diff options
Diffstat (limited to 'drivers/dma')
| -rw-r--r-- | drivers/dma/Kconfig | 37 | ||||
| -rw-r--r-- | drivers/dma/Makefile | 3 | ||||
| -rw-r--r-- | drivers/dma/dmaengine.c | 35 | ||||
| -rw-r--r-- | drivers/dma/dmatest.c | 444 | ||||
| -rw-r--r-- | drivers/dma/dw_dmac.c | 1122 | ||||
| -rw-r--r-- | drivers/dma/dw_dmac_regs.h | 225 | ||||
| -rw-r--r-- | drivers/dma/fsldma.c | 38 | ||||
| -rw-r--r-- | drivers/dma/ioat.c | 15 | ||||
| -rw-r--r-- | drivers/dma/ioat_dca.c | 244 | ||||
| -rw-r--r-- | drivers/dma/ioat_dma.c | 402 | ||||
| -rw-r--r-- | drivers/dma/ioatdma.h | 28 | ||||
| -rw-r--r-- | drivers/dma/ioatdma_hw.h | 1 | ||||
| -rw-r--r-- | drivers/dma/ioatdma_registers.h | 20 | ||||
| -rw-r--r-- | drivers/dma/iop-adma.c | 53 | ||||
| -rw-r--r-- | drivers/dma/mv_xor.c | 1375 | ||||
| -rw-r--r-- | drivers/dma/mv_xor.h | 183 |
16 files changed, 4135 insertions, 90 deletions
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig index 6239c3df30a..cd303901eb5 100644 --- a/drivers/dma/Kconfig +++ b/drivers/dma/Kconfig @@ -4,13 +4,14 @@ menuconfig DMADEVICES bool "DMA Engine support" - depends on (PCI && X86) || ARCH_IOP32X || ARCH_IOP33X || ARCH_IOP13XX || PPC - depends on !HIGHMEM64G + depends on !HIGHMEM64G && HAS_DMA help DMA engines can do asynchronous data transfers without involving the host CPU. Currently, this framework can be used to offload memory copies in the network stack and - RAID operations in the MD driver. + RAID operations in the MD driver. This menu only presents + DMA Device drivers supported by the configured arch, it may + be empty in some cases. if DMADEVICES @@ -37,6 +38,15 @@ config INTEL_IOP_ADMA help Enable support for the Intel(R) IOP Series RAID engines. +config DW_DMAC + tristate "Synopsys DesignWare AHB DMA support" + depends on AVR32 + select DMA_ENGINE + default y if CPU_AT32AP7000 + help + Support the Synopsys DesignWare AHB DMA controller. This + can be integrated in chips such as the Atmel AT32ap7000. + config FSL_DMA bool "Freescale MPC85xx/MPC83xx DMA support" depends on PPC @@ -46,6 +56,14 @@ config FSL_DMA MPC8560/40, MPC8555, MPC8548 and MPC8641 processors. The MPC8349, MPC8360 is also supported. +config MV_XOR + bool "Marvell XOR engine support" + depends on PLAT_ORION + select ASYNC_CORE + select DMA_ENGINE + ---help--- + Enable support for the Marvell XOR engine. + config DMA_ENGINE bool @@ -55,10 +73,19 @@ comment "DMA Clients" config NET_DMA bool "Network: TCP receive copy offload" depends on DMA_ENGINE && NET + default (INTEL_IOATDMA || FSL_DMA) help This enables the use of DMA engines in the network stack to offload receive copy-to-user operations, freeing CPU cycles. - Since this is the main user of the DMA engine, it should be enabled; - say Y here. + + Say Y here if you enabled INTEL_IOATDMA or FSL_DMA, otherwise + say N. + +config DMATEST + tristate "DMA Test client" + depends on DMA_ENGINE + help + Simple DMA test client. Say N unless you're debugging a + DMA Device driver. endif diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile index c8036d94590..14f59527d4f 100644 --- a/drivers/dma/Makefile +++ b/drivers/dma/Makefile @@ -1,6 +1,9 @@ obj-$(CONFIG_DMA_ENGINE) += dmaengine.o obj-$(CONFIG_NET_DMA) += iovlock.o +obj-$(CONFIG_DMATEST) += dmatest.o obj-$(CONFIG_INTEL_IOATDMA) += ioatdma.o ioatdma-objs := ioat.o ioat_dma.o ioat_dca.o obj-$(CONFIG_INTEL_IOP_ADMA) += iop-adma.o obj-$(CONFIG_FSL_DMA) += fsldma.o +obj-$(CONFIG_MV_XOR) += mv_xor.o +obj-$(CONFIG_DW_DMAC) += dw_dmac.o diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c index 97b329e7679..dc003a3a787 100644 --- a/drivers/dma/dmaengine.c +++ b/drivers/dma/dmaengine.c @@ -169,12 +169,18 @@ static void dma_client_chan_alloc(struct dma_client *client) enum dma_state_client ack; /* Find a channel */ - list_for_each_entry(device, &dma_device_list, global_node) + list_for_each_entry(device, &dma_device_list, global_node) { + /* Does the client require a specific DMA controller? */ + if (client->slave && client->slave->dma_dev + && client->slave->dma_dev != device->dev) + continue; + list_for_each_entry(chan, &device->channels, device_node) { if (!dma_chan_satisfies_mask(chan, client->cap_mask)) continue; - desc = chan->device->device_alloc_chan_resources(chan); + desc = chan->device->device_alloc_chan_resources( + chan, client); if (desc >= 0) { ack = client->event_callback(client, chan, @@ -183,12 +189,14 @@ static void dma_client_chan_alloc(struct dma_client *client) /* we are done once this client rejects * an available resource */ - if (ack == DMA_ACK) + if (ack == DMA_ACK) { dma_chan_get(chan); - else if (ack == DMA_NAK) + chan->client_count++; + } else if (ack == DMA_NAK) return; } } + } } enum dma_status dma_sync_wait(struct dma_chan *chan, dma_cookie_t cookie) @@ -272,8 +280,10 @@ static void dma_clients_notify_removed(struct dma_chan *chan) /* client was holding resources for this channel so * free it */ - if (ack == DMA_ACK) + if (ack == DMA_ACK) { dma_chan_put(chan); + chan->client_count--; + } } mutex_unlock(&dma_list_mutex); @@ -285,6 +295,10 @@ static void dma_clients_notify_removed(struct dma_chan *chan) */ void dma_async_client_register(struct dma_client *client) { + /* validate client data */ + BUG_ON(dma_has_cap(DMA_SLAVE, client->cap_mask) && + !client->slave); + mutex_lock(&dma_list_mutex); list_add_tail(&client->global_node, &dma_client_list); mutex_unlock(&dma_list_mutex); @@ -313,8 +327,10 @@ void dma_async_client_unregister(struct dma_client *client) ack = client->event_callback(client, chan, DMA_RESOURCE_REMOVED); - if (ack == DMA_ACK) + if (ack == DMA_ACK) { dma_chan_put(chan); + chan->client_count--; + } } list_del(&client->global_node); @@ -359,6 +375,10 @@ int dma_async_device_register(struct dma_device *device) !device->device_prep_dma_memset); BUG_ON(dma_has_cap(DMA_INTERRUPT, device->cap_mask) && !device->device_prep_dma_interrupt); + BUG_ON(dma_has_cap(DMA_SLAVE, device->cap_mask) && + !device->device_prep_slave_sg); + BUG_ON(dma_has_cap(DMA_SLAVE, device->cap_mask) && + !device->device_terminate_all); BUG_ON(!device->device_alloc_chan_resources); BUG_ON(!device->device_free_chan_resources); @@ -378,7 +398,7 @@ int dma_async_device_register(struct dma_device *device) chan->chan_id = chancnt++; chan->dev.class = &dma_devclass; - chan->dev.parent = NULL; + chan->dev.parent = device->dev; snprintf(chan->dev.bus_id, BUS_ID_SIZE, "dma%dchan%d", device->dev_id, chan->chan_id); @@ -394,6 +414,7 @@ int dma_async_device_register(struct dma_device *device) kref_get(&device->refcount); kref_get(&device->refcount); kref_init(&chan->refcount); + chan->client_count = 0; chan->slow_ref = 0; INIT_RCU_HEAD(&chan->rcu); } diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c new file mode 100644 index 00000000000..a08d1970474 --- /dev/null +++ b/drivers/dma/dmatest.c @@ -0,0 +1,444 @@ +/* + * DMA Engine test module + * + * Copyright (C) 2007 Atmel 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. + */ +#include <linux/delay.h> +#include <linux/dmaengine.h> +#include <linux/init.h> +#include <linux/kthread.h> +#include <linux/module.h> +#include <linux/moduleparam.h> +#include <linux/random.h> +#include <linux/wait.h> + +static unsigned int test_buf_size = 16384; +module_param(test_buf_size, uint, S_IRUGO); +MODULE_PARM_DESC(test_buf_size, "Size of the memcpy test buffer"); + +static char