diff options
Diffstat (limited to 'drivers/dma')
54 files changed, 10345 insertions, 1398 deletions
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig index 6b5f37e..a016490 100644 --- a/drivers/dma/Kconfig +++ b/drivers/dma/Kconfig @@ -33,6 +33,24 @@ if DMADEVICES comment "DMA Devices" +config INTEL_MIC_X100_DMA + tristate "Intel MIC X100 DMA Driver" + depends on 64BIT && X86 && INTEL_MIC_BUS + select DMA_ENGINE + help + This enables DMA support for the Intel Many Integrated Core + (MIC) family of PCIe form factor coprocessor X100 devices that + run a 64 bit Linux OS. This driver will be used by both MIC + host and card drivers. + + If you are building host kernel with a MIC device or a card + kernel for a MIC device, then say M (recommended) or Y, else + say N. If unsure say N. + + More information about the Intel MIC family as well as the Linux + OS and tools for MIC to use with this driver are available from + <http://software.intel.com/en-us/mic-developer>. + config INTEL_MID_DMAC tristate "Intel MID DMA support for Peripheral DMA controllers" depends on PCI && X86 @@ -197,7 +215,7 @@ config AMCC_PPC440SPE_ADMA config TIMB_DMA tristate "Timberdale FPGA DMA support" - depends on MFD_TIMBERDALE || HAS_IOMEM + depends on MFD_TIMBERDALE select DMA_ENGINE help Enable support for the Timberdale FPGA DMA engine. @@ -234,7 +252,7 @@ config PL330_DMA config PCH_DMA tristate "Intel EG20T PCH / LAPIS Semicon IOH(ML7213/ML7223/ML7831) DMA" - depends on PCI && X86 + depends on PCI && (X86_32 || COMPILE_TEST) select DMA_ENGINE help Enable support for Intel EG20T PCH DMA engine. @@ -269,7 +287,7 @@ config MXS_DMA select DMA_ENGINE help Support the MXS DMA engine. This engine including APBH-DMA - and APBX-DMA is integrated into Freescale i.MX23/28 chips. + and APBX-DMA is integrated into Freescale i.MX23/28/MX6Q/MX6DL chips. config EP93XX_DMA bool "Cirrus Logic EP93xx DMA support" @@ -308,7 +326,7 @@ config DMA_OMAP config DMA_BCM2835 tristate "BCM2835 DMA engine support" - depends on (ARCH_BCM2835 || MACH_BCM2708) + depends on ARCH_BCM2835 select DMA_ENGINE select DMA_VIRTUAL_CHANNELS @@ -350,6 +368,46 @@ config MOXART_DMA select DMA_VIRTUAL_CHANNELS help Enable support for the MOXA ART SoC DMA controller. + +config FSL_EDMA + tristate "Freescale eDMA engine support" + depends on OF + select DMA_ENGINE + select DMA_VIRTUAL_CHANNELS + help + Support the Freescale eDMA engine with programmable channel + multiplexing capability for DMA request sources(slot). + This module can be found on Freescale Vybrid and LS-1 SoCs. + +config XILINX_VDMA + tristate "Xilinx AXI VDMA Engine" + depends on (ARCH_ZYNQ || MICROBLAZE) + select DMA_ENGINE + help + Enable support for Xilinx AXI VDMA Soft IP. + + This engine provides high-bandwidth direct memory access + between memory and AXI4-Stream video type target + peripherals including peripherals which support AXI4- + Stream Video Protocol. It has two stream interfaces/ + channels, Memory Mapped to Stream (MM2S) and Stream to + Memory Mapped (S2MM) for the data transfers. + +config DMA_SUN6I + tristate "Allwinner A31 SoCs DMA support" + depends on MACH_SUN6I || COMPILE_TEST + depends on RESET_CONTROLLER + select DMA_ENGINE + select DMA_VIRTUAL_CHANNELS + help + Support for the DMA engine for Allwinner A31 SoCs. + +config NBPFAXI_DMA + tristate "Renesas Type-AXI NBPF DMA support" + select DMA_ENGINE + depends on ARM || COMPILE_TEST + help + Support for "Type-AXI" NBPF DMA IPs from Renesas config DMA_ENGINE bool @@ -364,6 +422,7 @@ config DMA_ACPI config DMA_OF def_bool y depends on OF + select DMA_ENGINE comment "DMA Clients" depends on DMA_ENGINE @@ -389,4 +448,13 @@ config DMATEST config DMA_ENGINE_RAID bool +config QCOM_BAM_DMA + tristate "QCOM BAM DMA support" + depends on ARCH_QCOM || (COMPILE_TEST && OF && ARM) + select DMA_ENGINE + select DMA_VIRTUAL_CHANNELS + ---help--- + Enable support for the QCOM BAM DMA controller. This controller + provides DMA capabilities for a variety of on-chip devices. + endif diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile index 0c9dc75..cb626c1 100644 --- a/drivers/dma/Makefile +++ b/drivers/dma/Makefile @@ -1,5 +1,5 @@ -ccflags-$(CONFIG_DMADEVICES_DEBUG) := -DDEBUG -ccflags-$(CONFIG_DMADEVICES_VDEBUG) += -DVERBOSE_DEBUG +subdir-ccflags-$(CONFIG_DMADEVICES_DEBUG) := -DDEBUG +subdir-ccflags-$(CONFIG_DMADEVICES_VDEBUG) += -DVERBOSE_DEBUG obj-$(CONFIG_DMA_ENGINE) += dmaengine.o obj-$(CONFIG_DMA_VIRTUAL_CHANNELS) += virt-dma.o @@ -43,3 +43,9 @@ obj-$(CONFIG_DMA_JZ4740) += dma-jz4740.o obj-$(CONFIG_TI_CPPI41) += cppi41.o obj-$(CONFIG_K3_DMA) += k3dma.o obj-$(CONFIG_MOXART_DMA) += moxart-dma.o +obj-$(CONFIG_FSL_EDMA) += fsl-edma.o +obj-$(CONFIG_QCOM_BAM_DMA) += qcom_bam_dma.o +obj-y += xilinx/ +obj-$(CONFIG_INTEL_MIC_X100_DMA) += mic_x100_dma.o +obj-$(CONFIG_NBPFAXI_DMA) += nbpfaxi.o +obj-$(CONFIG_DMA_SUN6I) += sun6i-dma.o diff --git a/drivers/dma/TODO b/drivers/dma/TODO index 734ed02..b8045cd 100644 --- a/drivers/dma/TODO +++ b/drivers/dma/TODO @@ -7,7 +7,6 @@ TODO for slave dma - imx-dma - imx-sdma - mxs-dma.c - - dw_dmac - intel_mid_dma 4. Check other subsystems for dma drivers and merge/move to dmaengine 5. Remove dma_slave_config's dma direction. diff --git a/drivers/dma/acpi-dma.c b/drivers/dma/acpi-dma.c index 1e506af..de361a1 100644 --- a/drivers/dma/acpi-dma.c +++ b/drivers/dma/acpi-dma.c @@ -13,6 +13,7 @@ */ #include <linux/device.h> +#include <linux/err.h> #include <linux/module.h> #include <linux/list.h> #include <linux/mutex.h> @@ -265,7 +266,7 @@ EXPORT_SYMBOL_GPL(devm_acpi_dma_controller_register); */ void devm_acpi_dma_controller_free(struct device *dev) { - WARN_ON(devres_destroy(dev, devm_acpi_dma_release, NULL, NULL)); + WARN_ON(devres_release(dev, devm_acpi_dma_release, NULL, NULL)); } EXPORT_SYMBOL_GPL(devm_acpi_dma_controller_free); @@ -343,7 +344,7 @@ static int acpi_dma_parse_fixed_dma(struct acpi_resource *res, void *data) * @index: index of FixedDMA descriptor for @dev * * Return: - * Pointer to appropriate dma channel on success or NULL on error. + * Pointer to appropriate dma channel on success or an error pointer. */ struct dma_chan *acpi_dma_request_slave_chan_by_index(struct device *dev, size_t index) @@ -358,10 +359,10 @@ struct dma_chan *acpi_dma_request_slave_chan_by_index(struct device *dev, /* Check if the device was enumerated by ACPI */ if (!dev || !ACPI_HANDLE(dev)) - return NULL; + return ERR_PTR(-ENODEV); if (acpi_bus_get_device(ACPI_HANDLE(dev), &adev)) - return NULL; + return ERR_PTR(-ENODEV); memset(&pdata, 0, sizeof(pdata)); pdata.index = index; @@ -376,7 +377,7 @@ struct dma_chan *acpi_dma_request_slave_chan_by_index(struct device *dev, acpi_dev_free_resource_list(&resource_list); if (dma_spec->slave_id < 0 || dma_spec->chan_id < 0) - return NULL; + return ERR_PTR(-ENODEV); mutex_lock(&acpi_dma_lock); @@ -399,7 +400,7 @@ struct dma_chan *acpi_dma_request_slave_chan_by_index(struct device *dev, } mutex_unlock(&acpi_dma_lock); - return chan; + return chan ? chan : ERR_PTR(-EPROBE_DEFER); } EXPORT_SYMBOL_GPL(acpi_dma_request_slave_chan_by_index); @@ -413,7 +414,7 @@ EXPORT_SYMBOL_GPL(acpi_dma_request_slave_chan_by_index); * the first FixedDMA descriptor is TX and second is RX. * * Return: - * Pointer to appropriate dma channel on success or NULL on error. + * Pointer to appropriate dma channel on success or an error pointer. */ struct dma_chan *acpi_dma_request_slave_chan_by_name(struct device *dev, const char *name) @@ -425,7 +426,7 @@ struct dma_chan *acpi_dma_request_slave_chan_by_name(struct device *dev, else if (!strcmp(name, "rx")) index = 1; else - return NULL; + return ERR_PTR(-ENODEV); return acpi_dma_request_slave_chan_by_index(dev, index); } diff --git a/drivers/dma/amba-pl08x.c b/drivers/dma/amba-pl08x.c index 8114731..e34024b 100644 --- a/drivers/dma/amba-pl08x.c +++ b/drivers/dma/amba-pl08x.c @@ -1040,7 +1040,7 @@ static int pl08x_fill_llis_for_desc(struct pl08x_driver_data *pl08x, if (early_bytes) { dev_vdbg(&pl08x->adev->dev, - "%s byte width LLIs (remain 0x%08x)\n", + "%s byte width LLIs (remain 0x%08zx)\n", __func__, bd.remainder); prep_byte_width_lli(pl08x, &bd, &cctl, early_bytes, num_llis++, &total_bytes); @@ -1653,7 +1653,7 @@ static struct dma_async_tx_descriptor *pl08x_prep_slave_sg( static struct dma_async_tx_descriptor *pl08x_prep_dma_cyclic( struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len, size_t period_len, enum dma_transfer_direction direction, - unsigned long flags, void *context) + unsigned long flags) { struct pl08x_dma_chan *plchan = to_pl08x_chan(chan); struct pl08x_driver_data *pl08x = plchan->host; @@ -1662,7 +1662,7 @@ static struct dma_async_tx_descriptor *pl08x_prep_dma_cyclic( dma_addr_t slave_addr; dev_dbg(&pl08x->adev->dev, - "%s prepare cyclic transaction of %d/%d bytes %s %s\n", + "%s prepare cyclic transaction of %zd/%zd bytes %s %s\n", __func__, period_len, buf_len, direction == DMA_MEM_TO_DEV ? "to" : "from", plchan->name); diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c index e2c04dc..ca9dd26 100644 --- a/drivers/dma/at_hdmac.c +++ b/drivers/dma/at_hdmac.c @@ -294,14 +294,16 @@ static int atc_get_bytes_left(struct dma_chan *chan) ret = -EINVAL; goto out; } - atchan->remain_desc -= (desc_cur->lli.ctrla & ATC_BTSIZE_MAX) - << (desc_first->tx_width); - if (atchan->remain_desc < 0) { + + count = (desc_cur->lli.ctrla & ATC_BTSIZE_MAX) + << desc_first->tx_width; + if (atchan->remain_desc < count) { ret = -EINVAL; goto out; - } else { - ret = atchan->remain_desc; } + + atchan->remain_desc -= count; + ret = atchan->remain_desc; } else { /* * Get residual bytes when current @@ -893,12 +895,11 @@ atc_dma_cyclic_fill_desc(struct dma_chan *chan, struct at_desc *desc, * @period_len: number of bytes for each period * @direction: transfer direction, to or from device * @flags: tx descriptor status flags - * @context: transfer context (ignored) */ static struct dma_async_tx_descriptor * atc_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len, size_t period_len, enum dma_transfer_direction direction, - unsigned long flags, void *context) + unsigned long flags) { struct at_dma_chan *atchan = to_at_dma_chan(chan); struct at_dma_slave *atslave = chan->private; @@ -1569,7 +1570,6 @@ static int at_dma_remove(struct platform_device *pdev) /* Disable interrupts */ atc_disable_chan_irq(atdma, chan->chan_id); - tasklet_disable(&atchan->tasklet); tasklet_kill(&atchan->tasklet); list_del(&chan->device_node); diff --git a/drivers/dma/bcm2835-dma.c b/drivers/dma/bcm2835-dma.c index a036021..6800797 100644 --- a/drivers/dma/bcm2835-dma.c +++ b/drivers/dma/bcm2835-dma.c @@ -335,7 +335,7 @@ static void bcm2835_dma_issue_pending(struct dma_chan *chan) static struct dma_async_tx_descriptor *bcm2835_dma_prep_dma_cyclic( struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len, size_t period_len, enum dma_transfer_direction direction, - unsigned long flags, void *context) + unsigned long flags) { struct bcm2835_chan *c = to_bcm2835_dma_chan(chan); enum dma_slave_buswidth dev_width; diff --git a/drivers/dma/cppi41.c b/drivers/dma/cppi41.c index c18aebf..8f8b0b6 100644 --- a/drivers/dma/cppi41.c +++ b/drivers/dma/cppi41.c @@ -86,6 +86,9 @@ #define USBSS_IRQ_PD_COMP (1 << 2) +/* Packet Descriptor */ +#define PD2_ZERO_LENGTH (1 << 19) + struct cppi41_channel { struct dma_chan chan; struct dma_async_tx_descriptor txd; @@ -307,7 +310,7 @@ static irqreturn_t cppi41_irq(int irq, void *data) __iormb(); while (val) { - u32 desc; + u32 desc, len; q_num = __fls(val); val &= ~(1 << q_num); @@ -319,9 +322,13 @@ static irqreturn_t cppi41_irq(int irq, void *data) q_num, desc); continue; } - c->residue = pd_trans_len(c->desc->pd6) - - pd_trans_len(c->desc->pd0); + if (c->desc->pd2 & PD2_ZERO_LENGTH) + len = 0; + else + len = pd_trans_len(c->desc->pd0); + + c->residue = pd_trans_len(c->desc->pd6) - len; dma_cookie_complete(&c->txd); c->txd.callback(c->txd.callback_param); } @@ -620,12 +627,15 @@ static int cppi41_stop_chan(struct dma_chan *chan) u32 desc_phys; int ret; + desc_phys = lower_32_bits(c->desc_phys); + desc_num = (desc_phys - cdd->descs_phys) / sizeof(struct cppi41_desc); + if (!cdd->chan_busy[desc_num]) + return 0; + ret = cppi41_tear_down_chan(c); if (ret) return ret; - desc_phys = lower_32_bits(c->desc_phys); - desc_num = (desc_phys - cdd->descs_phys) / sizeof(struct cppi41_desc); WARN_ON(!cdd->chan_busy[desc_num]); cdd->chan_busy[desc_num] = NULL; diff --git a/drivers/dma/dma-jz4740.c b/drivers/dma/dma-jz4740.c index 94c380f..ae2ab14 100644 --- a/drivers/dma/dma-jz4740.c +++ b/drivers/dma/dma-jz4740.c @@ -362,8 +362,9 @@ static void jz4740_dma_chan_irq(struct jz4740_dmaengine_chan *chan) vchan_cyclic_callback(&chan->desc->vdesc); } else { if (chan->next_sg == chan->desc->num_sgs) { - chan->desc = NULL; + list_del(&chan->desc->vdesc.node); vchan_cookie_complete(&chan->desc->vdesc); + chan->desc = NULL; } } } @@ -433,7 +434,7 @@ static struct dma_async_tx_descriptor *jz4740_dma_prep_slave_sg( static struct dma_async_tx_descriptor *jz4740_dma_prep_dma_cyclic( struct dma_chan *c, dma_addr_t buf_addr, size_t buf_len, size_t period_len, enum dma_transfer_direction direction, - unsigned long flags, void *context) + unsigned long flags) { struct jz4740_dmaengine_chan *chan = to_jz4740_dma_chan(c); struct jz4740_dma_desc *desc; @@ -614,4 +615,4 @@ module_platform_driver(jz4740_dma_driver); MODULE_AUTHOR("Lars-Peter Clausen <lars@metafoo.de>"); MODULE_DESCRIPTION("JZ4740 DMA driver"); -MODULE_LICENSE("GPLv2"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c index 268de18..24bfaf0 100644 --- a/drivers/dma/dmaengine.c +++ b/drivers/dma/dmaengine.c @@ -627,18 +627,13 @@ EXPORT_SYMBOL_GPL(__dma_request_channel); struct dma_chan *dma_request_slave_channel_reason(struct device *dev, const char *name) { - struct dma_chan *chan; - /* If device-tree is present get slave info from here */ if (dev->of_node) return of_dma_request_slave_channel(dev->of_node, name); /* If device was enumerated by ACPI get slave info from here */ - if (ACPI_HANDLE(dev)) { - chan = acpi_dma_request_slave_chan_by_name(dev, name); - if (chan) - return chan; - } + if (ACPI_HANDLE(dev)) + return acpi_dma_request_slave_chan_by_name(dev, name); return ERR_PTR(-ENODEV); } @@ -1014,6 +1009,7 @@ static void dmaengine_unmap(struct kref *kref) dma_unmap_page(dev, unmap->addr[i], unmap->len, DMA_BIDIRECTIONAL); } + cnt = unmap->map_cnt; mempool_free(unmap, __get_unmap_pool(cnt)->pool); } @@ -1079,6 +1075,7 @@ dmaengine_get_unmap_data(struct device *dev, int nr, gfp_t flags) memset(unmap, 0, sizeof(*unmap)); kref_init(&unmap->kref); unmap->dev = dev; + unmap->map_cnt = nr; return unmap; } diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c index 69616e2..a8d7809 100644 --- a/drivers/dma/dmatest.c +++ b/drivers/dma/dmatest.c @@ -340,7 +340,7 @@ static unsigned int min_odd(unsigned int x, unsigned int y) static void result(const char *err, unsigned int n, unsigned int src_off, unsigned int dst_off, unsigned int len, unsigned long data) { - pr_info("%s: result #%u: '%s' with src_off=0x%x dst_off=0x%x len=0x%x (%lu)", + pr_info("%s: result #%u: '%s' with src_off=0x%x dst_off=0x%x len=0x%x (%lu)\n", current->comm, n, err, src_off, dst_off, len, data); } @@ -348,7 +348,7 @@ static void dbg_result(const char *err, unsigned int n, unsigned int src_off, unsigned int dst_off, unsigned int len, unsigned long data) { - pr_debug("%s: result #%u: '%s' with src_off=0x%x dst_off=0x%x len=0x%x (%lu)", + pr_debug("%s: result #%u: '%s' with src_off=0x%x dst_off=0x%x len=0x%x (%lu)\n", current->comm, n, err, src_off, dst_off, len, data); } diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c index 13ac3f2..1af731b 100644 --- a/drivers/dma/dw/core.c +++ b/drivers/dma/dw/core.c @@ -33,8 +33,8 @@ * of which use ARM any more). See the "Databook" from Synopsys for * information beyond what licensees probably provide. * - * The driver has currently been tested only with the Atmel AT32AP7000, - * which does not support descriptor writeback. + * The driver has been tested with the Atmel AT32AP7000, which does not + * support descriptor writeback. */ static inline bool is_request_line_unset(struct dw_dma_chan *dwc) @@ -279,6 +279,19 @@ static void dwc_dostart(struct dw_dma_chan *dwc, struct dw_desc *first) channel_set_bit(dw, CH_EN, dwc->mask); } +static void dwc_dostart_first_queued(struct dw_dma_chan *dwc) +{ + struct dw_desc *desc; + + if (list_empty(&dwc->queue)) + return; + + list_move(dwc->queue.next, &dwc->active_list); + desc = dwc_first_active(dwc); + dev_vdbg(chan2dev(&dwc->chan), "%s: started %u\n", __func__, desc->txd.cookie); + dwc_dostart(dwc, desc); +} + /*----------------------------------------------------------------------*/ static void @@ -335,10 +348,7 @@ static void dwc_complete_all(struct dw_dma *dw, struct dw_dma_chan *dwc) * the completed ones. */ list_splice_init(&dwc->active_list, &list); - if (!list_empty(&dwc->queue)) { - list_move(dwc->queue.next, &dwc->active_list); - dwc_dostart(dwc, dwc_first_active(dwc)); - } + dwc_dostart_first_queued(dwc); spin_unlock_irqrestore(&dwc->lock, flags); @@ -467,10 +477,7 @@ static void dwc_scan_descriptors(struct dw_dma *dw, struct dw_dma_chan *dwc) /* Try to continue after resetting the channel... */ dwc_chan_disable(dw, dwc); - if (!list_empty(&dwc->queue)) { - list_move(dwc->queue.next, &dwc->active_list); - dwc_dostart(dwc, dwc_first_active(dwc)); - } + dwc_dostart_first_queued(dwc); spin_unlock_irqrestore(&dwc->lock, flags); } @@ -677,17 +684,9 @@ static dma_cookie_t dwc_tx_submit(struct dma_async_tx_descriptor *tx) * possible, perhaps even appending to those already submitted * for DMA. But this is hard to do in a race-free manner. */ - if (list_empty(&dwc->active_list)) { - dev_vdbg(chan2dev(tx->chan), "%s: started %u\n", __func__, - desc->txd.cookie); - list_add_tail(&desc->desc_node, &dwc->active_list); - dwc_dostart(dwc, dwc_first_active(dwc)); - } else { - dev_vdbg(chan2dev(tx->chan), "%s: queued %u\n", __func__, - desc->txd.cookie); - list_add_tail(&desc->desc_node, &dwc->queue); - } + dev_vdbg(chan2dev(tx->chan), "%s: queued %u\n", __func__, desc->txd.cookie); + list_add_tail(&desc->desc_node, &dwc->queue); spin_unlock_irqrestore(&dwc->lock, flags); @@ -1092,9 +1091,12 @@ dwc_tx_status(struct dma_chan *chan, static void dwc_issue_pending(struct dma_chan *chan) { struct dw_dma_chan *dwc = to_dw_dma_chan(chan); + unsigned long flags; - if (!list_empty(&dwc->queue)) - dwc_scan_descriptors(to_dw_dma(chan->device), dwc); + spin_lock_irqsave(&dwc->lock, flags); + if (list_empty(&dwc->active_list)) + dwc_dostart_first_queued(dwc); + spin_unlock_irqrestore(&dwc->lock, flags); } static int dwc_alloc_chan_resources(struct dma_chan *chan) @@ -1479,7 +1481,6 @@ static void dw_dma_off(struct dw_dma *dw) int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata) { struct dw_dma *dw; - size_t size; bool autocfg; unsigned int dw_params; unsigned int nr_channels; @@ -1487,6 +1488,20 @@ int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata) int err; int i; + dw = devm_kzalloc(chip->dev, sizeof(*dw), GFP_KERNEL); + if (!dw) + return -ENOMEM; + + dw->regs = chip->regs; + chip->dw = dw; + + dw->clk = devm_clk_get(chip->dev, "hclk"); + if (IS_ERR(dw->clk)) + return PTR_ERR(dw->clk); + err = clk_prepare_enable(dw->clk); + if (err) + return err; + dw_params = dma_read_byaddr(chip->regs, DW_PARAMS); autocfg = dw_params >> DW_PARAMS_EN & 0x1; @@ -1494,33 +1509,31 @@ int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata) if (!pdata && autocfg) { pdata = devm_kzalloc(chip->dev, sizeof(*pdata), GFP_KERNEL); - if (!pdata) - return -ENOMEM; + if (!pdata) { + err = -ENOMEM; + goto err_pdata; + } /* Fill platform data with the default values */ pdata->is_private = true; pdata->chan_allocation_order = CHAN_ALLOCATION_ASCENDING; pdata->chan_priority = CHAN_PRIORITY_ASCENDING; - } else if (!pdata || pdata->nr_channels > DW_DMA_MAX_NR_CHANNELS) - return -EINVAL; + } else if (!pdata || pdata->nr_channels > DW_DMA_MAX_NR_CHANNELS) { + err = -EINVAL; + goto err_pdata; + } if (autocfg) nr_channels = (dw_params >> DW_PARAMS_NR_CHAN & 0x7) + 1; else nr_channels = pdata->nr_channels; - size = sizeof(struct dw_dma) + nr_channels * sizeof(struct dw_dma_chan); - dw = devm_kzalloc(chip->dev, size, GFP_KERNEL); - if (!dw) - return -ENOMEM; - - dw->clk = devm_clk_get(chip->dev, "hclk"); - if (IS_ERR(dw->clk)) - return PTR_ERR(dw->clk); - clk_prepare_enable(dw->clk); - - dw->regs = chip->regs; - chip->dw = dw; + dw->chan = devm_kcalloc(chip->dev, nr_channels, sizeof(*dw->chan), + GFP_KERNEL); + if (!dw->chan) { + err = -ENOMEM; + goto err_pdata; + } /* Get hardware configuration parameters */ if (autocfg) { @@ -1545,21 +1558,22 @@ int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata) /* Disable BLOCK interrupts as well */ channel_clear_bit(dw, MASK.BLOCK, dw->all_chan_mask); - err = devm_request_irq(chip->dev, chip->irq, dw_dma_interrupt, - IRQF_SHARED, "dw_dmac", dw); - if (err) - return err; - /* Create a pool of consistent memory blocks for hardware descriptors */ dw->desc_pool = dmam_pool_create("dw_dmac_desc_pool", chip->dev, sizeof(struct dw_desc), 4, 0); if (!dw->desc_pool) { dev_err(chip->dev, "No memory for descriptors dma pool\n"); - return -ENOMEM; + err = -ENOMEM; + goto err_pdata; } tasklet_init(&dw->tasklet, dw_dma_tasklet, (unsigned long)dw); + err = request_irq(chip->irq, dw_dma_interrupt, IRQF_SHARED, + "dw_dmac", dw); + if (err) + goto err_pdata; + INIT_LIST_HEAD(&dw->dma.channels); for (i = 0; i < nr_channels; i++) { struct dw_dma_chan *dwc = &dw->chan[i]; @@ -1647,12 +1661,20 @@ int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata) dma_writel(dw, CFG, DW_CFG_DMA_EN); + err = dma_async_device_register(&dw->dma); + if (err) + goto err_dma_register; + dev_info(chip->dev, "DesignWare DMA Controller, %d channels\n", nr_channels); - dma_async_device_register(&dw->dma); - return 0; + +err_dma_register: + free_irq(chip->irq, dw); +err_pdata: + clk_disable_unprepare(dw->clk); + return err; } EXPORT_SYMBOL_GPL(dw_dma_probe); @@ -1664,6 +1686,7 @@ int dw_dma_remove(struct dw_dma_chip *chip) dw_dma_off(dw); dma_async_device_unregister(&dw->dma); + free_irq(chip->irq, dw); tasklet_kill(&dw->tasklet); list_for_each_entry_safe(dwc, _dwc, &dw->dma.channels, @@ -1672,6 +1695,8 @@ int dw_dma_remove(struct dw_dma_chip *chip) channel_clear_bit(dw, CH_EN, dwc->mask); } + clk_disable_unprepare(dw->clk); + return 0; } EXPORT_SYMBOL_GPL(dw_dma_remove); diff --git a/drivers/dma/dw/pci.c b/drivers/dma/dw/pci.c index e89fc24..39e30c3 100644 --- a/drivers/dma/dw/pci.c +++ b/drivers/dma/dw/pci.c @@ -75,7 +75,31 @@ static void dw_pci_remove(struct pci_dev *pdev) dev_warn(&pdev->dev, "can't remove device properly: %d\n", ret); } -static DEFINE_PCI_DEVICE_TABLE(dw_pci_id_table) = { +#ifdef CONFIG_PM_SLEEP + +static int dw_pci_suspend_late(struct device *dev) +{ + struct pci_dev *pci = to_pci_dev(dev); + struct dw_dma_chip *chip = pci_get_drvdata(pci); + + return dw_dma_suspend(chip); +}; + +static int dw_pci_resume_early(struct device *dev) +{ + struct pci_dev *pci = to_pci_dev(dev); + struct dw_dma_chip *chip = pci_get_drvdata(pci); + + return dw_dma_resume(chip); +}; + +#endif /* CONFIG_PM_SLEEP */ + +static const struct dev_pm_ops dw_pci_dev_pm_ops = { + SET_LATE_SYSTEM_SLEEP_PM_OPS(dw_pci_suspend_late, dw_pci_resume_early) +}; + +static const struct pci_device_id dw_pci_id_table[] = { /* Medfield */ { PCI_VDEVICE(INTEL, 0x0827), (kernel_ulong_t)&dw_pci_pdata }, { PCI_VDEVICE(INTEL, 0x0830), (kernel_ulong_t)&dw_pci_pdata }, @@ -83,6 +107,9 @@ static DEFINE_PCI_DEVICE_TABLE(dw_pci_id_table) = { /* BayTrail */ { PCI_VDEVICE(INTEL, 0x0f06), (kernel_ulong_t)&dw_pci_pdata }, { PCI_VDEVICE(INTEL, 0x0f40), (kernel_ulong_t)&dw_pci_pdata }, + + /* Haswell */ + { PCI_VDEVICE(INTEL, 0x9c60), (kernel_ulong_t)&dw_pci_pdata }, { } }; MODULE_DEVICE_TABLE(pci, dw_pci_id_table); @@ -92,6 +119,9 @@ static struct pci_driver dw_pci_driver = { .id_table = dw_pci_id_table, .probe = dw_pci_probe, .remove = dw_pci_remove, + .driver = { + .pm = &dw_pci_dev_pm_ops, + }, }; module_pci_driver(dw_pci_driver); diff --git a/drivers/dma/dw/platform.c b/drivers/dma/dw/platform.c index 453822c..c5b339a 100644 --- a/drivers/dma/dw/platform.c +++ b/drivers/dma/dw/platform.c @@ -256,7 +256,7 @@ MODULE_DEVICE_TABLE(acpi, dw_dma_acpi_id_table); #ifdef CONFIG_PM_SLEEP -static int dw_suspend_noirq(struct device *dev) +static int dw_suspend_late(struct device *dev) { struct platform_device *pdev = to_platform_device(dev); struct dw_dma_chip *chip = platform_get_drvdata(pdev); @@ -264,7 +264,7 @@ static int dw_suspend_noirq(struct device *dev) return dw_dma_suspend(chip); } -static int dw_resume_noirq(struct device *dev) +static int dw_resume_early(struct device *dev) { struct platform_device *pdev = to_platform_device(dev); struct dw_dma_chip *chip = platform_get_drvdata(pdev); @@ -272,20 +272,10 @@ static int dw_resume_noirq(struct device *dev) return dw_dma_resume(chip); } -#else /* !CONFIG_PM_SLEEP */ - -#define dw_suspend_noirq NULL -#define dw_resume_noirq NULL - -#endif /* !CONFIG_PM_SLEEP */ +#endif /* CONFIG_PM_SLEEP */ static const struct dev_pm_ops dw_dev_pm_ops = { - .suspend_noirq = dw_suspend_noirq, - .resume_noirq = dw_resume_noirq, - .freeze_noirq = dw_suspend_noirq, - .thaw_noirq = dw_resume_noirq, - .restore_noirq = dw_resume_noirq, - .poweroff_noirq = dw_suspend_noirq, + SET_LATE_SYSTEM_SLEEP_PM_OPS(dw_suspend_late, dw_resume_early) }; static struct platform_driver dw_driver = { diff --git a/drivers/dma/dw/regs.h b/drivers/dma/dw/regs.h index deb4274..bb98d3e 100644 --- a/drivers/dma/dw/regs.h +++ b/drivers/dma/dw/regs.h @@ -252,13 +252,13 @@ struct dw_dma { struct tasklet_struct tasklet; struct clk *clk; + /* channels */ + struct dw_dma_chan *chan; u8 all_chan_mask; /* hardware configuration */ unsigned char nr_masters; unsigned char data_width[4]; - - struct dw_dma_chan chan[0]; }; static inline struct dw_dma_regs __iomem *__dw_regs(struct dw_dma *dw) diff --git a/drivers/dma/edma.c b/drivers/dma/edma.c index cd8da45..7b65633 100644 --- a/drivers/dma/edma.c +++ b/drivers/dma/edma.c @@ -23,6 +23,7 @@ #include <linux/platform_device.h> #include <linux/slab.h> #include <linux/spinlock.h> +#include <linux/of.h> #include <linux/platform_data/edma.h> @@ -57,14 +58,48 @@ #define EDMA_MAX_SLOTS MAX_NR_SG #define EDMA_DESCRIPTORS 16 +struct edma_pset { + u32 len; + dma_addr_t addr; + struct edmacc_param param; +}; + struct edma_desc { struct virt_dma_desc vdesc; struct list_head node; + enum dma_transfer_direction direction; int cyclic; int absync; int pset_nr; + struct edma_chan *echan; int processed; - struct edmacc_param pset[0]; + + /* + * The following 4 elements are used for residue accounting. + * + * - processed_stat: the number of SG elements we have traversed + * so far to cover accounting. This is updated directly to processed + * during edma_callback and is always <= processed, because processed + * refers to the number of pending transfer (programmed to EDMA + * controller), where as processed_stat tracks number of transfers + * accounted for so far. + * + * - residue: The amount of bytes we have left to transfer for this desc + * + * - residue_stat: The residue in bytes of data we have covered + * so far for accounting. This is updated directly to residue + * during callbacks to keep it current. + * + * - sg_len: Tracks the length of the current intermediate transfer, + * this is required to update the residue during intermediate transfer + * completion callback. + */ + int processed_stat; + u32 sg_len; + u32 residue; + u32 residue_stat; + + struct edma_pset pset[0]; }; struct edma_cc; @@ -136,12 +171,14 @@ static void edma_execute(struct edma_chan *echan) /* Find out how many left */ left = edesc->pset_nr - edesc->processed; nslots = min(MAX_NR_SG, left); + edesc->sg_len = 0; /* Write descriptor PaRAM set(s) */ for (i = 0; i < nslots; i++) { j = i + edesc->processed; - edma_write_slot(echan->slot[i], &edesc->pset[j]); - dev_dbg(echan->vchan.chan.device->dev, + edma_write_slot(echan->slot[i], &edesc->pset[j].param); + edesc->sg_len += edesc->pset[j].len; + dev_vdbg(echan->vchan.chan.device->dev, "\n pset[%d]:\n" " chnum\t%d\n" " slot\t%d\n" @@ -154,14 +191,14 @@ static void edma_execute(struct edma_chan *echan) " cidx\t%08x\n" " lkrld\t%08x\n", j, echan->ch_num, echan->slot[i], - edesc->pset[j].opt, - edesc->pset[j].src, - edesc->pset[j].dst, - edesc->pset[j].a_b_cnt, - edesc->pset[j].ccnt, - edesc->pset[j].src_dst_bidx, - edesc->pset[j].src_dst_cidx, - edesc->pset[j].link_bcntrld); + edesc->pset[j].param.opt, + edesc->pset[j].param.src, + edesc->pset[j].param.dst, + edesc->pset[j].param.a_b_cnt, + edesc->pset[j].param.ccnt, + edesc->pset[j].param.src_dst_bidx, + edesc->pset[j].param.src_dst_cidx, + edesc->pset[j].param.link_bcntrld); /* Link to the previous slot if not the last set */ if (i != (nslots - 1)) edma_link(echan->slot[i], echan->slot[i+1]); @@ -182,11 +219,14 @@ static void edma_execute(struct edma_chan *echan) echan->ecc->dummy_slot); } - edma_resume(echan->ch_num); - if (edesc->processed <= MAX_NR_SG) { - dev_dbg(dev, "first transfer starting %d\n", echan->ch_num); + dev_dbg(dev, "first transfer starting on channel %d\n", + echan->ch_num); edma_start(echan->ch_num); + } else { + dev_dbg(dev, "chan: %d: completed %d elements, resuming\n", + echan->ch_num, edesc->processed); + edma_resume(echan->ch_num); } /* @@ -195,7 +235,7 @@ static void edma_execute(struct edma_chan *echan) * MAX_NR_SG */ if (echan->missed) { - dev_dbg(dev, "missed event in execute detected\n"); + dev_dbg(dev, "missed event on channel %d\n", echan->ch_num); edma_clean_channel(echan->ch_num); edma_stop(echan->ch_num); edma_start(echan->ch_num); @@ -217,8 +257,13 @@ static int edma_terminate_all(struct edma_chan *echan) * echan->edesc is NULL and exit.) */ if (echan->edesc) { + int cyclic = echan->edesc->cyclic; echan->edesc = NULL; edma_stop(echan->ch_num); + /* Move the cyclic channel back to default queue */ + if (cyclic) + edma_assign_channel_eventq(echan->ch_num, + EVENTQ_DEFAULT); } vchan_get_all_descriptors(&echan->vchan, &head); @@ -240,6 +285,26 @@ static int edma_slave_config(struct edma_chan *echan, return 0; } +static int edma_dma_pause(struct edma_chan *echan) +{ + /* Pause/Resume only allowed with cyclic mode */ + if (!echan->edesc->cyclic) + return -EINVAL; + + edma_pause(echan->ch_num); + return 0; +} + +static int edma_dma_resume(struct edma_chan *echan) +{ + /* Pause/Resume only allowed with cyclic mode */ + if (!echan->edesc->cyclic) + return -EINVAL; + + edma_resume(echan->ch_num); + return 0; +} + static int edma_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd, unsigned long arg) { @@ -255,6 +320,14 @@ static int edma_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd, config = (struct dma_slave_config *)arg; ret = edma_slave_config(echan, config); break; + case DMA_PAUSE: + ret = edma_dma_pause(echan); + break; + + case DMA_RESUME: + ret = edma_dma_resume(echan); + break; + default: ret = -ENOSYS; } @@ -273,18 +346,23 @@ static int edma_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd, * @dma_length: Total length of the DMA transfer * @direction: Direction of the transfer */ -static int edma_config_pset(struct dma_chan *chan, struct edmacc_param *pset, +static int edma_config_pset(struct dma_chan *chan, struct edma_pset *epset, dma_addr_t src_addr, dma_addr_t dst_addr, u32 burst, enum dma_slave_buswidth dev_width, unsigned int dma_length, enum dma_transfer_direction direction) { struct edma_chan *echan = to_edma_chan(chan); struct device *dev = chan->device->dev; + struct edmacc_param *param = &epset->param; int acnt, bcnt, ccnt, cidx; int src_bidx, dst_bidx, src_cidx, dst_cidx; int absync; acnt = dev_width; + + /* src/dst_maxburst == 0 is the same case as src/dst_maxburst == 1 */ + if (!burst) + burst = 1; /* * If the maxburst is equal to the fifo width, use * A-synced transfers. This allows for large contiguous @@ -335,41 +413,50 @@ static int edma_config_pset(struct dma_chan *chan, struct edmacc_param *pset, cidx = acnt * bcnt; } + epset->len = dma_length; + if (direction == DMA_MEM_TO_DEV) { src_bidx = acnt; src_cidx = cidx; dst_bidx = 0; dst_cidx = 0; + epset->addr = src_addr; } else if (direction == DMA_DEV_TO_MEM) { src_bidx = 0; src_cidx = 0; dst_bidx = acnt; dst_cidx = cidx; + epset->addr = dst_addr; + } else if (direction == DMA_MEM_TO_MEM) { + src_bidx = acnt; + src_cidx = cidx; + dst_bidx = acnt; + dst_cidx = cidx; } else { dev_err(dev, "%s: direction not implemented yet\n", __func__); return -EINVAL; } - pset->opt = EDMA_TCC(EDMA_CHAN_SLOT(echan->ch_num)); + param->opt = EDMA_TCC(EDMA_CHAN_SLOT(echan->ch_num)); /* Configure A or AB synchronized transfers */ if (absync) - pset->opt |= SYNCDIM; + param->opt |= SYNCDIM; - pset->src = src_addr; - pset->dst = dst_addr; + param->src = src_addr; + param->dst = dst_addr; - pset->src_dst_bidx = (dst_bidx << 16) | src_bidx; - pset->src_dst_cidx = (dst_cidx << 16) | src_cidx; + param->src_dst_bidx = (dst_bidx << 16) | src_bidx; + param->src_dst_cidx = (dst_cidx << 16) | src_cidx; - pset->a_b_cnt = bcnt << 16 | acnt; - pset->ccnt = ccnt; + param->a_b_cnt = bcnt << 16 | acnt; + param->ccnt = ccnt; /* * Only time when (bcntrld) auto reload is required is for * A-sync case, and in this case, a requirement of reload value * of SZ_64K-1 only is assured. 'link' is initially set to NULL * and then later will be populated by edma_execute. */ - pset->link_bcntrld = 0xffffffff; + param->link_bcntrld = 0xffffffff; return absync; } @@ -399,23 +486,26 @@ static struct dma_async_tx_descriptor *edma_prep_slave_sg( dev_width = echan->cfg.dst_addr_width; burst = echan->cfg.dst_maxburst; } else { - dev_err(dev, "%s: bad direction?\n", __func__); + dev_err(dev, "%s: bad direction: %d\n", __func__, direction); return NULL; } if (dev_width == DMA_SLAVE_BUSWIDTH_UNDEFINED) { - dev_err(dev, "Undefined slave buswidth\n"); + dev_err(dev, "%s: Undefined slave buswidth\n", __func__); return NULL; } edesc = kzalloc(sizeof(*edesc) + sg_len * sizeof(edesc->pset[0]), GFP_ATOMIC); if (!edesc) { - dev_dbg(dev, "Failed to allocate a descriptor\n"); + dev_err(dev, "%s: Failed to allocate a descriptor\n", __func__); return NULL; } edesc->pset_nr = sg_len; + edesc->residue = 0; + edesc->direction = direction; + edesc->echan = echan; /* Allocate a PaRAM slot, if needed */ nslots = min_t(unsigned, MAX_NR_SG, sg_len); @@ -427,7 +517,8 @@ static struct dma_async_tx_descriptor *edma_prep_slave_sg( EDMA_SLOT_ANY); if (echan->slot[i] < 0) { kfree(edesc); - dev_err(dev, "Failed to allocate slot\n"); + dev_err(dev, "%s: Failed to allocate slot\n", + __func__); return NULL; } } @@ -450,16 +541,56 @@ static struct dma_async_tx_descriptor *edma_prep_slave_sg( } edesc->absync = ret; + edesc->residue += sg_dma_len(sg); /* If this is the last in a current SG set of transactions, enable interrupts so that next set is processed */ if (!((i+1) % MAX_NR_SG)) - edesc->pset[i].opt |= TCINTEN; + edesc->pset[i].param.opt |= TCINTEN; /* If this is the last set, enable completion interrupt flag */ if (i == sg_len - 1) - edesc->pset[i].opt |= TCINTEN; + edesc->pset[i].param.opt |= TCINTEN; } + edesc->residue_stat = edesc->residue; + + return vchan_tx_prep(&echan->vchan, &edesc->vdesc, tx_flags); +} + +struct dma_async_tx_descriptor *edma_prep_dma_memcpy( + struct dma_chan *chan, dma_addr_t dest, dma_addr_t src, + size_t len, unsigned long tx_flags) +{ + int ret; + struct edma_desc *edesc; + struct device *dev = chan->device->dev; + struct edma_chan *echan = to_edma_chan(chan); + + if (unlikely(!echan || !len)) + return NULL; + + edesc = kzalloc(sizeof(*edesc) + sizeof(edesc->pset[0]), GFP_ATOMIC); + if (!edesc) { + dev_dbg(dev, "Failed to allocate a descriptor\n"); + return NULL; + } + + edesc->pset_nr = 1; + + ret = edma_config_pset(chan, &edesc->pset[0], src, dest, 1, + DMA_SLAVE_BUSWIDTH_4_BYTES, len, DMA_MEM_TO_MEM); + if (ret < 0) + return NULL; + + edesc->absync = ret; + + /* + * Enable intermediate transfer chaining to re-trigger channel + * on completion of every TR, and enable transfer-completion + * interrupt on completion of the whole transfer. + */ + edesc->pset[0].param.opt |= ITCCHEN; + edesc->pset[0].param.opt |= TCINTEN; return vchan_tx_prep(&echan->vchan, &edesc->vdesc, tx_flags); } @@ -467,7 +598,7 @@ static struct dma_async_tx_descriptor *edma_prep_slave_sg( static struct dma_async_tx_descriptor *edma_prep_dma_cyclic( struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len, size_t period_len, enum dma_transfer_direction direction, - unsigned long tx_flags, void *context) + unsigned long tx_flags) { struct edma_chan *echan = to_edma_chan(chan); struct device *dev = chan->device->dev; @@ -491,12 +622,12 @@ static struct dma_async_tx_descriptor *edma_prep_dma_cyclic( dev_width = echan->cfg.dst_addr_width; burst = echan->cfg.dst_maxburst; } else { - dev_err(dev, "%s: bad direction?\n", __func__); + dev_err(dev, "%s: bad direction: %d\n", __func__, direction); return NULL; } if (dev_width == DMA_SLAVE_BUSWIDTH_UNDEFINED) { - dev_err(dev, "Undefined slave buswidth\n"); + dev_err(dev, "%s: Undefined slave buswidth\n", __func__); return NULL; } @@ -521,16 +652,18 @@ static struct dma_async_tx_descriptor *edma_prep_dma_cyclic( edesc = kzalloc(sizeof(*edesc) + nslots * sizeof(edesc->pset[0]), GFP_ATOMIC); if (!edesc) { - dev_dbg(dev, "Failed to allocate a descriptor\n"); + dev_err(dev, "%s: Failed to allocate a descriptor\n", __func__); return NULL; } edesc->cyclic = 1; edesc->pset_nr = nslots; + edesc->residue = edesc->residue_stat = buf_len; + edesc->direction = direction; + edesc->echan = echan; - dev_dbg(dev, "%s: nslots=%d\n", __func__, nslots); - dev_dbg(dev, "%s: period_len=%d\n", __func__, period_len); - dev_dbg(dev, "%s: buf_len=%d\n", __func__, buf_len); + dev_dbg(dev, "%s: channel=%d nslots=%d period_len=%zu buf_len=%zu\n", + __func__, echan->ch_num, nslots, period_len, buf_len); for (i = 0; i < nslots; i++) { /* Allocate a PaRAM slot, if needed */ @@ -539,7 +672,9 @@ static struct dma_async_tx_descriptor *edma_prep_dma_cyclic( edma_alloc_slot(EDMA_CTLR(echan->ch_num), EDMA_SLOT_ANY); if (echan->slot[i] < 0) { - dev_err(dev, "Failed to allocate slot\n"); + kfree(edesc); + dev_err(dev, "%s: Failed to allocate slot\n", + __func__); return NULL; } } @@ -553,16 +688,18 @@ static struct dma_async_tx_descriptor *edma_prep_dma_cyclic( ret = edma_config_pset(chan, &edesc->pset[i], src_addr, dst_addr, burst, dev_width, period_len, direction); - if (ret < 0) + if (ret < 0) { + kfree(edesc); return NULL; + } if (direction == DMA_DEV_TO_MEM) dst_addr += period_len; else src_addr += period_len; - dev_dbg(dev, "%s: Configure period %d of buf:\n", __func__, i); - dev_dbg(dev, + dev_vdbg(dev, "%s: Configure period %d of buf:\n", __func__, i); + dev_vdbg(dev, "\n pset[%d]:\n" " chnum\t%d\n" " slot\t%d\n" @@ -575,24 +712,27 @@ static struct dma_async_tx_descriptor *edma_prep_dma_cyclic( " cidx\t%08x\n" " lkrld\t%08x\n", i, echan->ch_num, echan->slot[i], - edesc->pset[i].opt, - edesc->pset[i].src, - edesc->pset[i].dst, - edesc->pset[i].a_b_cnt, - edesc->pset[i].ccnt, - edesc->pset[i].src_dst_bidx, - edesc->pset[i].src_dst_cidx, - edesc->pset[i].link_bcntrld); + edesc->pset[i].param.opt, + edesc->pset[i].param.src, + edesc->pset[i].param.dst, + edesc->pset[i].param.a_b_cnt, + edesc->pset[i].param.ccnt, + edesc->pset[i].param.src_dst_bidx, + edesc->pset[i].param.src_dst_cidx, + edesc->pset[i].param.link_bcntrld); edesc->absync = ret; /* - * Enable interrupts for every period because callback - * has to be called for every period. + * Enable period interrupt only if it is requested */ - edesc->pset[i].opt |= TCINTEN; + if (tx_flags & DMA_PREP_INTERRUPT) + edesc->pset[i].param.opt |= TCINTEN; } + /* Place the cyclic channel to highest priority queue */ + edma_assign_channel_eventq(echan->ch_num, EVENTQ_0); + return vchan_tx_prep(&echan->vchan, &edesc->vdesc, tx_flags); } @@ -601,7 +741,6 @@ static void edma_callback(unsigned ch_num, u16 ch_status, void *data) struct edma_chan *echan = data; struct device *dev = echan->vchan.chan.device->dev; struct edma_desc *edesc; - unsigned long flags; struct edmacc_param p; edesc = echan->edesc; @@ -612,27 +751,34 @@ static void edma_callback(unsigned ch_num, u16 ch_status, void *data) switch (ch_status) { case EDMA_DMA_COMPLETE: - spin_lock_irqsave(&echan->vchan.lock, flags); + spin_lock(&echan->vchan.lock); if (edesc) { if (edesc->cyclic) { vchan_cyclic_callback(&edesc->vdesc); } else if (edesc->processed == edesc->pset_nr) { dev_dbg(dev, "Transfer complete, stopping channel %d\n", ch_num); + edesc->residue = 0; edma_stop(echan->ch_num); vchan_cookie_complete(&edesc->vdesc); edma_execute(echan); } else { dev_dbg(dev, "Intermediate transfer complete on channel %d\n", ch_num); + + /* Update statistics for tx_status */ + edesc->residue -= edesc->sg_len; + edesc->residue_stat = edesc->residue; + edesc->processed_stat = edesc->processed; + edma_execute(echan); } } - spin_unlock_irqrestore(&echan->vchan.lock, flags); + spin_unlock(&echan->vchan.lock); break; case EDMA_DMA_CC_ERROR: - spin_lock_irqsave(&echan->vchan.lock, flags); + spin_lock(&echan->vchan.lock); edma_read_slot(EDMA_CHAN_SLOT(echan->slot[0]), &p); @@ -663,7 +809,7 @@ static void edma_callback(unsigned ch_num, u16 ch_status, void *data) edma_trigger_channel(echan->ch_num); } - spin_unlock_irqrestore(&echan->vchan.lock, flags); + spin_unlock(&echan->vchan.lock); break; default: @@ -699,7 +845,7 @@ static int edma_alloc_chan_resources(struct dma_chan *chan) echan->alloced = true; echan->slot[0] = echan->ch_num; - dev_dbg(dev, "allocated channel for %u:%u\n", + dev_dbg(dev, "allocated channel %d for %u:%u\n", echan->ch_num, EDMA_CTLR(echan->ch_num), EDMA_CHAN_SLOT(echan->ch_num)); return 0; @@ -751,23 +897,52 @@ static void edma_issue_pending(struct dma_chan *chan) spin_unlock_irqrestore(&echan->vchan.lock, flags); } -static size_t edma_desc_size(struct edma_desc *edesc) +static u32 edma_residue(struct edma_desc *edesc) { + bool dst = edesc->direction == DMA_DEV_TO_MEM; + struct edma_pset *pset = edesc->pset; + dma_addr_t done, pos; int i; - size_t size; - - if (edesc->absync) - for (size = i = 0; i < edesc->pset_nr; i++) - size += (edesc->pset[i].a_b_cnt & 0xffff) * - (edesc->pset[i].a_b_cnt >> 16) * - edesc->pset[i].ccnt; - else - size = (edesc->pset[0].a_b_cnt & 0xffff) * - (edesc->pset[0].a_b_cnt >> 16) + - (edesc->pset[0].a_b_cnt & 0xffff) * - (SZ_64K - 1) * edesc->pset[0].ccnt; - - return size; + + /* + * We always read the dst/src position from the first RamPar + * pset. That's the one which is active now. + */ + pos = edma_get_position(edesc->echan->slot[0], dst); + + /* + * Cyclic is simple. Just subtract pset[0].addr from pos. + * + * We never update edesc->residue in the cyclic case, so we + * can tell the remaining room to the end of the circular + * buffer. + */ + if (edesc->cyclic) { + done = pos - pset->addr; + edesc->residue_stat = edesc->residue - done; + return edesc->residue_stat; + } + + /* + * For SG operation we catch up with the last processed + * status. + */ + pset += edesc->processed_stat; + + for (i = edesc->processed_stat; i < edesc->processed; i++, pset++) { + /* + * If we are inside this pset address range, we know + * this is the active one. Get the current delta and + * stop walking the psets. + */ + if (pos >= pset->addr && pos < pset->addr + pset->len) + return edesc->residue_stat - (pos - pset->addr); + + /* Otherwise mark it done and update residue_stat. */ + edesc->processed_stat++; + edesc->residue_stat -= pset->len; + } + return edesc->residue_stat; } /* Check request completion status */ @@ -785,13 +960,10 @@ static enum dma_status edma_tx_status(struct dma_chan *chan, return ret; spin_lock_irqsave(&echan->vchan.lock, flags); - vdesc = vchan_find_desc(&echan->vchan, cookie); - if (vdesc) { - txstate->residue = edma_desc_size(to_edma_desc(&vdesc->tx)); - } else if (echan->edesc && echan->edesc->vdesc.tx.cookie == cookie) { - struct edma_desc *edesc = echan->edesc; - txstate->residue = edma_desc_size(edesc); - } + if (echan->edesc && echan->edesc->vdesc.tx.cookie == cookie) + txstate->residue = edma_residue(echan->edesc); + else if ((vdesc = vchan_find_desc(&echan->vchan, cookie))) + txstate->residue = to_edma_desc(&vdesc->tx)->residue; spin_unlock_irqrestore(&echan->vchan.lock, flags); return ret; @@ -817,18 +989,44 @@ static void __init edma_chan_init(struct edma_cc *ecc, } } +#define EDMA_DMA_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)) + +static int edma_dma_device_slave_caps(struct dma_chan *dchan, + struct dma_slave_caps *caps) +{ + caps->src_addr_widths = EDMA_DMA_BUSWIDTHS; + caps->dstn_addr_widths = EDMA_DMA_BUSWIDTHS; + caps->directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV); + caps->cmd_pause = true; + caps->cmd_terminate = true; + caps->residue_granularity = DMA_RESIDUE_GRANULARITY_BURST; + + return 0; +} + static void edma_dma_init(struct edma_cc *ecc, struct dma_device *dma, struct device *dev) { dma->device_prep_slave_sg = edma_prep_slave_sg; dma->device_prep_dma_cyclic = edma_prep_dma_cyclic; + dma->device_prep_dma_memcpy = edma_prep_dma_memcpy; dma->device_alloc_chan_resources = edma_alloc_chan_resources; dma->device_free_chan_resources = edma_free_chan_resources; dma->device_issue_pending = edma_issue_pending; dma->device_tx_status = edma_tx_status; dma->device_control = edma_control; + dma->device_slave_caps = edma_dma_device_slave_caps; dma->dev = dev; + /* + * code using dma memcpy must make sure alignment of + * length is at dma->copy_align boundary. + */ + dma->copy_align = DMA_SLAVE_BUSWIDTH_4_BYTES; + INIT_LIST_HEAD(&dma->channels); } @@ -851,11 +1049,13 @@ static int edma_probe(struct platform_device *pdev) ecc->dummy_slot = edma_alloc_slot(ecc->ctlr, EDMA_SLOT_ANY); if (ecc->dummy_slot < 0) { dev_err(&pdev->dev, "Can't allocate PaRAM dummy slot\n"); - return -EIO; + return ecc->dummy_slot; } dma_cap_zero(ecc->dma_slave.cap_mask); dma_cap_set(DMA_SLAVE, ecc->dma_slave.cap_mask); + dma_cap_set(DMA_CYCLIC, ecc->dma_slave.cap_mask); + dma_cap_set(DMA_MEMCPY, ecc->dma_slave.cap_mask); edma_dma_init(ecc, &ecc->dma_slave, &pdev->dev); @@ -934,7 +1134,7 @@ static int edma_init(void) } } - if (EDMA_CTLRS == 2) { + if (!of_have_populated_dt() && EDMA_CTLRS == 2) { pdev1 = platform_device_register_full(&edma_dev_info1); if (IS_ERR(pdev1)) { platform_driver_unregister(&edma_driver); diff --git a/drivers/dma/ep93xx_dma.c b/drivers/dma/ep93xx_dma.c index cb4bf68..7650470 100644 --- a/drivers/dma/ep93xx_dma.c +++ b/drivers/dma/ep93xx_dma.c @@ -1092,7 +1092,6 @@ fail: * @period_len: length of a single period * @dir: direction of the operation * @flags: tx descriptor status flags - * @context: operation context (ignored) * * Prepares a descriptor for cyclic DMA operation. This means that once the * descriptor is submitted, we will be submitting in a @period_len sized @@ -1105,8 +1104,7 @@ fail: static struct dma_async_tx_descriptor * ep93xx_dma_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t dma_addr, size_t buf_len, size_t period_len, - enum dma_transfer_direction dir, unsigned long flags, - void *context) + enum dma_transfer_direction dir, unsigned long flags) { struct ep93xx_dma_chan *edmac = to_ep93xx_dma_chan(chan); struct ep93xx_dma_desc *desc, *first; diff --git a/drivers/dma/fsl-edma.c b/drivers/dma/fsl-edma.c new file mode 100644 index 0000000..3c5711d --- /dev/null +++ b/drivers/dma/fsl-edma.c @@ -0,0 +1,987 @@ +/* + * drivers/dma/fsl-edma.c + * + * Copyright 2013-2014 Freescale Semiconductor, Inc. + * + * Driver for the Freescale eDMA engine with flexible channel multiplexing + * capability for DMA request sources. The eDMA block can be found on some + * Vybrid and Layerscape SoCs. