diff options
Diffstat (limited to 'drivers')
| -rw-r--r-- | drivers/dma/Kconfig | 12 | ||||
| -rw-r--r-- | drivers/dma/Makefile | 1 | ||||
| -rw-r--r-- | drivers/dma/dmaengine.c | 419 | ||||
| -rw-r--r-- | drivers/dma/ioatdma.c | 369 | ||||
| -rw-r--r-- | drivers/dma/ioatdma.h | 16 | ||||
| -rw-r--r-- | drivers/dma/ioatdma_io.h | 118 | ||||
| -rw-r--r-- | drivers/dma/iop-adma.c | 1467 | ||||
| -rw-r--r-- | drivers/md/Kconfig | 2 | ||||
| -rw-r--r-- | drivers/md/Makefile | 4 | ||||
| -rw-r--r-- | drivers/md/md.c | 2 | ||||
| -rw-r--r-- | drivers/md/raid5.c | 2727 | ||||
| -rw-r--r-- | drivers/md/xor.c | 154 |
12 files changed, 3659 insertions, 1632 deletions
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig index 72be6c63edf..b31756d5997 100644 --- a/drivers/dma/Kconfig +++ b/drivers/dma/Kconfig @@ -8,8 +8,8 @@ menu "DMA Engine support" config DMA_ENGINE bool "Support for DMA engines" ---help--- - DMA engines offload copy operations from the CPU to dedicated - hardware, allowing the copies to happen asynchronously. + DMA engines offload bulk memory operations from the CPU to dedicated + hardware, allowing the operations to happen asynchronously. comment "DMA Clients" @@ -32,4 +32,12 @@ config INTEL_IOATDMA ---help--- Enable support for the Intel(R) I/OAT DMA engine. +config INTEL_IOP_ADMA + tristate "Intel IOP ADMA support" + depends on DMA_ENGINE && (ARCH_IOP32X || ARCH_IOP33X || ARCH_IOP13XX) + select ASYNC_CORE + default m + ---help--- + Enable support for the Intel(R) IOP Series RAID engines. + endmenu diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile index bdcfdbdb1ae..b3839b687ae 100644 --- a/drivers/dma/Makefile +++ b/drivers/dma/Makefile @@ -1,3 +1,4 @@ obj-$(CONFIG_DMA_ENGINE) += dmaengine.o obj-$(CONFIG_NET_DMA) += iovlock.o obj-$(CONFIG_INTEL_IOATDMA) += ioatdma.o +obj-$(CONFIG_INTEL_IOP_ADMA) += iop-adma.o diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c index 322ee2984e3..82489923af0 100644 --- a/drivers/dma/dmaengine.c +++ b/drivers/dma/dmaengine.c @@ -37,11 +37,11 @@ * Each device has a channels list, which runs unlocked but is never modified * once the device is registered, it's just setup by the driver. * - * Each client has a channels list, it's only modified under the client->lock - * and in an RCU callback, so it's safe to read under rcu_read_lock(). + * Each client is responsible for keeping track of the channels it uses. See + * the definition of dma_event_callback in dmaengine.h. * * Each device has a kref, which is initialized to 1 when the device is - * registered. A kref_put is done for each class_device registered. When the + * registered. A kref_get is done for each class_device registered. When the * class_device is released, the coresponding kref_put is done in the release * method. Every time one of the device's channels is allocated to a client, * a kref_get occurs. When the channel is freed, the coresponding kref_put @@ -51,14 +51,17 @@ * references to finish. * * Each channel has an open-coded implementation of Rusty Russell's "bigref," - * with a kref and a per_cpu local_t. A single reference is set when on an - * ADDED event, and removed with a REMOVE event. Net DMA client takes an - * extra reference per outstanding transaction. The relase function does a - * kref_put on the device. -ChrisL + * with a kref and a per_cpu local_t. A dma_chan_get is called when a client + * signals that it wants to use a channel, and dma_chan_put is called when + * a channel is removed or a client using it is unregesitered. A client can + * take extra references per outstanding transaction, as is the case with + * the NET DMA client. The release function does a kref_put on the device. + * -ChrisL, DanW */ #include <linux/init.h> #include <linux/module.h> +#include <linux/mm.h> #include <linux/device.h> #include <linux/dmaengine.h> #include <linux/hardirq.h> @@ -66,6 +69,7 @@ #include <linux/percpu.h> #include <linux/rcupdate.h> #include <linux/mutex.h> +#include <linux/jiffies.h> static DEFINE_MUTEX(dma_list_mutex); static LIST_HEAD(dma_device_list); @@ -100,8 +104,19 @@ static ssize_t show_bytes_transferred(struct class_device *cd, char *buf) static ssize_t show_in_use(struct class_device *cd, char *buf) { struct dma_chan *chan = container_of(cd, struct dma_chan, class_dev); + int in_use = 0; + + if (unlikely(chan->slow_ref) && + atomic_read(&chan->refcount.refcount) > 1) + in_use = 1; + else { + if (local_read(&(per_cpu_ptr(chan->local, + get_cpu())->refcount)) > 0) + in_use = 1; + put_cpu(); + } - return sprintf(buf, "%d\n", (chan->client ? 1 : 0)); + return sprintf(buf, "%d\n", in_use); } static struct class_device_attribute dma_class_attrs[] = { @@ -127,43 +142,72 @@ static struct class dma_devclass = { /* --- client and device registration --- */ +#define dma_chan_satisfies_mask(chan, mask) \ + __dma_chan_satisfies_mask((chan), &(mask)) +static int +__dma_chan_satisfies_mask(struct dma_chan *chan, dma_cap_mask_t *want) +{ + dma_cap_mask_t has; + + bitmap_and(has.bits, want->bits, chan->device->cap_mask.bits, + DMA_TX_TYPE_END); + return bitmap_equal(want->bits, has.bits, DMA_TX_TYPE_END); +} + /** - * dma_client_chan_alloc - try to allocate a channel to a client + * dma_client_chan_alloc - try to allocate channels to a client * @client: &dma_client * * Called with dma_list_mutex held. */ -static struct dma_chan *dma_client_chan_alloc(struct dma_client *client) +static void dma_client_chan_alloc(struct dma_client *client) { struct dma_device *device; struct dma_chan *chan; - unsigned long flags; int desc; /* allocated descriptor count */ + enum dma_state_client ack; - /* Find a channel, any DMA engine will do */ - list_for_each_entry(device, &dma_device_list, global_node) { + /* Find a channel */ + list_for_each_entry(device, &dma_device_list, global_node) list_for_each_entry(chan, &device->channels, device_node) { - if (chan->client) + if (!dma_chan_satisfies_mask(chan, client->cap_mask)) continue; desc = chan->device->device_alloc_chan_resources(chan); if (desc >= 0) { - kref_get(&device->refcount); - kref_init(&chan->refcount); - chan->slow_ref = 0; - INIT_RCU_HEAD(&chan->rcu); - chan->client = client; - spin_lock_irqsave(&client->lock, flags); - list_add_tail_rcu(&chan->client_node, - &client->channels); - spin_unlock_irqrestore(&client->lock, flags); - return chan; + ack = client->event_callback(client, + chan, + DMA_RESOURCE_AVAILABLE); + + /* we are done once this client rejects + * an available resource + */ + if (ack == DMA_ACK) { + dma_chan_get(chan); + kref_get(&device->refcount); + } else if (ack == DMA_NAK) + return; } } - } +} + +enum dma_status dma_sync_wait(struct dma_chan *chan, dma_cookie_t cookie) +{ + enum dma_status status; + unsigned long dma_sync_wait_timeout = jiffies + msecs_to_jiffies(5000); + + dma_async_issue_pending(chan); + do { + status = dma_async_is_tx_complete(chan, cookie, NULL, NULL); + if (time_after_eq(jiffies, dma_sync_wait_timeout)) { + printk(KERN_ERR "dma_sync_wait_timeout!\n"); + return DMA_ERROR; + } + } while (status == DMA_IN_PROGRESS); - return NULL; + return status; } +EXPORT_SYMBOL(dma_sync_wait); /** * dma_chan_cleanup - release a DMA channel's resources @@ -173,7 +217,6 @@ void dma_chan_cleanup(struct kref *kref) { struct dma_chan *chan = container_of(kref, struct dma_chan, refcount); chan->device->device_free_chan_resources(chan); - chan->client = NULL; kref_put(&chan->device->refcount, dma_async_device_cleanup); } EXPORT_SYMBOL(dma_chan_cleanup); @@ -189,7 +232,7 @@ static void dma_chan_free_rcu(struct rcu_head *rcu) kref_put(&chan->refcount, dma_chan_cleanup); } -static void dma_client_chan_free(struct dma_chan *chan) +static void dma_chan_release(struct dma_chan *chan) { atomic_add(0x7FFFFFFF, &chan->refcount.refcount); chan->slow_ref = 1; @@ -197,70 +240,57 @@ static void dma_client_chan_free(struct dma_chan *chan) } /** - * dma_chans_rebalance - reallocate channels to clients - * - * When the number of DMA channel in the system changes, - * channels need to be rebalanced among clients. + * dma_chans_notify_available - broadcast available channels to the clients */ -static void dma_chans_rebalance(void) +static void dma_clients_notify_available(void) { struct dma_client *client; - struct dma_chan *chan; - unsigned long flags; mutex_lock(&dma_list_mutex); - list_for_each_entry(client, &dma_client_list, global_node) { - while (client->chans_desired > client->chan_count) { - chan = dma_client_chan_alloc(client); - if (!chan) - break; - client->chan_count++; - client->event_callback(client, - chan, - DMA_RESOURCE_ADDED); - } - while (client->chans_desired < client->chan_count) { - spin_lock_irqsave(&client->lock, flags); - chan = list_entry(client->channels.next, - struct dma_chan, - client_node); - list_del_rcu(&chan->client_node); - spin_unlock_irqrestore(&client->lock, flags); - client->chan_count--; - client->event_callback(client, - chan, - DMA_RESOURCE_REMOVED); - dma_client_chan_free(chan); - } - } + list_for_each_entry(client, &dma_client_list, global_node) + dma_client_chan_alloc(client); mutex_unlock(&dma_list_mutex); } /** - * dma_async_client_register - allocate and register a &dma_client - * @event_callback: callback for notification of channel addition/removal + * dma_chans_notify_available - tell the clients that a channel is going away + * @chan: channel on its way out */ -struct dma_client *dma_async_client_register(dma_event_callback event_callback) +static void dma_clients_notify_removed(struct dma_chan *chan) { struct dma_client *client; + enum dma_state_client ack; - client = kzalloc(sizeof(*client), GFP_KERNEL); - if (!client) - return NULL; + mutex_lock(&dma_list_mutex); - INIT_LIST_HEAD(&client->channels); - spin_lock_init(&client->lock); - client->chans_desired = 0; - client->chan_count = 0; - client->event_callback = event_callback; + list_for_each_entry(client, &dma_client_list, global_node) { + ack = client->event_callback(client, chan, + DMA_RESOURCE_REMOVED); + + /* client was holding resources for this channel so + * free it + */ + if (ack == DMA_ACK) { + dma_chan_put(chan); + kref_put(&chan->device->refcount, + dma_async_device_cleanup); + } + } + mutex_unlock(&dma_list_mutex); +} + +/** + * dma_async_client_register - register a &dma_client + * @client: ptr to a client structure with valid 'event_callback' and 'cap_mask' + */ +void dma_async_client_register(struct dma_client *client) +{ mutex_lock(&dma_list_mutex); list_add_tail(&client->global_node, &dma_client_list); mutex_unlock(&dma_list_mutex); - - return client; } EXPORT_SYMBOL(dma_async_client_register); @@ -272,40 +302,42 @@ EXPORT_SYMBOL(dma_async_client_register); */ void dma_async_client_unregister(struct dma_client *client) { + struct dma_device *device; struct dma_chan *chan; + enum dma_state_client ack; if (!client) return; - rcu_read_lock(); - list_for_each_entry_rcu(chan, &client->channels, client_node) - dma_client_chan_free(chan); - rcu_read_unlock(); - mutex_lock(&dma_list_mutex); + /* free all channels the client is holding */ + list_for_each_entry(device, &dma_device_list, global_node) + list_for_each_entry(chan, &device->channels, device_node) { + ack = client->event_callback(client, chan, + DMA_RESOURCE_REMOVED); + + if (ack == DMA_ACK) { + dma_chan_put(chan); + kref_put(&chan->device->refcount, + dma_async_device_cleanup); + } + } + list_del(&client->global_node); mutex_unlock(&dma_list_mutex); - - kfree(client); - dma_chans_rebalance(); } EXPORT_SYMBOL(dma_async_client_unregister); /** - * dma_async_client_chan_request - request DMA channels - * @client: &dma_client - * @number: count of DMA channels