test_channel[BUS_ID_SIZE]; +module_param_string(channel, test_channel, sizeof(test_channel), S_IRUGO); +MODULE_PARM_DESC(channel, "Bus ID of the channel to test (default: any)"); + +static char test_device[BUS_ID_SIZE]; +module_param_string(device, test_device, sizeof(test_device), S_IRUGO); +MODULE_PARM_DESC(device, "Bus ID of the DMA Engine to test (default: any)"); + +static unsigned int threads_per_chan = 1; +module_param(threads_per_chan, uint, S_IRUGO); +MODULE_PARM_DESC(threads_per_chan, + "Number of threads to start per channel (default: 1)"); + +static unsigned int max_channels; +module_param(max_channels, uint, S_IRUGO); +MODULE_PARM_DESC(nr_channels, + "Maximum number of channels to use (default: all)"); + +/* + * Initialization patterns. All bytes in the source buffer has bit 7 + * set, all bytes in the destination buffer has bit 7 cleared. + * + * Bit 6 is set for all bytes which are to be copied by the DMA + * engine. Bit 5 is set for all bytes which are to be overwritten by + * the DMA engine. + * + * The remaining bits are the inverse of a counter which increments by + * one for each byte address. + */ +#define PATTERN_SRC 0x80 +#define PATTERN_DST 0x00 +#define PATTERN_COPY 0x40 +#define PATTERN_OVERWRITE 0x20 +#define PATTERN_COUNT_MASK 0x1f + +struct dmatest_thread { + struct list_head node; + struct task_struct *task; + struct dma_chan *chan; + u8 *srcbuf; + u8 *dstbuf; +}; + +struct dmatest_chan { + struct list_head node; + struct dma_chan *chan; + struct list_head threads; +}; + +/* + * These are protected by dma_list_mutex since they're only used by + * the DMA client event callback + */ +static LIST_HEAD(dmatest_channels); +static unsigned int nr_channels; + +static bool dmatest_match_channel(struct dma_chan *chan) +{ + if (test_channel[0] == '\0') + return true; + return strcmp(chan->dev.bus_id, test_channel) == 0; +} + +static bool dmatest_match_device(struct dma_device *device) +{ + if (test_device[0] == '\0') + return true; + return strcmp(device->dev->bus_id, test_device) == 0; +} + +static unsigned long dmatest_random(void) +{ + unsigned long buf; + + get_random_bytes(&buf, sizeof(buf)); + return buf; +} + +static void dmatest_init_srcbuf(u8 *buf, unsigned int start, unsigned int len) +{ + unsigned int i; + + for (i = 0; i < start; i++) + buf[i] = PATTERN_SRC | (~i & PATTERN_COUNT_MASK); + for ( ; i < start + len; i++) + buf[i] = PATTERN_SRC | PATTERN_COPY + | (~i & PATTERN_COUNT_MASK);; + for ( ; i < test_buf_size; i++) + buf[i] = PATTERN_SRC | (~i & PATTERN_COUNT_MASK); +} + +static void dmatest_init_dstbuf(u8 *buf, unsigned int start, unsigned int len) +{ + unsigned int i; + + for (i = 0; i < start; i++) + buf[i] = PATTERN_DST | (~i & PATTERN_COUNT_MASK); + for ( ; i < start + len; i++) + buf[i] = PATTERN_DST | PATTERN_OVERWRITE + | (~i & PATTERN_COUNT_MASK); + for ( ; i < test_buf_size; i++) + buf[i] = PATTERN_DST | (~i & PATTERN_COUNT_MASK); +} + +static void dmatest_mismatch(u8 actual, u8 pattern, unsigned int index, + unsigned int counter, bool is_srcbuf) +{ + u8 diff = actual ^ pattern; + u8 expected = pattern | (~counter & PATTERN_COUNT_MASK); + const char *thread_name = current->comm; + + if (is_srcbuf) + pr_warning("%s: srcbuf[0x%x] overwritten!" + " Expected %02x, got %02x\n", + thread_name, index, expected, actual); + else if ((pattern & PATTERN_COPY) + && (diff & (PATTERN_COPY | PATTERN_OVERWRITE))) + pr_warning("%s: dstbuf[0x%x] not copied!" + " Expected %02x, got %02x\n", + thread_name, index, expected, actual); + else if (diff & PATTERN_SRC) + pr_warning("%s: dstbuf[0x%x] was copied!" + " Expected %02x, got %02x\n", + thread_name, index, expected, actual); + else + pr_warning("%s: dstbuf[0x%x] mismatch!" + " Expected %02x, got %02x\n", + thread_name, index, expected, actual); +} + +static unsigned int dmatest_verify(u8 *buf, unsigned int start, + unsigned int end, unsigned int counter, u8 pattern, + bool is_srcbuf) +{ + unsigned int i; + unsigned int error_count = 0; + u8 actual; + + for (i = start; i < end; i++) { + actual = buf[i]; + if (actual != (pattern | (~counter & PATTERN_COUNT_MASK))) { + if (error_count < 32) + dmatest_mismatch(actual, pattern, i, counter, + is_srcbuf); + error_count++; + } + counter++; + } + + if (error_count > 32) + pr_warning("%s: %u errors suppressed\n", + current->comm, error_count - 32); + + return error_count; +} + +/* + * This function repeatedly tests DMA transfers of various lengths and + * offsets until it is told to exit by kthread_stop(). There may be + * multiple threads running this function in parallel for a single + * channel, and there may be multiple channels being tested in + * parallel. + * + * Before each test, the source and destination buffer is initialized + * with a known pattern. This pattern is different depending on + * whether it's in an area which is supposed to be copied or + * overwritten, and different in the source and destination buffers. + * So if the DMA engine doesn't copy exactly what we tell it to copy, + * we'll notice. + */ +static int dmatest_func(void *data) +{ + struct dmatest_thread *thread = data; + struct dma_chan *chan; + const char *thread_name; + unsigned int src_off, dst_off, len; + unsigned int error_count; + unsigned int failed_tests = 0; + unsigned int total_tests = 0; + dma_cookie_t cookie; + enum dma_status status; + int ret; + + thread_name = current->comm; + + ret = -ENOMEM; + thread->srcbuf = kmalloc(test_buf_size, GFP_KERNEL); + if (!thread->srcbuf) + goto err_srcbuf; + thread->dstbuf = kmalloc(test_buf_size, GFP_KERNEL); + if (!thread->dstbuf) + goto err_dstbuf; + + smp_rmb(); + chan = thread->chan; + dma_chan_get(chan); + + while (!kthread_should_stop()) { + total_tests++; + + len = dmatest_random() % test_buf_size + 1; + src_off = dmatest_random() % (test_buf_size - len + 1); + dst_off = dmatest_random() % (test_buf_size - len + 1); + + dmatest_init_srcbuf(thread->srcbuf, src_off, len); + dmatest_init_dstbuf(thread->dstbuf, dst_off, len); + + cookie = dma_async_memcpy_buf_to_buf(chan, + thread->dstbuf + dst_off, + thread->srcbuf + src_off, + len); + if (dma_submit_error(cookie)) { + pr_warning("%s: #%u: submit error %d with src_off=0x%x " + "dst_off=0x%x len=0x%x\n", + thread_name, total_tests - 1, cookie, + src_off, dst_off, len); + msleep(100); + failed_tests++; + continue; + } + dma_async_memcpy_issue_pending(chan); + + do { + msleep(1); + status = dma_async_memcpy_complete( + chan, cookie, NULL, NULL); + } while (status == DMA_IN_PROGRESS); + + if (status == DMA_ERROR) { + pr_warning("%s: #%u: error during copy\n", + thread_name, total_tests - 1); + failed_tests++; + continue; + } + + error_count = 0; + + pr_debug("%s: verifying source buffer...\n", thread_name); + error_count += dmatest_verify(thread->srcbuf, 0, src_off, + 0, PATTERN_SRC, true); + error_count += dmatest_verify(thread->srcbuf, src_off, + src_off + len, src_off, + PATTERN_SRC | PATTERN_COPY, true); + error_count += dmatest_verify(thread->srcbuf, src_off + len, + test_buf_size, src_off + len, + PATTERN_SRC, true); + + pr_debug("%s: verifying dest buffer...