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#include <linux/init.h> +#include <linux/module.h> +#include <linux/interrupt.h> +#include <linux/clk.h> +#include <linux/dma-mapping.h> +#include <linux/dmapool.h> +#include <linux/slab.h> +#include <linux/spinlock.h> +#include <linux/of.h> +#include <linux/of_device.h> +#include <linux/of_address.h> +#include <linux/of_irq.h> +#include <linux/of_dma.h> + +#include "virt-dma.h" + +#define EDMA_CR 0x00 +#define EDMA_ES 0x04 +#define EDMA_ERQ 0x0C +#define EDMA_EEI 0x14 +#define EDMA_SERQ 0x1B +#define EDMA_CERQ 0x1A +#define EDMA_SEEI 0x19 +#define EDMA_CEEI 0x18 +#define EDMA_CINT 0x1F +#define EDMA_CERR 0x1E +#define EDMA_SSRT 0x1D +#define EDMA_CDNE 0x1C +#define EDMA_INTR 0x24 +#define EDMA_ERR 0x2C + +#define EDMA_TCD_SADDR(x) (0x1000 + 32 * (x)) +#define EDMA_TCD_SOFF(x) (0x1004 + 32 * (x)) +#define EDMA_TCD_ATTR(x) (0x1006 + 32 * (x)) +#define EDMA_TCD_NBYTES(x) (0x1008 + 32 * (x)) +#define EDMA_TCD_SLAST(x) (0x100C + 32 * (x)) +#define EDMA_TCD_DADDR(x) (0x1010 + 32 * (x)) +#define EDMA_TCD_DOFF(x) (0x1014 + 32 * (x)) +#define EDMA_TCD_CITER_ELINK(x) (0x1016 + 32 * (x)) +#define EDMA_TCD_CITER(x) (0x1016 + 32 * (x)) +#define EDMA_TCD_DLAST_SGA(x) (0x1018 + 32 * (x)) +#define EDMA_TCD_CSR(x) (0x101C + 32 * (x)) +#define EDMA_TCD_BITER_ELINK(x) (0x101E + 32 * (x)) +#define EDMA_TCD_BITER(x) (0x101E + 32 * (x)) + +#define EDMA_CR_EDBG BIT(1) +#define EDMA_CR_ERCA BIT(2) +#define EDMA_CR_ERGA BIT(3) +#define EDMA_CR_HOE BIT(4) +#define EDMA_CR_HALT BIT(5) +#define EDMA_CR_CLM BIT(6) +#define EDMA_CR_EMLM BIT(7) +#define EDMA_CR_ECX BIT(16) +#define EDMA_CR_CX BIT(17) + +#define EDMA_SEEI_SEEI(x) ((x) & 0x1F) +#define EDMA_CEEI_CEEI(x) ((x) & 0x1F) +#define EDMA_CINT_CINT(x) ((x) & 0x1F) +#define EDMA_CERR_CERR(x) ((x) & 0x1F) + +#define EDMA_TCD_ATTR_DSIZE(x) (((x) & 0x0007)) +#define EDMA_TCD_ATTR_DMOD(x) (((x) & 0x001F) << 3) +#define EDMA_TCD_ATTR_SSIZE(x) (((x) & 0x0007) << 8) +#define EDMA_TCD_ATTR_SMOD(x) (((x) & 0x001F) << 11) +#define EDMA_TCD_ATTR_SSIZE_8BIT (0x0000) +#define EDMA_TCD_ATTR_SSIZE_16BIT (0x0100) +#define EDMA_TCD_ATTR_SSIZE_32BIT (0x0200) +#define EDMA_TCD_ATTR_SSIZE_64BIT (0x0300) +#define EDMA_TCD_ATTR_SSIZE_32BYTE (0x0500) +#define EDMA_TCD_ATTR_DSIZE_8BIT (0x0000) +#define EDMA_TCD_ATTR_DSIZE_16BIT (0x0001) +#define EDMA_TCD_ATTR_DSIZE_32BIT (0x0002) +#define EDMA_TCD_ATTR_DSIZE_64BIT (0x0003) +#define EDMA_TCD_ATTR_DSIZE_32BYTE (0x0005) + +#define EDMA_TCD_SOFF_SOFF(x) (x) +#define EDMA_TCD_NBYTES_NBYTES(x) (x) +#define EDMA_TCD_SLAST_SLAST(x) (x) +#define EDMA_TCD_DADDR_DADDR(x) (x) +#define EDMA_TCD_CITER_CITER(x) ((x) & 0x7FFF) +#define EDMA_TCD_DOFF_DOFF(x) (x) +#define EDMA_TCD_DLAST_SGA_DLAST_SGA(x) (x) +#define EDMA_TCD_BITER_BITER(x) ((x) & 0x7FFF) + +#define EDMA_TCD_CSR_START BIT(0) +#define EDMA_TCD_CSR_INT_MAJOR BIT(1) +#define EDMA_TCD_CSR_INT_HALF BIT(2) +#define EDMA_TCD_CSR_D_REQ BIT(3) +#define EDMA_TCD_CSR_E_SG BIT(4) +#define EDMA_TCD_CSR_E_LINK BIT(5) +#define EDMA_TCD_CSR_ACTIVE BIT(6) +#define EDMA_TCD_CSR_DONE BIT(7) + +#define EDMAMUX_CHCFG_DIS 0x0 +#define EDMAMUX_CHCFG_ENBL 0x80 +#define EDMAMUX_CHCFG_SOURCE(n) ((n) & 0x3F) + +#define DMAMUX_NR 2 + +#define FSL_EDMA_BUSWIDTHS BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) | \ + BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) | \ + BIT(DMA_SLAVE_BUSWIDTH_4_BYTES) | \ + BIT(DMA_SLAVE_BUSWIDTH_8_BYTES) + +struct fsl_edma_hw_tcd { + u32 saddr; + u16 soff; + u16 attr; + u32 nbytes; + u32 slast; + u32 daddr; + u16 doff; + u16 citer; + u32 dlast_sga; + u16 csr; + u16 biter; +}; + +struct fsl_edma_sw_tcd { + dma_addr_t ptcd; + struct fsl_edma_hw_tcd *vtcd; +}; + +struct fsl_edma_slave_config { + enum dma_transfer_direction dir; + enum dma_slave_buswidth addr_width; + u32 dev_addr; + u32 burst; + u32 attr; +}; + +struct fsl_edma_chan { + struct virt_dma_chan vchan; + enum dma_status status; + struct fsl_edma_engine *edma; + struct fsl_edma_desc *edesc; + struct fsl_edma_slave_config fsc; + struct dma_pool *tcd_pool; +}; + +struct fsl_edma_desc { + struct virt_dma_desc vdesc; + struct fsl_edma_chan *echan; + bool iscyclic; + unsigned int n_tcds; + struct fsl_edma_sw_tcd tcd[]; +}; + +struct fsl_edma_engine { + struct dma_device dma_dev; + void __iomem *membase; + void __iomem *muxbase[DMAMUX_NR]; + struct clk *muxclk[DMAMUX_NR]; + struct mutex fsl_edma_mutex; + u32 n_chans; + int txirq; + int errirq; + bool big_endian; + struct fsl_edma_chan chans[]; +}; + +/* + * R/W functions for big- or little-endian registers + * the eDMA controller's endian is independent of the CPU core's endian. + */ + +static u16 edma_readw(struct fsl_edma_engine *edma, void __iomem *addr) +{ + if (edma->big_endian) + return ioread16be(addr); + else + return ioread16(addr); +} + +static u32 edma_readl(struct fsl_edma_engine *edma, void __iomem *addr) +{ + if (edma->big_endian) + return ioread32be(addr); + else + return ioread32(addr); +} + +static void edma_writeb(struct fsl_edma_engine *edma, u8 val, void __iomem *addr) +{ + iowrite8(val, addr); +} + +static void edma_writew(struct fsl_edma_engine *edma, u16 val, void __iomem *addr) +{ + if (edma->big_endian) + iowrite16be(val, addr); + else + iowrite16(val, addr); +} + +static void edma_writel(struct fsl_edma_engine *edma, u32 val, void __iomem *addr) +{ + if (edma->big_endian) + iowrite32be(val, addr); + else + iowrite32(val, addr); +} + +static struct fsl_edma_chan *to_fsl_edma_chan(struct dma_chan *chan) +{ + return container_of(chan, struct fsl_edma_chan, vchan.chan); +} + +static struct fsl_edma_desc *to_fsl_edma_desc(struct virt_dma_desc *vd) +{ + return container_of(vd, struct fsl_edma_desc, vdesc); +} + +static void fsl_edma_enable_request(struct fsl_edma_chan *fsl_chan) +{ + void __iomem *addr = fsl_chan->edma->membase; + u32 ch = fsl_chan->vchan.chan.chan_id; + + edma_writeb(fsl_chan->edma, EDMA_SEEI_SEEI(ch), addr + EDMA_SEEI); + edma_writeb(fsl_chan->edma, ch, addr + EDMA_SERQ); +} + +static void fsl_edma_disable_request(struct fsl_edma_chan *fsl_chan) +{ + void __iomem *addr = fsl_chan->edma->membase; + u32 ch = fsl_chan->vchan.chan.chan_id; + + edma_writeb(fsl_chan->edma, ch, addr + EDMA_CERQ); + edma_writeb(fsl_chan->edma, EDMA_CEEI_CEEI(ch), addr + EDMA_CEEI); +} + +static void fsl_edma_chan_mux(struct fsl_edma_chan *fsl_chan, + unsigned int slot, bool enable) +{ + u32 ch = fsl_chan->vchan.chan.chan_id; + void __iomem *muxaddr; + unsigned chans_per_mux, ch_off; + + chans_per_mux = fsl_chan->edma->n_chans / DMAMUX_NR; + ch_off = fsl_chan->vchan.chan.chan_id % chans_per_mux; + muxaddr = fsl_chan->edma->muxbase[ch / chans_per_mux]; + + if (enable) + edma_writeb(fsl_chan->edma, + EDMAMUX_CHCFG_ENBL | EDMAMUX_CHCFG_SOURCE(slot), + muxaddr + ch_off); + else + edma_writeb(fsl_chan->edma, EDMAMUX_CHCFG_DIS, muxaddr + ch_off); +} + +static unsigned int fsl_edma_get_tcd_attr(enum dma_slave_buswidth addr_width) +{ + switch (addr_width) { + case 1: + return EDMA_TCD_ATTR_SSIZE_8BIT | EDMA_TCD_ATTR_DSIZE_8BIT; + case 2: + return EDMA_TCD_ATTR_SSIZE_16BIT | EDMA_TCD_ATTR_DSIZE_16BIT; + case 4: + return EDMA_TCD_ATTR_SSIZE_32BIT | EDMA_TCD_ATTR_DSIZE_32BIT; + case 8: + return EDMA_TCD_ATTR_SSIZE_64BIT | EDMA_TCD_ATTR_DSIZE_64BIT; + default: + return EDMA_TCD_ATTR_SSIZE_32BIT | EDMA_TCD_ATTR_DSIZE_32BIT; + } +} + +static void fsl_edma_free_desc(struct virt_dma_desc *vdesc) +{ + struct fsl_edma_desc *fsl_desc; + int i; + + fsl_desc = to_fsl_edma_desc(vdesc); + for (i = 0; i < fsl_desc->n_tcds; i++) + dma_pool_free(fsl_desc->echan->tcd_pool, + fsl_desc->tcd[i].vtcd, + fsl_desc->tcd[i].ptcd); + kfree(fsl_desc); +} + +static int fsl_edma_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd, + unsigned long arg) +{ + struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan); + struct dma_slave_config *cfg = (void *)arg; + unsigned long flags; + LIST_HEAD(head); + + switch (cmd) { + case DMA_TERMINATE_ALL: + spin_lock_irqsave(&fsl_chan->vchan.lock, flags); + fsl_edma_disable_request(fsl_chan); + fsl_chan->edesc = NULL; + vchan_get_all_descriptors(&fsl_chan->vchan, &head); + spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags); + vchan_dma_desc_free_list(&fsl_chan->vchan, &head); + return 0; + + case DMA_SLAVE_CONFIG: + fsl_chan->fsc.dir = cfg->direction; + if (cfg->direction == DMA_DEV_TO_MEM) { + fsl_chan->fsc.dev_addr = cfg->src_addr; + fsl_chan->fsc.addr_width = cfg->src_addr_width; + fsl_chan->fsc.burst = cfg->src_maxburst; + fsl_chan->fsc.attr = fsl_edma_get_tcd_attr(cfg->src_addr_width); + } else if (cfg->direction == DMA_MEM_TO_DEV) { + fsl_chan->fsc.dev_addr = cfg->dst_addr; + fsl_chan->fsc.addr_width = cfg->dst_addr_width; + fsl_chan->fsc.burst = cfg->dst_maxburst; + fsl_chan->fsc.attr = fsl_edma_get_tcd_attr(cfg->dst_addr_width); + } else { + return -EINVAL; + } + return 0; + + case DMA_PAUSE: + spin_lock_irqsave(&fsl_chan->vchan.lock, flags); + if (fsl_chan->edesc) { + fsl_edma_disable_request(fsl_chan); + fsl_chan->status = DMA_PAUSED; + } + spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags); + return 0; + + case DMA_RESUME: + spin_lock_irqsave(&fsl_chan->vchan.lock, flags); + if (fsl_chan->edesc) { + fsl_edma_enable_request(fsl_chan); + fsl_chan->status = DMA_IN_PROGRESS; + } + spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags); + return 0; + + default: + return -ENXIO; + } +} + +static size_t fsl_edma_desc_residue(struct fsl_edma_chan *fsl_chan, + struct virt_dma_desc *vdesc, bool in_progress) +{ + struct fsl_edma_desc *edesc = fsl_chan->edesc; + void __iomem *addr = fsl_chan->edma->membase; + u32 ch = fsl_chan->vchan.chan.chan_id; + enum dma_transfer_direction dir = fsl_chan->fsc.dir; + dma_addr_t cur_addr, dma_addr; + size_t len, size; + int i; + + /* calculate the total size in this desc */ + for (len = i = 0; i < fsl_chan->edesc->n_tcds; i++) + len += edma_readl(fsl_chan->edma, &(edesc->tcd[i].vtcd->nbytes)) + * edma_readw(fsl_chan->edma, &(edesc->tcd[i].vtcd->biter)); + + if (!in_progress) + return len; + + if (dir == DMA_MEM_TO_DEV) + cur_addr = edma_readl(fsl_chan->edma, addr + EDMA_TCD_SADDR(ch)); + else + cur_addr = edma_readl(fsl_chan->edma, addr + EDMA_TCD_DADDR(ch)); + + /* figure out the finished and calculate the residue */ + for (i = 0; i < fsl_chan->edesc->n_tcds; i++) { + size = edma_readl(fsl_chan->edma, &(edesc->tcd[i].vtcd->nbytes)) + * edma_readw(fsl_chan->edma, &(edesc->tcd[i].vtcd->biter)); + if (dir == DMA_MEM_TO_DEV) + dma_addr = edma_readl(fsl_chan->edma, + &(edesc->tcd[i].vtcd->saddr)); + else + dma_addr = edma_readl(fsl_chan->edma, + &(edesc->tcd[i].vtcd->daddr)); + + len -= size; + if (cur_addr > dma_addr && cur_addr < dma_addr + size) { + len += dma_addr + size - cur_addr; + break; + } + } + + return len; +} + +static enum dma_status fsl_edma_tx_status(struct dma_chan *chan, + dma_cookie_t cookie, struct dma_tx_state *txstate) +{ + struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan); + struct virt_dma_desc *vdesc; + enum dma_status status; + unsigned long flags; + + status = dma_cookie_status(chan, cookie, txstate); + if (status == DMA_COMPLETE) + return status; + + if (!txstate) + return fsl_chan->status; + + spin_lock_irqsave(&fsl_chan->vchan.lock, flags); + vdesc = vchan_find_desc(&fsl_chan->vchan, cookie); + if (fsl_chan->edesc && cookie == fsl_chan->edesc->vdesc.tx.cookie) + txstate->residue = fsl_edma_desc_residue(fsl_chan, vdesc, true); + else if (vdesc) + txstate->residue = fsl_edma_desc_residue(fsl_chan, vdesc, false); + else + txstate->residue = 0; + + spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags); + + return fsl_chan->status; +} + +static void fsl_edma_set_tcd_params(struct fsl_edma_chan *fsl_chan, + u32 src, u32 dst, u16 attr, u16 soff, u32 nbytes, + u32 slast, u16 citer, u16 biter, u32 doff, u32 dlast_sga, + u16 csr) +{ + void __iomem *addr = fsl_chan->edma->membase; + u32 ch = fsl_chan->vchan.chan.chan_id; + + /* + * TCD parameters have been swapped in fill_tcd_params(), + * so just write them to registers in the cpu endian here + */ + writew(0, addr + EDMA_TCD_CSR(ch)); + writel(src, addr + EDMA_TCD_SADDR(ch)); + writel(dst, addr + EDMA_TCD_DADDR(ch)); + writew(attr, addr + EDMA_TCD_ATTR(ch)); + writew(soff, addr + EDMA_TCD_SOFF(ch)); + writel(nbytes, addr + EDMA_TCD_NBYTES(ch)); + writel(slast, addr + EDMA_TCD_SLAST(ch)); + writew(citer, addr + EDMA_TCD_CITER(ch)); + writew(biter, addr + EDMA_TCD_BITER(ch)); + writew(doff, addr + EDMA_TCD_DOFF(ch)); + writel(dlast_sga, addr + EDMA_TCD_DLAST_SGA(ch)); + writew(csr, addr + EDMA_TCD_CSR(ch)); +} + +static void fill_tcd_params(struct fsl_edma_engine *edma, + struct fsl_edma_hw_tcd *tcd, u32 src, u32 dst, + u16 attr, u16 soff, u32 nbytes, u32 slast, u16 citer, + u16 biter, u16 doff, u32 dlast_sga, bool major_int, + bool disable_req, bool enable_sg) +{ + u16 csr = 0; + + /* + * eDMA hardware SGs require the TCD parameters stored in memory + * the same endian as the eDMA module so that they can be loaded + * automatically by the engine + */ + edma_writel(edma, src, &(tcd->saddr)); + edma_writel(edma, dst, &(tcd->daddr)); + edma_writew(edma, attr, &(tcd->attr)); + edma_writew(edma, EDMA_TCD_SOFF_SOFF(soff), &(tcd->soff)); + edma_writel(edma, EDMA_TCD_NBYTES_NBYTES(nbytes), &(tcd->nbytes)); + edma_writel(edma, EDMA_TCD_SLAST_SLAST(slast), &(tcd->slast)); + edma_writew(edma, EDMA_TCD_CITER_CITER(citer), &(tcd->citer)); + edma_writew(edma, EDMA_TCD_DOFF_DOFF(doff), &(tcd->doff)); + edma_writel(edma, EDMA_TCD_DLAST_SGA_DLAST_SGA(dlast_sga), &(tcd->dlast_sga)); + edma_writew(edma, EDMA_TCD_BITER_BITER(biter), &(tcd->biter)); + if (major_int) + csr |= EDMA_TCD_CSR_INT_MAJOR; + + if (disable_req) + csr |= EDMA_TCD_CSR_D_REQ; + + if (enable_sg) + csr |= EDMA_TCD_CSR_E_SG; + + edma_writew(edma, csr, &(tcd->csr)); +} + +static struct fsl_edma_desc *fsl_edma_alloc_desc(struct fsl_edma_chan *fsl_chan, + int sg_len) +{ + struct fsl_edma_desc *fsl_desc; + int i; + + fsl_desc = kzalloc(sizeof(*fsl_desc) + sizeof(struct fsl_edma_sw_tcd) * sg_len, + GFP_NOWAIT); + if (!fsl_desc) + return NULL; + + fsl_desc->echan = fsl_chan; + fsl_desc->n_tcds = sg_len; + for (i = 0; i < sg_len; i++) { + fsl_desc->tcd[i].vtcd = dma_pool_alloc(fsl_chan->tcd_pool, + GFP_NOWAIT, &fsl_desc->tcd[i].ptcd); + if (!fsl_desc->tcd[i].vtcd) + goto err; + } + return fsl_desc; + +err: + while (--i >= 0) + dma_pool_free(fsl_chan->tcd_pool, fsl_desc->tcd[i].vtcd, + fsl_desc->tcd[i].ptcd); + kfree(fsl_desc); + return NULL; +} + +static struct dma_async_tx_descriptor *fsl_edma_prep_dma_cyclic( + struct dma_chan *chan, dma_addr_t dma_addr, size_t buf_len, + size_t period_len, enum dma_transfer_direction direction, + unsigned long flags) +{ + struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan); + struct fsl_edma_desc *fsl_desc; + dma_addr_t dma_buf_next; + int sg_len, i; + u32 src_addr, dst_addr, last_sg, nbytes; + u16 soff, doff, iter; + + if (!is_slave_direction(fsl_chan->fsc.dir)) + return NULL; + + sg_len = buf_len / period_len; + fsl_desc = fsl_edma_alloc_desc(fsl_chan, sg_len); + if (!fsl_desc) + return NULL; + fsl_desc->iscyclic = true; + + dma_buf_next = dma_addr; + nbytes = fsl_chan->fsc.addr_width * fsl_chan->fsc.burst; + iter = period_len / nbytes; + + for (i = 0; i < sg_len; i++) { + if (dma_buf_next >= dma_addr + buf_len) + dma_buf_next = dma_addr; + + /* get next sg's physical address */ + last_sg = fsl_desc->tcd[(i + 1) % sg_len].ptcd; + + if (fsl_chan->fsc.dir == DMA_MEM_TO_DEV) { + src_addr = dma_buf_next; + dst_addr = fsl_chan->fsc.dev_addr; + soff = fsl_chan->fsc.addr_width; + doff = 0; + } else { + src_addr = fsl_chan->fsc.dev_addr; + dst_addr = dma_buf_next; + soff = 0; + doff = fsl_chan->fsc.addr_width; + } + + fill_tcd_params(fsl_chan->edma, fsl_desc->tcd[i].vtcd, src_addr, + dst_addr, fsl_chan->fsc.attr, soff, nbytes, 0, + iter, iter, doff, last_sg, true, false, true); + dma_buf_next += period_len; + } + + return vchan_tx_prep(&fsl_chan->vchan, &fsl_desc->vdesc, flags); +} + +static struct dma_async_tx_descriptor *fsl_edma_prep_slave_sg( + struct dma_chan *chan, struct scatterlist *sgl, + unsigned int sg_len, enum dma_transfer_direction direction, + unsigned long flags, void *context) +{ + struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan); + struct fsl_edma_desc *fsl_desc; + struct scatterlist *sg; + u32 src_addr, dst_addr, last_sg, nbytes; + u16 soff, doff, iter; + int i; + + if (!is_slave_direction(fsl_chan->fsc.dir)) + return NULL; + + fsl_desc = fsl_edma_alloc_desc(fsl_chan, sg_len); + if (!fsl_desc) + return NULL; + fsl_desc->iscyclic = false; + + nbytes = fsl_chan->fsc.addr_width * fsl_chan->fsc.burst; + for_each_sg(sgl, sg, sg_len, i) { + /* get next sg's physical address */ + last_sg = fsl_desc->tcd[(i + 1) % sg_len].ptcd; + + if (fsl_chan->fsc.dir == DMA_MEM_TO_DEV) { + src_addr = sg_dma_address(sg); + dst_addr = fsl_chan->fsc.dev_addr; + soff = fsl_chan->fsc.addr_width; + doff = 0; + } else { + src_addr = fsl_chan->fsc.dev_addr; + dst_addr = sg_dma_address(sg); + soff = 0; + doff = fsl_chan->fsc.addr_width; + } + + iter = sg_dma_len(sg) / nbytes; + if (i < sg_len - 1) { + last_sg = fsl_desc->tcd[(i + 1)].ptcd; + fill_tcd_params(fsl_chan->edma, fsl_desc->tcd[i].vtcd, + src_addr, dst_addr, fsl_chan->fsc.attr, + soff, nbytes, 0, iter, iter, doff, last_sg, + false, false, true); + } else { + last_sg = 0; + fill_tcd_params(fsl_chan->edma, fsl_desc->tcd[i].vtcd, + src_addr, dst_addr, fsl_chan->fsc.attr, + soff, nbytes, 0, iter, iter, doff, last_sg, + true, true, false); + } + } + + return vchan_tx_prep(&fsl_chan->vchan, &fsl_desc->vdesc, flags); +} + +static void fsl_edma_xfer_desc(struct fsl_edma_chan *fsl_chan) +{ + struct fsl_edma_hw_tcd *tcd; + struct virt_dma_desc *vdesc; + + vdesc = vchan_next_desc(&fsl_chan->vchan); + if (!vdesc) + return; + fsl_chan->edesc = to_fsl_edma_desc(vdesc); + tcd = fsl_chan->edesc->tcd[0].vtcd; + fsl_edma_set_tcd_params(fsl_chan, tcd->saddr, tcd->daddr, tcd->attr, + tcd->soff, tcd->nbytes, tcd->slast, tcd->citer, + tcd->biter, tcd->doff, tcd->dlast_sga, tcd->csr); + fsl_edma_enable_request(fsl_chan); + fsl_chan->status = DMA_IN_PROGRESS; +} + +static irqreturn_t fsl_edma_tx_handler(int irq, void *dev_id) +{ + struct fsl_edma_engine *fsl_edma = dev_id; + unsigned int intr, ch; + void __iomem *base_addr; + struct fsl_edma_chan *fsl_chan; + + base_addr = fsl_edma->membase; + + intr = edma_readl(fsl_edma, base_addr + EDMA_INTR); + if (!intr) + return IRQ_NONE; + + for (ch = 0; ch < fsl_edma->n_chans; ch++) { + if (intr & (0x1 << ch)) { + edma_writeb(fsl_edma, EDMA_CINT_CINT(ch), + base_addr + EDMA_CINT); + + fsl_chan = &fsl_edma->chans[ch]; + + spin_lock(&fsl_chan->vchan.lock); + if (!fsl_chan->edesc->iscyclic) { + list_del(&fsl_chan->edesc->vdesc.node); + vchan_cookie_complete(&fsl_chan->edesc->vdesc); + fsl_chan->edesc = NULL; + fsl_chan->status = DMA_COMPLETE; + } else { + vchan_cyclic_callback(&fsl_chan->edesc->vdesc); + } + + if (!fsl_chan->edesc) + fsl_edma_xfer_desc(fsl_chan); + + spin_unlock(&fsl_chan->vchan.lock); + } + } + return IRQ_HANDLED; +} + +static irqreturn_t fsl_edma_err_handler(int irq, void *dev_id) +{ + struct fsl_edma_engine *fsl_edma = dev_id; + unsigned int err, ch; + + err = edma_readl(fsl_edma, fsl_edma->membase + EDMA_ERR); + if (!err) + return IRQ_NONE; + + for (ch = 0; ch < fsl_edma->n_chans; ch++) { + if (err & (0x1 << ch)) { + fsl_edma_disable_request(&fsl_edma->chans[ch]); + edma_writeb(fsl_edma, EDMA_CERR_CERR(ch), + fsl_edma->membase + EDMA_CERR); + fsl_edma->chans[ch].status = DMA_ERROR; + } + } + return IRQ_HANDLED; +} + +static irqreturn_t fsl_edma_irq_handler(int irq, void *dev_id) +{ + if (fsl_edma_tx_handler(irq, dev_id) == IRQ_HANDLED) + return IRQ_HANDLED; + + return fsl_edma_err_handler(irq, dev_id); +} + +static void fsl_edma_issue_pending(struct dma_chan *chan) +{ + struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan); + unsigned long flags; + + spin_lock_irqsave(&fsl_chan->vchan.lock, flags); + + if (vchan_issue_pending(&fsl_chan->vchan) && !fsl_chan->edesc) + fsl_edma_xfer_desc(fsl_chan); + + spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags); +} + +static struct dma_chan *fsl_edma_xlate(struct of_phandle_args *dma_spec, + struct of_dma *ofdma) +{ + struct fsl_edma_engine *fsl_edma = ofdma->of_dma_data; + struct dma_chan *chan, *_chan; + unsigned long chans_per_mux = fsl_edma->n_chans / DMAMUX_NR; + + if (dma_spec->args_count != 2) + return NULL; + + mutex_lock(&fsl_edma->fsl_edma_mutex); + list_for_each_entry_safe(chan, _chan, &fsl_edma->dma_dev.channels, device_node) { + if (chan->client_count) + continue; + if ((chan->chan_id / chans_per_mux) == dma_spec->args[0]) { + chan = dma_get_slave_channel(chan); + if (chan) { + chan->device->privatecnt++; + fsl_edma_chan_mux(to_fsl_edma_chan(chan), + dma_spec->args[1], true); + mutex_unlock(&fsl_edma->fsl_edma_mutex); + return chan; + } + } + } + mutex_unlock(&fsl_edma->fsl_edma_mutex); + return NULL; +} + +static int fsl_edma_alloc_chan_resources(struct dma_chan *chan) +{ + struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan); + + fsl_chan->tcd_pool = dma_pool_create("tcd_pool", chan->device->dev, + sizeof(struct fsl_edma_hw_tcd), + 32, 0); + return 0; +} + +static void fsl_edma_free_chan_resources(struct dma_chan *chan) +{ + struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan); + unsigned long flags; + LIST_HEAD(head); + + spin_lock_irqsave(&fsl_chan->vchan.lock, flags); + fsl_edma_disable_request(fsl_chan); + fsl_edma_chan_mux(fsl_chan, 0, false); + fsl_chan->edesc = NULL; + vchan_get_all_descriptors(&fsl_chan->vchan, &head); + spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags); + + vchan_dma_desc_free_list(&fsl_chan->vchan, &head); + dma_pool_destroy(fsl_chan->tcd_pool); + fsl_chan->tcd_pool = NULL; +} + +static int fsl_dma_device_slave_caps(struct dma_chan *dchan, + struct dma_slave_caps *caps) +{ + caps->src_addr_widths = FSL_EDMA_BUSWIDTHS; + caps->dstn_addr_widths = FSL_EDMA_BUSWIDTHS; + caps->directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV); + caps->cmd_pause = true; + caps->cmd_terminate = true; + + return 0; +} + +static int +fsl_edma_irq_init(struct platform_device *pdev, struct fsl_edma_engine *fsl_edma) +{ + int ret; + + fsl_edma->txirq = platform_get_irq_byname(pdev, "edma-tx"); + if (fsl_edma->txirq < 0) { + dev_err(&pdev->dev, "Can't get edma-tx irq.\n"); + return fsl_edma->txirq; + } + + fsl_edma->errirq = platform_get_irq_byname(pdev, "edma-err"); + if (fsl_edma->errirq < 0) { + dev_err(&pdev->dev, "Can't get edma-err irq.\n"); + return fsl_edma->errirq; + } + + if (fsl_edma->txirq == fsl_edma->errirq) { + ret = devm_request_irq(&pdev->dev, fsl_edma->txirq, + fsl_edma_irq_handler, 0, "eDMA", fsl_edma); + if (ret) { + dev_err(&pdev->dev, "Can't register eDMA IRQ.\n"); + return ret; + } + } else { + ret = devm_request_irq(&pdev->dev, fsl_edma->txirq, + fsl_edma_tx_handler, 0, "eDMA tx", fsl_edma); + if (ret) { + dev_err(&pdev->dev, "Can't register eDMA tx IRQ.\n"); + return ret; + } + + ret = devm_request_irq(&pdev->dev, fsl_edma->errirq, + fsl_edma_err_handler, 0, "eDMA err", fsl_edma); + if (ret) { + dev_err(&pdev->dev, "Can't register eDMA err IRQ.\n"); + return ret; + } + } + + return 0; +} + +static int fsl_edma_probe(struct platform_device *pdev) +{ + struct device_node *np = pdev->dev.of_node; + struct fsl_edma_engine *fsl_edma; + struct fsl_edma_chan *fsl_chan; + struct resource *res; + int len, chans; + int ret, i; + + ret = of_property_read_u32(np, "dma-channels", &chans); + if (ret) { + dev_err(&pdev->dev, "Can't get dma-channels.\n"); + return ret; + } + + len = sizeof(*fsl_edma) + sizeof(*fsl_chan) * chans; + fsl_edma = devm_kzalloc(&pdev->dev, len, GFP_KERNEL); + if (!fsl_edma) + return -ENOMEM; + + fsl_edma->n_chans = chans; + mutex_init(&fsl_edma->fsl_edma_mutex); + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + fsl_edma->membase = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(fsl_edma->membase)) + return PTR_ERR(fsl_edma->membase); + + for (i = 0; i < DMAMUX_NR; i++) { + char clkname[32]; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 1 + i); + fsl_edma->muxbase[i] = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(fsl_edma->muxbase[i])) + return PTR_ERR(fsl_edma->muxbase[i]); + + sprintf(clkname, "dmamux%d", i); + fsl_edma->muxclk[i] = devm_clk_get(&pdev->dev, clkname); + if (IS_ERR(fsl_edma->muxclk[i])) { + dev_err(&pdev->dev, "Missing DMAMUX block clock.\n"); + return PTR_ERR(fsl_edma->muxclk[i]); + } + + ret = clk_prepare_enable(fsl_edma->muxclk[i]); + if (ret) { + dev_err(&pdev->dev, "DMAMUX clk block failed.\n"); + return ret; + } + + } + + ret = fsl_edma_irq_init(pdev, fsl_edma); + if (ret) + return ret; + + fsl_edma->big_endian = of_property_read_bool(np, "big-endian"); + + INIT_LIST_HEAD(&fsl_edma->dma_dev.channels); + for (i = 0; i < fsl_edma->n_chans; i++) { + struct fsl_edma_chan *fsl_chan = &fsl_edma->chans[i]; + + fsl_chan->edma = fsl_edma; + + fsl_chan->vchan.desc_free = fsl_edma_free_desc; + vchan_init(&fsl_chan->vchan, &fsl_edma->dma_dev); + + edma_writew(fsl_edma, 0x0, fsl_edma->membase + EDMA_TCD_CSR(i)); + fsl_edma_chan_mux(fsl_chan, 0, false); + } + + dma_cap_set(DMA_PRIVATE, fsl_edma->dma_dev.cap_mask); + dma_cap_set(DMA_SLAVE, fsl_edma->dma_dev.cap_mask); + dma_cap_set(DMA_CYCLIC, fsl_edma->dma_dev.cap_mask); + + fsl_edma->dma_dev.dev = &pdev->dev; + fsl_edma->dma_dev.device_alloc_chan_resources + = fsl_edma_alloc_chan_resources; + fsl_edma->dma_dev.device_free_chan_resources + = fsl_edma_free_chan_resources; + fsl_edma->dma_dev.device_tx_status = fsl_edma_tx_status; + fsl_edma->dma_dev.device_prep_slave_sg = fsl_edma_prep_slave_sg; + fsl_edma->dma_dev.device_prep_dma_cyclic = fsl_edma_prep_dma_cyclic; + fsl_edma->dma_dev.device_control = fsl_edma_control; + fsl_edma->dma_dev.device_issue_pending = fsl_edma_issue_pending; + fsl_edma->dma_dev.device_slave_caps = fsl_dma_device_slave_caps; + + platform_set_drvdata(pdev, fsl_edma); + + ret = dma_async_device_register(&fsl_edma->dma_dev); + if (ret) { + dev_err(&pdev->dev, "Can't register Freescale eDMA engine.\n"); + return ret; + } + + ret = of_dma_controller_register(np, fsl_edma_xlate, fsl_edma); + if (ret) { + dev_err(&pdev->dev, "Can't register Freescale eDMA of_dma.\n"); + dma_async_device_unregister(&fsl_edma->dma_dev); + return ret; + } + + /* enable round robin arbitration */ + edma_writel(fsl_edma, EDMA_CR_ERGA | EDMA_CR_ERCA, fsl_edma->membase + EDMA_CR); + + return 0; +} + +static int fsl_edma_remove(struct platform_device *pdev) +{ + struct device_node *np = pdev->dev.of_node; + struct fsl_edma_engine *fsl_edma = platform_get_drvdata(pdev); + int i; + + of_dma_controller_free(np); + dma_async_device_unregister(&fsl_edma->dma_dev); + + for (i = 0; i < DMAMUX_NR; i++) + clk_disable_unprepare(fsl_edma->muxclk[i]); + + return 0; +} + +static const struct of_device_id fsl_edma_dt_ids[] = { + { .compatible = "fsl,vf610-edma", }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, fsl_edma_dt_ids); + +static struct platform_driver fsl_edma_driver = { + .driver = { + .name = "fsl-edma", + .owner = THIS_MODULE, + .of_match_table = fsl_edma_dt_ids, + }, + .probe = fsl_edma_probe, + .remove = fsl_edma_remove, +}; + +static int __init fsl_edma_init(void) +{ + return platform_driver_register(&fsl_edma_driver); +} +subsys_initcall(fsl_edma_init); + +static void __exit fsl_edma_exit(void) +{ + platform_driver_unregister(&fsl_edma_driver); +} +module_exit(fsl_edma_exit); + +MODULE_ALIAS("platform:fsl-edma"); +MODULE_DESCRIPTION("Freescale eDMA engine driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/dma/fsldma.c b/drivers/dma/fsldma.c index f157c6f..d5d6885 100644 --- a/drivers/dma/fsldma.c +++ b/drivers/dma/fsldma.c @@ -61,6 +61,16 @@ static u32 get_sr(struct fsldma_chan *chan) return DMA_IN(chan, &chan->regs->sr, 32); } +static void set_mr(struct fsldma_chan *chan, u32 val) +{ + DMA_OUT(chan, &chan->regs->mr, val, 32); +} + +static u32 get_mr(struct fsldma_chan *chan) +{ + return DMA_IN(chan, &chan->regs->mr, 32); +} + static void set_cdar(struct fsldma_chan *chan, dma_addr_t addr) { DMA_OUT(chan, &chan->regs->cdar, addr | FSL_DMA_SNEN, 64); @@ -71,6 +81,11 @@ static dma_addr_t get_cdar(struct fsldma_chan *chan) return DMA_IN(chan, &chan->regs->cdar, 64) & ~FSL_DMA_SNEN; } +static void set_bcr(struct fsldma_chan *chan, u32 val) +{ + DMA_OUT(chan, &chan->regs->bcr, val, 32); +} + static u32 get_bcr(struct fsldma_chan *chan) { return DMA_IN(chan, &chan->regs->bcr, 32); @@ -135,7 +150,7 @@ static void set_ld_eol(struct fsldma_chan *chan, struct fsl_desc_sw *desc) static void dma_init(struct fsldma_chan *chan) { /* Reset the channel */ - DMA_OUT(chan, &chan->regs->mr, 0, 32); + set_mr(chan, 0); switch (chan->feature & FSL_DMA_IP_MASK) { case FSL_DMA_IP_85XX: @@ -144,16 +159,15 @@ static void dma_init(struct fsldma_chan *chan) * EOLNIE - End of links interrupt enable * BWC - Bandwidth sharing among channels */ - DMA_OUT(chan, &chan->regs->mr, FSL_DMA_MR_BWC - | FSL_DMA_MR_EIE | FSL_DMA_MR_EOLNIE, 32); + set_mr(chan, FSL_DMA_MR_BWC | FSL_DMA_MR_EIE + | FSL_DMA_MR_EOLNIE); break; case FSL_DMA_IP_83XX: /* Set the channel to below modes: * EOTIE - End-of-transfer interrupt enable * PRC_RM - PCI read multiple */ - DMA_OUT(chan, &chan->regs->mr, FSL_DMA_MR_EOTIE - | FSL_DMA_MR_PRC_RM, 32); + set_mr(chan, FSL_DMA_MR_EOTIE | FSL_DMA_MR_PRC_RM); break; } } @@ -175,10 +189,10 @@ static void dma_start(struct fsldma_chan *chan) { u32 mode; - mode = DMA_IN(chan, &chan->regs->mr, 32); + mode = get_mr(chan); if (chan->feature & FSL_DMA_CHAN_PAUSE_EXT) { - DMA_OUT(chan, &chan->regs->bcr, 0, 32); + set_bcr(chan, 0); mode |= FSL_DMA_MR_EMP_EN; } else { mode &= ~FSL_DMA_MR_EMP_EN; @@ -191,7 +205,7 @@ static void dma_start(struct fsldma_chan *chan) mode |= FSL_DMA_MR_CS; } - DMA_OUT(chan, &chan->regs->mr, mode, 32); + set_mr(chan, mode); } static void dma_halt(struct fsldma_chan *chan) @@ -200,7 +214,7 @@ static void dma_halt(struct fsldma_chan *chan) int i; /* read the mode register */ - mode = DMA_IN(chan, &chan->regs->mr, 32); + mode = get_mr(chan); /* * The 85xx controller supports channel abort, which will stop @@ -209,14 +223,14 @@ static void dma_halt(struct fsldma_chan *chan) */ if ((chan->feature & FSL_DMA_IP_MASK) == FSL_DMA_IP_85XX) { mode |= FSL_DMA_MR_CA; - DMA_OUT(chan, &chan->regs->mr, mode, 32); + set_mr(chan, mode); mode &= ~FSL_DMA_MR_CA; } /* stop the DMA controller */ mode &= ~(FSL_DMA_MR_CS | FSL_DMA_MR_EMS_EN); - DMA_OUT(chan, &chan->regs->mr, mode, 32); + set_mr(chan, mode); /* wait for the DMA controller to become idle */ for (i = 0; i < 100; i++) { @@ -245,7 +259,7 @@ static void fsl_chan_set_src_loop_size(struct fsldma_chan *chan, int size) { u32 mode; - mode = DMA_IN(chan, &chan->regs->mr, 32); + mode = get_mr(chan); switch (size) { case 0: @@ -259,7 +273,7 @@ static void fsl_chan_set_src_loop_size(struct fsldma_chan *chan, int size) break; } - DMA_OUT(chan, &chan->regs->mr, mode, 32); + set_mr(chan, mode); } /** @@ -277,7 +291,7 @@ static void fsl_chan_set_dst_loop_size(struct fsldma_chan *chan, int size) { u32 mode; - mode = DMA_IN(chan, &chan->regs->mr, 32); + mode = get_mr(chan); switch (size) { case 0: @@ -291,7 +305,7 @@ static void fsl_chan_set_dst_loop_size(struct fsldma_chan *chan, int size) break; } - DMA_OUT(chan, &chan->regs->mr, mode, 32); + set_mr(chan, mode); } /** @@ -312,10 +326,10 @@ static void fsl_chan_set_request_count(struct fsldma_chan *chan, int size) BUG_ON(size > 1024); - mode = DMA_IN(chan, &chan->regs->mr, 32); + mode = get_mr(chan); mode |= (__ilog2(size) << 24) & 0x0f000000; - DMA_OUT(chan, &chan->regs->mr, mode, 32); + set_mr(chan, mode); } /** @@ -382,10 +396,17 @@ static dma_cookie_t fsl_dma_tx_submit(struct dma_async_tx_descriptor *tx) struct fsldma_chan *chan = to_fsl_chan(tx->chan); struct fsl_desc_sw *desc = tx_to_fsl_desc(tx); struct fsl_desc_sw *child; - unsigned long flags; dma_cookie_t cookie = -EINVAL; - spin_lock_irqsave(&chan->desc_lock, flags); + spin_lock_bh(&chan->desc_lock); + +#ifdef CONFIG_PM + if (unlikely(chan->pm_state != RUNNING)) { + chan_dbg(chan, "cannot submit due to suspend\n"); + spin_unlock_bh(&chan->desc_lock); + return -1; + } +#endif /* * assign cookies to all of the software descriptors @@ -398,12 +419,25 @@ static dma_cookie_t fsl_dma_tx_submit(struct dma_async_tx_descriptor *tx) /* put this transaction onto the tail of the pending queue */ append_ld_queue(chan, desc); - spin_unlock_irqrestore(&chan->desc_lock, flags); + spin_unlock_bh(&chan->desc_lock); return cookie; } /** + * fsl_dma_free_descriptor - Free descriptor from channel's DMA pool. + * @chan : Freescale DMA channel + * @desc: descriptor to be freed + */ +static void fsl_dma_free_descriptor(struct fsldma_chan *chan, + struct fsl_desc_sw *desc) +{ + list_del(&desc->node); + chan_dbg(chan, "LD %p free\n", desc); + dma_pool_free(chan->desc_pool, desc, desc->async_tx.phys); +} + +/** * fsl_dma_alloc_descriptor - Allocate descriptor from channel's DMA pool. * @chan : Freescale DMA channel * @@ -426,14 +460,216 @@ static struct fsl_desc_sw *fsl_dma_alloc_descriptor(struct fsldma_chan *chan) desc->async_tx.tx_submit = fsl_dma_tx_submit; desc->async_tx.phys = pdesc; -#ifdef FSL_DMA_LD_DEBUG chan_dbg(chan, "LD %p allocated\n", desc); -#endif return desc; } /** + * fsldma_clean_completed_descriptor - free all descriptors which + * has been completed and acked + * @chan: Freescale DMA channel + * + * This function is used on all completed and acked descriptors. + * All descriptors should only be freed in this function. + */ +static void fsldma_clean_completed_descriptor(struct fsldma_chan *chan) +{ + struct fsl_desc_sw *desc, *_desc; + + /* Run the callback for each descriptor, in order */ + list_for_each_entry_safe(desc, _desc, &chan->ld_completed, node) + if (async_tx_test_ack(&desc->async_tx)) + fsl_dma_free_descriptor(chan, desc); +} + +/** + * fsldma_run_tx_complete_actions - cleanup a single link descriptor + * @chan: Freescale DMA channel + * @desc: descriptor to cleanup and free + * @cookie: Freescale DMA transaction identifier + * + * This function is used on a descriptor which has been executed by the DMA + * controller. It will run any callbacks, submit any dependencies. + */ +static dma_cookie_t fsldma_run_tx_complete_actions(struct fsldma_chan *chan, + struct fsl_desc_sw *desc, dma_cookie_t cookie) +{ + struct dma_async_tx_descriptor *txd = &desc->async_tx; + dma_cookie_t ret = cookie; + + BUG_ON(txd->cookie < 0); + + if (txd->cookie > 0) { + ret = txd->cookie; + + /* Run the link descriptor callback function */ + if (txd->callback) { + chan_dbg(chan, "LD %p callback\n", desc); + txd->callback(txd->callback_param); + } + } + + /* Run any dependencies */ + dma_run_dependencies(txd); + + return ret; +} + +/** + * fsldma_clean_running_descriptor - move the completed descriptor from + * ld_running to ld_completed + * @chan: Freescale DMA channel + * @desc: the descriptor which is completed + * + * Free the descriptor directly if acked by async_tx api, or move it to + * queue ld_completed. + */ +static void fsldma_clean_running_descriptor(struct fsldma_chan *chan, + struct fsl_desc_sw *desc) +{ + /* Remove from the list of transactions */ + list_del(&desc->node); + + /* + * the client is allowed to attach dependent operations + * until 'ack' is set + */ + if (!async_tx_test_ack(&desc->async_tx)) { + /* + * Move this descriptor to the list of descriptors which is + * completed, but still awaiting the 'ack' bit to be set. + */ + list_add_tail(&desc->node, &chan->ld_completed); + return; + } + + dma_pool_free(chan->desc_pool, desc, desc->async_tx.phys); +} + +/** + * fsl_chan_xfer_ld_queue - transfer any pending transactions + * @chan : Freescale DMA channel + * + * HARDWARE STATE: idle + * LOCKING: must hold chan->desc_lock + */ +static void fsl_chan_xfer_ld_queue(struct fsldma_chan *chan) +{ + struct fsl_desc_sw *desc; + + /* + * If the list of pending descriptors is empty, then we + * don't need to do any work at all + */ + if (list_empty(&chan->ld_pending)) { + chan_dbg(chan, "no pending LDs\n"); + return; + } + + /* + * The DMA controller is not idle, which means that the interrupt + * handler will start any queued transactions when it runs after + * this transaction finishes + */ + if (!chan->idle) { + chan_dbg(chan, "DMA controller still busy\n"); + return; + } + + /* + * If there are some link descriptors which have not been + * transferred, we need to start the controller + */ + + /* + * Move all elements from the queue of pending transactions + * onto the list of running transactions + */ + chan_dbg(chan, "idle, starting controller\n"); + desc = list_first_entry(&chan->ld_pending, struct fsl_desc_sw, node); + list_splice_tail_init(&chan->ld_pending, &chan->ld_running); + + /* + * The 85xx DMA controller doesn't clear the channel start bit + * automatically at the end of a transfer. Therefore we must clear + * it in software before starting the transfer. + */ + if ((chan->feature & FSL_DMA_IP_MASK) == FSL_DMA_IP_85XX) { + u32 mode; + + mode = get_mr(chan); + mode &= ~FSL_DMA_MR_CS; + set_mr(chan, mode); + } + + /* + * Program the descriptor's address into the DMA controller, + * then start the DMA transaction + */ + set_cdar(chan, desc->async_tx.phys); + get_cdar(chan); + + dma_start(chan); + chan->idle = false; +} + +/** + * fsldma_cleanup_descriptors - cleanup link descriptors which are completed + * and move them to ld_completed to free until flag 'ack' is set + * @chan: Freescale DMA channel + * + * This function is used on descriptors which have been executed by the DMA + * controller. It will run any callbacks, submit any dependencies, then + * free these descriptors if flag 'ack' is set. + */ +static void fsldma_cleanup_descriptors(struct fsldma_chan *chan) +{ + struct fsl_desc_sw *desc, *_desc; + dma_cookie_t cookie = 0; + dma_addr_t curr_phys = get_cdar(chan); + int seen_current = 0; + + fsldma_clean_completed_descriptor(chan); + + /* Run the callback for each descriptor, in order */ + list_for_each_entry_safe(desc, _desc, &chan->ld_running, node) { + /* + * do not advance past the current descriptor loaded into the + * hardware channel, subsequent descriptors are either in + * process or have not been submitted + */ + if (seen_current) + break; + + /* + * stop the search if we reach the current descriptor and the + * channel is busy + */ + if (desc->async_tx.phys == curr_phys) { + seen_current = 1; + if (!dma_is_idle(chan)) + break; + } + + cookie = fsldma_run_tx_complete_actions(chan, desc, cookie); + + fsldma_clean_running_descriptor(chan, desc); + } + + /* + * Start any pending transactions automatically + * + * In the ideal case, we keep the DMA controller busy while we go + * ahead and free the descriptors below. + */ + fsl_chan_xfer_ld_queue(chan); + + if (cookie > 0) + chan->common.completed_cookie = cookie; +} + +/** * fsl_dma_alloc_chan_resources - Allocate resources for DMA channel. * @chan : Freescale DMA channel * @@ -477,13 +713,8 @@ static void fsldma_free_desc_list(struct fsldma_chan *chan, { struct fsl_desc_sw *desc, *_desc; - list_for_each_entry_safe(desc, _desc, list, node) { - list_del(&desc->node); -#ifdef FSL_DMA_LD_DEBUG - chan_dbg(chan, "LD %p free\n", desc); -#endif - dma_pool_free(chan->desc_pool, desc, desc->async_tx.phys); - } + list_for_each_entry_safe(desc, _desc, list, node) + fsl_dma_free_descriptor(chan, desc); } static void fsldma_free_desc_list_reverse(struct fsldma_chan *chan, @@ -491,13 +722,8 @@ static void fsldma_free_desc_list_reverse(struct fsldma_chan *chan, { struct fsl_desc_sw *desc, *_desc; - list_for_each_entry_safe_reverse(desc, _desc, list, node) { - list_del(&desc->node); -#ifdef FSL_DMA_LD_DEBUG - chan_dbg(chan, "LD %p free\n", desc); -#endif - dma_pool_free(chan->desc_pool, desc, desc->async_tx.phys); - } + list_for_each_entry_safe_reverse(desc, _desc, list, node) + fsl_dma_free_descriptor(chan, desc); } /** @@ -507,48 +733,20 @@ static void fsldma_free_desc_list_reverse(struct fsldma_chan *chan, static void fsl_dma_free_chan_resources(struct dma_chan *dchan) { struct fsldma_chan *chan = to_fsl_chan(dchan); - unsigned long flags; chan_dbg(chan, "free all channel resources\n"); - spin_lock_irqsave(&chan->desc_lock, flags); + spin_lock_bh(&chan->desc_lock); + fsldma_cleanup_descriptors(chan); fsldma_free_desc_list(chan, &chan->ld_pending); fsldma_free_desc_list(chan, &chan->ld_running); - spin_unlock_irqrestore(&chan->desc_lock, flags); + fsldma_free_desc_list(chan, &chan->ld_completed); + spin_unlock_bh(&chan->desc_lock); dma_pool_destroy(chan->desc_pool); chan->desc_pool = NULL; } static struct dma_async_tx_descriptor * -fsl_dma_prep_interrupt(struct dma_chan *dchan, unsigned long flags) -{ - struct fsldma_chan *chan; - struct fsl_desc_sw *new; - - if (!dchan) - return NULL; - - chan = to_fsl_chan(dchan); - - new = fsl_dma_alloc_descriptor(chan); - if (!new) { - chan_err(chan, "%s\n", msg_ld_oom); - return NULL; - } - - new->async_tx.cookie = -EBUSY; - new->async_tx.flags = flags; - - /* Insert the link descriptor to the LD ring */ - list_add_tail(&new->node, &new->tx_list); - - /* Set End-of-link to the last link descriptor of new list */ - set_ld_eol(chan, new); - - return &new->async_tx; -} - -static struct dma_async_tx_descriptor * fsl_dma_prep_memcpy(struct dma_chan *dchan, dma_addr_t dma_dst, dma_addr_t dma_src, size_t len, unsigned long flags) @@ -761,7 +959,6 @@ static int fsl_dma_device_control(struct dma_chan *dchan, { struct dma_slave_config *config; struct fsldma_chan *chan; - unsigned long flags; int size; if (!dchan) @@ -771,7 +968,7 @@ static int fsl_dma_device_control(struct dma_chan *dchan, switch (cmd) { case DMA_TERMINATE_ALL: - spin_lock_irqsave(&chan->desc_lock, flags); + spin_lock_bh(&chan->desc_lock); /* Halt the DMA engine */ dma_halt(chan); @@ -779,9 +976,10 @@ static int fsl_dma_device_control(struct dma_chan *dchan, /* Remove and free all of the descriptors in the LD queue */ fsldma_free_desc_list(chan, &chan->ld_pending); fsldma_free_desc_list(chan, &chan->ld_running); + fsldma_free_desc_list(chan, &chan->ld_completed); chan->idle = true; - spin_unlock_irqrestore(&chan->desc_lock, flags); + spin_unlock_bh(&chan->desc_lock); return 0; case DMA_SLAVE_CONFIG: @@ -817,116 +1015,16 @@ static int fsl_dma_device_control(struct dma_chan *dchan, } /** - * fsldma_cleanup_descriptor - cleanup and free a single link descriptor - * @chan: Freescale DMA channel - * @desc: descriptor to cleanup and free - * - * This function is used on a descriptor which has been executed by the DMA - * controller. It will run any callbacks, submit any dependencies, and then - * free the descriptor. - */ -static void fsldma_cleanup_descriptor(struct fsldma_chan *chan, - struct fsl_desc_sw *desc) -{ - struct dma_async_tx_descriptor *txd = &desc->async_tx; - - /* Run the link descriptor callback function */ - if (txd->callback) { -#ifdef FSL_DMA_LD_DEBUG - chan_dbg(chan, "LD %p callback\n", desc); -#endif - txd->callback(txd->callback_param); - } - - /* Run any dependencies */ - dma_run_dependencies(txd); - - dma_descriptor_unmap(txd); -#ifdef FSL_DMA_LD_DEBUG - chan_dbg(chan, "LD %p free\n", desc); -#endif - dma_pool_free(chan->desc_pool, desc, txd->phys); -} - -/** - * fsl_chan_xfer_ld_queue - transfer any pending transactions - * @chan : Freescale DMA channel - * - * HARDWARE STATE: idle - * LOCKING: must hold chan->desc_lock - */ -static void fsl_chan_xfer_ld_queue(struct fsldma_chan *chan) -{ - struct fsl_desc_sw *desc; - - /* - * If the list of pending descriptors is empty, then we - * don't need to do any work at all - */ - if (list_empty(&chan->ld_pending)) { - chan_dbg(chan, "no pending LDs\n"); - return; - } - - /* - * The DMA controller is not idle, which means that the interrupt - * handler will start any queued transactions when it runs after - * this transaction finishes - */ - if (!chan->idle) { - chan_dbg(chan, "DMA controller still busy\n"); - return; - } - - /* - * If there are some link descriptors which have not been - * transferred, we need to start the controller - */ - - /* - * Move all elements from the queue of pending transactions - * onto the list of running transactions - */ - chan_dbg(chan, "idle, starting controller\n"); - desc = list_first_entry(&chan->ld_pending, struct fsl_desc_sw, node); - list_splice_tail_init(&chan->ld_pending, &chan->ld_running); - - /* - * The 85xx DMA controller doesn't clear the channel start bit - * automatically at the end of a transfer. Therefore we must clear - * it in software before starting the transfer. - */ - if ((chan->feature & FSL_DMA_IP_MASK) == FSL_DMA_IP_85XX) { - u32 mode; - - mode = DMA_IN(chan, &chan->regs->mr, 32); - mode &= ~FSL_DMA_MR_CS; - DMA_OUT(chan, &chan->regs->mr, mode, 32); - } - - /* - * Program the descriptor's address into the DMA controller, - * then start the DMA transaction - */ - set_cdar(chan, desc->async_tx.phys); - get_cdar(chan); - - dma_start(chan); - chan->idle = false; -} - -/** * fsl_dma_memcpy_issue_pending - Issue the DMA start command * @chan : Freescale DMA channel */ static void fsl_dma_memcpy_issue_pending(struct dma_chan *dchan) { struct fsldma_chan *chan = to_fsl_chan(dchan); - unsigned long flags; - spin_lock_irqsave(&chan->desc_lock, flags); + spin_lock_bh(&chan->desc_lock); fsl_chan_xfer_ld_queue(chan); - spin_unlock_irqrestore(&chan->desc_lock, flags); + spin_unlock_bh(&chan->desc_lock); } /** @@ -937,6 +1035,17 @@ static enum dma_status fsl_tx_status(struct dma_chan *dchan, dma_cookie_t cookie, struct dma_tx_state *txstate) { + struct fsldma_chan *chan = to_fsl_chan(dchan); + enum dma_status ret; + + ret = dma_cookie_status(dchan, cookie, txstate); + if (ret == DMA_COMPLETE) + return ret; + + spin_lock_bh(&chan->desc_lock); + fsldma_cleanup_descriptors(chan); + spin_unlock_bh(&chan->desc_lock); + return dma_cookie_status(dchan, cookie, txstate); } @@ -1014,52 +1123,18 @@ static irqreturn_t fsldma_chan_irq(int irq, void *data) static void dma_do_tasklet(unsigned long data) { struct fsldma_chan *chan = (struct fsldma_chan *)data; - struct fsl_desc_sw *desc, *_desc; - LIST_HEAD(ld_cleanup); - unsigned long flags; chan_dbg(chan, "tasklet entry\n"); - spin_lock_irqsave(&chan->desc_lock, flags); - - /* update the cookie if we have some descriptors to cleanup */ - if (!list_empty(&chan->ld_running)) { - dma_cookie_t cookie; - - desc = to_fsl_desc(chan->ld_running.prev); - cookie = desc->async_tx.cookie; - dma_cookie_complete(&desc->async_tx); - - chan_dbg(chan, "completed_cookie=%d\n", cookie); - } - - /* - * move the descriptors to a temporary list so we can drop the lock - * during the entire cleanup operation - */ - list_splice_tail_init(&chan->ld_running, &ld_cleanup); + spin_lock_bh(&chan->desc_lock); /* the hardware is now idle and ready for more */ chan->idle = true; - /* - * Start any pending transactions automatically - * - * In the ideal case, we keep the DMA controller busy while we go - * ahead and free the descriptors below. - */ - fsl_chan_xfer_ld_queue(chan); - spin_unlock_irqrestore(&chan->desc_lock, flags); - - /* Run the callback for each descriptor, in order */ - list_for_each_entry_safe(desc, _desc, &ld_cleanup, node) { + /* Run all cleanup for descriptors which have been completed */ + fsldma_cleanup_descriptors(chan); - /* Remove from the list of transactions */ - list_del(&desc->node); - - /* Run all cleanup for this descriptor */ - fsldma_cleanup_descriptor(chan, desc); - } + spin_unlock_bh(&chan->desc_lock); chan_dbg(chan, "tasklet exit\n"); } @@ -1243,7 +1318,11 @@ static int fsl_dma_chan_probe(struct fsldma_device *fdev, spin_lock_init(&chan->desc_lock); INIT_LIST_HEAD(&chan->ld_pending); INIT_LIST_HEAD(&chan->ld_running); + INIT_LIST_HEAD(&chan->ld_completed); chan->idle = true; +#ifdef CONFIG_PM + chan->pm_state = RUNNING; +#endif chan->common.device = &fdev->common; dma_cookie_init(&chan->common); @@ -1304,12 +1383,10 @@ static int fsldma_of_probe(struct platform_device *op) fdev->irq = irq_of_parse_and_map(op->dev.of_node, 0); dma_cap_set(DMA_MEMCPY, fdev->common.cap_mask); - dma_cap_set(DMA_INTERRUPT, fdev->common.cap_mask); dma_cap_set(DMA_SG, fdev->common.cap_mask); dma_cap_set(DMA_SLAVE, fdev->common.cap_mask); fdev->common.device_alloc_chan_resources = fsl_dma_alloc_chan_resources; fdev->common.device_free_chan_resources = fsl_dma_free_chan_resources; - fdev->common.device_prep_dma_interrupt = fsl_dma_prep_interrupt; fdev->common.device_prep_dma_memcpy = fsl_dma_prep_memcpy; fdev->common.device_prep_dma_sg = fsl_dma_prep_sg; fdev->common.device_tx_status = fsl_tx_status; @@ -1385,6 +1462,69 @@ static int fsldma_of_remove(struct platform_device *op) return 0; } +#ifdef CONFIG_PM +static int fsldma_suspend_late(struct device *dev) +{ + struct platform_device *pdev = to_platform_device(dev); + struct fsldma_device *fdev = platform_get_drvdata(pdev); + struct fsldma_chan *chan; + int i; + + for (i = 0; i < FSL_DMA_MAX_CHANS_PER_DEVICE; i++) { + chan = fdev->chan[i]; + if (!chan) + continue; + + spin_lock_bh(&chan->desc_lock); + if (unlikely(!chan->idle)) + goto out; + chan->regs_save.mr = get_mr(chan); + chan->pm_state = SUSPENDED; + spin_unlock_bh(&chan->desc_lock); + } + return 0; + +out: + for (; i >= 0; i--) { + chan = fdev->chan[i]; + if (!chan) + continue; + chan->pm_state = RUNNING; + spin_unlock_bh(&chan->desc_lock); + } + return -EBUSY; +} + +static int fsldma_resume_early(struct device *dev) +{ + struct platform_device *pdev = to_platform_device(dev); + struct fsldma_device *fdev = platform_get_drvdata(pdev); + struct fsldma_chan *chan; + u32 mode; + int i; + + for (i = 0; i < FSL_DMA_MAX_CHANS_PER_DEVICE; i++) { + chan = fdev->chan[i]; + if (!chan) + continue; + + spin_lock_bh(&chan->desc_lock); + mode = chan->regs_save.mr + & ~FSL_DMA_MR_CS & ~FSL_DMA_MR_CC & ~FSL_DMA_MR_CA; + set_mr(chan, mode); + chan->pm_state = RUNNING; + spin_unlock_bh(&chan->desc_lock); + } + + return 0; +} + +static const struct dev_pm_ops fsldma_pm_ops = { + .suspend_late = fsldma_suspend_late, + .resume_early = fsldma_resume_early, +}; +#endif + static const struct of_device_id fsldma_of_ids[] = { { .compatible = "fsl,elo3-dma", }, { .compatible = "fsl,eloplus-dma", }, @@ -1397,6 +1537,9 @@ static struct platform_driver fsldma_of_driver = { .name = "fsl-elo-dma", .owner = THIS_MODULE, .of_match_table = fsldma_of_ids, +#ifdef CONFIG_PM + .pm = &fsldma_pm_ops, +#endif }, .probe = fsldma_of_probe, .remove = fsldma_of_remove, diff --git a/drivers/dma/fsldma.h b/drivers/dma/fsldma.h index d56e835..239c20c 100644 --- a/drivers/dma/fsldma.h +++ b/drivers/dma/fsldma.h @@ -134,12 +134,36 @@ struct fsldma_device { #define FSL_DMA_CHAN_PAUSE_EXT 0x00001000 #define FSL_DMA_CHAN_START_EXT 0x00002000 +#ifdef CONFIG_PM +struct fsldma_chan_regs_save { + u32 mr; +}; + +enum fsldma_pm_state { + RUNNING = 0, + SUSPENDED, +}; +#endif + struct fsldma_chan { char name[8]; /* Channel name */ struct fsldma_chan_regs __iomem *regs; spinlock_t desc_lock; /* Descriptor operation lock */ - struct list_head ld_pending; /* Link descriptors queue */ - struct list_head ld_running; /* Link descriptors queue */ + /* + * Descriptors which are queued to run, but have not yet been + * submitted to the hardware for execution + */ + struct list_head ld_pending; + /* + * Descriptors which are currently being executed by the hardware + */ + struct list_head ld_running; + /* + * Descriptors which have finished execution by the hardware. These + * descriptors have already had their cleanup actions run. They are + * waiting for the ACK bit to be set by the async_tx API. + */ + struct list_head ld_completed; /* Link descriptors queue */ struct dma_chan common; /* DMA common channel */ struct dma_pool *desc_pool; /* Descriptors pool */ struct device *dev; /* Channel device */ @@ -148,6 +172,10 @@ struct fsldma_chan { struct tasklet_struct tasklet; u32 feature; bool idle; /* DMA controller is idle */ +#ifdef CONFIG_PM + struct fsldma_chan_regs_save regs_save; + enum fsldma_pm_state pm_state; +#endif void (*toggle_ext_pause)(struct fsldma_chan *fsl_chan, int enable); void (*toggle_ext_start)(struct fsldma_chan *fsl_chan, int enable); diff --git a/drivers/dma/imx-dma.c b/drivers/dma/imx-dma.c index 6f9ac20..9d2c9e7 100644 --- a/drivers/dma/imx-dma.c +++ b/drivers/dma/imx-dma.c @@ -422,12 +422,12 @@ static irqreturn_t imxdma_err_handler(int irq, void *dev_id) /* Tasklet error handler */ tasklet_schedule(&imxdma->channel[i].dma_tasklet); - printk(KERN_WARNING - "DMA timeout on channel %d -%s%s%s%s\n", i, - errcode & IMX_DMA_ERR_BURST ? " burst" : "", - errcode & IMX_DMA_ERR_REQUEST ? " request" : "", - errcode & IMX_DMA_ERR_TRANSFER ? " transfer" : "", - errcode & IMX_DMA_ERR_BUFFER ? " buffer" : ""); + dev_warn(imxdma->dev, + "DMA timeout on channel %d -%s%s%s%s\n", i, + errcode & IMX_DMA_ERR_BURST ? " burst" : "", + errcode & IMX_DMA_ERR_REQUEST ? " request" : "", + errcode & IMX_DMA_ERR_TRANSFER ? " transfer" : "", + errcode & IMX_DMA_ERR_BUFFER ? " buffer" : ""); } return IRQ_HANDLED; } @@ -866,7 +866,7 @@ static struct dma_async_tx_descriptor *imxdma_prep_slave_sg( static struct dma_async_tx_descriptor *imxdma_prep_dma_cyclic( struct dma_chan *chan, dma_addr_t dma_addr, size_t buf_len, size_t period_len, enum dma_transfer_direction direction, - unsigned long flags, void *context) + unsigned long flags) { struct imxdma_channel *imxdmac = to_imxdma_chan(chan); struct imxdma_engine *imxdma = imxdmac->imxdma; @@ -1236,6 +1236,7 @@ static int imxdma_remove(struct platform_device *pdev) static struct platform_driver imxdma_driver = { .driver = { .name = "imx-dma", + .owner = THIS_MODULE, .of_match_table = imx_dma_of_dev_id, }, .id_table = imx_dma_devtype, diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c index 19041ce..f7626e3 100644 --- a/drivers/dma/imx-sdma.c +++ b/drivers/dma/imx-sdma.c @@ -255,6 +255,7 @@ struct sdma_channel { enum dma_slave_buswidth word_size; unsigned int buf_tail; unsigned int num_bd; + unsigned int period_len; struct sdma_buffer_descriptor *bd; dma_addr_t bd_phys; unsigned int pc_from_device, pc_to_device; @@ -270,6 +271,7 @@ struct sdma_channel { unsigned int chn_count; unsigned int chn_real_count; struct tasklet_struct tasklet; + struct imx_dma_data data; }; #define IMX_DMA_SG_LOOP BIT(0) @@ -593,6 +595,12 @@ static void sdma_event_disable(struct sdma_channel *sdmac, unsigned int event) static void sdma_handle_channel_loop(struct sdma_channel *sdmac) { + if (sdmac->desc.callback) + sdmac->desc.callback(sdmac->desc.callback_param); +} + +static void sdma_update_channel_loop(struct sdma_channel *sdmac) +{ struct sdma_buffer_descriptor *bd; /* @@ -607,15 +615,10 @@ static void sdma_handle_channel_loop(struct sdma_channel *sdmac) if (bd->mode.status & BD_RROR) sdmac->status = DMA_ERROR; - else - sdmac->status = DMA_IN_PROGRESS; bd->mode.status |= BD_DONE; sdmac->buf_tail++; sdmac->buf_tail %= sdmac->num_bd; - - if (sdmac->desc.callback) - sdmac->desc.callback(sdmac->desc.callback_param); } } @@ -671,6 +674,9 @@ static irqreturn_t sdma_int_handler(int irq, void *dev_id) int channel = fls(stat) - 1; struct sdma_channel *sdmac = &sdma->channel[channel]; + if (sdmac->flags & IMX_DMA_SG_LOOP) + sdma_update_channel_loop(sdmac); + tasklet_schedule(&sdmac->tasklet); __clear_bit(channel, &stat); @@ -744,6 +750,11 @@ static void sdma_get_pc(struct sdma_channel *sdmac, emi_2_per = sdma->script_addrs->asrc_2_mcu_addr; per_2_per = sdma->script_addrs->per_2_per_addr; break; + case IMX_DMATYPE_ASRC_SP: + per_2_emi = sdma->script_addrs->shp_2_mcu_addr; + emi_2_per = sdma->script_addrs->mcu_2_shp_addr; + per_2_per = sdma->script_addrs->per_2_per_addr; + break; case IMX_DMATYPE_MSHC: per_2_emi = sdma->script_addrs->mshc_2_mcu_addr; emi_2_per = sdma->script_addrs->mcu_2_mshc_addr; @@ -906,14 +917,13 @@ static int sdma_request_channel(struct sdma_channel *sdmac) int channel = sdmac->channel; int ret = -EBUSY; - sdmac->bd = dma_alloc_coherent(NULL, PAGE_SIZE, &sdmac->bd_phys, GFP_KERNEL); + sdmac->bd = dma_zalloc_coherent(NULL, PAGE_SIZE, &sdmac->bd_phys, + GFP_KERNEL); if (!sdmac->bd) { ret = -ENOMEM; goto out; } - memset(sdmac->bd, 0, PAGE_SIZE); - sdma->channel_control[channel].base_bd_ptr = sdmac->bd_phys; sdma->channel_control[channel].current_bd_ptr = sdmac->bd_phys; @@ -1115,7 +1125,7 @@ err_out: static struct dma_async_tx_descriptor *sdma_prep_dma_cyclic( struct dma_chan *chan, dma_addr_t dma_addr, size_t buf_len, size_t period_len, enum dma_transfer_direction direction, - unsigned long flags, void *context) + unsigned long flags) { struct sdma_channel *sdmac = to_sdma_chan(chan); struct sdma_engine *sdma = sdmac->sdma; @@ -1131,6 +1141,7 @@ static struct dma_async_tx_descriptor *sdma_prep_dma_cyclic( sdmac->status = DMA_IN_PROGRESS; sdmac->buf_tail = 0; + sdmac->period_len = period_len; sdmac->flags |= IMX_DMA_SG_LOOP; sdmac->direction = direction; @@ -1227,9 +1238,15 @@ static enum dma_status sdma_tx_status(struct dma_chan *chan, struct dma_tx_state *txstate) { struct sdma_channel *sdmac = to_sdma_chan(chan); + u32 residue; + + if (sdmac->flags & IMX_DMA_SG_LOOP) + residue = (sdmac->num_bd - sdmac->buf_tail) * sdmac->period_len; + else + residue = sdmac->chn_count - sdmac->chn_real_count; dma_set_tx_state(txstate, chan->completed_cookie, chan->cookie, - sdmac->chn_count - sdmac->chn_real_count); + residue); return sdmac->status; } @@ -1402,12 +1419,14 @@ err_dma_alloc: static