requested - * - * Clients call dma_async_client_chan_request() to specify how many - * DMA channels they need, 0 to free all currently allocated. - * The resulting allocations/frees are indicated to the client via the - * event callback. + * dma_async_client_chan_request - send all available channels to the + * client that satisfy the capability mask + * @client - requester */ -void dma_async_client_chan_request(struct dma_client *client, - unsigned int number) +void dma_async_client_chan_request(struct dma_client *client) { - client->chans_desired = number; - dma_chans_rebalance(); + mutex_lock(&dma_list_mutex); + dma_client_chan_alloc(client); + mutex_unlock(&dma_list_mutex); } EXPORT_SYMBOL(dma_async_client_chan_request); @@ -316,12 +348,31 @@ EXPORT_SYMBOL(dma_async_client_chan_request); int dma_async_device_register(struct dma_device *device) { static int id; - int chancnt = 0; + int chancnt = 0, rc; struct dma_chan* chan; if (!device) return -ENODEV; + /* validate device routines */ + BUG_ON(dma_has_cap(DMA_MEMCPY, device->cap_mask) && + !device->device_prep_dma_memcpy); + BUG_ON(dma_has_cap(DMA_XOR, device->cap_mask) && + !device->device_prep_dma_xor); + BUG_ON(dma_has_cap(DMA_ZERO_SUM, device->cap_mask) && + !device->device_prep_dma_zero_sum); + BUG_ON(dma_has_cap(DMA_MEMSET, device->cap_mask) && + !device->device_prep_dma_memset); + BUG_ON(dma_has_cap(DMA_ZERO_SUM, device->cap_mask) && + !device->device_prep_dma_interrupt); + + BUG_ON(!device->device_alloc_chan_resources); + BUG_ON(!device->device_free_chan_resources); + BUG_ON(!device->device_dependency_added); + BUG_ON(!device->device_is_tx_complete); + BUG_ON(!device->device_issue_pending); + BUG_ON(!device->dev); + init_completion(&device->done); kref_init(&device->refcount); device->dev_id = id++; @@ -338,17 +389,38 @@ int dma_async_device_register(struct dma_device *device) snprintf(chan->class_dev.class_id, BUS_ID_SIZE, "dma%dchan%d", device->dev_id, chan->chan_id); + rc = class_device_register(&chan->class_dev); + if (rc) { + chancnt--; + free_percpu(chan->local); + chan->local = NULL; + goto err_out; + } + kref_get(&device->refcount); - class_device_register(&chan->class_dev); + kref_init(&chan->refcount); + chan->slow_ref = 0; + INIT_RCU_HEAD(&chan->rcu); } mutex_lock(&dma_list_mutex); list_add_tail(&device->global_node, &dma_device_list); mutex_unlock(&dma_list_mutex); - dma_chans_rebalance(); + dma_clients_notify_available(); return 0; + +err_out: + list_for_each_entry(chan, &device->channels, device_node) { + if (chan->local == NULL) + continue; + kref_put(&device->refcount, dma_async_device_cleanup); + class_device_unregister(&chan->class_dev); + chancnt--; + free_percpu(chan->local); + } + return rc; } EXPORT_SYMBOL(dma_async_device_register); @@ -371,32 +443,165 @@ static void dma_async_device_cleanup(struct kref *kref) void dma_async_device_unregister(struct dma_device *device) { struct dma_chan *chan; - unsigned long flags; mutex_lock(&dma_list_mutex); list_del(&device->global_node); mutex_unlock(&dma_list_mutex); list_for_each_entry(chan, &device->channels, device_node) { - if (chan->client) { - spin_lock_irqsave(&chan->client->lock, flags); - list_del(&chan->client_node); - chan->client->chan_count--; - spin_unlock_irqrestore(&chan->client->lock, flags); - chan->client->event_callback(chan->client, - chan, - DMA_RESOURCE_REMOVED); - dma_client_chan_free(chan); - } + dma_clients_notify_removed(chan); class_device_unregister(&chan->class_dev); + dma_chan_release(chan); } - dma_chans_rebalance(); kref_put(&device->refcount, dma_async_device_cleanup); wait_for_completion(&device->done); } EXPORT_SYMBOL(dma_async_device_unregister); +/** + * dma_async_memcpy_buf_to_buf - offloaded copy between virtual addresses + * @chan: DMA channel to offload copy to + * @dest: destination address (virtual) + * @src: source address (virtual) + * @len: length + * + * Both @dest and @src must be mappable to a bus address according to the + * DMA mapping API rules for streaming mappings. + * Both @dest and @src must stay memory resident (kernel memory or locked + * user space pages). + */ +dma_cookie_t +dma_async_memcpy_buf_to_buf(struct dma_chan *chan, void *dest, + void *src, size_t len) +{ + struct dma_device *dev = chan->device; + struct dma_async_tx_descriptor *tx; + dma_addr_t addr; + dma_cookie_t cookie; + int cpu; + + tx = dev->device_prep_dma_memcpy(chan, len, 0); + if (!tx) + return -ENOMEM; + + tx->ack = 1; + tx->callback = NULL; + addr = dma_map_single(dev->dev, src, len, DMA_TO_DEVICE); + tx->tx_set_src(addr, tx, 0); + addr = dma_map_single(dev->dev, dest, len, DMA_FROM_DEVICE); + tx->tx_set_dest(addr, tx, 0); + cookie = tx->tx_submit(tx); + + cpu = get_cpu(); + per_cpu_ptr(chan->local, cpu)->bytes_transferred += len; + per_cpu_ptr(chan->local, cpu)->memcpy_count++; + put_cpu(); + + return cookie; +} +EXPORT_SYMBOL(dma_async_memcpy_buf_to_buf); + +/** + * dma_async_memcpy_buf_to_pg - offloaded copy from address to page + * @chan: DMA channel to offload copy to + * @page: destination page + * @offset: offset in page to copy to + * @kdata: source address (virtual) + * @len: length + * + * Both @page/@offset and @kdata must be mappable to a bus address according + * to the DMA mapping API rules for streaming mappings. + * Both @page/@offset and @kdata must stay memory resident (kernel memory or + * locked user space pages) + */ +dma_cookie_t +dma_async_memcpy_buf_to_pg(struct dma_chan *chan, struct page *page, + unsigned int offset, void *kdata, size_t len) +{ + struct dma_device *dev = chan->device; + struct dma_async_tx_descriptor *tx; + dma_addr_t addr; + dma_cookie_t cookie; + int cpu; + + tx = dev->device_prep_dma_memcpy(chan, len, 0); + if (!tx) + return -ENOMEM; + + tx->ack = 1; + tx->callback = NULL; + addr = dma_map_single(dev->dev, kdata, len, DMA_TO_DEVICE); + tx->tx_set_src(addr, tx, 0); + addr = dma_map_page(dev->dev, page, offset, len, DMA_FROM_DEVICE); + tx->tx_set_dest(addr, tx, 0); + cookie = tx->tx_submit(tx); + + cpu = get_cpu(); + per_cpu_ptr(chan->local, cpu)->bytes_transferred += len; + per_cpu_ptr(chan->local, cpu)->memcpy_count++; + put_cpu(); + + return cookie; +} +EXPORT_SYMBOL(dma_async_memcpy_buf_to_pg); + +/** + * dma_async_memcpy_pg_to_pg - offloaded copy from page to page + * @chan: DMA channel to offload copy to + * @dest_pg: destination page + * @dest_off: offset in page to copy to + * @src_pg: source page + * @src_off: offset in page to copy from + * @len: length + * + * Both @dest_page/@dest_off and @src_page/@src_off must be mappable to a bus + * address according to the DMA mapping API rules for streaming mappings. + * Both @dest_page/@dest_off and @src_page/@src_off must stay memory resident + * (kernel memory or locked user space pages). + */ +dma_cookie_t +dma_async_memcpy_pg_to_pg(struct dma_chan *chan, struct page *dest_pg, + unsigned int dest_off, struct page *src_pg, unsigned int src_off, + size_t len) +{ + struct dma_device *dev = chan->device; + struct dma_async_tx_descriptor *tx; + dma_addr_t addr; + dma_cookie_t cookie; + int cpu; + + tx = dev->device_prep_dma_memcpy(chan, len, 0); + if (!tx) + return -ENOMEM; + + tx->ack = 1; + tx->callback = NULL; + addr = dma_map_page(dev->dev, src_pg, src_off, len, DMA_TO_DEVICE); + tx->tx_set_src(addr, tx, 0); + addr = dma_map_page(dev->dev, dest_pg, dest_off, len, DMA_FROM_DEVICE); + tx->tx_set_dest(addr, tx, 0); + cookie = tx->tx_submit(tx); + + cpu = get_cpu(); + per_cpu_ptr(chan->local, cpu)->bytes_transferred += len; + per_cpu_ptr(chan->local, cpu)->memcpy_count++; + put_cpu(); + + return cookie; +} +EXPORT_SYMBOL(dma_async_memcpy_pg_to_pg); + +void dma_async_tx_descriptor_init(struct dma_async_tx_descriptor *tx, + struct dma_chan *chan) +{ + tx->chan = chan; + spin_lock_init(&tx->lock); + INIT_LIST_HEAD(&tx->depend_node); + INIT_LIST_HEAD(&tx->depend_list); +} +EXPORT_SYMBOL(dma_async_tx_descriptor_init); + static int __init dma_bus_init(void) { mutex_init(&dma_list_mutex); diff --git a/drivers/dma/ioatdma.c b/drivers/dma/ioatdma.c index 85001413955..5fbe56b5cea 100644 --- a/drivers/dma/ioatdma.c +++ b/drivers/dma/ioatdma.c @@ -32,16 +32,17 @@ #include <linux/delay.h> #include <linux/dma-mapping.h> #include "ioatdma.h" -#include "ioatdma_io.h" #include "ioatdma_registers.h" #include "ioatdma_hw.h" #define to_ioat_chan(chan) container_of(chan, struct ioat_dma_chan, common) #define to_ioat_device(dev) container_of(dev, struct ioat_device, common) #define to_ioat_desc(lh) container_of(lh, struct ioat_desc_sw, node) +#define tx_to_ioat_desc(tx) container_of(tx, struct ioat_desc_sw, async_tx) /* internal functions */ static int __devinit ioat_probe(struct pci_dev *pdev, const struct pci_device_id *ent); +static void ioat_shutdown(struct pci_dev *pdev); static void __devexit ioat_remove(struct pci_dev *pdev); static int enumerate_dma_channels(struct ioat_device *device) @@ -51,8 +52,8 @@ static int enumerate_dma_channels(struct ioat_device *device) int i; struct ioat_dma_chan *ioat_chan; - device->common.chancnt = ioatdma_read8(device, IOAT_CHANCNT_OFFSET); - xfercap_scale = ioatdma_read8(device, IOAT_XFERCAP_OFFSET); + device->common.chancnt = readb(device->reg_base + IOAT_CHANCNT_OFFSET); + xfercap_scale = readb(device->reg_base + IOAT_XFERCAP_OFFSET); xfercap = (xfercap_scale == 0 ? -1 : (1UL << xfercap_scale)); for (i = 0; i < device->common.chancnt; i++) { @@ -71,13 +72,79 @@ static int enumerate_dma_channels(struct ioat_device *device) INIT_LIST_HEAD(&ioat_chan->used_desc); /* This should be made common somewhere in dmaengine.c */ ioat_chan->common.device = &device->common; - ioat_chan->common.client = NULL; list_add_tail(&ioat_chan->common.device_node, &device->common.channels); } return device->common.chancnt; } +static void +ioat_set_src(dma_addr_t addr, struct dma_async_tx_descriptor *tx, int index) +{ + struct ioat_desc_sw *iter, *desc = tx_to_ioat_desc(tx); + struct ioat_dma_chan *ioat_chan = to_ioat_chan(tx->chan); + + pci_unmap_addr_set(desc, src, addr); + + list_for_each_entry(iter, &desc->async_tx.tx_list, node) { + iter->hw->src_addr = addr; + addr += ioat_chan->xfercap; + } + +} + +static void +ioat_set_dest(dma_addr_t addr, struct dma_async_tx_descriptor *tx, int index) +{ + struct ioat_desc_sw *iter, *desc = tx_to_ioat_desc(tx); + struct ioat_dma_chan *ioat_chan = to_ioat_chan(tx->chan); + + pci_unmap_addr_set(desc, dst, addr); + + list_for_each_entry(iter, &desc->async_tx.tx_list, node) { + iter->hw->dst_addr = addr; + addr += ioat_chan->xfercap; + } +} + +static dma_cookie_t +ioat_tx_submit(struct dma_async_tx_descriptor *tx) +{ + struct ioat_dma_chan *ioat_chan = to_ioat_chan(tx->chan); + struct ioat_desc_sw *desc = tx_to_ioat_desc(tx); + int append = 0; + dma_cookie_t cookie; + struct ioat_desc_sw *group_start; + + group_start = list_entry(desc->async_tx.tx_list.next, + struct ioat_desc_sw, node); + spin_lock_bh(&ioat_chan->desc_lock); + /* cookie incr and addition to used_list must be atomic */ + cookie = ioat_chan->common.cookie; + cookie++; + if (cookie < 0) + cookie = 1; + ioat_chan->common.cookie = desc->async_tx.cookie = cookie; + + /* write address into NextDescriptor field of last desc in chain */ + to_ioat_desc(ioat_chan->used_desc.prev)->hw->next = + group_start->async_tx.phys; + list_splice_init(&desc->async_tx.tx_list, ioat_chan->used_desc.prev); + + ioat_chan->pending += desc->tx_cnt; + if (ioat_chan->pending >= 4) { + append = 1; + ioat_chan->pending = 0; + } + spin_unlock_bh(&ioat_chan->desc_lock); + + if (append) + writeb(IOAT_CHANCMD_APPEND, + ioat_chan->reg_base + IOAT_CHANCMD_OFFSET); + + return