udma_glue_tx_get_txcq_id(struct k3_udma_glue_tx_channel *tx_chn) +{ + return k3_ringacc_get_ring_id(tx_chn->ringtxcq); +} +EXPORT_SYMBOL_GPL(k3_udma_glue_tx_get_txcq_id); + +int k3_udma_glue_tx_get_irq(struct k3_udma_glue_tx_channel *tx_chn) +{ + tx_chn->virq = k3_ringacc_get_ring_irq_num(tx_chn->ringtxcq); + + return tx_chn->virq; +} +EXPORT_SYMBOL_GPL(k3_udma_glue_tx_get_irq); + +static int k3_udma_glue_cfg_rx_chn(struct k3_udma_glue_rx_channel *rx_chn) +{ + const struct udma_tisci_rm *tisci_rm = rx_chn->common.tisci_rm; + struct ti_sci_msg_rm_udmap_rx_ch_cfg req; + int ret; + + memset(&req, 0, sizeof(req)); + + req.valid_params = TI_SCI_MSG_VALUE_RM_UDMAP_CH_FETCH_SIZE_VALID | + TI_SCI_MSG_VALUE_RM_UDMAP_CH_CQ_QNUM_VALID | + TI_SCI_MSG_VALUE_RM_UDMAP_CH_CHAN_TYPE_VALID | + TI_SCI_MSG_VALUE_RM_UDMAP_CH_RX_FLOWID_START_VALID | + TI_SCI_MSG_VALUE_RM_UDMAP_CH_RX_FLOWID_CNT_VALID; + + req.nav_id = tisci_rm->tisci_dev_id; + req.index = rx_chn->udma_rchan_id; + req.rx_fetch_size = rx_chn->common.hdesc_size >> 2; + /* + * TODO: we can't support rxcq_qnum/RCHAN[a]_RCQ cfg with current sysfw + * and udmax impl, so just configure it to invalid value. + * req.rxcq_qnum = k3_ringacc_get_ring_id(rx_chn->flows[0].ringrx); + */ + req.rxcq_qnum = 0xFFFF; + if (rx_chn->flow_num && rx_chn->flow_id_base != rx_chn->udma_rchan_id) { + /* Default flow + extra ones */ + req.flowid_start = rx_chn->flow_id_base; + req.flowid_cnt = rx_chn->flow_num; + } + req.rx_chan_type = TI_SCI_RM_UDMAP_CHAN_TYPE_PKT_PBRR; + + ret = tisci_rm->tisci_udmap_ops->rx_ch_cfg(tisci_rm->tisci, &req); + if (ret) + dev_err(rx_chn->common.dev, "rchan%d cfg failed %d\n", + rx_chn->udma_rchan_id, ret); + + return ret; +} + +static void k3_udma_glue_release_rx_flow(struct k3_udma_glue_rx_channel *rx_chn, + u32 flow_num) +{ + struct k3_udma_glue_rx_flow *flow = &rx_chn->flows[flow_num]; + + if (IS_ERR_OR_NULL(flow->udma_rflow)) + return; + + if (flow->ringrxfdq) + k3_ringacc_ring_free(flow->ringrxfdq); + + if (flow->ringrx) + k3_ringacc_ring_free(flow->ringrx); + + xudma_rflow_put(rx_chn->common.udmax, flow->udma_rflow); + flow->udma_rflow = NULL; + rx_chn->flows_ready--; +} + +static int k3_udma_glue_cfg_rx_flow(struct k3_udma_glue_rx_channel *rx_chn, + u32 flow_idx, + struct k3_udma_glue_rx_flow_cfg *flow_cfg) +{ + struct k3_udma_glue_rx_flow *flow = &rx_chn->flows[flow_idx]; + const struct udma_tisci_rm *tisci_rm = rx_chn->common.tisci_rm; + struct device *dev = rx_chn->common.dev; + struct ti_sci_msg_rm_udmap_flow_cfg req; + int rx_ring_id; + int rx_ringfdq_id; + int ret = 0; + + flow->udma_rflow = xudma_rflow_get(rx_chn->common.udmax, + flow->udma_rflow_id); + if (IS_ERR(flow->udma_rflow)) { + ret = PTR_ERR(flow->udma_rflow); + dev_err(dev, "UDMAX rflow get err %d\n", ret); + return ret; + } + + if (flow->udma_rflow_id != xudma_rflow_get_id(flow->udma_rflow)) { + ret = -ENODEV; + goto err_rflow_put; + } + + /* request and cfg rings */ + flow->ringrx = k3_ringacc_request_ring(rx_chn->common.ringacc, + flow_cfg->ring_rxq_id, 0); + if (!flow->ringrx) { + ret = -ENODEV; + dev_err(dev, "Failed to get RX ring\n"); + goto err_rflow_put; + } + + flow->ringrxfdq = k3_ringacc_request_ring(rx_chn->common.ringacc, + flow_cfg->ring_rxfdq0_id, 0); + if (!flow->ringrxfdq) { + ret = -ENODEV; + dev_err(dev, "Failed to get RXFDQ ring\n"); + goto err_ringrx_free; + } + + ret = k3_ringacc_ring_cfg(flow->ringrx, &flow_cfg->rx_cfg); + if (ret) { + dev_err(dev, "Failed to cfg ringrx %d\n", ret); + goto err_ringrxfdq_free; + } + + ret = k3_ringacc_ring_cfg(flow->ringrxfdq, &flow_cfg->rxfdq_cfg); + if (ret) { + dev_err(dev, "Failed to cfg ringrxfdq %d\n", ret); + goto err_ringrxfdq_free; + } + + if (rx_chn->remote) { + rx_ring_id = TI_SCI_RESOURCE_NULL; + rx_ringfdq_id = TI_SCI_RESOURCE_NULL; + } else { + rx_ring_id = k3_ringacc_get_ring_id(flow->ringrx); + rx_ringfdq_id = k3_ringacc_get_ring_id(flow->ringrxfdq); + } + + memset(&req, 0, sizeof(req)); + + req.valid_params = + TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_EINFO_PRESENT_VALID | + TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_PSINFO_PRESENT_VALID | + TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_ERROR_HANDLING_VALID | + TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_DESC_TYPE_VALID | + TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_DEST_QNUM_VALID | + TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_SRC_TAG_HI_SEL_VALID | + TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_SRC_TAG_LO_SEL_VALID | + TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_DEST_TAG_HI_SEL_VALID | + TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_DEST_TAG_LO_SEL_VALID | + TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_FDQ0_SZ0_QNUM_VALID | + TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_FDQ1_QNUM_VALID | + TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_FDQ2_QNUM_VALID | + TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_FDQ3_QNUM_VALID; + req.nav_id = tisci_rm->tisci_dev_id; + req.flow_index = flow->udma_rflow_id; + if (rx_chn->common.epib) + req.rx_einfo_present = 1; + if (rx_chn->common.psdata_size) + req.rx_psinfo_present = 1; + if (flow_cfg->rx_error_handling) + req.rx_error_handling = 1; + req.rx_desc_type = 0; + req.rx_dest_qnum = rx_ring_id; + req.rx_src_tag_hi_sel = 0; + req.rx_src_tag_lo_sel = flow_cfg->src_tag_lo_sel; + req.rx_dest_tag_hi_sel = 0; + req.rx_dest_tag_lo_sel = 0; + req.rx_fdq0_sz0_qnum = rx_ringfdq_id; + req.rx_fdq1_qnum = rx_ringfdq_id; + req.rx_fdq2_qnum = rx_ringfdq_id; + req.rx_fdq3_qnum = rx_ringfdq_id; + + ret = tisci_rm->tisci_udmap_ops->rx_flow_cfg(tisci_rm->tisci, &req); + if (ret) { + dev_err(dev, "flow%d config failed: %d\n", flow->udma_rflow_id, + ret); + goto err_ringrxfdq_free; + } + + rx_chn->flows_ready++; + dev_dbg(dev, "flow%d config done. ready:%d\n", + flow->udma_rflow_id, rx_chn->flows_ready); + + return 0; + +err_ringrxfdq_free: + k3_ringacc_ring_free(flow->ringrxfdq); + +err_ringrx_free: + k3_ringacc_ring_free(flow->ringrx); + +err_rflow_put: + xudma_rflow_put(rx_chn->common.udmax, flow->udma_rflow); + flow->udma_rflow = NULL; + + return ret; +} + +static void k3_udma_glue_dump_rx_chn(struct k3_udma_glue_rx_channel *chn) +{ + struct device *dev = chn->common.dev; + + dev_dbg(dev, "dump_rx_chn:\n" + "udma_rchan_id: %d\n" + "src_thread: %08x\n" + "dst_thread: %08x\n" + "epib: %d\n" + "hdesc_size: %u\n" + "psdata_size: %u\n" + "swdata_size: %u\n" + "flow_id_base: %d\n" + "flow_num: %d\n", + chn->udma_rchan_id, + chn->common.src_thread, + chn->common.dst_thread, + chn->common.epib, + chn->common.hdesc_size, + chn->common.psdata_size, + chn->common.swdata_size, + chn->flow_id_base, + chn->flow_num); +} + +static void k3_udma_glue_dump_rx_rt_chn(struct k3_udma_glue_rx_channel *chn, + char *mark) +{ + struct device *dev = chn->common.dev; + + dev_dbg(dev, "=== dump ===> %s\n", mark); + + dev_dbg(dev, "0x%08X: %08X\n", UDMA_RCHAN_RT_CTL_REG, + xudma_rchanrt_read(chn->udma_rchanx, UDMA_RCHAN_RT_CTL_REG)); + dev_dbg(dev, "0x%08X: %08X\n", UDMA_RCHAN_RT_PEER_RT_EN_REG, + xudma_rchanrt_read(chn->udma_rchanx, + UDMA_RCHAN_RT_PEER_RT_EN_REG)); + dev_dbg(dev, "0x%08X: %08X\n", UDMA_RCHAN_RT_PCNT_REG, + xudma_rchanrt_read(chn->udma_rchanx, UDMA_RCHAN_RT_PCNT_REG)); + dev_dbg(dev, "0x%08X: %08X\n", UDMA_RCHAN_RT_BCNT_REG, + xudma_rchanrt_read(chn->udma_rchanx, UDMA_RCHAN_RT_BCNT_REG)); + dev_dbg(dev, "0x%08X: %08X\n", UDMA_RCHAN_RT_SBCNT_REG, + xudma_rchanrt_read(chn->udma_rchanx, UDMA_RCHAN_RT_SBCNT_REG)); +} + +static int +k3_udma_glue_allocate_rx_flows(struct k3_udma_glue_rx_channel *rx_chn, + struct k3_udma_glue_rx_channel_cfg *cfg) +{ + int ret; + + /* default rflow */ + if (cfg->flow_id_use_rxchan_id) + return 0; + + /* not a GP rflows */ + if (rx_chn->flow_id_base != -1 && + !xudma_rflow_is_gp(rx_chn->common.udmax, rx_chn->flow_id_base)) + return 0; + + /* Allocate range of GP rflows */ + ret = xudma_alloc_gp_rflow_range(rx_chn->common.udmax, + rx_chn->flow_id_base, + rx_chn->flow_num); + if (ret < 0) { + dev_err(rx_chn->common.dev, "UDMAX reserve_rflow %d cnt:%d err: %d\n", + rx_chn->flow_id_base, rx_chn->flow_num, ret); + return ret; + } + rx_chn->flow_id_base = ret; + + return 0; +} + +static struct k3_udma_glue_rx_channel * +k3_udma_glue_request_rx_chn_priv(struct device *dev, const char *name, + struct k3_udma_glue_rx_channel_cfg *cfg) +{ + struct k3_udma_glue_rx_channel *rx_chn; + int ret, i; + + if (cfg->flow_id_num <= 0) + return ERR_PTR(-EINVAL); + + if (cfg->flow_id_num != 1 && + (cfg->def_flow_cfg || cfg->flow_id_use_rxchan_id)) + return ERR_PTR(-EINVAL); + + rx_chn = devm_kzalloc(dev, sizeof(*rx_chn), GFP_KERNEL); + if (!rx_chn) + return ERR_PTR(-ENOMEM); + + rx_chn->common.dev = dev; + rx_chn->common.swdata_size = cfg->swdata_size; + rx_chn->remote = false; + + /* parse of udmap channel */ + ret = of_k3_udma_glue_parse_chn(dev->of_node, name, + &rx_chn->common, false); + if (ret) + goto err; + + rx_chn->common.hdesc_size = cppi5_hdesc_calc_size(rx_chn->common.epib, + rx_chn->common.psdata_size, + rx_chn->common.swdata_size); + + /* request and cfg UDMAP RX channel */ + rx_chn->udma_rchanx = xudma_rchan_get(rx_chn->common.udmax, -1); + if (IS_ERR(rx_chn->udma_rchanx)) { + ret = PTR_ERR(rx_chn->udma_rchanx); + dev_err(dev, "UDMAX rchanx get err %d\n", ret); + goto err; + } + rx_chn->udma_rchan_id = xudma_rchan_get_id(rx_chn->udma_rchanx); + + rx_chn->flow_num = cfg->flow_id_num; + rx_chn->flow_id_base = cfg->flow_id_base; + + /* Use RX channel id as flow id: target dev can't generate flow_id */ + if (cfg->flow_id_use_rxchan_id) + rx_chn->flow_id_base = rx_chn->udma_rchan_id; + + rx_chn->flows = devm_kcalloc(dev, rx_chn->flow_num, + sizeof(*rx_chn->flows), GFP_KERNEL); + if (!rx_chn->flows) { + ret = -ENOMEM; + goto err; + } + + ret = k3_udma_glue_allocate_rx_flows(rx_chn, cfg); + if (ret) + goto err; + + for (i = 0; i < rx_chn->flow_num; i++) + rx_chn->flows[i].udma_rflow_id = rx_chn->flow_id_base + i; + + /* request and cfg psi-l */ + rx_chn->common.dst_thread = + xudma_dev_get_psil_base(rx_chn->common.udmax) + + rx_chn->udma_rchan_id; + + ret = k3_udma_glue_cfg_rx_chn(rx_chn); + if (ret) { + dev_err(dev, "Failed to cfg rchan %d\n", ret); + goto err; + } + + /* init default RX flow only if flow_num = 1 */ + if (cfg->def_flow_cfg) { + ret = k3_udma_glue_cfg_rx_flow(rx_chn, 0, cfg->def_flow_cfg); + if (ret) + goto err; + } + + ret = xudma_navss_psil_pair(rx_chn->common.udmax, + rx_chn->common.src_thread, + rx_chn->common.dst_thread); + if (ret) { + dev_err(dev, "PSI-L request err %d\n", ret); + goto err; + } + + rx_chn->psil_paired = true; + + /* reset RX RT registers */ + k3_udma_glue_disable_rx_chn(rx_chn); + + k3_udma_glue_dump_rx_chn(rx_chn); + + return rx_chn; + +err: + k3_udma_glue_release_rx_chn(rx_chn); + return ERR_PTR(ret); +} + +static struct k3_udma_glue_rx_channel * +k3_udma_glue_request_remote_rx_chn(struct device *dev, const char *name, + struct k3_udma_glue_rx_channel_cfg *cfg) +{ + struct k3_udma_glue_rx_channel *rx_chn; + int ret, i; + + if (cfg->flow_id_num <= 0 || + cfg->flow_id_use_rxchan_id || + cfg->def_flow_cfg || + cfg->flow_id_base < 0) + return ERR_PTR(-EINVAL); + + /* + * Remote RX channel is under control of Remote CPU core, so + * Linux can only request and manipulate by dedicated RX flows + */ + + rx_chn = devm_kzalloc(dev, sizeof(*rx_chn), GFP_KERNEL); + if (!rx_chn) + return ERR_PTR(-ENOMEM); + + rx_chn->common.dev = dev; + rx_chn->common.swdata_size = cfg->swdata_size; + rx_chn->remote = true; + rx_chn->udma_rchan_id = -1; + rx_chn->flow_num = cfg->flow_id_num; + rx_chn->flow_id_base = cfg->flow_id_base; + rx_chn->psil_paired = false; + + /* parse of udmap channel */ + ret = of_k3_udma_glue_parse_chn(dev->of_node, name, + &rx_chn->common, false); + if (ret) + goto err; + + rx_chn->common.hdesc_size = cppi5_hdesc_calc_size(rx_chn->common.epib, + rx_chn->common.psdata_size, + rx_chn->common.swdata_size); + + rx_chn->flows = devm_kcalloc(dev, rx_chn->flow_num, + sizeof(*rx_chn->flows), GFP_KERNEL); + if (!rx_chn->flows) { + ret = -ENOMEM; + goto err; + } + + ret = k3_udma_glue_allocate_rx_flows(rx_chn, cfg); + if (ret) + goto err; + + for (i = 0; i < rx_chn->flow_num; i++) + rx_chn->flows[i].udma_rflow_id = rx_chn->flow_id_base + i; + + k3_udma_glue_dump_rx_chn(rx_chn); + + return rx_chn; + +err: + k3_udma_glue_release_rx_chn(rx_chn); + return ERR_PTR(ret); +} + +struct k3_udma_glue_rx_channel * +k3_udma_glue_request_rx_chn(struct device *dev, const char *name, + struct k3_udma_glue_rx_channel_cfg *cfg) +{ + if (cfg->remote) + return k3_udma_glue_request_remote_rx_chn(dev, name, cfg); + else + return k3_udma_glue_request_rx_chn_priv(dev, name, cfg); +} +EXPORT_SYMBOL_GPL(k3_udma_glue_request_rx_chn); + +void k3_udma_glue_release_rx_chn(struct k3_udma_glue_rx_channel *rx_chn) +{ + int i; + + if (IS_ERR_OR_NULL(rx_chn->common.udmax)) + return; + + if (rx_chn->psil_paired) { + xudma_navss_psil_unpair(rx_chn->common.udmax, + rx_chn->common.src_thread, + rx_chn->common.dst_thread); + rx_chn->psil_paired = false; + } + + for (i = 0; i < rx_chn->flow_num; i++) + k3_udma_glue_release_rx_flow(rx_chn, i); + + if (xudma_rflow_is_gp(rx_chn->common.udmax, rx_chn->flow_id_base)) + xudma_free_gp_rflow_range(rx_chn->common.udmax, + rx_chn->flow_id_base, + rx_chn->flow_num); + + if (!IS_ERR_OR_NULL(rx_chn->udma_rchanx)) + xudma_rchan_put(rx_chn->common.udmax, + rx_chn->udma_rchanx); +} +EXPORT_SYMBOL_GPL(k3_udma_glue_release_rx_chn); + +int k3_udma_glue_rx_flow_init(struct k3_udma_glue_rx_channel *rx_chn, + u32 flow_idx, + struct k3_udma_glue_rx_flow_cfg *flow_cfg) +{ + if (flow_idx >= rx_chn->flow_num) + return -EINVAL; + + return k3_udma_glue_cfg_rx_flow(rx_chn, flow_idx, flow_cfg); +} +EXPORT_SYMBOL_GPL(k3_udma_glue_rx_flow_init); + +u32 k3_udma_glue_rx_flow_get_fdq_id(struct k3_udma_glue_rx_channel *rx_chn, + u32 flow_idx) +{ + struct k3_udma_glue_rx_flow *flow; + + if (flow_idx >= rx_chn->flow_num) + return -EINVAL; + + flow = &rx_chn->flows[flow_idx]; + + return k3_ringacc_get_ring_id(flow->ringrxfdq); +} +EXPORT_SYMBOL_GPL(k3_udma_glue_rx_flow_get_fdq_id); + +u32 k3_udma_glue_rx_get_flow_id_base(struct k3_udma_glue_rx_channel *rx_chn) +{ + return rx_chn->flow_id_base; +} +EXPORT_SYMBOL_GPL(k3_udma_glue_rx_get_flow_id_base); + +int k3_udma_glue_rx_flow_enable(struct k3_udma_glue_rx_channel *rx_chn, + u32 flow_idx) +{ + struct k3_udma_glue_rx_flow *flow = &rx_chn->flows[flow_idx]; + const struct udma_tisci_rm *tisci_rm = rx_chn->common.tisci_rm; + struct device *dev = rx_chn->common.dev; + struct ti_sci_msg_rm_udmap_flow_cfg req; + int rx_ring_id; + int rx_ringfdq_id; + int ret = 0; + + if (!rx_chn->remote) + return -EINVAL; + + rx_ring_id = k3_ringacc_get_ring_id(flow->ringrx); + rx_ringfdq_id = k3_ringacc_get_ring_id(flow->ringrxfdq); + + memset(&req, 0, sizeof(req)); + + req.valid_params = + TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_DEST_QNUM_VALID | + TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_FDQ0_SZ0_QNUM_VALID | + TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_FDQ1_QNUM_VALID | + TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_FDQ2_QNUM_VALID | + TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_FDQ3_QNUM_VALID; + req.nav_id = tisci_rm->tisci_dev_id; + req.flow_index = flow->udma_rflow_id; + req.rx_dest_qnum = rx_ring_id; + req.rx_fdq0_sz0_qnum = rx_ringfdq_id; + req.rx_fdq1_qnum = rx_ringfdq_id; + req.rx_fdq2_qnum = rx_ringfdq_id; + req.rx_fdq3_qnum = rx_ringfdq_id; + + ret = tisci_rm->tisci_udmap_ops->rx_flow_cfg(tisci_rm->tisci, &req); + if (ret) { + dev_err(dev, "flow%d enable failed: %d\n", flow->udma_rflow_id, + ret); + } + + return ret; +} +EXPORT_SYMBOL_GPL(k3_udma_glue_rx_flow_enable); + +int k3_udma_glue_rx_flow_disable(struct k3_udma_glue_rx_channel *rx_chn, + u32 flow_idx) +{ + struct k3_udma_glue_rx_flow *flow = &rx_chn->flows[flow_idx]; + const struct udma_tisci_rm *tisci_rm = rx_chn->common.tisci_rm; + struct device *dev = rx_chn->common.dev; + struct ti_sci_msg_rm_udmap_flow_cfg req; + int ret = 0; + + if (!rx_chn->remote) + return -EINVAL; + + memset(&req, 0, sizeof(req)); + req.valid_params = + TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_DEST_QNUM_VALID | + TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_FDQ0_SZ0_QNUM_VALID | + TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_FDQ1_QNUM_VALID | + TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_FDQ2_QNUM_VALID | + TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_FDQ3_QNUM_VALID; + req.nav_id = tisci_rm->tisci_dev_id; + req.flow_index = flow->udma_rflow_id; + req.rx_dest_qnum = TI_SCI_RESOURCE_NULL; + req.rx_fdq0_sz0_qnum = TI_SCI_RESOURCE_NULL; + req.rx_fdq1_qnum = TI_SCI_RESOURCE_NULL; + req.rx_fdq2_qnum = TI_SCI_RESOURCE_NULL; + req.rx_fdq3_qnum = TI_SCI_RESOURCE_NULL; + + ret = tisci_rm->tisci_udmap_ops->rx_flow_cfg(tisci_rm->tisci, &req); + if (ret) { + dev_err(dev, "flow%d disable failed: %d\n", flow->udma_rflow_id, + ret); + } + + return ret; +} +EXPORT_SYMBOL_GPL(k3_udma_glue_rx_flow_disable); + +int k3_udma_glue_enable_rx_chn(struct k3_udma_glue_rx_channel *rx_chn) +{ + u32 rxrt_ctl; + + if (rx_chn->remote) + return -EINVAL; + + if (rx_chn->flows_ready < rx_chn->flow_num) + return -EINVAL; + + rxrt_ctl = xudma_rchanrt_read(rx_chn->udma_rchanx, + UDMA_RCHAN_RT_CTL_REG); + rxrt_ctl |= UDMA_CHAN_RT_CTL_EN; + xudma_rchanrt_write(rx_chn->udma_rchanx, UDMA_RCHAN_RT_CTL_REG, + rxrt_ctl); + + xudma_rchanrt_write(rx_chn->udma_rchanx, + UDMA_RCHAN_RT_PEER_RT_EN_REG, + UDMA_PEER_RT_EN_ENABLE); + + k3_udma_glue_dump_rx_rt_chn(rx_chn, "rxrt en"); + return 0; +} +EXPORT_SYMBOL_GPL(k3_udma_glue_enable_rx_chn); + +void k3_udma_glue_disable_rx_chn(struct k3_udma_glue_rx_channel *rx_chn) +{ + k3_udma_glue_dump_rx_rt_chn(rx_chn, "rxrt dis1"); + + xudma_rchanrt_write(rx_chn->udma_rchanx, + UDMA_RCHAN_RT_PEER_RT_EN_REG, + 0); + xudma_rchanrt_write(rx_chn->udma_rchanx, UDMA_RCHAN_RT_CTL_REG, 0); + + k3_udma_glue_dump_rx_rt_chn(rx_chn, "rxrt dis2"); +} +EXPORT_SYMBOL_GPL(k3_udma_glue_disable_rx_chn); + +void k3_udma_glue_tdown_rx_chn(struct k3_udma_glue_rx_channel *rx_chn, + bool sync) +{ + int i = 0; + u32 val; + + if (rx_chn->remote) + return; + + k3_udma_glue_dump_rx_rt_chn(rx_chn, "rxrt tdown1"); + + xudma_rchanrt_write(rx_chn->udma_rchanx, UDMA_RCHAN_RT_PEER_RT_EN_REG, + UDMA_PEER_RT_EN_ENABLE | UDMA_PEER_RT_EN_TEARDOWN); + + val = xudma_rchanrt_read(rx_chn->udma_rchanx, UDMA_RCHAN_RT_CTL_REG); + + while (sync && (val & UDMA_CHAN_RT_CTL_EN)) { + val = xudma_rchanrt_read(rx_chn->udma_rchanx, + UDMA_RCHAN_RT_CTL_REG); + udelay(1); + if (i > K3_UDMAX_TDOWN_TIMEOUT_US) { + dev_err(rx_chn->common.dev, "RX tdown timeout\n"); + break; + } + i++; + } + + val = xudma_rchanrt_read(rx_chn->udma_rchanx, + UDMA_RCHAN_RT_PEER_RT_EN_REG); + if (sync && (val & UDMA_PEER_RT_EN_ENABLE)) + dev_err(rx_chn->common.dev, "TX tdown peer not stopped\n"); + k3_udma_glue_dump_rx_rt_chn(rx_chn, "rxrt tdown2"); +} +EXPORT_SYMBOL_GPL(k3_udma_glue_tdown_rx_chn); + +void k3_udma_glue_reset_rx_chn(struct k3_udma_glue_rx_channel *rx_chn, + u32 flow_num, void *data, + void (*cleanup)(void *data, dma_addr_t desc_dma), bool skip_fdq) +{ + struct k3_udma_glue_rx_flow *flow = &rx_chn->flows[flow_num]; + struct device *dev = rx_chn->common.dev; + dma_addr_t desc_dma; + int occ_rx, i, ret; + + /* reset RXCQ as it is not input for udma - expected to be empty */ + occ_rx = k3_ringacc_ring_get_occ(flow->ringrx); + dev_dbg(dev, "RX reset flow %u occ_rx %u\n", flow_num, occ_rx); + if (flow->ringrx) + k3_ringacc_ring_reset(flow->ringrx); + + /* Skip RX FDQ in case one FDQ is used for the set of flows */ + if (skip_fdq) + return; + + /* + * RX FDQ reset need to be special way as it is input for udma and its + * state cached by udma, so: + * 1) save RX FDQ occ + * 2) clean up RX FDQ and call callback .cleanup() for each desc + * 3) reset RX FDQ in a special way + */ + occ_rx = k3_ringacc_ring_get_occ(flow->ringrxfdq); + dev_dbg(dev, "RX reset flow %u occ_rx_fdq %u\n", flow_num, occ_rx); + + for (i = 0; i < occ_rx; i++) { + ret = k3_ringacc_ring_pop(flow->ringrxfdq, &desc_dma); + if (ret) { + dev_err(dev, "RX reset pop %d\n", ret); + break; + } + cleanup(data, desc_dma); + } + + k3_ringacc_ring_reset_dma(flow->ringrxfdq, occ_rx); +} +EXPORT_SYMBOL_GPL(k3_udma_glue_reset_rx_chn); + +int k3_udma_glue_push_rx_chn(struct k3_udma_glue_rx_channel *rx_chn, + u32 flow_num, struct cppi5_host_desc_t *desc_rx, + dma_addr_t desc_dma) +{ + struct k3_udma_glue_rx_flow *flow = &rx_chn->flows[flow_num]; + + return k3_ringacc_ring_push(flow->ringrxfdq, &desc_dma); +} +EXPORT_SYMBOL_GPL(k3_udma_glue_push_rx_chn); + +int k3_udma_glue_pop_rx_chn(struct k3_udma_glue_rx_channel *rx_chn, + u32 flow_num, dma_addr_t *desc_dma) +{ + struct k3_udma_glue_rx_flow *flow = &rx_chn->flows[flow_num]; + + return k3_ringacc_ring_pop(flow->ringrx, desc_dma); +} +EXPORT_SYMBOL_GPL(k3_udma_glue_pop_rx_chn); + +int k3_udma_glue_rx_get_irq(struct k3_udma_glue_rx_channel *rx_chn, + u32 flow_num) +{ + struct k3_udma_glue_rx_flow *flow; + + flow = &rx_chn->flows[flow_num]; + + flow->virq = k3_ringacc_get_ring_irq_num(flow->ringrx); + + return flow->virq; +} +EXPORT_SYMBOL_GPL(k3_udma_glue_rx_get_irq); diff --git a/drivers/dma/ti/k3-udma-private.c b/drivers/dma/ti/k3-udma-private.c new file mode 100644 index 000000000000..0b8f3dd6b146 --- /dev/null +++ b/drivers/dma/ti/k3-udma-private.c @@ -0,0 +1,133 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com + * Author: Peter Ujfalusi <peter.ujfalusi@ti.com> + */ + +int xudma_navss_psil_pair(struct udma_dev *ud, u32 src_thread, u32 dst_thread) +{ + return navss_psil_pair(ud, src_thread, dst_thread); +} +EXPORT_SYMBOL(xudma_navss_psil_pair); + +int xudma_navss_psil_unpair(struct udma_dev *ud, u32 src_thread, u32 dst_thread) +{ + return navss_psil_unpair(ud, src_thread, dst_thread); +} +EXPORT_SYMBOL(xudma_navss_psil_unpair); + +struct udma_dev *of_xudma_dev_get(struct device_node *np, const char *property) +{ + struct device_node *udma_node = np; + struct platform_device *pdev; + struct udma_dev *ud; + + if (property) { + udma_node = of_parse_phandle(np, property, 0); + if (!udma_node) { + pr_err("UDMA node is not found\n"); + return ERR_PTR(-ENODEV); + } + } + + pdev = of_find_device_by_node(udma_node); + if (!pdev) { + pr_debug("UDMA device not found\n"); + return ERR_PTR(-EPROBE_DEFER); + } + + if (np != udma_node) + of_node_put(udma_node); + + ud = platform_get_drvdata(pdev); + if (!ud) { + pr_debug("UDMA has not been probed\n"); + return ERR_PTR(-EPROBE_DEFER); + } + + return ud; +} +EXPORT_SYMBOL(of_xudma_dev_get); + +u32 xudma_dev_get_psil_base(struct udma_dev *ud) +{ + return ud->psil_base; +} +EXPORT_SYMBOL(xudma_dev_get_psil_base); + +struct udma_tisci_rm *xudma_dev_get_tisci_rm(struct udma_dev *ud) +{ + return &ud->tisci_rm; +} +EXPORT_SYMBOL(xudma_dev_get_tisci_rm); + +int xudma_alloc_gp_rflow_range(struct udma_dev *ud, int from, int cnt) +{ + return __udma_alloc_gp_rflow_range(ud, from, cnt); +} +EXPORT_SYMBOL(xudma_alloc_gp_rflow_range); + +int xudma_free_gp_rflow_range(struct udma_dev *ud, int from, int cnt) +{ + return __udma_free_gp_rflow_range(ud, from, cnt); +} +EXPORT_SYMBOL(xudma_free_gp_rflow_range); + +bool xudma_rflow_is_gp(struct udma_dev *ud, int id) +{ + return !test_bit(id, ud->rflow_gp_map); +} +EXPORT_SYMBOL(xudma_rflow_is_gp); + +#define XUDMA_GET_PUT_RESOURCE(res) \ +struct udma_##res *xudma_##res##_get(struct udma_dev *ud, int id) \ +{ \ + return __udma_reserve_##res(ud, false, id); \ +} \ +EXPORT_SYMBOL(xudma_##res##_get); \ + \ +void xudma_##res##_put(struct udma_dev *ud, struct udma_##res *p) \ +{ \ + clear_bit(p->id, ud->res##_map); \ +} \ +EXPORT_SYMBOL(xudma_##res##_put) +XUDMA_GET_PUT_RESOURCE(tchan); +XUDMA_GET_PUT_RESOURCE(rchan); + +struct udma_rflow *xudma_rflow_get(struct udma_dev *ud, int id) +{ + return __udma_get_rflow(ud, id); +} +EXPORT_SYMBOL(xudma_rflow_get); + +void xudma_rflow_put(struct udma_dev *ud, struct udma_rflow *p) +{ + __udma_put_rflow(ud, p); +} +EXPORT_SYMBOL(xudma_rflow_put); + +#define XUDMA_GET_RESOURCE_ID(res) \ +int xudma_##res##_get_id(struct udma_##res *p) \ +{ \ + return p->id; \ +} \ +EXPORT_SYMBOL(xudma_##res##_get_id) +XUDMA_GET_RESOURCE_ID(tchan); +XUDMA_GET_RESOURCE_ID(rchan); +XUDMA_GET_RESOURCE_ID(rflow); + +/* Exported register access functions */ +#define XUDMA_RT_IO_FUNCTIONS(res) \ +u32 xudma_##res##rt_read(struct udma_##res *p, int reg) \ +{ \ + return udma_##res##rt_read(p, reg); \ +} \ +EXPORT_SYMBOL(xudma_##res##rt_read); \ + \ +void xudma_##res##rt_write(struct udma_##res *p, int reg, u32 val) \ +{ \ + udma_##res##rt_write(p, reg, val); \ +} \ +EXPORT_SYMBOL(xudma_##res##rt_write) +XUDMA_RT_IO_FUNCTIONS(tchan); +XUDMA_RT_IO_FUNCTIONS(rchan); diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c new file mode 100644 index 000000000000..0536866a58ce --- /dev/null +++ b/drivers/dma/ti/k3-udma.c @@ -0,0 +1,3661 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com + * Author: Peter Ujfalusi <peter.ujfalusi@ti.com> + */ + +#include <linux/kernel.h> +#include <linux/delay.h> +#include <linux/dmaengine.h> +#include <linux/dma-mapping.h> +#include <linux/dmapool.h> +#include <linux/err.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/list.h> +#include <linux/platform_device.h> +#include <linux/slab.h> +#include <linux/spinlock.h> +#include <linux/of.h> +#include <linux/of_dma.h> +#include <linux/of_device.h> +#include <linux/of_irq.h> +#include <linux/workqueue.h> +#include <linux/completion.h> +#include <linux/soc/ti/k3-ringacc.h> +#include <linux/soc/ti/ti_sci_protocol.h> +#include <linux/soc/ti/ti_sci_inta_msi.h> +#include <linux/dma/ti-cppi5.h> + +#include "../virt-dma.h" +#include "k3-udma.h" +#include "k3-psil-priv.h" + +struct udma_static_tr { + u8 elsize; /* RPSTR0 */ + u16 elcnt; /* RPSTR0 */ + u16 bstcnt; /* RPSTR1 */ +}; + +#define K3_UDMA_MAX_RFLOWS 1024 +#define K3_UDMA_DEFAULT_RING_SIZE 16 + +/* How SRC/DST tag should be updated by UDMA in the descriptor's Word 3 */ +#define UDMA_RFLOW_SRCTAG_NONE 0 +#define UDMA_RFLOW_SRCTAG_CFG_TAG 1 +#define UDMA_RFLOW_SRCTAG_FLOW_ID 2 +#define UDMA_RFLOW_SRCTAG_SRC_TAG 4 + +#define UDMA_RFLOW_DSTTAG_NONE 0 +#define UDMA_RFLOW_DSTTAG_CFG_TAG 1 +#define UDMA_RFLOW_DSTTAG_FLOW_ID 2 +#define UDMA_RFLOW_DSTTAG_DST_TAG_LO 4 +#define UDMA_RFLOW_DSTTAG_DST_TAG_HI 5 + +struct udma_chan; + +enum udma_mmr { + MMR_GCFG = 0, + MMR_RCHANRT, + MMR_TCHANRT, + MMR_LAST, +}; + +static const char * const mmr_names[] = { "gcfg", "rchanrt", "tchanrt" }; + +struct udma_tchan { + void __iomem *reg_rt; + + int id; + struct k3_ring *t_ring; /* Transmit ring */ + struct k3_ring *tc_ring; /* Transmit Completion ring */ +}; + +struct udma_rflow { + int id; + struct k3_ring *fd_ring; /* Free Descriptor ring */ + struct k3_ring *r_ring; /* Receive ring */ +}; + +struct udma_rchan { + void __iomem *reg_rt; + + int id; +}; + +#define UDMA_FLAG_PDMA_ACC32 BIT(0) +#define UDMA_FLAG_PDMA_BURST BIT(1) + +struct udma_match_data { + u32 psil_base; + bool enable_memcpy_support; + u32 flags; + u32 statictr_z_mask; + u32 rchan_oes_offset; + + u8 tpl_levels; + u32 level_start_idx[]; +}; + +struct udma_hwdesc { + size_t cppi5_desc_size; + void *cppi5_desc_vaddr; + dma_addr_t cppi5_desc_paddr; + + /* TR descriptor internal pointers */ + void *tr_req_base; + struct cppi5_tr_resp_t *tr_resp_base; +}; + +struct udma_rx_flush { + struct udma_hwdesc hwdescs[2]; + + size_t buffer_size; + void *buffer_vaddr; + dma_addr_t buffer_paddr; +}; + +struct udma_dev { + struct dma_device ddev; + struct device *dev; + void __iomem *mmrs[MMR_LAST]; + const struct udma_match_data *match_data; + + size_t desc_align; /* alignment to use for descriptors */ + + struct udma_tisci_rm tisci_rm; + + struct k3_ringacc *ringacc; + + struct work_struct purge_work; + struct list_head desc_to_purge; + spinlock_t lock; + + struct udma_rx_flush rx_flush; + + int tchan_cnt; + int echan_cnt; + int rchan_cnt; + int rflow_cnt; + unsigned long *tchan_map; + unsigned long *rchan_map; + unsigned long *rflow_gp_map; + unsigned long *rflow_gp_map_allocated; + unsigned long *rflow_in_use; + + struct udma_tchan *tchans; + struct udma_rchan *rchans; + struct udma_rflow *rflows; + + struct udma_chan *channels; + u32 psil_base; +}; + +struct udma_desc { + struct virt_dma_desc vd; + + bool terminated; + + enum dma_transfer_direction dir; + + struct udma_static_tr static_tr; + u32 residue; + + unsigned int sglen; + unsigned int desc_idx; /* Only used for cyclic in packet mode */ + unsigned int tr_idx; + + u32 metadata_size; + void *metadata; /* pointer to provided metadata buffer (EPIP, PSdata) */ + + unsigned int hwdesc_count; + struct udma_hwdesc hwdesc[0]; +}; + +enum udma_chan_state { + UDMA_CHAN_IS_IDLE = 0, /* not active, no teardown is in progress */ + UDMA_CHAN_IS_ACTIVE, /* Normal operation */ + UDMA_CHAN_IS_TERMINATING, /* channel is being terminated */ +}; + +struct udma_tx_drain { + struct delayed_work work; + ktime_t tstamp; + u32 residue; +}; + +struct udma_chan_config { + bool pkt_mode; /* TR or packet */ + bool needs_epib; /* EPIB is needed for the communication or not */ + u32 psd_size; /* size of Protocol Specific Data */ + u32 metadata_size; /* (needs_epib ? 16:0) + psd_size */ + u32 hdesc_size; /* Size of a packet descriptor in packet mode */ + bool notdpkt; /* Suppress sending TDC packet */ + int remote_thread_id; + u32 src_thread; + u32 dst_thread; + enum psil_endpoint_type ep_type; + bool enable_acc32; + bool enable_burst; + enum udma_tp_level channel_tpl; /* Channel Throughput Level */ + + enum dma_transfer_direction dir; +}; + +struct udma_chan { + struct virt_dma_chan vc; + struct dma_slave_config cfg; + struct udma_dev *ud; + struct udma_desc *desc; + struct udma_desc *terminated_desc; + struct udma_static_tr static_tr; + char *name; + + struct udma_tchan *tchan; + struct udma_rchan *rchan; + struct udma_rflow *rflow; + + bool psil_paired; + + int irq_num_ring; + int irq_num_udma; + + bool cyclic; + bool paused; + + enum udma_chan_state state; + struct completion teardown_completed; + + struct udma_tx_drain tx_drain; + + u32 bcnt; /* number of bytes completed since the start of the channel */ + u32 in_ring_cnt; /* number of descriptors in flight */ + + /* Channel configuration parameters */ + struct udma_chan_config config; + + /* dmapool for packet mode descriptors */ + bool use_dma_pool; + struct dma_pool *hdesc_pool; + + u32 id; +}; + +static inline struct udma_dev *to_udma_dev(struct dma_device *d) +{ + return container_of(d, struct udma_dev, ddev); +} + +static inline struct udma_chan *to_udma_chan(struct dma_chan *c) +{ + return container_of(c, struct udma_chan, vc.chan); +} + +static inline struct udma_desc *to_udma_desc(struct dma_async_tx_descriptor *t) +{ + return container_of(t, struct udma_desc, vd.tx); +} + +/* Generic register access functions */ +static inline u32 udma_read(void __iomem *base, int reg) +{ + return readl(base + reg); +} + +static inline void udma_write(void __iomem *base, int reg, u32 val) +{ + writel(val, base + reg); +} + +static inline void udma_update_bits(void __iomem *base, int reg, + u32 mask, u32 val) +{ + u32 tmp, orig; + + orig = readl(base + reg); + tmp = orig & ~mask; + tmp |= (val & mask); + + if (tmp != orig) + writel(tmp, base + reg); +} + +/* TCHANRT */ +static inline u32 udma_tchanrt_read(struct udma_tchan *tchan, int reg) +{ + if (!tchan) + return 0; + return udma_read(tchan->reg_rt, reg); +} + +static inline void udma_tchanrt_write(struct udma_tchan *tchan, int reg, + u32 val) +{ + if (!tchan) + return; + udma_write(tchan->reg_rt, reg, val); +} + +static inline void udma_tchanrt_update_bits(struct udma_tchan *tchan, int reg, + u32 mask, u32 val) +{ + if (!tchan) + return; + udma_update_bits(tchan->reg_rt, reg, mask, val); +} + +/* RCHANRT */ +static inline u32 udma_rchanrt_read(struct udma_rchan *rchan, int reg) +{ + if (!rchan) + return 0; + return udma_read(rchan->reg_rt, reg); +} + +static inline void udma_rchanrt_write(struct udma_rchan *rchan, int reg, + u32 val) +{ + if (!rchan) + return; + udma_write(rchan->reg_rt, reg, val); +} + +static inline void udma_rchanrt_update_bits(struct udma_rchan *rchan, int reg, + u32 mask, u32 val) +{ + if (!rchan) + return; + udma_update_bits(rchan->reg_rt, reg, mask, val); +} + +static int navss_psil_pair(struct udma_dev *ud, u32 src_thread, u32 dst_thread) +{ + struct udma_tisci_rm *tisci_rm = &ud->tisci_rm; + + dst_thread |= K3_PSIL_DST_THREAD_ID_OFFSET; + return tisci_rm->tisci_psil_ops->pair(tisci_rm->tisci, + tisci_rm->tisci_navss_dev_id, + src_thread, dst_thread); +} + +static int navss_psil_unpair(struct udma_dev *ud, u32 src_thread, + u32 dst_thread) +{ + struct udma_tisci_rm *tisci_rm = &ud->tisci_rm; + + dst_thread |= K3_PSIL_DST_THREAD_ID_OFFSET; + return tisci_rm->tisci_psil_ops->unpair(tisci_rm->tisci, + tisci_rm->tisci_navss_dev_id, + src_thread, dst_thread); +} + +static void udma_reset_uchan(struct udma_chan *uc) +{ + memset(&uc->config, 0, sizeof(uc->config)); + uc->config.remote_thread_id = -1; + uc->state = UDMA_CHAN_IS_IDLE; +} + +static void udma_dump_chan_stdata(struct udma_chan *uc) +{ + struct device *dev = uc->ud->dev; + u32 offset; + int i; + + if (uc->config.dir == DMA_MEM_TO_DEV || uc->config.dir == DMA_MEM_TO_MEM) { + dev_dbg(dev, "TCHAN State data:\n"); + for (i = 0; i < 32; i++) { + offset = UDMA_TCHAN_RT_STDATA_REG + i * 