bool sdma_filter_fn(struct dma_chan *chan, void *fn_param) { + struct sdma_channel *sdmac = to_sdma_chan(chan); struct imx_dma_data *data = fn_param; if (!imx_dma_is_general_purpose(chan)) return false; - chan->private = data; + sdmac->data = *data; + chan->private = &sdmac->data; return true; } diff --git a/drivers/dma/ipu/ipu_idmac.c b/drivers/dma/ipu/ipu_idmac.c index 128ca14..bbf6292 100644 --- a/drivers/dma/ipu/ipu_idmac.c +++ b/drivers/dma/ipu/ipu_idmac.c @@ -1532,11 +1532,17 @@ static int idmac_alloc_chan_resources(struct dma_chan *chan) #ifdef DEBUG if (chan->chan_id == IDMAC_IC_7) { ic_sof = ipu_irq_map(69); - if (ic_sof > 0) - request_irq(ic_sof, ic_sof_irq, 0, "IC SOF", ichan); + if (ic_sof > 0) { + ret = request_irq(ic_sof, ic_sof_irq, 0, "IC SOF", ichan); + if (ret) + dev_err(&chan->dev->device, "request irq failed for IC SOF"); + } ic_eof = ipu_irq_map(70); - if (ic_eof > 0) - request_irq(ic_eof, ic_eof_irq, 0, "IC EOF", ichan); + if (ic_eof > 0) { + ret = request_irq(ic_eof, ic_eof_irq, 0, "IC EOF", ichan); + if (ret) + dev_err(&chan->dev->device, "request irq failed for IC EOF"); + } } #endif diff --git a/drivers/dma/mic_x100_dma.c b/drivers/dma/mic_x100_dma.c new file mode 100644 index 0000000..6de2e67 --- /dev/null +++ b/drivers/dma/mic_x100_dma.c @@ -0,0 +1,774 @@ +/* + * Intel MIC Platform Software Stack (MPSS) + * + * Copyright(c) 2014 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Intel MIC X100 DMA Driver. + * + * Adapted from IOAT dma driver. + */ +#include <linux/module.h> +#include <linux/io.h> +#include <linux/seq_file.h> + +#include "mic_x100_dma.h" + +#define MIC_DMA_MAX_XFER_SIZE_CARD (1 * 1024 * 1024 -\ + MIC_DMA_ALIGN_BYTES) +#define MIC_DMA_MAX_XFER_SIZE_HOST (1 * 1024 * 1024 >> 1) +#define MIC_DMA_DESC_TYPE_SHIFT 60 +#define MIC_DMA_MEMCPY_LEN_SHIFT 46 +#define MIC_DMA_STAT_INTR_SHIFT 59 + +/* high-water mark for pushing dma descriptors */ +static int mic_dma_pending_level = 4; + +/* Status descriptor is used to write a 64 bit value to a memory location */ +enum mic_dma_desc_format_type { + MIC_DMA_MEMCPY = 1, + MIC_DMA_STATUS, +}; + +static inline u32 mic_dma_hw_ring_inc(u32 val) +{ + return (val + 1) % MIC_DMA_DESC_RX_SIZE; +} + +static inline u32 mic_dma_hw_ring_dec(u32 val) +{ + return val ? val - 1 : MIC_DMA_DESC_RX_SIZE - 1; +} + +static inline void mic_dma_hw_ring_inc_head(struct mic_dma_chan *ch) +{ + ch->head = mic_dma_hw_ring_inc(ch->head); +} + +/* Prepare a memcpy desc */ +static inline void mic_dma_memcpy_desc(struct mic_dma_desc *desc, + dma_addr_t src_phys, dma_addr_t dst_phys, u64 size) +{ + u64 qw0, qw1; + + qw0 = src_phys; + qw0 |= (size >> MIC_DMA_ALIGN_SHIFT) << MIC_DMA_MEMCPY_LEN_SHIFT; + qw1 = MIC_DMA_MEMCPY; + qw1 <<= MIC_DMA_DESC_TYPE_SHIFT; + qw1 |= dst_phys; + desc->qw0 = qw0; + desc->qw1 = qw1; +} + +/* Prepare a status desc. with @data to be written at @dst_phys */ +static inline void mic_dma_prep_status_desc(struct mic_dma_desc *desc, u64 data, + dma_addr_t dst_phys, bool generate_intr) +{ + u64 qw0, qw1; + + qw0 = data; + qw1 = (u64) MIC_DMA_STATUS << MIC_DMA_DESC_TYPE_SHIFT | dst_phys; + if (generate_intr) + qw1 |= (1ULL << MIC_DMA_STAT_INTR_SHIFT); + desc->qw0 = qw0; + desc->qw1 = qw1; +} + +static void mic_dma_cleanup(struct mic_dma_chan *ch) +{ + struct dma_async_tx_descriptor *tx; + u32 tail; + u32 last_tail; + + spin_lock(&ch->cleanup_lock); + tail = mic_dma_read_cmp_cnt(ch); + /* + * This is the barrier pair for smp_wmb() in fn. + * mic_dma_tx_submit_unlock. It's required so that we read the + * updated cookie value from tx->cookie. + */ + smp_rmb(); + for (last_tail = ch->last_tail; tail != last_tail;) { + tx = &ch->tx_array[last_tail]; + if (tx->cookie) { + dma_cookie_complete(tx); + if (tx->callback) { + tx->callback(tx->callback_param); + tx->callback = NULL; + } + } + last_tail = mic_dma_hw_ring_inc(last_tail); + } + /* finish all completion callbacks before incrementing tail */ + smp_mb(); + ch->last_tail = last_tail; + spin_unlock(&ch->cleanup_lock); +} + +static u32 mic_dma_ring_count(u32 head, u32 tail) +{ + u32 count; + + if (head >= tail) + count = (tail - 0) + (MIC_DMA_DESC_RX_SIZE - head); + else + count = tail - head; + return count - 1; +} + +/* Returns the num. of free descriptors on success, -ENOMEM on failure */ +static int mic_dma_avail_desc_ring_space(struct mic_dma_chan *ch, int required) +{ + struct device *dev = mic_dma_ch_to_device(ch); + u32 count; + + count = mic_dma_ring_count(ch->head, ch->last_tail); + if (count < required) { + mic_dma_cleanup(ch); + count = mic_dma_ring_count(ch->head, ch->last_tail); + } + + if (count < required) { + dev_dbg(dev, "Not enough desc space"); + dev_dbg(dev, "%s %d required=%u, avail=%u\n", + __func__, __LINE__, required, count); + return -ENOMEM; + } else { + return count; + } +} + +/* Program memcpy descriptors into the descriptor ring and update s/w head ptr*/ +static int mic_dma_prog_memcpy_desc(struct mic_dma_chan *ch, dma_addr_t src, + dma_addr_t dst, size_t len) +{ + size_t current_transfer_len; + size_t max_xfer_size = to_mic_dma_dev(ch)->max_xfer_size; + /* 3 is added to make sure we have enough space for status desc */ + int num_desc = len / max_xfer_size + 3; + int ret; + + if (len % max_xfer_size) + num_desc++; + + ret = mic_dma_avail_desc_ring_space(ch, num_desc); + if (ret < 0) + return ret; + do { + current_transfer_len = min(len, max_xfer_size); + mic_dma_memcpy_desc(&ch->desc_ring[ch->head], + src, dst, current_transfer_len); + mic_dma_hw_ring_inc_head(ch); + len -= current_transfer_len; + dst = dst + current_transfer_len; + src = src + current_transfer_len; + } while (len > 0); + return 0; +} + +/* It's a h/w quirk and h/w needs 2 status descriptors for every status desc */ +static void mic_dma_prog_intr(struct mic_dma_chan *ch) +{ + mic_dma_prep_status_desc(&ch->desc_ring[ch->head], 0, + ch->status_dest_micpa, false); + mic_dma_hw_ring_inc_head(ch); + mic_dma_prep_status_desc(&ch->desc_ring[ch->head], 0, + ch->status_dest_micpa, true); + mic_dma_hw_ring_inc_head(ch); +} + +/* Wrapper function to program memcpy descriptors/status descriptors */ +static int mic_dma_do_dma(struct mic_dma_chan *ch, int flags, dma_addr_t src, + dma_addr_t dst, size_t len) +{ + if (-ENOMEM == mic_dma_prog_memcpy_desc(ch, src, dst, len)) + return -ENOMEM; + /* Above mic_dma_prog_memcpy_desc() makes sure we have enough space */ + if (flags & DMA_PREP_FENCE) { + mic_dma_prep_status_desc(&ch->desc_ring[ch->head], 0, + ch->status_dest_micpa, false); + mic_dma_hw_ring_inc_head(ch); + } + + if (flags & DMA_PREP_INTERRUPT) + mic_dma_prog_intr(ch); + + return 0; +} + +static inline void mic_dma_issue_pending(struct dma_chan *ch) +{ + struct mic_dma_chan *mic_ch = to_mic_dma_chan(ch); + + spin_lock(&mic_ch->issue_lock); + /* + * Write to head triggers h/w to act on the descriptors. + * On MIC, writing the same head value twice causes + * a h/w error. On second write, h/w assumes we filled + * the entire ring & overwrote some of the descriptors. + */ + if (mic_ch->issued == mic_ch->submitted) + goto out; + mic_ch->issued = mic_ch->submitted; + /* + * make descriptor updates visible before advancing head, + * this is purposefully not smp_wmb() since we are also + * publishing the descriptor updates to a dma device + */ + wmb(); + mic_dma_write_reg(mic_ch, MIC_DMA_REG_DHPR, mic_ch->issued); +out: + spin_unlock(&mic_ch->issue_lock); +} + +static inline void mic_dma_update_pending(struct mic_dma_chan *ch) +{ + if (mic_dma_ring_count(ch->issued, ch->submitted) + > mic_dma_pending_level) + mic_dma_issue_pending(&ch->api_ch); +} + +static dma_cookie_t mic_dma_tx_submit_unlock(struct dma_async_tx_descriptor *tx) +{ + struct mic_dma_chan *mic_ch = to_mic_dma_chan(tx->chan); + dma_cookie_t cookie; + + dma_cookie_assign(tx); + cookie = tx->cookie; + /* + * We need an smp write barrier here because another CPU might see + * an update to submitted and update h/w head even before we + * assigned a cookie to this tx. + */ + smp_wmb(); + mic_ch->submitted = mic_ch->head; + spin_unlock(&mic_ch->prep_lock); + mic_dma_update_pending(mic_ch); + return cookie; +} + +static inline struct dma_async_tx_descriptor * +allocate_tx(struct mic_dma_chan *ch) +{ + u32 idx = mic_dma_hw_ring_dec(ch->head); + struct dma_async_tx_descriptor *tx = &ch->tx_array[idx]; + + dma_async_tx_descriptor_init(tx, &ch->api_ch); + tx->tx_submit = mic_dma_tx_submit_unlock; + return tx; +} + +/* + * Prepare a memcpy descriptor to be added to the ring. + * Note that the temporary descriptor adds an extra overhead of copying the + * descriptor to ring. So, we copy directly to the descriptor ring + */ +static struct dma_async_tx_descriptor * +mic_dma_prep_memcpy_lock(struct dma_chan *ch, dma_addr_t dma_dest, + dma_addr_t dma_src, size_t len, unsigned long flags) +{ + struct mic_dma_chan *mic_ch = to_mic_dma_chan(ch); + struct device *dev = mic_dma_ch_to_device(mic_ch); + int result; + + if (!len && !flags) + return NULL; + + spin_lock(&mic_ch->prep_lock); + result = mic_dma_do_dma(mic_ch, flags, dma_src, dma_dest, len); + if (result >= 0) + return allocate_tx(mic_ch); + dev_err(dev, "Error enqueueing dma, error=%d\n", result); + spin_unlock(&mic_ch->prep_lock); + return NULL; +} + +static struct dma_async_tx_descriptor * +mic_dma_prep_interrupt_lock(struct dma_chan *ch, unsigned long flags) +{ + struct mic_dma_chan *mic_ch = to_mic_dma_chan(ch); + int ret; + + spin_lock(&mic_ch->prep_lock); + ret = mic_dma_do_dma(mic_ch, flags, 0, 0, 0); + if (!ret) + return allocate_tx(mic_ch); + spin_unlock(&mic_ch->prep_lock); + return NULL; +} + +/* Return the status of the transaction */ +static enum dma_status +mic_dma_tx_status(struct dma_chan *ch, dma_cookie_t cookie, + struct dma_tx_state *txstate) +{ + struct mic_dma_chan *mic_ch = to_mic_dma_chan(ch); + + if (DMA_COMPLETE != dma_cookie_status(ch, cookie, txstate)) + mic_dma_cleanup(mic_ch); + + return dma_cookie_status(ch, cookie, txstate); +} + +static irqreturn_t mic_dma_thread_fn(int irq, void *data) +{ + mic_dma_cleanup((struct mic_dma_chan *)data); + return IRQ_HANDLED; +} + +static irqreturn_t mic_dma_intr_handler(int irq, void *data) +{ + struct mic_dma_chan *ch = ((struct mic_dma_chan *)data); + + mic_dma_ack_interrupt(ch); + return IRQ_WAKE_THREAD; +} + +static int mic_dma_alloc_desc_ring(struct mic_dma_chan *ch) +{ + u64 desc_ring_size = MIC_DMA_DESC_RX_SIZE * sizeof(*ch->desc_ring); + struct device *dev = &to_mbus_device(ch)->dev; + + desc_ring_size = ALIGN(desc_ring_size, MIC_DMA_ALIGN_BYTES); + ch->desc_ring = kzalloc(desc_ring_size, GFP_KERNEL); + + if (!ch->desc_ring) + return -ENOMEM; + + ch->desc_ring_micpa = dma_map_single(dev, ch->desc_ring, + desc_ring_size, DMA_BIDIRECTIONAL); + if (dma_mapping_error(dev, ch->desc_ring_micpa)) + goto map_error; + + ch->tx_array = vzalloc(MIC_DMA_DESC_RX_SIZE * sizeof(*ch->tx_array)); + if (!ch->tx_array) + goto tx_error; + return 0; +tx_error: + dma_unmap_single(dev, ch->desc_ring_micpa, desc_ring_size, + DMA_BIDIRECTIONAL); +map_error: + kfree(ch->desc_ring); + return -ENOMEM; +} + +static void mic_dma_free_desc_ring(struct mic_dma_chan *ch) +{ + u64 desc_ring_size = MIC_DMA_DESC_RX_SIZE * sizeof(*ch->desc_ring); + + vfree(ch->tx_array); + desc_ring_size = ALIGN(desc_ring_size, MIC_DMA_ALIGN_BYTES); + dma_unmap_single(&to_mbus_device(ch)->dev, ch->desc_ring_micpa, + desc_ring_size, DMA_BIDIRECTIONAL); + kfree(ch->desc_ring); + ch->desc_ring = NULL; +} + +static void mic_dma_free_status_dest(struct mic_dma_chan *ch) +{ + dma_unmap_single(&to_mbus_device(ch)->dev, ch->status_dest_micpa, + L1_CACHE_BYTES, DMA_BIDIRECTIONAL); + kfree(ch->status_dest); +} + +static int mic_dma_alloc_status_dest(struct mic_dma_chan *ch) +{ + struct device *dev = &to_mbus_device(ch)->dev; + + ch->status_dest = kzalloc(L1_CACHE_BYTES, GFP_KERNEL); + if (!ch->status_dest) + return -ENOMEM; + ch->status_dest_micpa = dma_map_single(dev, ch->status_dest, + L1_CACHE_BYTES, DMA_BIDIRECTIONAL); + if (dma_mapping_error(dev, ch->status_dest_micpa)) { + kfree(ch->status_dest); + ch->status_dest = NULL; + return -ENOMEM; + } + return 0; +} + +static int mic_dma_check_chan(struct mic_dma_chan *ch) +{ + if (mic_dma_read_reg(ch, MIC_DMA_REG_DCHERR) || + mic_dma_read_reg(ch, MIC_DMA_REG_DSTAT) & MIC_DMA_CHAN_QUIESCE) { + mic_dma_disable_chan(ch); + mic_dma_chan_mask_intr(ch); + dev_err(mic_dma_ch_to_device(ch), + "%s %d error setting up mic dma chan %d\n", + __func__, __LINE__, ch->ch_num); + return -EBUSY; + } + return 0; +} + +static int mic_dma_chan_setup(struct mic_dma_chan *ch) +{ + if (MIC_DMA_CHAN_MIC == ch->owner) + mic_dma_chan_set_owner(ch); + mic_dma_disable_chan(ch); + mic_dma_chan_mask_intr(ch); + mic_dma_write_reg(ch, MIC_DMA_REG_DCHERRMSK, 0); + mic_dma_chan_set_desc_ring(ch); + ch->last_tail = mic_dma_read_reg(ch, MIC_DMA_REG_DTPR); + ch->head = ch->last_tail; + ch->issued = 0; + mic_dma_chan_unmask_intr(ch); + mic_dma_enable_chan(ch); + return mic_dma_check_chan(ch); +} + +static void mic_dma_chan_destroy(struct mic_dma_chan *ch) +{ + mic_dma_disable_chan(ch); + mic_dma_chan_mask_intr(ch); +} + +static void mic_dma_unregister_dma_device(struct mic_dma_device *mic_dma_dev) +{ + dma_async_device_unregister(&mic_dma_dev->dma_dev); +} + +static int mic_dma_setup_irq(struct mic_dma_chan *ch) +{ + ch->cookie = + to_mbus_hw_ops(ch)->request_threaded_irq(to_mbus_device(ch), + mic_dma_intr_handler, mic_dma_thread_fn, + "mic dma_channel", ch, ch->ch_num); + if (IS_ERR(ch->cookie)) + return IS_ERR(ch->cookie); + return 0; +} + +static inline void mic_dma_free_irq(struct mic_dma_chan *ch) +{ + to_mbus_hw_ops(ch)->free_irq(to_mbus_device(ch), ch->cookie, ch); +} + +static int mic_dma_chan_init(struct mic_dma_chan *ch) +{ + int ret = mic_dma_alloc_desc_ring(ch); + + if (ret) + goto ring_error; + ret = mic_dma_alloc_status_dest(ch); + if (ret) + goto status_error; + ret = mic_dma_chan_setup(ch); + if (ret) + goto chan_error; + return ret; +chan_error: + mic_dma_free_status_dest(ch); +status_error: + mic_dma_free_desc_ring(ch); +ring_error: + return ret; +} + +static int mic_dma_drain_chan(struct mic_dma_chan *ch) +{ + struct dma_async_tx_descriptor *tx; + int err = 0; + dma_cookie_t cookie; + + tx = mic_dma_prep_memcpy_lock(&ch->api_ch, 0, 0, 0, DMA_PREP_FENCE); + if (!tx) { + err = -ENOMEM; + goto error; + } + + cookie = tx->tx_submit(tx); + if (dma_submit_error(cookie)) + err = -ENOMEM; + else + err = dma_sync_wait(&ch->api_ch, cookie); + if (err) { + dev_err(mic_dma_ch_to_device(ch), "%s %d TO chan 0x%x\n", + __func__, __LINE__, ch->ch_num); + err = -EIO; + } +error: + mic_dma_cleanup(ch); + return err; +} + +static inline void mic_dma_chan_uninit(struct mic_dma_chan *ch) +{ + mic_dma_chan_destroy(ch); + mic_dma_cleanup(ch); + mic_dma_free_status_dest(ch); + mic_dma_free_desc_ring(ch); +} + +static int mic_dma_init(struct mic_dma_device *mic_dma_dev, + enum mic_dma_chan_owner owner) +{ + int i, first_chan = mic_dma_dev->start_ch; + struct mic_dma_chan *ch; + int ret; + + for (i = first_chan; i < first_chan + MIC_DMA_NUM_CHAN; i++) { + unsigned long data; + ch = &mic_dma_dev->mic_ch[i]; + data = (unsigned long)ch; + ch->ch_num = i; + ch->owner = owner; + spin_lock_init(&ch->cleanup_lock); + spin_lock_init(&ch->prep_lock); + spin_lock_init(&ch->issue_lock); + ret = mic_dma_setup_irq(ch); + if (ret) + goto error; + } + return 0; +error: + for (i = i - 1; i >= first_chan; i--) + mic_dma_free_irq(ch); + return ret; +} + +static void mic_dma_uninit(struct mic_dma_device *mic_dma_dev) +{ + int i, first_chan = mic_dma_dev->start_ch; + struct mic_dma_chan *ch; + + for (i = first_chan; i < first_chan + MIC_DMA_NUM_CHAN; i++) { + ch = &mic_dma_dev->mic_ch[i]; + mic_dma_free_irq(ch); + } +} + +static int mic_dma_alloc_chan_resources(struct dma_chan *ch) +{ + int ret = mic_dma_chan_init(to_mic_dma_chan(ch)); + if (ret) + return ret; + return MIC_DMA_DESC_RX_SIZE; +} + +static void mic_dma_free_chan_resources(struct dma_chan *ch) +{ + struct mic_dma_chan *mic_ch = to_mic_dma_chan(ch); + mic_dma_drain_chan(mic_ch); + mic_dma_chan_uninit(mic_ch); +} + +/* Set the fn. handlers and register the dma device with dma api */ +static int mic_dma_register_dma_device(struct mic_dma_device *mic_dma_dev, + enum mic_dma_chan_owner owner) +{ + int i, first_chan = mic_dma_dev->start_ch; + + dma_cap_zero(mic_dma_dev->dma_dev.cap_mask); + /* + * This dma engine is not capable of host memory to host memory + * transfers + */ + dma_cap_set(DMA_MEMCPY, mic_dma_dev->dma_dev.cap_mask); + + if (MIC_DMA_CHAN_HOST == owner) + dma_cap_set(DMA_PRIVATE, mic_dma_dev->dma_dev.cap_mask); + mic_dma_dev->dma_dev.device_alloc_chan_resources = + mic_dma_alloc_chan_resources; + mic_dma_dev->dma_dev.device_free_chan_resources = + mic_dma_free_chan_resources; + mic_dma_dev->dma_dev.device_tx_status = mic_dma_tx_status; + mic_dma_dev->dma_dev.device_prep_dma_memcpy = mic_dma_prep_memcpy_lock; + mic_dma_dev->dma_dev.device_prep_dma_interrupt = + mic_dma_prep_interrupt_lock; + mic_dma_dev->dma_dev.device_issue_pending = mic_dma_issue_pending; + mic_dma_dev->dma_dev.copy_align = MIC_DMA_ALIGN_SHIFT; + INIT_LIST_HEAD(&mic_dma_dev->dma_dev.channels); + for (i = first_chan; i < first_chan + MIC_DMA_NUM_CHAN; i++) { + mic_dma_dev->mic_ch[i].api_ch.device = &mic_dma_dev->dma_dev; + dma_cookie_init(&mic_dma_dev->mic_ch[i].api_ch); + list_add_tail(&mic_dma_dev->mic_ch[i].api_ch.device_node, + &mic_dma_dev->dma_dev.channels); + } + return dma_async_device_register(&mic_dma_dev->dma_dev); +} + +/* + * Initializes dma channels and registers the dma device with the + * dma engine api. + */ +static struct mic_dma_device *mic_dma_dev_reg(struct mbus_device *mbdev, + enum mic_dma_chan_owner owner) +{ + struct mic_dma_device *mic_dma_dev; + int ret; + struct device *dev = &mbdev->dev; + + mic_dma_dev = kzalloc(sizeof(*mic_dma_dev), GFP_KERNEL); + if (!mic_dma_dev) { + ret = -ENOMEM; + goto alloc_error; + } + mic_dma_dev->mbdev = mbdev; + mic_dma_dev->dma_dev.dev = dev; + mic_dma_dev->mmio = mbdev->mmio_va; + if (MIC_DMA_CHAN_HOST == owner) { + mic_dma_dev->start_ch = 0; + mic_dma_dev->max_xfer_size = MIC_DMA_MAX_XFER_SIZE_HOST; + } else { + mic_dma_dev->start_ch = 4; + mic_dma_dev->max_xfer_size = MIC_DMA_MAX_XFER_SIZE_CARD; + } + ret = mic_dma_init(mic_dma_dev, owner); + if (ret) + goto init_error; + ret = mic_dma_register_dma_device(mic_dma_dev, owner); + if (ret) + goto reg_error; + return mic_dma_dev; +reg_error: + mic_dma_uninit(mic_dma_dev); +init_error: + kfree(mic_dma_dev); + mic_dma_dev = NULL; +alloc_error: + dev_err(dev, "Error at %s %d ret=%d\n", __func__, __LINE__, ret); + return mic_dma_dev; +} + +static void mic_dma_dev_unreg(struct mic_dma_device *mic_dma_dev) +{ + mic_dma_unregister_dma_device(mic_dma_dev); + mic_dma_uninit(mic_dma_dev); + kfree(mic_dma_dev); +} + +/* DEBUGFS CODE */ +static int mic_dma_reg_seq_show(struct seq_file *s, void *pos) +{ + struct mic_dma_device *mic_dma_dev = s->private; + int i, chan_num, first_chan = mic_dma_dev->start_ch; + struct mic_dma_chan *ch; + + seq_printf(s, "SBOX_DCR: %#x\n", + mic_dma_mmio_read(&mic_dma_dev->mic_ch[first_chan], + MIC_DMA_SBOX_BASE + MIC_DMA_SBOX_DCR)); + seq_puts(s, "DMA Channel Registers\n"); + seq_printf(s, "%-10s| %-10s %-10s %-10s %-10s %-10s", + "Channel", "DCAR", "DTPR", "DHPR", "DRAR_HI", "DRAR_LO"); + seq_printf(s, " %-11s %-14s %-10s\n", "DCHERR", "DCHERRMSK", "DSTAT"); + for (i = first_chan; i < first_chan + MIC_DMA_NUM_CHAN; i++) { + ch = &mic_dma_dev->mic_ch[i]; + chan_num = ch->ch_num; + seq_printf(s, "%-10i| %-#10x %-#10x %-#10x %-#10x", + chan_num, + mic_dma_read_reg(ch, MIC_DMA_REG_DCAR), + mic_dma_read_reg(ch, MIC_DMA_REG_DTPR), + mic_dma_read_reg(ch, MIC_DMA_REG_DHPR), + mic_dma_read_reg(ch, MIC_DMA_REG_DRAR_HI)); + seq_printf(s, " %-#10x %-#10x %-#14x %-#10x\n", + mic_dma_read_reg(ch, MIC_DMA_REG_DRAR_LO), + mic_dma_read_reg(ch, MIC_DMA_REG_DCHERR), + mic_dma_read_reg(ch, MIC_DMA_REG_DCHERRMSK), + mic_dma_read_reg(ch, MIC_DMA_REG_DSTAT)); + } + return 0; +} + +static int mic_dma_reg_debug_open(struct inode *inode, struct file *file) +{ + return single_open(file, mic_dma_reg_seq_show, inode->i_private); +} + +static int mic_dma_reg_debug_release(struct inode *inode, struct file *file) +{ + return single_release(inode, file); +} + +static const struct file_operations mic_dma_reg_ops = { + .owner = THIS_MODULE, + .open = mic_dma_reg_debug_open, + .read = seq_read, + .llseek = seq_lseek, + .release = mic_dma_reg_debug_release +}; + +/* Debugfs parent dir */ +static struct dentry *mic_dma_dbg; + +static int mic_dma_driver_probe(struct mbus_device *mbdev) +{ + struct mic_dma_device *mic_dma_dev; + enum mic_dma_chan_owner owner; + + if (MBUS_DEV_DMA_MIC == mbdev->id.device) + owner = MIC_DMA_CHAN_MIC; + else + owner = MIC_DMA_CHAN_HOST; + + mic_dma_dev = mic_dma_dev_reg(mbdev, owner); + dev_set_drvdata(&mbdev->dev, mic_dma_dev); + + if (mic_dma_dbg) { + mic_dma_dev->dbg_dir = debugfs_create_dir(dev_name(&mbdev->dev), + mic_dma_dbg); + if (mic_dma_dev->dbg_dir) + debugfs_create_file("mic_dma_reg", 0444, + mic_dma_dev->dbg_dir, mic_dma_dev, + &mic_dma_reg_ops); + } + return 0; +} + +static void mic_dma_driver_remove(struct mbus_device *mbdev) +{ + struct mic_dma_device *mic_dma_dev; + + mic_dma_dev = dev_get_drvdata(&mbdev->dev); + debugfs_remove_recursive(mic_dma_dev->dbg_dir); + mic_dma_dev_unreg(mic_dma_dev); +} + +static struct mbus_device_id id_table[] = { + {MBUS_DEV_DMA_MIC, MBUS_DEV_ANY_ID}, + {MBUS_DEV_DMA_HOST, MBUS_DEV_ANY_ID}, + {0}, +}; + +static struct mbus_driver mic_dma_driver = { + .driver.name = KBUILD_MODNAME, + .driver.owner = THIS_MODULE, + .id_table = id_table, + .probe = mic_dma_driver_probe, + .remove = mic_dma_driver_remove, +}; + +static int __init mic_x100_dma_init(void) +{ + int rc = mbus_register_driver(&mic_dma_driver); + if (rc) + return rc; + mic_dma_dbg = debugfs_create_dir(KBUILD_MODNAME, NULL); + return 0; +} + +static void __exit mic_x100_dma_exit(void) +{ + debugfs_remove_recursive(mic_dma_dbg); + mbus_unregister_driver(&mic_dma_driver); +} + +module_init(mic_x100_dma_init); +module_exit(mic_x100_dma_exit); + +MODULE_DEVICE_TABLE(mbus, id_table); +MODULE_AUTHOR("Intel Corporation"); +MODULE_DESCRIPTION("Intel(R) MIC X100 DMA Driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/dma/mic_x100_dma.h b/drivers/dma/mic_x100_dma.h new file mode 100644 index 0000000..f663b0b --- /dev/null +++ b/drivers/dma/mic_x100_dma.h @@ -0,0 +1,286 @@ +/* + * Intel MIC Platform Software Stack (MPSS) + * + * Copyright(c) 2014 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Intel MIC X100 DMA Driver. + * + * Adapted from IOAT dma driver. + */ +#ifndef _MIC_X100_DMA_H_ +#define _MIC_X100_DMA_H_ + +#include <linux/kernel.h> +#include <linux/delay.h> +#include <linux/sched.h> +#include <linux/debugfs.h> +#include <linux/slab.h> +#include <linux/interrupt.h> +#include <linux/mic_bus.h> + +#include "dmaengine.h" + +/* + * MIC has a total of 8 dma channels. + * Four channels are assigned for host SW use & the remaining for MIC SW. + * MIC DMA transfer size & addresses need to be 64 byte aligned. + */ +#define MIC_DMA_MAX_NUM_CHAN 8 +#define MIC_DMA_NUM_CHAN 4 +#define MIC_DMA_ALIGN_SHIFT 6 +#define MIC_DMA_ALIGN_BYTES (1 << MIC_DMA_ALIGN_SHIFT) +#define MIC_DMA_DESC_RX_SIZE (128 * 1024 - 4) + +/* + * Register descriptions + * All the registers are 32 bit registers. + * DCR is a global register and all others are per-channel. + * DCR - bits 0, 2, 4, 6, 8, 10, 12, 14 - enable bits for channels 0 to 7 + * bits 1, 3, 5, 7, 9, 11, 13, 15 - owner bits for channels 0 to 7 + * DCAR - bit 24 & 25 interrupt masks for mic owned & host owned channels + * DHPR - head of the descriptor ring updated by s/w + * DTPR - tail of the descriptor ring updated by h/w + * DRAR_LO - lower 32 bits of descriptor ring's mic address + * DRAR_HI - 3:0 - remaining 4 bits of descriptor ring's mic address + * 20:4 descriptor ring size + * 25:21 mic smpt entry number + * DSTAT - 16:0 h/w completion count; 31:28 dma engine status + * DCHERR - this register is non-zero on error + * DCHERRMSK - interrupt mask register + */ +#define MIC_DMA_HW_CMP_CNT_MASK 0x1ffff +#define MIC_DMA_CHAN_QUIESCE 0x20000000 +#define MIC_DMA_SBOX_BASE 0x00010000 +#define MIC_DMA_SBOX_DCR 0x0000A280 +#define MIC_DMA_SBOX_CH_BASE 0x0001A000 +#define MIC_DMA_SBOX_CHAN_OFF 0x40 +#define MIC_DMA_SBOX_DCAR_IM0 (0x1 << 24) +#define MIC_DMA_SBOX_DCAR_IM1 (0x1 << 25) +#define MIC_DMA_SBOX_DRARHI_SYS_MASK (0x1 << 26) +#define MIC_DMA_REG_DCAR 0 +#define MIC_DMA_REG_DHPR 4 +#define MIC_DMA_REG_DTPR 8 +#define MIC_DMA_REG_DRAR_LO 20 +#define MIC_DMA_REG_DRAR_HI 24 +#define MIC_DMA_REG_DSTAT 32 +#define MIC_DMA_REG_DCHERR 44 +#define MIC_DMA_REG_DCHERRMSK 48 + +/* HW dma desc */ +struct mic_dma_desc { + u64 qw0; + u64 qw1; +}; + +enum mic_dma_chan_owner { + MIC_DMA_CHAN_MIC = 0, + MIC_DMA_CHAN_HOST +}; + +/* + * mic_dma_chan - channel specific information + * @ch_num: channel number + * @owner: owner of this channel + * @last_tail: cached value of descriptor ring tail + * @head: index of next descriptor in desc_ring + * @issued: hardware notification point + * @submitted: index that will be used to submit descriptors to h/w + * @api_ch: dma engine api channel + * @desc_ring: dma descriptor ring + * @desc_ring_micpa: mic physical address of desc_ring + * @status_dest: destination for status (fence) descriptor + * @status_dest_micpa: mic address for status_dest, + * DMA controller uses this address + * @tx_array: array of async_tx + * @cleanup_lock: lock held when processing completed tx + * @prep_lock: lock held in prep_memcpy & released in tx_submit + * @issue_lock: lock used to synchronize writes to head + * @cookie: mic_irq cookie used with mic irq request + */ +struct mic_dma_chan { + int ch_num; + enum mic_dma_chan_owner owner; + u32 last_tail; + u32 head; + u32 issued; + u32 submitted; + struct dma_chan api_ch; + struct mic_dma_desc *desc_ring; + dma_addr_t desc_ring_micpa; + u64 *status_dest; + dma_addr_t status_dest_micpa; + struct dma_async_tx_descriptor *tx_array; + spinlock_t cleanup_lock; + spinlock_t prep_lock; + spinlock_t issue_lock; + struct mic_irq *cookie; +}; + +/* + * struct mic_dma_device - per mic device + * @mic_ch: dma channels + * @dma_dev: underlying dma device + * @mbdev: mic bus dma device + * @mmio: virtual address of the mmio space + * @dbg_dir: debugfs directory + * @start_ch: first channel number that can be used + * @max_xfer_size: maximum transfer size per dma descriptor + */ +struct mic_dma_device { + struct mic_dma_chan mic_ch[MIC_DMA_MAX_NUM_CHAN]; + struct dma_device dma_dev; + struct mbus_device *mbdev; + void __iomem *mmio; + struct dentry *dbg_dir; + int start_ch; + size_t max_xfer_size; +}; + +static inline struct mic_dma_chan *to_mic_dma_chan(struct dma_chan *ch) +{ + return container_of(ch, struct mic_dma_chan, api_ch); +} + +static inline struct mic_dma_device *to_mic_dma_dev(struct mic_dma_chan *ch) +{ + return + container_of((const typeof(((struct mic_dma_device *)0)->mic_ch)*) + (ch - ch->ch_num), struct mic_dma_device, mic_ch); +} + +static inline struct mbus_device *to_mbus_device(struct mic_dma_chan *ch) +{ + return to_mic_dma_dev(ch)->mbdev; +} + +static inline struct mbus_hw_ops *to_mbus_hw_ops(struct mic_dma_chan *ch) +{ + return to_mbus_device(ch)->hw_ops; +} + +static inline struct device *mic_dma_ch_to_device(struct mic_dma_chan *ch) +{ + return to_mic_dma_dev(ch)->dma_dev.dev; +} + +static inline void __iomem *mic_dma_chan_to_mmio(struct mic_dma_chan *ch) +{ + return to_mic_dma_dev(ch)->mmio; +} + +static inline u32 mic_dma_read_reg(struct mic_dma_chan *ch, u32 reg) +{ + return ioread32(mic_dma_chan_to_mmio(ch) + MIC_DMA_SBOX_CH_BASE + + ch->ch_num * MIC_DMA_SBOX_CHAN_OFF + reg); +} + +static inline void mic_dma_write_reg(struct mic_dma_chan *ch, u32 reg, u32 val) +{ + iowrite32(val, mic_dma_chan_to_mmio(ch) + MIC_DMA_SBOX_CH_BASE + + ch->ch_num * MIC_DMA_SBOX_CHAN_OFF + reg); +} + +static inline u32 mic_dma_mmio_read(struct mic_dma_chan *ch, u32 offset) +{ + return ioread32(mic_dma_chan_to_mmio(ch) + offset); +} + +static inline void mic_dma_mmio_write(struct mic_dma_chan *ch, u32 val, + u32 offset) +{ + iowrite32(val, mic_dma_chan_to_mmio(ch) + offset); +} + +static inline u32 mic_dma_read_cmp_cnt(struct mic_dma_chan *ch) +{ + return mic_dma_read_reg(ch, MIC_DMA_REG_DSTAT) & + MIC_DMA_HW_CMP_CNT_MASK; +} + +static inline void mic_dma_chan_set_owner(struct mic_dma_chan *ch) +{ + u32 dcr = mic_dma_mmio_read(ch, MIC_DMA_SBOX_BASE + MIC_DMA_SBOX_DCR); + u32 chan_num = ch->ch_num; + + dcr = (dcr & ~(0x1 << (chan_num * 2))) | (ch->owner << (chan_num * 2)); + mic_dma_mmio_write(ch, dcr, MIC_DMA_SBOX_BASE + MIC_DMA_SBOX_DCR); +} + +static inline void mic_dma_enable_chan(struct mic_dma_chan *ch) +{ + u32 dcr = mic_dma_mmio_read(ch, MIC_DMA_SBOX_BASE + MIC_DMA_SBOX_DCR); + + dcr |= 2 << (ch->ch_num << 1); + mic_dma_mmio_write(ch, dcr, MIC_DMA_SBOX_BASE + MIC_DMA_SBOX_DCR); +} + +static inline void mic_dma_disable_chan(struct mic_dma_chan *ch) +{ + u32 dcr = mic_dma_mmio_read(ch, MIC_DMA_SBOX_BASE + MIC_DMA_SBOX_DCR); + + dcr &= ~(2 << (ch->ch_num << 1)); + mic_dma_mmio_write(ch, dcr, MIC_DMA_SBOX_BASE + MIC_DMA_SBOX_DCR); +} + +static void mic_dma_chan_set_desc_ring(struct mic_dma_chan *ch) +{ + u32 drar_hi; + dma_addr_t desc_ring_micpa = ch->desc_ring_micpa; + + drar_hi = (MIC_DMA_DESC_RX_SIZE & 0x1ffff) << 4; + if (MIC_DMA_CHAN_MIC == ch->owner) { + drar_hi |= (desc_ring_micpa >> 32) & 0xf; + } else { + drar_hi |= MIC_DMA_SBOX_DRARHI_SYS_MASK; + drar_hi |= ((desc_ring_micpa >> 34) + & 0x1f) << 21; + drar_hi |= (desc_ring_micpa >> 32) & 0x3; + } + mic_dma_write_reg(ch, MIC_DMA_REG_DRAR_LO, (u32) desc_ring_micpa); + mic_dma_write_reg(ch, MIC_DMA_REG_DRAR_HI, drar_hi); +} + +static inline void mic_dma_chan_mask_intr(struct mic_dma_chan *ch) +{ + u32 dcar = mic_dma_read_reg(ch, MIC_DMA_REG_DCAR); + + if (MIC_DMA_CHAN_MIC == ch->owner) + dcar |= MIC_DMA_SBOX_DCAR_IM0; + else + dcar |= MIC_DMA_SBOX_DCAR_IM1; + mic_dma_write_reg(ch, MIC_DMA_REG_DCAR, dcar); +} + +static inline void mic_dma_chan_unmask_intr(struct mic_dma_chan *ch) +{ + u32 dcar = mic_dma_read_reg(ch, MIC_DMA_REG_DCAR); + + if (MIC_DMA_CHAN_MIC == ch->owner) + dcar &= ~MIC_DMA_SBOX_DCAR_IM0; + else + dcar &= ~MIC_DMA_SBOX_DCAR_IM1; + mic_dma_write_reg(ch, MIC_DMA_REG_DCAR, dcar); +} + +static void mic_dma_ack_interrupt(struct mic_dma_chan *ch) +{ + if (MIC_DMA_CHAN_MIC == ch->owner) { + /* HW errata */ + mic_dma_chan_mask_intr(ch); + mic_dma_chan_unmask_intr(ch); + } + to_mbus_hw_ops(ch)->ack_interrupt(to_mbus_device(ch), ch->ch_num); +} +#endif diff --git a/drivers/dma/mmp_pdma.c b/drivers/dma/mmp_pdma.c index b439679..a1a4db5 100644 --- a/drivers/dma/mmp_pdma.c +++ b/drivers/dma/mmp_pdma.c @@ -29,8 +29,8 @@ #define DALGN 0x00a0 #define DINT 0x00f0 #define DDADR 0x0200 -#define DSADR 0x0204 -#define DTADR 0x0208 +#define DSADR(n) (0x0204 + ((n) << 4)) +#define DTADR(n) (0x0208 + ((n) << 4)) #define DCMD 0x020c #define DCSR_RUN BIT(31) /* Run Bit (read / write) */ @@ -277,7 +277,7 @@ static void mmp_pdma_free_phy(struct mmp_pdma_chan *pchan) return; /* clear the channel mapping in DRCMR */ - reg = DRCMR(pchan->phy->vchan->drcmr); + reg = DRCMR(pchan->drcmr); writel(0, pchan->phy->base + reg); spin_lock_irqsave(&pdev->phy_lock, flags); @@ -601,7 +601,7 @@ static struct dma_async_tx_descriptor * mmp_pdma_prep_dma_cyclic(struct dma_chan *dchan, dma_addr_t buf_addr, size_t len, size_t period_len, enum dma_transfer_direction direction, - unsigned long flags, void *context) + unsigned long flags) { struct mmp_pdma_chan *chan; struct mmp_pdma_desc_sw *first = NULL, *prev = NULL, *new; @@ -748,11 +748,92 @@ static int mmp_pdma_control(struct dma_chan *dchan, enum dma_ctrl_cmd cmd, return 0; } +static unsigned int mmp_pdma_residue(struct mmp_pdma_chan *chan, + dma_cookie_t cookie) +{ + struct mmp_pdma_desc_sw *sw; + u32 curr, residue = 0; + bool passed = false; + bool cyclic = chan->cyclic_first != NULL; + + /* + * If the channel does not have a phy pointer anymore, it has already + * been completed. Therefore, its residue is 0. + */ + if (!chan->phy) + return 0; + + if (chan->dir == DMA_DEV_TO_MEM) + curr = readl(chan->phy->base + DTADR(chan->phy->idx)); + else + curr = readl(chan->phy->base + DSADR(chan->phy->idx)); + + list_for_each_entry(sw, &chan->chain_running, node) { + u32 start, end, len; + + if (chan->dir == DMA_DEV_TO_MEM) + start = sw->desc.dtadr; + else + start = sw->desc.dsadr; + + len = sw->desc.dcmd & DCMD_LENGTH; + end = start + len; + + /* + * 'passed' will be latched once we found the descriptor which + * lies inside the boundaries of the curr pointer. All + * descriptors that occur in the list _after_ we found that + * partially handled descriptor are still to be processed and + * are hence added to the residual bytes counter. + */ + + if (passed) { + residue += len; + } else if (curr >= start && curr <= end) { + residue += end - curr; + passed = true; + } + + /* + * Descriptors that have the ENDIRQEN bit set mark the end of a + * transaction chain, and the cookie assigned with it has been + * returned previously from mmp_pdma_tx_submit(). + * + * In case we have multiple transactions in the running chain, + * and the cookie does not match the one the user asked us + * about, reset the state variables and start over. + * + * This logic does not apply to cyclic transactions, where all + * descriptors have the ENDIRQEN bit set, and for which we + * can't have multiple transactions on one channel anyway. + */ + if (cyclic || !(sw->desc.dcmd & DCMD_ENDIRQEN)) + continue; + + if (sw->async_tx.cookie == cookie) { + return residue; + } else { + residue = 0; + passed = false; + } + } + + /* We should only get here in case of cyclic transactions */ + return residue; +} + static enum dma_status mmp_pdma_tx_status(struct dma_chan *dchan, dma_cookie_t cookie, struct dma_tx_state *txstate) { - return dma_cookie_status(dchan, cookie, txstate); + struct mmp_pdma_chan *chan = to_mmp_pdma_chan(dchan); + enum dma_status ret; + + ret = dma_cookie_status(dchan, cookie, txstate); + if (likely(ret != DMA_ERROR)) + dma_set_residue(txstate, mmp_pdma_residue(chan, cookie)); + + return ret; } /** @@ -858,8 +939,7 @@ static int mmp_pdma_chan_init(struct mmp_pdma_device *pdev, int idx, int irq) struct mmp_pdma_chan *chan; int ret; - chan = devm_kzalloc(pdev->dev, sizeof(struct mmp_pdma_chan), - GFP_KERNEL); + chan = devm_kzalloc(pdev->dev, sizeof(*chan), GFP_KERNEL); if (chan == NULL) return -ENOMEM; @@ -867,8 +947,8 @@ static int mmp_pdma_chan_init(struct mmp_pdma_device *pdev, int idx, int irq) phy->base = pdev->base; if (irq) { - ret = devm_request_irq(pdev->dev, irq, mmp_pdma_chan_handler, 0, - "pdma", phy); + ret = devm_request_irq(pdev->dev, irq, mmp_pdma_chan_handler, + IRQF_SHARED, "pdma", phy); if (ret) { dev_err(pdev->dev, "channel request irq fail!\n"); return ret; @@ -946,8 +1026,7 @@ static int mmp_pdma_probe(struct platform_device *op) irq_num++; } - pdev->phy = devm_kcalloc(pdev->dev, - dma_channels, sizeof(struct mmp_pdma_chan), + pdev->phy = devm_kcalloc(pdev->dev, dma_channels, sizeof(*pdev->phy), GFP_KERNEL); if (pdev->phy == NULL) return -ENOMEM; @@ -957,8 +1036,8 @@ static int mmp_pdma_probe(struct platform_device *op) if (irq_num != dma_channels) { /* all chan share one irq, demux inside */ irq = platform_get_irq(op, 0); - ret = devm_request_irq(pdev->dev, irq, mmp_pdma_int_handler, 0, - "pdma", pdev); + ret = devm_request_irq(pdev->dev, irq, mmp_pdma_int_handler, + IRQF_SHARED, "pdma", pdev); if (ret) return ret; } diff --git a/drivers/dma/mmp_tdma.c b/drivers/dma/mmp_tdma.c index 33f96aa..6ad30e2 100644 --- a/drivers/dma/mmp_tdma.c +++ b/drivers/dma/mmp_tdma.c @@ -22,6 +22,7 @@ #include <mach/regs-icu.h> #include <linux/platform_data/dma-mmp_tdma.h> #include <linux/of_device.h> +#include <linux/of_dma.h> #include "dmaengine.h" @@ -388,7 +389,7 @@ struct mmp_tdma_desc *mmp_tdma_alloc_descriptor(struct mmp_tdma_chan *tdmac) static struct dma_async_tx_descriptor *mmp_tdma_prep_dma_cyclic( struct dma_chan *chan, dma_addr_t dma_addr, size_t buf_len, size_t period_len, enum dma_transfer_direction direction, - unsigned long flags, void *context) + unsigned long flags) { struct mmp_tdma_chan *tdmac = to_mmp_tdma_chan(chan); struct mmp_tdma_desc *desc; @@ -541,6 +542,45 @@ static int mmp_tdma_chan_init(struct mmp_tdma_device *tdev, return 0; } +struct mmp_tdma_filter_param { + struct device_node *of_node; + unsigned int chan_id; +}; + +static bool mmp_tdma_filter_fn(struct dma_chan *chan, void *fn_param) +{ + struct mmp_tdma_filter_param *param = fn_param; + struct mmp_tdma_chan *tdmac = to_mmp_tdma_chan(chan); + struct dma_device *pdma_device = tdmac->chan.device; + + if (pdma_device->dev->of_node != param->of_node) + return false; + + if (chan->chan_id != param->chan_id) + return false; + + return true; +} + +struct dma_chan *mmp_tdma_xlate(struct of_phandle_args *dma_spec, + struct of_dma *ofdma) +{ + struct mmp_tdma_device *tdev = ofdma->of_dma_data; + dma_cap_mask_t mask = tdev->device.cap_mask; + struct mmp_tdma_filter_param param; + + if (dma_spec->args_count != 1) + return NULL; + + param.of_node = ofdma->of_node; + param.chan_id = dma_spec->args[0]; + + if (param.chan_id >= TDMA_CHANNEL_NUM) + return NULL; + + return dma_request_channel(mask, mmp_tdma_filter_fn, ¶m); +} + static struct of_device_id mmp_tdma_dt_ids[] = { { .compatible = "marvell,adma-1.0", .data = (void *)MMP_AUD_TDMA}, { .compatible = "marvell,pxa910-squ", .data = (void *)PXA910_SQU}, @@ -631,6 +671,16 @@ static int mmp_tdma_probe(struct platform_device *pdev) return ret; } + if (pdev->dev.of_node) { + ret = of_dma_controller_register(pdev->dev.of_node, + mmp_tdma_xlate, tdev); + if (ret) { + dev_err(tdev->device.dev, + "failed to register controller\n"); + dma_async_device_unregister(&tdev->device); + } + } + dev_info(tdev->device.dev, "initialized\n"); return 0; } diff --git a/drivers/dma/mpc512x_dma.c b/drivers/dma/mpc512x_dma.c index 448750d..881db2b 100644 --- a/drivers/dma/mpc512x_dma.c +++ b/drivers/dma/mpc512x_dma.c @@ -2,6 +2,7 @@ * Copyright (C) Freescale Semicondutor, Inc. 2007, 2008. * Copyright (C) Semihalf 2009 * Copyright (C) Ilya Yanok, Emcraft Systems 2010 + * Copyright (C) Alexander Popov, Promcontroller 2014 * * Written by Piotr Ziecik <kosmo@semihalf.com>. Hardware description * (defines, structures and comments) was taken from MPC5121 DMA driver @@ -29,8 +30,18 @@ */ /* - * This is initial version of MPC5121 DMA driver. Only memory to memory - * transfers are supported (tested using dmatest module). + * MPC512x and MPC8308 DMA driver. It supports + * memory to memory data transfers (tested using dmatest module) and + * data transfers between memory and peripheral I/O memory + * by means of slave scatter/gather with these limitations: + * - chunked transfers (described by s/g lists with more than one item) + * are refused as long as proper support for scatter/gather is missing; + * - transfers on MPC8308 always start from software as this SoC appears + * not to have external request lines for peripheral flow control; + * - only peripheral devices with 4-byte FIFO access register are supported; + * - minimal memory <-> I/O memory transfer chunk is 4 bytes and consequently + * source and destination addresses must be 4-byte aligned + * and transfer size must be aligned on (4 * maxburst) boundary; */ #include <linux/module.h> @@ -42,6 +53,7 @@ #include <linux/of_address.h> #include <linux/of_device.h> #include <linux/of_irq.h> +#include <linux/of_dma.h> #include <linux/of_platform.h> #include <linux/random.h> @@ -52,9 +64,17 @@ #define MPC_DMA_DESCRIPTORS 64 /* Macro definitions */ -#define MPC_DMA_CHANNELS 64 #define MPC_DMA_TCD_OFFSET 0x1000 +/* + * Maximum channel counts for individual hardware variants + * and the maximum channel count over all supported controllers, + * used for data structure size + */ +#define MPC8308_DMACHAN_MAX 16 +#define MPC512x_DMACHAN_MAX 64 +#define MPC_DMA_CHANNELS 64 + /* Arbitration mode of group and channel */ #define MPC_DMA_DMACR_EDCG (1 << 31) #define MPC_DMA_DMACR_ERGA (1 << 3) @@ -181,6 +201,7 @@ struct mpc_dma_desc { dma_addr_t tcd_paddr; int error; struct list_head node; + int will_access_peripheral; }; struct mpc_dma_chan { @@ -193,6 +214,12 @@ struct mpc_dma_chan { struct mpc_dma_tcd *tcd; dma_addr_t tcd_paddr; + /* Settings for access to peripheral FIFO */ + dma_addr_t src_per_paddr; + u32 src_tcd_nunits; + dma_addr_t dst_per_paddr; + u32 dst_tcd_nunits; + /* Lock for this structure */ spinlock_t lock; }; @@ -243,8 +270,23 @@ static void mpc_dma_execute(struct mpc_dma_chan *mchan) struct mpc_dma_desc *mdesc; int cid = mchan->chan.chan_id; - /* Move all queued descriptors to active list */ - list_splice_tail_init(&mchan->queued, &mchan->active); + while (!list_empty(&mchan->queued)) { + mdesc = list_first_entry(&mchan->queued, + struct mpc_dma_desc, node); + /* + * Grab either several mem-to-mem transfer descriptors + * or one peripheral transfer descriptor, + * don't mix mem-to-mem and peripheral transfer descriptors + * within the same 'active' list. + */ + if (mdesc->will_access_peripheral) { + if (list_empty(&mchan->active)) + list_move_tail(&mdesc->node, &mchan->active); + break; + } else { + list_move_tail(&mdesc->node, &mchan->active); + } + } /* Chain descriptors into one transaction */ list_for_each_entry(mdesc, &mchan->active, node) { @@ -270,7 +312,17 @@ static void mpc_dma_execute(struct mpc_dma_chan *mchan) if (first != prev) mdma->tcd[cid].e_sg = 1; - out_8(&mdma->regs->dmassrt, cid); + + if (mdma->is_mpc8308) { + /* MPC8308, no request lines, software initiated start */ + out_8(&mdma->regs->dmassrt, cid); + } else if (first->will_access_peripheral) { + /* Peripherals involved, start by external request signal */ + out_8(&mdma->regs->dmaserq, cid); + } else { + /* Memory to memory transfer, software initiated start */ + out_8(&mdma->regs->dmassrt, cid); + } } /* Handle interrupt on one half of DMA controller (32 channels) */ @@ -588,6 +640,7 @@ mpc_dma_prep_memcpy(struct dma_chan *chan, dma_addr_t dst, dma_addr_t src, } mdesc->error = 0; + mdesc->will_access_peripheral = 0; tcd = mdesc->tcd; /* Prepare Transfer Control Descriptor for this transaction */ @@ -635,6 +688,193 @@ mpc_dma_prep_memcpy(struct dma_chan *chan, dma_addr_t dst, dma_addr_t src, return &mdesc->desc; } +static struct dma_async_tx_descriptor * +mpc_dma_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl, + unsigned int sg_len, enum dma_transfer_direction direction, + unsigned long flags, void *context) +{ + struct mpc_dma *mdma = dma_chan_to_mpc_dma(chan); + struct mpc_dma_chan *mchan = dma_chan_to_mpc_dma_chan(chan); + struct mpc_dma_desc *mdesc = NULL; + dma_addr_t per_paddr; + u32 tcd_nunits; + struct mpc_dma_tcd *tcd; + unsigned long iflags; + struct scatterlist *sg; + size_t len; + int iter, i; + + /* Currently there is no proper support for scatter/gather */ + if (sg_len != 1) + return NULL; + + if (!is_slave_direction(direction)) + return NULL; + + for_each_sg(sgl, sg, sg_len, i) { + spin_lock_irqsave(&mchan->lock, iflags); + + mdesc = list_first_entry(&mchan->free, + struct mpc_dma_desc, node); + if (!mdesc) { + spin_unlock_irqrestore(&mchan->lock, iflags); + /* Try to free completed descriptors */ + mpc_dma_process_completed(mdma); + return NULL; + } + + list_del(&mdesc->node); + + if (direction == DMA_DEV_TO_MEM) { + per_paddr = mchan->src_per_paddr; + tcd_nunits = mchan->src_tcd_nunits; + } else { + per_paddr = mchan->dst_per_paddr; + tcd_nunits = mchan->dst_tcd_nunits; + } + + spin_unlock_irqrestore(&mchan->lock, iflags); + + if (per_paddr == 0 || tcd_nunits == 0) + goto err_prep; + + mdesc->error = 0; + mdesc->will_access_peripheral = 1; + + /* Prepare Transfer Control Descriptor for this transaction */ + tcd = mdesc->tcd; + + memset(tcd, 0, sizeof(struct mpc_dma_tcd)); + + if (!IS_ALIGNED(sg_dma_address(sg), 4)) + goto err_prep; + + if (direction == DMA_DEV_TO_MEM) { + tcd->saddr = per_paddr; + tcd->daddr = sg_dma_address(sg); + tcd->soff = 0; + tcd->doff = 4; + } else { + tcd->saddr = sg_dma_address(sg); + tcd->daddr = per_paddr; + tcd->soff = 4; + tcd->doff = 0; + } + + tcd->ssize = MPC_DMA_TSIZE_4; + tcd->dsize = MPC_DMA_TSIZE_4; + + len = sg_dma_len(sg); + tcd->nbytes = tcd_nunits * 4; + if (!IS_ALIGNED(len, tcd->nbytes)) + goto err_prep; + + iter = len / tcd->nbytes; + if (iter >= 1 << 15) { + /* len is too big */ + goto err_prep; + } + /* citer_linkch contains the high bits of iter */ + tcd->biter = iter & 0x1ff; + tcd->biter_linkch = iter >> 9; + tcd->citer = tcd->biter; + tcd->citer_linkch = tcd->biter_linkch; + + tcd->e_sg = 0; + tcd->d_req = 1; + + /* Place descriptor in prepared list */ + spin_lock_irqsave(&mchan->lock, iflags); + list_add_tail(&mdesc->node, &mchan->prepared); + spin_unlock_irqrestore(&mchan->lock, iflags); + } + + return &mdesc->desc; + +err_prep: + /* Put the descriptor back */ + spin_lock_irqsave(&mchan->lock, iflags); + list_add_tail(&mdesc->node, &mchan->free); + spin_unlock_irqrestore(&mchan->lock, iflags); + + return NULL; +} + +static int mpc_dma_device_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd, + unsigned long arg) +{ + struct mpc_dma_chan *mchan; + struct mpc_dma *mdma; + struct dma_slave_config *cfg; + unsigned long flags; + + mchan = dma_chan_to_mpc_dma_chan(chan); + switch (cmd) { + case DMA_TERMINATE_ALL: + /* Disable channel requests */ + mdma = dma_chan_to_mpc_dma(chan); + + spin_lock_irqsave(&mchan->lock, flags); + + out_8(&mdma->regs->dmacerq, chan->chan_id); + list_splice_tail_init(&mchan->prepared, &mchan->free); + list_splice_tail_init(&mchan->queued, &mchan->free); + list_splice_tail_init(&mchan->active, &mchan->free); + + spin_unlock_irqrestore(&mchan->lock, flags); + + return 0; + + case DMA_SLAVE_CONFIG: + /* + * Software constraints: + * - only transfers between a peripheral device and + * memory are supported; + * - only peripheral devices with 4-byte FIFO access register + * are supported; + * - minimal transfer chunk is 4 bytes and consequently + * source and destination addresses must be 4-byte aligned + * and transfer size must be aligned on (4 * maxburst) + * boundary; + * - during the transfer RAM address is being incremented by + * the size of minimal transfer chunk; + * - peripheral port's address is constant during the transfer. + */ + + cfg = (void *)arg; + + if (cfg->src_addr_width != DMA_SLAVE_BUSWIDTH_4_BYTES || + cfg->dst_addr_width != DMA_SLAVE_BUSWIDTH_4_BYTES || + !IS_ALIGNED(cfg->src_addr, 4) || + !IS_ALIGNED(cfg->dst_addr, 4)) { + return -EINVAL; + } + + spin_lock_irqsave(&mchan->lock, flags); + + mchan->src_per_paddr = cfg->src_addr; + mchan->src_tcd_nunits = cfg->src_maxburst; + mchan->dst_per_paddr = cfg->dst_addr; + mchan->dst_tcd_nunits = cfg->dst_maxburst; + + /* Apply defaults */ + if (mchan->src_tcd_nunits == 0) + mchan->src_tcd_nunits = 1; + if (mchan->dst_tcd_nunits == 0) + mchan->dst_tcd_nunits = 1; + + spin_unlock_irqrestore(&mchan->lock, flags); + + return 0; + + default: + /* Unknown command */ + break; + } + + return -ENXIO; +} + static int mpc_dma_probe(struct platform_device *op) { struct device_node *dn = op->dev.of_node; @@ -649,13 +889,15 @@ static int mpc_dma_probe(struct platform_device *op) mdma = devm_kzalloc(dev, sizeof(struct mpc_dma), GFP_KERNEL); if (!mdma) { dev_err(dev, "Memory exhausted!\n"); - return -ENOMEM; + retval = -ENOMEM; + goto err; } mdma->irq = irq_of_parse_and_map(dn, 0); if (mdma->irq == NO_IRQ) { dev_err(dev, "Error mapping IRQ!\n"); - return -EINVAL; + retval = -EINVAL; + goto err; } if (of_device_is_compatible(dn, "fsl,mpc8308-dma")) { @@ -663,14 +905,15 @@ static int mpc_dma_probe(struct platform_device *op) mdma->irq2 = irq_of_parse_and_map(dn, 1); if (mdma->irq2 == NO_IRQ) { dev_err(dev, "Error mapping IRQ!\n"); - return -EINVAL; + retval = -EINVAL; + goto err_dispose1; } } retval = of_address_to_resource(dn, 0, &res); if (retval) { dev_err(dev, "Error parsing memory region!\n"); - return retval; + goto err_dispose2; } regs_start = res.start; @@ -678,31 +921,34 @@ static int mpc_dma_probe(struct platform_device *op) if (!devm_request_mem_region(dev, regs_start, regs_size, DRV_NAME)) { dev_err(dev, "Error requesting memory region!\n"); - return -EBUSY; + retval = -EBUSY; + goto err_dispose2; } mdma->regs = devm_ioremap(dev, regs_start, regs_size); if (!mdma->regs) { dev_err(dev, "Error mapping memory region!\n"); - return -ENOMEM; + retval = -ENOMEM; + goto err_dispose2; } mdma->tcd = (struct mpc_dma_tcd *)((u8 *)(mdma->regs) + MPC_DMA_TCD_OFFSET); - retval = devm_request_irq(dev, mdma->irq, &mpc_dma_irq, 0, DRV_NAME, - mdma); + retval = request_irq(mdma->irq, &mpc_dma_irq, 0, DRV_NAME, mdma); if (retval) { dev_err(dev, "Error requesting IRQ!\n"); - return -EINVAL; + retval = -EINVAL; + goto err_dispose2; } if (mdma->is_mpc8308) { - retval = devm_request_irq(dev, mdma->irq2, &mpc_dma_irq, 0, - DRV_NAME, mdma); + retval = request_irq(mdma->irq2, &mpc_dma_irq, 0, + DRV_NAME, mdma); if (retval) { dev_err(dev, "Error requesting IRQ2!\n"); - return -EINVAL; + retval = -EINVAL; + goto err_free1; } } @@ -710,18 +956,21 @@ static int mpc_dma_probe(struct platform_device *op) dma = &mdma->dma; dma->dev = dev; - if (!mdma->is_mpc8308) - dma->chancnt = MPC_DMA_CHANNELS; + if (mdma->is_mpc8308) + dma->chancnt = MPC8308_DMACHAN_MAX; else - dma->chancnt = 16; /* MPC8308 DMA has only 16 channels */ + dma->chancnt = MPC512x_DMACHAN_MAX; dma->device_alloc_chan_resources = mpc_dma_alloc_chan_resources; dma->device_free_chan_resources = mpc_dma_free_chan_resources; dma->device_issue_pending = mpc_dma_issue_pending; dma->device_tx_status = mpc_dma_tx_status; dma->device_prep_dma_memcpy = mpc_dma_prep_memcpy; + dma->device_prep_slave_sg = mpc_dma_prep_slave_sg; + dma->device_control = mpc_dma_device_control; INIT_LIST_HEAD(&dma->channels); dma_cap_set(DMA_MEMCPY, dma->cap_mask); + dma_cap_set(DMA_SLAVE, dma->cap_mask); for (i = 0; i < dma->chancnt; i++) { mchan = &mdma->channels[i]; @@ -747,7 +996,19 @@ static int mpc_dma_probe(struct platform_device *op) * - Round-robin group arbitration, * - Round-robin channel arbitration. */ - if (!mdma->is_mpc8308) { + if (mdma->is_mpc8308) { + /* MPC8308 has 16 channels and lacks some registers */ + out_be32(&mdma->regs->dmacr, MPC_DMA_DMACR_ERCA); + + /* enable snooping */ + out_be32(&mdma->regs->dmagpor, MPC_DMA_DMAGPOR_SNOOP_ENABLE); + /* Disable error interrupts */ + out_be32(&mdma->regs->dmaeeil, 0); + + /* Clear interrupts status */ + out_be32(&mdma->regs->dmaintl, 0xFFFF); + out_be32(&mdma->regs->dmaerrl, 0xFFFF); + } else { out_be32(&mdma->regs->dmacr, MPC_DMA_DMACR_EDCG | MPC_DMA_DMACR_ERGA | MPC_DMA_DMACR_ERCA); @@ -768,28 +1029,35 @@ static int mpc_dma_probe(struct platform_device *op) /* Route interrupts to IPIC */ out_be32(&mdma->regs->dmaihsa, 0); out_be32(&mdma->regs->dmailsa, 0); - } else { - /* MPC8308 has 16 channels and lacks some registers */ - out_be32(&mdma->regs->dmacr, MPC_DMA_DMACR_ERCA); - - /* enable snooping */ - out_be32(&mdma->regs->dmagpor, MPC_DMA_DMAGPOR_SNOOP_ENABLE); - /* Disable error interrupts */ - out_be32(&mdma->regs->dmaeeil, 0); - - /* Clear interrupts status */ - out_be32(&mdma->regs->dmaintl, 0xFFFF); - out_be32(&mdma->regs->dmaerrl, 0xFFFF); } /* Register DMA engine */ dev_set_drvdata(dev, mdma); retval = dma_async_device_register(dma); - if (retval) { - devm_free_irq(dev, mdma->irq, mdma); - irq_dispose_mapping(mdma->irq); + if (retval) + goto err_free2; + + /* Register with OF helpers for DMA lookups (nonfatal) */ + if (dev->of_node) { + retval = of_dma_controller_register(dev->of_node, + of_dma_xlate_by_chan_id, mdma); + if (retval) + dev_warn(dev, "Could not register for OF lookup\n"); } + return 0; + +err_free2: + if (mdma->is_mpc8308) + free_irq(mdma->irq2, mdma); +err_free1: + free_irq(mdma->irq, mdma); +err_dispose2: + if (mdma->is_mpc8308) + irq_dispose_mapping(mdma->irq2); +err_dispose1: + irq_dispose_mapping(mdma->irq); +err: return retval; } @@ -798,8 +1066,14 @@ static int mpc_dma_remove(struct platform_device *op) struct device *dev = &op->dev; struct mpc_dma *mdma = dev_get_drvdata(dev); + if (dev->of_node) + of_dma_controller_free(dev->of_node); dma_async_device_unregister(&mdma->dma); - devm_free_irq(dev, mdma->irq, mdma); + if (mdma->is_mpc8308) { + free_irq(mdma->irq2, mdma); + irq_dispose_mapping(mdma->irq2); + } + free_irq(mdma->irq, mdma); irq_dispose_mapping(mdma->irq); return 0; @@ -807,6 +1081,7 @@ static int mpc_dma_remove(struct platform_device *op) static struct of_device_id mpc_dma_match[] = { { .compatible = "fsl,mpc5121-dma", }, + { .compatible = "fsl,mpc8308-dma", }, {}, }; diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c index 8eca90d..7938272 100644 --- a/drivers/dma/mv_xor.c +++ b/drivers/dma/mv_xor.c @@ -191,12 +191,10 @@ static void mv_set_mode(struct mv_xor_chan *chan, static void mv_chan_activate(struct mv_xor_chan *chan) { - u32 activation; - dev_dbg(mv_chan_to_devp(chan), " activate chan.