\n", + thread->task->comm); + error_count += dmatest_verify(thread->dstbuf, 0, dst_off, + 0, PATTERN_DST, false); + error_count += dmatest_verify(thread->dstbuf, dst_off, + dst_off + len, src_off, + PATTERN_SRC | PATTERN_COPY, false); + error_count += dmatest_verify(thread->dstbuf, dst_off + len, + test_buf_size, dst_off + len, + PATTERN_DST, false); + + if (error_count) { + pr_warning("%s: #%u: %u errors with " + "src_off=0x%x dst_off=0x%x len=0x%x\n", + thread_name, total_tests - 1, error_count, + src_off, dst_off, len); + failed_tests++; + } else { + pr_debug("%s: #%u: No errors with " + "src_off=0x%x dst_off=0x%x len=0x%x\n", + thread_name, total_tests - 1, + src_off, dst_off, len); + } + } + + ret = 0; + dma_chan_put(chan); + kfree(thread->dstbuf); +err_dstbuf: + kfree(thread->srcbuf); +err_srcbuf: + pr_notice("%s: terminating after %u tests, %u failures (status %d)\n", + thread_name, total_tests, failed_tests, ret); + return ret; +} + +static void dmatest_cleanup_channel(struct dmatest_chan *dtc) +{ + struct dmatest_thread *thread; + struct dmatest_thread *_thread; + int ret; + + list_for_each_entry_safe(thread, _thread, &dtc->threads, node) { + ret = kthread_stop(thread->task); + pr_debug("dmatest: thread %s exited with status %d\n", + thread->task->comm, ret); + list_del(&thread->node); + kfree(thread); + } + kfree(dtc); +} + +static enum dma_state_client dmatest_add_channel(struct dma_chan *chan) +{ + struct dmatest_chan *dtc; + struct dmatest_thread *thread; + unsigned int i; + + dtc = kmalloc(sizeof(struct dmatest_chan), GFP_ATOMIC); + if (!dtc) { + pr_warning("dmatest: No memory for %s\n", chan->dev.bus_id); + return DMA_NAK; + } + + dtc->chan = chan; + INIT_LIST_HEAD(&dtc->threads); + + for (i = 0; i < threads_per_chan; i++) { + thread = kzalloc(sizeof(struct dmatest_thread), GFP_KERNEL); + if (!thread) { + pr_warning("dmatest: No memory for %s-test%u\n", + chan->dev.bus_id, i); + break; + } + thread->chan = dtc->chan; + smp_wmb(); + thread->task = kthread_run(dmatest_func, thread, "%s-test%u", + chan->dev.bus_id, i); + if (IS_ERR(thread->task)) { + pr_warning("dmatest: Failed to run thread %s-test%u\n", + chan->dev.bus_id, i); + kfree(thread); + break; + } + + /* srcbuf and dstbuf are allocated by the thread itself */ + + list_add_tail(&thread->node, &dtc->threads); + } + + pr_info("dmatest: Started %u threads using %s\n", i, chan->dev.bus_id); + + list_add_tail(&dtc->node, &dmatest_channels); + nr_channels++; + + return DMA_ACK; +} + +static enum dma_state_client dmatest_remove_channel(struct dma_chan *chan) +{ + struct dmatest_chan *dtc, *_dtc; + + list_for_each_entry_safe(dtc, _dtc, &dmatest_channels, node) { + if (dtc->chan == chan) { + list_del(&dtc->node); + dmatest_cleanup_channel(dtc); + pr_debug("dmatest: lost channel %s\n", + chan->dev.bus_id); + return DMA_ACK; + } + } + + return DMA_DUP; +} + +/* + * Start testing threads as new channels are assigned to us, and kill + * them when the channels go away. + * + * When we unregister the client, all channels are removed so this + * will also take care of cleaning things up when the module is + * unloaded. + */ +static enum dma_state_client +dmatest_event(struct dma_client *client, struct dma_chan *chan, + enum dma_state state) +{ + enum dma_state_client ack = DMA_NAK; + + switch (state) { + case DMA_RESOURCE_AVAILABLE: + if (!dmatest_match_channel(chan) + || !dmatest_match_device(chan->device)) + ack = DMA_DUP; + else if (max_channels && nr_channels >= max_channels) + ack = DMA_NAK; + else + ack = dmatest_add_channel(chan); + break; + + case DMA_RESOURCE_REMOVED: + ack = dmatest_remove_channel(chan); + break; + + default: + pr_info("dmatest: Unhandled event %u (%s)\n", + state, chan->dev.bus_id); + break; + } + + return ack; +} + +static struct dma_client dmatest_client = { + .event_callback = dmatest_event, +}; + +static int __init dmatest_init(void) +{ + dma_cap_set(DMA_MEMCPY, dmatest_client.cap_mask); + dma_async_client_register(&dmatest_client); + dma_async_client_chan_request(&dmatest_client); + + return 0; +} +module_init(dmatest_init); + +static void __exit dmatest_exit(void) +{ + dma_async_client_unregister(&dmatest_client); +} +module_exit(dmatest_exit); + +MODULE_AUTHOR("Haavard Skinnemoen <hskinnemoen@atmel.com>"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/dma/dw_dmac.c b/drivers/dma/dw_dmac.c new file mode 100644 index 00000000000..94df9177124 --- /dev/null +++ b/drivers/dma/dw_dmac.c @@ -0,0 +1,1122 @@ +/* + * Driver for the Synopsys DesignWare DMA Controller (aka DMACA on + * AVR32 systems.) + * + * Copyright (C) 2007-2008 Atmel 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. + */ +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/dmaengine.h> +#include <linux/dma-mapping.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/io.h> +#include <linux/mm.h> +#include <linux/module.h> +#include <linux/platform_device.h> +#include <linux/slab.h> + +#include "dw_dmac_regs.h" + +/* + * This supports the Synopsys "DesignWare AHB Central DMA Controller", + * (DW_ahb_dmac) which is used with various AMBA 2.0 systems (not all + * 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. + */ + +/* NOTE: DMS+SMS is system-specific. We should get this information + * from the platform code somehow. + */ +#define DWC_DEFAULT_CTLLO (DWC_CTLL_DST_MSIZE(0) \ + | DWC_CTLL_SRC_MSIZE(0) \ + | DWC_CTLL_DMS(0) \ + | DWC_CTLL_SMS(1) \ + | DWC_CTLL_LLP_D_EN \ + | DWC_CTLL_LLP_S_EN) + +/* + * This is configuration-dependent and usually a funny size like 4095. + * Let's round it down to the nearest power of two. + * + * Note that this is a transfer count, i.e. if we transfer 32-bit + * words, we can do 8192 bytes per descriptor. + * + * This parameter is also system-specific. + */ +#define DWC_MAX_COUNT 2048U + +/* + * Number of descriptors to allocate for each channel. This should be + * made configurable somehow; preferably, the clients (at least the + * ones using slave transfers) should be able to give us a hint. + */ +#define NR_DESCS_PER_CHANNEL 64 + +/*----------------------------------------------------------------------*/ + +/* + * Because we're not relying on writeback from the controller (it may not + * even be configured into the core!) we don't need to use dma_pool. These + * descriptors -- and associated data -- are cacheable. We do need to make + * sure their dcache entries are written back before handing them off to + * the controller, though. + */ + +static struct dw_desc *dwc_first_active(struct dw_dma_chan *dwc) +{ + return list_entry(dwc->active_list.next, struct dw_desc, desc_node); +} + +static struct dw_desc *dwc_first_queued(struct dw_dma_chan *dwc) +{ + return list_entry(dwc->queue.next, struct dw_desc, desc_node); +} + +static struct dw_desc *dwc_desc_get(struct dw_dma_chan *dwc) +{ + struct dw_desc *desc, *_desc; + struct dw_desc *ret = NULL; + unsigned int i = 0; + + spin_lock_bh(&dwc->lock); + list_for_each_entry_safe(desc, _desc, &dwc->free_list, desc_node) { + if (async_tx_test_ack(&desc->txd)) { + list_del(&desc->desc_node); + ret = desc; + break; + } + dev_dbg(&dwc->chan.dev, "desc %p not ACKed\n", desc); + i++; + } + spin_unlock_bh(&dwc->lock); + + dev_vdbg(&dwc->chan.dev, "scanned %u descriptors on freelist\n", i); + + return ret; +} + +static void dwc_sync_desc_for_cpu(struct dw_dma_chan *dwc, struct dw_desc *desc) +{ + struct dw_desc *child; + + list_for_each_entry(child, &desc->txd.tx_list, desc_node) + dma_sync_single_for_cpu(dwc->chan.dev.parent, + child->txd.phys, sizeof(child->lli), + DMA_TO_DEVICE); + dma_sync_single_for_cpu(dwc->chan.dev.parent, + desc->txd.phys, sizeof(desc->lli), + DMA_TO_DEVICE); +} + +/* + * Move