4; + dev_dbg(dev, "TRT_STDATA[%02d]: 0x%08x\n", i, + udma_tchanrt_read(uc->tchan, offset)); + } + } + + if (uc->config.dir == DMA_DEV_TO_MEM || uc->config.dir == DMA_MEM_TO_MEM) { + dev_dbg(dev, "RCHAN State data:\n"); + for (i = 0; i < 32; i++) { + offset = UDMA_RCHAN_RT_STDATA_REG + i * 4; + dev_dbg(dev, "RRT_STDATA[%02d]: 0x%08x\n", i, + udma_rchanrt_read(uc->rchan, offset)); + } + } +} + +static inline dma_addr_t udma_curr_cppi5_desc_paddr(struct udma_desc *d, + int idx) +{ + return d->hwdesc[idx].cppi5_desc_paddr; +} + +static inline void *udma_curr_cppi5_desc_vaddr(struct udma_desc *d, int idx) +{ + return d->hwdesc[idx].cppi5_desc_vaddr; +} + +static struct udma_desc *udma_udma_desc_from_paddr(struct udma_chan *uc, + dma_addr_t paddr) +{ + struct udma_desc *d = uc->terminated_desc; + + if (d) { + dma_addr_t desc_paddr = udma_curr_cppi5_desc_paddr(d, + d->desc_idx); + + if (desc_paddr != paddr) + d = NULL; + } + + if (!d) { + d = uc->desc; + if (d) { + dma_addr_t desc_paddr = udma_curr_cppi5_desc_paddr(d, + d->desc_idx); + + if (desc_paddr != paddr) + d = NULL; + } + } + + return d; +} + +static void udma_free_hwdesc(struct udma_chan *uc, struct udma_desc *d) +{ + if (uc->use_dma_pool) { + int i; + + for (i = 0; i < d->hwdesc_count; i++) { + if (!d->hwdesc[i].cppi5_desc_vaddr) + continue; + + dma_pool_free(uc->hdesc_pool, + d->hwdesc[i].cppi5_desc_vaddr, + d->hwdesc[i].cppi5_desc_paddr); + + d->hwdesc[i].cppi5_desc_vaddr = NULL; + } + } else if (d->hwdesc[0].cppi5_desc_vaddr) { + struct udma_dev *ud = uc->ud; + + dma_free_coherent(ud->dev, d->hwdesc[0].cppi5_desc_size, + d->hwdesc[0].cppi5_desc_vaddr, + d->hwdesc[0].cppi5_desc_paddr); + + d->hwdesc[0].cppi5_desc_vaddr = NULL; + } +} + +static void udma_purge_desc_work(struct work_struct *work) +{ + struct udma_dev *ud = container_of(work, typeof(*ud), purge_work); + struct virt_dma_desc *vd, *_vd; + unsigned long flags; + LIST_HEAD(head); + + spin_lock_irqsave(&ud->lock, flags); + list_splice_tail_init(&ud->desc_to_purge, &head); + spin_unlock_irqrestore(&ud->lock, flags); + + list_for_each_entry_safe(vd, _vd, &head, node) { + struct udma_chan *uc = to_udma_chan(vd->tx.chan); + struct udma_desc *d = to_udma_desc(&vd->tx); + + udma_free_hwdesc(uc, d); + list_del(&vd->node); + kfree(d); + } + + /* If more to purge, schedule the work again */ + if (!list_empty(&ud->desc_to_purge)) + schedule_work(&ud->purge_work); +} + +static void udma_desc_free(struct virt_dma_desc *vd) +{ + struct udma_dev *ud = to_udma_dev(vd->tx.chan->device); + struct udma_chan *uc = to_udma_chan(vd->tx.chan); + struct udma_desc *d = to_udma_desc(&vd->tx); + unsigned long flags; + + if (uc->terminated_desc == d) + uc->terminated_desc = NULL; + + if (uc->use_dma_pool) { + udma_free_hwdesc(uc, d); + kfree(d); + return; + } + + spin_lock_irqsave(&ud->lock, flags); + list_add_tail(&vd->node, &ud->desc_to_purge); + spin_unlock_irqrestore(&ud->lock, flags); + + schedule_work(&ud->purge_work); +} + +static bool udma_is_chan_running(struct udma_chan *uc) +{ + u32 trt_ctl = 0; + u32 rrt_ctl = 0; + + if (uc->tchan) + trt_ctl = udma_tchanrt_read(uc->tchan, UDMA_TCHAN_RT_CTL_REG); + if (uc->rchan) + rrt_ctl = udma_rchanrt_read(uc->rchan, UDMA_RCHAN_RT_CTL_REG); + + if (trt_ctl & UDMA_CHAN_RT_CTL_EN || rrt_ctl & UDMA_CHAN_RT_CTL_EN) + return true; + + return false; +} + +static bool udma_is_chan_paused(struct udma_chan *uc) +{ + u32 val, pause_mask; + + switch (uc->config.dir) { + case DMA_DEV_TO_MEM: + val = udma_rchanrt_read(uc->rchan, + UDMA_RCHAN_RT_PEER_RT_EN_REG); + pause_mask = UDMA_PEER_RT_EN_PAUSE; + break; + case DMA_MEM_TO_DEV: + val = udma_tchanrt_read(uc->tchan, + UDMA_TCHAN_RT_PEER_RT_EN_REG); + pause_mask = UDMA_PEER_RT_EN_PAUSE; + break; + case DMA_MEM_TO_MEM: + val = udma_tchanrt_read(uc->tchan, UDMA_TCHAN_RT_CTL_REG); + pause_mask = UDMA_CHAN_RT_CTL_PAUSE; + break; + default: + return false; + } + + if (val & pause_mask) + return true; + + return false; +} + +static void udma_sync_for_device(struct udma_chan *uc, int idx) +{ + struct udma_desc *d = uc->desc; + + if (uc->cyclic && uc->config.pkt_mode) { + dma_sync_single_for_device(uc->ud->dev, + d->hwdesc[idx].cppi5_desc_paddr, + d->hwdesc[idx].cppi5_desc_size, + DMA_TO_DEVICE); + } else { + int i; + + for (i = 0; i < d->hwdesc_count; i++) { + if (!d->hwdesc[i].cppi5_desc_vaddr) + continue; + + dma_sync_single_for_device(uc->ud->dev, + d->hwdesc[i].cppi5_desc_paddr, + d->hwdesc[i].cppi5_desc_size, + DMA_TO_DEVICE); + } + } +} + +static inline dma_addr_t udma_get_rx_flush_hwdesc_paddr(struct udma_chan *uc) +{ + return uc->ud->rx_flush.hwdescs[uc->config.pkt_mode].cppi5_desc_paddr; +} + +static int udma_push_to_ring(struct udma_chan *uc, int idx) +{ + struct udma_desc *d = uc->desc; + struct k3_ring *ring = NULL; + dma_addr_t paddr; + int ret; + + switch (uc->config.dir) { + case DMA_DEV_TO_MEM: + ring = uc->rflow->fd_ring; + break; + case DMA_MEM_TO_DEV: + case DMA_MEM_TO_MEM: + ring = uc->tchan->t_ring; + break; + default: + return -EINVAL; + } + + /* RX flush packet: idx == -1 is only passed in case of DEV_TO_MEM */ + if (idx == -1) { + paddr = udma_get_rx_flush_hwdesc_paddr(uc); + } else { + paddr = udma_curr_cppi5_desc_paddr(d, idx); + + wmb(); /* Ensure that writes are not moved over this point */ + udma_sync_for_device(uc, idx); + } + + ret = k3_ringacc_ring_push(ring, &paddr); + if (!ret) + uc->in_ring_cnt++; + + return ret; +} + +static bool udma_desc_is_rx_flush(struct udma_chan *uc, dma_addr_t addr) +{ + if (uc->config.dir != DMA_DEV_TO_MEM) + return false; + + if (addr == udma_get_rx_flush_hwdesc_paddr(uc)) + return true; + + return false; +} + +static int udma_pop_from_ring(struct udma_chan *uc, dma_addr_t *addr) +{ + struct k3_ring *ring = NULL; + int ret = -ENOENT; + + switch (uc->config.dir) { + case DMA_DEV_TO_MEM: + ring = uc->rflow->r_ring; + break; + case DMA_MEM_TO_DEV: + case DMA_MEM_TO_MEM: + ring = uc->tchan->tc_ring; + break; + default: + break; + } + + if (ring && k3_ringacc_ring_get_occ(ring)) { + struct udma_desc *d = NULL; + + ret = k3_ringacc_ring_pop(ring, addr); + if (ret) + return ret; + + /* Teardown completion */ + if (cppi5_desc_is_tdcm(*addr)) + return ret; + + /* Check for flush descriptor */ + if (udma_desc_is_rx_flush(uc, *addr)) + return -ENOENT; + + d = udma_udma_desc_from_paddr(uc, *addr); + + if (d) + dma_sync_single_for_cpu(uc->ud->dev, *addr, + d->hwdesc[0].cppi5_desc_size, + DMA_FROM_DEVICE); + rmb(); /* Ensure that reads are not moved before this point */ + + if (!ret) + uc->in_ring_cnt--; + } + + return ret; +} + +static void udma_reset_rings(struct udma_chan *uc) +{ + struct k3_ring *ring1 = NULL; + struct k3_ring *ring2 = NULL; + + switch (uc->config.dir) { + case DMA_DEV_TO_MEM: + if (uc->rchan) { + ring1 = uc->rflow->fd_ring; + ring2 = uc->rflow->r_ring; + } + break; + case DMA_MEM_TO_DEV: + case DMA_MEM_TO_MEM: + if (uc->tchan) { + ring1 = uc->tchan->t_ring; + ring2 = uc->tchan->tc_ring; + } + break; + default: + break; + } + + if (ring1) + k3_ringacc_ring_reset_dma(ring1, + k3_ringacc_ring_get_occ(ring1)); + if (ring2) + k3_ringacc_ring_reset(ring2); + + /* make sure we are not leaking memory by stalled descriptor */ + if (uc->terminated_desc) { + udma_desc_free(&uc->terminated_desc->vd); + uc->terminated_desc = NULL; + } + + uc->in_ring_cnt = 0; +} + +static void udma_reset_counters(struct udma_chan *uc) +{ + u32 val; + + if (uc->tchan) { + val = udma_tchanrt_read(uc->tchan, UDMA_TCHAN_RT_BCNT_REG); + udma_tchanrt_write(uc->tchan, UDMA_TCHAN_RT_BCNT_REG, val); + + val = udma_tchanrt_read(uc->tchan, UDMA_TCHAN_RT_SBCNT_REG); + udma_tchanrt_write(uc->tchan, UDMA_TCHAN_RT_SBCNT_REG, val); + + val = udma_tchanrt_read(uc->tchan, UDMA_TCHAN_RT_PCNT_REG); + udma_tchanrt_write(uc->tchan, UDMA_TCHAN_RT_PCNT_REG, val); + + val = udma_tchanrt_read(uc->tchan, UDMA_TCHAN_RT_PEER_BCNT_REG); + udma_tchanrt_write(uc->tchan, UDMA_TCHAN_RT_PEER_BCNT_REG, val); + } + + if (uc->rchan) { + val = udma_rchanrt_read(uc->rchan, UDMA_RCHAN_RT_BCNT_REG); + udma_rchanrt_write(uc->rchan, UDMA_RCHAN_RT_BCNT_REG, val); + + val = udma_rchanrt_read(uc->rchan, UDMA_RCHAN_RT_SBCNT_REG); + udma_rchanrt_write(uc->rchan, UDMA_RCHAN_RT_SBCNT_REG, val); + + val = udma_rchanrt_read(uc->rchan, UDMA_RCHAN_RT_PCNT_REG); + udma_rchanrt_write(uc->rchan, UDMA_RCHAN_RT_PCNT_REG, val); + + val = udma_rchanrt_read(uc->rchan, UDMA_RCHAN_RT_PEER_BCNT_REG); + udma_rchanrt_write(uc->rchan, UDMA_RCHAN_RT_PEER_BCNT_REG, val); + } + + uc->bcnt = 0; +} + +static int udma_reset_chan(struct udma_chan *uc, bool hard) +{ + switch (uc->config.dir) { + case DMA_DEV_TO_MEM: + udma_rchanrt_write(uc->rchan, UDMA_RCHAN_RT_PEER_RT_EN_REG, 0); + udma_rchanrt_write(uc->rchan, UDMA_RCHAN_RT_CTL_REG, 0); + break; + case DMA_MEM_TO_DEV: + udma_tchanrt_write(uc->tchan, UDMA_TCHAN_RT_CTL_REG, 0); + udma_tchanrt_write(uc->tchan, UDMA_TCHAN_RT_PEER_RT_EN_REG, 0); + break; + case DMA_MEM_TO_MEM: + udma_rchanrt_write(uc->rchan, UDMA_RCHAN_RT_CTL_REG, 0); + udma_tchanrt_write(uc->tchan, UDMA_TCHAN_RT_CTL_REG, 0); + break; + default: + return -EINVAL; + } + + /* Reset all counters */ + udma_reset_counters(uc); + + /* Hard reset: re-initialize the channel to reset */ + if (hard) { + struct udma_chan_config ucc_backup; + int ret; + + memcpy(&ucc_backup, &uc->config, sizeof(uc->config)); + uc->ud->ddev.device_free_chan_resources(&uc->vc.chan); + + /* restore the channel configuration */ + memcpy(&uc->config, &ucc_backup, sizeof(uc->config)); + ret = uc->ud->ddev.device_alloc_chan_resources(&uc->vc.chan); + if (ret) + return ret; + + /* + * Setting forced teardown after forced reset helps recovering + * the rchan. + */ + if (uc->config.dir == DMA_DEV_TO_MEM) + udma_rchanrt_write(uc->rchan, UDMA_RCHAN_RT_CTL_REG, + UDMA_CHAN_RT_CTL_EN | + UDMA_CHAN_RT_CTL_TDOWN | + UDMA_CHAN_RT_CTL_FTDOWN); + } + uc->state = UDMA_CHAN_IS_IDLE; + + return 0; +} + +static void udma_start_desc(struct udma_chan *uc) +{ + struct udma_chan_config *ucc = &uc->config; + + if (ucc->pkt_mode && (uc->cyclic || ucc->dir == DMA_DEV_TO_MEM)) { + int i; + + /* Push all descriptors to ring for packet mode cyclic or RX */ + for (i = 0; i < uc->desc->sglen; i++) + udma_push_to_ring(uc, i); + } else { + udma_push_to_ring(uc, 0); + } +} + +static bool udma_chan_needs_reconfiguration(struct udma_chan *uc) +{ + /* Only PDMAs have staticTR */ + if (uc->config.ep_type == PSIL_EP_NATIVE) + return false; + + /* Check if the staticTR configuration has changed for TX */ + if (memcmp(&uc->static_tr, &uc->desc->static_tr, sizeof(uc->static_tr))) + return true; + + return false; +} + +static int udma_start(struct udma_chan *uc) +{ + struct virt_dma_desc *vd = vchan_next_desc(&uc->vc); + + if (!vd) { + uc->desc = NULL; + return -ENOENT; + } + + list_del(&vd->node); + + uc->desc = to_udma_desc(&vd->tx); + + /* Channel is already running and does not need reconfiguration */ + if (udma_is_chan_running(uc) && !udma_chan_needs_reconfiguration(uc)) { + udma_start_desc(uc); + goto out; + } + + /* Make sure that we clear the teardown bit, if it is set */ + udma_reset_chan(uc, false); + + /* Push descriptors before we start the channel */ + udma_start_desc(uc); + + switch (uc->desc->dir) { + case DMA_DEV_TO_MEM: + /* Config remote TR */ + if (uc->config.ep_type == PSIL_EP_PDMA_XY) { + u32 val = PDMA_STATIC_TR_Y(uc->desc->static_tr.elcnt) | + PDMA_STATIC_TR_X(uc->desc->static_tr.elsize); + const struct udma_match_data *match_data = + uc->ud->match_data; + + if (uc->config.enable_acc32) + val |= PDMA_STATIC_TR_XY_ACC32; + if (uc->config.enable_burst) + val |= PDMA_STATIC_TR_XY_BURST; + + udma_rchanrt_write(uc->rchan, + UDMA_RCHAN_RT_PEER_STATIC_TR_XY_REG, val); + + udma_rchanrt_write(uc->rchan, + UDMA_RCHAN_RT_PEER_STATIC_TR_Z_REG, + PDMA_STATIC_TR_Z(uc->desc->static_tr.bstcnt, + match_data->statictr_z_mask)); + + /* save the current staticTR configuration */ + memcpy(&uc->static_tr, &uc->desc->static_tr, + sizeof(uc->static_tr)); + } + + udma_rchanrt_write(uc->rchan, UDMA_RCHAN_RT_CTL_REG, + UDMA_CHAN_RT_CTL_EN); + + /* Enable remote */ + udma_rchanrt_write(uc->rchan, UDMA_RCHAN_RT_PEER_RT_EN_REG, + UDMA_PEER_RT_EN_ENABLE); + + break; + case DMA_MEM_TO_DEV: + /* Config remote TR */ + if (uc->config.ep_type == PSIL_EP_PDMA_XY) { + u32 val = PDMA_STATIC_TR_Y(uc->desc->static_tr.elcnt) | + PDMA_STATIC_TR_X(uc->desc->static_tr.elsize); + + if (uc->config.enable_acc32) + val |= PDMA_STATIC_TR_XY_ACC32; + if (uc->config.enable_burst) + val |= PDMA_STATIC_TR_XY_BURST; + + udma_tchanrt_write(uc->tchan, + UDMA_TCHAN_RT_PEER_STATIC_TR_XY_REG, val); + + /* save the current staticTR configuration */ + memcpy(&uc->static_tr, &uc->desc->static_tr, + sizeof(uc->static_tr)); + } + + /* Enable remote */ + udma_tchanrt_write(uc->tchan, UDMA_TCHAN_RT_PEER_RT_EN_REG, + UDMA_PEER_RT_EN_ENABLE); + + udma_tchanrt_write(uc->tchan, UDMA_TCHAN_RT_CTL_REG, + UDMA_CHAN_RT_CTL_EN); + + break; + case DMA_MEM_TO_MEM: + udma_rchanrt_write(uc->rchan, UDMA_RCHAN_RT_CTL_REG, + UDMA_CHAN_RT_CTL_EN); + udma_tchanrt_write(uc->tchan, UDMA_TCHAN_RT_CTL_REG, + UDMA_CHAN_RT_CTL_EN); + + break; + default: + return -EINVAL; + } + + uc->state = UDMA_CHAN_IS_ACTIVE; +out: + + return 0; +} + +static int udma_stop(struct udma_chan *uc) +{ + enum udma_chan_state old_state = uc->state; + + uc->state = UDMA_CHAN_IS_TERMINATING; + reinit_completion(&uc->teardown_completed); + + switch (uc->config.dir) { + case DMA_DEV_TO_MEM: + if (!uc->cyclic && !uc->desc) + udma_push_to_ring(uc, -1); + + udma_rchanrt_write(uc->rchan, UDMA_RCHAN_RT_PEER_RT_EN_REG, + UDMA_PEER_RT_EN_ENABLE | + UDMA_PEER_RT_EN_TEARDOWN); + break; + case DMA_MEM_TO_DEV: + udma_tchanrt_write(uc->tchan, UDMA_TCHAN_RT_PEER_RT_EN_REG, + UDMA_PEER_RT_EN_ENABLE | + UDMA_PEER_RT_EN_FLUSH); + udma_tchanrt_write(uc->tchan, UDMA_TCHAN_RT_CTL_REG, + UDMA_CHAN_RT_CTL_EN | + UDMA_CHAN_RT_CTL_TDOWN); + break; + case DMA_MEM_TO_MEM: + udma_tchanrt_write(uc->tchan, UDMA_TCHAN_RT_CTL_REG, + UDMA_CHAN_RT_CTL_EN | + UDMA_CHAN_RT_CTL_TDOWN); + break; + default: + uc->state = old_state; + complete_all(&uc->teardown_completed); + return -EINVAL; + } + + return 0; +} + +static void udma_cyclic_packet_elapsed(struct udma_chan *uc) +{ + struct udma_desc *d = uc->desc; + struct cppi5_host_desc_t *h_desc; + + h_desc = d->hwdesc[d->desc_idx].cppi5_desc_vaddr; + cppi5_hdesc_reset_to_original(h_desc); + udma_push_to_ring(uc, d->desc_idx); + d->desc_idx = (d->desc_idx + 1) % d->sglen; +} + +static inline void udma_fetch_epib(struct udma_chan *uc, struct udma_desc *d) +{ + struct cppi5_host_desc_t *h_desc = d->hwdesc[0].cppi5_desc_vaddr; + + memcpy(d->metadata, h_desc->epib, d->metadata_size); +} + +static bool udma_is_desc_really_done(struct udma_chan *uc, struct udma_desc *d) +{ + u32 peer_bcnt, bcnt; + + /* Only TX towards PDMA is affected */ + if (uc->config.ep_type == PSIL_EP_NATIVE || + uc->config.dir != DMA_MEM_TO_DEV) + return true; + + peer_bcnt = udma_tchanrt_read(uc->tchan, UDMA_TCHAN_RT_PEER_BCNT_REG); + bcnt = udma_tchanrt_read(uc->tchan, UDMA_TCHAN_RT_BCNT_REG); + + /* Transfer is incomplete, store current residue and time stamp */ + if (peer_bcnt < bcnt) { + uc->tx_drain.residue = bcnt - peer_bcnt; + uc->tx_drain.tstamp = ktime_get(); + return false; + } + + return true; +} + +static void udma_check_tx_completion(struct work_struct *work) +{ + struct udma_chan *uc = container_of(work, typeof(*uc), + tx_drain.work.work); + bool desc_done = true; + u32 residue_diff; + ktime_t time_diff; + unsigned long delay; + + while (1) { + if (uc->desc) { + /* Get previous residue and time stamp */ + residue_diff = uc->tx_drain.residue; + time_diff = uc->tx_drain.tstamp; + /* + * Get current residue and time stamp or see if + * transfer is complete + */ + desc_done = udma_is_desc_really_done(uc, uc->desc); + } + + if (!desc_done) { + /* + * Find the time delta and residue delta w.r.t + * previous poll + */ + time_diff = ktime_sub(uc->tx_drain.tstamp, + time_diff) + 1; + residue_diff -= uc->tx_drain.residue; + if (residue_diff) { + /* + * Try to guess when we should check + * next time by calculating rate at + * which data is being drained at the + * peer device + */ + delay = (time_diff / residue_diff) * + uc->tx_drain.residue; + } else { + /* No progress, check again in 1 second */ + schedule_delayed_work(&uc->tx_drain.work, HZ); + break; + } + + usleep_range(ktime_to_us(delay), + ktime_to_us(delay) + 10); + continue; + } + + if (uc->desc) { + struct udma_desc *d = uc->desc; + + uc->bcnt += d->residue; + udma_start(uc); + vchan_cookie_complete(&d->vd); + break; + } + + break; + } +} + +static irqreturn_t udma_ring_irq_handler(int irq, void *data) +{ + struct udma_chan *uc = data; + struct udma_desc *d; + unsigned long flags; + dma_addr_t paddr = 0; + + if (udma_pop_from_ring(uc, &paddr) || !paddr) + return IRQ_HANDLED; + + spin_lock_irqsave(&uc->vc.lock, flags); + + /* Teardown completion message */ + if (cppi5_desc_is_tdcm(paddr)) { + /* Compensate our internal pop/push counter */ + uc->in_ring_cnt++; + + complete_all(&uc->teardown_completed); + + if (uc->terminated_desc) { + udma_desc_free(&uc->terminated_desc->vd); + uc->terminated_desc = NULL; + } + + if (!uc->desc) + udma_start(uc); + + goto out; + } + + d = udma_udma_desc_from_paddr(uc, paddr); + + if (d) { + dma_addr_t desc_paddr = udma_curr_cppi5_desc_paddr(d, + d->desc_idx); + if (desc_paddr != paddr) { + dev_err(uc->ud->dev, "not matching descriptors!