\n"); - activation = readl_relaxed(XOR_ACTIVATION(chan)); - activation |= 0x1; - writel_relaxed(activation, XOR_ACTIVATION(chan)); + + /* writel ensures all descriptors are flushed before activation */ + writel(BIT(0), XOR_ACTIVATION(chan)); } static char mv_chan_is_busy(struct mv_xor_chan *chan) diff --git a/drivers/dma/mxs-dma.c b/drivers/dma/mxs-dma.c index ead4913..5ea6120 100644 --- a/drivers/dma/mxs-dma.c +++ b/drivers/dma/mxs-dma.c @@ -413,16 +413,14 @@ static int mxs_dma_alloc_chan_resources(struct dma_chan *chan) struct mxs_dma_engine *mxs_dma = mxs_chan->mxs_dma; int ret; - mxs_chan->ccw = dma_alloc_coherent(mxs_dma->dma_device.dev, - CCW_BLOCK_SIZE, &mxs_chan->ccw_phys, - GFP_KERNEL); + mxs_chan->ccw = dma_zalloc_coherent(mxs_dma->dma_device.dev, + CCW_BLOCK_SIZE, + &mxs_chan->ccw_phys, GFP_KERNEL); if (!mxs_chan->ccw) { ret = -ENOMEM; goto err_alloc; } - memset(mxs_chan->ccw, 0, CCW_BLOCK_SIZE); - if (mxs_chan->chan_irq != NO_IRQ) { ret = request_irq(mxs_chan->chan_irq, mxs_dma_int_handler, 0, "mxs-dma", mxs_dma); @@ -591,7 +589,7 @@ err_out: static struct dma_async_tx_descriptor *mxs_dma_prep_dma_cyclic( struct dma_chan *chan, dma_addr_t dma_addr, size_t buf_len, size_t period_len, enum dma_transfer_direction direction, - unsigned long flags, void *context) + unsigned long flags) { struct mxs_dma_chan *mxs_chan = to_mxs_dma_chan(chan); struct mxs_dma_engine *mxs_dma = mxs_chan->mxs_dma; diff --git a/drivers/dma/nbpfaxi.c b/drivers/dma/nbpfaxi.c new file mode 100644 index 0000000..5aeada5 --- /dev/null +++ b/drivers/dma/nbpfaxi.c @@ -0,0 +1,1517 @@ +/* + * Copyright (C) 2013-2014 Renesas Electronics Europe Ltd. + * Author: Guennadi Liakhovetski <g.liakhovetski@gmx.de> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + */ + +#include <linux/bitmap.h> +#include <linux/bitops.h> +#include <linux/clk.h> +#include <linux/dma-mapping.h> +#include <linux/dmaengine.h> +#include <linux/err.h> +#include <linux/interrupt.h> +#include <linux/io.h> +#include <linux/log2.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/of_device.h> +#include <linux/of_dma.h> +#include <linux/platform_device.h> +#include <linux/slab.h> + +#include <dt-bindings/dma/nbpfaxi.h> + +#include "dmaengine.h" + +#define NBPF_REG_CHAN_OFFSET 0 +#define NBPF_REG_CHAN_SIZE 0x40 + +/* Channel Current Transaction Byte register */ +#define NBPF_CHAN_CUR_TR_BYTE 0x20 + +/* Channel Status register */ +#define NBPF_CHAN_STAT 0x24 +#define NBPF_CHAN_STAT_EN 1 +#define NBPF_CHAN_STAT_TACT 4 +#define NBPF_CHAN_STAT_ERR 0x10 +#define NBPF_CHAN_STAT_END 0x20 +#define NBPF_CHAN_STAT_TC 0x40 +#define NBPF_CHAN_STAT_DER 0x400 + +/* Channel Control register */ +#define NBPF_CHAN_CTRL 0x28 +#define NBPF_CHAN_CTRL_SETEN 1 +#define NBPF_CHAN_CTRL_CLREN 2 +#define NBPF_CHAN_CTRL_STG 4 +#define NBPF_CHAN_CTRL_SWRST 8 +#define NBPF_CHAN_CTRL_CLRRQ 0x10 +#define NBPF_CHAN_CTRL_CLREND 0x20 +#define NBPF_CHAN_CTRL_CLRTC 0x40 +#define NBPF_CHAN_CTRL_SETSUS 0x100 +#define NBPF_CHAN_CTRL_CLRSUS 0x200 + +/* Channel Configuration register */ +#define NBPF_CHAN_CFG 0x2c +#define NBPF_CHAN_CFG_SEL 7 /* terminal SELect: 0..7 */ +#define NBPF_CHAN_CFG_REQD 8 /* REQuest Direction: DMAREQ is 0: input, 1: output */ +#define NBPF_CHAN_CFG_LOEN 0x10 /* LOw ENable: low DMA request line is: 0: inactive, 1: active */ +#define NBPF_CHAN_CFG_HIEN 0x20 /* HIgh ENable: high DMA request line is: 0: inactive, 1: active */ +#define NBPF_CHAN_CFG_LVL 0x40 /* LeVeL: DMA request line is sensed as 0: edge, 1: level */ +#define NBPF_CHAN_CFG_AM 0x700 /* ACK Mode: 0: Pulse mode, 1: Level mode, b'1x: Bus Cycle */ +#define NBPF_CHAN_CFG_SDS 0xf000 /* Source Data Size: 0: 8 bits,... , 7: 1024 bits */ +#define NBPF_CHAN_CFG_DDS 0xf0000 /* Destination Data Size: as above */ +#define NBPF_CHAN_CFG_SAD 0x100000 /* Source ADdress counting: 0: increment, 1: fixed */ +#define NBPF_CHAN_CFG_DAD 0x200000 /* Destination ADdress counting: 0: increment, 1: fixed */ +#define NBPF_CHAN_CFG_TM 0x400000 /* Transfer Mode: 0: single, 1: block TM */ +#define NBPF_CHAN_CFG_DEM 0x1000000 /* DMAEND interrupt Mask */ +#define NBPF_CHAN_CFG_TCM 0x2000000 /* DMATCO interrupt Mask */ +#define NBPF_CHAN_CFG_SBE 0x8000000 /* Sweep Buffer Enable */ +#define NBPF_CHAN_CFG_RSEL 0x10000000 /* RM: Register Set sELect */ +#define NBPF_CHAN_CFG_RSW 0x20000000 /* RM: Register Select sWitch */ +#define NBPF_CHAN_CFG_REN 0x40000000 /* RM: Register Set Enable */ +#define NBPF_CHAN_CFG_DMS 0x80000000 /* 0: register mode (RM), 1: link mode (LM) */ + +#define NBPF_CHAN_NXLA 0x38 +#define NBPF_CHAN_CRLA 0x3c + +/* Link Header field */ +#define NBPF_HEADER_LV 1 +#define NBPF_HEADER_LE 2 +#define NBPF_HEADER_WBD 4 +#define NBPF_HEADER_DIM 8 + +#define NBPF_CTRL 0x300 +#define NBPF_CTRL_PR 1 /* 0: fixed priority, 1: round robin */ +#define NBPF_CTRL_LVINT 2 /* DMAEND and DMAERR signalling: 0: pulse, 1: level */ + +#define NBPF_DSTAT_ER 0x314 +#define NBPF_DSTAT_END 0x318 + +#define NBPF_DMA_BUSWIDTHS \ + (BIT(DMA_SLAVE_BUSWIDTH_UNDEFINED) | \ + BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) | \ + BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) | \ + BIT(DMA_SLAVE_BUSWIDTH_4_BYTES) | \ + BIT(DMA_SLAVE_BUSWIDTH_8_BYTES)) + +struct nbpf_config { + int num_channels; + int buffer_size; +}; + +/* + * We've got 3 types of objects, used to describe DMA transfers: + * 1. high-level descriptor, containing a struct dma_async_tx_descriptor object + * in it, used to communicate with the user + * 2. hardware DMA link descriptors, that we pass to DMAC for DMA transfer + * queuing, these must be DMAable, using either the streaming DMA API or + * allocated from coherent memory - one per SG segment + * 3. one per SG segment descriptors, used to manage HW link descriptors from + * (2). They do not have to be DMAable. They can either be (a) allocated + * together with link descriptors as mixed (DMA / CPU) objects, or (b) + * separately. Even if allocated separately it would be best to link them + * to link descriptors once during channel resource allocation and always + * use them as a single object. + * Therefore for both cases (a) and (b) at run-time objects (2) and (3) shall be + * treated as a single SG segment descriptor. + */ + +struct nbpf_link_reg { + u32 header; + u32 src_addr; + u32 dst_addr; + u32 transaction_size; + u32 config; + u32 interval; + u32 extension; + u32 next; +} __packed; + +struct nbpf_device; +struct nbpf_channel; +struct nbpf_desc; + +struct nbpf_link_desc { + struct nbpf_link_reg *hwdesc; + dma_addr_t hwdesc_dma_addr; + struct nbpf_desc *desc; + struct list_head node; +}; + +/** + * struct nbpf_desc - DMA transfer descriptor + * @async_tx: dmaengine object + * @user_wait: waiting for a user ack + * @length: total transfer length + * @sg: list of hardware descriptors, represented by struct nbpf_link_desc + * @node: member in channel descriptor lists + */ +struct nbpf_desc { + struct dma_async_tx_descriptor async_tx; + bool user_wait; + size_t length; + struct nbpf_channel *chan; + struct list_head sg; + struct list_head node; +}; + +/* Take a wild guess: allocate 4 segments per descriptor */ +#define NBPF_SEGMENTS_PER_DESC 4 +#define NBPF_DESCS_PER_PAGE ((PAGE_SIZE - sizeof(struct list_head)) / \ + (sizeof(struct nbpf_desc) + \ + NBPF_SEGMENTS_PER_DESC * \ + (sizeof(struct nbpf_link_desc) + sizeof(struct nbpf_link_reg)))) +#define NBPF_SEGMENTS_PER_PAGE (NBPF_SEGMENTS_PER_DESC * NBPF_DESCS_PER_PAGE) + +struct nbpf_desc_page { + struct list_head node; + struct nbpf_desc desc[NBPF_DESCS_PER_PAGE]; + struct nbpf_link_desc ldesc[NBPF_SEGMENTS_PER_PAGE]; + struct nbpf_link_reg hwdesc[NBPF_SEGMENTS_PER_PAGE]; +}; + +/** + * struct nbpf_channel - one DMAC channel + * @dma_chan: standard dmaengine channel object + * @base: register address base + * @nbpf: DMAC + * @name: IRQ name + * @irq: IRQ number + * @slave_addr: address for slave DMA + * @slave_width:slave data size in bytes + * @slave_burst:maximum slave burst size in bytes + * @terminal: DMA terminal, assigned to this channel + * @dmarq_cfg: DMA request line configuration - high / low, edge / level for NBPF_CHAN_CFG + * @flags: configuration flags from DT + * @lock: protect descriptor lists + * @free_links: list of free link descriptors + * @free: list of free descriptors + * @queued: list of queued descriptors + * @active: list of descriptors, scheduled for processing + * @done: list of completed descriptors, waiting post-processing + * @desc_page: list of additionally allocated descriptor pages - if any + */ +struct nbpf_channel { + struct dma_chan dma_chan; + struct tasklet_struct tasklet; + void __iomem *base; + struct nbpf_device *nbpf; + char name[16]; + int irq; + dma_addr_t slave_src_addr; + size_t slave_src_width; + size_t slave_src_burst; + dma_addr_t slave_dst_addr; + size_t slave_dst_width; + size_t slave_dst_burst; + unsigned int terminal; + u32 dmarq_cfg; + unsigned long flags; + spinlock_t lock; + struct list_head free_links; + struct list_head free; + struct list_head queued; + struct list_head active; + struct list_head done; + struct list_head desc_page; + struct nbpf_desc *running; + bool paused; +}; + +struct nbpf_device { + struct dma_device dma_dev; + void __iomem *base; + struct clk *clk; + const struct nbpf_config *config; + struct nbpf_channel chan[]; +}; + +enum nbpf_model { + NBPF1B4, + NBPF1B8, + NBPF1B16, + NBPF4B4, + NBPF4B8, + NBPF4B16, + NBPF8B4, + NBPF8B8, + NBPF8B16, +}; + +static struct nbpf_config nbpf_cfg[] = { + [NBPF1B4] = { + .num_channels = 1, + .buffer_size = 4, + }, + [NBPF1B8] = { + .num_channels = 1, + .buffer_size = 8, + }, + [NBPF1B16] = { + .num_channels = 1, + .buffer_size = 16, + }, + [NBPF4B4] = { + .num_channels = 4, + .buffer_size = 4, + }, + [NBPF4B8] = { + .num_channels = 4, + .buffer_size = 8, + }, + [NBPF4B16] = { + .num_channels = 4, + .buffer_size = 16, + }, + [NBPF8B4] = { + .num_channels = 8, + .buffer_size = 4, + }, + [NBPF8B8] = { + .num_channels = 8, + .buffer_size = 8, + }, + [NBPF8B16] = { + .num_channels = 8, + .buffer_size = 16, + }, +}; + +#define nbpf_to_chan(d) container_of(d, struct nbpf_channel, dma_chan) + +/* + * dmaengine drivers seem to have a lot in common and instead of sharing more + * code, they reimplement those common algorithms independently. In this driver + * we try to separate the hardware-specific part from the (largely) generic + * part. This improves code readability and makes it possible in the future to + * reuse the generic code in form of a helper library. That generic code should + * be suitable for various DMA controllers, using transfer descriptors in RAM + * and pushing one SG list at a time to the DMA controller. + */ + +/* Hardware-specific part */ + +static inline u32 nbpf_chan_read(struct nbpf_channel *chan, + unsigned int offset) +{ + u32 data = ioread32(chan->base + offset); + dev_dbg(chan->dma_chan.device->dev, "%s(0x%p + 0x%x) = 0x%x\n", + __func__, chan->base, offset, data); + return data; +} + +static inline void nbpf_chan_write(struct nbpf_channel *chan, + unsigned int offset, u32 data) +{ + iowrite32(data, chan->base + offset); + dev_dbg(chan->dma_chan.device->dev, "%s(0x%p + 0x%x) = 0x%x\n", + __func__, chan->base, offset, data); +} + +static inline u32 nbpf_read(struct nbpf_device *nbpf, + unsigned int offset) +{ + u32 data = ioread32(nbpf->base + offset); + dev_dbg(nbpf->dma_dev.dev, "%s(0x%p + 0x%x) = 0x%x\n", + __func__, nbpf->base, offset, data); + return data; +} + +static inline void nbpf_write(struct nbpf_device *nbpf, + unsigned int offset, u32 data) +{ + iowrite32(data, nbpf->base + offset); + dev_dbg(nbpf->dma_dev.dev, "%s(0x%p + 0x%x) = 0x%x\n", + __func__, nbpf->base, offset, data); +} + +static void nbpf_chan_halt(struct nbpf_channel *chan) +{ + nbpf_chan_write(chan, NBPF_CHAN_CTRL, NBPF_CHAN_CTRL_CLREN); +} + +static bool nbpf_status_get(struct nbpf_channel *chan) +{ + u32 status = nbpf_read(chan->nbpf, NBPF_DSTAT_END); + + return status & BIT(chan - chan->nbpf->chan); +} + +static void nbpf_status_ack(struct nbpf_channel *chan) +{ + nbpf_chan_write(chan, NBPF_CHAN_CTRL, NBPF_CHAN_CTRL_CLREND); +} + +static u32 nbpf_error_get(struct nbpf_device *nbpf) +{ + return nbpf_read(nbpf, NBPF_DSTAT_ER); +} + +static struct nbpf_channel *nbpf_error_get_channel(struct nbpf_device *nbpf, u32 error) +{ + return nbpf->chan + __ffs(error); +} + +static void nbpf_error_clear(struct nbpf_channel *chan) +{ + u32 status; + int i; + + /* Stop the channel, make sure DMA has been aborted */ + nbpf_chan_halt(chan); + + for (i = 1000; i; i--) { + status = nbpf_chan_read(chan, NBPF_CHAN_STAT); + if (!(status & NBPF_CHAN_STAT_TACT)) + break; + cpu_relax(); + } + + if (!i) + dev_err(chan->dma_chan.device->dev, + "%s(): abort timeout, channel status 0x%x\n", __func__, status); + + nbpf_chan_write(chan, NBPF_CHAN_CTRL, NBPF_CHAN_CTRL_SWRST); +} + +static int nbpf_start(struct nbpf_desc *desc) +{ + struct nbpf_channel *chan = desc->chan; + struct nbpf_link_desc *ldesc = list_first_entry(&desc->sg, struct nbpf_link_desc, node); + + nbpf_chan_write(chan, NBPF_CHAN_NXLA, (u32)ldesc->hwdesc_dma_addr); + nbpf_chan_write(chan, NBPF_CHAN_CTRL, NBPF_CHAN_CTRL_SETEN | NBPF_CHAN_CTRL_CLRSUS); + chan->paused = false; + + /* Software trigger MEMCPY - only MEMCPY uses the block mode */ + if (ldesc->hwdesc->config & NBPF_CHAN_CFG_TM) + nbpf_chan_write(chan, NBPF_CHAN_CTRL, NBPF_CHAN_CTRL_STG); + + dev_dbg(chan->nbpf->dma_dev.dev, "%s(): next 0x%x, cur 0x%x\n", __func__, + nbpf_chan_read(chan, NBPF_CHAN_NXLA), nbpf_chan_read(chan, NBPF_CHAN_CRLA)); + + return 0; +} + +static void nbpf_chan_prepare(struct nbpf_channel *chan) +{ + chan->dmarq_cfg = (chan->flags & NBPF_SLAVE_RQ_HIGH ? NBPF_CHAN_CFG_HIEN : 0) | + (chan->flags & NBPF_SLAVE_RQ_LOW ? NBPF_CHAN_CFG_LOEN : 0) | + (chan->flags & NBPF_SLAVE_RQ_LEVEL ? + NBPF_CHAN_CFG_LVL | (NBPF_CHAN_CFG_AM & 0x200) : 0) | + chan->terminal; +} + +static void nbpf_chan_prepare_default(struct nbpf_channel *chan) +{ + /* Don't output DMAACK */ + chan->dmarq_cfg = NBPF_CHAN_CFG_AM & 0x400; + chan->terminal = 0; + chan->flags = 0; +} + +static void nbpf_chan_configure(struct nbpf_channel *chan) +{ + /* + * We assume, that only the link mode and DMA request line configuration + * have to be set in the configuration register manually. Dynamic + * per-transfer configuration will be loaded from transfer descriptors. + */ + nbpf_chan_write(chan, NBPF_CHAN_CFG, NBPF_CHAN_CFG_DMS | chan->dmarq_cfg); +} + +static u32 nbpf_xfer_ds(struct nbpf_device *nbpf, size_t size) +{ + /* Maximum supported bursts depend on the buffer size */ + return min_t(int, __ffs(size), ilog2(nbpf->config->buffer_size * 8)); +} + +static size_t nbpf_xfer_size(struct nbpf_device *nbpf, + enum dma_slave_buswidth width, u32 burst) +{ + size_t size; + + if (!burst) + burst = 1; + + switch (width) { + case DMA_SLAVE_BUSWIDTH_8_BYTES: + size = 8 * burst; + break; + + case DMA_SLAVE_BUSWIDTH_4_BYTES: + size = 4 * burst; + break; + + case DMA_SLAVE_BUSWIDTH_2_BYTES: + size = 2 * burst; + break; + + default: + pr_warn("%s(): invalid bus width %u\n", __func__, width); + case DMA_SLAVE_BUSWIDTH_1_BYTE: + size = burst; + } + + return nbpf_xfer_ds(nbpf, size); +} + +/* + * We need a way to recognise slaves, whose data is sent "raw" over the bus, + * i.e. it isn't known in advance how many bytes will be received. Therefore + * the slave driver has to provide a "large enough" buffer and either read the + * buffer, when it is full, or detect, that some data has arrived, then wait for + * a timeout, if no more data arrives - receive what's already there. We want to + * handle such slaves in a special way to allow an optimised mode for other + * users, for whom the amount of data is known in advance. So far there's no way + * to recognise such slaves. We use a data-width check to distinguish between + * the SD host and the PL011 UART. + */ + +static int nbpf_prep_one(struct nbpf_link_desc *ldesc, + enum dma_transfer_direction direction, + dma_addr_t src, dma_addr_t dst, size_t size, bool last) +{ + struct nbpf_link_reg *hwdesc = ldesc->hwdesc; + struct nbpf_desc *desc = ldesc->desc; + struct nbpf_channel *chan = desc->chan; + struct device *dev = chan->dma_chan.device->dev; + size_t mem_xfer, slave_xfer; + bool can_burst; + + hwdesc->header = NBPF_HEADER_WBD | NBPF_HEADER_LV | + (last ? NBPF_HEADER_LE : 0); + + hwdesc->src_addr = src; + hwdesc->dst_addr = dst; + hwdesc->transaction_size = size; + + /* + * set config: SAD, DAD, DDS, SDS, etc. + * Note on transfer sizes: the DMAC can perform unaligned DMA transfers, + * but it is important to have transaction size a multiple of both + * receiver and transmitter transfer sizes. It is also possible to use + * different RAM and device transfer sizes, and it does work well with + * some devices, e.g. with V08R07S01E SD host controllers, which can use + * 128 byte transfers. But this doesn't work with other devices, + * especially when the transaction size is unknown. This is the case, + * e.g. with serial drivers like amba-pl011.c. For reception it sets up + * the transaction size of 4K and if fewer bytes are received, it + * pauses DMA and reads out data received via DMA as well as those left + * in the Rx FIFO. For this to work with the RAM side using burst + * transfers we enable the SBE bit and terminate the transfer in our + * DMA_PAUSE handler. + */ + mem_xfer = nbpf_xfer_ds(chan->nbpf, size); + + switch (direction) { + case DMA_DEV_TO_MEM: + can_burst = chan->slave_src_width >= 3; + slave_xfer = min(mem_xfer, can_burst ? + chan->slave_src_burst : chan->slave_src_width); + /* + * Is the slave narrower than 64 bits, i.e. isn't using the full + * bus width and cannot use bursts? + */ + if (mem_xfer > chan->slave_src_burst && !can_burst) + mem_xfer = chan->slave_src_burst; + /* Device-to-RAM DMA is unreliable without REQD set */ + hwdesc->config = NBPF_CHAN_CFG_SAD | (NBPF_CHAN_CFG_DDS & (mem_xfer << 16)) | + (NBPF_CHAN_CFG_SDS & (slave_xfer << 12)) | NBPF_CHAN_CFG_REQD | + NBPF_CHAN_CFG_SBE; + break; + + case DMA_MEM_TO_DEV: + slave_xfer = min(mem_xfer, chan->slave_dst_width >= 3 ? + chan->slave_dst_burst : chan->slave_dst_width); + hwdesc->config = NBPF_CHAN_CFG_DAD | (NBPF_CHAN_CFG_SDS & (mem_xfer << 12)) | + (NBPF_CHAN_CFG_DDS & (slave_xfer << 16)) | NBPF_CHAN_CFG_REQD; + break; + + case DMA_MEM_TO_MEM: + hwdesc->config = NBPF_CHAN_CFG_TCM | NBPF_CHAN_CFG_TM | + (NBPF_CHAN_CFG_SDS & (mem_xfer << 12)) | + (NBPF_CHAN_CFG_DDS & (mem_xfer << 16)); + break; + + default: + return -EINVAL; + } + + hwdesc->config |= chan->dmarq_cfg | (last ? 0 : NBPF_CHAN_CFG_DEM) | + NBPF_CHAN_CFG_DMS; + + dev_dbg(dev, "%s(): desc @ %pad: hdr 0x%x, cfg 0x%x, %zu @ %pad -> %pad\n", + __func__, &ldesc->hwdesc_dma_addr, hwdesc->header, + hwdesc->config, size, &src, &dst); + + dma_sync_single_for_device(dev, ldesc->hwdesc_dma_addr, sizeof(*hwdesc), + DMA_TO_DEVICE); + + return 0; +} + +static size_t nbpf_bytes_left(struct nbpf_channel *chan) +{ + return nbpf_chan_read(chan, NBPF_CHAN_CUR_TR_BYTE); +} + +static void nbpf_configure(struct nbpf_device *nbpf) +{ + nbpf_write(nbpf, NBPF_CTRL, NBPF_CTRL_LVINT); +} + +static void nbpf_pause(struct nbpf_channel *chan) +{ + nbpf_chan_write(chan, NBPF_CHAN_CTRL, NBPF_CHAN_CTRL_SETSUS); + /* See comment in nbpf_prep_one() */ + nbpf_chan_write(chan, NBPF_CHAN_CTRL, NBPF_CHAN_CTRL_CLREN); +} + +/* Generic part */ + +/* DMA ENGINE functions */ +static void nbpf_issue_pending(struct dma_chan *dchan) +{ + struct nbpf_channel *chan = nbpf_to_chan(dchan); + unsigned long flags; + + dev_dbg(dchan->device->dev, "Entry %s()\n", __func__); + + spin_lock_irqsave(&chan->lock, flags); + if (list_empty(&chan->queued)) + goto unlock; + + list_splice_tail_init(&chan->queued, &chan->active); + + if (!chan->running) { + struct nbpf_desc *desc = list_first_entry(&chan->active, + struct nbpf_desc, node); + if (!nbpf_start(desc)) + chan->running = desc; + } + +unlock: + spin_unlock_irqrestore(&chan->lock, flags); +} + +static enum dma_status nbpf_tx_status(struct dma_chan *dchan, + dma_cookie_t cookie, struct dma_tx_state *state) +{ + struct nbpf_channel *chan = nbpf_to_chan(dchan); + enum dma_status status = dma_cookie_status(dchan, cookie, state); + + if (state) { + dma_cookie_t running; + unsigned long flags; + + spin_lock_irqsave(&chan->lock, flags); + running = chan->running ? chan->running->async_tx.cookie : -EINVAL; + + if (cookie == running) { + state->residue = nbpf_bytes_left(chan); + dev_dbg(dchan->device->dev, "%s(): residue %u\n", __func__, + state->residue); + } else if (status == DMA_IN_PROGRESS) { + struct nbpf_desc *desc; + bool found = false; + + list_for_each_entry(desc, &chan->active, node) + if (desc->async_tx.cookie == cookie) { + found = true; + break; + } + + if (!found) + list_for_each_entry(desc, &chan->queued, node) + if (desc->async_tx.cookie == cookie) { + found = true; + break; + + } + + state->residue = found ? desc->length : 0; + } + + spin_unlock_irqrestore(&chan->lock, flags); + } + + if (chan->paused) + status = DMA_PAUSED; + + return status; +} + +static dma_cookie_t nbpf_tx_submit(struct dma_async_tx_descriptor *tx) +{ + struct nbpf_desc *desc = container_of(tx, struct nbpf_desc, async_tx); + struct nbpf_channel *chan = desc->chan; + unsigned long flags; + dma_cookie_t cookie; + + spin_lock_irqsave(&chan->lock, flags); + cookie = dma_cookie_assign(tx); + list_add_tail(&desc->node, &chan->queued); + spin_unlock_irqrestore(&chan->lock, flags); + + dev_dbg(chan->dma_chan.device->dev, "Entry %s(%d)\n", __func__, cookie); + + return cookie; +} + +static int nbpf_desc_page_alloc(struct nbpf_channel *chan) +{ + struct dma_chan *dchan = &chan->dma_chan; + struct nbpf_desc_page *dpage = (void *)get_zeroed_page(GFP_KERNEL | GFP_DMA); + struct nbpf_link_desc *ldesc; + struct nbpf_link_reg *hwdesc; + struct nbpf_desc *desc; + LIST_HEAD(head); + LIST_HEAD(lhead); + int i; + struct device *dev = dchan->device->dev; + + if (!dpage) + return -ENOMEM; + + dev_dbg(dev, "%s(): alloc %lu descriptors, %lu segments, total alloc %zu\n", + __func__, NBPF_DESCS_PER_PAGE, NBPF_SEGMENTS_PER_PAGE, sizeof(*dpage)); + + for (i = 0, ldesc = dpage->ldesc, hwdesc = dpage->hwdesc; + i < ARRAY_SIZE(dpage->ldesc); + i++, ldesc++, hwdesc++) { + ldesc->hwdesc = hwdesc; + list_add_tail(&ldesc->node, &lhead); + ldesc->hwdesc_dma_addr = dma_map_single(dchan->device->dev, + hwdesc, sizeof(*hwdesc), DMA_TO_DEVICE); + + dev_dbg(dev, "%s(): mapped 0x%p to %pad\n", __func__, + hwdesc, &ldesc->hwdesc_dma_addr); + } + + for (i = 0, desc = dpage->desc; + i < ARRAY_SIZE(dpage->desc); + i++, desc++) { + dma_async_tx_descriptor_init(&desc->async_tx, dchan); + desc->async_tx.tx_submit = nbpf_tx_submit; + desc->chan = chan; + INIT_LIST_HEAD(&desc->sg); + list_add_tail(&desc->node, &head); + } + + /* + * This function cannot be called from interrupt context, so, no need to + * save flags + */ + spin_lock_irq(&chan->lock); + list_splice_tail(&lhead, &chan->free_links); + list_splice_tail(&head, &chan->free); + list_add(&dpage->node, &chan->desc_page); + spin_unlock_irq(&chan->lock); + + return ARRAY_SIZE(dpage->desc); +} + +static void nbpf_desc_put(struct nbpf_desc *desc) +{ + struct nbpf_channel *chan = desc->chan; + struct nbpf_link_desc *ldesc, *tmp; + unsigned long flags; + + spin_lock_irqsave(&chan->lock, flags); + list_for_each_entry_safe(ldesc, tmp, &desc->sg, node) + list_move(&ldesc->node, &chan->free_links); + + list_add(&desc->node, &chan->free); + spin_unlock_irqrestore(&chan->lock, flags); +} + +static void nbpf_scan_acked(struct nbpf_channel *chan) +{ + struct nbpf_desc *desc, *tmp; + unsigned long flags; + LIST_HEAD(head); + + spin_lock_irqsave(&chan->lock, flags); + list_for_each_entry_safe(desc, tmp, &chan->done, node) + if (async_tx_test_ack(&desc->async_tx) && desc->user_wait) { + list_move(&desc->node, &head); + desc->user_wait = false; + } + spin_unlock_irqrestore(&chan->lock, flags); + + list_for_each_entry_safe(desc, tmp, &head, node) { + list_del(&desc->node); + nbpf_desc_put(desc); + } +} + +/* + * We have to allocate descriptors with the channel lock dropped. This means, + * before we re-acquire the lock buffers can be taken already, so we have to + * re-check after re-acquiring the lock and possibly retry, if buffers are gone + * again. + */ +static struct nbpf_desc *nbpf_desc_get(struct nbpf_channel *chan, size_t len) +{ + struct nbpf_desc *desc = NULL; + struct nbpf_link_desc *ldesc, *prev = NULL; + + nbpf_scan_acked(chan); + + spin_lock_irq(&chan->lock); + + do { + int i = 0, ret; + + if (list_empty(&chan->free)) { + /* No more free descriptors */ + spin_unlock_irq(&chan->lock); + ret = nbpf_desc_page_alloc(chan); + if (ret < 0) + return NULL; + spin_lock_irq(&chan->lock); + continue; + } + desc = list_first_entry(&chan->free, struct nbpf_desc, node); + list_del(&desc->node); + + do { + if (list_empty(&chan->free_links)) { + /* No more free link descriptors */ + spin_unlock_irq(&chan->lock); + ret = nbpf_desc_page_alloc(chan); + if (ret < 0) { + nbpf_desc_put(desc); + return NULL; + } + spin_lock_irq(&chan->lock); + continue; + } + + ldesc = list_first_entry(&chan->free_links, + struct nbpf_link_desc, node); + ldesc->desc = desc; + if (prev) + prev->hwdesc->next = (u32)ldesc->hwdesc_dma_addr; + + prev = ldesc; + list_move_tail(&ldesc->node, &desc->sg); + + i++; + } while (i < len); + } while (!desc); + + prev->hwdesc->next = 0; + + spin_unlock_irq(&chan->lock); + + return desc; +} + +static void nbpf_chan_idle(struct nbpf_channel *chan) +{ + struct nbpf_desc *desc, *tmp; + unsigned long flags; + LIST_HEAD(head); + + spin_lock_irqsave(&chan->lock, flags); + + list_splice_init(&chan->done, &head); + list_splice_init(&chan->active, &head); + list_splice_init(&chan->queued, &head); + + chan->running = NULL; + + spin_unlock_irqrestore(&chan->lock, flags); + + list_for_each_entry_safe(desc, tmp, &head, node) { + dev_dbg(chan->nbpf->dma_dev.dev, "%s(): force-free desc %p cookie %d\n", + __func__, desc, desc->async_tx.cookie); + list_del(&desc->node); + nbpf_desc_put(desc); + } +} + +static int nbpf_control(struct dma_chan *dchan, enum dma_ctrl_cmd cmd, + unsigned long arg) +{ + struct nbpf_channel *chan = nbpf_to_chan(dchan); + struct dma_slave_config *config; + + dev_dbg(dchan->device->dev, "Entry %s(%d)\n", __func__, cmd); + + switch (cmd) { + case DMA_TERMINATE_ALL: + dev_dbg(dchan->device->dev, "Terminating\n"); + nbpf_chan_halt(chan); + nbpf_chan_idle(chan); + break; + + case DMA_SLAVE_CONFIG: + if (!arg) + return -EINVAL; + config = (struct dma_slave_config *)arg; + + /* + * We could check config->slave_id to match chan->terminal here, + * but with DT they would be coming from the same source, so + * such a check would be superflous + */ + + chan->slave_dst_addr = config->dst_addr; + chan->slave_dst_width = nbpf_xfer_size(chan->nbpf, + config->dst_addr_width, 1); + chan->slave_dst_burst = nbpf_xfer_size(chan->nbpf, + config->dst_addr_width, + config->dst_maxburst); + chan->slave_src_addr = config->src_addr; + chan->slave_src_width = nbpf_xfer_size(chan->nbpf, + config->src_addr_width, 1); + chan->slave_src_burst = nbpf_xfer_size(chan->nbpf, + config->src_addr_width, + config->src_maxburst); + break; + + case DMA_PAUSE: + chan->paused = true; + nbpf_pause(chan); + break; + + default: + return -ENXIO; + } + + return 0; +} + +static struct dma_async_tx_descriptor *nbpf_prep_sg(struct nbpf_channel *chan, + struct scatterlist *src_sg, struct scatterlist *dst_sg, + size_t len, enum dma_transfer_direction direction, + unsigned long flags) +{ + struct nbpf_link_desc *ldesc; + struct scatterlist *mem_sg; + struct nbpf_desc *desc; + bool inc_src, inc_dst; + size_t data_len = 0; + int i = 0; + + switch (direction) { + case DMA_DEV_TO_MEM: + mem_sg = dst_sg; + inc_src = false; + inc_dst = true; + break; + + case DMA_MEM_TO_DEV: + mem_sg = src_sg; + inc_src = true; + inc_dst = false; + break; + + default: + case DMA_MEM_TO_MEM: + mem_sg = src_sg; + inc_src = true; + inc_dst = true; + } + + desc = nbpf_desc_get(chan, len); + if (!desc) + return NULL; + + desc->async_tx.flags = flags; + desc->async_tx.cookie = -EBUSY; + desc->user_wait = false; + + /* + * This is a private descriptor list, and we own the descriptor. No need + * to lock. + */ + list_for_each_entry(ldesc, &desc->sg, node) { + int ret = nbpf_prep_one(ldesc, direction, + sg_dma_address(src_sg), + sg_dma_address(dst_sg), + sg_dma_len(mem_sg), + i == len - 1); + if (ret < 0) { + nbpf_desc_put(desc); + return NULL; + } + data_len += sg_dma_len(mem_sg); + if (inc_src) + src_sg = sg_next(src_sg); + if (inc_dst) + dst_sg = sg_next(dst_sg); + mem_sg = direction == DMA_DEV_TO_MEM ? dst_sg : src_sg; + i++; + } + + desc->length = data_len; + + /* The user has to return the descriptor to us ASAP via .tx_submit() */ + return &desc->async_tx; +} + +static struct dma_async_tx_descriptor *nbpf_prep_memcpy( + struct dma_chan *dchan, dma_addr_t dst, dma_addr_t src, + size_t len, unsigned long flags) +{ + struct nbpf_channel *chan = nbpf_to_chan(dchan); + struct scatterlist dst_sg; + struct scatterlist src_sg; + + sg_init_table(&dst_sg, 1); + sg_init_table(&src_sg, 1); + + sg_dma_address(&dst_sg) = dst; + sg_dma_address(&src_sg) = src; + + sg_dma_len(&dst_sg) = len; + sg_dma_len(&src_sg) = len; + + dev_dbg(dchan->device->dev, "%s(): %zu @ %pad -> %pad\n", + __func__, len, &src, &dst); + + return nbpf_prep_sg(chan, &src_sg, &dst_sg, 1, + DMA_MEM_TO_MEM, flags); +} + +static struct dma_async_tx_descriptor *nbpf_prep_memcpy_sg( + struct dma_chan *dchan, + struct scatterlist *dst_sg, unsigned int dst_nents, + struct scatterlist *src_sg, unsigned int src_nents, + unsigned long flags) +{ + struct nbpf_channel *chan = nbpf_to_chan(dchan); + + if (dst_nents != src_nents) + return NULL; + + return nbpf_prep_sg(chan, src_sg, dst_sg, src_nents, + DMA_MEM_TO_MEM, flags); +} + +static struct dma_async_tx_descriptor *nbpf_prep_slave_sg( + struct dma_chan *dchan, struct scatterlist *sgl, unsigned int sg_len, + enum dma_transfer_direction direction, unsigned long flags, void *context) +{ + struct nbpf_channel *chan = nbpf_to_chan(dchan); + struct scatterlist slave_sg; + + dev_dbg(dchan->device->dev, "Entry %s()\n", __func__); + + sg_init_table(&slave_sg, 1); + + switch (direction) { + case DMA_MEM_TO_DEV: + sg_dma_address(&slave_sg) = chan->slave_dst_addr; + return nbpf_prep_sg(chan, sgl, &slave_sg, sg_len, + direction, flags); + + case DMA_DEV_TO_MEM: + sg_dma_address(&slave_sg) = chan->slave_src_addr; + return nbpf_prep_sg(chan, &slave_sg, sgl, sg_len, + direction, flags); + + default: + return NULL; + } +} + +static int nbpf_alloc_chan_resources(struct dma_chan *dchan) +{ + struct nbpf_channel *chan = nbpf_to_chan(dchan); + int ret; + + INIT_LIST_HEAD(&chan->free); + INIT_LIST_HEAD(&chan->free_links); + INIT_LIST_HEAD(&chan->queued); + INIT_LIST_HEAD(&chan->active); + INIT_LIST_HEAD(&chan->done); + + ret = nbpf_desc_page_alloc(chan); + if (ret < 0) + return ret; + + dev_dbg(dchan->device->dev, "Entry %s(): terminal %u\n", __func__, + chan->terminal); + + nbpf_chan_configure(chan); + + return ret; +} + +static void nbpf_free_chan_resources(struct dma_chan *dchan) +{ + struct nbpf_channel *chan = nbpf_to_chan(dchan); + struct nbpf_desc_page *dpage, *tmp; + + dev_dbg(dchan->device->dev, "Entry %s()\n", __func__); + + nbpf_chan_halt(chan); + nbpf_chan_idle(chan); + /* Clean up for if a channel is re-used for MEMCPY after slave DMA */ + nbpf_chan_prepare_default(chan); + + list_for_each_entry_safe(dpage, tmp, &chan->desc_page, node) { + struct nbpf_link_desc *ldesc; + int i; + list_del(&dpage->node); + for (i = 0, ldesc = dpage->ldesc; + i < ARRAY_SIZE(dpage->ldesc); + i++, ldesc++) + dma_unmap_single(dchan->device->dev, ldesc->hwdesc_dma_addr, + sizeof(*ldesc->hwdesc), DMA_TO_DEVICE); + free_page((unsigned long)dpage); + } +} + +static int nbpf_slave_caps(struct dma_chan *dchan, + struct dma_slave_caps *caps) +{ + caps->src_addr_widths = NBPF_DMA_BUSWIDTHS; + caps->dstn_addr_widths = NBPF_DMA_BUSWIDTHS; + caps->directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV); + caps->cmd_pause = false; + caps->cmd_terminate = true; + + return 0; +} + +static struct dma_chan *nbpf_of_xlate(struct of_phandle_args *dma_spec, + struct of_dma *ofdma) +{ + struct nbpf_device *nbpf = ofdma->of_dma_data; + struct dma_chan *dchan; + struct nbpf_channel *chan; + + if (dma_spec->args_count != 2) + return NULL; + + dchan = dma_get_any_slave_channel(&nbpf->dma_dev); + if (!dchan) + return NULL; + + dev_dbg(dchan->device->dev, "Entry %s(%s)\n", __func__, + dma_spec->np->name); + + chan = nbpf_to_chan(dchan); + + chan->terminal = dma_spec->args[0]; + chan->flags = dma_spec->args[1]; + + nbpf_chan_prepare(chan); + nbpf_chan_configure(chan); + + return dchan; +} + +static void nbpf_chan_tasklet(unsigned long data) +{ + struct nbpf_channel *chan = (struct nbpf_channel *)data; + struct nbpf_desc *desc, *tmp; + dma_async_tx_callback callback; + void *param; + + while (!list_empty(&chan->done)) { + bool found = false, must_put, recycling = false; + + spin_lock_irq(&chan->lock); + + list_for_each_entry_safe(desc, tmp, &chan->done, node) { + if (!desc->user_wait) { + /* Newly completed descriptor, have to process */ + found = true; + break; + } else if (async_tx_test_ack(&desc->async_tx)) { + /* + * This descriptor was waiting for a user ACK, + * it can be recycled now. + */ + list_del(&desc->node); + spin_unlock_irq(&chan->lock); + nbpf_desc_put(desc); + recycling = true; + break; + } + } + + if (recycling) + continue; + + if (!found) { + /* This can happen if TERMINATE_ALL has been called */ + spin_unlock_irq(&chan->lock); + break; + } + + dma_cookie_complete(&desc->async_tx); + + /* + * With released lock we cannot dereference desc, maybe it's + * still on the "done" list + */ + if (async_tx_test_ack(&desc->async_tx)) { + list_del(&desc->node); + must_put = true; + } else { + desc->user_wait = true; + must_put = false; + } + + callback = desc->async_tx.callback; + param = desc->async_tx.callback_param; + + /* ack and callback completed descriptor */ + spin_unlock_irq(&chan->lock); + + if (callback) + callback(param); + + if (must_put) + nbpf_desc_put(desc); + } +} + +static irqreturn_t nbpf_chan_irq(int irq, void *dev) +{ + struct nbpf_channel *chan = dev; + bool done = nbpf_status_get(chan); + struct nbpf_desc *desc; + irqreturn_t ret; + bool bh = false; + + if (!done) + return IRQ_NONE; + + nbpf_status_ack(chan); + + dev_dbg(&chan->dma_chan.dev->device, "%s()\n", __func__); + + spin_lock(&chan->lock); + desc = chan->running; + if (WARN_ON(!desc)) { + ret = IRQ_NONE; + goto unlock; + } else { + ret = IRQ_HANDLED; + bh = true; + } + + list_move_tail(&desc->node, &chan->done); + chan->running = NULL; + + if (!list_empty(&chan->active)) { + desc = list_first_entry(&chan->active, + struct nbpf_desc, node); + if (!nbpf_start(desc)) + chan->running = desc; + } + +unlock: + spin_unlock(&chan->lock); + + if (bh) + tasklet_schedule(&chan->tasklet); + + return ret; +} + +static irqreturn_t nbpf_err_irq(int irq, void *dev) +{ + struct nbpf_device *nbpf = dev; + u32 error = nbpf_error_get(nbpf); + + dev_warn(nbpf->dma_dev.dev, "DMA error IRQ %u\n", irq); + + if (!error) + return IRQ_NONE; + + do { + struct nbpf_channel *chan = nbpf_error_get_channel(nbpf, error); + /* On error: abort all queued transfers, no callback */ + nbpf_error_clear(chan); + nbpf_chan_idle(chan); + error = nbpf_error_get(nbpf); + } while (error); + + return IRQ_HANDLED; +} + +static int nbpf_chan_probe(struct nbpf_device *nbpf, int n) +{ + struct dma_device *dma_dev = &nbpf->dma_dev; + struct nbpf_channel *chan = nbpf->chan + n; + int ret; + + chan->nbpf = nbpf; + chan->base = nbpf->base + NBPF_REG_CHAN_OFFSET + NBPF_REG_CHAN_SIZE * n; + INIT_LIST_HEAD(&chan->desc_page); + spin_lock_init(&chan->lock); + chan->dma_chan.device = dma_dev; + dma_cookie_init(&chan->dma_chan); + nbpf_chan_prepare_default(chan); + + dev_dbg(dma_dev->dev, "%s(): channel %d: -> %p\n", __func__, n, chan->base); + + snprintf(chan->name, sizeof(chan->name), "nbpf %d", n); + + tasklet_init(&chan->tasklet, nbpf_chan_tasklet, (unsigned long)chan); + ret = devm_request_irq(dma_dev->dev, chan->irq, + nbpf_chan_irq, IRQF_SHARED, + chan->name, chan); + if (ret < 0) + return ret; + + /* Add the channel to DMA device channel list */ + list_add_tail(&chan->dma_chan.device_node, + &dma_dev->channels); + + return 0; +} + +static const struct of_device_id nbpf_match[] = { + {.compatible = "renesas,nbpfaxi64dmac1b4", .data = &nbpf_cfg[NBPF1B4]}, + {.compatible = "renesas,nbpfaxi64dmac1b8", .data = &nbpf_cfg[NBPF1B8]}, + {.compatible = "renesas,nbpfaxi64dmac1b16", .data = &nbpf_cfg[NBPF1B16]}, + {.compatible = "renesas,nbpfaxi64dmac4b4", .data = &nbpf_cfg[NBPF4B4]}, + {.compatible = "renesas,nbpfaxi64dmac4b8", .data = &nbpf_cfg[NBPF4B8]}, + {.compatible = "renesas,nbpfaxi64dmac4b16", .data = &nbpf_cfg[NBPF4B16]}, + {.compatible = "renesas,nbpfaxi64dmac8b4", .data = &nbpf_cfg[NBPF8B4]}, + {.compatible = "renesas,nbpfaxi64dmac8b8", .data = &nbpf_cfg[NBPF8B8]}, + {.compatible = "renesas,nbpfaxi64dmac8b16", .data = &nbpf_cfg[NBPF8B16]}, + {} +}; +MODULE_DEVICE_TABLE(of, nbpf_match); + +static int nbpf_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + const struct of_device_id *of_id = of_match_device(nbpf_match, dev); + struct device_node *np = dev->of_node; + struct nbpf_device *nbpf; + struct dma_device *dma_dev; + struct resource *iomem, *irq_res; + const struct nbpf_config *cfg; + int num_channels; + int ret, irq, eirq, i; + int irqbuf[9] /* maximum 8 channels + error IRQ */; + unsigned int irqs = 0; + + BUILD_BUG_ON(sizeof(struct nbpf_desc_page) > PAGE_SIZE); + + /* DT only */ + if (!np || !of_id || !of_id->data) + return -ENODEV; + + cfg = of_id->data; + num_channels = cfg->num_channels; + + nbpf = devm_kzalloc(dev, sizeof(*nbpf) + num_channels * + sizeof(nbpf->chan[0]), GFP_KERNEL); + if (!nbpf) { + dev_err(dev, "Memory allocation failed\n"); + return -ENOMEM; + } + dma_dev = &nbpf->dma_dev; + dma_dev->dev = dev; + + iomem = platform_get_resource(pdev, IORESOURCE_MEM, 0); + nbpf->base = devm_ioremap_resource(dev, iomem); + if (IS_ERR(nbpf->base)) + return PTR_ERR(nbpf->base); + + nbpf->clk = devm_clk_get(dev, NULL); + if (IS_ERR(nbpf->clk)) + return PTR_ERR(nbpf->clk); + + nbpf->config = cfg; + + for (i = 0; irqs < ARRAY_SIZE(irqbuf); i++) { + irq_res = platform_get_resource(pdev, IORESOURCE_IRQ, i); + if (!irq_res) + break; + + for (irq = irq_res->start; irq <= irq_res->end; + irq++, irqs++) + irqbuf[irqs] = irq; + } + + /* + * 3 IRQ resource schemes are supported: + * 1. 1 shared IRQ for error and all channels + * 2. 2 IRQs: one for error and one shared for all channels + * 3. 1 IRQ for error and an own IRQ for each channel + */ + if (irqs != 1 && irqs != 2 && irqs != num_channels + 1) + return -ENXIO; + + if (irqs == 1) { + eirq = irqbuf[0]; + + for (i = 0; i <= num_channels; i++) + nbpf->chan[i].irq = irqbuf[0]; + } else { + eirq = platform_get_irq_byname(pdev, "error"); + if (eirq < 0) + return eirq; + + if (irqs == num_channels + 1) { + struct nbpf_channel *chan; + + for (i = 0, chan = nbpf->chan; i <= num_channels; + i++, chan++) { + /* Skip the error IRQ */ + if (irqbuf[i] == eirq) + i++; + chan->irq = irqbuf[i]; + } + + if (chan != nbpf->chan + num_channels) + return -EINVAL; + } else { + /* 2 IRQs and more than one channel */ + if (irqbuf[0] == eirq) + irq = irqbuf[1]; + else + irq = irqbuf[0]; + + for (i = 0; i <= num_channels; i++) + nbpf->chan[i].irq = irq; + } + } + + ret = devm_request_irq(dev, eirq, nbpf_err_irq, + IRQF_SHARED, "dma error", nbpf); + if (ret < 0) + return ret; + + INIT_LIST_HEAD(&dma_dev->channels); + + /* Create DMA Channel */ + for (i = 0; i < num_channels; i++) { + ret = nbpf_chan_probe(nbpf, i); + if (ret < 0) + return ret; + } + + dma_cap_set(DMA_MEMCPY, dma_dev->cap_mask); + dma_cap_set(DMA_SLAVE, dma_dev->cap_mask); + dma_cap_set(DMA_PRIVATE, dma_dev->cap_mask); + dma_cap_set(DMA_SG, dma_dev->cap_mask); + + /* Common and MEMCPY operations */ + dma_dev->device_alloc_chan_resources + = nbpf_alloc_chan_resources; + dma_dev->device_free_chan_resources = nbpf_free_chan_resources; + dma_dev->device_prep_dma_sg = nbpf_prep_memcpy_sg; + dma_dev->device_prep_dma_memcpy = nbpf_prep_memcpy; + dma_dev->device_tx_status = nbpf_tx_status; + dma_dev->device_issue_pending = nbpf_issue_pending; + dma_dev->device_slave_caps = nbpf_slave_caps; + + /* + * If we drop support for unaligned MEMCPY buffer addresses and / or + * lengths by setting + * dma_dev->copy_align = 4; + * then we can set transfer length to 4 bytes in nbpf_prep_one() for + * DMA_MEM_TO_MEM + */ + + /* Compulsory for DMA_SLAVE fields */ + dma_dev->device_prep_slave_sg = nbpf_prep_slave_sg; + dma_dev->device_control = nbpf_control; + + platform_set_drvdata(pdev, nbpf); + + ret = clk_prepare_enable(nbpf->clk); + if (ret < 0) + return ret; + + nbpf_configure(nbpf); + + ret = dma_async_device_register(dma_dev); + if (ret < 0) + goto e_clk_off; + + ret = of_dma_controller_register(np, nbpf_of_xlate, nbpf); + if (ret < 0) + goto e_dma_dev_unreg; + + return 0; + +e_dma_dev_unreg: + dma_async_device_unregister(dma_dev); +e_clk_off: + clk_disable_unprepare(nbpf->clk); + + return ret; +} + +static int nbpf_remove(struct platform_device *pdev) +{ + struct nbpf_device *nbpf = platform_get_drvdata(pdev); + + of_dma_controller_free(pdev->dev.of_node); + dma_async_device_unregister(&nbpf->dma_dev); + clk_disable_unprepare(nbpf->clk); + + return 0; +} + +static struct platform_device_id nbpf_ids[] = { + {"nbpfaxi64dmac1b4", (kernel_ulong_t)&nbpf_cfg[NBPF1B4]}, + {"nbpfaxi64dmac1b8", (kernel_ulong_t)&nbpf_cfg[NBPF1B8]}, + {"nbpfaxi64dmac1b16", (kernel_ulong_t)&nbpf_cfg[NBPF1B16]}, + {"nbpfaxi64dmac4b4", (kernel_ulong_t)&nbpf_cfg[NBPF4B4]}, + {"nbpfaxi64dmac4b8", (kernel_ulong_t)&nbpf_cfg[NBPF4B8]}, + {"nbpfaxi64dmac4b16", (kernel_ulong_t)&nbpf_cfg[NBPF4B16]}, + {"nbpfaxi64dmac8b4", (kernel_ulong_t)&nbpf_cfg[NBPF8B4]}, + {"nbpfaxi64dmac8b8", (kernel_ulong_t)&nbpf_cfg[NBPF8B8]}, + {"nbpfaxi64dmac8b16", (kernel_ulong_t)&nbpf_cfg[NBPF8B16]}, + {}, +}; +MODULE_DEVICE_TABLE(platform, nbpf_ids); + +#ifdef CONFIG_PM_RUNTIME +static int nbpf_runtime_suspend(struct device *dev) +{ + struct nbpf_device *nbpf = platform_get_drvdata(to_platform_device(dev)); + clk_disable_unprepare(nbpf->clk); + return 0; +} + +static int nbpf_runtime_resume(struct device *dev) +{ + struct nbpf_device *nbpf = platform_get_drvdata(to_platform_device(dev)); + return clk_prepare_enable(nbpf->clk); +} +#endif + +static const struct dev_pm_ops nbpf_pm_ops = { + SET_RUNTIME_PM_OPS(nbpf_runtime_suspend, nbpf_runtime_resume, NULL) +}; + +static struct platform_driver nbpf_driver = { + .driver = { + .owner = THIS_MODULE, + .name = "dma-nbpf", + .of_match_table = nbpf_match, + .pm = &nbpf_pm_ops, + }, + .id_table = nbpf_ids, + .probe = nbpf_probe, + .remove = nbpf_remove, +}; + +module_platform_driver(nbpf_driver); + +MODULE_AUTHOR("Guennadi Liakhovetski <g.liakhovetski@gmx.de>"); +MODULE_DESCRIPTION("dmaengine driver for NBPFAXI64* DMACs"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/dma/of-dma.c b/drivers/dma/of-dma.c index e8fe9dc..d5fbeaa 100644 --- a/drivers/dma/of-dma.c +++ b/drivers/dma/of-dma.c @@ -218,3 +218,38 @@ struct dma_chan *of_dma_simple_xlate(struct of_phandle_args *dma_spec, &dma_spec->args[0]); } EXPORT_SYMBOL_GPL(of_dma_simple_xlate); + +/** + * of_dma_xlate_by_chan_id - Translate dt property to DMA channel by channel id + * @dma_spec: pointer to DMA specifier as found in the device tree + * @of_dma: pointer to DMA controller data + * + * This function can be used as the of xlate callback for DMA driver which wants + * to match the channel based on the channel id. When using this xlate function + * the #dma-cells propety of the DMA controller dt node needs to be set to 1. + * The data parameter of of_dma_controller_register must be a pointer to the + * dma_device struct the function should match upon. + * + * Returns pointer to appropriate dma channel on success or NULL on error. + */ +struct dma_chan *of_dma_xlate_by_chan_id(struct of_phandle_args *dma_spec, + struct of_dma *ofdma) +{ + struct dma_device *dev = ofdma->of_dma_data; + struct dma_chan *chan, *candidate = NULL; + + if (!dev || dma_spec->args_count != 1) + return NULL; + + list_for_each_entry(chan, &dev->channels, device_node) + if (chan->chan_id == dma_spec->args[0]) { + candidate = chan; + break; + } + + if (!candidate) + return NULL; + + return dma_get_slave_channel(candidate); +} +EXPORT_SYMBOL_GPL(of_dma_xlate_by_chan_id); diff --git a/drivers/dma/omap-dma.c b/drivers/dma/omap-dma.c index 362e7c4..bbea824 100644 --- a/drivers/dma/omap-dma.c +++ b/drivers/dma/omap-dma.c @@ -5,6 +5,7 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ +#include <linux/delay.h> #include <linux/dmaengine.h> #include <linux/dma-mapping.h> #include <linux/err.h> @@ -26,11 +27,21 @@ struct omap_dmadev { spinlock_t lock; struct tasklet_struct task; struct list_head pending; + void __iomem *base; + const struct omap_dma_reg *reg_map; + struct omap_system_dma_plat_info *plat; + bool legacy; + spinlock_t irq_lock; + uint32_t irq_enable_mask; + struct omap_chan *lch_map[32]; }; struct omap_chan { struct virt_dma_chan vc; struct list_head node; + void __iomem *channel_base; + const struct omap_dma_reg *reg_map; + uint32_t ccr; struct dma_slave_config cfg; unsigned dma_sig; @@ -54,19 +65,93 @@ struct omap_desc { dma_addr_t dev_addr; int16_t fi; /* for OMAP_DMA_SYNC_PACKET */ - uint8_t es; /* OMAP_DMA_DATA_TYPE_xxx */ - uint8_t sync_mode; /* OMAP_DMA_SYNC_xxx */ - uint8_t sync_type; /* OMAP_DMA_xxx_SYNC* */ - uint8_t periph_port; /* Peripheral port */ + uint8_t es; /* CSDP_DATA_TYPE_xxx */ + uint32_t ccr; /* CCR value */ + uint16_t clnk_ctrl; /* CLNK_CTRL value */ + uint16_t cicr; /* CICR value */ + uint32_t csdp; /* CSDP value */ unsigned sglen; struct omap_sg sg[0]; }; +enum { + CCR_FS = BIT(5), + CCR_READ_PRIORITY = BIT(6), + CCR_ENABLE = BIT(7), + CCR_AUTO_INIT = BIT(8), /* OMAP1 only */ + CCR_REPEAT = BIT(9), /* OMAP1 only */ + CCR_OMAP31_DISABLE = BIT(10), /* OMAP1 only */ + CCR_SUSPEND_SENSITIVE = BIT(8), /* OMAP2+ only */ + CCR_RD_ACTIVE = BIT(9), /* OMAP2+ only */ + CCR_WR_ACTIVE = BIT(10), /* OMAP2+ only */ + CCR_SRC_AMODE_CONSTANT = 0 << 12, + CCR_SRC_AMODE_POSTINC = 1 << 12, + CCR_SRC_AMODE_SGLIDX = 2 << 12, + CCR_SRC_AMODE_DBLIDX = 3 << 12, + CCR_DST_AMODE_CONSTANT = 0 << 14, + CCR_DST_AMODE_POSTINC = 1 << 14, + CCR_DST_AMODE_SGLIDX = 2 << 14, + CCR_DST_AMODE_DBLIDX = 3 << 14, + CCR_CONSTANT_FILL = BIT(16), + CCR_TRANSPARENT_COPY = BIT(17), + CCR_BS = BIT(18), + CCR_SUPERVISOR = BIT(22), + CCR_PREFETCH = BIT(23), + CCR_TRIGGER_SRC = BIT(24), + CCR_BUFFERING_DISABLE = BIT(25), + CCR_WRITE_PRIORITY = BIT(26), + CCR_SYNC_ELEMENT = 0, + CCR_SYNC_FRAME = CCR_FS, + CCR_SYNC_BLOCK = CCR_BS, + CCR_SYNC_PACKET = CCR_BS | CCR_FS, + + CSDP_DATA_TYPE_8 = 0, + CSDP_DATA_TYPE_16 = 1, + CSDP_DATA_TYPE_32 = 2, + CSDP_SRC_PORT_EMIFF = 0 << 2, /* OMAP1 only */ + CSDP_SRC_PORT_EMIFS = 1 << 2, /* OMAP1 only */ + CSDP_SRC_PORT_OCP_T1 = 2 << 2, /* OMAP1 only */ + CSDP_SRC_PORT_TIPB = 3 << 2, /* OMAP1 only */ + CSDP_SRC_PORT_OCP_T2 = 4 << 2, /* OMAP1 only */ + CSDP_SRC_PORT_MPUI = 5 << 2, /* OMAP1 only */ + CSDP_SRC_PACKED = BIT(6), + CSDP_SRC_BURST_1 = 0 << 7, + CSDP_SRC_BURST_16 = 1 << 7, + CSDP_SRC_BURST_32 = 2 << 7, + CSDP_SRC_BURST_64 = 3 << 7, + CSDP_DST_PORT_EMIFF = 0 << 9, /* OMAP1 only */ + CSDP_DST_PORT_EMIFS = 1 << 9, /* OMAP1 only */ + CSDP_DST_PORT_OCP_T1 = 2 << 9, /* OMAP1 only */ + CSDP_DST_PORT_TIPB = 3 << 9, /* OMAP1 only */ + CSDP_DST_PORT_OCP_T2 = 4 << 9, /* OMAP1 only */ + CSDP_DST_PORT_MPUI = 5 << 9, /* OMAP1 only */ + CSDP_DST_PACKED = BIT(13), + CSDP_DST_BURST_1 = 0 << 14, + CSDP_DST_BURST_16 = 1 << 14, + CSDP_DST_BURST_32 = 2 << 14, + CSDP_DST_BURST_64 = 3 << 14, + + CICR_TOUT_IE = BIT(0), /* OMAP1 only */ + CICR_DROP_IE = BIT(1), + CICR_HALF_IE = BIT(2), + CICR_FRAME_IE = BIT(3), + CICR_LAST_IE = BIT(4), + CICR_BLOCK_IE = BIT(5), + CICR_PKT_IE = BIT(7), /* OMAP2+ only */ + CICR_TRANS_ERR_IE = BIT(8), /* OMAP2+ only */ + CICR_SUPERVISOR_ERR_IE = BIT(10), /* OMAP2+ only */ + CICR_MISALIGNED_ERR_IE = BIT(11), /* OMAP2+ only */ + CICR_DRAIN_IE = BIT(12), /* OMAP2+ only */ + CICR_SUPER_BLOCK_IE = BIT(14), /* OMAP2+ only */ + + CLNK_CTRL_ENABLE_LNK = BIT(15), +}; + static const unsigned es_bytes[] = { - [OMAP_DMA_DATA_TYPE_S8] = 1, - [OMAP_DMA_DATA_TYPE_S16] = 2, - [OMAP_DMA_DATA_TYPE_S32] = 4, + [CSDP_DATA_TYPE_8] = 1, + [CSDP_DATA_TYPE_16] = 2, + [CSDP_DATA_TYPE_32] = 4, }; static struct of_dma_filter_info omap_dma_info = { @@ -93,28 +178,214 @@ static void omap_dma_desc_free(struct virt_dma_desc *vd) kfree(container_of(vd, struct omap_desc, vd)); } +static void omap_dma_write(uint32_t val, unsigned type, void __iomem *addr) +{ + switch (type) { + case OMAP_DMA_REG_16BIT: + writew_relaxed(val, addr); + break; + case OMAP_DMA_REG_2X16BIT: + writew_relaxed(val, addr); + writew_relaxed(val >> 16, addr + 2); + break; + case OMAP_DMA_REG_32BIT: + writel_relaxed(val, addr); + break; + default: + WARN_ON(1); + } +} + +static unsigned omap_dma_read(unsigned type, void __iomem *addr) +{ + unsigned val; + + switch (type) { + case OMAP_DMA_REG_16BIT: + val = readw_relaxed(addr); + break; + case OMAP_DMA_REG_2X16BIT: + val = readw_relaxed(addr); + val |= readw_relaxed(addr + 2) << 16; + break; + case OMAP_DMA_REG_32BIT: + val = readl_relaxed(addr); + break; + default: + WARN_ON(1); + val = 0; + } + + return val; +} + +static void omap_dma_glbl_write(struct omap_dmadev *od, unsigned reg, unsigned val) +{ + const struct omap_dma_reg *r = od->reg_map + reg; + + WARN_ON(r->stride); + + omap_dma_write(val, r->type, od->base + r->offset); +} + +static unsigned omap_dma_glbl_read(struct omap_dmadev *od, unsigned reg) +{ + const struct omap_dma_reg *r = od->reg_map + reg; + + WARN_ON(r->stride); + + return omap_dma_read(r->type, od->base + r->offset); +} + +static void omap_dma_chan_write(struct omap_chan *c, unsigned reg, unsigned val) +{ + const struct omap_dma_reg *r = c->reg_map + reg; + + omap_dma_write(val, r->type, c->channel_base + r->offset); +} + +static unsigned omap_dma_chan_read(struct omap_chan *c, unsigned reg) +{ + const struct omap_dma_reg *r = c->reg_map + reg; + + return omap_dma_read(r->type, c->channel_base + r->offset); +} + +static void omap_dma_clear_csr(struct omap_chan *c) +{ + if (dma_omap1()) + omap_dma_chan_read(c, CSR); + else + omap_dma_chan_write(c, CSR, ~0); +} + +static unsigned omap_dma_get_csr(struct omap_chan *c) +{ + unsigned val = omap_dma_chan_read(c, CSR); + + if (!dma_omap1()) + omap_dma_chan_write(c, CSR, val); + + return val; +} + +static void omap_dma_assign(struct omap_dmadev *od, struct omap_chan *c, + unsigned lch) +{ + c->channel_base = od->base + od->plat->channel_stride * lch; + + od->lch_map[lch] = c; +} + +static void omap_dma_start(struct omap_chan *c, struct omap_desc *d) +{ + struct omap_dmadev *od = to_omap_dma_dev(c->vc.chan.device); + + if (__dma_omap15xx(od->plat->dma_attr)) + omap_dma_chan_write(c, CPC, 0); + else + omap_dma_chan_write(c, CDAC, 0); + + omap_dma_clear_csr(c); + + /* Enable interrupts */ + omap_dma_chan_write(c, CICR, d->cicr); + + /* Enable channel */ + omap_dma_chan_write(c, CCR, d->ccr | CCR_ENABLE); +} + +static void omap_dma_stop(struct omap_chan *c) +{ + struct omap_dmadev *od = to_omap_dma_dev(c->vc.chan.device); + uint32_t val; + + /* disable irq */ + omap_dma_chan_write(c, CICR, 0); + + omap_dma_clear_csr(c); + + val = omap_dma_chan_read(c, CCR); + if (od->plat->errata & DMA_ERRATA_i541 && val & CCR_TRIGGER_SRC) { + uint32_t sysconfig; + unsigned i; + + sysconfig = omap_dma_glbl_read(od, OCP_SYSCONFIG); + val = sysconfig & ~DMA_SYSCONFIG_MIDLEMODE_MASK; + val |= DMA_SYSCONFIG_MIDLEMODE(DMA_IDLEMODE_NO_IDLE); + omap_dma_glbl_write(od, OCP_SYSCONFIG, val); + + val = omap_dma_chan_read(c, CCR); + val &= ~CCR_ENABLE; + omap_dma_chan_write(c, CCR, val); + + /* Wait for sDMA FIFO to drain */ + for (i = 0; ; i++) { + val = omap_dma_chan_read(c, CCR); + if (!(val & (CCR_RD_ACTIVE | CCR_WR_ACTIVE))) + break; + + if (i > 100) + break; + + udelay(5); + } + + if (val & (CCR_RD_ACTIVE | CCR_WR_ACTIVE)) + dev_err(c->vc.chan.device->dev, + "DMA drain did not complete on lch %d\n", + c->dma_ch); + + omap_dma_glbl_write(od, OCP_SYSCONFIG, sysconfig); + } else { + val &= ~CCR_ENABLE; + omap_dma_chan_write(c, CCR, val); + } + + mb(); + + if (!