cookie; +} + static struct ioat_desc_sw *ioat_dma_alloc_descriptor( struct ioat_dma_chan *ioat_chan, gfp_t flags) @@ -99,8 +166,13 @@ static struct ioat_desc_sw *ioat_dma_alloc_descriptor( } memset(desc, 0, sizeof(*desc)); + dma_async_tx_descriptor_init(&desc_sw->async_tx, &ioat_chan->common); + desc_sw->async_tx.tx_set_src = ioat_set_src; + desc_sw->async_tx.tx_set_dest = ioat_set_dest; + desc_sw->async_tx.tx_submit = ioat_tx_submit; + INIT_LIST_HEAD(&desc_sw->async_tx.tx_list); desc_sw->hw = desc; - desc_sw->phys = phys; + desc_sw->async_tx.phys = phys; return desc_sw; } @@ -123,7 +195,7 @@ static int ioat_dma_alloc_chan_resources(struct dma_chan *chan) * In-use bit automatically set by reading chanctrl * If 0, we got it, if 1, someone else did */ - chanctrl = ioatdma_chan_read16(ioat_chan, IOAT_CHANCTRL_OFFSET); + chanctrl = readw(ioat_chan->reg_base + IOAT_CHANCTRL_OFFSET); if (chanctrl & IOAT_CHANCTRL_CHANNEL_IN_USE) return -EBUSY; @@ -132,12 +204,12 @@ static int ioat_dma_alloc_chan_resources(struct dma_chan *chan) IOAT_CHANCTRL_ERR_INT_EN | IOAT_CHANCTRL_ANY_ERR_ABORT_EN | IOAT_CHANCTRL_ERR_COMPLETION_EN; - ioatdma_chan_write16(ioat_chan, IOAT_CHANCTRL_OFFSET, chanctrl); + writew(chanctrl, ioat_chan->reg_base + IOAT_CHANCTRL_OFFSET); - chanerr = ioatdma_chan_read32(ioat_chan, IOAT_CHANERR_OFFSET); + chanerr = readl(ioat_chan->reg_base + IOAT_CHANERR_OFFSET); if (chanerr) { printk("IOAT: CHANERR = %x, clearing\n", chanerr); - ioatdma_chan_write32(ioat_chan, IOAT_CHANERR_OFFSET, chanerr); + writel(chanerr, ioat_chan->reg_base + IOAT_CHANERR_OFFSET); } /* Allocate descriptors */ @@ -161,10 +233,10 @@ static int ioat_dma_alloc_chan_resources(struct dma_chan *chan) &ioat_chan->completion_addr); memset(ioat_chan->completion_virt, 0, sizeof(*ioat_chan->completion_virt)); - ioatdma_chan_write32(ioat_chan, IOAT_CHANCMP_OFFSET_LOW, - ((u64) ioat_chan->completion_addr) & 0x00000000FFFFFFFF); - ioatdma_chan_write32(ioat_chan, IOAT_CHANCMP_OFFSET_HIGH, - ((u64) ioat_chan->completion_addr) >> 32); + writel(((u64) ioat_chan->completion_addr) & 0x00000000FFFFFFFF, + ioat_chan->reg_base + IOAT_CHANCMP_OFFSET_LOW); + writel(((u64) ioat_chan->completion_addr) >> 32, + ioat_chan->reg_base + IOAT_CHANCMP_OFFSET_HIGH); ioat_start_null_desc(ioat_chan); return i; @@ -182,18 +254,20 @@ static void ioat_dma_free_chan_resources(struct dma_chan *chan) ioat_dma_memcpy_cleanup(ioat_chan); - ioatdma_chan_write8(ioat_chan, IOAT_CHANCMD_OFFSET, IOAT_CHANCMD_RESET); + writeb(IOAT_CHANCMD_RESET, ioat_chan->reg_base + IOAT_CHANCMD_OFFSET); spin_lock_bh(&ioat_chan->desc_lock); list_for_each_entry_safe(desc, _desc, &ioat_chan->used_desc, node) { in_use_descs++; list_del(&desc->node); - pci_pool_free(ioat_device->dma_pool, desc->hw, desc->phys); + pci_pool_free(ioat_device->dma_pool, desc->hw, + desc->async_tx.phys); kfree(desc); } list_for_each_entry_safe(desc, _desc, &ioat_chan->free_desc, node) { list_del(&desc->node); - pci_pool_free(ioat_device->dma_pool, desc->hw, desc->phys); + pci_pool_free(ioat_device->dma_pool, desc->hw, + desc->async_tx.phys); kfree(desc); } spin_unlock_bh(&ioat_chan->desc_lock); @@ -210,50 +284,30 @@ static void ioat_dma_free_chan_resources(struct dma_chan *chan) ioat_chan->last_completion = ioat_chan->completion_addr = 0; /* Tell hw the chan is free */ - chanctrl = ioatdma_chan_read16(ioat_chan, IOAT_CHANCTRL_OFFSET); + chanctrl = readw(ioat_chan->reg_base + IOAT_CHANCTRL_OFFSET); chanctrl &= ~IOAT_CHANCTRL_CHANNEL_IN_USE; - ioatdma_chan_write16(ioat_chan, IOAT_CHANCTRL_OFFSET, chanctrl); + writew(chanctrl, ioat_chan->reg_base + IOAT_CHANCTRL_OFFSET); } -/** - * do_ioat_dma_memcpy - actual function that initiates a IOAT DMA transaction - * @ioat_chan: IOAT DMA channel handle - * @dest: DMA destination address - * @src: DMA source address - * @len: transaction length in bytes - */ - -static dma_cookie_t