\n"); + goto out; + } + + if (d == uc->desc) { + /* active descriptor */ + if (uc->cyclic) { + udma_cyclic_packet_elapsed(uc); + vchan_cyclic_callback(&d->vd); + } else { + if (udma_is_desc_really_done(uc, d)) { + uc->bcnt += d->residue; + udma_start(uc); + vchan_cookie_complete(&d->vd); + } else { + schedule_delayed_work(&uc->tx_drain.work, + 0); + } + } + } else { + /* + * terminated descriptor, mark the descriptor as + * completed to update the channel's cookie marker + */ + dma_cookie_complete(&d->vd.tx); + } + } +out: + spin_unlock_irqrestore(&uc->vc.lock, flags); + + return IRQ_HANDLED; +} + +static irqreturn_t udma_udma_irq_handler(int irq, void *data) +{ + struct udma_chan *uc = data; + struct udma_desc *d; + unsigned long flags; + + spin_lock_irqsave(&uc->vc.lock, flags); + d = uc->desc; + if (d) { + d->tr_idx = (d->tr_idx + 1) % d->sglen; + + if (uc->cyclic) { + vchan_cyclic_callback(&d->vd); + } else { + /* TODO: figure out the real amount of data */ + uc->bcnt += d->residue; + udma_start(uc); + vchan_cookie_complete(&d->vd); + } + } + + spin_unlock_irqrestore(&uc->vc.lock, flags); + + return IRQ_HANDLED; +} + +/** + * __udma_alloc_gp_rflow_range - alloc range of GP RX flows + * @ud: UDMA device + * @from: Start the search from this flow id number + * @cnt: Number of consecutive flow ids to allocate + * + * Allocate range of RX flow ids for future use, those flows can be requested + * only using explicit flow id number. if @from is set to -1 it will try to find + * first free range. if @from is positive value it will force allocation only + * of the specified range of flows. + * + * Returns -ENOMEM if can't find free range. + * -EEXIST if requested range is busy. + * -EINVAL if wrong input values passed. + * Returns flow id on success. + */ +static int __udma_alloc_gp_rflow_range(struct udma_dev *ud, int from, int cnt) +{ + int start, tmp_from; + DECLARE_BITMAP(tmp, K3_UDMA_MAX_RFLOWS); + + tmp_from = from; + if (tmp_from < 0) + tmp_from = ud->rchan_cnt; + /* default flows can't be allocated and accessible only by id */ + if (tmp_from < ud->rchan_cnt) + return -EINVAL; + + if (tmp_from + cnt > ud->rflow_cnt) + return -EINVAL; + + bitmap_or(tmp, ud->rflow_gp_map, ud->rflow_gp_map_allocated, + ud->rflow_cnt); + + start = bitmap_find_next_zero_area(tmp, + ud->rflow_cnt, + tmp_from, cnt, 0); + if (start >= ud->rflow_cnt) + return -ENOMEM; + + if (from >= 0 && start != from) + return -EEXIST; + + bitmap_set(ud->rflow_gp_map_allocated, start, cnt); + return start; +} + +static int __udma_free_gp_rflow_range(struct udma_dev *ud, int from, int cnt) +{ + if (from < ud->rchan_cnt) + return -EINVAL; + if (from + cnt > ud->rflow_cnt) + return -EINVAL; + + bitmap_clear(ud->rflow_gp_map_allocated, from, cnt); + return 0; +} + +static struct udma_rflow *__udma_get_rflow(struct udma_dev *ud, int id) +{ + /* + * Attempt to request rflow by ID can be made for any rflow + * if not in use with assumption that caller knows what's doing. + * TI-SCI FW will perform additional permission check ant way, it's + * safe + */ + + if (id < 0 || id >= ud->rflow_cnt) + return ERR_PTR(-ENOENT); + + if (test_bit(id, ud->rflow_in_use)) + return ERR_PTR(-ENOENT); + + /* GP rflow has to be allocated first */ + if (!test_bit(id, ud->rflow_gp_map) && + !test_bit(id, ud->rflow_gp_map_allocated)) + return ERR_PTR(-EINVAL); + + dev_dbg(ud->dev, "get rflow%d\n", id); + set_bit(id, ud->rflow_in_use); + return &ud->rflows[id]; +} + +static void __udma_put_rflow(struct udma_dev *ud, struct udma_rflow *rflow) +{ + if (!test_bit(rflow->id, ud->rflow_in_use)) { + dev_err(ud->dev, "attempt to put unused rflow%d\n", rflow->id); + return; + } + + dev_dbg(ud->dev, "put rflow%d\n", rflow->id); + clear_bit(rflow->id, ud->rflow_in_use); +} + +#define UDMA_RESERVE_RESOURCE(res) \ +static struct udma_##res *__udma_reserve_##res(struct udma_dev *ud, \ + enum udma_tp_level tpl, \ + int id) \ +{ \ + if (id >= 0) { \ + if (test_bit(id, ud->res##_map)) { \ + dev_err(ud->dev, "res##%d is in use\n", id); \ + return ERR_PTR(-ENOENT); \ + } \ + } else { \ + int start; \ + \ + if (tpl >= ud->match_data->tpl_levels) \ + tpl = ud->match_data->tpl_levels - 1; \ + \ + start = ud->match_data->level_start_idx[tpl]; \ + \ + id = find_next_zero_bit(ud->res##_map, ud->res##_cnt, \ + start); \ + if (id == ud->res##_cnt) { \ + return ERR_PTR(-ENOENT); \ + } \ + } \ + \ + set_bit(id, ud->res##_map); \ + return &ud->res##s[id]; \ +} + +UDMA_RESERVE_RESOURCE(tchan); +UDMA_RESERVE_RESOURCE(rchan); + +static int udma_get_tchan(struct udma_chan *uc) +{ + struct udma_dev *ud = uc->ud; + + if (uc->tchan) { + dev_dbg(ud->dev, "chan%d: already have tchan%d allocated\n", + uc->id, uc->tchan->id); + return 0; + } + + uc->tchan = __udma_reserve_tchan(ud, uc->config.channel_tpl, -1); + if (IS_ERR(uc->tchan)) + return PTR_ERR(uc->tchan); + + return 0; +} + +static int udma_get_rchan(struct udma_chan *uc) +{ + struct udma_dev *ud = uc->ud; + + if (uc->rchan) { + dev_dbg(ud->dev, "chan%d: already have rchan%d allocated\n", + uc->id, uc->rchan->id); + return 0; + } + + uc->rchan = __udma_reserve_rchan(ud, uc->config.channel_tpl, -1); + if (IS_ERR(uc->rchan)) + return PTR_ERR(uc->rchan); + + return 0; +} + +static int udma_get_chan_pair(struct udma_chan *uc) +{ + struct udma_dev *ud = uc->ud; + const struct udma_match_data *match_data = ud->match_data; + int chan_id, end; + + if ((uc->tchan && uc->rchan) && uc->tchan->id == uc->rchan->id) { + dev_info(ud->dev, "chan%d: already have %d pair allocated\n", + uc->id, uc->tchan->id); + return 0; + } + + if (uc->tchan) { + dev_err(ud->dev, "chan%d: already have tchan%d allocated\n", + uc->id, uc->tchan->id); + return -EBUSY; + } else if (uc->rchan) { + dev_err(ud->dev, "chan%d: already have rchan%d allocated\n", + uc->id, uc->rchan->id); + return -EBUSY; + } + + /* Can be optimized, but let's have it like this for now */ + end = min(ud->tchan_cnt, ud->rchan_cnt); + /* Try to use the highest TPL channel pair for MEM_TO_MEM channels */ + chan_id = match_data->level_start_idx[match_data->tpl_levels - 1]; + for (; chan_id < end; chan_id++) { + if (!test_bit(chan_id, ud->tchan_map) && + !test_bit(chan_id, ud->rchan_map)) + break; + } + + if (chan_id == end) + return -ENOENT; + + set_bit(chan_id, ud->tchan_map); + set_bit(chan_id, ud->rchan_map); + uc->tchan = &ud->tchans[chan_id]; + uc->rchan = &ud->rchans[chan_id]; + + return 0; +} + +static int udma_get_rflow(struct udma_chan *uc, int flow_id) +{ + struct udma_dev *ud = uc->ud; + + if (!uc->rchan) { + dev_err(ud->dev, "chan%d: does not have rchan??\n", uc->id); + return -EINVAL; + } + + if (uc->rflow) { + dev_dbg(ud->dev, "chan%d: already have rflow%d allocated\n", + uc->id, uc->rflow->id); + return 0; + } + + uc->rflow = __udma_get_rflow(ud, flow_id); + if (IS_ERR(uc->rflow)) + return PTR_ERR(uc->rflow); + + return 0; +} + +static void udma_put_rchan(struct udma_chan *uc) +{ + struct udma_dev *ud = uc->ud; + + if (uc->rchan) { + dev_dbg(ud->dev, "chan%d: put rchan%d\n", uc->id, + uc->rchan->id); + clear_bit(uc->rchan->id, ud->rchan_map); + uc->rchan = NULL; + } +} + +static void udma_put_tchan(struct udma_chan *uc) +{ + struct udma_dev *ud = uc->ud; + + if (uc->tchan) { + dev_dbg(ud->dev, "chan%d: put tchan%d\n", uc->id, + uc->tchan->id); + clear_bit(uc->tchan->id, ud->tchan_map); + uc->tchan = NULL; + } +} + +static void udma_put_rflow(struct udma_chan *uc) +{ + struct udma_dev *ud = uc->ud; + + if (uc->rflow) { + dev_dbg(ud->dev, "chan%d: put rflow%d\n", uc->id, + uc->rflow->id); + __udma_put_rflow(ud, uc->rflow); + uc->rflow = NULL; + } +} + +static void udma_free_tx_resources(struct udma_chan *uc) +{ + if (!uc->tchan) + return; + + k3_ringacc_ring_free(uc->tchan->t_ring); + k3_ringacc_ring_free(uc->tchan->tc_ring); + uc->tchan->t_ring = NULL; + uc->tchan->tc_ring = NULL; + + udma_put_tchan(uc); +} + +static int udma_alloc_tx_resources(struct udma_chan *uc) +{ + struct k3_ring_cfg ring_cfg; + struct udma_dev *ud = uc->ud; + int ret; + + ret = udma_get_tchan(uc); + if (ret) + return ret; + + uc->tchan->t_ring = k3_ringacc_request_ring(ud->ringacc, + uc->tchan->id, 0); + if (!uc->tchan->t_ring) { + ret = -EBUSY; + goto err_tx_ring; + } + + uc->tchan->tc_ring = k3_ringacc_request_ring(ud->ringacc, -1, 0); + if (!uc->tchan->tc_ring) { + ret = -EBUSY; + goto err_txc_ring; + } + + memset(&ring_cfg, 0, sizeof(ring_cfg)); + ring_cfg.size = K3_UDMA_DEFAULT_RING_SIZE; + ring_cfg.elm_size = K3_RINGACC_RING_ELSIZE_8; + ring_cfg.mode = K3_RINGACC_RING_MODE_MESSAGE; + + ret = k3_ringacc_ring_cfg(uc->tchan->t_ring, &ring_cfg); + ret |= k3_ringacc_ring_cfg(uc->tchan->tc_ring, &ring_cfg); + + if (ret) + goto err_ringcfg; + + return 0; + +err_ringcfg: + k3_ringacc_ring_free(uc->tchan->tc_ring); + uc->tchan->tc_ring = NULL; +err_txc_ring: + k3_ringacc_ring_free(uc->tchan->t_ring); + uc->tchan->t_ring = NULL; +err_tx_ring: + udma_put_tchan(uc); + + return ret; +} + +static void udma_free_rx_resources(struct udma_chan *uc) +{ + if (!uc->rchan) + return; + + if (uc->rflow) { + struct udma_rflow *rflow = uc->rflow; + + k3_ringacc_ring_free(rflow->fd_ring); + k3_ringacc_ring_free(rflow->r_ring); + rflow->fd_ring = NULL; + rflow->r_ring = NULL; + + udma_put_rflow(uc); + } + + udma_put_rchan(uc); +} + +static int udma_alloc_rx_resources(struct udma_chan *uc) +{ + struct udma_dev *ud = uc->ud; + struct k3_ring_cfg ring_cfg; + struct udma_rflow *rflow; + int fd_ring_id; + int ret; + + ret = udma_get_rchan(uc); + if (ret) + return ret; + + /* For MEM_TO_MEM we don't need rflow or rings */ + if (uc->config.dir == DMA_MEM_TO_MEM) + return 0; + + ret = udma_get_rflow(uc, uc->rchan->id); + if (ret) { + ret = -EBUSY; + goto err_rflow; + } + + rflow = uc->rflow; + fd_ring_id = ud->tchan_cnt + ud->echan_cnt + uc->rchan->id; + rflow->fd_ring = k3_ringacc_request_ring(ud->ringacc, fd_ring_id, 0); + if (!rflow->fd_ring) { + ret = -EBUSY; + goto err_rx_ring; + } + + rflow->r_ring = k3_ringacc_request_ring(ud->ringacc, -1, 0); + if (!rflow->r_ring) { + ret = -EBUSY; + goto err_rxc_ring; + } + + memset(&ring_cfg, 0, sizeof(ring_cfg)); + + if (uc->config.pkt_mode) + ring_cfg.size = SG_MAX_SEGMENTS; + else + ring_cfg.size = K3_UDMA_DEFAULT_RING_SIZE; + + ring_cfg.elm_size = K3_RINGACC_RING_ELSIZE_8; + ring_cfg.mode = K3_RINGACC_RING_MODE_MESSAGE; + + ret = k3_ringacc_ring_cfg(rflow->fd_ring, &ring_cfg); + ring_cfg.size = K3_UDMA_DEFAULT_RING_SIZE; + ret |= k3_ringacc_ring_cfg(rflow->r_ring, &ring_cfg); + + if (ret) + goto err_ringcfg; + + return 0; + +err_ringcfg: + k3_ringacc_ring_free(rflow->r_ring); + rflow->r_ring = NULL; +err_rxc_ring: + k3_ringacc_ring_free(rflow->fd_ring); + rflow->fd_ring = NULL; +err_rx_ring: + udma_put_rflow(uc); +err_rflow: + udma_put_rchan(uc); + + return ret; +} + +#define TISCI_TCHAN_VALID_PARAMS ( \ + TI_SCI_MSG_VALUE_RM_UDMAP_CH_PAUSE_ON_ERR_VALID | \ + TI_SCI_MSG_VALUE_RM_UDMAP_CH_TX_FILT_EINFO_VALID | \ + TI_SCI_MSG_VALUE_RM_UDMAP_CH_TX_FILT_PSWORDS_VALID | \ + TI_SCI_MSG_VALUE_RM_UDMAP_CH_CHAN_TYPE_VALID | \ + TI_SCI_MSG_VALUE_RM_UDMAP_CH_TX_SUPR_TDPKT_VALID | \ + TI_SCI_MSG_VALUE_RM_UDMAP_CH_FETCH_SIZE_VALID | \ + TI_SCI_MSG_VALUE_RM_UDMAP_CH_CQ_QNUM_VALID) + +#define TISCI_RCHAN_VALID_PARAMS ( \ + TI_SCI_MSG_VALUE_RM_UDMAP_CH_PAUSE_ON_ERR_VALID | \ + TI_SCI_MSG_VALUE_RM_UDMAP_CH_FETCH_SIZE_VALID | \ + TI_SCI_MSG_VALUE_RM_UDMAP_CH_CQ_QNUM_VALID | \ + TI_SCI_MSG_VALUE_RM_UDMAP_CH_CHAN_TYPE_VALID | \ + TI_SCI_MSG_VALUE_RM_UDMAP_CH_RX_IGNORE_SHORT_VALID | \ + TI_SCI_MSG_VALUE_RM_UDMAP_CH_RX_IGNORE_LONG_VALID | \ + TI_SCI_MSG_VALUE_RM_UDMAP_CH_RX_FLOWID_START_VALID | \ + TI_SCI_MSG_VALUE_RM_UDMAP_CH_RX_FLOWID_CNT_VALID) + +static int udma_tisci_m2m_channel_config(struct udma_chan *uc) +{ + struct udma_dev *ud = uc->ud; + struct udma_tisci_rm *tisci_rm = &ud->tisci_rm; + 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; + 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 }; + + req_tx.valid_params = TISCI_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; + + ret = tisci_ops->tx_ch_cfg(tisci_rm->tisci, &req_tx); + if (ret) { + dev_err(ud->dev, "tchan%d cfg failed %d\n", tchan->id, ret); + return ret; + } + + req_rx.valid_params = TISCI_RCHAN_VALID_PARAMS; + req_rx.nav_id = tisci_rm->tisci_dev_id; + req_rx.index = rchan->id; + req_rx.rx_fetch_size = sizeof(struct cppi5_desc_hdr_t) >> 2; + req_rx.rxcq_qnum = tc_ring; + req_rx.rx_chan_type = TI_SCI_RM_UDMAP_CHAN_TYPE_3RDP_BCOPY_PBRR; + + ret = tisci_ops->rx_ch_cfg(tisci_rm->tisci, &req_rx); + if (ret) + dev_err(ud->dev, "rchan%d alloc failed %d\n", rchan->id, ret); + + return ret; +} + +static int udma_tisci_tx_channel_config(struct udma_chan *uc) +{ + struct udma_dev *ud = uc->ud; + struct udma_tisci_rm *tisci_rm = &ud->tisci_rm; + const struct ti_sci_rm_udmap_ops *tisci_ops = tisci_rm->tisci_udmap_ops; + struct udma_tchan *tchan = uc->tchan; + int tc_ring = k3_ringacc_get_ring_id(tchan->tc_ring); + struct ti_sci_msg_rm_udmap_tx_ch_cfg req_tx = { 0 }; + u32 mode, fetch_size; + int ret = 0; + + if (uc->config.pkt_mode) { + mode = TI_SCI_RM_UDMAP_CHAN_TYPE_PKT_PBRR; + fetch_size = cppi5_hdesc_calc_size(uc->config.needs_epib, + uc->config.psd_size, 0); + } else { + mode = TI_SCI_RM_UDMAP_CHAN_TYPE_3RDP_PBRR; + fetch_size = sizeof(struct cppi5_desc_hdr_t); + } + + req_tx.valid_params = TISCI_TCHAN_VALID_PARAMS; + req_tx.nav_id = tisci_rm->tisci_dev_id; + req_tx.index = tchan->id; + req_tx.tx_chan_type = mode; + req_tx.tx_supr_tdpkt = uc->config.notdpkt; + req_tx.tx_fetch_size = fetch_size >> 2; + req_tx.txcq_qnum = tc_ring; + + ret = tisci_ops->tx_ch_cfg(tisci_rm->tisci, &req_tx); + if (ret) + dev_err(ud->dev, "tchan%d cfg failed %d\n", tchan->id, ret); + + return ret; +} + +static int udma_tisci_rx_channel_config(struct udma_chan *uc) +{ + struct udma_dev *ud = uc->ud; + struct udma_tisci_rm *tisci_rm = &ud->tisci_rm; + const struct ti_sci_rm_udmap_ops *tisci_ops = tisci_rm->tisci_udmap_ops; + struct udma_rchan *rchan = uc->rchan; + int fd_ring = k3_ringacc_get_ring_id(uc->rflow->fd_ring); + int rx_ring = k3_ringacc_get_ring_id(uc->rflow->r_ring); + struct ti_sci_msg_rm_udmap_rx_ch_cfg req_rx = { 0 }; + struct ti_sci_msg_rm_udmap_flow_cfg flow_req = { 0 }; + u32 mode, fetch_size; + int ret = 0; + + if (uc->config.pkt_mode) { + mode = TI_SCI_RM_UDMAP_CHAN_TYPE_PKT_PBRR; + fetch_size = cppi5_hdesc_calc_size(uc->config.needs_epib, + uc->config.psd_size, 0); + } else { + mode = TI_SCI_RM_UDMAP_CHAN_TYPE_3RDP_PBRR; + fetch_size = sizeof(struct cppi5_desc_hdr_t); + } + + req_rx.valid_params = TISCI_RCHAN_VALID_PARAMS; + req_rx.nav_id = tisci_rm->tisci_dev_id; + req_rx.index = rchan->id; + req_rx.rx_fetch_size = fetch_size >> 2; + req_rx.rxcq_qnum = rx_ring; + req_rx.rx_chan_type = mode; + + ret = tisci_ops->rx_ch_cfg(tisci_rm->tisci, &req_rx); + if (ret) { + dev_err(ud->dev, "rchan%d cfg failed %d\n", rchan->id, ret); + return ret; + } + + flow_req.valid_params = + TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_EINFO_PRESENT_VALID | + TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_PSINFO_PRESENT_VALID | + TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_ERROR_HANDLING_VALID | + TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_DESC_TYPE_VALID | + TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_DEST_QNUM_VALID | + TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_SRC_TAG_HI_SEL_VALID | + TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_SRC_TAG_LO_SEL_VALID | + TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_DEST_TAG_HI_SEL_VALID | + TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_DEST_TAG_LO_SEL_VALID | + TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_FDQ0_SZ0_QNUM_VALID | + TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_FDQ1_QNUM_VALID | + TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_FDQ2_QNUM_VALID | + TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_FDQ3_QNUM_VALID; + + flow_req.nav_id = tisci_rm->tisci_dev_id; + flow_req.flow_index = rchan->id; + + if (uc->config.needs_epib) + flow_req.rx_einfo_present = 1; + else + flow_req.rx_einfo_present = 