__dma_omap15xx(od->plat->dma_attr) && c->cyclic) { + val = omap_dma_chan_read(c, CLNK_CTRL); + + if (dma_omap1()) + val |= 1 << 14; /* set the STOP_LNK bit */ + else + val &= ~CLNK_CTRL_ENABLE_LNK; + + omap_dma_chan_write(c, CLNK_CTRL, val); + } +} + static void omap_dma_start_sg(struct omap_chan *c, struct omap_desc *d, unsigned idx) { struct omap_sg *sg = d->sg + idx; + unsigned cxsa, cxei, cxfi; - if (d->dir == DMA_DEV_TO_MEM) - omap_set_dma_dest_params(c->dma_ch, OMAP_DMA_PORT_EMIFF, - OMAP_DMA_AMODE_POST_INC, sg->addr, 0, 0); - else - omap_set_dma_src_params(c->dma_ch, OMAP_DMA_PORT_EMIFF, - OMAP_DMA_AMODE_POST_INC, sg->addr, 0, 0); + if (d->dir == DMA_DEV_TO_MEM) { + cxsa = CDSA; + cxei = CDEI; + cxfi = CDFI; + } else { + cxsa = CSSA; + cxei = CSEI; + cxfi = CSFI; + } - omap_set_dma_transfer_params(c->dma_ch, d->es, sg->en, sg->fn, - d->sync_mode, c->dma_sig, d->sync_type); + omap_dma_chan_write(c, cxsa, sg->addr); + omap_dma_chan_write(c, cxei, 0); + omap_dma_chan_write(c, cxfi, 0); + omap_dma_chan_write(c, CEN, sg->en); + omap_dma_chan_write(c, CFN, sg->fn); - omap_start_dma(c->dma_ch); + omap_dma_start(c, d); } static void omap_dma_start_desc(struct omap_chan *c) { struct virt_dma_desc *vd = vchan_next_desc(&c->vc); struct omap_desc *d; + unsigned cxsa, cxei, cxfi; if (!vd) { c->desc = NULL; @@ -126,12 +397,32 @@ static void omap_dma_start_desc(struct omap_chan *c) c->desc = d = to_omap_dma_desc(&vd->tx); c->sgidx = 0; - if (d->dir == DMA_DEV_TO_MEM) - omap_set_dma_src_params(c->dma_ch, d->periph_port, - OMAP_DMA_AMODE_CONSTANT, d->dev_addr, 0, d->fi); - else - omap_set_dma_dest_params(c->dma_ch, d->periph_port, - OMAP_DMA_AMODE_CONSTANT, d->dev_addr, 0, d->fi); + /* + * This provides the necessary barrier to ensure data held in + * DMA coherent memory is visible to the DMA engine prior to + * the transfer starting. + */ + mb(); + + omap_dma_chan_write(c, CCR, d->ccr); + if (dma_omap1()) + omap_dma_chan_write(c, CCR2, d->ccr >> 16); + + if (d->dir == DMA_DEV_TO_MEM) { + cxsa = CSSA; + cxei = CSEI; + cxfi = CSFI; + } else { + cxsa = CDSA; + cxei = CDEI; + cxfi = CDFI; + } + + omap_dma_chan_write(c, cxsa, d->dev_addr); + omap_dma_chan_write(c, cxei, 0); + omap_dma_chan_write(c, cxfi, d->fi); + omap_dma_chan_write(c, CSDP, d->csdp); + omap_dma_chan_write(c, CLNK_CTRL, d->clnk_ctrl); omap_dma_start_sg(c, d, 0); } @@ -186,24 +477,118 @@ static void omap_dma_sched(unsigned long data) } } +static irqreturn_t omap_dma_irq(int irq, void *devid) +{ + struct omap_dmadev *od = devid; + unsigned status, channel; + + spin_lock(&od->irq_lock); + + status = omap_dma_glbl_read(od, IRQSTATUS_L1); + status &= od->irq_enable_mask; + if (status == 0) { + spin_unlock(&od->irq_lock); + return IRQ_NONE; + } + + while ((channel = ffs(status)) != 0) { + unsigned mask, csr; + struct omap_chan *c; + + channel -= 1; + mask = BIT(channel); + status &= ~mask; + + c = od->lch_map[channel]; + if (c == NULL) { + /* This should never happen */ + dev_err(od->ddev.dev, "invalid channel %u\n", channel); + continue; + } + + csr = omap_dma_get_csr(c); + omap_dma_glbl_write(od, IRQSTATUS_L1, mask); + + omap_dma_callback(channel, csr, c); + } + + spin_unlock(&od->irq_lock); + + return IRQ_HANDLED; +} + static int omap_dma_alloc_chan_resources(struct dma_chan *chan) { + struct omap_dmadev *od = to_omap_dma_dev(chan->device); struct omap_chan *c = to_omap_dma_chan(chan); + int ret; + + if (od->legacy) { + 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); + } - dev_dbg(c->vc.chan.device->dev, "allocating channel for %u\n", c->dma_sig); + dev_dbg(od->ddev.dev, "allocating channel %u for %u\n", + c->dma_ch, c->dma_sig); - return omap_request_dma(c->dma_sig, "DMA engine", - omap_dma_callback, c, &c->dma_ch); + if (ret >= 0) { + omap_dma_assign(od, c, c->dma_ch); + + if (!od->legacy) { + unsigned val; + + spin_lock_irq(&od->irq_lock); + val = BIT(c->dma_ch); + omap_dma_glbl_write(od, IRQSTATUS_L1, val); + od->irq_enable_mask |= val; + omap_dma_glbl_write(od, IRQENABLE_L1, od->irq_enable_mask); + + val = omap_dma_glbl_read(od, IRQENABLE_L0); + val &= ~BIT(c->dma_ch); + omap_dma_glbl_write(od, IRQENABLE_L0, val); + spin_unlock_irq(&od->irq_lock); + } + } + + if (dma_omap1()) { + if (__dma_omap16xx(od->plat->dma_attr)) { + c->ccr = CCR_OMAP31_DISABLE; + /* Duplicate what plat-omap/dma.c does */ + c->ccr |= c->dma_ch + 1; + } else { + c->ccr = c->dma_sig & 0x1f; + } + } else { + c->ccr = c->dma_sig & 0x1f; + c->ccr |= (c->dma_sig & ~0x1f) << 14; + } + if (od->plat->errata & DMA_ERRATA_IFRAME_BUFFERING) + c->ccr |= CCR_BUFFERING_DISABLE; + + return ret; } static void omap_dma_free_chan_resources(struct dma_chan *chan) { + struct omap_dmadev *od = to_omap_dma_dev(chan->device); struct omap_chan *c = to_omap_dma_chan(chan); + if (!od->legacy) { + spin_lock_irq(&od->irq_lock); + od->irq_enable_mask &= ~BIT(c->dma_ch); + omap_dma_glbl_write(od, IRQENABLE_L1, od->irq_enable_mask); + spin_unlock_irq(&od->irq_lock); + } + + c->channel_base = NULL; + od->lch_map[c->dma_ch] = NULL; vchan_free_chan_resources(&c->vc); omap_free_dma(c->dma_ch); - dev_dbg(c->vc.chan.device->dev, "freeing channel for %u\n", c->dma_sig); + dev_dbg(od->ddev.dev, "freeing channel for %u\n", c->dma_sig); } static size_t omap_dma_sg_size(struct omap_sg *sg) @@ -239,6 +624,74 @@ static size_t omap_dma_desc_size_pos(struct omap_desc *d, dma_addr_t addr) return size; } +/* + * OMAP 3.2/3.3 erratum: sometimes 0 is returned if CSAC/CDAC is + * read before the DMA controller finished disabling the channel. + */ +static uint32_t omap_dma_chan_read_3_3(struct omap_chan *c, unsigned reg) +{ + struct omap_dmadev *od = to_omap_dma_dev(c->vc.chan.device); + uint32_t val; + + val = omap_dma_chan_read(c, reg); + if (val == 0 && od->plat->errata & DMA_ERRATA_3_3) + val = omap_dma_chan_read(c, reg); + + return val; +} + +static dma_addr_t omap_dma_get_src_pos(struct omap_chan *c) +{ + struct omap_dmadev *od = to_omap_dma_dev(c->vc.chan.device); + dma_addr_t addr, cdac; + + if (__dma_omap15xx(od->plat->dma_attr)) { + addr = omap_dma_chan_read(c, CPC); + } else { + addr = omap_dma_chan_read_3_3(c, CSAC); + cdac = omap_dma_chan_read_3_3(c, CDAC); + + /* + * CDAC == 0 indicates that the DMA transfer on the channel has + * not been started (no data has been transferred so far). + * Return the programmed source start address in this case. + */ + if (cdac == 0) + addr = omap_dma_chan_read(c, CSSA); + } + + if (dma_omap1()) + addr |= omap_dma_chan_read(c, CSSA) & 0xffff0000; + + return addr; +} + +static dma_addr_t omap_dma_get_dst_pos(struct omap_chan *c) +{ + struct omap_dmadev *od = to_omap_dma_dev(c->vc.chan.device); + dma_addr_t addr; + + if (__dma_omap15xx(od->plat->dma_attr)) { + addr = omap_dma_chan_read(c, CPC); + } else { + addr = omap_dma_chan_read_3_3(c, CDAC); + + /* + * CDAC == 0 indicates that the DMA transfer on the channel + * has not been started (no data has been transferred so + * far). Return the programmed destination start address in + * this case. + */ + if (addr == 0) + addr = omap_dma_chan_read(c, CDSA); + } + + if (dma_omap1()) + addr |= omap_dma_chan_read(c, CDSA) & 0xffff0000; + + return addr; +} + static enum dma_status omap_dma_tx_status(struct dma_chan *chan, dma_cookie_t cookie, struct dma_tx_state *txstate) { @@ -260,9 +713,9 @@ static enum dma_status omap_dma_tx_status(struct dma_chan *chan, dma_addr_t pos; if (d->dir == DMA_MEM_TO_DEV) - pos = omap_get_dma_src_pos(c->dma_ch); + pos = omap_dma_get_src_pos(c); else if (d->dir == DMA_DEV_TO_MEM) - pos = omap_get_dma_dst_pos(c->dma_ch); + pos = omap_dma_get_dst_pos(c); else pos = 0; @@ -304,24 +757,23 @@ static struct dma_async_tx_descriptor *omap_dma_prep_slave_sg( struct dma_chan *chan, struct scatterlist *sgl, unsigned sglen, enum dma_transfer_direction dir, unsigned long tx_flags, void *context) { + struct omap_dmadev *od = to_omap_dma_dev(chan->device); struct omap_chan *c = to_omap_dma_chan(chan); enum dma_slave_buswidth dev_width; struct scatterlist *sgent; struct omap_desc *d; dma_addr_t dev_addr; - unsigned i, j = 0, es, en, frame_bytes, sync_type; + unsigned i, j = 0, es, en, frame_bytes; u32 burst; if (dir == DMA_DEV_TO_MEM) { dev_addr = c->cfg.src_addr; dev_width = c->cfg.src_addr_width; burst = c->cfg.src_maxburst; - sync_type = OMAP_DMA_SRC_SYNC; } else if (dir == DMA_MEM_TO_DEV) { dev_addr = c->cfg.dst_addr; dev_width = c->cfg.dst_addr_width; burst = c->cfg.dst_maxburst; - sync_type = OMAP_DMA_DST_SYNC; } else { dev_err(chan->device->dev, "%s: bad direction?\n", __func__); return NULL; @@ -330,13 +782,13 @@ static struct dma_async_tx_descriptor *omap_dma_prep_slave_sg( /* Bus width translates to the element size (ES) */ switch (dev_width) { case DMA_SLAVE_BUSWIDTH_1_BYTE: - es = OMAP_DMA_DATA_TYPE_S8; + es = CSDP_DATA_TYPE_8; break; case DMA_SLAVE_BUSWIDTH_2_BYTES: - es = OMAP_DMA_DATA_TYPE_S16; + es = CSDP_DATA_TYPE_16; break; case DMA_SLAVE_BUSWIDTH_4_BYTES: - es = OMAP_DMA_DATA_TYPE_S32; + es = CSDP_DATA_TYPE_32; break; default: /* not reached */ return NULL; @@ -350,9 +802,31 @@ static struct dma_async_tx_descriptor *omap_dma_prep_slave_sg( d->dir = dir; d->dev_addr = dev_addr; d->es = es; - d->sync_mode = OMAP_DMA_SYNC_FRAME; - d->sync_type = sync_type; - d->periph_port = OMAP_DMA_PORT_TIPB; + + d->ccr = c->ccr | CCR_SYNC_FRAME; + if (dir == DMA_DEV_TO_MEM) + d->ccr |= CCR_DST_AMODE_POSTINC | CCR_SRC_AMODE_CONSTANT; + else + d->ccr |= CCR_DST_AMODE_CONSTANT | CCR_SRC_AMODE_POSTINC; + + d->cicr = CICR_DROP_IE | CICR_BLOCK_IE; + d->csdp = es; + + if (dma_omap1()) { + d->cicr |= CICR_TOUT_IE; + + if (dir == DMA_DEV_TO_MEM) + d->csdp |= CSDP_DST_PORT_EMIFF | CSDP_SRC_PORT_TIPB; + else + d->csdp |= CSDP_DST_PORT_TIPB | CSDP_SRC_PORT_EMIFF; + } else { + if (dir == DMA_DEV_TO_MEM) + d->ccr |= CCR_TRIGGER_SRC; + + d->cicr |= CICR_MISALIGNED_ERR_IE | CICR_TRANS_ERR_IE; + } + if (od->plat->errata & DMA_ERRATA_PARALLEL_CHANNELS) + d->clnk_ctrl = c->dma_ch; /* * Build our scatterlist entries: each contains the address, @@ -379,26 +853,24 @@ static struct dma_async_tx_descriptor *omap_dma_prep_slave_sg( static struct dma_async_tx_descriptor *omap_dma_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, - void *context) + size_t period_len, enum dma_transfer_direction dir, unsigned long flags) { + struct omap_dmadev *od = to_omap_dma_dev(chan->device); struct omap_chan *c = to_omap_dma_chan(chan); enum dma_slave_buswidth dev_width; struct omap_desc *d; dma_addr_t dev_addr; - unsigned es, sync_type; + unsigned es; u32 burst; if (dir == DMA_DEV_TO_MEM) { dev_addr = c->cfg.src_addr; dev_width = c->cfg.src_addr_width; burst = c->cfg.src_maxburst; - sync_type = OMAP_DMA_SRC_SYNC; } else if (dir == DMA_MEM_TO_DEV) { dev_addr = c->cfg.dst_addr; dev_width = c->cfg.dst_addr_width; burst = c->cfg.dst_maxburst; - sync_type = OMAP_DMA_DST_SYNC; } else { dev_err(chan->device->dev, "%s: bad direction?\n", __func__); return NULL; @@ -407,13 +879,13 @@ static struct dma_async_tx_descriptor *omap_dma_prep_dma_cyclic( /* Bus width translates to the element size (ES) */ switch (dev_width) { case DMA_SLAVE_BUSWIDTH_1_BYTE: - es = OMAP_DMA_DATA_TYPE_S8; + es = CSDP_DATA_TYPE_8; break; case DMA_SLAVE_BUSWIDTH_2_BYTES: - es = OMAP_DMA_DATA_TYPE_S16; + es = CSDP_DATA_TYPE_16; break; case DMA_SLAVE_BUSWIDTH_4_BYTES: - es = OMAP_DMA_DATA_TYPE_S32; + es = CSDP_DATA_TYPE_32; break; default: /* not reached */ return NULL; @@ -428,32 +900,51 @@ static struct dma_async_tx_descriptor *omap_dma_prep_dma_cyclic( d->dev_addr = dev_addr; d->fi = burst; d->es = es; - if (burst) - d->sync_mode = OMAP_DMA_SYNC_PACKET; - else - d->sync_mode = OMAP_DMA_SYNC_ELEMENT; - d->sync_type = sync_type; - d->periph_port = OMAP_DMA_PORT_MPUI; d->sg[0].addr = buf_addr; d->sg[0].en = period_len / es_bytes[es]; d->sg[0].fn = buf_len / period_len; d->sglen = 1; - if (!c->cyclic) { - c->cyclic = true; - omap_dma_link_lch(c->dma_ch, c->dma_ch); + d->ccr = c->ccr; + if (dir == DMA_DEV_TO_MEM) + d->ccr |= CCR_DST_AMODE_POSTINC | CCR_SRC_AMODE_CONSTANT; + else + d->ccr |= CCR_DST_AMODE_CONSTANT | CCR_SRC_AMODE_POSTINC; + + d->cicr = CICR_DROP_IE; + if (flags & DMA_PREP_INTERRUPT) + d->cicr |= CICR_FRAME_IE; - if (flags & DMA_PREP_INTERRUPT) - omap_enable_dma_irq(c->dma_ch, OMAP_DMA_FRAME_IRQ); + d->csdp = es; - omap_disable_dma_irq(c->dma_ch, OMAP_DMA_BLOCK_IRQ); - } + if (dma_omap1()) { + d->cicr |= CICR_TOUT_IE; + + if (dir == DMA_DEV_TO_MEM) + d->csdp |= CSDP_DST_PORT_EMIFF | CSDP_SRC_PORT_MPUI; + else + d->csdp |= CSDP_DST_PORT_MPUI | CSDP_SRC_PORT_EMIFF; + } else { + if (burst) + d->ccr |= CCR_SYNC_PACKET; + else + d->ccr |= CCR_SYNC_ELEMENT; - if (dma_omap2plus()) { - omap_set_dma_src_burst_mode(c->dma_ch, OMAP_DMA_DATA_BURST_16); - omap_set_dma_dest_burst_mode(c->dma_ch, OMAP_DMA_DATA_BURST_16); + if (dir == DMA_DEV_TO_MEM) + d->ccr |= CCR_TRIGGER_SRC; + + d->cicr |= CICR_MISALIGNED_ERR_IE | CICR_TRANS_ERR_IE; + + d->csdp |= CSDP_DST_BURST_64 | CSDP_SRC_BURST_64; } + if (__dma_omap15xx(od->plat->dma_attr)) + d->ccr |= CCR_AUTO_INIT | CCR_REPEAT; + else + d->clnk_ctrl = c->dma_ch | CLNK_CTRL_ENABLE_LNK; + + c->cyclic = true; + return vchan_tx_prep(&c->vc, &d->vd, flags); } @@ -483,20 +974,19 @@ static int omap_dma_terminate_all(struct omap_chan *c) /* * Stop DMA activity: we assume the callback will not be called - * after omap_stop_dma() returns (even if it does, it will see + * after omap_dma_stop() returns (even if it does, it will see * c->desc is NULL and exit.) */ if (c->desc) { c->desc = NULL; /* Avoid stopping the dma twice */ if (!c->paused) - omap_stop_dma(c->dma_ch); + omap_dma_stop(c); } if (c->cyclic) { c->cyclic = false; c->paused = false; - omap_dma_unlink_lch(c->dma_ch, c->dma_ch); } vchan_get_all_descriptors(&c->vc, &head); @@ -513,7 +1003,7 @@ static int omap_dma_pause(struct omap_chan *c) return -EINVAL; if (!c->paused) { - omap_stop_dma(c->dma_ch); + omap_dma_stop(c); c->paused = true; } @@ -527,7 +1017,12 @@ static int omap_dma_resume(struct omap_chan *c) return -EINVAL; if (c->paused) { - omap_start_dma(c->dma_ch); + mb(); + + /* Restore channel link register */ + omap_dma_chan_write(c, CLNK_CTRL, c->desc->clnk_ctrl); + + omap_dma_start(c, c->desc); c->paused = false; } @@ -573,6 +1068,7 @@ static int omap_dma_chan_init(struct omap_dmadev *od, int dma_sig) if (!c) return -ENOMEM; + c->reg_map = od->reg_map; c->dma_sig = dma_sig; c->vc.desc_free = omap_dma_desc_free; vchan_init(&c->vc, &od->ddev); @@ -594,18 +1090,46 @@ static void omap_dma_free(struct omap_dmadev *od) tasklet_kill(&c->vc.task); kfree(c); } - kfree(od); +} + +#define OMAP_DMA_BUSWIDTHS (BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) | \ + BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) | \ + BIT(DMA_SLAVE_BUSWIDTH_4_BYTES)) + +static int omap_dma_device_slave_caps(struct dma_chan *dchan, + struct dma_slave_caps *caps) +{ + caps->src_addr_widths = OMAP_DMA_BUSWIDTHS; + caps->dstn_addr_widths = OMAP_DMA_BUSWIDTHS; + caps->directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV); + caps->cmd_pause = true; + caps->cmd_terminate = true; + caps->residue_granularity = DMA_RESIDUE_GRANULARITY_BURST; + + return 0; } static int omap_dma_probe(struct platform_device *pdev) { struct omap_dmadev *od; - int rc, i; + struct resource *res; + int rc, i, irq; - od = kzalloc(sizeof(*od), GFP_KERNEL); + od = devm_kzalloc(&pdev->dev, sizeof(*od), GFP_KERNEL); if (!od) return -ENOMEM; + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + od->base = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(od->base)) + return PTR_ERR(od->base); + + od->plat = omap_get_plat_info(); + if (!od->plat) + return -EPROBE_DEFER; + + od->reg_map = od->plat->reg_map; + dma_cap_set(DMA_SLAVE, od->ddev.cap_mask); dma_cap_set(DMA_CYCLIC, od->ddev.cap_mask); od->ddev.device_alloc_chan_resources = omap_dma_alloc_chan_resources; @@ -615,10 +1139,12 @@ static int omap_dma_probe(struct platform_device *pdev) od->ddev.device_prep_slave_sg = omap_dma_prep_slave_sg; od->ddev.device_prep_dma_cyclic = omap_dma_prep_dma_cyclic; od->ddev.device_control = omap_dma_control; + od->ddev.device_slave_caps = omap_dma_device_slave_caps; od->ddev.dev = &pdev->dev; INIT_LIST_HEAD(&od->ddev.channels); INIT_LIST_HEAD(&od->pending); spin_lock_init(&od->lock); + spin_lock_init(&od->irq_lock); tasklet_init(&od->task, omap_dma_sched, (unsigned long)od); @@ -630,6 +1156,21 @@ static int omap_dma_probe(struct platform_device *pdev) } } + irq = platform_get_irq(pdev, 1); + if (irq <= 0) { + dev_info(&pdev->dev, "failed to get L1 IRQ: %d\n", irq); + od->legacy = true; + } else { + /* Disable all interrupts */ + od->irq_enable_mask = 0; + omap_dma_glbl_write(od, IRQENABLE_L1, 0); + + rc = devm_request_irq(&pdev->dev, irq, omap_dma_irq, + IRQF_SHARED, "omap-dma-engine", od); + if (rc) + return rc; + } + rc = dma_async_device_register(&od->ddev); if (rc) { pr_warn("OMAP-DMA: failed to register slave DMA engine device: %d\n", @@ -666,6 +1207,12 @@ static int omap_dma_remove(struct platform_device *pdev) of_dma_controller_free(pdev->dev.of_node); dma_async_device_unregister(&od->ddev); + + if (!od->legacy) { + /* Disable all interrupts */ + omap_dma_glbl_write(od, IRQENABLE_L0, 0); + } + omap_dma_free(od); return 0; diff --git a/drivers/dma/pch_dma.c b/drivers/dma/pch_dma.c index 61fdc54..9f9ca9f 100644 --- a/drivers/dma/pch_dma.c +++ b/drivers/dma/pch_dma.c @@ -21,6 +21,7 @@ #include <linux/dma-mapping.h> #include <linux/init.h> #include <linux/pci.h> +#include <linux/slab.h> #include <linux/interrupt.h> #include <linux/module.h> #include <linux/pch_dma.h> @@ -964,16 +965,16 @@ static void pch_dma_remove(struct pci_dev *pdev) if (pd) { dma_async_device_unregister(&pd->dma); + free_irq(pdev->irq, pd); + list_for_each_entry_safe(chan, _c, &pd->dma.channels, device_node) { pd_chan = to_pd_chan(chan); - tasklet_disable(&pd_chan->tasklet); tasklet_kill(&pd_chan->tasklet); } pci_pool_destroy(pd->pool); - free_irq(pdev->irq, pd); pci_iounmap(pdev, pd->membase); pci_release_regions(pdev); pci_disable_device(pdev); @@ -996,7 +997,7 @@ static void pch_dma_remove(struct pci_dev *pdev) #define PCI_DEVICE_ID_ML7831_DMA1_8CH 0x8810 #define PCI_DEVICE_ID_ML7831_DMA2_4CH 0x8815 -DEFINE_PCI_DEVICE_TABLE(pch_dma_id_table) = { +const struct pci_device_id pch_dma_id_table[] = { { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_EG20T_PCH_DMA_8CH), 8 }, { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_EG20T_PCH_DMA_4CH), 4 }, { PCI_VDEVICE(ROHM, PCI_DEVICE_ID_ML7213_DMA1_8CH), 8}, /* UART Video */ diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c index 73fa9b7..d5149aa 100644 --- a/drivers/dma/pl330.c +++ b/drivers/dma/pl330.c @@ -33,26 +33,15 @@ #define PL330_MAX_IRQS 32 #define PL330_MAX_PERI 32 -enum pl330_srccachectrl { - SCCTRL0, /* Noncacheable and nonbufferable */ - SCCTRL1, /* Bufferable only */ - SCCTRL2, /* Cacheable, but do not allocate */ - SCCTRL3, /* Cacheable and bufferable, but do not allocate */ - SINVALID1, - SINVALID2, - SCCTRL6, /* Cacheable write-through, allocate on reads only */ - SCCTRL7, /* Cacheable write-back, allocate on reads only */ -}; - -enum pl330_dstcachectrl { - DCCTRL0, /* Noncacheable and nonbufferable */ - DCCTRL1, /* Bufferable only */ - DCCTRL2, /* Cacheable, but do not allocate */ - DCCTRL3, /* Cacheable and bufferable, but do not allocate */ - DINVALID1, /* AWCACHE = 0x1000 */ - DINVALID2, - DCCTRL6, /* Cacheable write-through, allocate on writes only */ - DCCTRL7, /* Cacheable write-back, allocate on writes only */ +enum pl330_cachectrl { + CCTRL0, /* Noncacheable and nonbufferable */ + CCTRL1, /* Bufferable only */ + CCTRL2, /* Cacheable, but do not allocate */ + CCTRL3, /* Cacheable and bufferable, but do not allocate */ + INVALID1, /* AWCACHE = 0x1000 */ + INVALID2, + CCTRL6, /* Cacheable write-through, allocate on writes only */ + CCTRL7, /* Cacheable write-back, allocate on writes only */ }; enum pl330_byteswap { @@ -63,13 +52,6 @@ enum pl330_byteswap { SWAP_16, }; -enum pl330_reqtype { - MEMTOMEM, - MEMTODEV, - DEVTOMEM, - DEVTODEV, -}; - /* Register and Bit field Definitions */ #define DS 0x0 #define DS_ST_STOP 0x0 @@ -263,9 +245,6 @@ enum pl330_reqtype { */ #define MCODE_BUFF_PER_REQ 256 -/* If the _pl330_req is available to the client */ -#define IS_FREE(req) (*((u8 *)((req)->mc_cpu)) == CMD_DMAEND) - /* Use this _only_ to wait on transient states */ #define UNTIL(t, s) while (!(_state(t) & (s))) cpu_relax(); @@ -300,27 +279,6 @@ struct pl330_config { u32 irq_ns; }; -/* Handle to the DMAC provided to the PL330 core */ -struct pl330_info { - /* Owning device */ - struct device *dev; - /* Size of MicroCode buffers for each channel. */ - unsigned mcbufsz; - /* ioremap'ed address of PL330 registers. */ - void __iomem *base; - /* Client can freely use it. */ - void *client_data; - /* PL330 core data, Client must not touch it. */ - void *pl330_data; - /* Populated by the PL330 core driver during pl330_add */ - struct pl330_config pcfg; - /* - * If the DMAC has some reset mechanism, then the - * client may want to provide pointer to the method. - */ - void (*dmac_reset)(struct pl330_info *pi); -}; - /** * Request Configuration. * The PL330 core does not modify this and uses the last @@ -344,8 +302,8 @@ struct pl330_reqcfg { unsigned brst_len:5; unsigned brst_size:3; /* in power of 2 */ - enum pl330_dstcachectrl dcctl; - enum pl330_srccachectrl scctl; + enum pl330_cachectrl dcctl; + enum pl330_cachectrl scctl; enum pl330_byteswap swap; struct pl330_config *pcfg; }; @@ -359,11 +317,6 @@ struct pl330_xfer { u32 dst_addr; /* Size to xfer */ u32 bytes; - /* - * Pointer to next xfer in the list. - * The last xfer in the req must point to NULL. - */ - struct pl330_xfer *next; }; /* The xfer callbacks are made with one of these arguments. */ @@ -376,67 +329,6 @@ enum pl330_op_err { PL330_ERR_FAIL, }; -/* A request defining Scatter-Gather List ending with NULL xfer. */ -struct pl330_req { - enum pl330_reqtype rqtype; - /* Index of peripheral for the xfer. */ - unsigned peri:5; - /* Unique token for this xfer, set by the client. */ - void *token; - /* Callback to be called after xfer. */ - void (*xfer_cb)(void *token, enum pl330_op_err err); - /* If NULL, req will be done at last set parameters. */ - struct pl330_reqcfg *cfg; - /* Pointer to first xfer in the request. */ - struct pl330_xfer *x; - /* Hook to attach to DMAC's list of reqs with due callback */ - struct list_head rqd; -}; - -/* - * To know the status of the channel and DMAC, the client - * provides a pointer to this structure. The PL330 core - * fills it with current information. - */ -struct pl330_chanstatus { - /* - * If the DMAC engine halted due to some error, - * the client should remove-add DMAC. - */ - bool dmac_halted; - /* - * If channel is halted due to some error, - * the client should ABORT/FLUSH and START the channel. - */ - bool faulting; - /* Location of last load */ - u32 src_addr; - /* Location of last store */ - u32 dst_addr; - /* - * Pointer to the currently active req, NULL if channel is - * inactive, even though the requests may be present. - */ - struct pl330_req *top_req; - /* Pointer to req waiting second in the queue if any. */ - struct pl330_req *wait_req; -}; - -enum pl330_chan_op { - /* Start the channel */ - PL330_OP_START, - /* Abort the active xfer */ - PL330_OP_ABORT, - /* Stop xfer and flush queue */ - PL330_OP_FLUSH, -}; - -struct _xfer_spec { - u32 ccr; - struct pl330_req *r; - struct pl330_xfer *x; -}; - enum dmamov_dst { SAR = 0, CCR, @@ -454,12 +346,12 @@ enum pl330_cond { ALWAYS, }; +struct dma_pl330_desc; + struct _pl330_req { u32 mc_bus; void *mc_cpu; - /* Number of bytes taken to setup MC for the req */ - u32 mc_len; - struct pl330_req *r; + struct dma_pl330_desc *desc; }; /* ToBeDone for tasklet */ @@ -491,30 +383,6 @@ enum pl330_dmac_state { DYING, }; -/* A DMAC */ -struct pl330_dmac { - spinlock_t lock; - /* Holds list of reqs with due callbacks */ - struct list_head req_done; - /* Pointer to platform specific stuff */ - struct pl330_info *pinfo; - /* Maximum possible events/irqs */ - int events[32]; - /* BUS address of MicroCode buffer */ - dma_addr_t mcode_bus; - /* CPU address of MicroCode buffer */ - void *mcode_cpu; - /* List of all Channel threads */ - struct pl330_thread *channels; - /* Pointer to the MANAGER thread */ - struct pl330_thread *manager; - /* To handle bad news in interrupt */ - struct tasklet_struct tasks; - struct _pl330_tbd dmac_tbd; - /* State of DMAC operation */ - enum pl330_dmac_state state; -}; - enum desc_status { /* In the DMAC pool */ FREE, @@ -555,15 +423,16 @@ struct dma_pl330_chan { * As the parent, this DMAC also provides descriptors * to the channel. */ - struct dma_pl330_dmac *dmac; + struct pl330_dmac *dmac; /* To protect channel manipulation */ spinlock_t lock; - /* Token of a hardware channel thread of PL330 DMAC - * NULL if the channel is available to be acquired. + /* + * Hardware channel thread of PL330 DMAC. NULL if the channel is + * available. */ - void *pl330_chid; + struct pl330_thread *thread; /* For D-to-M and M-to-D channels */ int burst_sz; /* the peripheral fifo width */ @@ -574,9 +443,7 @@ struct dma_pl330_chan { bool cyclic; }; -struct dma_pl330_dmac { - struct pl330_info pif; - +struct pl330_dmac { /* DMA-Engine Device */ struct dma_device ddma; @@ -588,6 +455,32 @@ struct dma_pl330_dmac { /* To protect desc_pool manipulation */ spinlock_t pool_lock; + /* Size of MicroCode buffers for each channel. */ + unsigned mcbufsz; + /* ioremap'ed address of PL330 registers. */ + void __iomem *base; + /* Populated by the PL330 core driver during pl330_add */ + struct pl330_config pcfg; + + spinlock_t lock; + /* Maximum possible events/irqs */ + int events[32]; + /* BUS address of MicroCode buffer */ + dma_addr_t mcode_bus; + /* CPU address of MicroCode buffer */ + void *mcode_cpu; + /* List of all Channel threads */ + struct pl330_thread *channels; + /* Pointer to the MANAGER thread */ + struct pl330_thread *manager; + /* To handle bad news in interrupt */ + struct tasklet_struct tasks; + struct _pl330_tbd dmac_tbd; + /* State of DMAC operation */ + enum pl330_dmac_state state; + /* Holds list of reqs with due callbacks */ + struct list_head req_done; + /* Peripheral channels connected to this DMAC */ unsigned int num_peripherals; struct dma_pl330_chan *peripherals; /* keep at end */ @@ -604,49 +497,43 @@ struct dma_pl330_desc { struct pl330_xfer px; struct pl330_reqcfg rqcfg; - struct pl330_req req; enum desc_status status; /* The channel which currently holds this desc */ struct dma_pl330_chan *pchan; + + enum dma_transfer_direction rqtype; + /* Index of peripheral for the xfer. */ + unsigned peri:5; + /* Hook to attach to DMAC's list of reqs with due callback */ + struct list_head rqd; }; -static inline void _callback(struct pl330_req *r, enum pl330_op_err err) -{ - if (r && r->xfer_cb) - r->xfer_cb(r->token, err); -} +struct _xfer_spec { + u32 ccr; + struct dma_pl330_desc *desc; +}; static inline bool _queue_empty(struct pl330_thread *thrd) { - return (IS_FREE(&thrd->req[0]) && IS_FREE(&thrd->req[1])) - ? true : false; + return thrd->req[0].desc == NULL && thrd->req[1].desc == NULL; } static inline bool _queue_full(struct pl330_thread *thrd) { - return (IS_FREE(&thrd->req[0]) || IS_FREE(&thrd->req[1])) - ? false : true; + return thrd->req[0].desc != NULL && thrd->req[1].desc != NULL; } static inline bool is_manager(struct pl330_thread *thrd) { - struct pl330_dmac *pl330 = thrd->dmac; - - /* MANAGER is indexed at the end */ - if (thrd->id == pl330->pinfo->pcfg.num_chan) - return true; - else - return false; + return thrd->dmac->manager == thrd; } /* If manager of the thread is in Non-Secure mode */ static inline bool _manager_ns(struct pl330_thread *thrd) { - struct pl330_dmac *pl330 = thrd->dmac; - - return (pl330->pinfo->pcfg.mode & DMAC_MODE_NS) ? true : false; + return (thrd->dmac->pcfg.mode & DMAC_MODE_NS) ? true : false; } static inline u32 get_revision(u32 periph_id) @@ -1004,7 +891,7 @@ static inline u32 _emit_GO(unsigned dry_run, u8 buf[], /* Returns Time-Out */ static bool _until_dmac_idle(struct pl330_thread *thrd) { - void __iomem *regs = thrd->dmac->pinfo->base; + void __iomem *regs = thrd->dmac->base; unsigned long loops = msecs_to_loops(5); do { @@ -1024,7 +911,7 @@ static bool _until_dmac_idle(struct pl330_thread *thrd) static inline void _execute_DBGINSN(struct pl330_thread *thrd, u8 insn[], bool as_manager) { - void __iomem *regs = thrd->dmac->pinfo->base; + void __iomem *regs = thrd->dmac->base; u32 val; val = (insn[0] << 16) | (insn[1] << 24); @@ -1039,7 +926,7 @@ static inline void _execute_DBGINSN(struct pl330_thread *thrd, /* If timed out due to halted state-machine */ if (_until_dmac_idle(thrd)) { - dev_err(thrd->dmac->pinfo->dev, "DMAC halted!\n"); + dev_err(thrd->dmac->ddma.dev, "DMAC halted!\n"); return; } @@ -1047,25 +934,9 @@ static inline void _execute_DBGINSN(struct pl330_thread *thrd, writel(0, regs + DBGCMD); } -/* - * Mark a _pl330_req as free. - * We do it by writing DMAEND as the first instruction - * because no valid request is going to have DMAEND as - * its first instruction to execute. - */ -static void mark_free(struct pl330_thread *thrd, int idx) -{ - struct _pl330_req *req = &thrd->req[idx]; - - _emit_END(0, req->mc_cpu); - req->mc_len = 0; - - thrd->req_running = -1; -} - static inline u32 _state(struct pl330_thread *thrd) { - void __iomem *regs = thrd->dmac->pinfo->base; + void __iomem *regs = thrd->dmac->base; u32 val; if (is_manager(thrd)) @@ -1123,7 +994,7 @@ static inline u32 _state(struct pl330_thread *thrd) static void _stop(struct pl330_thread *thrd) { - void __iomem *regs = thrd->dmac->pinfo->base; + void __iomem *regs = thrd->dmac->base; u8 insn[6] = {0, 0, 0, 0, 0, 0}; if (_state(thrd) == PL330_STATE_FAULT_COMPLETING) @@ -1146,9 +1017,9 @@ static void _stop(struct pl330_thread *thrd) /* Start doing req 'idx' of thread 'thrd' */ static bool _trigger(struct pl330_thread *thrd) { - void __iomem *regs = thrd->dmac->pinfo->base; + void __iomem *regs = thrd->dmac->base; struct _pl330_req *req; - struct pl330_req *r; + struct dma_pl330_desc *desc; struct _arg_GO go; unsigned ns; u8 insn[6] = {0, 0, 0, 0, 0, 0}; @@ -1159,32 +1030,27 @@ static bool _trigger(struct pl330_thread *thrd) return true; idx = 1 - thrd->lstenq; - if (!IS_FREE(&thrd->req[idx])) + if (thrd->req[idx].desc != NULL) { req = &thrd->req[idx]; - else { + } else { idx = thrd->lstenq; - if (!IS_FREE(&thrd->req[idx])) + if (thrd->req[idx].desc != NULL) req = &thrd->req[idx]; else req = NULL; } /* Return if no request */ - if (!req || !req->r) + if (!req) return true; - r = req->r; + desc = req->desc; - if (r->cfg) - ns = r->cfg->nonsecure ? 1 : 0; - else if (readl(regs + CS(thrd->id)) & CS_CNS) - ns = 1; - else - ns = 0; + ns = desc->rqcfg.nonsecure ? 1 : 0; /* See 'Abort Sources' point-4 at Page 2-25 */ if (_manager_ns(thrd) && !ns) - dev_info(thrd->dmac->pinfo->dev, "%s:%d Recipe for ABORT!\n", + dev_info(thrd->dmac->ddma.dev, "%s:%d Recipe for ABORT!\n", __func__, __LINE__); go.chan = thrd->id; @@ -1240,7 +1106,7 @@ static inline int _ldst_memtomem(unsigned dry_run, u8 buf[], const struct _xfer_spec *pxs, int cyc) { int off = 0; - struct pl330_config *pcfg = pxs->r->cfg->pcfg; + struct pl330_config *pcfg = pxs->desc->rqcfg.pcfg; /* check lock-up free version */ if (get_revision(pcfg->periph_id) >= PERIPH_REV_R1P0) { @@ -1266,10 +1132,10 @@ static inline int _ldst_devtomem(unsigned dry_run, u8 buf[], int off = 0; while (cyc--) { - off += _emit_WFP(dry_run, &buf[off], SINGLE, pxs->r->peri); - off += _emit_LDP(dry_run, &buf[off], SINGLE, pxs->r->peri); + off += _emit_WFP(dry_run, &buf[off], SINGLE, pxs->desc->peri); + off += _emit_LDP(dry_run, &buf[off], SINGLE, pxs->desc->peri); off += _emit_ST(dry_run, &buf[off], ALWAYS); - off += _emit_FLUSHP(dry_run, &buf[off], pxs->r->peri); + off += _emit_FLUSHP(dry_run, &buf[off], pxs->desc->peri); } return off; @@ -1281,10 +1147,10 @@ static inline int _ldst_memtodev(unsigned dry_run, u8 buf[], int off = 0; while (cyc--) { - off += _emit_WFP(dry_run, &buf[off], SINGLE, pxs->r->peri); + off += _emit_WFP(dry_run, &buf[off], SINGLE, pxs->desc->peri); off += _emit_LD(dry_run, &buf[off], ALWAYS); - off += _emit_STP(dry_run, &buf[off], SINGLE, pxs->r->peri); - off += _emit_FLUSHP(dry_run, &buf[off], pxs->r->peri); + off += _emit_STP(dry_run, &buf[off], SINGLE, pxs->desc->peri); + off += _emit_FLUSHP(dry_run, &buf[off], pxs->desc->peri); } return off; @@ -1295,14 +1161,14 @@ static int _bursts(unsigned dry_run, u8 buf[], { int off = 0; - switch (pxs->r->rqtype) { - case MEMTODEV: + switch (pxs->desc->rqtype) { + case DMA_MEM_TO_DEV: off += _ldst_memtodev(dry_run, &buf[off], pxs, cyc); break; - case DEVTOMEM: + case DMA_DEV_TO_MEM: off += _ldst_devtomem(dry_run, &buf[off], pxs, cyc); break; - case MEMTOMEM: + case DMA_MEM_TO_MEM: off += _ldst_memtomem(dry_run, &buf[off], pxs, cyc); break; default: @@ -1395,7 +1261,7 @@ static inline int _loop(unsigned dry_run, u8 buf[], static inline int _setup_loops(unsigned dry_run, u8 buf[], const struct _xfer_spec *pxs) { - struct pl330_xfer *x = pxs->x; + struct pl330_xfer *x = &pxs->desc->px; u32 ccr = pxs->ccr; unsigned long c, bursts = BYTE_TO_BURST(x->bytes, ccr); int off = 0; @@ -1412,7 +1278,7 @@ static inline int _setup_loops(unsigned dry_run, u8 buf[], static inline int _setup_xfer(unsigned dry_run, u8 buf[], const struct _xfer_spec *pxs) { - struct pl330_xfer *x = pxs->x; + struct pl330_xfer *x = &pxs->desc->px; int off = 0; /* DMAMOV SAR, x->src_addr */ @@ -1443,17 +1309,12 @@ static int _setup_req(unsigned dry_run, struct pl330_thread *thrd, /* DMAMOV CCR, ccr */ off += _emit_MOV(dry_run, &buf[off], CCR, pxs->ccr); - x = pxs->r->x; - do { - /* Error if xfer length is not aligned at burst size */ - if (x->bytes % (BRST_SIZE(pxs->ccr) * BRST_LEN(pxs->ccr))) - return -EINVAL; - - pxs->x = x; - off += _setup_xfer(dry_run, &buf[off], pxs); + x = &pxs->desc->px; + /* Error if xfer length is not aligned at burst size */ + if (x->bytes % (BRST_SIZE(pxs->ccr) * BRST_LEN(pxs->ccr))) + return -EINVAL; - x = x->next; - } while (x); + off += _setup_xfer(dry_run, &buf[off], pxs); /* DMASEV peripheral/event */ off += _emit_SEV(dry_run, &buf[off], thrd->ev); @@ -1495,31 +1356,15 @@ static inline u32 _prepare_ccr(const struct pl330_reqcfg *rqc) return ccr; } -static inline bool _is_valid(u32 ccr) -{ - enum pl330_dstcachectrl dcctl; - enum pl330_srccachectrl scctl; - - dcctl = (ccr >> CC_DSTCCTRL_SHFT) & CC_DRCCCTRL_MASK; - scctl = (ccr >> CC_SRCCCTRL_SHFT) & CC_SRCCCTRL_MASK; - - if (dcctl == DINVALID1 || dcctl == DINVALID2 - || scctl == SINVALID1 || scctl == SINVALID2) - return false; - else - return true; -} - /* * Submit a list of xfers after which the client wants notification. * Client is not notified after each xfer unit, just once after all * xfer units are done or some error occurs. */ -static int pl330_submit_req(void *ch_id, struct pl330_req *r) +static int pl330_submit_req(struct pl330_thread *thrd, + struct dma_pl330_desc *desc) { - struct pl330_thread *thrd = ch_id; - struct pl330_dmac *pl330; - struct pl330_info *pi; + struct pl330_dmac *pl330 = thrd->dmac; struct _xfer_spec xs; unsigned long flags; void __iomem *regs; @@ -1528,25 +1373,24 @@ static int pl330_submit_req(void *ch_id, struct pl330_req *r) int ret = 0; /* No Req or Unacquired Channel or DMAC */ - if (!r || !thrd || thrd->free) + if (!desc || !thrd || thrd->free) return -EINVAL; - pl330 = thrd->dmac; - pi = pl330->pinfo; - regs = pi->base; + regs = thrd->dmac->base; if (pl330->state == DYING || pl330->dmac_tbd.reset_chan & (1 << thrd->id)) { - dev_info(thrd->dmac->pinfo->dev, "%s:%d\n", + dev_info(thrd->dmac->ddma.dev, "%s:%d\n", __func__, __LINE__); return -EAGAIN; } /* If request for non-existing peripheral */ - if (r->rqtype != MEMTOMEM && r->peri >= pi->pcfg.num_peri) { - dev_info(thrd->dmac->pinfo->dev, + if (desc->rqtype != DMA_MEM_TO_MEM && + desc->peri >= pl330->pcfg.num_peri) { + dev_info(thrd->dmac->ddma.dev, "%s:%d Invalid peripheral(%u)!\n", - __func__, __LINE__, r->peri); + __func__, __LINE__, desc->peri); return -EINVAL; } @@ -1557,41 +1401,26 @@ static int pl330_submit_req(void *ch_id, struct pl330_req *r) goto xfer_exit; } + /* Prefer Secure Channel */ + if (!_manager_ns(thrd)) + desc->rqcfg.nonsecure = 0; + else + desc->rqcfg.nonsecure = 1; - /* Use last settings, if not provided */ - if (r->cfg) { - /* Prefer Secure Channel */ - if (!_manager_ns(thrd)) - r->cfg->nonsecure = 0; - else - r->cfg->nonsecure = 1; - - ccr = _prepare_ccr(r->cfg); - } else { - ccr = readl(regs + CC(thrd->id)); - } - - /* If this req doesn't have valid xfer settings */ - if (!_is_valid(ccr)) { - ret = -EINVAL; - dev_info(thrd->dmac->pinfo->dev, "%s:%d Invalid CCR(%x)!\n", - __func__, __LINE__, ccr); - goto xfer_exit; - } + ccr = _prepare_ccr(&desc->rqcfg); - idx = IS_FREE(&thrd->req[0]) ? 0 : 1; + idx = thrd->req[0].desc == NULL ? 0 : 1; xs.ccr = ccr; - xs.r = r; + xs.desc = desc; /* First dry run to check if req is acceptable */ ret = _setup_req(1, thrd, idx, &xs); if (ret < 0) goto xfer_exit; - if (ret > pi->mcbufsz / 2) { - dev_info(thrd->dmac->pinfo->dev, - "%s:%d Trying increasing mcbufsz\n", + if (ret > pl330->mcbufsz / 2) { + dev_info(pl330->ddma.dev, "%s:%d Trying increasing mcbufsz\n", __func__, __LINE__); ret = -ENOMEM; goto xfer_exit; @@ -1599,8 +1428,8 @@ static int pl330_submit_req(void *ch_id, struct pl330_req *r) /* Hook the request */ thrd->lstenq = idx; - thrd->req[idx].mc_len = _setup_req(0, thrd, idx, &xs); - thrd->req[idx].r = r; + thrd->req[idx].desc = desc; + _setup_req(0, thrd, idx, &xs); ret = 0; @@ -1610,10 +1439,32 @@ xfer_exit: return ret; } +static void dma_pl330_rqcb(struct dma_pl330_desc *desc, enum pl330_op_err err) +{ + struct dma_pl330_chan *pch; + unsigned long flags; + + if (!desc) + return; + + pch = desc->pchan; + + /* If desc aborted */ + if (!pch) + return; + + spin_lock_irqsave(&pch->lock, flags); + + desc->status = DONE; + + spin_unlock_irqrestore(&pch->lock, flags); + + tasklet_schedule(&pch->task); +} + static void pl330_dotask(unsigned long data) { struct pl330_dmac *pl330 = (struct pl330_dmac *) data; - struct pl330_info *pi = pl330->pinfo; unsigned long flags; int i; @@ -1631,16 +1482,16 @@ static void pl330_dotask(unsigned long data) if (pl330->dmac_tbd.reset_mngr) { _stop(pl330->manager); /* Reset all channels */ - pl330->dmac_tbd.reset_chan = (1 << pi->pcfg.num_chan) - 1; + pl330->dmac_tbd.reset_chan = (1 << pl330->pcfg.num_chan) - 1; /* Clear the reset flag */ pl330->dmac_tbd.reset_mngr = false; } - for (i = 0; i < pi->pcfg.num_chan; i++) { + for (i = 0; i < pl330->pcfg.num_chan; i++) { if (pl330->dmac_tbd.reset_chan & (1 << i)) { struct pl330_thread *thrd = &pl330->channels[i]; - void __iomem *regs = pi->base; + void __iomem *regs = pl330->base; enum pl330_op_err err; _stop(thrd); @@ -1651,16 +1502,13 @@ static void pl330_dotask(unsigned long data) err = PL330_ERR_ABORT; spin_unlock_irqrestore(&pl330->lock, flags); - - _callback(thrd->req[1 - thrd->lstenq].r, err); - _callback(thrd->req[thrd->lstenq].r, err); - + dma_pl330_rqcb(thrd->req[1 - thrd->lstenq].desc, err); + dma_pl330_rqcb(thrd->req[thrd->lstenq].desc, err); spin_lock_irqsave(&pl330->lock, flags); - thrd->req[0].r = NULL; - thrd->req[1].r = NULL; - mark_free(thrd, 0); - mark_free(thrd, 1); + thrd->req[0].desc = NULL; + thrd->req[1].desc = NULL; + thrd->req_running = -1; /* Clear the reset flag */ pl330->dmac_tbd.reset_chan &= ~(1 << i); @@ -1673,20 +1521,15 @@ static void pl330_dotask(unsigned long data) } /* Returns 1 if state was updated, 0 otherwise */ -static int pl330_update(const struct pl330_info *pi) +static int pl330_update(struct pl330_dmac *pl330) { - struct pl330_req *rqdone, *tmp; - struct pl330_dmac *pl330; + struct dma_pl330_desc *descdone, *tmp; unsigned long flags; void __iomem *regs; u32 val; int id, ev, ret = 0; - if (!pi || !pi->pl330_data) - return 0; - - regs = pi->base; - pl330 = pi->pl330_data; + regs = pl330->base; spin_lock_irqsave(&pl330->lock, flags); @@ -1696,13 +1539,13 @@ static int pl330_update(const struct pl330_info *pi) else pl330->dmac_tbd.reset_mngr = false; - val = readl(regs + FSC) & ((1 << pi->pcfg.num_chan) - 1); + val = readl(regs + FSC) & ((1 << pl330->pcfg.num_chan) - 1); pl330->dmac_tbd.reset_chan |= val; if (val) { int i = 0; - while (i < pi->pcfg.num_chan) { + while (i < pl330->pcfg.num_chan) { if (val & (1 << i)) { - dev_info(pi->dev, + dev_info(pl330->ddma.dev, "Reset Channel-%d\t CS-%x FTC-%x\n", i, readl(regs + CS(i)), readl(regs + FTC(i))); @@ -1714,15 +1557,16 @@ static int pl330_update(const struct pl330_info *pi) /* Check which event happened i.e, thread notified */ val = readl(regs + ES); - if (pi->pcfg.num_events < 32 - && val & ~((1 << pi->pcfg.num_events) - 1)) { + if (pl330->pcfg.num_events < 32 + && val & ~((1 << pl330->pcfg.num_events) - 1)) { pl330->dmac_tbd.reset_dmac = true; - dev_err(pi->dev, "%s:%d Unexpected!\n", __func__, __LINE__); + dev_err(pl330->ddma.dev, "%s:%d Unexpected!\n", __func__, + __LINE__); ret = 1; goto updt_exit; } - for (ev = 0; ev < pi->pcfg.num_events; ev++) { + for (ev = 0; ev < pl330->pcfg.num_events; ev++) { if (val & (1 << ev)) { /* Event occurred */ struct pl330_thread *thrd; u32 inten = readl(regs + INTEN); @@ -1743,25 +1587,22 @@ static int pl330_update(const struct pl330_info *pi) continue; /* Detach the req */ - rqdone = thrd->req[active].r; - thrd->req[active].r = NULL; - - mark_free(thrd, active); + descdone = thrd->req[active].desc; + thrd->req[active].desc = NULL; /* Get going again ASAP */ _start(thrd); /* For now, just make a list of callbacks to be done */ - list_add_tail(&rqdone->rqd, &pl330->req_done); + list_add_tail(&descdone->rqd, &pl330->req_done); } } /* Now that we are in no hurry, do the callbacks */ - list_for_each_entry_safe(rqdone, tmp, &pl330->req_done, rqd) { - list_del(&rqdone->rqd); - + list_for_each_entry_safe(descdone, tmp, &pl330->req_done, rqd) { + list_del(&descdone->rqd); spin_unlock_irqrestore(&pl330->lock, flags); - _callback(rqdone, PL330_ERR_NONE); + dma_pl330_rqcb(descdone, PL330_ERR_NONE); spin_lock_irqsave(&pl330->lock, flags); } @@ -1778,65 +1619,13 @@ updt_exit: return ret; } -static int pl330_chan_ctrl(void *ch_id, enum pl330_chan_op op) -{ - struct pl330_thread *thrd = ch_id; - struct pl330_dmac *pl330; - unsigned long flags; - int ret = 0, active; - - if (!thrd || thrd->free || thrd->dmac->state == DYING) - return -EINVAL; - - pl330 = thrd->dmac; - active = thrd->req_running; - - spin_lock_irqsave(&pl330->lock, flags); - - switch (op) { - case PL330_OP_FLUSH: - /* Make sure the channel is stopped */ - _stop(thrd); - - thrd->req[0].r = NULL; - thrd->req[1].r = NULL; - mark_free(thrd, 0); - mark_free(thrd, 1); - break; - - case PL330_OP_ABORT: - /* Make sure the channel is stopped */ - _stop(thrd); - - /* ABORT is only for the active req */ - if (active == -1) - break; - - thrd->req[active].r = NULL; - mark_free(thrd, active); - - /* Start the next */ - case PL330_OP_START: - if ((active == -1) && !_start(thrd)) - ret = -EIO; - break; - - default: - ret = -EINVAL; - } - - spin_unlock_irqrestore(&pl330->lock, flags); - return ret; -} - /* Reserve an event */ static inline int _alloc_event(struct pl330_thread *thrd) { struct pl330_dmac *pl330 = thrd->dmac; - struct pl330_info *pi = pl330->pinfo; int ev; - for (ev = 0; ev < pi->pcfg.num_events; ev++) + for (ev = 0; ev < pl330->pcfg.num_events; ev++) if (pl330->events[ev] == -1) { pl330->events[ev] = thrd->id; return ev; @@ -1845,45 +1634,38 @@ static inline int _alloc_event(struct pl330_thread *thrd) return -1; } -static bool _chan_ns(const struct pl330_info *pi, int i) +static bool _chan_ns(const struct pl330_dmac *pl330, int i) { - return pi->pcfg.irq_ns & (1 << i); + return pl330->pcfg.irq_ns & (1 << i); } /* Upon success, returns IdentityToken for the * allocated channel, NULL otherwise. */ -static void *pl330_request_channel(const struct pl330_info *pi) +static struct pl330_thread *pl330_request_channel(struct pl330_dmac *pl330) { struct pl330_thread *thrd = NULL; - struct pl330_dmac *pl330; unsigned long flags; int chans, i; - if (!pi || !pi->pl330_data) - return NULL; - - pl330 = pi->pl330_data; - if (pl330->state == DYING) return NULL; - chans = pi->pcfg.num_chan; + chans = pl330->pcfg.num_chan; spin_lock_irqsave(&pl330->lock, flags); for (i = 0; i < chans; i++) { thrd = &pl330->channels[i]; if ((thrd->free) && (!_manager_ns(thrd) || - _chan_ns(pi, i))) { + _chan_ns(pl330, i))) { thrd->ev = _alloc_event(thrd); if (thrd->ev >= 0) { thrd->free = false; thrd->lstenq = 1; - thrd->req[0].r = NULL; - mark_free(thrd, 0); - thrd->req[1].r = NULL; - mark_free(thrd, 1); + thrd->req[0].desc = NULL; + thrd->req[1].desc = NULL; + thrd->req_running = -1; break; } } @@ -1899,17 +1681,15 @@ static void *pl330_request_channel(const struct pl330_info *pi) static inline void _free_event(struct pl330_thread *thrd, int ev) { struct pl330_dmac *pl330 = thrd->dmac; - struct pl330_info *pi = pl330->pinfo; /* If the event is valid and was held by the thread */ - if (ev >= 0 && ev < pi->pcfg.num_events + if (ev >= 0 && ev < pl330->pcfg.num_events && pl330->events[ev] == thrd->id) pl330->events[ev] = -1; } -static void pl330_release_channel(void *ch_id) +static void pl330_release_channel(struct pl330_thread *thrd) { - struct pl330_thread *thrd = ch_id; struct pl330_dmac *pl330; unsigned long flags; @@ -1918,8 +1698,8 @@ static void pl330_release_channel(void *ch_id) _stop(thrd); - _callback(thrd->req[1 - thrd->lstenq].r, PL330_ERR_ABORT); - _callback(thrd->req[thrd->lstenq].r, PL330_ERR_ABORT); + dma_pl330_rqcb(thrd->req[1 - thrd->lstenq].desc, PL330_ERR_ABORT); + dma_pl330_rqcb(thrd->req[thrd->lstenq].desc, PL330_ERR_ABORT); pl330 = thrd->dmac; @@ -1932,72 +1712,70 @@ static void pl330_release_channel(void *ch_id) /* Initialize the structure for PL330 configuration, that can be used * by the client driver the make best use of the DMAC */ -static void read_dmac_config(struct pl330_info *pi) +static void read_dmac_config(struct pl330_dmac *pl330) { - void __iomem *regs = pi->base; + void __iomem *regs = pl330->base; u32 val; val = readl(regs + CRD) >> CRD_DATA_WIDTH_SHIFT; val &= CRD_DATA_WIDTH_MASK; - pi->pcfg.data_bus_width = 8 * (1 << val); + pl330->pcfg.data_bus_width = 8 * (1 << val); val = readl(regs + CRD) >> CRD_DATA_BUFF_SHIFT; val &= CRD_DATA_BUFF_MASK; - pi->pcfg.data_buf_dep = val + 1; + pl330->pcfg.data_buf_dep = val + 1; val = readl(regs + CR0) >> CR0_NUM_CHANS_SHIFT; val &= CR0_NUM_CHANS_MASK; val += 1; - pi->pcfg.num_chan = val; + pl330->pcfg.num_chan = val; val = readl(regs + CR0); if (val & CR0_PERIPH_REQ_SET) { val = (val >> CR0_NUM_PERIPH_SHIFT) & CR0_NUM_PERIPH_MASK; val += 1; - pi->pcfg.num_peri = val; - pi->pcfg.peri_ns = readl(regs + CR4); + pl330->pcfg.num_peri = val; + pl330->pcfg.peri_ns = readl(regs + CR4); } else { - pi->pcfg.num_peri = 0; + pl330->pcfg.num_peri = 0; } val = readl(regs + CR0); if (val & CR0_BOOT_MAN_NS) - pi->pcfg.mode |= DMAC_MODE_NS; + pl330->pcfg.mode |= DMAC_MODE_NS; else - pi->pcfg.mode &= ~DMAC_MODE_NS; + pl330->pcfg.mode &= ~DMAC_MODE_NS; val = readl(regs + CR0) >> CR0_NUM_EVENTS_SHIFT; val &= CR0_NUM_EVENTS_MASK; val += 1; - pi->pcfg.num_events = val; + pl330->pcfg.num_events = val; - pi->pcfg.irq_ns = readl(regs + CR3); + pl330->pcfg.irq_ns = readl(regs + CR3); } static inline void _reset_thread(struct pl330_thread *thrd) { struct pl330_dmac *pl330 = thrd->dmac; - struct pl330_info *pi = pl330->pinfo; thrd->req[0].mc_cpu = pl330->mcode_cpu - + (thrd->id * pi->mcbufsz); + + (thrd->id * pl330->mcbufsz); thrd->req[0].mc_bus = pl330->mcode_bus - + (thrd->id * pi->mcbufsz); - thrd->req[0].r = NULL; - mark_free(thrd, 0); + + (thrd->id * pl330->mcbufsz); + thrd->req[0].desc = NULL; thrd->req[1].mc_cpu = thrd->req[0].mc_cpu - + pi->mcbufsz / 2; + + pl330->mcbufsz / 2; thrd->req[1].mc_bus = thrd->req[0].mc_bus - + pi->mcbufsz / 2; - thrd->req[1].r = NULL; - mark_free(thrd, 1); + + pl330->mcbufsz / 2; + thrd->req[1].desc = NULL; + + thrd->req_running = -1; } static int dmac_alloc_threads(struct pl330_dmac *pl330) { - struct pl330_info *pi = pl330->pinfo; - int chans = pi->pcfg.num_chan; + int chans = pl330->pcfg.num_chan; struct pl330_thread *thrd; int i; @@ -2028,29 +1806,28 @@ static int dmac_alloc_threads(struct pl330_dmac *pl330) static int dmac_alloc_resources(struct pl330_dmac *pl330) { - struct pl330_info *pi = pl330->pinfo; - int chans = pi->pcfg.num_chan; + int chans = pl330->pcfg.num_chan; int ret; /* * Alloc MicroCode buffer for 'chans' Channel threads. * A channel's buffer offset is (Channel_Id * MCODE_BUFF_PERCHAN) */ - pl330->mcode_cpu = dma_alloc_coherent(pi->dev, - chans * pi->mcbufsz, + pl330->mcode_cpu = dma_alloc_coherent(pl330->ddma.dev, + chans * pl330->mcbufsz, &pl330->mcode_bus, GFP_KERNEL); if (!pl330->mcode_cpu) { - dev_err(pi->dev, "%s:%d Can't allocate memory!\n", + dev_err(pl330->ddma.dev, "%s:%d Can't allocate memory!\n", __func__, __LINE__); return -ENOMEM; } ret = dmac_alloc_threads(pl330); if (ret) { - dev_err(pi->dev, "%s:%d Can't to create channels for DMAC!\n", + dev_err(pl330->ddma.dev, "%s:%d Can't to create channels for DMAC!\n", __func__, __LINE__); - dma_free_coherent(pi->dev, - chans * pi->mcbufsz, + dma_free_coherent(pl330->ddma.dev, + chans * pl330->mcbufsz, pl330->mcode_cpu, pl330->mcode_bus); return ret; } @@ -2058,71 +1835,45 @@ static int dmac_alloc_resources(struct pl330_dmac *pl330) return 0; } -static int pl330_add(struct pl330_info *pi) +static int pl330_add(struct pl330_dmac *pl330) { - struct pl330_dmac *pl330; void __iomem *regs; int i, ret; - if (!pi || !pi->dev) - return -EINVAL; - - /* If already added */ - if (pi->pl330_data) - return -EINVAL; - - /* - * If the SoC can perform reset on the DMAC, then do it - * before reading its configuration. - */ - if (pi->dmac_reset) - pi->dmac_reset(pi); - - regs = pi->base; + regs = pl330->base; /* Check if we can handle this DMAC */ - if ((pi->pcfg.periph_id & 0xfffff) != PERIPH_ID_VAL) { - dev_err(pi->dev, "PERIPH_ID 0x%x !\n", pi->pcfg.periph_id); + if ((pl330->pcfg.periph_id & 0xfffff) != PERIPH_ID_VAL) { + dev_err(pl330->ddma.dev, "PERIPH_ID 0x%x !\n", + pl330->pcfg.periph_id); return -EINVAL; } /* Read the configuration of the DMAC */ - read_dmac_config(pi); + read_dmac_config(pl330); - if (pi->pcfg.num_events == 0) { - dev_err(pi->dev, "%s:%d Can't work without events!\n", + if (pl330->pcfg.num_events == 0) { + dev_err(pl330->ddma.dev, "%s:%d Can't work without events!\n", __func__, __LINE__); return -EINVAL; } - pl330 = kzalloc(sizeof(*pl330), GFP_KERNEL); - if (!pl330) { - dev_err(pi->dev, "%s:%d Can't allocate memory!