do_ioat_dma_memcpy(struct ioat_dma_chan *ioat_chan, - dma_addr_t dest, - dma_addr_t src, - size_t len) +static struct dma_async_tx_descriptor * +ioat_dma_prep_memcpy(struct dma_chan *chan, size_t len, int int_en) { - struct ioat_desc_sw *first; - struct ioat_desc_sw *prev; - struct ioat_desc_sw *new; - dma_cookie_t cookie; + struct ioat_dma_chan *ioat_chan = to_ioat_chan(chan); + struct ioat_desc_sw *first, *prev, *new; LIST_HEAD(new_chain); u32 copy; size_t orig_len; - dma_addr_t orig_src, orig_dst; - unsigned int desc_count = 0; - unsigned int append = 0; - - if (!ioat_chan || !dest || !src) - return -EFAULT; + int desc_count = 0; if (!len) - return ioat_chan->common.cookie; + return NULL; orig_len = len; - orig_src = src; - orig_dst = dest; first = NULL; prev = NULL; spin_lock_bh(&ioat_chan->desc_lock); - while (len) { if (!list_empty(&ioat_chan->free_desc)) { new = to_ioat_desc(ioat_chan->free_desc.next); @@ -270,141 +324,36 @@ static dma_cookie_t do_ioat_dma_memcpy(struct ioat_dma_chan *ioat_chan, new->hw->size = copy; new->hw->ctl = 0; - new->hw->src_addr = src; - new->hw->dst_addr = dest; - new->cookie = 0; + new->async_tx.cookie = 0; + new->async_tx.ack = 1; /* chain together the physical address list for the HW */ if (!first) first = new; else - prev->hw->next = (u64) new->phys; + prev->hw->next = (u64) new->async_tx.phys; prev = new; - len -= copy; - dest += copy; - src += copy; - list_add_tail(&new->node, &new_chain); desc_count++; } - new->hw->ctl = IOAT_DMA_DESCRIPTOR_CTL_CP_STS; - new->hw->next = 0; - /* cookie incr and addition to used_list must be atomic */ + list_splice(&new_chain, &new->async_tx.tx_list); - cookie = ioat_chan->common.cookie; - cookie++; - if (cookie < 0) - cookie = 1; - ioat_chan->common.cookie = new->cookie = cookie; + new->hw->ctl = IOAT_DMA_DESCRIPTOR_CTL_CP_STS; + new->hw->next = 0; + new->tx_cnt = desc_count; + new->async_tx.ack = 0; /* client is in control of this ack */ + new->async_tx.cookie = -EBUSY; - pci_unmap_addr_set(new, src, orig_src); - pci_unmap_addr_set(new, dst, orig_dst); pci_unmap_len_set(new, src_len, orig_len); pci_unmap_len_set(new, dst_len, orig_len); - - /* write address into NextDescriptor field of last desc in chain */ - to_ioat_desc(ioat_chan->used_desc.prev)->hw->next = first->phys; - list_splice_init(&new_chain, ioat_chan->used_desc.prev); - - ioat_chan->pending += desc_count; - if (ioat_chan->pending >= 20) { - append = 1; - ioat_chan->pending = 0; - } - spin_unlock_bh(&ioat_chan->desc_lock); - if (append) - ioatdma_chan_write8(ioat_chan, - IOAT_CHANCMD_OFFSET, - IOAT_CHANCMD_APPEND); - return cookie; -} - -/** - * ioat_dma_memcpy_buf_to_buf - wrapper that takes src & dest bufs - * @chan: IOAT DMA channel handle - * @dest: DMA destination address - * @src: DMA source address - * @len: transaction length in bytes - */ - -static dma_cookie_t ioat_dma_memcpy_buf_to_buf(struct dma_chan *chan, - void *dest, - void *src, - size_t len) -{ - dma_addr_t dest_addr; - dma_addr_t src_addr; - struct ioat_dma_chan *ioat_chan = to_ioat_chan(chan); - - dest_addr = pci_map_single(ioat_chan->device->pdev, - dest, len, PCI_DMA_FROMDEVICE); - src_addr = pci_map_single(ioat_chan->device->pdev, - src, len, PCI_DMA_TODEVICE); - - return do_ioat_dma_memcpy(ioat_chan, dest_addr, src_addr, len); + return new ? &new->async_tx : NULL; } -/** - * ioat_dma_memcpy_buf_to_pg - wrapper, copying from a buf to a page - * @chan: IOAT DMA channel handle - * @page: pointer to the page to copy to - * @offset: offset into that page - * @src: DMA source address - * @len: transaction length in bytes - */ - -static dma_cookie_t ioat_dma_memcpy_buf_to_pg(struct dma_chan *chan, - struct page *page, - unsigned int offset, - void *src, - size_t len) -{ - dma_addr_t dest_addr; - dma_addr_t src_addr; - struct ioat_dma_chan *ioat_chan = to_ioat_chan(chan); - - dest_addr = pci_map_page(ioat_cha |