0; + if (uc->config.psd_size) + flow_req.rx_psinfo_present = 1; + else + flow_req.rx_psinfo_present = 0; + flow_req.rx_error_handling = 1; + flow_req.rx_dest_qnum = rx_ring; + flow_req.rx_src_tag_hi_sel = UDMA_RFLOW_SRCTAG_NONE; + flow_req.rx_src_tag_lo_sel = UDMA_RFLOW_SRCTAG_SRC_TAG; + flow_req.rx_dest_tag_hi_sel = UDMA_RFLOW_DSTTAG_DST_TAG_HI; + flow_req.rx_dest_tag_lo_sel = UDMA_RFLOW_DSTTAG_DST_TAG_LO; + flow_req.rx_fdq0_sz0_qnum = fd_ring; + flow_req.rx_fdq1_qnum = fd_ring; + flow_req.rx_fdq2_qnum = fd_ring; + flow_req.rx_fdq3_qnum = fd_ring; + + ret = tisci_ops->rx_flow_cfg(tisci_rm->tisci, &flow_req); + + if (ret) + dev_err(ud->dev, "flow%d config failed: %d\n", rchan->id, ret); + + return 0; +} + +static int udma_alloc_chan_resources(struct dma_chan *chan) +{ + struct udma_chan *uc = to_udma_chan(chan); + struct udma_dev *ud = to_udma_dev(chan->device); + const struct udma_match_data *match_data = ud->match_data; + struct k3_ring *irq_ring; + u32 irq_udma_idx; + int ret; + + if (uc->config.pkt_mode || uc->config.dir == DMA_MEM_TO_MEM) { + uc->use_dma_pool = true; + /* in case of MEM_TO_MEM we have maximum of two TRs */ + if (uc->config.dir == DMA_MEM_TO_MEM) { + uc->config.hdesc_size = cppi5_trdesc_calc_size( + sizeof(struct cppi5_tr_type15_t), 2); + uc->config.pkt_mode = false; + } + } + + if (uc->use_dma_pool) { + uc->hdesc_pool = dma_pool_create(uc->name, ud->ddev.dev, + uc->config.hdesc_size, + ud->desc_align, + 0); + if (!uc->hdesc_pool) { + dev_err(ud->ddev.dev, + "Descriptor pool allocation failed\n"); + uc->use_dma_pool = false; + return -ENOMEM; + } + } + + /* + * Make sure that the completion is in a known state: + * No teardown, the channel is idle + */ + reinit_completion(&uc->teardown_completed); + complete_all(&uc->teardown_completed); + uc->state = UDMA_CHAN_IS_IDLE; + + switch (uc->config.dir) { + case DMA_MEM_TO_MEM: + /* Non synchronized - mem to mem type of transfer */ + dev_dbg(uc->ud->dev, "%s: chan%d as MEM-to-MEM\n", __func__, + uc->id); + + ret = udma_get_chan_pair(uc); + if (ret) + return ret; + + ret = udma_alloc_tx_resources(uc); + if (ret) + return ret; + + ret = udma_alloc_rx_resources(uc); + if (ret) { + udma_free_tx_resources(uc); + return ret; + } + + uc->config.src_thread = ud->psil_base + uc->tchan->id; + uc->config.dst_thread = (ud->psil_base + uc->rchan->id) | + K3_PSIL_DST_THREAD_ID_OFFSET; + + irq_ring = uc->tchan->tc_ring; + irq_udma_idx = uc->tchan->id; + + ret = udma_tisci_m2m_channel_config(uc); + break; + case DMA_MEM_TO_DEV: + /* Slave transfer synchronized - mem to dev (TX) trasnfer */ + dev_dbg(uc->ud->dev, "%s: chan%d as MEM-to-DEV\n", __func__, + uc->id); + + ret = udma_alloc_tx_resources(uc); + if (ret) { + uc->config.remote_thread_id = -1; + return ret; + } + + uc->config.src_thread = ud->psil_base + uc->tchan->id; + uc->config.dst_thread = uc->config.remote_thread_id; + uc->config.dst_thread |= K3_PSIL_DST_THREAD_ID_OFFSET; + + irq_ring = uc->tchan->tc_ring; + irq_udma_idx = uc->tchan->id; + + ret = udma_tisci_tx_channel_config(uc); + break; + case DMA_DEV_TO_MEM: + /* Slave transfer synchronized - dev to mem (RX) trasnfer */ + dev_dbg(uc->ud->dev, "%s: chan%d as DEV-to-MEM\n", __func__, + uc->id); + + ret = udma_alloc_rx_resources(uc); + if (ret) { + uc->config.remote_thread_id = -1; + return ret; + } + + uc->config.src_thread = uc->config.remote_thread_id; + uc->config.dst_thread = (ud->psil_base + uc->rchan->id) | + K3_PSIL_DST_THREAD_ID_OFFSET; + + irq_ring = uc->rflow->r_ring; + irq_udma_idx = match_data->rchan_oes_offset + uc->rchan->id; + + ret = udma_tisci_rx_channel_config(uc); + break; + default: + /* Can not happen */ + dev_err(uc->ud->dev, "%s: chan%d invalid direction (%u)\n", + __func__, uc->id, uc->config.dir); + return -EINVAL; + } + + /* check if the channel configuration was successful */ + if (ret) + goto err_res_free; + + if (udma_is_chan_running(uc)) { + dev_warn(ud->dev, "chan%d: is running!\n", uc->id); + udma_stop(uc); + if (udma_is_chan_running(uc)) { + dev_err(ud->dev, "chan%d: won't stop!\n", uc->id); + goto err_res_free; + } + } + + /* PSI-L pairing */ + ret = navss_psil_pair(ud, uc->config.src_thread, uc->config.dst_thread); + if (ret) { + dev_err(ud->dev, "PSI-L pairing failed: 0x%04x -> 0x%04x\n", + uc->config.src_thread, uc->config.dst_thread); + goto err_res_free; + } + + uc->psil_paired = true; + + uc->irq_num_ring = k3_ringacc_get_ring_irq_num(irq_ring); + if (uc->irq_num_ring <= 0) { + dev_err(ud->dev, "Failed to get ring irq (index: %u)\n", + k3_ringacc_get_ring_id(irq_ring)); + ret = -EINVAL; + goto err_psi_free; + } + + ret = request_irq(uc->irq_num_ring, udma_ring_irq_handler, + IRQF_TRIGGER_HIGH, uc->name, uc); + if (ret) { + dev_err(ud->dev, "chan%d: ring irq request failed\n", uc->id); + goto err_irq_free; + } + + /* Event from UDMA (TR events) only needed for slave TR mode channels */ + if (is_slave_direction(uc->config.dir) && !uc->config.pkt_mode) { + uc->irq_num_udma = ti_sci_inta_msi_get_virq(ud->dev, + irq_udma_idx); + if (uc->irq_num_udma <= 0) { + dev_err(ud->dev, "Failed to get udma irq (index: %u)\n", + irq_udma_idx); + free_irq(uc->irq_num_ring, uc); + ret = -EINVAL; + goto err_irq_free; + } + + ret = request_irq(uc->irq_num_udma, udma_udma_irq_handler, 0, + uc->name, uc); + if (ret) { + dev_err(ud->dev, "chan%d: UDMA irq request failed\n", + uc->id); + free_irq(uc->irq_num_ring, uc); + goto err_irq_free; + } + } else { + uc->irq_num_udma = 0; + } + + udma_reset_rings(uc); + + INIT_DELAYED_WORK_ONSTACK(&uc->tx_drain.work, + udma_check_tx_completion); + return 0; + +err_irq_free: + uc->irq_num_ring = 0; + uc->irq_num_udma = 0; +err_psi_free: + navss_psil_unpair(ud, uc->config.src_thread, uc->config.dst_thread); + uc->psil_paired = false; +err_res_free: + udma_free_tx_resources(uc); + udma_free_rx_resources(uc); + + udma_reset_uchan(uc); + + if (uc->use_dma_pool) { + dma_pool_destroy(uc->hdesc_pool); + uc->use_dma_pool = false; + } + + return ret; +} + +static int udma_slave_config(struct dma_chan *chan, + struct dma_slave_config *cfg) +{ + struct udma_chan *uc = to_udma_chan(chan); + + memcpy(&uc->cfg, cfg, sizeof(uc->cfg)); + + return 0; +} + +static struct udma_desc *udma_alloc_tr_desc(struct udma_chan *uc, + size_t tr_size, int tr_count, + enum dma_transfer_direction dir) +{ + struct udma_hwdesc *hwdesc; + struct cppi5_desc_hdr_t *tr_desc; + struct udma_desc *d; + u32 reload_count = 0; + u32 ring_id; + + switch (tr_size) { + case 16: + case 32: + case 64: + case 128: + break; + default: + dev_err(uc->ud->dev, "Unsupported TR size of %zu\n", tr_size); + return NULL; + } + + /* We have only one descriptor containing multiple TRs */ + d = kzalloc(sizeof(*d) + sizeof(d->hwdesc[0]), GFP_NOWAIT); + if (!d) + return NULL; + + d->sglen = tr_count; + + d->hwdesc_count = 1; + hwdesc = &d->hwdesc[0]; + + /* Allocate memory for DMA ring descriptor */ + if (uc->use_dma_pool) { + hwdesc->cppi5_desc_size = uc->config.hdesc_size; + hwdesc->cppi5_desc_vaddr = dma_pool_zalloc(uc->hdesc_pool, + GFP_NOWAIT, + &hwdesc->cppi5_desc_paddr); + } else { + hwdesc->cppi5_desc_size = cppi5_trdesc_calc_size(tr_size, + tr_count); + hwdesc->cppi5_desc_size = ALIGN(hwdesc->cppi5_desc_size, + uc->ud->desc_align); + hwdesc->cppi5_desc_vaddr = dma_alloc_coherent(uc->ud->dev, + hwdesc->cppi5_desc_size, + &hwdesc->cppi5_desc_paddr, + GFP_NOWAIT); + } + + if (!hwdesc->cppi5_desc_vaddr) { + kfree(d); + return NULL; + } + + /* Start of the TR req records */ + hwdesc->tr_req_base = hwdesc->cppi5_desc_vaddr + tr_size; + /* Start address of the TR response array */ + hwdesc->tr_resp_base = hwdesc->tr_req_base + tr_size * tr_count; + + tr_desc = hwdesc->cppi5_desc_vaddr; + + if (uc->cyclic) + reload_count = CPPI5_INFO0_TRDESC_RLDCNT_INFINITE; + + if (dir == DMA_DEV_TO_MEM) + ring_id = k3_ringacc_get_ring_id(uc->rflow->r_ring); + else + ring_id = k3_ringacc_get_ring_id(uc->tchan->tc_ring); + + cppi5_trdesc_init(tr_desc, tr_count, tr_size, 0, reload_count); + cppi5_desc_set_pktids(tr_desc, uc->id, + CPPI5_INFO1_DESC_FLOWID_DEFAULT); + cppi5_desc_set_retpolicy(tr_desc, 0, ring_id); + + return d; +} + +/** + * udma_get_tr_counters - calculate TR counters for a given length + * @len: Length of the trasnfer + * @align_to: Preferred alignment + * @tr0_cnt0: First TR icnt0 + * @tr0_cnt1: First TR icnt1 + * @tr1_cnt0: Second (if used) TR icnt0 + * + * For len < SZ_64K only one TR is enough, tr1_cnt0 is not updated + * For len >= SZ_64K two TRs are used in a simple way: + * First TR: SZ_64K-alignment blocks (tr0_cnt0, tr0_cnt1) + * Second TR: the remaining length (tr1_cnt0) + * + * Returns the number of TRs the length needs (1 or 2) + * -EINVAL if the length can not be supported + */ +static int udma_get_tr_counters(size_t len, unsigned long align_to, + u16 *tr0_cnt0, u16 *tr0_cnt1, u16 *tr1_cnt0) +{ + if (len < SZ_64K) { + *tr0_cnt0 = len; + *tr0_cnt1 = 1; + + return 1; + } + + if (align_to > 3) + align_to = 3; + +realign: + *tr0_cnt0 = SZ_64K - BIT(align_to); + if (len / *tr0_cnt0 >= SZ_64K) { + if (align_to) { + align_to--; + goto realign; + } + return -EINVAL; + } + + *tr0_cnt1 = len / *tr0_cnt0; + *tr1_cnt0 = len % *tr0_cnt0; + + return 2; +} + +static struct udma_desc * +udma_prep_slave_sg_tr(struct udma_chan *uc, struct scatterlist *sgl, + unsigned int sglen, enum dma_transfer_direction dir, + unsigned long tx_flags, void *context) +{ + struct scatterlist *sgent; + struct udma_desc *d; + struct cppi5_tr_type1_t *tr_req = NULL; + u16 tr0_cnt0, tr0_cnt1, tr1_cnt0; + unsigned int i; + size_t tr_size; + int num_tr = 0; + int tr_idx = 0; + + if (!is_slave_direction(dir)) { + dev_err(uc->ud->dev, "Only slave cyclic is supported\n"); + return NULL; + } + + /* estimate the number of TRs we will need */ + for_each_sg(sgl, sgent, sglen, i) { + if (sg_dma_len(sgent) < SZ_64K) + num_tr++; + else + num_tr += 2; + } + + /* Now allocate and setup the descriptor. */ + tr_size = sizeof(struct cppi5_tr_type1_t); + d = udma_alloc_tr_desc(uc, tr_size, num_tr, dir); + if (!d) + return NULL; + + d->sglen = sglen; + + tr_req = d->hwdesc[0].tr_req_base; + for_each_sg(sgl, sgent, sglen, i) { + dma_addr_t sg_addr = sg_dma_address(sgent); + + num_tr = udma_get_tr_counters(sg_dma_len(sgent), __ffs(sg_addr), + &tr0_cnt0, &tr0_cnt1, &tr1_cnt0); + if (num_tr < 0) { + dev_err(uc->ud->dev, "size %u is not supported\n", + sg_dma_len(sgent)); + udma_free_hwdesc(uc, d); + kfree(d); + return NULL; + } + + cppi5_tr_init(&tr_req[i].flags, CPPI5_TR_TYPE1, false, false, + CPPI5_TR_EVENT_SIZE_COMPLETION, 0); + cppi5_tr_csf_set(&tr_req[i].flags, CPPI5_TR_CSF_SUPR_EVT); + + tr_req[tr_idx].addr = sg_addr; + tr_req[tr_idx].icnt0 = tr0_cnt0; + tr_req[tr_idx].icnt1 = tr0_cnt1; + tr_req[tr_idx].dim1 = tr0_cnt0; + tr_idx++; + + if (num_tr == 2) { + cppi5_tr_init(&tr_req[tr_idx].flags, CPPI5_TR_TYPE1, + false, false, + CPPI5_TR_EVENT_SIZE_COMPLETION, 0); + cppi5_tr_csf_set(&tr_req[tr_idx].flags, + CPPI5_TR_CSF_SUPR_EVT); + + tr_req[tr_idx].addr = sg_addr + tr0_cnt1 * tr0_cnt0; + tr_req[tr_idx].icnt0 = tr1_cnt0; + tr_req[tr_idx].icnt1 = 1; + tr_req[tr_idx].dim1 = tr1_cnt0; + tr_idx++; + } + + d->residue += sg_dma_len(sgent); + } + + cppi5_tr_csf_set(&tr_req[tr_idx - 1].flags, CPPI5_TR_CSF_EOP); + + return d; +} + +static int udma_configure_statictr(struct udma_chan *uc, struct udma_desc *d, + enum dma_slave_buswidth dev_width, + u16 elcnt) +{ + if (uc->config.ep_type != PSIL_EP_PDMA_XY) + return 0; + + /* Bus width translates to the element size (ES) */ + switch (dev_width) { + case DMA_SLAVE_BUSWIDTH_1_BYTE: + d->static_tr.elsize = 0; + break; + case DMA_SLAVE_BUSWIDTH_2_BYTES: + d->static_tr.elsize = 1; + break; + case DMA_SLAVE_BUSWIDTH_3_BYTES: + d->static_tr.elsize = 2; + break; + case DMA_SLAVE_BUSWIDTH_4_BYTES: + d->static_tr.elsize = 3; + break; + case DMA_SLAVE_BUSWIDTH_8_BYTES: + d->static_tr.elsize = 4; + break; + default: /* not reached */ + return -EINVAL; + } + + d->static_tr.elcnt = elcnt; + + /* + * PDMA must to close the packet when the channel is in packet mode. + * For TR mode when the channel is not cyclic we also need PDMA to close + * the packet otherwise the transfer will stall because PDMA holds on + * the data it has received from the peripheral. + */ + if (uc->config.pkt_mode || !uc->cyclic) { + unsigned int div = dev_width * elcnt; + + if (uc->cyclic) + d->static_tr.bstcnt = d->residue / d->sglen / div; + else + d->static_tr.bstcnt = d->residue / div; + + if (uc->config.dir == DMA_DEV_TO_MEM && + d->static_tr.bstcnt > uc->ud->match_data->statictr_z_mask) + return -EINVAL; + } else { + d->static_tr.bstcnt = 0; + } + + return 0; +} + +static struct udma_desc * +udma_prep_slave_sg_pkt(struct udma_chan *uc, struct scatterlist *sgl, + unsigned int sglen, enum dma_transfer_direction dir, + unsigned long tx_flags, void *context) +{ + struct scatterlist *sgent; + struct cppi5_host_desc_t *h_desc = NULL; + struct udma_desc *d; + u32 ring_id; + unsigned int i; + + d = kzalloc(sizeof(*d) + sglen * sizeof(d->hwdesc[0]), GFP_NOWAIT); + if (!d) + return NULL; + + d->sglen = sglen; + d->hwdesc_count = sglen; + + if (dir == DMA_DEV_TO_MEM) + ring_id = k3_ringacc_get_ring_id(uc->rflow->r_ring); + else + ring_id = k3_ringacc_get_ring_id(uc->tchan->tc_ring); + + for_each_sg(sgl, sgent, sglen, i) { + struct udma_hwdesc *hwdesc = &d->hwdesc[i]; + dma_addr_t sg_addr = sg_dma_address(sgent); + struct cppi5_host_desc_t *desc; + size_t sg_len = sg_dma_len(sgent); + + hwdesc->cppi5_desc_vaddr = dma_pool_zalloc(uc->hdesc_pool, + GFP_NOWAIT, + &hwdesc->cppi5_desc_paddr); + if (!hwdesc->cppi5_desc_vaddr) { + dev_err(uc->ud->dev, + "descriptor%d allocation failed\n", i); + + udma_free_hwdesc(uc, d); + kfree(d); + return NULL; + } + + d->residue += sg_len; + hwdesc->cppi5_desc_size = uc->config.hdesc_size; + desc = hwdesc->cppi5_desc_vaddr; + + if (i == 0) { + cppi5_hdesc_init(desc, 0, 0); + /* Flow and Packed ID */ + cppi5_desc_set_pktids(&desc->hdr, uc->id, + CPPI5_INFO1_DESC_FLOWID_DEFAULT); + cppi5_desc_set_retpolicy(&desc->hdr, 0, ring_id); + } else { + cppi5_hdesc_reset_hbdesc(desc); + cppi5_desc_set_retpolicy(&desc->hdr, 0, 0xffff); + } + + /* attach the sg buffer to the descriptor */ + cppi5_hdesc_attach_buf(desc, sg_addr, sg_len, sg_addr, sg_len); + + /* Attach link as host buffer descriptor */ + if (h_desc) + cppi5_hdesc_link_hbdesc(h_desc, + hwdesc->cppi5_desc_paddr); + + if (dir == DMA_MEM_TO_DEV) + h_desc = desc; + } + + if (d->residue >= SZ_4M) { + dev_err(uc->ud->dev, + "%s: Transfer size %u is over the supported 4M range\n", + __func__, d->residue); + udma_free_hwdesc(uc, d); + kfree(d); + return NULL; + } + + h_desc = d->hwdesc[0].cppi5_desc_vaddr; + cppi5_hdesc_set_pktlen(h_desc, d->residue); + + return d; +} + +static int udma_attach_metadata(struct dma_async_tx_descriptor *desc, + void *data, size_t len) +{ + struct udma_desc *d = to_udma_desc(desc); + struct udma_chan *uc = to_udma_chan(desc->chan); + struct cppi5_host_desc_t *h_desc; + u32 psd_size = len; + u32 flags = 0; + + if (!uc->config.pkt_mode || !uc->config.metadata_size) + return -ENOTSUPP; + + if (!data || len > uc->config.metadata_size) + return -EINVAL; + + if (uc->config.needs_epib && len < CPPI5_INFO0_HDESC_EPIB_SIZE) + return -EINVAL; + + h_desc = d->hwdesc[0].cppi5_desc_vaddr; + if (d->dir == DMA_MEM_TO_DEV) + memcpy(h_desc->epib, data, len); + + if (uc->config.needs_epib) + psd_size -= CPPI5_INFO0_HDESC_EPIB_SIZE; + + d->metadata = data; + d->metadata_size = len; + if (uc->config.needs_epib) + flags |= CPPI5_INFO0_HDESC_EPIB_PRESENT; + + cppi5_hdesc_update_flags(h_desc, flags); + cppi5_hdesc_update_psdata_size(h_desc, psd_size); + + return 0; +} + +static void *udma_get_metadata_ptr(struct dma_async_tx_descriptor *desc, + size_t *payload_len, size_t *max_len) +{ + struct udma_desc *d = to_udma_desc(desc); + struct udma_chan *uc = to_udma_chan(desc->chan); + struct cppi5_host_desc_t *h_desc; + + if (!uc->config.pkt_mode || !uc->config.metadata_size) + return ERR_PTR(-ENOTSUPP); + + h_desc = d->hwdesc[0].cppi5_desc_vaddr; + + *max_len = uc->config.metadata_size; + + *payload_len = cppi5_hdesc_epib_present(&h_desc->hdr) ? + CPPI5_INFO0_HDESC_EPIB_SIZE : 0; + *payload_len += cppi5_hdesc_get_psdata_size(h_desc); + + return h_desc->epib; +} + +static int udma_set_metadata_len(struct dma_async_tx_descriptor *desc, + size_t payload_len) +{ + struct udma_desc *d = to_udma_desc(desc); + struct udma_chan *uc = to_udma_chan(desc->chan); + struct cppi5_host_desc_t *h_desc; + u32 psd_size = payload_len; + u32 flags = 0; + + if (!uc->config.pkt_mode || !uc->config.metadata_size) + return -ENOTSUPP; + + if (payload_len > uc->config.metadata_size) + return -EINVAL; + + if (uc->config.needs_epib && payload_len < CPPI5_INFO0_HDESC_EPIB_SIZE) + return -EINVAL; + + h_desc = d->hwdesc[0].cppi5_desc_vaddr; + + if (uc->config.needs_epib) { + psd_size -= CPPI5_INFO0_HDESC_EPIB_SIZE; + flags |= CPPI5_INFO0_HDESC_EPIB_PRESENT; + } + + cppi5_hdesc_update_flags(h_desc, flags); + cppi5_hdesc_update_psdata_size(h_desc, psd_size); + + return 0; +} + +static struct dma_descriptor_metadata_ops metadata_ops = { + .attach = udma_attach_metadata, + .get_ptr = udma_get_metadata_ptr, + .set_len = udma_set_metadata_len, +}; + +static struct dma_async_tx_descriptor * +udma_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl, + unsigned int sglen, enum dma_transfer_direction dir, + unsigned long tx_flags, void *context) +{ + struct udma_chan *uc = to_udma_chan(chan); + enum dma_slave_buswidth dev_width; + struct udma_desc *d; + u32 burst; + + if (dir != uc->config.dir) { + dev_err(chan->device->dev, + "%s: chan%d is for %s, not supporting %s\n", + __func__, uc->id, + dmaengine_get_direction_text(uc->config.dir), + dmaengine_get_direction_text(dir)); + return NULL; + } + + if (dir == DMA_DEV_TO_MEM) { + dev_width = uc->cfg.src_addr_width; + burst = uc->cfg.src_maxburst; + } else if (dir == DMA_MEM_TO_DEV) { + dev_width = uc->cfg.dst_addr_width; + burst = uc->cfg.dst_maxburst; + } else { + dev_err(chan->device->dev, "%s: bad direction?