\n", - __func__, __LINE__); - return -ENOMEM; - } - - /* Assign the info structure and private data */ - pl330->pinfo = pi; - pi->pl330_data = pl330; - spin_lock_init(&pl330->lock); INIT_LIST_HEAD(&pl330->req_done); /* Use default MC buffer size if not provided */ - if (!pi->mcbufsz) - pi->mcbufsz = MCODE_BUFF_PER_REQ * 2; + if (!pl330->mcbufsz) + pl330->mcbufsz = MCODE_BUFF_PER_REQ * 2; /* Mark all events as free */ - for (i = 0; i < pi->pcfg.num_events; i++) + for (i = 0; i < pl330->pcfg.num_events; i++) pl330->events[i] = -1; /* Allocate resources needed by the DMAC */ ret = dmac_alloc_resources(pl330); if (ret) { - dev_err(pi->dev, "Unable to create channels for DMAC\n"); - kfree(pl330); + dev_err(pl330->ddma.dev, "Unable to create channels for DMAC\n"); return ret; } @@ -2135,15 +1886,13 @@ static int pl330_add(struct pl330_info *pi) static int dmac_free_threads(struct pl330_dmac *pl330) { - struct pl330_info *pi = pl330->pinfo; - int chans = pi->pcfg.num_chan; struct pl330_thread *thrd; int i; /* Release Channel threads */ - for (i = 0; i < chans; i++) { + for (i = 0; i < pl330->pcfg.num_chan; i++) { thrd = &pl330->channels[i]; - pl330_release_channel((void *)thrd); + pl330_release_channel(thrd); } /* Free memory */ @@ -2152,35 +1901,18 @@ static int dmac_free_threads(struct pl330_dmac *pl330) return 0; } -static void dmac_free_resources(struct pl330_dmac *pl330) +static void pl330_del(struct pl330_dmac *pl330) { - struct pl330_info *pi = pl330->pinfo; - int chans = pi->pcfg.num_chan; - - dmac_free_threads(pl330); - - dma_free_coherent(pi->dev, chans * pi->mcbufsz, - pl330->mcode_cpu, pl330->mcode_bus); -} - -static void pl330_del(struct pl330_info *pi) -{ - struct pl330_dmac *pl330; - - if (!pi || !pi->pl330_data) - return; - - pl330 = pi->pl330_data; - pl330->state = UNINIT; tasklet_kill(&pl330->tasks); /* Free DMAC resources */ - dmac_free_resources(pl330); + dmac_free_threads(pl330); - kfree(pl330); - pi->pl330_data = NULL; + dma_free_coherent(pl330->ddma.dev, + pl330->pcfg.num_chan * pl330->mcbufsz, pl330->mcode_cpu, + pl330->mcode_bus); } /* forward declaration */ @@ -2212,8 +1944,7 @@ static inline void fill_queue(struct dma_pl330_chan *pch) if (desc->status == BUSY) continue; - ret = pl330_submit_req(pch->pl330_chid, - &desc->req); + ret = pl330_submit_req(pch->thread, desc); if (!ret) { desc->status = BUSY; } else if (ret == -EAGAIN) { @@ -2222,7 +1953,7 @@ static inline void fill_queue(struct dma_pl330_chan *pch) } else { /* Unacceptable request */ desc->status = DONE; - dev_err(pch->dmac->pif.dev, "%s:%d Bad Desc(%d)\n", + dev_err(pch->dmac->ddma.dev, "%s:%d Bad Desc(%d)\n", __func__, __LINE__, desc->txd.cookie); tasklet_schedule(&pch->task); } @@ -2249,7 +1980,9 @@ static void pl330_tasklet(unsigned long data) fill_queue(pch); /* Make sure the PL330 Channel thread is active */ - pl330_chan_ctrl(pch->pl330_chid, PL330_OP_START); + spin_lock(&pch->thread->dmac->lock); + _start(pch->thread); + spin_unlock(&pch->thread->dmac->lock); while (!list_empty(&pch->completed_list)) { dma_async_tx_callback callback; @@ -2280,25 +2013,6 @@ static void pl330_tasklet(unsigned long data) spin_unlock_irqrestore(&pch->lock, flags); } -static void dma_pl330_rqcb(void *token, enum pl330_op_err err) -{ - struct dma_pl330_desc *desc = token; - struct dma_pl330_chan *pch = desc->pchan; - unsigned long flags; - - /* If desc aborted */ - if (!pch) - return; - - spin_lock_irqsave(&pch->lock, flags); - - desc->status = DONE; - - spin_unlock_irqrestore(&pch->lock, flags); - - tasklet_schedule(&pch->task); -} - bool pl330_filter(struct dma_chan *chan, void *param) { u8 *peri_id; @@ -2315,23 +2029,26 @@ static struct dma_chan *of_dma_pl330_xlate(struct of_phandle_args *dma_spec, struct of_dma *ofdma) { int count = dma_spec->args_count; - struct dma_pl330_dmac *pdmac = ofdma->of_dma_data; + struct pl330_dmac *pl330 = ofdma->of_dma_data; unsigned int chan_id; + if (!pl330) + return NULL; + if (count != 1) return NULL; chan_id = dma_spec->args[0]; - if (chan_id >= pdmac->num_peripherals) + if (chan_id >= pl330->num_peripherals) return NULL; - return dma_get_slave_channel(&pdmac->peripherals[chan_id].chan); + return dma_get_slave_channel(&pl330->peripherals[chan_id].chan); } static int pl330_alloc_chan_resources(struct dma_chan *chan) { struct dma_pl330_chan *pch = to_pchan(chan); - struct dma_pl330_dmac *pdmac = pch->dmac; + struct pl330_dmac *pl330 = pch->dmac; unsigned long flags; spin_lock_irqsave(&pch->lock, flags); @@ -2339,8 +2056,8 @@ static int pl330_alloc_chan_resources(struct dma_chan *chan) dma_cookie_init(chan); pch->cyclic = false; - pch->pl330_chid = pl330_request_channel(&pdmac->pif); - if (!pch->pl330_chid) { + pch->thread = pl330_request_channel(pl330); + if (!pch->thread) { spin_unlock_irqrestore(&pch->lock, flags); return -ENOMEM; } @@ -2357,7 +2074,7 @@ static int pl330_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd, unsigned struct dma_pl330_chan *pch = to_pchan(chan); struct dma_pl330_desc *desc; unsigned long flags; - struct dma_pl330_dmac *pdmac = pch->dmac; + struct pl330_dmac *pl330 = pch->dmac; struct dma_slave_config *slave_config; LIST_HEAD(list); @@ -2365,8 +2082,13 @@ static int pl330_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd, unsigned case DMA_TERMINATE_ALL: spin_lock_irqsave(&pch->lock, flags); - /* FLUSH the PL330 Channel thread */ - pl330_chan_ctrl(pch->pl330_chid, PL330_OP_FLUSH); + spin_lock(&pl330->lock); + _stop(pch->thread); + spin_unlock(&pl330->lock); + + pch->thread->req[0].desc = NULL; + pch->thread->req[1].desc = NULL; + pch->thread->req_running = -1; /* Mark all desc done */ list_for_each_entry(desc, &pch->submitted_list, node) { @@ -2384,9 +2106,9 @@ static int pl330_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd, unsigned dma_cookie_complete(&desc->txd); } - list_splice_tail_init(&pch->submitted_list, &pdmac->desc_pool); - list_splice_tail_init(&pch->work_list, &pdmac->desc_pool); - list_splice_tail_init(&pch->completed_list, &pdmac->desc_pool); + list_splice_tail_init(&pch->submitted_list, &pl330->desc_pool); + list_splice_tail_init(&pch->work_list, &pl330->desc_pool); + list_splice_tail_init(&pch->completed_list, &pl330->desc_pool); spin_unlock_irqrestore(&pch->lock, flags); break; case DMA_SLAVE_CONFIG: @@ -2409,7 +2131,7 @@ static int pl330_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd, unsigned } break; default: - dev_err(pch->dmac->pif.dev, "Not supported command.\n"); + dev_err(pch->dmac->ddma.dev, "Not supported command.\n"); return -ENXIO; } @@ -2425,8 +2147,8 @@ static void pl330_free_chan_resources(struct dma_chan *chan) spin_lock_irqsave(&pch->lock, flags); - pl330_release_channel(pch->pl330_chid); - pch->pl330_chid = NULL; + pl330_release_channel(pch->thread); + pch->thread = NULL; if (pch->cyclic) list_splice_tail_init(&pch->work_list, &pch->dmac->desc_pool); @@ -2489,57 +2211,46 @@ static dma_cookie_t pl330_tx_submit(struct dma_async_tx_descriptor *tx) static inline void _init_desc(struct dma_pl330_desc *desc) { - desc->req.x = &desc->px; - desc->req.token = desc; desc->rqcfg.swap = SWAP_NO; - desc->rqcfg.scctl = SCCTRL0; - desc->rqcfg.dcctl = DCCTRL0; - desc->req.cfg = &desc->rqcfg; - desc->req.xfer_cb = dma_pl330_rqcb; + desc->rqcfg.scctl = CCTRL0; + desc->rqcfg.dcctl = CCTRL0; desc->txd.tx_submit = pl330_tx_submit; INIT_LIST_HEAD(&desc->node); } /* Returns the number of descriptors added to the DMAC pool */ -static int add_desc(struct dma_pl330_dmac *pdmac, gfp_t flg, int count) +static int add_desc(struct pl330_dmac *pl330, gfp_t flg, int count) { struct dma_pl330_desc *desc; unsigned long flags; int i; - if (!pdmac) - return 0; - desc = kcalloc(count, sizeof(*desc), flg); if (!desc) return 0; - spin_lock_irqsave(&pdmac->pool_lock, flags); + spin_lock_irqsave(&pl330->pool_lock, flags); for (i = 0; i < count; i++) { _init_desc(&desc[i]); - list_add_tail(&desc[i].node, &pdmac->desc_pool); + list_add_tail(&desc[i].node, &pl330->desc_pool); } - spin_unlock_irqrestore(&pdmac->pool_lock, flags); + spin_unlock_irqrestore(&pl330->pool_lock, flags); return count; } -static struct dma_pl330_desc * -pluck_desc(struct dma_pl330_dmac *pdmac) +static struct dma_pl330_desc *pluck_desc(struct pl330_dmac *pl330) { struct dma_pl330_desc *desc = NULL; unsigned long flags; - if (!pdmac) - return NULL; - - spin_lock_irqsave(&pdmac->pool_lock, flags); + spin_lock_irqsave(&pl330->pool_lock, flags); - if (!list_empty(&pdmac->desc_pool)) { - desc = list_entry(pdmac->desc_pool.next, + if (!list_empty(&pl330->desc_pool)) { + desc = list_entry(pl330->desc_pool.next, struct dma_pl330_desc, node); list_del_init(&desc->node); @@ -2548,29 +2259,29 @@ pluck_desc(struct dma_pl330_dmac *pdmac) desc->txd.callback = NULL; } - spin_unlock_irqrestore(&pdmac->pool_lock, flags); + spin_unlock_irqrestore(&pl330->pool_lock, flags); return desc; } static struct dma_pl330_desc *pl330_get_desc(struct dma_pl330_chan *pch) { - struct dma_pl330_dmac *pdmac = pch->dmac; + struct pl330_dmac *pl330 = pch->dmac; u8 *peri_id = pch->chan.private; struct dma_pl330_desc *desc; /* Pluck one desc from the pool of DMAC */ - desc = pluck_desc(pdmac); + desc = pluck_desc(pl330); /* If the DMAC pool is empty, alloc new */ if (!desc) { - if (!add_desc(pdmac, GFP_ATOMIC, 1)) + if (!add_desc(pl330, GFP_ATOMIC, 1)) return NULL; /* Try again */ - desc = pluck_desc(pdmac); + desc = pluck_desc(pl330); if (!desc) { - dev_err(pch->dmac->pif.dev, + dev_err(pch->dmac->ddma.dev, "%s:%d ALERT!\n", __func__, __LINE__); return NULL; } @@ -2581,8 +2292,8 @@ static struct dma_pl330_desc *pl330_get_desc(struct dma_pl330_chan *pch) desc->txd.cookie = 0; async_tx_ack(&desc->txd); - desc->req.peri = peri_id ? pch->chan.chan_id : 0; - desc->rqcfg.pcfg = &pch->dmac->pif.pcfg; + desc->peri = peri_id ? pch->chan.chan_id : 0; + desc->rqcfg.pcfg = &pch->dmac->pcfg; dma_async_tx_descriptor_init(&desc->txd, &pch->chan); @@ -2592,7 +2303,6 @@ static struct dma_pl330_desc *pl330_get_desc(struct dma_pl330_chan *pch) static inline void fill_px(struct pl330_xfer *px, dma_addr_t dst, dma_addr_t src, size_t len) { - px->next = NULL; px->bytes = len; px->dst_addr = dst; px->src_addr = src; @@ -2605,7 +2315,7 @@ __pl330_prep_dma_memcpy(struct dma_pl330_chan *pch, dma_addr_t dst, struct dma_pl330_desc *desc = pl330_get_desc(pch); if (!desc) { - dev_err(pch->dmac->pif.dev, "%s:%d Unable to fetch desc\n", + dev_err(pch->dmac->ddma.dev, "%s:%d Unable to fetch desc\n", __func__, __LINE__); return NULL; } @@ -2629,11 +2339,11 @@ __pl330_prep_dma_memcpy(struct dma_pl330_chan *pch, dma_addr_t dst, static inline int get_burst_len(struct dma_pl330_desc *desc, size_t len) { struct dma_pl330_chan *pch = desc->pchan; - struct pl330_info *pi = &pch->dmac->pif; + struct pl330_dmac *pl330 = pch->dmac; int burst_len; - burst_len = pi->pcfg.data_bus_width / 8; - burst_len *= pi->pcfg.data_buf_dep; + burst_len = pl330->pcfg.data_bus_width / 8; + burst_len *= pl330->pcfg.data_buf_dep; burst_len >>= desc->rqcfg.brst_size; /* src/dst_burst_len can't be more than 16 */ @@ -2652,11 +2362,11 @@ static inline int get_burst_len(struct dma_pl330_desc *desc, size_t len) static struct dma_async_tx_descriptor *pl330_prep_dma_cyclic( struct dma_chan *chan, dma_addr_t dma_addr, size_t len, size_t period_len, enum dma_transfer_direction direction, - unsigned long flags, void *context) + unsigned long flags) { struct dma_pl330_desc *desc = NULL, *first = NULL; struct dma_pl330_chan *pch = to_pchan(chan); - struct dma_pl330_dmac *pdmac = pch->dmac; + struct pl330_dmac *pl330 = pch->dmac; unsigned int i; dma_addr_t dst; dma_addr_t src; @@ -2665,7 +2375,7 @@ static struct dma_async_tx_descriptor *pl330_prep_dma_cyclic( return NULL; if (!is_slave_direction(direction)) { - dev_err(pch->dmac->pif.dev, "%s:%d Invalid dma direction\n", + dev_err(pch->dmac->ddma.dev, "%s:%d Invalid dma direction\n", __func__, __LINE__); return NULL; } @@ -2673,23 +2383,23 @@ static struct dma_async_tx_descriptor *pl330_prep_dma_cyclic( for (i = 0; i < len / period_len; i++) { desc = pl330_get_desc(pch); if (!desc) { - dev_err(pch->dmac->pif.dev, "%s:%d Unable to fetch desc\n", + dev_err(pch->dmac->ddma.dev, "%s:%d Unable to fetch desc\n", __func__, __LINE__); if (!first) return NULL; - spin_lock_irqsave(&pdmac->pool_lock, flags); + spin_lock_irqsave(&pl330->pool_lock, flags); while (!list_empty(&first->node)) { desc = list_entry(first->node.next, struct dma_pl330_desc, node); - list_move_tail(&desc->node, &pdmac->desc_pool); + list_move_tail(&desc->node, &pl330->desc_pool); } - list_move_tail(&first->node, &pdmac->desc_pool); + list_move_tail(&first->node, &pl330->desc_pool); - spin_unlock_irqrestore(&pdmac->pool_lock, flags); + spin_unlock_irqrestore(&pl330->pool_lock, flags); return NULL; } @@ -2698,14 +2408,12 @@ static struct dma_async_tx_descriptor *pl330_prep_dma_cyclic( case DMA_MEM_TO_DEV: desc->rqcfg.src_inc = 1; desc->rqcfg.dst_inc = 0; - desc->req.rqtype = MEMTODEV; src = dma_addr; dst = pch->fifo_addr; break; case DMA_DEV_TO_MEM: desc->rqcfg.src_inc = 0; desc->rqcfg.dst_inc = 1; - desc->req.rqtype = DEVTOMEM; src = pch->fifo_addr; dst = dma_addr; break; @@ -2713,6 +2421,7 @@ static struct dma_async_tx_descriptor *pl330_prep_dma_cyclic( break; } + desc->rqtype = direction; desc->rqcfg.brst_size = pch->burst_sz; desc->rqcfg.brst_len = 1; fill_px(&desc->px, dst, src, period_len); @@ -2740,24 +2449,22 @@ pl330_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dst, { struct dma_pl330_desc *desc; struct dma_pl330_chan *pch = to_pchan(chan); - struct pl330_info *pi; + struct pl330_dmac *pl330 = pch->dmac; int burst; if (unlikely(!pch || !len)) return NULL; - pi = &pch->dmac->pif; - desc = __pl330_prep_dma_memcpy(pch, dst, src, len); if (!desc) return NULL; desc->rqcfg.src_inc = 1; desc->rqcfg.dst_inc = 1; - desc->req.rqtype = MEMTOMEM; + desc->rqtype = DMA_MEM_TO_MEM; /* Select max possible burst size */ - burst = pi->pcfg.data_bus_width / 8; + burst = pl330->pcfg.data_bus_width / 8; while (burst > 1) { if (!(len % burst)) @@ -2776,7 +2483,7 @@ pl330_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dst, return &desc->txd; } -static void __pl330_giveback_desc(struct dma_pl330_dmac *pdmac, +static void __pl330_giveback_desc(struct pl330_dmac *pl330, struct dma_pl330_desc *first) { unsigned long flags; @@ -2785,17 +2492,17 @@ static void __pl330_giveback_desc(struct dma_pl330_dmac *pdmac, if (!first) return; - spin_lock_irqsave(&pdmac->pool_lock, flags); + spin_lock_irqsave(&pl330->pool_lock, flags); while (!list_empty(&first->node)) { desc = list_entry(first->node.next, struct dma_pl330_desc, node); - list_move_tail(&desc->node, &pdmac->desc_pool); + list_move_tail(&desc->node, &pl330->desc_pool); } - list_move_tail(&first->node, &pdmac->desc_pool); + list_move_tail(&first->node, &pl330->desc_pool); - spin_unlock_irqrestore(&pdmac->pool_lock, flags); + spin_unlock_irqrestore(&pl330->pool_lock, flags); } static struct dma_async_tx_descriptor * @@ -2820,12 +2527,12 @@ pl330_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl, desc = pl330_get_desc(pch); if (!desc) { - struct dma_pl330_dmac *pdmac = pch->dmac; + struct pl330_dmac *pl330 = pch->dmac; - dev_err(pch->dmac->pif.dev, + dev_err(pch->dmac->ddma.dev, "%s:%d Unable to fetch desc\n", __func__, __LINE__); - __pl330_giveback_desc(pdmac, first); + __pl330_giveback_desc(pl330, first); return NULL; } @@ -2838,19 +2545,18 @@ pl330_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl, if (direction == DMA_MEM_TO_DEV) { desc->rqcfg.src_inc = 1; desc->rqcfg.dst_inc = 0; - desc->req.rqtype = MEMTODEV; fill_px(&desc->px, addr, sg_dma_address(sg), sg_dma_len(sg)); } else { desc->rqcfg.src_inc = 0; desc->rqcfg.dst_inc = 1; - desc->req.rqtype = DEVTOMEM; fill_px(&desc->px, sg_dma_address(sg), addr, sg_dma_len(sg)); } desc->rqcfg.brst_size = pch->burst_sz; desc->rqcfg.brst_len = 1; + desc->rqtype = direction; } /* Return the last desc in the chain */ @@ -2890,9 +2596,9 @@ static int pl330_probe(struct amba_device *adev, const struct amba_id *id) { struct dma_pl330_platdata *pdat; - struct dma_pl330_dmac *pdmac; + struct pl330_config *pcfg; + struct pl330_dmac *pl330; struct dma_pl330_chan *pch, *_p; - struct pl330_info *pi; struct dma_device *pd; struct resource *res; int i, ret, irq; @@ -2905,30 +2611,27 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id) return ret; /* Allocate a new DMAC and its Channels */ - pdmac = devm_kzalloc(&adev->dev, sizeof(*pdmac), GFP_KERNEL); - if (!pdmac) { + pl330 = devm_kzalloc(&adev->dev, sizeof(*pl330), GFP_KERNEL); + if (!pl330) { dev_err(&adev->dev, "unable to allocate mem\n"); return -ENOMEM; } - pi = &pdmac->pif; - pi->dev = &adev->dev; - pi->pl330_data = NULL; - pi->mcbufsz = pdat ? pdat->mcbuf_sz : 0; + pl330->mcbufsz = pdat ? pdat->mcbuf_sz : 0; res = &adev->res; - pi->base = devm_ioremap_resource(&adev->dev, res); - if (IS_ERR(pi->base)) - return PTR_ERR(pi->base); + pl330->base = devm_ioremap_resource(&adev->dev, res); + if (IS_ERR(pl330->base)) + return PTR_ERR(pl330->base); - amba_set_drvdata(adev, pdmac); + amba_set_drvdata(adev, pl330); for (i = 0; i < AMBA_NR_IRQS; i++) { irq = adev->irq[i]; if (irq) { ret = devm_request_irq(&adev->dev, irq, pl330_irq_handler, 0, - dev_name(&adev->dev), pi); + dev_name(&adev->dev), pl330); if (ret) return ret; } else { @@ -2936,38 +2639,40 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id) } } - pi->pcfg.periph_id = adev->periphid; - ret = pl330_add(pi); + pcfg = &pl330->pcfg; + + pcfg->periph_id = adev->periphid; + ret = pl330_add(pl330); if (ret) return ret; - INIT_LIST_HEAD(&pdmac->desc_pool); - spin_lock_init(&pdmac->pool_lock); + INIT_LIST_HEAD(&pl330->desc_pool); + spin_lock_init(&pl330->pool_lock); /* Create a descriptor pool of default size */ - if (!add_desc(pdmac, GFP_KERNEL, NR_DEFAULT_DESC)) + if (!add_desc(pl330, GFP_KERNEL, NR_DEFAULT_DESC)) dev_warn(&adev->dev, "unable to allocate desc\n"); - pd = &pdmac->ddma; + pd = &pl330->ddma; INIT_LIST_HEAD(&pd->channels); /* Initialize channel parameters */ if (pdat) - num_chan = max_t(int, pdat->nr_valid_peri, pi->pcfg.num_chan); + num_chan = max_t(int, pdat->nr_valid_peri, pcfg->num_chan); else - num_chan = max_t(int, pi->pcfg.num_peri, pi->pcfg.num_chan); + num_chan = max_t(int, pcfg->num_peri, pcfg->num_chan); - pdmac->num_peripherals = num_chan; + pl330->num_peripherals = num_chan; - pdmac->peripherals = kzalloc(num_chan * sizeof(*pch), GFP_KERNEL); - if (!pdmac->peripherals) { + pl330->peripherals = kzalloc(num_chan * sizeof(*pch), GFP_KERNEL); + if (!pl330->peripherals) { ret = -ENOMEM; - dev_err(&adev->dev, "unable to allocate pdmac->peripherals\n"); + dev_err(&adev->dev, "unable to allocate pl330->peripherals\n"); goto probe_err2; } for (i = 0; i < num_chan; i++) { - pch = &pdmac->peripherals[i]; + pch = &pl330->peripherals[i]; if (!adev->dev.of_node) pch->chan.private = pdat ? &pdat->peri_id[i] : NULL; else @@ -2977,9 +2682,9 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id) INIT_LIST_HEAD(&pch->work_list); INIT_LIST_HEAD(&pch->completed_list); spin_lock_init(&pch->lock); - pch->pl330_chid = NULL; + pch->thread = NULL; pch->chan.device = pd; - pch->dmac = pdmac; + pch->dmac = pl330; /* Add the channel to the DMAC list */ list_add_tail(&pch->chan.device_node, &pd->channels); @@ -2990,7 +2695,7 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id) pd->cap_mask = pdat->cap_mask; } else { dma_cap_set(DMA_MEMCPY, pd->cap_mask); - if (pi->pcfg.num_peri) { + if (pcfg->num_peri) { dma_cap_set(DMA_SLAVE, pd->cap_mask); dma_cap_set(DMA_CYCLIC, pd->cap_mask); dma_cap_set(DMA_PRIVATE, pd->cap_mask); @@ -3015,14 +2720,14 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id) if (adev->dev.of_node) { ret = of_dma_controller_register(adev->dev.of_node, - of_dma_pl330_xlate, pdmac); + of_dma_pl330_xlate, pl330); if (ret) { dev_err(&adev->dev, "unable to register DMA to the generic DT DMA helpers\n"); } } - adev->dev.dma_parms = &pdmac->dma_parms; + adev->dev.dma_parms = &pl330->dma_parms; /* * This is the limit for transfers with a buswidth of 1, larger @@ -3037,14 +2742,13 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id) "Loaded driver for PL330 DMAC-%d\n", adev->periphid); dev_info(&adev->dev, "\tDBUFF-%ux%ubytes Num_Chans-%u Num_Peri-%u Num_Events-%u\n", - pi->pcfg.data_buf_dep, - pi->pcfg.data_bus_width / 8, pi->pcfg.num_chan, - pi->pcfg.num_peri, pi->pcfg.num_events); + pcfg->data_buf_dep, pcfg->data_bus_width / 8, pcfg->num_chan, + pcfg->num_peri, pcfg->num_events); return 0; probe_err3: /* Idle the DMAC */ - list_for_each_entry_safe(pch, _p, &pdmac->ddma.channels, + list_for_each_entry_safe(pch, _p, &pl330->ddma.channels, chan.device_node) { /* Remove the channel */ @@ -3055,27 +2759,23 @@ probe_err3: pl330_free_chan_resources(&pch->chan); } probe_err2: - pl330_del(pi); + pl330_del(pl330); return ret; } static int pl330_remove(struct amba_device *adev) { - struct dma_pl330_dmac *pdmac = amba_get_drvdata(adev); + struct pl330_dmac *pl330 = amba_get_drvdata(adev); struct dma_pl330_chan *pch, *_p; - struct pl330_info *pi; - - if (!pdmac) - return 0; if (adev->dev.of_node) of_dma_controller_free(adev->dev.of_node); - dma_async_device_unregister(&pdmac->ddma); + dma_async_device_unregister(&pl330->ddma); /* Idle the DMAC */ - list_for_each_entry_safe(pch, _p, &pdmac->ddma.channels, + list_for_each_entry_safe(pch, _p, &pl330->ddma.channels, chan.device_node) { /* Remove the channel */ @@ -3086,9 +2786,7 @@ static int pl330_remove(struct amba_device *adev) pl330_free_chan_resources(&pch->chan); } - pi = &pdmac->pif; - - pl330_del(pi); + pl330_del(pl330); return 0; } diff --git a/drivers/dma/qcom_bam_dma.c b/drivers/dma/qcom_bam_dma.c new file mode 100644 index 0000000..7a4bbb0 --- /dev/null +++ b/drivers/dma/qcom_bam_dma.c @@ -0,0 +1,1127 @@ +/* + * Copyright (c) 2013-2014, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ +/* + * QCOM BAM DMA engine driver + * + * QCOM BAM DMA blocks are distributed amongst a number of the on-chip + * peripherals on the MSM 8x74. The configuration of the channels are dependent + * on the way they are hard wired to that specific peripheral. The peripheral + * device tree entries specify the configuration of each channel. + * + * The DMA controller requires the use of external memory for storage of the + * hardware descriptors for each channel. The descriptor FIFO is accessed as a + * circular buffer and operations are managed according to the offset within the + * FIFO. After pipe/channel reset, all of the pipe registers and internal state + * are back to defaults. + * + * During DMA operations, we write descriptors to the FIFO, being careful to + * handle wrapping and then write the last FIFO offset to that channel's + * P_EVNT_REG register to kick off the transaction. The P_SW_OFSTS register + * indicates the current FIFO offset that is being processed, so there is some + * indication of where the hardware is currently working. + */ + +#include <linux/kernel.h> +#include <linux/io.h> +#include <linux/init.h> +#include <linux/slab.h> +#include <linux/module.h> +#include <linux/interrupt.h> +#include <linux/dma-mapping.h> +#include <linux/scatterlist.h> +#include <linux/device.h> +#include <linux/platform_device.h> +#include <linux/of.h> +#include <linux/of_address.h> +#include <linux/of_irq.h> +#include <linux/of_dma.h> +#include <linux/clk.h> +#include <linux/dmaengine.h> + +#include "dmaengine.h" +#include "virt-dma.h" + +struct bam_desc_hw { + u32 addr; /* Buffer physical address */ + u16 size; /* Buffer size in bytes */ + u16 flags; +}; + +#define DESC_FLAG_INT BIT(15) +#define DESC_FLAG_EOT BIT(14) +#define DESC_FLAG_EOB BIT(13) +#define DESC_FLAG_NWD BIT(12) + +struct bam_async_desc { + struct virt_dma_desc vd; + + u32 num_desc; + u32 xfer_len; + + /* transaction flags, EOT|EOB|NWD */ + u16 flags; + + struct bam_desc_hw *curr_desc; + + enum dma_transfer_direction dir; + size_t length; + struct bam_desc_hw desc[0]; +}; + +#define BAM_CTRL 0x0000 +#define BAM_REVISION 0x0004 +#define BAM_SW_REVISION 0x0080 +#define BAM_NUM_PIPES 0x003C +#define BAM_TIMER 0x0040 +#define BAM_TIMER_CTRL 0x0044 +#define BAM_DESC_CNT_TRSHLD 0x0008 +#define BAM_IRQ_SRCS 0x000C +#define BAM_IRQ_SRCS_MSK 0x0010 +#define BAM_IRQ_SRCS_UNMASKED 0x0030 +#define BAM_IRQ_STTS 0x0014 +#define BAM_IRQ_CLR 0x0018 +#define BAM_IRQ_EN 0x001C +#define BAM_CNFG_BITS 0x007C +#define BAM_IRQ_SRCS_EE(ee) (0x0800 + ((ee) * 0x80)) +#define BAM_IRQ_SRCS_MSK_EE(ee) (0x0804 + ((ee) * 0x80)) +#define BAM_P_CTRL(pipe) (0x1000 + ((pipe) * 0x1000)) +#define BAM_P_RST(pipe) (0x1004 + ((pipe) * 0x1000)) +#define BAM_P_HALT(pipe) (0x1008 + ((pipe) * 0x1000)) +#define BAM_P_IRQ_STTS(pipe) (0x1010 + ((pipe) * 0x1000)) +#define BAM_P_IRQ_CLR(pipe) (0x1014 + ((pipe) * 0x1000)) +#define BAM_P_IRQ_EN(pipe) (0x1018 + ((pipe) * 0x1000)) +#define BAM_P_EVNT_DEST_ADDR(pipe) (0x182C + ((pipe) * 0x1000)) +#define BAM_P_EVNT_REG(pipe) (0x1818 + ((pipe) * 0x1000)) +#define BAM_P_SW_OFSTS(pipe) (0x1800 + ((pipe) * 0x1000)) +#define BAM_P_DATA_FIFO_ADDR(pipe) (0x1824 + ((pipe) * 0x1000)) +#define BAM_P_DESC_FIFO_ADDR(pipe) (0x181C + ((pipe) * 0x1000)) +#define BAM_P_EVNT_TRSHLD(pipe) (0x1828 + ((pipe) * 0x1000)) +#define BAM_P_FIFO_SIZES(pipe) (0x1820 + ((pipe) * 0x1000)) + +/* BAM CTRL */ +#define BAM_SW_RST BIT(0) +#define BAM_EN BIT(1) +#define BAM_EN_ACCUM BIT(4) +#define BAM_TESTBUS_SEL_SHIFT 5 +#define BAM_TESTBUS_SEL_MASK 0x3F +#define BAM_DESC_CACHE_SEL_SHIFT 13 +#define BAM_DESC_CACHE_SEL_MASK 0x3 +#define BAM_CACHED_DESC_STORE BIT(15) +#define IBC_DISABLE BIT(16) + +/* BAM REVISION */ +#define REVISION_SHIFT 0 +#define REVISION_MASK 0xFF +#define NUM_EES_SHIFT 8 +#define NUM_EES_MASK 0xF +#define CE_BUFFER_SIZE BIT(13) +#define AXI_ACTIVE BIT(14) +#define USE_VMIDMT BIT(15) +#define SECURED BIT(16) +#define BAM_HAS_NO_BYPASS BIT(17) +#define HIGH_FREQUENCY_BAM BIT(18) +#define INACTIV_TMRS_EXST BIT(19) +#define NUM_INACTIV_TMRS BIT(20) +#define DESC_CACHE_DEPTH_SHIFT 21 +#define DESC_CACHE_DEPTH_1 (0 << DESC_CACHE_DEPTH_SHIFT) +#define DESC_CACHE_DEPTH_2 (1 << DESC_CACHE_DEPTH_SHIFT) +#define DESC_CACHE_DEPTH_3 (2 << DESC_CACHE_DEPTH_SHIFT) +#define DESC_CACHE_DEPTH_4 (3 << DESC_CACHE_DEPTH_SHIFT) +#define CMD_DESC_EN BIT(23) +#define INACTIV_TMR_BASE_SHIFT 24 +#define INACTIV_TMR_BASE_MASK 0xFF + +/* BAM NUM PIPES */ +#define BAM_NUM_PIPES_SHIFT 0 +#define BAM_NUM_PIPES_MASK 0xFF +#define PERIPH_NON_PIPE_GRP_SHIFT 16 +#define PERIPH_NON_PIP_GRP_MASK 0xFF +#define BAM_NON_PIPE_GRP_SHIFT 24 +#define BAM_NON_PIPE_GRP_MASK 0xFF + +/* BAM CNFG BITS */ +#define BAM_PIPE_CNFG BIT(2) +#define BAM_FULL_PIPE BIT(11) +#define BAM_NO_EXT_P_RST BIT(12) +#define BAM_IBC_DISABLE BIT(13) +#define BAM_SB_CLK_REQ BIT(14) +#define BAM_PSM_CSW_REQ BIT(15) +#define BAM_PSM_P_RES BIT(16) +#define BAM_AU_P_RES BIT(17) +#define BAM_SI_P_RES BIT(18) +#define BAM_WB_P_RES BIT(19) +#define BAM_WB_BLK_CSW BIT(20) +#define BAM_WB_CSW_ACK_IDL BIT(21) +#define BAM_WB_RETR_SVPNT BIT(22) +#define BAM_WB_DSC_AVL_P_RST BIT(23) +#define BAM_REG_P_EN BIT(24) +#define BAM_PSM_P_HD_DATA BIT(25) +#define BAM_AU_ACCUMED BIT(26) +#define BAM_CMD_ENABLE BIT(27) + +#define BAM_CNFG_BITS_DEFAULT (BAM_PIPE_CNFG | \ + BAM_NO_EXT_P_RST | \ + BAM_IBC_DISABLE | \ + BAM_SB_CLK_REQ | \ + BAM_PSM_CSW_REQ | \ + BAM_PSM_P_RES | \ + BAM_AU_P_RES | \ + BAM_SI_P_RES | \ + BAM_WB_P_RES | \ + BAM_WB_BLK_CSW | \ + BAM_WB_CSW_ACK_IDL | \ + BAM_WB_RETR_SVPNT | \ + BAM_WB_DSC_AVL_P_RST | \ + BAM_REG_P_EN | \ + BAM_PSM_P_HD_DATA | \ + BAM_AU_ACCUMED | \ + BAM_CMD_ENABLE) + +/* PIPE CTRL */ +#define P_EN BIT(1) +#define P_DIRECTION BIT(3) +#define P_SYS_STRM BIT(4) +#define P_SYS_MODE BIT(5) +#define P_AUTO_EOB BIT(6) +#define P_AUTO_EOB_SEL_SHIFT 7 +#define P_AUTO_EOB_SEL_512 (0 << P_AUTO_EOB_SEL_SHIFT) +#define P_AUTO_EOB_SEL_256 (1 << P_AUTO_EOB_SEL_SHIFT) +#define P_AUTO_EOB_SEL_128 (2 << P_AUTO_EOB_SEL_SHIFT) +#define P_AUTO_EOB_SEL_64 (3 << P_AUTO_EOB_SEL_SHIFT) +#define P_PREFETCH_LIMIT_SHIFT 9 +#define P_PREFETCH_LIMIT_32 (0 << P_PREFETCH_LIMIT_SHIFT) +#define P_PREFETCH_LIMIT_16 (1 << P_PREFETCH_LIMIT_SHIFT) +#define P_PREFETCH_LIMIT_4 (2 << P_PREFETCH_LIMIT_SHIFT) +#define P_WRITE_NWD BIT(11) +#define P_LOCK_GROUP_SHIFT 16 +#define P_LOCK_GROUP_MASK 0x1F + +/* BAM_DESC_CNT_TRSHLD */ +#define CNT_TRSHLD 0xffff +#define DEFAULT_CNT_THRSHLD 0x4 + +/* BAM_IRQ_SRCS */ +#define BAM_IRQ BIT(31) +#define P_IRQ 0x7fffffff + +/* BAM_IRQ_SRCS_MSK */ +#define BAM_IRQ_MSK BAM_IRQ +#define P_IRQ_MSK P_IRQ + +/* BAM_IRQ_STTS */ +#define BAM_TIMER_IRQ BIT(4) +#define BAM_EMPTY_IRQ BIT(3) +#define BAM_ERROR_IRQ BIT(2) +#define BAM_HRESP_ERR_IRQ BIT(1) + +/* BAM_IRQ_CLR */ +#define BAM_TIMER_CLR BIT(4) +#define BAM_EMPTY_CLR BIT(3) +#define BAM_ERROR_CLR BIT(2) +#define BAM_HRESP_ERR_CLR BIT(1) + +/* BAM_IRQ_EN */ +#define BAM_TIMER_EN BIT(4) +#define BAM_EMPTY_EN BIT(3) +#define BAM_ERROR_EN BIT(2) +#define BAM_HRESP_ERR_EN BIT(1) + +/* BAM_P_IRQ_EN */ +#define P_PRCSD_DESC_EN BIT(0) +#define P_TIMER_EN BIT(1) +#define P_WAKE_EN BIT(2) +#define P_OUT_OF_DESC_EN BIT(3) +#define P_ERR_EN BIT(4) +#define P_TRNSFR_END_EN BIT(5) +#define P_DEFAULT_IRQS_EN (P_PRCSD_DESC_EN | P_ERR_EN | P_TRNSFR_END_EN) + +/* BAM_P_SW_OFSTS */ +#define P_SW_OFSTS_MASK 0xffff + +#define BAM_DESC_FIFO_SIZE SZ_32K +#define MAX_DESCRIPTORS (BAM_DESC_FIFO_SIZE / sizeof(struct bam_desc_hw) - 1) +#define BAM_MAX_DATA_SIZE (SZ_32K - 8) + +struct bam_chan { + struct virt_dma_chan vc; + + struct bam_device *bdev; + + /* configuration from device tree */ + u32 id; + + struct bam_async_desc *curr_txd; /* current running dma */ + + /* runtime configuration */ + struct dma_slave_config slave; + + /* fifo storage */ + struct bam_desc_hw *fifo_virt; + dma_addr_t fifo_phys; + + /* fifo markers */ + unsigned short head; /* start of active descriptor entries */ + unsigned short tail; /* end of active descriptor entries */ + + unsigned int initialized; /* is the channel hw initialized? */ + unsigned int paused; /* is the channel paused? */ + unsigned int reconfigure; /* new slave config? */ + + struct list_head node; +}; + +static inline struct bam_chan *to_bam_chan(struct dma_chan *common) +{ + return container_of(common, struct bam_chan, vc.chan); +} + +struct bam_device { + void __iomem *regs; + struct device *dev; + struct dma_device common; + struct device_dma_parameters dma_parms; + struct bam_chan *channels; + u32 num_channels; + + /* execution environment ID, from DT */ + u32 ee; + + struct clk *bamclk; + int irq; + + /* dma start transaction tasklet */ + struct tasklet_struct task; +}; + +/** + * bam_reset_channel - Reset individual BAM DMA channel + * @bchan: bam channel + * + * This function resets a specific BAM channel + */ +static void bam_reset_channel(struct bam_chan *bchan) +{ + struct bam_device *bdev = bchan->bdev; + + lockdep_assert_held(&bchan->vc.lock); + + /* reset channel */ + writel_relaxed(1, bdev->regs + BAM_P_RST(bchan->id)); + writel_relaxed(0, bdev->regs + BAM_P_RST(bchan->id)); + + /* don't allow cpu to reorder BAM register accesses done after this */ + wmb(); + + /* make sure hw is initialized when channel is used the first time */ + bchan->initialized = 0; +} + +/** + * bam_chan_init_hw - Initialize channel hardware + * @bchan: bam channel + * + * This function resets and initializes the BAM channel + */ +static void bam_chan_init_hw(struct bam_chan *bchan, + enum dma_transfer_direction dir) +{ + struct bam_device *bdev = bchan->bdev; + u32 val; + + /* Reset the channel to clear internal state of the FIFO */ + bam_reset_channel(bchan); + + /* + * write out 8 byte aligned address. We have enough space for this + * because we allocated 1 more descriptor (8 bytes) than we can use + */ + writel_relaxed(ALIGN(bchan->fifo_phys, sizeof(struct bam_desc_hw)), + bdev->regs + BAM_P_DESC_FIFO_ADDR(bchan->id)); + writel_relaxed(BAM_DESC_FIFO_SIZE, bdev->regs + + BAM_P_FIFO_SIZES(bchan->id)); + + /* enable the per pipe interrupts, enable EOT, ERR, and INT irqs */ + writel_relaxed(P_DEFAULT_IRQS_EN, bdev->regs + BAM_P_IRQ_EN(bchan->id)); + + /* unmask the specific pipe and EE combo */ + val = readl_relaxed(bdev->regs + BAM_IRQ_SRCS_MSK_EE(bdev->ee)); + val |= BIT(bchan->id); + writel_relaxed(val, bdev->regs + BAM_IRQ_SRCS_MSK_EE(bdev->ee)); + + /* don't allow cpu to reorder the channel enable done below */ + wmb(); + + /* set fixed direction and mode, then enable channel */ + val = P_EN | P_SYS_MODE; + if (dir == DMA_DEV_TO_MEM) + val |= P_DIRECTION; + + writel_relaxed(val, bdev->regs + BAM_P_CTRL(bchan->id)); + + bchan->initialized = 1; + + /* init FIFO pointers */ + bchan->head = 0; + bchan->tail = 0; +} + +/** + * bam_alloc_chan - Allocate channel resources for DMA channel. + * @chan: specified channel + * + * This function allocates the FIFO descriptor memory + */ +static int bam_alloc_chan(struct dma_chan *chan) +{ + struct bam_chan *bchan = to_bam_chan(chan); + struct bam_device *bdev = bchan->bdev; + + if (bchan->fifo_virt) + return 0; + + /* allocate FIFO descriptor space, but only if necessary */ + bchan->fifo_virt = dma_alloc_writecombine(bdev->dev, BAM_DESC_FIFO_SIZE, + &bchan->fifo_phys, GFP_KERNEL); + + if (!bchan->fifo_virt) { + dev_err(bdev->dev, "Failed to allocate desc fifo\n"); + return -ENOMEM; + } + + return 0; +} + +/** + * bam_free_chan - Frees dma resources associated with specific channel + * @chan: specified channel + * + * Free the allocated fifo descriptor memory and channel resources + * + */ +static void bam_free_chan(struct dma_chan *chan) +{ + struct bam_chan *bchan = to_bam_chan(chan); + struct bam_device *bdev = bchan->bdev; + u32 val; + unsigned long flags; + + vchan_free_chan_resources(to_virt_chan(chan)); + + if (bchan->curr_txd) { + dev_err(bchan->bdev->dev, "Cannot free busy channel\n"); + return; + } + + spin_lock_irqsave(&bchan->vc.lock, flags); + bam_reset_channel(bchan); + spin_unlock_irqrestore(&bchan->vc.lock, flags); + + dma_free_writecombine(bdev->dev, BAM_DESC_FIFO_SIZE, bchan->fifo_virt, + bchan->fifo_phys); + bchan->fifo_virt = NULL; + + /* mask irq for pipe/channel */ + val = readl_relaxed(bdev->regs + BAM_IRQ_SRCS_MSK_EE(bdev->ee)); + val &= ~BIT(bchan->id); + writel_relaxed(val, bdev->regs + BAM_IRQ_SRCS_MSK_EE(bdev->ee)); + + /* disable irq */ + writel_relaxed(0, bdev->regs + BAM_P_IRQ_EN(bchan->id)); +} + +/** + * bam_slave_config - set slave configuration for channel + * @chan: dma channel + * @cfg: slave configuration + * + * Sets slave configuration for channel + * + */ +static void bam_slave_config(struct bam_chan *bchan, + struct dma_slave_config *cfg) +{ + memcpy(&bchan->slave, cfg, sizeof(*cfg)); + bchan->reconfigure = 1; +} + +/** + * bam_prep_slave_sg - Prep slave sg transaction + * + * @chan: dma channel + * @sgl: scatter gather list + * @sg_len: length of sg + * @direction: DMA transfer direction + * @flags: DMA flags + * @context: transfer context (unused) + */ +static struct dma_async_tx_descriptor *bam_prep_slave_sg(struct dma_chan *chan, + struct scatterlist *sgl, unsigned int sg_len, + enum dma_transfer_direction direction, unsigned long flags, + void *context) +{ + struct bam_chan *bchan = to_bam_chan(chan); + struct bam_device *bdev = bchan->bdev; + struct bam_async_desc *async_desc; + struct scatterlist *sg; + u32 i; + struct bam_desc_hw *desc; + unsigned int num_alloc = 0; + + + if (!is_slave_direction(direction)) { + dev_err(bdev->dev, "invalid dma direction\n"); + return NULL; + } + + /* calculate number of required entries */ + for_each_sg(sgl, sg, sg_len, i) + num_alloc += DIV_ROUND_UP(sg_dma_len(sg), BAM_MAX_DATA_SIZE); + + /* allocate enough room to accomodate the number of entries */ + async_desc = kzalloc(sizeof(*async_desc) + + (num_alloc * sizeof(struct bam_desc_hw)), GFP_NOWAIT); + + if (!async_desc) + goto err_out; + + if (flags & DMA_PREP_FENCE) + async_desc->flags |= DESC_FLAG_NWD; + + if (flags & DMA_PREP_INTERRUPT) + async_desc->flags |= DESC_FLAG_EOT; + else + async_desc->flags |= DESC_FLAG_INT; + + async_desc->num_desc = num_alloc; + async_desc->curr_desc = async_desc->desc; + async_desc->dir = direction; + + /* fill in temporary descriptors */ + desc = async_desc->desc; + for_each_sg(sgl, sg, sg_len, i) { + unsigned int remainder = sg_dma_len(sg); + unsigned int curr_offset = 0; + + do { + desc->addr = sg_dma_address(sg) + curr_offset; + + if (remainder > BAM_MAX_DATA_SIZE) { + desc->size = BAM_MAX_DATA_SIZE; + remainder -= BAM_MAX_DATA_SIZE; + curr_offset += BAM_MAX_DATA_SIZE; + } else { + desc->size = remainder; + remainder = 0; + } + + async_desc->length += desc->size; + desc++; + } while (remainder > 0); + } + + return vchan_tx_prep(&bchan->vc, &async_desc->vd, flags); + +err_out: + kfree(async_desc); + return NULL; +} + +/** + * bam_dma_terminate_all - terminate all transactions on a channel + * @bchan: bam dma channel + * + * Dequeues and frees all transactions + * No callbacks are done + * + */ +static void bam_dma_terminate_all(struct bam_chan *bchan) +{ + unsigned long flag; + LIST_HEAD(head); + + /* remove all transactions, including active transaction */ + spin_lock_irqsave(&bchan->vc.lock, flag); + if (bchan->curr_txd) { + list_add(&bchan->curr_txd->vd.node, &bchan->vc.desc_issued); + bchan->curr_txd = NULL; + } + + vchan_get_all_descriptors(&bchan->vc, &head); + spin_unlock_irqrestore(&bchan->vc.lock, flag); + + vchan_dma_desc_free_list(&bchan->vc, &head); +} + +/** + * bam_control - DMA device control + * @chan: dma channel + * @cmd: control cmd + * @arg: cmd argument + * + * Perform DMA control command + * + */ +static int bam_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd, + unsigned long arg) +{ + struct bam_chan *bchan = to_bam_chan(chan); + struct bam_device *bdev = bchan->bdev; + int ret = 0; + unsigned long flag; + + switch (cmd) { + case DMA_PAUSE: + spin_lock_irqsave(&bchan->vc.lock, flag); + writel_relaxed(1, bdev->regs + BAM_P_HALT(bchan->id)); + bchan->paused = 1; + spin_unlock_irqrestore(&bchan->vc.lock, flag); + break; + + case DMA_RESUME: + spin_lock_irqsave(&bchan->vc.lock, flag); + writel_relaxed(0, bdev->regs + BAM_P_HALT(bchan->id)); + bchan->paused = 0; + spin_unlock_irqrestore(&bchan->vc.lock, flag); + break; + + case DMA_TERMINATE_ALL: + bam_dma_terminate_all(bchan); + break; + + case DMA_SLAVE_CONFIG: + spin_lock_irqsave(&bchan->vc.lock, flag); + bam_slave_config(bchan, (struct dma_slave_config *)arg); + spin_unlock_irqrestore(&bchan->vc.lock, flag); + break; + + default: + ret = -ENXIO; + break; + } + + return ret; +} + +/** + * process_channel_irqs - processes the channel interrupts + * @bdev: bam controller + * + * This function processes the channel interrupts + * + */ +static u32 process_channel_irqs(struct bam_device *bdev) +{ + u32 i, srcs, pipe_stts; + unsigned long flags; + struct bam_async_desc *async_desc; + + srcs = readl_relaxed(bdev->regs + BAM_IRQ_SRCS_EE(bdev->ee)); + + /* return early if no pipe/channel interrupts are present */ + if (!(srcs & P_IRQ)) + return srcs; + + for (i = 0; i < bdev->num_channels; i++) { + struct bam_chan *bchan = &bdev->channels[i]; + + if (!(srcs & BIT(i))) + continue; + + /* clear pipe irq */ + pipe_stts = readl_relaxed(bdev->regs + + BAM_P_IRQ_STTS(i)); + + writel_relaxed(pipe_stts, bdev->regs + + BAM_P_IRQ_CLR(i)); + + spin_lock_irqsave(&bchan->vc.lock, flags); + async_desc = bchan->curr_txd; + + if (async_desc) { + async_desc->num_desc -= async_desc->xfer_len; + async_desc->curr_desc += async_desc->xfer_len; + bchan->curr_txd = NULL; + + /* manage FIFO */ + bchan->head += async_desc->xfer_len; + bchan->head %= MAX_DESCRIPTORS; + + /* + * if complete, process cookie. Otherwise + * push back to front of desc_issued so that + * it gets restarted by the tasklet + */ + if (!async_desc->num_desc) + vchan_cookie_complete(&async_desc->vd); + else + list_add(&async_desc->vd.node, + &bchan->vc.desc_issued); + } + + spin_unlock_irqrestore(&bchan->vc.lock, flags); + } + + return srcs; +} + +/** + * bam_dma_irq - irq handler for bam controller + * @irq: IRQ of interrupt + * @data: callback data + * + * IRQ handler for the bam controller + */ +static irqreturn_t bam_dma_irq(int irq, void *data) +{ + struct bam_device *bdev = data; + u32 clr_mask = 0, srcs = 0; + + srcs |= process_channel_irqs(bdev); + + /* kick off tasklet to start next dma transfer */ + if (srcs & P_IRQ) + tasklet_schedule(&bdev->task); + + if (srcs & BAM_IRQ) + clr_mask = readl_relaxed(bdev->regs + BAM_IRQ_STTS); + + /* don't allow reorder of the various accesses to the BAM registers */ + mb(); + + writel_relaxed(clr_mask, bdev->regs + BAM_IRQ_CLR); + + return IRQ_HANDLED; +} + +/** + * bam_tx_status - returns status of transaction + * @chan: dma channel + * @cookie: transaction cookie + * @txstate: DMA transaction state + * + * Return status of dma transaction + */ +static enum dma_status bam_tx_status(struct dma_chan *chan, dma_cookie_t cookie, + struct dma_tx_state *txstate) +{ + struct bam_chan *bchan = to_bam_chan(chan); + struct virt_dma_desc *vd; + int ret; + size_t residue = 0; + unsigned int i; + unsigned long flags; + + ret = dma_cookie_status(chan, cookie, txstate); + if (ret == DMA_COMPLETE) + return ret; + + if (!txstate) + return bchan->paused ? DMA_PAUSED : ret; + + spin_lock_irqsave(&bchan->vc.lock, flags); + vd = vchan_find_desc(&bchan->vc, cookie); + if (vd) + residue = container_of(vd, struct bam_async_desc, vd)->length; + else if (bchan->curr_txd && bchan->curr_txd->vd.tx.cookie == cookie) + for (i = 0; i < bchan->curr_txd->num_desc; i++) + residue += bchan->curr_txd->curr_desc[i].size; + + spin_unlock_irqrestore(&bchan->vc.lock, flags); + + dma_set_residue(txstate, residue); + + if (ret == DMA_IN_PROGRESS && bchan->paused) + ret = DMA_PAUSED; + + return ret; +} + +/** + * bam_apply_new_config + * @bchan: bam dma channel + * @dir: DMA direction + */ +static void bam_apply_new_config(struct bam_chan *bchan, + enum dma_transfer_direction dir) +{ + struct bam_device *bdev = bchan->bdev; + u32 maxburst; + + if (dir == DMA_DEV_TO_MEM) + maxburst = bchan->slave.src_maxburst; + else + maxburst = bchan->slave.dst_maxburst; + + writel_relaxed(maxburst, bdev->regs + BAM_DESC_CNT_TRSHLD); + + bchan->reconfigure = 0; +} + +/** + * bam_start_dma - start next transaction + * @bchan - bam dma channel + */ +static void bam_start_dma(struct bam_chan *bchan) +{ + struct virt_dma_desc *vd = vchan_next_desc(&bchan->vc); + struct bam_device *bdev = bchan->bdev; + struct bam_async_desc *async_desc; + struct bam_desc_hw *desc; + struct bam_desc_hw *fifo = PTR_ALIGN(bchan->fifo_virt, + sizeof(struct bam_desc_hw)); + + lockdep_assert_held(&bchan->vc.lock); + + if (!vd) + return; + + list_del(&vd->node); + + async_desc = container_of(vd, struct bam_async_desc, vd); + bchan->curr_txd = async_desc; + + /* on first use, initialize the channel hardware */ + if (!bchan->initialized) + bam_chan_init_hw(bchan, async_desc->dir); + + /* apply new slave config changes, if necessary */ + if (bchan->reconfigure) + bam_apply_new_config(bchan, async_desc->dir); + + desc = bchan->curr_txd->curr_desc; + + if (async_desc->num_desc > MAX_DESCRIPTORS) + async_desc->xfer_len = MAX_DESCRIPTORS; + else + async_desc->xfer_len = async_desc->num_desc; + + /* set any special flags on the last descriptor */ + if (async_desc->num_desc == async_desc->xfer_len) + desc[async_desc->xfer_len - 1].flags = async_desc->flags; + else + desc[async_desc->xfer_len - 1].flags |= DESC_FLAG_INT; + + if (bchan->tail + async_desc->xfer_len > MAX_DESCRIPTORS) { + u32 partial = MAX_DESCRIPTORS - bchan->tail; + + memcpy(&fifo[bchan->tail], desc, + partial * sizeof(struct bam_desc_hw)); + memcpy(fifo, &desc[partial], (async_desc->xfer_len - partial) * + sizeof(struct bam_desc_hw)); + } else { + memcpy(&fifo[bchan->tail], desc, + async_desc->xfer_len * sizeof(struct bam_desc_hw)); + } + + bchan->tail += async_desc->xfer_len; + bchan->tail %= MAX_DESCRIPTORS; + + /* ensure descriptor writes and dma start not reordered */ + wmb(); + writel_relaxed(bchan->tail * sizeof(struct bam_desc_hw), + bdev->regs + BAM_P_EVNT_REG(bchan->id)); +} + +/** + * dma_tasklet - DMA IRQ tasklet + * @data: tasklet argument (bam controller structure) + * + * Sets up next DMA operation and then processes all completed transactions + */ +static void dma_tasklet(unsigned long data) +{ + struct bam_device *bdev = (struct bam_device *)data; + struct bam_chan *bchan; + unsigned long flags; + unsigned int i; + + /* go through the channels and kick off transactions */ + for (i = 0; i < bdev->num_channels; i++) { + bchan = &bdev->channels[i]; + spin_lock_irqsave(&bchan->vc.lock, flags); + + if (!list_empty(&bchan->vc.desc_issued) && !bchan->curr_txd) + bam_start_dma(bchan); + spin_unlock_irqrestore(&bchan->vc.lock, flags); + } +} + +/** + * bam_issue_pending - starts pending transactions + * @chan: dma channel + * + * Calls tasklet directly which in turn starts any pending transactions + */ +static void bam_issue_pending(struct dma_chan *chan) +{ + struct bam_chan *bchan = to_bam_chan(chan); + unsigned long flags; + + spin_lock_irqsave(&bchan->vc.lock, flags); + + /* if work pending and idle, start a transaction */ + if (vchan_issue_pending(&bchan->vc) && !bchan->curr_txd) + bam_start_dma(bchan); + + spin_unlock_irqrestore(&bchan->vc.lock, flags); +} + +/** + * bam_dma_free_desc - free descriptor memory + * @vd: virtual descriptor + * + */ +static void bam_dma_free_desc(struct virt_dma_desc *vd) +{ + struct bam_async_desc *async_desc = container_of(vd, + struct bam_async_desc, vd); + + kfree(async_desc); +} + +static struct dma_chan *bam_dma_xlate(struct of_phandle_args *dma_spec, + struct of_dma *of) +{ + struct bam_device *bdev = container_of(of->of_dma_data, + struct bam_device, common); + unsigned int request; + + if (dma_spec->args_count != 1) + return NULL; + + request = dma_spec->args[0]; + if (request >= bdev->num_channels) + return NULL; + + return dma_get_slave_channel(&(bdev->channels[request].vc.chan)); +} + +/** + * bam_init + * @bdev: bam device + * + * Initialization helper for global bam registers + */ +static int bam_init(struct bam_device *bdev) +{ + u32 val; + + /* read revision and configuration information */ + val = readl_relaxed(bdev->regs + BAM_REVISION) >> NUM_EES_SHIFT; + val &= NUM_EES_MASK; + + /* check that configured EE is within range */ + if (bdev->ee >= val) + return -EINVAL; + + val = readl_relaxed(bdev->regs + BAM_NUM_PIPES); + bdev->num_channels = val & BAM_NUM_PIPES_MASK; + + /* s/w reset bam */ + /* after reset all pipes are disabled and idle */ + val = readl_relaxed(bdev->regs + BAM_CTRL); + val |= BAM_SW_RST; + writel_relaxed(val, bdev->regs + BAM_CTRL); + val &= ~BAM_SW_RST; + writel_relaxed(val, bdev->regs + BAM_CTRL); + + /* make sure previous stores are visible before enabling BAM */ + wmb(); + + /* enable bam */ + val |= BAM_EN; + writel_relaxed(val, bdev->regs + BAM_CTRL); + + /* set descriptor threshhold, start with 4 bytes */ + writel_relaxed(DEFAULT_CNT_THRSHLD, bdev->regs + BAM_DESC_CNT_TRSHLD); + + /* Enable default set of h/w workarounds, ie all except BAM_FULL_PIPE */ + writel_relaxed(BAM_CNFG_BITS_DEFAULT, bdev->regs + BAM_CNFG_BITS); + + /* enable irqs for errors */ + writel_relaxed(BAM_ERROR_EN | BAM_HRESP_ERR_EN, + bdev->regs + BAM_IRQ_EN); + + /* unmask global bam interrupt */ + writel_relaxed(BAM_IRQ_MSK, bdev->regs + BAM_IRQ_SRCS_MSK_EE(bdev->ee)); + + return 0; +} + +static void bam_channel_init(struct bam_device *bdev, struct bam_chan *bchan, + u32 index) +{ + bchan->id = index; + bchan->bdev = bdev; + + vchan_init(&bchan->vc, &bdev->common); + bchan->vc.desc_free = bam_dma_free_desc; +} + +static int bam_dma_probe(struct platform_device *pdev) +{ + struct bam_device *bdev; + struct resource *iores; + int ret, i; + + bdev = devm_kzalloc(&pdev->dev, sizeof(*bdev), GFP_KERNEL); + if (!bdev) + return -ENOMEM; + + bdev->dev = &pdev->dev; + + iores = platform_get_resource(pdev, IORESOURCE_MEM, 0); + bdev->regs = devm_ioremap_resource(&pdev->dev, iores); + if (IS_ERR(bdev->regs)) + return PTR_ERR(bdev->regs); + + bdev->irq = platform_get_irq(pdev, 0); + if (bdev->irq < 0) + return bdev->irq; + + ret = of_property_read_u32(pdev->dev.of_node, "qcom,ee", &bdev->ee); + if (ret) { + dev_err(bdev->dev, "Execution environment unspecified\n"); + return ret; + } + + bdev->bamclk = devm_clk_get(bdev->dev, "bam_clk"); + if (IS_ERR(bdev->bamclk)) + return PTR_ERR(bdev->bamclk); + + ret = clk_prepare_enable(bdev->bamclk); + if (ret) { + dev_err(bdev->dev, "failed to prepare/enable clock\n"); + return ret; + } + + ret = bam_init(bdev); + if (ret) + goto err_disable_clk; + + tasklet_init(&bdev->task, dma_tasklet, (unsigned long)bdev); + + bdev->channels = devm_kcalloc(bdev->dev, bdev->num_channels, + sizeof(*bdev->channels), GFP_KERNEL); + + if (!bdev->channels) { + ret = -ENOMEM; + goto err_disable_clk; + } + + /* allocate and initialize channels */ + INIT_LIST_HEAD(&bdev->common.channels); + + for (i = 0; i < bdev->num_channels; i++) + bam_channel_init(bdev, &bdev->channels[i], i); + + ret = devm_request_irq(bdev->dev, bdev->irq, bam_dma_irq, + IRQF_TRIGGER_HIGH, "bam_dma", bdev); + if (ret) + goto err_disable_clk; + + /* set max dma segment size */ + bdev->common.dev = bdev->dev; + bdev->common.dev->dma_parms = &bdev->dma_parms; + ret = dma_set_max_seg_size(bdev->common.dev, BAM_MAX_DATA_SIZE); + if (ret) { + dev_err(bdev->dev, "cannot set maximum segment size\n"); + goto err_disable_clk; + } + + platform_set_drvdata(pdev, bdev); + + /* set capabilities */ + dma_cap_zero(bdev->common.cap_mask); + dma_cap_set(DMA_SLAVE, bdev->common.cap_mask); + + /* initialize dmaengine apis */ + bdev->common.device_alloc_chan_resources = bam_alloc_chan; + bdev->common.device_free_chan_resources = bam_free_chan; + bdev->common.device_prep_slave_sg = bam_prep_slave_sg; + bdev->common.device_control = bam_control; + bdev->common.device_issue_pending = bam_issue_pending; + bdev->common.device_tx_status = bam_tx_status; + bdev->common.dev = bdev->dev; + + ret = dma_async_device_register(&bdev->common); + if (ret) { + dev_err(bdev->dev, "failed to register dma async device\n"); + goto err_disable_clk; + } + + ret = of_dma_controller_register(pdev->dev.of_node, bam_dma_xlate, + &bdev->common); + if (ret) + goto err_unregister_dma; + + return 0; + +err_unregister_dma: + dma_async_device_unregister(&bdev->common); +err_disable_clk: + clk_disable_unprepare(bdev->bamclk); + return ret; +} + +static int bam_dma_remove(struct platform_device *pdev) +{ + struct bam_device *bdev = platform_get_drvdata(pdev); + u32 i; + + of_dma_controller_free(pdev->dev.of_node); + dma_async_device_unregister(&bdev->common); + + /* mask all interrupts for this execution environment */ + writel_relaxed(0, bdev->regs + BAM_IRQ_SRCS_MSK_EE(bdev->ee)); + + devm_free_irq(bdev->dev, bdev->irq, bdev); + + for (i = 0; i < bdev->num_channels; i++) { + bam_dma_terminate_all(&bdev->channels[i]); + tasklet_kill(&bdev->channels[i].vc.task); + + dma_free_writecombine(bdev->dev, BAM_DESC_FIFO_SIZE, + bdev->channels[i].fifo_virt, + bdev->channels[i].fifo_phys); + } + + tasklet_kill(&bdev->task); + + clk_disable_unprepare(bdev->bamclk); + + return 0; +} + +static const struct of_device_id bam_of_match[] = { + { .compatible = "qcom,bam-v1.4.0", }, + {} +}; +MODULE_DEVICE_TABLE(of, bam_of_match); + +static struct platform_driver bam_dma_driver = { + .probe = bam_dma_probe, + .remove = bam_dma_remove, + .driver = { + .name = "bam-dma-engine", + .owner = THIS_MODULE, + .of_match_table = bam_of_match, + }, +}; + +module_platform_driver(bam_dma_driver); + +MODULE_AUTHOR("Andy Gross <agross@codeaurora.org>"); +MODULE_DESCRIPTION("QCOM BAM DMA engine driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/dma/s3c24xx-dma.c b/drivers/dma/s3c24xx-dma.c index 4eddedb..7416572 100644 --- a/drivers/dma/s3c24xx-dma.c +++ b/drivers/dma/s3c24xx-dma.c @@ -164,6 +164,7 @@ struct s3c24xx_sg { * @disrcc: value for source control register * @didstc: value for destination control register * @dcon: base value for dcon register + * @cyclic: indicate cyclic transfer */ struct s3c24xx_txd { struct virt_dma_desc vd; @@ -173,6 +174,7 @@ struct s3c24xx_txd { u32 disrcc; u32 didstc; u32 dcon; + bool cyclic; }; struct s3c24xx_dma_chan; @@ -192,7 +194,7 @@ struct s3c24xx_dma_phy { unsigned int id; bool valid; void __iomem *base; - unsigned int irq; + int irq; struct clk *clk; spinlock_t lock; struct s3c24xx_dma_chan *serving; @@ -669,8 +671,10 @@ static irqreturn_t s3c24xx_dma_irq(int irq, void *data) /* when more sg's are in this txd, start the next one */ if (!list_is_last(txd->at, &txd->dsg_list)) { txd->at = txd->at->next; + if (txd->cyclic) + vchan_cyclic_callback(&txd->vd); s3c24xx_dma_start_next_sg(s3cchan, txd); - } else { + } else if (!txd->cyclic) { s3cchan->at = NULL; vchan_cookie_complete(&txd->vd); @@ -682,6 +686,12 @@ static irqreturn_t s3c24xx_dma_irq(int irq, void *data) s3c24xx_dma_start_next_txd(s3cchan); else s3c24xx_dma_phy_free(s3cchan); + } else { + vchan_cyclic_callback(&txd->vd); + + /* Cyclic: reset at beginning */ + txd->at = txd->dsg_list.next; + s3c24xx_dma_start_next_sg(s3cchan, txd); } } spin_unlock(&s3cchan->vc.lock); @@ -877,6 +887,103 @@ static struct dma_async_tx_descriptor *s3c24xx_dma_prep_memcpy( return vchan_tx_prep(&s3cchan->vc, &txd->vd, flags); } +static struct dma_async_tx_descriptor *s3c24xx_dma_prep_dma_cyclic( + struct dma_chan *chan, dma_addr_t addr, size_t size, size_t period, + enum dma_transfer_direction direction, unsigned long flags) +{ + struct s3c24xx_dma_chan *s3cchan = to_s3c24xx_dma_chan(chan); + struct s3c24xx_dma_engine *s3cdma = s3cchan->host; + const struct s3c24xx_dma_platdata *pdata = s3cdma->pdata; + struct s3c24xx_dma_channel *cdata = &pdata->channels[s3cchan->id]; + struct s3c24xx_txd *txd; + struct s3c24xx_sg *dsg; + unsigned sg_len; + dma_addr_t slave_addr; + u32 hwcfg = 0; + int i; + + dev_dbg(&s3cdma->pdev->dev, + "prepare cyclic transaction of %zu bytes with period %zu from %s\n", + size, period, s3cchan->name); + + if (!is_slave_direction(direction)) { + dev_err(&s3cdma->pdev->dev, + "direction %d unsupported\n", direction); + return NULL; + } + + txd = s3c24xx_dma_get_txd(); + if (!txd) + return NULL; + + txd->cyclic = 1; + + if (cdata->handshake) + txd->dcon |= S3C24XX_DCON_HANDSHAKE; + + switch (cdata->bus) { + case S3C24XX_DMA_APB: + txd->dcon |= S3C24XX_DCON_SYNC_PCLK; + hwcfg |= S3C24XX_DISRCC_LOC_APB; + break; + case S3C24XX_DMA_AHB: + txd->dcon |= S3C24XX_DCON_SYNC_HCLK; + hwcfg |= S3C24XX_DISRCC_LOC_AHB; + break; + } + + /* + * Always assume our peripheral desintation is a fixed + * address in memory. + */ + hwcfg |= S3C24XX_DISRCC_INC_FIXED; + + /* + * Individual dma operations are requested by the slave, + * so serve only single atomic operations (S3C24XX_DCON_SERV_SINGLE). + */ + txd->dcon |= S3C24XX_DCON_SERV_SINGLE; + + if (direction == DMA_MEM_TO_DEV) { + txd->disrcc = S3C24XX_DISRCC_LOC_AHB | + S3C24XX_DISRCC_INC_INCREMENT; + txd->didstc = hwcfg; + slave_addr = s3cchan->cfg.dst_addr; + txd->width = s3cchan->cfg.dst_addr_width; + } else { + txd->disrcc = hwcfg; + txd->didstc = S3C24XX_DIDSTC_LOC_AHB | + S3C24XX_DIDSTC_INC_INCREMENT; + slave_addr = s3cchan->cfg.src_addr; + txd->width = s3cchan->cfg.src_addr_width; + } + + sg_len = size / period; + + for (i = 0; i < sg_len; i++) { + dsg = kzalloc(sizeof(*dsg), GFP_NOWAIT); + if (!dsg) { + s3c24xx_dma_free_txd(txd); + return NULL; + } + list_add_tail(&dsg->node, &txd->dsg_list); + + dsg->len = period; + /* Check last period length */ + if (i == sg_len - 1) + dsg->len = size - period * i; + if (direction == DMA_MEM_TO_DEV) { + dsg->src_addr = addr + period * i; + dsg->dst_addr = slave_addr; + } else { /* DMA_DEV_TO_MEM */ + dsg->src_addr = slave_addr; + dsg->dst_addr = addr + period * i; + } + } + + return vchan_tx_prep(&s3cchan->vc, &txd->vd, flags); +} + static struct dma_async_tx_descriptor *s3c24xx_dma_prep_slave_sg( struct dma_chan *chan, struct scatterlist *sgl, unsigned int sg_len, enum dma_transfer_direction direction, @@ -961,7 +1068,6 @@ static struct dma_async_tx_descriptor *s3c24xx_dma_prep_slave_sg( dsg->src_addr = slave_addr; dsg->dst_addr = sg_dma_address(sg); } - break; } return vchan_tx_prep(&s3cchan->vc, &txd->vd, flags); @@ -1198,6 +1304,7 @@ static int s3c24xx_dma_probe(struct platform_device *pdev) /* Initialize slave engine for SoC internal dedicated peripherals */ dma_cap_set(DMA_SLAVE, s3cdma->slave.cap_mask); + dma_cap_set(DMA_CYCLIC, s3cdma->slave.cap_mask); dma_cap_set(DMA_PRIVATE, s3cdma->slave.cap_mask); s3cdma->slave.dev = &pdev->dev; s3cdma->slave.device_alloc_chan_resources = @@ -1207,6 +1314,7 @@ static int s3c24xx_dma_probe(struct platform_device *pdev) s3cdma->slave.device_tx_status = s3c24xx_dma_tx_status; s3cdma->slave.device_issue_pending = s3c24xx_dma_issue_pending; s3cdma->slave.device_prep_slave_sg = s3c24xx_dma_prep_slave_sg; + s3cdma->slave.device_prep_dma_cyclic = s3c24xx_dma_prep_dma_cyclic; s3cdma->slave.device_control = s3c24xx_dma_control; /* Register as many memcpy channels as there are physical channels */ diff --git a/drivers/dma/sa11x0-dma.c b/drivers/dma/sa11x0-dma.c index ab26d46..4b0ef04 100644 --- a/drivers/dma/sa11x0-dma.c +++ b/drivers/dma/sa11x0-dma.c @@ -113,11 +113,9 @@ struct sa11x0_dma_phy { struct sa11x0_dma_desc *txd_load; unsigned sg_done; struct sa11x0_dma_desc *txd_done; -#ifdef CONFIG_PM_SLEEP u32 dbs[2]; u32 dbt[2]; u32 dcsr; -#endif }; struct sa11x0_dma_dev { @@ -614,7 +612,7 @@ static struct dma_async_tx_descriptor *sa11x0_dma_prep_slave_sg( static struct dma_async_tx_descriptor *sa11x0_dma_prep_dma_cyclic( struct dma_chan *chan, dma_addr_t addr, size_t size, size_t period, - enum dma_transfer_direction dir, unsigned long flags, void *context) + enum dma_transfer_direction dir, unsigned long flags) { struct sa11x0_dma_chan *c = to_sa11x0_dma_chan(chan); struct sa11x0_dma_desc *txd; @@ -984,7 +982,6 @@ static int sa11x0_dma_remove(struct platform_device *pdev) return 0; } -#ifdef CONFIG_PM_SLEEP static int sa11x0_dma_suspend(struct device *dev) { struct sa11x0_dma_dev *d = dev_get_drvdata(dev); @@ -1054,7 +1051,6 @@ static int sa11x0_dma_resume(struct device *dev) return 0; } -#endif static const struct dev_pm_ops sa11x0_dma_pm_ops = { .suspend_noirq = sa11x0_dma_suspend, diff --git a/drivers/dma/sh/Kconfig b/drivers/dma/sh/Kconfig index dadd9e01..0349125 100644 --- a/drivers/dma/sh/Kconfig +++ b/drivers/dma/sh/Kconfig @@ -2,21 +2,39 @@ # DMA engine configuration for sh # +# +# DMA Engine Helpers +# + config SH_DMAE_BASE bool "Renesas SuperH DMA Engine support" - depends on (SUPERH && SH_DMA) || (ARM && ARCH_SHMOBILE) + depends on SUPERH || ARCH_SHMOBILE || COMPILE_TEST + depends on !SUPERH || SH_DMA depends on !SH_DMA_API default y select DMA_ENGINE help Enable support for the Renesas SuperH DMA controllers. +# +# DMA Controllers +# + config SH_DMAE tristate "Renesas SuperH DMAC support" depends on SH_DMAE_BASE help Enable support for the Renesas SuperH DMA controllers. +if SH_DMAE + +config SH_DMAE_R8A73A4 + def_bool y + depends on ARCH_R8A73A4 + depends on OF + +endif + config SUDMAC tristate "Renesas SUDMAC support" depends on SH_DMAE_BASE @@ -29,6 +47,8 @@ config RCAR_HPB_DMAE help Enable support for the Renesas R-Car series DMA controllers. -config SHDMA_R8A73A4 - def_bool y - depends on ARCH_R8A73A4 && SH_DMAE != n +config RCAR_AUDMAC_PP + tristate "Renesas R-Car Audio DMAC Peripheral Peripheral support" + depends on SH_DMAE_BASE + help + Enable support for the Renesas R-Car Audio DMAC Peripheral Peripheral controllers. diff --git a/drivers/dma/sh/Makefile b/drivers/dma/sh/Makefile index e856af2..0a5cfdb 100644 --- a/drivers/dma/sh/Makefile +++ b/drivers/dma/sh/Makefile @@ -1,9 +1,18 @@ +# +# DMA Engine Helpers +# + obj-$(CONFIG_SH_DMAE_BASE) += shdma-base.o shdma-of.o -obj-$(CONFIG_SH_DMAE) += shdma.o + +# +# DMA Controllers +# + shdma-y := shdmac.o -ifeq ($(CONFIG_OF),y) -shdma-$(CONFIG_SHDMA_R8A73A4) += shdma-r8a73a4.o -endif +shdma-$(CONFIG_SH_DMAE_R8A73A4) += shdma-r8a73a4.o shdma-objs := $(shdma-y) +obj-$(CONFIG_SH_DMAE) += shdma.o + obj-$(CONFIG_SUDMAC) += sudmac.o obj-$(CONFIG_RCAR_HPB_DMAE) += rcar-hpbdma.o +obj-$(CONFIG_RCAR_AUDMAC_PP) += rcar-audmapp.o diff --git a/drivers/dma/sh/rcar-audmapp.c b/drivers/dma/sh/rcar-audmapp.c new file mode 100644 index 0000000..dabbf0a --- /dev/null +++ b/drivers/dma/sh/rcar-audmapp.c @@ -0,0 +1,374 @@ +/* + * This is for Renesas R-Car Audio-DMAC-peri-peri. + * + * Copyright (C) 2014 Renesas Electronics Corporation + * Copyright (C) 2014 Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> + * + * based on the drivers/dma/sh/shdma.c + * + * Copyright (C) 2011-2012 Guennadi Liakhovetski <g.liakhovetski@gmx.de> + * Copyright (C) 2009 Nobuhiro Iwamatsu <iwamatsu.nobuhiro@renesas.com> + * Copyright (C) 2009 Renesas Solutions, Inc. All rights reserved. + * Copyright (C) 2007 Freescale Semiconductor, Inc. All rights reserved. + * + * This is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + */ +#include <linux/delay.