a descriptor, including any children, to the free list. + * `desc' must not be on any lists. + */ +static void dwc_desc_put(struct dw_dma_chan *dwc, struct dw_desc *desc) +{ + if (desc) { + struct dw_desc *child; + + dwc_sync_desc_for_cpu(dwc, desc); + + spin_lock_bh(&dwc->lock); + list_for_each_entry(child, &desc->txd.tx_list, desc_node) + dev_vdbg(&dwc->chan.dev, + "moving child desc %p to freelist\n", + child); + list_splice_init(&desc->txd.tx_list, &dwc->free_list); + dev_vdbg(&dwc->chan.dev, "moving desc %p to freelist\n", desc); + list_add(&desc->desc_node, &dwc->free_list); + spin_unlock_bh(&dwc->lock); + } +} + +/* Called with dwc->lock held and bh disabled */ +static dma_cookie_t +dwc_assign_cookie(struct dw_dma_chan *dwc, struct dw_desc *desc) +{ + dma_cookie_t cookie = dwc->chan.cookie; + + if (++cookie < 0) + cookie = 1; + + dwc->chan.cookie = cookie; + desc->txd.cookie = cookie; + + return cookie; +} + +/*----------------------------------------------------------------------*/ + +/* Called with dwc->lock held and bh disabled */ +static void dwc_dostart(struct dw_dma_chan *dwc, struct dw_desc *first) +{ + struct dw_dma *dw = to_dw_dma(dwc->chan.device); + + /* ASSERT: channel is idle */ + if (dma_readl(dw, CH_EN) & dwc->mask) { + dev_err(&dwc->chan.dev, + "BUG: Attempted to start non-idle channel\n"); + dev_err(&dwc->chan.dev, + " SAR: 0x%x DAR: 0x%x LLP: 0x%x CTL: 0x%x:%08x\n", + channel_readl(dwc, SAR), + channel_readl(dwc, DAR), + channel_readl(dwc, LLP), + channel_readl(dwc, CTL_HI), + channel_readl(dwc, CTL_LO)); + + /* The tasklet will hopefully advance the queue... */ + return; + } + + channel_writel(dwc, LLP, first->txd.phys); + channel_writel(dwc, CTL_LO, + DWC_CTLL_LLP_D_EN | DWC_CTLL_LLP_S_EN); + channel_writel(dwc, CTL_HI, 0); + channel_set_bit(dw, CH_EN, dwc->mask); +} + +/*----------------------------------------------------------------------*/ + +static void +dwc_descriptor_complete(struct dw_dma_chan *dwc, struct dw_desc *desc) +{ + dma_async_tx_callback callback; + void *param; + struct dma_async_tx_descriptor *txd = &desc->txd; + + dev_vdbg(&dwc->chan.dev, "descriptor %u complete\n", txd->cookie); + + dwc->completed = txd->cookie; + callback = txd->callback; + param = txd->callback_param; + + dwc_sync_desc_for_cpu(dwc, desc); + list_splice_init(&txd->tx_list, &dwc->free_list); + list_move(&desc->desc_node, &dwc->free_list); + + /* + * We use dma_unmap_page() regardless of how the buffers were + * mapped before they were submitted... + */ + if (!(txd->flags & DMA_COMPL_SKIP_DEST_UNMAP)) + dma_unmap_page(dwc->chan.dev.parent, desc->lli.dar, desc->len, + DMA_FROM_DEVICE); + if (!(txd->flags & DMA_COMPL_SKIP_SRC_UNMAP)) + dma_unmap_page(dwc->chan.dev.parent, desc->lli.sar, desc->len, + DMA_TO_DEVICE); + + /* + * The API requires that no submissions are done from a + * callback, so we don't need to drop the lock here + */ + if (callback) + callback(param); +} + +static void dwc_complete_all(struct dw_dma *dw, struct dw_dma_chan *dwc) +{ + struct dw_desc *desc, *_desc; + LIST_HEAD(list); + + if (dma_readl(dw, CH_EN) & dwc->mask) { + dev_err(&dwc->chan.dev, + "BUG: XFER bit set, but channel not idle!