\n", __func__); + return NULL; + } + + if (!burst) + burst = 1; + + if (uc->config.pkt_mode) + d = udma_prep_slave_sg_pkt(uc, sgl, sglen, dir, tx_flags, + context); + else + d = udma_prep_slave_sg_tr(uc, sgl, sglen, dir, tx_flags, + context); + + if (!d) + return NULL; + + d->dir = dir; + d->desc_idx = 0; + d->tr_idx = 0; + + /* static TR for remote PDMA */ + if (udma_configure_statictr(uc, d, dev_width, burst)) { + dev_err(uc->ud->dev, + "%s: StaticTR Z is limited to maximum 4095 (%u)\n", + __func__, d->static_tr.bstcnt); + + udma_free_hwdesc(uc, d); + kfree(d); + return NULL; + } + + if (uc->config.metadata_size) + d->vd.tx.metadata_ops = &metadata_ops; + + return vchan_tx_prep(&uc->vc, &d->vd, tx_flags); +} + +static struct udma_desc * +udma_prep_dma_cyclic_tr(struct udma_chan *uc, dma_addr_t buf_addr, + size_t buf_len, size_t period_len, + enum dma_transfer_direction dir, unsigned long flags) +{ + struct udma_desc *d; + size_t tr_size, period_addr; + struct cppi5_tr_type1_t *tr_req; + unsigned int periods = buf_len / period_len; + u16 tr0_cnt0, tr0_cnt1, tr1_cnt0; + unsigned int i; + int num_tr; + + if (!is_slave_direction(dir)) { + dev_err(uc->ud->dev, "Only slave cyclic is supported\n"); + return NULL; + } + + num_tr = udma_get_tr_counters(period_len, __ffs(buf_addr), &tr0_cnt0, + &tr0_cnt1, &tr1_cnt0); + if (num_tr < 0) { + dev_err(uc->ud->dev, "size %zu is not supported\n", + period_len); + return NULL; + } + + /* Now allocate and setup the descriptor. */ + tr_size = sizeof(struct cppi5_tr_type1_t); + d = udma_alloc_tr_desc(uc, tr_size, periods * num_tr, dir); + if (!d) + return NULL; + + tr_req = d->hwdesc[0].tr_req_base; + period_addr = buf_addr; + for (i = 0; i < periods; i++) { + int tr_idx = i * num_tr; + + cppi5_tr_init(&tr_req[tr_idx].flags, CPPI5_TR_TYPE1, false, + false, CPPI5_TR_EVENT_SIZE_COMPLETION, 0); + + tr_req[tr_idx].addr = period_addr; + tr_req[tr_idx].icnt0 = tr0_cnt0; + tr_req[tr_idx].icnt1 = tr0_cnt1; + tr_req[tr_idx].dim1 = tr0_cnt0; + + if (num_tr == 2) { + cppi5_tr_csf_set(&tr_req[tr_idx].flags, + CPPI5_TR_CSF_SUPR_EVT); + tr_idx++; + + cppi5_tr_init(&tr_req[tr_idx].flags, CPPI5_TR_TYPE1, + false, false, + CPPI5_TR_EVENT_SIZE_COMPLETION, 0); + + tr_req[tr_idx].addr = period_addr + tr0_cnt1 * tr0_cnt0; + tr_req[tr_idx].icnt0 = tr1_cnt0; + tr_req[tr_idx].icnt1 = 1; + tr_req[tr_idx].dim1 = tr1_cnt0; + } + + if (!(flags & DMA_PREP_INTERRUPT)) + cppi5_tr_csf_set(&tr_req[tr_idx].flags, + CPPI5_TR_CSF_SUPR_EVT); + + period_addr += period_len; + } + + return d; +} + +static struct udma_desc * +udma_prep_dma_cyclic_pkt(struct udma_chan *uc, dma_addr_t buf_addr, + size_t buf_len, size_t period_len, + enum dma_transfer_direction dir, unsigned long flags) +{ + struct udma_desc *d; + u32 ring_id; + int i; + int periods = buf_len / period_len; + + if (periods > (K3_UDMA_DEFAULT_RING_SIZE - 1)) + return NULL; + + if (period_len >= SZ_4M) + return NULL; + + d = kzalloc(sizeof(*d) + periods * sizeof(d->hwdesc[0]), GFP_NOWAIT); + if (!d) + return NULL; + + d->hwdesc_count = periods; + + /* TODO: re-check this... */ + if (dir == DMA_DEV_TO_MEM) + ring_id = k3_ringacc_get_ring_id(uc->rflow->r_ring); + else + ring_id = k3_ringacc_get_ring_id(uc->tchan->tc_ring); + + for (i = 0; i < periods; i++) { + struct udma_hwdesc *hwdesc = &d->hwdesc[i]; + dma_addr_t period_addr = buf_addr + (period_len * i); + struct cppi5_host_desc_t *h_desc; + + hwdesc->cppi5_desc_vaddr = dma_pool_zalloc(uc->hdesc_pool, + GFP_NOWAIT, + &hwdesc->cppi5_desc_paddr); + if (!hwdesc->cppi5_desc_vaddr) { + dev_err(uc->ud->dev, + "descriptor%d allocation failed\n", i); + + udma_free_hwdesc(uc, d); + kfree(d); + return NULL; + } + + hwdesc->cppi5_desc_size = uc->config.hdesc_size; + h_desc = hwdesc->cppi5_desc_vaddr; + + cppi5_hdesc_init(h_desc, 0, 0); + cppi5_hdesc_set_pktlen(h_desc, period_len); + + /* Flow and Packed ID */ + cppi5_desc_set_pktids(&h_desc->hdr, uc->id, + CPPI5_INFO1_DESC_FLOWID_DEFAULT); + cppi5_desc_set_retpolicy(&h_desc->hdr, 0, ring_id); + + /* attach each period to a new descriptor */ + cppi5_hdesc_attach_buf(h_desc, + period_addr, period_len, + period_addr, period_len); + } + + return d; +} + +static struct dma_async_tx_descriptor * +udma_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len, + size_t period_len, enum dma_transfer_direction dir, + unsigned long flags) +{ + struct udma_chan *uc = to_udma_chan(chan); + enum dma_slave_buswidth dev_width; + struct udma_desc *d; + u32 burst; + + if (dir != uc->config.dir) { + dev_err(chan->device->dev, + "%s: chan%d is for %s, not supporting %s\n", + __func__, uc->id, + dmaengine_get_direction_text(uc->config.dir), + dmaengine_get_direction_text(dir)); + return NULL; + } + + uc->cyclic = true; + + if (dir == DMA_DEV_TO_MEM) { + dev_width = uc->cfg.src_addr_width; + burst = uc->cfg.src_maxburst; + } else if (dir == DMA_MEM_TO_DEV) { + dev_width = uc->cfg.dst_addr_width; + burst = uc->cfg.dst_maxburst; + } else { + dev_err(uc->ud->dev, "%s: bad direction?\n", __func__); + return NULL; + } + + if (!burst) + burst = 1; + + if (uc->config.pkt_mode) + d = udma_prep_dma_cyclic_pkt(uc, buf_addr, buf_len, period_len, + dir, flags); + else + d = udma_prep_dma_cyclic_tr(uc, buf_addr, buf_len, period_len, + dir, flags); + + if (!d) + return NULL; + + d->sglen = buf_len / period_len; + + d->dir = dir; + d->residue = buf_len; + + /* static TR for remote PDMA */ + if (udma_configure_statictr(uc, d, dev_width, burst)) { + dev_err(uc->ud->dev, + "%s: StaticTR Z is limited to maximum 4095 (%u)\n", + __func__, d->static_tr.bstcnt); + + udma_free_hwdesc(uc, d); + kfree(d); + return NULL; + } + + if (uc->config.metadata_size) + d->vd.tx.metadata_ops = &metadata_ops; + + return vchan_tx_prep(&uc->vc, &d->vd, flags); +} + +static struct dma_async_tx_descriptor * +udma_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src, + size_t len, unsigned long tx_flags) +{ + struct udma_chan *uc = to_udma_chan(chan); + struct udma_desc *d; + struct cppi5_tr_type15_t *tr_req; + int num_tr; + size_t tr_size = sizeof(struct cppi5_tr_type15_t); + u16 tr0_cnt0, tr0_cnt1, tr1_cnt0; + + if (uc->config.dir != DMA_MEM_TO_MEM) { + dev_err(chan->device->dev, + "%s: chan%d is for %s, not supporting %s\n", + __func__, uc->id, + dmaengine_get_direction_text(uc->config.dir), + dmaengine_get_direction_text(DMA_MEM_TO_MEM)); + return NULL; + } + + num_tr = udma_get_tr_counters(len, __ffs(src | dest), &tr0_cnt0, + &tr0_cnt1, &tr1_cnt0); + if (num_tr < 0) { + dev_err(uc->ud->dev, "size %zu is not supported\n", + len); + return NULL; + } + + d = udma_alloc_tr_desc(uc, tr_size, num_tr, DMA_MEM_TO_MEM); + if (!d) + return NULL; + + d->dir = DMA_MEM_TO_MEM; + d->desc_idx = 0; + d->tr_idx = 0; + d->residue = len; + + tr_req = d->hwdesc[0].tr_req_base; + + cppi5_tr_init(&tr_req[0].flags, CPPI5_TR_TYPE15, false, true, + CPPI5_TR_EVENT_SIZE_COMPLETION, 0); + cppi5_tr_csf_set(&tr_req[0].flags, CPPI5_TR_CSF_SUPR_EVT); + + tr_req[0].addr = src; + tr_req[0].icnt0 = tr0_cnt0; + tr_req[0].icnt1 = tr0_cnt1; + tr_req[0].icnt2 = 1; + tr_req[0].icnt3 = 1; + tr_req[0].dim1 = tr0_cnt0; + + tr_req[0].daddr = dest; + tr_req[0].dicnt0 = tr0_cnt0; + tr_req[0].dicnt1 = tr0_cnt1; + tr_req[0].dicnt2 = 1; + tr_req[0].dicnt3 = 1; + tr_req[0].ddim1 = tr0_cnt0; + + if (num_tr == 2) { + cppi5_tr_init(&tr_req[1].flags, CPPI5_TR_TYPE15, false, true, + CPPI5_TR_EVENT_SIZE_COMPLETION, 0); + cppi5_tr_csf_set(&tr_req[1].flags, CPPI5_TR_CSF_SUPR_EVT); + + tr_req[1].addr = src + tr0_cnt1 * tr0_cnt0; + tr_req[1].icnt0 = tr1_cnt0; + tr_req[1].icnt1 = 1; + tr_req[1].icnt2 = 1; + tr_req[1].icnt3 = 1; + + tr_req[1].daddr = dest + tr0_cnt1 * tr0_cnt0; + tr_req[1].dicnt0 = tr1_cnt0; + tr_req[1].dicnt1 = 1; + tr_req[1].dicnt2 = 1; + tr_req[1].dicnt3 = 1; + } + + cppi5_tr_csf_set(&tr_req[num_tr - 1].flags, CPPI5_TR_CSF_EOP); + + if (uc->config.metadata_size) + d->vd.tx.metadata_ops = &metadata_ops; + + return vchan_tx_prep(&uc->vc, &d->vd, tx_flags); +} + +static void udma_issue_pending(struct dma_chan *chan) +{ + struct udma_chan *uc = to_udma_chan(chan); + unsigned long flags; + + spin_lock_irqsave(&uc->vc.lock, flags); + + /* If we have something pending and no active descriptor, then */ + if (vchan_issue_pending(&uc->vc) && !uc->desc) { + /* + * start a descriptor if the channel is NOT [marked as + * terminating _and_ it is still running (teardown has not + * completed yet)]. + */ + if (!(uc->state == UDMA_CHAN_IS_TERMINATING && + udma_is_chan_running(uc))) + udma_start(uc); + } + + spin_unlock_irqrestore(&uc->vc.lock, flags); +} + +static enum dma_status udma_tx_status(struct dma_chan *chan, + dma_cookie_t cookie, + struct dma_tx_state *txstate) +{ + struct udma_chan *uc = to_udma_chan(chan); + enum dma_status ret; + unsigned long flags; + + spin_lock_irqsave(&uc->vc.lock, flags); + + ret = dma_cookie_status(chan, cookie, txstate); + + if (!udma_is_chan_running(uc)) + ret = DMA_COMPLETE; + + if (ret == DMA_IN_PROGRESS && udma_is_chan_paused(uc)) + ret = DMA_PAUSED; + + if (ret == DMA_COMPLETE || !txstate) + goto out; + + if (uc->desc && uc->desc->vd.tx.cookie == cookie) { + u32 peer_bcnt = 0; + u32 bcnt = 0; + u32 residue = uc->desc->residue; + u32 delay = 0; + + if (uc->desc->dir == DMA_MEM_TO_DEV) { + bcnt = udma_tchanrt_read(uc->tchan, + UDMA_TCHAN_RT_SBCNT_REG); + + if (uc->config.ep_type != PSIL_EP_NATIVE) { + peer_bcnt = udma_tchanrt_read(uc->tchan, + UDMA_TCHAN_RT_PEER_BCNT_REG); + + if (bcnt > peer_bcnt) + delay = bcnt - peer_bcnt; + } + } else if (uc->desc->dir == DMA_DEV_TO_MEM) { + bcnt = udma_rchanrt_read(uc->rchan, + UDMA_RCHAN_RT_BCNT_REG); + + if (uc->config.ep_type != PSIL_EP_NATIVE) { + peer_bcnt = udma_rchanrt_read(uc->rchan, + UDMA_RCHAN_RT_PEER_BCNT_REG); + + if (peer_bcnt > bcnt) + delay = peer_bcnt - bcnt; + } + } else { + bcnt = udma_tchanrt_read(uc->tchan, + UDMA_TCHAN_RT_BCNT_REG); + } + + bcnt -= uc->bcnt; + if (bcnt && !(bcnt % uc->desc->residue)) + residue = 0; + else + residue -= bcnt % uc->desc->residue; + + if (!residue && (uc->config.dir == DMA_DEV_TO_MEM || !delay)) { + ret = DMA_COMPLETE; + delay = 0; + } + + dma_set_residue(txstate, residue); + dma_set_in_flight_bytes(txstate, delay); + + } else { + ret = DMA_COMPLETE; + } + +out: + spin_unlock_irqrestore(&uc->vc.lock, flags); + return ret; +} + +static int udma_pause(struct dma_chan *chan) +{ + struct udma_chan *uc = to_udma_chan(chan); + + /* pause the channel */ + switch (uc->config.dir) { + case DMA_DEV_TO_MEM: + udma_rchanrt_update_bits(uc->rchan, + UDMA_RCHAN_RT_PEER_RT_EN_REG, + UDMA_PEER_RT_EN_PAUSE, + UDMA_PEER_RT_EN_PAUSE); + break; + case DMA_MEM_TO_DEV: + udma_tchanrt_update_bits(uc->tchan, + UDMA_TCHAN_RT_PEER_RT_EN_REG, + UDMA_PEER_RT_EN_PAUSE, + UDMA_PEER_RT_EN_PAUSE); + break; + case DMA_MEM_TO_MEM: + udma_tchanrt_update_bits(uc->tchan, UDMA_TCHAN_RT_CTL_REG, + UDMA_CHAN_RT_CTL_PAUSE, + UDMA_CHAN_RT_CTL_PAUSE); + break; + default: + return -EINVAL; + } + + return 0; +} + +static int udma_resume(struct dma_chan *chan) +{ + struct udma_chan *uc = to_udma_chan(chan); + + /* resume the channel */ + switch (uc->config.dir) { + case DMA_DEV_TO_MEM: + udma_rchanrt_update_bits(uc->rchan, + UDMA_RCHAN_RT_PEER_RT_EN_REG, + UDMA_PEER_RT_EN_PAUSE, 0); + + break; + case DMA_MEM_TO_DEV: + udma_tchanrt_update_bits(uc->tchan, + UDMA_TCHAN_RT_PEER_RT_EN_REG, + UDMA_PEER_RT_EN_PAUSE, 0); + break; + case DMA_MEM_TO_MEM: + udma_tchanrt_update_bits(uc->tchan, UDMA_TCHAN_RT_CTL_REG, + UDMA_CHAN_RT_CTL_PAUSE, 0); + break; + default: + return -EINVAL; + } + + return 0; +} + +static int udma_terminate_all(struct dma_chan *chan) +{ + struct udma_chan *uc = to_udma_chan(chan); + unsigned long flags; + LIST_HEAD(head); + + spin_lock_irqsave(&uc->vc.lock, flags); + + if (udma_is_chan_running(uc)) + udma_stop(uc); + + if (uc->desc) { + uc->terminated_desc = uc->desc; + uc->desc = NULL; + uc->terminated_desc->terminated = true; + cancel_delayed_work(&uc->tx_drain.work); + } + + uc->paused = false; + + vchan_get_all_descriptors(&uc->vc, &head); + spin_unlock_irqrestore(&uc->vc.lock, flags); + vchan_dma_desc_free_list(&uc->vc, &head); + + return 0; +} + +static void udma_synchronize(struct dma_chan *chan) +{ + struct udma_chan *uc = to_udma_chan(chan); + unsigned long timeout = msecs_to_jiffies(1000); + + vchan_synchronize(&uc->vc); + + if (uc->state == UDMA_CHAN_IS_TERMINATING) { + timeout = wait_for_completion_timeout(&uc->teardown_completed, + timeout); + if (!timeout) { + dev_warn(uc->ud->dev, "chan%d teardown timeout!\n", + uc->id); + udma_dump_chan_stdata(uc); + udma_reset_chan(uc, true); + } + } + + udma_reset_chan(uc, false); + if (udma_is_chan_running(uc)) + dev_warn(uc->ud->dev, "chan%d refused to stop!\n", uc->id); + + cancel_delayed_work_sync(&uc->tx_drain.work); + udma_reset_rings(uc); +} + +static void udma_desc_pre_callback(struct virt_dma_chan *vc, + struct virt_dma_desc *vd, + struct dmaengine_result *result) +{ + struct udma_chan *uc = to_udma_chan(&vc->chan); + struct udma_desc *d; + + if (!vd) + return; + + d = to_udma_desc(&vd->tx); + + if (d->metadata_size) + udma_fetch_epib(uc, d); + + /* Provide residue information for the client */ + if (result) { + void *desc_vaddr = udma_curr_cppi5_desc_vaddr(d, d->desc_idx); + + if (cppi5_desc_get_type(desc_vaddr) == + CPPI5_INFO0_DESC_TYPE_VAL_HOST) { + result->residue = d->residue - + cppi5_hdesc_get_pktlen(desc_vaddr); + if (result->residue) + result->result = DMA_TRANS_ABORTED; + else + result->result = DMA_TRANS_NOERROR; + } else { + result->residue = 0; + result->result = DMA_TRANS_NOERROR; + } + } +} + +/* + * This tasklet handles the completion of a DMA descriptor by + * calling its callback and freeing it. + */ +static void udma_vchan_complete(unsigned long arg) +{ + struct virt_dma_chan *vc = (struct virt_dma_chan *)arg; + struct virt_dma_desc *vd, *_vd; + struct dmaengine_desc_callback cb; + LIST_HEAD(head); + + spin_lock_irq(&vc->lock); + list_splice_tail_init(&vc->desc_completed, &head); + vd = vc->cyclic; + if (vd) { + vc->cyclic = NULL; + dmaengine_desc_get_callback(&vd->tx, &cb); + } else { + memset(&cb, 0, sizeof(cb)); + } + spin_unlock_irq(&vc->lock); + + udma_desc_pre_callback(vc, vd, NULL); + dmaengine_desc_callback_invoke(&cb, NULL); + + list_for_each_entry_safe(vd, _vd, &head, node) { + struct dmaengine_result result; + + dmaengine_desc_get_callback(&vd->tx, &cb); + + list_del(&vd->node); + + udma_desc_pre_callback(vc, vd, &result); + dmaengine_desc_callback_invoke(&cb, &result); + + vchan_vdesc_fini(vd); + } +} + +static void udma_free_chan_resources(struct dma_chan *chan) +{ + struct udma_chan *uc = to_udma_chan(chan); + struct udma_dev *ud = to_udma_dev(chan->device); + + udma_terminate_all(chan); + if (uc->terminated_desc) { + udma_reset_chan(uc, false); + udma_reset_rings(uc); + } + + cancel_delayed_work_sync(&uc->tx_drain.work); + destroy_delayed_work_on_stack(&uc->tx_drain.work); + + if (uc->irq_num_ring > 0) { + free_irq(uc->irq_num_ring, uc); + + uc->irq_num_ring = 0; + } + if (uc->irq_num_udma > 0) { + free_irq(uc->irq_num_udma, uc); + + uc->irq_num_udma = 0; + } + + /* Release PSI-L pairing */ + if (uc->psil_paired) { + navss_psil_unpair(ud, uc->config.src_thread, + uc->config.dst_thread); + uc->psil_paired = false; + } + + vchan_free_chan_resources(&uc->vc); + tasklet_kill(&uc->vc.task); + + udma_free_tx_resources(uc); + udma_free_rx_resources(uc); + udma_reset_uchan(uc); + + if (uc->use_dma_pool) { + dma_pool_destroy(uc->hdesc_pool); + uc->use_dma_pool = false; + } +} + +static struct platform_driver udma_driver; + +static bool udma_dma_filter_fn(struct dma_chan *chan, void *param) +{ + struct udma_chan_config *ucc; + struct psil_endpoint_config *ep_config; + struct udma_chan *uc; + struct udma_dev *ud; + u32 *args; + + if (chan->device->dev->driver != &udma_driver.driver) + return false; + + uc = to_udma_chan(chan); + ucc = &uc->config; + ud = uc->ud; + args = param; + + ucc->remote_thread_id = args[0]; + + if (ucc->remote_thread_id & K3_PSIL_DST_THREAD_ID_OFFSET) + ucc->dir = DMA_MEM_TO_DEV; + else + ucc->dir = DMA_DEV_TO_MEM; + + ep_config = psil_get_ep_config(ucc->remote_thread_id); + if (IS_ERR(ep_config)) { + dev_err(ud->dev, "No configuration for psi-l thread 0x%04x\n", + ucc->remote_thread_id); + ucc->dir = DMA_MEM_TO_MEM; + ucc->remote_thread_id = -1; + return false; + } + + ucc->pkt_mode = ep_config->pkt_mode; + ucc->channel_tpl = ep_config->channel_tpl; + ucc->notdpkt = ep_config->notdpkt; + ucc->ep_type = ep_config->ep_type; + + if (ucc->ep_type != PSIL_EP_NATIVE) { + const struct udma_match_data *match_data = ud->match_data; + + if (match_data->flags & UDMA_FLAG_PDMA_ACC32) + ucc->enable_acc32 = ep_config->pdma_acc32; + if (match_data->flags & UDMA_FLAG_PDMA_BURST) + ucc->enable_burst = ep_config->pdma_burst; + } + + ucc->needs_epib = ep_config->needs_epib; + ucc->psd_size = ep_config->psd_size; + ucc->metadata_size = + (ucc->needs_epib ? CPPI5_INFO0_HDESC_EPIB_SIZE : 0) + + ucc->psd_size; + + if (ucc->pkt_mode) + ucc->hdesc_size = ALIGN(sizeof(struct cppi5_host_desc_t) + + ucc->metadata_size, ud->desc_align); + + dev_dbg(ud->dev, "chan%d: Remote thread: 0x%04x (%s)\n", uc->id, + ucc->remote_thread_id, dmaengine_get_direction_text(ucc->dir)); + + return true; +} + +static struct dma_chan *udma_of_xlate(struct of_phandle_args *dma_spec, + struct of_dma *ofdma) +{ + struct udma_dev *ud = ofdma->of_dma_data; + dma_cap_mask_t mask = ud->ddev.cap_mask; + struct dma_chan *chan; + + if (dma_spec->args_count != 1) + return NULL; + + chan = __dma_request_channel(&mask, udma_dma_filter_fn, + &dma_spec->args[0], ofdma->of_node); + if (!chan) { + dev_err(ud->dev, "get channel fail in %s.