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/dmaengine.h> +#include <linux/of_dma.h> +#include <linux/platform_data/dma-rcar-audmapp.h> +#include <linux/platform_device.h> +#include <linux/shdma-base.h> + +/* + * DMA register + */ +#define PDMASAR 0x00 +#define PDMADAR 0x04 +#define PDMACHCR 0x0c + +/* PDMACHCR */ +#define PDMACHCR_DE (1 << 0) + +#define AUDMAPP_MAX_CHANNELS 29 + +/* Default MEMCPY transfer size = 2^2 = 4 bytes */ +#define LOG2_DEFAULT_XFER_SIZE 2 +#define AUDMAPP_SLAVE_NUMBER 256 +#define AUDMAPP_LEN_MAX (16 * 1024 * 1024) + +struct audmapp_chan { + struct shdma_chan shdma_chan; + void __iomem *base; + dma_addr_t slave_addr; + u32 chcr; +}; + +struct audmapp_device { + struct shdma_dev shdma_dev; + struct audmapp_pdata *pdata; + struct device *dev; + void __iomem *chan_reg; +}; + +struct audmapp_desc { + struct shdma_desc shdma_desc; + dma_addr_t src; + dma_addr_t dst; +}; + +#define to_shdma_chan(c) container_of(c, struct shdma_chan, dma_chan) + +#define to_chan(chan) container_of(chan, struct audmapp_chan, shdma_chan) +#define to_desc(sdesc) container_of(sdesc, struct audmapp_desc, shdma_desc) +#define to_dev(chan) container_of(chan->shdma_chan.dma_chan.device, \ + struct audmapp_device, shdma_dev.dma_dev) + +static void audmapp_write(struct audmapp_chan *auchan, u32 data, u32 reg) +{ + struct audmapp_device *audev = to_dev(auchan); + struct device *dev = audev->dev; + + dev_dbg(dev, "w %p : %08x\n", auchan->base + reg, data); + + iowrite32(data, auchan->base + reg); +} + +static u32 audmapp_read(struct audmapp_chan *auchan, u32 reg) +{ + return ioread32(auchan->base + reg); +} + +static void audmapp_halt(struct shdma_chan *schan) +{ + struct audmapp_chan *auchan = to_chan(schan); + int i; + + audmapp_write(auchan, 0, PDMACHCR); + + for (i = 0; i < 1024; i++) { + if (0 == audmapp_read(auchan, PDMACHCR)) + return; + udelay(1); + } +} + +static void audmapp_start_xfer(struct shdma_chan *schan, + struct shdma_desc *sdesc) +{ + struct audmapp_chan *auchan = to_chan(schan); + struct audmapp_device *audev = to_dev(auchan); + struct audmapp_desc *desc = to_desc(sdesc); + struct device *dev = audev->dev; + u32 chcr = auchan->chcr | PDMACHCR_DE; + + dev_dbg(dev, "src/dst/chcr = %pad/%pad/%08x\n", + &desc->src, &desc->dst, chcr); + + audmapp_write(auchan, desc->src, PDMASAR); + audmapp_write(auchan, desc->dst, PDMADAR); + audmapp_write(auchan, chcr, PDMACHCR); +} + +static void audmapp_get_config(struct audmapp_chan *auchan, int slave_id, + u32 *chcr, dma_addr_t *dst) +{ + struct audmapp_device *audev = to_dev(auchan); + struct audmapp_pdata *pdata = audev->pdata; + struct audmapp_slave_config *cfg; + int i; + + *chcr = 0; + *dst = 0; + + if (!pdata) { /* DT */ + *chcr = ((u32)slave_id) << 16; + auchan->shdma_chan.slave_id = (slave_id) >> 8; + return; + } + + /* non-DT */ + + if (slave_id >= AUDMAPP_SLAVE_NUMBER) + return; + + for (i = 0, cfg = pdata->slave; i < pdata->slave_num; i++, cfg++) + if (cfg->slave_id == slave_id) { + *chcr = cfg->chcr; + *dst = cfg->dst; + break; + } +} + +static int audmapp_set_slave(struct shdma_chan *schan, int slave_id, + dma_addr_t slave_addr, bool try) +{ + struct audmapp_chan *auchan = to_chan(schan); + u32 chcr; + dma_addr_t dst; + + audmapp_get_config(auchan, slave_id, &chcr, &dst); + + if (try) + return 0; + + auchan->chcr = chcr; + auchan->slave_addr = slave_addr ? : dst; + + return 0; +} + +static int audmapp_desc_setup(struct shdma_chan *schan, + struct shdma_desc *sdesc, + dma_addr_t src, dma_addr_t dst, size_t *len) +{ + struct audmapp_desc *desc = to_desc(sdesc); + + if (*len > (size_t)AUDMAPP_LEN_MAX) + *len = (size_t)AUDMAPP_LEN_MAX; + + desc->src = src; + desc->dst = dst; + + return 0; +} + +static void audmapp_setup_xfer(struct shdma_chan *schan, + int slave_id) +{ +} + +static dma_addr_t audmapp_slave_addr(struct shdma_chan *schan) +{ + struct audmapp_chan *auchan = to_chan(schan); + + return auchan->slave_addr; +} + +static bool audmapp_channel_busy(struct shdma_chan *schan) +{ + struct audmapp_chan *auchan = to_chan(schan); + u32 chcr = audmapp_read(auchan, PDMACHCR); + + return chcr & ~PDMACHCR_DE; +} + +static bool audmapp_desc_completed(struct shdma_chan *schan, + struct shdma_desc *sdesc) +{ + return true; +} + +static struct shdma_desc *audmapp_embedded_desc(void *buf, int i) +{ + return &((struct audmapp_desc *)buf)[i].shdma_desc; +} + +static const struct shdma_ops audmapp_shdma_ops = { + .halt_channel = audmapp_halt, + .desc_setup = audmapp_desc_setup, + .set_slave = audmapp_set_slave, + .start_xfer = audmapp_start_xfer, + .embedded_desc = audmapp_embedded_desc, + .setup_xfer = audmapp_setup_xfer, + .slave_addr = audmapp_slave_addr, + .channel_busy = audmapp_channel_busy, + .desc_completed = audmapp_desc_completed, +}; + +static int audmapp_chan_probe(struct platform_device *pdev, + struct audmapp_device *audev, int id) +{ + struct shdma_dev *sdev = &audev->shdma_dev; + struct audmapp_chan *auchan; + struct shdma_chan *schan; + struct device *dev = audev->dev; + + auchan = devm_kzalloc(dev, sizeof(*auchan), GFP_KERNEL); + if (!auchan) + return -ENOMEM; + + schan = &auchan->shdma_chan; + schan->max_xfer_len = AUDMAPP_LEN_MAX; + + shdma_chan_probe(sdev, schan, id); + + auchan->base = audev->chan_reg + 0x20 + (0x10 * id); + dev_dbg(dev, "%02d : %p / %p", id, auchan->base, audev->chan_reg); + + return 0; +} + +static void audmapp_chan_remove(struct audmapp_device *audev) +{ + struct dma_device *dma_dev = &audev->shdma_dev.dma_dev; + struct shdma_chan *schan; + int i; + + shdma_for_each_chan(schan, &audev->shdma_dev, i) { + BUG_ON(!schan); + shdma_chan_remove(schan); + } + dma_dev->chancnt = 0; +} + +static struct dma_chan *audmapp_of_xlate(struct of_phandle_args *dma_spec, + struct of_dma *ofdma) +{ + dma_cap_mask_t mask; + struct dma_chan *chan; + u32 chcr = dma_spec->args[0]; + + if (dma_spec->args_count != 1) + return NULL; + + dma_cap_zero(mask); + dma_cap_set(DMA_SLAVE, mask); + + chan = dma_request_channel(mask, shdma_chan_filter, NULL); + if (chan) + to_shdma_chan(chan)->hw_req = chcr; + + return chan; +} + +static int audmapp_probe(struct platform_device *pdev) +{ + struct audmapp_pdata *pdata = pdev->dev.platform_data; + struct device_node *np = pdev->dev.of_node; + struct audmapp_device *audev; + struct shdma_dev *sdev; + struct dma_device *dma_dev; + struct resource *res; + int err, i; + + if (np) + of_dma_controller_register(np, audmapp_of_xlate, pdev); + else if (!pdata) + return -ENODEV; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + + audev = devm_kzalloc(&pdev->dev, sizeof(*audev), GFP_KERNEL); + if (!audev) + return -ENOMEM; + + audev->dev = &pdev->dev; + audev->pdata = pdata; + audev->chan_reg = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(audev->chan_reg)) + return PTR_ERR(audev->chan_reg); + + sdev = &audev->shdma_dev; + sdev->ops = &audmapp_shdma_ops; + sdev->desc_size = sizeof(struct audmapp_desc); + + dma_dev = &sdev->dma_dev; + dma_dev->copy_align = LOG2_DEFAULT_XFER_SIZE; + dma_cap_set(DMA_SLAVE, dma_dev->cap_mask); + + err = shdma_init(&pdev->dev, sdev, AUDMAPP_MAX_CHANNELS); + if (err < 0) + return err; + + platform_set_drvdata(pdev, audev); + + /* Create DMA Channel */ + for (i = 0; i < AUDMAPP_MAX_CHANNELS; i++) { + err = audmapp_chan_probe(pdev, audev, i); + if (err) + goto chan_probe_err; + } + + err = dma_async_device_register(dma_dev); + if (err < 0) + goto chan_probe_err; + + return err; + +chan_probe_err: + audmapp_chan_remove(audev); + shdma_cleanup(sdev); + + return err; +} + +static int audmapp_remove(struct platform_device *pdev) +{ + struct audmapp_device *audev = platform_get_drvdata(pdev); + struct dma_device *dma_dev = &audev->shdma_dev.dma_dev; + + dma_async_device_unregister(dma_dev); + + audmapp_chan_remove(audev); + shdma_cleanup(&audev->shdma_dev); + + return 0; +} + +static const struct of_device_id audmapp_of_match[] = { + { .compatible = "renesas,rcar-audmapp", }, + {}, +}; + +static struct platform_driver audmapp_driver = { + .probe = audmapp_probe, + .remove = audmapp_remove, + .driver = { + .owner = THIS_MODULE, + .name = "rcar-audmapp-engine", + .of_match_table = audmapp_of_match, + }, +}; +module_platform_driver(audmapp_driver); + +MODULE_AUTHOR("Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>"); +MODULE_DESCRIPTION("Renesas R-Car Audio DMAC peri-peri driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/dma/sh/rcar-hpbdma.c b/drivers/dma/sh/rcar-hpbdma.c index 3083d90..b212d94 100644 --- a/drivers/dma/sh/rcar-hpbdma.c +++ b/drivers/dma/sh/rcar-hpbdma.c @@ -18,6 +18,7 @@ #include <linux/dmaengine.h> #include <linux/delay.h> +#include <linux/err.h> #include <linux/init.h> #include <linux/interrupt.h> #include <linux/module.h> diff --git a/drivers/dma/sh/shdma-arm.h b/drivers/dma/sh/shdma-arm.h index a2b8258..a1b0ef4 100644 --- a/drivers/dma/sh/shdma-arm.h +++ b/drivers/dma/sh/shdma-arm.h @@ -45,7 +45,7 @@ enum { ((((i) & TS_LOW_BIT) << TS_LOW_SHIFT) |\ (((i) & TS_HI_BIT) << TS_HI_SHIFT)) -#define CHCR_TX(xmit_sz) (DM_FIX | SM_INC | 0x800 | TS_INDEX2VAL((xmit_sz))) -#define CHCR_RX(xmit_sz) (DM_INC | SM_FIX | 0x800 | TS_INDEX2VAL((xmit_sz))) +#define CHCR_TX(xmit_sz) (DM_FIX | SM_INC | RS_ERS | TS_INDEX2VAL((xmit_sz))) +#define CHCR_RX(xmit_sz) (DM_INC | SM_FIX | RS_ERS | TS_INDEX2VAL((xmit_sz))) #endif diff --git a/drivers/dma/sh/shdma-base.c b/drivers/dma/sh/shdma-base.c index 2e7b394..42d4974 100644 --- a/drivers/dma/sh/shdma-base.c +++ b/drivers/dma/sh/shdma-base.c @@ -73,8 +73,7 @@ static void shdma_chan_xfer_ld_queue(struct shdma_chan *schan) static dma_cookie_t shdma_tx_submit(struct dma_async_tx_descriptor *tx) { struct shdma_desc *chunk, *c, *desc = - container_of(tx, struct shdma_desc, async_tx), - *last = desc; + container_of(tx, struct shdma_desc, async_tx); struct shdma_chan *schan = to_shdma_chan(tx->chan); dma_async_tx_callback callback = tx->callback; dma_cookie_t cookie; @@ -98,19 +97,20 @@ static dma_cookie_t shdma_tx_submit(struct dma_async_tx_descriptor *tx) &chunk->node == &schan->ld_free)) break; chunk->mark = DESC_SUBMITTED; - /* Callback goes to the last chunk */ - chunk->async_tx.callback = NULL; + if (chunk->chunks == 1) { + chunk->async_tx.callback = callback; + chunk->async_tx.callback_param = tx->callback_param; + } else { + /* Callback goes to the last chunk */ + chunk->async_tx.callback = NULL; + } chunk->cookie = cookie; list_move_tail(&chunk->node, &schan->ld_queue); - last = chunk; dev_dbg(schan->dev, "submit #%d@%p on %d\n", - tx->cookie, &last->async_tx, schan->id); + tx->cookie, &chunk->async_tx, schan->id); } - last->async_tx.callback = callback; - last->async_tx.callback_param = tx->callback_param; - if (power_up) { int ret; schan->pm_state = SHDMA_PM_BUSY; @@ -206,45 +206,6 @@ static int shdma_setup_slave(struct shdma_chan *schan, int slave_id, return 0; } -/* - * This is the standard shdma filter function to be used as a replacement to the - * "old" method, using the .private pointer. If for some reason you allocate a - * channel without slave data, use something like ERR_PTR(-EINVAL) as a filter - * parameter. If this filter is used, the slave driver, after calling - * dma_request_channel(), will also have to call dmaengine_slave_config() with - * .slave_id, .direction, and either .src_addr or .dst_addr set. - * NOTE: this filter doesn't support multiple DMAC drivers with the DMA_SLAVE - * capability! If this becomes a requirement, hardware glue drivers, using this - * services would have to provide their own filters, which first would check - * the device driver, similar to how other DMAC drivers, e.g., sa11x0-dma.c, do - * this, and only then, in case of a match, call this common filter. - * NOTE 2: This filter function is also used in the DT case by shdma_of_xlate(). - * In that case the MID-RID value is used for slave channel filtering and is - * passed to this function in the "arg" parameter. - */ -bool shdma_chan_filter(struct dma_chan *chan, void *arg) -{ - struct shdma_chan *schan = to_shdma_chan(chan); - struct shdma_dev *sdev = to_shdma_dev(schan->dma_chan.device); - const struct shdma_ops *ops = sdev->ops; - int match = (int)arg; - int ret; - - if (match < 0) - /* No slave requested - arbitrary channel */ - return true; - - if (!schan->dev->of_node && match >= slave_num) - return false; - - ret = ops->set_slave(schan, match, 0, true); - if (ret < 0) - return false; - - return true; -} -EXPORT_SYMBOL(shdma_chan_filter); - static int shdma_alloc_chan_resources(struct dma_chan *chan) { struct shdma_chan *schan = to_shdma_chan(chan); @@ -295,6 +256,51 @@ esetslave: return ret; } +/* + * This is the standard shdma filter function to be used as a replacement to the + * "old" method, using the .private pointer. If for some reason you allocate a + * channel without slave data, use something like ERR_PTR(-EINVAL) as a filter + * parameter. If this filter is used, the slave driver, after calling + * dma_request_channel(), will also have to call dmaengine_slave_config() with + * .slave_id, .direction, and either .src_addr or .dst_addr set. + * NOTE: this filter doesn't support multiple DMAC drivers with the DMA_SLAVE + * capability! If this becomes a requirement, hardware glue drivers, using this + * services would have to provide their own filters, which first would check + * the device driver, similar to how other DMAC drivers, e.g., sa11x0-dma.c, do + * this, and only then, in case of a match, call this common filter. + * NOTE 2: This filter function is also used in the DT case by shdma_of_xlate(). + * In that case the MID-RID value is used for slave channel filtering and is + * passed to this function in the "arg" parameter. + */ +bool shdma_chan_filter(struct dma_chan *chan, void *arg) +{ + struct shdma_chan *schan; + struct shdma_dev *sdev; + int match = (long)arg; + int ret; + + /* Only support channels handled by this driver. */ + if (chan->device->device_alloc_chan_resources != + shdma_alloc_chan_resources) + return false; + + if (match < 0) + /* No slave requested - arbitrary channel */ + return true; + + schan = to_shdma_chan(chan); + if (!schan->dev->of_node && match >= slave_num) + return false; + + sdev = to_shdma_dev(schan->dma_chan.device); + ret = sdev->ops->set_slave(schan, match, 0, true); + if (ret < 0) + return false; + + return true; +} +EXPORT_SYMBOL(shdma_chan_filter); + static dma_async_tx_callback __ld_cleanup(struct shdma_chan *schan, bool all) { struct shdma_desc *desc, *_desc; @@ -304,6 +310,7 @@ static dma_async_tx_callback __ld_cleanup(struct shdma_chan *schan, bool all) dma_async_tx_callback callback = NULL; void *param = NULL; unsigned long flags; + LIST_HEAD(cyclic_list); spin_lock_irqsave(&schan->chan_lock, flags); list_for_each_entry_safe(desc, _desc, &schan->ld_queue, node) { @@ -369,10 +376,16 @@ static dma_async_tx_callback __ld_cleanup(struct shdma_chan *schan, bool all) if (((desc->mark == DESC_COMPLETED || desc->mark == DESC_WAITING) && async_tx_test_ack(&desc->async_tx)) || all) { - /* Remove from ld_queue list */ - desc->mark = DESC_IDLE; - list_move(&desc->node, &schan->ld_free); + if (all || !desc->cyclic) { + /* Remove from ld_queue list */ + desc->mark = DESC_IDLE; + list_move(&desc->node, &schan->ld_free); + } else { + /* reuse as cyclic */ + desc->mark = DESC_SUBMITTED; + list_move_tail(&desc->node, &cyclic_list); + } if (list_empty(&schan->ld_queue)) { dev_dbg(schan->dev, "Bring down channel %d\n", schan->id); @@ -389,6 +402,8 @@ static dma_async_tx_callback __ld_cleanup(struct shdma_chan *schan, bool all) */ schan->dma_chan.completed_cookie = schan->dma_chan.cookie; + list_splice_tail(&cyclic_list, &schan->ld_queue); + spin_unlock_irqrestore(&schan->chan_lock, flags); if (callback) @@ -491,8 +506,8 @@ static struct shdma_desc *shdma_add_desc(struct shdma_chan *schan, } dev_dbg(schan->dev, - "chaining (%u/%u)@%x -> %x with %p, cookie %d\n", - copy_size, *len, *src, *dst, &new->async_tx, + "chaining (%zu/%zu)@%pad -> %pad with %p, cookie %d\n", + copy_size, *len, src, dst, &new->async_tx, new->async_tx.cookie); new->mark = DESC_PREPARED; @@ -521,7 +536,7 @@ static struct shdma_desc *shdma_add_desc(struct shdma_chan *schan, */ static struct dma_async_tx_descriptor *shdma_prep_sg(struct shdma_chan *schan, struct scatterlist *sgl, unsigned int sg_len, dma_addr_t *addr, - enum dma_transfer_direction direction, unsigned long flags) + enum dma_transfer_direction direction, unsigned long flags, bool cyclic) { struct scatterlist *sg; struct shdma_desc *first = NULL, *new = NULL /* compiler... */; @@ -555,8 +570,8 @@ static struct dma_async_tx_descriptor *shdma_prep_sg(struct shdma_chan *schan, goto err_get_desc; do { - dev_dbg(schan->dev, "Add SG #%d@%p[%d], dma %llx\n", - i, sg, len, (unsigned long long)sg_addr); + dev_dbg(schan->dev, "Add SG #%d@%p[%zu], dma %pad\n", + i, sg, len, &sg_addr); if (direction == DMA_DEV_TO_MEM) new = shdma_add_desc(schan, flags, @@ -569,7 +584,11 @@ static struct dma_async_tx_descriptor *shdma_prep_sg(struct shdma_chan *schan, if (!new) goto err_get_desc; - new->chunks = chunks--; + new->cyclic = cyclic; + if (cyclic) + new->chunks = 1; + else + new->chunks = chunks--; list_add_tail(&new->node, &tx_list); } while (len); } @@ -612,7 +631,8 @@ static struct dma_async_tx_descriptor *shdma_prep_memcpy( sg_dma_address(&sg) = dma_src; sg_dma_len(&sg) = len; - return shdma_prep_sg(schan, &sg, 1, &dma_dest, DMA_MEM_TO_MEM, flags); + return shdma_prep_sg(schan, &sg, 1, &dma_dest, DMA_MEM_TO_MEM, + flags, false); } static struct dma_async_tx_descriptor *shdma_prep_slave_sg( @@ -640,7 +660,71 @@ static struct dma_async_tx_descriptor *shdma_prep_slave_sg( slave_addr = ops->slave_addr(schan); return shdma_prep_sg(schan, sgl, sg_len, &slave_addr, - direction, flags); + direction, flags, false); +} + +#define SHDMA_MAX_SG_LEN 32 + +static struct dma_async_tx_descriptor *shdma_prep_dma_cyclic( + struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len, + size_t period_len, enum dma_transfer_direction direction, + unsigned long flags) +{ + struct shdma_chan *schan = to_shdma_chan(chan); + struct shdma_dev *sdev = to_shdma_dev(schan->dma_chan.device); + struct dma_async_tx_descriptor *desc; + const struct shdma_ops *ops = sdev->ops; + unsigned int sg_len = buf_len / period_len; + int slave_id = schan->slave_id; + dma_addr_t slave_addr; + struct scatterlist *sgl; + int i; + + if (!chan) + return NULL; + + BUG_ON(!schan->desc_num); + + if (sg_len > SHDMA_MAX_SG_LEN) { + dev_err(schan->dev, "sg length %d exceds limit %d", + sg_len, SHDMA_MAX_SG_LEN); + return NULL; + } + + /* Someone calling slave DMA on a generic channel? */ + if (slave_id < 0 || (buf_len < period_len)) { + dev_warn(schan->dev, + "%s: bad parameter: buf_len=%zu, period_len=%zu, id=%d\n", + __func__, buf_len, period_len, slave_id); + return NULL; + } + + slave_addr = ops->slave_addr(schan); + + /* + * Allocate the sg list dynamically as it would consumer too much stack + * space. + */ + sgl = kcalloc(sg_len, sizeof(*sgl), GFP_KERNEL); + if (!sgl) + return NULL; + + sg_init_table(sgl, sg_len); + + for (i = 0; i < sg_len; i++) { + dma_addr_t src = buf_addr + (period_len * i); + + sg_set_page(&sgl[i], pfn_to_page(PFN_DOWN(src)), period_len, + offset_in_page(src)); + sg_dma_address(&sgl[i]) = src; + sg_dma_len(&sgl[i]) = period_len; + } + + desc = shdma_prep_sg(schan, sgl, sg_len, &slave_addr, + direction, flags, true); + + kfree(sgl); + return desc; } static int shdma_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd, @@ -915,6 +999,7 @@ int shdma_init(struct device *dev, struct shdma_dev *sdev, /* Compulsory for DMA_SLAVE fields */ dma_dev->device_prep_slave_sg = shdma_prep_slave_sg; + dma_dev->device_prep_dma_cyclic = shdma_prep_dma_cyclic; dma_dev->device_control = shdma_control; dma_dev->dev = dev; diff --git a/drivers/dma/sh/shdma-of.c b/drivers/dma/sh/shdma-of.c index 06473a0..b4ff9d3 100644 --- a/drivers/dma/sh/shdma-of.c +++ b/drivers/dma/sh/shdma-of.c @@ -33,7 +33,8 @@ static struct dma_chan *shdma_of_xlate(struct of_phandle_args *dma_spec, /* Only slave DMA channels can be allocated via DT */ dma_cap_set(DMA_SLAVE, mask); - chan = dma_request_channel(mask, shdma_chan_filter, (void *)id); + chan = dma_request_channel(mask, shdma_chan_filter, + (void *)(uintptr_t)id); if (chan) to_shdma_chan(chan)->hw_req = id; diff --git a/drivers/dma/sh/shdma.h b/drivers/dma/sh/shdma.h index 758a57b..2c0a969 100644 --- a/drivers/dma/sh/shdma.h +++ b/drivers/dma/sh/shdma.h @@ -62,7 +62,7 @@ struct sh_dmae_desc { #define to_sh_dev(chan) container_of(chan->shdma_chan.dma_chan.device,\ struct sh_dmae_device, shdma_dev.dma_dev) -#ifdef CONFIG_SHDMA_R8A73A4 +#ifdef CONFIG_SH_DMAE_R8A73A4 extern const struct sh_dmae_pdata r8a73a4_dma_pdata; #define r8a73a4_shdma_devid (&r8a73a4_dma_pdata) #else diff --git a/drivers/dma/sh/shdmac.c b/drivers/dma/sh/shdmac.c index 0d765c0..58eb857 100644 --- a/drivers/dma/sh/shdmac.c +++ b/drivers/dma/sh/shdmac.c @@ -18,31 +18,32 @@ * */ +#include <linux/delay.h> +#include <linux/dmaengine.h> +#include <linux/err.h> #include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/kdebug.h> #include <linux/module.h> +#include <linux/notifier.h> #include <linux/of.h> #include <linux/of_device.h> -#include <linux/slab.h> -#include <linux/interrupt.h> -#include <linux/dmaengine.h> -#include <linux/delay.h> #include <linux/platform_device.h> #include <linux/pm_runtime.h> +#include <linux/rculist.h> #include <linux/sh_dma.h> -#include <linux/notifier.h> -#include <linux/kdebug.h> +#include <linux/slab.h> #include <linux/spinlock.h> -#include <linux/rculist.h> #include "../dmaengine.h" #include "shdma.h" -/* DMA register */ -#define SAR 0x00 -#define DAR 0x04 -#define TCR 0x08 -#define CHCR 0x0C -#define DMAOR 0x40 +/* DMA registers */ +#define SAR 0x00 /* Source Address Register */ +#define DAR 0x04 /* Destination Address Register */ +#define TCR 0x08 /* Transfer Count Register */ +#define CHCR 0x0C /* Channel Control Register */ +#define DMAOR 0x40 /* DMA Operation Register */ #define TEND 0x18 /* USB-DMAC */ @@ -238,9 +239,8 @@ static void dmae_init(struct sh_dmae_chan *sh_chan) { /* * Default configuration for dual address memory-memory transfer. - * 0x400 represents auto-request. */ - u32 chcr = DM_INC | SM_INC | 0x400 | log2size_to_chcr(sh_chan, + u32 chcr = DM_INC | SM_INC | RS_AUTO | log2size_to_chcr(sh_chan, LOG2_DEFAULT_XFER_SIZE); sh_chan->xmit_shift = calc_xmit_shift(sh_chan, chcr); chcr_write(sh_chan, chcr); @@ -443,6 +443,7 @@ static bool sh_dmae_reset(struct sh_dmae_device *shdev) return ret; } +#if defined(CONFIG_CPU_SH4) || defined(CONFIG_ARM) static irqreturn_t sh_dmae_err(int irq, void *data) { struct sh_dmae_device *shdev = data; @@ -453,6 +454,7 @@ static irqreturn_t sh_dmae_err(int irq, void *data) sh_dmae_reset(shdev); return IRQ_HANDLED; } +#endif static bool sh_dmae_desc_completed(struct shdma_chan *schan, struct shdma_desc *sdesc) @@ -637,7 +639,7 @@ static int sh_dmae_resume(struct device *dev) #define sh_dmae_resume NULL #endif -const struct dev_pm_ops sh_dmae_pm = { +static const struct dev_pm_ops sh_dmae_pm = { .suspend = sh_dmae_suspend, .resume = sh_dmae_resume, .runtime_suspend = sh_dmae_runtime_suspend, @@ -685,9 +687,12 @@ MODULE_DEVICE_TABLE(of, sh_dmae_of_match); static int sh_dmae_probe(struct platform_device *pdev) { const struct sh_dmae_pdata *pdata; - unsigned long irqflags = 0, - chan_flag[SH_DMAE_MAX_CHANNELS] = {}; - int errirq, chan_irq[SH_DMAE_MAX_CHANNELS]; + unsigned long chan_flag[SH_DMAE_MAX_CHANNELS] = {}; + int chan_irq[SH_DMAE_MAX_CHANNELS]; +#if defined(CONFIG_CPU_SH4) || defined(CONFIG_ARM) + unsigned long irqflags = 0; + int errirq; +#endif int err, i, irq_cnt = 0, irqres = 0, irq_cap = 0; struct sh_dmae_device *shdev; struct dma_device *dma_dev; diff --git a/drivers/dma/sh/sudmac.c b/drivers/dma/sh/sudmac.c index c7e9cdf..3ce1039 100644 --- a/drivers/dma/sh/sudmac.c +++ b/drivers/dma/sh/sudmac.c @@ -14,12 +14,13 @@ * published by the Free Software Foundation. */ +#include <linux/dmaengine.h> +#include <linux/err.h> #include <linux/init.h> -#include <linux/module.h> -#include <linux/slab.h> #include <linux/interrupt.h> -#include <linux/dmaengine.h> +#include <linux/module.h> #include <linux/platform_device.h> +#include <linux/slab.h> #include <linux/sudmac.h> struct sudmac_chan { @@ -178,8 +179,8 @@ static int sudmac_desc_setup(struct shdma_chan *schan, struct sudmac_chan *sc = to_chan(schan); struct sudmac_desc *sd = to_desc(sdesc); - dev_dbg(sc->shdma_chan.dev, "%s: src=%x, dst=%x, len=%d\n", - __func__, src, dst, *len); + dev_dbg(sc->shdma_chan.dev, "%s: src=%pad, dst=%pad, len=%zu\n", + __func__, &src, &dst, *len); if (*len > schan->max_xfer_len) *len = schan->max_xfer_len; diff --git a/drivers/dma/sirf-dma.c b/drivers/dma/sirf-dma.c index d4d3a310..aac03ab 100644 --- a/drivers/dma/sirf-dma.c +++ b/drivers/dma/sirf-dma.c @@ -18,6 +18,7 @@ #include <linux/of_device.h> #include <linux/of_platform.h> #include <linux/clk.h> +#include <linux/of_dma.h> #include <linux/sirfsoc_dma.h> #include "dmaengine.h" @@ -579,7 +580,7 @@ err_dir: static struct dma_async_tx_descriptor * sirfsoc_dma_prep_cyclic(struct dma_chan *chan, dma_addr_t addr, size_t buf_len, size_t period_len, - enum dma_transfer_direction direction, unsigned long flags, void *context) + enum dma_transfer_direction direction, unsigned long flags) { struct sirfsoc_dma_chan *schan = dma_chan_to_sirfsoc_dma_chan(chan); struct sirfsoc_dma_desc *sdesc = NULL; @@ -659,6 +660,18 @@ static int sirfsoc_dma_device_slave_caps(struct dma_chan *dchan, return 0; } +static struct dma_chan *of_dma_sirfsoc_xlate(struct of_phandle_args *dma_spec, + struct of_dma *ofdma) +{ + struct sirfsoc_dma *sdma = ofdma->of_dma_data; + unsigned int request = dma_spec->args[0]; + + if (request >= SIRFSOC_DMA_CHANNELS) + return NULL; + + return dma_get_slave_channel(&sdma->channels[request].chan); +} + static int sirfsoc_dma_probe(struct platform_device *op) { struct device_node *dn = op->dev.of_node; @@ -764,11 +777,20 @@ static int sirfsoc_dma_probe(struct platform_device *op) if (ret) goto free_irq; + /* Device-tree DMA controller registration */ + ret = of_dma_controller_register(dn, of_dma_sirfsoc_xlate, sdma); + if (ret) { + dev_err(dev, "failed to register DMA controller\n"); + goto unreg_dma_dev; + } + pm_runtime_enable(&op->dev); dev_info(dev, "initialized SIRFSOC DMAC driver\n"); return 0; +unreg_dma_dev: + dma_async_device_unregister(dma); free_irq: free_irq(sdma->irq, sdma); irq_dispose: @@ -781,6 +803,7 @@ static int sirfsoc_dma_remove(struct platform_device *op) struct device *dev = &op->dev; struct sirfsoc_dma *sdma = dev_get_drvdata(dev); + of_dma_controller_free(op->dev.of_node); dma_async_device_unregister(&sdma->dma); free_irq(sdma->irq, sdma); irq_dispose_mapping(sdma->irq); diff --git a/drivers/dma/ste_dma40.c b/drivers/dma/ste_dma40.c index bf18c78..5fe5933 100644 --- a/drivers/dma/ste_dma40.c +++ b/drivers/dma/ste_dma40.c @@ -556,7 +556,6 @@ struct d40_gen_dmac { * later * @reg_val_backup_chan: Backup data for standard channel parameter registers. * @gcc_pwr_off_mask: Mask to maintain the channels that can be turned off. - * @initialized: true if the dma has been initialized * @gen_dmac: the struct for generic registers values to represent u8500/8540 * DMA controller */ @@ -594,7 +593,6 @@ struct d40_base { u32 reg_val_backup_v4[BACKUP_REGS_SZ_MAX]; u32 *reg_val_backup_chan; u16 gcc_pwr_off_mask; - bool initialized; struct d40_gen_dmac gen_dmac; }; @@ -1056,62 +1054,6 @@ static int d40_sg_2_dmalen(struct scatterlist *sgl, int sg_len, return len; } - -#ifdef CONFIG_PM -static void dma40_backup(void __iomem *baseaddr, u32 *backup, - u32 *regaddr, int num, bool save) -{ - int i; - - for (i = 0; i < num; i++) { - void __iomem *addr = baseaddr + regaddr[i]; - - if (save) - backup[i] = readl_relaxed(addr); - else - writel_relaxed(backup[i], addr); - } -} - -static void d40_save_restore_registers(struct d40_base *base, bool save) -{ - int i; - - /* Save/Restore channel specific registers */ - for (i = 0; i < base->num_phy_chans; i++) { - void __iomem *addr; - int idx; - - if (base->phy_res[i].reserved) - continue; - - addr = base->virtbase + D40_DREG_PCBASE + i * D40_DREG_PCDELTA; - idx = i * ARRAY_SIZE(d40_backup_regs_chan); - - dma40_backup(addr, &base->reg_val_backup_chan[idx], - d40_backup_regs_chan, - ARRAY_SIZE(d40_backup_regs_chan), - save); - } - - /* Save/Restore global registers */ - dma40_backup(base->virtbase, base->reg_val_backup, - d40_backup_regs, ARRAY_SIZE(d40_backup_regs), - save); - - /* Save/Restore registers only existing on dma40 v3 and later */ - if (base->gen_dmac.backup) - dma40_backup(base->virtbase, base->reg_val_backup_v4, - base->gen_dmac.backup, - base->gen_dmac.backup_size, - save); -} -#else -static void d40_save_restore_registers(struct d40_base *base, bool save) -{ -} -#endif - static int __d40_execute_command_phy(struct d40_chan *d40c, enum d40_command command) { @@ -1495,8 +1437,8 @@ static int d40_pause(struct d40_chan *d40c) if (!d40c->busy) return 0; - pm_runtime_get_sync(d40c->base->dev); spin_lock_irqsave(&d40c->lock, flags); + pm_runtime_get_sync(d40c->base->dev); res = d40_channel_execute_command(d40c, D40_DMA_SUSPEND_REQ); @@ -2589,8 +2531,7 @@ d40_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl, static struct dma_async_tx_descriptor * dma40_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t dma_addr, size_t buf_len, size_t period_len, - enum dma_transfer_direction direction, unsigned long flags, - void *context) + enum dma_transfer_direction direction, unsigned long flags) { unsigned int periods = buf_len / period_len; struct dma_async_tx_descriptor *txd; @@ -2998,18 +2939,88 @@ failure1: } /* Suspend resume functionality */ -#ifdef CONFIG_PM -static int dma40_pm_suspend(struct device *dev) +#ifdef CONFIG_PM_SLEEP +static int dma40_suspend(struct device *dev) { struct platform_device *pdev = to_platform_device(dev); struct d40_base *base = platform_get_drvdata(pdev); - int ret = 0; + int ret; + + ret = pm_runtime_force_suspend(dev); + if (ret) + return ret; if (base->lcpa_regulator) ret = regulator_disable(base->lcpa_regulator); return ret; } +static int dma40_resume(struct device *dev) +{ + struct platform_device *pdev = to_platform_device(dev); + struct d40_base *base = platform_get_drvdata(pdev); + int ret = 0; + + if (base->lcpa_regulator) { + ret = regulator_enable(base->lcpa_regulator); + if (ret) + return ret; + } + + return pm_runtime_force_resume(dev); +} +#endif + +#ifdef CONFIG_PM +static void dma40_backup(void __iomem *baseaddr, u32 *backup, + u32 *regaddr, int num, bool save) +{ + int i; + + for (i = 0; i < num; i++) { + void __iomem *addr = baseaddr + regaddr[i]; + + if (save) + backup[i] = readl_relaxed(addr); + else + writel_relaxed(backup[i], addr); + } +} + +static void d40_save_restore_registers(struct d40_base *base, bool save) +{ + int i; + + /* Save/Restore channel specific registers */ + for (i = 0; i < base->num_phy_chans; i++) { + void __iomem *addr; + int idx; + + if (base->phy_res[i].reserved) + continue; + + addr = base->virtbase + D40_DREG_PCBASE + i * D40_DREG_PCDELTA; + idx = i * ARRAY_SIZE(d40_backup_regs_chan); + + dma40_backup(addr, &base->reg_val_backup_chan[idx], + d40_backup_regs_chan, + ARRAY_SIZE(d40_backup_regs_chan), + save); + } + + /* Save/Restore global registers */ + dma40_backup(base->virtbase, base->reg_val_backup, + d40_backup_regs, ARRAY_SIZE(d40_backup_regs), + save); + + /* Save/Restore registers only existing on dma40 v3 and later */ + if (base->gen_dmac.backup) + dma40_backup(base->virtbase, base->reg_val_backup_v4, + base->gen_dmac.backup, + base->gen_dmac.backup_size, + save); +} + static int dma40_runtime_suspend(struct device *dev) { struct platform_device *pdev = to_platform_device(dev); @@ -3030,36 +3041,20 @@ static int dma40_runtime_resume(struct device *dev) struct platform_device *pdev = to_platform_device(dev); struct d40_base *base = platform_get_drvdata(pdev); - if (base->initialized) - d40_save_restore_registers(base, false); + d40_save_restore_registers(base, false); writel_relaxed(D40_DREG_GCC_ENABLE_ALL, base->virtbase + D40_DREG_GCC); return 0; } - -static int dma40_resume(struct device *dev) -{ - struct platform_device *pdev = to_platform_device(dev); - struct d40_base *base = platform_get_drvdata(pdev); - int ret = 0; - - if (base->lcpa_regulator) - ret = regulator_enable(base->lcpa_regulator); - - return ret; -} +#endif static const struct dev_pm_ops dma40_pm_ops = { - .suspend = dma40_pm_suspend, - .runtime_suspend = dma40_runtime_suspend, - .runtime_resume = dma40_runtime_resume, - .resume = dma40_resume, + SET_LATE_SYSTEM_SLEEP_PM_OPS(dma40_suspend, dma40_resume) + SET_PM_RUNTIME_PM_OPS(dma40_runtime_suspend, + dma40_runtime_resume, + NULL) }; -#define DMA40_PM_OPS (&dma40_pm_ops) -#else -#define DMA40_PM_OPS NULL -#endif /* Initialization functions. */ @@ -3645,12 +3640,6 @@ static int __init d40_probe(struct platform_device *pdev) goto failure; } - pm_runtime_irq_safe(base->dev); - pm_runtime_set_autosuspend_delay(base->dev, DMA40_AUTOSUSPEND_DELAY); - pm_runtime_use_autosuspend(base->dev); - pm_runtime_enable(base->dev); - pm_runtime_resume(base->dev); - if (base->plat_data->use_esram_lcla) { base->lcpa_regulator = regulator_get(base->dev, "lcla_esram"); @@ -3671,7 +3660,15 @@ static int __init d40_probe(struct platform_device *pdev) } } - base->initialized = true; + writel_relaxed(D40_DREG_GCC_ENABLE_ALL, base->virtbase + D40_DREG_GCC); + + pm_runtime_irq_safe(base->dev); + pm_runtime_set_autosuspend_delay(base->dev, DMA40_AUTOSUSPEND_DELAY); + pm_runtime_use_autosuspend(base->dev); + pm_runtime_mark_last_busy(base->dev); + pm_runtime_set_active(base->dev); + pm_runtime_enable(base->dev); + ret = d40_dmaengine_init(base, num_reserved_chans); if (ret) goto failure; @@ -3754,7 +3751,7 @@ static struct platform_driver d40_driver = { .driver = { .owner = THIS_MODULE, .name = D40_NAME, - .pm = DMA40_PM_OPS, + .pm = &dma40_pm_ops, .of_match_table = d40_match, }, }; diff --git a/drivers/dma/sun6i-dma.c b/drivers/dma/sun6i-dma.c new file mode 100644 index 0000000..1f92a56 --- /dev/null +++ b/drivers/dma/sun6i-dma.c @@ -0,0 +1,1053 @@ +/* + * Copyright (C) 2013-2014 Allwinner Tech Co., Ltd + * Author: Sugar <shuge@allwinnertech.com> + * + * Copyright (C) 2014 Maxime Ripard + * Maxime Ripard <maxime.ripard@free-electrons.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/dmaengine.h> +#include <linux/dmapool.h> +#include <linux/interrupt.h> +#include <linux/module.h> +#include <linux/of_dma.h> +#include <linux/platform_device.h> +#include <linux/reset.h> +#include <linux/slab.h> +#include <linux/types.h> + +#include "virt-dma.h" + +/* + * There's 16 physical channels that can work in parallel. + * + * However we have 30 different endpoints for our requests. + * + * Since the channels are able to handle only an unidirectional + * transfer, we need to allocate more virtual channels so that + * everyone can grab one channel. + * + * Some devices can't work in both direction (mostly because it + * wouldn't make sense), so we have a bit fewer virtual channels than + * 2 channels per endpoints. + */ + +#define NR_MAX_CHANNELS 16 +#define NR_MAX_REQUESTS 30 +#define NR_MAX_VCHANS 53 + +/* + * Common registers + */ +#define DMA_IRQ_EN(x) ((x) * 0x04) +#define DMA_IRQ_HALF BIT(0) +#define DMA_IRQ_PKG BIT(1) +#define DMA_IRQ_QUEUE BIT(2) + +#define DMA_IRQ_CHAN_NR 8 +#define DMA_IRQ_CHAN_WIDTH 4 + + +#define DMA_IRQ_STAT(x) ((x) * 0x04 + 0x10) + +#define DMA_STAT 0x30 + +/* + * Channels specific registers + */ +#define DMA_CHAN_ENABLE 0x00 +#define DMA_CHAN_ENABLE_START BIT(0) +#define DMA_CHAN_ENABLE_STOP 0 + +#define DMA_CHAN_PAUSE 0x04 +#define DMA_CHAN_PAUSE_PAUSE BIT(1) +#define DMA_CHAN_PAUSE_RESUME 0 + +#define DMA_CHAN_LLI_ADDR 0x08 + +#define DMA_CHAN_CUR_CFG 0x0c +#define DMA_CHAN_CFG_SRC_DRQ(x) ((x) & 0x1f) +#define DMA_CHAN_CFG_SRC_IO_MODE BIT(5) +#define DMA_CHAN_CFG_SRC_LINEAR_MODE (0 << 5) +#define DMA_CHAN_CFG_SRC_BURST(x) (((x) & 0x3) << 7) +#define DMA_CHAN_CFG_SRC_WIDTH(x) (((x) & 0x3) << 9) + +#define DMA_CHAN_CFG_DST_DRQ(x) (DMA_CHAN_CFG_SRC_DRQ(x) << 16) +#define DMA_CHAN_CFG_DST_IO_MODE (DMA_CHAN_CFG_SRC_IO_MODE << 16) +#define DMA_CHAN_CFG_DST_LINEAR_MODE (DMA_CHAN_CFG_SRC_LINEAR_MODE << 16) +#define DMA_CHAN_CFG_DST_BURST(x) (DMA_CHAN_CFG_SRC_BURST(x) << 16) +#define DMA_CHAN_CFG_DST_WIDTH(x) (DMA_CHAN_CFG_SRC_WIDTH(x) << 16) + +#define DMA_CHAN_CUR_SRC 0x10 + +#define DMA_CHAN_CUR_DST 0x14 + +#define DMA_CHAN_CUR_CNT 0x18 + +#define DMA_CHAN_CUR_PARA 0x1c + + +/* + * Various hardware related defines + */ +#define LLI_LAST_ITEM 0xfffff800 +#define NORMAL_WAIT 8 +#define DRQ_SDRAM 1 + +/* + * Hardware representation of the LLI + * + * The hardware will be fed the physical address of this structure, + * and read its content in order to start the transfer. + */ +struct sun6i_dma_lli { + u32 cfg; + u32 src; + u32 dst; + u32 len; + u32 para; + u32 p_lli_next; + + /* + * This field is not used by the DMA controller, but will be + * used by the CPU to go through the list (mostly for dumping + * or freeing it). + */ + struct sun6i_dma_lli *v_lli_next; +}; + + +struct sun6i_desc { + struct virt_dma_desc vd; + dma_addr_t p_lli; + struct sun6i_dma_lli *v_lli; +}; + +struct sun6i_pchan { + u32 idx; + void __iomem *base; + struct sun6i_vchan *vchan; + struct sun6i_desc *desc; + struct sun6i_desc *done; +}; + +struct sun6i_vchan { + struct virt_dma_chan vc; + struct list_head node; + struct dma_slave_config cfg; + struct sun6i_pchan *phy; + u8 port; +}; + +struct sun6i_dma_dev { + struct dma_device slave; + void __iomem *base; + struct clk *clk; + int irq; + spinlock_t lock; + struct reset_control *rstc; + struct tasklet_struct task; + atomic_t tasklet_shutdown; + struct list_head pending; + struct dma_pool *pool; + struct sun6i_pchan *pchans; + struct sun6i_vchan *vchans; +}; + +static struct device *chan2dev(struct dma_chan *chan) +{ + return &chan->dev->device; +} + +static inline struct sun6i_dma_dev *to_sun6i_dma_dev(struct dma_device *d) +{ + return container_of(d, struct sun6i_dma_dev, slave); +} + +static inline struct sun6i_vchan *to_sun6i_vchan(struct dma_chan *chan) +{ + return container_of(chan, struct sun6i_vchan, vc.chan); +} + +static inline struct sun6i_desc * +to_sun6i_desc(struct dma_async_tx_descriptor *tx) +{ + return container_of(tx, struct sun6i_desc, vd.tx); +} + +static inline void sun6i_dma_dump_com_regs(struct sun6i_dma_dev *sdev) +{ + dev_dbg(sdev->slave.dev, "Common register:\n" + "\tmask0(%04x): 0x%08x\n" + "\tmask1(%04x): 0x%08x\n" + "\tpend0(%04x): 0x%08x\n" + "\tpend1(%04x): 0x%08x\n" + "\tstats(%04x): 0x%08x\n", + DMA_IRQ_EN(0), readl(sdev->base + DMA_IRQ_EN(0)), + DMA_IRQ_EN(1), readl(sdev->base + DMA_IRQ_EN(1)), + DMA_IRQ_STAT(0), readl(sdev->base + DMA_IRQ_STAT(0)), + DMA_IRQ_STAT(1), readl(sdev->base + DMA_IRQ_STAT(1)), + DMA_STAT, readl(sdev->base + DMA_STAT)); +} + +static inline void sun6i_dma_dump_chan_regs(struct sun6i_dma_dev *sdev, + struct sun6i_pchan *pchan) +{ + phys_addr_t reg = virt_to_phys(pchan->base); + + dev_dbg(sdev->slave.dev, "Chan %d reg: %pa\n" + "\t___en(%04x): \t0x%08x\n" + "\tpause(%04x): \t0x%08x\n" + "\tstart(%04x): \t0x%08x\n" + "\t__cfg(%04x): \t0x%08x\n" + "\t__src(%04x): \t0x%08x\n" + "\t__dst(%04x): \t0x%08x\n" + "\tcount(%04x): \t0x%08x\n" + "\t_para(%04x): \t0x%08x\n\n", + pchan->idx, ®, + DMA_CHAN_ENABLE, + readl(pchan->base + DMA_CHAN_ENABLE), + DMA_CHAN_PAUSE, + readl(pchan->base + DMA_CHAN_PAUSE), + DMA_CHAN_LLI_ADDR, + readl(pchan->base + DMA_CHAN_LLI_ADDR), + DMA_CHAN_CUR_CFG, + readl(pchan->base + DMA_CHAN_CUR_CFG), + DMA_CHAN_CUR_SRC, + readl(pchan->base + DMA_CHAN_CUR_SRC), + DMA_CHAN_CUR_DST, + readl(pchan->base + DMA_CHAN_CUR_DST), + DMA_CHAN_CUR_CNT, + readl(pchan->base + DMA_CHAN_CUR_CNT), + DMA_CHAN_CUR_PARA, + readl(pchan->base + DMA_CHAN_CUR_PARA)); +} + +static inline int convert_burst(u32 maxburst, u8 *burst) +{ + switch (maxburst) { + case 1: + *burst = 0; + break; + case 8: + *burst = 2; + break; + default: + return -EINVAL; + } + + return 0; +} + +static inline int convert_buswidth(enum dma_slave_buswidth addr_width, u8 *width) +{ + if ((addr_width < DMA_SLAVE_BUSWIDTH_1_BYTE) || + (addr_width > DMA_SLAVE_BUSWIDTH_4_BYTES)) + return -EINVAL; + + *width = addr_width >> 1; + return 0; +} + +static void *sun6i_dma_lli_add(struct sun6i_dma_lli *prev, + struct sun6i_dma_lli *next, + dma_addr_t next_phy, + struct sun6i_desc *txd) +{ + if ((!prev && !txd) || !next) + return NULL; + + if (!prev) { + txd->p_lli = next_phy; + txd->v_lli = next; + } else { + prev->p_lli_next = next_phy; + prev->v_lli_next = next; + } + + next->p_lli_next = LLI_LAST_ITEM; + next->v_lli_next = NULL; + + return next; +} + +static inline int sun6i_dma_cfg_lli(struct sun6i_dma_lli *lli, + dma_addr_t src, + dma_addr_t dst, u32 len, + struct dma_slave_config *config) +{ + u8 src_width, dst_width, src_burst, dst_burst; + int ret; + + if (!config) + return -EINVAL; + + ret = convert_burst(config->src_maxburst, &src_burst); + if (ret) + return ret; + + ret = convert_burst(config->dst_maxburst, &dst_burst); + if (ret) + return ret; + + ret = convert_buswidth(config->src_addr_width, &src_width); + if (ret) + return ret; + + ret = convert_buswidth(config->dst_addr_width, &dst_width); + if (ret) + return ret; + + lli->cfg = DMA_CHAN_CFG_SRC_BURST(src_burst) | + DMA_CHAN_CFG_SRC_WIDTH(src_width) | + DMA_CHAN_CFG_DST_BURST(dst_burst) | + DMA_CHAN_CFG_DST_WIDTH(dst_width); + + lli->src = src; + lli->dst = dst; + lli->len = len; + lli->para = NORMAL_WAIT; + + return 0; +} + +static inline void sun6i_dma_dump_lli(struct sun6i_vchan *vchan, + struct sun6i_dma_lli *lli) +{ + phys_addr_t p_lli = virt_to_phys(lli); + + dev_dbg(chan2dev(&vchan->vc.chan), + "\n\tdesc: p - %pa v - 0x%p\n" + "\t\tc - 0x%08x s - 0x%08x d - 0x%08x\n" + "\t\tl - 0x%08x p - 0x%08x n - 0x%08x\n", + &p_lli, lli, + lli->cfg, lli->src, lli->dst, + lli->len, lli->para, lli->p_lli_next); +} + +static void sun6i_dma_free_desc(struct virt_dma_desc *vd) +{ + struct sun6i_desc *txd = to_sun6i_desc(&vd->tx); + struct sun6i_dma_dev *sdev = to_sun6i_dma_dev(vd->tx.chan->device); + struct sun6i_dma_lli *v_lli, *v_next; + dma_addr_t p_lli, p_next; + + if (unlikely(!txd)) + return; + + p_lli = txd->p_lli; + v_lli = txd->v_lli; + + while (v_lli) { + v_next = v_lli->v_lli_next; + p_next = v_lli->p_lli_next; + + dma_pool_free(sdev->pool, v_lli, p_lli); + + v_lli = v_next; + p_lli = p_next; + } + + kfree(txd); +} + +static int sun6i_dma_terminate_all(struct sun6i_vchan *vchan) +{ + struct sun6i_dma_dev *sdev = to_sun6i_dma_dev(vchan->vc.chan.device); + struct sun6i_pchan *pchan = vchan->phy; + unsigned long flags; + LIST_HEAD(head); + + spin_lock(&sdev->lock); + list_del_init(&vchan->node); + spin_unlock(&sdev->lock); + + spin_lock_irqsave(&vchan->vc.lock, flags); + + vchan_get_all_descriptors(&vchan->vc, &head); + + if (pchan) { + writel(DMA_CHAN_ENABLE_STOP, pchan->base + DMA_CHAN_ENABLE); + writel(DMA_CHAN_PAUSE_RESUME, pchan->base + DMA_CHAN_PAUSE); + + vchan->phy = NULL; + pchan->vchan = NULL; + pchan->desc = NULL; + pchan->done = NULL; + } + + spin_unlock_irqrestore(&vchan->vc.lock, flags); + + vchan_dma_desc_free_list(&vchan->vc, &head); + + return 0; +} + +static int sun6i_dma_start_desc(struct sun6i_vchan *vchan) +{ + struct sun6i_dma_dev *sdev = to_sun6i_dma_dev(vchan->vc.chan.device); + struct virt_dma_desc *desc = vchan_next_desc(&vchan->vc); + struct sun6i_pchan *pchan = vchan->phy; + u32 irq_val, irq_reg, irq_offset; + + if (!pchan) + return -EAGAIN; + + if (!desc) { + pchan->desc = NULL; + pchan->done = NULL; + return -EAGAIN; + } + + list_del(&desc->node); + + pchan->desc = to_sun6i_desc(&desc->tx); + pchan->done = NULL; + + sun6i_dma_dump_lli(vchan, pchan->desc->v_lli); + + irq_reg = pchan->idx / DMA_IRQ_CHAN_NR; + irq_offset = pchan->idx % DMA_IRQ_CHAN_NR; + + irq_val = readl(sdev->base + DMA_IRQ_EN(irq_offset)); + irq_val |= DMA_IRQ_QUEUE << (irq_offset * DMA_IRQ_CHAN_WIDTH); + writel(irq_val, sdev->base + DMA_IRQ_EN(irq_offset)); + + writel(pchan->desc->p_lli, pchan->base + DMA_CHAN_LLI_ADDR); + writel(DMA_CHAN_ENABLE_START, pchan->base + DMA_CHAN_ENABLE); + + sun6i_dma_dump_com_regs(sdev); + sun6i_dma_dump_chan_regs(sdev, pchan); + + return 0; +} + +static void sun6i_dma_tasklet(unsigned long data) +{ + struct sun6i_dma_dev *sdev = (struct sun6i_dma_dev *)data; + struct sun6i_vchan *vchan; + struct sun6i_pchan *pchan; + unsigned int pchan_alloc = 0; + unsigned int pchan_idx; + + list_for_each_entry(vchan, &sdev->slave.channels, vc.chan.device_node) { + spin_lock_irq(&vchan->vc.lock); + + pchan = vchan->phy; + + if (pchan && pchan->done) { + if (sun6i_dma_start_desc(vchan)) { + /* + * No current txd associated with this channel + */ + dev_dbg(sdev->slave.dev, "pchan %u: free\n", + pchan->idx); + + /* Mark this channel free */ + vchan->phy = NULL; + pchan->vchan = NULL; + } + } + spin_unlock_irq(&vchan->vc.lock); + } + + spin_lock_irq(&sdev->lock); + for (pchan_idx = 0; pchan_idx < NR_MAX_CHANNELS; pchan_idx++) { + pchan = &sdev->pchans[pchan_idx]; + + if (pchan->vchan || list_empty(&sdev->pending)) + continue; + + vchan = list_first_entry(&sdev->pending, + struct sun6i_vchan, node); + + /* Remove from pending channels */ + list_del_init(&vchan->node); + pchan_alloc |= BIT(pchan_idx); + + /* Mark this channel allocated */ + pchan->vchan = vchan; + vchan->phy = pchan; + dev_dbg(sdev->slave.dev, "pchan %u: alloc vchan %p\n", + pchan->idx, &vchan->vc); + } + spin_unlock_irq(&sdev->lock); + + for (pchan_idx = 0; pchan_idx < NR_MAX_CHANNELS; pchan_idx++) { + if (!