\n"); + + /* Try to continue after resetting the channel... */ + channel_clear_bit(dw, CH_EN, dwc->mask); + while (dma_readl(dw, CH_EN) & dwc->mask) + cpu_relax(); + } + + /* + * Submit queued descriptors ASAP, i.e. before we go through + * the completed ones. + */ + if (!list_empty(&dwc->queue)) + dwc_dostart(dwc, dwc_first_queued(dwc)); + list_splice_init(&dwc->active_list, &list); + list_splice_init(&dwc->queue, &dwc->active_list); + + list_for_each_entry_safe(desc, _desc, &list, desc_node) + dwc_descriptor_complete(dwc, desc); +} + +static void dwc_scan_descriptors(struct dw_dma *dw, struct dw_dma_chan *dwc) +{ + dma_addr_t llp; + struct dw_desc *desc, *_desc; + struct dw_desc *child; + u32 status_xfer; + + /* + * Clear block interrupt flag before scanning so that we don't + * miss any, and read LLP before RAW_XFER to ensure it is + * valid if we decide to scan the list. + */ + dma_writel(dw, CLEAR.BLOCK, dwc->mask); + llp = channel_readl(dwc, LLP); + status_xfer = dma_readl(dw, RAW.XFER); + + if (status_xfer & dwc->mask) { + /* Everything we've submitted is done */ + dma_writel(dw, CLEAR.XFER, dwc->mask); + dwc_complete_all(dw, dwc); + return; + } + + dev_vdbg(&dwc->chan.dev, "scan_descriptors: llp=0x%x\n", llp); + + list_for_each_entry_safe(desc, _desc, &dwc->active_list, desc_node) { + if (desc->lli.llp == llp) + /* This one is currently in progress */ + return; + + list_for_each_entry(child, &desc->txd.tx_list, desc_node) + if (child->lli.llp == llp) + /* Currently in progress */ + return; + + /* + * No descriptors so far seem to be in progress, i.e. + * this one must be done. + */ + dwc_descriptor_complete(dwc, desc); + } + + dev_err(&dwc->chan.dev, + "BUG: All descriptors done, but channel not idle!\n"); + + /* Try to continue after resetting the channel... */ + channel_clear_bit(dw, CH_EN, dwc->mask); + while (dma_readl(dw, CH_EN) & dwc->mask) + cpu_relax(); + + if (!list_empty(&dwc->queue)) { + dwc_dostart(dwc, dwc_first_queued(dwc)); + list_splice_init(&dwc->queue, &dwc->active_list); + } +} + +static void dwc_dump_lli(struct dw_dma_chan *dwc, struct dw_lli *lli) +{ + dev_printk(KERN_CRIT, &dwc->chan.dev, + " desc: s0x%x d0x%x l0x%x c0x%x:%x\n", + lli->sar, lli->dar, lli->llp, + lli->ctlhi, lli->ctllo); +} + +static void dwc_handle_error(struct dw_dma *dw, struct dw_dma_chan *dwc) +{ + struct dw_desc *bad_desc; + struct dw_desc *child; + + dwc_scan_descriptors(dw, dwc); + + /* + * The descriptor currently at the head of the active list is + * borked. Since we don't have any way to report errors, we'll + * just have to scream loudly and try to carry on. + */ + bad_desc = dwc_first_active(dwc); + list_del_init(&bad_desc->desc_node); + list_splice_init(&dwc->queue, dwc->active_list.prev); + + /* Clear the error flag and try to restart the controller */ + dma_writel(dw, CLEAR.ERROR, dwc->mask); + if (!list_empty(&dwc->active_list)) + dwc_dostart(dwc, dwc_first_active(dwc)); + + /* + * KERN_CRITICAL may seem harsh, but since this only happens + * when someone submits a bad physical address in a + * descriptor, we should consider ourselves lucky that the + * controller flagged an error instead of scribbling over + * random memory locations. + */ + dev_printk(KERN_CRIT, &dwc->chan.dev, + "Bad descriptor submitted for DMA!\n"); + dev_printk(KERN_CRIT, &dwc->chan.dev, + " cookie: %d\n", bad_desc->txd.cookie); + dwc_dump_lli(dwc, &bad_desc->lli); + list_for_each_entry(child, &bad_desc->txd.tx_list, desc_node) + dwc_dump_lli(dwc, &child->lli); + + /* Pretend the descriptor completed successfully */ + dwc_descriptor_complete(dwc, bad_desc); +} + +static void dw_dma_tasklet(unsigned long data) +{ + struct dw_dma *dw = (struct dw_dma *)data; + struct dw_dma_chan *dwc; + u32 status_block; + u32 status_xfer; + u32 status_err; + int i; + + status_block = dma_readl(dw, RAW.BLOCK); + status_xfer = dma_readl(dw, RAW.BLOCK); + status_err = dma_readl(dw, RAW.ERROR); + + dev_vdbg(dw->dma.dev, "tasklet: status_block=%x status_err=%x\n", + status_block, status_err); + + for (i = 0; i < dw->dma.chancnt; i++) { + dwc = &dw->chan[i]; + spin_lock(&dwc->lock); + if (status_err & (1 << i)) + dwc_handle_ |