\n", __func__); + return ERR_PTR(-EINVAL); + } + + return chan; +} + +static struct udma_match_data am654_main_data = { + .psil_base = 0x1000, + .enable_memcpy_support = true, + .statictr_z_mask = GENMASK(11, 0), + .rchan_oes_offset = 0x2000, + .tpl_levels = 2, + .level_start_idx = { + [0] = 8, /* Normal channels */ + [1] = 0, /* High Throughput channels */ + }, +}; + +static struct udma_match_data am654_mcu_data = { + .psil_base = 0x6000, + .enable_memcpy_support = true, /* TEST: DMA domains */ + .statictr_z_mask = GENMASK(11, 0), + .rchan_oes_offset = 0x2000, + .tpl_levels = 2, + .level_start_idx = { + [0] = 2, /* Normal channels */ + [1] = 0, /* High Throughput channels */ + }, +}; + +static struct udma_match_data j721e_main_data = { + .psil_base = 0x1000, + .enable_memcpy_support = true, + .flags = UDMA_FLAG_PDMA_ACC32 | UDMA_FLAG_PDMA_BURST, + .statictr_z_mask = GENMASK(23, 0), + .rchan_oes_offset = 0x400, + .tpl_levels = 3, + .level_start_idx = { + [0] = 16, /* Normal channels */ + [1] = 4, /* High Throughput channels */ + [2] = 0, /* Ultra High Throughput channels */ + }, +}; + +static struct udma_match_data j721e_mcu_data = { + .psil_base = 0x6000, + .enable_memcpy_support = false, /* MEM_TO_MEM is slow via MCU UDMA */ + .flags = UDMA_FLAG_PDMA_ACC32 | UDMA_FLAG_PDMA_BURST, + .statictr_z_mask = GENMASK(23, 0), + .rchan_oes_offset = 0x400, + .tpl_levels = 2, + .level_start_idx = { + [0] = 2, /* Normal channels */ + [1] = 0, /* High Throughput channels */ + }, +}; + +static const struct of_device_id udma_of_match[] = { + { + .compatible = "ti,am654-navss-main-udmap", + .data = &am654_main_data, + }, + { + .compatible = "ti,am654-navss-mcu-udmap", + .data = &am654_mcu_data, + }, { + .compatible = "ti,j721e-navss-main-udmap", + .data = &j721e_main_data, + }, { + .compatible = "ti,j721e-navss-mcu-udmap", + .data = &j721e_mcu_data, + }, + { /* Sentinel */ }, +}; + +static int udma_get_mmrs(struct platform_device *pdev, struct udma_dev *ud) +{ + struct resource *res; + int i; + + for (i = 0; i < MMR_LAST; i++) { + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, + mmr_names[i]); + ud->mmrs[i] = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(ud->mmrs[i])) + return PTR_ERR(ud->mmrs[i]); + } + + return 0; +} + +static int udma_setup_resources(struct udma_dev *ud) +{ + struct device *dev = ud->dev; + int ch_count, ret, i, j; + u32 cap2, cap3; + struct ti_sci_resource_desc *rm_desc; + struct ti_sci_resource *rm_res, irq_res; + struct udma_tisci_rm *tisci_rm = &ud->tisci_rm; + static const char * const range_names[] = { "ti,sci-rm-range-tchan", + "ti,sci-rm-range-rchan", + "ti,sci-rm-range-rflow" }; + + cap2 = udma_read(ud->mmrs[MMR_GCFG], 0x28); + cap3 = udma_read(ud->mmrs[MMR_GCFG], 0x2c); + + ud->rflow_cnt = cap3 & 0x3fff; + ud->tchan_cnt = cap2 & 0x1ff; + ud->echan_cnt = (cap2 >> 9) & 0x1ff; + ud->rchan_cnt = (cap2 >> 18) & 0x1ff; + ch_count = ud->tchan_cnt + ud->rchan_cnt; + + ud->tchan_map = devm_kmalloc_array(dev, BITS_TO_LONGS(ud->tchan_cnt), + sizeof(unsigned long), GFP_KERNEL); + ud->tchans = devm_kcalloc(dev, ud->tchan_cnt, sizeof(*ud->tchans), + GFP_KERNEL); + ud->rchan_map = devm_kmalloc_array(dev, BITS_TO_LONGS(ud->rchan_cnt), + sizeof(unsigned long), GFP_KERNEL); + ud->rchans = devm_kcalloc(dev, ud->rchan_cnt, sizeof(*ud->rchans), + GFP_KERNEL); + ud->rflow_gp_map = devm_kmalloc_array(dev, BITS_TO_LONGS(ud->rflow_cnt), + sizeof(unsigned long), + GFP_KERNEL); + ud->rflow_gp_map_allocated = devm_kcalloc(dev, + BITS_TO_LONGS(ud->rflow_cnt), + sizeof(unsigned long), + GFP_KERNEL); + ud->rflow_in_use = devm_kcalloc(dev, BITS_TO_LONGS(ud->rflow_cnt), + sizeof(unsigned long), + GFP_KERNEL); + ud->rflows = devm_kcalloc(dev, ud->rflow_cnt, sizeof(*ud->rflows), + GFP_KERNEL); + + if (!ud->tchan_map || !ud->rchan_map || !ud->rflow_gp_map || + !ud->rflow_gp_map_allocated || !ud->tchans || !ud->rchans || + !ud->rflows || !ud->rflow_in_use) + return -ENOMEM; + + /* + * RX flows with the same Ids as RX channels are reserved to be used + * as default flows if remote HW can't generate flow_ids. Those + * RX flows can be requested only explicitly by id. + */ + bitmap_set(ud->rflow_gp_map_allocated, 0, ud->rchan_cnt); + + /* by default no GP rflows are assigned to Linux */ + bitmap_set(ud->rflow_gp_map, 0, ud->rflow_cnt); + + /* Get resource ranges from tisci */ + for (i = 0; i < RM_RANGE_LAST; i++) + tisci_rm->rm_ranges[i] = + devm_ti_sci_get_of_resource(tisci_rm->tisci, dev, + tisci_rm->tisci_dev_id, + (char *)range_names[i]); + + /* tchan ranges */ + rm_res = tisci_rm->rm_ranges[RM_RANGE_TCHAN]; + if (IS_ERR(rm_res)) { + bitmap_zero(ud->tchan_map, ud->tchan_cnt); + } else { + bitmap_fill(ud->tchan_map, ud->tchan_cnt); + for (i = 0; i < rm_res->sets; i++) { + rm_desc = &rm_res->desc[i]; + bitmap_clear(ud->tchan_map, rm_desc->start, + rm_desc->num); + dev_dbg(dev, "ti-sci-res: tchan: %d:%d\n", + rm_desc->start, rm_desc->num); + } + } + irq_res.sets = rm_res->sets; + + /* rchan and matching default flow ranges */ + rm_res = tisci_rm->rm_ranges[RM_RANGE_RCHAN]; + if (IS_ERR(rm_res)) { + bitmap_zero(ud->rchan_map, ud->rchan_cnt); + } else { + bitmap_fill(ud->rchan_map, ud->rchan_cnt); + for (i = 0; i < rm_res->sets; i++) { + rm_desc = &rm_res->desc[i]; + bitmap_clear(ud->rchan_map, rm_desc->start, + rm_desc->num); + dev_dbg(dev, "ti-sci-res: rchan: %d:%d\n", + rm_desc->start, rm_desc->num); + } + } + + irq_res.sets += rm_res->sets; + irq_res.desc = kcalloc(irq_res.sets, sizeof(*irq_res.desc), GFP_KERNEL); + rm_res = tisci_rm->rm_ranges[RM_RANGE_TCHAN]; + for (i = 0; i < rm_res->sets; i++) { + irq_res.desc[i].start = rm_res->desc[i].start; + irq_res.desc[i].num = rm_res->desc[i].num; + } + rm_res = tisci_rm->rm_ranges[RM_RANGE_RCHAN]; + for (j = 0; j < rm_res->sets; j++, i++) { + irq_res.desc[i].start = rm_res->desc[j].start + + ud->match_data->rchan_oes_offset; + irq_res.desc[i].num = rm_res->desc[j].num; + } + ret = ti_sci_inta_msi_domain_alloc_irqs(ud->dev, &irq_res); + kfree(irq_res.desc); + if (ret) { + dev_err(ud->dev, "Failed to allocate MSI interrupts\n"); + return ret; + } + + /* GP rflow ranges */ + rm_res = tisci_rm->rm_ranges[RM_RANGE_RFLOW]; + if (IS_ERR(rm_res)) { + /* all gp flows are assigned exclusively to Linux */ + bitmap_clear(ud->rflow_gp_map, ud->rchan_cnt, + ud->rflow_cnt - ud->rchan_cnt); + } else { + for (i = 0; i < rm_res->sets; i++) { + rm_desc = &rm_res->desc[i]; + bitmap_clear(ud->rflow_gp_map, rm_desc->start, + rm_desc->num); + dev_dbg(dev, "ti-sci-res: rflow: %d:%d\n", + rm_desc->start, rm_desc->num); + } + } + + ch_count -= bitmap_weight(ud->tchan_map, ud->tchan_cnt); + ch_count -= bitmap_weight(ud->rchan_map, ud->rchan_cnt); + if (!ch_count) + return -ENODEV; + + ud->channels = devm_kcalloc(dev, ch_count, sizeof(*ud->channels), + GFP_KERNEL); + if (!ud->channels) + return -ENOMEM; + + dev_info(dev, "Channels: %d (tchan: %u, rchan: %u, gp-rflow: %u)\n", + ch_count, + ud->tchan_cnt - bitmap_weight(ud->tchan_map, ud->tchan_cnt), + ud->rchan_cnt - bitmap_weight(ud->rchan_map, ud->rchan_cnt), + ud->rflow_cnt - bitmap_weight(ud->rflow_gp_map, + ud->rflow_cnt)); + + return ch_count; +} + +static int udma_setup_rx_flush(struct udma_dev *ud) +{ + struct udma_rx_flush *rx_flush = &ud->rx_flush; + struct cppi5_desc_hdr_t *tr_desc; + struct cppi5_tr_type1_t *tr_req; + struct cppi5_host_desc_t *desc; + struct device *dev = ud->dev; + struct udma_hwdesc *hwdesc; + size_t tr_size; + + /* Allocate 1K buffer for discarded data on RX channel teardown */ + rx_flush->buffer_size = SZ_1K; + rx_flush->buffer_vaddr = devm_kzalloc(dev, rx_flush->buffer_size, + GFP_KERNEL); + if (!rx_flush->buffer_vaddr) + return -ENOMEM; + + rx_flush->buffer_paddr = dma_map_single(dev, rx_flush->buffer_vaddr, + rx_flush->buffer_size, + DMA_TO_DEVICE); + if (dma_mapping_error(dev, rx_flush->buffer_paddr)) + return -ENOMEM; + + /* Set up descriptor to be used for TR mode */ + hwdesc = &rx_flush->hwdescs[0]; + tr_size = sizeof(struct cppi5_tr_type1_t); + hwdesc->cppi5_desc_size = cppi5_trdesc_calc_size(tr_size, 1); + hwdesc->cppi5_desc_size = ALIGN(hwdesc->cppi5_desc_size, + ud->desc_align); + + hwdesc->cppi5_desc_vaddr = devm_kzalloc(dev, hwdesc->cppi5_desc_size, + GFP_KERNEL); + if (!hwdesc->cppi5_desc_vaddr) + return -ENOMEM; + + hwdesc->cppi5_desc_paddr = dma_map_single(dev, hwdesc->cppi5_desc_vaddr, + hwdesc->cppi5_desc_size, + DMA_TO_DEVICE); + if (dma_mapping_error(dev, hwdesc->cppi5_desc_paddr)) + return -ENOMEM; + + /* Start of the TR req records */ + hwdesc->tr_req_base = hwdesc->cppi5_desc_vaddr + tr_size; + /* Start address of the TR response array */ + hwdesc->tr_resp_base = hwdesc->tr_req_base + tr_size; + + tr_desc = hwdesc->cppi5_desc_vaddr; + cppi5_trdesc_init(tr_desc, 1, tr_size, 0, 0); + cppi5_desc_set_pktids(tr_desc, 0, CPPI5_INFO1_DESC_FLOWID_DEFAULT); + cppi5_desc_set_retpolicy(tr_desc, 0, 0); + + tr_req = hwdesc->tr_req_base; + cppi5_tr_init(&tr_req->flags, CPPI5_TR_TYPE1, false, false, + CPPI5_TR_EVENT_SIZE_COMPLETION, 0); + cppi5_tr_csf_set(&tr_req->flags, CPPI5_TR_CSF_SUPR_EVT); + + tr_req->addr = rx_flush->buffer_paddr; + tr_req->icnt0 = rx_flush->buffer_size; + tr_req->icnt1 = 1; + + /* Set up descriptor to be used for packet mode */ + hwdesc = &rx_flush->hwdescs[1]; + hwdesc->cppi5_desc_size = ALIGN(sizeof(struct cppi5_host_desc_t) + + CPPI5_INFO0_HDESC_EPIB_SIZE + + CPPI5_INFO0_HDESC_PSDATA_MAX_SIZE, + ud->desc_align); + + hwdesc->cppi5_desc_vaddr = devm_kzalloc(dev, hwdesc->cppi5_desc_size, + GFP_KERNEL); + if (!hwdesc->cppi5_desc_vaddr) + return -ENOMEM; + + hwdesc->cppi5_desc_paddr = dma_map_single(dev, hwdesc->cppi5_desc_vaddr, + hwdesc->cppi5_desc_size, + DMA_TO_DEVICE); + if (dma_mapping_error(dev, hwdesc->cppi5_desc_paddr)) + return -ENOMEM; + + desc = hwdesc->cppi5_desc_vaddr; + cppi5_hdesc_init(desc, 0, 0); + cppi5_desc_set_pktids(&desc->hdr, 0, CPPI5_INFO1_DESC_FLOWID_DEFAULT); + cppi5_desc_set_retpolicy(&desc->hdr, 0, 0); + + cppi5_hdesc_attach_buf(desc, + rx_flush->buffer_paddr, rx_flush->buffer_size, + rx_flush->buffer_paddr, rx_flush->buffer_size); + + dma_sync_single_for_device(dev, hwdesc->cppi5_desc_paddr, + hwdesc->cppi5_desc_size, DMA_TO_DEVICE); + return 0; +} + +#define TI_UDMAC_BUSWIDTHS (BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) | \ + BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) | \ + BIT(DMA_SLAVE_BUSWIDTH_3_BYTES) | \ + BIT(DMA_SLAVE_BUSWIDTH_4_BYTES) | \ + BIT(DMA_SLAVE_BUSWIDTH_8_BYTES)) + +static int udma_probe(struct platform_device *pdev) +{ + struct device_node *navss_node = pdev->dev.parent->of_node; + struct device *dev = &pdev->dev; + struct udma_dev *ud; + const struct of_device_id *match; + int i, ret; + int ch_count; + + ret = dma_coerce_mask_and_coherent(dev, DMA_BIT_MASK(48)); + if (ret) + dev_err(dev, "failed to set dma mask stuff\n"); + + ud = devm_kzalloc(dev, sizeof(*ud), GFP_KERNEL); + if (!ud) + return -ENOMEM; + + ret = udma_get_mmrs(pdev, ud); + if (ret) + return ret; + + ud->tisci_rm.tisci = ti_sci_get_by_phandle(dev->of_node, "ti,sci"); + if (IS_ERR(ud->tisci_rm.tisci)) + return PTR_ERR(ud->tisci_rm.tisci); + + ret = of_property_read_u32(dev->of_node, "ti,sci-dev-id", + &ud->tisci_rm.tisci_dev_id); + if (ret) { + dev_err(dev, "ti,sci-dev-id read failure %d\n", ret); + return ret; + } + pdev->id = ud->tisci_rm.tisci_dev_id; + + ret = of_property_read_u32(navss_node, "ti,sci-dev-id", + &ud->tisci_rm.tisci_navss_dev_id); + if (ret) { + dev_err(dev, "NAVSS ti,sci-dev-id read failure %d\n", ret); + return ret; + } + + ud->tisci_rm.tisci_udmap_ops = &ud->tisci_rm.tisci->ops.rm_udmap_ops; + ud->tisci_rm.tisci_psil_ops = &ud->tisci_rm.tisci->ops.rm_psil_ops; + + ud->ringacc = of_k3_ringacc_get_by_phandle(dev->of_node, "ti,ringacc"); + if (IS_ERR(ud->ringacc)) + return PTR_ERR(ud->ringacc); + + dev->msi_domain = of_msi_get_domain(dev, dev->of_node, + DOMAIN_BUS_TI_SCI_INTA_MSI); + if (!dev->msi_domain) { + dev_err(dev, "Failed to get MSI domain\n"); + return -EPROBE_DEFER; + } + + match = of_match_node(udma_of_match, dev->of_node); + if (!match) { + dev_err(dev, "No compatible match found\n"); + return -ENODEV; + } + ud->match_data = match->data; + + dma_cap_set(DMA_SLAVE, ud->ddev.cap_mask); + dma_cap_set(DMA_CYCLIC, ud->ddev.cap_mask); + + ud->ddev.device_alloc_chan_resources = udma_alloc_chan_resources; + ud->ddev.device_config = udma_slave_config; + ud->ddev.device_prep_slave_sg = udma_prep_slave_sg; + ud->ddev.device_prep_dma_cyclic = udma_prep_dma_cyclic; + ud->ddev.device_issue_pending = udma_issue_pending; + ud->ddev.device_tx_status = udma_tx_status; + ud->ddev.device_pause = udma_pause; + ud->ddev.device_resume = udma_resume; + ud->ddev.device_terminate_all = udma_terminate_all; + ud->ddev.device_synchronize = udma_synchronize; + + ud->ddev.device_free_chan_resources = udma_free_chan_resources; + ud->ddev.src_addr_widths = TI_UDMAC_BUSWIDTHS; + 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) { + dma_cap_set(DMA_MEMCPY, ud->ddev.cap_mask); + ud->ddev.device_prep_dma_memcpy = udma_prep_dma_memcpy; + ud->ddev.directions |= BIT(DMA_MEM_TO_MEM); + } + + ud->ddev.dev = dev; + ud->dev = dev; + ud->psil_base = ud->match_data->psil_base; + + INIT_LIST_HEAD(&ud->ddev.channels); + INIT_LIST_HEAD(&ud->desc_to_purge); + + ch_count = udma_setup_resources(ud); + if (ch_count <= 0) + return ch_count; + + spin_lock_init(&ud->lock); + INIT_WORK(&ud->purge_work, udma_purge_desc_work); + + ud->desc_align = 64; + if (ud->desc_align < dma_get_cache_alignment()) + ud->desc_align = dma_get_cache_alignment(); + + ret = udma_setup_rx_flush(ud); + if (ret) + return ret; + + for (i = 0; i < ud->tchan_cnt; i++) { + struct udma_tchan *tchan = &ud->tchans[i]; + + tchan->id = i; + tchan->reg_rt = ud->mmrs[MMR_TCHANRT] + i * 0x1000; + } + + for (i = 0; i < ud->rchan_cnt; i++) { + struct udma_rchan *rchan = &ud->rchans[i]; + + rchan->id = i; + rchan->reg_rt = ud->mmrs[MMR_RCHANRT] + i * 0x1000; + } + + for (i = 0; i < ud->rflow_cnt; i++) { + struct udma_rflow *rflow = &ud->rflows[i]; + + rflow->id = i; + } + + for (i = 0; i < ch_count; i++) { + struct udma_chan *uc = &ud->channels[i]; + + uc->ud = ud; + uc->vc.desc_free = udma_desc_free; + uc->id = i; + uc->tchan = NULL; + uc->rchan = NULL; + uc->config.remote_thread_id = -1; + uc->config.dir = DMA_MEM_TO_MEM; + uc->name = devm_kasprintf(dev, GFP_KERNEL, "%s chan%d", + dev_name(dev), i); + + vchan_init(&uc->vc, &ud->ddev); + /* Use custom vchan completion handling */ + tasklet_init(&uc->vc.task, udma_vchan_complete, + (unsigned long)&uc->vc); + init_completion(&uc->teardown_completed); + } + + ret = dma_async_device_register(&ud->ddev); + if (ret) { + dev_err(dev, "failed to register slave DMA engine: %d\n", ret); + return ret; + } + + platform_set_drvdata(pdev, ud); + + ret = of_dma_controller_register(dev->of_node, udma_of_xlate, ud); + if (ret) { + dev_err(dev, "failed to register of_dma controller\n"); + dma_async_device_unregister(&ud->ddev); + } + + return ret; +} + +static struct platform_driver udma_driver = { + .driver = { + .name = "ti-udma", + .of_match_table = udma_of_match, + .suppress_bind_attrs = true, + }, + .probe = udma_probe, +}; +builtin_platform_driver(udma_driver); + +/* Private interfaces to UDMA */ +#include "k3-udma-private.c" diff --git a/drivers/dma/ti/k3-udma.h b/drivers/dma/ti/k3-udma.h new file mode 100644 index 000000000000..128d8744a435 --- /dev/null +++ b/drivers/dma/ti/k3-udma.h @@ -0,0 +1,151 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com + */ + +#ifndef K3_UDMA_H_ +#define K3_UDMA_H_ + +#include <linux/soc/ti/ti_sci_protocol.h> + +/* Global registers */ +#define UDMA_REV_REG 0x0 +#define UDMA_PERF_CTL_REG 0x4 +#define UDMA_EMU_CTL_REG 0x8 +#define UDMA_PSIL_TO_REG 0x10 +#define UDMA_UTC_CTL_REG 0x1c +#define UDMA_CAP_REG(i) (0x20 + ((i) * 4)) +#define UDMA_RX_FLOW_ID_FW_OES_REG 0x80 +#define UDMA_RX_FLOW_ID_FW_STATUS_REG 0x88 + +/* TX chan RT regs */ +#define UDMA_TCHAN_RT_CTL_REG 0x0 +#define UDMA_TCHAN_RT_SWTRIG_REG 0x8 +#define UDMA_TCHAN_RT_STDATA_REG 0x80 + +#define UDMA_TCHAN_RT_PEER_REG(i) (0x200 + ((i) * 0x4)) +#define UDMA_TCHAN_RT_PEER_STATIC_TR_XY_REG \ + UDMA_TCHAN_RT_PEER_REG(0) /* PSI-L: 0x400 */ +#define UDMA_TCHAN_RT_PEER_STATIC_TR_Z_REG \ + UDMA_TCHAN_RT_PEER_REG(1) /* PSI-L: 0x401 */ +#define UDMA_TCHAN_RT_PEER_BCNT_REG \ + UDMA_TCHAN_RT_PEER_REG(4) /* PSI-L: 0x404 */ +#define UDMA_TCHAN_RT_PEER_RT_EN_REG \ + UDMA_TCHAN_RT_PEER_REG(8) /* PSI-L: 0x408 */ + +#define UDMA_TCHAN_RT_PCNT_REG 0x400 +#define UDMA_TCHAN_RT_BCNT_REG 0x408 +#define UDMA_TCHAN_RT_SBCNT_REG 0x410 + +/* RX chan RT regs */ +#define UDMA_RCHAN_RT_CTL_REG 0x0 +#define UDMA_RCHAN_RT_SWTRIG_REG 0x8 +#define UDMA_RCHAN_RT_STDATA_REG 0x80 + +#define UDMA_RCHAN_RT_PEER_REG(i) (0x200 + ((i) * 0x4)) +#define UDMA_RCHAN_RT_PEER_STATIC_TR_XY_REG \ + UDMA_RCHAN_RT_PEER_REG(0) /* PSI-L: 0x400 */ +#define UDMA_RCHAN_RT_PEER_STATIC_TR_Z_REG \ + UDMA_RCHAN_RT_PEER_REG(1) /* PSI-L: 0x401 */ +#define UDMA_RCHAN_RT_PEER_BCNT_REG \ + UDMA_RCHAN_RT_PEER_REG(4) /* PSI-L: 0x404 */ +#define UDMA_RCHAN_RT_PEER_RT_EN_REG \ + UDMA_RCHAN_RT_PEER_REG(8) /* PSI-L: 0x408 */ + +#define UDMA_RCHAN_RT_PCNT_REG 0x400 +#define UDMA_RCHAN_RT_BCNT_REG 0x408 +#define UDMA_RCHAN_RT_SBCNT_REG 0x410 + +/* UDMA_TCHAN_RT_CTL_REG/UDMA_RCHAN_RT_CTL_REG */ +#define UDMA_CHAN_RT_CTL_EN BIT(31) +#define UDMA_CHAN_RT_CTL_TDOWN BIT(30) +#define UDMA_CHAN_RT_CTL_PAUSE BIT(29) +#define UDMA_CHAN_RT_CTL_FTDOWN BIT(28) +#define UDMA_CHAN_RT_CTL_ERROR BIT(0) + +/* UDMA_TCHAN_RT_PEER_RT_EN_REG/UDMA_RCHAN_RT_PEER_RT_EN_REG (PSI-L: 0x408) */ +#define UDMA_PEER_RT_EN_ENABLE BIT(31) +#define UDMA_PEER_RT_EN_TEARDOWN BIT(30) +#define UDMA_PEER_RT_EN_PAUSE BIT(29) +#define UDMA_PEER_RT_EN_FLUSH BIT(28) +#define UDMA_PEER_RT_EN_IDLE BIT(1) + +/* + * UDMA_TCHAN_RT_PEER_STATIC_TR_XY_REG / + * UDMA_RCHAN_RT_PEER_STATIC_TR_XY_REG + */ +#define PDMA_STATIC_TR_X_MASK GENMASK(26, 24) +#define PDMA_STATIC_TR_X_SHIFT (24) +#define PDMA_STATIC_TR_Y_MASK GENMASK(11, 0) +#define PDMA_STATIC_TR_Y_SHIFT (0) + +#define PDMA_STATIC_TR_Y(x) \ + (((x) << PDMA_STATIC_TR_Y_SHIFT) & PDMA_STATIC_TR_Y_MASK) +#define PDMA_STATIC_TR_X(x) \ + (((x) << PDMA_STATIC_TR_X_SHIFT) & PDMA_STATIC_TR_X_MASK) + +#define PDMA_STATIC_TR_XY_ACC32 BIT(30) +#define PDMA_STATIC_TR_XY_BURST BIT(31) + +/* + * UDMA_TCHAN_RT_PEER_STATIC_TR_Z_REG / + * UDMA_RCHAN_RT_PEER_STATIC_TR_Z_REG + */ +#define PDMA_STATIC_TR_Z(x, mask) ((x) & (mask)) + +struct udma_dev; +struct udma_tchan; +struct udma_rchan; +struct udma_rflow; + +enum udma_rm_range { + RM_RANGE_TCHAN = 0, + RM_RANGE_RCHAN, + RM_RANGE_RFLOW, + RM_RANGE_LAST, +}; + +struct udma_tisci_rm { + const struct ti_sci_handle *tisci; + const struct ti_sci_rm_udmap_ops *tisci_udmap_ops; + u32 tisci_dev_id; + + /* tisci information for PSI-L thread pairing/unpairing */ + const struct ti_sci_rm_psil_ops *tisci_psil_ops; + u32 tisci_navss_dev_id; + + struct ti_sci_resource *rm_ranges[RM_RANGE_LAST]; +}; + +/* Direct access to UDMA low lever resources for the glue layer */ +int xudma_navss_psil_pair(struct udma_dev *ud, u32 src_thread, u32 dst_thread); +int xudma_navss_psil_unpair(struct udma_dev *ud, u32 src_thread, + u32 dst_thread); + +struct udma_dev *of_xudma_dev_get(struct device_node *np, const char *property); +void xudma_dev_put(struct udma_dev *ud); +u32 xudma_dev_get_psil_base(struct udma_dev *ud); +struct udma_tisci_rm *xudma_dev_get_tisci_rm(struct udma_dev *ud); + +int xudma_alloc_gp_rflow_range(struct udma_dev *ud, int from, int cnt); +int xudma_free_gp_rflow_range(struct udma_dev *ud, int from, int cnt); + +struct udma_tchan *xudma_tchan_get(struct udma_dev *ud, int id); +struct udma_rchan *xudma_rchan_get(struct udma_dev *ud, int id); +struct udma_rflow *xudma_rflow_get(struct udma_dev *ud, int id); + +void xudma_tchan_put(struct udma_dev *ud, struct udma_tchan *p); +void xudma_rchan_put(struct udma_dev *ud, struct udma_rchan *p); +void xudma_rflow_put(struct udma_dev *ud, struct udma_rflow *p); + +int xudma_tchan_get_id(struct udma_tchan *p); +int xudma_rchan_get_id(struct udma_rchan *p); +int xudma_rflow_get_id(struct udma_rflow *p); + +u32 xudma_tchanrt_read(struct udma_tchan *tchan, int reg); +void xudma_tchanrt_write(struct udma_tchan *tchan, int reg, u32 val); +u32 xudma_rchanrt_read(struct udma_rchan *rchan, int reg); +void xudma_rchanrt_write(struct udma_rchan *rchan, int reg, u32 val); +bool xudma_rflow_is_gp(struct udma_dev *ud, int id); + +#endif /* K3_UDMA_H_ */ diff --git a/drivers/dma/ti/omap-dma.c b/drivers/dma/ti/omap-dma.c index 6b6ba238b81a..a014ab96e673 100644 --- a/drivers/dma/ti/omap-dma.c +++ b/drivers/dma/ti/omap-dma.c @@ -2,6 +2,7 @@ /* * OMAP DMAengine support */ +#include <linux/cpu_pm.h> #include <linux/delay.h> #include <linux/dmaengine.h> #include <linux/dma-mapping.h> @@ -23,12 +24,33 @@ #define OMAP_SDMA_REQUESTS 127 #define OMAP_SDMA_CHANNELS 32 +struct omap_dma_config { + int lch_end; + unsigned int rw_priority:1; + unsigned int needs_busy_check:1; + unsigned int may_lose_context:1; + unsigned int needs_lch_clear:1; +}; + +struct omap_dma_context { + u32 irqenable_l0; + u32 irqenable_l1; + u32 ocp_sysconfig; + u32 gcr; +}; + struct omap_dmadev { struct dma_device ddev; spinlock_t lock; void __iomem *base; const struct omap_dma_reg *reg_map; struct omap_system_dma_plat_info *plat; + const struct omap_dma_config *cfg; + struct notifier_block nb; + struct omap_dma_context context; + int lch_count; + DECLARE_BITMAP(lch_bitmap, OMAP_SDMA_CHANNELS); + struct mutex lch_lock; /* for assigning logical channels */ bool legacy; bool ll123_supported; struct dma_pool *desc_pool; @@ -376,6 +398,19 @@ static unsigned omap_dma_get_csr(struct omap_chan *c) return val; } +static void omap_dma_clear_lch(struct omap_dmadev *od, int lch) +{ + struct omap_chan *c; + int i; + + c = od->lch_map[lch]; + if (!c) + return; + + for (i = CSDP; i <= od->cfg->lch_end; i++) + omap_dma_chan_write(c, i, 0); +} + static void omap_dma_assign(struct omap_dmadev *od, struct omap_chan *c, unsigned lch) { @@ -633,6 +668,37 @@ static irqreturn_t omap_dma_irq(int irq, void *devid) return IRQ_HANDLED; } +static int omap_dma_get_lch(struct omap_dmadev *od, int *lch) +{ + int channel; + + mutex_lock(&od->lch_lock); + channel = find_first_zero_bit(od->lch_bitmap, od->lch_count); + if (channel >= od->lch_count) + goto out_busy; + set_bit(channel, od->lch_bitmap); + mutex_unlock(&od->lch_lock); + + omap_dma_clear_lch(od, channel); + *lch = channel; + + return 0; + +out_busy: + mutex_unlock(&od->lch_lock); + *lch = -EINVAL; + + return -EBUSY; +} + +static void omap_dma_put_lch(struct omap_dmadev *od, int lch) +{ + omap_dma_clear_lch(od, lch); + mutex_lock(&od->lch_lock); + clear_bit(lch, od->lch_bitmap); + mutex_unlock(&od->lch_lock); +} + static int omap_dma_alloc_chan_resources(struct dma_chan *chan) { struct omap_dmadev *od = to_omap_dma_dev(chan->device); @@ -644,8 +710,7 @@ static int omap_dma_alloc_chan_resources(struct dma_chan *chan) ret = omap_request_dma(c->dma_sig, "DMA engine", omap_dma_callback, c, &c->dma_ch); } else { - ret = omap_request_dma(c->dma_sig, "DMA engine", NULL, NULL, - &c->dma_ch); + ret = omap_dma_get_lch(od, &c->dma_ch); } dev_dbg(dev, "allocating channel %u for %u\n", c->dma_ch, c->dma_sig); @@ -702,7 +767,11 @@ static void omap_dma_free_chan_resources(struct dma_chan *chan) c->channel_base = NULL; od->lch_map[c->dma_ch] = NULL; vchan_free_chan_resources(&c->vc); - omap_free_dma(c->dma_ch); + + if (od->legacy) + omap_free_dma(c->dma_ch); + else + omap_dma_put_lch(od, c->dma_ch); dev_dbg(od->ddev.dev, "freeing channel %u used for %u\n", c->dma_ch, c->dma_sig); @@ -1453,16 +1522,128 @@ static void omap_dma_free(struct omap_dmadev *od) } } +/* Currently only used for omap2. For omap1, also a check for lcd_dma is needed */ +static int omap_dma_busy_notifier(struct notifier_block *nb, + unsigned long cmd, void *v) +{ + struct omap_dmadev *od; + struct omap_chan *c; + int lch = -1; + + od = container_of(nb, struct omap_dmadev, nb); + + switch (cmd) { + case CPU_CLUSTER_PM_ENTER: + while (1) { + lch = find_next_bit(od->lch_bitmap, od->lch_count, + lch + 1); + if (lch >= od->lch_count) + break; + c = od->lch_map[lch]; + if (!c) + continue; + if (omap_dma_chan_read(c, CCR) & CCR_ENABLE) + return NOTIFY_BAD; + } + break; + case CPU_CLUSTER_PM_ENTER_FAILED: + case CPU_CLUSTER_PM_EXIT: + break; + } + + return NOTIFY_OK; +} + +/* + * We are using IRQENABLE_L1, and legacy DMA code was using IRQENABLE_L0. + * As the DSP may be using IRQENABLE_L2 and L3, let's not touch those for + * now. Context save seems to be only currently needed on omap3. + */ +static void omap_dma_context_save(struct omap_dmadev *od) +{ + od->context.irqenable_l0 = omap_dma_glbl_read(od, IRQENABLE_L0); + od->context.irqenable_l1 = omap_dma_glbl_read(od, IRQENABLE_L1); + od->context.ocp_sysconfig = omap_dma_glbl_read(od, OCP_SYSCONFIG); + od->context.gcr = omap_dma_glbl_read(od, GCR); +} + +static void omap_dma_context_restore(struct omap_dmadev *od) +{ + int i; + + omap_dma_glbl_write(od, GCR, od->context.gcr); + omap_dma_glbl_write(od, OCP_SYSCONFIG, od->context.ocp_sysconfig); + omap_dma_glbl_write(od, IRQENABLE_L0, od->context.irqenable_l0); + omap_dma_glbl_write(od, IRQENABLE_L1, od->context.irqenable_l1); + + /* Clear IRQSTATUS_L0 as legacy DMA code is no longer doing it */ + if (od->plat->errata & DMA_ROMCODE_BUG) + omap_dma_glbl_write(od, IRQSTATUS_L0, 0); + + /* Clear dma channels */ + for (i = 0; i < od->lch_count; i++) + omap_dma_clear_lch(od, i); +} + +/* Currently only used for omap3 */ +static int omap_dma_context_notifier(struct notifier_block *nb, + unsigned long cmd, void *v) +{ + struct omap_dmadev *od; + + od = container_of(nb, struct omap_dmadev, nb); + + switch (cmd) { + case CPU_CLUSTER_PM_ENTER: + omap_dma_context_save(od); + break; + case CPU_CLUSTER_PM_ENTER_FAILED: + case CPU_CLUSTER_PM_EXIT: + omap_dma_context_restore(od); + break; + } + + return NOTIFY_OK; +} + +static void omap_dma_init_gcr(struct omap_dmadev *od, int arb_rate, + int max_fifo_depth, int tparams) +{ + u32 val; + + /* Set only for omap2430 and later */ + if (!od->cfg->rw_priority) + return; + + if (max_fifo_depth == 0) + max_fifo_depth = 1; + if (arb_rate == 0) + arb_rate = 1; + + val = 0xff & max_fifo_depth; + val |= (0x3 & tparams) << 12; + val |= (arb_rate & 0xff) << 16; + + omap_dma_glbl_write(od, GCR, val); +} + #define OMAP_DMA_BUSWIDTHS (BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) | \ BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) | \ BIT(DMA_SLAVE_BUSWIDTH_4_BYTES)) +/* + * No flags currently set for default configuration as omap1 is still + * using platform data. + */ +static const struct omap_dma_config default_cfg; + static int omap_dma_probe(struct platform_device *pdev) { + const struct omap_dma_config *conf; struct omap_dmadev *od; struct resource *res; int rc, i, irq; - u32 lch_count; + u32 val; od = devm_kzalloc(&pdev->dev, sizeof(*od), GFP_KERNEL); if (!od) @@ -1473,9 +1654,21 @@ static int omap_dma_probe(struct platform_device *pdev) if (IS_ERR(od->base)) return PTR_ERR(od->base); - od->plat = omap_get_plat_info(); - if (!od->plat) - return -EPROBE_DEFER; + conf = of_device_get_match_data(&pdev->dev); + if (conf) { + od->cfg = conf; + od->plat = dev_get_platdata(&pdev->dev); + if (!od->plat) { + dev_err(&pdev->dev, "omap_system_dma_plat_info is missing"); + return -ENODEV; + } + } else { + od->cfg = &default_cfg; + + od->plat = omap_get_plat_info(); + if (!od->plat) + return -EPROBE_DEFER; + } od->reg_map = od->plat->reg_map; @@ -1507,6 +1700,7 @@ static int omap_dma_probe(struct platform_device *pdev) od->ddev.max_burst = SZ_16M - 1; /* CCEN: 24bit unsigned */ od->ddev.dev = &pdev->dev; INIT_LIST_HEAD(&od->ddev.channels); + mutex_init(&od->lch_lock); spin_lock_init(&od->lock); spin_lock_init(&od->irq_lock); @@ -1522,18 +1716,30 @@ static int omap_dma_probe(struct platform_device *pdev) /* Number of available logical channels */ if (!pdev->dev.of_node) { - lch_count = od->plat->dma_attr->lch_count; - if (unlikely(!lch_count)) - lch_count = OMAP_SDMA_CHANNELS; + od->lch_count = od->plat->dma_attr->lch_count; + if (unlikely(!od->lch_count)) + od->lch_count = OMAP_SDMA_CHANNELS; } else if (of_property_read_u32(pdev->dev.of_node, "dma-channels", - &lch_count)) { + &od->lch_count)) { dev_info(&pdev->dev, "Missing dma-channels property, using %u.\n", OMAP_SDMA_CHANNELS); - lch_count = OMAP_SDMA_CHANNELS; + od->lch_count = OMAP_SDMA_CHANNELS; + } + + /* Mask of allowed logical channels */ + if (pdev->dev.of_node && !of_property_read_u32(pdev->dev.of_node, + "dma-channel-mask", + &val)) { + /* Tag channels not in mask as reserved */ + val = ~val; + bitmap_from_arr32(od->lch_bitmap, &val, od->lch_count); } + if (od->plat->dma_attr->dev_caps & HS_CHANNELS_RESERVED) + bitmap_set(od->lch_bitmap, 0, 2); - od->lch_map = devm_kcalloc(&pdev->dev, lch_count, sizeof(*od->lch_map), + od->lch_map = devm_kcalloc(&pdev->dev, od->lch_count, + sizeof(*od->lch_map), GFP_KERNEL); if (!od->lch_map) return -ENOMEM; @@ -1605,6 +1811,16 @@ static int omap_dma_probe(struct platform_device *pdev) } } + omap_dma_init_gcr(od, DMA_DEFAULT_ARB_RATE, DMA_DEFAULT_FIFO_DEPTH, 0); + + if (od->cfg->needs_busy_check) { + od->nb.notifier_call = omap_dma_busy_notifier; + cpu_pm_register_notifier(&od->nb); + } else if (od->cfg->may_lose_context) { + od->nb.notifier_call = omap_dma_context_notifier; + cpu_pm_register_notifier(&od->nb); + } + dev_info(&pdev->dev, "OMAP DMA engine driver%s\n", od->ll123_supported ? " (LinkedList1/2/3 supported)" : ""); @@ -1616,6 +1832,9 @@ static int omap_dma_remove(struct platform_device *pdev) struct omap_dmadev *od = platform_get_drvdata(pdev); int irq; + if (od->cfg->may_lose_context) + cpu_pm_unregister_notifier(&od->nb); + if (pdev->dev.of_node) of_dma_controller_free(pdev->dev.of_node); @@ -1637,12 +1856,45 @@ static int omap_dma_remove(struct platform_device *pdev) return 0; } +static const struct omap_dma_config omap2420_data = { + .lch_end = CCFN, + .rw_priority = true, + .needs_lch_clear = true, + .needs_busy_check = true, +}; + +static const struct omap_dma_config omap2430_data = { + .lch_end = CCFN, + .rw_priority = true, + .needs_lch_clear = true, +}; + +static const struct omap_dma_config omap3430_data = { + .lch_end = CCFN, + .rw_priority = true, + .needs_lch_clear = true, + .may_lose_context = true, +}; + +static const struct omap_dma_config omap3630_data = { + .lch_end = CCDN, + .rw_priority = true, + .needs_lch_clear = true, + .may_lose_context = true, +}; + +static const struct omap_dma_config omap4_data = { + .lch_end = CCDN, + .rw_priority = true, + .needs_lch_clear = true, +}; + static const struct of_device_id omap_dma_match[] = { - { .compatible = "ti,omap2420-sdma", }, - { .compatible = "ti,omap2430-sdma", }, - { .compatible = "ti,omap3430-sdma", }, - { .compatible = "ti,omap3630-sdma", }, - { .compatible = "ti,omap4430-sdma", }, + { .compatible = "ti,omap2420-sdma", .data = &omap2420_data, }, + { .compatible = "ti,omap2430-sdma", .data = &omap2430_data, }, + { .compatible = "ti,omap3430-sdma", .data = &omap3430_data, }, + { .compatible = "ti,omap3630-sdma", .data = &omap3630_data, }, + { .compatible = "ti,omap4430-sdma", .data = &omap4_data, }, {}, }; MODULE_DEVICE_TABLE(of, omap_dma_match); |