(pchan_alloc & BIT(pchan_idx))) + continue; + + pchan = sdev->pchans + pchan_idx; + vchan = pchan->vchan; + if (vchan) { + spin_lock_irq(&vchan->vc.lock); + sun6i_dma_start_desc(vchan); + spin_unlock_irq(&vchan->vc.lock); + } + } +} + +static irqreturn_t sun6i_dma_interrupt(int irq, void *dev_id) +{ + struct sun6i_dma_dev *sdev = dev_id; + struct sun6i_vchan *vchan; + struct sun6i_pchan *pchan; + int i, j, ret = IRQ_NONE; + u32 status; + + for (i = 0; i < 2; i++) { + status = readl(sdev->base + DMA_IRQ_STAT(i)); + if (!status) + continue; + + dev_dbg(sdev->slave.dev, "DMA irq status %s: 0x%x\n", + i ? "high" : "low", status); + + writel(status, sdev->base + DMA_IRQ_STAT(i)); + + for (j = 0; (j < 8) && status; j++) { + if (status & DMA_IRQ_QUEUE) { + pchan = sdev->pchans + j; + vchan = pchan->vchan; + + if (vchan) { + spin_lock(&vchan->vc.lock); + vchan_cookie_complete(&pchan->desc->vd); + pchan->done = pchan->desc; + spin_unlock(&vchan->vc.lock); + } + } + + status = status >> 4; + } + + if (!atomic_read(&sdev->tasklet_shutdown)) + tasklet_schedule(&sdev->task); + ret = IRQ_HANDLED; + } + + return ret; +} + +static struct dma_async_tx_descriptor *sun6i_dma_prep_dma_memcpy( + struct dma_chan *chan, dma_addr_t dest, dma_addr_t src, + size_t len, unsigned long flags) +{ + struct sun6i_dma_dev *sdev = to_sun6i_dma_dev(chan->device); + struct sun6i_vchan *vchan = to_sun6i_vchan(chan); + struct dma_slave_config *sconfig = &vchan->cfg; + struct sun6i_dma_lli *v_lli; + struct sun6i_desc *txd; + dma_addr_t p_lli; + int ret; + + dev_dbg(chan2dev(chan), + "%s; chan: %d, dest: %pad, src: %pad, len: %zu. flags: 0x%08lx\n", + __func__, vchan->vc.chan.chan_id, &dest, &src, len, flags); + + if (!len) + return NULL; + + txd = kzalloc(sizeof(*txd), GFP_NOWAIT); + if (!txd) + return NULL; + + v_lli = dma_pool_alloc(sdev->pool, GFP_NOWAIT, &p_lli); + if (!v_lli) { + dev_err(sdev->slave.dev, "Failed to alloc lli memory\n"); + goto err_txd_free; + } + + ret = sun6i_dma_cfg_lli(v_lli, src, dest, len, sconfig); + if (ret) + goto err_dma_free; + + v_lli->cfg |= DMA_CHAN_CFG_SRC_DRQ(DRQ_SDRAM) | + DMA_CHAN_CFG_DST_DRQ(DRQ_SDRAM) | + DMA_CHAN_CFG_DST_LINEAR_MODE | + DMA_CHAN_CFG_SRC_LINEAR_MODE; + + sun6i_dma_lli_add(NULL, v_lli, p_lli, txd); + + sun6i_dma_dump_lli(vchan, v_lli); + + return vchan_tx_prep(&vchan->vc, &txd->vd, flags); + +err_dma_free: + dma_pool_free(sdev->pool, v_lli, p_lli); +err_txd_free: + kfree(txd); + return NULL; +} + +static struct dma_async_tx_descriptor *sun6i_dma_prep_slave_sg( + struct dma_chan *chan, struct scatterlist *sgl, + unsigned int sg_len, enum dma_transfer_direction dir, + unsigned long flags, void *context) +{ + struct sun6i_dma_dev *sdev = to_sun6i_dma_dev(chan->device); + struct sun6i_vchan *vchan = to_sun6i_vchan(chan); + struct dma_slave_config *sconfig = &vchan->cfg; + struct sun6i_dma_lli *v_lli, *prev = NULL; + struct sun6i_desc *txd; + struct scatterlist *sg; + dma_addr_t p_lli; + int i, ret; + + if (!sgl) + return NULL; + + if (!is_slave_direction(dir)) { + dev_err(chan2dev(chan), "Invalid DMA direction\n"); + return NULL; + } + + txd = kzalloc(sizeof(*txd), GFP_NOWAIT); + if (!txd) + return NULL; + + for_each_sg(sgl, sg, sg_len, i) { + v_lli = dma_pool_alloc(sdev->pool, GFP_NOWAIT, &p_lli); + if (!v_lli) + goto err_lli_free; + + if (dir == DMA_MEM_TO_DEV) { + ret = sun6i_dma_cfg_lli(v_lli, sg_dma_address(sg), + sconfig->dst_addr, sg_dma_len(sg), + sconfig); + if (ret) + goto err_cur_lli_free; + + v_lli->cfg |= DMA_CHAN_CFG_DST_IO_MODE | + DMA_CHAN_CFG_SRC_LINEAR_MODE | + DMA_CHAN_CFG_SRC_DRQ(DRQ_SDRAM) | + DMA_CHAN_CFG_DST_DRQ(vchan->port); + + dev_dbg(chan2dev(chan), + "%s; chan: %d, dest: %pad, src: %pad, len: %u. flags: 0x%08lx\n", + __func__, vchan->vc.chan.chan_id, + &sconfig->dst_addr, &sg_dma_address(sg), + sg_dma_len(sg), flags); + + } else { + ret = sun6i_dma_cfg_lli(v_lli, sconfig->src_addr, + sg_dma_address(sg), sg_dma_len(sg), + sconfig); + if (ret) + goto err_cur_lli_free; + + v_lli->cfg |= DMA_CHAN_CFG_DST_LINEAR_MODE | + DMA_CHAN_CFG_SRC_IO_MODE | + DMA_CHAN_CFG_DST_DRQ(DRQ_SDRAM) | + DMA_CHAN_CFG_SRC_DRQ(vchan->port); + + dev_dbg(chan2dev(chan), + "%s; chan: %d, dest: %pad, src: %pad, len: %u. flags: 0x%08lx\n", + __func__, vchan->vc.chan.chan_id, + &sg_dma_address(sg), &sconfig->src_addr, + sg_dma_len(sg), flags); + } + + prev = sun6i_dma_lli_add(prev, v_lli, p_lli, txd); + } + + dev_dbg(chan2dev(chan), "First: %pad\n", &txd->p_lli); + for (prev = txd->v_lli; prev; prev = prev->v_lli_next) + sun6i_dma_dump_lli(vchan, prev); + + return vchan_tx_prep(&vchan->vc, &txd->vd, flags); + +err_cur_lli_free: + dma_pool_free(sdev->pool, v_lli, p_lli); +err_lli_free: + for (prev = txd->v_lli; prev; prev = prev->v_lli_next) + dma_pool_free(sdev->pool, prev, virt_to_phys(prev)); + kfree(txd); + return NULL; +} + +static int sun6i_dma_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd, + unsigned long arg) +{ + struct sun6i_dma_dev *sdev = to_sun6i_dma_dev(chan->device); + struct sun6i_vchan *vchan = to_sun6i_vchan(chan); + struct sun6i_pchan *pchan = vchan->phy; + unsigned long flags; + int ret = 0; + + switch (cmd) { + case DMA_RESUME: + dev_dbg(chan2dev(chan), "vchan %p: resume\n", &vchan->vc); + + spin_lock_irqsave(&vchan->vc.lock, flags); + + if (pchan) { + writel(DMA_CHAN_PAUSE_RESUME, + pchan->base + DMA_CHAN_PAUSE); + } else if (!list_empty(&vchan->vc.desc_issued)) { + spin_lock(&sdev->lock); + list_add_tail(&vchan->node, &sdev->pending); + spin_unlock(&sdev->lock); + } + + spin_unlock_irqrestore(&vchan->vc.lock, flags); + break; + + case DMA_PAUSE: + dev_dbg(chan2dev(chan), "vchan %p: pause\n", &vchan->vc); + + if (pchan) { + writel(DMA_CHAN_PAUSE_PAUSE, + pchan->base + DMA_CHAN_PAUSE); + } else { + spin_lock(&sdev->lock); + list_del_init(&vchan->node); + spin_unlock(&sdev->lock); + } + break; + + case DMA_TERMINATE_ALL: + ret = sun6i_dma_terminate_all(vchan); + break; + case DMA_SLAVE_CONFIG: + memcpy(&vchan->cfg, (void *)arg, sizeof(struct dma_slave_config)); + break; + default: + ret = -ENXIO; + break; + } + return ret; +} + +static enum dma_status sun6i_dma_tx_status(struct dma_chan *chan, + dma_cookie_t cookie, + struct dma_tx_state *state) +{ + struct sun6i_vchan *vchan = to_sun6i_vchan(chan); + struct sun6i_pchan *pchan = vchan->phy; + struct sun6i_dma_lli *lli; + struct virt_dma_desc *vd; + struct sun6i_desc *txd; + enum dma_status ret; + unsigned long flags; + size_t bytes = 0; + + ret = dma_cookie_status(chan, cookie, state); + if (ret == DMA_COMPLETE) + return ret; + + spin_lock_irqsave(&vchan->vc.lock, flags); + + vd = vchan_find_desc(&vchan->vc, cookie); + txd = to_sun6i_desc(&vd->tx); + + if (vd) { + for (lli = txd->v_lli; lli != NULL; lli = lli->v_lli_next) + bytes += lli->len; + } else if (!pchan || !pchan->desc) { + bytes = 0; + } else { + bytes = readl(pchan->base + DMA_CHAN_CUR_CNT); + } + + spin_unlock_irqrestore(&vchan->vc.lock, flags); + + dma_set_residue(state, bytes); + + return ret; +} + +static void sun6i_dma_issue_pending(struct dma_chan *chan) +{ + struct sun6i_dma_dev *sdev = to_sun6i_dma_dev(chan->device); + struct sun6i_vchan *vchan = to_sun6i_vchan(chan); + unsigned long flags; + + spin_lock_irqsave(&vchan->vc.lock, flags); + + if (vchan_issue_pending(&vchan->vc)) { + spin_lock(&sdev->lock); + + if (!vchan->phy && list_empty(&vchan->node)) { + list_add_tail(&vchan->node, &sdev->pending); + tasklet_schedule(&sdev->task); + dev_dbg(chan2dev(chan), "vchan %p: issued\n", + &vchan->vc); + } + + spin_unlock(&sdev->lock); + } else { + dev_dbg(chan2dev(chan), "vchan %p: nothing to issue\n", + &vchan->vc); + } + + spin_unlock_irqrestore(&vchan->vc.lock, flags); +} + +static int sun6i_dma_alloc_chan_resources(struct dma_chan *chan) +{ + return 0; +} + +static void sun6i_dma_free_chan_resources(struct dma_chan *chan) +{ + struct sun6i_dma_dev *sdev = to_sun6i_dma_dev(chan->device); + struct sun6i_vchan *vchan = to_sun6i_vchan(chan); + unsigned long flags; + + spin_lock_irqsave(&sdev->lock, flags); + list_del_init(&vchan->node); + spin_unlock_irqrestore(&sdev->lock, flags); + + vchan_free_chan_resources(&vchan->vc); +} + +static struct dma_chan *sun6i_dma_of_xlate(struct of_phandle_args *dma_spec, + struct of_dma *ofdma) +{ + struct sun6i_dma_dev *sdev = ofdma->of_dma_data; + struct sun6i_vchan *vchan; + struct dma_chan *chan; + u8 port = dma_spec->args[0]; + + if (port > NR_MAX_REQUESTS) + return NULL; + + chan = dma_get_any_slave_channel(&sdev->slave); + if (!chan) + return NULL; + + vchan = to_sun6i_vchan(chan); + vchan->port = port; + + return chan; +} + +static inline void sun6i_kill_tasklet(struct sun6i_dma_dev *sdev) +{ + /* Disable all interrupts from DMA */ + writel(0, sdev->base + DMA_IRQ_EN(0)); + writel(0, sdev->base + DMA_IRQ_EN(1)); + + /* Prevent spurious interrupts from scheduling the tasklet */ + atomic_inc(&sdev->tasklet_shutdown); + + /* Make sure we won't have any further interrupts */ + devm_free_irq(sdev->slave.dev, sdev->irq, sdev); + + /* Actually prevent the tasklet from being scheduled */ + tasklet_kill(&sdev->task); +} + +static inline void sun6i_dma_free(struct sun6i_dma_dev *sdev) +{ + int i; + + for (i = 0; i < NR_MAX_VCHANS; i++) { + struct sun6i_vchan *vchan = &sdev->vchans[i]; + + list_del(&vchan->vc.chan.device_node); + tasklet_kill(&vchan->vc.task); + } +} + +static int sun6i_dma_probe(struct platform_device *pdev) +{ + struct sun6i_dma_dev *sdc; + struct resource *res; + struct clk *mux, *pll6; + int ret, i; + + sdc = devm_kzalloc(&pdev->dev, sizeof(*sdc), GFP_KERNEL); + if (!sdc) + return -ENOMEM; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + sdc->base = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(sdc->base)) + return PTR_ERR(sdc->base); + + sdc->irq = platform_get_irq(pdev, 0); + if (sdc->irq < 0) { + dev_err(&pdev->dev, "Cannot claim IRQ\n"); + return sdc->irq; + } + + sdc->clk = devm_clk_get(&pdev->dev, NULL); + if (IS_ERR(sdc->clk)) { + dev_err(&pdev->dev, "No clock specified\n"); + return PTR_ERR(sdc->clk); + } + + mux = clk_get(NULL, "ahb1_mux"); + if (IS_ERR(mux)) { + dev_err(&pdev->dev, "Couldn't get AHB1 Mux\n"); + return PTR_ERR(mux); + } + + pll6 = clk_get(NULL, "pll6"); + if (IS_ERR(pll6)) { + dev_err(&pdev->dev, "Couldn't get PLL6\n"); + clk_put(mux); + return PTR_ERR(pll6); + } + + ret = clk_set_parent(mux, pll6); + clk_put(pll6); + clk_put(mux); + + if (ret) { + dev_err(&pdev->dev, "Couldn't reparent AHB1 on PLL6\n"); + return ret; + } + + sdc->rstc = devm_reset_control_get(&pdev->dev, NULL); + if (IS_ERR(sdc->rstc)) { + dev_err(&pdev->dev, "No reset controller specified\n"); + return PTR_ERR(sdc->rstc); + } + + sdc->pool = dmam_pool_create(dev_name(&pdev->dev), &pdev->dev, + sizeof(struct sun6i_dma_lli), 4, 0); + if (!sdc->pool) { + dev_err(&pdev->dev, "No memory for descriptors dma pool\n"); + return -ENOMEM; + } + + platform_set_drvdata(pdev, sdc); + INIT_LIST_HEAD(&sdc->pending); + spin_lock_init(&sdc->lock); + + dma_cap_set(DMA_PRIVATE, sdc->slave.cap_mask); + dma_cap_set(DMA_MEMCPY, sdc->slave.cap_mask); + dma_cap_set(DMA_SLAVE, sdc->slave.cap_mask); + + INIT_LIST_HEAD(&sdc->slave.channels); + sdc->slave.device_alloc_chan_resources = sun6i_dma_alloc_chan_resources; + sdc->slave.device_free_chan_resources = sun6i_dma_free_chan_resources; + sdc->slave.device_tx_status = sun6i_dma_tx_status; + sdc->slave.device_issue_pending = sun6i_dma_issue_pending; + sdc->slave.device_prep_slave_sg = sun6i_dma_prep_slave_sg; + sdc->slave.device_prep_dma_memcpy = sun6i_dma_prep_dma_memcpy; + sdc->slave.device_control = sun6i_dma_control; + sdc->slave.chancnt = NR_MAX_VCHANS; + + sdc->slave.dev = &pdev->dev; + + sdc->pchans = devm_kcalloc(&pdev->dev, NR_MAX_CHANNELS, + sizeof(struct sun6i_pchan), GFP_KERNEL); + if (!sdc->pchans) + return -ENOMEM; + + sdc->vchans = devm_kcalloc(&pdev->dev, NR_MAX_VCHANS, + sizeof(struct sun6i_vchan), GFP_KERNEL); + if (!sdc->vchans) + return -ENOMEM; + + tasklet_init(&sdc->task, sun6i_dma_tasklet, (unsigned long)sdc); + + for (i = 0; i < NR_MAX_CHANNELS; i++) { + struct sun6i_pchan *pchan = &sdc->pchans[i]; + + pchan->idx = i; + pchan->base = sdc->base + 0x100 + i * 0x40; + } + + for (i = 0; i < NR_MAX_VCHANS; i++) { + struct sun6i_vchan *vchan = &sdc->vchans[i]; + + INIT_LIST_HEAD(&vchan->node); + vchan->vc.desc_free = sun6i_dma_free_desc; + vchan_init(&vchan->vc, &sdc->slave); + } + + ret = reset_control_deassert(sdc->rstc); + if (ret) { + dev_err(&pdev->dev, "Couldn't deassert the device from reset\n"); + goto err_chan_free; + } + + ret = clk_prepare_enable(sdc->clk); + if (ret) { + dev_err(&pdev->dev, "Couldn't enable the clock\n"); + goto err_reset_assert; + } + + ret = devm_request_irq(&pdev->dev, sdc->irq, sun6i_dma_interrupt, 0, + dev_name(&pdev->dev), sdc); + if (ret) { + dev_err(&pdev->dev, "Cannot request IRQ\n"); + goto err_clk_disable; + } + + ret = dma_async_device_register(&sdc->slave); + if (ret) { + dev_warn(&pdev->dev, "Failed to register DMA engine device\n"); + goto err_irq_disable; + } + + ret = of_dma_controller_register(pdev->dev.of_node, sun6i_dma_of_xlate, + sdc); + if (ret) { + dev_err(&pdev->dev, "of_dma_controller_register failed\n"); + goto err_dma_unregister; + } + + return 0; + +err_dma_unregister: + dma_async_device_unregister(&sdc->slave); +err_irq_disable: + sun6i_kill_tasklet(sdc); +err_clk_disable: + clk_disable_unprepare(sdc->clk); +err_reset_assert: + reset_control_assert(sdc->rstc); +err_chan_free: + sun6i_dma_free(sdc); + return ret; +} + +static int sun6i_dma_remove(struct platform_device *pdev) +{ + struct sun6i_dma_dev *sdc = platform_get_drvdata(pdev); + + of_dma_controller_free(pdev->dev.of_node); + dma_async_device_unregister(&sdc->slave); + + sun6i_kill_tasklet(sdc); + + clk_disable_unprepare(sdc->clk); + reset_control_assert(sdc->rstc); + + sun6i_dma_free(sdc); + + return 0; +} + +static struct of_device_id sun6i_dma_match[] = { + { .compatible = "allwinner,sun6i-a31-dma" }, + { /* sentinel */ } +}; + +static struct platform_driver sun6i_dma_driver = { + .probe = sun6i_dma_probe, + .remove = sun6i_dma_remove, + .driver = { + .name = "sun6i-dma", + .of_match_table = sun6i_dma_match, + }, +}; +module_platform_driver(sun6i_dma_driver); + +MODULE_DESCRIPTION("Allwinner A31 DMA Controller Driver"); +MODULE_AUTHOR("Sugar <shuge@allwinnertech.com>"); +MODULE_AUTHOR("Maxime Ripard <maxime.ripard@free-electrons.com>"); +MODULE_LICENSE("GPL"); diff --git a/drivers/dma/tegra20-apb-dma.c b/drivers/dma/tegra20-apb-dma.c index 03ad64e..16efa60 100644 --- a/drivers/dma/tegra20-apb-dma.c +++ b/drivers/dma/tegra20-apb-dma.c @@ -1055,7 +1055,7 @@ static struct dma_async_tx_descriptor *tegra_dma_prep_slave_sg( static struct dma_async_tx_descriptor *tegra_dma_prep_dma_cyclic( struct dma_chan *dc, dma_addr_t buf_addr, size_t buf_len, size_t period_len, enum dma_transfer_direction direction, - unsigned long flags, void *context) + unsigned long flags) { struct tegra_dma_channel *tdc = to_tegra_dma_chan(dc); struct tegra_dma_desc *dma_desc = NULL; diff --git a/drivers/dma/xilinx/Makefile b/drivers/dma/xilinx/Makefile new file mode 100644 index 0000000..3c4e9f2 --- /dev/null +++ b/drivers/dma/xilinx/Makefile @@ -0,0 +1 @@ +obj-$(CONFIG_XILINX_VDMA) += xilinx_vdma.o diff --git a/drivers/dma/xilinx/xilinx_vdma.c b/drivers/dma/xilinx/xilinx_vdma.c new file mode 100644 index 0000000..42a13e8 --- /dev/null +++ b/drivers/dma/xilinx/xilinx_vdma.c @@ -0,0 +1,1379 @@ +/* + * DMA driver for Xilinx Video DMA Engine + * + * Copyright (C) 2010-2014 Xilinx, Inc. All rights reserved. + * + * Based on the Freescale DMA driver. + * + * Description: + * The AXI Video Direct Memory Access (AXI VDMA) core is a soft Xilinx IP + * core that provides high-bandwidth direct memory access between memory + * and AXI4-Stream type video target peripherals. The core provides efficient + * two dimensional DMA operations with independent asynchronous read (S2MM) + * and write (MM2S) channel operation. It can be configured to have either + * one channel or two channels. If configured as two channels, one is to + * transmit to the video device (MM2S) and another is to receive from the + * video device (S2MM). Initialization, status, interrupt and management + * registers are accessed through an AXI4-Lite slave interface. + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + */ + +#include <linux/amba/xilinx_dma.h> +#include <linux/bitops.h> +#include <linux/dmapool.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/io.h> +#include <linux/module.h> +#include <linux/of_address.h> +#include <linux/of_dma.h> +#include <linux/of_platform.h> +#include <linux/of_irq.h> +#include <linux/slab.h> + +#include "../dmaengine.h" + +/* Register/Descriptor Offsets */ +#define XILINX_VDMA_MM2S_CTRL_OFFSET 0x0000 +#define XILINX_VDMA_S2MM_CTRL_OFFSET 0x0030 +#define XILINX_VDMA_MM2S_DESC_OFFSET 0x0050 +#define XILINX_VDMA_S2MM_DESC_OFFSET 0x00a0 + +/* Control Registers */ +#define XILINX_VDMA_REG_DMACR 0x0000 +#define XILINX_VDMA_DMACR_DELAY_MAX 0xff +#define XILINX_VDMA_DMACR_DELAY_SHIFT 24 +#define XILINX_VDMA_DMACR_FRAME_COUNT_MAX 0xff +#define XILINX_VDMA_DMACR_FRAME_COUNT_SHIFT 16 +#define XILINX_VDMA_DMACR_ERR_IRQ BIT(14) +#define XILINX_VDMA_DMACR_DLY_CNT_IRQ BIT(13) +#define XILINX_VDMA_DMACR_FRM_CNT_IRQ BIT(12) +#define XILINX_VDMA_DMACR_MASTER_SHIFT 8 +#define XILINX_VDMA_DMACR_FSYNCSRC_SHIFT 5 +#define XILINX_VDMA_DMACR_FRAMECNT_EN BIT(4) +#define XILINX_VDMA_DMACR_GENLOCK_EN BIT(3) +#define XILINX_VDMA_DMACR_RESET BIT(2) +#define XILINX_VDMA_DMACR_CIRC_EN BIT(1) +#define XILINX_VDMA_DMACR_RUNSTOP BIT(0) +#define XILINX_VDMA_DMACR_FSYNCSRC_MASK GENMASK(6, 5) + +#define XILINX_VDMA_REG_DMASR 0x0004 +#define XILINX_VDMA_DMASR_EOL_LATE_ERR BIT(15) +#define XILINX_VDMA_DMASR_ERR_IRQ BIT(14) +#define XILINX_VDMA_DMASR_DLY_CNT_IRQ BIT(13) +#define XILINX_VDMA_DMASR_FRM_CNT_IRQ BIT(12) +#define XILINX_VDMA_DMASR_SOF_LATE_ERR BIT(11) +#define XILINX_VDMA_DMASR_SG_DEC_ERR BIT(10) +#define XILINX_VDMA_DMASR_SG_SLV_ERR BIT(9) +#define XILINX_VDMA_DMASR_EOF_EARLY_ERR BIT(8) +#define XILINX_VDMA_DMASR_SOF_EARLY_ERR BIT(7) +#define XILINX_VDMA_DMASR_DMA_DEC_ERR BIT(6) +#define XILINX_VDMA_DMASR_DMA_SLAVE_ERR BIT(5) +#define XILINX_VDMA_DMASR_DMA_INT_ERR BIT(4) +#define XILINX_VDMA_DMASR_IDLE BIT(1) +#define XILINX_VDMA_DMASR_HALTED BIT(0) +#define XILINX_VDMA_DMASR_DELAY_MASK GENMASK(31, 24) +#define XILINX_VDMA_DMASR_FRAME_COUNT_MASK GENMASK(23, 16) + +#define XILINX_VDMA_REG_CURDESC 0x0008 +#define XILINX_VDMA_REG_TAILDESC 0x0010 +#define XILINX_VDMA_REG_REG_INDEX 0x0014 +#define XILINX_VDMA_REG_FRMSTORE 0x0018 +#define XILINX_VDMA_REG_THRESHOLD 0x001c +#define XILINX_VDMA_REG_FRMPTR_STS 0x0024 +#define XILINX_VDMA_REG_PARK_PTR 0x0028 +#define XILINX_VDMA_PARK_PTR_WR_REF_SHIFT 8 +#define XILINX_VDMA_PARK_PTR_RD_REF_SHIFT 0 +#define XILINX_VDMA_REG_VDMA_VERSION 0x002c + +/* Register Direct Mode Registers */ +#define XILINX_VDMA_REG_VSIZE 0x0000 +#define XILINX_VDMA_REG_HSIZE 0x0004 + +#define XILINX_VDMA_REG_FRMDLY_STRIDE 0x0008 +#define XILINX_VDMA_FRMDLY_STRIDE_FRMDLY_SHIFT 24 +#define XILINX_VDMA_FRMDLY_STRIDE_STRIDE_SHIFT 0 + +#define XILINX_VDMA_REG_START_ADDRESS(n) (0x000c + 4 * (n)) + +/* HW specific definitions */ +#define XILINX_VDMA_MAX_CHANS_PER_DEVICE 0x2 + +#define XILINX_VDMA_DMAXR_ALL_IRQ_MASK \ + (XILINX_VDMA_DMASR_FRM_CNT_IRQ | \ + XILINX_VDMA_DMASR_DLY_CNT_IRQ | \ + XILINX_VDMA_DMASR_ERR_IRQ) + +#define XILINX_VDMA_DMASR_ALL_ERR_MASK \ + (XILINX_VDMA_DMASR_EOL_LATE_ERR | \ + XILINX_VDMA_DMASR_SOF_LATE_ERR | \ + XILINX_VDMA_DMASR_SG_DEC_ERR | \ + XILINX_VDMA_DMASR_SG_SLV_ERR | \ + XILINX_VDMA_DMASR_EOF_EARLY_ERR | \ + XILINX_VDMA_DMASR_SOF_EARLY_ERR | \ + XILINX_VDMA_DMASR_DMA_DEC_ERR | \ + XILINX_VDMA_DMASR_DMA_SLAVE_ERR | \ + XILINX_VDMA_DMASR_DMA_INT_ERR) + +/* + * Recoverable errors are DMA Internal error, SOF Early, EOF Early + * and SOF Late. They are only recoverable when C_FLUSH_ON_FSYNC + * is enabled in the h/w system. + */ +#define XILINX_VDMA_DMASR_ERR_RECOVER_MASK \ + (XILINX_VDMA_DMASR_SOF_LATE_ERR | \ + XILINX_VDMA_DMASR_EOF_EARLY_ERR | \ + XILINX_VDMA_DMASR_SOF_EARLY_ERR | \ + XILINX_VDMA_DMASR_DMA_INT_ERR) + +/* Axi VDMA Flush on Fsync bits */ +#define XILINX_VDMA_FLUSH_S2MM 3 +#define XILINX_VDMA_FLUSH_MM2S 2 +#define XILINX_VDMA_FLUSH_BOTH 1 + +/* Delay loop counter to prevent hardware failure */ +#define XILINX_VDMA_LOOP_COUNT 1000000 + +/** + * struct xilinx_vdma_desc_hw - Hardware Descriptor + * @next_desc: Next Descriptor Pointer @0x00 + * @pad1: Reserved @0x04 + * @buf_addr: Buffer address @0x08 + * @pad2: Reserved @0x0C + * @vsize: Vertical Size @0x10 + * @hsize: Horizontal Size @0x14 + * @stride: Number of bytes between the first + * pixels of each horizontal line @0x18 + */ +struct xilinx_vdma_desc_hw { + u32 next_desc; + u32 pad1; + u32 buf_addr; + u32 pad2; + u32 vsize; + u32 hsize; + u32 stride; +} __aligned(64); + +/** + * struct xilinx_vdma_tx_segment - Descriptor segment + * @hw: Hardware descriptor + * @node: Node in the descriptor segments list + * @phys: Physical address of segment + */ +struct xilinx_vdma_tx_segment { + struct xilinx_vdma_desc_hw hw; + struct list_head node; + dma_addr_t phys; +} __aligned(64); + +/** + * struct xilinx_vdma_tx_descriptor - Per Transaction structure + * @async_tx: Async transaction descriptor + * @segments: TX segments list + * @node: Node in the channel descriptors list + */ +struct xilinx_vdma_tx_descriptor { + struct dma_async_tx_descriptor async_tx; + struct list_head segments; + struct list_head node; +}; + +/** + * struct xilinx_vdma_chan - Driver specific VDMA channel structure + * @xdev: Driver specific device structure + * @ctrl_offset: Control registers offset + * @desc_offset: TX descriptor registers offset + * @lock: Descriptor operation lock + * @pending_list: Descriptors waiting + * @active_desc: Active descriptor + * @allocated_desc: Allocated descriptor + * @done_list: Complete descriptors + * @common: DMA common channel + * @desc_pool: Descriptors pool + * @dev: The dma device + * @irq: Channel IRQ + * @id: Channel ID + * @direction: Transfer direction + * @num_frms: Number of frames + * @has_sg: Support scatter transfers + * @genlock: Support genlock mode + * @err: Channel has errors + * @tasklet: Cleanup work after irq + * @config: Device configuration info + * @flush_on_fsync: Flush on Frame sync + */ +struct xilinx_vdma_chan { + struct xilinx_vdma_device *xdev; + u32 ctrl_offset; + u32 desc_offset; + spinlock_t lock; + struct list_head pending_list; + struct xilinx_vdma_tx_descriptor *active_desc; + struct xilinx_vdma_tx_descriptor *allocated_desc; + struct list_head done_list; + struct dma_chan common; + struct dma_pool *desc_pool; + struct device *dev; + int irq; + int id; + enum dma_transfer_direction direction; + int num_frms; + bool has_sg; + bool genlock; + bool err; + struct tasklet_struct tasklet; + struct xilinx_vdma_config config; + bool flush_on_fsync; +}; + +/** + * struct xilinx_vdma_device - VDMA device structure + * @regs: I/O mapped base address + * @dev: Device Structure + * @common: DMA device structure + * @chan: Driver specific VDMA channel + * @has_sg: Specifies whether Scatter-Gather is present or not + * @flush_on_fsync: Flush on frame sync + */ +struct xilinx_vdma_device { + void __iomem *regs; + struct device *dev; + struct dma_device common; + struct xilinx_vdma_chan *chan[XILINX_VDMA_MAX_CHANS_PER_DEVICE]; + bool has_sg; + u32 flush_on_fsync; +}; + +/* Macros */ +#define to_xilinx_chan(chan) \ + container_of(chan, struct xilinx_vdma_chan, common) +#define to_vdma_tx_descriptor(tx) \ + container_of(tx, struct xilinx_vdma_tx_descriptor, async_tx) + +/* IO accessors */ +static inline u32 vdma_read(struct xilinx_vdma_chan *chan, u32 reg) +{ + return ioread32(chan->xdev->regs + reg); +} + +static inline void vdma_write(struct xilinx_vdma_chan *chan, u32 reg, u32 value) +{ + iowrite32(value, chan->xdev->regs + reg); +} + +static inline void vdma_desc_write(struct xilinx_vdma_chan *chan, u32 reg, + u32 value) +{ + vdma_write(chan, chan->desc_offset + reg, value); +} + +static inline u32 vdma_ctrl_read(struct xilinx_vdma_chan *chan, u32 reg) +{ + return vdma_read(chan, chan->ctrl_offset + reg); +} + +static inline void vdma_ctrl_write(struct xilinx_vdma_chan *chan, u32 reg, + u32 value) +{ + vdma_write(chan, chan->ctrl_offset + reg, value); +} + +static inline void vdma_ctrl_clr(struct xilinx_vdma_chan *chan, u32 reg, + u32 clr) +{ + vdma_ctrl_write(chan, reg, vdma_ctrl_read(chan, reg) & ~clr); +} + +static inline void vdma_ctrl_set(struct xilinx_vdma_chan *chan, u32 reg, + u32 set) +{ + vdma_ctrl_write(chan, reg, vdma_ctrl_read(chan, reg) | set); +} + +/* ----------------------------------------------------------------------------- + * Descriptors and segments alloc and free + */ + +/** + * xilinx_vdma_alloc_tx_segment - Allocate transaction segment + * @chan: Driver specific VDMA channel + * + * Return: The allocated segment on success and NULL on failure. + */ +static struct xilinx_vdma_tx_segment * +xilinx_vdma_alloc_tx_segment(struct xilinx_vdma_chan *chan) +{ + struct xilinx_vdma_tx_segment *segment; + dma_addr_t phys; + + segment = dma_pool_alloc(chan->desc_pool, GFP_ATOMIC, &phys); + if (!segment) + return NULL; + + memset(segment, 0, sizeof(*segment)); + segment->phys = phys; + + return segment; +} + +/** + * xilinx_vdma_free_tx_segment - Free transaction segment + * @chan: Driver specific VDMA channel + * @segment: VDMA transaction segment + */ +static void xilinx_vdma_free_tx_segment(struct xilinx_vdma_chan *chan, + struct xilinx_vdma_tx_segment *segment) +{ + dma_pool_free(chan->desc_pool, segment, segment->phys); +} + +/** + * xilinx_vdma_tx_descriptor - Allocate transaction descriptor + * @chan: Driver specific VDMA channel + * + * Return: The allocated descriptor on success and NULL on failure. + */ +static struct xilinx_vdma_tx_descriptor * +xilinx_vdma_alloc_tx_descriptor(struct xilinx_vdma_chan *chan) +{ + struct xilinx_vdma_tx_descriptor *desc; + unsigned long flags; + + if (chan->allocated_desc) + return chan->allocated_desc; + + desc = kzalloc(sizeof(*desc), GFP_KERNEL); + if (!desc) + return NULL; + + spin_lock_irqsave(&chan->lock, flags); + chan->allocated_desc = desc; + spin_unlock_irqrestore(&chan->lock, flags); + + INIT_LIST_HEAD(&desc->segments); + + return desc; +} + +/** + * xilinx_vdma_free_tx_descriptor - Free transaction descriptor + * @chan: Driver specific VDMA channel + * @desc: VDMA transaction descriptor + */ +static void +xilinx_vdma_free_tx_descriptor(struct xilinx_vdma_chan *chan, + struct xilinx_vdma_tx_descriptor *desc) +{ + struct xilinx_vdma_tx_segment *segment, *next; + + if (!desc) + return; + + list_for_each_entry_safe(segment, next, &desc->segments, node) { + list_del(&segment->node); + xilinx_vdma_free_tx_segment(chan, segment); + } + + kfree(desc); +} + +/* Required functions */ + +/** + * xilinx_vdma_free_desc_list - Free descriptors list + * @chan: Driver specific VDMA channel + * @list: List to parse and delete the descriptor + */ +static void xilinx_vdma_free_desc_list(struct xilinx_vdma_chan *chan, + struct list_head *list) +{ + struct xilinx_vdma_tx_descriptor *desc, *next; + + list_for_each_entry_safe(desc, next, list, node) { + list_del(&desc->node); + xilinx_vdma_free_tx_descriptor(chan, desc); + } +} + +/** + * xilinx_vdma_free_descriptors - Free channel descriptors + * @chan: Driver specific VDMA channel + */ +static void xilinx_vdma_free_descriptors(struct xilinx_vdma_chan *chan) +{ + unsigned long flags; + + spin_lock_irqsave(&chan->lock, flags); + + xilinx_vdma_free_desc_list(chan, &chan->pending_list); + xilinx_vdma_free_desc_list(chan, &chan->done_list); + + xilinx_vdma_free_tx_descriptor(chan, chan->active_desc); + chan->active_desc = NULL; + + spin_unlock_irqrestore(&chan->lock, flags); +} + +/** + * xilinx_vdma_free_chan_resources - Free channel resources + * @dchan: DMA channel + */ +static void xilinx_vdma_free_chan_resources(struct dma_chan *dchan) +{ + struct xilinx_vdma_chan *chan = to_xilinx_chan(dchan); + + dev_dbg(chan->dev, "Free all channel resources.\n"); + + xilinx_vdma_free_descriptors(chan); + dma_pool_destroy(chan->desc_pool); + chan->desc_pool = NULL; +} + +/** + * xilinx_vdma_chan_desc_cleanup - Clean channel descriptors + * @chan: Driver specific VDMA channel + */ +static void xilinx_vdma_chan_desc_cleanup(struct xilinx_vdma_chan *chan) +{ + struct xilinx_vdma_tx_descriptor *desc, *next; + unsigned long flags; + + spin_lock_irqsave(&chan->lock, flags); + + list_for_each_entry_safe(desc, next, &chan->done_list, node) { + dma_async_tx_callback callback; + void *callback_param; + + /* Remove from the list of running transactions */ + list_del(&desc->node); + + /* Run the link descriptor callback function */ + callback = desc->async_tx.callback; + callback_param = desc->async_tx.callback_param; + if (callback) { + spin_unlock_irqrestore(&chan->lock, flags); + callback(callback_param); + spin_lock_irqsave(&chan->lock, flags); + } + + /* Run any dependencies, then free the descriptor */ + dma_run_dependencies(&desc->async_tx); + xilinx_vdma_free_tx_descriptor(chan, desc); + } + + spin_unlock_irqrestore(&chan->lock, flags); +} + +/** + * xilinx_vdma_do_tasklet - Schedule completion tasklet + * @data: Pointer to the Xilinx VDMA channel structure + */ +static void xilinx_vdma_do_tasklet(unsigned long data) +{ + struct xilinx_vdma_chan *chan = (struct xilinx_vdma_chan *)data; + + xilinx_vdma_chan_desc_cleanup(chan); +} + +/** + * xilinx_vdma_alloc_chan_resources - Allocate channel resources + * @dchan: DMA channel + * + * Return: '0' on success and failure value on error + */ +static int xilinx_vdma_alloc_chan_resources(struct dma_chan *dchan) +{ + struct xilinx_vdma_chan *chan = to_xilinx_chan(dchan); + + /* Has this channel already been allocated? */ + if (chan->desc_pool) + return 0; + + /* + * We need the descriptor to be aligned to 64bytes + * for meeting Xilinx VDMA specification requirement. + */ + chan->desc_pool = dma_pool_create("xilinx_vdma_desc_pool", + chan->dev, + sizeof(struct xilinx_vdma_tx_segment), + __alignof__(struct xilinx_vdma_tx_segment), 0); + if (!chan->desc_pool) { + dev_err(chan->dev, + "unable to allocate channel %d descriptor pool\n", + chan->id); + return -ENOMEM; + } + + dma_cookie_init(dchan); + return 0; +} + +/** + * xilinx_vdma_tx_status - Get VDMA transaction status + * @dchan: DMA channel + * @cookie: Transaction identifier + * @txstate: Transaction state + * + * Return: DMA transaction status + */ +static enum dma_status xilinx_vdma_tx_status(struct dma_chan *dchan, + dma_cookie_t cookie, + struct dma_tx_state *txstate) +{ + return dma_cookie_status(dchan, cookie, txstate); +} + +/** + * xilinx_vdma_is_running - Check if VDMA channel is running + * @chan: Driver specific VDMA channel + * + * Return: '1' if running, '0' if not. + */ +static bool xilinx_vdma_is_running(struct xilinx_vdma_chan *chan) +{ + return !(vdma_ctrl_read(chan, XILINX_VDMA_REG_DMASR) & + XILINX_VDMA_DMASR_HALTED) && + (vdma_ctrl_read(chan, XILINX_VDMA_REG_DMACR) & + XILINX_VDMA_DMACR_RUNSTOP); +} + +/** + * xilinx_vdma_is_idle - Check if VDMA channel is idle + * @chan: Driver specific VDMA channel + * + * Return: '1' if idle, '0' if not. + */ +static bool xilinx_vdma_is_idle(struct xilinx_vdma_chan *chan) +{ + return vdma_ctrl_read(chan, XILINX_VDMA_REG_DMASR) & + XILINX_VDMA_DMASR_IDLE; +} + +/** + * xilinx_vdma_halt - Halt VDMA channel + * @chan: Driver specific VDMA channel + */ +static void xilinx_vdma_halt(struct xilinx_vdma_chan *chan) +{ + int loop = XILINX_VDMA_LOOP_COUNT; + + vdma_ctrl_clr(chan, XILINX_VDMA_REG_DMACR, XILINX_VDMA_DMACR_RUNSTOP); + + /* Wait for the hardware to halt */ + do { + if (vdma_ctrl_read(chan, XILINX_VDMA_REG_DMASR) & + XILINX_VDMA_DMASR_HALTED) + break; + } while (loop--); + + if (!loop) { + dev_err(chan->dev, "Cannot stop channel %p: %x\n", + chan, vdma_ctrl_read(chan, XILINX_VDMA_REG_DMASR)); + chan->err = true; + } + + return; +} + +/** + * xilinx_vdma_start - Start VDMA channel + * @chan: Driver specific VDMA channel + */ +static void xilinx_vdma_start(struct xilinx_vdma_chan *chan) +{ + int loop = XILINX_VDMA_LOOP_COUNT; + + vdma_ctrl_set(chan, XILINX_VDMA_REG_DMACR, XILINX_VDMA_DMACR_RUNSTOP); + + /* Wait for the hardware to start */ + do { + if (!(vdma_ctrl_read(chan, XILINX_VDMA_REG_DMASR) & + XILINX_VDMA_DMASR_HALTED)) + break; + } while (loop--); + + if (!loop) { + dev_err(chan->dev, "Cannot start channel %p: %x\n", + chan, vdma_ctrl_read(chan, XILINX_VDMA_REG_DMASR)); + + chan->err = true; + } + + return; +} + +/** + * xilinx_vdma_start_transfer - Starts VDMA transfer + * @chan: Driver specific channel struct pointer + */ +static void xilinx_vdma_start_transfer(struct xilinx_vdma_chan *chan) +{ + struct xilinx_vdma_config *config = &chan->config; + struct xilinx_vdma_tx_descriptor *desc; + unsigned long flags; + u32 reg; + struct xilinx_vdma_tx_segment *head, *tail = NULL; + + if (chan->err) + return; + + spin_lock_irqsave(&chan->lock, flags); + + /* There's already an active descriptor, bail out. */ + if (chan->active_desc) + goto out_unlock; + + if (list_empty(&chan->pending_list)) + goto out_unlock; + + desc = list_first_entry(&chan->pending_list, + struct xilinx_vdma_tx_descriptor, node); + + /* If it is SG mode and hardware is busy, cannot submit */ + if (chan->has_sg && xilinx_vdma_is_running(chan) && + !xilinx_vdma_is_idle(chan)) { + dev_dbg(chan->dev, "DMA controller still busy\n"); + goto out_unlock; + } + + /* + * If hardware is idle, then all descriptors on the running lists are + * done, start new transfers + */ + if (chan->has_sg) { + head = list_first_entry(&desc->segments, + struct xilinx_vdma_tx_segment, node); + tail = list_entry(desc->segments.prev, + struct xilinx_vdma_tx_segment, node); + + vdma_ctrl_write(chan, XILINX_VDMA_REG_CURDESC, head->phys); + } + + /* Configure the hardware using info in the config structure */ + reg = vdma_ctrl_read(chan, XILINX_VDMA_REG_DMACR); + + if (config->frm_cnt_en) + reg |= XILINX_VDMA_DMACR_FRAMECNT_EN; + else + reg &= ~XILINX_VDMA_DMACR_FRAMECNT_EN; + + /* + * With SG, start with circular mode, so that BDs can be fetched. + * In direct register mode, if not parking, enable circular mode + */ + if (chan->has_sg || !config->park) + reg |= XILINX_VDMA_DMACR_CIRC_EN; + + if (config->park) + reg &= ~XILINX_VDMA_DMACR_CIRC_EN; + + vdma_ctrl_write(chan, XILINX_VDMA_REG_DMACR, reg); + + if (config->park && (config->park_frm >= 0) && + (config->park_frm < chan->num_frms)) { + if (chan->direction == DMA_MEM_TO_DEV) + vdma_write(chan, XILINX_VDMA_REG_PARK_PTR, + config->park_frm << + XILINX_VDMA_PARK_PTR_RD_REF_SHIFT); + else + vdma_write(chan, XILINX_VDMA_REG_PARK_PTR, + config->park_frm << + XILINX_VDMA_PARK_PTR_WR_REF_SHIFT); + } + + /* Start the hardware */ + xilinx_vdma_start(chan); + + if (chan->err) + goto out_unlock; + + /* Start the transfer */ + if (chan->has_sg) { + vdma_ctrl_write(chan, XILINX_VDMA_REG_TAILDESC, tail->phys); + } else { + struct xilinx_vdma_tx_segment *segment, *last = NULL; + int i = 0; + + list_for_each_entry(segment, &desc->segments, node) { + vdma_desc_write(chan, + XILINX_VDMA_REG_START_ADDRESS(i++), + segment->hw.buf_addr); + last = segment; + } + + if (!last) + goto out_unlock; + + /* HW expects these parameters to be same for one transaction */ + vdma_desc_write(chan, XILINX_VDMA_REG_HSIZE, last->hw.hsize); + vdma_desc_write(chan, XILINX_VDMA_REG_FRMDLY_STRIDE, + last->hw.stride); + vdma_desc_write(chan, XILINX_VDMA_REG_VSIZE, last->hw.vsize); + } + + list_del(&desc->node); + chan->active_desc = desc; + +out_unlock: + spin_unlock_irqrestore(&chan->lock, flags); +} + +/** + * xilinx_vdma_issue_pending - Issue pending transactions + * @dchan: DMA channel + */ +static void xilinx_vdma_issue_pending(struct dma_chan *dchan) +{ + struct xilinx_vdma_chan *chan = to_xilinx_chan(dchan); + + xilinx_vdma_start_transfer(chan); +} + +/** + * xilinx_vdma_complete_descriptor - Mark the active descriptor as complete + * @chan : xilinx DMA channel + * + * CONTEXT: hardirq + */ +static void xilinx_vdma_complete_descriptor(struct xilinx_vdma_chan *chan) +{ + struct xilinx_vdma_tx_descriptor *desc; + unsigned long flags; + + spin_lock_irqsave(&chan->lock, flags); + + desc = chan->active_desc; + if (!desc) { + dev_dbg(chan->dev, "no running descriptors\n"); + goto out_unlock; + } + + dma_cookie_complete(&desc->async_tx); + list_add_tail(&desc->node, &chan->done_list); + + chan->active_desc = NULL; + +out_unlock: + spin_unlock_irqrestore(&chan->lock, flags); +} + +/** + * xilinx_vdma_reset - Reset VDMA channel + * @chan: Driver specific VDMA channel + * + * Return: '0' on success and failure value on error + */ +static int xilinx_vdma_reset(struct xilinx_vdma_chan *chan) +{ + int loop = XILINX_VDMA_LOOP_COUNT; + u32 tmp; + + vdma_ctrl_set(chan, XILINX_VDMA_REG_DMACR, XILINX_VDMA_DMACR_RESET); + + tmp = vdma_ctrl_read(chan, XILINX_VDMA_REG_DMACR) & + XILINX_VDMA_DMACR_RESET; + + /* Wait for the hardware to finish reset */ + do { + tmp = vdma_ctrl_read(chan, XILINX_VDMA_REG_DMACR) & + XILINX_VDMA_DMACR_RESET; + } while (loop-- && tmp); + + if (!loop) { + dev_err(chan->dev, "reset timeout, cr %x, sr %x\n", + vdma_ctrl_read(chan, XILINX_VDMA_REG_DMACR), + vdma_ctrl_read(chan, XILINX_VDMA_REG_DMASR)); + return -ETIMEDOUT; + } + + chan->err = false; + + return 0; +} + +/** + * xilinx_vdma_chan_reset - Reset VDMA channel and enable interrupts + * @chan: Driver specific VDMA channel + * + * Return: '0' on success and failure value on error + */ +static int xilinx_vdma_chan_reset(struct xilinx_vdma_chan *chan) +{ + int err; + + /* Reset VDMA */ + err = xilinx_vdma_reset(chan); + if (err) + return err; + + /* Enable interrupts */ + vdma_ctrl_set(chan, XILINX_VDMA_REG_DMACR, + XILINX_VDMA_DMAXR_ALL_IRQ_MASK); + + return 0; +} + +/** + * xilinx_vdma_irq_handler - VDMA Interrupt handler + * @irq: IRQ number + * @data: Pointer to the Xilinx VDMA channel structure + * + * Return: IRQ_HANDLED/IRQ_NONE + */ +static irqreturn_t xilinx_vdma_irq_handler(int irq, void *data) +{ + struct xilinx_vdma_chan *chan = data; + u32 status; + + /* Read the status and ack the interrupts. */ + status = vdma_ctrl_read(chan, XILINX_VDMA_REG_DMASR); + if (!(status & XILINX_VDMA_DMAXR_ALL_IRQ_MASK)) + return IRQ_NONE; + + vdma_ctrl_write(chan, XILINX_VDMA_REG_DMASR, + status & XILINX_VDMA_DMAXR_ALL_IRQ_MASK); + + if (status & XILINX_VDMA_DMASR_ERR_IRQ) { + /* + * An error occurred. If C_FLUSH_ON_FSYNC is enabled and the + * error is recoverable, ignore it. Otherwise flag the error. + * + * Only recoverable errors can be cleared in the DMASR register, + * make sure not to write to other error bits to 1. + */ + u32 errors = status & XILINX_VDMA_DMASR_ALL_ERR_MASK; + vdma_ctrl_write(chan, XILINX_VDMA_REG_DMASR, + errors & XILINX_VDMA_DMASR_ERR_RECOVER_MASK); + + if (!chan->flush_on_fsync || + (errors & ~XILINX_VDMA_DMASR_ERR_RECOVER_MASK)) { + dev_err(chan->dev, + "Channel %p has errors %x, cdr %x tdr %x\n", + chan, errors, + vdma_ctrl_read(chan, XILINX_VDMA_REG_CURDESC), + vdma_ctrl_read(chan, XILINX_VDMA_REG_TAILDESC)); + chan->err = true; + } + } + + if (status & XILINX_VDMA_DMASR_DLY_CNT_IRQ) { + /* + * Device takes too long to do the transfer when user requires + * responsiveness. + */ + dev_dbg(chan->dev, "Inter-packet latency too long\n"); + } + + if (status & XILINX_VDMA_DMASR_FRM_CNT_IRQ) { + xilinx_vdma_complete_descriptor(chan); + xilinx_vdma_start_transfer(chan); + } + + tasklet_schedule(&chan->tasklet); + return IRQ_HANDLED; +} + +/** + * xilinx_vdma_tx_submit - Submit DMA transaction + * @tx: Async transaction descriptor + * + * Return: cookie value on success and failure value on error + */ +static dma_cookie_t xilinx_vdma_tx_submit(struct dma_async_tx_descriptor *tx) +{ + struct xilinx_vdma_tx_descriptor *desc = to_vdma_tx_descriptor(tx); + struct xilinx_vdma_chan *chan = to_xilinx_chan(tx->chan); + dma_cookie_t cookie; + unsigned long flags; + int err; + + if (chan->err) { + /* + * If reset fails, need to hard reset the system. + * Channel is no longer functional + */ + err = xilinx_vdma_chan_reset(chan); + if (err < 0) + return err; + } + + spin_lock_irqsave(&chan->lock, flags); + + cookie = dma_cookie_assign(tx); + + /* Append the transaction to the pending transactions queue. */ + list_add_tail(&desc->node, &chan->pending_list); + + /* Free the allocated desc */ + chan->allocated_desc = NULL; + + spin_unlock_irqrestore(&chan->lock, flags); + + return cookie; +} + +/** + * xilinx_vdma_dma_prep_interleaved - prepare a descriptor for a + * DMA_SLAVE transaction + * @dchan: DMA channel + * @xt: Interleaved template pointer + * @flags: transfer ack flags + * + * Return: Async transaction descriptor on success and NULL on failure + */ +static struct dma_async_tx_descriptor * +xilinx_vdma_dma_prep_interleaved(struct dma_chan *dchan, + struct dma_interleaved_template *xt, + unsigned long flags) +{ + struct xilinx_vdma_chan *chan = to_xilinx_chan(dchan); + struct xilinx_vdma_tx_descriptor *desc; + struct xilinx_vdma_tx_segment *segment, *prev = NULL; + struct xilinx_vdma_desc_hw *hw; + + if (!is_slave_direction(xt->dir)) + return NULL; + + if (!xt->numf || !xt->sgl[0].size) + return NULL; + + /* Allocate a transaction descriptor. */ + desc = xilinx_vdma_alloc_tx_descriptor(chan); + if (!desc) + return NULL; + + dma_async_tx_descriptor_init(&desc->async_tx, &chan->common); + desc->async_tx.tx_submit = xilinx_vdma_tx_submit; + async_tx_ack(&desc->async_tx); + + /* Allocate the link descriptor from DMA pool */ + segment = xilinx_vdma_alloc_tx_segment(chan); + if (!segment) + goto error; + + /* Fill in the hardware descriptor */ + hw = &segment->hw; + hw->vsize = xt->numf; + hw->hsize = xt->sgl[0].size; + hw->stride = xt->sgl[0].icg << + XILINX_VDMA_FRMDLY_STRIDE_STRIDE_SHIFT; + hw->stride |= chan->config.frm_dly << + XILINX_VDMA_FRMDLY_STRIDE_FRMDLY_SHIFT; + + if (xt->dir != DMA_MEM_TO_DEV) + hw->buf_addr = xt->dst_start; + else + hw->buf_addr = xt->src_start; + + /* Link the previous next descriptor to current */ + prev = list_last_entry(&desc->segments, + struct xilinx_vdma_tx_segment, node); + prev->hw.next_desc = segment->phys; + + /* Insert the segment into the descriptor segments list. */ + list_add_tail(&segment->node, &desc->segments); + + prev = segment; + + /* Link the last hardware descriptor with the first. */ + segment = list_first_entry(&desc->segments, + struct xilinx_vdma_tx_segment, node); + prev->hw.next_desc = segment->phys; + + return &desc->async_tx; + +error: + xilinx_vdma_free_tx_descriptor(chan, desc); + return NULL; +} + +/** + * xilinx_vdma_terminate_all - Halt the channel and free descriptors + * @chan: Driver specific VDMA Channel pointer + */ +static void xilinx_vdma_terminate_all(struct xilinx_vdma_chan *chan) +{ + /* Halt the DMA engine */ + xilinx_vdma_halt(chan); + + /* Remove and free all of the descriptors in the lists */ + xilinx_vdma_free_descriptors(chan); +} + +/** + * xilinx_vdma_channel_set_config - Configure VDMA channel + * Run-time configuration for Axi VDMA, supports: + * . halt the channel + * . configure interrupt coalescing and inter-packet delay threshold + * . start/stop parking + * . enable genlock + * + * @dchan: DMA channel + * @cfg: VDMA device configuration pointer + * + * Return: '0' on success and failure value on error + */ +int xilinx_vdma_channel_set_config(struct dma_chan *dchan, + struct xilinx_vdma_config *cfg) +{ + struct xilinx_vdma_chan *chan = to_xilinx_chan(dchan); + u32 dmacr; + + if (cfg->reset) + return xilinx_vdma_chan_reset(chan); + + dmacr = vdma_ctrl_read(chan, XILINX_VDMA_REG_DMACR); + + chan->config.frm_dly = cfg->frm_dly; + chan->config.park = cfg->park; + + /* genlock settings */ + chan->config.gen_lock = cfg->gen_lock; + chan->config.master = cfg->master; + + if (cfg->gen_lock && chan->genlock) { + dmacr |= XILINX_VDMA_DMACR_GENLOCK_EN; + dmacr |= cfg->master << XILINX_VDMA_DMACR_MASTER_SHIFT; + } + + chan->config.frm_cnt_en = cfg->frm_cnt_en; + if (cfg->park) + chan->config.park_frm = cfg->park_frm; + else + chan->config.park_frm = -1; + + chan->config.coalesc = cfg->coalesc; + chan->config.delay = cfg->delay; + + if (cfg->coalesc <= XILINX_VDMA_DMACR_FRAME_COUNT_MAX) { + dmacr |= cfg->coalesc << XILINX_VDMA_DMACR_FRAME_COUNT_SHIFT; + chan->config.coalesc = cfg->coalesc; + } + + if (cfg->delay <= XILINX_VDMA_DMACR_DELAY_MAX) { + dmacr |= cfg->delay << XILINX_VDMA_DMACR_DELAY_SHIFT; + chan->config.delay = cfg->delay; + } + + /* FSync Source selection */ + dmacr &= ~XILINX_VDMA_DMACR_FSYNCSRC_MASK; + dmacr |= cfg->ext_fsync << XILINX_VDMA_DMACR_FSYNCSRC_SHIFT; + + vdma_ctrl_write(chan, XILINX_VDMA_REG_DMACR, dmacr); + + return 0; +} +EXPORT_SYMBOL(xilinx_vdma_channel_set_config); + +/** + * xilinx_vdma_device_control - Configure DMA channel of the device + * @dchan: DMA Channel pointer + * @cmd: DMA control command + * @arg: Channel configuration + * + * Return: '0' on success and failure value on error + */ +static int xilinx_vdma_device_control(struct dma_chan *dchan, + enum dma_ctrl_cmd cmd, unsigned long arg) +{ + struct xilinx_vdma_chan *chan = to_xilinx_chan(dchan); + + if (cmd != DMA_TERMINATE_ALL) + return -ENXIO; + + xilinx_vdma_terminate_all(chan); + + return 0; +} + +/* ----------------------------------------------------------------------------- + * Probe and remove + */ + +/** + * xilinx_vdma_chan_remove - Per Channel remove function + * @chan: Driver specific VDMA channel + */ +static void xilinx_vdma_chan_remove(struct xilinx_vdma_chan *chan) +{ + /* Disable all interrupts */ + vdma_ctrl_clr(chan, XILINX_VDMA_REG_DMACR, + XILINX_VDMA_DMAXR_ALL_IRQ_MASK); + + if (chan->irq > 0) + free_irq(chan->irq, chan); + + tasklet_kill(&chan->tasklet); + + list_del(&chan->common.device_node); +} + +/** + * xilinx_vdma_chan_probe - Per Channel Probing + * It get channel features from the device tree entry and + * initialize special channel handling routines + * + * @xdev: Driver specific device structure + * @node: Device node + * + * Return: '0' on success and failure value on error + */ +static int xilinx_vdma_chan_probe(struct xilinx_vdma_device *xdev, + struct device_node *node) +{ + struct xilinx_vdma_chan *chan; + bool has_dre = false; + u32 value, width; + int err; + + /* Allocate and initialize the channel structure */ + chan = devm_kzalloc(xdev->dev, sizeof(*chan), GFP_KERNEL); + if (!chan) + return -ENOMEM; + + chan->dev = xdev->dev; + chan->xdev = xdev; + chan->has_sg = xdev->has_sg; + + spin_lock_init(&chan->lock); + INIT_LIST_HEAD(&chan->pending_list); + INIT_LIST_HEAD(&chan->done_list); + + /* Retrieve the channel properties from the device tree */ + has_dre = of_property_read_bool(node, "xlnx,include-dre"); + + chan->genlock = of_property_read_bool(node, "xlnx,genlock-mode"); + + err = of_property_read_u32(node, "xlnx,datawidth", &value); + if (err) { + dev_err(xdev->dev, "missing xlnx,datawidth property\n"); + return err; + } + width = value >> 3; /* Convert bits to bytes */ + + /* If data width is greater than 8 bytes, DRE is not in hw */ + if (width > 8) + has_dre = false; + + if (!has_dre) + xdev->common.copy_align = fls(width - 1); + + if (of_device_is_compatible(node, "xlnx,axi-vdma-mm2s-channel")) { + chan->direction = DMA_MEM_TO_DEV; + chan->id = 0; + + chan->ctrl_offset = XILINX_VDMA_MM2S_CTRL_OFFSET; + chan->desc_offset = XILINX_VDMA_MM2S_DESC_OFFSET; + + if (xdev->flush_on_fsync == XILINX_VDMA_FLUSH_BOTH || + xdev->flush_on_fsync == XILINX_VDMA_FLUSH_MM2S) + chan->flush_on_fsync = true; + } else if (of_device_is_compatible(node, + "xlnx,axi-vdma-s2mm-channel")) { + chan->direction = DMA_DEV_TO_MEM; + chan->id = 1; + + chan->ctrl_offset = XILINX_VDMA_S2MM_CTRL_OFFSET; + chan->desc_offset = XILINX_VDMA_S2MM_DESC_OFFSET; + + if (xdev->flush_on_fsync == XILINX_VDMA_FLUSH_BOTH || + xdev->flush_on_fsync == XILINX_VDMA_FLUSH_S2MM) + chan->flush_on_fsync = true; + } else { + dev_err(xdev->dev, "Invalid channel compatible node\n"); + return -EINVAL; + } + + /* Request the interrupt */ + chan->irq = irq_of_parse_and_map(node, 0); + err = request_irq(chan->irq, xilinx_vdma_irq_handler, IRQF_SHARED, + "xilinx-vdma-controller", chan); + if (err) { + dev_err(xdev->dev, "unable to request IRQ %d\n", chan->irq); + return err; + } + + /* Initialize the tasklet */ + tasklet_init(&chan->tasklet, xilinx_vdma_do_tasklet, + (unsigned long)chan); + + /* + * Initialize the DMA channel and add it to the DMA engine channels + * list. + */ + chan->common.device = &xdev->common; + + list_add_tail(&chan->common.device_node, &xdev->common.channels); + xdev->chan[chan->id] = chan; + + /* Reset the channel */ + err = xilinx_vdma_chan_reset(chan); + if (err < 0) { + dev_err(xdev->dev, "Reset channel failed\n"); + return err; + } + + return 0; +} + +/** + * of_dma_xilinx_xlate - Translation function + * @dma_spec: Pointer to DMA specifier as found in the device tree + * @ofdma: Pointer to DMA controller data + * + * Return: DMA channel pointer on success and NULL on error + */ +static struct dma_chan *of_dma_xilinx_xlate(struct of_phandle_args *dma_spec, + struct of_dma *ofdma) +{ + struct xilinx_vdma_device *xdev = ofdma->of_dma_data; + int chan_id = dma_spec->args[0]; + + if (chan_id >= XILINX_VDMA_MAX_CHANS_PER_DEVICE) + return NULL; + + return dma_get_slave_channel(&xdev->chan[chan_id]->common); +} + +/** + * xilinx_vdma_probe - Driver probe function + * @pdev: Pointer to the platform_device structure + * + * Return: '0' on success and failure value on error + */ +static int xilinx_vdma_probe(struct platform_device *pdev) +{ + struct device_node *node = pdev->dev.of_node; + struct xilinx_vdma_device *xdev; + struct device_node *child; + struct resource *io; + u32 num_frames; + int i, err; + + /* Allocate and initialize the DMA engine structure */ + xdev = devm_kzalloc(&pdev->dev, sizeof(*xdev), GFP_KERNEL); + if (!xdev) + return -ENOMEM; + + xdev->dev = &pdev->dev; + + /* Request and map I/O memory */ + io = platform_get_resource(pdev, IORESOURCE_MEM, 0); + xdev->regs = devm_ioremap_resource(&pdev->dev, io); + if (IS_ERR(xdev->regs)) + return PTR_ERR(xdev->regs); + + /* Retrieve the DMA engine properties from the device tree */ + xdev->has_sg = of_property_read_bool(node, "xlnx,include-sg"); + + err = of_property_read_u32(node, "xlnx,num-fstores", &num_frames); + if (err < 0) { + dev_err(xdev->dev, "missing xlnx,num-fstores property\n"); + return err; + } + + err = of_property_read_u32(node, "xlnx,flush-fsync", + &xdev->flush_on_fsync); + if (err < 0) + dev_warn(xdev->dev, "missing xlnx,flush-fsync property\n"); + + /* Initialize the DMA engine */ + xdev->common.dev = &pdev->dev; + + INIT_LIST_HEAD(&xdev->common.channels); + dma_cap_set(DMA_SLAVE, xdev->common.cap_mask); + dma_cap_set(DMA_PRIVATE, xdev->common.cap_mask); + + xdev->common.device_alloc_chan_resources = + xilinx_vdma_alloc_chan_resources; + xdev->common.device_free_chan_resources = + xilinx_vdma_free_chan_resources; + xdev->common.device_prep_interleaved_dma = + xilinx_vdma_dma_prep_interleaved; + xdev->common.device_control = xilinx_vdma_device_control; + xdev->common.device_tx_status = xilinx_vdma_tx_status; + xdev->common.device_issue_pending = xilinx_vdma_issue_pending; + + platform_set_drvdata(pdev, xdev); + + /* Initialize the channels */ + for_each_child_of_node(node, child) { + err = xilinx_vdma_chan_probe(xdev, child); + if (err < 0) + goto error; + } + + for (i = 0; i < XILINX_VDMA_MAX_CHANS_PER_DEVICE; i++) + if (xdev->chan[i]) + xdev->chan[i]->num_frms = num_frames; + + /* Register the DMA engine with the core */ + dma_async_device_register(&xdev->common); + + err = of_dma_controller_register(node, of_dma_xilinx_xlate, + xdev); + if (err < 0) { + dev_err(&pdev->dev, "Unable to register DMA to DT\n"); + dma_async_device_unregister(&xdev->common); + goto error; + } + + dev_info(&pdev->dev, "Xilinx AXI VDMA Engine Driver Probed!!\n"); + + return 0; + +error: + for (i = 0; i < XILINX_VDMA_MAX_CHANS_PER_DEVICE; i++) + if (xdev->chan[i]) + xilinx_vdma_chan_remove(xdev->chan[i]); + + return err; +} + +/** + * xilinx_vdma_remove - Driver remove function + * @pdev: Pointer to the platform_device structure + * + * Return: Always '0' + */ +static int xilinx_vdma_remove(struct platform_device *pdev) +{ + struct xilinx_vdma_device *xdev = platform_get_drvdata(pdev); + int i; + + of_dma_controller_free(pdev->dev.of_node); + + dma_async_device_unregister(&xdev->common); + + for (i = 0; i < XILINX_VDMA_MAX_CHANS_PER_DEVICE; i++) + if (xdev->chan[i]) + xilinx_vdma_chan_remove(xdev->chan[i]); + + return 0; +} + +static const struct of_device_id xilinx_vdma_of_ids[] = { + { .compatible = "xlnx,axi-vdma-1.00.a",}, + {} +}; + +static struct platform_driver xilinx_vdma_driver = { + .driver = { + .name = "xilinx-vdma", + .owner = THIS_MODULE, + .of_match_table = xilinx_vdma_of_ids, + }, + .probe = xilinx_vdma_probe, + .remove = xilinx_vdma_remove, +}; + +module_platform_driver(xilinx_vdma_driver); + +MODULE_AUTHOR("Xilinx, Inc."); +MODULE_DESCRIPTION("Xilinx VDMA driver"); +MODULE_LICENSE("GPL v2"); |